| { | |
| "best_metric": 0.0614437460899353, | |
| "best_model_checkpoint": "saves/psy-course-doc-info/Llama-3.1-8B-Instruct/train/fold5/checkpoint-110", | |
| "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": 0.4104160666465759, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.3524, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.4222511053085327, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.3604, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.4528347849845886, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.3911, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.34735360741615295, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.3148, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.42906707525253296, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.351, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.4764420688152313, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.35, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.4587888717651367, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.3345, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.41820383071899414, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.302, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.38304615020751953, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.2891, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.4108593463897705, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.2537, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.272151917219162, | |
| "eval_runtime": 30.4673, | |
| "eval_samples_per_second": 1.477, | |
| "eval_steps_per_second": 1.477, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.5432822704315186, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.27, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.549644947052002, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.2584, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.5306810140609741, | |
| "learning_rate": 0.0001, | |
| "loss": 0.254, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.3548853397369385, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.2318, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.3058301508426666, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.2017, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.4197262227535248, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.2052, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.3757355511188507, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.1776, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.3411768078804016, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.1889, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.3357405662536621, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.1703, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.26065245270729065, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.1476, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.1518031656742096, | |
| "eval_runtime": 30.2735, | |
| "eval_samples_per_second": 1.486, | |
| "eval_steps_per_second": 1.486, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.20792262256145477, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.1431, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.37166184186935425, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.1358, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.4214726984500885, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.1448, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.3889068067073822, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.1253, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.26998522877693176, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.1356, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.4674984812736511, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.2001, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.28575921058654785, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1085, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.29869183897972107, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.1239, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.3498165011405945, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.114, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.25564539432525635, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.0956, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.10986688733100891, | |
| "eval_runtime": 30.2855, | |
| "eval_samples_per_second": 1.486, | |
| "eval_steps_per_second": 1.486, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.1968832015991211, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.0801, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.27864232659339905, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.0944, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.21983446180820465, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.0962, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.3046473264694214, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1179, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.31073394417762756, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.1155, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.3046381175518036, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.1016, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.293750524520874, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.0948, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.25460678339004517, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.0902, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.38608038425445557, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.0967, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.22034339606761932, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.0829, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.0902557298541069, | |
| "eval_runtime": 30.2638, | |
| "eval_samples_per_second": 1.487, | |
| "eval_steps_per_second": 1.487, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.20284916460514069, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0676, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.25570327043533325, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.0934, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.2329011708498001, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.0663, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.31940925121307373, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.1042, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.19122415781021118, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.0561, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.2673824429512024, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.0803, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.2752120792865753, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.0865, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.21201737225055695, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0721, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.2631378173828125, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.0834, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.20114241540431976, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.07, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.07789895683526993, | |
| "eval_runtime": 30.2861, | |
| "eval_samples_per_second": 1.486, | |
| "eval_steps_per_second": 1.486, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.33843809366226196, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.1099, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.20786449313163757, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.0655, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.23501335084438324, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0516, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.25182685256004333, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.063, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.26829418540000916, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.072, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.2456829994916916, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.0639, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.21625754237174988, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.0613, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.27295294404029846, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.0729, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.23634514212608337, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.059, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.21690741181373596, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0664, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.07125767320394516, | |
| "eval_runtime": 30.279, | |
| "eval_samples_per_second": 1.486, | |
| "eval_steps_per_second": 1.486, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.22500324249267578, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0658, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.22004781663417816, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0561, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.39001134037971497, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.0575, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.20158539712429047, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0497, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.2276362031698227, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0621, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.24017484486103058, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0619, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.2285294234752655, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.0639, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.18061533570289612, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0451, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.18759796023368835, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0487, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.24042659997940063, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0584, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.06725884228944778, | |
| "eval_runtime": 30.218, | |
| "eval_samples_per_second": 1.489, | |
| "eval_steps_per_second": 1.489, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.2368227243423462, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.058, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.21359050273895264, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.0678, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.18271395564079285, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0454, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.193449929356575, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0611, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.21560706198215485, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0561, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.35089680552482605, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0981, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.1758938729763031, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0457, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.2086019665002823, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0563, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.15222765505313873, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0448, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.22839152812957764, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0521, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.0648355558514595, | |
| "eval_runtime": 30.2677, | |
| "eval_samples_per_second": 1.487, | |
| "eval_steps_per_second": 1.487, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.16493357717990875, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0477, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.2016870081424713, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0502, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.1723877191543579, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0476, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.1821114420890808, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0426, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.15526282787322998, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0494, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.19435639679431915, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0458, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.15111303329467773, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0443, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.2207111120223999, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0458, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.16492444276809692, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.049, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.238309845328331, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0493, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.06370572745800018, | |
| "eval_runtime": 30.2552, | |
| "eval_samples_per_second": 1.487, | |
| "eval_steps_per_second": 1.487, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.24373754858970642, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.0524, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.19682925939559937, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0432, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.19353125989437103, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0503, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.2142736166715622, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0575, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.22623366117477417, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.061, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.24655097723007202, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0424, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.19729213416576385, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0486, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.18009215593338013, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0507, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.21661217510700226, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0476, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.23137158155441284, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.035, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.06266605108976364, | |
| "eval_runtime": 30.266, | |
| "eval_samples_per_second": 1.487, | |
| "eval_steps_per_second": 1.487, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.34158170223236084, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0602, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.3994427025318146, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.0746, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.2226848304271698, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0444, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.150822252035141, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0339, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.21457140147686005, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0512, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.18267565965652466, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0406, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.15435825288295746, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0431, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.18329615890979767, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0456, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.20356465876102448, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0488, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.18102215230464935, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0447, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.0614437460899353, | |
| "eval_runtime": 30.2325, | |
| "eval_samples_per_second": 1.488, | |
| "eval_steps_per_second": 1.488, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.18073691427707672, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0388, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.16422803699970245, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0334, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.19758668541908264, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0451, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.19398516416549683, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0472, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.21082225441932678, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0437, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.17613369226455688, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0374, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.24232444167137146, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0534, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.18357758224010468, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0453, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.22436165809631348, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0566, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.18541714549064636, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0459, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.06152466684579849, | |
| "eval_runtime": 30.2569, | |
| "eval_samples_per_second": 1.487, | |
| "eval_steps_per_second": 1.487, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.19532428681850433, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0459, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.1529971808195114, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0318, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.17730271816253662, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.0464, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.17921102046966553, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0511, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.17385323345661163, | |
| "learning_rate": 0.0, | |
| "loss": 0.039, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.6522533121425408e+17, | |
| "train_loss": 0.0994399946630001, | |
| "train_runtime": 4817.6285, | |
| "train_samples_per_second": 0.42, | |
| "train_steps_per_second": 0.026 | |
| } | |
| ], | |
| "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": 1.6522533121425408e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |