| { | |
| "best_metric": 0.07105293869972229, | |
| "best_model_checkpoint": "saves/psy-course-doc/Qwen2.5-7B-Instruct/train/fold8/checkpoint-120", | |
| "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": 0.1868298202753067, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.2309, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.18279753625392914, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.2478, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.21671271324157715, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.2279, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.18672101199626923, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.262, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.16858762502670288, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.2781, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.22064264118671417, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.1929, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.17838694155216217, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.2836, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.18181541562080383, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.2072, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.16831634938716888, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.2313, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.17103101313114166, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.1678, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.18528540432453156, | |
| "eval_runtime": 21.7653, | |
| "eval_samples_per_second": 2.068, | |
| "eval_steps_per_second": 2.068, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.17013779282569885, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.2071, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.1327929049730301, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.1534, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.10475656390190125, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1688, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.09205988794565201, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.1518, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.09766896814107895, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.1421, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.11214997619390488, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.1588, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.09874926507472992, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.1752, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.11309217661619186, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.1958, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.09698560833930969, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.1521, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.09516795724630356, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.2057, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.12000219523906708, | |
| "eval_runtime": 21.7681, | |
| "eval_samples_per_second": 2.067, | |
| "eval_steps_per_second": 2.067, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.11490920931100845, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.1248, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.09830869734287262, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.1291, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.09417690336704254, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.1249, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.10335355997085571, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.1216, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.08114749938249588, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.1275, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.18091371655464172, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.271, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.06726603955030441, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0833, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.08096066862344742, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.1421, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.07401004433631897, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.1404, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.0746835395693779, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.0673, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.09145325422286987, | |
| "eval_runtime": 21.7763, | |
| "eval_samples_per_second": 2.066, | |
| "eval_steps_per_second": 2.066, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.06728620827198029, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.0526, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.07975295931100845, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.1593, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.05279506370425224, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.0579, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.07161711901426315, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1076, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.07799088209867477, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.1208, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.08278154581785202, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.1284, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.08736036717891693, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.105, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.09331925958395004, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.0793, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.08145543932914734, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.1009, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.07455835491418839, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.0982, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.08214997500181198, | |
| "eval_runtime": 21.7939, | |
| "eval_samples_per_second": 2.065, | |
| "eval_steps_per_second": 2.065, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.08338115364313126, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1039, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.06493010371923447, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.0918, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.06883358955383301, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.1034, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.0772809311747551, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.127, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.06465648114681244, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.0396, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.05760206654667854, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.0637, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.08240170031785965, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.1835, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.06131649389863014, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0865, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.05616225302219391, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.0581, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.06130716949701309, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.0891, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.0771004855632782, | |
| "eval_runtime": 21.7453, | |
| "eval_samples_per_second": 2.069, | |
| "eval_steps_per_second": 2.069, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.1203281581401825, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.1239, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.05960683524608612, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.0792, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.0512566901743412, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0634, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.06991548091173172, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.1574, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.06921303272247314, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1217, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.07973436266183853, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.1404, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.06023266166448593, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.1042, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.06274905800819397, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.099, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.06198497861623764, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0401, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.061861295253038406, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0763, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.07488537579774857, | |
| "eval_runtime": 21.7372, | |
| "eval_samples_per_second": 2.07, | |
| "eval_steps_per_second": 2.07, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.06693781167268753, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0948, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.04852902889251709, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0565, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.0796937495470047, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.0929, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.0650988221168518, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0439, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.07308197021484375, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0784, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.06614898145198822, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.062, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.06226956099271774, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.1083, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.06937666982412338, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0661, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.07096434384584427, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0883, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.07018528878688812, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0509, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.07292327284812927, | |
| "eval_runtime": 21.7309, | |
| "eval_samples_per_second": 2.071, | |
| "eval_steps_per_second": 2.071, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.04997608810663223, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0549, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.0775761529803276, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.1306, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.05562743544578552, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.072, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.07207901775836945, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0578, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.05793574079871178, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0531, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.15450118482112885, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.2015, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.06680703908205032, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.1108, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.07221418619155884, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0599, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.08308330923318863, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0825, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.08082571625709534, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0463, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.07214194536209106, | |
| "eval_runtime": 21.7346, | |
| "eval_samples_per_second": 2.07, | |
| "eval_steps_per_second": 2.07, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.07321686297655106, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0983, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.05445065349340439, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0576, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.08311997354030609, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0711, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.06639759987592697, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0702, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.07754135876893997, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.1092, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.05395815521478653, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0483, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.05955814570188522, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0425, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.06142286956310272, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.1308, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.05392776429653168, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0543, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.07074186205863953, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0305, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.07150960713624954, | |
| "eval_runtime": 21.753, | |
| "eval_samples_per_second": 2.069, | |
| "eval_steps_per_second": 2.069, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.07016747444868088, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.0483, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.06681767851114273, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0769, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.06709405034780502, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0661, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.0665164664387703, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.112, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.0771573930978775, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0793, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.062010809779167175, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0254, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.07360262423753738, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0921, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.07366364449262619, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.1451, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.07421759516000748, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.1039, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.05935444310307503, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0505, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.07133489102125168, | |
| "eval_runtime": 21.7373, | |
| "eval_samples_per_second": 2.07, | |
| "eval_steps_per_second": 2.07, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.09624148905277252, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.144, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.12751835584640503, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.1655, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.07455002516508102, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.1134, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.06696426123380661, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0481, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.06412757933139801, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0808, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.06346351653337479, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0488, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.06537764519453049, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0194, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.056524328887462616, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0253, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.062042903155088425, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.1144, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.059958767145872116, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0645, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.07106943428516388, | |
| "eval_runtime": 21.7532, | |
| "eval_samples_per_second": 2.069, | |
| "eval_steps_per_second": 2.069, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.060797806829214096, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.094, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.056455742567777634, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0744, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.06785272806882858, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0933, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.06774047017097473, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0541, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.05584665387868881, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0748, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.07345107942819595, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0781, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.0609910674393177, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.1058, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.08062499016523361, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1542, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.06287279725074768, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0482, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.07574119418859482, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0858, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.07105293869972229, | |
| "eval_runtime": 21.7278, | |
| "eval_samples_per_second": 2.071, | |
| "eval_steps_per_second": 2.071, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.07911939918994904, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0174, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.06001194566488266, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0623, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.054641127586364746, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.0797, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.07878218591213226, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0763, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.06516701728105545, | |
| "learning_rate": 0.0, | |
| "loss": 0.1182, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.4521433822274355e+17, | |
| "train_loss": 0.10799009439349175, | |
| "train_runtime": 3470.8125, | |
| "train_samples_per_second": 0.583, | |
| "train_steps_per_second": 0.036 | |
| } | |
| ], | |
| "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": 1.4521433822274355e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |