| { | |
| "best_metric": 0.06946441531181335, | |
| "best_model_checkpoint": "saves/psy-course-doc/Qwen2.5-7B-Instruct/train/fold9/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": 0.18727460503578186, | |
| "learning_rate": 7.692307692307694e-06, | |
| "loss": 0.258, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.07901234567901234, | |
| "grad_norm": 0.17821623384952545, | |
| "learning_rate": 1.5384615384615387e-05, | |
| "loss": 0.2558, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.11851851851851852, | |
| "grad_norm": 0.21921306848526, | |
| "learning_rate": 2.307692307692308e-05, | |
| "loss": 0.2103, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1580246913580247, | |
| "grad_norm": 0.1655219942331314, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.3484, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.19753086419753085, | |
| "grad_norm": 0.2014666050672531, | |
| "learning_rate": 3.846153846153846e-05, | |
| "loss": 0.257, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.23703703703703705, | |
| "grad_norm": 0.2115616500377655, | |
| "learning_rate": 4.615384615384616e-05, | |
| "loss": 0.2142, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2765432098765432, | |
| "grad_norm": 0.21360763907432556, | |
| "learning_rate": 5.384615384615385e-05, | |
| "loss": 0.2203, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3160493827160494, | |
| "grad_norm": 0.17155516147613525, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.2691, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.17387287318706512, | |
| "learning_rate": 6.923076923076924e-05, | |
| "loss": 0.1956, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "grad_norm": 0.14809465408325195, | |
| "learning_rate": 7.692307692307693e-05, | |
| "loss": 0.2634, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3950617283950617, | |
| "eval_loss": 0.18892718851566315, | |
| "eval_runtime": 21.4194, | |
| "eval_samples_per_second": 2.101, | |
| "eval_steps_per_second": 2.101, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.4345679012345679, | |
| "grad_norm": 0.14302557706832886, | |
| "learning_rate": 8.461538461538461e-05, | |
| "loss": 0.1897, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.4740740740740741, | |
| "grad_norm": 0.12145882844924927, | |
| "learning_rate": 9.230769230769232e-05, | |
| "loss": 0.2119, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5135802469135803, | |
| "grad_norm": 0.11013402044773102, | |
| "learning_rate": 0.0001, | |
| "loss": 0.161, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.5530864197530864, | |
| "grad_norm": 0.09988079965114594, | |
| "learning_rate": 9.998033131915266e-05, | |
| "loss": 0.1809, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 0.10233993828296661, | |
| "learning_rate": 9.992134075089084e-05, | |
| "loss": 0.1277, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.6320987654320988, | |
| "grad_norm": 0.10312012583017349, | |
| "learning_rate": 9.982307470588098e-05, | |
| "loss": 0.1862, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.671604938271605, | |
| "grad_norm": 0.10356580466032028, | |
| "learning_rate": 9.968561049466214e-05, | |
| "loss": 0.1464, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.1099441722035408, | |
| "learning_rate": 9.950905626682228e-05, | |
| "loss": 0.1121, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.7506172839506173, | |
| "grad_norm": 0.09946368634700775, | |
| "learning_rate": 9.92935509259118e-05, | |
| "loss": 0.1706, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "grad_norm": 0.08879581093788147, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.1843, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7901234567901234, | |
| "eval_loss": 0.11882688850164413, | |
| "eval_runtime": 21.4294, | |
| "eval_samples_per_second": 2.1, | |
| "eval_steps_per_second": 2.1, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.8296296296296296, | |
| "grad_norm": 0.11438848823308945, | |
| "learning_rate": 9.874639560909117e-05, | |
| "loss": 0.1227, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.8691358024691358, | |
| "grad_norm": 0.11357422173023224, | |
| "learning_rate": 9.841517610611309e-05, | |
| "loss": 0.1119, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.908641975308642, | |
| "grad_norm": 0.12170927971601486, | |
| "learning_rate": 9.804586609725499e-05, | |
| "loss": 0.1318, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.9481481481481482, | |
| "grad_norm": 0.09682313352823257, | |
| "learning_rate": 9.763875613614482e-05, | |
| "loss": 0.1461, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 0.07887136191129684, | |
| "learning_rate": 9.719416651541839e-05, | |
| "loss": 0.1308, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.0271604938271606, | |
| "grad_norm": 0.18343709409236908, | |
| "learning_rate": 9.671244701472999e-05, | |
| "loss": 0.2167, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.07480595260858536, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.1183, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.106172839506173, | |
| "grad_norm": 0.07301326841115952, | |
| "learning_rate": 9.563916325306594e-05, | |
| "loss": 0.1497, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.145679012345679, | |
| "grad_norm": 0.07822959870100021, | |
| "learning_rate": 9.504844339512095e-05, | |
| "loss": 0.1221, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "grad_norm": 0.07124387472867966, | |
| "learning_rate": 9.442228179894362e-05, | |
| "loss": 0.0905, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.1851851851851851, | |
| "eval_loss": 0.09007365256547928, | |
| "eval_runtime": 21.4398, | |
| "eval_samples_per_second": 2.099, | |
| "eval_steps_per_second": 2.099, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.2246913580246914, | |
| "grad_norm": 0.09570447355508804, | |
| "learning_rate": 9.376117109543769e-05, | |
| "loss": 0.1559, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.2641975308641975, | |
| "grad_norm": 0.08178304880857468, | |
| "learning_rate": 9.306563141162046e-05, | |
| "loss": 0.1369, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.3037037037037038, | |
| "grad_norm": 0.07171113789081573, | |
| "learning_rate": 9.233620996141421e-05, | |
| "loss": 0.1302, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.34320987654321, | |
| "grad_norm": 0.08152975887060165, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.117, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.382716049382716, | |
| "grad_norm": 0.07075482606887817, | |
| "learning_rate": 9.077804344796302e-05, | |
| "loss": 0.0569, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 0.08588957041501999, | |
| "learning_rate": 8.995052426791247e-05, | |
| "loss": 0.1374, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.4617283950617284, | |
| "grad_norm": 0.09398827701807022, | |
| "learning_rate": 8.90915741234015e-05, | |
| "loss": 0.0776, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.5012345679012347, | |
| "grad_norm": 0.07304003834724426, | |
| "learning_rate": 8.820186879108038e-05, | |
| "loss": 0.1581, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.5407407407407407, | |
| "grad_norm": 0.08817372471094131, | |
| "learning_rate": 8.728210824415827e-05, | |
| "loss": 0.1376, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "grad_norm": 0.08125587552785873, | |
| "learning_rate": 8.633301610170135e-05, | |
| "loss": 0.0487, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.5802469135802468, | |
| "eval_loss": 0.08006139099597931, | |
| "eval_runtime": 21.4435, | |
| "eval_samples_per_second": 2.099, | |
| "eval_steps_per_second": 2.099, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.6197530864197531, | |
| "grad_norm": 0.08263380080461502, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0366, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.6592592592592592, | |
| "grad_norm": 0.06218172609806061, | |
| "learning_rate": 8.434984630174509e-05, | |
| "loss": 0.0598, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.6987654320987655, | |
| "grad_norm": 0.08572252839803696, | |
| "learning_rate": 8.33173288976002e-05, | |
| "loss": 0.1128, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.7382716049382716, | |
| "grad_norm": 0.08314324915409088, | |
| "learning_rate": 8.225859917710439e-05, | |
| "loss": 0.1644, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.057930175215005875, | |
| "learning_rate": 8.117449009293668e-05, | |
| "loss": 0.0391, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.817283950617284, | |
| "grad_norm": 0.06859392672777176, | |
| "learning_rate": 8.006585456492029e-05, | |
| "loss": 0.0596, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.8567901234567903, | |
| "grad_norm": 0.07236019521951675, | |
| "learning_rate": 7.89335648089903e-05, | |
| "loss": 0.121, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.8962962962962964, | |
| "grad_norm": 0.0819316953420639, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.1166, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.9358024691358025, | |
| "grad_norm": 0.06272662431001663, | |
| "learning_rate": 7.660160382576683e-05, | |
| "loss": 0.0762, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.06243712827563286, | |
| "learning_rate": 7.540376726232648e-05, | |
| "loss": 0.0796, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "eval_loss": 0.07556910067796707, | |
| "eval_runtime": 21.4491, | |
| "eval_samples_per_second": 2.098, | |
| "eval_steps_per_second": 2.098, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0148148148148146, | |
| "grad_norm": 0.11002784222364426, | |
| "learning_rate": 7.4185944355262e-05, | |
| "loss": 0.1496, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 2.054320987654321, | |
| "grad_norm": 0.06127890571951866, | |
| "learning_rate": 7.294909322337689e-05, | |
| "loss": 0.0663, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 2.093827160493827, | |
| "grad_norm": 0.06523426622152328, | |
| "learning_rate": 7.169418695587791e-05, | |
| "loss": 0.1134, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.06284269690513611, | |
| "learning_rate": 7.042221284679982e-05, | |
| "loss": 0.1054, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 2.1728395061728394, | |
| "grad_norm": 0.0617842972278595, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0548, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 2.212345679012346, | |
| "grad_norm": 0.07507811486721039, | |
| "learning_rate": 6.783107663311565e-05, | |
| "loss": 0.1385, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 2.251851851851852, | |
| "grad_norm": 0.06047966703772545, | |
| "learning_rate": 6.651395309775837e-05, | |
| "loss": 0.0892, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 2.291358024691358, | |
| "grad_norm": 0.07440383732318878, | |
| "learning_rate": 6.518383725548074e-05, | |
| "loss": 0.0941, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 2.330864197530864, | |
| "grad_norm": 0.08216129243373871, | |
| "learning_rate": 6.384177557124247e-05, | |
| "loss": 0.0956, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "grad_norm": 0.06874312460422516, | |
| "learning_rate": 6.248882390836135e-05, | |
| "loss": 0.0814, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.3703703703703702, | |
| "eval_loss": 0.07336278259754181, | |
| "eval_runtime": 21.4509, | |
| "eval_samples_per_second": 2.098, | |
| "eval_steps_per_second": 2.098, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 2.4098765432098768, | |
| "grad_norm": 0.06465183198451996, | |
| "learning_rate": 6.112604669781572e-05, | |
| "loss": 0.0385, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 2.449382716049383, | |
| "grad_norm": 0.07423505187034607, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.086, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.06170642748475075, | |
| "learning_rate": 5.837531116523682e-05, | |
| "loss": 0.0641, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 2.528395061728395, | |
| "grad_norm": 0.06919082999229431, | |
| "learning_rate": 5.698951697677498e-05, | |
| "loss": 0.0543, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 2.567901234567901, | |
| "grad_norm": 0.10222210735082626, | |
| "learning_rate": 5.559822380516539e-05, | |
| "loss": 0.1129, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 2.6074074074074076, | |
| "grad_norm": 0.08813044428825378, | |
| "learning_rate": 5.420252624646238e-05, | |
| "loss": 0.0722, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 2.6469135802469137, | |
| "grad_norm": 0.07499007880687714, | |
| "learning_rate": 5.2803522361859594e-05, | |
| "loss": 0.1294, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 2.68641975308642, | |
| "grad_norm": 0.08920853585004807, | |
| "learning_rate": 5.140231281379345e-05, | |
| "loss": 0.1683, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 2.725925925925926, | |
| "grad_norm": 0.08307864516973495, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1073, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "grad_norm": 0.07773951441049576, | |
| "learning_rate": 4.859768718620656e-05, | |
| "loss": 0.1069, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.765432098765432, | |
| "eval_loss": 0.07204687595367432, | |
| "eval_runtime": 21.4608, | |
| "eval_samples_per_second": 2.097, | |
| "eval_steps_per_second": 2.097, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 2.8049382716049385, | |
| "grad_norm": 0.06657297164201736, | |
| "learning_rate": 4.7196477638140404e-05, | |
| "loss": 0.0854, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 2.8444444444444446, | |
| "grad_norm": 0.06645756959915161, | |
| "learning_rate": 4.579747375353763e-05, | |
| "loss": 0.119, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 2.8839506172839506, | |
| "grad_norm": 0.07942323386669159, | |
| "learning_rate": 4.4401776194834613e-05, | |
| "loss": 0.1061, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 2.9234567901234567, | |
| "grad_norm": 0.08287160843610764, | |
| "learning_rate": 4.3010483023225045e-05, | |
| "loss": 0.0643, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 0.07614369690418243, | |
| "learning_rate": 4.162468883476319e-05, | |
| "loss": 0.0633, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 3.0024691358024693, | |
| "grad_norm": 0.11767338961362839, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.1492, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0419753086419754, | |
| "grad_norm": 0.04986137896776199, | |
| "learning_rate": 3.887395330218429e-05, | |
| "loss": 0.0515, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 3.0814814814814815, | |
| "grad_norm": 0.0710039958357811, | |
| "learning_rate": 3.7511176091638653e-05, | |
| "loss": 0.1576, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 3.1209876543209876, | |
| "grad_norm": 0.06671445816755295, | |
| "learning_rate": 3.6158224428757535e-05, | |
| "loss": 0.0509, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "grad_norm": 0.075251005589962, | |
| "learning_rate": 3.4816162744519263e-05, | |
| "loss": 0.1258, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.1604938271604937, | |
| "eval_loss": 0.07056884467601776, | |
| "eval_runtime": 21.4545, | |
| "eval_samples_per_second": 2.097, | |
| "eval_steps_per_second": 2.097, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "grad_norm": 0.07180268317461014, | |
| "learning_rate": 3.3486046902241664e-05, | |
| "loss": 0.0759, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 3.2395061728395063, | |
| "grad_norm": 0.0519411638379097, | |
| "learning_rate": 3.216892336688435e-05, | |
| "loss": 0.0316, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 3.2790123456790123, | |
| "grad_norm": 0.06611500680446625, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1292, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 3.3185185185185184, | |
| "grad_norm": 0.0613199807703495, | |
| "learning_rate": 2.9577787153200197e-05, | |
| "loss": 0.0542, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 3.3580246913580245, | |
| "grad_norm": 0.06923973560333252, | |
| "learning_rate": 2.8305813044122097e-05, | |
| "loss": 0.0896, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 3.397530864197531, | |
| "grad_norm": 0.06416472792625427, | |
| "learning_rate": 2.705090677662311e-05, | |
| "loss": 0.0586, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 3.437037037037037, | |
| "grad_norm": 0.058038849383592606, | |
| "learning_rate": 2.581405564473801e-05, | |
| "loss": 0.074, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 3.476543209876543, | |
| "grad_norm": 0.0762609988451004, | |
| "learning_rate": 2.459623273767354e-05, | |
| "loss": 0.1782, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 3.5160493827160493, | |
| "grad_norm": 0.06254488229751587, | |
| "learning_rate": 2.3398396174233178e-05, | |
| "loss": 0.1273, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.06214343383908272, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0816, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "eval_loss": 0.0701000764966011, | |
| "eval_runtime": 21.4516, | |
| "eval_samples_per_second": 2.098, | |
| "eval_steps_per_second": 2.098, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 3.595061728395062, | |
| "grad_norm": 0.06238280236721039, | |
| "learning_rate": 2.1066435191009715e-05, | |
| "loss": 0.1253, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 3.634567901234568, | |
| "grad_norm": 0.06397870928049088, | |
| "learning_rate": 1.9934145435079702e-05, | |
| "loss": 0.0711, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 3.674074074074074, | |
| "grad_norm": 0.059364404529333115, | |
| "learning_rate": 1.8825509907063327e-05, | |
| "loss": 0.0552, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 3.71358024691358, | |
| "grad_norm": 0.062334094196558, | |
| "learning_rate": 1.774140082289563e-05, | |
| "loss": 0.1002, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 3.753086419753086, | |
| "grad_norm": 0.06302722543478012, | |
| "learning_rate": 1.6682671102399805e-05, | |
| "loss": 0.0582, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 3.7925925925925927, | |
| "grad_norm": 0.07526195049285889, | |
| "learning_rate": 1.5650153698254916e-05, | |
| "loss": 0.062, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 3.832098765432099, | |
| "grad_norm": 0.06862392276525497, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1092, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 3.871604938271605, | |
| "grad_norm": 0.06513164192438126, | |
| "learning_rate": 1.3666983898298657e-05, | |
| "loss": 0.0834, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 3.911111111111111, | |
| "grad_norm": 0.06487555056810379, | |
| "learning_rate": 1.2717891755841722e-05, | |
| "loss": 0.0775, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.07505253702402115, | |
| "learning_rate": 1.1798131208919627e-05, | |
| "loss": 0.0711, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "eval_loss": 0.06961710005998611, | |
| "eval_runtime": 21.4663, | |
| "eval_samples_per_second": 2.096, | |
| "eval_steps_per_second": 2.096, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.9901234567901236, | |
| "grad_norm": 0.07023700326681137, | |
| "learning_rate": 1.090842587659851e-05, | |
| "loss": 0.0289, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 4.029629629629629, | |
| "grad_norm": 0.10853932052850723, | |
| "learning_rate": 1.004947573208756e-05, | |
| "loss": 0.0778, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 4.069135802469136, | |
| "grad_norm": 0.07031593471765518, | |
| "learning_rate": 9.221956552036992e-06, | |
| "loss": 0.092, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 4.108641975308642, | |
| "grad_norm": 0.05810968577861786, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0383, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 4.148148148148148, | |
| "grad_norm": 0.07230714708566666, | |
| "learning_rate": 7.663790038585793e-06, | |
| "loss": 0.1186, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 4.187654320987654, | |
| "grad_norm": 0.06782855838537216, | |
| "learning_rate": 6.934368588379553e-06, | |
| "loss": 0.0848, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 4.22716049382716, | |
| "grad_norm": 0.05907970294356346, | |
| "learning_rate": 6.238828904562316e-06, | |
| "loss": 0.054, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 4.266666666666667, | |
| "grad_norm": 0.06153102219104767, | |
| "learning_rate": 5.577718201056392e-06, | |
| "loss": 0.0806, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 4.306172839506173, | |
| "grad_norm": 0.07810863107442856, | |
| "learning_rate": 4.951556604879048e-06, | |
| "loss": 0.0843, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "grad_norm": 0.05811045691370964, | |
| "learning_rate": 4.360836746934055e-06, | |
| "loss": 0.0574, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.345679012345679, | |
| "eval_loss": 0.0694764107465744, | |
| "eval_runtime": 21.5001, | |
| "eval_samples_per_second": 2.093, | |
| "eval_steps_per_second": 2.093, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 4.385185185185185, | |
| "grad_norm": 0.06662862747907639, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0852, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 4.424691358024692, | |
| "grad_norm": 0.07076907157897949, | |
| "learning_rate": 3.2875529852700147e-06, | |
| "loss": 0.1034, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 4.4641975308641975, | |
| "grad_norm": 0.06786970049142838, | |
| "learning_rate": 2.8058334845816213e-06, | |
| "loss": 0.0864, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 4.503703703703704, | |
| "grad_norm": 0.06239473074674606, | |
| "learning_rate": 2.361243863855184e-06, | |
| "loss": 0.0569, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.54320987654321, | |
| "grad_norm": 0.06177065894007683, | |
| "learning_rate": 1.9541339027450256e-06, | |
| "loss": 0.0711, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 4.582716049382716, | |
| "grad_norm": 0.0672239288687706, | |
| "learning_rate": 1.584823893886933e-06, | |
| "loss": 0.0501, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 4.622222222222222, | |
| "grad_norm": 0.06448009610176086, | |
| "learning_rate": 1.2536043909088191e-06, | |
| "loss": 0.0601, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 4.661728395061728, | |
| "grad_norm": 0.06586714833974838, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.0859, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 4.701234567901235, | |
| "grad_norm": 0.07247553765773773, | |
| "learning_rate": 7.064490740882057e-07, | |
| "loss": 0.1015, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "grad_norm": 0.06972544640302658, | |
| "learning_rate": 4.909437331777179e-07, | |
| "loss": 0.0956, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.7407407407407405, | |
| "eval_loss": 0.06946441531181335, | |
| "eval_runtime": 21.5036, | |
| "eval_samples_per_second": 2.093, | |
| "eval_steps_per_second": 2.093, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 4.780246913580247, | |
| "grad_norm": 0.06849628686904907, | |
| "learning_rate": 3.143895053378698e-07, | |
| "loss": 0.1398, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 4.8197530864197535, | |
| "grad_norm": 0.05882110819220543, | |
| "learning_rate": 1.7692529411904578e-07, | |
| "loss": 0.0837, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 4.859259259259259, | |
| "grad_norm": 0.057644881308078766, | |
| "learning_rate": 7.865924910916977e-08, | |
| "loss": 0.084, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 4.898765432098766, | |
| "grad_norm": 0.06452777981758118, | |
| "learning_rate": 1.9668680847356735e-08, | |
| "loss": 0.0735, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.06288420408964157, | |
| "learning_rate": 0.0, | |
| "loss": 0.0781, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "step": 125, | |
| "total_flos": 1.4264769399939072e+17, | |
| "train_loss": 0.11290014976263046, | |
| "train_runtime": 3322.1997, | |
| "train_samples_per_second": 0.61, | |
| "train_steps_per_second": 0.038 | |
| } | |
| ], | |
| "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": 1.4264769399939072e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |