diff --git "a/wandb/run-20211106_211610-dtkf2u0m/files/output.log" "b/wandb/run-20211106_211610-dtkf2u0m/files/output.log" --- "a/wandb/run-20211106_211610-dtkf2u0m/files/output.log" +++ "b/wandb/run-20211106_211610-dtkf2u0m/files/output.log" @@ -22452,5 +22452,3737 @@ To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... +To disable this warning, you can either: + - Avoid using `tokenizers` before the fork if possible + - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) +huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... +To disable this warning, you can either: + - Avoid using `tokenizers` before the fork if possible + - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) +huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... +To disable this warning, you can either: + - Avoid using `tokenizers` before the fork if possible + - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) +huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... +To disable this warning, you can either: + - Avoid using `tokenizers` before the fork if possible + - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) +huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... +To disable this warning, you can either: + - Avoid using `tokenizers` before the fork if possible +11/07/2021 09:54:34 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.80000, 'steps': 89999, 'loss/train': 1.3141337633132935}}}███████████████████████████| 10.9M/10.9M [00:19<00:00, 596kB/s] +Upload file wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb: 5%|█████▎ | 1.34M/27.8M [00:01<00:20, 1.37MB/s] +Upload file wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb: 58%|███████████████████████████████████████████████████████████████▌ | 16.2M/27.8M [00:02<00:01, 9.68MB/s] +Upload file wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb: 58%|███████████████████████████████████████████████████████████████▌ | 16.2M/27.8M [00:02<00:01, 9.68MB/s] +Upload file wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb: 58%|███████████████████████████████████████████████████████████████▌ | 16.2M/27.8M [00:02<00:01, 9.68MB/s] +Upload file wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb: 58%|███████████████████████████████████████████████████████████████▌ | 16.2M/27.8M [00:02<00:01, 9.68MB/s] +Upload file wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb: 58%|███████████████████████████████████████████████████████████████▌ | 16.2M/27.8M [00:02<00:01, 9.68MB/s] +Upload file wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████| 27.8M/27.8M [00:12<00:00, 9.68MB/s] +Upload file wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████| 27.8M/27.8M [00:12<00:00, 9.68MB/s] +Upload file wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb: 100%|█████████████████████████████████████████████████████���███████████████████████████████████████████████████████| 27.8M/27.8M [00:12<00:00, 9.68MB/s] +Upload file wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████| 27.8M/27.8M [00:12<00:00, 9.68MB/s] +Upload file wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████| 27.8M/27.8M [00:12<00:00, 9.68MB/s] +Upload file wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████| 27.8M/27.8M [00:12<00:00, 9.68MB/s] +Upload file wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████| 27.8M/27.8M [00:12<00:00, 9.68MB/s] +huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... +To disable this warning, you can either: + - Avoid using `tokenizers` before the fork if possible + - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) +huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... +To disable this warning, you can either: + - Avoid using `tokenizers` before the fork if possible +Upload file wandb/run-20211106_211610-dtkf2u0m/run-dtkf2u0m.wandb: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:03 - INFO - __main__ - Step 90005: {'lr': 0.00017677401091511114, 'samples': 17280960, 'steps': 90004, 'loss/train': 0.14744818210601807}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:03 - INFO - __main__ - Step 90005: {'lr': 0.00017677401091511114, 'samples': 17280960, 'steps': 90004, 'loss/train': 0.14744818210601807}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:06 - INFO - __main__ - Step 90011: {'lr': 0.00017674356750636494, 'samples': 17282112, 'steps': 90010, 'loss/train': 1.4505771398544312}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:09 - INFO - __main__ - Step 90017: {'lr': 0.0001767131252859145, 'samples': 17283264, 'steps': 90016, 'loss/train': 1.6236997842788696}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:09 - INFO - __main__ - Step 90017: {'lr': 0.0001767131252859145, 'samples': 17283264, 'steps': 90016, 'loss/train': 1.6236997842788696}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:14 - INFO - __main__ - Step 90026: {'lr': 0.00017666746418437392, 'samples': 17284992, 'steps': 90025, 'loss/train': 1.3274627923965454}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:16 - INFO - __main__ - Step 90030: {'lr': 0.00017664717122047307, 'samples': 17285760, 'steps': 90029, 'loss/train': 1.2036980390548706}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:17 - INFO - __main__ - Step 90034: {'lr': 0.00017662687878539885, 'samples': 17286528, 'steps': 90033, 'loss/train': 1.3146265745162964}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:19 - INFO - __main__ - Step 90038: {'lr': 0.00017660658687929722, 'samples': 17287296, 'steps': 90037, 'loss/train': 1.7477999925613403}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:22 - INFO - __main__ - Step 90042: {'lr': 0.00017658629550231463, 'samples': 17288064, 'steps': 90041, 'loss/train': 1.6811933517456055}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:24 - INFO - __main__ - Step 90046: {'lr': 0.00017656600465459744, 'samples': 17288832, 'steps': 90045, 'loss/train': 0.8904002904891968}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:25 - INFO - __main__ - Step 90050: {'lr': 0.00017654571433629176, 'samples': 17289600, 'steps': 90049, 'loss/train': 1.5268011093139648}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:27 - INFO - __main__ - Step 90054: {'lr': 0.00017652542454754398, 'samples': 17290368, 'steps': 90053, 'loss/train': 1.493564486503601}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:27 - INFO - __main__ - Step 90054: {'lr': 0.00017652542454754398, 'samples': 17290368, 'steps': 90053, 'loss/train': 1.493564486503601}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:31 - INFO - __main__ - Step 90061: {'lr': 0.00017648991869192405, 'samples': 17291712, 'steps': 90060, 'loss/train': 1.3485932350158691}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:33 - INFO - __main__ - Step 90066: {'lr': 0.0001764645583601107, 'samples': 17292672, 'steps': 90065, 'loss/train': 1.5910234451293945}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:36 - INFO - __main__ - Step 90071: {'lr': 0.00017643919885664588, 'samples': 17293632, 'steps': 90070, 'loss/train': 0.8817723989486694}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:36 - INFO - __main__ - Step 90071: {'lr': 0.00017643919885664588, 'samples': 17293632, 'steps': 90070, 'loss/train': 0.8817723989486694}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:39 - INFO - __main__ - Step 90078: {'lr': 0.00017640369694396413, 'samples': 17294976, 'steps': 90077, 'loss/train': 1.3708593845367432}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:41 - INFO - __main__ - Step 90082: {'lr': 0.00017638341086621706, 'samples': 17295744, 'steps': 90081, 'loss/train': 0.4502171576023102}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:44 - INFO - __main__ - Step 90087: {'lr': 0.00017635805401538667, 'samples': 17296704, 'steps': 90086, 'loss/train': 1.596861481666565}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:46 - INFO - __main__ - Step 90091: {'lr': 0.0001763377691319832, 'samples': 17297472, 'steps': 90090, 'loss/train': 1.636279582977295}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:48 - INFO - __main__ - Step 90095: {'lr': 0.00017631748477963673, 'samples': 17298240, 'steps': 90094, 'loss/train': 1.1399166584014893}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:49 - INFO - __main__ - Step 90099: {'lr': 0.00017629720095849367, 'samples': 17299008, 'steps': 90098, 'loss/train': 1.1545395851135254}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:52 - INFO - __main__ - Step 90103: {'lr': 0.0001762769176687, 'samples': 17299776, 'steps': 90102, 'loss/train': 0.9943256378173828}254}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:54 - INFO - __main__ - Step 90108: {'lr': 0.00017625156430389093, 'samples': 17300736, 'steps': 90107, 'loss/train': 1.339103102684021}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:54 - INFO - __main__ - Step 90108: {'lr': 0.00017625156430389093, 'samples': 17300736, 'steps': 90107, 'loss/train': 1.339103102684021}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:57 - INFO - __main__ - Step 90115: {'lr': 0.0001762160709888784, 'samples': 17302080, 'steps': 90114, 'loss/train': 0.9452076554298401}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:55:59 - INFO - __main__ - Step 90119: {'lr': 0.000176195789825945, 'samples': 17302848, 'steps': 90118, 'loss/train': 1.3537747859954834}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:02 - INFO - __main__ - Step 90124: {'lr': 0.0001761704391205338, 'samples': 17303808, 'steps': 90123, 'loss/train': 1.5535056591033936}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:04 - INFO - __main__ - Step 90128: {'lr': 0.00017615015915498745, 'samples': 17304576, 'steps': 90127, 'loss/train': 1.5392345190048218}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:05 - INFO - __main__ - Step 90132: {'lr': 0.00017612987972185056, 'samples': 17305344, 'steps': 90131, 'loss/train': 0.9457494020462036}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:07 - INFO - __main__ - Step 90136: {'lr': 0.00017610960082126958, 'samples': 17306112, 'steps': 90135, 'loss/train': 1.7871013879776}36}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:10 - INFO - __main__ - Step 90141: {'lr': 0.00017608425294467263, 'samples': 17307072, 'steps': 90140, 'loss/train': 0.6502556204795837}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:12 - INFO - __main__ - Step 90145: {'lr': 0.00017606397524287665, 'samples': 17307840, 'steps': 90144, 'loss/train': 1.6768218278884888}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:14 - INFO - __main__ - Step 90149: {'lr': 0.00017604369807411153, 'samples': 17308608, 'steps': 90148, 'loss/train': 1.4957091808319092}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:15 - INFO - __main__ - Step 90153: {'lr': 0.00017602342143852357, 'samples': 17309376, 'steps': 90152, 'loss/train': 1.3566293716430664}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:18 - INFO - __main__ - Step 90157: {'lr': 0.00017600314533625889, 'samples': 17310144, 'steps': 90156, 'loss/train': 1.1602576971054077}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:20 - INFO - __main__ - Step 90162: {'lr': 0.0001759778009586365, 'samples': 17311104, 'steps': 90161, 'loss/train': 1.3883213996887207}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:20 - INFO - __main__ - Step 90162: {'lr': 0.0001759778009586365, 'samples': 17311104, 'steps': 90161, 'loss/train': 1.3883213996887207}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:24 - INFO - __main__ - Step 90169: {'lr': 0.00017594232023086616, 'samples': 17312448, 'steps': 90168, 'loss/train': 1.5267140865325928}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:25 - INFO - __main__ - Step 90173: {'lr': 0.00017592204626335628, 'samples': 17313216, 'steps': 90172, 'loss/train': 0.6878520846366882}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:27 - INFO - __main__ - Step 90177: {'lr': 0.0001759017728299005, 'samples': 17313984, 'steps': 90176, 'loss/train': 1.5498930215835571}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:27 - INFO - __main__ - Step 90177: {'lr': 0.0001759017728299005, 'samples': 17313984, 'steps': 90176, 'loss/train': 1.5498930215835571}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:32 - INFO - __main__ - Step 90186: {'lr': 0.00017585615955801755, 'samples': 17315712, 'steps': 90185, 'loss/train': 1.6561596393585205}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:34 - INFO - __main__ - Step 90190: {'lr': 0.00017583588786124703, 'samples': 17316480, 'steps': 90189, 'loss/train': 1.1794757843017578}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:36 - INFO - __main__ - Step 90194: {'lr': 0.00017581561669915196, 'samples': 17317248, 'steps': 90193, 'loss/train': 1.5845050811767578}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:38 - INFO - __main__ - Step 90198: {'lr': 0.00017579534607187815, 'samples': 17318016, 'steps': 90197, 'loss/train': 1.3110543489456177}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:40 - INFO - __main__ - Step 90203: {'lr': 0.00017577000854010117, 'samples': 17318976, 'steps': 90202, 'loss/train': 1.3514479398727417}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:42 - INFO - __main__ - Step 90207: {'lr': 0.00017574973911670998, 'samples': 17319744, 'steps': 90206, 'loss/train': 1.090510606765747}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:42 - INFO - __main__ - Step 90207: {'lr': 0.00017574973911670998, 'samples': 17319744, 'steps': 90206, 'loss/train': 1.090510606765747}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:45 - INFO - __main__ - Step 90214: {'lr': 0.00017571426891391996, 'samples': 17321088, 'steps': 90213, 'loss/train': 1.0812321901321411}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:48 - INFO - __main__ - Step 90219: {'lr': 0.00017568893405889874, 'samples': 17322048, 'steps': 90218, 'loss/train': 1.306175947189331}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:48 - INFO - __main__ - Step 90219: {'lr': 0.00017568893405889874, 'samples': 17322048, 'steps': 90218, 'loss/train': 1.306175947189331}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:52 - INFO - __main__ - Step 90227: {'lr': 0.00017564840003212123, 'samples': 17323584, 'steps': 90226, 'loss/train': 1.3913753032684326}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:53 - INFO - __main__ - Step 90231: {'lr': 0.00017562813382269985, 'samples': 17324352, 'steps': 90230, 'loss/train': 0.8448482751846313}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:56 - INFO - __main__ - Step 90235: {'lr': 0.00017560786814945157, 'samples': 17325120, 'steps': 90234, 'loss/train': 0.9594841003417969}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:56:58 - INFO - __main__ - Step 90240: {'lr': 0.00017558253681210705, 'samples': 17326080, 'steps': 90239, 'loss/train': 1.9297430515289307}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:00 - INFO - __main__ - Step 90245: {'lr': 0.00017555720631304655, 'samples': 17327040, 'steps': 90244, 'loss/train': 1.3047287464141846}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:02 - INFO - __main__ - Step 90249: {'lr': 0.0001755369425175545, 'samples': 17327808, 'steps': 90248, 'loss/train': 1.4721684455871582}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:04 - INFO - __main__ - Step 90253: {'lr': 0.00017551667925889275, 'samples': 17328576, 'steps': 90252, 'loss/train': 1.2871826887130737}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:06 - INFO - __main__ - Step 90257: {'lr': 0.00017549641653720764, 'samples': 17329344, 'steps': 90256, 'loss/train': 1.3070130348205566}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:08 - INFO - __main__ - Step 90261: {'lr': 0.00017547615435264523, 'samples': 17330112, 'steps': 90260, 'loss/train': 1.5161832571029663}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:10 - INFO - __main__ - Step 90266: {'lr': 0.00017545082737749335, 'samples': 17331072, 'steps': 90265, 'loss/train': 1.41855788230896}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:12 - INFO - __main__ - Step 90270: {'lr': 0.00017543056640199095, 'samples': 17331840, 'steps': 90269, 'loss/train': 0.9538955092430115}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:12 - INFO - __main__ - Step 90270: {'lr': 0.00017543056640199095, 'samples': 17331840, 'steps': 90269, 'loss/train': 0.9538955092430115}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:16 - INFO - __main__ - Step 90277: {'lr': 0.0001753951109885432, 'samples': 17333184, 'steps': 90276, 'loss/train': 1.4577233791351318}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:18 - INFO - __main__ - Step 90282: {'lr': 0.00017536978670165215, 'samples': 17334144, 'steps': 90281, 'loss/train': 0.9068219661712646}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:21 - INFO - __main__ - Step 90287: {'lr': 0.00017534446325544162, 'samples': 17335104, 'steps': 90286, 'loss/train': 1.1116780042648315}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:23 - INFO - __main__ - Step 90291: {'lr': 0.0001753242051039549, 'samples': 17335872, 'steps': 90290, 'loss/train': 1.3597497940063477}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:25 - INFO - __main__ - Step 90295: {'lr': 0.00017530394749083235, 'samples': 17336640, 'steps': 90294, 'loss/train': 1.3256367444992065}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:26 - INFO - __main__ - Step 90299: {'lr': 0.00017528369041622, 'samples': 17337408, 'steps': 90298, 'loss/train': 0.9884231090545654}65}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:28 - INFO - __main__ - Step 90303: {'lr': 0.000175263433880264, 'samples': 17338176, 'steps': 90302, 'loss/train': 1.1883231401443481}5}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:30 - INFO - __main__ - Step 90307: {'lr': 0.00017524317788311018, 'samples': 17338944, 'steps': 90306, 'loss/train': 1.7303836345672607}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:33 - INFO - __main__ - Step 90311: {'lr': 0.0001752229224249047, 'samples': 17339712, 'steps': 90310, 'loss/train': 1.3354766368865967}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:33 - INFO - __main__ - Step 90311: {'lr': 0.0001752229224249047, 'samples': 17339712, 'steps': 90310, 'loss/train': 1.3354766368865967}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:36 - INFO - __main__ - Step 90318: {'lr': 0.00017518747667032885, 'samples': 17341056, 'steps': 90317, 'loss/train': 1.3627568483352661}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:36 - INFO - __main__ - Step 90318: {'lr': 0.00017518747667032885, 'samples': 17341056, 'steps': 90317, 'loss/train': 1.3627568483352661}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:41 - INFO - __main__ - Step 90327: {'lr': 0.00017514190598448675, 'samples': 17342784, 'steps': 90326, 'loss/train': 1.164007306098938}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:43 - INFO - __main__ - Step 90331: {'lr': 0.00017512165322321327, 'samples': 17343552, 'steps': 90330, 'loss/train': 1.9194461107254028}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:44 - INFO - __main__ - Step 90335: {'lr': 0.00017510140100176425, 'samples': 17344320, 'steps': 90334, 'loss/train': 1.5904561281204224}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:46 - INFO - __main__ - Step 90339: {'lr': 0.00017508114932028563, 'samples': 17345088, 'steps': 90338, 'loss/train': 1.3632270097732544}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:49 - INFO - __main__ - Step 90344: {'lr': 0.00017505583547799337, 'samples': 17346048, 'steps': 90343, 'loss/train': 1.233899474143982}}}██��████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:51 - INFO - __main__ - Step 90348: {'lr': 0.0001750355850119821, 'samples': 17346816, 'steps': 90347, 'loss/train': 1.2156656980514526}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:53 - INFO - __main__ - Step 90352: {'lr': 0.00017501533508641572, 'samples': 17347584, 'steps': 90351, 'loss/train': 1.2658473253250122}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:54 - INFO - __main__ - Step 90356: {'lr': 0.0001749950857014404, 'samples': 17348352, 'steps': 90355, 'loss/train': 1.3850407600402832}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:56 - INFO - __main__ - Step 90360: {'lr': 0.00017497483685720189, 'samples': 17349120, 'steps': 90359, 'loss/train': 5.716197490692139}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:57:56 - INFO - __main__ - Step 90360: {'lr': 0.00017497483685720189, 'samples': 17349120, 'steps': 90359, 'loss/train': 5.716197490692139}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:00 - INFO - __main__ - Step 90367: {'lr': 0.00017493940268137188, 'samples': 17350464, 'steps': 90366, 'loss/train': 1.5029209852218628}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:02 - INFO - __main__ - Step 90371: {'lr': 0.0001749191553249126, 'samples': 17351232, 'steps': 90370, 'loss/train': 0.12995073199272156}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:04 - INFO - __main__ - Step 90376: {'lr': 0.00017489384689053662, 'samples': 17352192, 'steps': 90375, 'loss/train': 1.3855992555618286}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:04 - INFO - __main__ - Step 90376: {'lr': 0.00017489384689053662, 'samples': 17352192, 'steps': 90375, 'loss/train': 1.3855992555618286}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:09 - INFO - __main__ - Step 90384: {'lr': 0.00017485335515542085, 'samples': 17353728, 'steps': 90383, 'loss/train': 1.1394675970077515}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:10 - INFO - __main__ - Step 90388: {'lr': 0.00017483311010042796, 'samples': 17354496, 'steps': 90387, 'loss/train': 1.335822343826294}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:13 - INFO - __main__ - Step 90392: {'lr': 0.00017481286558733978, 'samples': 17355264, 'steps': 90391, 'loss/train': 0.6012700200080872}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:15 - INFO - __main__ - Step 90396: {'lr': 0.00017479262161630222, 'samples': 17356032, 'steps': 90395, 'loss/train': 1.137945294380188}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:17 - INFO - __main__ - Step 90400: {'lr': 0.00017477237818746115, 'samples': 17356800, 'steps': 90399, 'loss/train': 1.6689339876174927}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:18 - INFO - __main__ - Step 90404: {'lr': 0.0001747521353009626, 'samples': 17357568, 'steps': 90403, 'loss/train': 1.4574368000030518}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:20 - INFO - __main__ - Step 90408: {'lr': 0.00017473189295695249, 'samples': 17358336, 'steps': 90407, 'loss/train': 0.9031802415847778}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:20 - INFO - __main__ - Step 90408: {'lr': 0.00017473189295695249, 'samples': 17358336, 'steps': 90407, 'loss/train': 0.9031802415847778}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:24 - INFO - __main__ - Step 90416: {'lr': 0.00017469140989698122, 'samples': 17359872, 'steps': 90415, 'loss/train': 0.980841338634491}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:26 - INFO - __main__ - Step 90420: {'lr': 0.00017467116918131194, 'samples': 17360640, 'steps': 90419, 'loss/train': 2.155827283859253}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:26 - INFO - __main__ - Step 90420: {'lr': 0.00017467116918131194, 'samples': 17360640, 'steps': 90419, 'loss/train': 2.155827283859253}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:29 - INFO - __main__ - Step 90425: {'lr': 0.00017464586905043772, 'samples': 17361600, 'steps': 90424, 'loss/train': 1.046202301979065}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:32 - INFO - __main__ - Step 90431: {'lr': 0.0001746155100138761, 'samples': 17362752, 'steps': 90430, 'loss/train': 0.536493718624115}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:34 - INFO - __main__ - Step 90435: {'lr': 0.00017459527133547976, 'samples': 17363520, 'steps': 90434, 'loss/train': 1.4395161867141724}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:36 - INFO - __main__ - Step 90440: {'lr': 0.0001745699737519661, 'samples': 17364480, 'steps': 90439, 'loss/train': 1.4896670579910278}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:39 - INFO - __main__ - Step 90445: {'lr': 0.0001745446770181425, 'samples': 17365440, 'steps': 90444, 'loss/train': 1.461923599243164}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:39 - INFO - __main__ - Step 90445: {'lr': 0.0001745446770181425, 'samples': 17365440, 'steps': 90444, 'loss/train': 1.461923599243164}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:42 - INFO - __main__ - Step 90452: {'lr': 0.00017450926301881158, 'samples': 17366784, 'steps': 90451, 'loss/train': 1.790251612663269}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:44 - INFO - __main__ - Step 90456: {'lr': 0.0001744890271960443, 'samples': 17367552, 'steps': 90455, 'loss/train': 1.2950642108917236}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:44 - INFO - __main__ - Step 90456: {'lr': 0.0001744890271960443, 'samples': 17367552, 'steps': 90455, 'loss/train': 1.2950642108917236}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:48 - INFO - __main__ - Step 90463: {'lr': 0.00017445361581621644, 'samples': 17368896, 'steps': 90462, 'loss/train': 1.7347183227539062}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:51 - INFO - __main__ - Step 90468: {'lr': 0.00017442832299463762, 'samples': 17369856, 'steps': 90467, 'loss/train': 1.6411794424057007}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:53 - INFO - __main__ - Step 90472: {'lr': 0.0001744080893502867, 'samples': 17370624, 'steps': 90471, 'loss/train': 1.4653606414794922}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:53 - INFO - __main__ - Step 90472: {'lr': 0.0001744080893502867, 'samples': 17370624, 'steps': 90471, 'loss/train': 1.4653606414794922}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:56 - INFO - __main__ - Step 90479: {'lr': 0.00017437268178409148, 'samples': 17371968, 'steps': 90478, 'loss/train': 1.5253348350524902}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:58:59 - INFO - __main__ - Step 90484: {'lr': 0.00017434739168763007, 'samples': 17372928, 'steps': 90483, 'loss/train': 1.6561311483383179}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:01 - INFO - __main__ - Step 90488: {'lr': 0.0001743271602240295, 'samples': 17373696, 'steps': 90487, 'loss/train': 1.3352100849151611}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:01 - INFO - __main__ - Step 90488: {'lr': 0.0001743271602240295, 'samples': 17373696, 'steps': 90487, 'loss/train': 1.3352100849151611}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:04 - INFO - __main__ - Step 90495: {'lr': 0.00017429175647555115, 'samples': 17375040, 'steps': 90494, 'loss/train': 2.74178147315979}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:06 - INFO - __main__ - Step 90500: {'lr': 0.00017426646910712428, 'samples': 17376000, 'steps': 90499, 'loss/train': 1.767688274383545}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:06 - INFO - __main__ - Step 90500: {'lr': 0.00017426646910712428, 'samples': 17376000, 'steps': 90499, 'loss/train': 1.767688274383545}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:11 - INFO - __main__ - Step 90508: {'lr': 0.00017422601109222662, 'samples': 17377536, 'steps': 90507, 'loss/train': 0.9942478537559509}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:12 - INFO - __main__ - Step 90512: {'lr': 0.00017420578290412703, 'samples': 17378304, 'steps': 90511, 'loss/train': 1.7863572835922241}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:14 - INFO - __main__ - Step 90516: {'lr': 0.00017418555526245476, 'samples': 17379072, 'steps': 90515, 'loss/train': 1.3381112813949585}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:16 - INFO - __main__ - Step 90521: {'lr': 0.00017416027147899984, 'samples': 17380032, 'steps': 90520, 'loss/train': 1.213720440864563}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:19 - INFO - __main__ - Step 90526: {'lr': 0.0001741349885498502, 'samples': 17380992, 'steps': 90525, 'loss/train': 1.191081166267395}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:21 - INFO - __main__ - Step 90530: {'lr': 0.0001741147628218218, 'samples': 17381760, 'steps': 90529, 'loss/train': 0.7332841157913208}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:21 - INFO - __main__ - Step 90530: {'lr': 0.0001741147628218218, 'samples': 17381760, 'steps': 90529, 'loss/train': 0.7332841157913208}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:24 - INFO - __main__ - Step 90537: {'lr': 0.00017407936911427923, 'samples': 17383104, 'steps': 90536, 'loss/train': 1.3598071336746216}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:27 - INFO - __main__ - Step 90542: {'lr': 0.0001740540889208204, 'samples': 17384064, 'steps': 90541, 'loss/train': 0.5651528835296631}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:27 - INFO - __main__ - Step 90542: {'lr': 0.0001740540889208204, 'samples': 17384064, 'steps': 90541, 'loss/train': 0.5651528835296631}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:31 - INFO - __main__ - Step 90550: {'lr': 0.00017401364239084754, 'samples': 17385600, 'steps': 90549, 'loss/train': 1.4271320104599}1}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:32 - INFO - __main__ - Step 90554: {'lr': 0.00017399341994750692, 'samples': 17386368, 'steps': 90553, 'loss/train': 1.879335880279541}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:35 - INFO - __main__ - Step 90558: {'lr': 0.00017397319805212465, 'samples': 17387136, 'steps': 90557, 'loss/train': 1.2909905910491943}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:37 - INFO - __main__ - Step 90563: {'lr': 0.00017394792145368514, 'samples': 17388096, 'steps': 90562, 'loss/train': 1.467996597290039}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:37 - INFO - __main__ - Step 90563: {'lr': 0.00017394792145368514, 'samples': 17388096, 'steps': 90562, 'loss/train': 1.467996597290039}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:40 - INFO - __main__ - Step 90570: {'lr': 0.00017391253565518522, 'samples': 17389440, 'steps': 90569, 'loss/train': 1.618923306465149}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:43 - INFO - __main__ - Step 90574: {'lr': 0.0001738923159530938, 'samples': 17390208, 'steps': 90573, 'loss/train': 1.499133586883545}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:45 - INFO - __main__ - Step 90579: {'lr': 0.00017386704209708794, 'samples': 17391168, 'steps': 90578, 'loss/train': 1.4331235885620117}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:45 - INFO - __main__ - Step 90579: {'lr': 0.00017386704209708794, 'samples': 17391168, 'steps': 90578, 'loss/train': 1.4331235885620117}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:48 - INFO - __main__ - Step 90586: {'lr': 0.0001738316601395257, 'samples': 17392512, 'steps': 90585, 'loss/train': 1.446710228919983}7}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:51 - INFO - __main__ - Step 90591: {'lr': 0.00017380638834225826, 'samples': 17393472, 'steps': 90590, 'loss/train': 1.4521089792251587}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:53 - INFO - __main__ - Step 90595: {'lr': 0.00017378617152240063, 'samples': 17394240, 'steps': 90594, 'loss/train': 1.0167865753173828}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:53 - INFO - __main__ - Step 90595: {'lr': 0.00017378617152240063, 'samples': 17394240, 'steps': 90594, 'loss/train': 1.0167865753173828}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:56 - INFO - __main__ - Step 90602: {'lr': 0.0001737507934098574, 'samples': 17395584, 'steps': 90601, 'loss/train': 1.000494122505188}8}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 09:59:59 - INFO - __main__ - Step 90607: {'lr': 0.00017372552436012523, 'samples': 17396544, 'steps': 90606, 'loss/train': 1.4004936218261719}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:01 - INFO - __main__ - Step 90612: {'lr': 0.00017370025616959573, 'samples': 17397504, 'steps': 90611, 'loss/train': 1.2611310482025146}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:03 - INFO - __main__ - Step 90616: {'lr': 0.00017368004223598912, 'samples': 17398272, 'steps': 90615, 'loss/train': 1.3316253423690796}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:05 - INFO - __main__ - Step 90620: {'lr': 0.00017365982885260008, 'samples': 17399040, 'steps': 90619, 'loss/train': 1.380651593208313}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:07 - INFO - __main__ - Step 90624: {'lr': 0.00017363961601957434, 'samples': 17399808, 'steps': 90623, 'loss/train': 1.593830943107605}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:09 - INFO - __main__ - Step 90628: {'lr': 0.0001736194037370575, 'samples': 17400576, 'steps': 90627, 'loss/train': 1.4519051313400269}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:11 - INFO - __main__ - Step 90633: {'lr': 0.00017359413915828668, 'samples': 17401536, 'steps': 90632, 'loss/train': 1.6062027215957642}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:13 - INFO - __main__ - Step 90637: {'lr': 0.00017357392811494788, 'samples': 17402304, 'steps': 90636, 'loss/train': 1.7459847927093506}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:13 - INFO - __main__ - Step 90637: {'lr': 0.00017357392811494788, 'samples': 17402304, 'steps': 90636, 'loss/train': 1.7459847927093506}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:17 - INFO - __main__ - Step 90644: {'lr': 0.00017353856011499423, 'samples': 17403648, 'steps': 90643, 'loss/train': 0.37086859345436096}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:19 - INFO - __main__ - Step 90648: {'lr': 0.00017351835058720792, 'samples': 17404416, 'steps': 90647, 'loss/train': 0.8730949759483337}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:21 - INFO - __main__ - Step 90653: {'lr': 0.00017349308945287484, 'samples': 17405376, 'steps': 90652, 'loss/train': 1.870360016822815}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:21 - INFO - __main__ - Step 90653: {'lr': 0.00017349308945287484, 'samples': 17405376, 'steps': 90652, 'loss/train': 1.870360016822815}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:25 - INFO - __main__ - Step 90660: {'lr': 0.00017345772531273117, 'samples': 17406720, 'steps': 90659, 'loss/train': 1.2895289659500122}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:27 - INFO - __main__ - Step 90665: {'lr': 0.00017343246624724614, 'samples': 17407680, 'steps': 90664, 'loss/train': 1.376447319984436}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:27 - INFO - __main__ - Step 90665: {'lr': 0.00017343246624724614, 'samples': 17407680, 'steps': 90664, 'loss/train': 1.376447319984436}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:31 - INFO - __main__ - Step 90672: {'lr': 0.000173397105004637, 'samples': 17409024, 'steps': 90671, 'loss/train': 1.1052051782608032}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:33 - INFO - __main__ - Step 90676: {'lr': 0.00017337689933959267, 'samples': 17409792, 'steps': 90675, 'loss/train': 1.5633021593093872}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:35 - INFO - __main__ - Step 90681: {'lr': 0.000173351643035121, 'samples': 17410752, 'steps': 90680, 'loss/train': 1.4554238319396973}2}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:35 - INFO - __main__ - Step 90681: {'lr': 0.000173351643035121, 'samples': 17410752, 'steps': 90680, 'loss/train': 1.4554238319396973}2}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:39 - INFO - __main__ - Step 90689: {'lr': 0.00017331123474398618, 'samples': 17412288, 'steps': 90688, 'loss/train': 1.197777271270752}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:39 - INFO - __main__ - Step 90689: {'lr': 0.00017331123474398618, 'samples': 17412288, 'steps': 90688, 'loss/train': 1.197777271270752}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:42 - INFO - __main__ - Step 90696: {'lr': 0.0001732758793033291, 'samples': 17413632, 'steps': 90695, 'loss/train': 1.2417323589324951}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:45 - INFO - __main__ - Step 90702: {'lr': 0.00017324557598813654, 'samples': 17414784, 'steps': 90701, 'loss/train': 1.0871772766113281}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:45 - INFO - __main__ - Step 90702: {'lr': 0.00017324557598813654, 'samples': 17414784, 'steps': 90701, 'loss/train': 1.0871772766113281}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:48 - INFO - __main__ - Step 90709: {'lr': 0.00017321022369403484, 'samples': 17416128, 'steps': 90708, 'loss/train': 2.0508079528808594}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:50 - INFO - __main__ - Step 90713: {'lr': 0.0001731900231442758, 'samples': 17416896, 'steps': 90712, 'loss/train': 1.4087014198303223}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:53 - INFO - __main__ - Step 90718: {'lr': 0.00017316477323580547, 'samples': 17417856, 'steps': 90717, 'loss/train': 1.6821919679641724}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:55 - INFO - __main__ - Step 90723: {'lr': 0.0001731395241928542, 'samples': 17418816, 'steps': 90722, 'loss/train': 1.3514724969863892}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:55 - INFO - __main__ - Step 90723: {'lr': 0.0001731395241928542, 'samples': 17418816, 'steps': 90722, 'loss/train': 1.3514724969863892}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:00:59 - INFO - __main__ - Step 90730: {'lr': 0.00017310417698733631, 'samples': 17420160, 'steps': 90729, 'loss/train': 1.5250980854034424}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:01 - INFO - __main__ - Step 90734: {'lr': 0.0001730839793463907, 'samples': 17420928, 'steps': 90733, 'loss/train': 0.9838910102844238}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:03 - INFO - __main__ - Step 90739: {'lr': 0.00017305873307501212, 'samples': 17421888, 'steps': 90738, 'loss/train': 1.230529546737671}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:03 - INFO - __main__ - Step 90739: {'lr': 0.00017305873307501212, 'samples': 17421888, 'steps': 90738, 'loss/train': 1.230529546737671}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] + torch.nn.utils.clip_grad_norm_(parameters, max_norm, norm_type=norm_type)501212, 'samples': 17421888, 'steps': 90738, 'loss/train': 1.230529546737671}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:09 - INFO - __main__ - Step 90750: {'lr': 0.0001730031943292119, 'samples': 17424000, 'steps': 90749, 'loss/train': 1.2392898797988892}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:11 - INFO - __main__ - Step 90756: {'lr': 0.00017297290223704508, 'samples': 17425152, 'steps': 90755, 'loss/train': 1.4785592555999756}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:11 - INFO - __main__ - Step 90756: {'lr': 0.00017297290223704508, 'samples': 17425152, 'steps': 90755, 'loss/train': 1.4785592555999756}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:15 - INFO - __main__ - Step 90763: {'lr': 0.0001729375630420637, 'samples': 17426496, 'steps': 90762, 'loss/train': 1.9851211309432983}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:17 - INFO - __main__ - Step 90768: {'lr': 0.00017291232180158289, 'samples': 17427456, 'steps': 90767, 'loss/train': 1.1872127056121826}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:17 - INFO - __main__ - Step 90768: {'lr': 0.00017291232180158289, 'samples': 17427456, 'steps': 90767, 'loss/train': 1.1872127056121826}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:21 - INFO - __main__ - Step 90775: {'lr': 0.0001728769855238233, 'samples': 17428800, 'steps': 90774, 'loss/train': 1.202199101448059}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:23 - INFO - __main__ - Step 90779: {'lr': 0.00017285679412956315, 'samples': 17429568, 'steps': 90778, 'loss/train': 1.577003836631775}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:25 - INFO - __main__ - Step 90783: {'lr': 0.00017283660329145558, 'samples': 17430336, 'steps': 90782, 'loss/train': 1.3178248405456543}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:27 - INFO - __main__ - Step 90788: {'lr': 0.00017281136552613265, 'samples': 17431296, 'steps': 90787, 'loss/train': 1.6064475774765015}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:29 - INFO - __main__ - Step 90792: {'lr': 0.00017279117593990063, 'samples': 17432064, 'steps': 90791, 'loss/train': 1.5055913925170898}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:31 - INFO - __main__ - Step 90796: {'lr': 0.00017277098691029441, 'samples': 17432832, 'steps': 90795, 'loss/train': 1.474041223526001}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:33 - INFO - __main__ - Step 90800: {'lr': 0.0001727507984374594, 'samples': 17433600, 'steps': 90799, 'loss/train': 1.1695481538772583}}}█████████████���█████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:35 - INFO - __main__ - Step 90804: {'lr': 0.00017273061052154107, 'samples': 17434368, 'steps': 90803, 'loss/train': 0.4196327030658722}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:37 - INFO - __main__ - Step 90809: {'lr': 0.00017270537641002917, 'samples': 17435328, 'steps': 90808, 'loss/train': 1.7435128688812256}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:40 - INFO - __main__ - Step 90814: {'lr': 0.00017268014316921138, 'samples': 17436288, 'steps': 90813, 'loss/train': 0.8714263439178467}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:42 - INFO - __main__ - Step 90818: {'lr': 0.00017265995720364797, 'samples': 17437056, 'steps': 90817, 'loss/train': 1.3641982078552246}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:42 - INFO - __main__ - Step 90818: {'lr': 0.00017265995720364797, 'samples': 17437056, 'steps': 90817, 'loss/train': 1.3641982078552246}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:45 - INFO - __main__ - Step 90825: {'lr': 0.0001726246331056563, 'samples': 17438400, 'steps': 90824, 'loss/train': 1.497603178024292}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:47 - INFO - __main__ - Step 90830: {'lr': 0.00017259940265296976, 'samples': 17439360, 'steps': 90829, 'loss/train': 1.3474242687225342}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:47 - INFO - __main__ - Step 90830: {'lr': 0.00017259940265296976, 'samples': 17439360, 'steps': 90829, 'loss/train': 1.3474242687225342}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:47 - INFO - __main__ - Step 90830: {'lr': 0.00017259940265296976, 'samples': 17439360, 'steps': 90829, 'loss/train': 1.3474242687225342}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:53 - INFO - __main__ - Step 90841: {'lr': 0.00017254389872650477, 'samples': 17441472, 'steps': 90840, 'loss/train': 1.1481537818908691}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:56 - INFO - __main__ - Step 90846: {'lr': 0.00017251867106485974, 'samples': 17442432, 'steps': 90845, 'loss/train': 1.3717129230499268}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:58 - INFO - __main__ - Step 90850: {'lr': 0.0001724984895639441, 'samples': 17443200, 'steps': 90849, 'loss/train': 1.0904229879379272}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:01:58 - INFO - __main__ - Step 90850: {'lr': 0.0001724984895639441, 'samples': 17443200, 'steps': 90849, 'loss/train': 1.0904229879379272}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:01 - INFO - __main__ - Step 90857: {'lr': 0.0001724631732818873, 'samples': 17444544, 'steps': 90856, 'loss/train': 0.41471222043037415}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:03 - INFO - __main__ - Step 90861: {'lr': 0.00017244299331784508, 'samples': 17445312, 'steps': 90860, 'loss/train': 0.5044549107551575}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:05 - INFO - __main__ - Step 90866: {'lr': 0.00017241776914909423, 'samples': 17446272, 'steps': 90865, 'loss/train': 1.391155481338501}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:08 - INFO - __main__ - Step 90871: {'lr': 0.00017239254585427722, 'samples': 17447232, 'steps': 90870, 'loss/train': 1.6012749671936035}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:08 - INFO - __main__ - Step 90871: {'lr': 0.00017239254585427722, 'samples': 17447232, 'steps': 90870, 'loss/train': 1.6012749671936035}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:11 - INFO - __main__ - Step 90878: {'lr': 0.00017235723471028337, 'samples': 17448576, 'steps': 90877, 'loss/train': 1.283045768737793}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:13 - INFO - __main__ - Step 90882: {'lr': 0.0001723370576833273, 'samples': 17449344, 'steps': 90881, 'loss/train': 1.4307562112808228}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:16 - INFO - __main__ - Step 90888: {'lr': 0.00017230679319275039, 'samples': 17450496, 'steps': 90887, 'loss/train': 1.972109317779541}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:18 - INFO - __main__ - Step 90892: {'lr': 0.0001722866175658161, 'samples': 17451264, 'steps': 90891, 'loss/train': 1.3806867599487305}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:20 - INFO - __main__ - Step 90896: {'lr': 0.0001722664424991449, 'samples': 17452032, 'steps': 90895, 'loss/train': 1.6436522006988525}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:20 - INFO - __main__ - Step 90896: {'lr': 0.0001722664424991449, 'samples': 17452032, 'steps': 90895, 'loss/train': 1.6436522006988525}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:23 - INFO - __main__ - Step 90903: {'lr': 0.0001722311374810412, 'samples': 17453376, 'steps': 90902, 'loss/train': 1.159103512763977}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:26 - INFO - __main__ - Step 90908: {'lr': 0.00017220592066216527, 'samples': 17454336, 'steps': 90907, 'loss/train': 1.4246491193771362}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:28 - INFO - __main__ - Step 90913: {'lr': 0.0001721807047196095, 'samples': 17455296, 'steps': 90912, 'loss/train': 1.8041881322860718}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:30 - INFO - __main__ - Step 90917: {'lr': 0.00017216053259670638, 'samples': 17456064, 'steps': 90916, 'loss/train': 1.2293827533721924}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:32 - INFO - __main__ - Step 90921: {'lr': 0.0001721403610349756, 'samples': 17456832, 'steps': 90920, 'loss/train': 1.4016817808151245}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:34 - INFO - __main__ - Step 90925: {'lr': 0.0001721201900345623, 'samples': 17457600, 'steps': 90924, 'loss/train': 1.5021966695785522}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:36 - INFO - __main__ - Step 90929: {'lr': 0.0001721000195956121, 'samples': 17458368, 'steps': 90928, 'loss/train': 1.6959307193756104}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:38 - INFO - __main__ - Step 90934: {'lr': 0.00017207480733670333, 'samples': 17459328, 'steps': 90933, 'loss/train': 1.10098135471344}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:40 - INFO - __main__ - Step 90938: {'lr': 0.00017205463816157666, 'samples': 17460096, 'steps': 90937, 'loss/train': 1.249803900718689}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:42 - INFO - __main__ - Step 90942: {'lr': 0.00017203446954838563, 'samples': 17460864, 'steps': 90941, 'loss/train': 1.4266585111618042}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:42 - INFO - __main__ - Step 90942: {'lr': 0.00017203446954838563, 'samples': 17460864, 'steps': 90941, 'loss/train': 1.4266585111618042}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:45 - INFO - __main__ - Step 90949: {'lr': 0.00017199917582789631, 'samples': 17462208, 'steps': 90948, 'loss/train': 1.4269237518310547}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:45 - INFO - __main__ - Step 90949: {'lr': 0.00017199917582789631, 'samples': 17462208, 'steps': 90948, 'loss/train': 1.4269237518310547}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:50 - INFO - __main__ - Step 90958: {'lr': 0.00017195380071788585, 'samples': 17463936, 'steps': 90957, 'loss/train': 1.4316151142120361}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:52 - INFO - __main__ - Step 90962: {'lr': 0.00017193363491655402, 'samples': 17464704, 'steps': 90961, 'loss/train': 1.3703103065490723}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:54 - INFO - __main__ - Step 90966: {'lr': 0.0001719134696780301, 'samples': 17465472, 'steps': 90965, 'loss/train': 1.5033605098724365}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:56 - INFO - __main__ - Step 90970: {'lr': 0.00017189330500245954, 'samples': 17466240, 'steps': 90969, 'loss/train': 1.472920536994934}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:02:58 - INFO - __main__ - Step 90975: {'lr': 0.00017186809994987107, 'samples': 17467200, 'steps': 90974, 'loss/train': 0.26463308930397034}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:00 - INFO - __main__ - Step 90979: {'lr': 0.0001718479365414771, 'samples': 17467968, 'steps': 90978, 'loss/train': 1.8689799308776855}4}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:02 - INFO - __main__ - Step 90983: {'lr': 0.00017182777369650898, 'samples': 17468736, 'steps': 90982, 'loss/train': 1.4653409719467163}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:04 - INFO - __main__ - Step 90987: {'lr': 0.00017180761141511215, 'samples': 17469504, 'steps': 90986, 'loss/train': 1.6866122484207153}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:06 - INFO - __main__ - Step 90992: {'lr': 0.00017178240935610933, 'samples': 17470464, 'steps': 90991, 'loss/train': 1.8760197162628174}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:06 - INFO - __main__ - Step 90992: {'lr': 0.00017178240935610933, 'samples': 17470464, 'steps': 90991, 'loss/train': 1.8760197162628174}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:10 - INFO - __main__ - Step 90997: {'lr': 0.00017175720817819753, 'samples': 17471424, 'steps': 90996, 'loss/train': 0.49548232555389404}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:12 - INFO - __main__ - Step 91003: {'lr': 0.0001717269679281433, 'samples': 17472576, 'steps': 91002, 'loss/train': 1.1743091344833374}4}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:14 - INFO - __main__ - Step 91007: {'lr': 0.0001717068084667825, 'samples': 17473344, 'steps': 91006, 'loss/train': 1.1020389795303345}4}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:16 - INFO - __main__ - Step 91011: {'lr': 0.00017168664956986501, 'samples': 17474112, 'steps': 91010, 'loss/train': 1.2773441076278687}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:18 - INFO - __main__ - Step 91015: {'lr': 0.0001716664912375362, 'samples': 17474880, 'steps': 91014, 'loss/train': 0.8659502267837524}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:18 - INFO - __main__ - Step 91015: {'lr': 0.0001716664912375362, 'samples': 17474880, 'steps': 91014, 'loss/train': 0.8659502267837524}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:18 - INFO - __main__ - Step 91015: {'lr': 0.0001716664912375362, 'samples': 17474880, 'steps': 91014, 'loss/train': 0.8659502267837524}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:24 - INFO - __main__ - Step 91026: {'lr': 0.0001716110587359782, 'samples': 17476992, 'steps': 91025, 'loss/train': 1.5634592771530151}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:26 - INFO - __main__ - Step 91032: {'lr': 0.0001715808246272076, 'samples': 17478144, 'steps': 91031, 'loss/train': 1.349709391593933}}}}██████████████████��████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:29 - INFO - __main__ - Step 91036: {'lr': 0.000171560669261353, 'samples': 17478912, 'steps': 91035, 'loss/train': 1.3246372938156128}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:31 - INFO - __main__ - Step 91040: {'lr': 0.00017154051446099537, 'samples': 17479680, 'steps': 91039, 'loss/train': 1.4123868942260742}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:33 - INFO - __main__ - Step 91044: {'lr': 0.00017152036022627975, 'samples': 17480448, 'steps': 91043, 'loss/train': 1.0355415344238281}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:34 - INFO - __main__ - Step 91048: {'lr': 0.00017150020655735154, 'samples': 17481216, 'steps': 91047, 'loss/train': 1.507782220840454}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:36 - INFO - __main__ - Step 91052: {'lr': 0.0001714800534543561, 'samples': 17481984, 'steps': 91051, 'loss/train': 1.2615793943405151}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:38 - INFO - __main__ - Step 91057: {'lr': 0.0001714548628716761, 'samples': 17482944, 'steps': 91056, 'loss/train': 1.9136332273483276}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:38 - INFO - __main__ - Step 91057: {'lr': 0.0001714548628716761, 'samples': 17482944, 'steps': 91056, 'loss/train': 1.9136332273483276}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:42 - INFO - __main__ - Step 91064: {'lr': 0.00017141959754241916, 'samples': 17484288, 'steps': 91063, 'loss/train': 1.466196894645691}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:44 - INFO - __main__ - Step 91068: {'lr': 0.00017139944670460755, 'samples': 17485056, 'steps': 91067, 'loss/train': 1.5781985521316528}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:46 - INFO - __main__ - Step 91073: {'lr': 0.00017137425895422437, 'samples': 17486016, 'steps': 91072, 'loss/train': 1.1582558155059814}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:49 - INFO - __main__ - Step 91078: {'lr': 0.00017134907208952993, 'samples': 17486976, 'steps': 91077, 'loss/train': 0.1866437941789627}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:51 - INFO - __main__ - Step 91082: {'lr': 0.00017132892323566085, 'samples': 17487744, 'steps': 91081, 'loss/train': 0.4788397252559662}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:51 - INFO - __main__ - Step 91082: {'lr': 0.00017132892323566085, 'samples': 17487744, 'steps': 91081, 'loss/train': 0.4788397252559662}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:54 - INFO - __main__ - Step 91089: {'lr': 0.00017129366410622432, 'samples': 17489088, 'steps': 91088, 'loss/train': 1.5693994760513306}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:56 - INFO - __main__ - Step 91094: {'lr': 0.00017126848007764008, 'samples': 17490048, 'steps': 91093, 'loss/train': 1.5615043640136719}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:59 - INFO - __main__ - Step 91099: {'lr': 0.00017124329693593598, 'samples': 17491008, 'steps': 91098, 'loss/train': 1.0956145524978638}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:03:59 - INFO - __main__ - Step 91099: {'lr': 0.00017124329693593598, 'samples': 17491008, 'steps': 91098, 'loss/train': 1.0956145524978638}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:02 - INFO - __main__ - Step 91105: {'lr': 0.00017121307833697235, 'samples': 17492160, 'steps': 91104, 'loss/train': 1.435557246208191}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:04 - INFO - __main__ - Step 91110: {'lr': 0.00017118789714740332, 'samples': 17493120, 'steps': 91109, 'loss/train': 0.8633219003677368}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:04 - INFO - __main__ - Step 91110: {'lr': 0.00017118789714740332, 'samples': 17493120, 'steps': 91109, 'loss/train': 0.8633219003677368}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:08 - INFO - __main__ - Step 91117: {'lr': 0.00017115264497355383, 'samples': 17494464, 'steps': 91116, 'loss/train': 1.7465263605117798}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:10 - INFO - __main__ - Step 91122: {'lr': 0.00017112746591515233, 'samples': 17495424, 'steps': 91121, 'loss/train': 1.3189162015914917}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:13 - INFO - __main__ - Step 91126: {'lr': 0.0001711073233081149, 'samples': 17496192, 'steps': 91125, 'loss/train': 1.839024543762207}7}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:13 - INFO - __main__ - Step 91126: {'lr': 0.0001711073233081149, 'samples': 17496192, 'steps': 91125, 'loss/train': 1.839024543762207}7}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:16 - INFO - __main__ - Step 91133: {'lr': 0.00017107207511447793, 'samples': 17497536, 'steps': 91132, 'loss/train': 1.4766162633895874}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:19 - INFO - __main__ - Step 91138: {'lr': 0.00017104689890017454, 'samples': 17498496, 'steps': 91137, 'loss/train': 1.5001730918884277}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:21 - INFO - __main__ - Step 91142: {'lr': 0.000171026758569069, 'samples': 17499264, 'steps': 91141, 'loss/train': 1.4049038887023926}7}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:23 - INFO - __main__ - Step 91146: {'lr': 0.0001710066188073095, 'samples': 17500032, 'steps': 91145, 'loss/train': 1.4620858430862427}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:25 - INFO - __main__ - Step 91150: {'lr': 0.0001709864796150412, 'samples': 17500800, 'steps': 91149, 'loss/train': 1.4680781364440918}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:26 - INFO - __main__ - Step 91154: {'lr': 0.0001709663409924092, 'samples': 17501568, 'steps': 91153, 'loss/train': 1.4218530654907227}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:29 - INFO - __main__ - Step 91159: {'lr': 0.00017094116851539153, 'samples': 17502528, 'steps': 91158, 'loss/train': 1.2835404872894287}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:29 - INFO - __main__ - Step 91159: {'lr': 0.00017094116851539153, 'samples': 17502528, 'steps': 91158, 'loss/train': 1.2835404872894287}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:32 - INFO - __main__ - Step 91164: {'lr': 0.00017091599692894123, 'samples': 17503488, 'steps': 91163, 'loss/train': 1.440803050994873}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:32 - INFO - __main__ - Step 91164: {'lr': 0.00017091599692894123, 'samples': 17503488, 'steps': 91163, 'loss/train': 1.440803050994873}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:37 - INFO - __main__ - Step 91173: {'lr': 0.00017087069031846498, 'samples': 17505216, 'steps': 91172, 'loss/train': 1.1451759338378906}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:38 - INFO - __main__ - Step 91177: {'lr': 0.0001708505549740596, 'samples': 17505984, 'steps': 91176, 'loss/train': 1.075728416442871}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:40 - INFO - __main__ - Step 91181: {'lr': 0.0001708304202002704, 'samples': 17506752, 'steps': 91180, 'loss/train': 1.0663374662399292}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:40 - INFO - __main__ - Step 91181: {'lr': 0.0001708304202002704, 'samples': 17506752, 'steps': 91180, 'loss/train': 1.0663374662399292}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:45 - INFO - __main__ - Step 91189: {'lr': 0.00017079015236512167, 'samples': 17508288, 'steps': 91188, 'loss/train': 1.3204582929611206}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:46 - INFO - __main__ - Step 91193: {'lr': 0.0001707700193040523, 'samples': 17509056, 'steps': 91192, 'loss/train': 1.1278618574142456}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:48 - INFO - __main__ - Step 91197: {'lr': 0.00017074988681417986, 'samples': 17509824, 'steps': 91196, 'loss/train': 0.6712296605110168}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:50 - INFO - __main__ - Step 91201: {'lr': 0.00017072975489564957, 'samples': 17510592, 'steps': 91200, 'loss/train': 1.3524197340011597}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:52 - INFO - __main__ - Step 91205: {'lr': 0.00017070962354860637, 'samples': 17511360, 'steps': 91204, 'loss/train': 1.4704904556274414}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:55 - INFO - __main__ - Step 91209: {'lr': 0.0001706894927731955, 'samples': 17512128, 'steps': 91208, 'loss/train': 0.7523512840270996}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:56 - INFO - __main__ - Step 91213: {'lr': 0.00017066936256956205, 'samples': 17512896, 'steps': 91212, 'loss/train': 1.3646070957183838}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:04:59 - INFO - __main__ - Step 91218: {'lr': 0.00017064420061930344, 'samples': 17513856, 'steps': 91217, 'loss/train': 1.1837769746780396}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:01 - INFO - __main__ - Step 91222: {'lr': 0.00017062407170269996, 'samples': 17514624, 'steps': 91221, 'loss/train': 1.65607488155365}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:01 - INFO - __main__ - Step 91222: {'lr': 0.00017062407170269996, 'samples': 17514624, 'steps': 91221, 'loss/train': 1.65607488155365}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:04 - INFO - __main__ - Step 91228: {'lr': 0.00017059387940080703, 'samples': 17515776, 'steps': 91227, 'loss/train': 1.2842695713043213}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:06 - INFO - __main__ - Step 91232: {'lr': 0.00017057375191509834, 'samples': 17516544, 'steps': 91231, 'loss/train': 1.7042371034622192}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:08 - INFO - __main__ - Step 91236: {'lr': 0.00017055362500200148, 'samples': 17517312, 'steps': 91235, 'loss/train': 1.5776647329330444}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:08 - INFO - __main__ - Step 91236: {'lr': 0.00017055362500200148, 'samples': 17517312, 'steps': 91235, 'loss/train': 1.5776647329330444}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:12 - INFO - __main__ - Step 91244: {'lr': 0.0001705133728942238, 'samples': 17518848, 'steps': 91243, 'loss/train': 1.7854468822479248}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:14 - INFO - __main__ - Step 91248: {'lr': 0.00017049324769983316, 'samples': 17519616, 'steps': 91247, 'loss/train': 0.8454214334487915}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:17 - INFO - __main__ - Step 91253: {'lr': 0.0001704680920129134, 'samples': 17520576, 'steps': 91252, 'loss/train': 1.6376200914382935}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:19 - INFO - __main__ - Step 91257: {'lr': 0.00017044796810840944, 'samples': 17521344, 'steps': 91256, 'loss/train': 1.656106948852539}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:19 - INFO - __main__ - Step 91257: {'lr': 0.00017044796810840944, 'samples': 17521344, 'steps': 91256, 'loss/train': 1.656106948852539}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:22 - INFO - __main__ - Step 91265: {'lr': 0.0001704077220201024, 'samples': 17522880, 'steps': 91264, 'loss/train': 1.4198641777038574}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:24 - INFO - __main__ - Step 91269: {'lr': 0.0001703875998365897, 'samples': 17523648, 'steps': 91268, 'loss/train': 1.2942326068878174}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:27 - INFO - __main__ - Step 91274: {'lr': 0.0001703624479143384, 'samples': 17524608, 'steps': 91273, 'loss/train': 1.4274370670318604}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:27 - INFO - __main__ - Step 91274: {'lr': 0.0001703624479143384, 'samples': 17524608, 'steps': 91273, 'loss/train': 1.4274370670318604}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:30 - INFO - __main__ - Step 91281: {'lr': 0.0001703272367303551, 'samples': 17525952, 'steps': 91280, 'loss/train': 1.2879928350448608}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:32 - INFO - __main__ - Step 91285: {'lr': 0.00017030711684352828, 'samples': 17526720, 'steps': 91284, 'loss/train': 1.0825468301773071}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:35 - INFO - __main__ - Step 91290: {'lr': 0.00017028196779295034, 'samples': 17527680, 'steps': 91289, 'loss/train': 1.4476888179779053}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:37 - INFO - __main__ - Step 91294: {'lr': 0.00017026184919902932, 'samples': 17528448, 'steps': 91293, 'loss/train': 1.1649945974349976}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:37 - INFO - __main__ - Step 91294: {'lr': 0.00017026184919902932, 'samples': 17528448, 'steps': 91293, 'loss/train': 1.1649945974349976}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:40 - INFO - __main__ - Step 91301: {'lr': 0.00017022664304301287, 'samples': 17529792, 'steps': 91300, 'loss/train': 1.7646725177764893}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:43 - INFO - __main__ - Step 91306: {'lr': 0.00017020149686700937, 'samples': 17530752, 'steps': 91305, 'loss/train': 1.1036608219146729}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:45 - INFO - __main__ - Step 91311: {'lr': 0.0001701763515899053, 'samples': 17531712, 'steps': 91310, 'loss/train': 1.5035629272460938}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:45 - INFO - __main__ - Step 91311: {'lr': 0.0001701763515899053, 'samples': 17531712, 'steps': 91310, 'loss/train': 1.5035629272460938}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:49 - INFO - __main__ - Step 91318: {'lr': 0.00017014114971264965, 'samples': 17533056, 'steps': 91317, 'loss/train': 1.5191997289657593}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:50 - INFO - __main__ - Step 91322: {'lr': 0.00017012103514579775, 'samples': 17533824, 'steps': 91321, 'loss/train': 1.1261495351791382}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:50 - INFO - __main__ - Step 91322: {'lr': 0.00017012103514579775, 'samples': 17533824, 'steps': 91321, 'loss/train': 1.1261495351791382}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:54 - INFO - __main__ - Step 91329: {'lr': 0.0001700858360395948, 'samples': 17535168, 'steps': 91328, 'loss/train': 1.6297506093978882}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:56 - INFO - __main__ - Step 91333: {'lr': 0.00017006572305674987, 'samples': 17535936, 'steps': 91332, 'loss/train': 1.1864266395568848}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:05:58 - INFO - __main__ - Step 91338: {'lr': 0.00017004058263859657, 'samples': 17536896, 'steps': 91337, 'loss/train': 1.1433144807815552}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:01 - INFO - __main__ - Step 91343: {'lr': 0.00017001544312115522, 'samples': 17537856, 'steps': 91342, 'loss/train': 1.2542108297348022}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:01 - INFO - __main__ - Step 91343: {'lr': 0.00017001544312115522, 'samples': 17537856, 'steps': 91342, 'loss/train': 1.2542108297348022}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:04 - INFO - __main__ - Step 91350: {'lr': 0.00016998024931047273, 'samples': 17539200, 'steps': 91349, 'loss/train': 1.7904645204544067}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:06 - INFO - __main__ - Step 91354: {'lr': 0.00016996013935468608, 'samples': 17539968, 'steps': 91353, 'loss/train': 1.3688372373580933}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:09 - INFO - __main__ - Step 91359: {'lr': 0.0001699350027214261, 'samples': 17540928, 'steps': 91358, 'loss/train': 1.293900489807129}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:09 - INFO - __main__ - Step 91359: {'lr': 0.0001699350027214261, 'samples': 17540928, 'steps': 91358, 'loss/train': 1.293900489807129}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:13 - INFO - __main__ - Step 91367: {'lr': 0.00016989478598428267, 'samples': 17542464, 'steps': 91366, 'loss/train': 1.2098374366760254}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:14 - INFO - __main__ - Step 91371: {'lr': 0.00016987467848189857, 'samples': 17543232, 'steps': 91370, 'loss/train': 1.4804768562316895}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:17 - INFO - __main__ - Step 91375: {'lr': 0.00016985457155716625, 'samples': 17544000, 'steps': 91374, 'loss/train': 1.4940910339355469}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:17 - INFO - __main__ - Step 91375: {'lr': 0.00016985457155716625, 'samples': 17544000, 'steps': 91374, 'loss/train': 1.4940910339355469}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:17 - INFO - __main__ - Step 91375: {'lr': 0.00016985457155716625, 'samples': 17544000, 'steps': 91374, 'loss/train': 1.4940910339355469}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:22 - INFO - __main__ - Step 91386: {'lr': 0.00016979928049385258, 'samples': 17546112, 'steps': 91385, 'loss/train': 0.9445826411247253}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:24 - INFO - __main__ - Step 91390: {'lr': 0.00016977917573660534, 'samples': 17546880, 'steps': 91389, 'loss/train': 1.3551080226898193}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:27 - INFO - __main__ - Step 91395: {'lr': 0.00016975404560335412, 'samples': 17547840, 'steps': 91394, 'loss/train': 1.689666748046875}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:27 - INFO - __main__ - Step 91395: {'lr': 0.00016975404560335412, 'samples': 17547840, 'steps': 91394, 'loss/train': 1.689666748046875}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:31 - INFO - __main__ - Step 91401: {'lr': 0.00016972389063667798, 'samples': 17548992, 'steps': 91400, 'loss/train': 1.7840617895126343}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:33 - INFO - __main__ - Step 91406: {'lr': 0.00016969876249246787, 'samples': 17549952, 'steps': 91405, 'loss/train': 1.1561403274536133}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:35 - INFO - __main__ - Step 91410: {'lr': 0.0001696786606283711, 'samples': 17550720, 'steps': 91409, 'loss/train': 1.593117594718933}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:37 - INFO - __main__ - Step 91414: {'lr': 0.00016965855934333925, 'samples': 17551488, 'steps': 91413, 'loss/train': 2.0148086547851562}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:39 - INFO - __main__ - Step 91419: {'lr': 0.00016963343355158028, 'samples': 17552448, 'steps': 91418, 'loss/train': 1.693266749382019}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:39 - INFO - __main__ - Step 91419: {'lr': 0.00016963343355158028, 'samples': 17552448, 'steps': 91418, 'loss/train': 1.693266749382019}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:39 - INFO - __main__ - Step 91419: {'lr': 0.00016963343355158028, 'samples': 17552448, 'steps': 91418, 'loss/train': 1.693266749382019}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:44 - INFO - __main__ - Step 91430: {'lr': 0.00016957815999675923, 'samples': 17554560, 'steps': 91429, 'loss/train': 1.2158445119857788}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:46 - INFO - __main__ - Step 91434: {'lr': 0.00016955806160922553, 'samples': 17555328, 'steps': 91433, 'loss/train': 0.8072934150695801}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:49 - INFO - __main__ - Step 91440: {'lr': 0.0001695279151153471, 'samples': 17556480, 'steps': 91439, 'loss/train': 0.8452351093292236}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:49 - INFO - __main__ - Step 91440: {'lr': 0.0001695279151153471, 'samples': 17556480, 'steps': 91439, 'loss/train': 0.8452351093292236}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:53 - INFO - __main__ - Step 91447: {'lr': 0.00016949274585566308, 'samples': 17557824, 'steps': 91446, 'loss/train': 1.3463484048843384}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:54 - INFO - __main__ - Step 91451: {'lr': 0.00016947264993385093, 'samples': 17558592, 'steps': 91450, 'loss/train': 1.277622938156128}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:56 - INFO - __main__ - Step 91455: {'lr': 0.0001694525545925889, 'samples': 17559360, 'steps': 91454, 'loss/train': 1.4367897510528564}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:06:59 - INFO - __main__ - Step 91460: {'lr': 0.00016942743623263074, 'samples': 17560320, 'steps': 91459, 'loss/train': 1.4880216121673584}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:01 - INFO - __main__ - Step 91464: {'lr': 0.00016940734219813615, 'samples': 17561088, 'steps': 91463, 'loss/train': 1.4385836124420166}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:03 - INFO - __main__ - Step 91468: {'lr': 0.0001693872487446625, 'samples': 17561856, 'steps': 91467, 'loss/train': 1.4051114320755005}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:05 - INFO - __main__ - Step 91472: {'lr': 0.00016936715587235465, 'samples': 17562624, 'steps': 91471, 'loss/train': 1.2289648056030273}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:06 - INFO - __main__ - Step 91476: {'lr': 0.0001693470635813574, 'samples': 17563392, 'steps': 91475, 'loss/train': 1.689540982246399}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:09 - INFO - __main__ - Step 91481: {'lr': 0.00016932194903529965, 'samples': 17564352, 'steps': 91480, 'loss/train': 0.6590220332145691}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:11 - INFO - __main__ - Step 91485: {'lr': 0.00016930185805278102, 'samples': 17565120, 'steps': 91484, 'loss/train': 1.276667833328247}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:13 - INFO - __main__ - Step 91489: {'lr': 0.0001692817676520438, 'samples': 17565888, 'steps': 91488, 'loss/train': 1.3047637939453125}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:15 - INFO - __main__ - Step 91493: {'lr': 0.00016926167783323272, 'samples': 17566656, 'steps': 91492, 'loss/train': 1.2962689399719238}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:17 - INFO - __main__ - Step 91497: {'lr': 0.0001692415885964928, 'samples': 17567424, 'steps': 91496, 'loss/train': 1.1872953176498413}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:19 - INFO - __main__ - Step 91501: {'lr': 0.0001692214999419688, 'samples': 17568192, 'steps': 91500, 'loss/train': 0.5300586223602295}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:21 - INFO - __main__ - Step 91506: {'lr': 0.00016919638994277543, 'samples': 17569152, 'steps': 91505, 'loss/train': 0.9032590389251709}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:23 - INFO - __main__ - Step 91510: {'lr': 0.00016917630259876668, 'samples': 17569920, 'steps': 91509, 'loss/train': 1.2112195491790771}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:23 - INFO - __main__ - Step 91510: {'lr': 0.00016917630259876668, 'samples': 17569920, 'steps': 91509, 'loss/train': 1.2112195491790771}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:26 - INFO - __main__ - Step 91517: {'lr': 0.00016914115114892805, 'samples': 17571264, 'steps': 91516, 'loss/train': 1.5914798974990845}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:29 - INFO - __main__ - Step 91522: {'lr': 0.0001691160440634391, 'samples': 17572224, 'steps': 91521, 'loss/train': 1.1952263116836548}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:29 - INFO - __main__ - Step 91522: {'lr': 0.0001691160440634391, 'samples': 17572224, 'steps': 91521, 'loss/train': 1.1952263116836548}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:33 - INFO - __main__ - Step 91530: {'lr': 0.00016907587462191773, 'samples': 17573760, 'steps': 91529, 'loss/train': 1.3909586668014526}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:35 - INFO - __main__ - Step 91534: {'lr': 0.00016905579077620048, 'samples': 17574528, 'steps': 91533, 'loss/train': 1.3680247068405151}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:37 - INFO - __main__ - Step 91538: {'lr': 0.00016903570751403873, 'samples': 17575296, 'steps': 91537, 'loss/train': 1.6117993593215942}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:39 - INFO - __main__ - Step 91543: {'lr': 0.0001690106042571818, 'samples': 17576256, 'steps': 91542, 'loss/train': 1.1166439056396484}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:39 - INFO - __main__ - Step 91543: {'lr': 0.0001690106042571818, 'samples': 17576256, 'steps': 91542, 'loss/train': 1.1166439056396484}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:43 - INFO - __main__ - Step 91551: {'lr': 0.0001689704409439421, 'samples': 17577792, 'steps': 91550, 'loss/train': 0.4917445182800293}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:45 - INFO - __main__ - Step 91555: {'lr': 0.00016895036016350589, 'samples': 17578560, 'steps': 91554, 'loss/train': 1.4410536289215088}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:47 - INFO - __main__ - Step 91559: {'lr': 0.0001689302799673851, 'samples': 17579328, 'steps': 91558, 'loss/train': 1.200127124786377}8}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:49 - INFO - __main__ - Step 91564: {'lr': 0.00016890518054414843, 'samples': 17580288, 'steps': 91563, 'loss/train': 1.5530080795288086}}��██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:51 - INFO - __main__ - Step 91569: {'lr': 0.00016888008203441352, 'samples': 17581248, 'steps': 91568, 'loss/train': 1.2190011739730835}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:51 - INFO - __main__ - Step 91569: {'lr': 0.00016888008203441352, 'samples': 17581248, 'steps': 91568, 'loss/train': 1.2190011739730835}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:55 - INFO - __main__ - Step 91576: {'lr': 0.00016884494565600608, 'samples': 17582592, 'steps': 91575, 'loss/train': 1.2437679767608643}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:57 - INFO - __main__ - Step 91580: {'lr': 0.00016882486852991664, 'samples': 17583360, 'steps': 91579, 'loss/train': 1.556339979171753}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:07:59 - INFO - __main__ - Step 91584: {'lr': 0.00016880479198904725, 'samples': 17584128, 'steps': 91583, 'loss/train': 1.558046579360962}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:02 - INFO - __main__ - Step 91590: {'lr': 0.00016877467827534762, 'samples': 17585280, 'steps': 91589, 'loss/train': 1.5945978164672852}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:02 - INFO - __main__ - Step 91590: {'lr': 0.00016877467827534762, 'samples': 17585280, 'steps': 91589, 'loss/train': 1.5945978164672852}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:06 - INFO - __main__ - Step 91597: {'lr': 0.00016873954727464802, 'samples': 17586624, 'steps': 91596, 'loss/train': 0.7523378133773804}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:07 - INFO - __main__ - Step 91601: {'lr': 0.00016871947322257913, 'samples': 17587392, 'steps': 91600, 'loss/train': 1.2782890796661377}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:09 - INFO - __main__ - Step 91605: {'lr': 0.00016869939975649035, 'samples': 17588160, 'steps': 91604, 'loss/train': 1.2778267860412598}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:11 - INFO - __main__ - Step 91610: {'lr': 0.0001686743087481341, 'samples': 17589120, 'steps': 91609, 'loss/train': 1.3725072145462036}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:11 - INFO - __main__ - Step 91610: {'lr': 0.0001686743087481341, 'samples': 17589120, 'steps': 91609, 'loss/train': 1.3725072145462036}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:15 - INFO - __main__ - Step 91618: {'lr': 0.0001686341650403751, 'samples': 17590656, 'steps': 91617, 'loss/train': 1.4276150465011597}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:17 - INFO - __main__ - Step 91622: {'lr': 0.00016861409406631573, 'samples': 17591424, 'steps': 91621, 'loss/train': 1.239927053451538}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:19 - INFO - __main__ - Step 91626: {'lr': 0.00016859402367899615, 'samples': 17592192, 'steps': 91625, 'loss/train': 1.6687766313552856}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:22 - INFO - __main__ - Step 91631: {'lr': 0.00016856893652016986, 'samples': 17593152, 'steps': 91630, 'loss/train': 1.3402307033538818}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:22 - INFO - __main__ - Step 91631: {'lr': 0.00016856893652016986, 'samples': 17593152, 'steps': 91630, 'loss/train': 1.3402307033538818}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:22 - INFO - __main__ - Step 91631: {'lr': 0.00016856893652016986, 'samples': 17593152, 'steps': 91630, 'loss/train': 1.3402307033538818}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:27 - INFO - __main__ - Step 91641: {'lr': 0.00016851876495466834, 'samples': 17595072, 'steps': 91640, 'loss/train': 1.3050854206085205}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:30 - INFO - __main__ - Step 91647: {'lr': 0.00016848866377750378, 'samples': 17596224, 'steps': 91646, 'loss/train': 1.6552166938781738}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:30 - INFO - __main__ - Step 91647: {'lr': 0.00016848866377750378, 'samples': 17596224, 'steps': 91646, 'loss/train': 1.6552166938781738}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:33 - INFO - __main__ - Step 91654: {'lr': 0.0001684535474086253, 'samples': 17597568, 'steps': 91653, 'loss/train': 1.3515913486480713}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:33 - INFO - __main__ - Step 91654: {'lr': 0.0001684535474086253, 'samples': 17597568, 'steps': 91653, 'loss/train': 1.3515913486480713}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:37 - INFO - __main__ - Step 91661: {'lr': 0.00016841843284018198, 'samples': 17598912, 'steps': 91660, 'loss/train': 1.7563822269439697}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:39 - INFO - __main__ - Step 91665: {'lr': 0.000168398368181157, 'samples': 17599680, 'steps': 91664, 'loss/train': 1.3540664911270142}7}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:41 - INFO - __main__ - Step 91669: {'lr': 0.00016837830411042698, 'samples': 17600448, 'steps': 91668, 'loss/train': 1.045675277709961}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:43 - INFO - __main__ - Step 91674: {'lr': 0.00016835322484952476, 'samples': 17601408, 'steps': 91673, 'loss/train': 1.4969698190689087}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:43 - INFO - __main__ - Step 91674: {'lr': 0.00016835322484952476, 'samples': 17601408, 'steps': 91673, 'loss/train': 1.4969698190689087}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:47 - INFO - __main__ - Step 91681: {'lr': 0.00016831811542945341, 'samples': 17602752, 'steps': 91680, 'loss/train': 1.3799798488616943}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:49 - INFO - __main__ - Step 91686: {'lr': 0.0001682930383763524, 'samples': 17603712, 'steps': 91685, 'loss/train': 1.4557353258132935}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:51 - INFO - __main__ - Step 91691: {'lr': 0.00016826796224364871, 'samples': 17604672, 'steps': 91690, 'loss/train': 1.7207820415496826}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:51 - INFO - __main__ - Step 91691: {'lr': 0.00016826796224364871, 'samples': 17604672, 'steps': 91690, 'loss/train': 1.7207820415496826}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:55 - INFO - __main__ - Step 91698: {'lr': 0.00016823285720466907, 'samples': 17606016, 'steps': 91697, 'loss/train': 1.1301116943359375}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:57 - INFO - __main__ - Step 91702: {'lr': 0.0001682127979928915, 'samples': 17606784, 'steps': 91701, 'loss/train': 1.2765322923660278}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:59 - INFO - __main__ - Step 91707: {'lr': 0.00016818772480735761, 'samples': 17607744, 'steps': 91706, 'loss/train': 0.7278129458427429}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:08:59 - INFO - __main__ - Step 91707: {'lr': 0.00016818772480735761, 'samples': 17607744, 'steps': 91706, 'loss/train': 0.7278129458427429}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:03 - INFO - __main__ - Step 91715: {'lr': 0.0001681476096275152, 'samples': 17609280, 'steps': 91714, 'loss/train': 1.1525863409042358}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:05 - INFO - __main__ - Step 91719: {'lr': 0.00016812755292267578, 'samples': 17610048, 'steps': 91718, 'loss/train': 1.4806389808654785}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:07 - INFO - __main__ - Step 91723: {'lr': 0.00016810749680808373, 'samples': 17610816, 'steps': 91722, 'loss/train': 1.8748496770858765}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:09 - INFO - __main__ - Step 91728: {'lr': 0.0001680824274950995, 'samples': 17611776, 'steps': 91727, 'loss/train': 1.0229536294937134}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:09 - INFO - __main__ - Step 91728: {'lr': 0.0001680824274950995, 'samples': 17611776, 'steps': 91727, 'loss/train': 1.0229536294937134}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:13 - INFO - __main__ - Step 91736: {'lr': 0.0001680423185138033, 'samples': 17613312, 'steps': 91735, 'loss/train': 1.2030911445617676}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:15 - INFO - __main__ - Step 91740: {'lr': 0.00016802226490937575, 'samples': 17614080, 'steps': 91739, 'loss/train': 1.4088549613952637}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:17 - INFO - __main__ - Step 91744: {'lr': 0.0001680022118959546, 'samples': 17614848, 'steps': 91743, 'loss/train': 1.4428614377975464}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:19 - INFO - __main__ - Step 91748: {'lr': 0.00016798215947368448, 'samples': 17615616, 'steps': 91747, 'loss/train': 1.5746937990188599}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:22 - INFO - __main__ - Step 91753: {'lr': 0.00016795709477737317, 'samples': 17616576, 'steps': 91752, 'loss/train': 1.4931063652038574}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:24 - INFO - __main__ - Step 91757: {'lr': 0.00016793704368572133, 'samples': 17617344, 'steps': 91756, 'loss/train': 1.311335563659668}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:24 - INFO - __main__ - Step 91757: {'lr': 0.00016793704368572133, 'samples': 17617344, 'steps': 91756, 'loss/train': 1.311335563659668}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:27 - INFO - __main__ - Step 91764: {'lr': 0.00016790195569900524, 'samples': 17618688, 'steps': 91763, 'loss/train': 1.5124998092651367}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:29 - INFO - __main__ - Step 91769: {'lr': 0.00016787689396106917, 'samples': 17619648, 'steps': 91768, 'loss/train': 1.5759484767913818}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:32 - INFO - __main__ - Step 91774: {'lr': 0.00016785183314821806, 'samples': 17620608, 'steps': 91773, 'loss/train': 1.2006475925445557}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:32 - INFO - __main__ - Step 91774: {'lr': 0.00016785183314821806, 'samples': 17620608, 'steps': 91773, 'loss/train': 1.2006475925445557}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:36 - INFO - __main__ - Step 91781: {'lr': 0.00016781674956490715, 'samples': 17621952, 'steps': 91780, 'loss/train': 1.330990195274353}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:37 - INFO - __main__ - Step 91785: {'lr': 0.00016779670261763652, 'samples': 17622720, 'steps': 91784, 'loss/train': 1.0430256128311157}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:39 - INFO - __main__ - Step 91789: {'lr': 0.00016777665626299855, 'samples': 17623488, 'steps': 91788, 'loss/train': 1.5172191858291626}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:42 - INFO - __main__ - Step 91794: {'lr': 0.00016775159915331087, 'samples': 17624448, 'steps': 91793, 'loss/train': 0.9706909656524658}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:44 - INFO - __main__ - Step 91798: {'lr': 0.0001677315541326246, 'samples': 17625216, 'steps': 91797, 'loss/train': 1.0457606315612793}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:46 - INFO - __main__ - Step 91802: {'lr': 0.00016771150970504062, 'samples': 17625984, 'steps': 91801, 'loss/train': 1.831748366355896}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:47 - INFO - __main__ - Step 91806: {'lr': 0.0001676914658707035, 'samples': 17626752, 'steps': 91805, 'loss/train': 1.2335140705108643}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:50 - INFO - __main__ - Step 91810: {'lr': 0.00016767142262975757, 'samples': 17627520, 'steps': 91809, 'loss/train': 1.1894193887710571}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:50 - INFO - __main__ - Step 91810: {'lr': 0.00016767142262975757, 'samples': 17627520, 'steps': 91809, 'loss/train': 1.1894193887710571}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:53 - INFO - __main__ - Step 91816: {'lr': 0.00016764135888126341, 'samples': 17628672, 'steps': 91815, 'loss/train': 1.0809221267700195}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:56 - INFO - __main__ - Step 91821: {'lr': 0.00016761630677800989, 'samples': 17629632, 'steps': 91820, 'loss/train': 1.1241768598556519}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:58 - INFO - __main__ - Step 91825: {'lr': 0.0001675962657635682, 'samples': 17630400, 'steps': 91824, 'loss/train': 1.6207095384597778}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:09:59 - INFO - __main__ - Step 91829: {'lr': 0.0001675762253432041, 'samples': 17631168, 'steps': 91828, 'loss/train': 0.36946165561676025}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:02 - INFO - __main__ - Step 91834: {'lr': 0.00016755117565339084, 'samples': 17632128, 'steps': 91833, 'loss/train': 0.9454692006111145}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:04 - INFO - __main__ - Step 91839: {'lr': 0.00016752612689233172, 'samples': 17633088, 'steps': 91838, 'loss/train': 1.3095091581344604}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:04 - INFO - __main__ - Step 91839: {'lr': 0.00016752612689233172, 'samples': 17633088, 'steps': 91838, 'loss/train': 1.3095091581344604}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:08 - INFO - __main__ - Step 91846: {'lr': 0.00016749106018769332, 'samples': 17634432, 'steps': 91845, 'loss/train': 1.2931032180786133}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:09 - INFO - __main__ - Step 91850: {'lr': 0.00016747102288860695, 'samples': 17635200, 'steps': 91849, 'loss/train': 1.596989631652832}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:11 - INFO - __main__ - Step 91854: {'lr': 0.00016745098618450117, 'samples': 17635968, 'steps': 91853, 'loss/train': 1.1730855703353882}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:14 - INFO - __main__ - Step 91859: {'lr': 0.0001674259411412804, 'samples': 17636928, 'steps': 91858, 'loss/train': 1.106895923614502}2}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:16 - INFO - __main__ - Step 91864: {'lr': 0.00016740089702822457, 'samples': 17637888, 'steps': 91863, 'loss/train': 0.8603522181510925}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:16 - INFO - __main__ - Step 91864: {'lr': 0.00016740089702822457, 'samples': 17637888, 'steps': 91863, 'loss/train': 0.8603522181510925}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:19 - INFO - __main__ - Step 91871: {'lr': 0.00016736583683316057, 'samples': 17639232, 'steps': 91870, 'loss/train': 1.3951977491378784}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:22 - INFO - __main__ - Step 91875: {'lr': 0.00016734580325507243, 'samples': 17640000, 'steps': 91874, 'loss/train': 1.3294072151184082}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:24 - INFO - __main__ - Step 91880: {'lr': 0.00016732076212044002, 'samples': 17640960, 'steps': 91879, 'loss/train': 1.3906055688858032}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:24 - INFO - __main__ - Step 91880: {'lr': 0.00016732076212044002, 'samples': 17640960, 'steps': 91879, 'loss/train': 1.3906055688858032}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:28 - INFO - __main__ - Step 91887: {'lr': 0.00016728570609668547, 'samples': 17642304, 'steps': 91886, 'loss/train': 1.4973599910736084}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:29 - INFO - __main__ - Step 91891: {'lr': 0.00016726567490299698, 'samples': 17643072, 'steps': 91890, 'loss/train': 1.5794405937194824}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:32 - INFO - __main__ - Step 91895: {'lr': 0.0001672456443057695, 'samples': 17643840, 'steps': 91894, 'loss/train': 3.9659128189086914}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:34 - INFO - __main__ - Step 91900: {'lr': 0.00016722060689822838, 'samples': 17644800, 'steps': 91899, 'loss/train': 1.402150273323059}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:34 - INFO - __main__ - Step 91900: {'lr': 0.00016722060689822838, 'samples': 17644800, 'steps': 91899, 'loss/train': 1.402150273323059}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:38 - INFO - __main__ - Step 91908: {'lr': 0.00016718054898583396, 'samples': 17646336, 'steps': 91907, 'loss/train': 1.3642683029174805}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:40 - INFO - __main__ - Step 91912: {'lr': 0.00016716052092517652, 'samples': 17647104, 'steps': 91911, 'loss/train': 0.8250459432601929}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:43 - INFO - __main__ - Step 91917: {'lr': 0.00016713548668921107, 'samples': 17648064, 'steps': 91916, 'loss/train': 1.3501816987991333}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:45 - INFO - __main__ - Step 91921: {'lr': 0.00016711545997249956, 'samples': 17648832, 'steps': 91920, 'loss/train': 1.3014812469482422}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:45 - INFO - __main__ - Step 91921: {'lr': 0.00016711545997249956, 'samples': 17648832, 'steps': 91920, 'loss/train': 1.3014812469482422}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:48 - INFO - __main__ - Step 91928: {'lr': 0.0001670804146561814, 'samples': 17650176, 'steps': 91927, 'loss/train': 1.3467894792556763}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:50 - INFO - __main__ - Step 91933: {'lr': 0.0001670553834082061, 'samples': 17651136, 'steps': 91932, 'loss/train': 1.3530820608139038}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:50 - INFO - __main__ - Step 91933: {'lr': 0.0001670553834082061, 'samples': 17651136, 'steps': 91932, 'loss/train': 1.3530820608139038}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:54 - INFO - __main__ - Step 91941: {'lr': 0.00016701533535498837, 'samples': 17652672, 'steps': 91940, 'loss/train': 0.8258083462715149}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:56 - INFO - __main__ - Step 91945: {'lr': 0.0001669953122257059, 'samples': 17653440, 'steps': 91944, 'loss/train': 1.3164931535720825}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:10:58 - INFO - __main__ - Step 91949: {'lr': 0.00016697528969483353, 'samples': 17654208, 'steps': 91948, 'loss/train': 0.9148712158203125}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:00 - INFO - __main__ - Step 91953: {'lr': 0.0001669552677625156, 'samples': 17654976, 'steps': 91952, 'loss/train': 1.092864751815796}5}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:02 - INFO - __main__ - Step 91958: {'lr': 0.0001669302411890554, 'samples': 17655936, 'steps': 91957, 'loss/train': 0.8648205399513245}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:02 - INFO - __main__ - Step 91958: {'lr': 0.0001669302411890554, 'samples': 17655936, 'steps': 91957, 'loss/train': 0.8648205399513245}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:06 - INFO - __main__ - Step 91965: {'lr': 0.0001668952055583321, 'samples': 17657280, 'steps': 91964, 'loss/train': 1.672492504119873}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:06 - INFO - __main__ - Step 91965: {'lr': 0.0001668952055583321, 'samples': 17657280, 'steps': 91964, 'loss/train': 1.672492504119873}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:06 - INFO - __main__ - Step 91965: {'lr': 0.0001668952055583321, 'samples': 17657280, 'steps': 91964, 'loss/train': 1.672492504119873}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:11 - INFO - __main__ - Step 91976: {'lr': 0.0001668401532746213, 'samples': 17659392, 'steps': 91975, 'loss/train': 0.8518202304840088}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:13 - INFO - __main__ - Step 91980: {'lr': 0.00016682013538632125, 'samples': 17660160, 'steps': 91979, 'loss/train': 1.4060888290405273}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:16 - INFO - __main__ - Step 91985: {'lr': 0.00016679511386925337, 'samples': 17661120, 'steps': 91984, 'loss/train': 1.2891408205032349}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:18 - INFO - __main__ - Step 91990: {'lr': 0.00016677009328945632, 'samples': 17662080, 'steps': 91989, 'loss/train': 1.5705349445343018}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:18 - INFO - __main__ - Step 91990: {'lr': 0.00016677009328945632, 'samples': 17662080, 'steps': 91989, 'loss/train': 1.5705349445343018}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:22 - INFO - __main__ - Step 91997: {'lr': 0.0001667350660528924, 'samples': 17663424, 'steps': 91996, 'loss/train': 1.571846842765808}8}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:23 - INFO - __main__ - Step 92001: {'lr': 0.0001667150513144856, 'samples': 17664192, 'steps': 92000, 'loss/train': 1.5566900968551636}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:26 - INFO - __main__ - Step 92006: {'lr': 0.0001666900337358496, 'samples': 17665152, 'steps': 92005, 'loss/train': 1.349738597869873}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:28 - INFO - __main__ - Step 92011: {'lr': 0.00016666501709566823, 'samples': 17666112, 'steps': 92010, 'loss/train': 1.698442816734314}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:30 - INFO - __main__ - Step 92015: {'lr': 0.0001666450044593998, 'samples': 17666880, 'steps': 92014, 'loss/train': 1.1924840211868286}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:30 - INFO - __main__ - Step 92015: {'lr': 0.0001666450044593998, 'samples': 17666880, 'steps': 92014, 'loss/train': 1.1924840211868286}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:34 - INFO - __main__ - Step 92022: {'lr': 0.0001666099837920182, 'samples': 17668224, 'steps': 92021, 'loss/train': 1.4902268648147583}}}███████████���███████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:36 - INFO - __main__ - Step 92026: {'lr': 0.00016658997280866988, 'samples': 17668992, 'steps': 92025, 'loss/train': 1.3709720373153687}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:38 - INFO - __main__ - Step 92032: {'lr': 0.0001665599574611905, 'samples': 17670144, 'steps': 92031, 'loss/train': 1.273848295211792}7}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:40 - INFO - __main__ - Step 92036: {'lr': 0.0001665399479814435, 'samples': 17670912, 'steps': 92035, 'loss/train': 1.5508043766021729}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:42 - INFO - __main__ - Step 92040: {'lr': 0.00016651993910338946, 'samples': 17671680, 'steps': 92039, 'loss/train': 1.4355967044830322}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:42 - INFO - __main__ - Step 92040: {'lr': 0.00016651993910338946, 'samples': 17671680, 'steps': 92039, 'loss/train': 1.4355967044830322}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:46 - INFO - __main__ - Step 92047: {'lr': 0.00016648492501505246, 'samples': 17673024, 'steps': 92046, 'loss/train': 0.9938133358955383}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:48 - INFO - __main__ - Step 92052: {'lr': 0.00016645991608082777, 'samples': 17673984, 'steps': 92051, 'loss/train': 0.8232744336128235}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:51 - INFO - __main__ - Step 92056: {'lr': 0.0001664399096109881, 'samples': 17674752, 'steps': 92055, 'loss/train': 1.3846968412399292}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:51 - INFO - __main__ - Step 92056: {'lr': 0.0001664399096109881, 'samples': 17674752, 'steps': 92055, 'loss/train': 1.3846968412399292}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:54 - INFO - __main__ - Step 92063: {'lr': 0.00016640489973841473, 'samples': 17676096, 'steps': 92062, 'loss/train': 1.5169618129730225}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:56 - INFO - __main__ - Step 92068: {'lr': 0.00016637989381653131, 'samples': 17677056, 'steps': 92067, 'loss/train': 1.0359196662902832}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:11:59 - INFO - __main__ - Step 92073: {'lr': 0.00016635488883659616, 'samples': 17678016, 'steps': 92072, 'loss/train': 1.4253791570663452}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:01 - INFO - __main__ - Step 92077: {'lr': 0.00016633488553104015, 'samples': 17678784, 'steps': 92076, 'loss/train': 0.9690409898757935}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:03 - INFO - __main__ - Step 92081: {'lr': 0.00016631488282865537, 'samples': 17679552, 'steps': 92080, 'loss/train': 1.4903638362884521}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:04 - INFO - __main__ - Step 92085: {'lr': 0.00016629488072958615, 'samples': 17680320, 'steps': 92084, 'loss/train': 1.4634177684783936}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:06 - INFO - __main__ - Step 92089: {'lr': 0.0001662748792339768, 'samples': 17681088, 'steps': 92088, 'loss/train': 1.5804036855697632}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:08 - INFO - __main__ - Step 92094: {'lr': 0.00016624987821329995, 'samples': 17682048, 'steps': 92093, 'loss/train': 1.4919517040252686}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:11 - INFO - __main__ - Step 92098: {'lr': 0.00016622987807600218, 'samples': 17682816, 'steps': 92097, 'loss/train': 1.2044155597686768}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:11 - INFO - __main__ - Step 92098: {'lr': 0.00016622987807600218, 'samples': 17682816, 'steps': 92097, 'loss/train': 1.2044155597686768}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:14 - INFO - __main__ - Step 92105: {'lr': 0.0001661948792890206, 'samples': 17684160, 'steps': 92104, 'loss/train': 1.4645920991897583}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:16 - INFO - __main__ - Step 92110: {'lr': 0.00016616988128825602, 'samples': 17685120, 'steps': 92109, 'loss/train': 1.5246654748916626}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:16 - INFO - __main__ - Step 92110: {'lr': 0.00016616988128825602, 'samples': 17685120, 'steps': 92109, 'loss/train': 1.5246654748916626}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:21 - INFO - __main__ - Step 92118: {'lr': 0.00016612988645132296, 'samples': 17686656, 'steps': 92117, 'loss/train': 1.395470142364502}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:22 - INFO - __main__ - Step 92122: {'lr': 0.00016610988993975818, 'samples': 17687424, 'steps': 92121, 'loss/train': 0.9783124327659607}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:24 - INFO - __main__ - Step 92126: {'lr': 0.00016608989403298684, 'samples': 17688192, 'steps': 92125, 'loss/train': 1.7592384815216064}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:27 - INFO - __main__ - Step 92131: {'lr': 0.0001660649000002331, 'samples': 17689152, 'steps': 92130, 'loss/train': 1.5535978078842163}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:27 - INFO - __main__ - Step 92131: {'lr': 0.0001660649000002331, 'samples': 17689152, 'steps': 92130, 'loss/train': 1.5535978078842163}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:30 - INFO - __main__ - Step 92138: {'lr': 0.00016602990994287497, 'samples': 17690496, 'steps': 92137, 'loss/train': 5.291414260864258}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:32 - INFO - __main__ - Step 92142: {'lr': 0.00016600991645671897, 'samples': 17691264, 'steps': 92141, 'loss/train': 1.6944715976715088}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:35 - INFO - __main__ - Step 92147: {'lr': 0.00016598492545054502, 'samples': 17692224, 'steps': 92146, 'loss/train': 1.2443050146102905}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:35 - INFO - __main__ - Step 92147: {'lr': 0.00016598492545054502, 'samples': 17692224, 'steps': 92146, 'loss/train': 1.2443050146102905}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:38 - INFO - __main__ - Step 92154: {'lr': 0.00016594993963191224, 'samples': 17693568, 'steps': 92153, 'loss/train': 1.6073150634765625}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:40 - INFO - __main__ - Step 92159: {'lr': 0.00016592495089756505, 'samples': 17694528, 'steps': 92158, 'loss/train': 1.434714436531067}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:43 - INFO - __main__ - Step 92164: {'lr': 0.00016589996311029082, 'samples': 17695488, 'steps': 92163, 'loss/train': 1.317513108253479}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:43 - INFO - __main__ - Step 92164: {'lr': 0.00016589996311029082, 'samples': 17695488, 'steps': 92163, 'loss/train': 1.317513108253479}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:47 - INFO - __main__ - Step 92171: {'lr': 0.00016586498179972545, 'samples': 17696832, 'steps': 92170, 'loss/train': 2.5771007537841797}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:48 - INFO - __main__ - Step 92175: {'lr': 0.00016584499331337156, 'samples': 17697600, 'steps': 92174, 'loss/train': 5.75645112991333}7}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:50 - INFO - __main__ - Step 92180: {'lr': 0.00016582000855862232, 'samples': 17698560, 'steps': 92179, 'loss/train': 1.5356673002243042}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:53 - INFO - __main__ - Step 92185: {'lr': 0.00016579502475212837, 'samples': 17699520, 'steps': 92184, 'loss/train': 0.6823630928993225}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:53 - INFO - __main__ - Step 92185: {'lr': 0.00016579502475212837, 'samples': 17699520, 'steps': 92184, 'loss/train': 0.6823630928993225}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:56 - INFO - __main__ - Step 92192: {'lr': 0.0001657600490166411, 'samples': 17700864, 'steps': 92191, 'loss/train': 1.5925285816192627}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:12:58 - INFO - __main__ - Step 92196: {'lr': 0.00016574006371708645, 'samples': 17701632, 'steps': 92195, 'loss/train': 1.3165194988250732}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:01 - INFO - __main__ - Step 92201: {'lr': 0.0001657150829468999, 'samples': 17702592, 'steps': 92200, 'loss/train': 1.5646997690200806}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:03 - INFO - __main__ - Step 92206: {'lr': 0.00016569010312615052, 'samples': 17703552, 'steps': 92205, 'loss/train': 1.5537039041519165}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:03 - INFO - __main__ - Step 92206: {'lr': 0.00016569010312615052, 'samples': 17703552, 'steps': 92205, 'loss/train': 1.5537039041519165}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:07 - INFO - __main__ - Step 92213: {'lr': 0.00016565513297269146, 'samples': 17704896, 'steps': 92212, 'loss/train': 1.694804072380066}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:08 - INFO - __main__ - Step 92217: {'lr': 0.00016563515086390706, 'samples': 17705664, 'steps': 92216, 'loss/train': 1.3093591928482056}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:11 - INFO - __main__ - Step 92222: {'lr': 0.00016561017408324712, 'samples': 17706624, 'steps': 92221, 'loss/train': 1.4464941024780273}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:11 - INFO - __main__ - Step 92222: {'lr': 0.00016561017408324712, 'samples': 17706624, 'steps': 92221, 'loss/train': 1.4464941024780273}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:15 - INFO - __main__ - Step 92229: {'lr': 0.00016557520818742607, 'samples': 17707968, 'steps': 92228, 'loss/train': 1.3165888786315918}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:16 - INFO - __main__ - Step 92233: {'lr': 0.00016555522851236987, 'samples': 17708736, 'steps': 92232, 'loss/train': 0.9745898842811584}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:19 - INFO - __main__ - Step 92238: {'lr': 0.00016553025477468065, 'samples': 17709696, 'steps': 92237, 'loss/train': 1.284397840499878}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:21 - INFO - __main__ - Step 92242: {'lr': 0.00016551027646960942, 'samples': 17710464, 'steps': 92241, 'loss/train': 1.807320475578308}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:23 - INFO - __main__ - Step 92247: {'lr': 0.00016548530444485698, 'samples': 17711424, 'steps': 92246, 'loss/train': 1.3025211095809937}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:23 - INFO - __main__ - Step 92247: {'lr': 0.00016548530444485698, 'samples': 17711424, 'steps': 92246, 'loss/train': 1.3025211095809937}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:26 - INFO - __main__ - Step 92253: {'lr': 0.00016545533927185254, 'samples': 17712576, 'steps': 92252, 'loss/train': 0.8677536845207214}}████████████████��██████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:29 - INFO - __main__ - Step 92258: {'lr': 0.0001654303693419274, 'samples': 17713536, 'steps': 92257, 'loss/train': 1.6066726446151733}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:29 - INFO - __main__ - Step 92258: {'lr': 0.0001654303693419274, 'samples': 17713536, 'steps': 92257, 'loss/train': 1.6066726446151733}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:33 - INFO - __main__ - Step 92266: {'lr': 0.00016539041943566433, 'samples': 17715072, 'steps': 92265, 'loss/train': 2.090813398361206}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:35 - INFO - __main__ - Step 92270: {'lr': 0.00016537044539743126, 'samples': 17715840, 'steps': 92269, 'loss/train': 0.786201000213623}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:36 - INFO - __main__ - Step 92274: {'lr': 0.00016535047196932257, 'samples': 17716608, 'steps': 92273, 'loss/train': 1.5324323177337646}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:38 - INFO - __main__ - Step 92278: {'lr': 0.00016533049915148224, 'samples': 17717376, 'steps': 92277, 'loss/train': 0.14162449538707733}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:41 - INFO - __main__ - Step 92283: {'lr': 0.00016530553398759097, 'samples': 17718336, 'steps': 92282, 'loss/train': 1.2269879579544067}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:43 - INFO - __main__ - Step 92287: {'lr': 0.00016528556254338084, 'samples': 17719104, 'steps': 92286, 'loss/train': 1.1515402793884277}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:44 - INFO - __main__ - Step 92291: {'lr': 0.000165265591709907, 'samples': 17719872, 'steps': 92290, 'loss/train': 1.240840196609497}77}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:47 - INFO - __main__ - Step 92295: {'lr': 0.00016524562148731347, 'samples': 17720640, 'steps': 92294, 'loss/train': 0.9684673547744751}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:49 - INFO - __main__ - Step 92300: {'lr': 0.00016522065956834115, 'samples': 17721600, 'steps': 92299, 'loss/train': 1.4314666986465454}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:49 - INFO - __main__ - Step 92300: {'lr': 0.00016522065956834115, 'samples': 17721600, 'steps': 92299, 'loss/train': 1.4314666986465454}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:53 - INFO - __main__ - Step 92307: {'lr': 0.00016518571448625405, 'samples': 17722944, 'steps': 92306, 'loss/train': 1.4102747440338135}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:54 - INFO - __main__ - Step 92311: {'lr': 0.0001651657467086212, 'samples': 17723712, 'steps': 92310, 'loss/train': 1.128462314605713}5}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:56 - INFO - __main__ - Step 92315: {'lr': 0.00016514577954258842, 'samples': 17724480, 'steps': 92314, 'loss/train': 0.5786054730415344}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:13:59 - INFO - __main__ - Step 92320: {'lr': 0.0001651208214453295, 'samples': 17725440, 'steps': 92319, 'loss/train': 1.1547166109085083}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:01 - INFO - __main__ - Step 92324: {'lr': 0.00016510085565592326, 'samples': 17726208, 'steps': 92323, 'loss/train': 1.2895710468292236}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:03 - INFO - __main__ - Step 92328: {'lr': 0.00016508089047858487, 'samples': 17726976, 'steps': 92327, 'loss/train': 1.4571216106414795}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:04 - INFO - __main__ - Step 92332: {'lr': 0.0001650609259134585, 'samples': 17727744, 'steps': 92331, 'loss/train': 1.1811835765838623}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:07 - INFO - __main__ - Step 92336: {'lr': 0.00016504096196068776, 'samples': 17728512, 'steps': 92335, 'loss/train': 1.0330393314361572}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:09 - INFO - __main__ - Step 92341: {'lr': 0.00016501600788106893, 'samples': 17729472, 'steps': 92340, 'loss/train': 1.102745771408081}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:11 - INFO - __main__ - Step 92346: {'lr': 0.00016499105475876208, 'samples': 17730432, 'steps': 92345, 'loss/train': 1.4632225036621094}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:13 - INFO - __main__ - Step 92350: {'lr': 0.00016497109295037, 'samples': 17731200, 'steps': 92349, 'loss/train': 1.4324556589126587}94}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:13 - INFO - __main__ - Step 92350: {'lr': 0.00016497109295037, 'samples': 17731200, 'steps': 92349, 'loss/train': 1.4324556589126587}94}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:17 - INFO - __main__ - Step 92357: {'lr': 0.00016493616126080993, 'samples': 17732544, 'steps': 92356, 'loss/train': 1.2445465326309204}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:19 - INFO - __main__ - Step 92361: {'lr': 0.00016491620113852348, 'samples': 17733312, 'steps': 92360, 'loss/train': 1.6520750522613525}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:21 - INFO - __main__ - Step 92367: {'lr': 0.00016488626210526218, 'samples': 17734464, 'steps': 92366, 'loss/train': 1.815798282623291}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:21 - INFO - __main__ - Step 92367: {'lr': 0.00016488626210526218, 'samples': 17734464, 'steps': 92366, 'loss/train': 1.815798282623291}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:24 - INFO - __main__ - Step 92373: {'lr': 0.00016485632445263472, 'samples': 17735616, 'steps': 92372, 'loss/train': 1.3192720413208008}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:26 - INFO - __main__ - Step 92377: {'lr': 0.00016483636678480825, 'samples': 17736384, 'steps': 92376, 'loss/train': 1.3578836917877197}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:29 - INFO - __main__ - Step 92382: {'lr': 0.00016481142056344388, 'samples': 17737344, 'steps': 92381, 'loss/train': 1.0124398469924927}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:29 - INFO - __main__ - Step 92382: {'lr': 0.00016481142056344388, 'samples': 17737344, 'steps': 92381, 'loss/train': 1.0124398469924927}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:33 - INFO - __main__ - Step 92390: {'lr': 0.00016477150860538025, 'samples': 17738880, 'steps': 92389, 'loss/train': 1.434588074684143}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:35 - INFO - __main__ - Step 92394: {'lr': 0.0001647515535479399, 'samples': 17739648, 'steps': 92393, 'loss/train': 1.9479113817214966}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:37 - INFO - __main__ - Step 92398: {'lr': 0.0001647315991050858, 'samples': 17740416, 'steps': 92397, 'loss/train': 1.1401844024658203}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:39 - INFO - __main__ - Step 92403: {'lr': 0.00016470665691599892, 'samples': 17741376, 'steps': 92402, 'loss/train': 1.0853384733200073}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:41 - INFO - __main__ - Step 92407: {'lr': 0.00016468670385648952, 'samples': 17742144, 'steps': 92406, 'loss/train': 1.6330853700637817}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:43 - INFO - __main__ - Step 92411: {'lr': 0.0001646667514120339, 'samples': 17742912, 'steps': 92410, 'loss/train': 1.3342344760894775}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:45 - INFO - __main__ - Step 92415: {'lr': 0.00016464679958277568, 'samples': 17743680, 'steps': 92414, 'loss/train': 1.1678916215896606}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:47 - INFO - __main__ - Step 92419: {'lr': 0.00016462684836885888, 'samples': 17744448, 'steps': 92418, 'loss/train': 1.7548986673355103}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:49 - INFO - __main__ - Step 92424: {'lr': 0.00016460191021700578, 'samples': 17745408, 'steps': 92423, 'loss/train': 1.3012244701385498}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:49 - INFO - __main__ - Step 92424: {'lr': 0.00016460191021700578, 'samples': 17745408, 'steps': 92423, 'loss/train': 1.3012244701385498}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:53 - INFO - __main__ - Step 92432: {'lr': 0.00016456201117506886, 'samples': 17746944, 'steps': 92431, 'loss/train': 1.0234566926956177}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:55 - INFO - __main__ - Step 92436: {'lr': 0.0001645420625779574, 'samples': 17747712, 'steps': 92435, 'loss/train': 1.1681838035583496}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:57 - INFO - __main__ - Step 92440: {'lr': 0.00016452211459694243, 'samples': 17748480, 'steps': 92439, 'loss/train': 1.610959529876709}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:14:59 - INFO - __main__ - Step 92444: {'lr': 0.00016450216723216775, 'samples': 17749248, 'steps': 92443, 'loss/train': 1.1765373945236206}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:01 - INFO - __main__ - Step 92449: {'lr': 0.00016447723389300623, 'samples': 17750208, 'steps': 92448, 'loss/train': 1.2738795280456543}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:01 - INFO - __main__ - Step 92449: {'lr': 0.00016447723389300623, 'samples': 17750208, 'steps': 92448, 'loss/train': 1.2738795280456543}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:05 - INFO - __main__ - Step 92456: {'lr': 0.00016444232883672317, 'samples': 17751552, 'steps': 92455, 'loss/train': 2.340329885482788}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:07 - INFO - __main__ - Step 92460: {'lr': 0.00016442238393834746, 'samples': 17752320, 'steps': 92459, 'loss/train': 1.5078010559082031}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:07 - INFO - __main__ - Step 92460: {'lr': 0.00016442238393834746, 'samples': 17752320, 'steps': 92459, 'loss/train': 1.5078010559082031}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:07 - INFO - __main__ - Step 92460: {'lr': 0.00016442238393834746, 'samples': 17752320, 'steps': 92459, 'loss/train': 1.5078010559082031}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:13 - INFO - __main__ - Step 92471: {'lr': 0.00016436753864944304, 'samples': 17754432, 'steps': 92470, 'loss/train': 2.047581195831299}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:15 - INFO - __main__ - Step 92476: {'lr': 0.00016434261051587518, 'samples': 17755392, 'steps': 92475, 'loss/train': 0.8350712060928345}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:15 - INFO - __main__ - Step 92476: {'lr': 0.00016434261051587518, 'samples': 17755392, 'steps': 92475, 'loss/train': 0.8350712060928345}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:19 - INFO - __main__ - Step 92484: {'lr': 0.00016430272750927018, 'samples': 17756928, 'steps': 92483, 'loss/train': 1.289831519126892}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:21 - INFO - __main__ - Step 92488: {'lr': 0.00016428278693262857, 'samples': 17757696, 'steps': 92487, 'loss/train': 1.4472410678863525}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:23 - INFO - __main__ - Step 92492: {'lr': 0.00016426284697395276, 'samples': 17758464, 'steps': 92491, 'loss/train': 1.410550832748413}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:25 - INFO - __main__ - Step 92497: {'lr': 0.00016423792289484103, 'samples': 17759424, 'steps': 92496, 'loss/train': 1.4293814897537231}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:28 - INFO - __main__ - Step 92502: {'lr': 0.00016421299978180604, 'samples': 17760384, 'steps': 92501, 'loss/train': 1.8240631818771362}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:28 - INFO - __main__ - Step 92502: {'lr': 0.00016421299978180604, 'samples': 17760384, 'steps': 92501, 'loss/train': 1.8240631818771362}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:31 - INFO - __main__ - Step 92509: {'lr': 0.00016417810904710057, 'samples': 17761728, 'steps': 92508, 'loss/train': 1.7958470582962036}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:33 - INFO - __main__ - Step 92513: {'lr': 0.00016415817233510267, 'samples': 17762496, 'steps': 92512, 'loss/train': 1.156864881515503}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:35 - INFO - __main__ - Step 92518: {'lr': 0.00016413325231539984, 'samples': 17763456, 'steps': 92517, 'loss/train': 1.0999387502670288}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:38 - INFO - __main__ - Step 92523: {'lr': 0.00016410833326295268, 'samples': 17764416, 'steps': 92522, 'loss/train': 1.495737075805664}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:38 - INFO - __main__ - Step 92523: {'lr': 0.00016410833326295268, 'samples': 17764416, 'steps': 92522, 'loss/train': 1.495737075805664}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:42 - INFO - __main__ - Step 92530: {'lr': 0.00016407344821505086, 'samples': 17765760, 'steps': 92529, 'loss/train': 1.7753881216049194}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:43 - INFO - __main__ - Step 92534: {'lr': 0.0001640535147536927, 'samples': 17766528, 'steps': 92533, 'loss/train': 1.2079702615737915}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:43 - INFO - __main__ - Step 92534: {'lr': 0.0001640535147536927, 'samples': 17766528, 'steps': 92533, 'loss/train': 1.2079702615737915}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:47 - INFO - __main__ - Step 92542: {'lr': 0.00016401364968997566, 'samples': 17768064, 'steps': 92541, 'loss/train': 1.6076635122299194}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:49 - INFO - __main__ - Step 92546: {'lr': 0.00016399371808790424, 'samples': 17768832, 'steps': 92545, 'loss/train': 1.0021189451217651}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:51 - INFO - __main__ - Step 92550: {'lr': 0.00016397378710588246, 'samples': 17769600, 'steps': 92549, 'loss/train': 0.5009363293647766}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:53 - INFO - __main__ - Step 92554: {'lr': 0.00016395385674405406, 'samples': 17770368, 'steps': 92553, 'loss/train': 1.0471147298812866}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:56 - INFO - __main__ - Step 92559: {'lr': 0.00016392894466413433, 'samples': 17771328, 'steps': 92558, 'loss/train': 1.360984444618225}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:58 - INFO - __main__ - Step 92563: {'lr': 0.0001639090156982662, 'samples': 17772096, 'steps': 92562, 'loss/train': 1.778415322303772}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:15:58 - INFO - __main__ - Step 92563: {'lr': 0.0001639090156982662, 'samples': 17772096, 'steps': 92562, 'loss/train': 1.778415322303772}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:01 - INFO - __main__ - Step 92570: {'lr': 0.0001638741415015474, 'samples': 17773440, 'steps': 92569, 'loss/train': 1.150863766670227}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:01 - INFO - __main__ - Step 92570: {'lr': 0.0001638741415015474, 'samples': 17773440, 'steps': 92569, 'loss/train': 1.150863766670227}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:05 - INFO - __main__ - Step 92578: {'lr': 0.00016383428760518982, 'samples': 17774976, 'steps': 92577, 'loss/train': 1.3351610898971558}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:07 - INFO - __main__ - Step 92582: {'lr': 0.00016381436158873769, 'samples': 17775744, 'steps': 92581, 'loss/train': 1.3899332284927368}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:10 - INFO - __main__ - Step 92588: {'lr': 0.00016378447372912205, 'samples': 17776896, 'steps': 92587, 'loss/train': 1.628021478652954}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:10 - INFO - __main__ - Step 92588: {'lr': 0.00016378447372912205, 'samples': 17776896, 'steps': 92587, 'loss/train': 1.628021478652954}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:14 - INFO - __main__ - Step 92595: {'lr': 0.00016374960632716047, 'samples': 17778240, 'steps': 92594, 'loss/train': 1.3985692262649536}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:15 - INFO - __main__ - Step 92599: {'lr': 0.00016372968295240697, 'samples': 17779008, 'steps': 92598, 'loss/train': 1.2833517789840698}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:17 - INFO - __main__ - Step 92604: {'lr': 0.0001637047796086035, 'samples': 17779968, 'steps': 92603, 'loss/train': 1.2612721920013428}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:17 - INFO - __main__ - Step 92604: {'lr': 0.0001637047796086035, 'samples': 17779968, 'steps': 92603, 'loss/train': 1.2612721920013428}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:22 - INFO - __main__ - Step 92612: {'lr': 0.0001636649362805659, 'samples': 17781504, 'steps': 92611, 'loss/train': 1.362117052078247}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:24 - INFO - __main__ - Step 92616: {'lr': 0.00016364501555010536, 'samples': 17782272, 'steps': 92615, 'loss/train': 1.2940796613693237}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:25 - INFO - __main__ - Step 92620: {'lr': 0.00016362509544220826, 'samples': 17783040, 'steps': 92619, 'loss/train': 1.0445475578308105}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:27 - INFO - __main__ - Step 92624: {'lr': 0.00016360517595701837, 'samples': 17783808, 'steps': 92623, 'loss/train': 1.2904982566833496}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:30 - INFO - __main__ - Step 92629: {'lr': 0.00016358027747643186, 'samples': 17784768, 'steps': 92628, 'loss/train': 1.5591871738433838}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:30 - INFO - __main__ - Step 92629: {'lr': 0.00016358027747643186, 'samples': 17784768, 'steps': 92628, 'loss/train': 1.5591871738433838}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:33 - INFO - __main__ - Step 92636: {'lr': 0.00016354542123912796, 'samples': 17786112, 'steps': 92635, 'loss/train': 1.1945165395736694}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:35 - INFO - __main__ - Step 92640: {'lr': 0.0001635255042462029, 'samples': 17786880, 'steps': 92639, 'loss/train': 1.8257728815078735}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:37 - INFO - __main__ - Step 92645: {'lr': 0.000163500608881755, 'samples': 17787840, 'steps': 92644, 'loss/train': 0.9351515173912048}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:37 - INFO - __main__ - Step 92645: {'lr': 0.000163500608881755, 'samples': 17787840, 'steps': 92644, 'loss/train': 0.9351515173912048}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:42 - INFO - __main__ - Step 92653: {'lr': 0.00016346077832547017, 'samples': 17789376, 'steps': 92652, 'loss/train': 0.7921027541160583}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:43 - INFO - __main__ - Step 92657: {'lr': 0.0001634408639830936, 'samples': 17790144, 'steps': 92656, 'loss/train': 1.3610957860946655}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:45 - INFO - __main__ - Step 92661: {'lr': 0.00016342095026475244, 'samples': 17790912, 'steps': 92660, 'loss/train': 0.6654432415962219}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:47 - INFO - __main__ - Step 92666: {'lr': 0.00016339605899459456, 'samples': 17791872, 'steps': 92665, 'loss/train': 0.9279698729515076}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:47 - INFO - __main__ - Step 92666: {'lr': 0.00016339605899459456, 'samples': 17791872, 'steps': 92665, 'loss/train': 0.9279698729515076}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:47 - INFO - __main__ - Step 92666: {'lr': 0.00016339605899459456, 'samples': 17791872, 'steps': 92665, 'loss/train': 0.9279698729515076}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:53 - INFO - __main__ - Step 92677: {'lr': 0.00016334130163461294, 'samples': 17793984, 'steps': 92676, 'loss/train': 1.7580686807632446}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:55 - INFO - __main__ - Step 92681: {'lr': 0.0001633213910386021, 'samples': 17794752, 'steps': 92680, 'loss/train': 1.2093024253845215}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:58 - INFO - __main__ - Step 92687: {'lr': 0.00016329152631631196, 'samples': 17795904, 'steps': 92686, 'loss/train': 1.2023320198059082}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:16:58 - INFO - __main__ - Step 92687: {'lr': 0.00016329152631631196, 'samples': 17795904, 'steps': 92686, 'loss/train': 1.2023320198059082}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:01 - INFO - __main__ - Step 92694: {'lr': 0.00016325668591800308, 'samples': 17797248, 'steps': 92693, 'loss/train': 1.0019067525863647}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:03 - INFO - __main__ - Step 92698: {'lr': 0.00016323677797879448, 'samples': 17798016, 'steps': 92697, 'loss/train': 1.2870374917984009}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:03 - INFO - __main__ - Step 92698: {'lr': 0.00016323677797879448, 'samples': 17798016, 'steps': 92697, 'loss/train': 1.2870374917984009}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:08 - INFO - __main__ - Step 92706: {'lr': 0.00016319696397704082, 'samples': 17799552, 'steps': 92705, 'loss/train': 1.6974927186965942}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:10 - INFO - __main__ - Step 92710: {'lr': 0.00016317705791478294, 'samples': 17800320, 'steps': 92709, 'loss/train': 1.5754075050354004}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:11 - INFO - __main__ - Step 92714: {'lr': 0.00016315715247846219, 'samples': 17801088, 'steps': 92713, 'loss/train': 1.4957975149154663}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:13 - INFO - __main__ - Step 92718: {'lr': 0.00016313724766822221, 'samples': 17801856, 'steps': 92717, 'loss/train': 1.6485741138458252}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:16 - INFO - __main__ - Step 92723: {'lr': 0.00016311236753606702, 'samples': 17802816, 'steps': 92722, 'loss/train': 1.190447449684143}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:18 - INFO - __main__ - Step 92727: {'lr': 0.0001630924641350334, 'samples': 17803584, 'steps': 92726, 'loss/train': 1.210171103477478}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:20 - INFO - __main__ - Step 92731: {'lr': 0.0001630725613605469, 'samples': 17804352, 'steps': 92730, 'loss/train': 1.5126031637191772}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:21 - INFO - __main__ - Step 92735: {'lr': 0.00016305265921275107, 'samples': 17805120, 'steps': 92734, 'loss/train': 1.1682028770446777}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:21 - INFO - __main__ - Step 92735: {'lr': 0.00016305265921275107, 'samples': 17805120, 'steps': 92734, 'loss/train': 1.1682028770446777}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:25 - INFO - __main__ - Step 92740: {'lr': 0.00016302778240950843, 'samples': 17806080, 'steps': 92739, 'loss/train': 1.7493408918380737}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:28 - INFO - __main__ - Step 92746: {'lr': 0.0001629979315388571, 'samples': 17807232, 'steps': 92745, 'loss/train': 1.8687664270401}737}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:28 - INFO - __main__ - Step 92746: {'lr': 0.0001629979315388571, 'samples': 17807232, 'steps': 92745, 'loss/train': 1.8687664270401}737}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:31 - INFO - __main__ - Step 92753: {'lr': 0.00016296310730681273, 'samples': 17808576, 'steps': 92752, 'loss/train': 1.196974754333496}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:33 - INFO - __main__ - Step 92757: {'lr': 0.00016294320860837976, 'samples': 17809344, 'steps': 92756, 'loss/train': 2.031006097793579}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:36 - INFO - __main__ - Step 92762: {'lr': 0.00016291833611795046, 'samples': 17810304, 'steps': 92761, 'loss/train': 1.4197282791137695}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:36 - INFO - __main__ - Step 92762: {'lr': 0.00016291833611795046, 'samples': 17810304, 'steps': 92761, 'loss/train': 1.4197282791137695}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:40 - INFO - __main__ - Step 92770: {'lr': 0.000162878542173738, 'samples': 17811840, 'steps': 92769, 'loss/train': 1.620589256286621}95}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:41 - INFO - __main__ - Step 92774: {'lr': 0.00016285864614369418, 'samples': 17812608, 'steps': 92773, 'loss/train': 1.6992754936218262}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:44 - INFO - __main__ - Step 92779: {'lr': 0.00016283377698960843, 'samples': 17813568, 'steps': 92778, 'loss/train': 1.064462423324585}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:46 - INFO - __main__ - Step 92783: {'lr': 0.00016281388237328998, 'samples': 17814336, 'steps': 92782, 'loss/train': 1.605318546295166}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:48 - INFO - __main__ - Step 92788: {'lr': 0.00016278901498681503, 'samples': 17815296, 'steps': 92787, 'loss/train': 1.213597297668457}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:48 - INFO - __main__ - Step 92788: {'lr': 0.00016278901498681503, 'samples': 17815296, 'steps': 92787, 'loss/train': 1.213597297668457}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:52 - INFO - __main__ - Step 92794: {'lr': 0.0001627591754198351, 'samples': 17816448, 'steps': 92793, 'loss/train': 1.339980125427246}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:54 - INFO - __main__ - Step 92799: {'lr': 0.00016273431019500558, 'samples': 17817408, 'steps': 92798, 'loss/train': 1.946974754333496}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:54 - INFO - __main__ - Step 92799: {'lr': 0.00016273431019500558, 'samples': 17817408, 'steps': 92798, 'loss/train': 1.946974754333496}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:17:58 - INFO - __main__ - Step 92806: {'lr': 0.00016269950053177118, 'samples': 17818752, 'steps': 92805, 'loss/train': 1.328283429145813}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:00 - INFO - __main__ - Step 92810: {'lr': 0.00016267961016098559, 'samples': 17819520, 'steps': 92809, 'loss/train': 0.9924872517585754}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:02 - INFO - __main__ - Step 92814: {'lr': 0.0001626597204197236, 'samples': 17820288, 'steps': 92813, 'loss/train': 1.486737608909607}4}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:02 - INFO - __main__ - Step 92814: {'lr': 0.0001626597204197236, 'samples': 17820288, 'steps': 92813, 'loss/train': 1.486737608909607}4}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:05 - INFO - __main__ - Step 92821: {'lr': 0.0001626249148877372, 'samples': 17821632, 'steps': 92820, 'loss/train': 1.5460155010223389}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:08 - INFO - __main__ - Step 92825: {'lr': 0.00016260502687840423, 'samples': 17822400, 'steps': 92824, 'loss/train': 1.246734857559204}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:10 - INFO - __main__ - Step 92830: {'lr': 0.00016258016775277833, 'samples': 17823360, 'steps': 92829, 'loss/train': 1.6749136447906494}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:12 - INFO - __main__ - Step 92834: {'lr': 0.0001625602811612847, 'samples': 17824128, 'steps': 92833, 'loss/train': 1.488869309425354}4}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:14 - INFO - __main__ - Step 92838: {'lr': 0.00016254039520017483, 'samples': 17824896, 'steps': 92837, 'loss/train': 0.6838464736938477}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:16 - INFO - __main__ - Step 92842: {'lr': 0.00016252050986959222, 'samples': 17825664, 'steps': 92841, 'loss/train': 1.8610998392105103}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:18 - INFO - __main__ - Step 92846: {'lr': 0.00016250062516968007, 'samples': 17826432, 'steps': 92845, 'loss/train': 1.4685817956924438}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:20 - INFO - __main__ - Step 92851: {'lr': 0.0001624757701818887, 'samples': 17827392, 'steps': 92850, 'loss/train': 1.1060237884521484}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:22 - INFO - __main__ - Step 92855: {'lr': 0.00016245588690150947, 'samples': 17828160, 'steps': 92854, 'loss/train': 1.5406414270401}4}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:22 - INFO - __main__ - Step 92855: {'lr': 0.00016245588690150947, 'samples': 17828160, 'steps': 92854, 'loss/train': 1.5406414270401}4}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:26 - INFO - __main__ - Step 92862: {'lr': 0.0001624210926796039, 'samples': 17829504, 'steps': 92861, 'loss/train': 1.4486231803894043}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:26 - INFO - __main__ - Step 92862: {'lr': 0.0001624210926796039, 'samples': 17829504, 'steps': 92861, 'loss/train': 1.4486231803894043}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:30 - INFO - __main__ - Step 92869: {'lr': 0.00016238630039132194, 'samples': 17830848, 'steps': 92868, 'loss/train': 1.3301124572753906}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:32 - INFO - __main__ - Step 92874: {'lr': 0.0001623614499411114, 'samples': 17831808, 'steps': 92873, 'loss/train': 1.357712984085083}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:32 - INFO - __main__ - Step 92874: {'lr': 0.0001623614499411114, 'samples': 17831808, 'steps': 92873, 'loss/train': 1.357712984085083}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:36 - INFO - __main__ - Step 92882: {'lr': 0.0001623216912742971, 'samples': 17833344, 'steps': 92881, 'loss/train': 1.4505845308303833}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:38 - INFO - __main__ - Step 92886: {'lr': 0.0001623018128889741, 'samples': 17834112, 'steps': 92885, 'loss/train': 0.417248010635376}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:40 - INFO - __main__ - Step 92890: {'lr': 0.00016228193513589828, 'samples': 17834880, 'steps': 92889, 'loss/train': 1.7892842292785645}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:42 - INFO - __main__ - Step 92895: {'lr': 0.00016225708883386956, 'samples': 17835840, 'steps': 92894, 'loss/train': 1.3022401332855225}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:42 - INFO - __main__ - Step 92895: {'lr': 0.00016225708883386956, 'samples': 17835840, 'steps': 92894, 'loss/train': 1.3022401332855225}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:47 - INFO - __main__ - Step 92903: {'lr': 0.00016221733680659112, 'samples': 17837376, 'steps': 92902, 'loss/train': 1.5439468622207642}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:48 - INFO - __main__ - Step 92907: {'lr': 0.0001621974617421646, 'samples': 17838144, 'steps': 92906, 'loss/train': 1.4153062105178833}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:48 - INFO - __main__ - Step 92907: {'lr': 0.0001621974617421646, 'samples': 17838144, 'steps': 92906, 'loss/train': 1.4153062105178833}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:52 - INFO - __main__ - Step 92915: {'lr': 0.00016215771351245345, 'samples': 17839680, 'steps': 92914, 'loss/train': 1.5724648237228394}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:54 - INFO - __main__ - Step 92919: {'lr': 0.00016213784034745527, 'samples': 17840448, 'steps': 92918, 'loss/train': 1.3633586168289185}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:56 - INFO - __main__ - Step 92923: {'lr': 0.0001621179678158865, 'samples': 17841216, 'steps': 92922, 'loss/train': 1.4913617372512817}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:58 - INFO - __main__ - Step 92927: {'lr': 0.00016209809591789025, 'samples': 17841984, 'steps': 92926, 'loss/train': 1.1816767454147339}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:18:58 - INFO - __main__ - Step 92927: {'lr': 0.00016209809591789025, 'samples': 17841984, 'steps': 92926, 'loss/train': 1.1816767454147339}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:02 - INFO - __main__ - Step 92935: {'lr': 0.00016205835402318875, 'samples': 17843520, 'steps': 92934, 'loss/train': 1.1736692190170288}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:04 - INFO - __main__ - Step 92939: {'lr': 0.00016203848402676985, 'samples': 17844288, 'steps': 92938, 'loss/train': 1.3841971158981323}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:06 - INFO - __main__ - Step 92943: {'lr': 0.00016201861466449657, 'samples': 17845056, 'steps': 92942, 'loss/train': 1.299153208732605}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:08 - INFO - __main__ - Step 92948: {'lr': 0.00016199377885364058, 'samples': 17846016, 'steps': 92947, 'loss/train': 1.5433671474456787}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:10 - INFO - __main__ - Step 92953: {'lr': 0.00016196894403414073, 'samples': 17846976, 'steps': 92952, 'loss/train': 1.3472697734832764}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:10 - INFO - __main__ - Step 92953: {'lr': 0.00016196894403414073, 'samples': 17846976, 'steps': 92952, 'loss/train': 1.3472697734832764}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:14 - INFO - __main__ - Step 92960: {'lr': 0.00016193417695285184, 'samples': 17848320, 'steps': 92959, 'loss/train': 1.0571173429489136}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:16 - INFO - __main__ - Step 92964: {'lr': 0.00016191431092219317, 'samples': 17849088, 'steps': 92963, 'loss/train': 1.4357631206512451}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:18 - INFO - __main__ - Step 92969: {'lr': 0.00016188947927691283, 'samples': 17850048, 'steps': 92968, 'loss/train': 1.6030714511871338}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:18 - INFO - __main__ - Step 92969: {'lr': 0.00016188947927691283, 'samples': 17850048, 'steps': 92968, 'loss/train': 1.6030714511871338}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:22 - INFO - __main__ - Step 92977: {'lr': 0.00016184975070904513, 'samples': 17851584, 'steps': 92976, 'loss/train': 1.3656402826309204}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:24 - INFO - __main__ - Step 92981: {'lr': 0.00016182988737829907, 'samples': 17852352, 'steps': 92980, 'loss/train': 1.2896772623062134}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:26 - INFO - __main__ - Step 92985: {'lr': 0.0001618100246832025, 'samples': 17853120, 'steps': 92984, 'loss/train': 1.532159686088562}4}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:28 - INFO - __main__ - Step 92989: {'lr': 0.00016179016262389865, 'samples': 17853888, 'steps': 92988, 'loss/train': 1.3046929836273193}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:30 - INFO - __main__ - Step 92994: {'lr': 0.00016176533594407033, 'samples': 17854848, 'steps': 92993, 'loss/train': 1.179703712463379}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:30 - INFO - __main__ - Step 92994: {'lr': 0.00016176533594407033, 'samples': 17854848, 'steps': 92993, 'loss/train': 1.179703712463379}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:34 - INFO - __main__ - Step 93001: {'lr': 0.0001617305802621748, 'samples': 17856192, 'steps': 93000, 'loss/train': 1.5502358675003052}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:36 - INFO - __main__ - Step 93005: {'lr': 0.00016171072074747353, 'samples': 17856960, 'steps': 93004, 'loss/train': 1.5784331560134888}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:38 - INFO - __main__ - Step 93010: {'lr': 0.0001616858972492038, 'samples': 17857920, 'steps': 93009, 'loss/train': 1.1485201120376587}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:41 - INFO - __main__ - Step 93015: {'lr': 0.0001616610747457584, 'samples': 17858880, 'steps': 93014, 'loss/train': 1.3594958782196045}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:42 - INFO - __main__ - Step 93019: {'lr': 0.00016164121745946354, 'samples': 17859648, 'steps': 93018, 'loss/train': 1.546528935432434}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:45 - INFO - __main__ - Step 93023: {'lr': 0.00016162136081017826, 'samples': 17860416, 'steps': 93022, 'loss/train': 1.435797095298767}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:47 - INFO - __main__ - Step 93027: {'lr': 0.0001616015047980458, 'samples': 17861184, 'steps': 93026, 'loss/train': 2.5479307174682617}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:48 - INFO - __main__ - Step 93031: {'lr': 0.0001615816494232094, 'samples': 17861952, 'steps': 93030, 'loss/train': 1.4695215225219727}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:50 - INFO - __main__ - Step 93035: {'lr': 0.000161561794685812, 'samples': 17862720, 'steps': 93034, 'loss/train': 1.645426869392395}7}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:50 - INFO - __main__ - Step 93035: {'lr': 0.000161561794685812, 'samples': 17862720, 'steps': 93034, 'loss/train': 1.645426869392395}7}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:55 - INFO - __main__ - Step 93043: {'lr': 0.00016152208712390723, 'samples': 17864256, 'steps': 93042, 'loss/train': 1.5940603017807007}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:56 - INFO - __main__ - Step 93047: {'lr': 0.00016150223429968596, 'samples': 17865024, 'steps': 93046, 'loss/train': 1.1757047176361084}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:19:58 - INFO - __main__ - Step 93051: {'lr': 0.00016148238211347637, 'samples': 17865792, 'steps': 93050, 'loss/train': 1.1179845333099365}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:01 - INFO - __main__ - Step 93056: {'lr': 0.0001614575677781364, 'samples': 17866752, 'steps': 93055, 'loss/train': 1.5161755084991455}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:03 - INFO - __main__ - Step 93060: {'lr': 0.00016143771702797628, 'samples': 17867520, 'steps': 93059, 'loss/train': 0.9658939838409424}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:03 - INFO - __main__ - Step 93060: {'lr': 0.00016143771702797628, 'samples': 17867520, 'steps': 93059, 'loss/train': 0.9658939838409424}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:06 - INFO - __main__ - Step 93067: {'lr': 0.00016140297975161688, 'samples': 17868864, 'steps': 93066, 'loss/train': 1.4737416505813599}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:08 - INFO - __main__ - Step 93072: {'lr': 0.00016137816860892906, 'samples': 17869824, 'steps': 93071, 'loss/train': 0.9405996203422546}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:08 - INFO - __main__ - Step 93072: {'lr': 0.00016137816860892906, 'samples': 17869824, 'steps': 93071, 'loss/train': 0.9405996203422546}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:13 - INFO - __main__ - Step 93080: {'lr': 0.00016133847285718943, 'samples': 17871360, 'steps': 93079, 'loss/train': 0.8548104166984558}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:15 - INFO - __main__ - Step 93084: {'lr': 0.00016131862594003649, 'samples': 17872128, 'steps': 93083, 'loss/train': 1.5275729894638062}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:16 - INFO - __main__ - Step 93088: {'lr': 0.0001612987796622188, 'samples': 17872896, 'steps': 93087, 'loss/train': 1.0241918563842773}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:18 - INFO - __main__ - Step 93093: {'lr': 0.00016127397271423007, 'samples': 17873856, 'steps': 93092, 'loss/train': 1.3872150182724}3}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:18 - INFO - __main__ - Step 93093: {'lr': 0.00016127397271423007, 'samples': 17873856, 'steps': 93092, 'loss/train': 1.3872150182724}3}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:23 - INFO - __main__ - Step 93101: {'lr': 0.00016123428367645045, 'samples': 17875392, 'steps': 93100, 'loss/train': 1.270164132118225}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:24 - INFO - __main__ - Step 93105: {'lr': 0.00016121444011740416, 'samples': 17876160, 'steps': 93104, 'loss/train': 1.7621020078659058}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:26 - INFO - __main__ - Step 93109: {'lr': 0.00016119459719844432, 'samples': 17876928, 'steps': 93108, 'loss/train': 1.5535088777542114}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:29 - INFO - __main__ - Step 93114: {'lr': 0.00016116979445008413, 'samples': 17877888, 'steps': 93113, 'loss/train': 1.2552497386932373}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:29 - INFO - __main__ - Step 93114: {'lr': 0.00016116979445008413, 'samples': 17877888, 'steps': 93113, 'loss/train': 1.2552497386932373}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:33 - INFO - __main__ - Step 93122: {'lr': 0.00016113011213415084, 'samples': 17879424, 'steps': 93121, 'loss/train': 1.2508338689804077}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:34 - INFO - __main__ - Step 93126: {'lr': 0.00016111027193715444, 'samples': 17880192, 'steps': 93125, 'loss/train': 1.0891183614730835}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:37 - INFO - __main__ - Step 93130: {'lr': 0.00016109043238099534, 'samples': 17880960, 'steps': 93129, 'loss/train': 2.930649518966675}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:39 - INFO - __main__ - Step 93135: {'lr': 0.000161065633837192, 'samples': 17881920, 'steps': 93134, 'loss/train': 1.5198088884353638}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:41 - INFO - __main__ - Step 93139: {'lr': 0.0001610457957234402, 'samples': 17882688, 'steps': 93138, 'loss/train': 1.023189663887024}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:43 - INFO - __main__ - Step 93143: {'lr': 0.00016102595825099054, 'samples': 17883456, 'steps': 93142, 'loss/train': 1.3578764200210571}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:43 - INFO - __main__ - Step 93143: {'lr': 0.00016102595825099054, 'samples': 17883456, 'steps': 93142, 'loss/train': 1.3578764200210571}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:46 - INFO - __main__ - Step 93150: {'lr': 0.0001609912442177675, 'samples': 17884800, 'steps': 93149, 'loss/train': 1.395085096359253}1}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:46 - INFO - __main__ - Step 93150: {'lr': 0.0001609912442177675, 'samples': 17884800, 'steps': 93149, 'loss/train': 1.395085096359253}1}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:46 - INFO - __main__ - Step 93150: {'lr': 0.0001609912442177675, 'samples': 17884800, 'steps': 93149, 'loss/train': 1.395085096359253}1}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:52 - INFO - __main__ - Step 93162: {'lr': 0.00016093173901903312, 'samples': 17887104, 'steps': 93161, 'loss/train': 0.5293936133384705}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:55 - INFO - __main__ - Step 93168: {'lr': 0.00016090198858659507, 'samples': 17888256, 'steps': 93167, 'loss/train': 1.4106558561325073}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:55 - INFO - __main__ - Step 93168: {'lr': 0.00016090198858659507, 'samples': 17888256, 'steps': 93167, 'loss/train': 1.4106558561325073}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:20:58 - INFO - __main__ - Step 93175: {'lr': 0.00016086728157543607, 'samples': 17889600, 'steps': 93174, 'loss/train': 1.5402907133102417}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:00 - INFO - __main__ - Step 93179: {'lr': 0.00016084744988114206, 'samples': 17890368, 'steps': 93178, 'loss/train': 1.456344723701477}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:00 - INFO - __main__ - Step 93179: {'lr': 0.00016084744988114206, 'samples': 17890368, 'steps': 93178, 'loss/train': 1.456344723701477}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:04 - INFO - __main__ - Step 93186: {'lr': 0.00016081274596278777, 'samples': 17891712, 'steps': 93185, 'loss/train': 0.7343735098838806}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:07 - INFO - __main__ - Step 93191: {'lr': 0.000160787958655225, 'samples': 17892672, 'steps': 93190, 'loss/train': 1.118606448173523}06}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:09 - INFO - __main__ - Step 93196: {'lr': 0.00016076317235260137, 'samples': 17893632, 'steps': 93195, 'loss/train': 1.3651883602142334}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:11 - INFO - __main__ - Step 93200: {'lr': 0.00016074334403424635, 'samples': 17894400, 'steps': 93199, 'loss/train': 1.3853503465652466}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:11 - INFO - __main__ - Step 93200: {'lr': 0.00016074334403424635, 'samples': 17894400, 'steps': 93199, 'loss/train': 1.3853503465652466}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:14 - INFO - __main__ - Step 93207: {'lr': 0.0001607086460255915, 'samples': 17895744, 'steps': 93206, 'loss/train': 1.382276177406311}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:16 - INFO - __main__ - Step 93211: {'lr': 0.00016068881947715796, 'samples': 17896512, 'steps': 93210, 'loss/train': 1.9079020023345947}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:16 - INFO - __main__ - Step 93211: {'lr': 0.00016068881947715796, 'samples': 17896512, 'steps': 93210, 'loss/train': 1.9079020023345947}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:21 - INFO - __main__ - Step 93219: {'lr': 0.0001606491683120615, 'samples': 17898048, 'steps': 93218, 'loss/train': 1.4919339418411255}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:22 - INFO - __main__ - Step 93223: {'lr': 0.00016062934369568427, 'samples': 17898816, 'steps': 93222, 'loss/train': 1.4226783514022827}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:24 - INFO - __main__ - Step 93227: {'lr': 0.0001606095197236117, 'samples': 17899584, 'steps': 93226, 'loss/train': 1.4257094860076904}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:27 - INFO - __main__ - Step 93232: {'lr': 0.0001605847406647921, 'samples': 17900544, 'steps': 93231, 'loss/train': 1.4166818857192993}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:29 - INFO - __main__ - Step 93236: {'lr': 0.00016056491814292752, 'samples': 17901312, 'steps': 93235, 'loss/train': 1.3485288619995117}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:29 - INFO - __main__ - Step 93236: {'lr': 0.00016056491814292752, 'samples': 17901312, 'steps': 93235, 'loss/train': 1.3485288619995117}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:32 - INFO - __main__ - Step 93243: {'lr': 0.00016053023028122587, 'samples': 17902656, 'steps': 93242, 'loss/train': 1.3268638849258423}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:34 - INFO - __main__ - Step 93248: {'lr': 0.00016050545444651972, 'samples': 17903616, 'steps': 93247, 'loss/train': 1.5596964359283447}}█████████���█████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:37 - INFO - __main__ - Step 93253: {'lr': 0.00016048067961993494, 'samples': 17904576, 'steps': 93252, 'loss/train': 1.7020950317382812}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:39 - INFO - __main__ - Step 93257: {'lr': 0.00016046086048470215, 'samples': 17905344, 'steps': 93256, 'loss/train': 1.609190583229065}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:41 - INFO - __main__ - Step 93261: {'lr': 0.00016044104199498878, 'samples': 17906112, 'steps': 93260, 'loss/train': 1.3460981845855713}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:42 - INFO - __main__ - Step 93265: {'lr': 0.0001604212241509374, 'samples': 17906880, 'steps': 93264, 'loss/train': 1.5092118978500366}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:44 - INFO - __main__ - Step 93269: {'lr': 0.0001604014069526911, 'samples': 17907648, 'steps': 93268, 'loss/train': 1.175777554512024}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:47 - INFO - __main__ - Step 93274: {'lr': 0.00016037663636326427, 'samples': 17908608, 'steps': 93273, 'loss/train': 1.2680351734161377}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:49 - INFO - __main__ - Step 93278: {'lr': 0.00016035682061860162, 'samples': 17909376, 'steps': 93277, 'loss/train': 1.4920933246612549}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:51 - INFO - __main__ - Step 93282: {'lr': 0.0001603370055202083, 'samples': 17910144, 'steps': 93281, 'loss/train': 1.746585488319397}9}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:53 - INFO - __main__ - Step 93286: {'lr': 0.00016031719106822726, 'samples': 17910912, 'steps': 93285, 'loss/train': 1.5624492168426514}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:54 - INFO - __main__ - Step 93290: {'lr': 0.00016029737726280113, 'samples': 17911680, 'steps': 93289, 'loss/train': 1.5288504362106323}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:57 - INFO - __main__ - Step 93294: {'lr': 0.00016027756410407293, 'samples': 17912448, 'steps': 93293, 'loss/train': 1.011857032775879}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:21:57 - INFO - __main__ - Step 93294: {'lr': 0.00016027756410407293, 'samples': 17912448, 'steps': 93293, 'loss/train': 1.011857032775879}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:01 - INFO - __main__ - Step 93302: {'lr': 0.00016023793972728162, 'samples': 17913984, 'steps': 93301, 'loss/train': 1.0839083194732666}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:03 - INFO - __main__ - Step 93306: {'lr': 0.00016021812850950407, 'samples': 17914752, 'steps': 93305, 'loss/train': 1.5786868333816528}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:05 - INFO - __main__ - Step 93310: {'lr': 0.0001601983179389957, 'samples': 17915520, 'steps': 93309, 'loss/train': 1.7563496828079224}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:07 - INFO - __main__ - Step 93314: {'lr': 0.0001601785080158995, 'samples': 17916288, 'steps': 93313, 'loss/train': 1.1704646348953247}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:09 - INFO - __main__ - Step 93318: {'lr': 0.00016015869874035803, 'samples': 17917056, 'steps': 93317, 'loss/train': 1.508829116821289}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:11 - INFO - __main__ - Step 93322: {'lr': 0.00016013889011251426, 'samples': 17917824, 'steps': 93321, 'loss/train': 1.218714714050293}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:13 - INFO - __main__ - Step 93327: {'lr': 0.00016011413023875204, 'samples': 17918784, 'steps': 93326, 'loss/train': 1.1671537160873413}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:15 - INFO - __main__ - Step 93332: {'lr': 0.00016008937137751935, 'samples': 17919744, 'steps': 93331, 'loss/train': 1.888564109802246}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:15 - INFO - __main__ - Step 93332: {'lr': 0.00016008937137751935, 'samples': 17919744, 'steps': 93331, 'loss/train': 1.888564109802246}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:18 - INFO - __main__ - Step 93337: {'lr': 0.00016006461352909522, 'samples': 17920704, 'steps': 93336, 'loss/train': 1.277133822441101}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:21 - INFO - __main__ - Step 93342: {'lr': 0.00016003985669375858, 'samples': 17921664, 'steps': 93341, 'loss/train': 1.3204911947250366}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:23 - INFO - __main__ - Step 93346: {'lr': 0.0001600200519550996, 'samples': 17922432, 'steps': 93345, 'loss/train': 1.2606616020202637}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:25 - INFO - __main__ - Step 93350: {'lr': 0.00016000024786513782, 'samples': 17923200, 'steps': 93349, 'loss/train': 1.3925141096115112}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:26 - INFO - __main__ - Step 93354: {'lr': 0.0001599804444240161, 'samples': 17923968, 'steps': 93353, 'loss/train': 1.583892583847046}2}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:28 - INFO - __main__ - Step 93358: {'lr': 0.00015996064163187706, 'samples': 17924736, 'steps': 93357, 'loss/train': 1.2125914096832275}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:28 - INFO - __main__ - Step 93358: {'lr': 0.00015996064163187706, 'samples': 17924736, 'steps': 93357, 'loss/train': 1.2125914096832275}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:33 - INFO - __main__ - Step 93367: {'lr': 0.000159916087723147, 'samples': 17926464, 'steps': 93366, 'loss/train': 0.9493730664253235}5}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:35 - INFO - __main__ - Step 93371: {'lr': 0.00015989628704118794, 'samples': 17927232, 'steps': 93370, 'loss/train': 1.5959234237670898}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:36 - INFO - __main__ - Step 93375: {'lr': 0.0001598764870088183, 'samples': 17928000, 'steps': 93374, 'loss/train': 0.5434019565582275}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:38 - INFO - __main__ - Step 93379: {'lr': 0.00015985668762618095, 'samples': 17928768, 'steps': 93378, 'loss/train': 1.4412678480148315}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:41 - INFO - __main__ - Step 93384: {'lr': 0.00015983193931178762, 'samples': 17929728, 'steps': 93383, 'loss/train': 1.1490390300750732}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:43 - INFO - __main__ - Step 93389: {'lr': 0.00015980719201310272, 'samples': 17930688, 'steps': 93388, 'loss/train': 1.613396167755127}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:45 - INFO - __main__ - Step 93393: {'lr': 0.00015978739490565225, 'samples': 17931456, 'steps': 93392, 'loss/train': 1.2982057332992554}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:47 - INFO - __main__ - Step 93397: {'lr': 0.00015976759844857623, 'samples': 17932224, 'steps': 93396, 'loss/train': 0.3429526388645172}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:49 - INFO - __main__ - Step 93401: {'lr': 0.00015974780264201743, 'samples': 17932992, 'steps': 93400, 'loss/train': 1.236457109451294}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:51 - INFO - __main__ - Step 93405: {'lr': 0.0001597280074861186, 'samples': 17933760, 'steps': 93404, 'loss/train': 1.2135932445526123}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:53 - INFO - __main__ - Step 93410: {'lr': 0.00015970326445645315, 'samples': 17934720, 'steps': 93409, 'loss/train': 1.5245120525360107}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:55 - INFO - __main__ - Step 93414: {'lr': 0.000159683470765061, 'samples': 17935488, 'steps': 93413, 'loss/train': 1.5804595947265625}7}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:57 - INFO - __main__ - Step 93418: {'lr': 0.00015966367772479262, 'samples': 17936256, 'steps': 93417, 'loss/train': 1.4809303283691406}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:22:57 - INFO - __main__ - Step 93418: {'lr': 0.00015966367772479262, 'samples': 17936256, 'steps': 93417, 'loss/train': 1.4809303283691406}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:00 - INFO - __main__ - Step 93425: {'lr': 0.00015962904147151874, 'samples': 17937600, 'steps': 93424, 'loss/train': 1.2906298637390137}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:00 - INFO - __main__ - Step 93425: {'lr': 0.00015962904147151874, 'samples': 17937600, 'steps': 93424, 'loss/train': 1.2906298637390137}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:05 - INFO - __main__ - Step 93434: {'lr': 0.0001595845120778106, 'samples': 17939328, 'steps': 93433, 'loss/train': 1.5232505798339844}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:07 - INFO - __main__ - Step 93438: {'lr': 0.00015956472229530127, 'samples': 17940096, 'steps': 93437, 'loss/train': 1.745011568069458}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:09 - INFO - __main__ - Step 93442: {'lr': 0.00015954493316477182, 'samples': 17940864, 'steps': 93441, 'loss/train': 1.3709615468978882}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:11 - INFO - __main__ - Step 93447: {'lr': 0.0001595201976686741, 'samples': 17941824, 'steps': 93446, 'loss/train': 2.6289491653442383}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:13 - INFO - __main__ - Step 93451: {'lr': 0.00015950041000562093, 'samples': 17942592, 'steps': 93450, 'loss/train': 0.9734323620796204}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:15 - INFO - __main__ - Step 93455: {'lr': 0.00015948062299501125, 'samples': 17943360, 'steps': 93454, 'loss/train': 1.2977830171585083}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:15 - INFO - __main__ - Step 93455: {'lr': 0.00015948062299501125, 'samples': 17943360, 'steps': 93454, 'loss/train': 1.2977830171585083}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:19 - INFO - __main__ - Step 93462: {'lr': 0.00015944599729681563, 'samples': 17944704, 'steps': 93461, 'loss/train': 1.866256594657898}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:21 - INFO - __main__ - Step 93468: {'lr': 0.00015941631971819184, 'samples': 17945856, 'steps': 93467, 'loss/train': 1.586348295211792}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:21 - INFO - __main__ - Step 93468: {'lr': 0.00015941631971819184, 'samples': 17945856, 'steps': 93467, 'loss/train': 1.586348295211792}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:25 - INFO - __main__ - Step 93475: {'lr': 0.00015938169773360817, 'samples': 17947200, 'steps': 93474, 'loss/train': 1.130565881729126}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:27 - INFO - __main__ - Step 93479: {'lr': 0.00015936191464065502, 'samples': 17947968, 'steps': 93478, 'loss/train': 1.4178364276885986}}██████████████��████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:29 - INFO - __main__ - Step 93483: {'lr': 0.00015934213220114386, 'samples': 17948736, 'steps': 93482, 'loss/train': 1.2513784170150757}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:29 - INFO - __main__ - Step 93483: {'lr': 0.00015934213220114386, 'samples': 17948736, 'steps': 93482, 'loss/train': 1.2513784170150757}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:33 - INFO - __main__ - Step 93492: {'lr': 0.00015929762410212957, 'samples': 17950464, 'steps': 93491, 'loss/train': 1.2433359622955322}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:33 - INFO - __main__ - Step 93492: {'lr': 0.00015929762410212957, 'samples': 17950464, 'steps': 93491, 'loss/train': 1.2433359622955322}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:37 - INFO - __main__ - Step 93499: {'lr': 0.00015926300898037104, 'samples': 17951808, 'steps': 93498, 'loss/train': 1.5950417518615723}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:39 - INFO - __main__ - Step 93504: {'lr': 0.0001592382851198968, 'samples': 17952768, 'steps': 93503, 'loss/train': 1.528629183769226}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:41 - INFO - __main__ - Step 93509: {'lr': 0.0001592135622818182, 'samples': 17953728, 'steps': 93508, 'loss/train': 1.105638861656189}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:41 - INFO - __main__ - Step 93509: {'lr': 0.0001592135622818182, 'samples': 17953728, 'steps': 93508, 'loss/train': 1.105638861656189}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:44 - INFO - __main__ - Step 93515: {'lr': 0.0001591838962260784, 'samples': 17954880, 'steps': 93514, 'loss/train': 1.6604782342910767}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:44 - INFO - __main__ - Step 93515: {'lr': 0.0001591838962260784, 'samples': 17954880, 'steps': 93514, 'loss/train': 1.6604782342910767}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:49 - INFO - __main__ - Step 93523: {'lr': 0.00015914434377671378, 'samples': 17956416, 'steps': 93522, 'loss/train': 1.3756650686264038}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:51 - INFO - __main__ - Step 93527: {'lr': 0.00015912456853447605, 'samples': 17957184, 'steps': 93526, 'loss/train': 1.3564549684524536}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:53 - INFO - __main__ - Step 93532: {'lr': 0.00015909985040300447, 'samples': 17958144, 'steps': 93531, 'loss/train': 1.5024025440216064}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:55 - INFO - __main__ - Step 93536: {'lr': 0.00015908007663506153, 'samples': 17958912, 'steps': 93535, 'loss/train': 1.7427774667739868}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:55 - INFO - __main__ - Step 93536: {'lr': 0.00015908007663506153, 'samples': 17958912, 'steps': 93535, 'loss/train': 1.7427774667739868}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:23:58 - INFO - __main__ - Step 93543: {'lr': 0.00015904547411848115, 'samples': 17960256, 'steps': 93542, 'loss/train': 1.563359022140503}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:01 - INFO - __main__ - Step 93547: {'lr': 0.00015902570215343425, 'samples': 17961024, 'steps': 93546, 'loss/train': 1.3082371950149536}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:03 - INFO - __main__ - Step 93552: {'lr': 0.00015900098811945368, 'samples': 17961984, 'steps': 93551, 'loss/train': 1.5655827522277832}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:05 - INFO - __main__ - Step 93556: {'lr': 0.00015898121763030547, 'samples': 17962752, 'steps': 93555, 'loss/train': 1.3715391159057617}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:07 - INFO - __main__ - Step 93560: {'lr': 0.00015896144779734366, 'samples': 17963520, 'steps': 93559, 'loss/train': 1.269461750984192}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:09 - INFO - __main__ - Step 93564: {'lr': 0.00015894167862071098, 'samples': 17964288, 'steps': 93563, 'loss/train': 1.2898799180984497}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:11 - INFO - __main__ - Step 93568: {'lr': 0.00015892191010054995, 'samples': 17965056, 'steps': 93567, 'loss/train': 1.4105597734451294}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:13 - INFO - __main__ - Step 93573: {'lr': 0.00015889720037372886, 'samples': 17966016, 'steps': 93572, 'loss/train': 1.7988522052764893}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:16 - INFO - __main__ - Step 93578: {'lr': 0.00015887249167314567, 'samples': 17966976, 'steps': 93577, 'loss/train': 1.3830158710479736}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:16 - INFO - __main__ - Step 93578: {'lr': 0.00015887249167314567, 'samples': 17966976, 'steps': 93577, 'loss/train': 1.3830158710479736}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:19 - INFO - __main__ - Step 93585: {'lr': 0.00015883790121693885, 'samples': 17968320, 'steps': 93584, 'loss/train': 1.3957451581954956}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:21 - INFO - __main__ - Step 93589: {'lr': 0.0001588181361455917, 'samples': 17969088, 'steps': 93588, 'loss/train': 1.433793067932129}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:23 - INFO - __main__ - Step 93594: {'lr': 0.0001587934307308402, 'samples': 17970048, 'steps': 93593, 'loss/train': 1.777646541595459}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:23 - INFO - __main__ - Step 93594: {'lr': 0.0001587934307308402, 'samples': 17970048, 'steps': 93593, 'loss/train': 1.777646541595459}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:28 - INFO - __main__ - Step 93602: {'lr': 0.00015875390420435953, 'samples': 17971584, 'steps': 93601, 'loss/train': 1.2219834327697754}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:29 - INFO - __main__ - Step 93606: {'lr': 0.00015873414192778604, 'samples': 17972352, 'steps': 93605, 'loss/train': 1.5894200801849365}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:31 - INFO - __main__ - Step 93610: {'lr': 0.00015871438030918032, 'samples': 17973120, 'steps': 93609, 'loss/train': 1.654977560043335}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:34 - INFO - __main__ - Step 93615: {'lr': 0.00015868967921140736, 'samples': 17974080, 'steps': 93614, 'loss/train': 1.3698898553848267}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:36 - INFO - __main__ - Step 93619: {'lr': 0.00015866991907375006, 'samples': 17974848, 'steps': 93618, 'loss/train': 1.563151478767395}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:38 - INFO - __main__ - Step 93623: {'lr': 0.00015865015959452358, 'samples': 17975616, 'steps': 93622, 'loss/train': 1.3696435689926147}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:40 - INFO - __main__ - Step 93627: {'lr': 0.0001586304007738703, 'samples': 17976384, 'steps': 93626, 'loss/train': 1.393221378326416}7}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:41 - INFO - __main__ - Step 93631: {'lr': 0.0001586106426119328, 'samples': 17977152, 'steps': 93630, 'loss/train': 1.052596092224121}7}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:44 - INFO - __main__ - Step 93636: {'lr': 0.00015858594583604684, 'samples': 17978112, 'steps': 93635, 'loss/train': 1.4591717720031738}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:46 - INFO - __main__ - Step 93640: {'lr': 0.00015856618915674044, 'samples': 17978880, 'steps': 93639, 'loss/train': 0.6413478255271912}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:46 - INFO - __main__ - Step 93640: {'lr': 0.00015856618915674044, 'samples': 17978880, 'steps': 93639, 'loss/train': 0.6413478255271912}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:49 - INFO - __main__ - Step 93647: {'lr': 0.00015853161655418843, 'samples': 17980224, 'steps': 93646, 'loss/train': 1.7548729181289673}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:52 - INFO - __main__ - Step 93652: {'lr': 0.00015850692307446272, 'samples': 17981184, 'steps': 93651, 'loss/train': 0.3849007487297058}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:54 - INFO - __main__ - Step 93657: {'lr': 0.0001584822306253711, 'samples': 17982144, 'steps': 93656, 'loss/train': 0.1030687466263771}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:56 - INFO - __main__ - Step 93661: {'lr': 0.00015846247740834146, 'samples': 17982912, 'steps': 93660, 'loss/train': 1.410837173461914}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:58 - INFO - __main__ - Step 93665: {'lr': 0.00015844272485123807, 'samples': 17983680, 'steps': 93664, 'loss/train': 1.3959094285964966}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:24:59 - INFO - __main__ - Step 93669: {'lr': 0.00015842297295420336, 'samples': 17984448, 'steps': 93668, 'loss/train': 1.2483165264129639}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:02 - INFO - __main__ - Step 93673: {'lr': 0.0001584032217173798, 'samples': 17985216, 'steps': 93672, 'loss/train': 1.4069849252700806}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:02 - INFO - __main__ - Step 93673: {'lr': 0.0001584032217173798, 'samples': 17985216, 'steps': 93672, 'loss/train': 1.4069849252700806}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:02 - INFO - __main__ - Step 93673: {'lr': 0.0001584032217173798, 'samples': 17985216, 'steps': 93672, 'loss/train': 1.4069849252700806}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:07 - INFO - __main__ - Step 93684: {'lr': 0.0001583489092214912, 'samples': 17987328, 'steps': 93683, 'loss/train': 1.3766611814498901}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:09 - INFO - __main__ - Step 93689: {'lr': 0.00015832422337504475, 'samples': 17988288, 'steps': 93688, 'loss/train': 1.76311194896698}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:12 - INFO - __main__ - Step 93694: {'lr': 0.00015829953856129052, 'samples': 17989248, 'steps': 93693, 'loss/train': 0.9230802655220032}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:14 - INFO - __main__ - Step 93698: {'lr': 0.0001582797914540124, 'samples': 17990016, 'steps': 93697, 'loss/train': 1.1231532096862793}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:16 - INFO - __main__ - Step 93702: {'lr': 0.00015826004500797775, 'samples': 17990784, 'steps': 93701, 'loss/train': 1.7414249181747437}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:17 - INFO - __main__ - Step 93706: {'lr': 0.0001582402992233287, 'samples': 17991552, 'steps': 93705, 'loss/train': 1.4172680377960205}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:20 - INFO - __main__ - Step 93711: {'lr': 0.00015821561792280796, 'samples': 17992512, 'steps': 93710, 'loss/train': 1.4537220001220703}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:22 - INFO - __main__ - Step 93715: {'lr': 0.00015819587362679745, 'samples': 17993280, 'steps': 93714, 'loss/train': 1.5006885528564453}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:22 - INFO - __main__ - Step 93715: {'lr': 0.00015819587362679745, 'samples': 17993280, 'steps': 93714, 'loss/train': 1.5006885528564453}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:25 - INFO - __main__ - Step 93722: {'lr': 0.000158161322701437, 'samples': 17994624, 'steps': 93721, 'loss/train': 1.37932288646698}453}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:27 - INFO - __main__ - Step 93726: {'lr': 0.00015814158022585184, 'samples': 17995392, 'steps': 93725, 'loss/train': 1.6220910549163818}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:30 - INFO - __main__ - Step 93731: {'lr': 0.00015811690306266187, 'samples': 17996352, 'steps': 93730, 'loss/train': 1.2371900081634521}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:32 - INFO - __main__ - Step 93735: {'lr': 0.00015809716207731639, 'samples': 17997120, 'steps': 93734, 'loss/train': 1.4734159708023071}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:32 - INFO - __main__ - Step 93735: {'lr': 0.00015809716207731639, 'samples': 17997120, 'steps': 93734, 'loss/train': 1.4734159708023071}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:35 - INFO - __main__ - Step 93742: {'lr': 0.0001580626169473325, 'samples': 17998464, 'steps': 93741, 'loss/train': 1.5232120752334595}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:38 - INFO - __main__ - Step 93747: {'lr': 0.00015803794309720927, 'samples': 17999424, 'steps': 93746, 'loss/train': 1.672642707824707}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:40 - INFO - __main__ - Step 93751: {'lr': 0.0001580182047629577, 'samples': 18000192, 'steps': 93750, 'loss/train': 1.359389305114746}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:40 - INFO - __main__ - Step 93751: {'lr': 0.0001580182047629577, 'samples': 18000192, 'steps': 93750, 'loss/train': 1.359389305114746}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:43 - INFO - __main__ - Step 93758: {'lr': 0.00015798366427375785, 'samples': 18001536, 'steps': 93757, 'loss/train': 1.2085425853729248}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:45 - INFO - __main__ - Step 93763: {'lr': 0.0001579589937395477, 'samples': 18002496, 'steps': 93762, 'loss/train': 1.3014581203460693}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:48 - INFO - __main__ - Step 93768: {'lr': 0.0001579343242421439, 'samples': 18003456, 'steps': 93767, 'loss/train': 1.931429386138916}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:50 - INFO - __main__ - Step 93772: {'lr': 0.0001579145893909083, 'samples': 18004224, 'steps': 93771, 'loss/train': 1.5943677425384521}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:50 - INFO - __main__ - Step 93772: {'lr': 0.0001579145893909083, 'samples': 18004224, 'steps': 93771, 'loss/train': 1.5943677425384521}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:53 - INFO - __main__ - Step 93779: {'lr': 0.00015788005499878377, 'samples': 18005568, 'steps': 93778, 'loss/train': 1.6593722105026245}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:55 - INFO - __main__ - Step 93783: {'lr': 0.00015786032197355015, 'samples': 18006336, 'steps': 93782, 'loss/train': 0.9091300368309021}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:25:58 - INFO - __main__ - Step 93789: {'lr': 0.0001578307236812457, 'samples': 18007488, 'steps': 93788, 'loss/train': 1.337988018989563}1}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:00 - INFO - __main__ - Step 93793: {'lr': 0.00015781099231694745, 'samples': 18008256, 'steps': 93792, 'loss/train': 1.0640690326690674}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:00 - INFO - __main__ - Step 93793: {'lr': 0.00015781099231694745, 'samples': 18008256, 'steps': 93792, 'loss/train': 1.0640690326690674}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:03 - INFO - __main__ - Step 93800: {'lr': 0.00015777646402876058, 'samples': 18009600, 'steps': 93799, 'loss/train': 1.402199387550354}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:05 - INFO - __main__ - Step 93804: {'lr': 0.00015775673449251816, 'samples': 18010368, 'steps': 93803, 'loss/train': 5.801753044128418}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:08 - INFO - __main__ - Step 93810: {'lr': 0.00015772714143510086, 'samples': 18011520, 'steps': 93809, 'loss/train': 0.879173755645752}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:10 - INFO - __main__ - Step 93814: {'lr': 0.0001577074135616608, 'samples': 18012288, 'steps': 93813, 'loss/train': 1.6483283042907715}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:10 - INFO - __main__ - Step 93814: {'lr': 0.0001577074135616608, 'samples': 18012288, 'steps': 93813, 'loss/train': 1.6483283042907715}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:13 - INFO - __main__ - Step 93821: {'lr': 0.00015767289138427247, 'samples': 18013632, 'steps': 93820, 'loss/train': 1.391677737236023}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:16 - INFO - __main__ - Step 93826: {'lr': 0.0001576482339341287, 'samples': 18014592, 'steps': 93825, 'loss/train': 1.525024175643921}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:18 - INFO - __main__ - Step 93831: {'lr': 0.00015762357752429186, 'samples': 18015552, 'steps': 93830, 'loss/train': 1.2599871158599854}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:18 - INFO - __main__ - Step 93831: {'lr': 0.00015762357752429186, 'samples': 18015552, 'steps': 93830, 'loss/train': 1.2599871158599854}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:22 - INFO - __main__ - Step 93838: {'lr': 0.000157589060298765, 'samples': 18016896, 'steps': 93837, 'loss/train': 1.290550947189331}54}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:23 - INFO - __main__ - Step 93842: {'lr': 0.00015756933708590033, 'samples': 18017664, 'steps': 93841, 'loss/train': 0.8918753862380981}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:25 - INFO - __main__ - Step 93846: {'lr': 0.0001575496145394009, 'samples': 18018432, 'steps': 93845, 'loss/train': 1.099596619606018}1}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:28 - INFO - __main__ - Step 93851: {'lr': 0.00015752496229356957, 'samples': 18019392, 'steps': 93850, 'loss/train': 1.1563693284988403}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:30 - INFO - __main__ - Step 93855: {'lr': 0.00015750524124691196, 'samples': 18020160, 'steps': 93854, 'loss/train': 1.3544812202453613}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:32 - INFO - __main__ - Step 93859: {'lr': 0.00015748552086708169, 'samples': 18020928, 'steps': 93858, 'loss/train': 1.7045865058898926}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:34 - INFO - __main__ - Step 93863: {'lr': 0.00015746580115422106, 'samples': 18021696, 'steps': 93862, 'loss/train': 1.742024540901184}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:36 - INFO - __main__ - Step 93867: {'lr': 0.0001574460821084721, 'samples': 18022464, 'steps': 93866, 'loss/train': 1.1309937238693237}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:36 - INFO - __main__ - Step 93867: {'lr': 0.0001574460821084721, 'samples': 18022464, 'steps': 93866, 'loss/train': 1.1309937238693237}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:36 - INFO - __main__ - Step 93867: {'lr': 0.0001574460821084721, 'samples': 18022464, 'steps': 93866, 'loss/train': 1.1309937238693237}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:41 - INFO - __main__ - Step 93877: {'lr': 0.00015739678741364635, 'samples': 18024384, 'steps': 93876, 'loss/train': 1.5059322118759155}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:44 - INFO - __main__ - Step 93883: {'lr': 0.00015736721259943648, 'samples': 18025536, 'steps': 93882, 'loss/train': 1.9432874917984009}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:46 - INFO - __main__ - Step 93887: {'lr': 0.00015734749689137842, 'samples': 18026304, 'steps': 93886, 'loss/train': 1.4391052722930908}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:48 - INFO - __main__ - Step 93891: {'lr': 0.000157327781851285, 'samples': 18027072, 'steps': 93890, 'loss/train': 1.5159516334533691}8}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:48 - INFO - __main__ - Step 93891: {'lr': 0.000157327781851285, 'samples': 18027072, 'steps': 93890, 'loss/train': 1.5159516334533691}8}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:51 - INFO - __main__ - Step 93898: {'lr': 0.00015729328213883877, 'samples': 18028416, 'steps': 93897, 'loss/train': 1.4548518657684326}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:54 - INFO - __main__ - Step 93904: {'lr': 0.0001572637125858296, 'samples': 18029568, 'steps': 93903, 'loss/train': 1.6866692304611206}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:56 - INFO - __main__ - Step 93908: {'lr': 0.00015724400038617136, 'samples': 18030336, 'steps': 93907, 'loss/train': 1.4597550630569458}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:58 - INFO - __main__ - Step 93912: {'lr': 0.00015722428885522384, 'samples': 18031104, 'steps': 93911, 'loss/train': 1.4924150705337524}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:26:58 - INFO - __main__ - Step 93912: {'lr': 0.00015722428885522384, 'samples': 18031104, 'steps': 93911, 'loss/train': 1.4924150705337524}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:01 - INFO - __main__ - Step 93919: {'lr': 0.00015718979528557843, 'samples': 18032448, 'steps': 93918, 'loss/train': 1.1535046100616455}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:04 - INFO - __main__ - Step 93924: {'lr': 0.00015716515827606688, 'samples': 18033408, 'steps': 93923, 'loss/train': 0.5162572860717773}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:04 - INFO - __main__ - Step 93924: {'lr': 0.00015716515827606688, 'samples': 18033408, 'steps': 93923, 'loss/train': 0.5162572860717773}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:08 - INFO - __main__ - Step 93932: {'lr': 0.0001571257412361212, 'samples': 18034944, 'steps': 93931, 'loss/train': 1.6142915487289429}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:09 - INFO - __main__ - Step 93936: {'lr': 0.00015710603372042232, 'samples': 18035712, 'steps': 93935, 'loss/train': 1.2937393188476562}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:11 - INFO - __main__ - Step 93940: {'lr': 0.00015708632687442878, 'samples': 18036480, 'steps': 93939, 'loss/train': 1.5140278339385986}}█████████████████████████���█| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:14 - INFO - __main__ - Step 93945: {'lr': 0.00015706169425892664, 'samples': 18037440, 'steps': 93944, 'loss/train': 1.2610459327697754}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:16 - INFO - __main__ - Step 93949: {'lr': 0.00015704198892028972, 'samples': 18038208, 'steps': 93948, 'loss/train': 1.3979966640472412}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:16 - INFO - __main__ - Step 93949: {'lr': 0.00015704198892028972, 'samples': 18038208, 'steps': 93948, 'loss/train': 1.3979966640472412}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:20 - INFO - __main__ - Step 93956: {'lr': 0.00015700750619035024, 'samples': 18039552, 'steps': 93955, 'loss/train': 1.63399076461792}2}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:20 - INFO - __main__ - Step 93956: {'lr': 0.00015700750619035024, 'samples': 18039552, 'steps': 93955, 'loss/train': 1.63399076461792}2}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:24 - INFO - __main__ - Step 93964: {'lr': 0.0001569680998702371, 'samples': 18041088, 'steps': 93963, 'loss/train': 1.3722106218338013}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:26 - INFO - __main__ - Step 93968: {'lr': 0.0001569483977161592, 'samples': 18041856, 'steps': 93967, 'loss/train': 1.3187578916549683}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:28 - INFO - __main__ - Step 93973: {'lr': 0.00015692377096694992, 'samples': 18042816, 'steps': 93972, 'loss/train': 1.1529178619384766}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:30 - INFO - __main__ - Step 93977: {'lr': 0.00015690407032246595, 'samples': 18043584, 'steps': 93976, 'loss/train': 0.12990589439868927}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:30 - INFO - __main__ - Step 93977: {'lr': 0.00015690407032246595, 'samples': 18043584, 'steps': 93976, 'loss/train': 0.12990589439868927}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:34 - INFO - __main__ - Step 93984: {'lr': 0.00015686959580968668, 'samples': 18044928, 'steps': 93983, 'loss/train': 1.0101122856140137}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:36 - INFO - __main__ - Step 93989: {'lr': 0.00015684497241655072, 'samples': 18045888, 'steps': 93988, 'loss/train': 1.3233212232589722}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:38 - INFO - __main__ - Step 93994: {'lr': 0.00015682035007277023, 'samples': 18046848, 'steps': 93993, 'loss/train': 0.138332337141037}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:40 - INFO - __main__ - Step 93998: {'lr': 0.00015680065295346825, 'samples': 18047616, 'steps': 93997, 'loss/train': 1.1617215871810913}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:42 - INFO - __main__ - Step 94002: {'lr': 0.00015678095650607316, 'samples': 18048384, 'steps': 94001, 'loss/train': 1.1624504327774048}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:42 - INFO - __main__ - Step 94002: {'lr': 0.00015678095650607316, 'samples': 18048384, 'steps': 94001, 'loss/train': 1.1624504327774048}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:46 - INFO - __main__ - Step 94009: {'lr': 0.0001567464893403351, 'samples': 18049728, 'steps': 94008, 'loss/train': 1.1230921745300293}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:48 - INFO - __main__ - Step 94014: {'lr': 0.00015672187119674996, 'samples': 18050688, 'steps': 94013, 'loss/train': 0.24971330165863037}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:51 - INFO - __main__ - Step 94019: {'lr': 0.00015669725410390688, 'samples': 18051648, 'steps': 94018, 'loss/train': 1.2981969118118286}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:51 - INFO - __main__ - Step 94019: {'lr': 0.00015669725410390688, 'samples': 18051648, 'steps': 94018, 'loss/train': 1.2981969118118286}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:54 - INFO - __main__ - Step 94026: {'lr': 0.00015666279193970146, 'samples': 18052992, 'steps': 94025, 'loss/train': 0.8081356287002563}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:56 - INFO - __main__ - Step 94030: {'lr': 0.00015664310019963105, 'samples': 18053760, 'steps': 94029, 'loss/train': 1.0473726987838745}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:27:58 - INFO - __main__ - Step 94035: {'lr': 0.00015661848647102627, 'samples': 18054720, 'steps': 94034, 'loss/train': 1.1222279071807861}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:00 - INFO - __main__ - Step 94039: {'lr': 0.000156598796245502, 'samples': 18055488, 'steps': 94038, 'loss/train': 1.5207798480987549}1}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:02 - INFO - __main__ - Step 94043: {'lr': 0.00015657910669333996, 'samples': 18056256, 'steps': 94042, 'loss/train': 1.5886794328689575}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:04 - INFO - __main__ - Step 94047: {'lr': 0.0001565594178146821, 'samples': 18057024, 'steps': 94046, 'loss/train': 1.1348118782043457}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:06 - INFO - __main__ - Step 94051: {'lr': 0.00015653972960967045, 'samples': 18057792, 'steps': 94050, 'loss/train': 1.2285019159317017}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:09 - INFO - __main__ - Step 94056: {'lr': 0.00015651512030093697, 'samples': 18058752, 'steps': 94055, 'loss/train': 1.4664572477340698}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:11 - INFO - __main__ - Step 94060: {'lr': 0.00015649543361214804, 'samples': 18059520, 'steps': 94059, 'loss/train': 1.6951442956924438}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:11 - INFO - __main__ - Step 94060: {'lr': 0.00015649543361214804, 'samples': 18059520, 'steps': 94059, 'loss/train': 1.6951442956924438}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:14 - INFO - __main__ - Step 94067: {'lr': 0.00015646098352892394, 'samples': 18060864, 'steps': 94066, 'loss/train': 1.0776307582855225}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:16 - INFO - __main__ - Step 94071: {'lr': 0.00015644129869427198, 'samples': 18061632, 'steps': 94070, 'loss/train': 1.0836347341537476}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:18 - INFO - __main__ - Step 94076: {'lr': 0.00015641669359948605, 'samples': 18062592, 'steps': 94075, 'loss/train': 1.3104852437973022}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:20 - INFO - __main__ - Step 94080: {'lr': 0.00015639701028265357, 'samples': 18063360, 'steps': 94079, 'loss/train': 1.1707240343093872}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:23 - INFO - __main__ - Step 94084: {'lr': 0.00015637732764063806, 'samples': 18064128, 'steps': 94083, 'loss/train': 1.308734655380249}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:24 - INFO - __main__ - Step 94088: {'lr': 0.0001563576456735814, 'samples': 18064896, 'steps': 94087, 'loss/train': 1.2114235162734985}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:26 - INFO - __main__ - Step 94092: {'lr': 0.00015633796438162565, 'samples': 18065664, 'steps': 94091, 'loss/train': 1.3787888288497925}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:29 - INFO - __main__ - Step 94097: {'lr': 0.0001563133637162575, 'samples': 18066624, 'steps': 94096, 'loss/train': 1.6005651950836182}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:31 - INFO - __main__ - Step 94101: {'lr': 0.0001562936839437972, 'samples': 18067392, 'steps': 94100, 'loss/train': 1.4122458696365356}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:31 - INFO - __main__ - Step 94101: {'lr': 0.0001562936839437972, 'samples': 18067392, 'steps': 94100, 'loss/train': 1.4122458696365356}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:34 - INFO - __main__ - Step 94108: {'lr': 0.000156259245967648, 'samples': 18068736, 'steps': 94107, 'loss/train': 1.496869683265686}6}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:37 - INFO - __main__ - Step 94113: {'lr': 0.00015623464868035547, 'samples': 18069696, 'steps': 94112, 'loss/train': 1.5147966146469116}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:37 - INFO - __main__ - Step 94113: {'lr': 0.00015623464868035547, 'samples': 18069696, 'steps': 94112, 'loss/train': 1.5147966146469116}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:41 - INFO - __main__ - Step 94121: {'lr': 0.00015619529521776221, 'samples': 18071232, 'steps': 94120, 'loss/train': 1.0995794534683228}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:43 - INFO - __main__ - Step 94125: {'lr': 0.00015617561950080145, 'samples': 18072000, 'steps': 94124, 'loss/train': 1.0967170000076294}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:44 - INFO - __main__ - Step 94129: {'lr': 0.00015615594446025376, 'samples': 18072768, 'steps': 94128, 'loss/train': 1.7496733665466309}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:47 - INFO - __main__ - Step 94134: {'lr': 0.0001561313516109913, 'samples': 18073728, 'steps': 94133, 'loss/train': 1.5189520120620728}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:47 - INFO - __main__ - Step 94134: {'lr': 0.0001561313516109913, 'samples': 18073728, 'steps': 94133, 'loss/train': 1.5189520120620728}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:47 - INFO - __main__ - Step 94134: {'lr': 0.0001561313516109913, 'samples': 18073728, 'steps': 94133, 'loss/train': 1.5189520120620728}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:52 - INFO - __main__ - Step 94145: {'lr': 0.00015607725106503103, 'samples': 18075840, 'steps': 94144, 'loss/train': 1.2516883611679077}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:54 - INFO - __main__ - Step 94149: {'lr': 0.00015605757940867637, 'samples': 18076608, 'steps': 94148, 'loss/train': 1.4590760469436646}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:57 - INFO - __main__ - Step 94154: {'lr': 0.0001560329907906523, 'samples': 18077568, 'steps': 94153, 'loss/train': 1.3003920316696167}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:28:59 - INFO - __main__ - Step 94159: {'lr': 0.0001560084032311304, 'samples': 18078528, 'steps': 94158, 'loss/train': 1.0057995319366455}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:01 - INFO - __main__ - Step 94163: {'lr': 0.00015598873394582046, 'samples': 18079296, 'steps': 94162, 'loss/train': 1.3988823890686035}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:01 - INFO - __main__ - Step 94163: {'lr': 0.00015598873394582046, 'samples': 18079296, 'steps': 94162, 'loss/train': 1.3988823890686035}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:04 - INFO - __main__ - Step 94170: {'lr': 0.00015595431432747443, 'samples': 18080640, 'steps': 94169, 'loss/train': 1.1971951723098755}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:07 - INFO - __main__ - Step 94175: {'lr': 0.00015592973015702042, 'samples': 18081600, 'steps': 94174, 'loss/train': 1.2684319019317627}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:09 - INFO - __main__ - Step 94180: {'lr': 0.0001559051470462317, 'samples': 18082560, 'steps': 94179, 'loss/train': 1.712214469909668}7}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:09 - INFO - __main__ - Step 94180: {'lr': 0.0001559051470462317, 'samples': 18082560, 'steps': 94179, 'loss/train': 1.712214469909668}7}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:12 - INFO - __main__ - Step 94187: {'lr': 0.0001558707324718925, 'samples': 18083904, 'steps': 94186, 'loss/train': 1.2086750268936157}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:14 - INFO - __main__ - Step 94191: {'lr': 0.00015585106793388303, 'samples': 18084672, 'steps': 94190, 'loss/train': 1.422806739807129}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:17 - INFO - __main__ - Step 94196: {'lr': 0.00015582648821588408, 'samples': 18085632, 'steps': 94195, 'loss/train': 1.8085401058197021}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:17 - INFO - __main__ - Step 94196: {'lr': 0.00015582648821588408, 'samples': 18085632, 'steps': 94195, 'loss/train': 1.8085401058197021}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:21 - INFO - __main__ - Step 94203: {'lr': 0.00015579207839293917, 'samples': 18086976, 'steps': 94202, 'loss/train': 1.553073763847351}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:22 - INFO - __main__ - Step 94207: {'lr': 0.00015577241657079184, 'samples': 18087744, 'steps': 94206, 'loss/train': 1.3894344568252563}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:24 - INFO - __main__ - Step 94211: {'lr': 0.00015575275542796443, 'samples': 18088512, 'steps': 94210, 'loss/train': 5.121862888336182}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:27 - INFO - __main__ - Step 94217: {'lr': 0.00015572326498775835, 'samples': 18089664, 'steps': 94216, 'loss/train': 1.4270069599151611}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:29 - INFO - __main__ - Step 94221: {'lr': 0.00015570360554385089, 'samples': 18090432, 'steps': 94220, 'loss/train': 1.7215831279754639}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:29 - INFO - __main__ - Step 94221: {'lr': 0.00015570360554385089, 'samples': 18090432, 'steps': 94220, 'loss/train': 1.7215831279754639}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:32 - INFO - __main__ - Step 94228: {'lr': 0.0001556692031529054, 'samples': 18091776, 'steps': 94227, 'loss/train': 0.7664121389389038}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:34 - INFO - __main__ - Step 94232: {'lr': 0.00015564954557883292, 'samples': 18092544, 'steps': 94231, 'loss/train': 1.4123419523239136}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:37 - INFO - __main__ - Step 94237: {'lr': 0.00015562497456779833, 'samples': 18093504, 'steps': 94236, 'loss/train': 1.0005046129226685}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:39 - INFO - __main__ - Step 94242: {'lr': 0.00015560040461986204, 'samples': 18094464, 'steps': 94241, 'loss/train': 1.417618751525879}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:41 - INFO - __main__ - Step 94246: {'lr': 0.0001555807494271297, 'samples': 18095232, 'steps': 94245, 'loss/train': 0.9918766021728516}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:41 - INFO - __main__ - Step 94246: {'lr': 0.0001555807494271297, 'samples': 18095232, 'steps': 94245, 'loss/train': 0.9918766021728516}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:44 - INFO - __main__ - Step 94253: {'lr': 0.00015554635447787192, 'samples': 18096576, 'steps': 94252, 'loss/train': 1.3009412288665771}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:47 - INFO - __main__ - Step 94258: {'lr': 0.0001555217879337098, 'samples': 18097536, 'steps': 94257, 'loss/train': 1.6087898015975952}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:49 - INFO - __main__ - Step 94263: {'lr': 0.00015549722245380827, 'samples': 18098496, 'steps': 94262, 'loss/train': 1.564321756362915}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:51 - INFO - __main__ - Step 94267: {'lr': 0.0001554775708363408, 'samples': 18099264, 'steps': 94266, 'loss/train': 1.321814775466919}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:53 - INFO - __main__ - Step 94271: {'lr': 0.00015545791990031872, 'samples': 18100032, 'steps': 94270, 'loss/train': 1.1999995708465576}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:55 - INFO - __main__ - Step 94275: {'lr': 0.00015543826964588392, 'samples': 18100800, 'steps': 94274, 'loss/train': 1.0049678087234497}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:57 - INFO - __main__ - Step 94279: {'lr': 0.00015541862007317807, 'samples': 18101568, 'steps': 94278, 'loss/train': 1.591689944267273}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:59 - INFO - __main__ - Step 94284: {'lr': 0.00015539405906619282, 'samples': 18102528, 'steps': 94283, 'loss/train': 1.5131224393844604}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:29:59 - INFO - __main__ - Step 94284: {'lr': 0.00015539405906619282, 'samples': 18102528, 'steps': 94283, 'loss/train': 1.5131224393844604}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:03 - INFO - __main__ - Step 94292: {'lr': 0.0001553547636717863, 'samples': 18104064, 'steps': 94291, 'loss/train': 1.5983655452728271}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:03 - INFO - __main__ - Step 94292: {'lr': 0.0001553547636717863, 'samples': 18104064, 'steps': 94291, 'loss/train': 1.5983655452728271}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:07 - INFO - __main__ - Step 94299: {'lr': 0.00015532038244054025, 'samples': 18105408, 'steps': 94298, 'loss/train': 1.2945231199264526}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:09 - INFO - __main__ - Step 94304: {'lr': 0.0001552958256980126, 'samples': 18106368, 'steps': 94303, 'loss/train': 1.162545919418335}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:09 - INFO - __main__ - Step 94304: {'lr': 0.0001552958256980126, 'samples': 18106368, 'steps': 94303, 'loss/train': 1.162545919418335}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:13 - INFO - __main__ - Step 94312: {'lr': 0.00015525653712903994, 'samples': 18107904, 'steps': 94311, 'loss/train': 1.3919661045074463}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:15 - INFO - __main__ - Step 94316: {'lr': 0.0001552368938690414, 'samples': 18108672, 'steps': 94315, 'loss/train': 0.9982638955116272}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:15 - INFO - __main__ - Step 94316: {'lr': 0.0001552368938690414, 'samples': 18108672, 'steps': 94315, 'loss/train': 0.9982638955116272}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:15 - INFO - __main__ - Step 94316: {'lr': 0.0001552368938690414, 'samples': 18108672, 'steps': 94315, 'loss/train': 0.9982638955116272}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:21 - INFO - __main__ - Step 94326: {'lr': 0.00015518778870827031, 'samples': 18110592, 'steps': 94325, 'loss/train': 2.0065677165985107}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:21 - INFO - __main__ - Step 94326: {'lr': 0.00015518778870827031, 'samples': 18110592, 'steps': 94325, 'loss/train': 2.0065677165985107}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:25 - INFO - __main__ - Step 94334: {'lr': 0.0001551485076554535, 'samples': 18112128, 'steps': 94333, 'loss/train': 1.5664525032043457}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:26 - INFO - __main__ - Step 94338: {'lr': 0.00015512886815470113, 'samples': 18112896, 'steps': 94337, 'loss/train': 1.169625997543335}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:29 - INFO - __main__ - Step 94342: {'lr': 0.00015510922933790818, 'samples': 18113664, 'steps': 94341, 'loss/train': 1.3915493488311768}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:29 - INFO - __main__ - Step 94342: {'lr': 0.00015510922933790818, 'samples': 18113664, 'steps': 94341, 'loss/train': 1.3915493488311768}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:33 - INFO - __main__ - Step 94351: {'lr': 0.00015506504450158446, 'samples': 18115392, 'steps': 94350, 'loss/train': 1.1450035572052002}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:35 - INFO - __main__ - Step 94355: {'lr': 0.00015504540790863764, 'samples': 18116160, 'steps': 94354, 'loss/train': 1.5479092597961426}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:37 - INFO - __main__ - Step 94359: {'lr': 0.00015502577200025204, 'samples': 18116928, 'steps': 94358, 'loss/train': 1.2564914226531982}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:39 - INFO - __main__ - Step 94363: {'lr': 0.00015500613677656928, 'samples': 18117696, 'steps': 94362, 'loss/train': 1.1490029096603394}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:41 - INFO - __main__ - Step 94368: {'lr': 0.00015498159371004456, 'samples': 18118656, 'steps': 94367, 'loss/train': 1.5250211954116821}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:41 - INFO - __main__ - Step 94368: {'lr': 0.00015498159371004456, 'samples': 18118656, 'steps': 94367, 'loss/train': 1.5250211954116821}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:45 - INFO - __main__ - Step 94376: {'lr': 0.00015494232703003918, 'samples': 18120192, 'steps': 94375, 'loss/train': 1.3745983839035034}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:47 - INFO - __main__ - Step 94380: {'lr': 0.00015492269471792218, 'samples': 18120960, 'steps': 94379, 'loss/train': 1.2210936546325684}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:49 - INFO - __main__ - Step 94384: {'lr': 0.00015490306309125102, 'samples': 18121728, 'steps': 94383, 'loss/train': 1.4348080158233643}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:51 - INFO - __main__ - Step 94388: {'lr': 0.00015488343215016738, 'samples': 18122496, 'steps': 94387, 'loss/train': 1.1554787158966064}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:53 - INFO - __main__ - Step 94393: {'lr': 0.00015485889443813555, 'samples': 18123456, 'steps': 94392, 'loss/train': 1.2375833988189697}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:55 - INFO - __main__ - Step 94397: {'lr': 0.0001548392650401409, 'samples': 18124224, 'steps': 94396, 'loss/train': 1.2947380542755127}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:55 - INFO - __main__ - Step 94397: {'lr': 0.0001548392650401409, 'samples': 18124224, 'steps': 94396, 'loss/train': 1.2947380542755127}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:30:58 - INFO - __main__ - Step 94404: {'lr': 0.00015480491524453687, 'samples': 18125568, 'steps': 94403, 'loss/train': 1.3030046224594116}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:01 - INFO - __main__ - Step 94410: {'lr': 0.00015477547423540578, 'samples': 18126720, 'steps': 94409, 'loss/train': 1.5307682752609253}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:03 - INFO - __main__ - Step 94414: {'lr': 0.00015475584775408968, 'samples': 18127488, 'steps': 94413, 'loss/train': 1.7207826375961304}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:05 - INFO - __main__ - Step 94418: {'lr': 0.0001547362219594222, 'samples': 18128256, 'steps': 94417, 'loss/train': 1.849234700202942}4}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:07 - INFO - __main__ - Step 94422: {'lr': 0.000154716596851545, 'samples': 18129024, 'steps': 94421, 'loss/train': 1.4514334201812744}4}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:09 - INFO - __main__ - Step 94426: {'lr': 0.0001546969724305995, 'samples': 18129792, 'steps': 94425, 'loss/train': 1.572954535484314}4}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:11 - INFO - __main__ - Step 94430: {'lr': 0.00015467734869672716, 'samples': 18130560, 'steps': 94429, 'loss/train': 1.3245649337768555}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:11 - INFO - __main__ - Step 94430: {'lr': 0.00015467734869672716, 'samples': 18130560, 'steps': 94429, 'loss/train': 1.3245649337768555}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:15 - INFO - __main__ - Step 94438: {'lr': 0.00015463810329076789, 'samples': 18132096, 'steps': 94437, 'loss/train': 0.07710301131010056}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:17 - INFO - __main__ - Step 94442: {'lr': 0.00015461848161896392, 'samples': 18132864, 'steps': 94441, 'loss/train': 1.6635476350784302}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:19 - INFO - __main__ - Step 94446: {'lr': 0.000154598860634799, 'samples': 18133632, 'steps': 94445, 'loss/train': 1.3432530164718628}2}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:21 - INFO - __main__ - Step 94451: {'lr': 0.00015457433537180068, 'samples': 18134592, 'steps': 94450, 'loss/train': 1.6763607263565063}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:23 - INFO - __main__ - Step 94455: {'lr': 0.00015455471593534082, 'samples': 18135360, 'steps': 94454, 'loss/train': 1.1919769048690796}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:25 - INFO - __main__ - Step 94459: {'lr': 0.00015453509718697968, 'samples': 18136128, 'steps': 94458, 'loss/train': 1.5013511180877686}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:27 - INFO - __main__ - Step 94463: {'lr': 0.0001545154791268587, 'samples': 18136896, 'steps': 94462, 'loss/train': 1.4963529109954834}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:29 - INFO - __main__ - Step 94467: {'lr': 0.00015449586175511932, 'samples': 18137664, 'steps': 94466, 'loss/train': 1.543015718460083}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:31 - INFO - __main__ - Step 94472: {'lr': 0.00015447134100869737, 'samples': 18138624, 'steps': 94471, 'loss/train': 1.1925225257873535}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:33 - INFO - __main__ - Step 94476: {'lr': 0.00015445172518633373, 'samples': 18139392, 'steps': 94475, 'loss/train': 1.4587717056274414}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:33 - INFO - __main__ - Step 94476: {'lr': 0.00015445172518633373, 'samples': 18139392, 'steps': 94475, 'loss/train': 1.4587717056274414}}███████���███████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:37 - INFO - __main__ - Step 94483: {'lr': 0.00015441739915480685, 'samples': 18140736, 'steps': 94482, 'loss/train': 1.1728624105453491}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:39 - INFO - __main__ - Step 94488: {'lr': 0.0001543928818528562, 'samples': 18141696, 'steps': 94487, 'loss/train': 1.251320242881775}1}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:39 - INFO - __main__ - Step 94488: {'lr': 0.0001543928818528562, 'samples': 18141696, 'steps': 94487, 'loss/train': 1.251320242881775}1}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:43 - INFO - __main__ - Step 94496: {'lr': 0.00015435365640996285, 'samples': 18143232, 'steps': 94495, 'loss/train': 1.0958709716796875}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:45 - INFO - __main__ - Step 94500: {'lr': 0.00015433404472276786, 'samples': 18144000, 'steps': 94499, 'loss/train': 1.2280486822128296}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:47 - INFO - __main__ - Step 94504: {'lr': 0.0001543144337252625, 'samples': 18144768, 'steps': 94503, 'loss/train': 1.191165566444397}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:49 - INFO - __main__ - Step 94509: {'lr': 0.00015428992094847232, 'samples': 18145728, 'steps': 94508, 'loss/train': 1.132437825202942}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:51 - INFO - __main__ - Step 94513: {'lr': 0.00015427031150328562, 'samples': 18146496, 'steps': 94512, 'loss/train': 1.373999834060669}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:53 - INFO - __main__ - Step 94518: {'lr': 0.000154245800667341, 'samples': 18147456, 'steps': 94517, 'loss/train': 1.2776018381118774}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:53 - INFO - __main__ - Step 94518: {'lr': 0.000154245800667341, 'samples': 18147456, 'steps': 94517, 'loss/train': 1.2776018381118774}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:57 - INFO - __main__ - Step 94525: {'lr': 0.00015421148730918578, 'samples': 18148800, 'steps': 94524, 'loss/train': 1.2601845264434814}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:31:59 - INFO - __main__ - Step 94529: {'lr': 0.00015419188062544374, 'samples': 18149568, 'steps': 94528, 'loss/train': 2.012903928756714}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:01 - INFO - __main__ - Step 94534: {'lr': 0.00015416737324210013, 'samples': 18150528, 'steps': 94533, 'loss/train': 1.3347607851028442}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:03 - INFO - __main__ - Step 94538: {'lr': 0.00015414776811266471, 'samples': 18151296, 'steps': 94537, 'loss/train': 0.7185602784156799}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:06 - INFO - __main__ - Step 94544: {'lr': 0.0001541183617142417, 'samples': 18152448, 'steps': 94543, 'loss/train': 1.1402229070663452}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:06 - INFO - __main__ - Step 94544: {'lr': 0.0001541183617142417, 'samples': 18152448, 'steps': 94543, 'loss/train': 1.1402229070663452}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:09 - INFO - __main__ - Step 94551: {'lr': 0.00015408405621517528, 'samples': 18153792, 'steps': 94550, 'loss/train': 1.4535576105117798}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:11 - INFO - __main__ - Step 94555: {'lr': 0.0001540644540236043, 'samples': 18154560, 'steps': 94554, 'loss/train': 1.2147177457809448}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:11 - INFO - __main__ - Step 94555: {'lr': 0.0001540644540236043, 'samples': 18154560, 'steps': 94554, 'loss/train': 1.2147177457809448}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:15 - INFO - __main__ - Step 94563: {'lr': 0.00015402525171550352, 'samples': 18156096, 'steps': 94562, 'loss/train': 1.4904241561889648}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:17 - INFO - __main__ - Step 94567: {'lr': 0.0001540056515992562, 'samples': 18156864, 'steps': 94566, 'loss/train': 1.1850473880767822}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:19 - INFO - __main__ - Step 94571: {'lr': 0.00015398605217506605, 'samples': 18157632, 'steps': 94570, 'loss/train': 1.302493691444397}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:21 - INFO - __main__ - Step 94576: {'lr': 0.00015396155386824902, 'samples': 18158592, 'steps': 94575, 'loss/train': 0.10838284343481064}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:21 - INFO - __main__ - Step 94576: {'lr': 0.00015396155386824902, 'samples': 18158592, 'steps': 94575, 'loss/train': 0.10838284343481064}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:21 - INFO - __main__ - Step 94576: {'lr': 0.00015396155386824902, 'samples': 18158592, 'steps': 94575, 'loss/train': 0.10838284343481064}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:27 - INFO - __main__ - Step 94587: {'lr': 0.00015390766140170289, 'samples': 18160704, 'steps': 94586, 'loss/train': 0.4918782413005829}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:29 - INFO - __main__ - Step 94591: {'lr': 0.00015388806543991797, 'samples': 18161472, 'steps': 94590, 'loss/train': 1.3196663856506348}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:31 - INFO - __main__ - Step 94596: {'lr': 0.00015386357146210072, 'samples': 18162432, 'steps': 94595, 'loss/train': 1.4697540998458862}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:31 - INFO - __main__ - Step 94596: {'lr': 0.00015386357146210072, 'samples': 18162432, 'steps': 94595, 'loss/train': 1.4697540998458862}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:35 - INFO - __main__ - Step 94604: {'lr': 0.00015382438335022276, 'samples': 18163968, 'steps': 94603, 'loss/train': 1.3278779983520508}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:37 - INFO - __main__ - Step 94608: {'lr': 0.00015380479033425906, 'samples': 18164736, 'steps': 94607, 'loss/train': 1.7715847492218018}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:39 - INFO - __main__ - Step 94612: {'lr': 0.0001537851980118006, 'samples': 18165504, 'steps': 94611, 'loss/train': 1.6626660823822021}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:41 - INFO - __main__ - Step 94617: {'lr': 0.00015376070858418454, 'samples': 18166464, 'steps': 94616, 'loss/train': 0.16943322122097015}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:44 - INFO - __main__ - Step 94622: {'lr': 0.00015373622024066687, 'samples': 18167424, 'steps': 94621, 'loss/train': 0.9812050461769104}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:44 - INFO - __main__ - Step 94622: {'lr': 0.00015373622024066687, 'samples': 18167424, 'steps': 94621, 'loss/train': 0.9812050461769104}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:48 - INFO - __main__ - Step 94629: {'lr': 0.00015370193838155292, 'samples': 18168768, 'steps': 94628, 'loss/train': 0.8591702580451965}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:49 - INFO - __main__ - Step 94633: {'lr': 0.00015368234970231415, 'samples': 18169536, 'steps': 94632, 'loss/train': 1.1420464515686035}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:51 - INFO - __main__ - Step 94637: {'lr': 0.00015366276171746335, 'samples': 18170304, 'steps': 94636, 'loss/train': 0.6896917819976807}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:54 - INFO - __main__ - Step 94642: {'lr': 0.000153638277713098, 'samples': 18171264, 'steps': 94641, 'loss/train': 1.2426568269729614}7}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:56 - INFO - __main__ - Step 94646: {'lr': 0.00015361869129113654, 'samples': 18172032, 'steps': 94645, 'loss/train': 1.0304428339004517}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:56 - INFO - __main__ - Step 94646: {'lr': 0.00015361869129113654, 'samples': 18172032, 'steps': 94645, 'loss/train': 1.0304428339004517}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:32:59 - INFO - __main__ - Step 94653: {'lr': 0.00015358441672476398, 'samples': 18173376, 'steps': 94652, 'loss/train': 1.4708718061447144}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:02 - INFO - __main__ - Step 94658: {'lr': 0.00015355993619489794, 'samples': 18174336, 'steps': 94657, 'loss/train': 1.420148491859436}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:04 - INFO - __main__ - Step 94663: {'lr': 0.00015353545675139192, 'samples': 18175296, 'steps': 94662, 'loss/train': 1.5695812702178955}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:06 - INFO - __main__ - Step 94667: {'lr': 0.00015351587397895167, 'samples': 18176064, 'steps': 94666, 'loss/train': 1.1676150560379028}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:06 - INFO - __main__ - Step 94667: {'lr': 0.00015351587397895167, 'samples': 18176064, 'steps': 94666, 'loss/train': 1.1676150560379028}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:09 - INFO - __main__ - Step 94674: {'lr': 0.00015348160580102525, 'samples': 18177408, 'steps': 94673, 'loss/train': 1.088426113128662}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:12 - INFO - __main__ - Step 94679: {'lr': 0.00015345712983572457, 'samples': 18178368, 'steps': 94678, 'loss/train': 1.685915231704712}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:14 - INFO - __main__ - Step 94684: {'lr': 0.0001534326549579422, 'samples': 18179328, 'steps': 94683, 'loss/train': 1.742186188697815}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:14 - INFO - __main__ - Step 94684: {'lr': 0.0001534326549579422, 'samples': 18179328, 'steps': 94683, 'loss/train': 1.742186188697815}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:18 - INFO - __main__ - Step 94691: {'lr': 0.00015339839195660217, 'samples': 18180672, 'steps': 94690, 'loss/train': 1.418200135231018}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:20 - INFO - __main__ - Step 94695: {'lr': 0.0001533788140562434, 'samples': 18181440, 'steps': 94694, 'loss/train': 0.2451763153076172}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:22 - INFO - __main__ - Step 94699: {'lr': 0.00015335923685246087, 'samples': 18182208, 'steps': 94698, 'loss/train': 0.2002914547920227}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:24 - INFO - __main__ - Step 94705: {'lr': 0.00015332987235317625, 'samples': 18183360, 'steps': 94704, 'loss/train': 1.5074502229690552}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:24 - INFO - __main__ - Step 94705: {'lr': 0.00015332987235317625, 'samples': 18183360, 'steps': 94704, 'loss/train': 1.5074502229690552}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:28 - INFO - __main__ - Step 94712: {'lr': 0.00015329561575260303, 'samples': 18184704, 'steps': 94711, 'loss/train': 1.4765396118164062}}████████████��██████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:30 - INFO - __main__ - Step 94716: {'lr': 0.0001532760415108441, 'samples': 18185472, 'steps': 94715, 'loss/train': 1.3522682189941406}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:32 - INFO - __main__ - Step 94720: {'lr': 0.00015325646796640225, 'samples': 18186240, 'steps': 94719, 'loss/train': 1.3220727443695068}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:34 - INFO - __main__ - Step 94725: {'lr': 0.00015323200201666732, 'samples': 18187200, 'steps': 94724, 'loss/train': 1.4660474061965942}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:36 - INFO - __main__ - Step 94729: {'lr': 0.00015321243004170506, 'samples': 18187968, 'steps': 94728, 'loss/train': 0.5220288038253784}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:38 - INFO - __main__ - Step 94733: {'lr': 0.00015319285876451853, 'samples': 18188736, 'steps': 94732, 'loss/train': 1.4114402532577515}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:40 - INFO - __main__ - Step 94737: {'lr': 0.000153173288185249, 'samples': 18189504, 'steps': 94736, 'loss/train': 1.4354352951049805}5}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:42 - INFO - __main__ - Step 94741: {'lr': 0.0001531537183040373, 'samples': 18190272, 'steps': 94740, 'loss/train': 1.2237378358840942}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:44 - INFO - __main__ - Step 94746: {'lr': 0.00015312925693438162, 'samples': 18191232, 'steps': 94745, 'loss/train': 1.2727686166763306}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:47 - INFO - __main__ - Step 94750: {'lr': 0.0001531096886243163, 'samples': 18192000, 'steps': 94749, 'loss/train': 1.3844761848449707}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:49 - INFO - __main__ - Step 94754: {'lr': 0.0001530901210127673, 'samples': 18192768, 'steps': 94753, 'loss/train': 0.5253903269767761}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:50 - INFO - __main__ - Step 94758: {'lr': 0.00015307055409987587, 'samples': 18193536, 'steps': 94757, 'loss/train': 1.401605486869812}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:52 - INFO - __main__ - Step 94762: {'lr': 0.000153050987885783, 'samples': 18194304, 'steps': 94761, 'loss/train': 0.8450825214385986}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:55 - INFO - __main__ - Step 94767: {'lr': 0.00015302653110106748, 'samples': 18195264, 'steps': 94766, 'loss/train': 1.3140727281570435}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:55 - INFO - __main__ - Step 94767: {'lr': 0.00015302653110106748, 'samples': 18195264, 'steps': 94766, 'loss/train': 1.3140727281570435}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:33:58 - INFO - __main__ - Step 94774: {'lr': 0.00015299229343770677, 'samples': 18196608, 'steps': 94773, 'loss/train': 1.6882483959197998}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:00 - INFO - __main__ - Step 94778: {'lr': 0.00015297273002021897, 'samples': 18197376, 'steps': 94777, 'loss/train': 1.2352596521377563}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:02 - INFO - __main__ - Step 94783: {'lr': 0.0001529482767320529, 'samples': 18198336, 'steps': 94782, 'loss/train': 1.248017430305481}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:04 - INFO - __main__ - Step 94787: {'lr': 0.00015292871488864702, 'samples': 18199104, 'steps': 94786, 'loss/train': 1.3215702772140503}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:07 - INFO - __main__ - Step 94791: {'lr': 0.0001529091537450624, 'samples': 18199872, 'steps': 94790, 'loss/train': 0.3221157193183899}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:09 - INFO - __main__ - Step 94795: {'lr': 0.00015288959330143987, 'samples': 18200640, 'steps': 94794, 'loss/train': 1.2089636325836182}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:10 - INFO - __main__ - Step 94799: {'lr': 0.00015287003355792054, 'samples': 18201408, 'steps': 94798, 'loss/train': 1.6937211751937866}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:12 - INFO - __main__ - Step 94803: {'lr': 0.00015285047451464546, 'samples': 18202176, 'steps': 94802, 'loss/train': 1.5099900960922241}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:15 - INFO - __main__ - Step 94808: {'lr': 0.00015282602669548494, 'samples': 18203136, 'steps': 94807, 'loss/train': 1.4428951740264893}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:17 - INFO - __main__ - Step 94812: {'lr': 0.00015280646922827487, 'samples': 18203904, 'steps': 94811, 'loss/train': 1.5845789909362793}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:19 - INFO - __main__ - Step 94816: {'lr': 0.00015278691246176738, 'samples': 18204672, 'steps': 94815, 'loss/train': 1.7877916097640991}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:20 - INFO - __main__ - Step 94820: {'lr': 0.00015276735639610335, 'samples': 18205440, 'steps': 94819, 'loss/train': 1.2757316827774048}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:22 - INFO - __main__ - Step 94824: {'lr': 0.0001527478010314237, 'samples': 18206208, 'steps': 94823, 'loss/train': 0.9344918727874756}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:25 - INFO - __main__ - Step 94829: {'lr': 0.00015272335781154838, 'samples': 18207168, 'steps': 94828, 'loss/train': 1.474396824836731}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:27 - INFO - __main__ - Step 94833: {'lr': 0.00015270380402459933, 'samples': 18207936, 'steps': 94832, 'loss/train': 1.4552454948425293}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:29 - INFO - __main__ - Step 94837: {'lr': 0.00015268425093909287, 'samples': 18208704, 'steps': 94836, 'loss/train': 1.23208749294281}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:29 - INFO - __main__ - Step 94837: {'lr': 0.00015268425093909287, 'samples': 18208704, 'steps': 94836, 'loss/train': 1.23208749294281}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:32 - INFO - __main__ - Step 94844: {'lr': 0.00015265003472772688, 'samples': 18210048, 'steps': 94843, 'loss/train': 2.1670033931732178}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:35 - INFO - __main__ - Step 94850: {'lr': 0.0001526207082572387, 'samples': 18211200, 'steps': 94849, 'loss/train': 1.4202831983566284}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:37 - INFO - __main__ - Step 94854: {'lr': 0.00015260115815443598, 'samples': 18211968, 'steps': 94853, 'loss/train': 0.7929124236106873}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:39 - INFO - __main__ - Step 94858: {'lr': 0.00015258160875381593, 'samples': 18212736, 'steps': 94857, 'loss/train': 1.3067234754562378}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:39 - INFO - __main__ - Step 94858: {'lr': 0.00015258160875381593, 'samples': 18212736, 'steps': 94857, 'loss/train': 1.3067234754562378}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:42 - INFO - __main__ - Step 94865: {'lr': 0.00015254739899278171, 'samples': 18214080, 'steps': 94864, 'loss/train': 1.4141838550567627}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:45 - INFO - __main__ - Step 94870: {'lr': 0.00015252296476646094, 'samples': 18215040, 'steps': 94869, 'loss/train': 1.493151307106018}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:45 - INFO - __main__ - Step 94870: {'lr': 0.00015252296476646094, 'samples': 18215040, 'steps': 94869, 'loss/train': 1.493151307106018}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:49 - INFO - __main__ - Step 94878: {'lr': 0.00015248387228838795, 'samples': 18216576, 'steps': 94877, 'loss/train': 1.4275513887405396}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:50 - INFO - __main__ - Step 94882: {'lr': 0.00015246432710382324, 'samples': 18217344, 'steps': 94881, 'loss/train': 0.7839977741241455}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:53 - INFO - __main__ - Step 94886: {'lr': 0.00015244478262242775, 'samples': 18218112, 'steps': 94885, 'loss/train': 0.06964508444070816}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:55 - INFO - __main__ - Step 94891: {'lr': 0.00015242035300972945, 'samples': 18219072, 'steps': 94890, 'loss/train': 1.3188711404800415}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:55 - INFO - __main__ - Step 94891: {'lr': 0.00015242035300972945, 'samples': 18219072, 'steps': 94890, 'loss/train': 1.3188711404800415}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:34:59 - INFO - __main__ - Step 94898: {'lr': 0.00015238615339866472, 'samples': 18220416, 'steps': 94897, 'loss/train': 0.8178684711456299}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:00 - INFO - __main__ - Step 94902: {'lr': 0.00015236661173135453, 'samples': 18221184, 'steps': 94901, 'loss/train': 0.8480095267295837}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:02 - INFO - __main__ - Step 94906: {'lr': 0.00015234707076791786, 'samples': 18221952, 'steps': 94905, 'loss/train': 1.4471057653427124}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:05 - INFO - __main__ - Step 94911: {'lr': 0.00015232264555365893, 'samples': 18222912, 'steps': 94910, 'loss/train': 1.3446348905563354}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:07 - INFO - __main__ - Step 94916: {'lr': 0.00015229822143969778, 'samples': 18223872, 'steps': 94915, 'loss/train': 0.8911372423171997}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:07 - INFO - __main__ - Step 94916: {'lr': 0.00015229822143969778, 'samples': 18223872, 'steps': 94915, 'loss/train': 0.8911372423171997}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:10 - INFO - __main__ - Step 94922: {'lr': 0.0001522689139557247, 'samples': 18225024, 'steps': 94921, 'loss/train': 0.3091946542263031}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:13 - INFO - __main__ - Step 94927: {'lr': 0.00015224449226338696, 'samples': 18225984, 'steps': 94926, 'loss/train': 1.307652235031128}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:15 - INFO - __main__ - Step 94932: {'lr': 0.0001522200716722272, 'samples': 18226944, 'steps': 94931, 'loss/train': 1.1312158107757568}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:15 - INFO - __main__ - Step 94932: {'lr': 0.0001522200716722272, 'samples': 18226944, 'steps': 94931, 'loss/train': 1.1312158107757568}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:18 - INFO - __main__ - Step 94939: {'lr': 0.0001521858846951066, 'samples': 18228288, 'steps': 94938, 'loss/train': 1.9352948665618896}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:20 - INFO - __main__ - Step 94943: {'lr': 0.00015216635024917834, 'samples': 18229056, 'steps': 94942, 'loss/train': 0.8135735988616943}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:23 - INFO - __main__ - Step 94948: {'lr': 0.000152141933183637, 'samples': 18230016, 'steps': 94947, 'loss/train': 1.7167387008666992}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:25 - INFO - __main__ - Step 94953: {'lr': 0.0001521175172204291, 'samples': 18230976, 'steps': 94952, 'loss/train': 1.2541251182556152}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:27 - INFO - __main__ - Step 94957: {'lr': 0.00015209798524372758, 'samples': 18231744, 'steps': 94956, 'loss/train': 1.0694457292556763}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:27 - INFO - __main__ - Step 94957: {'lr': 0.00015209798524372758, 'samples': 18231744, 'steps': 94956, 'loss/train': 1.0694457292556763}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:30 - INFO - __main__ - Step 94964: {'lr': 0.00015206380598294046, 'samples': 18233088, 'steps': 94963, 'loss/train': 1.3876101970672607}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:32 - INFO - __main__ - Step 94968: {'lr': 0.00015204427594755582, 'samples': 18233856, 'steps': 94967, 'loss/train': 1.319311261177063}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:35 - INFO - __main__ - Step 94973: {'lr': 0.0001520198643964316, 'samples': 18234816, 'steps': 94972, 'loss/train': 5.044995307922363}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:35 - INFO - __main__ - Step 94973: {'lr': 0.0001520198643964316, 'samples': 18234816, 'steps': 94972, 'loss/train': 5.044995307922363}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:39 - INFO - __main__ - Step 94979: {'lr': 0.00015199057199200187, 'samples': 18235968, 'steps': 94978, 'loss/train': 0.4436163306236267}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:41 - INFO - __main__ - Step 94984: {'lr': 0.0001519661628693992, 'samples': 18236928, 'steps': 94983, 'loss/train': 0.9533984661102295}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:43 - INFO - __main__ - Step 94988: {'lr': 0.00015194663636640938, 'samples': 18237696, 'steps': 94987, 'loss/train': 1.6541509628295898}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:45 - INFO - __main__ - Step 94992: {'lr': 0.000151927110570321, 'samples': 18238464, 'steps': 94991, 'loss/train': 0.9027819037437439}8}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:47 - INFO - __main__ - Step 94996: {'lr': 0.00015190758548127464, 'samples': 18239232, 'steps': 94995, 'loss/train': 1.1314321756362915}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:49 - INFO - __main__ - Step 95001: {'lr': 0.00015188318011445906, 'samples': 18240192, 'steps': 95000, 'loss/train': 1.4184300899505615}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:49 - INFO - __main__ - Step 95001: {'lr': 0.00015188318011445906, 'samples': 18240192, 'steps': 95000, 'loss/train': 1.4184300899505615}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:49 - INFO - __main__ - Step 95001: {'lr': 0.00015188318011445906, 'samples': 18240192, 'steps': 95000, 'loss/train': 1.4184300899505615}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:55 - INFO - __main__ - Step 95011: {'lr': 0.0001518343726968473, 'samples': 18242112, 'steps': 95010, 'loss/train': 1.6076737642288208}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:55 - INFO - __main__ - Step 95011: {'lr': 0.0001518343726968473, 'samples': 18242112, 'steps': 95010, 'loss/train': 1.6076737642288208}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:35:58 - INFO - __main__ - Step 95019: {'lr': 0.00015179532994735034, 'samples': 18243648, 'steps': 95018, 'loss/train': 1.2968288660049438}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:00 - INFO - __main__ - Step 95023: {'lr': 0.00015177580963451965, 'samples': 18244416, 'steps': 95022, 'loss/train': 1.5891822576522827}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:03 - INFO - __main__ - Step 95028: {'lr': 0.00015175141023930966, 'samples': 18245376, 'steps': 95027, 'loss/train': 1.4567004442214966}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:03 - INFO - __main__ - Step 95028: {'lr': 0.00015175141023930966, 'samples': 18245376, 'steps': 95027, 'loss/train': 1.4567004442214966}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:07 - INFO - __main__ - Step 95036: {'lr': 0.00015171237350909158, 'samples': 18246912, 'steps': 95035, 'loss/train': 1.3187177181243896}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:09 - INFO - __main__ - Step 95040: {'lr': 0.00015169285620679745, 'samples': 18247680, 'steps': 95039, 'loss/train': 1.5099292993545532}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:10 - INFO - __main__ - Step 95044: {'lr': 0.00015167333961323425, 'samples': 18248448, 'steps': 95043, 'loss/train': 1.0174058675765991}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:13 - INFO - __main__ - Step 95048: {'lr': 0.00015165382372854273, 'samples': 18249216, 'steps': 95047, 'loss/train': 1.4800649881362915}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:13 - INFO - __main__ - Step 95048: {'lr': 0.00015165382372854273, 'samples': 18249216, 'steps': 95047, 'loss/train': 1.4800649881362915}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:16 - INFO - __main__ - Step 95056: {'lr': 0.00015161479408633713, 'samples': 18250752, 'steps': 95055, 'loss/train': 5.36776876449585}5}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:19 - INFO - __main__ - Step 95060: {'lr': 0.00015159528032910463, 'samples': 18251520, 'steps': 95059, 'loss/train': 1.5066163539886475}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:21 - INFO - __main__ - Step 95065: {'lr': 0.00015157088913022242, 'samples': 18252480, 'steps': 95064, 'loss/train': 0.8920952677726746}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:23 - INFO - __main__ - Step 95070: {'lr': 0.00015154649904010624, 'samples': 18253440, 'steps': 95069, 'loss/train': 1.2011699676513672}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:25 - INFO - __main__ - Step 95074: {'lr': 0.00015152698776650948, 'samples': 18254208, 'steps': 95073, 'loss/train': 1.031006097793579}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:27 - INFO - __main__ - Step 95078: {'lr': 0.00015150747720283934, 'samples': 18254976, 'steps': 95077, 'loss/train': 1.334852933883667}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:27 - INFO - __main__ - Step 95078: {'lr': 0.00015150747720283934, 'samples': 18254976, 'steps': 95077, 'loss/train': 1.334852933883667}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:31 - INFO - __main__ - Step 95085: {'lr': 0.0001514733354251009, 'samples': 18256320, 'steps': 95084, 'loss/train': 1.4259333610534668}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:33 - INFO - __main__ - Step 95090: {'lr': 0.00015144894977279588, 'samples': 18257280, 'steps': 95089, 'loss/train': 0.5299057960510254}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:35 - INFO - __main__ - Step 95095: {'lr': 0.0001514245652306304, 'samples': 18258240, 'steps': 95094, 'loss/train': 0.8576415777206421}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:35 - INFO - __main__ - Step 95095: {'lr': 0.0001514245652306304, 'samples': 18258240, 'steps': 95094, 'loss/train': 0.8576415777206421}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:39 - INFO - __main__ - Step 95102: {'lr': 0.00015139042873715624, 'samples': 18259584, 'steps': 95101, 'loss/train': 0.05646722391247749}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:41 - INFO - __main__ - Step 95106: {'lr': 0.0001513709231469113, 'samples': 18260352, 'steps': 95105, 'loss/train': 1.3384792804718018}9}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:43 - INFO - __main__ - Step 95111: {'lr': 0.00015134654215903824, 'samples': 18261312, 'steps': 95110, 'loss/train': 1.2441000938415527}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:45 - INFO - __main__ - Step 95115: {'lr': 0.00015132703816885768, 'samples': 18262080, 'steps': 95114, 'loss/train': 1.454143762588501}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:45 - INFO - __main__ - Step 95115: {'lr': 0.00015132703816885768, 'samples': 18262080, 'steps': 95114, 'loss/train': 1.454143762588501}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:49 - INFO - __main__ - Step 95122: {'lr': 0.0001512929078978561, 'samples': 18263424, 'steps': 95121, 'loss/train': 0.985346794128418}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:51 - INFO - __main__ - Step 95126: {'lr': 0.00015127340586427646, 'samples': 18264192, 'steps': 95125, 'loss/train': 1.5218706130981445}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:53 - INFO - __main__ - Step 95132: {'lr': 0.00015124415414849142, 'samples': 18265344, 'steps': 95131, 'loss/train': 1.2309571504592896}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:55 - INFO - __main__ - Step 95136: {'lr': 0.00015122465389456256, 'samples': 18266112, 'steps': 95135, 'loss/train': 0.7378812432289124}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:36:58 - INFO - __main__ - Step 95140: {'lr': 0.00015120515435274018, 'samples': 18266880, 'steps': 95139, 'loss/train': 1.452340006828308}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:00 - INFO - __main__ - Step 95144: {'lr': 0.0001511856555231646, 'samples': 18267648, 'steps': 95143, 'loss/train': 1.4359638690948486}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:01 - INFO - __main__ - Step 95148: {'lr': 0.00015116615740597654, 'samples': 18268416, 'steps': 95147, 'loss/train': 1.047562599182129}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:03 - INFO - __main__ - Step 95152: {'lr': 0.00015114666000131652, 'samples': 18269184, 'steps': 95151, 'loss/train': 1.1481095552444458}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:06 - INFO - __main__ - Step 95157: {'lr': 0.0001511222892476984, 'samples': 18270144, 'steps': 95156, 'loss/train': 1.0226068496704102}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:08 - INFO - __main__ - Step 95161: {'lr': 0.00015110279344674043, 'samples': 18270912, 'steps': 95160, 'loss/train': 1.2916101217269897}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:10 - INFO - __main__ - Step 95165: {'lr': 0.00015108329835876745, 'samples': 18271680, 'steps': 95164, 'loss/train': 1.1259486675262451}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:11 - INFO - __main__ - Step 95169: {'lr': 0.0001510638039839199, 'samples': 18272448, 'steps': 95168, 'loss/train': 1.454773187637329}1}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:13 - INFO - __main__ - Step 95173: {'lr': 0.00015104431032233827, 'samples': 18273216, 'steps': 95172, 'loss/train': 1.2490599155426025}}███████████████████████���███| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:16 - INFO - __main__ - Step 95178: {'lr': 0.00015101994424860564, 'samples': 18274176, 'steps': 95177, 'loss/train': 0.7412286996841431}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:16 - INFO - __main__ - Step 95178: {'lr': 0.00015101994424860564, 'samples': 18274176, 'steps': 95177, 'loss/train': 0.7412286996841431}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:18 - INFO - __main__ - Step 95184: {'lr': 0.00015099070643191393, 'samples': 18275328, 'steps': 95183, 'loss/train': 1.7219878435134888}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:21 - INFO - __main__ - Step 95188: {'lr': 0.0001509712154463313, 'samples': 18276096, 'steps': 95187, 'loss/train': 1.2985308170318604}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:21 - INFO - __main__ - Step 95188: {'lr': 0.0001509712154463313, 'samples': 18276096, 'steps': 95187, 'loss/train': 1.2985308170318604}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:25 - INFO - __main__ - Step 95197: {'lr': 0.0001509273633393038, 'samples': 18277824, 'steps': 95196, 'loss/train': 0.9308603405952454}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:27 - INFO - __main__ - Step 95201: {'lr': 0.00015090787467451872, 'samples': 18278592, 'steps': 95200, 'loss/train': 1.410526156425476}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:29 - INFO - __main__ - Step 95205: {'lr': 0.00015088838672412376, 'samples': 18279360, 'steps': 95204, 'loss/train': 1.3128619194030762}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:31 - INFO - __main__ - Step 95209: {'lr': 0.0001508688994882595, 'samples': 18280128, 'steps': 95208, 'loss/train': 1.742853045463562}2}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:33 - INFO - __main__ - Step 95214: {'lr': 0.00015084454144845177, 'samples': 18281088, 'steps': 95213, 'loss/train': 1.5326939821243286}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:35 - INFO - __main__ - Step 95218: {'lr': 0.00015082505582079497, 'samples': 18281856, 'steps': 95217, 'loss/train': 1.494893193244934}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:37 - INFO - __main__ - Step 95222: {'lr': 0.00015080557090812547, 'samples': 18282624, 'steps': 95221, 'loss/train': 1.0268231630325317}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:39 - INFO - __main__ - Step 95226: {'lr': 0.00015078608671058349, 'samples': 18283392, 'steps': 95225, 'loss/train': 1.289203405380249}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:41 - INFO - __main__ - Step 95230: {'lr': 0.00015076660322830974, 'samples': 18284160, 'steps': 95229, 'loss/train': 1.583662509918213}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:44 - INFO - __main__ - Step 95235: {'lr': 0.0001507422498815273, 'samples': 18285120, 'steps': 95234, 'loss/train': 1.2924981117248535}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:46 - INFO - __main__ - Step 95239: {'lr': 0.00015072276800912035, 'samples': 18285888, 'steps': 95238, 'loss/train': 1.3423861265182495}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:48 - INFO - __main__ - Step 95243: {'lr': 0.00015070328685243807, 'samples': 18286656, 'steps': 95242, 'loss/train': 1.452865719795227}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:49 - INFO - __main__ - Step 95247: {'lr': 0.00015068380641162084, 'samples': 18287424, 'steps': 95246, 'loss/train': 1.2770382165908813}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:51 - INFO - __main__ - Step 95251: {'lr': 0.00015066432668680915, 'samples': 18288192, 'steps': 95250, 'loss/train': 1.3040522336959839}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:53 - INFO - __main__ - Step 95256: {'lr': 0.00015063997803789115, 'samples': 18289152, 'steps': 95255, 'loss/train': 1.1975828409194946}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:56 - INFO - __main__ - Step 95261: {'lr': 0.0001506156305082255, 'samples': 18290112, 'steps': 95260, 'loss/train': 1.4508699178695679}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:58 - INFO - __main__ - Step 95265: {'lr': 0.000150596153290539, 'samples': 18290880, 'steps': 95264, 'loss/train': 1.777541160583496}9}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:37:58 - INFO - __main__ - Step 95265: {'lr': 0.000150596153290539, 'samples': 18290880, 'steps': 95264, 'loss/train': 1.777541160583496}9}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:01 - INFO - __main__ - Step 95271: {'lr': 0.00015056693880774816, 'samples': 18292032, 'steps': 95270, 'loss/train': 1.7908464670181274}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:03 - INFO - __main__ - Step 95276: {'lr': 0.00015054259463748507, 'samples': 18292992, 'steps': 95275, 'loss/train': 1.5190918445587158}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:05 - INFO - __main__ - Step 95280: {'lr': 0.00015052312010791285, 'samples': 18293760, 'steps': 95279, 'loss/train': 1.3883110284805298}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:07 - INFO - __main__ - Step 95284: {'lr': 0.00015050364629550455, 'samples': 18294528, 'steps': 95283, 'loss/train': 1.6050347089767456}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:09 - INFO - __main__ - Step 95288: {'lr': 0.00015048417320040076, 'samples': 18295296, 'steps': 95287, 'loss/train': 1.6615434885025024}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:11 - INFO - __main__ - Step 95292: {'lr': 0.00015046470082274156, 'samples': 18296064, 'steps': 95291, 'loss/train': 1.4359309673309326}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:13 - INFO - __main__ - Step 95297: {'lr': 0.0001504403613597881, 'samples': 18297024, 'steps': 95296, 'loss/train': 1.1741278171539307}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:16 - INFO - __main__ - Step 95302: {'lr': 0.00015041602301833561, 'samples': 18297984, 'steps': 95301, 'loss/train': 1.3591642379760742}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:16 - INFO - __main__ - Step 95302: {'lr': 0.00015041602301833561, 'samples': 18297984, 'steps': 95301, 'loss/train': 1.3591642379760742}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:19 - INFO - __main__ - Step 95309: {'lr': 0.00015038195122494562, 'samples': 18299328, 'steps': 95308, 'loss/train': 1.2941653728485107}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:21 - INFO - __main__ - Step 95313: {'lr': 0.00015036248261617434, 'samples': 18300096, 'steps': 95312, 'loss/train': 1.238427758216858}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:23 - INFO - __main__ - Step 95318: {'lr': 0.00015033814786536714, 'samples': 18301056, 'steps': 95317, 'loss/train': 1.5147607326507568}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:25 - INFO - __main__ - Step 95322: {'lr': 0.0001503186808730178, 'samples': 18301824, 'steps': 95321, 'loss/train': 1.1534732580184937}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:28 - INFO - __main__ - Step 95326: {'lr': 0.00015029921459930632, 'samples': 18302592, 'steps': 95325, 'loss/train': 1.1791197061538696}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:30 - INFO - __main__ - Step 95330: {'lr': 0.0001502797490443731, 'samples': 18303360, 'steps': 95329, 'loss/train': 1.3401896953582764}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:31 - INFO - __main__ - Step 95334: {'lr': 0.00015026028420835825, 'samples': 18304128, 'steps': 95333, 'loss/train': 1.0218181610107422}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:33 - INFO - __main__ - Step 95338: {'lr': 0.00015024082009140226, 'samples': 18304896, 'steps': 95337, 'loss/train': 1.5886223316192627}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:35 - INFO - __main__ - Step 95343: {'lr': 0.00015021649095659761, 'samples': 18305856, 'steps': 95342, 'loss/train': 1.260650634765625}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:38 - INFO - __main__ - Step 95348: {'lr': 0.0001501921629458156, 'samples': 18306816, 'steps': 95347, 'loss/train': 1.3360350131988525}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:40 - INFO - __main__ - Step 95352: {'lr': 0.0001501727013466705, 'samples': 18307584, 'steps': 95351, 'loss/train': 1.4185417890548706}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:40 - INFO - __main__ - Step 95352: {'lr': 0.0001501727013466705, 'samples': 18307584, 'steps': 95351, 'loss/train': 1.4185417890548706}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:43 - INFO - __main__ - Step 95359: {'lr': 0.00015013864528000577, 'samples': 18308928, 'steps': 95358, 'loss/train': 0.08325207233428955}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:46 - INFO - __main__ - Step 95364: {'lr': 0.0001501143208679381, 'samples': 18309888, 'steps': 95363, 'loss/train': 0.9231928586959839}5}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:48 - INFO - __main__ - Step 95368: {'lr': 0.00015009486214839573, 'samples': 18310656, 'steps': 95367, 'loss/train': 1.5761182308197021}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:50 - INFO - __main__ - Step 95372: {'lr': 0.0001500754041491049, 'samples': 18311424, 'steps': 95371, 'loss/train': 0.4893127381801605}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:51 - INFO - __main__ - Step 95376: {'lr': 0.00015005594687020574, 'samples': 18312192, 'steps': 95375, 'loss/train': 0.7833857536315918}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:54 - INFO - __main__ - Step 95380: {'lr': 0.00015003649031183848, 'samples': 18312960, 'steps': 95379, 'loss/train': 1.2381805181503296}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:56 - INFO - __main__ - Step 95384: {'lr': 0.00015001703447414352, 'samples': 18313728, 'steps': 95383, 'loss/train': 1.3663173913955688}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:56 - INFO - __main__ - Step 95384: {'lr': 0.00015001703447414352, 'samples': 18313728, 'steps': 95383, 'loss/train': 1.3663173913955688}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:38:59 - INFO - __main__ - Step 95392: {'lr': 0.00014997812496133134, 'samples': 18315264, 'steps': 95391, 'loss/train': 1.5948344469070435}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:01 - INFO - __main__ - Step 95396: {'lr': 0.00014995867128649466, 'samples': 18316032, 'steps': 95395, 'loss/train': 1.3388582468032837}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:04 - INFO - __main__ - Step 95401: {'lr': 0.00014993435520719954, 'samples': 18316992, 'steps': 95400, 'loss/train': 1.645056962966919}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:04 - INFO - __main__ - Step 95401: {'lr': 0.00014993435520719954, 'samples': 18316992, 'steps': 95400, 'loss/train': 1.645056962966919}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:08 - INFO - __main__ - Step 95409: {'lr': 0.0001498954518250191, 'samples': 18318528, 'steps': 95408, 'loss/train': 1.1271514892578125}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:09 - INFO - __main__ - Step 95413: {'lr': 0.0001498760012163923, 'samples': 18319296, 'steps': 95412, 'loss/train': 1.0195789337158203}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:12 - INFO - __main__ - Step 95417: {'lr': 0.00014985655132959469, 'samples': 18320064, 'steps': 95416, 'loss/train': 0.29895728826522827}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:14 - INFO - __main__ - Step 95421: {'lr': 0.00014983710216476663, 'samples': 18320832, 'steps': 95420, 'loss/train': 1.3783631324768066}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:16 - INFO - __main__ - Step 95425: {'lr': 0.00014981765372204834, 'samples': 18321600, 'steps': 95424, 'loss/train': 1.3633216619491577}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:18 - INFO - __main__ - Step 95429: {'lr': 0.00014979820600157984, 'samples': 18322368, 'steps': 95428, 'loss/train': 1.3368200063705444}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:20 - INFO - __main__ - Step 95433: {'lr': 0.0001497787590035015, 'samples': 18323136, 'steps': 95432, 'loss/train': 1.7240864038467407}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:22 - INFO - __main__ - Step 95438: {'lr': 0.00014975445127197833, 'samples': 18324096, 'steps': 95437, 'loss/train': 1.219923496246338}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:24 - INFO - __main__ - Step 95442: {'lr': 0.00014973500589979033, 'samples': 18324864, 'steps': 95441, 'loss/train': 1.5682339668273926}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:24 - INFO - __main__ - Step 95442: {'lr': 0.00014973500589979033, 'samples': 18324864, 'steps': 95441, 'loss/train': 1.5682339668273926}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:27 - INFO - __main__ - Step 95449: {'lr': 0.0001497009782378933, 'samples': 18326208, 'steps': 95448, 'loss/train': 1.5142040252685547}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:30 - INFO - __main__ - Step 95454: {'lr': 0.0001496766741208616, 'samples': 18327168, 'steps': 95453, 'loss/train': 1.4638175964355469}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:30 - INFO - __main__ - Step 95454: {'lr': 0.0001496766741208616, 'samples': 18327168, 'steps': 95453, 'loss/train': 1.4638175964355469}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:34 - INFO - __main__ - Step 95462: {'lr': 0.0001496377898843402, 'samples': 18328704, 'steps': 95461, 'loss/train': 1.2420003414154053}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:34 - INFO - __main__ - Step 95462: {'lr': 0.0001496377898843402, 'samples': 18328704, 'steps': 95461, 'loss/train': 1.2420003414154053}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:37 - INFO - __main__ - Step 95469: {'lr': 0.000149603768551483, 'samples': 18330048, 'steps': 95468, 'loss/train': 1.098944067955017}3}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:40 - INFO - __main__ - Step 95475: {'lr': 0.00014957460917324817, 'samples': 18331200, 'steps': 95474, 'loss/train': 1.2827177047729492}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:42 - INFO - __main__ - Step 95479: {'lr': 0.00014955517049273175, 'samples': 18331968, 'steps': 95478, 'loss/train': 1.347690463066101}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:42 - INFO - __main__ - Step 95479: {'lr': 0.00014955517049273175, 'samples': 18331968, 'steps': 95478, 'loss/train': 1.347690463066101}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:45 - INFO - __main__ - Step 95486: {'lr': 0.00014952115454437953, 'samples': 18333312, 'steps': 95485, 'loss/train': 1.5655776262283325}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:47 - INFO - __main__ - Step 95490: {'lr': 0.00014950171785559153, 'samples': 18334080, 'steps': 95489, 'loss/train': 1.629355549812317}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:50 - INFO - __main__ - Step 95496: {'lr': 0.00014947256418094244, 'samples': 18335232, 'steps': 95495, 'loss/train': 0.981548011302948}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:50 - INFO - __main__ - Step 95496: {'lr': 0.00014947256418094244, 'samples': 18335232, 'steps': 95495, 'loss/train': 0.981548011302948}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:54 - INFO - __main__ - Step 95503: {'lr': 0.00014943855362152485, 'samples': 18336576, 'steps': 95502, 'loss/train': 1.6973724365234375}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:55 - INFO - __main__ - Step 95507: {'lr': 0.0001494191200129467, 'samples': 18337344, 'steps': 95506, 'loss/train': 1.2396819591522217}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:39:58 - INFO - __main__ - Step 95512: {'lr': 0.0001493948290219449, 'samples': 18338304, 'steps': 95511, 'loss/train': 1.4069451093673706}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:00 - INFO - __main__ - Step 95516: {'lr': 0.00014937539704509072, 'samples': 18339072, 'steps': 95515, 'loss/train': 1.1636102199554443}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:02 - INFO - __main__ - Step 95521: {'lr': 0.00014935110809418713, 'samples': 18340032, 'steps': 95520, 'loss/train': 1.507258653640747}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:02 - INFO - __main__ - Step 95521: {'lr': 0.00014935110809418713, 'samples': 18340032, 'steps': 95520, 'loss/train': 1.507258653640747}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:06 - INFO - __main__ - Step 95528: {'lr': 0.00014931710546771843, 'samples': 18341376, 'steps': 95527, 'loss/train': 1.7268024682998657}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:08 - INFO - __main__ - Step 95533: {'lr': 0.00014929281923832473, 'samples': 18342336, 'steps': 95532, 'loss/train': 1.041250228881836}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:10 - INFO - __main__ - Step 95537: {'lr': 0.00014927339107158436, 'samples': 18343104, 'steps': 95536, 'loss/train': 1.5254157781600952}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:10 - INFO - __main__ - Step 95537: {'lr': 0.00014927339107158436, 'samples': 18343104, 'steps': 95536, 'loss/train': 1.5254157781600952}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:13 - INFO - __main__ - Step 95544: {'lr': 0.00014923939352722853, 'samples': 18344448, 'steps': 95543, 'loss/train': 1.8573557138442993}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:15 - INFO - __main__ - Step 95548: {'lr': 0.00014921996735780285, 'samples': 18345216, 'steps': 95547, 'loss/train': 1.75882887840271}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:18 - INFO - __main__ - Step 95553: {'lr': 0.00014919568566776055, 'samples': 18346176, 'steps': 95552, 'loss/train': 0.9557512998580933}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:20 - INFO - __main__ - Step 95558: {'lr': 0.00014917140511324002, 'samples': 18347136, 'steps': 95557, 'loss/train': 1.3114339113235474}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:20 - INFO - __main__ - Step 95558: {'lr': 0.00014917140511324002, 'samples': 18347136, 'steps': 95557, 'loss/train': 1.3114339113235474}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:24 - INFO - __main__ - Step 95565: {'lr': 0.0001491374142451084, 'samples': 18348480, 'steps': 95564, 'loss/train': 1.3055469989776611}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:26 - INFO - __main__ - Step 95569: {'lr': 0.00014911799189167897, 'samples': 18349248, 'steps': 95568, 'loss/train': 1.3722277879714966}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:28 - INFO - __main__ - Step 95574: {'lr': 0.00014909371497266583, 'samples': 18350208, 'steps': 95573, 'loss/train': 1.5147273540496826}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:30 - INFO - __main__ - Step 95578: {'lr': 0.00014907429425584483, 'samples': 18350976, 'steps': 95577, 'loss/train': 1.5990585088729858}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:33 - INFO - __main__ - Step 95582: {'lr': 0.00014905487426663283, 'samples': 18351744, 'steps': 95581, 'loss/train': 0.9072967767715454}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:34 - INFO - __main__ - Step 95586: {'lr': 0.00014903545500517004, 'samples': 18352512, 'steps': 95585, 'loss/train': 1.276658296585083}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:36 - INFO - __main__ - Step 95590: {'lr': 0.00014901603647159617, 'samples': 18353280, 'steps': 95589, 'loss/train': 1.3307369947433472}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:39 - INFO - __main__ - Step 95595: {'lr': 0.0001489917643284361, 'samples': 18354240, 'steps': 95594, 'loss/train': 1.3917579650878906}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:41 - INFO - __main__ - Step 95599: {'lr': 0.0001489723474331246, 'samples': 18355008, 'steps': 95598, 'loss/train': 1.0463882684707642}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:41 - INFO - __main__ - Step 95599: {'lr': 0.0001489723474331246, 'samples': 18355008, 'steps': 95598, 'loss/train': 1.0463882684707642}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:44 - INFO - __main__ - Step 95606: {'lr': 0.00014893836961899122, 'samples': 18356352, 'steps': 95605, 'loss/train': 1.3746315240859985}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:46 - INFO - __main__ - Step 95611: {'lr': 0.0001489141011178138, 'samples': 18357312, 'steps': 95610, 'loss/train': 1.2319364547729492}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:49 - INFO - __main__ - Step 95616: {'lr': 0.00014888983375532994, 'samples': 18358272, 'steps': 95615, 'loss/train': 1.291101336479187}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:49 - INFO - __main__ - Step 95616: {'lr': 0.00014888983375532994, 'samples': 18358272, 'steps': 95615, 'loss/train': 1.291101336479187}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:53 - INFO - __main__ - Step 95623: {'lr': 0.00014885586136137842, 'samples': 18359616, 'steps': 95622, 'loss/train': 1.0204899311065674}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:54 - INFO - __main__ - Step 95627: {'lr': 0.00014883644956741428, 'samples': 18360384, 'steps': 95626, 'loss/train': 1.0448057651519775}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:56 - INFO - __main__ - Step 95631: {'lr': 0.00014881703850277392, 'samples': 18361152, 'steps': 95630, 'loss/train': 0.7172181010246277}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:40:59 - INFO - __main__ - Step 95636: {'lr': 0.0001487927756977982, 'samples': 18362112, 'steps': 95635, 'loss/train': 1.2419612407684326}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:01 - INFO - __main__ - Step 95640: {'lr': 0.000148773366274648, 'samples': 18362880, 'steps': 95639, 'loss/train': 1.3674647808074951}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:01 - INFO - __main__ - Step 95640: {'lr': 0.000148773366274648, 'samples': 18362880, 'steps': 95639, 'loss/train': 1.3674647808074951}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:04 - INFO - __main__ - Step 95647: {'lr': 0.00014873940154024883, 'samples': 18364224, 'steps': 95646, 'loss/train': 1.4438670873641968}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:06 - INFO - __main__ - Step 95652: {'lr': 0.0001487151423844282, 'samples': 18365184, 'steps': 95651, 'loss/train': 1.6687921285629272}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:09 - INFO - __main__ - Step 95657: {'lr': 0.00014869088436954243, 'samples': 18366144, 'steps': 95656, 'loss/train': 1.4171829223632812}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:11 - INFO - __main__ - Step 95661: {'lr': 0.00014867147877929048, 'samples': 18366912, 'steps': 95660, 'loss/train': 0.589092493057251}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:13 - INFO - __main__ - Step 95665: {'lr': 0.0001486520739195517, 'samples': 18367680, 'steps': 95664, 'loss/train': 1.4718431234359741}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:14 - INFO - __main__ - Step 95669: {'lr': 0.00014863266979046582, 'samples': 18368448, 'steps': 95668, 'loss/train': 1.4787884950637817}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:16 - INFO - __main__ - Step 95673: {'lr': 0.00014861326639217283, 'samples': 18369216, 'steps': 95672, 'loss/train': 1.7338563203811646}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:19 - INFO - __main__ - Step 95678: {'lr': 0.00014858901317219727, 'samples': 18370176, 'steps': 95677, 'loss/train': 1.6475002765655518}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:19 - INFO - __main__ - Step 95678: {'lr': 0.00014858901317219727, 'samples': 18370176, 'steps': 95677, 'loss/train': 1.6475002765655518}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:22 - INFO - __main__ - Step 95685: {'lr': 0.00014855506058345002, 'samples': 18371520, 'steps': 95684, 'loss/train': 1.110032081604004}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:24 - INFO - __main__ - Step 95689: {'lr': 0.00014853566010972736, 'samples': 18372288, 'steps': 95688, 'loss/train': 1.6964635848999023}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:24 - INFO - __main__ - Step 95689: {'lr': 0.00014853566010972736, 'samples': 18372288, 'steps': 95688, 'loss/train': 1.6964635848999023}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:28 - INFO - __main__ - Step 95697: {'lr': 0.0001484968613568987, 'samples': 18373824, 'steps': 95696, 'loss/train': 1.4586480855941772}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:30 - INFO - __main__ - Step 95701: {'lr': 0.00014847746307807233, 'samples': 18374592, 'steps': 95700, 'loss/train': 1.82334566116333}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:32 - INFO - __main__ - Step 95705: {'lr': 0.0001484580655311579, 'samples': 18375360, 'steps': 95704, 'loss/train': 1.3272370100021362}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:34 - INFO - __main__ - Step 95710: {'lr': 0.00014843381962697876, 'samples': 18376320, 'steps': 95709, 'loss/train': 1.8865585327148438}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:34 - INFO - __main__ - Step 95710: {'lr': 0.00014843381962697876, 'samples': 18376320, 'steps': 95709, 'loss/train': 1.8865585327148438}}█████���█████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:38 - INFO - __main__ - Step 95718: {'lr': 0.00014839502856014183, 'samples': 18377856, 'steps': 95717, 'loss/train': 1.0019372701644897}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:40 - INFO - __main__ - Step 95722: {'lr': 0.0001483756341254126, 'samples': 18378624, 'steps': 95721, 'loss/train': 0.983285129070282}7}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:42 - INFO - __main__ - Step 95726: {'lr': 0.0001483562404233293, 'samples': 18379392, 'steps': 95725, 'loss/train': 0.8506258130073547}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:44 - INFO - __main__ - Step 95730: {'lr': 0.0001483368474540317, 'samples': 18380160, 'steps': 95729, 'loss/train': 1.3336783647537231}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:47 - INFO - __main__ - Step 95736: {'lr': 0.0001483077593743646, 'samples': 18381312, 'steps': 95735, 'loss/train': 1.4947596788406372}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:49 - INFO - __main__ - Step 95740: {'lr': 0.00014828836823764307, 'samples': 18382080, 'steps': 95739, 'loss/train': 1.609140157699585}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:51 - INFO - __main__ - Step 95744: {'lr': 0.00014826897783419663, 'samples': 18382848, 'steps': 95743, 'loss/train': 1.5257748365402222}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:51 - INFO - __main__ - Step 95744: {'lr': 0.00014826897783419663, 'samples': 18382848, 'steps': 95743, 'loss/train': 1.5257748365402222}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:54 - INFO - __main__ - Step 95751: {'lr': 0.00014823504639302905, 'samples': 18384192, 'steps': 95750, 'loss/train': 0.904188871383667}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:56 - INFO - __main__ - Step 95756: {'lr': 0.00014821081102490575, 'samples': 18385152, 'steps': 95755, 'loss/train': 1.2824580669403076}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:41:59 - INFO - __main__ - Step 95761: {'lr': 0.0001481865768033984, 'samples': 18386112, 'steps': 95760, 'loss/train': 1.356045126914978}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:01 - INFO - __main__ - Step 95765: {'lr': 0.00014816719025193939, 'samples': 18386880, 'steps': 95764, 'loss/train': 1.121256709098816}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:01 - INFO - __main__ - Step 95765: {'lr': 0.00014816719025193939, 'samples': 18386880, 'steps': 95764, 'loss/train': 1.121256709098816}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:04 - INFO - __main__ - Step 95772: {'lr': 0.0001481332655535156, 'samples': 18388224, 'steps': 95771, 'loss/train': 0.7719798684120178}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:06 - INFO - __main__ - Step 95777: {'lr': 0.00014810903500301365, 'samples': 18389184, 'steps': 95776, 'loss/train': 2.2610867023468018}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:09 - INFO - __main__ - Step 95781: {'lr': 0.00014808965138898795, 'samples': 18389952, 'steps': 95780, 'loss/train': 1.6964213848114014}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:11 - INFO - __main__ - Step 95785: {'lr': 0.00014807026850966994, 'samples': 18390720, 'steps': 95784, 'loss/train': 1.3954168558120728}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:11 - INFO - __main__ - Step 95785: {'lr': 0.00014807026850966994, 'samples': 18390720, 'steps': 95784, 'loss/train': 1.3954168558120728}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:14 - INFO - __main__ - Step 95792: {'lr': 0.0001480363502391741, 'samples': 18392064, 'steps': 95791, 'loss/train': 1.417860984802246}8}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:17 - INFO - __main__ - Step 95798: {'lr': 0.00014800727922765016, 'samples': 18393216, 'steps': 95797, 'loss/train': 1.5577119588851929}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:19 - INFO - __main__ - Step 95802: {'lr': 0.00014798789947239878, 'samples': 18393984, 'steps': 95801, 'loss/train': 1.4650177955627441}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:21 - INFO - __main__ - Step 95806: {'lr': 0.00014796852045258855, 'samples': 18394752, 'steps': 95805, 'loss/train': 1.83645761013031}1}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:22 - INFO - __main__ - Step 95810: {'lr': 0.00014794914216835928, 'samples': 18395520, 'steps': 95809, 'loss/train': 1.6357002258300781}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:24 - INFO - __main__ - Step 95814: {'lr': 0.0001479297646198508, 'samples': 18396288, 'steps': 95813, 'loss/train': 1.8967548608779907}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:27 - INFO - __main__ - Step 95819: {'lr': 0.00014790554371903503, 'samples': 18397248, 'steps': 95818, 'loss/train': 1.1559598445892334}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:29 - INFO - __main__ - Step 95823: {'lr': 0.00014788616782640874, 'samples': 18398016, 'steps': 95822, 'loss/train': 1.1957985162734985}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:31 - INFO - __main__ - Step 95827: {'lr': 0.00014786679266995718, 'samples': 18398784, 'steps': 95826, 'loss/train': 1.405630111694336}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:33 - INFO - __main__ - Step 95831: {'lr': 0.00014784741824981986, 'samples': 18399552, 'steps': 95830, 'loss/train': 0.9945093393325806}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:34 - INFO - __main__ - Step 95835: {'lr': 0.0001478280445661366, 'samples': 18400320, 'steps': 95834, 'loss/train': 1.0128921270370483}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:37 - INFO - __main__ - Step 95840: {'lr': 0.00014780382849738388, 'samples': 18401280, 'steps': 95839, 'loss/train': 0.7286389470100403}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:39 - INFO - __main__ - Step 95845: {'lr': 0.00014777961357983148, 'samples': 18402240, 'steps': 95844, 'loss/train': 1.4416714906692505}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:39 - INFO - __main__ - Step 95845: {'lr': 0.00014777961357983148, 'samples': 18402240, 'steps': 95844, 'loss/train': 1.4416714906692505}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:43 - INFO - __main__ - Step 95852: {'lr': 0.0001477457146297943, 'samples': 18403584, 'steps': 95851, 'loss/train': 1.620156168937683}5}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:45 - INFO - __main__ - Step 95856: {'lr': 0.00014772634481478617, 'samples': 18404352, 'steps': 95855, 'loss/train': 1.2434630393981934}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:47 - INFO - __main__ - Step 95861: {'lr': 0.00014770213358290818, 'samples': 18405312, 'steps': 95860, 'loss/train': 1.4640074968338013}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:49 - INFO - __main__ - Step 95866: {'lr': 0.0001476779235033763, 'samples': 18406272, 'steps': 95865, 'loss/train': 1.355322003364563}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:49 - INFO - __main__ - Step 95866: {'lr': 0.0001476779235033763, 'samples': 18406272, 'steps': 95865, 'loss/train': 1.355322003364563}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:52 - INFO - __main__ - Step 95871: {'lr': 0.00014765371457646303, 'samples': 18407232, 'steps': 95870, 'loss/train': 1.172415018081665}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:54 - INFO - __main__ - Step 95876: {'lr': 0.0001476295068024412, 'samples': 18408192, 'steps': 95875, 'loss/train': 1.4255061149597168}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:54 - INFO - __main__ - Step 95876: {'lr': 0.0001476295068024412, 'samples': 18408192, 'steps': 95875, 'loss/train': 1.4255061149597168}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:42:54 - INFO - __main__ - Step 95876: {'lr': 0.0001476295068024412, 'samples': 18408192, 'steps': 95875, 'loss/train': 1.4255061149597168}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:00 - INFO - __main__ - Step 95887: {'lr': 0.00014757625375911486, 'samples': 18410304, 'steps': 95886, 'loss/train': 1.584752082824707}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:03 - INFO - __main__ - Step 95892: {'lr': 0.00014755204967617803, 'samples': 18411264, 'steps': 95891, 'loss/train': 1.6102244853973389}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:05 - INFO - __main__ - Step 95896: {'lr': 0.00014753268724072187, 'samples': 18412032, 'steps': 95895, 'loss/train': 0.7942976355552673}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:07 - INFO - __main__ - Step 95900: {'lr': 0.0001475133255439887, 'samples': 18412800, 'steps': 95899, 'loss/train': 1.393396258354187}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:08 - INFO - __main__ - Step 95904: {'lr': 0.00014749396458611818, 'samples': 18413568, 'steps': 95903, 'loss/train': 0.9633151292800903}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:11 - INFO - __main__ - Step 95909: {'lr': 0.0001474697644280183, 'samples': 18414528, 'steps': 95908, 'loss/train': 1.4275400638580322}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:11 - INFO - __main__ - Step 95909: {'lr': 0.0001474697644280183, 'samples': 18414528, 'steps': 95908, 'loss/train': 1.4275400638580322}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:14 - INFO - __main__ - Step 95916: {'lr': 0.0001474358861470782, 'samples': 18415872, 'steps': 95915, 'loss/train': 1.6526955366134644}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:16 - INFO - __main__ - Step 95920: {'lr': 0.00014741652814605395, 'samples': 18416640, 'steps': 95919, 'loss/train': 1.6642521619796753}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:19 - INFO - __main__ - Step 95925: {'lr': 0.00014739233168479688, 'samples': 18417600, 'steps': 95924, 'loss/train': 1.5035039186477661}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:21 - INFO - __main__ - Step 95930: {'lr': 0.00014736813637937558, 'samples': 18418560, 'steps': 95929, 'loss/train': 1.6854907274246216}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:21 - INFO - __main__ - Step 95930: {'lr': 0.00014736813637937558, 'samples': 18418560, 'steps': 95929, 'loss/train': 1.6854907274246216}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:24 - INFO - __main__ - Step 95937: {'lr': 0.00014733426489410895, 'samples': 18419904, 'steps': 95936, 'loss/train': 2.0713539123535156}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:26 - INFO - __main__ - Step 95941: {'lr': 0.00014731491077733396, 'samples': 18420672, 'steps': 95940, 'loss/train': 1.3995044231414795}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:29 - INFO - __main__ - Step 95946: {'lr': 0.00014729071917241865, 'samples': 18421632, 'steps': 95945, 'loss/train': 0.3697997033596039}}██████████��████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:31 - INFO - __main__ - Step 95950: {'lr': 0.00014727136672149937, 'samples': 18422400, 'steps': 95949, 'loss/train': 1.6321163177490234}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:31 - INFO - __main__ - Step 95950: {'lr': 0.00014727136672149937, 'samples': 18422400, 'steps': 95949, 'loss/train': 1.6321163177490234}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:34 - INFO - __main__ - Step 95958: {'lr': 0.00014723266404162105, 'samples': 18423936, 'steps': 95957, 'loss/train': 1.0707542896270752}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:36 - INFO - __main__ - Step 95962: {'lr': 0.00014721331381294128, 'samples': 18424704, 'steps': 95961, 'loss/train': 1.279589056968689}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:39 - INFO - __main__ - Step 95967: {'lr': 0.00014718912706917491, 'samples': 18425664, 'steps': 95966, 'loss/train': 1.4224027395248413}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:39 - INFO - __main__ - Step 95967: {'lr': 0.00014718912706917491, 'samples': 18425664, 'steps': 95966, 'loss/train': 1.4224027395248413}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:43 - INFO - __main__ - Step 95975: {'lr': 0.00014715043068816176, 'samples': 18427200, 'steps': 95974, 'loss/train': 1.4127840995788574}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:45 - INFO - __main__ - Step 95979: {'lr': 0.0001471310836098037, 'samples': 18427968, 'steps': 95978, 'loss/train': 1.664720058441162}4}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:47 - INFO - __main__ - Step 95983: {'lr': 0.00014711173727306395, 'samples': 18428736, 'steps': 95982, 'loss/train': 1.3149206638336182}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:49 - INFO - __main__ - Step 95988: {'lr': 0.00014708755539525267, 'samples': 18429696, 'steps': 95987, 'loss/train': 1.3944432735443115}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:51 - INFO - __main__ - Step 95992: {'lr': 0.00014706821072766417, 'samples': 18430464, 'steps': 95991, 'loss/train': 0.5841900110244751}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:53 - INFO - __main__ - Step 95996: {'lr': 0.00014704886680214725, 'samples': 18431232, 'steps': 95995, 'loss/train': 1.4283671379089355}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:55 - INFO - __main__ - Step 96000: {'lr': 0.00014702952361884142, 'samples': 18432000, 'steps': 95999, 'loss/train': 1.7424241304397583}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:57 - INFO - __main__ - Step 96004: {'lr': 0.00014701018117788621, 'samples': 18432768, 'steps': 96003, 'loss/train': 1.480239748954773}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:43:57 - INFO - __main__ - Step 96004: {'lr': 0.00014701018117788621, 'samples': 18432768, 'steps': 96003, 'loss/train': 1.480239748954773}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:01 - INFO - __main__ - Step 96012: {'lr': 0.00014697149852358493, 'samples': 18434304, 'steps': 96011, 'loss/train': 1.0800424814224243}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:03 - INFO - __main__ - Step 96016: {'lr': 0.00014695215831051796, 'samples': 18435072, 'steps': 96015, 'loss/train': 1.4355316162109375}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:05 - INFO - __main__ - Step 96020: {'lr': 0.00014693281884035916, 'samples': 18435840, 'steps': 96019, 'loss/train': 1.0565481185913086}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:07 - INFO - __main__ - Step 96024: {'lr': 0.00014691348011324808, 'samples': 18436608, 'steps': 96023, 'loss/train': 1.0712916851043701}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:07 - INFO - __main__ - Step 96024: {'lr': 0.00014691348011324808, 'samples': 18436608, 'steps': 96023, 'loss/train': 1.0712916851043701}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:11 - INFO - __main__ - Step 96033: {'lr': 0.00014686997069473848, 'samples': 18438336, 'steps': 96032, 'loss/train': 1.5001444816589355}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:13 - INFO - __main__ - Step 96037: {'lr': 0.0001468506343834953, 'samples': 18439104, 'steps': 96036, 'loss/train': 1.5722757577896118}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:15 - INFO - __main__ - Step 96041: {'lr': 0.00014683129881589232, 'samples': 18439872, 'steps': 96040, 'loss/train': 1.2319341897964478}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:17 - INFO - __main__ - Step 96046: {'lr': 0.00014680713040234495, 'samples': 18440832, 'steps': 96045, 'loss/train': 1.371938943862915}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:17 - INFO - __main__ - Step 96046: {'lr': 0.00014680713040234495, 'samples': 18440832, 'steps': 96045, 'loss/train': 1.371938943862915}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:22 - INFO - __main__ - Step 96054: {'lr': 0.00014676846335863242, 'samples': 18442368, 'steps': 96053, 'loss/train': 0.6500841379165649}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:23 - INFO - __main__ - Step 96058: {'lr': 0.00014674913095305537, 'samples': 18443136, 'steps': 96057, 'loss/train': 1.2305554151535034}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:25 - INFO - __main__ - Step 96062: {'lr': 0.00014672979929185022, 'samples': 18443904, 'steps': 96061, 'loss/train': 1.6453698873519897}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:27 - INFO - __main__ - Step 96067: {'lr': 0.00014670563576232921, 'samples': 18444864, 'steps': 96066, 'loss/train': 1.1386008262634277}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:30 - INFO - __main__ - Step 96071: {'lr': 0.0001466863057764707, 'samples': 18445632, 'steps': 96070, 'loss/train': 1.1898099184036255}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:32 - INFO - __main__ - Step 96075: {'lr': 0.00014666697653543693, 'samples': 18446400, 'steps': 96074, 'loss/train': 1.280398964881897}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:33 - INFO - __main__ - Step 96079: {'lr': 0.00014664764803936747, 'samples': 18447168, 'steps': 96078, 'loss/train': 1.2547533512115479}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:35 - INFO - __main__ - Step 96083: {'lr': 0.00014662832028840167, 'samples': 18447936, 'steps': 96082, 'loss/train': 1.0855945348739624}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:37 - INFO - __main__ - Step 96087: {'lr': 0.00014660899328267874, 'samples': 18448704, 'steps': 96086, 'loss/train': 1.0705841779708862}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:39 - INFO - __main__ - Step 96091: {'lr': 0.00014658966702233808, 'samples': 18449472, 'steps': 96090, 'loss/train': 1.4681605100631714}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:39 - INFO - __main__ - Step 96091: {'lr': 0.00014658966702233808, 'samples': 18449472, 'steps': 96090, 'loss/train': 1.4681605100631714}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:43 - INFO - __main__ - Step 96098: {'lr': 0.0001465558478607372, 'samples': 18450816, 'steps': 96097, 'loss/train': 1.2374827861785889}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:45 - INFO - __main__ - Step 96103: {'lr': 0.0001465316927150031, 'samples': 18451776, 'steps': 96102, 'loss/train': 1.551200032234192}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:45 - INFO - __main__ - Step 96103: {'lr': 0.0001465316927150031, 'samples': 18451776, 'steps': 96102, 'loss/train': 1.551200032234192}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:49 - INFO - __main__ - Step 96111: {'lr': 0.00014649304690624544, 'samples': 18453312, 'steps': 96110, 'loss/train': 2.082451105117798}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:51 - INFO - __main__ - Step 96115: {'lr': 0.00014647372512112416, 'samples': 18454080, 'steps': 96114, 'loss/train': 1.6154382228851318}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:53 - INFO - __main__ - Step 96119: {'lr': 0.00014645440408236036, 'samples': 18454848, 'steps': 96118, 'loss/train': 1.4549554586410522}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:53 - INFO - __main__ - Step 96119: {'lr': 0.00014645440408236036, 'samples': 18454848, 'steps': 96118, 'loss/train': 1.4549554586410522}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:57 - INFO - __main__ - Step 96128: {'lr': 0.00014641093447473287, 'samples': 18456576, 'steps': 96127, 'loss/train': 1.3540596961975098}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:44:59 - INFO - __main__ - Step 96132: {'lr': 0.0001463916158625928, 'samples': 18457344, 'steps': 96131, 'loss/train': 1.2378544807434082}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:01 - INFO - __main__ - Step 96136: {'lr': 0.00014637229799740225, 'samples': 18458112, 'steps': 96135, 'loss/train': 0.9263071417808533}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:03 - INFO - __main__ - Step 96140: {'lr': 0.00014635298087930032, 'samples': 18458880, 'steps': 96139, 'loss/train': 1.0975141525268555}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:05 - INFO - __main__ - Step 96145: {'lr': 0.00014632883553247853, 'samples': 18459840, 'steps': 96144, 'loss/train': 1.6013127565383911}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:05 - INFO - __main__ - Step 96145: {'lr': 0.00014632883553247853, 'samples': 18459840, 'steps': 96144, 'loss/train': 1.6013127565383911}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:09 - INFO - __main__ - Step 96152: {'lr': 0.00014629503400891936, 'samples': 18461184, 'steps': 96151, 'loss/train': 1.4621576070785522}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:11 - INFO - __main__ - Step 96156: {'lr': 0.0001462757198805648, 'samples': 18461952, 'steps': 96155, 'loss/train': 1.4500706195831299}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:13 - INFO - __main__ - Step 96161: {'lr': 0.00014625157827171054, 'samples': 18462912, 'steps': 96160, 'loss/train': 1.5194412469863892}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:16 - INFO - __main__ - Step 96166: {'lr': 0.0001462274378315422, 'samples': 18463872, 'steps': 96165, 'loss/train': 1.6049919128417969}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:18 - INFO - __main__ - Step 96170: {'lr': 0.0001462081263210442, 'samples': 18464640, 'steps': 96169, 'loss/train': 1.5447665452957153}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:18 - INFO - __main__ - Step 96170: {'lr': 0.0001462081263210442, 'samples': 18464640, 'steps': 96169, 'loss/train': 1.5447665452957153}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:21 - INFO - __main__ - Step 96177: {'lr': 0.0001461743329782865, 'samples': 18465984, 'steps': 96176, 'loss/train': 1.5767723321914673}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:23 - INFO - __main__ - Step 96182: {'lr': 0.00014615019627974054, 'samples': 18466944, 'steps': 96181, 'loss/train': 1.8655766248703003}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:26 - INFO - __main__ - Step 96187: {'lr': 0.00014612606075102252, 'samples': 18467904, 'steps': 96186, 'loss/train': 1.1208040714263916}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:28 - INFO - __main__ - Step 96191: {'lr': 0.000146106753170507, 'samples': 18468672, 'steps': 96190, 'loss/train': 1.2850171327590942}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:30 - INFO - __main__ - Step 96195: {'lr': 0.00014608744633899453, 'samples': 18469440, 'steps': 96194, 'loss/train': 1.4665364027023315}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:31 - INFO - __main__ - Step 96199: {'lr': 0.00014606814025662436, 'samples': 18470208, 'steps': 96198, 'loss/train': 1.3654154539108276}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:33 - INFO - __main__ - Step 96203: {'lr': 0.0001460488349235357, 'samples': 18470976, 'steps': 96202, 'loss/train': 1.2764419317245483}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:36 - INFO - __main__ - Step 96208: {'lr': 0.00014602470431106392, 'samples': 18471936, 'steps': 96207, 'loss/train': 1.2818728685379028}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:38 - INFO - __main__ - Step 96212: {'lr': 0.0001460054006643674, 'samples': 18472704, 'steps': 96211, 'loss/train': 1.2870274782180786}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:40 - INFO - __main__ - Step 96216: {'lr': 0.00014598609776740474, 'samples': 18473472, 'steps': 96215, 'loss/train': 1.0942540168762207}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:42 - INFO - __main__ - Step 96220: {'lr': 0.00014596679562031494, 'samples': 18474240, 'steps': 96219, 'loss/train': 1.4533721208572388}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:43 - INFO - __main__ - Step 96224: {'lr': 0.0001459474942232372, 'samples': 18475008, 'steps': 96223, 'loss/train': 1.2750760316848755}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:46 - INFO - __main__ - Step 96229: {'lr': 0.00014592336853180672, 'samples': 18475968, 'steps': 96228, 'loss/train': 1.5285817384719849}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:48 - INFO - __main__ - Step 96233: {'lr': 0.00014590406882276504, 'samples': 18476736, 'steps': 96232, 'loss/train': 0.3990049660205841}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:50 - INFO - __main__ - Step 96237: {'lr': 0.00014588476986418774, 'samples': 18477504, 'steps': 96236, 'loss/train': 1.7053589820861816}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:50 - INFO - __main__ - Step 96237: {'lr': 0.00014588476986418774, 'samples': 18477504, 'steps': 96236, 'loss/train': 1.7053589820861816}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:53 - INFO - __main__ - Step 96244: {'lr': 0.0001458509984929006, 'samples': 18478848, 'steps': 96243, 'loss/train': 1.3658525943756104}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:55 - INFO - __main__ - Step 96249: {'lr': 0.00014582687749263297, 'samples': 18479808, 'steps': 96248, 'loss/train': 1.093275547027588}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:45:58 - INFO - __main__ - Step 96254: {'lr': 0.0001458027576658353, 'samples': 18480768, 'steps': 96253, 'loss/train': 1.2880525588989258}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:00 - INFO - __main__ - Step 96258: {'lr': 0.0001457834626494781, 'samples': 18481536, 'steps': 96257, 'loss/train': 1.4969325065612793}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:00 - INFO - __main__ - Step 96258: {'lr': 0.0001457834626494781, 'samples': 18481536, 'steps': 96257, 'loss/train': 1.4969325065612793}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:04 - INFO - __main__ - Step 96265: {'lr': 0.0001457496981788339, 'samples': 18482880, 'steps': 96264, 'loss/train': 1.7321319580078125}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:04 - INFO - __main__ - Step 96265: {'lr': 0.0001457496981788339, 'samples': 18482880, 'steps': 96264, 'loss/train': 1.7321319580078125}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:08 - INFO - __main__ - Step 96273: {'lr': 0.00014571111303084144, 'samples': 18484416, 'steps': 96272, 'loss/train': 1.5881953239440918}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:09 - INFO - __main__ - Step 96277: {'lr': 0.00014569182158455873, 'samples': 18485184, 'steps': 96276, 'loss/train': 1.3215045928955078}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:12 - INFO - __main__ - Step 96282: {'lr': 0.0001456677083342139, 'samples': 18486144, 'steps': 96281, 'loss/train': 0.871557354927063}8}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:12 - INFO - __main__ - Step 96282: {'lr': 0.0001456677083342139, 'samples': 18486144, 'steps': 96281, 'loss/train': 0.871557354927063}8}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:16 - INFO - __main__ - Step 96290: {'lr': 0.0001456291295783223, 'samples': 18487680, 'steps': 96289, 'loss/train': 1.4549400806427002}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:17 - INFO - __main__ - Step 96294: {'lr': 0.00014560984132897664, 'samples': 18488448, 'steps': 96293, 'loss/train': 1.322605013847351}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:19 - INFO - __main__ - Step 96298: {'lr': 0.0001455905538322166, 'samples': 18489216, 'steps': 96297, 'loss/train': 1.7116316556930542}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:22 - INFO - __main__ - Step 96303: {'lr': 0.00014556644551980157, 'samples': 18490176, 'steps': 96302, 'loss/train': 1.07626211643219}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:22 - INFO - __main__ - Step 96303: {'lr': 0.00014556644551980157, 'samples': 18490176, 'steps': 96302, 'loss/train': 1.07626211643219}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:26 - INFO - __main__ - Step 96311: {'lr': 0.00014552787466697037, 'samples': 18491712, 'steps': 96310, 'loss/train': 1.1667556762695312}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:28 - INFO - __main__ - Step 96315: {'lr': 0.00014550859037024981, 'samples': 18492480, 'steps': 96314, 'loss/train': 1.8108196258544922}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:30 - INFO - __main__ - Step 96319: {'lr': 0.0001454893068268448, 'samples': 18493248, 'steps': 96318, 'loss/train': 1.1436582803726196}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:32 - INFO - __main__ - Step 96324: {'lr': 0.00014546520345715025, 'samples': 18494208, 'steps': 96323, 'loss/train': 0.3155548572540283}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:32 - INFO - __main__ - Step 96324: {'lr': 0.00014546520345715025, 'samples': 18494208, 'steps': 96323, 'loss/train': 0.3155548572540283}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:36 - INFO - __main__ - Step 96332: {'lr': 0.0001454266405150436, 'samples': 18495744, 'steps': 96331, 'loss/train': 1.4001131057739258}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:38 - INFO - __main__ - Step 96336: {'lr': 0.0001454073601747802, 'samples': 18496512, 'steps': 96335, 'loss/train': 1.6396219730377197}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:40 - INFO - __main__ - Step 96340: {'lr': 0.00014538808058856217, 'samples': 18497280, 'steps': 96339, 'loss/train': 1.4284024238586426}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:42 - INFO - __main__ - Step 96345: {'lr': 0.0001453639821663774, 'samples': 18498240, 'steps': 96344, 'loss/train': 1.8024448156356812}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:42 - INFO - __main__ - Step 96345: {'lr': 0.0001453639821663774, 'samples': 18498240, 'steps': 96344, 'loss/train': 1.8024448156356812}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:46 - INFO - __main__ - Step 96352: {'lr': 0.0001453302463555694, 'samples': 18499584, 'steps': 96351, 'loss/train': 1.7225089073181152}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:48 - INFO - __main__ - Step 96357: {'lr': 0.00014530615076268317, 'samples': 18500544, 'steps': 96356, 'loss/train': 0.9900149703025818}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:50 - INFO - __main__ - Step 96361: {'lr': 0.00014528687513748294, 'samples': 18501312, 'steps': 96360, 'loss/train': 1.5378637313842773}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:50 - INFO - __main__ - Step 96361: {'lr': 0.00014528687513748294, 'samples': 18501312, 'steps': 96360, 'loss/train': 1.5378637313842773}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:54 - INFO - __main__ - Step 96368: {'lr': 0.00014525314460997777, 'samples': 18502656, 'steps': 96367, 'loss/train': 1.2456773519515991}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:56 - INFO - __main__ - Step 96373: {'lr': 0.00014522905279192152, 'samples': 18503616, 'steps': 96372, 'loss/train': 1.7625523805618286}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:46:58 - INFO - __main__ - Step 96378: {'lr': 0.0001452049621540697, 'samples': 18504576, 'steps': 96377, 'loss/train': 0.11105266213417053}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:01 - INFO - __main__ - Step 96382: {'lr': 0.00014518569049371758, 'samples': 18505344, 'steps': 96381, 'loss/train': 1.0839040279388428}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:01 - INFO - __main__ - Step 96382: {'lr': 0.00014518569049371758, 'samples': 18505344, 'steps': 96381, 'loss/train': 1.0839040279388428}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:04 - INFO - __main__ - Step 96389: {'lr': 0.00014515196690645182, 'samples': 18506688, 'steps': 96388, 'loss/train': 1.3755689859390259}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:06 - INFO - __main__ - Step 96393: {'lr': 0.00014513269732445338, 'samples': 18507456, 'steps': 96392, 'loss/train': 1.420705795288086}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:08 - INFO - __main__ - Step 96398: {'lr': 0.00014510861141013226, 'samples': 18508416, 'steps': 96397, 'loss/train': 1.4836173057556152}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:08 - INFO - __main__ - Step 96398: {'lr': 0.00014510861141013226, 'samples': 18508416, 'steps': 96397, 'loss/train': 1.4836173057556152}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:11 - INFO - __main__ - Step 96405: {'lr': 0.00014507489311516602, 'samples': 18509760, 'steps': 96404, 'loss/train': 1.4406756162643433}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:14 - INFO - __main__ - Step 96409: {'lr': 0.00014505562655810263, 'samples': 18510528, 'steps': 96408, 'loss/train': 1.3778939247131348}}█████████████████████���█████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:16 - INFO - __main__ - Step 96414: {'lr': 0.00014503154442573174, 'samples': 18511488, 'steps': 96413, 'loss/train': 1.086053490638733}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:16 - INFO - __main__ - Step 96414: {'lr': 0.00014503154442573174, 'samples': 18511488, 'steps': 96413, 'loss/train': 1.086053490638733}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:20 - INFO - __main__ - Step 96422: {'lr': 0.0001449930154735039, 'samples': 18513024, 'steps': 96421, 'loss/train': 1.118165135383606}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:22 - INFO - __main__ - Step 96426: {'lr': 0.00014497375213286912, 'samples': 18513792, 'steps': 96425, 'loss/train': 1.3332282304763794}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:24 - INFO - __main__ - Step 96430: {'lr': 0.00014495448954940566, 'samples': 18514560, 'steps': 96429, 'loss/train': 1.3700796365737915}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:26 - INFO - __main__ - Step 96435: {'lr': 0.00014493041238506016, 'samples': 18515520, 'steps': 96434, 'loss/train': 1.2395097017288208}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:26 - INFO - __main__ - Step 96435: {'lr': 0.00014493041238506016, 'samples': 18515520, 'steps': 96434, 'loss/train': 1.2395097017288208}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:30 - INFO - __main__ - Step 96442: {'lr': 0.0001448967063434319, 'samples': 18516864, 'steps': 96441, 'loss/train': 0.872055172920227}8}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:32 - INFO - __main__ - Step 96446: {'lr': 0.00014487744679004242, 'samples': 18517632, 'steps': 96445, 'loss/train': 1.5027961730957031}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:34 - INFO - __main__ - Step 96450: {'lr': 0.00014485818799451843, 'samples': 18518400, 'steps': 96449, 'loss/train': 1.3119237422943115}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:36 - INFO - __main__ - Step 96455: {'lr': 0.00014483411556607352, 'samples': 18519360, 'steps': 96454, 'loss/train': 1.1237283945083618}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:36 - INFO - __main__ - Step 96455: {'lr': 0.00014483411556607352, 'samples': 18519360, 'steps': 96454, 'loss/train': 1.1237283945083618}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:40 - INFO - __main__ - Step 96463: {'lr': 0.00014479560214475295, 'samples': 18520896, 'steps': 96462, 'loss/train': 1.565994143486023}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:42 - INFO - __main__ - Step 96467: {'lr': 0.00014477634657170671, 'samples': 18521664, 'steps': 96466, 'loss/train': 1.098114252090454}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:44 - INFO - __main__ - Step 96471: {'lr': 0.00014475709175725506, 'samples': 18522432, 'steps': 96470, 'loss/train': 1.3728322982788086}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:46 - INFO - __main__ - Step 96476: {'lr': 0.00014473302430617523, 'samples': 18523392, 'steps': 96475, 'loss/train': 1.3466750383377075}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:49 - INFO - __main__ - Step 96481: {'lr': 0.00014470895804088736, 'samples': 18524352, 'steps': 96480, 'loss/train': 1.2885632514953613}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:49 - INFO - __main__ - Step 96481: {'lr': 0.00014470895804088736, 'samples': 18524352, 'steps': 96480, 'loss/train': 1.2885632514953613}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:52 - INFO - __main__ - Step 96488: {'lr': 0.00014467526726213092, 'samples': 18525696, 'steps': 96487, 'loss/train': 1.9607264995574951}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:54 - INFO - __main__ - Step 96492: {'lr': 0.00014465601643257742, 'samples': 18526464, 'steps': 96491, 'loss/train': 1.1520638465881348}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:56 - INFO - __main__ - Step 96497: {'lr': 0.00014463195396364532, 'samples': 18527424, 'steps': 96496, 'loss/train': 1.7788581848144531}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:47:56 - INFO - __main__ - Step 96497: {'lr': 0.00014463195396364532, 'samples': 18527424, 'steps': 96496, 'loss/train': 1.7788581848144531}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:00 - INFO - __main__ - Step 96505: {'lr': 0.00014459345648228173, 'samples': 18528960, 'steps': 96504, 'loss/train': 1.0057330131530762}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:03 - INFO - __main__ - Step 96510: {'lr': 0.00014456939709993238, 'samples': 18529920, 'steps': 96509, 'loss/train': 1.2154439687728882}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:03 - INFO - __main__ - Step 96510: {'lr': 0.00014456939709993238, 'samples': 18529920, 'steps': 96509, 'loss/train': 1.2154439687728882}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:06 - INFO - __main__ - Step 96517: {'lr': 0.00014453571595993093, 'samples': 18531264, 'steps': 96516, 'loss/train': 1.5957555770874023}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:09 - INFO - __main__ - Step 96523: {'lr': 0.0001445068482646325, 'samples': 18532416, 'steps': 96522, 'loss/train': 1.4058887958526611}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:09 - INFO - __main__ - Step 96523: {'lr': 0.0001445068482646325, 'samples': 18532416, 'steps': 96522, 'loss/train': 1.4058887958526611}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:13 - INFO - __main__ - Step 96530: {'lr': 0.00014447317144959554, 'samples': 18533760, 'steps': 96529, 'loss/train': 1.3319815397262573}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:14 - INFO - __main__ - Step 96534: {'lr': 0.0001444539286013137, 'samples': 18534528, 'steps': 96533, 'loss/train': 1.2431652545928955}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:16 - INFO - __main__ - Step 96538: {'lr': 0.00014443468651395073, 'samples': 18535296, 'steps': 96537, 'loss/train': 1.7781298160552979}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:19 - INFO - __main__ - Step 96543: {'lr': 0.00014441063497500067, 'samples': 18536256, 'steps': 96542, 'loss/train': 1.4912004470825195}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:19 - INFO - __main__ - Step 96543: {'lr': 0.00014441063497500067, 'samples': 18536256, 'steps': 96542, 'loss/train': 1.4912004470825195}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:22 - INFO - __main__ - Step 96550: {'lr': 0.00014437696481876252, 'samples': 18537600, 'steps': 96549, 'loss/train': 1.6057230234146118}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:24 - INFO - __main__ - Step 96554: {'lr': 0.00014435772577646243, 'samples': 18538368, 'steps': 96553, 'loss/train': 1.7637983560562134}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:27 - INFO - __main__ - Step 96559: {'lr': 0.00014433367804462095, 'samples': 18539328, 'steps': 96558, 'loss/train': 1.507103443145752}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:29 - INFO - __main__ - Step 96564: {'lr': 0.00014430963150306982, 'samples': 18540288, 'steps': 96563, 'loss/train': 1.4633008241653442}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:29 - INFO - __main__ - Step 96564: {'lr': 0.00014430963150306982, 'samples': 18540288, 'steps': 96563, 'loss/train': 1.4633008241653442}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:32 - INFO - __main__ - Step 96571: {'lr': 0.0001442759683451019, 'samples': 18541632, 'steps': 96570, 'loss/train': 1.3706531524658203}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:34 - INFO - __main__ - Step 96575: {'lr': 0.00014425673330281435, 'samples': 18542400, 'steps': 96574, 'loss/train': 1.1373943090438843}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:37 - INFO - __main__ - Step 96580: {'lr': 0.00014423269057201266, 'samples': 18543360, 'steps': 96579, 'loss/train': 1.6503098011016846}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:39 - INFO - __main__ - Step 96584: {'lr': 0.00014421345724518637, 'samples': 18544128, 'steps': 96583, 'loss/train': 1.7390238046646118}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:39 - INFO - __main__ - Step 96584: {'lr': 0.00014421345724518637, 'samples': 18544128, 'steps': 96583, 'loss/train': 1.7390238046646118}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:42 - INFO - __main__ - Step 96591: {'lr': 0.0001441798007584564, 'samples': 18545472, 'steps': 96590, 'loss/train': 1.1804722547531128}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:44 - INFO - __main__ - Step 96596: {'lr': 0.00014415576184117741, 'samples': 18546432, 'steps': 96595, 'loss/train': 0.6861744523048401}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:44 - INFO - __main__ - Step 96596: {'lr': 0.00014415576184117741, 'samples': 18546432, 'steps': 96595, 'loss/train': 0.6861744523048401}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:48 - INFO - __main__ - Step 96603: {'lr': 0.00014412210936010206, 'samples': 18547776, 'steps': 96602, 'loss/train': 0.6712766289710999}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:50 - INFO - __main__ - Step 96607: {'lr': 0.00014410288042042137, 'samples': 18548544, 'steps': 96606, 'loss/train': 1.0163054466247559}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:52 - INFO - __main__ - Step 96612: {'lr': 0.00014407884531943778, 'samples': 18549504, 'steps': 96611, 'loss/train': 1.3018832206726074}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:55 - INFO - __main__ - Step 96617: {'lr': 0.00014405481141161513, 'samples': 18550464, 'steps': 96616, 'loss/train': 1.303456425666809}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:55 - INFO - __main__ - Step 96617: {'lr': 0.00014405481141161513, 'samples': 18550464, 'steps': 96616, 'loss/train': 1.303456425666809}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:48:59 - INFO - __main__ - Step 96624: {'lr': 0.00014402116594568944, 'samples': 18551808, 'steps': 96623, 'loss/train': 1.221198558807373}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:00 - INFO - __main__ - Step 96628: {'lr': 0.00014400194101566612, 'samples': 18552576, 'steps': 96627, 'loss/train': 0.6551637649536133}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:02 - INFO - __main__ - Step 96632: {'lr': 0.0001439827168498204, 'samples': 18553344, 'steps': 96631, 'loss/train': 1.4713139533996582}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:05 - INFO - __main__ - Step 96637: {'lr': 0.00014395868771734872, 'samples': 18554304, 'steps': 96636, 'loss/train': 1.2951135635375977}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:07 - INFO - __main__ - Step 96641: {'lr': 0.00014393946527140882, 'samples': 18555072, 'steps': 96640, 'loss/train': 1.269399881362915}}}██████████████████████████��| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:09 - INFO - __main__ - Step 96645: {'lr': 0.00014392024359009676, 'samples': 18555840, 'steps': 96644, 'loss/train': 1.6248564720153809}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:10 - INFO - __main__ - Step 96649: {'lr': 0.00014390102267355123, 'samples': 18556608, 'steps': 96648, 'loss/train': 1.6156861782073975}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:13 - INFO - __main__ - Step 96653: {'lr': 0.0001438818025219106, 'samples': 18557376, 'steps': 96652, 'loss/train': 1.2908239364624023}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:15 - INFO - __main__ - Step 96658: {'lr': 0.00014385777840821853, 'samples': 18558336, 'steps': 96657, 'loss/train': 1.4292662143707275}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:15 - INFO - __main__ - Step 96658: {'lr': 0.00014385777840821853, 'samples': 18558336, 'steps': 96657, 'loss/train': 1.4292662143707275}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:19 - INFO - __main__ - Step 96666: {'lr': 0.00014381934231337835, 'samples': 18559872, 'steps': 96665, 'loss/train': 1.1729612350463867}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:21 - INFO - __main__ - Step 96670: {'lr': 0.00014380012541412974, 'samples': 18560640, 'steps': 96669, 'loss/train': 1.635115385055542}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:23 - INFO - __main__ - Step 96674: {'lr': 0.0001437809092805136, 'samples': 18561408, 'steps': 96673, 'loss/train': 1.4085042476654053}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:23 - INFO - __main__ - Step 96674: {'lr': 0.0001437809092805136, 'samples': 18561408, 'steps': 96673, 'loss/train': 1.4085042476654053}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:27 - INFO - __main__ - Step 96682: {'lr': 0.00014374247931073244, 'samples': 18562944, 'steps': 96681, 'loss/train': 1.8492215871810913}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:29 - INFO - __main__ - Step 96686: {'lr': 0.00014372326547484472, 'samples': 18563712, 'steps': 96685, 'loss/train': 1.3370939493179321}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:30 - INFO - __main__ - Step 96690: {'lr': 0.00014370405240514333, 'samples': 18564480, 'steps': 96689, 'loss/train': 1.724951148033142}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:32 - INFO - __main__ - Step 96694: {'lr': 0.00014368484010176703, 'samples': 18565248, 'steps': 96693, 'loss/train': 1.8345168828964233}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:35 - INFO - __main__ - Step 96699: {'lr': 0.00014366082580040214, 'samples': 18566208, 'steps': 96698, 'loss/train': 1.304900884628296}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:37 - INFO - __main__ - Step 96704: {'lr': 0.0001436368126969072, 'samples': 18567168, 'steps': 96703, 'loss/train': 1.551031470298767}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:37 - INFO - __main__ - Step 96704: {'lr': 0.0001436368126969072, 'samples': 18567168, 'steps': 96703, 'loss/train': 1.551031470298767}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:40 - INFO - __main__ - Step 96711: {'lr': 0.00014360319636495033, 'samples': 18568512, 'steps': 96710, 'loss/train': 1.7546859979629517}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:42 - INFO - __main__ - Step 96715: {'lr': 0.0001435839880870527, 'samples': 18569280, 'steps': 96714, 'loss/train': 1.023710012435913}7}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:45 - INFO - __main__ - Step 96720: {'lr': 0.0001435599788185586, 'samples': 18570240, 'steps': 96719, 'loss/train': 1.4497565031051636}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:45 - INFO - __main__ - Step 96720: {'lr': 0.0001435599788185586, 'samples': 18570240, 'steps': 96719, 'loss/train': 1.4497565031051636}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:45 - INFO - __main__ - Step 96720: {'lr': 0.0001435599788185586, 'samples': 18570240, 'steps': 96719, 'loss/train': 1.4497565031051636}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:50 - INFO - __main__ - Step 96730: {'lr': 0.00014351196387885824, 'samples': 18572160, 'steps': 96729, 'loss/train': 1.74794602394104}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:53 - INFO - __main__ - Step 96736: {'lr': 0.00014348315721802906, 'samples': 18573312, 'steps': 96735, 'loss/train': 1.5310050249099731}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:53 - INFO - __main__ - Step 96736: {'lr': 0.00014348315721802906, 'samples': 18573312, 'steps': 96735, 'loss/train': 1.5310050249099731}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:56 - INFO - __main__ - Step 96743: {'lr': 0.00014344955163086008, 'samples': 18574656, 'steps': 96742, 'loss/train': 1.549575924873352}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:49:58 - INFO - __main__ - Step 96747: {'lr': 0.00014343034949436417, 'samples': 18575424, 'steps': 96746, 'loss/train': 1.339741587638855}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:01 - INFO - __main__ - Step 96752: {'lr': 0.0001434063479041799, 'samples': 18576384, 'steps': 96751, 'loss/train': 1.0633825063705444}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:03 - INFO - __main__ - Step 96757: {'lr': 0.0001433823475147321, 'samples': 18577344, 'steps': 96756, 'loss/train': 1.9466301202774048}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:03 - INFO - __main__ - Step 96757: {'lr': 0.0001433823475147321, 'samples': 18577344, 'steps': 96756, 'loss/train': 1.9466301202774048}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:07 - INFO - __main__ - Step 96764: {'lr': 0.000143348748987257, 'samples': 18578688, 'steps': 96763, 'loss/train': 1.3894469738006592}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:08 - INFO - __main__ - Step 96768: {'lr': 0.00014332955088587114, 'samples': 18579456, 'steps': 96767, 'loss/train': 1.4975244998931885}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:10 - INFO - __main__ - Step 96772: {'lr': 0.0001433103535535102, 'samples': 18580224, 'steps': 96771, 'loss/train': 1.319065809249878}5}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:13 - INFO - __main__ - Step 96778: {'lr': 0.0001432815589971934, 'samples': 18581376, 'steps': 96777, 'loss/train': 1.350236177444458}5}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:13 - INFO - __main__ - Step 96778: {'lr': 0.0001432815589971934, 'samples': 18581376, 'steps': 96777, 'loss/train': 1.350236177444458}5}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:13 - INFO - __main__ - Step 96778: {'lr': 0.0001432815589971934, 'samples': 18581376, 'steps': 96777, 'loss/train': 1.350236177444458}5}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:18 - INFO - __main__ - Step 96788: {'lr': 0.00014323357191708397, 'samples': 18583296, 'steps': 96787, 'loss/train': 2.6076812744140625}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:21 - INFO - __main__ - Step 96794: {'lr': 0.0001432047819780305, 'samples': 18584448, 'steps': 96793, 'loss/train': 0.9969381093978882}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:21 - INFO - __main__ - Step 96794: {'lr': 0.0001432047819780305, 'samples': 18584448, 'steps': 96793, 'loss/train': 0.9969381093978882}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:24 - INFO - __main__ - Step 96801: {'lr': 0.0001431711959053069, 'samples': 18585792, 'steps': 96800, 'loss/train': 1.645283818244934}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:26 - INFO - __main__ - Step 96805: {'lr': 0.00014315200492268201, 'samples': 18586560, 'steps': 96804, 'loss/train': 1.5838309526443481}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:29 - INFO - __main__ - Step 96810: {'lr': 0.00014312801727765851, 'samples': 18587520, 'steps': 96809, 'loss/train': 2.338048219680786}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:29 - INFO - __main__ - Step 96810: {'lr': 0.00014312801727765851, 'samples': 18587520, 'steps': 96809, 'loss/train': 2.338048219680786}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:33 - INFO - __main__ - Step 96818: {'lr': 0.00014308963954978615, 'samples': 18589056, 'steps': 96817, 'loss/train': 1.1587783098220825}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:34 - INFO - __main__ - Step 96822: {'lr': 0.00014307045184191276, 'samples': 18589824, 'steps': 96821, 'loss/train': 0.8930279612541199}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:37 - INFO - __main__ - Step 96826: {'lr': 0.00014305126490493208, 'samples': 18590592, 'steps': 96825, 'loss/train': 1.518880844116211}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:39 - INFO - __main__ - Step 96831: {'lr': 0.0001430272823179851, 'samples': 18591552, 'steps': 96830, 'loss/train': 1.0890586376190186}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:41 - INFO - __main__ - Step 96836: {'lr': 0.00014300330093604458, 'samples': 18592512, 'steps': 96835, 'loss/train': 0.07695842534303665}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:43 - INFO - __main__ - Step 96840: {'lr': 0.00014298411669827826, 'samples': 18593280, 'steps': 96839, 'loss/train': 1.558397889137268}5}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:43 - INFO - __main__ - Step 96840: {'lr': 0.00014298411669827826, 'samples': 18593280, 'steps': 96839, 'loss/train': 1.558397889137268}5}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:47 - INFO - __main__ - Step 96847: {'lr': 0.00014295054613872903, 'samples': 18594624, 'steps': 96846, 'loss/train': 1.2319146394729614}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:49 - INFO - __main__ - Step 96852: {'lr': 0.00014292656861462428, 'samples': 18595584, 'steps': 96851, 'loss/train': 1.5187643766403198}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:51 - INFO - __main__ - Step 96856: {'lr': 0.00014290738746374886, 'samples': 18596352, 'steps': 96855, 'loss/train': 0.4792807400226593}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:54 - INFO - __main__ - Step 96861: {'lr': 0.00014288341211089219, 'samples': 18597312, 'steps': 96860, 'loss/train': 1.0645523071289062}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:56 - INFO - __main__ - Step 96865: {'lr': 0.00014286423269736526, 'samples': 18598080, 'steps': 96864, 'loss/train': 1.3832366466522217}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:56 - INFO - __main__ - Step 96865: {'lr': 0.00014286423269736526, 'samples': 18598080, 'steps': 96864, 'loss/train': 1.3832366466522217}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:50:59 - INFO - __main__ - Step 96872: {'lr': 0.00014283067058231468, 'samples': 18599424, 'steps': 96871, 'loss/train': 1.4461969137191772}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:01 - INFO - __main__ - Step 96877: {'lr': 0.00014280669909161515, 'samples': 18600384, 'steps': 96876, 'loss/train': 1.3267314434051514}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:04 - INFO - __main__ - Step 96882: {'lr': 0.00014278272880840668, 'samples': 18601344, 'steps': 96881, 'loss/train': 1.3204537630081177}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:04 - INFO - __main__ - Step 96882: {'lr': 0.00014278272880840668, 'samples': 18601344, 'steps': 96881, 'loss/train': 1.3204537630081177}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:06 - INFO - __main__ - Step 96888: {'lr': 0.00014275396606282513, 'samples': 18602496, 'steps': 96887, 'loss/train': 1.0176128149032593}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:09 - INFO - __main__ - Step 96893: {'lr': 0.00014272999843704771, 'samples': 18603456, 'steps': 96892, 'loss/train': 1.4377212524414062}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:09 - INFO - __main__ - Step 96893: {'lr': 0.00014272999843704771, 'samples': 18603456, 'steps': 96892, 'loss/train': 1.4377212524414062}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:13 - INFO - __main__ - Step 96901: {'lr': 0.00014269165274929496, 'samples': 18604992, 'steps': 96900, 'loss/train': 1.8668227195739746}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:15 - INFO - __main__ - Step 96905: {'lr': 0.00014267248106578513, 'samples': 18605760, 'steps': 96904, 'loss/train': 1.3579559326171875}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:16 - INFO - __main__ - Step 96909: {'lr': 0.0001426533101560372, 'samples': 18606528, 'steps': 96908, 'loss/train': 1.4484161138534546}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:19 - INFO - __main__ - Step 96913: {'lr': 0.00014263414002018955, 'samples': 18607296, 'steps': 96912, 'loss/train': 1.4072625637054443}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:21 - INFO - __main__ - Step 96918: {'lr': 0.00014261017843888768, 'samples': 18608256, 'steps': 96917, 'loss/train': 1.0451124906539917}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:24 - INFO - __main__ - Step 96923: {'lr': 0.00014258621806729067, 'samples': 18609216, 'steps': 96922, 'loss/train': 1.020399570465088}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:26 - INFO - __main__ - Step 96927: {'lr': 0.00014256705064118197, 'samples': 18609984, 'steps': 96926, 'loss/train': 0.7307353019714355}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:28 - INFO - __main__ - Step 96931: {'lr': 0.00014254788398959542, 'samples': 18610752, 'steps': 96930, 'loss/train': 1.0727794170379639}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:29 - INFO - __main__ - Step 96935: {'lr': 0.00014252871811266905, 'samples': 18611520, 'steps': 96934, 'loss/train': 1.0981223583221436}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:31 - INFO - __main__ - Step 96939: {'lr': 0.0001425095530105411, 'samples': 18612288, 'steps': 96938, 'loss/train': 1.1504825353622437}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:34 - INFO - __main__ - Step 96944: {'lr': 0.00014248559772265195, 'samples': 18613248, 'steps': 96943, 'loss/train': 0.9501208662986755}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:36 - INFO - __main__ - Step 96948: {'lr': 0.0001424664343643256, 'samples': 18614016, 'steps': 96947, 'loss/train': 1.0780726671218872}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:38 - INFO - __main__ - Step 96952: {'lr': 0.00014244727178124668, 'samples': 18614784, 'steps': 96951, 'loss/train': 1.3335679769515991}}███���███████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:38 - INFO - __main__ - Step 96952: {'lr': 0.00014244727178124668, 'samples': 18614784, 'steps': 96951, 'loss/train': 1.3335679769515991}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:41 - INFO - __main__ - Step 96959: {'lr': 0.00014241373912671337, 'samples': 18616128, 'steps': 96958, 'loss/train': 1.3409785032272339}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:43 - INFO - __main__ - Step 96964: {'lr': 0.00014238978868487618, 'samples': 18617088, 'steps': 96963, 'loss/train': 1.2413660287857056}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:46 - INFO - __main__ - Step 96969: {'lr': 0.0001423658394552266, 'samples': 18618048, 'steps': 96968, 'loss/train': 1.234145164489746}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:46 - INFO - __main__ - Step 96969: {'lr': 0.0001423658394552266, 'samples': 18618048, 'steps': 96968, 'loss/train': 1.234145164489746}6}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:49 - INFO - __main__ - Step 96976: {'lr': 0.00014233231257070573, 'samples': 18619392, 'steps': 96975, 'loss/train': 1.170230746269226}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:52 - INFO - __main__ - Step 96980: {'lr': 0.00014231315541822682, 'samples': 18620160, 'steps': 96979, 'loss/train': 0.5941416621208191}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:52 - INFO - __main__ - Step 96980: {'lr': 0.00014231315541822682, 'samples': 18620160, 'steps': 96979, 'loss/train': 0.5941416621208191}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:55 - INFO - __main__ - Step 96986: {'lr': 0.00014228442114521262, 'samples': 18621312, 'steps': 96985, 'loss/train': 5.724117279052734}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:51:57 - INFO - __main__ - Step 96991: {'lr': 0.00014226047725239278, 'samples': 18622272, 'steps': 96990, 'loss/train': 1.338580846786499}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:00 - INFO - __main__ - Step 96996: {'lr': 0.00014223653457321722, 'samples': 18623232, 'steps': 96995, 'loss/train': 1.4133702516555786}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:02 - INFO - __main__ - Step 97000: {'lr': 0.00014221738130388174, 'samples': 18624000, 'steps': 96999, 'loss/train': 0.9033804535865784}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:04 - INFO - __main__ - Step 97004: {'lr': 0.0001421982288115892, 'samples': 18624768, 'steps': 97003, 'loss/train': 0.9533843994140625}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:05 - INFO - __main__ - Step 97008: {'lr': 0.0001421790770964777, 'samples': 18625536, 'steps': 97007, 'loss/train': 1.173203945159912}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:07 - INFO - __main__ - Step 97012: {'lr': 0.00014215992615868538, 'samples': 18626304, 'steps': 97011, 'loss/train': 1.480625033378601}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:07 - INFO - __main__ - Step 97012: {'lr': 0.00014215992615868538, 'samples': 18626304, 'steps': 97011, 'loss/train': 1.480625033378601}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:12 - INFO - __main__ - Step 97020: {'lr': 0.00014212162661561017, 'samples': 18627840, 'steps': 97019, 'loss/train': 1.4253581762313843}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:14 - INFO - __main__ - Step 97024: {'lr': 0.00014210247801060355, 'samples': 18628608, 'steps': 97023, 'loss/train': 0.9497612118721008}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:15 - INFO - __main__ - Step 97028: {'lr': 0.0001420833301834682, 'samples': 18629376, 'steps': 97027, 'loss/train': 1.8321298360824585}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:18 - INFO - __main__ - Step 97033: {'lr': 0.00014205939649364094, 'samples': 18630336, 'steps': 97032, 'loss/train': 1.6103535890579224}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:20 - INFO - __main__ - Step 97037: {'lr': 0.0001420402504172208, 'samples': 18631104, 'steps': 97036, 'loss/train': 1.181477665901184}4}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:22 - INFO - __main__ - Step 97041: {'lr': 0.0001420211051191206, 'samples': 18631872, 'steps': 97040, 'loss/train': 1.5923422574996948}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:22 - INFO - __main__ - Step 97041: {'lr': 0.0001420211051191206, 'samples': 18631872, 'steps': 97040, 'loss/train': 1.5923422574996948}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:25 - INFO - __main__ - Step 97048: {'lr': 0.00014198760272069285, 'samples': 18633216, 'steps': 97047, 'loss/train': 1.5101730823516846}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:27 - INFO - __main__ - Step 97053: {'lr': 0.00014196367389612003, 'samples': 18634176, 'steps': 97052, 'loss/train': 1.2677325010299683}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:27 - INFO - __main__ - Step 97053: {'lr': 0.00014196367389612003, 'samples': 18634176, 'steps': 97052, 'loss/train': 1.2677325010299683}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:32 - INFO - __main__ - Step 97061: {'lr': 0.00014192539030824977, 'samples': 18635712, 'steps': 97060, 'loss/train': 1.7300693988800049}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:33 - INFO - __main__ - Step 97065: {'lr': 0.00014190624968296765, 'samples': 18636480, 'steps': 97064, 'loss/train': 1.1287533044815063}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:36 - INFO - __main__ - Step 97069: {'lr': 0.00014188710983697162, 'samples': 18637248, 'steps': 97068, 'loss/train': 1.549246072769165}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:38 - INFO - __main__ - Step 97073: {'lr': 0.00014186797077039948, 'samples': 18638016, 'steps': 97072, 'loss/train': 1.3142551183700562}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:40 - INFO - __main__ - Step 97077: {'lr': 0.00014184883248338946, 'samples': 18638784, 'steps': 97076, 'loss/train': 1.7304065227508545}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:42 - INFO - __main__ - Step 97081: {'lr': 0.0001418296949760793, 'samples': 18639552, 'steps': 97080, 'loss/train': 1.3043440580368042}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:43 - INFO - __main__ - Step 97085: {'lr': 0.000141810558248607, 'samples': 18640320, 'steps': 97084, 'loss/train': 1.108165979385376}2}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:46 - INFO - __main__ - Step 97090: {'lr': 0.00014178663843612404, 'samples': 18641280, 'steps': 97089, 'loss/train': 1.1403855085372925}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:48 - INFO - __main__ - Step 97095: {'lr': 0.00014176271984262274, 'samples': 18642240, 'steps': 97094, 'loss/train': 1.6849037408828735}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:48 - INFO - __main__ - Step 97095: {'lr': 0.00014176271984262274, 'samples': 18642240, 'steps': 97094, 'loss/train': 1.6849037408828735}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:51 - INFO - __main__ - Step 97101: {'lr': 0.00014173401913985644, 'samples': 18643392, 'steps': 97100, 'loss/train': 0.09694083034992218}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:53 - INFO - __main__ - Step 97105: {'lr': 0.00014171488631364328, 'samples': 18644160, 'steps': 97104, 'loss/train': 1.3428436517715454}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:56 - INFO - __main__ - Step 97110: {'lr': 0.00014169097137870383, 'samples': 18645120, 'steps': 97109, 'loss/train': 1.0740469694137573}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:52:58 - INFO - __main__ - Step 97114: {'lr': 0.00014167184030918213, 'samples': 18645888, 'steps': 97113, 'loss/train': 1.6063740253448486}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:00 - INFO - __main__ - Step 97118: {'lr': 0.00014165271002063647, 'samples': 18646656, 'steps': 97117, 'loss/train': 1.593920350074768}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:01 - INFO - __main__ - Step 97122: {'lr': 0.00014163358051320462, 'samples': 18647424, 'steps': 97121, 'loss/train': 0.8597118854522705}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:04 - INFO - __main__ - Step 97126: {'lr': 0.00014161445178702454, 'samples': 18648192, 'steps': 97125, 'loss/train': 1.3340609073638916}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:06 - INFO - __main__ - Step 97131: {'lr': 0.0001415905419781449, 'samples': 18649152, 'steps': 97130, 'loss/train': 0.6399369835853577}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:08 - INFO - __main__ - Step 97135: {'lr': 0.00014157141501028553, 'samples': 18649920, 'steps': 97134, 'loss/train': 1.6232376098632812}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:10 - INFO - __main__ - Step 97139: {'lr': 0.00014155228882412613, 'samples': 18650688, 'steps': 97138, 'loss/train': 1.2193069458007812}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:10 - INFO - __main__ - Step 97139: {'lr': 0.00014155228882412613, 'samples': 18650688, 'steps': 97138, 'loss/train': 1.2193069458007812}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:14 - INFO - __main__ - Step 97146: {'lr': 0.00014151881987972751, 'samples': 18652032, 'steps': 97145, 'loss/train': 0.3157970607280731}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:14 - INFO - __main__ - Step 97146: {'lr': 0.00014151881987972751, 'samples': 18652032, 'steps': 97145, 'loss/train': 0.3157970607280731}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:18 - INFO - __main__ - Step 97155: {'lr': 0.0001414757918992458, 'samples': 18653760, 'steps': 97154, 'loss/train': 1.759022831916809}1}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:20 - INFO - __main__ - Step 97159: {'lr': 0.00014145666962365444, 'samples': 18654528, 'steps': 97158, 'loss/train': 1.59822678565979}1}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:22 - INFO - __main__ - Step 97163: {'lr': 0.00014143754813059021, 'samples': 18655296, 'steps': 97162, 'loss/train': 1.1820178031921387}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:24 - INFO - __main__ - Step 97167: {'lr': 0.00014141842742019102, 'samples': 18656064, 'steps': 97166, 'loss/train': 1.0270535945892334}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:26 - INFO - __main__ - Step 97172: {'lr': 0.00014139452763302485, 'samples': 18657024, 'steps': 97171, 'loss/train': 1.9697881937026978}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:28 - INFO - __main__ - Step 97176: {'lr': 0.00014137540868412602, 'samples': 18657792, 'steps': 97175, 'loss/train': 1.373569369316101}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:30 - INFO - __main__ - Step 97180: {'lr': 0.0001413562905183402, 'samples': 18658560, 'steps': 97179, 'loss/train': 0.6880878806114197}}}████████��██████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:32 - INFO - __main__ - Step 97184: {'lr': 0.00014133717313580534, 'samples': 18659328, 'steps': 97183, 'loss/train': 1.4884105920791626}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:34 - INFO - __main__ - Step 97188: {'lr': 0.00014131805653665912, 'samples': 18660096, 'steps': 97187, 'loss/train': 1.3427823781967163}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:34 - INFO - __main__ - Step 97188: {'lr': 0.00014131805653665912, 'samples': 18660096, 'steps': 97187, 'loss/train': 1.3427823781967163}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:38 - INFO - __main__ - Step 97196: {'lr': 0.00014127982568908393, 'samples': 18661632, 'steps': 97195, 'loss/train': 1.5002670288085938}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:38 - INFO - __main__ - Step 97196: {'lr': 0.00014127982568908393, 'samples': 18661632, 'steps': 97195, 'loss/train': 1.5002670288085938}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:41 - INFO - __main__ - Step 97203: {'lr': 0.00014124637626926882, 'samples': 18662976, 'steps': 97202, 'loss/train': 1.588222622871399}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:44 - INFO - __main__ - Step 97208: {'lr': 0.0001412224852965817, 'samples': 18663936, 'steps': 97207, 'loss/train': 1.131264567375183}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:44 - INFO - __main__ - Step 97208: {'lr': 0.0001412224852965817, 'samples': 18663936, 'steps': 97207, 'loss/train': 1.131264567375183}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:48 - INFO - __main__ - Step 97216: {'lr': 0.00014118426228909486, 'samples': 18665472, 'steps': 97215, 'loss/train': 1.0847662687301636}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:50 - INFO - __main__ - Step 97220: {'lr': 0.0001411651519620191, 'samples': 18666240, 'steps': 97219, 'loss/train': 1.1309168338775635}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:52 - INFO - __main__ - Step 97224: {'lr': 0.00014114604241957226, 'samples': 18667008, 'steps': 97223, 'loss/train': 1.310687780380249}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:54 - INFO - __main__ - Step 97229: {'lr': 0.00014112215659510782, 'samples': 18667968, 'steps': 97228, 'loss/train': 0.9704346656799316}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:54 - INFO - __main__ - Step 97229: {'lr': 0.00014112215659510782, 'samples': 18667968, 'steps': 97228, 'loss/train': 0.9704346656799316}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:58 - INFO - __main__ - Step 97234: {'lr': 0.00014109827199711028, 'samples': 18668928, 'steps': 97233, 'loss/train': 1.7570271492004395}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:53:58 - INFO - __main__ - Step 97234: {'lr': 0.00014109827199711028, 'samples': 18668928, 'steps': 97233, 'loss/train': 1.7570271492004395}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:02 - INFO - __main__ - Step 97242: {'lr': 0.00014106005919203702, 'samples': 18670464, 'steps': 97241, 'loss/train': 1.3071393966674805}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:04 - INFO - __main__ - Step 97247: {'lr': 0.00014103617778411253, 'samples': 18671424, 'steps': 97246, 'loss/train': 1.4037420749664307}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:06 - INFO - __main__ - Step 97252: {'lr': 0.0001410122976036236, 'samples': 18672384, 'steps': 97251, 'loss/train': 0.5840388536453247}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:06 - INFO - __main__ - Step 97252: {'lr': 0.0001410122976036236, 'samples': 18672384, 'steps': 97251, 'loss/train': 0.5840388536453247}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:06 - INFO - __main__ - Step 97252: {'lr': 0.0001410122976036236, 'samples': 18672384, 'steps': 97251, 'loss/train': 0.5840388536453247}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:12 - INFO - __main__ - Step 97262: {'lr': 0.00014096454092602775, 'samples': 18674304, 'steps': 97261, 'loss/train': 1.2779291868209839}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:14 - INFO - __main__ - Step 97268: {'lr': 0.00014093588927755802, 'samples': 18675456, 'steps': 97267, 'loss/train': 1.470815658569336}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:17 - INFO - __main__ - Step 97272: {'lr': 0.00014091678916140153, 'samples': 18676224, 'steps': 97271, 'loss/train': 1.473704218864441}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:19 - INFO - __main__ - Step 97276: {'lr': 0.00014089768983166444, 'samples': 18676992, 'steps': 97275, 'loss/train': 1.209798812866211}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:21 - INFO - __main__ - Step 97280: {'lr': 0.00014087859128848453, 'samples': 18677760, 'steps': 97279, 'loss/train': 1.3724349737167358}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:22 - INFO - __main__ - Step 97284: {'lr': 0.00014085949353199925, 'samples': 18678528, 'steps': 97283, 'loss/train': 1.6594539880752563}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:24 - INFO - __main__ - Step 97288: {'lr': 0.00014084039656234642, 'samples': 18679296, 'steps': 97287, 'loss/train': 1.3478325605392456}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:26 - INFO - __main__ - Step 97292: {'lr': 0.00014082130037966386, 'samples': 18680064, 'steps': 97291, 'loss/train': 1.0215696096420288}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:26 - INFO - __main__ - Step 97292: {'lr': 0.00014082130037966386, 'samples': 18680064, 'steps': 97291, 'loss/train': 1.0215696096420288}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:30 - INFO - __main__ - Step 97299: {'lr': 0.00014078788395403014, 'samples': 18681408, 'steps': 97298, 'loss/train': 1.1879709959030151}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:32 - INFO - __main__ - Step 97304: {'lr': 0.00014076401655481336, 'samples': 18682368, 'steps': 97303, 'loss/train': 1.325385570526123}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:32 - INFO - __main__ - Step 97304: {'lr': 0.00014076401655481336, 'samples': 18682368, 'steps': 97303, 'loss/train': 1.325385570526123}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:36 - INFO - __main__ - Step 97312: {'lr': 0.00014072583127562084, 'samples': 18683904, 'steps': 97311, 'loss/train': 1.1242194175720215}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:38 - INFO - __main__ - Step 97316: {'lr': 0.00014070673981764981, 'samples': 18684672, 'steps': 97315, 'loss/train': 1.4424760341644287}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:40 - INFO - __main__ - Step 97320: {'lr': 0.0001406876491476125, 'samples': 18685440, 'steps': 97319, 'loss/train': 1.1660076379776}287}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:42 - INFO - __main__ - Step 97324: {'lr': 0.00014066855926564659, 'samples': 18686208, 'steps': 97323, 'loss/train': 1.2552061080932617}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:44 - INFO - __main__ - Step 97329: {'lr': 0.0001406446980216241, 'samples': 18687168, 'steps': 97328, 'loss/train': 1.4546494483947754}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:46 - INFO - __main__ - Step 97333: {'lr': 0.0001406256099133218, 'samples': 18687936, 'steps': 97332, 'loss/train': 1.3164901733398438}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:46 - INFO - __main__ - Step 97333: {'lr': 0.0001406256099133218, 'samples': 18687936, 'steps': 97332, 'loss/train': 1.3164901733398438}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:50 - INFO - __main__ - Step 97340: {'lr': 0.00014059220762124852, 'samples': 18689280, 'steps': 97339, 'loss/train': 0.9306468963623047}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:52 - INFO - __main__ - Step 97345: {'lr': 0.00014056835032007708, 'samples': 18690240, 'steps': 97344, 'loss/train': 1.0797678232192993}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:54 - INFO - __main__ - Step 97350: {'lr': 0.0001405444942516109, 'samples': 18691200, 'steps': 97349, 'loss/train': 1.4693301916122437}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:54 - INFO - __main__ - Step 97350: {'lr': 0.0001405444942516109, 'samples': 18691200, 'steps': 97349, 'loss/train': 1.4693301916122437}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:54:58 - INFO - __main__ - Step 97357: {'lr': 0.0001405110978272148, 'samples': 18692544, 'steps': 97356, 'loss/train': 1.228217601776123}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:00 - INFO - __main__ - Step 97361: {'lr': 0.00014049201524143234, 'samples': 18693312, 'steps': 97360, 'loss/train': 1.450724482536316}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:02 - INFO - __main__ - Step 97365: {'lr': 0.0001404729334451315, 'samples': 18694080, 'steps': 97364, 'loss/train': 1.437983512878418}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:04 - INFO - __main__ - Step 97370: {'lr': 0.00014044908231017372, 'samples': 18695040, 'steps': 97369, 'loss/train': 1.5011833906173706}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:06 - INFO - __main__ - Step 97375: {'lr': 0.00014042523240926486, 'samples': 18696000, 'steps': 97374, 'loss/train': 1.6331045627593994}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:09 - INFO - __main__ - Step 97379: {'lr': 0.0001404061533772334, 'samples': 18696768, 'steps': 97378, 'loss/train': 1.0994014739990234}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:11 - INFO - __main__ - Step 97383: {'lr': 0.00014038707513530267, 'samples': 18697536, 'steps': 97382, 'loss/train': 1.3893383741378784}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:12 - INFO - __main__ - Step 97387: {'lr': 0.0001403679976836103, 'samples': 18698304, 'steps': 97386, 'loss/train': 1.5970542430877686}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:14 - INFO - __main__ - Step 97391: {'lr': 0.0001403489210222937, 'samples': 18699072, 'steps': 97390, 'loss/train': 1.5562995672225952}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:16 - INFO - __main__ - Step 97395: {'lr': 0.0001403298451514904, 'samples': 18699840, 'steps': 97394, 'loss/train': 1.1550168991088867}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:16 - INFO - __main__ - Step 97395: {'lr': 0.0001403298451514904, 'samples': 18699840, 'steps': 97394, 'loss/train': 1.1550168991088867}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:20 - INFO - __main__ - Step 97402: {'lr': 0.00014029646428017113, 'samples': 18701184, 'steps': 97401, 'loss/train': 1.4160741567611694}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:22 - INFO - __main__ - Step 97406: {'lr': 0.0001402773905839886, 'samples': 18701952, 'steps': 97405, 'loss/train': 1.1341277360916138}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:24 - INFO - __main__ - Step 97411: {'lr': 0.0001402535495761612, 'samples': 18702912, 'steps': 97410, 'loss/train': 0.9865967035293579}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:27 - INFO - __main__ - Step 97416: {'lr': 0.00014022970980458527, 'samples': 18703872, 'steps': 97415, 'loss/train': 1.39313805103302}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:27 - INFO - __main__ - Step 97416: {'lr': 0.00014022970980458527, 'samples': 18703872, 'steps': 97415, 'loss/train': 1.39313805103302}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:30 - INFO - __main__ - Step 97423: {'lr': 0.0001401963362017926, 'samples': 18705216, 'steps': 97422, 'loss/train': 0.9107914566993713}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:32 - INFO - __main__ - Step 97427: {'lr': 0.0001401772666600466, 'samples': 18705984, 'steps': 97426, 'loss/train': 1.0432415008544922}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:34 - INFO - __main__ - Step 97432: {'lr': 0.0001401534308462797, 'samples': 18706944, 'steps': 97431, 'loss/train': 1.2700903415679932}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:37 - INFO - __main__ - Step 97437: {'lr': 0.00014012959626989206, 'samples': 18707904, 'steps': 97436, 'loss/train': 1.4703593254089355}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:39 - INFO - __main__ - Step 97441: {'lr': 0.0001401105294998755, 'samples': 18708672, 'steps': 97440, 'loss/train': 1.9497935771942139}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:39 - INFO - __main__ - Step 97441: {'lr': 0.0001401105294998755, 'samples': 18708672, 'steps': 97440, 'loss/train': 1.9497935771942139}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:42 - INFO - __main__ - Step 97448: {'lr': 0.00014007716455873725, 'samples': 18710016, 'steps': 97447, 'loss/train': 1.4339606761932373}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:44 - INFO - __main__ - Step 97452: {'lr': 0.00014005809996768935, 'samples': 18710784, 'steps': 97451, 'loss/train': 1.4372365474700928}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:44 - INFO - __main__ - Step 97452: {'lr': 0.00014005809996768935, 'samples': 18710784, 'steps': 97451, 'loss/train': 1.4372365474700928}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:49 - INFO - __main__ - Step 97460: {'lr': 0.00014001997316356095, 'samples': 18712320, 'steps': 97459, 'loss/train': 0.12713727355003357}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:50 - INFO - __main__ - Step 97464: {'lr': 0.0001400009109507553, 'samples': 18713088, 'steps': 97463, 'loss/train': 1.5821572542190552}7}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:52 - INFO - __main__ - Step 97468: {'lr': 0.00013998184953097195, 'samples': 18713856, 'steps': 97467, 'loss/train': 1.0934065580368042}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:52 - INFO - __main__ - Step 97468: {'lr': 0.00013998184953097195, 'samples': 18713856, 'steps': 97467, 'loss/train': 1.0934065580368042}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:52 - INFO - __main__ - Step 97468: {'lr': 0.00013998184953097195, 'samples': 18713856, 'steps': 97467, 'loss/train': 1.0934065580368042}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:55:58 - INFO - __main__ - Step 97479: {'lr': 0.00013992943471671055, 'samples': 18715968, 'steps': 97478, 'loss/train': 1.262378215789795}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:00 - INFO - __main__ - Step 97484: {'lr': 0.00013990561178480948, 'samples': 18716928, 'steps': 97483, 'loss/train': 1.7293143272399902}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:00 - INFO - __main__ - Step 97484: {'lr': 0.00013990561178480948, 'samples': 18716928, 'steps': 97483, 'loss/train': 1.7293143272399902}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:05 - INFO - __main__ - Step 97492: {'lr': 0.00013986749767343448, 'samples': 18718464, 'steps': 97491, 'loss/train': 0.9957885146141052}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:06 - INFO - __main__ - Step 97496: {'lr': 0.00013984844180865453, 'samples': 18719232, 'steps': 97495, 'loss/train': 1.5373814105987549}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:09 - INFO - __main__ - Step 97500: {'lr': 0.00013982938673799596, 'samples': 18720000, 'steps': 97499, 'loss/train': 1.2569489479064941}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:11 - INFO - __main__ - Step 97504: {'lr': 0.00013981033246159624, 'samples': 18720768, 'steps': 97503, 'loss/train': 1.3819923400878906}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:13 - INFO - __main__ - Step 97508: {'lr': 0.00013979127897959288, 'samples': 18721536, 'steps': 97507, 'loss/train': 1.0306785106658936}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:13 - INFO - __main__ - Step 97508: {'lr': 0.00013979127897959288, 'samples': 18721536, 'steps': 97507, 'loss/train': 1.0306785106658936}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:16 - INFO - __main__ - Step 97515: {'lr': 0.00013975793729801582, 'samples': 18722880, 'steps': 97514, 'loss/train': 1.4895460605621338}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:19 - INFO - __main__ - Step 97520: {'lr': 0.00013973412330133345, 'samples': 18723840, 'steps': 97519, 'loss/train': 1.1962472200393677}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:19 - INFO - __main__ - Step 97520: {'lr': 0.00013973412330133345, 'samples': 18723840, 'steps': 97519, 'loss/train': 1.1962472200393677}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:23 - INFO - __main__ - Step 97528: {'lr': 0.00013969602349032633, 'samples': 18725376, 'steps': 97527, 'loss/train': 1.4497555494308472}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:23 - INFO - __main__ - Step 97528: {'lr': 0.00013969602349032633, 'samples': 18725376, 'steps': 97527, 'loss/train': 1.4497555494308472}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:26 - INFO - __main__ - Step 97535: {'lr': 0.00013966268876497434, 'samples': 18726720, 'steps': 97534, 'loss/train': 1.3947205543518066}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:29 - INFO - __main__ - Step 97540: {'lr': 0.00013963887973831153, 'samples': 18727680, 'steps': 97539, 'loss/train': 1.447018027305603}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:31 - INFO - __main__ - Step 97545: {'lr': 0.0001396150719548241, 'samples': 18728640, 'steps': 97544, 'loss/train': 1.29905366897583}3}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:33 - INFO - __main__ - Step 97549: {'lr': 0.00013959602662330078, 'samples': 18729408, 'steps': 97548, 'loss/train': 1.5553427934646606}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:35 - INFO - __main__ - Step 97553: {'lr': 0.00013957698208771864, 'samples': 18730176, 'steps': 97552, 'loss/train': 0.7850678563117981}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:36 - INFO - __main__ - Step 97557: {'lr': 0.000139557938348215, 'samples': 18730944, 'steps': 97556, 'loss/train': 1.459364652633667}81}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:38 - INFO - __main__ - Step 97561: {'lr': 0.0001395388954049273, 'samples': 18731712, 'steps': 97560, 'loss/train': 1.1512260437011719}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:41 - INFO - __main__ - Step 97566: {'lr': 0.00013951509284570516, 'samples': 18732672, 'steps': 97565, 'loss/train': 1.2672295570373535}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:43 - INFO - __main__ - Step 97570: {'lr': 0.000139496051694405, 'samples': 18733440, 'steps': 97569, 'loss/train': 1.4672465324401855}5}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:45 - INFO - __main__ - Step 97574: {'lr': 0.0001394770113397667, 'samples': 18734208, 'steps': 97573, 'loss/train': 1.3703473806381226}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:45 - INFO - __main__ - Step 97574: {'lr': 0.0001394770113397667, 'samples': 18734208, 'steps': 97573, 'loss/train': 1.3703473806381226}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:48 - INFO - __main__ - Step 97581: {'lr': 0.00013944369263653057, 'samples': 18735552, 'steps': 97580, 'loss/train': 1.7102653980255127}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:48 - INFO - __main__ - Step 97581: {'lr': 0.00013944369263653057, 'samples': 18735552, 'steps': 97580, 'loss/train': 1.7102653980255127}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:52 - INFO - __main__ - Step 97588: {'lr': 0.00013941037637422765, 'samples': 18736896, 'steps': 97587, 'loss/train': 0.8320348262786865}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:55 - INFO - __main__ - Step 97594: {'lr': 0.00013938182152130937, 'samples': 18738048, 'steps': 97593, 'loss/train': 1.4094116687774658}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:57 - INFO - __main__ - Step 97598: {'lr': 0.00013936278594952543, 'samples': 18738816, 'steps': 97597, 'loss/train': 0.6952365040779114}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:56:57 - INFO - __main__ - Step 97598: {'lr': 0.00013936278594952543, 'samples': 18738816, 'steps': 97597, 'loss/train': 0.6952365040779114}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:00 - INFO - __main__ - Step 97605: {'lr': 0.00013932947561826588, 'samples': 18740160, 'steps': 97604, 'loss/train': 1.7186225652694702}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:02 - INFO - __main__ - Step 97609: {'lr': 0.00013931044224027467, 'samples': 18740928, 'steps': 97608, 'loss/train': 1.0502307415008545}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:05 - INFO - __main__ - Step 97614: {'lr': 0.0001392866516399895, 'samples': 18741888, 'steps': 97613, 'loss/train': 0.07569380849599838}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:07 - INFO - __main__ - Step 97619: {'lr': 0.00013926286228684734, 'samples': 18742848, 'steps': 97618, 'loss/train': 1.1344492435455322}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:07 - INFO - __main__ - Step 97619: {'lr': 0.00013926286228684734, 'samples': 18742848, 'steps': 97618, 'loss/train': 1.1344492435455322}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:10 - INFO - __main__ - Step 97625: {'lr': 0.00013923431670968307, 'samples': 18744000, 'steps': 97624, 'loss/train': 0.04709068313241005}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:13 - INFO - __main__ - Step 97630: {'lr': 0.00013921053010119928, 'samples': 18744960, 'steps': 97629, 'loss/train': 1.4993786811828613}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:15 - INFO - __main__ - Step 97634: {'lr': 0.00013919150171295971, 'samples': 18745728, 'steps': 97633, 'loss/train': 0.8753668665885925}}███████████████████���███████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:17 - INFO - __main__ - Step 97639: {'lr': 0.00013916771735106987, 'samples': 18746688, 'steps': 97638, 'loss/train': 1.3314586877822876}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:19 - INFO - __main__ - Step 97643: {'lr': 0.0001391486907604529, 'samples': 18747456, 'steps': 97642, 'loss/train': 1.2723978757858276}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:19 - INFO - __main__ - Step 97643: {'lr': 0.0001391486907604529, 'samples': 18747456, 'steps': 97642, 'loss/train': 1.2723978757858276}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:22 - INFO - __main__ - Step 97650: {'lr': 0.0001391153961499493, 'samples': 18748800, 'steps': 97649, 'loss/train': 1.3411997556686401}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:25 - INFO - __main__ - Step 97655: {'lr': 0.00013909161578414786, 'samples': 18749760, 'steps': 97654, 'loss/train': 1.6282063722610474}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:27 - INFO - __main__ - Step 97660: {'lr': 0.00013906783666768648, 'samples': 18750720, 'steps': 97659, 'loss/train': 1.51374351978302}4}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:29 - INFO - __main__ - Step 97664: {'lr': 0.0001390488142742223, 'samples': 18751488, 'steps': 97663, 'loss/train': 1.204357624053955}4}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:31 - INFO - __main__ - Step 97668: {'lr': 0.0001390297926806445, 'samples': 18752256, 'steps': 97667, 'loss/train': 1.5312024354934692}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:31 - INFO - __main__ - Step 97668: {'lr': 0.0001390297926806445, 'samples': 18752256, 'steps': 97667, 'loss/train': 1.5312024354934692}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:35 - INFO - __main__ - Step 97675: {'lr': 0.00013899650681702198, 'samples': 18753600, 'steps': 97674, 'loss/train': 1.3758437633514404}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:38 - INFO - __main__ - Step 97681: {'lr': 0.0001389679780273883, 'samples': 18754752, 'steps': 97680, 'loss/train': 1.2001314163208008}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:40 - INFO - __main__ - Step 97685: {'lr': 0.0001389489598348569, 'samples': 18755520, 'steps': 97684, 'loss/train': 1.429070234298706}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:40 - INFO - __main__ - Step 97685: {'lr': 0.0001389489598348569, 'samples': 18755520, 'steps': 97684, 'loss/train': 1.429070234298706}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:43 - INFO - __main__ - Step 97692: {'lr': 0.00013891567992446797, 'samples': 18756864, 'steps': 97691, 'loss/train': 1.3824615478515625}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:45 - INFO - __main__ - Step 97696: {'lr': 0.00013889666393393353, 'samples': 18757632, 'steps': 97695, 'loss/train': 1.022942066192627}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:47 - INFO - __main__ - Step 97701: {'lr': 0.00013887289507216394, 'samples': 18758592, 'steps': 97700, 'loss/train': 1.3646489381790161}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:47 - INFO - __main__ - Step 97701: {'lr': 0.00013887289507216394, 'samples': 18758592, 'steps': 97700, 'loss/train': 1.3646489381790161}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:50 - INFO - __main__ - Step 97708: {'lr': 0.00013883962076877731, 'samples': 18759936, 'steps': 97707, 'loss/train': 1.4923830032348633}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:53 - INFO - __main__ - Step 97713: {'lr': 0.00013881585491178707, 'samples': 18760896, 'steps': 97712, 'loss/train': 1.418515920639038}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:55 - INFO - __main__ - Step 97717: {'lr': 0.0001387968431279435, 'samples': 18761664, 'steps': 97716, 'loss/train': 1.348921775817871}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:57 - INFO - __main__ - Step 97722: {'lr': 0.0001387730795255498, 'samples': 18762624, 'steps': 97721, 'loss/train': 1.2610852718353271}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:57:57 - INFO - __main__ - Step 97722: {'lr': 0.0001387730795255498, 'samples': 18762624, 'steps': 97721, 'loss/train': 1.2610852718353271}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:01 - INFO - __main__ - Step 97728: {'lr': 0.00013874456485656622, 'samples': 18763776, 'steps': 97727, 'loss/train': 1.2865047454833984}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:03 - INFO - __main__ - Step 97732: {'lr': 0.0001387255560798149, 'samples': 18764544, 'steps': 97731, 'loss/train': 1.4618405103683472}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:05 - INFO - __main__ - Step 97737: {'lr': 0.00013870179623700927, 'samples': 18765504, 'steps': 97736, 'loss/train': 1.2780922651290894}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:05 - INFO - __main__ - Step 97737: {'lr': 0.00013870179623700927, 'samples': 18765504, 'steps': 97736, 'loss/train': 1.2780922651290894}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:09 - INFO - __main__ - Step 97744: {'lr': 0.0001386685345634098, 'samples': 18766848, 'steps': 97743, 'loss/train': 0.12306948006153107}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:11 - INFO - __main__ - Step 97748: {'lr': 0.00013864952899634783, 'samples': 18767616, 'steps': 97747, 'loss/train': 1.541203498840332}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:13 - INFO - __main__ - Step 97753: {'lr': 0.00013862577316642438, 'samples': 18768576, 'steps': 97752, 'loss/train': 1.198941707611084}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:13 - INFO - __main__ - Step 97753: {'lr': 0.00013862577316642438, 'samples': 18768576, 'steps': 97752, 'loss/train': 1.198941707611084}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:17 - INFO - __main__ - Step 97761: {'lr': 0.00013858776644820058, 'samples': 18770112, 'steps': 97760, 'loss/train': 0.9793931245803833}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:20 - INFO - __main__ - Step 97765: {'lr': 0.00013856876429383546, 'samples': 18770880, 'steps': 97764, 'loss/train': 1.29975426197052}3}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:21 - INFO - __main__ - Step 97769: {'lr': 0.0001385497629428174, 'samples': 18771648, 'steps': 97768, 'loss/train': 1.4031038284301758}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:23 - INFO - __main__ - Step 97773: {'lr': 0.00013853076239528345, 'samples': 18772416, 'steps': 97772, 'loss/train': 1.403512716293335}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:23 - INFO - __main__ - Step 97773: {'lr': 0.00013853076239528345, 'samples': 18772416, 'steps': 97772, 'loss/train': 1.403512716293335}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:27 - INFO - __main__ - Step 97781: {'lr': 0.0001384927637112159, 'samples': 18773952, 'steps': 97780, 'loss/train': 1.6958340406417847}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:29 - INFO - __main__ - Step 97785: {'lr': 0.00013847376557495612, 'samples': 18774720, 'steps': 97784, 'loss/train': 1.7706862688064575}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:31 - INFO - __main__ - Step 97789: {'lr': 0.00013845476824272845, 'samples': 18775488, 'steps': 97788, 'loss/train': 0.04993930086493492}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:33 - INFO - __main__ - Step 97793: {'lr': 0.00013843577171466966, 'samples': 18776256, 'steps': 97792, 'loss/train': 1.64992356300354}92}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:33 - INFO - __main__ - Step 97793: {'lr': 0.00013843577171466966, 'samples': 18776256, 'steps': 97792, 'loss/train': 1.64992356300354}92}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:37 - INFO - __main__ - Step 97800: {'lr': 0.00013840252972601027, 'samples': 18777600, 'steps': 97799, 'loss/train': 0.7635474801063538}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:39 - INFO - __main__ - Step 97804: {'lr': 0.00013838353541012239, 'samples': 18778368, 'steps': 97803, 'loss/train': 1.6507028341293335}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:41 - INFO - __main__ - Step 97809: {'lr': 0.0001383597936468632, 'samples': 18779328, 'steps': 97808, 'loss/train': 0.9794755578041077}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:41 - INFO - __main__ - Step 97809: {'lr': 0.0001383597936468632, 'samples': 18779328, 'steps': 97808, 'loss/train': 0.9794755578041077}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:45 - INFO - __main__ - Step 97817: {'lr': 0.00013832180944153429, 'samples': 18780864, 'steps': 97816, 'loss/train': 1.2971062660217285}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:47 - INFO - __main__ - Step 97821: {'lr': 0.00013830281854649258, 'samples': 18781632, 'steps': 97820, 'loss/train': 1.955767035484314}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:49 - INFO - __main__ - Step 97825: {'lr': 0.0001382838284567153, 'samples': 18782400, 'steps': 97824, 'loss/train': 1.8072059154510498}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:51 - INFO - __main__ - Step 97829: {'lr': 0.00013826483917233945, 'samples': 18783168, 'steps': 97828, 'loss/train': 1.293258786201477}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:54 - INFO - __main__ - Step 97835: {'lr': 0.00013823635675620243, 'samples': 18784320, 'steps': 97834, 'loss/train': 1.4824907779693604}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:56 - INFO - __main__ - Step 97839: {'lr': 0.00013821736948592883, 'samples': 18785088, 'steps': 97838, 'loss/train': 1.213954210281372}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:56 - INFO - __main__ - Step 97839: {'lr': 0.00013821736948592883, 'samples': 18785088, 'steps': 97838, 'loss/train': 1.213954210281372}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:58:59 - INFO - __main__ - Step 97846: {'lr': 0.000138184143702182, 'samples': 18786432, 'steps': 97845, 'loss/train': 1.5855779647827148}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:01 - INFO - __main__ - Step 97850: {'lr': 0.00013816515864840904, 'samples': 18787200, 'steps': 97849, 'loss/train': 1.1922905445098877}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:03 - INFO - __main__ - Step 97855: {'lr': 0.00013814142846500744, 'samples': 18788160, 'steps': 97854, 'loss/train': 1.2191779613494873}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:03 - INFO - __main__ - Step 97855: {'lr': 0.00013814142846500744, 'samples': 18788160, 'steps': 97854, 'loss/train': 1.2191779613494873}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:08 - INFO - __main__ - Step 97863: {'lr': 0.00013810346279256693, 'samples': 18789696, 'steps': 97862, 'loss/train': 4.129947185516357}}}████████████████████████��██| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:09 - INFO - __main__ - Step 97867: {'lr': 0.00013808448116633064, 'samples': 18790464, 'steps': 97866, 'loss/train': 1.54781174659729}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:11 - INFO - __main__ - Step 97871: {'lr': 0.0001380655003469329, 'samples': 18791232, 'steps': 97870, 'loss/train': 1.7174363136291504}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:11 - INFO - __main__ - Step 97871: {'lr': 0.0001380655003469329, 'samples': 18791232, 'steps': 97870, 'loss/train': 1.7174363136291504}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:15 - INFO - __main__ - Step 97879: {'lr': 0.0001380275411292003, 'samples': 18792768, 'steps': 97878, 'loss/train': 1.2809308767318726}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:17 - INFO - __main__ - Step 97883: {'lr': 0.00013800856273113915, 'samples': 18793536, 'steps': 97882, 'loss/train': 0.897771418094635}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:19 - INFO - __main__ - Step 97887: {'lr': 0.0001379895851404637, 'samples': 18794304, 'steps': 97886, 'loss/train': 1.858672857284546}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:21 - INFO - __main__ - Step 97892: {'lr': 0.00013796586428771414, 'samples': 18795264, 'steps': 97891, 'loss/train': 1.051766276359558}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:24 - INFO - __main__ - Step 97897: {'lr': 0.00013794214469698595, 'samples': 18796224, 'steps': 97896, 'loss/train': 1.7273247241973877}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:24 - INFO - __main__ - Step 97897: {'lr': 0.00013794214469698595, 'samples': 18796224, 'steps': 97896, 'loss/train': 1.7273247241973877}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:27 - INFO - __main__ - Step 97904: {'lr': 0.00013790893939067092, 'samples': 18797568, 'steps': 97903, 'loss/train': 2.099257707595825}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:29 - INFO - __main__ - Step 97908: {'lr': 0.0001378899660410155, 'samples': 18798336, 'steps': 97907, 'loss/train': 2.029127836227417}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:32 - INFO - __main__ - Step 97913: {'lr': 0.00013786625049055102, 'samples': 18799296, 'steps': 97912, 'loss/train': 1.4358528852462769}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:32 - INFO - __main__ - Step 97913: {'lr': 0.00013786625049055102, 'samples': 18799296, 'steps': 97912, 'loss/train': 1.4358528852462769}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:36 - INFO - __main__ - Step 97921: {'lr': 0.0001378283082372571, 'samples': 18800832, 'steps': 97920, 'loss/train': 1.0947426557540894}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:37 - INFO - __main__ - Step 97925: {'lr': 0.0001378093383235699, 'samples': 18801600, 'steps': 97924, 'loss/train': 1.392905831336975}}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:39 - INFO - __main__ - Step 97929: {'lr': 0.0001377903692187047, 'samples': 18802368, 'steps': 97928, 'loss/train': 1.4663580656051636}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:42 - INFO - __main__ - Step 97934: {'lr': 0.00013776665897523755, 'samples': 18803328, 'steps': 97933, 'loss/train': 1.4297106266021729}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:42 - INFO - __main__ - Step 97934: {'lr': 0.00013776665897523755, 'samples': 18803328, 'steps': 97933, 'loss/train': 1.4297106266021729}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:45 - INFO - __main__ - Step 97941: {'lr': 0.0001377334667584092, 'samples': 18804672, 'steps': 97940, 'loss/train': 1.4304559230804443}}}███████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:47 - INFO - __main__ - Step 97945: {'lr': 0.00013771450089019983, 'samples': 18805440, 'steps': 97944, 'loss/train': 0.048488449305295944}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:50 - INFO - __main__ - Step 97950: {'lr': 0.0001376907946933218, 'samples': 18806400, 'steps': 97949, 'loss/train': 1.552969217300415}944}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:52 - INFO - __main__ - Step 97954: {'lr': 0.00013767183064669278, 'samples': 18807168, 'steps': 97953, 'loss/train': 1.1354866027832031}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:52 - INFO - __main__ - Step 97954: {'lr': 0.00013767183064669278, 'samples': 18807168, 'steps': 97953, 'loss/train': 1.1354866027832031}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:55 - INFO - __main__ - Step 97961: {'lr': 0.00013763864551378786, 'samples': 18808512, 'steps': 97960, 'loss/train': 1.3093805313110352}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 10:59:58 - INFO - __main__ - Step 97966: {'lr': 0.00013761494336623332, 'samples': 18809472, 'steps': 97965, 'loss/train': 1.4472204446792603}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:00 - INFO - __main__ - Step 97970: {'lr': 0.0001375959825596783, 'samples': 18810240, 'steps': 97969, 'loss/train': 1.1871880292892456}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:02 - INFO - __main__ - Step 97975: {'lr': 0.00013757228269106964, 'samples': 18811200, 'steps': 97974, 'loss/train': 1.0659441947937012}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:04 - INFO - __main__ - Step 97979: {'lr': 0.0001375533237080175, 'samples': 18811968, 'steps': 97978, 'loss/train': 1.6705032587051392}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:06 - INFO - __main__ - Step 97983: {'lr': 0.0001375343655356331, 'samples': 18812736, 'steps': 97982, 'loss/train': 1.2457787990570068}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:08 - INFO - __main__ - Step 97987: {'lr': 0.00013751540817405312, 'samples': 18813504, 'steps': 97986, 'loss/train': 0.974490225315094}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:10 - INFO - __main__ - Step 97991: {'lr': 0.0001374964516234144, 'samples': 18814272, 'steps': 97990, 'loss/train': 1.2109510898590088}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:12 - INFO - __main__ - Step 97996: {'lr': 0.00013747275707571, 'samples': 18815232, 'steps': 97995, 'loss/train': 0.9514252543449402}8}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:14 - INFO - __main__ - Step 98000: {'lr': 0.00013745380235018846, 'samples': 18816000, 'steps': 97999, 'loss/train': 1.3948689699172974}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:14 - INFO - __main__ - Step 98000: {'lr': 0.00013745380235018846, 'samples': 18816000, 'steps': 97999, 'loss/train': 1.3948689699172974}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:17 - INFO - __main__ - Step 98007: {'lr': 0.0001374206335330038, 'samples': 18817344, 'steps': 98006, 'loss/train': 1.9875253438949585}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:20 - INFO - __main__ - Step 98012: {'lr': 0.00013739694304248202, 'samples': 18818304, 'steps': 98011, 'loss/train': 1.3120198249816895}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:22 - INFO - __main__ - Step 98016: {'lr': 0.00013737799156332144, 'samples': 18819072, 'steps': 98015, 'loss/train': 0.3856896758079529}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:24 - INFO - __main__ - Step 98020: {'lr': 0.00013735904089609273, 'samples': 18819840, 'steps': 98019, 'loss/train': 1.5010744333267212}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:24 - INFO - __main__ - Step 98020: {'lr': 0.00013735904089609273, 'samples': 18819840, 'steps': 98019, 'loss/train': 1.5010744333267212}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:27 - INFO - __main__ - Step 98027: {'lr': 0.0001373258791825642, 'samples': 18821184, 'steps': 98026, 'loss/train': 1.390015959739685}2}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:30 - INFO - __main__ - Step 98032: {'lr': 0.00013730219376736357, 'samples': 18822144, 'steps': 98031, 'loss/train': 1.3805707693099976}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:30 - INFO - __main__ - Step 98032: {'lr': 0.00013730219376736357, 'samples': 18822144, 'steps': 98031, 'loss/train': 1.3805707693099976}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:33 - INFO - __main__ - Step 98039: {'lr': 0.0001372690363188978, 'samples': 18823488, 'steps': 98038, 'loss/train': 1.5661981105804443}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:35 - INFO - __main__ - Step 98043: {'lr': 0.00013725009032292812, 'samples': 18824256, 'steps': 98042, 'loss/train': 1.317029356956482}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:38 - INFO - __main__ - Step 98048: {'lr': 0.00013722640897105798, 'samples': 18825216, 'steps': 98047, 'loss/train': 1.5964598655700684}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:40 - INFO - __main__ - Step 98053: {'lr': 0.0001372027288895387, 'samples': 18826176, 'steps': 98052, 'loss/train': 1.1730071306228638}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:42 - INFO - __main__ - Step 98057: {'lr': 0.0001371837857391553, 'samples': 18826944, 'steps': 98056, 'loss/train': 1.413114309310913}}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:42 - INFO - __main__ - Step 98057: {'lr': 0.0001371837857391553, 'samples': 18826944, 'steps': 98056, 'loss/train': 1.413114309310913}}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:45 - INFO - __main__ - Step 98064: {'lr': 0.00013715063718314647, 'samples': 18828288, 'steps': 98063, 'loss/train': 0.9453704357147217}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:48 - INFO - __main__ - Step 98069: {'lr': 0.00013712696116854287, 'samples': 18829248, 'steps': 98068, 'loss/train': 1.1537275314331055}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:50 - INFO - __main__ - Step 98074: {'lr': 0.00013710328642541062, 'samples': 18830208, 'steps': 98073, 'loss/train': 1.3729221820831299}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:50 - INFO - __main__ - Step 98074: {'lr': 0.00013710328642541062, 'samples': 18830208, 'steps': 98073, 'loss/train': 1.3729221820831299}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:53 - INFO - __main__ - Step 98080: {'lr': 0.00013707487841236931, 'samples': 18831360, 'steps': 98079, 'loss/train': 1.258007526397705}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:56 - INFO - __main__ - Step 98085: {'lr': 0.0001370512064674125, 'samples': 18832320, 'steps': 98084, 'loss/train': 0.04296347498893738}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:00:58 - INFO - __main__ - Step 98090: {'lr': 0.00013702753579478017, 'samples': 18833280, 'steps': 98089, 'loss/train': 1.2017964124679565}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:00 - INFO - __main__ - Step 98094: {'lr': 0.00013700860017292716, 'samples': 18834048, 'steps': 98093, 'loss/train': 1.2220146656036377}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:02 - INFO - __main__ - Step 98098: {'lr': 0.0001369896653656692, 'samples': 18834816, 'steps': 98097, 'loss/train': 1.1635990142822266}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:02 - INFO - __main__ - Step 98098: {'lr': 0.0001369896653656692, 'samples': 18834816, 'steps': 98097, 'loss/train': 1.1635990142822266}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:05 - INFO - __main__ - Step 98105: {'lr': 0.00013695653141349712, 'samples': 18836160, 'steps': 98104, 'loss/train': 1.1272742748260498}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:08 - INFO - __main__ - Step 98110: {'lr': 0.0001369328658328295, 'samples': 18837120, 'steps': 98109, 'loss/train': 1.5581170320510864}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:10 - INFO - __main__ - Step 98115: {'lr': 0.0001369092015258194, 'samples': 18838080, 'steps': 98114, 'loss/train': 1.1341944932937622}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:12 - INFO - __main__ - Step 98119: {'lr': 0.00013689027099742407, 'samples': 18838848, 'steps': 98118, 'loss/train': 1.0338398218154907}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:12 - INFO - __main__ - Step 98119: {'lr': 0.00013689027099742407, 'samples': 18838848, 'steps': 98118, 'loss/train': 1.0338398218154907}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:16 - INFO - __main__ - Step 98126: {'lr': 0.0001368571445349859, 'samples': 18840192, 'steps': 98125, 'loss/train': 1.0226839780807495}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:18 - INFO - __main__ - Step 98131: {'lr': 0.00013683348430547164, 'samples': 18841152, 'steps': 98130, 'loss/train': 1.5982780456542969}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:20 - INFO - __main__ - Step 98136: {'lr': 0.00013680982535073445, 'samples': 18842112, 'steps': 98135, 'loss/train': 1.1952072381973267}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:22 - INFO - __main__ - Step 98140: {'lr': 0.00013679089910496344, 'samples': 18842880, 'steps': 98139, 'loss/train': 1.1616300344467163}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:22 - INFO - __main__ - Step 98140: {'lr': 0.00013679089910496344, 'samples': 18842880, 'steps': 98139, 'loss/train': 1.1616300344467163}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:26 - INFO - __main__ - Step 98147: {'lr': 0.0001367577801388416, 'samples': 18844224, 'steps': 98146, 'loss/train': 1.2417876720428467}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:28 - INFO - __main__ - Step 98151: {'lr': 0.00013673885613785087, 'samples': 18844992, 'steps': 98150, 'loss/train': 1.17228102684021}}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:30 - INFO - __main__ - Step 98156: {'lr': 0.00013671520228488725, 'samples': 18845952, 'steps': 98155, 'loss/train': 1.4378468990325928}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:33 - INFO - __main__ - Step 98161: {'lr': 0.00013669154970803312, 'samples': 18846912, 'steps': 98160, 'loss/train': 1.2357975244522095}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:35 - INFO - __main__ - Step 98165: {'lr': 0.00013667262856552784, 'samples': 18847680, 'steps': 98164, 'loss/train': 1.5419600009918213}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:37 - INFO - __main__ - Step 98169: {'lr': 0.00013665370824003949, 'samples': 18848448, 'steps': 98168, 'loss/train': 1.328662633895874}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:38 - INFO - __main__ - Step 98173: {'lr': 0.00013663478873170458, 'samples': 18849216, 'steps': 98172, 'loss/train': 1.6211578845977783}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:40 - INFO - __main__ - Step 98177: {'lr': 0.0001366158700406595, 'samples': 18849984, 'steps': 98176, 'loss/train': 1.4336516857147217}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:43 - INFO - __main__ - Step 98182: {'lr': 0.00013659222282637483, 'samples': 18850944, 'steps': 98181, 'loss/train': 1.57320237159729}}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:43 - INFO - __main__ - Step 98182: {'lr': 0.00013659222282637483, 'samples': 18850944, 'steps': 98181, 'loss/train': 1.57320237159729}}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:47 - INFO - __main__ - Step 98189: {'lr': 0.00013655911887262728, 'samples': 18852288, 'steps': 98188, 'loss/train': 1.7194836139678955}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:48 - INFO - __main__ - Step 98193: {'lr': 0.0001365402034521055, 'samples': 18853056, 'steps': 98192, 'loss/train': 0.820099413394928}5}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:50 - INFO - __main__ - Step 98197: {'lr': 0.00013652128884955537, 'samples': 18853824, 'steps': 98196, 'loss/train': 1.5002152919769287}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:50 - INFO - __main__ - Step 98197: {'lr': 0.00013652128884955537, 'samples': 18853824, 'steps': 98196, 'loss/train': 1.5002152919769287}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:54 - INFO - __main__ - Step 98205: {'lr': 0.00013648346209891573, 'samples': 18855360, 'steps': 98204, 'loss/train': 1.4838238954544067}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:56 - INFO - __main__ - Step 98209: {'lr': 0.00013646454995109905, 'samples': 18856128, 'steps': 98208, 'loss/train': 0.8161880373954773}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:58 - INFO - __main__ - Step 98213: {'lr': 0.00013644563862179942, 'samples': 18856896, 'steps': 98212, 'loss/train': 1.3514961004257202}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:01:58 - INFO - __main__ - Step 98213: {'lr': 0.00013644563862179942, 'samples': 18856896, 'steps': 98212, 'loss/train': 1.3514961004257202}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:02 - INFO - __main__ - Step 98221: {'lr': 0.00013640781841929705, 'samples': 18858432, 'steps': 98220, 'loss/train': 1.3716034889221191}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:02 - INFO - __main__ - Step 98221: {'lr': 0.00013640781841929705, 'samples': 18858432, 'steps': 98220, 'loss/train': 1.3716034889221191}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:06 - INFO - __main__ - Step 98228: {'lr': 0.00013637472842917153, 'samples': 18859776, 'steps': 98227, 'loss/train': 1.1207438707351685}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:08 - INFO - __main__ - Step 98234: {'lr': 0.0001363463675771789, 'samples': 18860928, 'steps': 98233, 'loss/train': 0.7235524654388428}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:08 - INFO - __main__ - Step 98234: {'lr': 0.0001363463675771789, 'samples': 18860928, 'steps': 98233, 'loss/train': 0.7235524654388428}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:12 - INFO - __main__ - Step 98241: {'lr': 0.00013631328224663407, 'samples': 18862272, 'steps': 98240, 'loss/train': 1.4385548830032349}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:14 - INFO - __main__ - Step 98245: {'lr': 0.00013629437747037933, 'samples': 18863040, 'steps': 98244, 'loss/train': 1.074336290359497}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:16 - INFO - __main__ - Step 98250: {'lr': 0.00013627074765284192, 'samples': 18864000, 'steps': 98249, 'loss/train': 1.6777364015579224}4}█████████████████████��████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:16 - INFO - __main__ - Step 98250: {'lr': 0.00013627074765284192, 'samples': 18864000, 'steps': 98249, 'loss/train': 1.6777364015579224}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:16 - INFO - __main__ - Step 98250: {'lr': 0.00013627074765284192, 'samples': 18864000, 'steps': 98249, 'loss/train': 1.6777364015579224}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:22 - INFO - __main__ - Step 98260: {'lr': 0.00013622349186138166, 'samples': 18865920, 'steps': 98259, 'loss/train': 0.1321917623281479}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:25 - INFO - __main__ - Step 98266: {'lr': 0.00013619514084713426, 'samples': 18867072, 'steps': 98265, 'loss/train': 1.3228312730789185}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:25 - INFO - __main__ - Step 98266: {'lr': 0.00013619514084713426, 'samples': 18867072, 'steps': 98265, 'loss/train': 1.3228312730789185}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:28 - INFO - __main__ - Step 98273: {'lr': 0.00013616206699705943, 'samples': 18868416, 'steps': 98272, 'loss/train': 1.2607026100158691}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:30 - INFO - __main__ - Step 98278: {'lr': 0.0001361384443572004, 'samples': 18869376, 'steps': 98277, 'loss/train': 1.2759649753570557}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:33 - INFO - __main__ - Step 98283: {'lr': 0.00013611482299994787, 'samples': 18870336, 'steps': 98282, 'loss/train': 1.684382677078247}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:35 - INFO - __main__ - Step 98287: {'lr': 0.00013609592683780142, 'samples': 18871104, 'steps': 98286, 'loss/train': 1.7432996034622192}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:37 - INFO - __main__ - Step 98291: {'lr': 0.00013607703149682955, 'samples': 18871872, 'steps': 98290, 'loss/train': 1.1300022602081299}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:37 - INFO - __main__ - Step 98291: {'lr': 0.00013607703149682955, 'samples': 18871872, 'steps': 98290, 'loss/train': 1.1300022602081299}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:40 - INFO - __main__ - Step 98298: {'lr': 0.0001360439666264901, 'samples': 18873216, 'steps': 98297, 'loss/train': 1.2554845809936523}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:42 - INFO - __main__ - Step 98303: {'lr': 0.00013602035040232439, 'samples': 18874176, 'steps': 98302, 'loss/train': 1.425254464149475}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:45 - INFO - __main__ - Step 98308: {'lr': 0.00013599673546209535, 'samples': 18875136, 'steps': 98307, 'loss/train': 1.2419558763504028}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:45 - INFO - __main__ - Step 98308: {'lr': 0.00013599673546209535, 'samples': 18875136, 'steps': 98307, 'loss/train': 1.2419558763504028}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:48 - INFO - __main__ - Step 98314: {'lr': 0.00013596839922899165, 'samples': 18876288, 'steps': 98313, 'loss/train': 0.7850956320762634}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:51 - INFO - __main__ - Step 98319: {'lr': 0.00013594478711435987, 'samples': 18877248, 'steps': 98318, 'loss/train': 1.3887382745742798}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:51 - INFO - __main__ - Step 98319: {'lr': 0.00013594478711435987, 'samples': 18877248, 'steps': 98318, 'loss/train': 1.3887382745742798}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:54 - INFO - __main__ - Step 98326: {'lr': 0.00013591173231237874, 'samples': 18878592, 'steps': 98325, 'loss/train': 1.3830368518829346}4}█████��████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:56 - INFO - __main__ - Step 98331: {'lr': 0.000135888123281685, 'samples': 18879552, 'steps': 98330, 'loss/train': 1.6683658361434937}6}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:59 - INFO - __main__ - Step 98336: {'lr': 0.00013586451553641743, 'samples': 18880512, 'steps': 98335, 'loss/train': 1.3318308591842651}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:02:59 - INFO - __main__ - Step 98336: {'lr': 0.00013586451553641743, 'samples': 18880512, 'steps': 98335, 'loss/train': 1.3318308591842651}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:03 - INFO - __main__ - Step 98343: {'lr': 0.00013583146685306542, 'samples': 18881856, 'steps': 98342, 'loss/train': 1.3426573276519775}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:04 - INFO - __main__ - Step 98348: {'lr': 0.00013580786219390587, 'samples': 18882816, 'steps': 98347, 'loss/train': 1.8999954462051392}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:06 - INFO - __main__ - Step 98352: {'lr': 0.00013578897939272333, 'samples': 18883584, 'steps': 98351, 'loss/train': 1.4418045282363892}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:09 - INFO - __main__ - Step 98357: {'lr': 0.00013576537704915003, 'samples': 18884544, 'steps': 98356, 'loss/train': 1.2418649196624756}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:11 - INFO - __main__ - Step 98361: {'lr': 0.00013574649610078096, 'samples': 18885312, 'steps': 98360, 'loss/train': 1.3043992519378662}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:13 - INFO - __main__ - Step 98365: {'lr': 0.00013572761597610577, 'samples': 18886080, 'steps': 98364, 'loss/train': 5.212090015411377}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:14 - INFO - __main__ - Step 98369: {'lr': 0.00013570873667526062, 'samples': 18886848, 'steps': 98368, 'loss/train': 1.3635631799697876}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:16 - INFO - __main__ - Step 98373: {'lr': 0.00013568985819838148, 'samples': 18887616, 'steps': 98372, 'loss/train': 0.8819230198860168}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:19 - INFO - __main__ - Step 98378: {'lr': 0.00013566626126119226, 'samples': 18888576, 'steps': 98377, 'loss/train': 1.6655287742614746}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:21 - INFO - __main__ - Step 98382: {'lr': 0.00013564738463873438, 'samples': 18889344, 'steps': 98381, 'loss/train': 1.4288396835327148}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:23 - INFO - __main__ - Step 98386: {'lr': 0.00013562850884068486, 'samples': 18890112, 'steps': 98385, 'loss/train': 1.7386648654937744}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:24 - INFO - __main__ - Step 98390: {'lr': 0.00013560963386717996, 'samples': 18890880, 'steps': 98389, 'loss/train': 1.517714500427246}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:27 - INFO - __main__ - Step 98394: {'lr': 0.00013559075971835544, 'samples': 18891648, 'steps': 98393, 'loss/train': 0.8906887769699097}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:29 - INFO - __main__ - Step 98399: {'lr': 0.00013556716819223923, 'samples': 18892608, 'steps': 98398, 'loss/train': 1.3864307403564453}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:31 - INFO - __main__ - Step 98403: {'lr': 0.00013554829589944344, 'samples': 18893376, 'steps': 98402, 'loss/train': 1.4164586067199707}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:33 - INFO - __main__ - Step 98407: {'lr': 0.00013552942443177042, 'samples': 18894144, 'steps': 98406, 'loss/train': 1.1964280605316162}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:34 - INFO - __main__ - Step 98411: {'lr': 0.0001355105537893563, 'samples': 18894912, 'steps': 98410, 'loss/train': 1.569361925125122}2}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:37 - INFO - __main__ - Step 98415: {'lr': 0.00013549168397233692, 'samples': 18895680, 'steps': 98414, 'loss/train': 0.5137991309165955}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:39 - INFO - __main__ - Step 98420: {'lr': 0.00013546809786198137, 'samples': 18896640, 'steps': 98419, 'loss/train': 1.3054800033569336}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:41 - INFO - __main__ - Step 98424: {'lr': 0.0001354492299025979, 'samples': 18897408, 'steps': 98423, 'loss/train': 0.7076557278633118}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:41 - INFO - __main__ - Step 98424: {'lr': 0.0001354492299025979, 'samples': 18897408, 'steps': 98423, 'loss/train': 0.7076557278633118}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:44 - INFO - __main__ - Step 98431: {'lr': 0.00013541621296092856, 'samples': 18898752, 'steps': 98430, 'loss/train': 1.2383227348327637}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:46 - INFO - __main__ - Step 98435: {'lr': 0.00013539734727292398, 'samples': 18899520, 'steps': 98434, 'loss/train': 1.3349436521530151}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:49 - INFO - __main__ - Step 98440: {'lr': 0.00013537376632479325, 'samples': 18900480, 'steps': 98439, 'loss/train': 1.1633957624435425}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:51 - INFO - __main__ - Step 98445: {'lr': 0.0001353501866678828, 'samples': 18901440, 'steps': 98444, 'loss/train': 1.113924503326416}5}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:53 - INFO - __main__ - Step 98449: {'lr': 0.00013533132387221166, 'samples': 18902208, 'steps': 98448, 'loss/train': 1.286073923110962}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:55 - INFO - __main__ - Step 98453: {'lr': 0.00013531246190322743, 'samples': 18902976, 'steps': 98452, 'loss/train': 1.3400344848632812}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:57 - INFO - __main__ - Step 98457: {'lr': 0.00013529360076106612, 'samples': 18903744, 'steps': 98456, 'loss/train': 1.40067458152771}2}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:03:59 - INFO - __main__ - Step 98461: {'lr': 0.00013527474044586386, 'samples': 18904512, 'steps': 98460, 'loss/train': 1.0798609256744385}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:01 - INFO - __main__ - Step 98466: {'lr': 0.00013525116621497903, 'samples': 18905472, 'steps': 98465, 'loss/train': 1.6195857524871826}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:03 - INFO - __main__ - Step 98470: {'lr': 0.00013523230776093143, 'samples': 18906240, 'steps': 98469, 'loss/train': 1.2968119382858276}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:05 - INFO - __main__ - Step 98474: {'lr': 0.0001352134501342847, 'samples': 18907008, 'steps': 98473, 'loss/train': 1.2796759605407715}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:07 - INFO - __main__ - Step 98478: {'lr': 0.00013519459333517466, 'samples': 18907776, 'steps': 98477, 'loss/train': 1.5978097915649414}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:09 - INFO - __main__ - Step 98482: {'lr': 0.00013517573736373734, 'samples': 18908544, 'steps': 98481, 'loss/train': 1.6164947748184204}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:11 - INFO - __main__ - Step 98486: {'lr': 0.0001351568822201087, 'samples': 18909312, 'steps': 98485, 'loss/train': 1.2863751649856567}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:13 - INFO - __main__ - Step 98491: {'lr': 0.00013513331445488594, 'samples': 18910272, 'steps': 98490, 'loss/train': 1.2164909839630127}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:15 - INFO - __main__ - Step 98495: {'lr': 0.00013511446117432375, 'samples': 18911040, 'steps': 98494, 'loss/train': 1.2502626180648804}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:15 - INFO - __main__ - Step 98495: {'lr': 0.00013511446117432375, 'samples': 18911040, 'steps': 98494, 'loss/train': 1.2502626180648804}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:19 - INFO - __main__ - Step 98502: {'lr': 0.0001350814699263993, 'samples': 18912384, 'steps': 98501, 'loss/train': 1.3866060972213745}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:21 - INFO - __main__ - Step 98507: {'lr': 0.00013505790630268338, 'samples': 18913344, 'steps': 98506, 'loss/train': 1.027584433555603}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:23 - INFO - __main__ - Step 98512: {'lr': 0.00013503434397374578, 'samples': 18914304, 'steps': 98511, 'loss/train': 1.86878502368927}}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:23 - INFO - __main__ - Step 98512: {'lr': 0.00013503434397374578, 'samples': 18914304, 'steps': 98511, 'loss/train': 1.86878502368927}}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:26 - INFO - __main__ - Step 98518: {'lr': 0.0001350060708885019, 'samples': 18915456, 'steps': 98517, 'loss/train': 1.528324007987976}}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:28 - INFO - __main__ - Step 98522: {'lr': 0.00013498722320126738, 'samples': 18916224, 'steps': 98521, 'loss/train': 1.6278483867645264}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:31 - INFO - __main__ - Step 98527: {'lr': 0.0001349636647582573, 'samples': 18917184, 'steps': 98526, 'loss/train': 1.3802285194396973}}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:33 - INFO - __main__ - Step 98531: {'lr': 0.00013494481893684134, 'samples': 18917952, 'steps': 98530, 'loss/train': 1.2943000793457031}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:33 - INFO - __main__ - Step 98531: {'lr': 0.00013494481893684134, 'samples': 18917952, 'steps': 98530, 'loss/train': 1.2943000793457031}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:36 - INFO - __main__ - Step 98539: {'lr': 0.00013490712978256537, 'samples': 18919488, 'steps': 98538, 'loss/train': 1.4234387874603271}4}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:38 - INFO - __main__ - Step 98543: {'lr': 0.00013488828644997724, 'samples': 18920256, 'steps': 98542, 'loss/train': 0.36781924962997437}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:41 - INFO - __main__ - Step 98548: {'lr': 0.00013486473345127804, 'samples': 18921216, 'steps': 98547, 'loss/train': 0.9993444085121155}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:41 - INFO - __main__ - Step 98548: {'lr': 0.00013486473345127804, 'samples': 18921216, 'steps': 98547, 'loss/train': 0.9993444085121155}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:45 - INFO - __main__ - Step 98556: {'lr': 0.00013482705135113487, 'samples': 18922752, 'steps': 98555, 'loss/train': 1.1513434648513794}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:46 - INFO - __main__ - Step 98560: {'lr': 0.000134808211546479, 'samples': 18923520, 'steps': 98559, 'loss/train': 1.3050888776779175}4}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:48 - INFO - __main__ - Step 98564: {'lr': 0.00013478937257228142, 'samples': 18924288, 'steps': 98563, 'loss/train': 0.9965879321098328}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:51 - INFO - __main__ - Step 98569: {'lr': 0.00013476582502257336, 'samples': 18925248, 'steps': 98568, 'loss/train': 1.1334362030029297}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:53 - INFO - __main__ - Step 98574: {'lr': 0.00013474227877093375, 'samples': 18926208, 'steps': 98573, 'loss/train': 1.2779675722122192}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:53 - INFO - __main__ - Step 98574: {'lr': 0.00013474227877093375, 'samples': 18926208, 'steps': 98573, 'loss/train': 1.2779675722122192}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:57 - INFO - __main__ - Step 98581: {'lr': 0.00013470931619989846, 'samples': 18927552, 'steps': 98580, 'loss/train': 1.5833542346954346}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:04:59 - INFO - __main__ - Step 98585: {'lr': 0.000134690481587835, 'samples': 18928320, 'steps': 98584, 'loss/train': 1.2877286672592163}6}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:01 - INFO - __main__ - Step 98590: {'lr': 0.000134666939491797, 'samples': 18929280, 'steps': 98589, 'loss/train': 1.2452013492584229}6}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:01 - INFO - __main__ - Step 98590: {'lr': 0.000134666939491797, 'samples': 18929280, 'steps': 98589, 'loss/train': 1.2452013492584229}6}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:05 - INFO - __main__ - Step 98598: {'lr': 0.0001346292748405461, 'samples': 18930816, 'steps': 98597, 'loss/train': 1.262235164642334}6}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:07 - INFO - __main__ - Step 98602: {'lr': 0.00013461044376247516, 'samples': 18931584, 'steps': 98601, 'loss/train': 1.3136805295944214}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:09 - INFO - __main__ - Step 98606: {'lr': 0.00013459161351628827, 'samples': 18932352, 'steps': 98605, 'loss/train': 1.4113832712173462}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:11 - INFO - __main__ - Step 98611: {'lr': 0.00013456807687859852, 'samples': 18933312, 'steps': 98610, 'loss/train': 1.3829959630966187}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:13 - INFO - __main__ - Step 98615: {'lr': 0.00013454924850464712, 'samples': 18934080, 'steps': 98614, 'loss/train': 1.4574110507965088}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:13 - INFO - __main__ - Step 98615: {'lr': 0.00013454924850464712, 'samples': 18934080, 'steps': 98614, 'loss/train': 1.4574110507965088}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:17 - INFO - __main__ - Step 98622: {'lr': 0.00013451630085309647, 'samples': 18935424, 'steps': 98621, 'loss/train': 1.5499961376190186}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:19 - INFO - __main__ - Step 98627: {'lr': 0.00013449276837728725, 'samples': 18936384, 'steps': 98626, 'loss/train': 1.334861397743225}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:22 - INFO - __main__ - Step 98632: {'lr': 0.00013446923720262244, 'samples': 18937344, 'steps': 98631, 'loss/train': 1.7710411548614502}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:24 - INFO - __main__ - Step 98636: {'lr': 0.00013445041319989283, 'samples': 18938112, 'steps': 98635, 'loss/train': 1.2863768339157104}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:24 - INFO - __main__ - Step 98636: {'lr': 0.00013445041319989283, 'samples': 18938112, 'steps': 98635, 'loss/train': 1.2863768339157104}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:27 - INFO - __main__ - Step 98643: {'lr': 0.00013441747319969455, 'samples': 18939456, 'steps': 98642, 'loss/train': 1.1609183549880981}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:27 - INFO - __main__ - Step 98643: {'lr': 0.00013441747319969455, 'samples': 18939456, 'steps': 98642, 'loss/train': 1.1609183549880981}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:30 - INFO - __main__ - Step 98648: {'lr': 0.00013439394619047315, 'samples': 18940416, 'steps': 98647, 'loss/train': 0.8308822512626648}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:33 - INFO - __main__ - Step 98654: {'lr': 0.00013436571549841071, 'samples': 18941568, 'steps': 98653, 'loss/train': 1.381831169128418}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:33 - INFO - __main__ - Step 98654: {'lr': 0.00013436571549841071, 'samples': 18941568, 'steps': 98653, 'loss/train': 1.381831169128418}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:36 - INFO - __main__ - Step 98661: {'lr': 0.00013433278206172433, 'samples': 18942912, 'steps': 98660, 'loss/train': 1.9537456035614014}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:39 - INFO - __main__ - Step 98665: {'lr': 0.00013431396410159275, 'samples': 18943680, 'steps': 98664, 'loss/train': 1.3954282999038696}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:41 - INFO - __main__ - Step 98670: {'lr': 0.00013429044282428694, 'samples': 18944640, 'steps': 98669, 'loss/train': 2.4692530632019043}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:43 - INFO - __main__ - Step 98674: {'lr': 0.00013427162674089444, 'samples': 18945408, 'steps': 98673, 'loss/train': 1.6519277095794678}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:45 - INFO - __main__ - Step 98678: {'lr': 0.00013425281149182872, 'samples': 18946176, 'steps': 98677, 'loss/train': 1.1860836744308472}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:47 - INFO - __main__ - Step 98682: {'lr': 0.00013423399707722527, 'samples': 18946944, 'steps': 98681, 'loss/train': 0.8157587647438049}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:49 - INFO - __main__ - Step 98686: {'lr': 0.00013421518349721983, 'samples': 18947712, 'steps': 98685, 'loss/train': 1.3977375030517578}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:51 - INFO - __main__ - Step 98691: {'lr': 0.00013419166769607316, 'samples': 18948672, 'steps': 98690, 'loss/train': 1.3939487934112549}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:53 - INFO - __main__ - Step 98695: {'lr': 0.0001341728559944091, 'samples': 18949440, 'steps': 98694, 'loss/train': 0.5208776593208313}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:55 - INFO - __main__ - Step 98699: {'lr': 0.00013415404512778382, 'samples': 18950208, 'steps': 98698, 'loss/train': 0.6608111262321472}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:57 - INFO - __main__ - Step 98703: {'lr': 0.00013413523509633301, 'samples': 18950976, 'steps': 98702, 'loss/train': 0.9259989261627197}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:05:59 - INFO - __main__ - Step 98707: {'lr': 0.00013411642590019214, 'samples': 18951744, 'steps': 98706, 'loss/train': 1.2927075624465942}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:01 - INFO - __main__ - Step 98712: {'lr': 0.00013409291557987726, 'samples': 18952704, 'steps': 98711, 'loss/train': 1.3187243938446045}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:01 - INFO - __main__ - Step 98712: {'lr': 0.00013409291557987726, 'samples': 18952704, 'steps': 98711, 'loss/train': 1.3187243938446045}}}████████████████���█████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:06 - INFO - __main__ - Step 98720: {'lr': 0.00013405530178323282, 'samples': 18954240, 'steps': 98719, 'loss/train': 1.6318130493164062}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:06 - INFO - __main__ - Step 98720: {'lr': 0.00013405530178323282, 'samples': 18954240, 'steps': 98719, 'loss/train': 1.6318130493164062}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:09 - INFO - __main__ - Step 98727: {'lr': 0.00013402239245388365, 'samples': 18955584, 'steps': 98726, 'loss/train': 0.7239967584609985}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:11 - INFO - __main__ - Step 98732: {'lr': 0.0001339988873577521, 'samples': 18956544, 'steps': 98731, 'loss/train': 1.401559829711914}5}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:14 - INFO - __main__ - Step 98737: {'lr': 0.00013397538356832827, 'samples': 18957504, 'steps': 98736, 'loss/train': 1.1313494443893433}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:16 - INFO - __main__ - Step 98741: {'lr': 0.0001339565814777967, 'samples': 18958272, 'steps': 98740, 'loss/train': 1.219545841217041}3}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:18 - INFO - __main__ - Step 98745: {'lr': 0.00013393778022386326, 'samples': 18959040, 'steps': 98744, 'loss/train': 1.2968547344207764}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:19 - INFO - __main__ - Step 98749: {'lr': 0.00013391897980666323, 'samples': 18959808, 'steps': 98748, 'loss/train': 1.5466150045394897}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:21 - INFO - __main__ - Step 98753: {'lr': 0.00013390018022633223, 'samples': 18960576, 'steps': 98752, 'loss/train': 1.5349522829055786}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:21 - INFO - __main__ - Step 98753: {'lr': 0.00013390018022633223, 'samples': 18960576, 'steps': 98752, 'loss/train': 1.5349522829055786}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:26 - INFO - __main__ - Step 98761: {'lr': 0.00013386258357681968, 'samples': 18962112, 'steps': 98760, 'loss/train': 0.6261943578720093}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:27 - INFO - __main__ - Step 98765: {'lr': 0.00013384378650790907, 'samples': 18962880, 'steps': 98764, 'loss/train': 1.9698034524917603}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:29 - INFO - __main__ - Step 98769: {'lr': 0.0001338249902764096, 'samples': 18963648, 'steps': 98768, 'loss/train': 1.0816618204116821}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:32 - INFO - __main__ - Step 98774: {'lr': 0.00013380149616485127, 'samples': 18964608, 'steps': 98773, 'loss/train': 1.1713227033615112}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:32 - INFO - __main__ - Step 98774: {'lr': 0.00013380149616485127, 'samples': 18964608, 'steps': 98773, 'loss/train': 1.1713227033615112}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:36 - INFO - __main__ - Step 98782: {'lr': 0.00013376390830904496, 'samples': 18966144, 'steps': 98781, 'loss/train': 0.6799478530883789}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:37 - INFO - __main__ - Step 98786: {'lr': 0.00013374511563805472, 'samples': 18966912, 'steps': 98785, 'loss/train': 1.0036935806274414}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:39 - INFO - __main__ - Step 98790: {'lr': 0.0001337263238051869, 'samples': 18967680, 'steps': 98789, 'loss/train': 1.2703149318695068}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:42 - INFO - __main__ - Step 98795: {'lr': 0.00013370283519291827, 'samples': 18968640, 'steps': 98794, 'loss/train': 1.336119532585144}}}}���█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:42 - INFO - __main__ - Step 98795: {'lr': 0.00013370283519291827, 'samples': 18968640, 'steps': 98794, 'loss/train': 1.336119532585144}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:45 - INFO - __main__ - Step 98802: {'lr': 0.0001336699533366733, 'samples': 18969984, 'steps': 98801, 'loss/train': 1.9809859991073608}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:45 - INFO - __main__ - Step 98802: {'lr': 0.0001336699533366733, 'samples': 18969984, 'steps': 98801, 'loss/train': 1.9809859991073608}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:49 - INFO - __main__ - Step 98809: {'lr': 0.0001336370740488379, 'samples': 18971328, 'steps': 98808, 'loss/train': 1.6191954612731934}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:51 - INFO - __main__ - Step 98813: {'lr': 0.0001336182870378035, 'samples': 18972096, 'steps': 98812, 'loss/train': 1.6279008388519287}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:54 - INFO - __main__ - Step 98818: {'lr': 0.00013359480445392186, 'samples': 18973056, 'steps': 98817, 'loss/train': 1.6802738904953003}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:54 - INFO - __main__ - Step 98818: {'lr': 0.00013359480445392186, 'samples': 18973056, 'steps': 98817, 'loss/train': 1.6802738904953003}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:58 - INFO - __main__ - Step 98825: {'lr': 0.00013356193103946306, 'samples': 18974400, 'steps': 98824, 'loss/train': 0.24194471538066864}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:06:59 - INFO - __main__ - Step 98829: {'lr': 0.00013354314738538863, 'samples': 18975168, 'steps': 98828, 'loss/train': 1.3938204050064087}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:02 - INFO - __main__ - Step 98834: {'lr': 0.00013351966899846884, 'samples': 18976128, 'steps': 98833, 'loss/train': 1.4983659982681274}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:02 - INFO - __main__ - Step 98834: {'lr': 0.00013351966899846884, 'samples': 18976128, 'steps': 98833, 'loss/train': 1.4983659982681274}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:02 - INFO - __main__ - Step 98834: {'lr': 0.00013351966899846884, 'samples': 18976128, 'steps': 98833, 'loss/train': 1.4983659982681274}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:07 - INFO - __main__ - Step 98845: {'lr': 0.0001334680211662308, 'samples': 18978240, 'steps': 98844, 'loss/train': 1.6971997022628784}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:10 - INFO - __main__ - Step 98851: {'lr': 0.00013343985229907703, 'samples': 18979392, 'steps': 98850, 'loss/train': 1.6245990991592407}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:12 - INFO - __main__ - Step 98855: {'lr': 0.0001334210741046836, 'samples': 18980160, 'steps': 98854, 'loss/train': 1.265575885772705}7}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:12 - INFO - __main__ - Step 98855: {'lr': 0.0001334210741046836, 'samples': 18980160, 'steps': 98854, 'loss/train': 1.265575885772705}7}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:15 - INFO - __main__ - Step 98862: {'lr': 0.0001333882142869302, 'samples': 18981504, 'steps': 98861, 'loss/train': 1.5491455793380737}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:18 - INFO - __main__ - Step 98867: {'lr': 0.00013336474456479685, 'samples': 18982464, 'steps': 98866, 'loss/train': 1.7206683158874512}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:20 - INFO - __main__ - Step 98872: {'lr': 0.00013334127615651452, 'samples': 18983424, 'steps': 98871, 'loss/train': 1.1591172218322754}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:22 - INFO - __main__ - Step 98876: {'lr': 0.00013332250237603921, 'samples': 18984192, 'steps': 98875, 'loss/train': 1.5728108882904053}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:22 - INFO - __main__ - Step 98876: {'lr': 0.00013332250237603921, 'samples': 18984192, 'steps': 98875, 'loss/train': 1.5728108882904053}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:25 - INFO - __main__ - Step 98882: {'lr': 0.00013329434328256096, 'samples': 18985344, 'steps': 98881, 'loss/train': 1.0834996700286865}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:27 - INFO - __main__ - Step 98887: {'lr': 0.00013327087881741823, 'samples': 18986304, 'steps': 98886, 'loss/train': 1.692151665687561}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:27 - INFO - __main__ - Step 98887: {'lr': 0.00013327087881741823, 'samples': 18986304, 'steps': 98886, 'loss/train': 1.692151665687561}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:32 - INFO - __main__ - Step 98895: {'lr': 0.00013323333840830967, 'samples': 18987840, 'steps': 98894, 'loss/train': 1.6074554920196533}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:34 - INFO - __main__ - Step 98899: {'lr': 0.00013321456946640582, 'samples': 18988608, 'steps': 98898, 'loss/train': 1.361863374710083}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:35 - INFO - __main__ - Step 98903: {'lr': 0.00013319580136644948, 'samples': 18989376, 'steps': 98902, 'loss/train': 1.474034070968628}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:37 - INFO - __main__ - Step 98907: {'lr': 0.00013317703410857572, 'samples': 18990144, 'steps': 98906, 'loss/train': 1.3367795944213867}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:40 - INFO - __main__ - Step 98912: {'lr': 0.0001331535762206185, 'samples': 18991104, 'steps': 98911, 'loss/train': 1.5746128559112549}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:40 - INFO - __main__ - Step 98912: {'lr': 0.0001331535762206185, 'samples': 18991104, 'steps': 98911, 'loss/train': 1.5746128559112549}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:44 - INFO - __main__ - Step 98920: {'lr': 0.0001331160463377551, 'samples': 18992640, 'steps': 98919, 'loss/train': 1.231615662574768}}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:46 - INFO - __main__ - Step 98924: {'lr': 0.00013309728266024223, 'samples': 18993408, 'steps': 98923, 'loss/train': 1.1150457859039307}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:47 - INFO - __main__ - Step 98928: {'lr': 0.0001330785198255225, 'samples': 18994176, 'steps': 98927, 'loss/train': 1.5267914533615112}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:49 - INFO - __main__ - Step 98932: {'lr': 0.00013305975783373082, 'samples': 18994944, 'steps': 98931, 'loss/train': 1.2531720399856567}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:52 - INFO - __main__ - Step 98938: {'lr': 0.00013303161642682978, 'samples': 18996096, 'steps': 98937, 'loss/train': 1.2989174127578735}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:52 - INFO - __main__ - Step 98938: {'lr': 0.00013303161642682978, 'samples': 18996096, 'steps': 98937, 'loss/train': 1.2989174127578735}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:56 - INFO - __main__ - Step 98945: {'lr': 0.00013299878718351594, 'samples': 18997440, 'steps': 98944, 'loss/train': 0.44292888045310974}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:07:57 - INFO - __main__ - Step 98949: {'lr': 0.00013298002877567834, 'samples': 18998208, 'steps': 98948, 'loss/train': 1.2932748794555664}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:00 - INFO - __main__ - Step 98953: {'lr': 0.00013296127121147894, 'samples': 18998976, 'steps': 98952, 'loss/train': 1.1648809909820557}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:02 - INFO - __main__ - Step 98958: {'lr': 0.00013293782544280213, 'samples': 18999936, 'steps': 98957, 'loss/train': 1.9054423570632935}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:04 - INFO - __main__ - Step 98962: {'lr': 0.0001329190697772833, 'samples': 19000704, 'steps': 98961, 'loss/train': 1.4839279651641846}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:06 - INFO - __main__ - Step 98966: {'lr': 0.00013290031495584225, 'samples': 19001472, 'steps': 98965, 'loss/train': 1.5449353456497192}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:08 - INFO - __main__ - Step 98970: {'lr': 0.00013288156097861415, 'samples': 19002240, 'steps': 98969, 'loss/train': 1.5489603281021118}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:10 - INFO - __main__ - Step 98974: {'lr': 0.00013286280784573435, 'samples': 19003008, 'steps': 98973, 'loss/train': 1.405431866645813}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:12 - INFO - __main__ - Step 98979: {'lr': 0.0001328393676172051, 'samples': 19003968, 'steps': 98978, 'loss/train': 1.3811395168304443}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:12 - INFO - __main__ - Step 98979: {'lr': 0.0001328393676172051, 'samples': 19003968, 'steps': 98978, 'loss/train': 1.3811395168304443}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:15 - INFO - __main__ - Step 98986: {'lr': 0.0001328065535145358, 'samples': 19005312, 'steps': 98985, 'loss/train': 0.9041839838027954}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:18 - INFO - __main__ - Step 98990: {'lr': 0.00013278780376040056, 'samples': 19006080, 'steps': 98989, 'loss/train': 1.063883900642395}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:20 - INFO - __main__ - Step 98995: {'lr': 0.00013276436775606248, 'samples': 19007040, 'steps': 98994, 'loss/train': 1.2664657831192017}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:20 - INFO - __main__ - Step 98995: {'lr': 0.00013276436775606248, 'samples': 19007040, 'steps': 98994, 'loss/train': 1.2664657831192017}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:24 - INFO - __main__ - Step 99003: {'lr': 0.00013272687289610897, 'samples': 19008576, 'steps': 99002, 'loss/train': 1.561203956604004}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:26 - INFO - __main__ - Step 99007: {'lr': 0.00013270812673425963, 'samples': 19009344, 'steps': 99006, 'loss/train': 1.0511279106140137}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:28 - INFO - __main__ - Step 99011: {'lr': 0.00013268938141800885, 'samples': 19010112, 'steps': 99010, 'loss/train': 0.9778432846069336}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:30 - INFO - __main__ - Step 99016: {'lr': 0.0001326659509620243, 'samples': 19011072, 'steps': 99015, 'loss/train': 1.4485821723937988}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:32 - INFO - __main__ - Step 99020: {'lr': 0.00013264720754886428, 'samples': 19011840, 'steps': 99019, 'loss/train': 1.1889883279800415}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:34 - INFO - __main__ - Step 99024: {'lr': 0.00013262846498174203, 'samples': 19012608, 'steps': 99023, 'loss/train': 1.4039644002914429}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:36 - INFO - __main__ - Step 99028: {'lr': 0.00013260972326079268, 'samples': 19013376, 'steps': 99027, 'loss/train': 1.8564770221710205}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:38 - INFO - __main__ - Step 99032: {'lr': 0.0001325909823861512, 'samples': 19014144, 'steps': 99031, 'loss/train': 1.664642572402954}5}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:38 - INFO - __main__ - Step 99032: {'lr': 0.0001325909823861512, 'samples': 19014144, 'steps': 99031, 'loss/train': 1.664642572402954}5}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:42 - INFO - __main__ - Step 99040: {'lr': 0.00013255350317633265, 'samples': 19015680, 'steps': 99039, 'loss/train': 1.413082480430603}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:44 - INFO - __main__ - Step 99044: {'lr': 0.00013253476484142567, 'samples': 19016448, 'steps': 99043, 'loss/train': 0.0484987273812294}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:46 - INFO - __main__ - Step 99048: {'lr': 0.00013251602735336705, 'samples': 19017216, 'steps': 99047, 'loss/train': 1.2453235387802124}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:48 - INFO - __main__ - Step 99053: {'lr': 0.00013249260668438017, 'samples': 19018176, 'steps': 99052, 'loss/train': 1.696810007095337}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:48 - INFO - __main__ - Step 99053: {'lr': 0.00013249260668438017, 'samples': 19018176, 'steps': 99052, 'loss/train': 1.696810007095337}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:48 - INFO - __main__ - Step 99053: {'lr': 0.00013249260668438017, 'samples': 19018176, 'steps': 99052, 'loss/train': 1.696810007095337}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:54 - INFO - __main__ - Step 99064: {'lr': 0.00013244108587231784, 'samples': 19020288, 'steps': 99063, 'loss/train': 1.1649279594421387}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:57 - INFO - __main__ - Step 99069: {'lr': 0.00013241766944002104, 'samples': 19021248, 'steps': 99068, 'loss/train': 1.2806930541992188}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:59 - INFO - __main__ - Step 99073: {'lr': 0.0001323989372478249, 'samples': 19022016, 'steps': 99072, 'loss/train': 0.9023018479347229}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:08:59 - INFO - __main__ - Step 99073: {'lr': 0.0001323989372478249, 'samples': 19022016, 'steps': 99072, 'loss/train': 0.9023018479347229}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:02 - INFO - __main__ - Step 99080: {'lr': 0.00013236615795164818, 'samples': 19023360, 'steps': 99079, 'loss/train': 1.4458521604537964}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:02 - INFO - __main__ - Step 99080: {'lr': 0.00013236615795164818, 'samples': 19023360, 'steps': 99079, 'loss/train': 1.4458521604537964}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:06 - INFO - __main__ - Step 99088: {'lr': 0.0001323286990791565, 'samples': 19024896, 'steps': 99087, 'loss/train': 1.4551652669906616}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:08 - INFO - __main__ - Step 99092: {'lr': 0.00013230997091534413, 'samples': 19025664, 'steps': 99091, 'loss/train': 1.274825096130371}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:10 - INFO - __main__ - Step 99096: {'lr': 0.00013229124360000078, 'samples': 19026432, 'steps': 99095, 'loss/train': 1.3457118272781372}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:12 - INFO - __main__ - Step 99100: {'lr': 0.00013227251713326133, 'samples': 19027200, 'steps': 99099, 'loss/train': 1.4814577102661133}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:14 - INFO - __main__ - Step 99105: {'lr': 0.00013224911024339205, 'samples': 19028160, 'steps': 99104, 'loss/train': 1.4790033102035522}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:16 - INFO - __main__ - Step 99109: {'lr': 0.0001322303856865053, 'samples': 19028928, 'steps': 99108, 'loss/train': 0.9933347702026367}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:16 - INFO - __main__ - Step 99109: {'lr': 0.0001322303856865053, 'samples': 19028928, 'steps': 99108, 'loss/train': 0.9933347702026367}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:20 - INFO - __main__ - Step 99116: {'lr': 0.00013219761975504356, 'samples': 19030272, 'steps': 99115, 'loss/train': 1.317287564277649}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:22 - INFO - __main__ - Step 99121: {'lr': 0.0001321742171106411, 'samples': 19031232, 'steps': 99120, 'loss/train': 1.2958383560180664}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:24 - INFO - __main__ - Step 99125: {'lr': 0.00013215549595073505, 'samples': 19032000, 'steps': 99124, 'loss/train': 1.166322946548462}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:26 - INFO - __main__ - Step 99129: {'lr': 0.0001321367756404117, 'samples': 19032768, 'steps': 99128, 'loss/train': 1.2974028587341309}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:28 - INFO - __main__ - Step 99133: {'lr': 0.00013211805617980598, 'samples': 19033536, 'steps': 99132, 'loss/train': 1.5705078840255737}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:30 - INFO - __main__ - Step 99137: {'lr': 0.00013209933756905273, 'samples': 19034304, 'steps': 99136, 'loss/train': 1.5316345691680908}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:32 - INFO - __main__ - Step 99142: {'lr': 0.00013207594050092193, 'samples': 19035264, 'steps': 99141, 'loss/train': 1.024368166923523}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:32 - INFO - __main__ - Step 99142: {'lr': 0.00013207594050092193, 'samples': 19035264, 'steps': 99141, 'loss/train': 1.024368166923523}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:36 - INFO - __main__ - Step 99150: {'lr': 0.00013203850795502997, 'samples': 19036800, 'steps': 99149, 'loss/train': 1.259636640548706}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:38 - INFO - __main__ - Step 99154: {'lr': 0.00013201979295765555, 'samples': 19037568, 'steps': 99153, 'loss/train': 1.3441728353500366}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:40 - INFO - __main__ - Step 99158: {'lr': 0.0001320010788108421, 'samples': 19038336, 'steps': 99157, 'loss/train': 1.8779852390289307}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:42 - INFO - __main__ - Step 99163: {'lr': 0.0001319776873236323, 'samples': 19039296, 'steps': 99162, 'loss/train': 2.4107284545898438}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:42 - INFO - __main__ - Step 99163: {'lr': 0.0001319776873236323, 'samples': 19039296, 'steps': 99162, 'loss/train': 2.4107284545898438}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:47 - INFO - __main__ - Step 99171: {'lr': 0.00013194026370951572, 'samples': 19040832, 'steps': 99170, 'loss/train': 1.3633341789245605}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:48 - INFO - __main__ - Step 99175: {'lr': 0.0001319215531790916, 'samples': 19041600, 'steps': 99174, 'loss/train': 1.4919836521148682}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:50 - INFO - __main__ - Step 99179: {'lr': 0.00013190284349993658, 'samples': 19042368, 'steps': 99178, 'loss/train': 1.0268223285675049}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:52 - INFO - __main__ - Step 99184: {'lr': 0.00013187945759829576, 'samples': 19043328, 'steps': 99183, 'loss/train': 1.4916070699691772}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:55 - INFO - __main__ - Step 99189: {'lr': 0.00013185607302723716, 'samples': 19044288, 'steps': 99188, 'loss/train': 1.085240125656128}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:57 - INFO - __main__ - Step 99193: {'lr': 0.00013183736632858657, 'samples': 19045056, 'steps': 99192, 'loss/train': 0.578855037689209}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:09:57 - INFO - __main__ - Step 99193: {'lr': 0.00013183736632858657, 'samples': 19045056, 'steps': 99192, 'loss/train': 0.578855037689209}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:00 - INFO - __main__ - Step 99200: {'lr': 0.00013180463165585627, 'samples': 19046400, 'steps': 99199, 'loss/train': 1.4668654203414917}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:03 - INFO - __main__ - Step 99205: {'lr': 0.00013178125134443136, 'samples': 19047360, 'steps': 99204, 'loss/train': 1.1186803579330444}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:05 - INFO - __main__ - Step 99210: {'lr': 0.00013175787236469495, 'samples': 19048320, 'steps': 99209, 'loss/train': 1.3284562826156616}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:05 - INFO - __main__ - Step 99210: {'lr': 0.00013175787236469495, 'samples': 19048320, 'steps': 99209, 'loss/train': 1.3284562826156616}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:05 - INFO - __main__ - Step 99210: {'lr': 0.00013175787236469495, 'samples': 19048320, 'steps': 99209, 'loss/train': 1.3284562826156616}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:10 - INFO - __main__ - Step 99220: {'lr': 0.00013171111840134142, 'samples': 19050240, 'steps': 99219, 'loss/train': 0.972144603729248}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:12 - INFO - __main__ - Step 99225: {'lr': 0.00013168774341825086, 'samples': 19051200, 'steps': 99224, 'loss/train': 1.4078203439712524}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:15 - INFO - __main__ - Step 99229: {'lr': 0.00013166904439134005, 'samples': 19051968, 'steps': 99228, 'loss/train': 0.7313032150268555}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:17 - INFO - __main__ - Step 99233: {'lr': 0.00013165034621751882, 'samples': 19052736, 'steps': 99232, 'loss/train': 1.2843306064605713}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:18 - INFO - __main__ - Step 99237: {'lr': 0.00013163164889692198, 'samples': 19053504, 'steps': 99236, 'loss/train': 1.1814903020858765}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:20 - INFO - __main__ - Step 99241: {'lr': 0.00013161295242968452, 'samples': 19054272, 'steps': 99240, 'loss/train': 1.3997892141342163}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:20 - INFO - __main__ - Step 99241: {'lr': 0.00013161295242968452, 'samples': 19054272, 'steps': 99240, 'loss/train': 1.3997892141342163}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:25 - INFO - __main__ - Step 99249: {'lr': 0.00013157556205582626, 'samples': 19055808, 'steps': 99248, 'loss/train': 1.725691795349121}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:25 - INFO - __main__ - Step 99249: {'lr': 0.00013157556205582626, 'samples': 19055808, 'steps': 99248, 'loss/train': 1.725691795349121}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:28 - INFO - __main__ - Step 99256: {'lr': 0.0001315428482800753, 'samples': 19057152, 'steps': 99255, 'loss/train': 1.3475888967514038}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:31 - INFO - __main__ - Step 99262: {'lr': 0.00013151480998245633, 'samples': 19058304, 'steps': 99261, 'loss/train': 1.1504853963851929}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:31 - INFO - __main__ - Step 99262: {'lr': 0.00013151480998245633, 'samples': 19058304, 'steps': 99261, 'loss/train': 1.1504853963851929}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:34 - INFO - __main__ - Step 99269: {'lr': 0.00013148210106440195, 'samples': 19059648, 'steps': 99268, 'loss/train': 1.5916181802749634}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:36 - INFO - __main__ - Step 99273: {'lr': 0.0001314634114288902, 'samples': 19060416, 'steps': 99272, 'loss/train': 1.147074818611145}4}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:38 - INFO - __main__ - Step 99277: {'lr': 0.00013144472264795058, 'samples': 19061184, 'steps': 99276, 'loss/train': 1.2516379356384277}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:41 - INFO - __main__ - Step 99282: {'lr': 0.00013142136287372342, 'samples': 19062144, 'steps': 99281, 'loss/train': 1.1871638298034668}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:43 - INFO - __main__ - Step 99286: {'lr': 0.0001314026760160637, 'samples': 19062912, 'steps': 99285, 'loss/train': 1.4563300609588623}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:45 - INFO - __main__ - Step 99290: {'lr': 0.00013138399001341394, 'samples': 19063680, 'steps': 99289, 'loss/train': 1.797187328338623}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:46 - INFO - __main__ - Step 99294: {'lr': 0.00013136530486590887, 'samples': 19064448, 'steps': 99293, 'loss/train': 1.6220754384994507}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:48 - INFO - __main__ - Step 99298: {'lr': 0.0001313466205736833, 'samples': 19065216, 'steps': 99297, 'loss/train': 1.4711822271347046}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:51 - INFO - __main__ - Step 99303: {'lr': 0.00013132326641134313, 'samples': 19066176, 'steps': 99302, 'loss/train': 1.4038728475570679}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:51 - INFO - __main__ - Step 99303: {'lr': 0.00013132326641134313, 'samples': 19066176, 'steps': 99302, 'loss/train': 1.4038728475570679}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:55 - INFO - __main__ - Step 99310: {'lr': 0.00013129057283002988, 'samples': 19067520, 'steps': 99309, 'loss/train': 0.7491765022277832}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:56 - INFO - __main__ - Step 99314: {'lr': 0.00013127189196026883, 'samples': 19068288, 'steps': 99313, 'loss/train': 1.0305227041244507}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:10:58 - INFO - __main__ - Step 99318: {'lr': 0.0001312532119464606, 'samples': 19069056, 'steps': 99317, 'loss/train': 1.376615047454834}7}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:01 - INFO - __main__ - Step 99323: {'lr': 0.0001312298631330893, 'samples': 19070016, 'steps': 99322, 'loss/train': 0.5027155876159668}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:01 - INFO - __main__ - Step 99323: {'lr': 0.0001312298631330893, 'samples': 19070016, 'steps': 99322, 'loss/train': 0.5027155876159668}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:04 - INFO - __main__ - Step 99330: {'lr': 0.00013119717704209986, 'samples': 19071360, 'steps': 99329, 'loss/train': 1.1465250253677368}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:06 - INFO - __main__ - Step 99334: {'lr': 0.0001311785004534497, 'samples': 19072128, 'steps': 99333, 'loss/train': 1.0953712463378906}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:08 - INFO - __main__ - Step 99339: {'lr': 0.0001311551559222834, 'samples': 19073088, 'steps': 99338, 'loss/train': 1.5316916704177856}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:11 - INFO - __main__ - Step 99344: {'lr': 0.00013113181272985834, 'samples': 19074048, 'steps': 99343, 'loss/train': 1.7406561374664307}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:13 - INFO - __main__ - Step 99348: {'lr': 0.0001311131391399888, 'samples': 19074816, 'steps': 99347, 'loss/train': 1.5657298564910889}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:13 - INFO - __main__ - Step 99348: {'lr': 0.0001311131391399888, 'samples': 19074816, 'steps': 99347, 'loss/train': 1.5657298564910889}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:16 - INFO - __main__ - Step 99355: {'lr': 0.0001310804624201885, 'samples': 19076160, 'steps': 99354, 'loss/train': 1.4215375185012817}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:19 - INFO - __main__ - Step 99360: {'lr': 0.00013105712351350264, 'samples': 19077120, 'steps': 99359, 'loss/train': 1.180750846862793}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:19 - INFO - __main__ - Step 99360: {'lr': 0.00013105712351350264, 'samples': 19077120, 'steps': 99359, 'loss/train': 1.180750846862793}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:23 - INFO - __main__ - Step 99368: {'lr': 0.00013101978404979353, 'samples': 19078656, 'steps': 99367, 'loss/train': 1.112125277519226}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:24 - INFO - __main__ - Step 99372: {'lr': 0.00013100111560452725, 'samples': 19079424, 'steps': 99371, 'loss/train': 1.3321503400802612}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:27 - INFO - __main__ - Step 99376: {'lr': 0.000130982448017166, 'samples': 19080192, 'steps': 99375, 'loss/train': 1.809155821800232}12}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:29 - INFO - __main__ - Step 99381: {'lr': 0.00013095911473959827, 'samples': 19081152, 'steps': 99380, 'loss/train': 1.1611515283584595}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:31 - INFO - __main__ - Step 99385: {'lr': 0.0001309404490830152, 'samples': 19081920, 'steps': 99384, 'loss/train': 0.5549300312995911}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:31 - INFO - __main__ - Step 99385: {'lr': 0.0001309404490830152, 'samples': 19081920, 'steps': 99384, 'loss/train': 0.5549300312995911}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:34 - INFO - __main__ - Step 99392: {'lr': 0.00013090778624946211, 'samples': 19083264, 'steps': 99391, 'loss/train': 0.5832856297492981}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:37 - INFO - __main__ - Step 99396: {'lr': 0.00013088912295364428, 'samples': 19084032, 'steps': 99395, 'loss/train': 1.8238142728805542}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:39 - INFO - __main__ - Step 99401: {'lr': 0.00013086579504145203, 'samples': 19084992, 'steps': 99400, 'loss/train': 1.5472619533538818}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:41 - INFO - __main__ - Step 99405: {'lr': 0.00013084713367792628, 'samples': 19085760, 'steps': 99404, 'loss/train': 1.7505402565002441}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:43 - INFO - __main__ - Step 99409: {'lr': 0.00013082847317341556, 'samples': 19086528, 'steps': 99408, 'loss/train': 1.1511167287826538}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:45 - INFO - __main__ - Step 99413: {'lr': 0.00013080981352805445, 'samples': 19087296, 'steps': 99412, 'loss/train': 1.3874880075454712}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:47 - INFO - __main__ - Step 99417: {'lr': 0.0001307911547419776, 'samples': 19088064, 'steps': 99416, 'loss/train': 1.0921225547790527}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:49 - INFO - __main__ - Step 99422: {'lr': 0.00013076783246795463, 'samples': 19089024, 'steps': 99421, 'loss/train': 2.1595160961151123}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:51 - INFO - __main__ - Step 99426: {'lr': 0.00013074917561575877, 'samples': 19089792, 'steps': 99425, 'loss/train': 1.1056419610977173}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:51 - INFO - __main__ - Step 99426: {'lr': 0.00013074917561575877, 'samples': 19089792, 'steps': 99425, 'loss/train': 1.1056419610977173}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:54 - INFO - __main__ - Step 99433: {'lr': 0.00013071652819320146, 'samples': 19091136, 'steps': 99432, 'loss/train': 1.503124475479126}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:57 - INFO - __main__ - Step 99438: {'lr': 0.00013069321021803718, 'samples': 19092096, 'steps': 99437, 'loss/train': 1.299461841583252}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:59 - INFO - __main__ - Step 99443: {'lr': 0.00013066989358681796, 'samples': 19093056, 'steps': 99442, 'loss/train': 0.9239675998687744}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:11:59 - INFO - __main__ - Step 99443: {'lr': 0.00013066989358681796, 'samples': 19093056, 'steps': 99442, 'loss/train': 0.9239675998687744}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:02 - INFO - __main__ - Step 99450: {'lr': 0.00013063725256143852, 'samples': 19094400, 'steps': 99449, 'loss/train': 1.0777900218963623}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:04 - INFO - __main__ - Step 99454: {'lr': 0.0001306186017301161, 'samples': 19095168, 'steps': 99453, 'loss/train': 1.3486965894699097}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:07 - INFO - __main__ - Step 99459: {'lr': 0.00013059528940128563, 'samples': 19096128, 'steps': 99458, 'loss/train': 1.6659141778945923}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:09 - INFO - __main__ - Step 99464: {'lr': 0.00013057197841750322, 'samples': 19097088, 'steps': 99463, 'loss/train': 1.2491772174835205}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:09 - INFO - __main__ - Step 99464: {'lr': 0.00013057197841750322, 'samples': 19097088, 'steps': 99463, 'loss/train': 1.2491772174835205}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:13 - INFO - __main__ - Step 99471: {'lr': 0.0001305393453003883, 'samples': 19098432, 'steps': 99470, 'loss/train': 1.4166969060897827}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:15 - INFO - __main__ - Step 99475: {'lr': 0.00013052069898904478, 'samples': 19099200, 'steps': 99474, 'loss/train': 1.091049313545227}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:17 - INFO - __main__ - Step 99480: {'lr': 0.0001304973923111804, 'samples': 19100160, 'steps': 99479, 'loss/train': 1.3459457159042358}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:17 - INFO - __main__ - Step 99480: {'lr': 0.0001304973923111804, 'samples': 19100160, 'steps': 99479, 'loss/train': 1.3459457159042358}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:17 - INFO - __main__ - Step 99480: {'lr': 0.0001304973923111804, 'samples': 19100160, 'steps': 99479, 'loss/train': 1.3459457159042358}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:23 - INFO - __main__ - Step 99491: {'lr': 0.00013044612235869923, 'samples': 19102272, 'steps': 99490, 'loss/train': 1.4002193212509155}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:25 - INFO - __main__ - Step 99496: {'lr': 0.0001304228199894415, 'samples': 19103232, 'steps': 99495, 'loss/train': 0.9725179076194763}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:27 - INFO - __main__ - Step 99500: {'lr': 0.00013040417906385598, 'samples': 19104000, 'steps': 99499, 'loss/train': 1.2365241050720215}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:29 - INFO - __main__ - Step 99504: {'lr': 0.000130385539000479, 'samples': 19104768, 'steps': 99503, 'loss/train': 1.5786142349243164}5}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:32 - INFO - __main__ - Step 99508: {'lr': 0.00013036689979944492, 'samples': 19105536, 'steps': 99507, 'loss/train': 2.0829052925109863}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:33 - INFO - __main__ - Step 99512: {'lr': 0.0001303482614608882, 'samples': 19106304, 'steps': 99511, 'loss/train': 1.5774052143096924}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:35 - INFO - __main__ - Step 99516: {'lr': 0.00013032962398494297, 'samples': 19107072, 'steps': 99515, 'loss/train': 1.3778257369995117}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:38 - INFO - __main__ - Step 99521: {'lr': 0.00013030632835326378, 'samples': 19108032, 'steps': 99520, 'loss/train': 1.3969788551330566}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:38 - INFO - __main__ - Step 99521: {'lr': 0.00013030632835326378, 'samples': 19108032, 'steps': 99520, 'loss/train': 1.3969788551330566}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:41 - INFO - __main__ - Step 99528: {'lr': 0.00013027371673412087, 'samples': 19109376, 'steps': 99527, 'loss/train': 1.1618123054504395}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:43 - INFO - __main__ - Step 99532: {'lr': 0.00013025508270996574, 'samples': 19110144, 'steps': 99531, 'loss/train': 1.4856802225112915}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:43 - INFO - __main__ - Step 99532: {'lr': 0.00013025508270996574, 'samples': 19110144, 'steps': 99531, 'loss/train': 1.4856802225112915}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:47 - INFO - __main__ - Step 99540: {'lr': 0.00013021781725164016, 'samples': 19111680, 'steps': 99539, 'loss/train': 1.2735601663589478}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:48 - INFO - __main__ - Step 99544: {'lr': 0.0001301991858177382, 'samples': 19112448, 'steps': 99543, 'loss/train': 1.4960018396377563}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:51 - INFO - __main__ - Step 99548: {'lr': 0.00013018055524752266, 'samples': 19113216, 'steps': 99547, 'loss/train': 1.3063549995422363}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:53 - INFO - __main__ - Step 99553: {'lr': 0.0001301572682495169, 'samples': 19114176, 'steps': 99552, 'loss/train': 1.5929239988327026}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:55 - INFO - __main__ - Step 99558: {'lr': 0.00013013398260149317, 'samples': 19115136, 'steps': 99557, 'loss/train': 1.2603482007980347}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:55 - INFO - __main__ - Step 99558: {'lr': 0.00013013398260149317, 'samples': 19115136, 'steps': 99557, 'loss/train': 1.2603482007980347}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:12:59 - INFO - __main__ - Step 99565: {'lr': 0.00013010138496272945, 'samples': 19116480, 'steps': 99564, 'loss/train': 1.4642747640609741}}}█████████████████████��████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:01 - INFO - __main__ - Step 99569: {'lr': 0.0001300827589290708, 'samples': 19117248, 'steps': 99568, 'loss/train': 1.5632964372634888}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:03 - INFO - __main__ - Step 99574: {'lr': 0.0001300594776027525, 'samples': 19118208, 'steps': 99573, 'loss/train': 1.303639531135559}}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:06 - INFO - __main__ - Step 99579: {'lr': 0.00013003619762751804, 'samples': 19119168, 'steps': 99578, 'loss/train': 1.166676640510559}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:06 - INFO - __main__ - Step 99579: {'lr': 0.00013003619762751804, 'samples': 19119168, 'steps': 99578, 'loss/train': 1.166676640510559}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:10 - INFO - __main__ - Step 99586: {'lr': 0.0001300036079325096, 'samples': 19120512, 'steps': 99585, 'loss/train': 0.9676076769828796}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:11 - INFO - __main__ - Step 99590: {'lr': 0.00012998498643910906, 'samples': 19121280, 'steps': 99589, 'loss/train': 0.4941423833370209}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:13 - INFO - __main__ - Step 99594: {'lr': 0.00012996636581093904, 'samples': 19122048, 'steps': 99593, 'loss/train': 1.3959218263626099}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:15 - INFO - __main__ - Step 99599: {'lr': 0.00012994309124266158, 'samples': 19123008, 'steps': 99598, 'loss/train': 1.0203458070755005}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:18 - INFO - __main__ - Step 99603: {'lr': 0.00012992447256175124, 'samples': 19123776, 'steps': 99602, 'loss/train': 1.5792347192764282}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:20 - INFO - __main__ - Step 99607: {'lr': 0.0001299058547465079, 'samples': 19124544, 'steps': 99606, 'loss/train': 1.6377439498901367}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:21 - INFO - __main__ - Step 99611: {'lr': 0.00012988723779706554, 'samples': 19125312, 'steps': 99610, 'loss/train': 2.103031873703003}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:23 - INFO - __main__ - Step 99615: {'lr': 0.0001298686217135585, 'samples': 19126080, 'steps': 99614, 'loss/train': 1.5699092149734497}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:26 - INFO - __main__ - Step 99620: {'lr': 0.0001298453528271008, 'samples': 19127040, 'steps': 99619, 'loss/train': 1.1691551208496094}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:28 - INFO - __main__ - Step 99624: {'lr': 0.00012982673869243894, 'samples': 19127808, 'steps': 99623, 'loss/train': 1.9725182056427002}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:30 - INFO - __main__ - Step 99628: {'lr': 0.0001298081254241485, 'samples': 19128576, 'steps': 99627, 'loss/train': 1.0192748308181763}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:30 - INFO - __main__ - Step 99628: {'lr': 0.0001298081254241485, 'samples': 19128576, 'steps': 99627, 'loss/train': 1.0192748308181763}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:30 - INFO - __main__ - Step 99628: {'lr': 0.0001298081254241485, 'samples': 19128576, 'steps': 99627, 'loss/train': 1.0192748308181763}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:35 - INFO - __main__ - Step 99638: {'lr': 0.00012976159604467837, 'samples': 19130496, 'steps': 99637, 'loss/train': 0.7794243693351746}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:37 - INFO - __main__ - Step 99642: {'lr': 0.00012974298580974484, 'samples': 19131264, 'steps': 99641, 'loss/train': 1.631463646888733}}}}█████��████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:39 - INFO - __main__ - Step 99647: {'lr': 0.0001297197242352777, 'samples': 19132224, 'steps': 99646, 'loss/train': 0.7351295351982117}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:41 - INFO - __main__ - Step 99651: {'lr': 0.0001297011159512272, 'samples': 19132992, 'steps': 99650, 'loss/train': 1.3057100772857666}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:41 - INFO - __main__ - Step 99651: {'lr': 0.0001297011159512272, 'samples': 19132992, 'steps': 99650, 'loss/train': 1.3057100772857666}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:45 - INFO - __main__ - Step 99658: {'lr': 0.00012966855354110517, 'samples': 19134336, 'steps': 99657, 'loss/train': 0.3220337927341461}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:47 - INFO - __main__ - Step 99663: {'lr': 0.00012964529630327514, 'samples': 19135296, 'steps': 99662, 'loss/train': 1.0847690105438232}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:50 - INFO - __main__ - Step 99668: {'lr': 0.0001296220404211944, 'samples': 19136256, 'steps': 99667, 'loss/train': 1.6778277158737183}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:50 - INFO - __main__ - Step 99668: {'lr': 0.0001296220404211944, 'samples': 19136256, 'steps': 99667, 'loss/train': 1.6778277158737183}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:53 - INFO - __main__ - Step 99675: {'lr': 0.00012958948446443907, 'samples': 19137600, 'steps': 99674, 'loss/train': 1.4688918590545654}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:55 - INFO - __main__ - Step 99679: {'lr': 0.00012957088225414539, 'samples': 19138368, 'steps': 99678, 'loss/train': 1.642937421798706}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:57 - INFO - __main__ - Step 99684: {'lr': 0.00012954763071222286, 'samples': 19139328, 'steps': 99683, 'loss/train': 0.9081193804740906}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:13:57 - INFO - __main__ - Step 99684: {'lr': 0.00012954763071222286, 'samples': 19139328, 'steps': 99683, 'loss/train': 0.9081193804740906}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:02 - INFO - __main__ - Step 99692: {'lr': 0.00012951043106750252, 'samples': 19140864, 'steps': 99691, 'loss/train': 1.1801596879959106}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:03 - INFO - __main__ - Step 99696: {'lr': 0.0001294918325480531, 'samples': 19141632, 'steps': 99695, 'loss/train': 1.5300147533416748}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:05 - INFO - __main__ - Step 99700: {'lr': 0.00012947323489738966, 'samples': 19142400, 'steps': 99699, 'loss/train': 1.337225317955017}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:07 - INFO - __main__ - Step 99705: {'lr': 0.00012944998905599475, 'samples': 19143360, 'steps': 99704, 'loss/train': 1.2105001211166382}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:07 - INFO - __main__ - Step 99705: {'lr': 0.00012944998905599475, 'samples': 19143360, 'steps': 99704, 'loss/train': 1.2105001211166382}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:12 - INFO - __main__ - Step 99713: {'lr': 0.0001294127985344066, 'samples': 19144896, 'steps': 99712, 'loss/train': 0.9565947651863098}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:13 - INFO - __main__ - Step 99717: {'lr': 0.000129394204577579, 'samples': 19145664, 'steps': 99716, 'loss/train': 1.521910548210144}8}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:15 - INFO - __main__ - Step 99721: {'lr': 0.0001293756114902413, 'samples': 19146432, 'steps': 99720, 'loss/train': 1.5648049116134644}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:15 - INFO - __main__ - Step 99721: {'lr': 0.0001293756114902413, 'samples': 19146432, 'steps': 99720, 'loss/train': 1.5648049116134644}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:20 - INFO - __main__ - Step 99730: {'lr': 0.00012933378022349747, 'samples': 19148160, 'steps': 99729, 'loss/train': 1.0106863975524902}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:22 - INFO - __main__ - Step 99734: {'lr': 0.0001293151899629272, 'samples': 19148928, 'steps': 99733, 'loss/train': 0.9752723574638367}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:23 - INFO - __main__ - Step 99738: {'lr': 0.00012929660057241622, 'samples': 19149696, 'steps': 99737, 'loss/train': 1.9623489379882812}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:25 - INFO - __main__ - Step 99742: {'lr': 0.00012927801205209877, 'samples': 19150464, 'steps': 99741, 'loss/train': 1.11711847782135}2}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:28 - INFO - __main__ - Step 99747: {'lr': 0.00012925477762561554, 'samples': 19151424, 'steps': 99746, 'loss/train': 2.1119370460510254}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:30 - INFO - __main__ - Step 99752: {'lr': 0.00012923154455928064, 'samples': 19152384, 'steps': 99751, 'loss/train': 1.1958879232406616}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:30 - INFO - __main__ - Step 99752: {'lr': 0.00012923154455928064, 'samples': 19152384, 'steps': 99751, 'loss/train': 1.1958879232406616}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:33 - INFO - __main__ - Step 99759: {'lr': 0.00012919902055195937, 'samples': 19153728, 'steps': 99758, 'loss/train': 1.6108616590499878}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:35 - INFO - __main__ - Step 99763: {'lr': 0.0001291804366023558, 'samples': 19154496, 'steps': 99762, 'loss/train': 1.1031019687652588}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:35 - INFO - __main__ - Step 99763: {'lr': 0.0001291804366023558, 'samples': 19154496, 'steps': 99762, 'loss/train': 1.1031019687652588}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:40 - INFO - __main__ - Step 99771: {'lr': 0.00012914327131637542, 'samples': 19156032, 'steps': 99770, 'loss/train': 0.841533899307251}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:42 - INFO - __main__ - Step 99775: {'lr': 0.00012912468998026644, 'samples': 19156800, 'steps': 99774, 'loss/train': 0.920987069606781}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:43 - INFO - __main__ - Step 99779: {'lr': 0.00012910610951559037, 'samples': 19157568, 'steps': 99778, 'loss/train': 1.5853945016860962}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:45 - INFO - __main__ - Step 99783: {'lr': 0.00012908752992248093, 'samples': 19158336, 'steps': 99782, 'loss/train': 1.1066713333129883}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:48 - INFO - __main__ - Step 99788: {'lr': 0.0001290643066569389, 'samples': 19159296, 'steps': 99787, 'loss/train': 1.3470009565353394}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:48 - INFO - __main__ - Step 99788: {'lr': 0.0001290643066569389, 'samples': 19159296, 'steps': 99787, 'loss/train': 1.3470009565353394}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:48 - INFO - __main__ - Step 99788: {'lr': 0.0001290643066569389, 'samples': 19159296, 'steps': 99787, 'loss/train': 1.3470009565353394}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:54 - INFO - __main__ - Step 99799: {'lr': 0.00012901322026838958, 'samples': 19161408, 'steps': 99798, 'loss/train': 1.6183356046676636}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:54 - INFO - __main__ - Step 99799: {'lr': 0.00012901322026838958, 'samples': 19161408, 'steps': 99798, 'loss/train': 1.6183356046676636}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:14:57 - INFO - __main__ - Step 99806: {'lr': 0.00012898071418265876, 'samples': 19162752, 'steps': 99805, 'loss/train': 1.1120935678482056}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:00 - INFO - __main__ - Step 99811: {'lr': 0.00012895749718583462, 'samples': 19163712, 'steps': 99810, 'loss/train': 1.2906382083892822}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:02 - INFO - __main__ - Step 99815: {'lr': 0.00012893892457008072, 'samples': 19164480, 'steps': 99814, 'loss/train': 1.0040501356124878}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:04 - INFO - __main__ - Step 99819: {'lr': 0.0001289203528270989, 'samples': 19165248, 'steps': 99818, 'loss/train': 0.5585747361183167}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:05 - INFO - __main__ - Step 99823: {'lr': 0.00012890178195702295, 'samples': 19166016, 'steps': 99822, 'loss/train': 0.435686856508255}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:07 - INFO - __main__ - Step 99827: {'lr': 0.0001288832119599868, 'samples': 19166784, 'steps': 99826, 'loss/train': 1.4991806745529175}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:10 - INFO - __main__ - Step 99832: {'lr': 0.0001288600006916079, 'samples': 19167744, 'steps': 99831, 'loss/train': 3.041618824005127}}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:12 - INFO - __main__ - Step 99836: {'lr': 0.00012884143265940086, 'samples': 19168512, 'steps': 99835, 'loss/train': 1.5450348854064941}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:14 - INFO - __main__ - Step 99840: {'lr': 0.00012882286550066865, 'samples': 19169280, 'steps': 99839, 'loss/train': 0.48129066824913025}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:15 - INFO - __main__ - Step 99844: {'lr': 0.0001288042992155452, 'samples': 19170048, 'steps': 99843, 'loss/train': 1.717084527015686}25}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:18 - INFO - __main__ - Step 99848: {'lr': 0.00012878573380416448, 'samples': 19170816, 'steps': 99847, 'loss/train': 0.6767792105674744}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:20 - INFO - __main__ - Step 99853: {'lr': 0.00012876252826884288, 'samples': 19171776, 'steps': 99852, 'loss/train': 1.7974975109100342}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:22 - INFO - __main__ - Step 99858: {'lr': 0.0001287393240992146, 'samples': 19172736, 'steps': 99857, 'loss/train': 1.6685283184051514}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:22 - INFO - __main__ - Step 99858: {'lr': 0.0001287393240992146, 'samples': 19172736, 'steps': 99857, 'loss/train': 1.6685283184051514}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:26 - INFO - __main__ - Step 99865: {'lr': 0.00012870684055659766, 'samples': 19174080, 'steps': 99864, 'loss/train': 1.0876471996307373}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:28 - INFO - __main__ - Step 99869: {'lr': 0.0001286882797345612, 'samples': 19174848, 'steps': 99868, 'loss/train': 1.362058401107788}3}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:30 - INFO - __main__ - Step 99874: {'lr': 0.00012866507993690817, 'samples': 19175808, 'steps': 99873, 'loss/train': 1.5116145610809326}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:32 - INFO - __main__ - Step 99878: {'lr': 0.00012864652108286273, 'samples': 19176576, 'steps': 99877, 'loss/train': 1.3312352895736694}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:32 - INFO - __main__ - Step 99878: {'lr': 0.00012864652108286273, 'samples': 19176576, 'steps': 99877, 'loss/train': 1.3312352895736694}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:35 - INFO - __main__ - Step 99885: {'lr': 0.0001286140451935438, 'samples': 19177920, 'steps': 99884, 'loss/train': 1.1684197187423706}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:38 - INFO - __main__ - Step 99890: {'lr': 0.00012859084977054203, 'samples': 19178880, 'steps': 99889, 'loss/train': 1.0120488405227661}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:38 - INFO - __main__ - Step 99890: {'lr': 0.00012859084977054203, 'samples': 19178880, 'steps': 99889, 'loss/train': 1.0120488405227661}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:42 - INFO - __main__ - Step 99898: {'lr': 0.00012855373993851237, 'samples': 19180416, 'steps': 99897, 'loss/train': 0.8924877047538757}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:43 - INFO - __main__ - Step 99902: {'lr': 0.00012853518633575421, 'samples': 19181184, 'steps': 99901, 'loss/train': 0.9761576056480408}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:46 - INFO - __main__ - Step 99906: {'lr': 0.00012851663360867872, 'samples': 19181952, 'steps': 99905, 'loss/train': 1.3133898973464966}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:48 - INFO - __main__ - Step 99911: {'lr': 0.00012849344393146695, 'samples': 19182912, 'steps': 99910, 'loss/train': 1.0668801069259644}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:48 - INFO - __main__ - Step 99911: {'lr': 0.00012849344393146695, 'samples': 19182912, 'steps': 99910, 'loss/train': 1.0668801069259644}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:52 - INFO - __main__ - Step 99918: {'lr': 0.00012846098068288614, 'samples': 19184256, 'steps': 99917, 'loss/train': 1.4692776203155518}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:54 - INFO - __main__ - Step 99922: {'lr': 0.00012844243145987902, 'samples': 19185024, 'steps': 99921, 'loss/train': 0.09121531248092651}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:56 - INFO - __main__ - Step 99927: {'lr': 0.00012841924616350509, 'samples': 19185984, 'steps': 99926, 'loss/train': 1.3330224752426147}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:15:58 - INFO - __main__ - Step 99932: {'lr': 0.00012839606223669135, 'samples': 19186944, 'steps': 99931, 'loss/train': 1.517983078956604}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:00 - INFO - __main__ - Step 99936: {'lr': 0.00012837751608149925, 'samples': 19187712, 'steps': 99935, 'loss/train': 1.164741039276123}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:02 - INFO - __main__ - Step 99940: {'lr': 0.00012835897080312668, 'samples': 19188480, 'steps': 99939, 'loss/train': 1.2757151126861572}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:02 - INFO - __main__ - Step 99940: {'lr': 0.00012835897080312668, 'samples': 19188480, 'steps': 99939, 'loss/train': 1.2757151126861572}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:06 - INFO - __main__ - Step 99947: {'lr': 0.00012832651867622345, 'samples': 19189824, 'steps': 99946, 'loss/train': 0.9355164170265198}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:08 - INFO - __main__ - Step 99953: {'lr': 0.0001282987047055657, 'samples': 19190976, 'steps': 99952, 'loss/train': 0.21213218569755554}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:08 - INFO - __main__ - Step 99953: {'lr': 0.0001282987047055657, 'samples': 19190976, 'steps': 99952, 'loss/train': 0.21213218569755554}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:12 - INFO - __main__ - Step 99960: {'lr': 0.00012826625756823425, 'samples': 19192320, 'steps': 99959, 'loss/train': 1.389358401298523}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:14 - INFO - __main__ - Step 99964: {'lr': 0.00012824771755358565, 'samples': 19193088, 'steps': 99963, 'loss/train': 1.270076036453247}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:16 - INFO - __main__ - Step 99968: {'lr': 0.00012822917841669233, 'samples': 19193856, 'steps': 99967, 'loss/train': 1.637995719909668}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:16 - INFO - __main__ - Step 99968: {'lr': 0.00012822917841669233, 'samples': 19193856, 'steps': 99967, 'loss/train': 1.637995719909668}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:20 - INFO - __main__ - Step 99976: {'lr': 0.0001281921027767057, 'samples': 19195392, 'steps': 99975, 'loss/train': 1.3248534202575684}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:22 - INFO - __main__ - Step 99980: {'lr': 0.00012817356627387987, 'samples': 19196160, 'steps': 99979, 'loss/train': 1.7154347896575928}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:24 - INFO - __main__ - Step 99984: {'lr': 0.00012815503064934376, 'samples': 19196928, 'steps': 99983, 'loss/train': 1.360336422920227}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:26 - INFO - __main__ - Step 99989: {'lr': 0.00012813186235397224, 'samples': 19197888, 'steps': 99988, 'loss/train': 1.294065237045288}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:28 - INFO - __main__ - Step 99993: {'lr': 0.00012811332870607667, 'samples': 19198656, 'steps': 99992, 'loss/train': 1.0042076110839844}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:30 - INFO - __main__ - Step 99997: {'lr': 0.00012809479593690518, 'samples': 19199424, 'steps': 99996, 'loss/train': 1.399559497833252}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:30 - INFO - __main__ - Step 99997: {'lr': 0.00012809479593690518, 'samples': 19199424, 'steps': 99996, 'loss/train': 1.399559497833252}}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:33 - INFO - __main__ - Step 100004: {'lr': 0.00012806236570568676, 'samples': 19200768, 'steps': 100003, 'loss/train': 1.3466306924819946}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:36 - INFO - __main__ - Step 100010: {'lr': 0.00012803457050740059, 'samples': 19201920, 'steps': 100009, 'loss/train': 1.6503721475601196}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:38 - INFO - __main__ - Step 100014: {'lr': 0.0001280160414742969, 'samples': 19202688, 'steps': 100013, 'loss/train': 1.4542646408081055}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:40 - INFO - __main__ - Step 100018: {'lr': 0.00012799751332061854, 'samples': 19203456, 'steps': 100017, 'loss/train': 1.345199465751648}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:40 - INFO - __main__ - Step 100018: {'lr': 0.00012799751332061854, 'samples': 19203456, 'steps': 100017, 'loss/train': 1.345199465751648}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:44 - INFO - __main__ - Step 100025: {'lr': 0.00012796509116820071, 'samples': 19204800, 'steps': 100024, 'loss/train': 1.30027437210083}}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:46 - INFO - __main__ - Step 100030: {'lr': 0.00012794193413747184, 'samples': 19205760, 'steps': 100029, 'loss/train': 1.2800105810165405}████████████████���█████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:48 - INFO - __main__ - Step 100035: {'lr': 0.00012791877848168014, 'samples': 19206720, 'steps': 100034, 'loss/train': 1.3344018459320068}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:50 - INFO - __main__ - Step 100039: {'lr': 0.00012790025494717662, 'samples': 19207488, 'steps': 100038, 'loss/train': 1.3040705919265747}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:50 - INFO - __main__ - Step 100039: {'lr': 0.00012790025494717662, 'samples': 19207488, 'steps': 100038, 'loss/train': 1.3040705919265747}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:54 - INFO - __main__ - Step 100046: {'lr': 0.00012786784088000182, 'samples': 19208832, 'steps': 100045, 'loss/train': 1.3318833112716675}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:56 - INFO - __main__ - Step 100051: {'lr': 0.00012784468962576134, 'samples': 19209792, 'steps': 100050, 'loss/train': 0.8095641136169434}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:16:58 - INFO - __main__ - Step 100056: {'lr': 0.00012782153974755318, 'samples': 19210752, 'steps': 100055, 'loss/train': 1.5439120531082153}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:00 - INFO - __main__ - Step 100060: {'lr': 0.00012780302083590528, 'samples': 19211520, 'steps': 100059, 'loss/train': 1.0987226963043213}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:00 - INFO - __main__ - Step 100060: {'lr': 0.00012780302083590528, 'samples': 19211520, 'steps': 100059, 'loss/train': 1.0987226963043213}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:04 - INFO - __main__ - Step 100067: {'lr': 0.00012777061486041468, 'samples': 19212864, 'steps': 100066, 'loss/train': 0.7287965416908264}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:06 - INFO - __main__ - Step 100071: {'lr': 0.00012775209837173122, 'samples': 19213632, 'steps': 100070, 'loss/train': 1.4100741147994995}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:06 - INFO - __main__ - Step 100071: {'lr': 0.00012775209837173122, 'samples': 19213632, 'steps': 100070, 'loss/train': 1.4100741147994995}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:10 - INFO - __main__ - Step 100080: {'lr': 0.00012771043949475345, 'samples': 19215360, 'steps': 100079, 'loss/train': 1.659069299697876}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:12 - INFO - __main__ - Step 100084: {'lr': 0.00012769192587087496, 'samples': 19216128, 'steps': 100083, 'loss/train': 1.2340351343154907}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:14 - INFO - __main__ - Step 100088: {'lr': 0.00012767341312875868, 'samples': 19216896, 'steps': 100087, 'loss/train': 0.9167482852935791}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:16 - INFO - __main__ - Step 100092: {'lr': 0.00012765490126853788, 'samples': 19217664, 'steps': 100091, 'loss/train': 1.2517671585083008}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:19 - INFO - __main__ - Step 100098: {'lr': 0.00012762713513205277, 'samples': 19218816, 'steps': 100097, 'loss/train': 1.189474105834961}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:21 - INFO - __main__ - Step 100102: {'lr': 0.0001276086254771548, 'samples': 19219584, 'steps': 100101, 'loss/train': 1.8476800918579102}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:21 - INFO - __main__ - Step 100102: {'lr': 0.0001276086254771548, 'samples': 19219584, 'steps': 100101, 'loss/train': 1.8476800918579102}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:24 - INFO - __main__ - Step 100108: {'lr': 0.00012758086264927937, 'samples': 19220736, 'steps': 100107, 'loss/train': 1.0210758447647095}���█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:26 - INFO - __main__ - Step 100113: {'lr': 0.00012755772847626885, 'samples': 19221696, 'steps': 100112, 'loss/train': 1.3302336931228638}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:26 - INFO - __main__ - Step 100113: {'lr': 0.00012755772847626885, 'samples': 19221696, 'steps': 100112, 'loss/train': 1.3302336931228638}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:30 - INFO - __main__ - Step 100121: {'lr': 0.00012752071666843163, 'samples': 19223232, 'steps': 100120, 'loss/train': 1.7797472476959229}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:32 - INFO - __main__ - Step 100125: {'lr': 0.00012750221208894085, 'samples': 19224000, 'steps': 100124, 'loss/train': 1.1198550462722778}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:34 - INFO - __main__ - Step 100129: {'lr': 0.00012748370839258, 'samples': 19224768, 'steps': 100128, 'loss/train': 1.4989598989486694}78}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:36 - INFO - __main__ - Step 100134: {'lr': 0.0001274605800142333, 'samples': 19225728, 'steps': 100133, 'loss/train': 1.7465637922286987}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:36 - INFO - __main__ - Step 100134: {'lr': 0.0001274605800142333, 'samples': 19225728, 'steps': 100133, 'loss/train': 1.7465637922286987}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:40 - INFO - __main__ - Step 100142: {'lr': 0.0001274235774801344, 'samples': 19227264, 'steps': 100141, 'loss/train': 1.4699828624725342}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:42 - INFO - __main__ - Step 100146: {'lr': 0.00012740507753856327, 'samples': 19228032, 'steps': 100145, 'loss/train': 1.4506263732910156}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:44 - INFO - __main__ - Step 100150: {'lr': 0.00012738657848082225, 'samples': 19228800, 'steps': 100149, 'loss/train': 1.5934377908706665}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:46 - INFO - __main__ - Step 100155: {'lr': 0.00012736345590173525, 'samples': 19229760, 'steps': 100154, 'loss/train': 1.0720117092132568}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:46 - INFO - __main__ - Step 100155: {'lr': 0.00012736345590173525, 'samples': 19229760, 'steps': 100154, 'loss/train': 1.0720117092132568}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:50 - INFO - __main__ - Step 100162: {'lr': 0.0001273310866119134, 'samples': 19231104, 'steps': 100161, 'loss/train': 1.4381790161132812}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:52 - INFO - __main__ - Step 100166: {'lr': 0.00012731259109082627, 'samples': 19231872, 'steps': 100165, 'loss/train': 0.9265416860580444}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:54 - INFO - __main__ - Step 100171: {'lr': 0.00012728947293330685, 'samples': 19232832, 'steps': 100170, 'loss/train': 1.1486279964447021}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:56 - INFO - __main__ - Step 100175: {'lr': 0.00012727097940252514, 'samples': 19233600, 'steps': 100174, 'loss/train': 1.0884590148925781}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:17:56 - INFO - __main__ - Step 100175: {'lr': 0.00012727097940252514, 'samples': 19233600, 'steps': 100174, 'loss/train': 1.0884590148925781}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:00 - INFO - __main__ - Step 100183: {'lr': 0.00012723399499548575, 'samples': 19235136, 'steps': 100182, 'loss/train': 2.0331192016601562}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:02 - INFO - __main__ - Step 100187: {'lr': 0.00012721550411949457, 'samples': 19235904, 'steps': 100186, 'loss/train': 1.773400068283081}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:04 - INFO - __main__ - Step 100192: {'lr': 0.00012719239176932917, 'samples': 19236864, 'steps': 100191, 'loss/train': 1.452890157699585}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:04 - INFO - __main__ - Step 100192: {'lr': 0.00012719239176932917, 'samples': 19236864, 'steps': 100191, 'loss/train': 1.452890157699585}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:09 - INFO - __main__ - Step 100200: {'lr': 0.00012715541488660405, 'samples': 19238400, 'steps': 100199, 'loss/train': 1.4968267679214478}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:09 - INFO - __main__ - Step 100200: {'lr': 0.00012715541488660405, 'samples': 19238400, 'steps': 100199, 'loss/train': 1.4968267679214478}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:12 - INFO - __main__ - Step 100207: {'lr': 0.0001271230630201564, 'samples': 19239744, 'steps': 100206, 'loss/train': 1.1472960710525513}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:14 - INFO - __main__ - Step 100212: {'lr': 0.00012709995620507436, 'samples': 19240704, 'steps': 100211, 'loss/train': 1.2885316610336304}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:17 - INFO - __main__ - Step 100217: {'lr': 0.00012707685077441384, 'samples': 19241664, 'steps': 100216, 'loss/train': 1.765580177307129}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:19 - INFO - __main__ - Step 100221: {'lr': 0.00012705836742684385, 'samples': 19242432, 'steps': 100220, 'loss/train': 1.519779920578003}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:19 - INFO - __main__ - Step 100221: {'lr': 0.00012705836742684385, 'samples': 19242432, 'steps': 100220, 'loss/train': 1.519779920578003}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:22 - INFO - __main__ - Step 100228: {'lr': 0.00012702602370140735, 'samples': 19243776, 'steps': 100227, 'loss/train': 0.8395498991012573}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:24 - INFO - __main__ - Step 100233: {'lr': 0.00012700292270264481, 'samples': 19244736, 'steps': 100232, 'loss/train': 1.294349193572998}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:24 - INFO - __main__ - Step 100233: {'lr': 0.00012700292270264481, 'samples': 19244736, 'steps': 100232, 'loss/train': 1.294349193572998}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:24 - INFO - __main__ - Step 100233: {'lr': 0.00012700292270264481, 'samples': 19244736, 'steps': 100232, 'loss/train': 1.294349193572998}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:30 - INFO - __main__ - Step 100243: {'lr': 0.00012695672486192397, 'samples': 19246656, 'steps': 100242, 'loss/train': 1.808809757232666}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:33 - INFO - __main__ - Step 100249: {'lr': 0.00012692900881854552, 'samples': 19247808, 'steps': 100248, 'loss/train': 1.497756838798523}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:35 - INFO - __main__ - Step 100253: {'lr': 0.00012691053256534324, 'samples': 19248576, 'steps': 100252, 'loss/train': 1.1801577806472778}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:35 - INFO - __main__ - Step 100253: {'lr': 0.00012691053256534324, 'samples': 19248576, 'steps': 100252, 'loss/train': 1.1801577806472778}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:38 - INFO - __main__ - Step 100260: {'lr': 0.00012687820125761466, 'samples': 19249920, 'steps': 100259, 'loss/train': 1.2920604944229126}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:41 - INFO - __main__ - Step 100265: {'lr': 0.00012685510913064174, 'samples': 19250880, 'steps': 100264, 'loss/train': 1.94098699092865}6}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:43 - INFO - __main__ - Step 100270: {'lr': 0.0001268320183908486, 'samples': 19251840, 'steps': 100269, 'loss/train': 1.0567479133605957}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:43 - INFO - __main__ - Step 100270: {'lr': 0.0001268320183908486, 'samples': 19251840, 'steps': 100269, 'loss/train': 1.0567479133605957}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:47 - INFO - __main__ - Step 100276: {'lr': 0.00012680431133454018, 'samples': 19252992, 'steps': 100275, 'loss/train': 1.6791898012161255}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:49 - INFO - __main__ - Step 100281: {'lr': 0.0001267812236474579, 'samples': 19253952, 'steps': 100280, 'loss/train': 1.232207179069519}5}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:51 - INFO - __main__ - Step 100285: {'lr': 0.00012676275449714818, 'samples': 19254720, 'steps': 100284, 'loss/train': 1.6832624673843384}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:53 - INFO - __main__ - Step 100289: {'lr': 0.00012674428623529928, 'samples': 19255488, 'steps': 100288, 'loss/train': 1.2676069736480713}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:55 - INFO - __main__ - Step 100294: {'lr': 0.00012672120215758909, 'samples': 19256448, 'steps': 100293, 'loss/train': 1.5738798379898071}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:57 - INFO - __main__ - Step 100298: {'lr': 0.00012670273589526383, 'samples': 19257216, 'steps': 100297, 'loss/train': 1.583533525466919}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:18:59 - INFO - __main__ - Step 100302: {'lr': 0.00012668427052183208, 'samples': 19257984, 'steps': 100301, 'loss/train': 1.6352787017822266}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:01 - INFO - __main__ - Step 100306: {'lr': 0.000126665806037427, 'samples': 19258752, 'steps': 100305, 'loss/train': 1.1176350116729736}6}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:03 - INFO - __main__ - Step 100310: {'lr': 0.00012664734244218165, 'samples': 19259520, 'steps': 100309, 'loss/train': 1.5695656538009644}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:05 - INFO - __main__ - Step 100315: {'lr': 0.00012662426419870863, 'samples': 19260480, 'steps': 100314, 'loss/train': 1.662404179573059}}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:07 - INFO - __main__ - Step 100319: {'lr': 0.00012660580260455946, 'samples': 19261248, 'steps': 100318, 'loss/train': 1.1336127519607544}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:07 - INFO - __main__ - Step 100319: {'lr': 0.00012660580260455946, 'samples': 19261248, 'steps': 100318, 'loss/train': 1.1336127519607544}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:10 - INFO - __main__ - Step 100326: {'lr': 0.00012657349695545988, 'samples': 19262592, 'steps': 100325, 'loss/train': 1.4783682823181152}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:10 - INFO - __main__ - Step 100326: {'lr': 0.00012657349695545988, 'samples': 19262592, 'steps': 100325, 'loss/train': 1.4783682823181152}██████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:15 - INFO - __main__ - Step 100334: {'lr': 0.00012653657955051818, 'samples': 19264128, 'steps': 100333, 'loss/train': 1.6383143663406372}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:15 - INFO - __main__ - Step 100334: {'lr': 0.00012653657955051818, 'samples': 19264128, 'steps': 100333, 'loss/train': 1.6383143663406372}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:18 - INFO - __main__ - Step 100341: {'lr': 0.00012650427974177005, 'samples': 19265472, 'steps': 100340, 'loss/train': 1.3132671117782593}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:20 - INFO - __main__ - Step 100346: {'lr': 0.0001264812101191236, 'samples': 19266432, 'steps': 100345, 'loss/train': 1.0848276615142822}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:23 - INFO - __main__ - Step 100351: {'lr': 0.0001264581418878686, 'samples': 19267392, 'steps': 100350, 'loss/train': 1.0178005695343018}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:23 - INFO - __main__ - Step 100351: {'lr': 0.0001264581418878686, 'samples': 19267392, 'steps': 100350, 'loss/train': 1.0178005695343018}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:26 - INFO - __main__ - Step 100358: {'lr': 0.00012642584870214418, 'samples': 19268736, 'steps': 100357, 'loss/train': 1.3126636743545532}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:29 - INFO - __main__ - Step 100362: {'lr': 0.0001264073966780863, 'samples': 19269504, 'steps': 100361, 'loss/train': 0.25144556164741516}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:31 - INFO - __main__ - Step 100367: {'lr': 0.00012638433290103028, 'samples': 19270464, 'steps': 100366, 'loss/train': 1.0102996826171875}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:33 - INFO - __main__ - Step 100371: {'lr': 0.0001263658828819607, 'samples': 19271232, 'steps': 100370, 'loss/train': 1.431461215019226}5}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:33 - INFO - __main__ - Step 100371: {'lr': 0.0001263658828819607, 'samples': 19271232, 'steps': 100370, 'loss/train': 1.431461215019226}5}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:36 - INFO - __main__ - Step 100378: {'lr': 0.0001263335974934124, 'samples': 19272576, 'steps': 100377, 'loss/train': 1.155129313468933}5}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:38 - INFO - __main__ - Step 100382: {'lr': 0.00012631514992579828, 'samples': 19273344, 'steps': 100381, 'loss/train': 1.4893518686294556}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:41 - INFO - __main__ - Step 100387: {'lr': 0.0001262920917202322, 'samples': 19274304, 'steps': 100386, 'loss/train': 0.8137231469154358}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:43 - INFO - __main__ - Step 100392: {'lr': 0.00012626903490818792, 'samples': 19275264, 'steps': 100391, 'loss/train': 1.2669057846069336}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:45 - INFO - __main__ - Step 100396: {'lr': 0.00012625059046206277, 'samples': 19276032, 'steps': 100395, 'loss/train': 1.2739650011062622}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:45 - INFO - __main__ - Step 100396: {'lr': 0.00012625059046206277, 'samples': 19276032, 'steps': 100395, 'loss/train': 1.2739650011062622}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:48 - INFO - __main__ - Step 100403: {'lr': 0.00012621831482816749, 'samples': 19277376, 'steps': 100402, 'loss/train': 1.150076985359192}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:51 - INFO - __main__ - Step 100408: {'lr': 0.00012619526247713842, 'samples': 19278336, 'steps': 100407, 'loss/train': 2.546436309814453}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:53 - INFO - __main__ - Step 100413: {'lr': 0.00012617221152072205, 'samples': 19279296, 'steps': 100412, 'loss/train': 0.6829764246940613}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:53 - INFO - __main__ - Step 100413: {'lr': 0.00012617221152072205, 'samples': 19279296, 'steps': 100412, 'loss/train': 0.6829764246940613}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:56 - INFO - __main__ - Step 100420: {'lr': 0.00012613994252518262, 'samples': 19280640, 'steps': 100419, 'loss/train': 1.3803844451904297}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:19:58 - INFO - __main__ - Step 100424: {'lr': 0.00012612150432692195, 'samples': 19281408, 'steps': 100423, 'loss/train': 1.4589450359344482}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:01 - INFO - __main__ - Step 100429: {'lr': 0.0001260984578350107, 'samples': 19282368, 'steps': 100428, 'loss/train': 1.1977354288101196}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:03 - INFO - __main__ - Step 100434: {'lr': 0.00012607541273880251, 'samples': 19283328, 'steps': 100433, 'loss/train': 1.497431755065918}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:05 - INFO - __main__ - Step 100438: {'lr': 0.0001260569776669167, 'samples': 19284096, 'steps': 100437, 'loss/train': 0.6873278617858887}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:05 - INFO - __main__ - Step 100438: {'lr': 0.0001260569776669167, 'samples': 19284096, 'steps': 100437, 'loss/train': 0.6873278617858887}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:09 - INFO - __main__ - Step 100445: {'lr': 0.00012602471844129867, 'samples': 19285440, 'steps': 100444, 'loss/train': 1.357630729675293}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:11 - INFO - __main__ - Step 100450: {'lr': 0.00012600167781308473, 'samples': 19286400, 'steps': 100449, 'loss/train': 1.4837199449539185}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:13 - INFO - __main__ - Step 100455: {'lr': 0.00012597863858166412, 'samples': 19287360, 'steps': 100454, 'loss/train': 1.4540272951126099}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:15 - INFO - __main__ - Step 100459: {'lr': 0.00012596020820239312, 'samples': 19288128, 'steps': 100458, 'loss/train': 1.5227681398391724}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:17 - INFO - __main__ - Step 100463: {'lr': 0.0001259417787173688, 'samples': 19288896, 'steps': 100462, 'loss/train': 1.3239730596542358}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:17 - INFO - __main__ - Step 100463: {'lr': 0.0001259417787173688, 'samples': 19288896, 'steps': 100462, 'loss/train': 1.3239730596542358}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:21 - INFO - __main__ - Step 100470: {'lr': 0.00012590952927075692, 'samples': 19290240, 'steps': 100469, 'loss/train': 1.4935221672058105}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:24 - INFO - __main__ - Step 100476: {'lr': 0.00012588188906853648, 'samples': 19291392, 'steps': 100475, 'loss/train': 1.2202389240264893}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:24 - INFO - __main__ - Step 100476: {'lr': 0.00012588188906853648, 'samples': 19291392, 'steps': 100475, 'loss/train': 1.2202389240264893}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:27 - INFO - __main__ - Step 100482: {'lr': 0.00012585425087964153, 'samples': 19292544, 'steps': 100481, 'loss/train': 0.4255905747413635}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:29 - INFO - __main__ - Step 100486: {'lr': 0.00012583582653911369, 'samples': 19293312, 'steps': 100485, 'loss/train': 1.3702703714370728}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:31 - INFO - __main__ - Step 100490: {'lr': 0.00012581740309372918, 'samples': 19294080, 'steps': 100489, 'loss/train': 1.3825725317001343}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:33 - INFO - __main__ - Step 100494: {'lr': 0.00012579898054362098, 'samples': 19294848, 'steps': 100493, 'loss/train': 1.9319523572921753}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:35 - INFO - __main__ - Step 100498: {'lr': 0.0001257805588889217, 'samples': 19295616, 'steps': 100497, 'loss/train': 1.1894968748092651}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:37 - INFO - __main__ - Step 100502: {'lr': 0.00012576213812976424, 'samples': 19296384, 'steps': 100501, 'loss/train': 0.7428439259529114}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:39 - INFO - __main__ - Step 100507: {'lr': 0.00012573911344037546, 'samples': 19297344, 'steps': 100506, 'loss/train': 1.3132280111312866}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:42 - INFO - __main__ - Step 100512: {'lr': 0.00012571609015073754, 'samples': 19298304, 'steps': 100511, 'loss/train': 0.8308529257774353}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:42 - INFO - __main__ - Step 100512: {'lr': 0.00012571609015073754, 'samples': 19298304, 'steps': 100511, 'loss/train': 0.8308529257774353}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:45 - INFO - __main__ - Step 100518: {'lr': 0.00012568846405120853, 'samples': 19299456, 'steps': 100517, 'loss/train': 1.4263023138046265}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:47 - INFO - __main__ - Step 100522: {'lr': 0.00012567004777175203, 'samples': 19300224, 'steps': 100521, 'loss/train': 1.3085567951202393}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:49 - INFO - __main__ - Step 100527: {'lr': 0.00012564702868292311, 'samples': 19301184, 'steps': 100526, 'loss/train': 1.0670444965362549}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:51 - INFO - __main__ - Step 100532: {'lr': 0.0001256240109948823, 'samples': 19302144, 'steps': 100531, 'loss/train': 1.3593987226486206}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:51 - INFO - __main__ - Step 100532: {'lr': 0.0001256240109948823, 'samples': 19302144, 'steps': 100531, 'loss/train': 1.3593987226486206}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:55 - INFO - __main__ - Step 100539: {'lr': 0.00012559178858544324, 'samples': 19303488, 'steps': 100538, 'loss/train': 1.7523338794708252}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:57 - INFO - __main__ - Step 100543: {'lr': 0.00012557337701324503, 'samples': 19304256, 'steps': 100542, 'loss/train': 1.6667805910110474}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:20:59 - INFO - __main__ - Step 100548: {'lr': 0.00012555036380946906, 'samples': 19305216, 'steps': 100547, 'loss/train': 1.16202712059021}4}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:02 - INFO - __main__ - Step 100552: {'lr': 0.00012553195425578728, 'samples': 19305984, 'steps': 100551, 'loss/train': 0.7690213322639465}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:04 - INFO - __main__ - Step 100556: {'lr': 0.00012551354559943963, 'samples': 19306752, 'steps': 100555, 'loss/train': 1.1834967136383057}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:06 - INFO - __main__ - Step 100560: {'lr': 0.0001254951378405589, 'samples': 19307520, 'steps': 100559, 'loss/train': 1.861322045326233}7}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:07 - INFO - __main__ - Step 100564: {'lr': 0.00012547673097927753, 'samples': 19308288, 'steps': 100563, 'loss/train': 1.2975021600723267}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:09 - INFO - __main__ - Step 100568: {'lr': 0.0001254583250157284, 'samples': 19309056, 'steps': 100567, 'loss/train': 1.3453141450881958}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:12 - INFO - __main__ - Step 100573: {'lr': 0.00012543531882393017, 'samples': 19310016, 'steps': 100572, 'loss/train': 1.1393530368804932}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:14 - INFO - __main__ - Step 100577: {'lr': 0.00012541691488076367, 'samples': 19310784, 'steps': 100576, 'loss/train': 1.6277475357055664}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:16 - INFO - __main__ - Step 100581: {'lr': 0.00012539851183576063, 'samples': 19311552, 'steps': 100580, 'loss/train': 1.3658286333084106}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:17 - INFO - __main__ - Step 100585: {'lr': 0.00012538010968905382, 'samples': 19312320, 'steps': 100584, 'loss/train': 1.2274959087371826}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:19 - INFO - __main__ - Step 100589: {'lr': 0.00012536170844077568, 'samples': 19313088, 'steps': 100588, 'loss/train': 1.2397220134735107}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:22 - INFO - __main__ - Step 100594: {'lr': 0.00012533870814404564, 'samples': 19314048, 'steps': 100593, 'loss/train': 0.652056097984314}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:24 - INFO - __main__ - Step 100598: {'lr': 0.0001253203089177173, 'samples': 19314816, 'steps': 100597, 'loss/train': 1.2380229234695435}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:26 - INFO - __main__ - Step 100602: {'lr': 0.00012530191059024904, 'samples': 19315584, 'steps': 100601, 'loss/train': 1.5166183710098267}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:26 - INFO - __main__ - Step 100602: {'lr': 0.00012530191059024904, 'samples': 19315584, 'steps': 100601, 'loss/train': 1.5166183710098267}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:29 - INFO - __main__ - Step 100609: {'lr': 0.00012526971568045997, 'samples': 19316928, 'steps': 100608, 'loss/train': 1.2195626497268677}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:29 - INFO - __main__ - Step 100609: {'lr': 0.00012526971568045997, 'samples': 19316928, 'steps': 100608, 'loss/train': 1.2195626497268677}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:34 - INFO - __main__ - Step 100617: {'lr': 0.00012523292486997794, 'samples': 19318464, 'steps': 100616, 'loss/train': 1.278036117553711}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:35 - INFO - __main__ - Step 100621: {'lr': 0.0001252145308139054, 'samples': 19319232, 'steps': 100620, 'loss/train': 1.38057541847229}1}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:37 - INFO - __main__ - Step 100625: {'lr': 0.00012519613765745542, 'samples': 19320000, 'steps': 100624, 'loss/train': 1.4221079349517822}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:40 - INFO - __main__ - Step 100630: {'lr': 0.00012517314747718914, 'samples': 19320960, 'steps': 100629, 'loss/train': 1.4266983270645142}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:40 - INFO - __main__ - Step 100630: {'lr': 0.00012517314747718914, 'samples': 19320960, 'steps': 100629, 'loss/train': 1.4266983270645142}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:44 - INFO - __main__ - Step 100638: {'lr': 0.00012513636611361347, 'samples': 19322496, 'steps': 100637, 'loss/train': 1.6292662620544434}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:45 - INFO - __main__ - Step 100642: {'lr': 0.0001251179767820385, 'samples': 19323264, 'steps': 100641, 'loss/train': 1.182454228401184}4}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:47 - INFO - __main__ - Step 100646: {'lr': 0.000125099588350782, 'samples': 19324032, 'steps': 100645, 'loss/train': 1.545809030532837}}4}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:50 - INFO - __main__ - Step 100651: {'lr': 0.0001250766040779864, 'samples': 19324992, 'steps': 100650, 'loss/train': 1.4368808269500732}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:50 - INFO - __main__ - Step 100651: {'lr': 0.0001250766040779864, 'samples': 19324992, 'steps': 100650, 'loss/train': 1.4368808269500732}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:54 - INFO - __main__ - Step 100658: {'lr': 0.00012504442846024994, 'samples': 19326336, 'steps': 100657, 'loss/train': 2.5754570960998535}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:56 - INFO - __main__ - Step 100663: {'lr': 0.00012502144756520255, 'samples': 19327296, 'steps': 100662, 'loss/train': 1.2539050579071045}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:58 - INFO - __main__ - Step 100667: {'lr': 0.0001250030638627936, 'samples': 19328064, 'steps': 100666, 'loss/train': 1.422594666481018}5}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:21:58 - INFO - __main__ - Step 100667: {'lr': 0.0001250030638627936, 'samples': 19328064, 'steps': 100666, 'loss/train': 1.422594666481018}5}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:01 - INFO - __main__ - Step 100674: {'lr': 0.00012497089455204265, 'samples': 19329408, 'steps': 100673, 'loss/train': 1.6215307712554932}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:03 - INFO - __main__ - Step 100678: {'lr': 0.0001249525133281069, 'samples': 19330176, 'steps': 100677, 'loss/train': 0.8907338976860046}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:05 - INFO - __main__ - Step 100682: {'lr': 0.00012493413300568274, 'samples': 19330944, 'steps': 100681, 'loss/train': 1.8452390432357788}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:07 - INFO - __main__ - Step 100687: {'lr': 0.00012491115887060483, 'samples': 19331904, 'steps': 100686, 'loss/train': 1.0119448900222778}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:10 - INFO - __main__ - Step 100692: {'lr': 0.00012488818614460445, 'samples': 19332864, 'steps': 100691, 'loss/train': 1.2111918926239014}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:10 - INFO - __main__ - Step 100692: {'lr': 0.00012488818614460445, 'samples': 19332864, 'steps': 100691, 'loss/train': 1.2111918926239014}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:13 - INFO - __main__ - Step 100699: {'lr': 0.00012485602669594698, 'samples': 19334208, 'steps': 100698, 'loss/train': 1.2148308753967285}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:15 - INFO - __main__ - Step 100704: {'lr': 0.00012483305735278846, 'samples': 19335168, 'steps': 100703, 'loss/train': 1.201257348060608}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:18 - INFO - __main__ - Step 100708: {'lr': 0.00012481468289341863, 'samples': 19335936, 'steps': 100707, 'loss/train': 0.6476646065711975}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:20 - INFO - __main__ - Step 100712: {'lr': 0.0001247963093365538, 'samples': 19336704, 'steps': 100711, 'loss/train': 0.9354365468025208}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:22 - INFO - __main__ - Step 100716: {'lr': 0.00012477793668232666, 'samples': 19337472, 'steps': 100715, 'loss/train': 1.055092692375183}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:23 - INFO - __main__ - Step 100720: {'lr': 0.0001247595649308696, 'samples': 19338240, 'steps': 100719, 'loss/train': 1.1698188781738281}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:25 - INFO - __main__ - Step 100724: {'lr': 0.00012474119408231504, 'samples': 19339008, 'steps': 100723, 'loss/train': 1.242475152015686}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:28 - INFO - __main__ - Step 100729: {'lr': 0.0001247182317915302, 'samples': 19339968, 'steps': 100728, 'loss/train': 2.0578255653381348}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:30 - INFO - __main__ - Step 100733: {'lr': 0.00012469986297499063, 'samples': 19340736, 'steps': 100732, 'loss/train': 1.6817952394485474}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:30 - INFO - __main__ - Step 100733: {'lr': 0.00012469986297499063, 'samples': 19340736, 'steps': 100732, 'loss/train': 1.6817952394485474}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:33 - INFO - __main__ - Step 100740: {'lr': 0.0001246677197197707, 'samples': 19342080, 'steps': 100739, 'loss/train': 1.3962374925613403}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:36 - INFO - __main__ - Step 100745: {'lr': 0.00012464476194589883, 'samples': 19343040, 'steps': 100744, 'loss/train': 0.625195324420929}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:36 - INFO - __main__ - Step 100745: {'lr': 0.00012464476194589883, 'samples': 19343040, 'steps': 100744, 'loss/train': 0.625195324420929}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:40 - INFO - __main__ - Step 100753: {'lr': 0.00012460803244493455, 'samples': 19344576, 'steps': 100752, 'loss/train': 1.3073548078536987}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:41 - INFO - __main__ - Step 100757: {'lr': 0.00012458966905037864, 'samples': 19345344, 'steps': 100756, 'loss/train': 1.682469367980957}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:43 - INFO - __main__ - Step 100761: {'lr': 0.00012457130655995017, 'samples': 19346112, 'steps': 100760, 'loss/train': 1.6170716285705566}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:46 - INFO - __main__ - Step 100766: {'lr': 0.00012454835471854521, 'samples': 19347072, 'steps': 100765, 'loss/train': 1.7105607986450195}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:48 - INFO - __main__ - Step 100770: {'lr': 0.00012452999426288723, 'samples': 19347840, 'steps': 100769, 'loss/train': 1.4915541410446167}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:50 - INFO - __main__ - Step 100774: {'lr': 0.0001245116347117869, 'samples': 19348608, 'steps': 100773, 'loss/train': 2.166860580444336}7}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:50 - INFO - __main__ - Step 100774: {'lr': 0.0001245116347117869, 'samples': 19348608, 'steps': 100773, 'loss/train': 2.166860580444336}7}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:53 - INFO - __main__ - Step 100781: {'lr': 0.00012447950767435092, 'samples': 19349952, 'steps': 100780, 'loss/train': 1.4470858573913574}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:56 - INFO - __main__ - Step 100787: {'lr': 0.00012445197241941103, 'samples': 19351104, 'steps': 100786, 'loss/train': 1.0306757688522339}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:22:58 - INFO - __main__ - Step 100791: {'lr': 0.00012443361671415687, 'samples': 19351872, 'steps': 100790, 'loss/train': 1.2139861583709717}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:00 - INFO - __main__ - Step 100795: {'lr': 0.0001244152619141552, 'samples': 19352640, 'steps': 100794, 'loss/train': 1.4425697326660156}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:02 - INFO - __main__ - Step 100799: {'lr': 0.00012439690801953815, 'samples': 19353408, 'steps': 100798, 'loss/train': 0.7365450859069824}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:04 - INFO - __main__ - Step 100803: {'lr': 0.00012437855503043813, 'samples': 19354176, 'steps': 100802, 'loss/train': 1.4194430112838745}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:06 - INFO - __main__ - Step 100807: {'lr': 0.00012436020294698757, 'samples': 19354944, 'steps': 100806, 'loss/train': 1.8905922174453735}}███████████████████████���█| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:08 - INFO - __main__ - Step 100812: {'lr': 0.0001243372641164452, 'samples': 19355904, 'steps': 100811, 'loss/train': 1.421855092048645}5}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:10 - INFO - __main__ - Step 100816: {'lr': 0.00012431891407118937, 'samples': 19356672, 'steps': 100815, 'loss/train': 1.5570052862167358}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:12 - INFO - __main__ - Step 100820: {'lr': 0.0001243005649320129, 'samples': 19357440, 'steps': 100819, 'loss/train': 0.982189416885376}8}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:14 - INFO - __main__ - Step 100824: {'lr': 0.000124282216699048, 'samples': 19358208, 'steps': 100823, 'loss/train': 0.05032085254788399}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:16 - INFO - __main__ - Step 100828: {'lr': 0.00012426386937242705, 'samples': 19358976, 'steps': 100827, 'loss/train': 1.6103545427322388}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:18 - INFO - __main__ - Step 100832: {'lr': 0.00012424552295228216, 'samples': 19359744, 'steps': 100831, 'loss/train': 1.834947109222412}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:18 - INFO - __main__ - Step 100832: {'lr': 0.00012424552295228216, 'samples': 19359744, 'steps': 100831, 'loss/train': 1.834947109222412}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:21 - INFO - __main__ - Step 100839: {'lr': 0.00012421341889863472, 'samples': 19361088, 'steps': 100838, 'loss/train': 1.1959969997406006}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:23 - INFO - __main__ - Step 100843: {'lr': 0.00012419507497198138, 'samples': 19361856, 'steps': 100842, 'loss/train': 1.2363258600234985}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:26 - INFO - __main__ - Step 100848: {'lr': 0.00012417214633910962, 'samples': 19362816, 'steps': 100847, 'loss/train': 1.313966155052185}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:26 - INFO - __main__ - Step 100848: {'lr': 0.00012417214633910962, 'samples': 19362816, 'steps': 100847, 'loss/train': 1.313966155052185}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:30 - INFO - __main__ - Step 100856: {'lr': 0.00012413546347481895, 'samples': 19364352, 'steps': 100855, 'loss/train': 0.6135240197181702}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:31 - INFO - __main__ - Step 100860: {'lr': 0.0001241171234037103, 'samples': 19365120, 'steps': 100859, 'loss/train': 1.2935534715652466}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:34 - INFO - __main__ - Step 100864: {'lr': 0.00012409878424013573, 'samples': 19365888, 'steps': 100863, 'loss/train': 1.0840879678726196}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:36 - INFO - __main__ - Step 100868: {'lr': 0.0001240804459842276, 'samples': 19366656, 'steps': 100867, 'loss/train': 1.5909299850463867}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:36 - INFO - __main__ - Step 100868: {'lr': 0.0001240804459842276, 'samples': 19366656, 'steps': 100867, 'loss/train': 1.5909299850463867}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:40 - INFO - __main__ - Step 100874: {'lr': 0.0001240529403025288, 'samples': 19367808, 'steps': 100873, 'loss/train': 1.3951184749603271}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:41 - INFO - __main__ - Step 100878: {'lr': 0.00012403460431636477, 'samples': 19368576, 'steps': 100877, 'loss/train': 1.7510682344436646}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:44 - INFO - __main__ - Step 100883: {'lr': 0.00012401168561073175, 'samples': 19369536, 'steps': 100882, 'loss/train': 1.4298293590545654}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:46 - INFO - __main__ - Step 100888: {'lr': 0.00012398876832430837, 'samples': 19370496, 'steps': 100887, 'loss/train': 1.4015183448791504}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:48 - INFO - __main__ - Step 100892: {'lr': 0.00012397043551717418, 'samples': 19371264, 'steps': 100891, 'loss/train': 1.4816036224365234}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:50 - INFO - __main__ - Step 100896: {'lr': 0.00012395210361863172, 'samples': 19372032, 'steps': 100895, 'loss/train': 1.59525465965271}4}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:50 - INFO - __main__ - Step 100896: {'lr': 0.00012395210361863172, 'samples': 19372032, 'steps': 100895, 'loss/train': 1.59525465965271}4}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:53 - INFO - __main__ - Step 100903: {'lr': 0.00012392002498287836, 'samples': 19373376, 'steps': 100902, 'loss/train': 0.7509637475013733}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:56 - INFO - __main__ - Step 100908: {'lr': 0.0001238971133758755, 'samples': 19374336, 'steps': 100907, 'loss/train': 1.4367316961288452}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:23:56 - INFO - __main__ - Step 100908: {'lr': 0.0001238971133758755, 'samples': 19374336, 'steps': 100907, 'loss/train': 1.4367316961288452}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:00 - INFO - __main__ - Step 100916: {'lr': 0.0001238604577594189, 'samples': 19375872, 'steps': 100915, 'loss/train': 1.2676864862442017}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:02 - INFO - __main__ - Step 100920: {'lr': 0.0001238421313152013, 'samples': 19376640, 'steps': 100919, 'loss/train': 0.12427399307489395}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:04 - INFO - __main__ - Step 100924: {'lr': 0.00012382380578050036, 'samples': 19377408, 'steps': 100923, 'loss/train': 1.1578923463821411}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:06 - INFO - __main__ - Step 100929: {'lr': 0.00012380090014133316, 'samples': 19378368, 'steps': 100928, 'loss/train': 1.4770269393920898}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:08 - INFO - __main__ - Step 100933: {'lr': 0.0001237825766535276, 'samples': 19379136, 'steps': 100932, 'loss/train': 1.1312841176986694}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:08 - INFO - __main__ - Step 100933: {'lr': 0.0001237825766535276, 'samples': 19379136, 'steps': 100932, 'loss/train': 1.1312841176986694}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:12 - INFO - __main__ - Step 100941: {'lr': 0.00012374593240788658, 'samples': 19380672, 'steps': 100940, 'loss/train': 1.3061274290084839}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:14 - INFO - __main__ - Step 100945: {'lr': 0.0001237276116503152, 'samples': 19381440, 'steps': 100944, 'loss/train': 1.6611802577972412}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:16 - INFO - __main__ - Step 100950: {'lr': 0.00012370471198353534, 'samples': 19382400, 'steps': 100949, 'loss/train': 1.6378109455108643}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:16 - INFO - __main__ - Step 100950: {'lr': 0.00012370471198353534, 'samples': 19382400, 'steps': 100949, 'loss/train': 1.6378109455108643}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:20 - INFO - __main__ - Step 100958: {'lr': 0.00012366807547594354, 'samples': 19383936, 'steps': 100957, 'loss/train': 0.9621509909629822}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:22 - INFO - __main__ - Step 100962: {'lr': 0.00012364975858823884, 'samples': 19384704, 'steps': 100961, 'loss/train': 1.0215650796890259}}████████████████��████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:24 - INFO - __main__ - Step 100966: {'lr': 0.00012363144261143757, 'samples': 19385472, 'steps': 100965, 'loss/train': 1.4657591581344604}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:26 - INFO - __main__ - Step 100970: {'lr': 0.00012361312754567187, 'samples': 19386240, 'steps': 100969, 'loss/train': 0.8932575583457947}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:28 - INFO - __main__ - Step 100975: {'lr': 0.00012359023499480972, 'samples': 19387200, 'steps': 100974, 'loss/train': 1.1330276727676392}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:28 - INFO - __main__ - Step 100975: {'lr': 0.00012359023499480972, 'samples': 19387200, 'steps': 100974, 'loss/train': 1.1330276727676392}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:33 - INFO - __main__ - Step 100983: {'lr': 0.00012355360987536846, 'samples': 19388736, 'steps': 100982, 'loss/train': 1.432859182357788}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:34 - INFO - __main__ - Step 100987: {'lr': 0.00012353529868297685, 'samples': 19389504, 'steps': 100986, 'loss/train': 1.194886326789856}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:36 - INFO - __main__ - Step 100991: {'lr': 0.000123516988402314, 'samples': 19390272, 'steps': 100990, 'loss/train': 1.2469922304153442}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:39 - INFO - __main__ - Step 100996: {'lr': 0.00012349410183380488, 'samples': 19391232, 'steps': 100995, 'loss/train': 1.5374937057495117}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:39 - INFO - __main__ - Step 100996: {'lr': 0.00012349410183380488, 'samples': 19391232, 'steps': 100995, 'loss/train': 1.5374937057495117}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:39 - INFO - __main__ - Step 100996: {'lr': 0.00012349410183380488, 'samples': 19391232, 'steps': 100995, 'loss/train': 1.5374937057495117}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:44 - INFO - __main__ - Step 101006: {'lr': 0.00012344833297216496, 'samples': 19393152, 'steps': 101005, 'loss/train': 1.1538740396499634}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:46 - INFO - __main__ - Step 101011: {'lr': 0.00012342545067954965, 'samples': 19394112, 'steps': 101010, 'loss/train': 1.4514005184173584}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:50 - INFO - __main__ - Step 101016: {'lr': 0.00012340256981274787, 'samples': 19395072, 'steps': 101015, 'loss/train': 1.3779529333114624}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:53 - INFO - __main__ - Step 101022: {'lr': 0.0001233751146550223, 'samples': 19396224, 'steps': 101021, 'loss/train': 1.463753581047058}4}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:53 - INFO - __main__ - Step 101022: {'lr': 0.0001233751146550223, 'samples': 19396224, 'steps': 101021, 'loss/train': 1.463753581047058}4}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:56 - INFO - __main__ - Step 101029: {'lr': 0.00012334308623371964, 'samples': 19397568, 'steps': 101028, 'loss/train': 1.5031373500823975}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:24:58 - INFO - __main__ - Step 101034: {'lr': 0.00012332021050198027, 'samples': 19398528, 'steps': 101033, 'loss/train': 1.496986985206604}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:01 - INFO - __main__ - Step 101039: {'lr': 0.00012329733619723986, 'samples': 19399488, 'steps': 101038, 'loss/train': 1.4131757020950317}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:01 - INFO - __main__ - Step 101039: {'lr': 0.00012329733619723986, 'samples': 19399488, 'steps': 101038, 'loss/train': 1.4131757020950317}}█████████████���███████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:04 - INFO - __main__ - Step 101046: {'lr': 0.0001232653145684522, 'samples': 19400832, 'steps': 101045, 'loss/train': 1.0700314044952393}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:06 - INFO - __main__ - Step 101050: {'lr': 0.00012324701775111714, 'samples': 19401600, 'steps': 101049, 'loss/train': 0.16593840718269348}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:09 - INFO - __main__ - Step 101055: {'lr': 0.00012322414801450493, 'samples': 19402560, 'steps': 101054, 'loss/train': 1.5559340715408325}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:09 - INFO - __main__ - Step 101055: {'lr': 0.00012322414801450493, 'samples': 19402560, 'steps': 101054, 'loss/train': 1.5559340715408325}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:13 - INFO - __main__ - Step 101063: {'lr': 0.00012318755940644106, 'samples': 19404096, 'steps': 101062, 'loss/train': 0.5518665313720703}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:15 - INFO - __main__ - Step 101067: {'lr': 0.00012316926647369675, 'samples': 19404864, 'steps': 101066, 'loss/train': 1.4535208940505981}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:16 - INFO - __main__ - Step 101071: {'lr': 0.0001231509744553199, 'samples': 19405632, 'steps': 101070, 'loss/train': 0.946509599685669}1}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:19 - INFO - __main__ - Step 101075: {'lr': 0.00012313268335144257, 'samples': 19406400, 'steps': 101074, 'loss/train': 1.2028634548187256}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:21 - INFO - __main__ - Step 101080: {'lr': 0.00012310982075781148, 'samples': 19407360, 'steps': 101079, 'loss/train': 1.2412669658660889}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:21 - INFO - __main__ - Step 101080: {'lr': 0.00012310982075781148, 'samples': 19407360, 'steps': 101079, 'loss/train': 1.2412669658660889}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:24 - INFO - __main__ - Step 101087: {'lr': 0.0001230778155281255, 'samples': 19408704, 'steps': 101086, 'loss/train': 1.4444211721420288}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:26 - INFO - __main__ - Step 101091: {'lr': 0.00012305952808356433, 'samples': 19409472, 'steps': 101090, 'loss/train': 1.5563995838165283}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:29 - INFO - __main__ - Step 101096: {'lr': 0.0001230366700648202, 'samples': 19410432, 'steps': 101095, 'loss/train': 1.8681073188781738}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:31 - INFO - __main__ - Step 101100: {'lr': 0.00012301838467955155, 'samples': 19411200, 'steps': 101099, 'loss/train': 1.1627202033996582}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:33 - INFO - __main__ - Step 101104: {'lr': 0.0001230001002097381, 'samples': 19411968, 'steps': 101103, 'loss/train': 1.4004981517791748}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:33 - INFO - __main__ - Step 101104: {'lr': 0.0001230001002097381, 'samples': 19411968, 'steps': 101103, 'loss/train': 1.4004981517791748}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:36 - INFO - __main__ - Step 101111: {'lr': 0.0001229681045907755, 'samples': 19413312, 'steps': 101110, 'loss/train': 1.5222183465957642}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:36 - INFO - __main__ - Step 101111: {'lr': 0.0001229681045907755, 'samples': 19413312, 'steps': 101110, 'loss/train': 1.5222183465957642}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:40 - INFO - __main__ - Step 101118: {'lr': 0.0001229361117765048, 'samples': 19414656, 'steps': 101117, 'loss/train': 1.2876300811767578}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:42 - INFO - __main__ - Step 101123: {'lr': 0.00012291326148386114, 'samples': 19415616, 'steps': 101122, 'loss/train': 1.4922082424163818}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:42 - INFO - __main__ - Step 101123: {'lr': 0.00012291326148386114, 'samples': 19415616, 'steps': 101122, 'loss/train': 1.4922082424163818}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:47 - INFO - __main__ - Step 101131: {'lr': 0.00012287670399343102, 'samples': 19417152, 'steps': 101130, 'loss/train': 1.2912522554397583}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:48 - INFO - __main__ - Step 101135: {'lr': 0.00012285842662286518, 'samples': 19417920, 'steps': 101134, 'loss/train': 1.3297075033187866}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:50 - INFO - __main__ - Step 101139: {'lr': 0.0001228401501689079, 'samples': 19418688, 'steps': 101138, 'loss/train': 1.5085904598236084}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:53 - INFO - __main__ - Step 101144: {'lr': 0.00012281730589064262, 'samples': 19419648, 'steps': 101143, 'loss/train': 1.4045161008834839}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:55 - INFO - __main__ - Step 101148: {'lr': 0.00012279903149953615, 'samples': 19420416, 'steps': 101147, 'loss/train': 1.539445400238037}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:55 - INFO - __main__ - Step 101148: {'lr': 0.00012279903149953615, 'samples': 19420416, 'steps': 101147, 'loss/train': 1.539445400238037}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:25:58 - INFO - __main__ - Step 101155: {'lr': 0.00012276705352179867, 'samples': 19421760, 'steps': 101154, 'loss/train': 1.842391014099121}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:01 - INFO - __main__ - Step 101160: {'lr': 0.00012274421382896388, 'samples': 19422720, 'steps': 101159, 'loss/train': 1.0176959037780762}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:03 - INFO - __main__ - Step 101164: {'lr': 0.0001227259431067947, 'samples': 19423488, 'steps': 101163, 'loss/train': 1.9680858850479126}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:05 - INFO - __main__ - Step 101168: {'lr': 0.00012270767330218902, 'samples': 19424256, 'steps': 101167, 'loss/train': 1.0462911128997803}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:07 - INFO - __main__ - Step 101172: {'lr': 0.00012268940441527865, 'samples': 19425024, 'steps': 101171, 'loss/train': 1.0634068250656128}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:08 - INFO - __main__ - Step 101176: {'lr': 0.00012267113644619536, 'samples': 19425792, 'steps': 101175, 'loss/train': 1.1404653787612915}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:10 - INFO - __main__ - Step 101180: {'lr': 0.00012265286939507086, 'samples': 19426560, 'steps': 101179, 'loss/train': 1.3812332153320312}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:13 - INFO - __main__ - Step 101185: {'lr': 0.00012263003687224526, 'samples': 19427520, 'steps': 101184, 'loss/train': 1.183737874031067}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:15 - INFO - __main__ - Step 101189: {'lr': 0.00012261177188700932, 'samples': 19428288, 'steps': 101188, 'loss/train': 1.5328885316848755}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:15 - INFO - __main__ - Step 101189: {'lr': 0.00012261177188700932, 'samples': 19428288, 'steps': 101188, 'loss/train': 1.5328885316848755}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:18 - INFO - __main__ - Step 101196: {'lr': 0.00012257981037279382, 'samples': 19429632, 'steps': 101195, 'loss/train': 1.6280089616775513}}██████��██████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:18 - INFO - __main__ - Step 101196: {'lr': 0.00012257981037279382, 'samples': 19429632, 'steps': 101195, 'loss/train': 1.6280089616775513}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:22 - INFO - __main__ - Step 101204: {'lr': 0.00012254328637283148, 'samples': 19431168, 'steps': 101203, 'loss/train': 1.5397460460662842}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:24 - INFO - __main__ - Step 101208: {'lr': 0.00012252502575110512, 'samples': 19431936, 'steps': 101207, 'loss/train': 1.299210548400879}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:27 - INFO - __main__ - Step 101213: {'lr': 0.00012250220126632332, 'samples': 19432896, 'steps': 101212, 'loss/train': 1.4148085117340088}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:29 - INFO - __main__ - Step 101217: {'lr': 0.0001224839427125594, 'samples': 19433664, 'steps': 101216, 'loss/train': 1.2066577672958374}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:29 - INFO - __main__ - Step 101217: {'lr': 0.0001224839427125594, 'samples': 19433664, 'steps': 101216, 'loss/train': 1.2066577672958374}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:32 - INFO - __main__ - Step 101224: {'lr': 0.00012245199245563713, 'samples': 19435008, 'steps': 101223, 'loss/train': 1.3407707214355469}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:34 - INFO - __main__ - Step 101228: {'lr': 0.0001224337364302876, 'samples': 19435776, 'steps': 101227, 'loss/train': 0.9073700904846191}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:37 - INFO - __main__ - Step 101233: {'lr': 0.0001224109176919025, 'samples': 19436736, 'steps': 101232, 'loss/train': 1.2006711959838867}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:39 - INFO - __main__ - Step 101237: {'lr': 0.00012239266373599607, 'samples': 19437504, 'steps': 101236, 'loss/train': 1.410408616065979}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:41 - INFO - __main__ - Step 101241: {'lr': 0.00012237441070005604, 'samples': 19438272, 'steps': 101240, 'loss/train': 0.5344693064689636}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:42 - INFO - __main__ - Step 101245: {'lr': 0.000122356158584214, 'samples': 19439040, 'steps': 101244, 'loss/train': 1.4351974725723267}6}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:45 - INFO - __main__ - Step 101249: {'lr': 0.0001223379073886014, 'samples': 19439808, 'steps': 101248, 'loss/train': 1.4726701974868774}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:47 - INFO - __main__ - Step 101254: {'lr': 0.00012231509468835886, 'samples': 19440768, 'steps': 101253, 'loss/train': 1.2759636640548706}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:49 - INFO - __main__ - Step 101258: {'lr': 0.00012229684556374384, 'samples': 19441536, 'steps': 101257, 'loss/train': 1.2945237159729004}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:49 - INFO - __main__ - Step 101258: {'lr': 0.00012229684556374384, 'samples': 19441536, 'steps': 101257, 'loss/train': 1.2945237159729004}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:52 - INFO - __main__ - Step 101265: {'lr': 0.0001222649118110778, 'samples': 19442880, 'steps': 101264, 'loss/train': 1.3305848836898804}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:55 - INFO - __main__ - Step 101270: {'lr': 0.00012224210371436755, 'samples': 19443840, 'steps': 101269, 'loss/train': 1.2633976936340332}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:57 - INFO - __main__ - Step 101275: {'lr': 0.00012221929705680086, 'samples': 19444800, 'steps': 101274, 'loss/train': 1.0778768062591553}}███���█████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:26:59 - INFO - __main__ - Step 101279: {'lr': 0.00012220105276710333, 'samples': 19445568, 'steps': 101278, 'loss/train': 1.1105891466140747}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:01 - INFO - __main__ - Step 101283: {'lr': 0.0001221828093987535, 'samples': 19446336, 'steps': 101282, 'loss/train': 1.3701599836349487}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:01 - INFO - __main__ - Step 101283: {'lr': 0.0001221828093987535, 'samples': 19446336, 'steps': 101282, 'loss/train': 1.3701599836349487}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:04 - INFO - __main__ - Step 101290: {'lr': 0.00012215088572153002, 'samples': 19447680, 'steps': 101289, 'loss/train': 1.5789374113082886}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:07 - INFO - __main__ - Step 101295: {'lr': 0.0001221280848231058, 'samples': 19448640, 'steps': 101294, 'loss/train': 1.610235571861267}6}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:09 - INFO - __main__ - Step 101300: {'lr': 0.00012210528536510948, 'samples': 19449600, 'steps': 101299, 'loss/train': 1.4384722709655762}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:11 - INFO - __main__ - Step 101304: {'lr': 0.00012208704683599293, 'samples': 19450368, 'steps': 101303, 'loss/train': 1.0750707387924194}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:11 - INFO - __main__ - Step 101304: {'lr': 0.00012208704683599293, 'samples': 19450368, 'steps': 101303, 'loss/train': 1.0750707387924194}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:15 - INFO - __main__ - Step 101311: {'lr': 0.00012205513162908888, 'samples': 19451712, 'steps': 101310, 'loss/train': 1.297237515449524}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:15 - INFO - __main__ - Step 101311: {'lr': 0.00012205513162908888, 'samples': 19451712, 'steps': 101310, 'loss/train': 1.297237515449524}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:19 - INFO - __main__ - Step 101319: {'lr': 0.00012201866056595279, 'samples': 19453248, 'steps': 101318, 'loss/train': 1.284055471420288}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:20 - INFO - __main__ - Step 101323: {'lr': 0.0001220004264183131, 'samples': 19454016, 'steps': 101322, 'loss/train': 1.4320480823516846}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:22 - INFO - __main__ - Step 101327: {'lr': 0.00012198219319346743, 'samples': 19454784, 'steps': 101326, 'loss/train': 1.8464399576187134}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:25 - INFO - __main__ - Step 101332: {'lr': 0.00012195940296028984, 'samples': 19455744, 'steps': 101331, 'loss/train': 0.20168174803256989}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:27 - INFO - __main__ - Step 101336: {'lr': 0.00012194117181221168, 'samples': 19456512, 'steps': 101335, 'loss/train': 1.046228051185608}9}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:29 - INFO - __main__ - Step 101340: {'lr': 0.0001219229415873547, 'samples': 19457280, 'steps': 101339, 'loss/train': 1.2700765132904053}9}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:31 - INFO - __main__ - Step 101344: {'lr': 0.00012190471228585057, 'samples': 19458048, 'steps': 101343, 'loss/train': 1.4025328159332275}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:33 - INFO - __main__ - Step 101348: {'lr': 0.00012188648390783049, 'samples': 19458816, 'steps': 101347, 'loss/train': 1.343144178390503}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:35 - INFO - __main__ - Step 101353: {'lr': 0.00012186369973415523, 'samples': 19459776, 'steps': 101352, 'loss/train': 1.4192053079605103}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:37 - INFO - __main__ - Step 101357: {'lr': 0.0001218454734344551, 'samples': 19460544, 'steps': 101356, 'loss/train': 1.3761242628097534}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:39 - INFO - __main__ - Step 101361: {'lr': 0.00012182724805866607, 'samples': 19461312, 'steps': 101360, 'loss/train': 1.3853405714035034}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:41 - INFO - __main__ - Step 101365: {'lr': 0.00012180902360691982, 'samples': 19462080, 'steps': 101364, 'loss/train': 1.2218133211135864}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:43 - INFO - __main__ - Step 101369: {'lr': 0.00012179080007934746, 'samples': 19462848, 'steps': 101368, 'loss/train': 1.4032315015792847}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:45 - INFO - __main__ - Step 101373: {'lr': 0.00012177257747608048, 'samples': 19463616, 'steps': 101372, 'loss/train': 1.6144028902053833}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:47 - INFO - __main__ - Step 101378: {'lr': 0.00012174980052200146, 'samples': 19464576, 'steps': 101377, 'loss/train': 1.4210253953933716}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:49 - INFO - __main__ - Step 101382: {'lr': 0.00012173157999890194, 'samples': 19465344, 'steps': 101381, 'loss/train': 0.1988002508878708}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:51 - INFO - __main__ - Step 101386: {'lr': 0.00012171336040053477, 'samples': 19466112, 'steps': 101385, 'loss/train': 1.461118221282959}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:53 - INFO - __main__ - Step 101390: {'lr': 0.00012169514172703128, 'samples': 19466880, 'steps': 101389, 'loss/train': 1.310351848602295}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:55 - INFO - __main__ - Step 101394: {'lr': 0.0001216769239785229, 'samples': 19467648, 'steps': 101393, 'loss/train': 1.4568254947662354}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:57 - INFO - __main__ - Step 101399: {'lr': 0.00012165415309386166, 'samples': 19468608, 'steps': 101398, 'loss/train': 1.3253085613250732}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:27:59 - INFO - __main__ - Step 101403: {'lr': 0.00012163593742707222, 'samples': 19469376, 'steps': 101402, 'loss/train': 1.6441493034362793}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:01 - INFO - __main__ - Step 101407: {'lr': 0.00012161772268570471, 'samples': 19470144, 'steps': 101406, 'loss/train': 1.908919095993042}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:01 - INFO - __main__ - Step 101407: {'lr': 0.00012161772268570471, 'samples': 19470144, 'steps': 101406, 'loss/train': 1.908919095993042}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:05 - INFO - __main__ - Step 101414: {'lr': 0.00012158584911550269, 'samples': 19471488, 'steps': 101413, 'loss/train': 1.483489751815796}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:05 - INFO - __main__ - Step 101414: {'lr': 0.00012158584911550269, 'samples': 19471488, 'steps': 101413, 'loss/train': 1.483489751815796}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:09 - INFO - __main__ - Step 101423: {'lr': 0.00012154487297707911, 'samples': 19473216, 'steps': 101422, 'loss/train': 0.8564873337745667}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:11 - INFO - __main__ - Step 101427: {'lr': 0.00012152666286479039, 'samples': 19473984, 'steps': 101426, 'loss/train': 1.278848648071289}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:12 - INFO - __main__ - Step 101431: {'lr': 0.0001215084536787113, 'samples': 19474752, 'steps': 101430, 'loss/train': 1.5259968042373657}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:15 - INFO - __main__ - Step 101436: {'lr': 0.00012148569349879484, 'samples': 19475712, 'steps': 101435, 'loss/train': 0.8615953922271729}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:15 - INFO - __main__ - Step 101436: {'lr': 0.00012148569349879484, 'samples': 19475712, 'steps': 101435, 'loss/train': 0.8615953922271729}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:19 - INFO - __main__ - Step 101444: {'lr': 0.00012144928022217635, 'samples': 19477248, 'steps': 101443, 'loss/train': 1.554343819618225}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:21 - INFO - __main__ - Step 101448: {'lr': 0.00012143107497395286, 'samples': 19478016, 'steps': 101447, 'loss/train': 1.2557196617126465}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:23 - INFO - __main__ - Step 101452: {'lr': 0.00012141287065262805, 'samples': 19478784, 'steps': 101451, 'loss/train': 1.4452106952667236}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:25 - INFO - __main__ - Step 101456: {'lr': 0.00012139466725833326, 'samples': 19479552, 'steps': 101455, 'loss/train': 1.4095011949539185}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:27 - INFO - __main__ - Step 101461: {'lr': 0.00012137191431930075, 'samples': 19480512, 'steps': 101460, 'loss/train': 1.276069164276123}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:27 - INFO - __main__ - Step 101461: {'lr': 0.00012137191431930075, 'samples': 19480512, 'steps': 101460, 'loss/train': 1.276069164276123}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:30 - INFO - __main__ - Step 101468: {'lr': 0.0001213400626389414, 'samples': 19481856, 'steps': 101467, 'loss/train': 1.1037694215774536}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:32 - INFO - __main__ - Step 101472: {'lr': 0.00012132186295407899, 'samples': 19482624, 'steps': 101471, 'loss/train': 1.9227213859558105}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:35 - INFO - __main__ - Step 101477: {'lr': 0.00012129911465257504, 'samples': 19483584, 'steps': 101476, 'loss/train': 1.742929220199585}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:37 - INFO - __main__ - Step 101481: {'lr': 0.00012128091705519086, 'samples': 19484352, 'steps': 101480, 'loss/train': 0.9899769425392151}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:39 - INFO - __main__ - Step 101485: {'lr': 0.00012126272038578806, 'samples': 19485120, 'steps': 101484, 'loss/train': 1.972767949104309}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:39 - INFO - __main__ - Step 101485: {'lr': 0.00012126272038578806, 'samples': 19485120, 'steps': 101484, 'loss/train': 1.972767949104309}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:42 - INFO - __main__ - Step 101492: {'lr': 0.00012123087844768283, 'samples': 19486464, 'steps': 101491, 'loss/train': 1.2712907791137695}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:45 - INFO - __main__ - Step 101497: {'lr': 0.00012120813594677942, 'samples': 19487424, 'steps': 101496, 'loss/train': 1.0635172128677368}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:45 - INFO - __main__ - Step 101497: {'lr': 0.00012120813594677942, 'samples': 19487424, 'steps': 101496, 'loss/train': 1.0635172128677368}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:49 - INFO - __main__ - Step 101505: {'lr': 0.0001211717509630852, 'samples': 19488960, 'steps': 101504, 'loss/train': 5.852468967437744}8}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:51 - INFO - __main__ - Step 101509: {'lr': 0.00012115355986432497, 'samples': 19489728, 'steps': 101508, 'loss/train': 1.0902458429336548}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:53 - INFO - __main__ - Step 101514: {'lr': 0.00012113082229715502, 'samples': 19490688, 'steps': 101513, 'loss/train': 0.6290778517723083}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:53 - INFO - __main__ - Step 101514: {'lr': 0.00012113082229715502, 'samples': 19490688, 'steps': 101513, 'loss/train': 0.6290778517723083}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:58 - INFO - __main__ - Step 101522: {'lr': 0.00012109444520924561, 'samples': 19492224, 'steps': 101521, 'loss/train': 1.170771598815918}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:28:59 - INFO - __main__ - Step 101526: {'lr': 0.00012107625805921391, 'samples': 19492992, 'steps': 101525, 'loss/train': 1.32510507106781}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:01 - INFO - __main__ - Step 101530: {'lr': 0.0001210580718386389, 'samples': 19493760, 'steps': 101529, 'loss/train': 1.4191949367523193}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:03 - INFO - __main__ - Step 101535: {'lr': 0.0001210353403701685, 'samples': 19494720, 'steps': 101534, 'loss/train': 1.3892375230789185}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:03 - INFO - __main__ - Step 101535: {'lr': 0.0001210353403701685, 'samples': 19494720, 'steps': 101534, 'loss/train': 1.3892375230789185}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:07 - INFO - __main__ - Step 101542: {'lr': 0.00012100351875496573, 'samples': 19496064, 'steps': 101541, 'loss/train': 0.8568156361579895}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:09 - INFO - __main__ - Step 101546: {'lr': 0.0001209853362535289, 'samples': 19496832, 'steps': 101545, 'loss/train': 1.6274733543395996}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:11 - INFO - __main__ - Step 101550: {'lr': 0.00012096715468220431, 'samples': 19497600, 'steps': 101549, 'loss/train': 1.3111296892166138}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:13 - INFO - __main__ - Step 101555: {'lr': 0.00012094442902621874, 'samples': 19498560, 'steps': 101554, 'loss/train': 0.9298396110534668}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:15 - INFO - __main__ - Step 101560: {'lr': 0.00012092170482399431, 'samples': 19499520, 'steps': 101559, 'loss/train': 1.2717481851577759}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:17 - INFO - __main__ - Step 101564: {'lr': 0.00012090352650909483, 'samples': 19500288, 'steps': 101563, 'loss/train': 1.2261123657226562}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:17 - INFO - __main__ - Step 101564: {'lr': 0.00012090352650909483, 'samples': 19500288, 'steps': 101563, 'loss/train': 1.2261123657226562}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:21 - INFO - __main__ - Step 101571: {'lr': 0.00012087171669760155, 'samples': 19501632, 'steps': 101570, 'loss/train': 1.246108055114746}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:23 - INFO - __main__ - Step 101576: {'lr': 0.00012084899714913311, 'samples': 19502592, 'steps': 101575, 'loss/train': 1.3805408477783203}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:25 - INFO - __main__ - Step 101580: {'lr': 0.00012083082255782824, 'samples': 19503360, 'steps': 101579, 'loss/train': 1.1080831289291382}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:28 - INFO - __main__ - Step 101585: {'lr': 0.00012080810562824926, 'samples': 19504320, 'steps': 101584, 'loss/train': 1.6686677932739258}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:28 - INFO - __main__ - Step 101585: {'lr': 0.00012080810562824926, 'samples': 19504320, 'steps': 101584, 'loss/train': 1.6686677932739258}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:31 - INFO - __main__ - Step 101592: {'lr': 0.00012077630437179479, 'samples': 19505664, 'steps': 101591, 'loss/train': 1.0202275514602661}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:33 - INFO - __main__ - Step 101597: {'lr': 0.00012075359093535812, 'samples': 19506624, 'steps': 101596, 'loss/train': 1.2160303592681885}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:33 - INFO - __main__ - Step 101597: {'lr': 0.00012075359093535812, 'samples': 19506624, 'steps': 101596, 'loss/train': 1.2160303592681885}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:37 - INFO - __main__ - Step 101605: {'lr': 0.00012071725246546073, 'samples': 19508160, 'steps': 101604, 'loss/train': 1.2629625797271729}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:37 - INFO - __main__ - Step 101605: {'lr': 0.00012071725246546073, 'samples': 19508160, 'steps': 101604, 'loss/train': 1.2629625797271729}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:41 - INFO - __main__ - Step 101612: {'lr': 0.00012068545936253728, 'samples': 19509504, 'steps': 101611, 'loss/train': 0.2661668658256531}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:43 - INFO - __main__ - Step 101617: {'lr': 0.00012066275175127935, 'samples': 19510464, 'steps': 101616, 'loss/train': 1.3655316829681396}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:45 - INFO - __main__ - Step 101621: {'lr': 0.00012064458671125336, 'samples': 19511232, 'steps': 101620, 'loss/train': 0.3383299708366394}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:48 - INFO - __main__ - Step 101625: {'lr': 0.0001206264226037963, 'samples': 19512000, 'steps': 101624, 'loss/train': 0.9840372800827026}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:49 - INFO - __main__ - Step 101629: {'lr': 0.00012060825942903894, 'samples': 19512768, 'steps': 101628, 'loss/train': 0.6824367046356201}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:51 - INFO - __main__ - Step 101633: {'lr': 0.00012059009718711233, 'samples': 19513536, 'steps': 101632, 'loss/train': 1.754284381866455}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:53 - INFO - __main__ - Step 101638: {'lr': 0.00012056739569669688, 'samples': 19514496, 'steps': 101637, 'loss/train': 1.3556504249572754}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:56 - INFO - __main__ - Step 101643: {'lr': 0.00012054469566428971, 'samples': 19515456, 'steps': 101642, 'loss/train': 1.31638503074646}4}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:56 - INFO - __main__ - Step 101643: {'lr': 0.00012054469566428971, 'samples': 19515456, 'steps': 101642, 'loss/train': 1.31638503074646}4}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:29:59 - INFO - __main__ - Step 101650: {'lr': 0.00012051291806886067, 'samples': 19516800, 'steps': 101649, 'loss/train': 1.166671872138977}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:01 - INFO - __main__ - Step 101654: {'lr': 0.00012049476072644352, 'samples': 19517568, 'steps': 101653, 'loss/train': 1.2734516859054565}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:04 - INFO - __main__ - Step 101659: {'lr': 0.00012047206536138133, 'samples': 19518528, 'steps': 101658, 'loss/train': 1.5165202617645264}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:04 - INFO - __main__ - Step 101659: {'lr': 0.00012047206536138133, 'samples': 19518528, 'steps': 101658, 'loss/train': 1.5165202617645264}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:07 - INFO - __main__ - Step 101666: {'lr': 0.00012044029430160977, 'samples': 19519872, 'steps': 101665, 'loss/train': 1.2834768295288086}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:09 - INFO - __main__ - Step 101670: {'lr': 0.00012042214069457397, 'samples': 19520640, 'steps': 101669, 'loss/train': 1.0168360471725464}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:11 - INFO - __main__ - Step 101675: {'lr': 0.00012039944999947477, 'samples': 19521600, 'steps': 101674, 'loss/train': 1.124882459640503}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:13 - INFO - __main__ - Step 101679: {'lr': 0.00012038129849451124, 'samples': 19522368, 'steps': 101678, 'loss/train': 1.1109845638275146}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:16 - INFO - __main__ - Step 101683: {'lr': 0.00012036314792401467, 'samples': 19523136, 'steps': 101682, 'loss/train': 1.3834847211837769}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:16 - INFO - __main__ - Step 101683: {'lr': 0.00012036314792401467, 'samples': 19523136, 'steps': 101682, 'loss/train': 1.3834847211837769}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:19 - INFO - __main__ - Step 101690: {'lr': 0.00012033138667460058, 'samples': 19524480, 'steps': 101689, 'loss/train': 1.744284987449646}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:22 - INFO - __main__ - Step 101696: {'lr': 0.00012030416502514504, 'samples': 19525632, 'steps': 101695, 'loss/train': 1.2623049020767212}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:22 - INFO - __main__ - Step 101696: {'lr': 0.00012030416502514504, 'samples': 19525632, 'steps': 101695, 'loss/train': 1.2623049020767212}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:25 - INFO - __main__ - Step 101703: {'lr': 0.00012027240909311656, 'samples': 19526976, 'steps': 101702, 'loss/train': 1.1571052074432373}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:27 - INFO - __main__ - Step 101707: {'lr': 0.00012025426413216963, 'samples': 19527744, 'steps': 101706, 'loss/train': 1.4115800857543945}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:29 - INFO - __main__ - Step 101711: {'lr': 0.00012023612010660551, 'samples': 19528512, 'steps': 101710, 'loss/train': 1.6273910999298096}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:31 - INFO - __main__ - Step 101716: {'lr': 0.00012021344139023186, 'samples': 19529472, 'steps': 101715, 'loss/train': 1.4104139804840088}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:31 - INFO - __main__ - Step 101716: {'lr': 0.00012021344139023186, 'samples': 19529472, 'steps': 101715, 'loss/train': 1.4104139804840088}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:36 - INFO - __main__ - Step 101724: {'lr': 0.00012017715848509076, 'samples': 19531008, 'steps': 101723, 'loss/train': 1.6820766925811768}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:37 - INFO - __main__ - Step 101728: {'lr': 0.00012015901843636295, 'samples': 19531776, 'steps': 101727, 'loss/train': 0.9100181460380554}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:39 - INFO - __main__ - Step 101733: {'lr': 0.00012013634469181614, 'samples': 19532736, 'steps': 101732, 'loss/train': 1.006213665008545}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:42 - INFO - __main__ - Step 101737: {'lr': 0.0001201182067494285, 'samples': 19533504, 'steps': 101736, 'loss/train': 1.541221022605896}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:44 - INFO - __main__ - Step 101741: {'lr': 0.00012010006974340454, 'samples': 19534272, 'steps': 101740, 'loss/train': 5.6946539878845215}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:45 - INFO - __main__ - Step 101745: {'lr': 0.00012008193367387518, 'samples': 19535040, 'steps': 101744, 'loss/train': 1.5754610300064087}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:47 - INFO - __main__ - Step 101749: {'lr': 0.0001200637985409709, 'samples': 19535808, 'steps': 101748, 'loss/train': 1.4828088283538818}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:50 - INFO - __main__ - Step 101754: {'lr': 0.00012004113094216898, 'samples': 19536768, 'steps': 101753, 'loss/train': 2.1444358825683594}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:50 - INFO - __main__ - Step 101754: {'lr': 0.00012004113094216898, 'samples': 19536768, 'steps': 101753, 'loss/train': 2.1444358825683594}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:54 - INFO - __main__ - Step 101761: {'lr': 0.0001200093987633169, 'samples': 19538112, 'steps': 101760, 'loss/train': 1.6905252933502197}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:55 - INFO - __main__ - Step 101765: {'lr': 0.00011999126737822085, 'samples': 19538880, 'steps': 101764, 'loss/train': 1.0414793491363525}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:30:57 - INFO - __main__ - Step 101769: {'lr': 0.00011997313693040377, 'samples': 19539648, 'steps': 101768, 'loss/train': 1.554802417755127}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:00 - INFO - __main__ - Step 101774: {'lr': 0.00011995047518887981, 'samples': 19540608, 'steps': 101773, 'loss/train': 0.6359546184539795}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:02 - INFO - __main__ - Step 101778: {'lr': 0.00011993234685041795, 'samples': 19541376, 'steps': 101777, 'loss/train': 1.1766448020935059}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:04 - INFO - __main__ - Step 101782: {'lr': 0.00011991421944965982, 'samples': 19542144, 'steps': 101781, 'loss/train': 0.5929391384124756}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:05 - INFO - __main__ - Step 101786: {'lr': 0.00011989609298673592, 'samples': 19542912, 'steps': 101785, 'loss/train': 1.1804986000061035}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:07 - INFO - __main__ - Step 101790: {'lr': 0.00011987796746177704, 'samples': 19543680, 'steps': 101789, 'loss/train': 1.3300570249557495}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:10 - INFO - __main__ - Step 101795: {'lr': 0.0001198553118747909, 'samples': 19544640, 'steps': 101794, 'loss/train': 1.1746582984924316}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:12 - INFO - __main__ - Step 101799: {'lr': 0.00011983718846073103, 'samples': 19545408, 'steps': 101798, 'loss/train': 0.8423688411712646}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:14 - INFO - __main__ - Step 101803: {'lr': 0.00011981906598506084, 'samples': 19546176, 'steps': 101802, 'loss/train': 1.4289164543151855}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:16 - INFO - __main__ - Step 101807: {'lr': 0.00011980094444791095, 'samples': 19546944, 'steps': 101806, 'loss/train': 1.5141892433166504}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:17 - INFO - __main__ - Step 101811: {'lr': 0.00011978282384941214, 'samples': 19547712, 'steps': 101810, 'loss/train': 1.127354383468628}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:19 - INFO - __main__ - Step 101815: {'lr': 0.00011976470418969485, 'samples': 19548480, 'steps': 101814, 'loss/train': 1.5553100109100342}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:19 - INFO - __main__ - Step 101815: {'lr': 0.00011976470418969485, 'samples': 19548480, 'steps': 101814, 'loss/train': 1.5553100109100342}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:24 - INFO - __main__ - Step 101823: {'lr': 0.00011972846768712764, 'samples': 19550016, 'steps': 101822, 'loss/train': 1.3940372467041016}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:25 - INFO - __main__ - Step 101827: {'lr': 0.0001197103508445389, 'samples': 19550784, 'steps': 101826, 'loss/train': 1.5927979946136475}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:28 - INFO - __main__ - Step 101831: {'lr': 0.00011969223494125425, 'samples': 19551552, 'steps': 101830, 'loss/train': 0.15115824341773987}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:30 - INFO - __main__ - Step 101835: {'lr': 0.00011967411997740429, 'samples': 19552320, 'steps': 101834, 'loss/train': 1.8165404796600342}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:32 - INFO - __main__ - Step 101839: {'lr': 0.00011965600595311973, 'samples': 19553088, 'steps': 101838, 'loss/train': 1.0310977697372437}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:33 - INFO - __main__ - Step 101843: {'lr': 0.00011963789286853093, 'samples': 19553856, 'steps': 101842, 'loss/train': 1.9928758144378662}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:36 - INFO - __main__ - Step 101847: {'lr': 0.00011961978072376859, 'samples': 19554624, 'steps': 101846, 'loss/train': 0.8797428011894226}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:36 - INFO - __main__ - Step 101847: {'lr': 0.00011961978072376859, 'samples': 19554624, 'steps': 101846, 'loss/train': 0.8797428011894226}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:39 - INFO - __main__ - Step 101853: {'lr': 0.00011959261426908544, 'samples': 19555776, 'steps': 101852, 'loss/train': 1.056114673614502}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:41 - INFO - __main__ - Step 101858: {'lr': 0.00011956997717271848, 'samples': 19556736, 'steps': 101857, 'loss/train': 1.1731173992156982}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:41 - INFO - __main__ - Step 101858: {'lr': 0.00011956997717271848, 'samples': 19556736, 'steps': 101857, 'loss/train': 1.1731173992156982}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:41 - INFO - __main__ - Step 101858: {'lr': 0.00011956997717271848, 'samples': 19556736, 'steps': 101857, 'loss/train': 1.1731173992156982}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:47 - INFO - __main__ - Step 101869: {'lr': 0.00011952018073280873, 'samples': 19558848, 'steps': 101868, 'loss/train': 0.824339747428894}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:49 - INFO - __main__ - Step 101874: {'lr': 0.00011949754833891981, 'samples': 19559808, 'steps': 101873, 'loss/train': 0.8418935537338257}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:52 - INFO - __main__ - Step 101879: {'lr': 0.00011947491741509059, 'samples': 19560768, 'steps': 101878, 'loss/train': 1.6024792194366455}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:54 - INFO - __main__ - Step 101883: {'lr': 0.00011945681373464166, 'samples': 19561536, 'steps': 101882, 'loss/train': 1.352506399154663}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:54 - INFO - __main__ - Step 101883: {'lr': 0.00011945681373464166, 'samples': 19561536, 'steps': 101882, 'loss/train': 1.352506399154663}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:57 - INFO - __main__ - Step 101890: {'lr': 0.00011942513455853305, 'samples': 19562880, 'steps': 101889, 'loss/train': 0.8998444080352783}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:31:59 - INFO - __main__ - Step 101895: {'lr': 0.00011940250834060821, 'samples': 19563840, 'steps': 101894, 'loss/train': 1.2096049785614014}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:02 - INFO - __main__ - Step 101900: {'lr': 0.00011937988359381363, 'samples': 19564800, 'steps': 101899, 'loss/train': 1.2120311260223389}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:04 - INFO - __main__ - Step 101904: {'lr': 0.00011936178485576321, 'samples': 19565568, 'steps': 101903, 'loss/train': 1.2878649234771729}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:04 - INFO - __main__ - Step 101904: {'lr': 0.00011936178485576321, 'samples': 19565568, 'steps': 101903, 'loss/train': 1.2878649234771729}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:07 - INFO - __main__ - Step 101911: {'lr': 0.00011933011433050051, 'samples': 19566912, 'steps': 101910, 'loss/train': 1.1019856929779053}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:10 - INFO - __main__ - Step 101915: {'lr': 0.00011931201818276072, 'samples': 19567680, 'steps': 101914, 'loss/train': 1.3311035633087158}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:12 - INFO - __main__ - Step 101920: {'lr': 0.00011928939932303612, 'samples': 19568640, 'steps': 101919, 'loss/train': 0.4492985010147095}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:14 - INFO - __main__ - Step 101924: {'lr': 0.00011927130529537538, 'samples': 19569408, 'steps': 101923, 'loss/train': 1.6052261590957642}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:15 - INFO - __main__ - Step 101928: {'lr': 0.00011925321221018396, 'samples': 19570176, 'steps': 101927, 'loss/train': 1.2485389709472656}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:18 - INFO - __main__ - Step 101932: {'lr': 0.00011923512006759238, 'samples': 19570944, 'steps': 101931, 'loss/train': 1.2121652364730835}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:20 - INFO - __main__ - Step 101937: {'lr': 0.0001192125062150824, 'samples': 19571904, 'steps': 101936, 'loss/train': 1.2633756399154663}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:22 - INFO - __main__ - Step 101941: {'lr': 0.00011919441619381708, 'samples': 19572672, 'steps': 101940, 'loss/train': 1.7410529851913452}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:22 - INFO - __main__ - Step 101941: {'lr': 0.00011919441619381708, 'samples': 19572672, 'steps': 101940, 'loss/train': 1.7410529851913452}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:25 - INFO - __main__ - Step 101948: {'lr': 0.00011916276092583191, 'samples': 19574016, 'steps': 101947, 'loss/train': 1.1555274724960327}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:28 - INFO - __main__ - Step 101953: {'lr': 0.00011914015178868468, 'samples': 19574976, 'steps': 101952, 'loss/train': 1.315491795539856}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:30 - INFO - __main__ - Step 101958: {'lr': 0.0001191175441256232, 'samples': 19575936, 'steps': 101957, 'loss/train': 1.615080714225769}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:30 - INFO - __main__ - Step 101958: {'lr': 0.0001191175441256232, 'samples': 19575936, 'steps': 101957, 'loss/train': 1.615080714225769}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:30 - INFO - __main__ - Step 101958: {'lr': 0.0001191175441256232, 'samples': 19575936, 'steps': 101957, 'loss/train': 1.615080714225769}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:36 - INFO - __main__ - Step 101968: {'lr': 0.00011907233322277586, 'samples': 19577856, 'steps': 101967, 'loss/train': 1.3429021835327148}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:38 - INFO - __main__ - Step 101973: {'lr': 0.00011904972998349945, 'samples': 19578816, 'steps': 101972, 'loss/train': 0.6394945979118347}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:40 - INFO - __main__ - Step 101977: {'lr': 0.00011903164845414111, 'samples': 19579584, 'steps': 101976, 'loss/train': 1.0252811908721924}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:42 - INFO - __main__ - Step 101981: {'lr': 0.00011901356786897985, 'samples': 19580352, 'steps': 101980, 'loss/train': 1.7011704444885254}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:44 - INFO - __main__ - Step 101985: {'lr': 0.00011899548822814613, 'samples': 19581120, 'steps': 101984, 'loss/train': 1.1034934520721436}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:46 - INFO - __main__ - Step 101990: {'lr': 0.0001189728900052629, 'samples': 19582080, 'steps': 101989, 'loss/train': 1.4662169218063354}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:48 - INFO - __main__ - Step 101994: {'lr': 0.00011895481248964238, 'samples': 19582848, 'steps': 101993, 'loss/train': 1.2556759119033813}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:50 - INFO - __main__ - Step 101998: {'lr': 0.00011893673591877297, 'samples': 19583616, 'steps': 101997, 'loss/train': 1.643775224685669}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:52 - INFO - __main__ - Step 102002: {'lr': 0.00011891866029278483, 'samples': 19584384, 'steps': 102001, 'loss/train': 1.031388759613037}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:54 - INFO - __main__ - Step 102006: {'lr': 0.00011890058561180836, 'samples': 19585152, 'steps': 102005, 'loss/train': 1.0098702907562256}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:56 - INFO - __main__ - Step 102011: {'lr': 0.00011887799358970902, 'samples': 19586112, 'steps': 102010, 'loss/train': 2.136354446411133}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:32:58 - INFO - __main__ - Step 102015: {'lr': 0.0001188599210354852, 'samples': 19586880, 'steps': 102014, 'loss/train': 1.44599187374115}3}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:01 - INFO - __main__ - Step 102019: {'lr': 0.00011884184942669651, 'samples': 19587648, 'steps': 102018, 'loss/train': 1.9214707612991333}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:02 - INFO - __main__ - Step 102023: {'lr': 0.00011882377876347327, 'samples': 19588416, 'steps': 102022, 'loss/train': 1.5001435279846191}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:04 - INFO - __main__ - Step 102027: {'lr': 0.00011880570904594582, 'samples': 19589184, 'steps': 102026, 'loss/train': 1.5151596069335938}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:07 - INFO - __main__ - Step 102032: {'lr': 0.00011878312322911938, 'samples': 19590144, 'steps': 102031, 'loss/train': 1.444366216659546}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:07 - INFO - __main__ - Step 102032: {'lr': 0.00011878312322911938, 'samples': 19590144, 'steps': 102031, 'loss/train': 1.444366216659546}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:10 - INFO - __main__ - Step 102038: {'lr': 0.00011875602220005204, 'samples': 19591296, 'steps': 102037, 'loss/train': 1.7310230731964111}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:12 - INFO - __main__ - Step 102043: {'lr': 0.00011873343963539795, 'samples': 19592256, 'steps': 102042, 'loss/train': 1.1831058263778687}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:15 - INFO - __main__ - Step 102048: {'lr': 0.00011871085854941099, 'samples': 19593216, 'steps': 102047, 'loss/train': 1.7573003768920898}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:15 - INFO - __main__ - Step 102048: {'lr': 0.00011871085854941099, 'samples': 19593216, 'steps': 102047, 'loss/train': 1.7573003768920898}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:18 - INFO - __main__ - Step 102055: {'lr': 0.00011867924751367448, 'samples': 19594560, 'steps': 102054, 'loss/train': 1.222645878791809}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:20 - INFO - __main__ - Step 102059: {'lr': 0.00011866118536640169, 'samples': 19595328, 'steps': 102058, 'loss/train': 2.089855194091797}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:23 - INFO - __main__ - Step 102064: {'lr': 0.00011863860901385901, 'samples': 19596288, 'steps': 102063, 'loss/train': 0.5821849703788757}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:23 - INFO - __main__ - Step 102064: {'lr': 0.00011863860901385901, 'samples': 19596288, 'steps': 102063, 'loss/train': 0.5821849703788757}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:27 - INFO - __main__ - Step 102071: {'lr': 0.00011860700460631155, 'samples': 19597632, 'steps': 102070, 'loss/train': 1.2867941856384277}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:28 - INFO - __main__ - Step 102075: {'lr': 0.00011858894624729155, 'samples': 19598400, 'steps': 102074, 'loss/train': 1.3578321933746338}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:30 - INFO - __main__ - Step 102079: {'lr': 0.00011857088883566033, 'samples': 19599168, 'steps': 102078, 'loss/train': 1.7939642667770386}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:30 - INFO - __main__ - Step 102079: {'lr': 0.00011857088883566033, 'samples': 19599168, 'steps': 102078, 'loss/train': 1.7939642667770386}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:34 - INFO - __main__ - Step 102087: {'lr': 0.00011853477685508445, 'samples': 19600704, 'steps': 102086, 'loss/train': 1.415819764137268}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:36 - INFO - __main__ - Step 102091: {'lr': 0.00011851672228640037, 'samples': 19601472, 'steps': 102090, 'loss/train': 1.4842113256454468}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:38 - INFO - __main__ - Step 102095: {'lr': 0.00011849866866562556, 'samples': 19602240, 'steps': 102094, 'loss/train': 1.4590457677841187}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:41 - INFO - __main__ - Step 102100: {'lr': 0.00011847610297285288, 'samples': 19603200, 'steps': 102099, 'loss/train': 1.5066097974777222}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:43 - INFO - __main__ - Step 102104: {'lr': 0.00011845805148535005, 'samples': 19603968, 'steps': 102103, 'loss/train': 1.1851638555526733}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:43 - INFO - __main__ - Step 102104: {'lr': 0.00011845805148535005, 'samples': 19603968, 'steps': 102103, 'loss/train': 1.1851638555526733}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:46 - INFO - __main__ - Step 102111: {'lr': 0.00011842646366422317, 'samples': 19605312, 'steps': 102110, 'loss/train': 1.08878493309021}3}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:46 - INFO - __main__ - Step 102111: {'lr': 0.00011842646366422317, 'samples': 19605312, 'steps': 102110, 'loss/train': 1.08878493309021}3}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:46 - INFO - __main__ - Step 102111: {'lr': 0.00011842646366422317, 'samples': 19605312, 'steps': 102110, 'loss/train': 1.08878493309021}3}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:52 - INFO - __main__ - Step 102123: {'lr': 0.00011837231987259672, 'samples': 19607616, 'steps': 102122, 'loss/train': 1.4670480489730835}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:54 - INFO - __main__ - Step 102127: {'lr': 0.00011835427383978192, 'samples': 19608384, 'steps': 102126, 'loss/train': 1.7840124368667603}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:56 - INFO - __main__ - Step 102132: {'lr': 0.00011833171763342324, 'samples': 19609344, 'steps': 102131, 'loss/train': 1.0677529573440552}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:33:59 - INFO - __main__ - Step 102136: {'lr': 0.00011831367373622256, 'samples': 19610112, 'steps': 102135, 'loss/train': 1.716078519821167}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:01 - INFO - __main__ - Step 102140: {'lr': 0.0001182956307883952, 'samples': 19610880, 'steps': 102139, 'loss/train': 1.526396632194519}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:02 - INFO - __main__ - Step 102144: {'lr': 0.00011827758879007105, 'samples': 19611648, 'steps': 102143, 'loss/train': 1.859777569770813}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:04 - INFO - __main__ - Step 102148: {'lr': 0.00011825954774138025, 'samples': 19612416, 'steps': 102147, 'loss/train': 1.376586675643921}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:07 - INFO - __main__ - Step 102153: {'lr': 0.00011823699776613698, 'samples': 19613376, 'steps': 102152, 'loss/train': 1.2012673616409302}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:07 - INFO - __main__ - Step 102153: {'lr': 0.00011823699776613698, 'samples': 19613376, 'steps': 102152, 'loss/train': 1.2012673616409302}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:10 - INFO - __main__ - Step 102160: {'lr': 0.00011820543029440887, 'samples': 19614720, 'steps': 102159, 'loss/train': 1.066344141960144}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:12 - INFO - __main__ - Step 102164: {'lr': 0.00011818739304555227, 'samples': 19615488, 'steps': 102163, 'loss/train': 1.0236279964447021}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:14 - INFO - __main__ - Step 102169: {'lr': 0.00011816484782083295, 'samples': 19616448, 'steps': 102168, 'loss/train': 1.1615993976593018}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:17 - INFO - __main__ - Step 102173: {'lr': 0.00011814681271029734, 'samples': 19617216, 'steps': 102172, 'loss/train': 1.3661881685256958}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:19 - INFO - __main__ - Step 102177: {'lr': 0.00011812877855033782, 'samples': 19617984, 'steps': 102176, 'loss/train': 1.135132908821106}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:21 - INFO - __main__ - Step 102181: {'lr': 0.00011811074534108451, 'samples': 19618752, 'steps': 102180, 'loss/train': 1.262332558631897}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:22 - INFO - __main__ - Step 102185: {'lr': 0.0001180927130826675, 'samples': 19619520, 'steps': 102184, 'loss/train': 1.1161072254180908}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:24 - INFO - __main__ - Step 102189: {'lr': 0.0001180746817752166, 'samples': 19620288, 'steps': 102188, 'loss/train': 0.9898638129234314}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:27 - INFO - __main__ - Step 102194: {'lr': 0.00011805214397839725, 'samples': 19621248, 'steps': 102193, 'loss/train': 0.9547217488288879}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:29 - INFO - __main__ - Step 102198: {'lr': 0.00011803411481109561, 'samples': 19622016, 'steps': 102197, 'loss/train': 1.326424241065979}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:29 - INFO - __main__ - Step 102198: {'lr': 0.00011803411481109561, 'samples': 19622016, 'steps': 102197, 'loss/train': 1.326424241065979}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:32 - INFO - __main__ - Step 102205: {'lr': 0.00011800256605767498, 'samples': 19623360, 'steps': 102204, 'loss/train': 1.1609227657318115}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:35 - INFO - __main__ - Step 102210: {'lr': 0.00011798003301804261, 'samples': 19624320, 'steps': 102209, 'loss/train': 0.8074084520339966}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:37 - INFO - __main__ - Step 102215: {'lr': 0.00011795750146556433, 'samples': 19625280, 'steps': 102214, 'loss/train': 1.3076646327972412}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:37 - INFO - __main__ - Step 102215: {'lr': 0.00011795750146556433, 'samples': 19625280, 'steps': 102214, 'loss/train': 1.3076646327972412}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:41 - INFO - __main__ - Step 102222: {'lr': 0.0001179259597909966, 'samples': 19626624, 'steps': 102221, 'loss/train': 1.4980429410934448}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:42 - INFO - __main__ - Step 102226: {'lr': 0.00011790793728614485, 'samples': 19627392, 'steps': 102225, 'loss/train': 1.6591202020645142}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:44 - INFO - __main__ - Step 102230: {'lr': 0.00011788991573359134, 'samples': 19628160, 'steps': 102229, 'loss/train': 1.6047478914260864}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:44 - INFO - __main__ - Step 102230: {'lr': 0.00011788991573359134, 'samples': 19628160, 'steps': 102229, 'loss/train': 1.6047478914260864}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:48 - INFO - __main__ - Step 102238: {'lr': 0.00011785387548589896, 'samples': 19629696, 'steps': 102237, 'loss/train': 1.2346327304840088}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:50 - INFO - __main__ - Step 102242: {'lr': 0.00011783585679102002, 'samples': 19630464, 'steps': 102241, 'loss/train': 0.9302211999893188}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:52 - INFO - __main__ - Step 102246: {'lr': 0.00011781783904895896, 'samples': 19631232, 'steps': 102245, 'loss/train': 1.459730863571167}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:54 - INFO - __main__ - Step 102251: {'lr': 0.00011779531821148081, 'samples': 19632192, 'steps': 102250, 'loss/train': 1.2030473947525024}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:54 - INFO - __main__ - Step 102251: {'lr': 0.00011779531821148081, 'samples': 19632192, 'steps': 102250, 'loss/train': 1.2030473947525024}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:54 - INFO - __main__ - Step 102251: {'lr': 0.00011779531821148081, 'samples': 19632192, 'steps': 102250, 'loss/train': 1.2030473947525024}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:34:54 - INFO - __main__ - Step 102251: {'lr': 0.00011779531821148081, 'samples': 19632192, 'steps': 102250, 'loss/train': 1.2030473947525024}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:02 - INFO - __main__ - Step 102264: {'lr': 0.00011773677100428942, 'samples': 19634688, 'steps': 102263, 'loss/train': 1.7549690008163452}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:05 - INFO - __main__ - Step 102270: {'lr': 0.00011770975261304401, 'samples': 19635840, 'steps': 102269, 'loss/train': 1.3360038995742798}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:05 - INFO - __main__ - Step 102270: {'lr': 0.00011770975261304401, 'samples': 19635840, 'steps': 102269, 'loss/train': 1.3360038995742798}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:05 - INFO - __main__ - Step 102270: {'lr': 0.00011770975261304401, 'samples': 19635840, 'steps': 102269, 'loss/train': 1.3360038995742798}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:10 - INFO - __main__ - Step 102280: {'lr': 0.00011766472672982015, 'samples': 19637760, 'steps': 102279, 'loss/train': 1.7919517755508423}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:13 - INFO - __main__ - Step 102285: {'lr': 0.0001176422160241401, 'samples': 19638720, 'steps': 102284, 'loss/train': 0.4333227276802063}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:15 - INFO - __main__ - Step 102289: {'lr': 0.00011762420853307462, 'samples': 19639488, 'steps': 102288, 'loss/train': 1.5865209102630615}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:15 - INFO - __main__ - Step 102289: {'lr': 0.00011762420853307462, 'samples': 19639488, 'steps': 102288, 'loss/train': 1.5865209102630615}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:18 - INFO - __main__ - Step 102296: {'lr': 0.00011759269772017806, 'samples': 19640832, 'steps': 102295, 'loss/train': 1.3100054264068604}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:21 - INFO - __main__ - Step 102302: {'lr': 0.00011756569077872136, 'samples': 19641984, 'steps': 102301, 'loss/train': 1.3498846292495728}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:21 - INFO - __main__ - Step 102302: {'lr': 0.00011756569077872136, 'samples': 19641984, 'steps': 102301, 'loss/train': 1.3498846292495728}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:25 - INFO - __main__ - Step 102309: {'lr': 0.00011753418539550101, 'samples': 19643328, 'steps': 102308, 'loss/train': 2.0992586612701416}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:26 - INFO - __main__ - Step 102313: {'lr': 0.00011751618363244557, 'samples': 19644096, 'steps': 102312, 'loss/train': 1.5262730121612549}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:28 - INFO - __main__ - Step 102317: {'lr': 0.00011749818282451275, 'samples': 19644864, 'steps': 102316, 'loss/train': 2.034003973007202}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:31 - INFO - __main__ - Step 102322: {'lr': 0.00011747568315793567, 'samples': 19645824, 'steps': 102321, 'loss/train': 0.1296757310628891}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:33 - INFO - __main__ - Step 102326: {'lr': 0.0001174576844995032, 'samples': 19646592, 'steps': 102325, 'loss/train': 1.3872599601745605}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:35 - INFO - __main__ - Step 102330: {'lr': 0.00011743968679661507, 'samples': 19647360, 'steps': 102329, 'loss/train': 1.5335696935653687}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:37 - INFO - __main__ - Step 102334: {'lr': 0.00011742169004940115, 'samples': 19648128, 'steps': 102333, 'loss/train': 0.3349030911922455}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:38 - INFO - __main__ - Step 102338: {'lr': 0.000117403694257991, 'samples': 19648896, 'steps': 102337, 'loss/train': 1.2319668531417847}5}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:41 - INFO - __main__ - Step 102342: {'lr': 0.00011738569942251443, 'samples': 19649664, 'steps': 102341, 'loss/train': 1.5955750942230225}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:41 - INFO - __main__ - Step 102342: {'lr': 0.00011738569942251443, 'samples': 19649664, 'steps': 102341, 'loss/train': 1.5955750942230225}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:45 - INFO - __main__ - Step 102350: {'lr': 0.00011734971261988104, 'samples': 19651200, 'steps': 102349, 'loss/train': 1.1522936820983887}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:46 - INFO - __main__ - Step 102354: {'lr': 0.00011733172065298358, 'samples': 19651968, 'steps': 102353, 'loss/train': 1.28263521194458}7}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:48 - INFO - __main__ - Step 102358: {'lr': 0.00011731372964253861, 'samples': 19652736, 'steps': 102357, 'loss/train': 1.3303706645965576}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:51 - INFO - __main__ - Step 102363: {'lr': 0.00011729124222469134, 'samples': 19653696, 'steps': 102362, 'loss/train': 1.1670762300491333}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:51 - INFO - __main__ - Step 102363: {'lr': 0.00011729124222469134, 'samples': 19653696, 'steps': 102362, 'loss/train': 1.1670762300491333}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:54 - INFO - __main__ - Step 102370: {'lr': 0.00011725976235121557, 'samples': 19655040, 'steps': 102369, 'loss/train': 1.6743392944335938}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:56 - INFO - __main__ - Step 102374: {'lr': 0.00011724177516787754, 'samples': 19655808, 'steps': 102373, 'loss/train': 1.6722662448883057}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:59 - INFO - __main__ - Step 102379: {'lr': 0.00011721929253464323, 'samples': 19656768, 'steps': 102378, 'loss/train': 1.4049830436706543}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:35:59 - INFO - __main__ - Step 102379: {'lr': 0.00011721929253464323, 'samples': 19656768, 'steps': 102378, 'loss/train': 1.4049830436706543}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:03 - INFO - __main__ - Step 102387: {'lr': 0.00011718332343267857, 'samples': 19658304, 'steps': 102386, 'loss/train': 0.2352754920721054}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:04 - INFO - __main__ - Step 102391: {'lr': 0.00011716534031791485, 'samples': 19659072, 'steps': 102390, 'loss/train': 1.609163761138916}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:06 - INFO - __main__ - Step 102395: {'lr': 0.00011714735816080308, 'samples': 19659840, 'steps': 102394, 'loss/train': 0.998603880405426}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:09 - INFO - __main__ - Step 102400: {'lr': 0.00011712488181130903, 'samples': 19660800, 'steps': 102399, 'loss/train': 1.2605152130126953}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:11 - INFO - __main__ - Step 102404: {'lr': 0.00011710690180938818, 'samples': 19661568, 'steps': 102403, 'loss/train': 1.4898165464401245}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:13 - INFO - __main__ - Step 102408: {'lr': 0.00011708892276554067, 'samples': 19662336, 'steps': 102407, 'loss/train': 0.8538132905960083}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:15 - INFO - __main__ - Step 102412: {'lr': 0.00011707094467989598, 'samples': 19663104, 'steps': 102411, 'loss/train': 1.1063693761825562}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:17 - INFO - __main__ - Step 102416: {'lr': 0.00011705296755258376, 'samples': 19663872, 'steps': 102415, 'loss/train': 1.4933804273605347}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:19 - INFO - __main__ - Step 102421: {'lr': 0.00011703049749129613, 'samples': 19664832, 'steps': 102420, 'loss/train': 1.5921494960784912}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:21 - INFO - __main__ - Step 102425: {'lr': 0.00011701252252070587, 'samples': 19665600, 'steps': 102424, 'loss/train': 1.4973171949386597}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:23 - INFO - __main__ - Step 102429: {'lr': 0.00011699454850886935, 'samples': 19666368, 'steps': 102428, 'loss/train': 1.6129342317581177}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:23 - INFO - __main__ - Step 102429: {'lr': 0.00011699454850886935, 'samples': 19666368, 'steps': 102428, 'loss/train': 1.6129342317581177}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:27 - INFO - __main__ - Step 102436: {'lr': 0.00011696309629554627, 'samples': 19667712, 'steps': 102435, 'loss/train': 1.1927984952926636}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:29 - INFO - __main__ - Step 102442: {'lr': 0.00011693613959335942, 'samples': 19668864, 'steps': 102441, 'loss/train': 1.3170689344406128}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:31 - INFO - __main__ - Step 102446: {'lr': 0.00011691816965767157, 'samples': 19669632, 'steps': 102445, 'loss/train': 1.0388332605361938}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:31 - INFO - __main__ - Step 102446: {'lr': 0.00011691816965767157, 'samples': 19669632, 'steps': 102445, 'loss/train': 1.0388332605361938}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:35 - INFO - __main__ - Step 102453: {'lr': 0.00011688672457893363, 'samples': 19670976, 'steps': 102452, 'loss/train': 1.7463619709014893}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:37 - INFO - __main__ - Step 102457: {'lr': 0.00011686875728200083, 'samples': 19671744, 'steps': 102456, 'loss/train': 1.1553137302398682}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:37 - INFO - __main__ - Step 102457: {'lr': 0.00011686875728200083, 'samples': 19671744, 'steps': 102456, 'loss/train': 1.1553137302398682}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:37 - INFO - __main__ - Step 102457: {'lr': 0.00011686875728200083, 'samples': 19671744, 'steps': 102456, 'loss/train': 1.1553137302398682}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:42 - INFO - __main__ - Step 102468: {'lr': 0.00011681935216474296, 'samples': 19673856, 'steps': 102467, 'loss/train': 1.1777565479278564}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:45 - INFO - __main__ - Step 102473: {'lr': 0.00011679689769346596, 'samples': 19674816, 'steps': 102472, 'loss/train': 1.4052072763442993}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:47 - INFO - __main__ - Step 102478: {'lr': 0.00011677444472267054, 'samples': 19675776, 'steps': 102477, 'loss/train': 1.377241611480713}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:49 - INFO - __main__ - Step 102482: {'lr': 0.00011675648342655095, 'samples': 19676544, 'steps': 102481, 'loss/train': 1.3685567378997803}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:49 - INFO - __main__ - Step 102482: {'lr': 0.00011675648342655095, 'samples': 19676544, 'steps': 102481, 'loss/train': 1.3685567378997803}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:52 - INFO - __main__ - Step 102489: {'lr': 0.00011672505346986214, 'samples': 19677888, 'steps': 102488, 'loss/train': 1.3894259929656982}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:55 - INFO - __main__ - Step 102494: {'lr': 0.00011670260530230736, 'samples': 19678848, 'steps': 102493, 'loss/train': 1.0222828388214111}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:57 - INFO - __main__ - Step 102498: {'lr': 0.0001166846478493628, 'samples': 19679616, 'steps': 102497, 'loss/train': 1.189178466796875}1}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:36:59 - INFO - __main__ - Step 102502: {'lr': 0.00011666669135753571, 'samples': 19680384, 'steps': 102501, 'loss/train': 1.7292520999908447}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:00 - INFO - __main__ - Step 102506: {'lr': 0.0001166487358269555, 'samples': 19681152, 'steps': 102505, 'loss/train': 1.5569164752960205}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:02 - INFO - __main__ - Step 102510: {'lr': 0.00011663078125775173, 'samples': 19681920, 'steps': 102509, 'loss/train': 0.7512518167495728}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:05 - INFO - __main__ - Step 102515: {'lr': 0.00011660833939837962, 'samples': 19682880, 'steps': 102514, 'loss/train': 1.4847896099090576}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:07 - INFO - __main__ - Step 102519: {'lr': 0.0001165903869927458, 'samples': 19683648, 'steps': 102518, 'loss/train': 1.3400708436965942}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:09 - INFO - __main__ - Step 102523: {'lr': 0.0001165724355489091, 'samples': 19684416, 'steps': 102522, 'loss/train': 1.3903629779815674}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:11 - INFO - __main__ - Step 102527: {'lr': 0.0001165544850669987, 'samples': 19685184, 'steps': 102526, 'loss/train': 1.026153802871704}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:13 - INFO - __main__ - Step 102531: {'lr': 0.00011653653554714416, 'samples': 19685952, 'steps': 102530, 'loss/train': 1.155552864074707}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:15 - INFO - __main__ - Step 102536: {'lr': 0.00011651410000041423, 'samples': 19686912, 'steps': 102535, 'loss/train': 1.0252431631088257}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:17 - INFO - __main__ - Step 102540: {'lr': 0.00011649615264565846, 'samples': 19687680, 'steps': 102539, 'loss/train': 0.745124340057373}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:17 - INFO - __main__ - Step 102540: {'lr': 0.00011649615264565846, 'samples': 19687680, 'steps': 102539, 'loss/train': 0.745124340057373}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:21 - INFO - __main__ - Step 102547: {'lr': 0.00011646474709087246, 'samples': 19689024, 'steps': 102546, 'loss/train': 0.7949965000152588}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:23 - INFO - __main__ - Step 102551: {'lr': 0.00011644680238323813, 'samples': 19689792, 'steps': 102550, 'loss/train': 1.2386184930801392}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:23 - INFO - __main__ - Step 102551: {'lr': 0.00011644680238323813, 'samples': 19689792, 'steps': 102550, 'loss/train': 1.2386184930801392}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:23 - INFO - __main__ - Step 102551: {'lr': 0.00011644680238323813, 'samples': 19689792, 'steps': 102550, 'loss/train': 1.2386184930801392}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:29 - INFO - __main__ - Step 102563: {'lr': 0.00011639297403784533, 'samples': 19692096, 'steps': 102562, 'loss/train': 1.1846859455108643}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:31 - INFO - __main__ - Step 102568: {'lr': 0.00011637054811895159, 'samples': 19693056, 'steps': 102567, 'loss/train': 1.358803391456604}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:31 - INFO - __main__ - Step 102568: {'lr': 0.00011637054811895159, 'samples': 19693056, 'steps': 102567, 'loss/train': 1.358803391456604}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:34 - INFO - __main__ - Step 102575: {'lr': 0.00011633915436143452, 'samples': 19694400, 'steps': 102574, 'loss/train': 0.8073808550834656}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:36 - INFO - __main__ - Step 102579: {'lr': 0.0001163212163963416, 'samples': 19695168, 'steps': 102578, 'loss/train': 1.7591508626937866}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:39 - INFO - __main__ - Step 102584: {'lr': 0.0001162987952952465, 'samples': 19696128, 'steps': 102583, 'loss/train': 0.189786896109581}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:39 - INFO - __main__ - Step 102584: {'lr': 0.0001162987952952465, 'samples': 19696128, 'steps': 102583, 'loss/train': 0.189786896109581}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:39 - INFO - __main__ - Step 102584: {'lr': 0.0001162987952952465, 'samples': 19696128, 'steps': 102583, 'loss/train': 0.189786896109581}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:45 - INFO - __main__ - Step 102595: {'lr': 0.00011624947417463858, 'samples': 19698240, 'steps': 102594, 'loss/train': 1.6905481815338135}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:47 - INFO - __main__ - Step 102599: {'lr': 0.00011623154102952648, 'samples': 19699008, 'steps': 102598, 'loss/train': 1.675042986869812}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:49 - INFO - __main__ - Step 102604: {'lr': 0.00011620912595431668, 'samples': 19699968, 'steps': 102603, 'loss/train': 1.5044909715652466}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:49 - INFO - __main__ - Step 102604: {'lr': 0.00011620912595431668, 'samples': 19699968, 'steps': 102603, 'loss/train': 1.5044909715652466}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:53 - INFO - __main__ - Step 102611: {'lr': 0.00011617774738101172, 'samples': 19701312, 'steps': 102610, 'loss/train': 1.4031468629837036}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:55 - INFO - __main__ - Step 102615: {'lr': 0.00011615981809421158, 'samples': 19702080, 'steps': 102614, 'loss/train': 1.1185861825942993}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:57 - INFO - __main__ - Step 102620: {'lr': 0.00011613740784261865, 'samples': 19703040, 'steps': 102619, 'loss/train': 1.2563927173614502}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:37:57 - INFO - __main__ - Step 102620: {'lr': 0.00011613740784261865, 'samples': 19703040, 'steps': 102619, 'loss/train': 1.2563927173614502}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:02 - INFO - __main__ - Step 102628: {'lr': 0.00011610155457662871, 'samples': 19704576, 'steps': 102627, 'loss/train': 1.9179202318191528}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:03 - INFO - __main__ - Step 102632: {'lr': 0.00011608362939155098, 'samples': 19705344, 'steps': 102631, 'loss/train': 1.111308217048645}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:05 - INFO - __main__ - Step 102636: {'lr': 0.00011606570517192357, 'samples': 19706112, 'steps': 102635, 'loss/train': 1.5734738111495972}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:05 - INFO - __main__ - Step 102636: {'lr': 0.00011606570517192357, 'samples': 19706112, 'steps': 102635, 'loss/train': 1.5734738111495972}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:09 - INFO - __main__ - Step 102644: {'lr': 0.00011602985962953692, 'samples': 19707648, 'steps': 102643, 'loss/train': 1.0244876146316528}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:11 - INFO - __main__ - Step 102648: {'lr': 0.00011601193830703602, 'samples': 19708416, 'steps': 102647, 'loss/train': 0.3117143213748932}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:13 - INFO - __main__ - Step 102652: {'lr': 0.00011599401795050235, 'samples': 19709184, 'steps': 102651, 'loss/train': 1.3990370035171509}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:15 - INFO - __main__ - Step 102657: {'lr': 0.0001159716188634236, 'samples': 19710144, 'steps': 102656, 'loss/train': 1.1771830320358276}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:15 - INFO - __main__ - Step 102657: {'lr': 0.0001159716188634236, 'samples': 19710144, 'steps': 102656, 'loss/train': 1.1771830320358276}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:20 - INFO - __main__ - Step 102665: {'lr': 0.00011593578346454073, 'samples': 19711680, 'steps': 102664, 'loss/train': 1.0602774620056152}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:20 - INFO - __main__ - Step 102665: {'lr': 0.00011593578346454073, 'samples': 19711680, 'steps': 102664, 'loss/train': 1.0602774620056152}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:23 - INFO - __main__ - Step 102672: {'lr': 0.00011590443066186451, 'samples': 19713024, 'steps': 102671, 'loss/train': 1.4014626741409302}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:25 - INFO - __main__ - Step 102677: {'lr': 0.00011588203761541154, 'samples': 19713984, 'steps': 102676, 'loss/train': 1.4520550966262817}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:28 - INFO - __main__ - Step 102682: {'lr': 0.00011585964607974559, 'samples': 19714944, 'steps': 102681, 'loss/train': 1.3257185220718384}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:28 - INFO - __main__ - Step 102682: {'lr': 0.00011585964607974559, 'samples': 19714944, 'steps': 102681, 'loss/train': 1.3257185220718384}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:28 - INFO - __main__ - Step 102682: {'lr': 0.00011585964607974559, 'samples': 19714944, 'steps': 102681, 'loss/train': 1.3257185220718384}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:33 - INFO - __main__ - Step 102692: {'lr': 0.00011581486754178403, 'samples': 19716864, 'steps': 102691, 'loss/train': 0.5393563508987427}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:35 - INFO - __main__ - Step 102697: {'lr': 0.00011579248053999272, 'samples': 19717824, 'steps': 102696, 'loss/train': 1.689946174621582}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:38 - INFO - __main__ - Step 102702: {'lr': 0.00011577009504999744, 'samples': 19718784, 'steps': 102701, 'loss/train': 1.3956875801086426}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:38 - INFO - __main__ - Step 102702: {'lr': 0.00011577009504999744, 'samples': 19718784, 'steps': 102701, 'loss/train': 1.3956875801086426}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:41 - INFO - __main__ - Step 102709: {'lr': 0.00011573875790430119, 'samples': 19720128, 'steps': 102708, 'loss/train': 1.770261526107788}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:43 - INFO - __main__ - Step 102713: {'lr': 0.00011572085229477203, 'samples': 19720896, 'steps': 102712, 'loss/train': 1.0875312089920044}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:46 - INFO - __main__ - Step 102718: {'lr': 0.0001156984716442181, 'samples': 19721856, 'steps': 102717, 'loss/train': 1.5195404291152954}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:46 - INFO - __main__ - Step 102718: {'lr': 0.0001156984716442181, 'samples': 19721856, 'steps': 102717, 'loss/train': 1.5195404291152954}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:46 - INFO - __main__ - Step 102718: {'lr': 0.0001156984716442181, 'samples': 19721856, 'steps': 102717, 'loss/train': 1.5195404291152954}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:51 - INFO - __main__ - Step 102729: {'lr': 0.00011564923953860373, 'samples': 19723968, 'steps': 102728, 'loss/train': 1.3661513328552246}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:53 - INFO - __main__ - Step 102734: {'lr': 0.00011562686373007284, 'samples': 19724928, 'steps': 102733, 'loss/train': 1.303132176399231}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:56 - INFO - __main__ - Step 102739: {'lr': 0.00011560448943520357, 'samples': 19725888, 'steps': 102738, 'loss/train': 1.3602294921875}1}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:56 - INFO - __main__ - Step 102739: {'lr': 0.00011560448943520357, 'samples': 19725888, 'steps': 102738, 'loss/train': 1.3602294921875}1}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:38:59 - INFO - __main__ - Step 102746: {'lr': 0.00011557316796581774, 'samples': 19727232, 'steps': 102745, 'loss/train': 0.5364639163017273}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:01 - INFO - __main__ - Step 102750: {'lr': 0.00011555527131582173, 'samples': 19728000, 'steps': 102749, 'loss/train': 1.1629987955093384}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:04 - INFO - __main__ - Step 102755: {'lr': 0.00011553290186636293, 'samples': 19728960, 'steps': 102754, 'loss/train': 1.4217138290405273}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:04 - INFO - __main__ - Step 102755: {'lr': 0.00011553290186636293, 'samples': 19728960, 'steps': 102754, 'loss/train': 1.4217138290405273}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:07 - INFO - __main__ - Step 102762: {'lr': 0.00011550158718190659, 'samples': 19730304, 'steps': 102761, 'loss/train': 1.318320870399475}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:09 - INFO - __main__ - Step 102766: {'lr': 0.00011548369440972272, 'samples': 19731072, 'steps': 102765, 'loss/train': 1.2280908823013306}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:11 - INFO - __main__ - Step 102771: {'lr': 0.00011546132980825477, 'samples': 19732032, 'steps': 102770, 'loss/train': 1.2914445400238037}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:11 - INFO - __main__ - Step 102771: {'lr': 0.00011546132980825477, 'samples': 19732032, 'steps': 102770, 'loss/train': 1.2914445400238037}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:16 - INFO - __main__ - Step 102779: {'lr': 0.00011542554959830545, 'samples': 19733568, 'steps': 102778, 'loss/train': 1.4837173223495483}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:16 - INFO - __main__ - Step 102779: {'lr': 0.00011542554959830545, 'samples': 19733568, 'steps': 102778, 'loss/train': 1.4837173223495483}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:19 - INFO - __main__ - Step 102786: {'lr': 0.00011539424509801591, 'samples': 19734912, 'steps': 102785, 'loss/train': 1.3901572227478027}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:22 - INFO - __main__ - Step 102791: {'lr': 0.00011537188656016432, 'samples': 19735872, 'steps': 102790, 'loss/train': 1.5409233570098877}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:24 - INFO - __main__ - Step 102795: {'lr': 0.00011535400082177516, 'samples': 19736640, 'steps': 102794, 'loss/train': 1.0186656713485718}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:24 - INFO - __main__ - Step 102795: {'lr': 0.00011535400082177516, 'samples': 19736640, 'steps': 102794, 'loss/train': 1.0186656713485718}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:24 - INFO - __main__ - Step 102795: {'lr': 0.00011535400082177516, 'samples': 19736640, 'steps': 102794, 'loss/train': 1.0186656713485718}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:29 - INFO - __main__ - Step 102805: {'lr': 0.00011530929072294313, 'samples': 19738560, 'steps': 102804, 'loss/train': 1.7728123664855957}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:32 - INFO - __main__ - Step 102810: {'lr': 0.00011528693794925949, 'samples': 19739520, 'steps': 102809, 'loss/train': 2.052493095397949}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:32 - INFO - __main__ - Step 102810: {'lr': 0.00011528693794925949, 'samples': 19739520, 'steps': 102809, 'loss/train': 2.052493095397949}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:36 - INFO - __main__ - Step 102817: {'lr': 0.0001152556466155432, 'samples': 19740864, 'steps': 102816, 'loss/train': 1.4342164993286133}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:37 - INFO - __main__ - Step 102821: {'lr': 0.0001152377671890772, 'samples': 19741632, 'steps': 102820, 'loss/train': 1.4047572612762451}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:40 - INFO - __main__ - Step 102826: {'lr': 0.00011521541927224994, 'samples': 19742592, 'steps': 102825, 'loss/train': 1.2428052425384521}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:40 - INFO - __main__ - Step 102826: {'lr': 0.00011521541927224994, 'samples': 19742592, 'steps': 102825, 'loss/train': 1.2428052425384521}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:43 - INFO - __main__ - Step 102832: {'lr': 0.00011518860377623059, 'samples': 19743744, 'steps': 102831, 'loss/train': 0.16930843889713287}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:45 - INFO - __main__ - Step 102836: {'lr': 0.00011517072799373615, 'samples': 19744512, 'steps': 102835, 'loss/train': 1.190798044204712}7}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:48 - INFO - __main__ - Step 102841: {'lr': 0.00011514838463255294, 'samples': 19745472, 'steps': 102840, 'loss/train': 1.327752709388733}7}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:50 - INFO - __main__ - Step 102846: {'lr': 0.00011512604279042127, 'samples': 19746432, 'steps': 102845, 'loss/train': 1.4164270162582397}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:50 - INFO - __main__ - Step 102846: {'lr': 0.00011512604279042127, 'samples': 19746432, 'steps': 102845, 'loss/train': 1.4164270162582397}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:53 - INFO - __main__ - Step 102853: {'lr': 0.00011509476676392235, 'samples': 19747776, 'steps': 102852, 'loss/train': 1.4140222072601318}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:56 - INFO - __main__ - Step 102857: {'lr': 0.0001150768960860327, 'samples': 19748544, 'steps': 102856, 'loss/train': 1.5969425439834595}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:39:58 - INFO - __main__ - Step 102861: {'lr': 0.00011505902638085122, 'samples': 19749312, 'steps': 102860, 'loss/train': 1.5592161417007446}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:00 - INFO - __main__ - Step 102865: {'lr': 0.00011504115764850689, 'samples': 19750080, 'steps': 102864, 'loss/train': 1.5564109086990356}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:02 - INFO - __main__ - Step 102869: {'lr': 0.0001150232898891285, 'samples': 19750848, 'steps': 102868, 'loss/train': 1.5264973640441895}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:03 - INFO - __main__ - Step 102873: {'lr': 0.00011500542310284496, 'samples': 19751616, 'steps': 102872, 'loss/train': 2.247835159301758}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:05 - INFO - __main__ - Step 102877: {'lr': 0.0001149875572897849, 'samples': 19752384, 'steps': 102876, 'loss/train': 1.143891453742981}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:08 - INFO - __main__ - Step 102882: {'lr': 0.00011496522639225171, 'samples': 19753344, 'steps': 102881, 'loss/train': 1.611701250076294}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:10 - INFO - __main__ - Step 102886: {'lr': 0.0001149473627694157, 'samples': 19754112, 'steps': 102885, 'loss/train': 1.697304606437683}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:10 - INFO - __main__ - Step 102886: {'lr': 0.0001149473627694157, 'samples': 19754112, 'steps': 102885, 'loss/train': 1.697304606437683}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:13 - INFO - __main__ - Step 102893: {'lr': 0.0001149161037723564, 'samples': 19755456, 'steps': 102892, 'loss/train': 1.496872067451477}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:16 - INFO - __main__ - Step 102898: {'lr': 0.00011489377774327548, 'samples': 19756416, 'steps': 102897, 'loss/train': 0.8636860251426697}}███████████████████████���█| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:16 - INFO - __main__ - Step 102898: {'lr': 0.00011489377774327548, 'samples': 19756416, 'steps': 102897, 'loss/train': 0.8636860251426697}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:19 - INFO - __main__ - Step 102905: {'lr': 0.0001148625238594431, 'samples': 19757760, 'steps': 102904, 'loss/train': 1.1915607452392578}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:22 - INFO - __main__ - Step 102909: {'lr': 0.00011484466583680786, 'samples': 19758528, 'steps': 102908, 'loss/train': 1.0970064401626587}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:22 - INFO - __main__ - Step 102909: {'lr': 0.00011484466583680786, 'samples': 19758528, 'steps': 102908, 'loss/train': 1.0970064401626587}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:26 - INFO - __main__ - Step 102917: {'lr': 0.00011480895271481381, 'samples': 19760064, 'steps': 102916, 'loss/train': 1.3950409889221191}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:28 - INFO - __main__ - Step 102921: {'lr': 0.00011479109761571235, 'samples': 19760832, 'steps': 102920, 'loss/train': 1.6707243919372559}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:29 - INFO - __main__ - Step 102925: {'lr': 0.00011477324349137971, 'samples': 19761600, 'steps': 102924, 'loss/train': 1.665656566619873}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:32 - INFO - __main__ - Step 102929: {'lr': 0.00011475539034194443, 'samples': 19762368, 'steps': 102928, 'loss/train': 1.6283948421478271}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:34 - INFO - __main__ - Step 102934: {'lr': 0.00011473307527629601, 'samples': 19763328, 'steps': 102933, 'loss/train': 1.6489646434783936}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:34 - INFO - __main__ - Step 102934: {'lr': 0.00011473307527629601, 'samples': 19763328, 'steps': 102933, 'loss/train': 1.6489646434783936}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:37 - INFO - __main__ - Step 102940: {'lr': 0.00011470629920886314, 'samples': 19764480, 'steps': 102939, 'loss/train': 1.508772373199463}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:40 - INFO - __main__ - Step 102945: {'lr': 0.00011468398749575188, 'samples': 19765440, 'steps': 102944, 'loss/train': 1.914021611213684}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:42 - INFO - __main__ - Step 102949: {'lr': 0.00011466613922273428, 'samples': 19766208, 'steps': 102948, 'loss/train': 1.241376280784607}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:44 - INFO - __main__ - Step 102953: {'lr': 0.00011464829192538625, 'samples': 19766976, 'steps': 102952, 'loss/train': 0.9386645555496216}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:46 - INFO - __main__ - Step 102957: {'lr': 0.00011463044560383659, 'samples': 19767744, 'steps': 102956, 'loss/train': 1.3518657684326172}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:48 - INFO - __main__ - Step 102962: {'lr': 0.00011460813907431169, 'samples': 19768704, 'steps': 102961, 'loss/train': 1.4627740383148193}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:48 - INFO - __main__ - Step 102962: {'lr': 0.00011460813907431169, 'samples': 19768704, 'steps': 102961, 'loss/train': 1.4627740383148193}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:48 - INFO - __main__ - Step 102962: {'lr': 0.00011460813907431169, 'samples': 19768704, 'steps': 102961, 'loss/train': 1.4627740383148193}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:53 - INFO - __main__ - Step 102972: {'lr': 0.00011456353059092448, 'samples': 19770624, 'steps': 102971, 'loss/train': 1.539237380027771}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:56 - INFO - __main__ - Step 102977: {'lr': 0.00011454122863756458, 'samples': 19771584, 'steps': 102976, 'loss/train': 1.0516568422317505}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:40:58 - INFO - __main__ - Step 102982: {'lr': 0.00011451892821009557, 'samples': 19772544, 'steps': 102981, 'loss/train': 2.429189920425415}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:00 - INFO - __main__ - Step 102986: {'lr': 0.00011450108896693048, 'samples': 19773312, 'steps': 102985, 'loss/train': 1.383633017539978}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:00 - INFO - __main__ - Step 102986: {'lr': 0.00011450108896693048, 'samples': 19773312, 'steps': 102985, 'loss/train': 1.383633017539978}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:04 - INFO - __main__ - Step 102993: {'lr': 0.00011446987264203721, 'samples': 19774656, 'steps': 102992, 'loss/train': 1.328263759613037}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:06 - INFO - __main__ - Step 102998: {'lr': 0.00011444757709910666, 'samples': 19775616, 'steps': 102997, 'loss/train': 0.9147663712501526}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:08 - INFO - __main__ - Step 103002: {'lr': 0.00011442974176415113, 'samples': 19776384, 'steps': 103001, 'loss/train': 1.4296404123306274}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:10 - INFO - __main__ - Step 103006: {'lr': 0.00011441190740656956, 'samples': 19777152, 'steps': 103005, 'loss/train': 1.6542900800704956}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:12 - INFO - __main__ - Step 103010: {'lr': 0.00011439407402649036, 'samples': 19777920, 'steps': 103009, 'loss/train': 1.4327476024627686}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:14 - INFO - __main__ - Step 103014: {'lr': 0.00011437624162404212, 'samples': 19778688, 'steps': 103013, 'loss/train': 1.5675543546676636}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:16 - INFO - __main__ - Step 103019: {'lr': 0.00011435395249597139, 'samples': 19779648, 'steps': 103018, 'loss/train': 1.2747935056686401}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:18 - INFO - __main__ - Step 103023: {'lr': 0.00011433612229366295, 'samples': 19780416, 'steps': 103022, 'loss/train': 1.6677734851837158}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:18 - INFO - __main__ - Step 103023: {'lr': 0.00011433612229366295, 'samples': 19780416, 'steps': 103022, 'loss/train': 1.6677734851837158}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:22 - INFO - __main__ - Step 103030: {'lr': 0.00011430492179313043, 'samples': 19781760, 'steps': 103029, 'loss/train': 1.4295305013656616}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:24 - INFO - __main__ - Step 103035: {'lr': 0.00011428263755554465, 'samples': 19782720, 'steps': 103034, 'loss/train': 1.1778219938278198}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:24 - INFO - __main__ - Step 103035: {'lr': 0.00011428263755554465, 'samples': 19782720, 'steps': 103034, 'loss/train': 1.1778219938278198}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:27 - INFO - __main__ - Step 103042: {'lr': 0.00011425144219137096, 'samples': 19784064, 'steps': 103041, 'loss/train': 1.192582368850708}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:29 - INFO - __main__ - Step 103046: {'lr': 0.00011423361761459841, 'samples': 19784832, 'steps': 103045, 'loss/train': 1.2895442247390747}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:32 - INFO - __main__ - Step 103051: {'lr': 0.00011421133827006802, 'samples': 19785792, 'steps': 103050, 'loss/train': 0.3457473814487457}}████████████████��████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:34 - INFO - __main__ - Step 103055: {'lr': 0.00011419351589574862, 'samples': 19786560, 'steps': 103054, 'loss/train': 1.0931155681610107}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:36 - INFO - __main__ - Step 103059: {'lr': 0.00011417569450050619, 'samples': 19787328, 'steps': 103058, 'loss/train': 1.4268276691436768}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:38 - INFO - __main__ - Step 103063: {'lr': 0.00011415787408446904, 'samples': 19788096, 'steps': 103062, 'loss/train': 1.6380784511566162}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:40 - INFO - __main__ - Step 103067: {'lr': 0.00011414005464776578, 'samples': 19788864, 'steps': 103066, 'loss/train': 1.3110994100570679}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:42 - INFO - __main__ - Step 103072: {'lr': 0.0001141177817292706, 'samples': 19789824, 'steps': 103071, 'loss/train': 1.1667377948760986}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:44 - INFO - __main__ - Step 103076: {'lr': 0.00011409996449653828, 'samples': 19790592, 'steps': 103075, 'loss/train': 1.4282079935073853}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:44 - INFO - __main__ - Step 103076: {'lr': 0.00011409996449653828, 'samples': 19790592, 'steps': 103075, 'loss/train': 1.4282079935073853}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:48 - INFO - __main__ - Step 103083: {'lr': 0.00011406878669686047, 'samples': 19791936, 'steps': 103082, 'loss/train': 1.595716953277588}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:48 - INFO - __main__ - Step 103083: {'lr': 0.00011406878669686047, 'samples': 19791936, 'steps': 103082, 'loss/train': 1.595716953277588}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:52 - INFO - __main__ - Step 103091: {'lr': 0.00011403315860075078, 'samples': 19793472, 'steps': 103090, 'loss/train': 1.366689682006836}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:54 - INFO - __main__ - Step 103095: {'lr': 0.00011401534602298114, 'samples': 19794240, 'steps': 103094, 'loss/train': 1.4453643560409546}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:56 - INFO - __main__ - Step 103099: {'lr': 0.00011399753442557298, 'samples': 19795008, 'steps': 103098, 'loss/train': 1.3277220726013184}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:41:58 - INFO - __main__ - Step 103103: {'lr': 0.0001139797238086545, 'samples': 19795776, 'steps': 103102, 'loss/train': 1.562617301940918}4}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:00 - INFO - __main__ - Step 103108: {'lr': 0.00011395746191651581, 'samples': 19796736, 'steps': 103107, 'loss/train': 0.8270094394683838}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:00 - INFO - __main__ - Step 103108: {'lr': 0.00011395746191651581, 'samples': 19796736, 'steps': 103107, 'loss/train': 0.8270094394683838}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:04 - INFO - __main__ - Step 103114: {'lr': 0.0001139307496688276, 'samples': 19797888, 'steps': 103113, 'loss/train': 1.7814445495605469}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:04 - INFO - __main__ - Step 103114: {'lr': 0.0001139307496688276, 'samples': 19797888, 'steps': 103113, 'loss/train': 1.7814445495605469}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:08 - INFO - __main__ - Step 103122: {'lr': 0.00011389513677205084, 'samples': 19799424, 'steps': 103121, 'loss/train': 1.521618127822876}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:10 - INFO - __main__ - Step 103126: {'lr': 0.00011387733179544041, 'samples': 19800192, 'steps': 103125, 'loss/train': 1.4707441329956055}}█████████████���███████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:12 - INFO - __main__ - Step 103131: {'lr': 0.00011385507695472468, 'samples': 19801152, 'steps': 103130, 'loss/train': 1.6209700107574463}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:15 - INFO - __main__ - Step 103136: {'lr': 0.00011383282364762904, 'samples': 19802112, 'steps': 103135, 'loss/train': 1.2555259466171265}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:15 - INFO - __main__ - Step 103136: {'lr': 0.00011383282364762904, 'samples': 19802112, 'steps': 103135, 'loss/train': 1.2555259466171265}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:18 - INFO - __main__ - Step 103143: {'lr': 0.00011380167159465413, 'samples': 19803456, 'steps': 103142, 'loss/train': 1.7374801635742188}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:20 - INFO - __main__ - Step 103147: {'lr': 0.00011378387177159646, 'samples': 19804224, 'steps': 103146, 'loss/train': 1.9558559656143188}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:22 - INFO - __main__ - Step 103152: {'lr': 0.00011376162337376936, 'samples': 19805184, 'steps': 103151, 'loss/train': 1.4736636877059937}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:24 - INFO - __main__ - Step 103156: {'lr': 0.0001137438257604601, 'samples': 19805952, 'steps': 103155, 'loss/train': 1.3182071447372437}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:27 - INFO - __main__ - Step 103160: {'lr': 0.00011372602912946964, 'samples': 19806720, 'steps': 103159, 'loss/train': 1.899271011352539}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:29 - INFO - __main__ - Step 103164: {'lr': 0.00011370823348092635, 'samples': 19807488, 'steps': 103163, 'loss/train': 1.053952932357788}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:30 - INFO - __main__ - Step 103168: {'lr': 0.00011369043881495863, 'samples': 19808256, 'steps': 103167, 'loss/train': 1.565725326538086}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:32 - INFO - __main__ - Step 103172: {'lr': 0.00011367264513169456, 'samples': 19809024, 'steps': 103171, 'loss/train': 1.1301496028900146}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:32 - INFO - __main__ - Step 103172: {'lr': 0.00011367264513169456, 'samples': 19809024, 'steps': 103171, 'loss/train': 1.1301496028900146}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:37 - INFO - __main__ - Step 103180: {'lr': 0.00011363706071379092, 'samples': 19810560, 'steps': 103179, 'loss/train': 1.221262812614441}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:38 - INFO - __main__ - Step 103184: {'lr': 0.0001136192699794078, 'samples': 19811328, 'steps': 103183, 'loss/train': 1.5883612632751465}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:40 - INFO - __main__ - Step 103188: {'lr': 0.00011360148022824152, 'samples': 19812096, 'steps': 103187, 'loss/train': 1.4369757175445557}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:42 - INFO - __main__ - Step 103193: {'lr': 0.0001135792444221278, 'samples': 19813056, 'steps': 103192, 'loss/train': 1.3904643058776855}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:45 - INFO - __main__ - Step 103197: {'lr': 0.00011356145688366831, 'samples': 19813824, 'steps': 103196, 'loss/train': 1.5365108251571655}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:47 - INFO - __main__ - Step 103201: {'lr': 0.00011354367032884244, 'samples': 19814592, 'steps': 103200, 'loss/train': 0.7418365478515625}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:48 - INFO - __main__ - Step 103205: {'lr': 0.00011352588475777856, 'samples': 19815360, 'steps': 103204, 'loss/train': 0.7803447842597961}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:50 - INFO - __main__ - Step 103209: {'lr': 0.00011350810017060464, 'samples': 19816128, 'steps': 103208, 'loss/train': 0.469216525554657}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:53 - INFO - __main__ - Step 103214: {'lr': 0.00011348587082042811, 'samples': 19817088, 'steps': 103213, 'loss/train': 0.971868634223938}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:53 - INFO - __main__ - Step 103214: {'lr': 0.00011348587082042811, 'samples': 19817088, 'steps': 103213, 'loss/train': 0.971868634223938}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:57 - INFO - __main__ - Step 103221: {'lr': 0.00011345475231370564, 'samples': 19818432, 'steps': 103220, 'loss/train': 1.4656710624694824}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:42:58 - INFO - __main__ - Step 103225: {'lr': 0.00011343697166337425, 'samples': 19819200, 'steps': 103224, 'loss/train': 1.4136427640914917}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:00 - INFO - __main__ - Step 103229: {'lr': 0.00011341919199757387, 'samples': 19819968, 'steps': 103228, 'loss/train': 1.5005377531051636}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:03 - INFO - __main__ - Step 103235: {'lr': 0.00011339252434514947, 'samples': 19821120, 'steps': 103234, 'loss/train': 0.7963549494743347}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:05 - INFO - __main__ - Step 103239: {'lr': 0.00011337474714123766, 'samples': 19821888, 'steps': 103238, 'loss/train': 1.749988079071045}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:05 - INFO - __main__ - Step 103239: {'lr': 0.00011337474714123766, 'samples': 19821888, 'steps': 103238, 'loss/train': 1.749988079071045}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:08 - INFO - __main__ - Step 103246: {'lr': 0.00011334363940457634, 'samples': 19823232, 'steps': 103245, 'loss/train': 1.2485884428024292}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:11 - INFO - __main__ - Step 103250: {'lr': 0.00011332586490966707, 'samples': 19824000, 'steps': 103249, 'loss/train': 1.5348072052001953}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:13 - INFO - __main__ - Step 103255: {'lr': 0.00011330364817666864, 'samples': 19824960, 'steps': 103254, 'loss/train': 1.3524940013885498}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:15 - INFO - __main__ - Step 103259: {'lr': 0.00011328587589893666, 'samples': 19825728, 'steps': 103258, 'loss/train': 1.4907366037368774}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:15 - INFO - __main__ - Step 103259: {'lr': 0.00011328587589893666, 'samples': 19825728, 'steps': 103258, 'loss/train': 1.4907366037368774}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:18 - INFO - __main__ - Step 103266: {'lr': 0.00011325477678463198, 'samples': 19827072, 'steps': 103265, 'loss/train': 1.5774726867675781}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:21 - INFO - __main__ - Step 103271: {'lr': 0.00011323256497997572, 'samples': 19828032, 'steps': 103270, 'loss/train': 1.6428449153900146}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:23 - INFO - __main__ - Step 103275: {'lr': 0.00011321479664549414, 'samples': 19828800, 'steps': 103274, 'loss/train': 1.139201045036316}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:25 - INFO - __main__ - Step 103279: {'lr': 0.00011319702929714526, 'samples': 19829568, 'steps': 103278, 'loss/train': 1.1388602256774902}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:26 - INFO - __main__ - Step 103283: {'lr': 0.00011317926293505732, 'samples': 19830336, 'steps': 103282, 'loss/train': 1.6695231199264526}}██████��██████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:29 - INFO - __main__ - Step 103287: {'lr': 0.00011316149755935839, 'samples': 19831104, 'steps': 103286, 'loss/train': 1.4584927558898926}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:29 - INFO - __main__ - Step 103287: {'lr': 0.00011316149755935839, 'samples': 19831104, 'steps': 103286, 'loss/train': 1.4584927558898926}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:33 - INFO - __main__ - Step 103295: {'lr': 0.00011312596976763991, 'samples': 19832640, 'steps': 103294, 'loss/train': 1.8449199199676514}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:35 - INFO - __main__ - Step 103299: {'lr': 0.00011310820735187643, 'samples': 19833408, 'steps': 103298, 'loss/train': 1.8230185508728027}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:37 - INFO - __main__ - Step 103303: {'lr': 0.00011309044592301432, 'samples': 19834176, 'steps': 103302, 'loss/train': 1.694885492324829}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:39 - INFO - __main__ - Step 103307: {'lr': 0.00011307268548118141, 'samples': 19834944, 'steps': 103306, 'loss/train': 1.1716443300247192}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:41 - INFO - __main__ - Step 103311: {'lr': 0.00011305492602650589, 'samples': 19835712, 'steps': 103310, 'loss/train': 1.2184748649597168}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:42 - INFO - __main__ - Step 103315: {'lr': 0.00011303716755911583, 'samples': 19836480, 'steps': 103314, 'loss/train': 0.5964123010635376}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:45 - INFO - __main__ - Step 103319: {'lr': 0.0001130194100791391, 'samples': 19837248, 'steps': 103318, 'loss/train': 1.6259052753448486}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:47 - INFO - __main__ - Step 103324: {'lr': 0.00011299721461791334, 'samples': 19838208, 'steps': 103323, 'loss/train': 1.1973531246185303}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:49 - INFO - __main__ - Step 103328: {'lr': 0.00011297945936008497, 'samples': 19838976, 'steps': 103327, 'loss/train': 1.3934829235076904}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:51 - INFO - __main__ - Step 103332: {'lr': 0.00011296170509008596, 'samples': 19839744, 'steps': 103331, 'loss/train': 1.0988963842391968}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:53 - INFO - __main__ - Step 103336: {'lr': 0.00011294395180804443, 'samples': 19840512, 'steps': 103335, 'loss/train': 1.4546657800674438}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:55 - INFO - __main__ - Step 103340: {'lr': 0.00011292619951408831, 'samples': 19841280, 'steps': 103339, 'loss/train': 1.4652659893035889}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:57 - INFO - __main__ - Step 103344: {'lr': 0.00011290844820834572, 'samples': 19842048, 'steps': 103343, 'loss/train': 1.310532569885254}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:43:59 - INFO - __main__ - Step 103348: {'lr': 0.00011289069789094444, 'samples': 19842816, 'steps': 103347, 'loss/train': 0.5161005258560181}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:01 - INFO - __main__ - Step 103352: {'lr': 0.00011287294856201255, 'samples': 19843584, 'steps': 103351, 'loss/train': 1.1528481245040894}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:03 - INFO - __main__ - Step 103356: {'lr': 0.00011285520022167808, 'samples': 19844352, 'steps': 103355, 'loss/train': 1.3966008424758911}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:05 - INFO - __main__ - Step 103361: {'lr': 0.0001128330161866698, 'samples': 19845312, 'steps': 103360, 'loss/train': 1.3910471200942993}}}███���█████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:07 - INFO - __main__ - Step 103365: {'lr': 0.00011281527007114706, 'samples': 19846080, 'steps': 103364, 'loss/train': 1.2809163331985474}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:09 - INFO - __main__ - Step 103369: {'lr': 0.00011279752494463757, 'samples': 19846848, 'steps': 103368, 'loss/train': 1.3373680114746094}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:12 - INFO - __main__ - Step 103373: {'lr': 0.00011277978080726906, 'samples': 19847616, 'steps': 103372, 'loss/train': 1.0597271919250488}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:13 - INFO - __main__ - Step 103377: {'lr': 0.0001127620376591696, 'samples': 19848384, 'steps': 103376, 'loss/train': 1.071413516998291}8}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:16 - INFO - __main__ - Step 103381: {'lr': 0.00011274429550046702, 'samples': 19849152, 'steps': 103380, 'loss/train': 2.295464515686035}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:16 - INFO - __main__ - Step 103381: {'lr': 0.00011274429550046702, 'samples': 19849152, 'steps': 103380, 'loss/train': 2.295464515686035}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:19 - INFO - __main__ - Step 103388: {'lr': 0.00011271324910385875, 'samples': 19850496, 'steps': 103387, 'loss/train': 1.4874944686889648}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:21 - INFO - __main__ - Step 103393: {'lr': 0.00011269107496202008, 'samples': 19851456, 'steps': 103392, 'loss/train': 1.2638658285140991}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:21 - INFO - __main__ - Step 103393: {'lr': 0.00011269107496202008, 'samples': 19851456, 'steps': 103392, 'loss/train': 1.2638658285140991}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:25 - INFO - __main__ - Step 103401: {'lr': 0.00011265559955238496, 'samples': 19852992, 'steps': 103400, 'loss/train': 1.0893192291259766}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:27 - INFO - __main__ - Step 103405: {'lr': 0.00011263786333274984, 'samples': 19853760, 'steps': 103404, 'loss/train': 1.2373111248016357}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:29 - INFO - __main__ - Step 103409: {'lr': 0.00011262012810340694, 'samples': 19854528, 'steps': 103408, 'loss/train': 1.5378228425979614}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:31 - INFO - __main__ - Step 103413: {'lr': 0.00011260239386448396, 'samples': 19855296, 'steps': 103412, 'loss/train': 1.101731777191162}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:33 - INFO - __main__ - Step 103418: {'lr': 0.00011258022745880315, 'samples': 19856256, 'steps': 103417, 'loss/train': 1.7069885730743408}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:36 - INFO - __main__ - Step 103422: {'lr': 0.00011256249544879271, 'samples': 19857024, 'steps': 103421, 'loss/train': 1.6006667613983154}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:36 - INFO - __main__ - Step 103422: {'lr': 0.00011256249544879271, 'samples': 19857024, 'steps': 103421, 'loss/train': 1.6006667613983154}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:39 - INFO - __main__ - Step 103429: {'lr': 0.00011253146681554913, 'samples': 19858368, 'steps': 103428, 'loss/train': 1.6675951480865479}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:42 - INFO - __main__ - Step 103434: {'lr': 0.00011250930536428547, 'samples': 19859328, 'steps': 103433, 'loss/train': 1.9671369791030884}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:42 - INFO - __main__ - Step 103434: {'lr': 0.00011250930536428547, 'samples': 19859328, 'steps': 103433, 'loss/train': 1.9671369791030884}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:45 - INFO - __main__ - Step 103441: {'lr': 0.00011247828193452215, 'samples': 19860672, 'steps': 103440, 'loss/train': 1.5409198999404907}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:48 - INFO - __main__ - Step 103446: {'lr': 0.00011245612420074896, 'samples': 19861632, 'steps': 103445, 'loss/train': 0.11420916020870209}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:50 - INFO - __main__ - Step 103450: {'lr': 0.00011243839912927123, 'samples': 19862400, 'steps': 103449, 'loss/train': 2.0593228340148926}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:50 - INFO - __main__ - Step 103450: {'lr': 0.00011243839912927123, 'samples': 19862400, 'steps': 103449, 'loss/train': 2.0593228340148926}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:53 - INFO - __main__ - Step 103457: {'lr': 0.00011240738264061251, 'samples': 19863744, 'steps': 103456, 'loss/train': 1.2255724668502808}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:56 - INFO - __main__ - Step 103462: {'lr': 0.00011238522986572977, 'samples': 19864704, 'steps': 103461, 'loss/train': 1.1597539186477661}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:44:56 - INFO - __main__ - Step 103462: {'lr': 0.00011238522986572977, 'samples': 19864704, 'steps': 103461, 'loss/train': 1.1597539186477661}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:00 - INFO - __main__ - Step 103470: {'lr': 0.0001123497886503898, 'samples': 19866240, 'steps': 103469, 'loss/train': 1.0200334787368774}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:02 - INFO - __main__ - Step 103474: {'lr': 0.0001123320695312095, 'samples': 19867008, 'steps': 103473, 'loss/train': 1.5295113325119019}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:03 - INFO - __main__ - Step 103478: {'lr': 0.00011231435140452583, 'samples': 19867776, 'steps': 103477, 'loss/train': 0.876252293586731}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:06 - INFO - __main__ - Step 103482: {'lr': 0.00011229663427046663, 'samples': 19868544, 'steps': 103481, 'loss/train': 1.2791571617126465}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:06 - INFO - __main__ - Step 103482: {'lr': 0.00011229663427046663, 'samples': 19868544, 'steps': 103481, 'loss/train': 1.2791571617126465}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:09 - INFO - __main__ - Step 103488: {'lr': 0.00011227006043082818, 'samples': 19869696, 'steps': 103487, 'loss/train': 1.5692262649536133}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:11 - INFO - __main__ - Step 103493: {'lr': 0.0001122479172710665, 'samples': 19870656, 'steps': 103492, 'loss/train': 1.3417445421218872}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:14 - INFO - __main__ - Step 103498: {'lr': 0.00011222577566302902, 'samples': 19871616, 'steps': 103497, 'loss/train': 1.428093433380127}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:14 - INFO - __main__ - Step 103498: {'lr': 0.00011222577566302902, 'samples': 19871616, 'steps': 103497, 'loss/train': 1.428093433380127}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:17 - INFO - __main__ - Step 103505: {'lr': 0.00011219478001914781, 'samples': 19872960, 'steps': 103504, 'loss/train': 1.3108950853347778}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:19 - INFO - __main__ - Step 103509: {'lr': 0.00011217706958864426, 'samples': 19873728, 'steps': 103508, 'loss/train': 1.5282385349273682}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:22 - INFO - __main__ - Step 103514: {'lr': 0.00011215493294779969, 'samples': 19874688, 'steps': 103513, 'loss/train': 1.2855743169784546}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:24 - INFO - __main__ - Step 103518: {'lr': 0.00011213722475310765, 'samples': 19875456, 'steps': 103517, 'loss/train': 1.1686667203903198}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:26 - INFO - __main__ - Step 103522: {'lr': 0.00011211951755231692, 'samples': 19876224, 'steps': 103521, 'loss/train': 1.5960978269577026}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:27 - INFO - __main__ - Step 103526: {'lr': 0.0001121018113455553, 'samples': 19876992, 'steps': 103525, 'loss/train': 1.4705100059509277}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:29 - INFO - __main__ - Step 103530: {'lr': 0.00011208410613295047, 'samples': 19877760, 'steps': 103529, 'loss/train': 1.4320732355117798}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:32 - INFO - __main__ - Step 103535: {'lr': 0.00011206197601542173, 'samples': 19878720, 'steps': 103534, 'loss/train': 1.56797456741333}8}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:32 - INFO - __main__ - Step 103535: {'lr': 0.00011206197601542173, 'samples': 19878720, 'steps': 103534, 'loss/train': 1.56797456741333}8}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:35 - INFO - __main__ - Step 103542: {'lr': 0.0001120309964613526, 'samples': 19880064, 'steps': 103541, 'loss/train': 1.3383831977844238}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:37 - INFO - __main__ - Step 103546: {'lr': 0.00011201329522665107, 'samples': 19880832, 'steps': 103545, 'loss/train': 1.308884859085083}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:40 - INFO - __main__ - Step 103551: {'lr': 0.00011199117008221932, 'samples': 19881792, 'steps': 103550, 'loss/train': 1.3925292491912842}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:42 - INFO - __main__ - Step 103556: {'lr': 0.0001119690464924038, 'samples': 19882752, 'steps': 103555, 'loss/train': 0.379334419965744}2}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:42 - INFO - __main__ - Step 103556: {'lr': 0.0001119690464924038, 'samples': 19882752, 'steps': 103555, 'loss/train': 0.379334419965744}2}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:45 - INFO - __main__ - Step 103563: {'lr': 0.00011193807607889192, 'samples': 19884096, 'steps': 103562, 'loss/train': 1.4688103199005127}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:47 - INFO - __main__ - Step 103567: {'lr': 0.00011192038006828698, 'samples': 19884864, 'steps': 103566, 'loss/train': 1.3130242824554443}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:47 - INFO - __main__ - Step 103567: {'lr': 0.00011192038006828698, 'samples': 19884864, 'steps': 103566, 'loss/train': 1.3130242824554443}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:52 - INFO - __main__ - Step 103575: {'lr': 0.00011188499103359892, 'samples': 19886400, 'steps': 103574, 'loss/train': 2.0192315578460693}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:53 - INFO - __main__ - Step 103579: {'lr': 0.00011186729800977085, 'samples': 19887168, 'steps': 103578, 'loss/train': 1.4511831998825073}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:53 - INFO - __main__ - Step 103579: {'lr': 0.00011186729800977085, 'samples': 19887168, 'steps': 103578, 'loss/train': 1.4511831998825073}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:58 - INFO - __main__ - Step 103586: {'lr': 0.00011183633761440645, 'samples': 19888512, 'steps': 103585, 'loss/train': 0.37513843178749084}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:45:59 - INFO - __main__ - Step 103590: {'lr': 0.00011181864732946573, 'samples': 19889280, 'steps': 103589, 'loss/train': 1.3832817077636719}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:01 - INFO - __main__ - Step 103594: {'lr': 0.00011180095804072315, 'samples': 19890048, 'steps': 103593, 'loss/train': 0.9020841121673584}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:04 - INFO - __main__ - Step 103599: {'lr': 0.00011177884783089299, 'samples': 19891008, 'steps': 103598, 'loss/train': 1.4749382734298706}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:04 - INFO - __main__ - Step 103599: {'lr': 0.00011177884783089299, 'samples': 19891008, 'steps': 103598, 'loss/train': 1.4749382734298706}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:08 - INFO - __main__ - Step 103607: {'lr': 0.00011174347473384474, 'samples': 19892544, 'steps': 103606, 'loss/train': 1.7937846183776855}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:09 - INFO - __main__ - Step 103611: {'lr': 0.00011172578968036712, 'samples': 19893312, 'steps': 103610, 'loss/train': 0.9258628487586975}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:11 - INFO - __main__ - Step 103615: {'lr': 0.000111708105623757, 'samples': 19894080, 'steps': 103614, 'loss/train': 1.2673842906951904}5}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:14 - INFO - __main__ - Step 103620: {'lr': 0.00011168600195503364, 'samples': 19895040, 'steps': 103619, 'loss/train': 2.259232759475708}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:16 - INFO - __main__ - Step 103625: {'lr': 0.00011166389984436423, 'samples': 19896000, 'steps': 103624, 'loss/train': 1.0267678499221802}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:16 - INFO - __main__ - Step 103625: {'lr': 0.00011166389984436423, 'samples': 19896000, 'steps': 103624, 'loss/train': 1.0267678499221802}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:20 - INFO - __main__ - Step 103632: {'lr': 0.00011163295950743139, 'samples': 19897344, 'steps': 103631, 'loss/train': 2.046485424041748}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:22 - INFO - __main__ - Step 103636: {'lr': 0.00011161528068646767, 'samples': 19898112, 'steps': 103635, 'loss/train': 1.589772343635559}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:24 - INFO - __main__ - Step 103640: {'lr': 0.00011159760286316836, 'samples': 19898880, 'steps': 103639, 'loss/train': 1.0360136032104492}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:26 - INFO - __main__ - Step 103644: {'lr': 0.00011157992603766073, 'samples': 19899648, 'steps': 103643, 'loss/train': 0.8877982497215271}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:28 - INFO - __main__ - Step 103648: {'lr': 0.00011156225021007227, 'samples': 19900416, 'steps': 103647, 'loss/train': 1.3189188241958618}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:30 - INFO - __main__ - Step 103652: {'lr': 0.00011154457538053054, 'samples': 19901184, 'steps': 103651, 'loss/train': 1.8423964977264404}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:32 - INFO - __main__ - Step 103657: {'lr': 0.0001115224832473004, 'samples': 19902144, 'steps': 103656, 'loss/train': 1.3583693504333496}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:34 - INFO - __main__ - Step 103661: {'lr': 0.00011150481066382937, 'samples': 19902912, 'steps': 103660, 'loss/train': 0.8916557431221008}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:34 - INFO - __main__ - Step 103661: {'lr': 0.00011150481066382937, 'samples': 19902912, 'steps': 103660, 'loss/train': 0.8916557431221008}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:38 - INFO - __main__ - Step 103668: {'lr': 0.00011147388604537786, 'samples': 19904256, 'steps': 103667, 'loss/train': 1.681624412536621}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:38 - INFO - __main__ - Step 103668: {'lr': 0.00011147388604537786, 'samples': 19904256, 'steps': 103667, 'loss/train': 1.681624412536621}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:42 - INFO - __main__ - Step 103676: {'lr': 0.00011143854736939391, 'samples': 19905792, 'steps': 103675, 'loss/train': 1.3860715627670288}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:44 - INFO - __main__ - Step 103680: {'lr': 0.00011142087952974598, 'samples': 19906560, 'steps': 103679, 'loss/train': 1.4111964702606201}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:46 - INFO - __main__ - Step 103684: {'lr': 0.00011140321268916376, 'samples': 19907328, 'steps': 103683, 'loss/train': 0.7785894870758057}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:48 - INFO - __main__ - Step 103689: {'lr': 0.00011138113054356632, 'samples': 19908288, 'steps': 103688, 'loss/train': 0.7610182166099548}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:50 - INFO - __main__ - Step 103693: {'lr': 0.00011136346595134796, 'samples': 19909056, 'steps': 103692, 'loss/train': 1.0578582286834717}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:50 - INFO - __main__ - Step 103693: {'lr': 0.00011136346595134796, 'samples': 19909056, 'steps': 103692, 'loss/train': 1.0578582286834717}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:54 - INFO - __main__ - Step 103700: {'lr': 0.00011133255532004036, 'samples': 19910400, 'steps': 103699, 'loss/train': 1.4389457702636719}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:56 - INFO - __main__ - Step 103705: {'lr': 0.00011131047817208043, 'samples': 19911360, 'steps': 103704, 'loss/train': 1.5020387172698975}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:59 - INFO - __main__ - Step 103710: {'lr': 0.00011128840258640433, 'samples': 19912320, 'steps': 103709, 'loss/train': 1.2942230701446533}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:46:59 - INFO - __main__ - Step 103710: {'lr': 0.00011128840258640433, 'samples': 19912320, 'steps': 103709, 'loss/train': 1.2942230701446533}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:02 - INFO - __main__ - Step 103717: {'lr': 0.00011125749939156835, 'samples': 19913664, 'steps': 103716, 'loss/train': 1.0605570077896118}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:04 - INFO - __main__ - Step 103722: {'lr': 0.00011123542755638841, 'samples': 19914624, 'steps': 103721, 'loss/train': 1.4209126234054565}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:06 - INFO - __main__ - Step 103726: {'lr': 0.0001112177712136856, 'samples': 19915392, 'steps': 103725, 'loss/train': 1.2080662250518799}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:09 - INFO - __main__ - Step 103731: {'lr': 0.00011119570219231754, 'samples': 19916352, 'steps': 103730, 'loss/train': 0.9556599855422974}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:09 - INFO - __main__ - Step 103731: {'lr': 0.00011119570219231754, 'samples': 19916352, 'steps': 103730, 'loss/train': 0.9556599855422974}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:13 - INFO - __main__ - Step 103738: {'lr': 0.00011116480818926694, 'samples': 19917696, 'steps': 103737, 'loss/train': 1.4205293655395508}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:14 - INFO - __main__ - Step 103742: {'lr': 0.00011114715584944827, 'samples': 19918464, 'steps': 103741, 'loss/train': 1.3259367942810059}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:16 - INFO - __main__ - Step 103747: {'lr': 0.00011112509183240108, 'samples': 19919424, 'steps': 103746, 'loss/train': 1.1885169744491577}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:16 - INFO - __main__ - Step 103747: {'lr': 0.00011112509183240108, 'samples': 19919424, 'steps': 103746, 'loss/train': 1.1885169744491577}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:21 - INFO - __main__ - Step 103755: {'lr': 0.00011108979265912336, 'samples': 19920960, 'steps': 103754, 'loss/train': 1.034071683883667}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:23 - INFO - __main__ - Step 103759: {'lr': 0.00011107214457459991, 'samples': 19921728, 'steps': 103758, 'loss/train': 1.56337571144104}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:24 - INFO - __main__ - Step 103763: {'lr': 0.00011105449749165655, 'samples': 19922496, 'steps': 103762, 'loss/train': 1.2529950141906738}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:24 - INFO - __main__ - Step 103763: {'lr': 0.00011105449749165655, 'samples': 19922496, 'steps': 103762, 'loss/train': 1.2529950141906738}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:28 - INFO - __main__ - Step 103770: {'lr': 0.00011102361750693996, 'samples': 19923840, 'steps': 103769, 'loss/train': 1.4432138204574585}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:30 - INFO - __main__ - Step 103774: {'lr': 0.00011100597317899747, 'samples': 19924608, 'steps': 103773, 'loss/train': 1.3346340656280518}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:32 - INFO - __main__ - Step 103778: {'lr': 0.00011098832985311191, 'samples': 19925376, 'steps': 103777, 'loss/train': 0.998872697353363}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:34 - INFO - __main__ - Step 103783: {'lr': 0.00011096627710509142, 'samples': 19926336, 'steps': 103782, 'loss/train': 0.5662245750427246}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:36 - INFO - __main__ - Step 103787: {'lr': 0.00011094863603429928, 'samples': 19927104, 'steps': 103786, 'loss/train': 0.7556708455085754}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:36 - INFO - __main__ - Step 103787: {'lr': 0.00011094863603429928, 'samples': 19927104, 'steps': 103786, 'loss/train': 0.7556708455085754}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:40 - INFO - __main__ - Step 103794: {'lr': 0.00011091776657268377, 'samples': 19928448, 'steps': 103793, 'loss/train': 1.698318600654602}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:42 - INFO - __main__ - Step 103798: {'lr': 0.0001109001282589911, 'samples': 19929216, 'steps': 103797, 'loss/train': 1.2503595352172852}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:42 - INFO - __main__ - Step 103798: {'lr': 0.0001109001282589911, 'samples': 19929216, 'steps': 103797, 'loss/train': 1.2503595352172852}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:46 - INFO - __main__ - Step 103806: {'lr': 0.0001108648546401933, 'samples': 19930752, 'steps': 103805, 'loss/train': 1.6869242191314697}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:48 - INFO - __main__ - Step 103810: {'lr': 0.00011084721933534236, 'samples': 19931520, 'steps': 103809, 'loss/train': 0.8496022820472717}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:50 - INFO - __main__ - Step 103814: {'lr': 0.00011082958503369306, 'samples': 19932288, 'steps': 103813, 'loss/train': 1.5248404741287231}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:50 - INFO - __main__ - Step 103814: {'lr': 0.00011082958503369306, 'samples': 19932288, 'steps': 103813, 'loss/train': 1.5248404741287231}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:54 - INFO - __main__ - Step 103822: {'lr': 0.00011079431944050738, 'samples': 19933824, 'steps': 103821, 'loss/train': 1.0629663467407227}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:56 - INFO - __main__ - Step 103826: {'lr': 0.00011077668814922543, 'samples': 19934592, 'steps': 103825, 'loss/train': 1.3523845672607422}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:47:59 - INFO - __main__ - Step 103831: {'lr': 0.00011075465044660496, 'samples': 19935552, 'steps': 103830, 'loss/train': 1.361082673072815}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:01 - INFO - __main__ - Step 103835: {'lr': 0.0001107370214138492, 'samples': 19936320, 'steps': 103834, 'loss/train': 0.6033650636672974}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:03 - INFO - __main__ - Step 103839: {'lr': 0.00011071939338508949, 'samples': 19937088, 'steps': 103838, 'loss/train': 1.319192886352539}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:03 - INFO - __main__ - Step 103839: {'lr': 0.00011071939338508949, 'samples': 19937088, 'steps': 103838, 'loss/train': 1.319192886352539}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:06 - INFO - __main__ - Step 103846: {'lr': 0.00011068854675100745, 'samples': 19938432, 'steps': 103845, 'loss/train': 1.271488070487976}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:09 - INFO - __main__ - Step 103852: {'lr': 0.00011066210922700348, 'samples': 19939584, 'steps': 103851, 'loss/train': 0.8706030249595642}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:09 - INFO - __main__ - Step 103852: {'lr': 0.00011066210922700348, 'samples': 19939584, 'steps': 103851, 'loss/train': 0.8706030249595642}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:09 - INFO - __main__ - Step 103852: {'lr': 0.00011066210922700348, 'samples': 19939584, 'steps': 103851, 'loss/train': 0.8706030249595642}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:09 - INFO - __main__ - Step 103852: {'lr': 0.00011066210922700348, 'samples': 19939584, 'steps': 103851, 'loss/train': 0.8706030249595642}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:16 - INFO - __main__ - Step 103865: {'lr': 0.00011060483567932938, 'samples': 19942080, 'steps': 103864, 'loss/train': 2.877915382385254}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:18 - INFO - __main__ - Step 103870: {'lr': 0.00011058281021794325, 'samples': 19943040, 'steps': 103869, 'loss/train': 1.144775629043579}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:18 - INFO - __main__ - Step 103870: {'lr': 0.00011058281021794325, 'samples': 19943040, 'steps': 103869, 'loss/train': 1.144775629043579}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:23 - INFO - __main__ - Step 103878: {'lr': 0.0001105475727464287, 'samples': 19944576, 'steps': 103877, 'loss/train': 1.3096612691879272}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:24 - INFO - __main__ - Step 103882: {'lr': 0.00011052995551865069, 'samples': 19945344, 'steps': 103881, 'loss/train': 1.8185957670211792}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:24 - INFO - __main__ - Step 103882: {'lr': 0.00011052995551865069, 'samples': 19945344, 'steps': 103881, 'loss/train': 1.8185957670211792}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:28 - INFO - __main__ - Step 103889: {'lr': 0.00011049912778957283, 'samples': 19946688, 'steps': 103888, 'loss/train': 3.6018686294555664}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:30 - INFO - __main__ - Step 103893: {'lr': 0.00011048151332719461, 'samples': 19947456, 'steps': 103892, 'loss/train': 1.4908908605575562}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:30 - INFO - __main__ - Step 103893: {'lr': 0.00011048151332719461, 'samples': 19947456, 'steps': 103892, 'loss/train': 1.4908908605575562}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:35 - INFO - __main__ - Step 103901: {'lr': 0.00011044628742007909, 'samples': 19948992, 'steps': 103900, 'loss/train': 1.2026313543319702}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:36 - INFO - __main__ - Step 103905: {'lr': 0.0001104286759755958, 'samples': 19949760, 'steps': 103904, 'loss/train': 1.0644856691360474}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:38 - INFO - __main__ - Step 103909: {'lr': 0.00011041106553733157, 'samples': 19950528, 'steps': 103908, 'loss/train': 0.9283954501152039}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:41 - INFO - __main__ - Step 103914: {'lr': 0.00011038905390469, 'samples': 19951488, 'steps': 103913, 'loss/train': 1.1670342683792114}39}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:43 - INFO - __main__ - Step 103918: {'lr': 0.00011037144573088253, 'samples': 19952256, 'steps': 103917, 'loss/train': 1.2464721202850342}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:45 - INFO - __main__ - Step 103922: {'lr': 0.0001103538385637067, 'samples': 19953024, 'steps': 103921, 'loss/train': 1.3775641918182373}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:46 - INFO - __main__ - Step 103926: {'lr': 0.00011033623240328928, 'samples': 19953792, 'steps': 103925, 'loss/train': 1.3243792057037354}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:48 - INFO - __main__ - Step 103930: {'lr': 0.00011031862724975724, 'samples': 19954560, 'steps': 103929, 'loss/train': 0.770973801612854}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:51 - INFO - __main__ - Step 103935: {'lr': 0.0001102966222239683, 'samples': 19955520, 'steps': 103934, 'loss/train': 1.3338687419891357}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:51 - INFO - __main__ - Step 103935: {'lr': 0.0001102966222239683, 'samples': 19955520, 'steps': 103934, 'loss/train': 1.3338687419891357}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:51 - INFO - __main__ - Step 103935: {'lr': 0.0001102966222239683, 'samples': 19955520, 'steps': 103934, 'loss/train': 1.3338687419891357}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:51 - INFO - __main__ - Step 103935: {'lr': 0.0001102966222239683, 'samples': 19955520, 'steps': 103934, 'loss/train': 1.3338687419891357}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:48:58 - INFO - __main__ - Step 103948: {'lr': 0.00011023941652247329, 'samples': 19958016, 'steps': 103947, 'loss/train': 1.7864831686019897}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:00 - INFO - __main__ - Step 103953: {'lr': 0.00011021741716318093, 'samples': 19958976, 'steps': 103952, 'loss/train': 1.4499515295028687}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:03 - INFO - __main__ - Step 103958: {'lr': 0.00011019541937848546, 'samples': 19959936, 'steps': 103957, 'loss/train': 2.6294491291046143}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:03 - INFO - __main__ - Step 103958: {'lr': 0.00011019541937848546, 'samples': 19959936, 'steps': 103957, 'loss/train': 2.6294491291046143}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:07 - INFO - __main__ - Step 103965: {'lr': 0.0001101646251257064, 'samples': 19961280, 'steps': 103964, 'loss/train': 1.6129286289215088}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:08 - INFO - __main__ - Step 103969: {'lr': 0.00011014702979595759, 'samples': 19962048, 'steps': 103968, 'loss/train': 1.301087737083435}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:11 - INFO - __main__ - Step 103974: {'lr': 0.00011012503705163729, 'samples': 19963008, 'steps': 103973, 'loss/train': 1.3010551929473877}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:13 - INFO - __main__ - Step 103978: {'lr': 0.00011010744399062808, 'samples': 19963776, 'steps': 103977, 'loss/train': 1.4255353212356567}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:13 - INFO - __main__ - Step 103978: {'lr': 0.00011010744399062808, 'samples': 19963776, 'steps': 103977, 'loss/train': 1.4255353212356567}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:17 - INFO - __main__ - Step 103984: {'lr': 0.00011008105629015672, 'samples': 19964928, 'steps': 103983, 'loss/train': 1.6855570077896118}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:19 - INFO - __main__ - Step 103988: {'lr': 0.00011006346575072249, 'samples': 19965696, 'steps': 103987, 'loss/train': 1.8301599025726318}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:20 - INFO - __main__ - Step 103992: {'lr': 0.00011004587622014003, 'samples': 19966464, 'steps': 103991, 'loss/train': 1.289534091949463}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:22 - INFO - __main__ - Step 103997: {'lr': 0.00011002389072580313, 'samples': 19967424, 'steps': 103996, 'loss/train': 0.9840849041938782}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:25 - INFO - __main__ - Step 104001: {'lr': 0.00011000630346560118, 'samples': 19968192, 'steps': 104000, 'loss/train': 1.1032440662384033}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:27 - INFO - __main__ - Step 104006: {'lr': 0.00010998432080964093, 'samples': 19969152, 'steps': 104005, 'loss/train': 1.5993155241012573}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:29 - INFO - __main__ - Step 104010: {'lr': 0.00010996673582046124, 'samples': 19969920, 'steps': 104009, 'loss/train': 0.4511600732803345}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:29 - INFO - __main__ - Step 104010: {'lr': 0.00010996673582046124, 'samples': 19969920, 'steps': 104009, 'loss/train': 0.4511600732803345}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:32 - INFO - __main__ - Step 104017: {'lr': 0.00010993596451870074, 'samples': 19971264, 'steps': 104016, 'loss/train': 1.0768991708755493}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:35 - INFO - __main__ - Step 104022: {'lr': 0.00010991398691072452, 'samples': 19972224, 'steps': 104021, 'loss/train': 1.039174199104309}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:35 - INFO - __main__ - Step 104022: {'lr': 0.00010991398691072452, 'samples': 19972224, 'steps': 104021, 'loss/train': 1.039174199104309}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:39 - INFO - __main__ - Step 104030: {'lr': 0.00010987882602033635, 'samples': 19973760, 'steps': 104029, 'loss/train': 1.6384570598602295}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:41 - INFO - __main__ - Step 104034: {'lr': 0.00010986124709035356, 'samples': 19974528, 'steps': 104033, 'loss/train': 1.5828566551208496}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:43 - INFO - __main__ - Step 104038: {'lr': 0.0001098436691706804, 'samples': 19975296, 'steps': 104037, 'loss/train': 1.2406632900238037}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:43 - INFO - __main__ - Step 104038: {'lr': 0.0001098436691706804, 'samples': 19975296, 'steps': 104037, 'loss/train': 1.2406632900238037}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:47 - INFO - __main__ - Step 104045: {'lr': 0.00010981291024269144, 'samples': 19976640, 'steps': 104044, 'loss/train': 0.918048620223999}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:48 - INFO - __main__ - Step 104049: {'lr': 0.0001097953351020235, 'samples': 19977408, 'steps': 104048, 'loss/train': 1.3803975582122803}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:51 - INFO - __main__ - Step 104054: {'lr': 0.00010977336759761986, 'samples': 19978368, 'steps': 104053, 'loss/train': 1.317831039428711}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:53 - INFO - __main__ - Step 104059: {'lr': 0.000109751401672815, 'samples': 19979328, 'steps': 104058, 'loss/train': 1.2407829761505127}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:55 - INFO - __main__ - Step 104063: {'lr': 0.00010973383007044863, 'samples': 19980096, 'steps': 104062, 'loss/train': 1.2990601062774658}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:57 - INFO - __main__ - Step 104067: {'lr': 0.00010971625947931068, 'samples': 19980864, 'steps': 104066, 'loss/train': 1.296183705329895}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:49:59 - INFO - __main__ - Step 104071: {'lr': 0.00010969868989952769, 'samples': 19981632, 'steps': 104070, 'loss/train': 1.1833122968673706}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:01 - INFO - __main__ - Step 104075: {'lr': 0.00010968112133122638, 'samples': 19982400, 'steps': 104074, 'loss/train': 1.6004464626312256}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:01 - INFO - __main__ - Step 104075: {'lr': 0.00010968112133122638, 'samples': 19982400, 'steps': 104074, 'loss/train': 1.6004464626312256}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:05 - INFO - __main__ - Step 104083: {'lr': 0.0001096459872295755, 'samples': 19983936, 'steps': 104082, 'loss/train': 1.2150593996047974}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:07 - INFO - __main__ - Step 104087: {'lr': 0.00010962842169647916, 'samples': 19984704, 'steps': 104086, 'loss/train': 0.8803451657295227}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:08 - INFO - __main__ - Step 104091: {'lr': 0.00010961085717537109, 'samples': 19985472, 'steps': 104090, 'loss/train': 1.6062918901443481}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:11 - INFO - __main__ - Step 104095: {'lr': 0.00010959329366637802, 'samples': 19986240, 'steps': 104094, 'loss/train': 1.7251732349395752}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:13 - INFO - __main__ - Step 104100: {'lr': 0.00010957134070361602, 'samples': 19987200, 'steps': 104099, 'loss/train': 1.319576621055603}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:13 - INFO - __main__ - Step 104100: {'lr': 0.00010957134070361602, 'samples': 19987200, 'steps': 104099, 'loss/train': 1.319576621055603}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:16 - INFO - __main__ - Step 104107: {'lr': 0.00010954060921335409, 'samples': 19988544, 'steps': 104106, 'loss/train': 1.026045560836792}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:18 - INFO - __main__ - Step 104111: {'lr': 0.00010952304975408676, 'samples': 19989312, 'steps': 104110, 'loss/train': 1.5176138877868652}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:21 - INFO - __main__ - Step 104116: {'lr': 0.0001095011018541941, 'samples': 19990272, 'steps': 104115, 'loss/train': 1.5441941022872925}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:23 - INFO - __main__ - Step 104120: {'lr': 0.00010948354467378754, 'samples': 19991040, 'steps': 104119, 'loss/train': 0.6683568954467773}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:23 - INFO - __main__ - Step 104120: {'lr': 0.00010948354467378754, 'samples': 19991040, 'steps': 104119, 'loss/train': 0.6683568954467773}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:26 - INFO - __main__ - Step 104127: {'lr': 0.00010945282204576235, 'samples': 19992384, 'steps': 104126, 'loss/train': 1.2827292680740356}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:29 - INFO - __main__ - Step 104132: {'lr': 0.00010943087921127071, 'samples': 19993344, 'steps': 104131, 'loss/train': 1.211431860923767}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:31 - INFO - __main__ - Step 104137: {'lr': 0.00010940893796023607, 'samples': 19994304, 'steps': 104136, 'loss/train': 1.1647791862487793}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:31 - INFO - __main__ - Step 104137: {'lr': 0.00010940893796023607, 'samples': 19994304, 'steps': 104136, 'loss/train': 1.1647791862487793}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:34 - INFO - __main__ - Step 104144: {'lr': 0.00010937822286946566, 'samples': 19995648, 'steps': 104143, 'loss/train': 1.1906546354293823}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:37 - INFO - __main__ - Step 104148: {'lr': 0.00010936067278294609, 'samples': 19996416, 'steps': 104147, 'loss/train': 1.555348515510559}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:39 - INFO - __main__ - Step 104153: {'lr': 0.00010933873660063432, 'samples': 19997376, 'steps': 104152, 'loss/train': 1.4071922302246094}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:42 - INFO - __main__ - Step 104158: {'lr': 0.00010931680200281741, 'samples': 19998336, 'steps': 104157, 'loss/train': 1.3346034288406372}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:42 - INFO - __main__ - Step 104158: {'lr': 0.00010931680200281741, 'samples': 19998336, 'steps': 104157, 'loss/train': 1.3346034288406372}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:45 - INFO - __main__ - Step 104165: {'lr': 0.00010928609622829566, 'samples': 19999680, 'steps': 104164, 'loss/train': 1.389060378074646}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:47 - INFO - __main__ - Step 104169: {'lr': 0.00010926855146625986, 'samples': 20000448, 'steps': 104168, 'loss/train': 1.3026748895645142}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:49 - INFO - __main__ - Step 104173: {'lr': 0.00010925100771880678, 'samples': 20001216, 'steps': 104172, 'loss/train': 1.3526246547698975}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:51 - INFO - __main__ - Step 104177: {'lr': 0.00010923346498606296, 'samples': 20001984, 'steps': 104176, 'loss/train': 1.3926721811294556}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:53 - INFO - __main__ - Step 104181: {'lr': 0.00010921592326815468, 'samples': 20002752, 'steps': 104180, 'loss/train': 1.3068736791610718}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:55 - INFO - __main__ - Step 104185: {'lr': 0.00010919838256520856, 'samples': 20003520, 'steps': 104184, 'loss/train': 1.700769305229187}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:57 - INFO - __main__ - Step 104190: {'lr': 0.00010917645811400909, 'samples': 20004480, 'steps': 104189, 'loss/train': 1.8054662942886353}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:59 - INFO - __main__ - Step 104194: {'lr': 0.00010915891969519007, 'samples': 20005248, 'steps': 104193, 'loss/train': 1.703566551208496}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:50:59 - INFO - __main__ - Step 104194: {'lr': 0.00010915891969519007, 'samples': 20005248, 'steps': 104193, 'loss/train': 1.703566551208496}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:03 - INFO - __main__ - Step 104201: {'lr': 0.0001091282299055743, 'samples': 20006592, 'steps': 104200, 'loss/train': 1.4365577697753906}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:05 - INFO - __main__ - Step 104206: {'lr': 0.00010910631053147729, 'samples': 20007552, 'steps': 104205, 'loss/train': 1.4583981037139893}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:07 - INFO - __main__ - Step 104211: {'lr': 0.00010908439274449325, 'samples': 20008512, 'steps': 104210, 'loss/train': 1.2662289142608643}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:07 - INFO - __main__ - Step 104211: {'lr': 0.00010908439274449325, 'samples': 20008512, 'steps': 104210, 'loss/train': 1.2662289142608643}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:11 - INFO - __main__ - Step 104218: {'lr': 0.00010905371050953569, 'samples': 20009856, 'steps': 104217, 'loss/train': 1.1087826490402222}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:13 - INFO - __main__ - Step 104222: {'lr': 0.00010903617920098308, 'samples': 20010624, 'steps': 104221, 'loss/train': 1.4185415506362915}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:15 - INFO - __main__ - Step 104227: {'lr': 0.00010901426649441987, 'samples': 20011584, 'steps': 104226, 'loss/train': 1.345070719718933}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:17 - INFO - __main__ - Step 104231: {'lr': 0.00010899673747262545, 'samples': 20012352, 'steps': 104230, 'loss/train': 1.292345643043518}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:19 - INFO - __main__ - Step 104235: {'lr': 0.00010897920946737327, 'samples': 20013120, 'steps': 104234, 'loss/train': 1.6646921634674072}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:19 - INFO - __main__ - Step 104235: {'lr': 0.00010897920946737327, 'samples': 20013120, 'steps': 104234, 'loss/train': 1.6646921634674072}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:23 - INFO - __main__ - Step 104242: {'lr': 0.00010894853790461706, 'samples': 20014464, 'steps': 104241, 'loss/train': 1.873067021369934}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:25 - INFO - __main__ - Step 104247: {'lr': 0.00010892663155213429, 'samples': 20015424, 'steps': 104246, 'loss/train': 1.2633394002914429}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:28 - INFO - __main__ - Step 104252: {'lr': 0.00010890472678878858, 'samples': 20016384, 'steps': 104251, 'loss/train': 1.0804413557052612}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:28 - INFO - __main__ - Step 104252: {'lr': 0.00010890472678878858, 'samples': 20016384, 'steps': 104251, 'loss/train': 1.0804413557052612}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:31 - INFO - __main__ - Step 104259: {'lr': 0.00010887406279032478, 'samples': 20017728, 'steps': 104258, 'loss/train': 1.2192376852035522}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:33 - INFO - __main__ - Step 104263: {'lr': 0.00010885654190440658, 'samples': 20018496, 'steps': 104262, 'loss/train': 0.9740169644355774}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:35 - INFO - __main__ - Step 104268: {'lr': 0.00010883464222795766, 'samples': 20019456, 'steps': 104267, 'loss/train': 1.3228224515914917}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:35 - INFO - __main__ - Step 104268: {'lr': 0.00010883464222795766, 'samples': 20019456, 'steps': 104267, 'loss/train': 1.3228224515914917}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:40 - INFO - __main__ - Step 104276: {'lr': 0.0001087996060533023, 'samples': 20020992, 'steps': 104275, 'loss/train': 1.6237397193908691}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:42 - INFO - __main__ - Step 104280: {'lr': 0.00010878208949285684, 'samples': 20021760, 'steps': 104279, 'loss/train': 1.5574103593826294}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:43 - INFO - __main__ - Step 104284: {'lr': 0.00010876457395050105, 'samples': 20022528, 'steps': 104283, 'loss/train': 1.2626336812973022}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:45 - INFO - __main__ - Step 104288: {'lr': 0.00010874705942636131, 'samples': 20023296, 'steps': 104287, 'loss/train': 1.2391993999481201}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:48 - INFO - __main__ - Step 104293: {'lr': 0.00010872516770324544, 'samples': 20024256, 'steps': 104292, 'loss/train': 1.3217240571975708}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:50 - INFO - __main__ - Step 104297: {'lr': 0.0001087076554705535, 'samples': 20025024, 'steps': 104296, 'loss/train': 0.9850212931632996}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:52 - INFO - __main__ - Step 104301: {'lr': 0.00010869014425648804, 'samples': 20025792, 'steps': 104300, 'loss/train': 2.142334461212158}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:53 - INFO - __main__ - Step 104305: {'lr': 0.00010867263406117514, 'samples': 20026560, 'steps': 104304, 'loss/train': 1.2288154363632202}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:55 - INFO - __main__ - Step 104309: {'lr': 0.00010865512488474113, 'samples': 20027328, 'steps': 104308, 'loss/train': 1.1655292510986328}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:58 - INFO - __main__ - Step 104314: {'lr': 0.00010863323984718945, 'samples': 20028288, 'steps': 104313, 'loss/train': 1.6123887300491333}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:51:58 - INFO - __main__ - Step 104314: {'lr': 0.00010863323984718945, 'samples': 20028288, 'steps': 104313, 'loss/train': 1.6123887300491333}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:01 - INFO - __main__ - Step 104321: {'lr': 0.00010860260346997474, 'samples': 20029632, 'steps': 104320, 'loss/train': 1.6413233280181885}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:03 - INFO - __main__ - Step 104325: {'lr': 0.0001085850983703186, 'samples': 20030400, 'steps': 104324, 'loss/train': 1.6340487003326416}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:06 - INFO - __main__ - Step 104330: {'lr': 0.00010856321842944894, 'samples': 20031360, 'steps': 104329, 'loss/train': 0.5749872326850891}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:08 - INFO - __main__ - Step 104334: {'lr': 0.00010854571562386756, 'samples': 20032128, 'steps': 104333, 'loss/train': 1.5461745262145996}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:10 - INFO - __main__ - Step 104338: {'lr': 0.00010852821383808015, 'samples': 20032896, 'steps': 104337, 'loss/train': 1.2276599407196045}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:11 - INFO - __main__ - Step 104342: {'lr': 0.00010851071307221272, 'samples': 20033664, 'steps': 104341, 'loss/train': 1.703507900238037}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:13 - INFO - __main__ - Step 104346: {'lr': 0.00010849321332639151, 'samples': 20034432, 'steps': 104345, 'loss/train': 1.47083580493927}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:16 - INFO - __main__ - Step 104351: {'lr': 0.0001084713400787473, 'samples': 20035392, 'steps': 104350, 'loss/train': 1.1681945323944092}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:18 - INFO - __main__ - Step 104355: {'lr': 0.00010845384262849134, 'samples': 20036160, 'steps': 104354, 'loss/train': 1.232789397239685}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:18 - INFO - __main__ - Step 104355: {'lr': 0.00010845384262849134, 'samples': 20036160, 'steps': 104354, 'loss/train': 1.232789397239685}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:21 - INFO - __main__ - Step 104362: {'lr': 0.00010842322454609216, 'samples': 20037504, 'steps': 104361, 'loss/train': 1.3604927062988281}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:24 - INFO - __main__ - Step 104367: {'lr': 0.00010840135640096558, 'samples': 20038464, 'steps': 104366, 'loss/train': 1.332020878791809}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:26 - INFO - __main__ - Step 104372: {'lr': 0.00010837948985089299, 'samples': 20039424, 'steps': 104371, 'loss/train': 1.1809035539627075}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:26 - INFO - __main__ - Step 104372: {'lr': 0.00010837948985089299, 'samples': 20039424, 'steps': 104371, 'loss/train': 1.1809035539627075}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:29 - INFO - __main__ - Step 104379: {'lr': 0.00010834887936095134, 'samples': 20040768, 'steps': 104378, 'loss/train': 1.1440186500549316}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:31 - INFO - __main__ - Step 104383: {'lr': 0.00010833138905653767, 'samples': 20041536, 'steps': 104382, 'loss/train': 1.4969546794891357}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:34 - INFO - __main__ - Step 104388: {'lr': 0.00010830952761229334, 'samples': 20042496, 'steps': 104387, 'loss/train': 1.541641354560852}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:36 - INFO - __main__ - Step 104392: {'lr': 0.0001082920396060699, 'samples': 20043264, 'steps': 104391, 'loss/train': 1.5822778940200806}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:36 - INFO - __main__ - Step 104392: {'lr': 0.0001082920396060699, 'samples': 20043264, 'steps': 104391, 'loss/train': 1.5822778940200806}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:40 - INFO - __main__ - Step 104399: {'lr': 0.00010826143805353423, 'samples': 20044608, 'steps': 104398, 'loss/train': 1.3210091590881348}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:40 - INFO - __main__ - Step 104399: {'lr': 0.00010826143805353423, 'samples': 20044608, 'steps': 104398, 'loss/train': 1.3210091590881348}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:44 - INFO - __main__ - Step 104407: {'lr': 0.00010822646868258831, 'samples': 20046144, 'steps': 104406, 'loss/train': 0.4023608863353729}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:46 - INFO - __main__ - Step 104411: {'lr': 0.00010820898553019545, 'samples': 20046912, 'steps': 104410, 'loss/train': 1.4591537714004517}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:47 - INFO - __main__ - Step 104415: {'lr': 0.0001081915034000241, 'samples': 20047680, 'steps': 104414, 'loss/train': 1.4241960048675537}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:49 - INFO - __main__ - Step 104419: {'lr': 0.00010817402229220032, 'samples': 20048448, 'steps': 104418, 'loss/train': 1.2136777639389038}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:52 - INFO - __main__ - Step 104424: {'lr': 0.00010815217234528873, 'samples': 20049408, 'steps': 104423, 'loss/train': 1.3389360904693604}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:54 - INFO - __main__ - Step 104428: {'lr': 0.0001081346935382076, 'samples': 20050176, 'steps': 104427, 'loss/train': 1.4679287672042847}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:54 - INFO - __main__ - Step 104428: {'lr': 0.0001081346935382076, 'samples': 20050176, 'steps': 104427, 'loss/train': 1.4679287672042847}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:52:57 - INFO - __main__ - Step 104435: {'lr': 0.00010810410808690076, 'samples': 20051520, 'steps': 104434, 'loss/train': 0.9635074734687805}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:00 - INFO - __main__ - Step 104440: {'lr': 0.00010808226325401082, 'samples': 20052480, 'steps': 104439, 'loss/train': 1.4778292179107666}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:00 - INFO - __main__ - Step 104440: {'lr': 0.00010808226325401082, 'samples': 20052480, 'steps': 104439, 'loss/train': 1.4778292179107666}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:03 - INFO - __main__ - Step 104447: {'lr': 0.00010805168317374972, 'samples': 20053824, 'steps': 104446, 'loss/train': 0.8120316863059998}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:06 - INFO - __main__ - Step 104451: {'lr': 0.00010803421024924246, 'samples': 20054592, 'steps': 104450, 'loss/train': 4.493049144744873}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:07 - INFO - __main__ - Step 104455: {'lr': 0.00010801673834821668, 'samples': 20055360, 'steps': 104454, 'loss/train': 0.7054550647735596}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:10 - INFO - __main__ - Step 104459: {'lr': 0.00010799926747079847, 'samples': 20056128, 'steps': 104458, 'loss/train': 1.3359017372131348}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:12 - INFO - __main__ - Step 104464: {'lr': 0.00010797743031366546, 'samples': 20057088, 'steps': 104463, 'loss/train': 1.4616777896881104}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:14 - INFO - __main__ - Step 104468: {'lr': 0.0001079599617398245, 'samples': 20057856, 'steps': 104467, 'loss/train': 1.3857676982879639}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:16 - INFO - __main__ - Step 104472: {'lr': 0.00010794249419000038, 'samples': 20058624, 'steps': 104471, 'loss/train': 1.4183629751205444}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:16 - INFO - __main__ - Step 104472: {'lr': 0.00010794249419000038, 'samples': 20058624, 'steps': 104471, 'loss/train': 1.4183629751205444}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:19 - INFO - __main__ - Step 104479: {'lr': 0.00010791192844222722, 'samples': 20059968, 'steps': 104478, 'loss/train': 1.3515795469284058}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:22 - INFO - __main__ - Step 104484: {'lr': 0.0001078900976858879, 'samples': 20060928, 'steps': 104483, 'loss/train': 1.9061124324798584}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:24 - INFO - __main__ - Step 104488: {'lr': 0.00010787263423339008, 'samples': 20061696, 'steps': 104487, 'loss/train': 1.0246511697769165}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:26 - INFO - __main__ - Step 104492: {'lr': 0.00010785517180553864, 'samples': 20062464, 'steps': 104491, 'loss/train': 1.2539623975753784}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:27 - INFO - __main__ - Step 104496: {'lr': 0.00010783771040245944, 'samples': 20063232, 'steps': 104495, 'loss/train': 0.7166416049003601}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:30 - INFO - __main__ - Step 104500: {'lr': 0.00010782025002427848, 'samples': 20064000, 'steps': 104499, 'loss/train': 1.0753788948059082}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:32 - INFO - __main__ - Step 104505: {'lr': 0.00010779842599300696, 'samples': 20064960, 'steps': 104504, 'loss/train': 0.6836594343185425}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:32 - INFO - __main__ - Step 104505: {'lr': 0.00010779842599300696, 'samples': 20064960, 'steps': 104504, 'loss/train': 0.6836594343185425}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:36 - INFO - __main__ - Step 104513: {'lr': 0.00010776351087491426, 'samples': 20066496, 'steps': 104512, 'loss/train': 1.6304038763046265}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:38 - INFO - __main__ - Step 104517: {'lr': 0.00010774605485395458, 'samples': 20067264, 'steps': 104516, 'loss/train': 0.6117398142814636}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:40 - INFO - __main__ - Step 104521: {'lr': 0.00010772859985855379, 'samples': 20068032, 'steps': 104520, 'loss/train': 0.7455692887306213}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:42 - INFO - __main__ - Step 104526: {'lr': 0.00010770678255668684, 'samples': 20068992, 'steps': 104525, 'loss/train': 1.8447716236114502}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:42 - INFO - __main__ - Step 104526: {'lr': 0.00010770678255668684, 'samples': 20068992, 'steps': 104525, 'loss/train': 1.8447716236114502}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:46 - INFO - __main__ - Step 104533: {'lr': 0.0001076762410269634, 'samples': 20070336, 'steps': 104532, 'loss/train': 1.0961147546768188}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:48 - INFO - __main__ - Step 104537: {'lr': 0.00010765879013505673, 'samples': 20071104, 'steps': 104536, 'loss/train': 1.278095006942749}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:50 - INFO - __main__ - Step 104541: {'lr': 0.000107641340269338, 'samples': 20071872, 'steps': 104540, 'loss/train': 1.4128048419952393}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:50 - INFO - __main__ - Step 104541: {'lr': 0.000107641340269338, 'samples': 20071872, 'steps': 104540, 'loss/train': 1.4128048419952393}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:50 - INFO - __main__ - Step 104541: {'lr': 0.000107641340269338, 'samples': 20071872, 'steps': 104540, 'loss/train': 1.4128048419952393}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:56 - INFO - __main__ - Step 104552: {'lr': 0.00010759335843092068, 'samples': 20073984, 'steps': 104551, 'loss/train': 1.1244008541107178}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:53:58 - INFO - __main__ - Step 104557: {'lr': 0.00010757155107085951, 'samples': 20074944, 'steps': 104556, 'loss/train': 1.3966730833053589}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:00 - INFO - __main__ - Step 104562: {'lr': 0.00010754974531519995, 'samples': 20075904, 'steps': 104561, 'loss/train': 1.4702919721603394}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:00 - INFO - __main__ - Step 104562: {'lr': 0.00010754974531519995, 'samples': 20075904, 'steps': 104561, 'loss/train': 1.4702919721603394}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:04 - INFO - __main__ - Step 104569: {'lr': 0.00010751921995313876, 'samples': 20077248, 'steps': 104568, 'loss/train': 1.6321765184402466}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:06 - INFO - __main__ - Step 104574: {'lr': 0.00010749741804904494, 'samples': 20078208, 'steps': 104573, 'loss/train': 1.6367374658584595}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:08 - INFO - __main__ - Step 104578: {'lr': 0.00010747997768152845, 'samples': 20078976, 'steps': 104577, 'loss/train': 1.6953941583633423}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:11 - INFO - __main__ - Step 104583: {'lr': 0.00010745817866703741, 'samples': 20079936, 'steps': 104582, 'loss/train': 1.437633752822876}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:13 - INFO - __main__ - Step 104587: {'lr': 0.00010744074061152134, 'samples': 20080704, 'steps': 104586, 'loss/train': 1.6456869840621948}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:15 - INFO - __main__ - Step 104591: {'lr': 0.00010742330358376531, 'samples': 20081472, 'steps': 104590, 'loss/train': 1.165547251701355}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:16 - INFO - __main__ - Step 104595: {'lr': 0.00010740586758389511, 'samples': 20082240, 'steps': 104594, 'loss/train': 0.7972999811172485}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:18 - INFO - __main__ - Step 104599: {'lr': 0.00010738843261203629, 'samples': 20083008, 'steps': 104598, 'loss/train': 1.6667473316192627}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:18 - INFO - __main__ - Step 104599: {'lr': 0.00010738843261203629, 'samples': 20083008, 'steps': 104598, 'loss/train': 1.6667473316192627}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:22 - INFO - __main__ - Step 104606: {'lr': 0.00010735792388531405, 'samples': 20084352, 'steps': 104605, 'loss/train': 0.5924108624458313}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:24 - INFO - __main__ - Step 104610: {'lr': 0.00010734049174113478, 'samples': 20085120, 'steps': 104609, 'loss/train': 1.316432237625122}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:26 - INFO - __main__ - Step 104614: {'lr': 0.0001073230606254383, 'samples': 20085888, 'steps': 104613, 'loss/train': 1.558160662651062}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:26 - INFO - __main__ - Step 104614: {'lr': 0.0001073230606254383, 'samples': 20085888, 'steps': 104613, 'loss/train': 1.558160662651062}}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:30 - INFO - __main__ - Step 104622: {'lr': 0.00010728820147999638, 'samples': 20087424, 'steps': 104621, 'loss/train': 1.6309314966201782}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:32 - INFO - __main__ - Step 104626: {'lr': 0.00010727077345050218, 'samples': 20088192, 'steps': 104625, 'loss/train': 0.5765485167503357}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:34 - INFO - __main__ - Step 104630: {'lr': 0.00010725334644999338, 'samples': 20088960, 'steps': 104629, 'loss/train': 1.4257056713104248}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:34 - INFO - __main__ - Step 104630: {'lr': 0.00010725334644999338, 'samples': 20088960, 'steps': 104629, 'loss/train': 1.4257056713104248}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:38 - INFO - __main__ - Step 104638: {'lr': 0.00010721849553643456, 'samples': 20090496, 'steps': 104637, 'loss/train': 1.0089384317398071}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:40 - INFO - __main__ - Step 104642: {'lr': 0.00010720107162363571, 'samples': 20091264, 'steps': 104641, 'loss/train': 1.0975511074066162}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:42 - INFO - __main__ - Step 104646: {'lr': 0.00010718364874032485, 'samples': 20092032, 'steps': 104645, 'loss/train': 1.175686001777649}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:44 - INFO - __main__ - Step 104651: {'lr': 0.00010716187158409488, 'samples': 20092992, 'steps': 104650, 'loss/train': 1.2820186614990234}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:47 - INFO - __main__ - Step 104656: {'lr': 0.00010714009603688132, 'samples': 20093952, 'steps': 104655, 'loss/train': 1.6349050998687744}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:47 - INFO - __main__ - Step 104656: {'lr': 0.00010714009603688132, 'samples': 20093952, 'steps': 104655, 'loss/train': 1.6349050998687744}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:50 - INFO - __main__ - Step 104663: {'lr': 0.00010710961297439702, 'samples': 20095296, 'steps': 104662, 'loss/train': 1.0149381160736084}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:52 - INFO - __main__ - Step 104667: {'lr': 0.00010709219549795812, 'samples': 20096064, 'steps': 104666, 'loss/train': 1.528607964515686}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:55 - INFO - __main__ - Step 104672: {'lr': 0.00010707042510124545, 'samples': 20097024, 'steps': 104671, 'loss/train': 1.441550850868225}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:57 - INFO - __main__ - Step 104676: {'lr': 0.00010705300994309697, 'samples': 20097792, 'steps': 104675, 'loss/train': 0.685964822769165}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:54:59 - INFO - __main__ - Step 104680: {'lr': 0.00010703559581550382, 'samples': 20098560, 'steps': 104679, 'loss/train': 1.3263862133026123}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:00 - INFO - __main__ - Step 104684: {'lr': 0.00010701818271859154, 'samples': 20099328, 'steps': 104683, 'loss/train': 1.3616509437561035}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:02 - INFO - __main__ - Step 104688: {'lr': 0.00010700077065248573, 'samples': 20100096, 'steps': 104687, 'loss/train': 1.180167555809021}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:05 - INFO - __main__ - Step 104693: {'lr': 0.00010697900701961614, 'samples': 20101056, 'steps': 104692, 'loss/train': 1.3016706705093384}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:07 - INFO - __main__ - Step 104697: {'lr': 0.00010696159727328364, 'samples': 20101824, 'steps': 104696, 'loss/train': 1.549648404121399}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:09 - INFO - __main__ - Step 104701: {'lr': 0.00010694418855816557, 'samples': 20102592, 'steps': 104700, 'loss/train': 1.6700760126113892}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:09 - INFO - __main__ - Step 104701: {'lr': 0.00010694418855816557, 'samples': 20102592, 'steps': 104700, 'loss/train': 1.6700760126113892}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:12 - INFO - __main__ - Step 104708: {'lr': 0.00010691372578844582, 'samples': 20103936, 'steps': 104707, 'loss/train': 0.39238426089286804}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:15 - INFO - __main__ - Step 104713: {'lr': 0.00010689196860135234, 'samples': 20104896, 'steps': 104712, 'loss/train': 1.3064231872558594}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:17 - INFO - __main__ - Step 104717: {'lr': 0.00010687456401234657, 'samples': 20105664, 'steps': 104716, 'loss/train': 1.7955447435379028}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:19 - INFO - __main__ - Step 104721: {'lr': 0.00010685716045518263, 'samples': 20106432, 'steps': 104720, 'loss/train': 1.2124685049057007}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:20 - INFO - __main__ - Step 104725: {'lr': 0.00010683975792998593, 'samples': 20107200, 'steps': 104724, 'loss/train': 1.272539734840393}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:22 - INFO - __main__ - Step 104729: {'lr': 0.00010682235643688207, 'samples': 20107968, 'steps': 104728, 'loss/train': 1.221250295639038}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:25 - INFO - __main__ - Step 104734: {'lr': 0.00010680060602207368, 'samples': 20108928, 'steps': 104733, 'loss/train': 1.4073082208633423}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:27 - INFO - __main__ - Step 104738: {'lr': 0.00010678320685163707, 'samples': 20109696, 'steps': 104737, 'loss/train': 0.9309832453727722}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:27 - INFO - __main__ - Step 104738: {'lr': 0.00010678320685163707, 'samples': 20109696, 'steps': 104737, 'loss/train': 0.9309832453727722}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:30 - INFO - __main__ - Step 104745: {'lr': 0.0001067527607879027, 'samples': 20111040, 'steps': 104744, 'loss/train': 1.2644000053405762}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:32 - INFO - __main__ - Step 104750: {'lr': 0.00010673101553583159, 'samples': 20112000, 'steps': 104749, 'loss/train': 1.609340786933899}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:32 - INFO - __main__ - Step 104750: {'lr': 0.00010673101553583159, 'samples': 20112000, 'steps': 104749, 'loss/train': 1.609340786933899}}}█████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:37 - INFO - __main__ - Step 104758: {'lr': 0.00010669622648946912, 'samples': 20113536, 'steps': 104757, 'loss/train': 0.060806240886449814}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:38 - INFO - __main__ - Step 104762: {'lr': 0.00010667883351591637, 'samples': 20114304, 'steps': 104761, 'loss/train': 1.2115739583969116}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:40 - INFO - __main__ - Step 104766: {'lr': 0.00010666144157561653, 'samples': 20115072, 'steps': 104765, 'loss/train': 1.4246861934661865}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:43 - INFO - __main__ - Step 104771: {'lr': 0.00010663970310344474, 'samples': 20116032, 'steps': 104770, 'loss/train': 1.139891266822815}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:45 - INFO - __main__ - Step 104775: {'lr': 0.00010662231348842232, 'samples': 20116800, 'steps': 104774, 'loss/train': 1.4167135953903198}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:47 - INFO - __main__ - Step 104779: {'lr': 0.00010660492490706031, 'samples': 20117568, 'steps': 104778, 'loss/train': 1.5643082857131958}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:48 - INFO - __main__ - Step 104783: {'lr': 0.0001065875373594841, 'samples': 20118336, 'steps': 104782, 'loss/train': 1.6731202602386475}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:50 - INFO - __main__ - Step 104787: {'lr': 0.00010657015084581886, 'samples': 20119104, 'steps': 104786, 'loss/train': 1.7916730642318726}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:53 - INFO - __main__ - Step 104792: {'lr': 0.00010654841915786579, 'samples': 20120064, 'steps': 104791, 'loss/train': 1.4564460515975952}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:55 - INFO - __main__ - Step 104796: {'lr': 0.00010653103497095887, 'samples': 20120832, 'steps': 104795, 'loss/train': 1.5089120864868164}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:57 - INFO - __main__ - Step 104800: {'lr': 0.0001065136518183703, 'samples': 20121600, 'steps': 104799, 'loss/train': 1.456134557723999}4}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:55:57 - INFO - __main__ - Step 104800: {'lr': 0.0001065136518183703, 'samples': 20121600, 'steps': 104799, 'loss/train': 1.456134557723999}4}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:00 - INFO - __main__ - Step 104807: {'lr': 0.00010648323379054606, 'samples': 20122944, 'steps': 104806, 'loss/train': 1.0816106796264648}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:03 - INFO - __main__ - Step 104812: {'lr': 0.00010646150856776843, 'samples': 20123904, 'steps': 104811, 'loss/train': 1.2322471141815186}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:05 - INFO - __main__ - Step 104817: {'lr': 0.00010643978496189663, 'samples': 20124864, 'steps': 104816, 'loss/train': 0.8320887088775635}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:07 - INFO - __main__ - Step 104821: {'lr': 0.00010642240724153568, 'samples': 20125632, 'steps': 104820, 'loss/train': 1.9116206169128418}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:07 - INFO - __main__ - Step 104821: {'lr': 0.00010642240724153568, 'samples': 20125632, 'steps': 104820, 'loss/train': 1.9116206169128418}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:10 - INFO - __main__ - Step 104828: {'lr': 0.00010639199872169262, 'samples': 20126976, 'steps': 104827, 'loss/train': 1.7246757745742798}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:13 - INFO - __main__ - Step 104833: {'lr': 0.0001063702802915634, 'samples': 20127936, 'steps': 104832, 'loss/train': 1.2807562351226807}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:15 - INFO - __main__ - Step 104838: {'lr': 0.00010634856347936766, 'samples': 20128896, 'steps': 104837, 'loss/train': 1.3638392686843872}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:17 - INFO - __main__ - Step 104842: {'lr': 0.00010633119119468745, 'samples': 20129664, 'steps': 104841, 'loss/train': 0.8512518405914307}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:17 - INFO - __main__ - Step 104842: {'lr': 0.00010633119119468745, 'samples': 20129664, 'steps': 104841, 'loss/train': 0.8512518405914307}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:20 - INFO - __main__ - Step 104849: {'lr': 0.00010630079218886798, 'samples': 20131008, 'steps': 104848, 'loss/train': 1.0222678184509277}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:23 - INFO - __main__ - Step 104853: {'lr': 0.00010628342275282682, 'samples': 20131776, 'steps': 104852, 'loss/train': 1.2125836610794067}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:23 - INFO - __main__ - Step 104853: {'lr': 0.00010628342275282682, 'samples': 20131776, 'steps': 104852, 'loss/train': 1.2125836610794067}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:26 - INFO - __main__ - Step 104860: {'lr': 0.00010625302873295428, 'samples': 20133120, 'steps': 104859, 'loss/train': 0.8120563626289368}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:28 - INFO - __main__ - Step 104864: {'lr': 0.00010623566214649927, 'samples': 20133888, 'steps': 104863, 'loss/train': 1.3154776096343994}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:31 - INFO - __main__ - Step 104869: {'lr': 0.00010621395537094988, 'samples': 20134848, 'steps': 104868, 'loss/train': 1.4448399543762207}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:31 - INFO - __main__ - Step 104869: {'lr': 0.00010621395537094988, 'samples': 20134848, 'steps': 104868, 'loss/train': 1.4448399543762207}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:35 - INFO - __main__ - Step 104877: {'lr': 0.00010617922789913686, 'samples': 20136384, 'steps': 104876, 'loss/train': 1.3904436826705933}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:36 - INFO - __main__ - Step 104881: {'lr': 0.00010616186571844982, 'samples': 20137152, 'steps': 104880, 'loss/train': 1.386563777923584}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:38 - INFO - __main__ - Step 104885: {'lr': 0.00010614450457474267, 'samples': 20137920, 'steps': 104884, 'loss/train': 1.2172988653182983}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:38 - INFO - __main__ - Step 104885: {'lr': 0.00010614450457474267, 'samples': 20137920, 'steps': 104884, 'loss/train': 1.2172988653182983}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:43 - INFO - __main__ - Step 104893: {'lr': 0.0001061097853987688, 'samples': 20139456, 'steps': 104892, 'loss/train': 1.6089067459106445}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:45 - INFO - __main__ - Step 104897: {'lr': 0.00010609242736675231, 'samples': 20140224, 'steps': 104896, 'loss/train': 1.2308640480041504}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:47 - INFO - __main__ - Step 104901: {'lr': 0.0001060750703722164, 'samples': 20140992, 'steps': 104900, 'loss/train': 1.6083855628967285}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:49 - INFO - __main__ - Step 104905: {'lr': 0.00010605771441528602, 'samples': 20141760, 'steps': 104904, 'loss/train': 4.1161885261535645}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:51 - INFO - __main__ - Step 104909: {'lr': 0.00010604035949608643, 'samples': 20142528, 'steps': 104908, 'loss/train': 1.1183736324310303}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:52 - INFO - __main__ - Step 104913: {'lr': 0.0001060230056147427, 'samples': 20143296, 'steps': 104912, 'loss/train': 1.7215162515640259}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:55 - INFO - __main__ - Step 104917: {'lr': 0.00010600565277138008, 'samples': 20144064, 'steps': 104916, 'loss/train': 1.6755871772766113}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:57 - INFO - __main__ - Step 104922: {'lr': 0.00010598396317702802, 'samples': 20145024, 'steps': 104921, 'loss/train': 1.3131749629974365}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:59 - INFO - __main__ - Step 104926: {'lr': 0.00010596661266957991, 'samples': 20145792, 'steps': 104925, 'loss/train': 1.3765596151351929}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:56:59 - INFO - __main__ - Step 104926: {'lr': 0.00010596661266957991, 'samples': 20145792, 'steps': 104925, 'loss/train': 1.3765596151351929}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:02 - INFO - __main__ - Step 104933: {'lr': 0.0001059362517802411, 'samples': 20147136, 'steps': 104932, 'loss/train': 1.4159595966339111}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:05 - INFO - __main__ - Step 104938: {'lr': 0.0001059145673780613, 'samples': 20148096, 'steps': 104937, 'loss/train': 1.2990401983261108}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:07 - INFO - __main__ - Step 104943: {'lr': 0.00010589288459894838, 'samples': 20149056, 'steps': 104942, 'loss/train': 1.5327945947647095}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:09 - INFO - __main__ - Step 104947: {'lr': 0.00010587553954443021, 'samples': 20149824, 'steps': 104946, 'loss/train': 1.5457180738449097}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:09 - INFO - __main__ - Step 104947: {'lr': 0.00010587553954443021, 'samples': 20149824, 'steps': 104946, 'loss/train': 1.5457180738449097}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:13 - INFO - __main__ - Step 104954: {'lr': 0.00010584518819929858, 'samples': 20151168, 'steps': 104953, 'loss/train': 1.7494665384292603}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:15 - INFO - __main__ - Step 104958: {'lr': 0.00010582784600245273, 'samples': 20151936, 'steps': 104957, 'loss/train': 1.504917860031128}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:17 - INFO - __main__ - Step 104962: {'lr': 0.00010581050484499477, 'samples': 20152704, 'steps': 104961, 'loss/train': 1.115997076034546}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:19 - INFO - __main__ - Step 104966: {'lr': 0.00010579316472704974, 'samples': 20153472, 'steps': 104965, 'loss/train': 1.4380515813827515}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:22 - INFO - __main__ - Step 104971: {'lr': 0.0001057714910416242, 'samples': 20154432, 'steps': 104970, 'loss/train': 1.5236109495162964}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:22 - INFO - __main__ - Step 104971: {'lr': 0.0001057714910416242, 'samples': 20154432, 'steps': 104970, 'loss/train': 1.5236109495162964}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:22 - INFO - __main__ - Step 104971: {'lr': 0.0001057714910416242, 'samples': 20154432, 'steps': 104970, 'loss/train': 1.5236109495162964}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:27 - INFO - __main__ - Step 104981: {'lr': 0.00010572814854505252, 'samples': 20156352, 'steps': 104980, 'loss/train': 0.3743956685066223}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:29 - INFO - __main__ - Step 104987: {'lr': 0.00010570214616730478, 'samples': 20157504, 'steps': 104986, 'loss/train': 1.4483401775360107}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:31 - INFO - __main__ - Step 104991: {'lr': 0.00010568481254914793, 'samples': 20158272, 'steps': 104990, 'loss/train': 1.296118974685669}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:31 - INFO - __main__ - Step 104991: {'lr': 0.00010568481254914793, 'samples': 20158272, 'steps': 104990, 'loss/train': 1.296118974685669}}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:35 - INFO - __main__ - Step 104998: {'lr': 0.00010565448122095725, 'samples': 20159616, 'steps': 104997, 'loss/train': 1.1247024536132812}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:35 - INFO - __main__ - Step 104998: {'lr': 0.00010565448122095725, 'samples': 20159616, 'steps': 104997, 'loss/train': 1.1247024536132812}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:35 - INFO - __main__ - Step 104998: {'lr': 0.00010565448122095725, 'samples': 20159616, 'steps': 104997, 'loss/train': 1.1247024536132812}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +11/07/2021 11:57:35 - INFO - __main__ - Step 104998: {'lr': 0.00010565448122095725, 'samples': 20159616, 'steps': 104997, 'loss/train': 1.1247024536132812}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... +To disable this warning, you can either: + - Avoid using `tokenizers` before the fork if possible + - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) +11/07/2021 11:57:35 - INFO - __main__ - Step 104998: {'lr': 0.00010565448122095725, 'samples': 20159616, 'steps': 104997, 'loss/train': 1.1247024536132812}4}████████████████████████| 27.8M/27.8M [00:24<00:00, 1.21MB/s] +huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... +To disable this warning, you can either: + - Avoid using `tokenizers` before the fork if possible + - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) +huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... +To disable this warning, you can either: + - Avoid using `tokenizers` before the fork if possible + - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) +huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... +To disable this warning, you can either: + - Avoid using `tokenizers` before the fork if possible + - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) +huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... +To disable this warning, you can either: + - Avoid using `tokenizers` before the fork if possible + - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) +huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... +To disable this warning, you can either: + - Avoid using `tokenizers` before the fork if possible + - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) +huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... +To disable this warning, you can either: + - Avoid using `tokenizers` before the fork if possible + - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) +huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... To disable this warning, you can either: - Avoid using `tokenizers` before the fork if possible