| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 902, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011092623405435386, | |
| "grad_norm": 2.009918689727783, | |
| "learning_rate": 1.998002219755827e-05, | |
| "loss": 0.5022, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.022185246810870772, | |
| "grad_norm": 0.49915584921836853, | |
| "learning_rate": 1.995782463928968e-05, | |
| "loss": 0.1943, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.033277870216306155, | |
| "grad_norm": 0.47061625123023987, | |
| "learning_rate": 1.993562708102109e-05, | |
| "loss": 0.1436, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.044370493621741544, | |
| "grad_norm": 0.2260124832391739, | |
| "learning_rate": 1.99134295227525e-05, | |
| "loss": 0.1106, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05546311702717693, | |
| "grad_norm": 0.31766048073768616, | |
| "learning_rate": 1.989123196448391e-05, | |
| "loss": 0.0994, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06655574043261231, | |
| "grad_norm": 0.2788391709327698, | |
| "learning_rate": 1.9869034406215316e-05, | |
| "loss": 0.111, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0776483638380477, | |
| "grad_norm": 0.24376386404037476, | |
| "learning_rate": 1.9846836847946726e-05, | |
| "loss": 0.0849, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08874098724348309, | |
| "grad_norm": 0.1789788454771042, | |
| "learning_rate": 1.982463928967814e-05, | |
| "loss": 0.0971, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09983361064891846, | |
| "grad_norm": 0.29698437452316284, | |
| "learning_rate": 1.9802441731409546e-05, | |
| "loss": 0.0856, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.11092623405435385, | |
| "grad_norm": 0.2553412616252899, | |
| "learning_rate": 1.9780244173140956e-05, | |
| "loss": 0.0976, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.12201885745978924, | |
| "grad_norm": 0.20608791708946228, | |
| "learning_rate": 1.9758046614872365e-05, | |
| "loss": 0.0947, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.13311148086522462, | |
| "grad_norm": 0.23551669716835022, | |
| "learning_rate": 1.9735849056603775e-05, | |
| "loss": 0.0965, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.14420410427066002, | |
| "grad_norm": 0.3207148611545563, | |
| "learning_rate": 1.9713651498335185e-05, | |
| "loss": 0.0931, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1552967276760954, | |
| "grad_norm": 0.34813177585601807, | |
| "learning_rate": 1.9691453940066595e-05, | |
| "loss": 0.1, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.16638935108153077, | |
| "grad_norm": 0.41501104831695557, | |
| "learning_rate": 1.9669256381798e-05, | |
| "loss": 0.0922, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17748197448696618, | |
| "grad_norm": 0.24550506472587585, | |
| "learning_rate": 1.964705882352941e-05, | |
| "loss": 0.0857, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.18857459789240155, | |
| "grad_norm": 0.4205056130886078, | |
| "learning_rate": 1.9624861265260825e-05, | |
| "loss": 0.0831, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.19966722129783693, | |
| "grad_norm": 0.6002993583679199, | |
| "learning_rate": 1.9602663706992235e-05, | |
| "loss": 0.0792, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.21075984470327233, | |
| "grad_norm": 0.27535638213157654, | |
| "learning_rate": 1.958046614872364e-05, | |
| "loss": 0.0786, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2218524681087077, | |
| "grad_norm": 0.41602805256843567, | |
| "learning_rate": 1.955826859045505e-05, | |
| "loss": 0.0789, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23294509151414308, | |
| "grad_norm": 0.41827332973480225, | |
| "learning_rate": 1.953607103218646e-05, | |
| "loss": 0.0663, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.24403771491957849, | |
| "grad_norm": 0.47976112365722656, | |
| "learning_rate": 1.951387347391787e-05, | |
| "loss": 0.0727, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.25513033832501386, | |
| "grad_norm": 0.7771281599998474, | |
| "learning_rate": 1.949167591564928e-05, | |
| "loss": 0.0776, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.26622296173044924, | |
| "grad_norm": 1.0573914051055908, | |
| "learning_rate": 1.946947835738069e-05, | |
| "loss": 0.0828, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2773155851358846, | |
| "grad_norm": 0.5186040997505188, | |
| "learning_rate": 1.9447280799112097e-05, | |
| "loss": 0.0767, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28840820854132004, | |
| "grad_norm": 0.5594862699508667, | |
| "learning_rate": 1.942508324084351e-05, | |
| "loss": 0.0699, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2995008319467554, | |
| "grad_norm": 0.5147818922996521, | |
| "learning_rate": 1.940288568257492e-05, | |
| "loss": 0.0591, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.3105934553521908, | |
| "grad_norm": 0.5510437488555908, | |
| "learning_rate": 1.938068812430633e-05, | |
| "loss": 0.0761, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.32168607875762617, | |
| "grad_norm": 0.4817625880241394, | |
| "learning_rate": 1.9358490566037736e-05, | |
| "loss": 0.0688, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.33277870216306155, | |
| "grad_norm": 0.504362940788269, | |
| "learning_rate": 1.9336293007769146e-05, | |
| "loss": 0.0691, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.343871325568497, | |
| "grad_norm": 0.5732384920120239, | |
| "learning_rate": 1.9314095449500556e-05, | |
| "loss": 0.057, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.35496394897393235, | |
| "grad_norm": 0.5892298221588135, | |
| "learning_rate": 1.9291897891231966e-05, | |
| "loss": 0.059, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.36605657237936773, | |
| "grad_norm": 0.3680512309074402, | |
| "learning_rate": 1.9269700332963376e-05, | |
| "loss": 0.0706, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.3771491957848031, | |
| "grad_norm": 0.41971662640571594, | |
| "learning_rate": 1.9247502774694786e-05, | |
| "loss": 0.053, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3882418191902385, | |
| "grad_norm": 0.37261390686035156, | |
| "learning_rate": 1.9225305216426195e-05, | |
| "loss": 0.0632, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.39933444259567386, | |
| "grad_norm": 0.48256734013557434, | |
| "learning_rate": 1.9203107658157605e-05, | |
| "loss": 0.0651, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4104270660011093, | |
| "grad_norm": 0.7914339303970337, | |
| "learning_rate": 1.9180910099889015e-05, | |
| "loss": 0.0659, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.42151968940654466, | |
| "grad_norm": 0.6772429347038269, | |
| "learning_rate": 1.915871254162042e-05, | |
| "loss": 0.0655, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.43261231281198004, | |
| "grad_norm": 0.5621687173843384, | |
| "learning_rate": 1.913651498335183e-05, | |
| "loss": 0.0707, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.4437049362174154, | |
| "grad_norm": 0.30515748262405396, | |
| "learning_rate": 1.911431742508324e-05, | |
| "loss": 0.0548, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4547975596228508, | |
| "grad_norm": 0.5506859421730042, | |
| "learning_rate": 1.909211986681465e-05, | |
| "loss": 0.0554, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.46589018302828616, | |
| "grad_norm": 0.6387749314308167, | |
| "learning_rate": 1.906992230854606e-05, | |
| "loss": 0.0554, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4769828064337216, | |
| "grad_norm": 0.18500734865665436, | |
| "learning_rate": 1.904772475027747e-05, | |
| "loss": 0.0558, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.48807542983915697, | |
| "grad_norm": 0.6815407276153564, | |
| "learning_rate": 1.902552719200888e-05, | |
| "loss": 0.0537, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.49916805324459235, | |
| "grad_norm": 0.4826994836330414, | |
| "learning_rate": 1.900332963374029e-05, | |
| "loss": 0.0567, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5102606766500277, | |
| "grad_norm": 0.24618124961853027, | |
| "learning_rate": 1.89811320754717e-05, | |
| "loss": 0.0614, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5213533000554631, | |
| "grad_norm": 1.0037415027618408, | |
| "learning_rate": 1.895893451720311e-05, | |
| "loss": 0.0604, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.5324459234608985, | |
| "grad_norm": 0.6000948548316956, | |
| "learning_rate": 1.8936736958934517e-05, | |
| "loss": 0.0683, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5435385468663338, | |
| "grad_norm": 0.3302474319934845, | |
| "learning_rate": 1.8914539400665927e-05, | |
| "loss": 0.0543, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5546311702717692, | |
| "grad_norm": 0.5560783743858337, | |
| "learning_rate": 1.8892341842397337e-05, | |
| "loss": 0.0569, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5657237936772047, | |
| "grad_norm": 0.8041097521781921, | |
| "learning_rate": 1.8870144284128747e-05, | |
| "loss": 0.0544, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.5768164170826401, | |
| "grad_norm": 0.6846103668212891, | |
| "learning_rate": 1.8847946725860156e-05, | |
| "loss": 0.058, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5879090404880755, | |
| "grad_norm": 0.50434809923172, | |
| "learning_rate": 1.8825749167591566e-05, | |
| "loss": 0.0654, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5990016638935108, | |
| "grad_norm": 0.54362553358078, | |
| "learning_rate": 1.8803551609322976e-05, | |
| "loss": 0.0582, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6100942872989462, | |
| "grad_norm": 0.6166839599609375, | |
| "learning_rate": 1.8781354051054386e-05, | |
| "loss": 0.0672, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6211869107043816, | |
| "grad_norm": 0.4353054165840149, | |
| "learning_rate": 1.8759156492785796e-05, | |
| "loss": 0.0532, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.632279534109817, | |
| "grad_norm": 0.6025580167770386, | |
| "learning_rate": 1.8736958934517206e-05, | |
| "loss": 0.0746, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.6433721575152523, | |
| "grad_norm": 0.7259892225265503, | |
| "learning_rate": 1.8714761376248612e-05, | |
| "loss": 0.0642, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.6544647809206877, | |
| "grad_norm": 0.4940318465232849, | |
| "learning_rate": 1.8692563817980022e-05, | |
| "loss": 0.0547, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.6655574043261231, | |
| "grad_norm": 0.7005699872970581, | |
| "learning_rate": 1.8670366259711435e-05, | |
| "loss": 0.0522, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6766500277315585, | |
| "grad_norm": 0.4530707895755768, | |
| "learning_rate": 1.8648168701442845e-05, | |
| "loss": 0.054, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.687742651136994, | |
| "grad_norm": 0.9097110629081726, | |
| "learning_rate": 1.8625971143174252e-05, | |
| "loss": 0.0622, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.6988352745424293, | |
| "grad_norm": 0.5374599695205688, | |
| "learning_rate": 1.860377358490566e-05, | |
| "loss": 0.0522, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.7099278979478647, | |
| "grad_norm": 0.3849945664405823, | |
| "learning_rate": 1.858157602663707e-05, | |
| "loss": 0.0571, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.7210205213533001, | |
| "grad_norm": 0.5918008685112, | |
| "learning_rate": 1.855937846836848e-05, | |
| "loss": 0.0576, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.7321131447587355, | |
| "grad_norm": 0.3229956030845642, | |
| "learning_rate": 1.853718091009989e-05, | |
| "loss": 0.0537, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.7432057681641708, | |
| "grad_norm": 0.5264039039611816, | |
| "learning_rate": 1.85149833518313e-05, | |
| "loss": 0.06, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.7542983915696062, | |
| "grad_norm": 0.36795660853385925, | |
| "learning_rate": 1.8492785793562708e-05, | |
| "loss": 0.0511, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.7653910149750416, | |
| "grad_norm": 0.5905130505561829, | |
| "learning_rate": 1.847058823529412e-05, | |
| "loss": 0.0636, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.776483638380477, | |
| "grad_norm": 0.36266571283340454, | |
| "learning_rate": 1.844839067702553e-05, | |
| "loss": 0.0598, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7875762617859123, | |
| "grad_norm": 0.4978592097759247, | |
| "learning_rate": 1.8426193118756937e-05, | |
| "loss": 0.0607, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.7986688851913477, | |
| "grad_norm": 0.4635021686553955, | |
| "learning_rate": 1.8403995560488347e-05, | |
| "loss": 0.0543, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.8097615085967831, | |
| "grad_norm": 0.44571858644485474, | |
| "learning_rate": 1.8381798002219757e-05, | |
| "loss": 0.0678, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.8208541320022186, | |
| "grad_norm": 0.8265877366065979, | |
| "learning_rate": 1.8359600443951167e-05, | |
| "loss": 0.0552, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.831946755407654, | |
| "grad_norm": 0.5776472091674805, | |
| "learning_rate": 1.8337402885682577e-05, | |
| "loss": 0.0505, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.8430393788130893, | |
| "grad_norm": 0.299274742603302, | |
| "learning_rate": 1.8315205327413986e-05, | |
| "loss": 0.0619, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.8541320022185247, | |
| "grad_norm": 0.587645947933197, | |
| "learning_rate": 1.8293007769145393e-05, | |
| "loss": 0.0575, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.8652246256239601, | |
| "grad_norm": 0.39164137840270996, | |
| "learning_rate": 1.8270810210876806e-05, | |
| "loss": 0.0458, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.8763172490293955, | |
| "grad_norm": 0.4663292169570923, | |
| "learning_rate": 1.8248612652608216e-05, | |
| "loss": 0.048, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.8874098724348308, | |
| "grad_norm": 0.5804581642150879, | |
| "learning_rate": 1.8226415094339626e-05, | |
| "loss": 0.0557, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8985024958402662, | |
| "grad_norm": 0.4279440939426422, | |
| "learning_rate": 1.8204217536071032e-05, | |
| "loss": 0.051, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.9095951192457016, | |
| "grad_norm": 0.5384302735328674, | |
| "learning_rate": 1.8182019977802442e-05, | |
| "loss": 0.0558, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.920687742651137, | |
| "grad_norm": 0.5049973726272583, | |
| "learning_rate": 1.8159822419533852e-05, | |
| "loss": 0.047, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.9317803660565723, | |
| "grad_norm": 0.8061177134513855, | |
| "learning_rate": 1.8137624861265262e-05, | |
| "loss": 0.0572, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.9428729894620078, | |
| "grad_norm": 0.6056540012359619, | |
| "learning_rate": 1.8115427302996672e-05, | |
| "loss": 0.0539, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.9539656128674432, | |
| "grad_norm": 0.3001384139060974, | |
| "learning_rate": 1.8093229744728082e-05, | |
| "loss": 0.053, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.9650582362728786, | |
| "grad_norm": 0.6709749102592468, | |
| "learning_rate": 1.807103218645949e-05, | |
| "loss": 0.0526, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.9761508596783139, | |
| "grad_norm": 0.8233507871627808, | |
| "learning_rate": 1.80488346281909e-05, | |
| "loss": 0.0621, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.9872434830837493, | |
| "grad_norm": 0.5757150650024414, | |
| "learning_rate": 1.802663706992231e-05, | |
| "loss": 0.0546, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.9983361064891847, | |
| "grad_norm": 0.6834889054298401, | |
| "learning_rate": 1.800443951165372e-05, | |
| "loss": 0.0462, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8720027017899359, | |
| "eval_f1": 0.5678449258836944, | |
| "eval_loss": 0.34414270520210266, | |
| "eval_precision": 0.7929936305732485, | |
| "eval_recall": 0.4422735346358792, | |
| "eval_runtime": 2.727, | |
| "eval_samples_per_second": 361.937, | |
| "eval_steps_per_second": 11.368, | |
| "step": 902 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 9010, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9622905843747798.0, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |