| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.7777777777777777, |
| "eval_steps": 100, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.008888888888888889, |
| "grad_norm": 6.312672588322296, |
| "learning_rate": 1.4792899408284025e-07, |
| "loss": 1.1997, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.017777777777777778, |
| "grad_norm": 6.5395437094474875, |
| "learning_rate": 2.958579881656805e-07, |
| "loss": 1.2188, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.02666666666666667, |
| "grad_norm": 5.051656620162693, |
| "learning_rate": 4.4378698224852073e-07, |
| "loss": 1.1654, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.035555555555555556, |
| "grad_norm": 3.245773084025693, |
| "learning_rate": 5.91715976331361e-07, |
| "loss": 1.0942, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.044444444444444446, |
| "grad_norm": 2.594184571301331, |
| "learning_rate": 7.396449704142013e-07, |
| "loss": 1.0498, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.05333333333333334, |
| "grad_norm": 2.168963351286361, |
| "learning_rate": 8.875739644970415e-07, |
| "loss": 0.9403, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.06222222222222222, |
| "grad_norm": 1.9004139854270057, |
| "learning_rate": 1.0355029585798817e-06, |
| "loss": 0.9099, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.07111111111111111, |
| "grad_norm": 2.2242455117026494, |
| "learning_rate": 1.183431952662722e-06, |
| "loss": 0.8998, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.08, |
| "grad_norm": 1.8519949378838332, |
| "learning_rate": 1.3313609467455623e-06, |
| "loss": 0.859, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.08888888888888889, |
| "grad_norm": 1.8728553263645957, |
| "learning_rate": 1.4792899408284026e-06, |
| "loss": 0.8711, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.08888888888888889, |
| "eval_loss": 0.8548257946968079, |
| "eval_runtime": 38.267, |
| "eval_samples_per_second": 52.264, |
| "eval_steps_per_second": 6.533, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.09777777777777778, |
| "grad_norm": 2.116764307544036, |
| "learning_rate": 1.6272189349112426e-06, |
| "loss": 0.8557, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.10666666666666667, |
| "grad_norm": 2.0364313595247467, |
| "learning_rate": 1.775147928994083e-06, |
| "loss": 0.8619, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.11555555555555555, |
| "grad_norm": 1.7761221870002313, |
| "learning_rate": 1.9230769230769234e-06, |
| "loss": 0.86, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.12444444444444444, |
| "grad_norm": 1.8902384905200484, |
| "learning_rate": 2.0710059171597635e-06, |
| "loss": 0.8483, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.13333333333333333, |
| "grad_norm": 2.0970800465534793, |
| "learning_rate": 2.2189349112426035e-06, |
| "loss": 0.8841, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.14222222222222222, |
| "grad_norm": 2.0388812214422005, |
| "learning_rate": 2.366863905325444e-06, |
| "loss": 0.8491, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.1511111111111111, |
| "grad_norm": 1.9949400049388208, |
| "learning_rate": 2.5147928994082845e-06, |
| "loss": 0.8252, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 1.7986729179125904, |
| "learning_rate": 2.6627218934911246e-06, |
| "loss": 0.8345, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.1688888888888889, |
| "grad_norm": 1.8870696385512356, |
| "learning_rate": 2.8106508875739646e-06, |
| "loss": 0.8259, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.17777777777777778, |
| "grad_norm": 1.8573694639357368, |
| "learning_rate": 2.958579881656805e-06, |
| "loss": 0.8052, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.17777777777777778, |
| "eval_loss": 0.8143225312232971, |
| "eval_runtime": 37.9982, |
| "eval_samples_per_second": 52.634, |
| "eval_steps_per_second": 6.579, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.18666666666666668, |
| "grad_norm": 1.8655947177959404, |
| "learning_rate": 3.106508875739645e-06, |
| "loss": 0.827, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.19555555555555557, |
| "grad_norm": 1.870936582770945, |
| "learning_rate": 3.2544378698224853e-06, |
| "loss": 0.813, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.20444444444444446, |
| "grad_norm": 2.109320545375679, |
| "learning_rate": 3.4023668639053257e-06, |
| "loss": 0.8174, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.21333333333333335, |
| "grad_norm": 1.8097321542077869, |
| "learning_rate": 3.550295857988166e-06, |
| "loss": 0.8182, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.2222222222222222, |
| "grad_norm": 1.728199611021706, |
| "learning_rate": 3.6982248520710063e-06, |
| "loss": 0.8123, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.2311111111111111, |
| "grad_norm": 2.0315555925984348, |
| "learning_rate": 3.846153846153847e-06, |
| "loss": 0.7728, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.24, |
| "grad_norm": 1.5850711075399915, |
| "learning_rate": 3.9940828402366864e-06, |
| "loss": 0.7917, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.24888888888888888, |
| "grad_norm": 1.927987824759959, |
| "learning_rate": 4.142011834319527e-06, |
| "loss": 0.8142, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.2577777777777778, |
| "grad_norm": 1.9163193176432178, |
| "learning_rate": 4.289940828402367e-06, |
| "loss": 0.8177, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.26666666666666666, |
| "grad_norm": 1.9493054796009528, |
| "learning_rate": 4.437869822485207e-06, |
| "loss": 0.8071, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.26666666666666666, |
| "eval_loss": 0.8015236854553223, |
| "eval_runtime": 38.0122, |
| "eval_samples_per_second": 52.615, |
| "eval_steps_per_second": 6.577, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.27555555555555555, |
| "grad_norm": 1.7023378433784926, |
| "learning_rate": 4.5857988165680475e-06, |
| "loss": 0.8152, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.28444444444444444, |
| "grad_norm": 1.8979776132841102, |
| "learning_rate": 4.733727810650888e-06, |
| "loss": 0.8301, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.29333333333333333, |
| "grad_norm": 1.975097152658989, |
| "learning_rate": 4.8816568047337285e-06, |
| "loss": 0.8332, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.3022222222222222, |
| "grad_norm": 1.8218939536712146, |
| "learning_rate": 4.99999464967688e-06, |
| "loss": 0.8286, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.3111111111111111, |
| "grad_norm": 1.8977171195446734, |
| "learning_rate": 4.999807390772256e-06, |
| "loss": 0.8209, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 1.880983857135489, |
| "learning_rate": 4.999352638611963e-06, |
| "loss": 0.8311, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.3288888888888889, |
| "grad_norm": 2.085715913698874, |
| "learning_rate": 4.998630441857007e-06, |
| "loss": 0.8194, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.3377777777777778, |
| "grad_norm": 1.8193588799474414, |
| "learning_rate": 4.997640877786446e-06, |
| "loss": 0.7961, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.3466666666666667, |
| "grad_norm": 1.7395847960563042, |
| "learning_rate": 4.996384052289124e-06, |
| "loss": 0.8235, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 1.7517335960292617, |
| "learning_rate": 4.994860099852339e-06, |
| "loss": 0.7912, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.35555555555555557, |
| "eval_loss": 0.7962385416030884, |
| "eval_runtime": 38.0506, |
| "eval_samples_per_second": 52.562, |
| "eval_steps_per_second": 6.57, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.36444444444444446, |
| "grad_norm": 1.7751508270993985, |
| "learning_rate": 4.993069183547456e-06, |
| "loss": 0.7956, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.37333333333333335, |
| "grad_norm": 1.905940982272453, |
| "learning_rate": 4.991011495012451e-06, |
| "loss": 0.8383, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.38222222222222224, |
| "grad_norm": 1.9604410876662892, |
| "learning_rate": 4.98868725443141e-06, |
| "loss": 0.8427, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.39111111111111113, |
| "grad_norm": 1.8801968456938927, |
| "learning_rate": 4.986096710510968e-06, |
| "loss": 0.8253, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.4, |
| "grad_norm": 1.834581689663337, |
| "learning_rate": 4.9832401404536915e-06, |
| "loss": 0.8211, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.4088888888888889, |
| "grad_norm": 1.816476724466639, |
| "learning_rate": 4.980117849928419e-06, |
| "loss": 0.792, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.4177777777777778, |
| "grad_norm": 1.7561196396819305, |
| "learning_rate": 4.976730173037556e-06, |
| "loss": 0.8199, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.4266666666666667, |
| "grad_norm": 1.883523346070099, |
| "learning_rate": 4.973077472281319e-06, |
| "loss": 0.8085, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.43555555555555553, |
| "grad_norm": 1.8002160041857591, |
| "learning_rate": 4.969160138518946e-06, |
| "loss": 0.7981, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "grad_norm": 1.8807969403322338, |
| "learning_rate": 4.964978590926879e-06, |
| "loss": 0.8086, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.4444444444444444, |
| "eval_loss": 0.7913944721221924, |
| "eval_runtime": 37.9142, |
| "eval_samples_per_second": 52.751, |
| "eval_steps_per_second": 6.594, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.4533333333333333, |
| "grad_norm": 1.7162663123083326, |
| "learning_rate": 4.960533276953902e-06, |
| "loss": 0.8121, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.4622222222222222, |
| "grad_norm": 1.8966249612321189, |
| "learning_rate": 4.955824672273265e-06, |
| "loss": 0.7929, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.4711111111111111, |
| "grad_norm": 1.9877589179045125, |
| "learning_rate": 4.950853280731785e-06, |
| "loss": 0.8092, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 1.6886441919837933, |
| "learning_rate": 4.945619634295929e-06, |
| "loss": 0.8393, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.4888888888888889, |
| "grad_norm": 1.6732855356580696, |
| "learning_rate": 4.940124292994895e-06, |
| "loss": 0.8036, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.49777777777777776, |
| "grad_norm": 1.8728351825828837, |
| "learning_rate": 4.9343678448606816e-06, |
| "loss": 0.8118, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.5066666666666667, |
| "grad_norm": 1.7910848529169285, |
| "learning_rate": 4.928350905865165e-06, |
| "loss": 0.7975, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.5155555555555555, |
| "grad_norm": 1.8879257679795278, |
| "learning_rate": 4.92207411985419e-06, |
| "loss": 0.8133, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.5244444444444445, |
| "grad_norm": 1.82915454709858, |
| "learning_rate": 4.915538158478674e-06, |
| "loss": 0.8131, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "grad_norm": 1.9822261774763363, |
| "learning_rate": 4.908743721122734e-06, |
| "loss": 0.7614, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.5333333333333333, |
| "eval_loss": 0.7859019637107849, |
| "eval_runtime": 37.9245, |
| "eval_samples_per_second": 52.736, |
| "eval_steps_per_second": 6.592, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.5422222222222223, |
| "grad_norm": 1.7590845282435732, |
| "learning_rate": 4.901691534828853e-06, |
| "loss": 0.785, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.5511111111111111, |
| "grad_norm": 1.7642623616476127, |
| "learning_rate": 4.894382354220077e-06, |
| "loss": 0.8031, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.56, |
| "grad_norm": 1.9487864823051528, |
| "learning_rate": 4.886816961419272e-06, |
| "loss": 0.7899, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.5688888888888889, |
| "grad_norm": 1.8294787755068975, |
| "learning_rate": 4.8789961659654276e-06, |
| "loss": 0.8079, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.5777777777777777, |
| "grad_norm": 1.8448471765270655, |
| "learning_rate": 4.870920804727034e-06, |
| "loss": 0.8053, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.5866666666666667, |
| "grad_norm": 1.9086870869024488, |
| "learning_rate": 4.862591741812533e-06, |
| "loss": 0.7919, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.5955555555555555, |
| "grad_norm": 1.8399676032417565, |
| "learning_rate": 4.8540098684778505e-06, |
| "loss": 0.8049, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.6044444444444445, |
| "grad_norm": 1.7627163023842312, |
| "learning_rate": 4.845176103031035e-06, |
| "loss": 0.7853, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.6133333333333333, |
| "grad_norm": 1.880754220932831, |
| "learning_rate": 4.836091390733983e-06, |
| "loss": 0.7671, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.6222222222222222, |
| "grad_norm": 1.9327151521828667, |
| "learning_rate": 4.826756703701298e-06, |
| "loss": 0.7758, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.6222222222222222, |
| "eval_loss": 0.7827751636505127, |
| "eval_runtime": 37.9583, |
| "eval_samples_per_second": 52.689, |
| "eval_steps_per_second": 6.586, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.6311111111111111, |
| "grad_norm": 1.7085337797540057, |
| "learning_rate": 4.817173040796263e-06, |
| "loss": 0.7581, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 1.8693393810766439, |
| "learning_rate": 4.807341427523969e-06, |
| "loss": 0.8092, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.6488888888888888, |
| "grad_norm": 1.9224847774084641, |
| "learning_rate": 4.797262915921561e-06, |
| "loss": 0.7905, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.6577777777777778, |
| "grad_norm": 1.7921622260237242, |
| "learning_rate": 4.7869385844456825e-06, |
| "loss": 0.8371, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.6666666666666666, |
| "grad_norm": 1.7662786771403587, |
| "learning_rate": 4.776369537857062e-06, |
| "loss": 0.8039, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.6755555555555556, |
| "grad_norm": 1.67555577960425, |
| "learning_rate": 4.765556907102306e-06, |
| "loss": 0.8153, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.6844444444444444, |
| "grad_norm": 1.8971436028748803, |
| "learning_rate": 4.7545018491928755e-06, |
| "loss": 0.777, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.6933333333333334, |
| "grad_norm": 1.6522195956975418, |
| "learning_rate": 4.743205547081281e-06, |
| "loss": 0.7826, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.7022222222222222, |
| "grad_norm": 1.678020666686354, |
| "learning_rate": 4.731669209534504e-06, |
| "loss": 0.797, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 1.8314853043295487, |
| "learning_rate": 4.719894071004645e-06, |
| "loss": 0.8026, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "eval_loss": 0.77940833568573, |
| "eval_runtime": 37.9303, |
| "eval_samples_per_second": 52.728, |
| "eval_steps_per_second": 6.591, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.72, |
| "grad_norm": 1.6824200358042496, |
| "learning_rate": 4.707881391496837e-06, |
| "loss": 0.7976, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.7288888888888889, |
| "grad_norm": 1.7994312639466354, |
| "learning_rate": 4.695632456434414e-06, |
| "loss": 0.7883, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.7377777777777778, |
| "grad_norm": 1.873881222655515, |
| "learning_rate": 4.683148576521363e-06, |
| "loss": 0.7901, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.7466666666666667, |
| "grad_norm": 1.7081859666296215, |
| "learning_rate": 4.670431087602079e-06, |
| "loss": 0.7747, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.7555555555555555, |
| "grad_norm": 1.817576578011179, |
| "learning_rate": 4.657481350518409e-06, |
| "loss": 0.8109, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.7644444444444445, |
| "grad_norm": 1.827616370549138, |
| "learning_rate": 4.644300750964045e-06, |
| "loss": 0.8191, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.7733333333333333, |
| "grad_norm": 1.783716604929134, |
| "learning_rate": 4.630890699336244e-06, |
| "loss": 0.7728, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.7822222222222223, |
| "grad_norm": 1.8315774625359147, |
| "learning_rate": 4.6172526305849094e-06, |
| "loss": 0.7899, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.7911111111111111, |
| "grad_norm": 1.9174012768682513, |
| "learning_rate": 4.603388004059037e-06, |
| "loss": 0.8334, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 1.7128496253638654, |
| "learning_rate": 4.589298303350565e-06, |
| "loss": 0.8, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.8, |
| "eval_loss": 0.7756551504135132, |
| "eval_runtime": 38.0779, |
| "eval_samples_per_second": 52.524, |
| "eval_steps_per_second": 6.565, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.8088888888888889, |
| "grad_norm": 2.087290188435175, |
| "learning_rate": 4.574985036135613e-06, |
| "loss": 0.7719, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.8177777777777778, |
| "grad_norm": 1.7974331962068042, |
| "learning_rate": 4.5604497340131635e-06, |
| "loss": 0.765, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.8266666666666667, |
| "grad_norm": 1.722447066657561, |
| "learning_rate": 4.545693952341159e-06, |
| "loss": 0.8213, |
| "step": 930 |
| }, |
| { |
| "epoch": 0.8355555555555556, |
| "grad_norm": 1.8137932027496781, |
| "learning_rate": 4.5307192700700804e-06, |
| "loss": 0.8189, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.8444444444444444, |
| "grad_norm": 1.7200813454468675, |
| "learning_rate": 4.515527289573986e-06, |
| "loss": 0.7995, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.8533333333333334, |
| "grad_norm": 1.7492699579153432, |
| "learning_rate": 4.50011963647905e-06, |
| "loss": 0.8045, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.8622222222222222, |
| "grad_norm": 1.8904981608159812, |
| "learning_rate": 4.484497959489608e-06, |
| "loss": 0.8056, |
| "step": 970 |
| }, |
| { |
| "epoch": 0.8711111111111111, |
| "grad_norm": 1.7842392668053924, |
| "learning_rate": 4.468663930211743e-06, |
| "loss": 0.7881, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.88, |
| "grad_norm": 1.8109751414374233, |
| "learning_rate": 4.452619242974408e-06, |
| "loss": 0.7913, |
| "step": 990 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "grad_norm": 1.6941534156764066, |
| "learning_rate": 4.436365614648128e-06, |
| "loss": 0.7568, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.8888888888888888, |
| "eval_loss": 0.7739697098731995, |
| "eval_runtime": 38.0044, |
| "eval_samples_per_second": 52.625, |
| "eval_steps_per_second": 6.578, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.8977777777777778, |
| "grad_norm": 1.7398957715176837, |
| "learning_rate": 4.4199047844612825e-06, |
| "loss": 0.812, |
| "step": 1010 |
| }, |
| { |
| "epoch": 0.9066666666666666, |
| "grad_norm": 1.804683657893465, |
| "learning_rate": 4.4032385138139985e-06, |
| "loss": 0.8158, |
| "step": 1020 |
| }, |
| { |
| "epoch": 0.9155555555555556, |
| "grad_norm": 1.8261068083326866, |
| "learning_rate": 4.386368586089674e-06, |
| "loss": 0.7766, |
| "step": 1030 |
| }, |
| { |
| "epoch": 0.9244444444444444, |
| "grad_norm": 1.929492696716588, |
| "learning_rate": 4.369296806464141e-06, |
| "loss": 0.801, |
| "step": 1040 |
| }, |
| { |
| "epoch": 0.9333333333333333, |
| "grad_norm": 1.8472605566952744, |
| "learning_rate": 4.3520250017125076e-06, |
| "loss": 0.7876, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.9422222222222222, |
| "grad_norm": 1.790367907695698, |
| "learning_rate": 4.334555020013675e-06, |
| "loss": 0.7681, |
| "step": 1060 |
| }, |
| { |
| "epoch": 0.9511111111111111, |
| "grad_norm": 1.6599756385687388, |
| "learning_rate": 4.316888730752583e-06, |
| "loss": 0.8135, |
| "step": 1070 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 1.6291519979649327, |
| "learning_rate": 4.299028024320166e-06, |
| "loss": 0.7741, |
| "step": 1080 |
| }, |
| { |
| "epoch": 0.9688888888888889, |
| "grad_norm": 1.5442340466379858, |
| "learning_rate": 4.280974811911071e-06, |
| "loss": 0.8041, |
| "step": 1090 |
| }, |
| { |
| "epoch": 0.9777777777777777, |
| "grad_norm": 1.7271244824498846, |
| "learning_rate": 4.262731025319159e-06, |
| "loss": 0.7954, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.9777777777777777, |
| "eval_loss": 0.771242082118988, |
| "eval_runtime": 38.2542, |
| "eval_samples_per_second": 52.282, |
| "eval_steps_per_second": 6.535, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.9866666666666667, |
| "grad_norm": 1.730188161467645, |
| "learning_rate": 4.244298616730781e-06, |
| "loss": 0.8021, |
| "step": 1110 |
| }, |
| { |
| "epoch": 0.9955555555555555, |
| "grad_norm": 1.739908218239288, |
| "learning_rate": 4.2256795585158894e-06, |
| "loss": 0.8171, |
| "step": 1120 |
| }, |
| { |
| "epoch": 1.0044444444444445, |
| "grad_norm": 1.6139566050826326, |
| "learning_rate": 4.2068758430169805e-06, |
| "loss": 0.708, |
| "step": 1130 |
| }, |
| { |
| "epoch": 1.0133333333333334, |
| "grad_norm": 1.626198851176862, |
| "learning_rate": 4.187889482335905e-06, |
| "loss": 0.6309, |
| "step": 1140 |
| }, |
| { |
| "epoch": 1.0222222222222221, |
| "grad_norm": 1.7768887610773263, |
| "learning_rate": 4.168722508118562e-06, |
| "loss": 0.6455, |
| "step": 1150 |
| }, |
| { |
| "epoch": 1.031111111111111, |
| "grad_norm": 1.5692860084569409, |
| "learning_rate": 4.1493769713374995e-06, |
| "loss": 0.6528, |
| "step": 1160 |
| }, |
| { |
| "epoch": 1.04, |
| "grad_norm": 1.6046426624256729, |
| "learning_rate": 4.12985494207245e-06, |
| "loss": 0.6443, |
| "step": 1170 |
| }, |
| { |
| "epoch": 1.048888888888889, |
| "grad_norm": 1.741907151593938, |
| "learning_rate": 4.110158509288822e-06, |
| "loss": 0.6194, |
| "step": 1180 |
| }, |
| { |
| "epoch": 1.0577777777777777, |
| "grad_norm": 1.7983079569047793, |
| "learning_rate": 4.090289780614167e-06, |
| "loss": 0.6544, |
| "step": 1190 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 1.955188619876201, |
| "learning_rate": 4.070250882112652e-06, |
| "loss": 0.6518, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "eval_loss": 0.7851578593254089, |
| "eval_runtime": 38.1241, |
| "eval_samples_per_second": 52.46, |
| "eval_steps_per_second": 6.558, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.0755555555555556, |
| "grad_norm": 1.7232020856742132, |
| "learning_rate": 4.050043958057561e-06, |
| "loss": 0.6258, |
| "step": 1210 |
| }, |
| { |
| "epoch": 1.0844444444444445, |
| "grad_norm": 1.593862025253077, |
| "learning_rate": 4.029671170701841e-06, |
| "loss": 0.6347, |
| "step": 1220 |
| }, |
| { |
| "epoch": 1.0933333333333333, |
| "grad_norm": 1.8219516480738216, |
| "learning_rate": 4.009134700046735e-06, |
| "loss": 0.6266, |
| "step": 1230 |
| }, |
| { |
| "epoch": 1.1022222222222222, |
| "grad_norm": 1.714593831219954, |
| "learning_rate": 3.988436743608506e-06, |
| "loss": 0.6077, |
| "step": 1240 |
| }, |
| { |
| "epoch": 1.1111111111111112, |
| "grad_norm": 1.7671062357329015, |
| "learning_rate": 3.967579516183292e-06, |
| "loss": 0.6797, |
| "step": 1250 |
| }, |
| { |
| "epoch": 1.12, |
| "grad_norm": 1.6809718048297995, |
| "learning_rate": 3.946565249610108e-06, |
| "loss": 0.6416, |
| "step": 1260 |
| }, |
| { |
| "epoch": 1.1288888888888888, |
| "grad_norm": 1.7070363329071652, |
| "learning_rate": 3.925396192532032e-06, |
| "loss": 0.6252, |
| "step": 1270 |
| }, |
| { |
| "epoch": 1.1377777777777778, |
| "grad_norm": 1.7723751757721016, |
| "learning_rate": 3.90407461015558e-06, |
| "loss": 0.6467, |
| "step": 1280 |
| }, |
| { |
| "epoch": 1.1466666666666667, |
| "grad_norm": 1.7601350100326427, |
| "learning_rate": 3.882602784008327e-06, |
| "loss": 0.6068, |
| "step": 1290 |
| }, |
| { |
| "epoch": 1.1555555555555554, |
| "grad_norm": 1.7206913356738147, |
| "learning_rate": 3.8609830116947596e-06, |
| "loss": 0.6344, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.1555555555555554, |
| "eval_loss": 0.7862110137939453, |
| "eval_runtime": 37.9389, |
| "eval_samples_per_second": 52.716, |
| "eval_steps_per_second": 6.59, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.1644444444444444, |
| "grad_norm": 1.6860528463901245, |
| "learning_rate": 3.839217606650426e-06, |
| "loss": 0.6412, |
| "step": 1310 |
| }, |
| { |
| "epoch": 1.1733333333333333, |
| "grad_norm": 1.8854670032384495, |
| "learning_rate": 3.817308897894387e-06, |
| "loss": 0.6335, |
| "step": 1320 |
| }, |
| { |
| "epoch": 1.1822222222222223, |
| "grad_norm": 1.728477549429402, |
| "learning_rate": 3.7952592297799904e-06, |
| "loss": 0.6068, |
| "step": 1330 |
| }, |
| { |
| "epoch": 1.1911111111111112, |
| "grad_norm": 1.6820412004849736, |
| "learning_rate": 3.7730709617440227e-06, |
| "loss": 0.6379, |
| "step": 1340 |
| }, |
| { |
| "epoch": 1.2, |
| "grad_norm": 1.648510966848167, |
| "learning_rate": 3.750746468054227e-06, |
| "loss": 0.625, |
| "step": 1350 |
| }, |
| { |
| "epoch": 1.208888888888889, |
| "grad_norm": 1.548799904758873, |
| "learning_rate": 3.7282881375552475e-06, |
| "loss": 0.622, |
| "step": 1360 |
| }, |
| { |
| "epoch": 1.2177777777777778, |
| "grad_norm": 1.6536705835515702, |
| "learning_rate": 3.70569837341301e-06, |
| "loss": 0.6554, |
| "step": 1370 |
| }, |
| { |
| "epoch": 1.2266666666666666, |
| "grad_norm": 1.6426851875006678, |
| "learning_rate": 3.6829795928575703e-06, |
| "loss": 0.6234, |
| "step": 1380 |
| }, |
| { |
| "epoch": 1.2355555555555555, |
| "grad_norm": 1.6903272164553882, |
| "learning_rate": 3.6601342269244528e-06, |
| "loss": 0.6482, |
| "step": 1390 |
| }, |
| { |
| "epoch": 1.2444444444444445, |
| "grad_norm": 1.86253547762314, |
| "learning_rate": 3.6371647201945216e-06, |
| "loss": 0.6181, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.2444444444444445, |
| "eval_loss": 0.7869328856468201, |
| "eval_runtime": 38.111, |
| "eval_samples_per_second": 52.478, |
| "eval_steps_per_second": 6.56, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.2533333333333334, |
| "grad_norm": 1.6989175526314024, |
| "learning_rate": 3.6140735305323943e-06, |
| "loss": 0.6278, |
| "step": 1410 |
| }, |
| { |
| "epoch": 1.2622222222222224, |
| "grad_norm": 1.8101109025301771, |
| "learning_rate": 3.5908631288234374e-06, |
| "loss": 0.6706, |
| "step": 1420 |
| }, |
| { |
| "epoch": 1.271111111111111, |
| "grad_norm": 1.9867263313582206, |
| "learning_rate": 3.5675359987093665e-06, |
| "loss": 0.6385, |
| "step": 1430 |
| }, |
| { |
| "epoch": 1.28, |
| "grad_norm": 1.7574128013903643, |
| "learning_rate": 3.5440946363224855e-06, |
| "loss": 0.6301, |
| "step": 1440 |
| }, |
| { |
| "epoch": 1.2888888888888888, |
| "grad_norm": 1.4549225489268687, |
| "learning_rate": 3.5205415500185836e-06, |
| "loss": 0.6311, |
| "step": 1450 |
| }, |
| { |
| "epoch": 1.2977777777777777, |
| "grad_norm": 1.6494499992222607, |
| "learning_rate": 3.4968792601085296e-06, |
| "loss": 0.6596, |
| "step": 1460 |
| }, |
| { |
| "epoch": 1.3066666666666666, |
| "grad_norm": 1.8893405889710921, |
| "learning_rate": 3.473110298588584e-06, |
| "loss": 0.6493, |
| "step": 1470 |
| }, |
| { |
| "epoch": 1.3155555555555556, |
| "grad_norm": 1.6296063762923343, |
| "learning_rate": 3.4492372088694605e-06, |
| "loss": 0.6688, |
| "step": 1480 |
| }, |
| { |
| "epoch": 1.3244444444444445, |
| "grad_norm": 1.8187009493229125, |
| "learning_rate": 3.4252625455041684e-06, |
| "loss": 0.6553, |
| "step": 1490 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "grad_norm": 1.6186019742868865, |
| "learning_rate": 3.4011888739146587e-06, |
| "loss": 0.6511, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.3333333333333333, |
| "eval_loss": 0.7797905206680298, |
| "eval_runtime": 38.0768, |
| "eval_samples_per_second": 52.525, |
| "eval_steps_per_second": 6.566, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.3422222222222222, |
| "grad_norm": 1.5328967371738955, |
| "learning_rate": 3.377018770117315e-06, |
| "loss": 0.6541, |
| "step": 1510 |
| }, |
| { |
| "epoch": 1.3511111111111112, |
| "grad_norm": 1.7168181133470535, |
| "learning_rate": 3.3527548204472985e-06, |
| "loss": 0.6492, |
| "step": 1520 |
| }, |
| { |
| "epoch": 1.3599999999999999, |
| "grad_norm": 1.82949982113254, |
| "learning_rate": 3.3283996212818015e-06, |
| "loss": 0.6125, |
| "step": 1530 |
| }, |
| { |
| "epoch": 1.3688888888888888, |
| "grad_norm": 1.967299918797367, |
| "learning_rate": 3.303955778762217e-06, |
| "loss": 0.6609, |
| "step": 1540 |
| }, |
| { |
| "epoch": 1.3777777777777778, |
| "grad_norm": 1.7517637260410819, |
| "learning_rate": 3.2794259085152703e-06, |
| "loss": 0.6451, |
| "step": 1550 |
| }, |
| { |
| "epoch": 1.3866666666666667, |
| "grad_norm": 1.7338666575605146, |
| "learning_rate": 3.254812635373128e-06, |
| "loss": 0.6064, |
| "step": 1560 |
| }, |
| { |
| "epoch": 1.3955555555555557, |
| "grad_norm": 1.805258582558589, |
| "learning_rate": 3.2301185930925318e-06, |
| "loss": 0.6349, |
| "step": 1570 |
| }, |
| { |
| "epoch": 1.4044444444444444, |
| "grad_norm": 2.0099902327429495, |
| "learning_rate": 3.205346424072967e-06, |
| "loss": 0.6354, |
| "step": 1580 |
| }, |
| { |
| "epoch": 1.4133333333333333, |
| "grad_norm": 1.6968495111035833, |
| "learning_rate": 3.180498779073915e-06, |
| "loss": 0.6008, |
| "step": 1590 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 1.8666501019542727, |
| "learning_rate": 3.1555783169312048e-06, |
| "loss": 0.6341, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "eval_loss": 0.7812256217002869, |
| "eval_runtime": 37.9688, |
| "eval_samples_per_second": 52.675, |
| "eval_steps_per_second": 6.584, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.431111111111111, |
| "grad_norm": 1.7447699710116413, |
| "learning_rate": 3.1305877042725036e-06, |
| "loss": 0.6548, |
| "step": 1610 |
| }, |
| { |
| "epoch": 1.44, |
| "grad_norm": 1.6795897002264613, |
| "learning_rate": 3.1055296152319732e-06, |
| "loss": 0.6442, |
| "step": 1620 |
| }, |
| { |
| "epoch": 1.448888888888889, |
| "grad_norm": 1.8760743794492893, |
| "learning_rate": 3.0804067311641217e-06, |
| "loss": 0.66, |
| "step": 1630 |
| }, |
| { |
| "epoch": 1.4577777777777778, |
| "grad_norm": 1.9884017264018043, |
| "learning_rate": 3.0552217403568855e-06, |
| "loss": 0.6269, |
| "step": 1640 |
| }, |
| { |
| "epoch": 1.4666666666666668, |
| "grad_norm": 1.8411666706892968, |
| "learning_rate": 3.0299773377439677e-06, |
| "loss": 0.6277, |
| "step": 1650 |
| }, |
| { |
| "epoch": 1.4755555555555555, |
| "grad_norm": 1.5184757968572182, |
| "learning_rate": 3.0046762246164608e-06, |
| "loss": 0.6382, |
| "step": 1660 |
| }, |
| { |
| "epoch": 1.4844444444444445, |
| "grad_norm": 1.9260639142140834, |
| "learning_rate": 2.979321108333799e-06, |
| "loss": 0.6097, |
| "step": 1670 |
| }, |
| { |
| "epoch": 1.4933333333333334, |
| "grad_norm": 1.741956992068052, |
| "learning_rate": 2.953914702034054e-06, |
| "loss": 0.6319, |
| "step": 1680 |
| }, |
| { |
| "epoch": 1.5022222222222221, |
| "grad_norm": 1.595093207157502, |
| "learning_rate": 2.928459724343613e-06, |
| "loss": 0.6747, |
| "step": 1690 |
| }, |
| { |
| "epoch": 1.511111111111111, |
| "grad_norm": 1.7200717117012048, |
| "learning_rate": 2.9029588990862717e-06, |
| "loss": 0.6537, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.511111111111111, |
| "eval_loss": 0.7793934941291809, |
| "eval_runtime": 38.0687, |
| "eval_samples_per_second": 52.537, |
| "eval_steps_per_second": 6.567, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.52, |
| "grad_norm": 1.6792977916911906, |
| "learning_rate": 2.8774149549917697e-06, |
| "loss": 0.6332, |
| "step": 1710 |
| }, |
| { |
| "epoch": 1.528888888888889, |
| "grad_norm": 1.7336128902509544, |
| "learning_rate": 2.8518306254037996e-06, |
| "loss": 0.6462, |
| "step": 1720 |
| }, |
| { |
| "epoch": 1.537777777777778, |
| "grad_norm": 1.6738874310796588, |
| "learning_rate": 2.82620864798753e-06, |
| "loss": 0.6446, |
| "step": 1730 |
| }, |
| { |
| "epoch": 1.5466666666666666, |
| "grad_norm": 1.5853846000954395, |
| "learning_rate": 2.800551764436652e-06, |
| "loss": 0.6864, |
| "step": 1740 |
| }, |
| { |
| "epoch": 1.5555555555555556, |
| "grad_norm": 1.7102684215364048, |
| "learning_rate": 2.774862720180008e-06, |
| "loss": 0.6244, |
| "step": 1750 |
| }, |
| { |
| "epoch": 1.5644444444444443, |
| "grad_norm": 1.6441239452770726, |
| "learning_rate": 2.749144264087814e-06, |
| "loss": 0.6183, |
| "step": 1760 |
| }, |
| { |
| "epoch": 1.5733333333333333, |
| "grad_norm": 1.8848908060309273, |
| "learning_rate": 2.7233991481775173e-06, |
| "loss": 0.6524, |
| "step": 1770 |
| }, |
| { |
| "epoch": 1.5822222222222222, |
| "grad_norm": 1.5767138461588817, |
| "learning_rate": 2.697630127319312e-06, |
| "loss": 0.6415, |
| "step": 1780 |
| }, |
| { |
| "epoch": 1.5911111111111111, |
| "grad_norm": 1.6578116610765519, |
| "learning_rate": 2.6718399589413533e-06, |
| "loss": 0.6488, |
| "step": 1790 |
| }, |
| { |
| "epoch": 1.6, |
| "grad_norm": 1.6463146375379087, |
| "learning_rate": 2.6460314027347002e-06, |
| "loss": 0.6626, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.6, |
| "eval_loss": 0.7779668569564819, |
| "eval_runtime": 38.0224, |
| "eval_samples_per_second": 52.601, |
| "eval_steps_per_second": 6.575, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.608888888888889, |
| "grad_norm": 1.3794992178377827, |
| "learning_rate": 2.6202072203580098e-06, |
| "loss": 0.6213, |
| "step": 1810 |
| }, |
| { |
| "epoch": 1.6177777777777778, |
| "grad_norm": 1.6547672801771742, |
| "learning_rate": 2.594370175142029e-06, |
| "loss": 0.622, |
| "step": 1820 |
| }, |
| { |
| "epoch": 1.6266666666666667, |
| "grad_norm": 1.8131058123768224, |
| "learning_rate": 2.5685230317938946e-06, |
| "loss": 0.6115, |
| "step": 1830 |
| }, |
| { |
| "epoch": 1.6355555555555554, |
| "grad_norm": 1.5043497534471073, |
| "learning_rate": 2.542668556101305e-06, |
| "loss": 0.6278, |
| "step": 1840 |
| }, |
| { |
| "epoch": 1.6444444444444444, |
| "grad_norm": 1.6388736348728028, |
| "learning_rate": 2.516809514636556e-06, |
| "loss": 0.6419, |
| "step": 1850 |
| }, |
| { |
| "epoch": 1.6533333333333333, |
| "grad_norm": 1.6660885474749705, |
| "learning_rate": 2.4909486744605105e-06, |
| "loss": 0.6158, |
| "step": 1860 |
| }, |
| { |
| "epoch": 1.6622222222222223, |
| "grad_norm": 1.7074374325187731, |
| "learning_rate": 2.4650888028264993e-06, |
| "loss": 0.6404, |
| "step": 1870 |
| }, |
| { |
| "epoch": 1.6711111111111112, |
| "grad_norm": 1.5200201087278384, |
| "learning_rate": 2.439232666884216e-06, |
| "loss": 0.6334, |
| "step": 1880 |
| }, |
| { |
| "epoch": 1.6800000000000002, |
| "grad_norm": 1.7294919605993466, |
| "learning_rate": 2.413383033383614e-06, |
| "loss": 0.6486, |
| "step": 1890 |
| }, |
| { |
| "epoch": 1.6888888888888889, |
| "grad_norm": 1.6336612869980456, |
| "learning_rate": 2.3875426683788497e-06, |
| "loss": 0.6116, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.6888888888888889, |
| "eval_loss": 0.7765544056892395, |
| "eval_runtime": 37.883, |
| "eval_samples_per_second": 52.794, |
| "eval_steps_per_second": 6.599, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.6977777777777778, |
| "grad_norm": 1.709115790338184, |
| "learning_rate": 2.3617143369322988e-06, |
| "loss": 0.6252, |
| "step": 1910 |
| }, |
| { |
| "epoch": 1.7066666666666666, |
| "grad_norm": 1.7821417246615834, |
| "learning_rate": 2.33590080281868e-06, |
| "loss": 0.6107, |
| "step": 1920 |
| }, |
| { |
| "epoch": 1.7155555555555555, |
| "grad_norm": 1.6445009506847397, |
| "learning_rate": 2.310104828229313e-06, |
| "loss": 0.6142, |
| "step": 1930 |
| }, |
| { |
| "epoch": 1.7244444444444444, |
| "grad_norm": 1.841236220247559, |
| "learning_rate": 2.2843291734765544e-06, |
| "loss": 0.6502, |
| "step": 1940 |
| }, |
| { |
| "epoch": 1.7333333333333334, |
| "grad_norm": 1.842694284367171, |
| "learning_rate": 2.2585765966984236e-06, |
| "loss": 0.674, |
| "step": 1950 |
| }, |
| { |
| "epoch": 1.7422222222222223, |
| "grad_norm": 1.8090827021490723, |
| "learning_rate": 2.2328498535634704e-06, |
| "loss": 0.6175, |
| "step": 1960 |
| }, |
| { |
| "epoch": 1.751111111111111, |
| "grad_norm": 1.6878272228854192, |
| "learning_rate": 2.2071516969758988e-06, |
| "loss": 0.6231, |
| "step": 1970 |
| }, |
| { |
| "epoch": 1.76, |
| "grad_norm": 1.9731653412399757, |
| "learning_rate": 2.181484876780996e-06, |
| "loss": 0.629, |
| "step": 1980 |
| }, |
| { |
| "epoch": 1.7688888888888887, |
| "grad_norm": 1.6667636315286483, |
| "learning_rate": 2.1558521394708793e-06, |
| "loss": 0.6658, |
| "step": 1990 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 1.7254699126772677, |
| "learning_rate": 2.1302562278906106e-06, |
| "loss": 0.6327, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "eval_loss": 0.7731255292892456, |
| "eval_runtime": 38.4418, |
| "eval_samples_per_second": 52.027, |
| "eval_steps_per_second": 6.503, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 3375, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 102798860353536.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
