| { | |
| "best_metric": 0.09076610952615738, | |
| "best_model_checkpoint": "saves/psy-course-doc-info/MentaLLaMA-chat-7B/train/fold2/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": 0.24663323163986206, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.396, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.2477671205997467, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.4232, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.263531893491745, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.4225, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.23312927782535553, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.3992, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.28300321102142334, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.4271, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 1.4011518955230713, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 1.8319, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.3299415409564972, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.4206, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.5316458344459534, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.6921, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.3822180926799774, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.4205, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.31560224294662476, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.3885, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.43442925810813904, | |
| "eval_runtime": 32.9947, | |
| "eval_samples_per_second": 1.364, | |
| "eval_steps_per_second": 1.364, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.28216806054115295, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.3614, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.3426050543785095, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.3954, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.24308516085147858, | |
| "learning_rate": 0.0001, | |
| "loss": 0.3337, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.2314092516899109, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.3037, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.21914787590503693, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.2691, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.6148584485054016, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.4753, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.1599431335926056, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.2258, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.18857978284358978, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.2455, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.28784433007240295, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.2871, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.20797975361347198, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.2237, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.26759687066078186, | |
| "eval_runtime": 33.1319, | |
| "eval_samples_per_second": 1.358, | |
| "eval_steps_per_second": 1.358, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.20990042388439178, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.2343, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.210429847240448, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.2149, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.21932411193847656, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.2444, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.16824950277805328, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.1789, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.19204705953598022, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.1958, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.2959022521972656, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.3435, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.1339321732521057, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.138, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.7362474203109741, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.3116, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.16554364562034607, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.1631, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.1534777134656906, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.1832, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.1873324066400528, | |
| "eval_runtime": 33.1859, | |
| "eval_samples_per_second": 1.356, | |
| "eval_steps_per_second": 1.356, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.12305423617362976, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.1331, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.20600298047065735, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.1732, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.2041948139667511, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.1497, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.14868822693824768, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.1308, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.18193790316581726, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.133, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.16779907047748566, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.1323, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.13922376930713654, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.1451, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.2667795717716217, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.1937, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.18684104084968567, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.1519, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.17263275384902954, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.1462, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.15912017226219177, | |
| "eval_runtime": 33.2756, | |
| "eval_samples_per_second": 1.352, | |
| "eval_steps_per_second": 1.352, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.14088325202465057, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1137, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.23659411072731018, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.1609, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.20979824662208557, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.1365, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.15397435426712036, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.1344, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 3.92313814163208, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.8716, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.2112623006105423, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.1102, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.20745016634464264, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.1357, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.19207710027694702, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1132, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.23581749200820923, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.1223, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.26504454016685486, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.1137, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.13370537757873535, | |
| "eval_runtime": 33.242, | |
| "eval_samples_per_second": 1.354, | |
| "eval_steps_per_second": 1.354, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.29836392402648926, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.1884, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.1594570130109787, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.0986, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.37628644704818726, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.1334, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.30639582872390747, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.1617, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.17987194657325745, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0841, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.23170703649520874, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.1227, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.30856576561927795, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.1229, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.2813984453678131, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.0862, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.1890581250190735, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0997, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.22219303250312805, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0833, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.11862096935510635, | |
| "eval_runtime": 33.4501, | |
| "eval_samples_per_second": 1.345, | |
| "eval_steps_per_second": 1.345, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.32195284962654114, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0945, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.20843565464019775, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0936, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.23486849665641785, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.1098, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.22342218458652496, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0985, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.19964225590229034, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0917, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.1994989663362503, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0752, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.23633407056331635, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.0867, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.18411295115947723, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0897, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.23902778327465057, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0899, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.3357221782207489, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0996, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.10703333467245102, | |
| "eval_runtime": 33.6262, | |
| "eval_samples_per_second": 1.338, | |
| "eval_steps_per_second": 1.338, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.18525512516498566, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0791, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.18786416947841644, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.0861, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.2027207911014557, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0834, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 4.252847671508789, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.681, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.32096734642982483, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0948, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.46108517050743103, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1643, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.1711740344762802, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0769, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 1.9557204246520996, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.504, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.20599444210529327, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0695, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.2824552357196808, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0826, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.0994119644165039, | |
| "eval_runtime": 33.6642, | |
| "eval_samples_per_second": 1.337, | |
| "eval_steps_per_second": 1.337, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.22812792658805847, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0841, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.24667735397815704, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0599, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.18871454894542694, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0666, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.26361897587776184, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0876, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.19328255951404572, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.067, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.33101722598075867, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0827, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.313803493976593, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0734, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.15373966097831726, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0664, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.19037875533103943, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0748, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.24030755460262299, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.07, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.09435347467660904, | |
| "eval_runtime": 33.6286, | |
| "eval_samples_per_second": 1.338, | |
| "eval_steps_per_second": 1.338, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.2508762776851654, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.088, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.15514883399009705, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.066, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.20216505229473114, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0665, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.21634361147880554, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0872, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.2662385404109955, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.1302, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.22098056972026825, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0761, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.23511505126953125, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0899, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.1778053492307663, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0726, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.17188893258571625, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0792, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.19501493871212006, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.061, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.09192973375320435, | |
| "eval_runtime": 33.8465, | |
| "eval_samples_per_second": 1.33, | |
| "eval_steps_per_second": 1.33, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.2595723867416382, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.1094, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.3107694685459137, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.1165, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.1863652765750885, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0655, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.1593368947505951, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0719, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.20057342946529388, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0827, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.15131554007530212, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0481, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.24239127337932587, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0968, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.15222519636154175, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0545, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.18803313374519348, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0813, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.1561780422925949, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0597, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.0911686047911644, | |
| "eval_runtime": 33.7715, | |
| "eval_samples_per_second": 1.332, | |
| "eval_steps_per_second": 1.332, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.2134198397397995, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0604, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.1826525181531906, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0647, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.19802053272724152, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0619, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.23511645197868347, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.1327, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.2081468254327774, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0516, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.17238399386405945, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0649, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.14157335460186005, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.052, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.16426832973957062, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0666, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.20188003778457642, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0746, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.23054467141628265, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0841, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.09076610952615738, | |
| "eval_runtime": 33.9814, | |
| "eval_samples_per_second": 1.324, | |
| "eval_steps_per_second": 1.324, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.1652701050043106, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0662, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.13462711870670319, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0541, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.20249080657958984, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.0938, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.26019683480262756, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0637, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 1.4604827165603638, | |
| "learning_rate": 0.0, | |
| "loss": 0.3963, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.8134448342269952e+17, | |
| "train_loss": 0.17924573558568954, | |
| "train_runtime": 5839.6203, | |
| "train_samples_per_second": 0.347, | |
| "train_steps_per_second": 0.021 | |
| } | |
| ], | |
| "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": 1.8134448342269952e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |