| { | |
| "best_metric": 0.08166717737913132, | |
| "best_model_checkpoint": "saves/psy-course-doc/Ministral-8B-Instruct-2410/train/fold5/checkpoint-80", | |
| "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": 0.2608383595943451, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.193, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.2739827632904053, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.1848, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.29375824332237244, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.2284, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.24989710748195648, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.2558, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.2933337688446045, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.2082, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.27104246616363525, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.177, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.3017788231372833, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.2691, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.20777066051959991, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.1839, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.23570074141025543, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.1842, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.19519267976284027, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.1374, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.15143676102161407, | |
| "eval_runtime": 23.8035, | |
| "eval_samples_per_second": 1.89, | |
| "eval_steps_per_second": 1.89, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.23228688538074493, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.0921, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.19485501945018768, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.1193, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.20170904695987701, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0706, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.21589572727680206, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.1553, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.2030184119939804, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.108, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.18924479186534882, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.0641, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.15578563511371613, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.1252, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.13807904720306396, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.0889, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.13024358451366425, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.0753, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.12695220112800598, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.081, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.10153083503246307, | |
| "eval_runtime": 23.9128, | |
| "eval_samples_per_second": 1.882, | |
| "eval_steps_per_second": 1.882, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.15657182037830353, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.1199, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.12229763716459274, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.0511, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.111344113945961, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.0801, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.14376555383205414, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.1022, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.10361433029174805, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.0537, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.11647197604179382, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.0648, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.09697144478559494, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0817, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.09467044472694397, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.0619, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.1080031618475914, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.0643, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.09614257514476776, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.0675, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.09128404408693314, | |
| "eval_runtime": 23.8449, | |
| "eval_samples_per_second": 1.887, | |
| "eval_steps_per_second": 1.887, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.09131722152233124, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.0539, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.12834537029266357, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.0802, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.1032692939043045, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.063, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.10833238065242767, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.0856, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.1199575886130333, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.0834, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.16978178918361664, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.0629, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.10243354737758636, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.0663, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.10259146243333817, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.0983, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.0987490564584732, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.0508, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.0943879559636116, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.0969, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.08728183805942535, | |
| "eval_runtime": 23.8357, | |
| "eval_samples_per_second": 1.888, | |
| "eval_steps_per_second": 1.888, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.1278013437986374, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0684, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.09197275340557098, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.0627, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.08644460141658783, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.0511, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.14504744112491608, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.12, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.09097104519605637, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.0324, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.09147904068231583, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.0521, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.0917946919798851, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.0482, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.10255839675664902, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0916, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.13830173015594482, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.0961, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.10138488560914993, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.0546, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.08438044786453247, | |
| "eval_runtime": 23.8229, | |
| "eval_samples_per_second": 1.889, | |
| "eval_steps_per_second": 1.889, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.09391544759273529, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.0611, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.13201846182346344, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.1134, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.0926932543516159, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.0426, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.10242126882076263, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.0755, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.11139488220214844, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1064, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.10886554419994354, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.0579, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.13153661787509918, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.0871, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.1118181049823761, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.0873, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.08345295488834381, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0246, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.09620598703622818, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0562, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.0832722932100296, | |
| "eval_runtime": 23.7778, | |
| "eval_samples_per_second": 1.893, | |
| "eval_steps_per_second": 1.893, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.1237940639257431, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0531, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.1100258007645607, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0411, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.1080050840973854, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.0914, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.09219429641962051, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0564, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.11984851956367493, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.0763, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.1027103066444397, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0211, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.1025909036397934, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.066, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.08136707544326782, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.0327, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.09417865425348282, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0301, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.11798197031021118, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.0502, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.08251234889030457, | |
| "eval_runtime": 23.8046, | |
| "eval_samples_per_second": 1.89, | |
| "eval_steps_per_second": 1.89, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.10102754831314087, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0375, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.11923184990882874, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.0907, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.09162813425064087, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.0316, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.10411273688077927, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0606, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.11636317521333694, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0439, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.10171887278556824, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0631, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.07914586365222931, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0358, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.10216517746448517, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.0702, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.09483199566602707, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0659, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.0997677743434906, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.0538, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.08166717737913132, | |
| "eval_runtime": 23.8227, | |
| "eval_samples_per_second": 1.889, | |
| "eval_steps_per_second": 1.889, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.1063404455780983, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0771, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.056223608553409576, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0085, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.1012742891907692, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0586, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.09964168071746826, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0437, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.0838206559419632, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0307, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.09745898097753525, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0418, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.10451015084981918, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.0412, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.10873839259147644, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.0611, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.12379412353038788, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.0609, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.11690313369035721, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0325, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.08311446756124496, | |
| "eval_runtime": 23.8424, | |
| "eval_samples_per_second": 1.887, | |
| "eval_steps_per_second": 1.887, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.12106270343065262, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.0306, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.10837742686271667, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0489, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.10839777439832687, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.052, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.12313923239707947, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.0485, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.11231550574302673, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.041, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.143199160695076, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.0841, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.1412321925163269, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0667, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.15026360750198364, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0919, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.14176741242408752, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0818, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.08459971100091934, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0153, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.08174756169319153, | |
| "eval_runtime": 23.825, | |
| "eval_samples_per_second": 1.889, | |
| "eval_steps_per_second": 1.889, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.10399176925420761, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0406, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.1305747926235199, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.0642, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.13290198147296906, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.0667, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.08288413286209106, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0256, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.11641150712966919, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.0651, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.10249906778335571, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0371, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.11602521687746048, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.0569, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.09697198867797852, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0148, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.12643811106681824, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0397, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.09974046796560287, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0427, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.08196596801280975, | |
| "eval_runtime": 23.8327, | |
| "eval_samples_per_second": 1.888, | |
| "eval_steps_per_second": 1.888, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.1062353327870369, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0484, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.1080995723605156, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.0434, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.09961345046758652, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0257, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.12004464119672775, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0536, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.11470311135053635, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.037, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.07819245010614395, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0134, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.1119803637266159, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0624, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.08947642892599106, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0213, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.11834932118654251, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.0474, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.1297232210636139, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0694, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.08215589076280594, | |
| "eval_runtime": 23.8095, | |
| "eval_samples_per_second": 1.89, | |
| "eval_steps_per_second": 1.89, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.11614278703927994, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.0609, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.0959644466638565, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0346, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.10608977824449539, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.038, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.13928034901618958, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0968, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.12597979605197906, | |
| "learning_rate": 0.0, | |
| "loss": 0.0489, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.5332406494035968e+17, | |
| "train_loss": 0.07298124569654464, | |
| "train_runtime": 3863.347, | |
| "train_samples_per_second": 0.524, | |
| "train_steps_per_second": 0.032 | |
| } | |
| ], | |
| "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": 1.5332406494035968e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |