| { | |
| "best_metric": 1.7047967910766602, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.2883922134102379, | |
| "eval_steps": 50, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002883922134102379, | |
| "grad_norm": 1.5703037977218628, | |
| "learning_rate": 1e-05, | |
| "loss": 2.0589, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002883922134102379, | |
| "eval_loss": 3.8151354789733887, | |
| "eval_runtime": 22.9981, | |
| "eval_samples_per_second": 12.697, | |
| "eval_steps_per_second": 3.174, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005767844268204758, | |
| "grad_norm": 2.1479856967926025, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5782, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.008651766402307137, | |
| "grad_norm": 1.895737648010254, | |
| "learning_rate": 3e-05, | |
| "loss": 2.6209, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011535688536409516, | |
| "grad_norm": 1.6626169681549072, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6939, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.014419610670511895, | |
| "grad_norm": 1.5387909412384033, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6016, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.017303532804614274, | |
| "grad_norm": 2.0145578384399414, | |
| "learning_rate": 6e-05, | |
| "loss": 2.1304, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.020187454938716654, | |
| "grad_norm": 1.9654802083969116, | |
| "learning_rate": 7e-05, | |
| "loss": 2.3349, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.023071377072819033, | |
| "grad_norm": 1.785875678062439, | |
| "learning_rate": 8e-05, | |
| "loss": 2.9965, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02595529920692141, | |
| "grad_norm": 2.299412488937378, | |
| "learning_rate": 9e-05, | |
| "loss": 2.5219, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02883922134102379, | |
| "grad_norm": 2.9634199142456055, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5635, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03172314347512617, | |
| "grad_norm": 2.4284486770629883, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 2.4461, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03460706560922855, | |
| "grad_norm": 2.6376311779022217, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 1.8255, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03749098774333093, | |
| "grad_norm": 2.8831024169921875, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 2.0168, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04037490987743331, | |
| "grad_norm": 3.3589651584625244, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 2.213, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.043258832011535686, | |
| "grad_norm": 3.8879942893981934, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 2.687, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.046142754145638065, | |
| "grad_norm": 3.271531105041504, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 2.1461, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.049026676279740444, | |
| "grad_norm": 3.1234054565429688, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 1.7346, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.05191059841384282, | |
| "grad_norm": 2.665754556655884, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 2.0615, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0547945205479452, | |
| "grad_norm": 2.4743616580963135, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 2.1874, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05767844268204758, | |
| "grad_norm": 2.5432615280151367, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 2.2189, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06056236481614996, | |
| "grad_norm": 2.983246326446533, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 1.9692, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06344628695025234, | |
| "grad_norm": 2.45336651802063, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 2.2483, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06633020908435472, | |
| "grad_norm": 2.5861599445343018, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 1.9138, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0692141312184571, | |
| "grad_norm": 2.33628511428833, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 2.0424, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07209805335255948, | |
| "grad_norm": 2.60402512550354, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.2653, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07498197548666186, | |
| "grad_norm": 2.733616828918457, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 1.9203, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07786589762076424, | |
| "grad_norm": 2.5261662006378174, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 2.2836, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08074981975486661, | |
| "grad_norm": 2.428677558898926, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 2.1752, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.083633741888969, | |
| "grad_norm": 2.755263566970825, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 2.2118, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08651766402307137, | |
| "grad_norm": 2.6693482398986816, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 2.1495, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08940158615717375, | |
| "grad_norm": 2.810084581375122, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 2.333, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.09228550829127613, | |
| "grad_norm": 4.237344741821289, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 2.186, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.09516943042537851, | |
| "grad_norm": 2.355196475982666, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 2.2242, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09805335255948089, | |
| "grad_norm": 3.7081375122070312, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 1.9646, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.10093727469358327, | |
| "grad_norm": 2.576308250427246, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 2.332, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.10382119682768565, | |
| "grad_norm": 3.081573247909546, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 2.5147, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.10670511896178803, | |
| "grad_norm": 3.4703218936920166, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 2.2131, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.1095890410958904, | |
| "grad_norm": 3.222766876220703, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 2.0428, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.11247296322999278, | |
| "grad_norm": 3.741807460784912, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 2.4813, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.11535688536409516, | |
| "grad_norm": 3.2622110843658447, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.3364, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11824080749819754, | |
| "grad_norm": 3.205472946166992, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 2.3985, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.12112472963229992, | |
| "grad_norm": 3.706458568572998, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 2.367, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1240086517664023, | |
| "grad_norm": 3.5190389156341553, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 2.269, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.12689257390050468, | |
| "grad_norm": 3.884115695953369, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 2.1178, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12977649603460706, | |
| "grad_norm": 4.250286102294922, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 2.4075, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.13266041816870944, | |
| "grad_norm": 4.229992866516113, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.9127, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.13554434030281182, | |
| "grad_norm": 5.310244560241699, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 2.8375, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1384282624369142, | |
| "grad_norm": 6.2029924392700195, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 3.3432, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.14131218457101657, | |
| "grad_norm": 6.517217636108398, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 3.1984, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.14419610670511895, | |
| "grad_norm": 7.523353099822998, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 3.4522, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14419610670511895, | |
| "eval_loss": 1.9131253957748413, | |
| "eval_runtime": 23.3802, | |
| "eval_samples_per_second": 12.489, | |
| "eval_steps_per_second": 3.122, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.14708002883922133, | |
| "grad_norm": 3.465303421020508, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 1.7546, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.1499639509733237, | |
| "grad_norm": 3.992642641067505, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 2.0861, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.1528478731074261, | |
| "grad_norm": 3.0011038780212402, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 2.0782, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.15573179524152847, | |
| "grad_norm": 4.233003616333008, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 1.9653, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.15861571737563085, | |
| "grad_norm": 2.497156858444214, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0433, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.16149963950973323, | |
| "grad_norm": 2.493154525756836, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 2.1094, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.1643835616438356, | |
| "grad_norm": 3.013134717941284, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 1.9088, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.167267483777938, | |
| "grad_norm": 2.9068727493286133, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 1.8023, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.17015140591204037, | |
| "grad_norm": 2.271667957305908, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 1.4342, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.17303532804614274, | |
| "grad_norm": 2.3056743144989014, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 1.7894, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.17591925018024512, | |
| "grad_norm": 2.148430109024048, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 2.0033, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.1788031723143475, | |
| "grad_norm": 2.3220510482788086, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 1.896, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.18168709444844988, | |
| "grad_norm": 2.2510859966278076, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 1.5744, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.18457101658255226, | |
| "grad_norm": 2.2365784645080566, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 2.1132, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.18745493871665464, | |
| "grad_norm": 2.7383601665496826, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 1.4043, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.19033886085075702, | |
| "grad_norm": 2.8318002223968506, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 1.3849, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.1932227829848594, | |
| "grad_norm": 2.526379108428955, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 1.5758, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.19610670511896178, | |
| "grad_norm": 2.327927827835083, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 1.5936, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.19899062725306416, | |
| "grad_norm": 2.5951497554779053, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 1.5208, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.20187454938716654, | |
| "grad_norm": 2.753805637359619, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.6412, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.20475847152126891, | |
| "grad_norm": 3.426722526550293, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 1.3787, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.2076423936553713, | |
| "grad_norm": 2.781561851501465, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 1.7158, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 2.8658552169799805, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 1.6013, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.21341023792357605, | |
| "grad_norm": 2.959545850753784, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 1.6079, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.21629416005767843, | |
| "grad_norm": 3.6071605682373047, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 1.7696, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.2191780821917808, | |
| "grad_norm": 2.7387630939483643, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 1.4193, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.2220620043258832, | |
| "grad_norm": 2.911520004272461, | |
| "learning_rate": 1.526708147705013e-05, | |
| "loss": 1.5238, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.22494592645998557, | |
| "grad_norm": 2.791823148727417, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 2.2312, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.22782984859408795, | |
| "grad_norm": 2.8899409770965576, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 1.9362, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.23071377072819033, | |
| "grad_norm": 3.4697084426879883, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 1.6951, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2335976928622927, | |
| "grad_norm": 3.7092645168304443, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 1.7158, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.23648161499639508, | |
| "grad_norm": 2.560610294342041, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.7651, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.23936553713049746, | |
| "grad_norm": 3.0181474685668945, | |
| "learning_rate": 8.548121372247918e-06, | |
| "loss": 1.5948, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.24224945926459984, | |
| "grad_norm": 2.751650810241699, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 1.7458, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.24513338139870222, | |
| "grad_norm": 3.0843162536621094, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.6558, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.2480173035328046, | |
| "grad_norm": 3.3699612617492676, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 1.7587, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.250901225666907, | |
| "grad_norm": 3.3418948650360107, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 1.6909, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.25378514780100936, | |
| "grad_norm": 3.3619613647460938, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 2.0362, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.25666906993511174, | |
| "grad_norm": 3.0680737495422363, | |
| "learning_rate": 3.6408072716606346e-06, | |
| "loss": 1.8151, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.2595529920692141, | |
| "grad_norm": 2.8170669078826904, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 1.6345, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2624369142033165, | |
| "grad_norm": 3.9491117000579834, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 1.9444, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.2653208363374189, | |
| "grad_norm": 4.594845771789551, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 2.2793, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.26820475847152125, | |
| "grad_norm": 3.526573657989502, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 2.1539, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.27108868060562363, | |
| "grad_norm": 4.229367733001709, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 2.1262, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.273972602739726, | |
| "grad_norm": 3.984933614730835, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 1.929, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.2768565248738284, | |
| "grad_norm": 5.746740818023682, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 2.4956, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.27974044700793077, | |
| "grad_norm": 5.947922706604004, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 2.5408, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.28262436914203315, | |
| "grad_norm": 7.675450325012207, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 3.0644, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.28550829127613553, | |
| "grad_norm": 8.340805053710938, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 3.1979, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.2883922134102379, | |
| "grad_norm": 12.863282203674316, | |
| "learning_rate": 0.0, | |
| "loss": 3.8005, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2883922134102379, | |
| "eval_loss": 1.7047967910766602, | |
| "eval_runtime": 23.369, | |
| "eval_samples_per_second": 12.495, | |
| "eval_steps_per_second": 3.124, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.41887283560448e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |