| { | |
| "best_metric": 0.15065895020961761, | |
| "best_model_checkpoint": "saves/psy-course-info/Llama3-OpenBioLLM-8B/train/fold1/checkpoint-90", | |
| "epoch": 4.938271604938271, | |
| "eval_steps": 10, | |
| "global_step": 125, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03950617283950617, | |
| "grad_norm": 3.0266354084014893, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.8044, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 2.7545979022979736, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 1.0543, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 3.436570405960083, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.9637, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 3.260969638824463, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.9253, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 3.48811411857605, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 1.0063, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 3.1750481128692627, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.9354, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 2.6605045795440674, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.7956, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 1.8658115863800049, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.7156, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 1.9442992210388184, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.7273, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 1.4981564283370972, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.5198, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.5015671849250793, | |
| "eval_runtime": 19.3011, | |
| "eval_samples_per_second": 2.331, | |
| "eval_steps_per_second": 2.331, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 1.3176920413970947, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.4448, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 1.4542604684829712, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.5058, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 1.2523777484893799, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4258, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 1.061900019645691, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.2848, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 1.009539008140564, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.3333, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 1.0671191215515137, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.3718, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.9506099820137024, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.232, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 1.0324467420578003, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.2587, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.7604952454566956, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.2877, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.9865992069244385, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.255, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.24946804344654083, | |
| "eval_runtime": 19.2039, | |
| "eval_samples_per_second": 2.343, | |
| "eval_steps_per_second": 2.343, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.6814547181129456, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.2186, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.6453701853752136, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.2174, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.6355133056640625, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.1912, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.6928957104682922, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.2412, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.6595496535301208, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.2774, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 1.4999443292617798, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.3648, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.5701374411582947, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1664, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.6932143568992615, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.2712, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.5702258944511414, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.1666, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.6305382251739502, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.2111, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.20211933553218842, | |
| "eval_runtime": 19.2511, | |
| "eval_samples_per_second": 2.338, | |
| "eval_steps_per_second": 2.338, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.6781132221221924, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.1878, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.7474590539932251, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.2222, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.6464303731918335, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.2205, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.6342009902000427, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1516, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.5502495765686035, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.1929, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.9800194501876831, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.1887, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.4909915328025818, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.1198, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.5605656504631042, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.1327, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 1.0153040885925293, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.2028, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.6423051953315735, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.1268, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.17976433038711548, | |
| "eval_runtime": 19.2355, | |
| "eval_samples_per_second": 2.339, | |
| "eval_steps_per_second": 2.339, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.7444939613342285, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1904, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.5496087670326233, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.1364, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.6592587232589722, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.1524, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.6778094172477722, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.1444, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.8962506651878357, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.2192, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.6817356944084167, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.1513, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.6316496729850769, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.1405, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.6903754472732544, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1162, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.7566717267036438, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.2169, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.6865474581718445, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.122, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.16953954100608826, | |
| "eval_runtime": 19.2378, | |
| "eval_samples_per_second": 2.339, | |
| "eval_steps_per_second": 2.339, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 1.2375051975250244, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.226, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.6000056862831116, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.0914, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.5429364442825317, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.1101, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.6248661279678345, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.1528, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.6743581295013428, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1233, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.7042228579521179, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.1189, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.48001235723495483, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.0855, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.6637732982635498, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.0977, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.5641061067581177, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0843, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.6591428518295288, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0984, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.16232524812221527, | |
| "eval_runtime": 19.2267, | |
| "eval_samples_per_second": 2.34, | |
| "eval_steps_per_second": 2.34, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.6936379075050354, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0997, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.8590863943099976, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.1849, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.8724762201309204, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.1388, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.7268065810203552, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.1579, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.6837067604064941, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.1277, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.584983229637146, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0922, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.73332279920578, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.1113, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.5340074896812439, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0899, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.618689775466919, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0749, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.5566624402999878, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0732, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.1524766981601715, | |
| "eval_runtime": 19.2317, | |
| "eval_samples_per_second": 2.34, | |
| "eval_steps_per_second": 2.34, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.571286141872406, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0796, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.6639549136161804, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.1408, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.8859966993331909, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.1507, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.6509288549423218, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.1063, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.813045859336853, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.1217, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 1.411219835281372, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.218, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.49604693055152893, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0683, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.6909966468811035, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0829, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.6037319302558899, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.1044, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.5923836827278137, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0726, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.1539728194475174, | |
| "eval_runtime": 19.2384, | |
| "eval_samples_per_second": 2.339, | |
| "eval_steps_per_second": 2.339, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.55913907289505, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0828, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.5650818943977356, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0742, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.7615413069725037, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.072, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.5601615905761719, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0921, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.7153237462043762, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0752, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.6471256017684937, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0871, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.6173242926597595, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0874, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.5788525938987732, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0781, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.5925896763801575, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0736, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.5686795711517334, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0705, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.15065895020961761, | |
| "eval_runtime": 19.2412, | |
| "eval_samples_per_second": 2.339, | |
| "eval_steps_per_second": 2.339, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.715358555316925, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.1066, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.6285521388053894, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0742, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.7287279367446899, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.076, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.584709107875824, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0787, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.5803191661834717, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0657, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.6027998924255371, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0774, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.6973051428794861, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0817, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.6387346386909485, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0588, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.6541065573692322, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0782, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.6163211464881897, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.097, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.15166276693344116, | |
| "eval_runtime": 19.2442, | |
| "eval_samples_per_second": 2.338, | |
| "eval_steps_per_second": 2.338, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.834725558757782, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0834, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 1.2114893198013306, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.1065, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.4666559398174286, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0553, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.8054733872413635, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0724, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.45573511719703674, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.046, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.6370751857757568, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0771, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.5112573504447937, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0621, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.5506611466407776, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0742, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.6445054411888123, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0732, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.5202900171279907, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0495, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.15176202356815338, | |
| "eval_runtime": 19.2575, | |
| "eval_samples_per_second": 2.337, | |
| "eval_steps_per_second": 2.337, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.5771532654762268, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0736, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.5677194595336914, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0663, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.42305389046669006, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0411, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.5345879197120667, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.059, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.4867326617240906, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0513, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.5048791766166687, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0545, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.5188657641410828, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0515, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.49358126521110535, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0576, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.5929109454154968, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0709, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.6397348642349243, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0504, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.15273258090019226, | |
| "eval_runtime": 19.2601, | |
| "eval_samples_per_second": 2.336, | |
| "eval_steps_per_second": 2.336, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.6079633235931396, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0519, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.5618969798088074, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0844, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.738714337348938, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.0745, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.6914772391319275, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0692, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.6855793595314026, | |
| "learning_rate": 0.0, | |
| "loss": 0.0743, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.2628188898630042e+17, | |
| "train_loss": 0.19368722805380822, | |
| "train_runtime": 3339.1879, | |
| "train_samples_per_second": 0.606, | |
| "train_steps_per_second": 0.037 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 125, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.2628188898630042e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |