| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0270929287455974, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000270929287455974, | |
| "grad_norm": 1.0075852870941162, | |
| "learning_rate": 1e-05, | |
| "loss": 4.6362, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000270929287455974, | |
| "eval_loss": 2.204838991165161, | |
| "eval_runtime": 232.8963, | |
| "eval_samples_per_second": 13.345, | |
| "eval_steps_per_second": 1.67, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000541858574911948, | |
| "grad_norm": 0.7891753911972046, | |
| "learning_rate": 2e-05, | |
| "loss": 3.9172, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.000812787862367922, | |
| "grad_norm": 0.9741008281707764, | |
| "learning_rate": 3e-05, | |
| "loss": 4.7505, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001083717149823896, | |
| "grad_norm": 0.90495365858078, | |
| "learning_rate": 4e-05, | |
| "loss": 4.4032, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00135464643727987, | |
| "grad_norm": 1.0100457668304443, | |
| "learning_rate": 5e-05, | |
| "loss": 4.5474, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001625575724735844, | |
| "grad_norm": 0.9469624757766724, | |
| "learning_rate": 6e-05, | |
| "loss": 4.1974, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.001896505012191818, | |
| "grad_norm": 1.2900989055633545, | |
| "learning_rate": 7e-05, | |
| "loss": 4.356, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002167434299647792, | |
| "grad_norm": 1.331476092338562, | |
| "learning_rate": 8e-05, | |
| "loss": 4.3353, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002438363587103766, | |
| "grad_norm": 1.0620654821395874, | |
| "learning_rate": 9e-05, | |
| "loss": 4.1061, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002438363587103766, | |
| "eval_loss": 2.091578722000122, | |
| "eval_runtime": 234.1485, | |
| "eval_samples_per_second": 13.274, | |
| "eval_steps_per_second": 1.661, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00270929287455974, | |
| "grad_norm": 1.3079955577850342, | |
| "learning_rate": 0.0001, | |
| "loss": 3.7498, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002980222162015714, | |
| "grad_norm": 1.1652690172195435, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 3.782, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003251151449471688, | |
| "grad_norm": 1.0940849781036377, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 4.314, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.003522080736927662, | |
| "grad_norm": 0.8360046148300171, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 3.4797, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003793010024383636, | |
| "grad_norm": 1.2037752866744995, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 3.7035, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.00406393931183961, | |
| "grad_norm": 1.4434421062469482, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 3.7721, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004334868599295584, | |
| "grad_norm": 1.6885652542114258, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 3.9332, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004605797886751558, | |
| "grad_norm": 1.7948238849639893, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 3.467, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004876727174207532, | |
| "grad_norm": 1.9752076864242554, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 3.9104, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.004876727174207532, | |
| "eval_loss": 1.873294472694397, | |
| "eval_runtime": 233.735, | |
| "eval_samples_per_second": 13.297, | |
| "eval_steps_per_second": 1.664, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005147656461663506, | |
| "grad_norm": 2.20110821723938, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 3.4929, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.00541858574911948, | |
| "grad_norm": 1.6183526515960693, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 3.768, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005689515036575454, | |
| "grad_norm": 1.4906808137893677, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 4.0027, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005960444324031428, | |
| "grad_norm": 1.279463529586792, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 3.181, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006231373611487402, | |
| "grad_norm": 1.5670361518859863, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 3.6572, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006502302898943376, | |
| "grad_norm": 1.7471691370010376, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 3.8337, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00677323218639935, | |
| "grad_norm": 1.6388347148895264, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.8581, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007044161473855324, | |
| "grad_norm": 1.5806576013565063, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 3.7995, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007315090761311298, | |
| "grad_norm": 1.4929829835891724, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 3.9813, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007315090761311298, | |
| "eval_loss": 1.7370423078536987, | |
| "eval_runtime": 233.8325, | |
| "eval_samples_per_second": 13.292, | |
| "eval_steps_per_second": 1.664, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007586020048767272, | |
| "grad_norm": 1.6387741565704346, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 3.6443, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.007856949336223246, | |
| "grad_norm": 1.9017878770828247, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 4.1088, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.00812787862367922, | |
| "grad_norm": 1.892134428024292, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 3.7689, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.008398807911135195, | |
| "grad_norm": 1.6073269844055176, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 3.5192, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008669737198591168, | |
| "grad_norm": 1.9570190906524658, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 3.852, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008940666486047142, | |
| "grad_norm": 1.5949461460113525, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 3.4371, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009211595773503115, | |
| "grad_norm": 1.2864899635314941, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 2.9907, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.00948252506095909, | |
| "grad_norm": 1.1819583177566528, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 2.6687, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.009753454348415064, | |
| "grad_norm": 1.6467957496643066, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 3.2719, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009753454348415064, | |
| "eval_loss": 1.6752654314041138, | |
| "eval_runtime": 233.8576, | |
| "eval_samples_per_second": 13.29, | |
| "eval_steps_per_second": 1.663, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010024383635871038, | |
| "grad_norm": 1.2391555309295654, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 3.0545, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010295312923327011, | |
| "grad_norm": 1.87485933303833, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 3.2457, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010566242210782985, | |
| "grad_norm": 1.3642981052398682, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 2.9937, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.01083717149823896, | |
| "grad_norm": 2.1650807857513428, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 3.3383, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.011108100785694934, | |
| "grad_norm": 1.1839669942855835, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 3.3796, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011379030073150907, | |
| "grad_norm": 1.4667418003082275, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 3.1791, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01164995936060688, | |
| "grad_norm": 2.1223866939544678, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 3.541, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.011920888648062856, | |
| "grad_norm": 1.6458444595336914, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 3.2844, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.01219181793551883, | |
| "grad_norm": 1.5712699890136719, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 3.2106, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01219181793551883, | |
| "eval_loss": 1.638505220413208, | |
| "eval_runtime": 234.0386, | |
| "eval_samples_per_second": 13.28, | |
| "eval_steps_per_second": 1.662, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.012462747222974803, | |
| "grad_norm": 1.6857413053512573, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 3.5275, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.012733676510430777, | |
| "grad_norm": 2.234515905380249, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 3.6425, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.013004605797886752, | |
| "grad_norm": 1.8203272819519043, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 2.9848, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013275535085342726, | |
| "grad_norm": 2.177682399749756, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 3.8714, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0135464643727987, | |
| "grad_norm": 1.284415364265442, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 2.8472, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013817393660254673, | |
| "grad_norm": 1.7614214420318604, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 3.1347, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.014088322947710648, | |
| "grad_norm": 1.6398626565933228, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 3.2098, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.014359252235166622, | |
| "grad_norm": 1.405993938446045, | |
| "learning_rate": 5.348782368720626e-05, | |
| "loss": 2.858, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.014630181522622595, | |
| "grad_norm": 1.9929529428482056, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 3.2367, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.014630181522622595, | |
| "eval_loss": 1.6083791255950928, | |
| "eval_runtime": 234.097, | |
| "eval_samples_per_second": 13.277, | |
| "eval_steps_per_second": 1.662, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.014901110810078569, | |
| "grad_norm": 1.4126490354537964, | |
| "learning_rate": 5e-05, | |
| "loss": 3.062, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.015172040097534544, | |
| "grad_norm": 1.6564135551452637, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 3.5186, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.015442969384990518, | |
| "grad_norm": 2.3048603534698486, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 3.425, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.01571389867244649, | |
| "grad_norm": 2.091020107269287, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 3.7023, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.015984827959902467, | |
| "grad_norm": 1.5611733198165894, | |
| "learning_rate": 4.3041344951996746e-05, | |
| "loss": 3.481, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.01625575724735844, | |
| "grad_norm": 1.8734015226364136, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 2.9785, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.016526686534814414, | |
| "grad_norm": 1.6963518857955933, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 2.8544, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.01679761582227039, | |
| "grad_norm": 1.8010172843933105, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 3.151, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.01706854510972636, | |
| "grad_norm": 1.5065714120864868, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 2.8421, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.01706854510972636, | |
| "eval_loss": 1.5903106927871704, | |
| "eval_runtime": 234.0281, | |
| "eval_samples_per_second": 13.28, | |
| "eval_steps_per_second": 1.662, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.017339474397182336, | |
| "grad_norm": 1.854354739189148, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 3.0782, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.017610403684638308, | |
| "grad_norm": 1.5748767852783203, | |
| "learning_rate": 3.289899283371657e-05, | |
| "loss": 2.8266, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.017881332972094283, | |
| "grad_norm": 2.1482014656066895, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 2.9115, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.01815226225955026, | |
| "grad_norm": 1.5997191667556763, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 3.0273, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.01842319154700623, | |
| "grad_norm": 1.9772167205810547, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 3.3768, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.018694120834462206, | |
| "grad_norm": 1.9302130937576294, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 3.3976, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.01896505012191818, | |
| "grad_norm": 1.626615047454834, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.3308, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.019235979409374153, | |
| "grad_norm": 2.0286331176757812, | |
| "learning_rate": 2.350403678833976e-05, | |
| "loss": 3.3103, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.019506908696830128, | |
| "grad_norm": 2.0638129711151123, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 3.4762, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.019506908696830128, | |
| "eval_loss": 1.576021671295166, | |
| "eval_runtime": 233.8565, | |
| "eval_samples_per_second": 13.29, | |
| "eval_steps_per_second": 1.663, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.0197778379842861, | |
| "grad_norm": 1.4248108863830566, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 2.6845, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.020048767271742075, | |
| "grad_norm": 2.354829788208008, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 3.6582, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.02031969655919805, | |
| "grad_norm": 1.7262550592422485, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 3.2972, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.020590625846654022, | |
| "grad_norm": 2.1070995330810547, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 2.8003, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.020861555134109998, | |
| "grad_norm": 1.7353930473327637, | |
| "learning_rate": 1.526708147705013e-05, | |
| "loss": 2.8643, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.02113248442156597, | |
| "grad_norm": 1.5347745418548584, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 3.3596, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.021403413709021945, | |
| "grad_norm": 2.028477668762207, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 3.304, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.02167434299647792, | |
| "grad_norm": 2.2143213748931885, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 3.6186, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.021945272283933892, | |
| "grad_norm": 1.5614761114120483, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 2.5853, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.021945272283933892, | |
| "eval_loss": 1.5685601234436035, | |
| "eval_runtime": 234.3138, | |
| "eval_samples_per_second": 13.264, | |
| "eval_steps_per_second": 1.66, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.022216201571389867, | |
| "grad_norm": 2.075254201889038, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 2.9721, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.022487130858845843, | |
| "grad_norm": 1.7247716188430786, | |
| "learning_rate": 8.548121372247918e-06, | |
| "loss": 3.0975, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.022758060146301815, | |
| "grad_norm": 1.402299165725708, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 3.0619, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.02302898943375779, | |
| "grad_norm": 1.8681529760360718, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.9484, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.02329991872121376, | |
| "grad_norm": 1.9394612312316895, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 3.5302, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.023570848008669737, | |
| "grad_norm": 2.028913974761963, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 3.3207, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.023841777296125712, | |
| "grad_norm": 2.744318962097168, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 3.9265, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.024112706583581684, | |
| "grad_norm": 1.7354165315628052, | |
| "learning_rate": 3.6408072716606346e-06, | |
| "loss": 3.1633, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.02438363587103766, | |
| "grad_norm": 1.4790713787078857, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 2.5952, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02438363587103766, | |
| "eval_loss": 1.565293312072754, | |
| "eval_runtime": 233.712, | |
| "eval_samples_per_second": 13.298, | |
| "eval_steps_per_second": 1.664, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.024654565158493635, | |
| "grad_norm": 2.140333890914917, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 3.3539, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.024925494445949607, | |
| "grad_norm": 1.8280593156814575, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 3.2755, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.025196423733405582, | |
| "grad_norm": 1.7533349990844727, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 3.144, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.025467353020861554, | |
| "grad_norm": 1.1463032960891724, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 2.7731, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.02573828230831753, | |
| "grad_norm": 2.131800651550293, | |
| "learning_rate": 7.596123493895991e-07, | |
| "loss": 3.745, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.026009211595773504, | |
| "grad_norm": 1.580354928970337, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 2.718, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.026280140883229476, | |
| "grad_norm": 1.5779976844787598, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 2.9536, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.02655107017068545, | |
| "grad_norm": 1.7121436595916748, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 3.272, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.026821999458141427, | |
| "grad_norm": 1.9496688842773438, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 3.1555, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.026821999458141427, | |
| "eval_loss": 1.5646346807479858, | |
| "eval_runtime": 233.9547, | |
| "eval_samples_per_second": 13.285, | |
| "eval_steps_per_second": 1.663, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.0270929287455974, | |
| "grad_norm": 2.362600088119507, | |
| "learning_rate": 0.0, | |
| "loss": 3.1908, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.301305142280192e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |