| { | |
| "best_metric": 0.10513312369585037, | |
| "best_model_checkpoint": "/users/u2023000898/train_moe/pretrain_data_chunk/60000_3/checkpoint-1800", | |
| "epoch": 2.9985985985985986, | |
| "eval_steps": 100, | |
| "global_step": 1872, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.016016016016016016, | |
| "grad_norm": 13.409518938793026, | |
| "learning_rate": 5.319148936170213e-07, | |
| "loss": 1.2929, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03203203203203203, | |
| "grad_norm": 10.369912201219414, | |
| "learning_rate": 1.0638297872340427e-06, | |
| "loss": 1.2223, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04804804804804805, | |
| "grad_norm": 5.44261186688239, | |
| "learning_rate": 1.595744680851064e-06, | |
| "loss": 0.943, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06406406406406406, | |
| "grad_norm": 3.605857199785854, | |
| "learning_rate": 2.1276595744680853e-06, | |
| "loss": 0.7396, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.08008008008008008, | |
| "grad_norm": 1.9924246604906095, | |
| "learning_rate": 2.6595744680851065e-06, | |
| "loss": 0.6245, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0960960960960961, | |
| "grad_norm": 2.3307973177641075, | |
| "learning_rate": 3.191489361702128e-06, | |
| "loss": 0.5384, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.11211211211211211, | |
| "grad_norm": 2.417305413795213, | |
| "learning_rate": 3.723404255319149e-06, | |
| "loss": 0.4779, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.12812812812812813, | |
| "grad_norm": 2.4395863243528044, | |
| "learning_rate": 4.255319148936171e-06, | |
| "loss": 0.4384, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.14414414414414414, | |
| "grad_norm": 2.967607994777358, | |
| "learning_rate": 4.787234042553192e-06, | |
| "loss": 0.4194, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.16016016016016016, | |
| "grad_norm": 1.8226498622217497, | |
| "learning_rate": 5.319148936170213e-06, | |
| "loss": 0.3881, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.16016016016016016, | |
| "eval_loss": 0.38211190700531006, | |
| "eval_runtime": 5.3031, | |
| "eval_samples_per_second": 11.314, | |
| "eval_steps_per_second": 5.657, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.17617617617617617, | |
| "grad_norm": 2.0417129648638404, | |
| "learning_rate": 5.851063829787235e-06, | |
| "loss": 0.3735, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1921921921921922, | |
| "grad_norm": 1.8910151101905892, | |
| "learning_rate": 6.382978723404256e-06, | |
| "loss": 0.3597, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2082082082082082, | |
| "grad_norm": 2.356033958506011, | |
| "learning_rate": 6.914893617021278e-06, | |
| "loss": 0.3451, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.22422422422422422, | |
| "grad_norm": 1.6182433590940526, | |
| "learning_rate": 7.446808510638298e-06, | |
| "loss": 0.3299, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.24024024024024024, | |
| "grad_norm": 1.5854757979381888, | |
| "learning_rate": 7.97872340425532e-06, | |
| "loss": 0.3224, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.25625625625625625, | |
| "grad_norm": 1.6564206751789106, | |
| "learning_rate": 8.510638297872341e-06, | |
| "loss": 0.3077, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.2722722722722723, | |
| "grad_norm": 1.647017991315564, | |
| "learning_rate": 9.042553191489362e-06, | |
| "loss": 0.3017, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.2882882882882883, | |
| "grad_norm": 2.0446337917200434, | |
| "learning_rate": 9.574468085106385e-06, | |
| "loss": 0.2859, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.30430430430430433, | |
| "grad_norm": 1.434904669145637, | |
| "learning_rate": 9.999965197129365e-06, | |
| "loss": 0.2877, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.3203203203203203, | |
| "grad_norm": 2.9106697114797573, | |
| "learning_rate": 9.998747147528375e-06, | |
| "loss": 0.2773, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3203203203203203, | |
| "eval_loss": 0.2963399589061737, | |
| "eval_runtime": 4.7335, | |
| "eval_samples_per_second": 12.676, | |
| "eval_steps_per_second": 6.338, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.33633633633633636, | |
| "grad_norm": 2.310160659638816, | |
| "learning_rate": 9.995789438861128e-06, | |
| "loss": 0.2793, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.35235235235235235, | |
| "grad_norm": 1.6140139693791007, | |
| "learning_rate": 9.991093100466482e-06, | |
| "loss": 0.2678, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.3683683683683684, | |
| "grad_norm": 1.6727704090132902, | |
| "learning_rate": 9.98465976675951e-06, | |
| "loss": 0.2633, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.3843843843843844, | |
| "grad_norm": 1.6386702854417348, | |
| "learning_rate": 9.976491676662679e-06, | |
| "loss": 0.2556, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4004004004004004, | |
| "grad_norm": 1.5318495172198847, | |
| "learning_rate": 9.966591672826674e-06, | |
| "loss": 0.2501, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4164164164164164, | |
| "grad_norm": 1.4131958267494484, | |
| "learning_rate": 9.95496320064109e-06, | |
| "loss": 0.239, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.43243243243243246, | |
| "grad_norm": 2.116850571157825, | |
| "learning_rate": 9.941610307035385e-06, | |
| "loss": 0.2352, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.44844844844844844, | |
| "grad_norm": 1.4833918481789057, | |
| "learning_rate": 9.926537639070457e-06, | |
| "loss": 0.2343, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.4644644644644645, | |
| "grad_norm": 1.4499258247835383, | |
| "learning_rate": 9.90975044232139e-06, | |
| "loss": 0.2246, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.4804804804804805, | |
| "grad_norm": 1.5412749043910834, | |
| "learning_rate": 9.891254559051886e-06, | |
| "loss": 0.2209, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4804804804804805, | |
| "eval_loss": 0.22802673280239105, | |
| "eval_runtime": 4.7226, | |
| "eval_samples_per_second": 12.705, | |
| "eval_steps_per_second": 6.352, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.4964964964964965, | |
| "grad_norm": 1.6016396794420027, | |
| "learning_rate": 9.871056426181052e-06, | |
| "loss": 0.2206, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.5125125125125125, | |
| "grad_norm": 1.4910134315726407, | |
| "learning_rate": 9.849163073043223e-06, | |
| "loss": 0.2229, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.5285285285285285, | |
| "grad_norm": 1.5947649628687839, | |
| "learning_rate": 9.82558211894163e-06, | |
| "loss": 0.206, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.5445445445445446, | |
| "grad_norm": 2.281846286082721, | |
| "learning_rate": 9.800321770496726e-06, | |
| "loss": 0.2106, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.5605605605605606, | |
| "grad_norm": 1.628823704341528, | |
| "learning_rate": 9.773390818790136e-06, | |
| "loss": 0.2049, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.5765765765765766, | |
| "grad_norm": 1.8232097235612017, | |
| "learning_rate": 9.744798636305189e-06, | |
| "loss": 0.2045, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.5925925925925926, | |
| "grad_norm": 1.880889712421178, | |
| "learning_rate": 9.714555173665112e-06, | |
| "loss": 0.1948, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.6086086086086087, | |
| "grad_norm": 1.8941186642260008, | |
| "learning_rate": 9.68267095617003e-06, | |
| "loss": 0.1947, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.6246246246246246, | |
| "grad_norm": 1.6000201393992286, | |
| "learning_rate": 9.649157080133962e-06, | |
| "loss": 0.1923, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.6406406406406406, | |
| "grad_norm": 3.414988222682504, | |
| "learning_rate": 9.614025209023084e-06, | |
| "loss": 0.1945, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6406406406406406, | |
| "eval_loss": 0.19540859758853912, | |
| "eval_runtime": 4.7637, | |
| "eval_samples_per_second": 12.595, | |
| "eval_steps_per_second": 6.298, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6566566566566566, | |
| "grad_norm": 1.9420429807772246, | |
| "learning_rate": 9.577287569396632e-06, | |
| "loss": 0.1894, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.6726726726726727, | |
| "grad_norm": 1.3642644226107268, | |
| "learning_rate": 9.538956946651816e-06, | |
| "loss": 0.1782, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.6886886886886887, | |
| "grad_norm": 1.6342771748206477, | |
| "learning_rate": 9.499046680574267e-06, | |
| "loss": 0.1723, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.7047047047047047, | |
| "grad_norm": 1.487958949075534, | |
| "learning_rate": 9.457570660695542e-06, | |
| "loss": 0.1785, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.7207207207207207, | |
| "grad_norm": 1.7299656441999525, | |
| "learning_rate": 9.41454332145928e-06, | |
| "loss": 0.1767, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.7367367367367368, | |
| "grad_norm": 1.4998181975998246, | |
| "learning_rate": 9.369979637197774e-06, | |
| "loss": 0.1738, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.7527527527527528, | |
| "grad_norm": 1.5911390545676716, | |
| "learning_rate": 9.323895116920591e-06, | |
| "loss": 0.1688, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.7687687687687688, | |
| "grad_norm": 2.394239823663753, | |
| "learning_rate": 9.27630579891716e-06, | |
| "loss": 0.1628, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.7847847847847848, | |
| "grad_norm": 1.542509136620149, | |
| "learning_rate": 9.227228245175127e-06, | |
| "loss": 0.1676, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.8008008008008008, | |
| "grad_norm": 1.5343832382043492, | |
| "learning_rate": 9.176679535616477e-06, | |
| "loss": 0.1592, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8008008008008008, | |
| "eval_loss": 0.1710364669561386, | |
| "eval_runtime": 4.7555, | |
| "eval_samples_per_second": 12.617, | |
| "eval_steps_per_second": 6.309, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8168168168168168, | |
| "grad_norm": 1.8010583431481462, | |
| "learning_rate": 9.124677262153405e-06, | |
| "loss": 0.1586, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.8328328328328328, | |
| "grad_norm": 1.6686707098067743, | |
| "learning_rate": 9.071239522565978e-06, | |
| "loss": 0.1556, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.8488488488488488, | |
| "grad_norm": 1.7504894762611782, | |
| "learning_rate": 9.016384914203771e-06, | |
| "loss": 0.1592, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.8648648648648649, | |
| "grad_norm": 1.4989615763117103, | |
| "learning_rate": 8.960132527513642e-06, | |
| "loss": 0.1616, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.8808808808808809, | |
| "grad_norm": 1.5542001700716142, | |
| "learning_rate": 8.902501939395887e-06, | |
| "loss": 0.155, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.8968968968968969, | |
| "grad_norm": 2.502100279988363, | |
| "learning_rate": 8.8435132063911e-06, | |
| "loss": 0.1514, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.9129129129129129, | |
| "grad_norm": 1.5418563195158612, | |
| "learning_rate": 8.783186857700137e-06, | |
| "loss": 0.1455, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.928928928928929, | |
| "grad_norm": 1.6683319786348245, | |
| "learning_rate": 8.721543888039534e-06, | |
| "loss": 0.1417, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.944944944944945, | |
| "grad_norm": 1.762643457697612, | |
| "learning_rate": 8.658605750334972e-06, | |
| "loss": 0.155, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.960960960960961, | |
| "grad_norm": 1.9599503664864883, | |
| "learning_rate": 8.594394348255239e-06, | |
| "loss": 0.1393, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.960960960960961, | |
| "eval_loss": 0.1448938250541687, | |
| "eval_runtime": 4.5683, | |
| "eval_samples_per_second": 13.134, | |
| "eval_steps_per_second": 6.567, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.9769769769769769, | |
| "grad_norm": 1.9697402213513955, | |
| "learning_rate": 8.528932028589337e-06, | |
| "loss": 0.142, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.992992992992993, | |
| "grad_norm": 1.6768033303014018, | |
| "learning_rate": 8.462241573469378e-06, | |
| "loss": 0.1426, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.0092092092092093, | |
| "grad_norm": 1.5267241545230772, | |
| "learning_rate": 8.394346192441967e-06, | |
| "loss": 0.1415, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.0252252252252252, | |
| "grad_norm": 1.476716477059175, | |
| "learning_rate": 8.325269514390835e-06, | |
| "loss": 0.1176, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.0412412412412413, | |
| "grad_norm": 1.4540927119806955, | |
| "learning_rate": 8.255035579313545e-06, | |
| "loss": 0.1223, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.0572572572572572, | |
| "grad_norm": 1.5802819169958848, | |
| "learning_rate": 8.183668829955111e-06, | |
| "loss": 0.1117, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.0732732732732733, | |
| "grad_norm": 2.1509571510914203, | |
| "learning_rate": 8.111194103301461e-06, | |
| "loss": 0.1176, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.0892892892892894, | |
| "grad_norm": 1.4577026982979966, | |
| "learning_rate": 8.037636621935686e-06, | |
| "loss": 0.1193, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.1053053053053052, | |
| "grad_norm": 1.5430361342124643, | |
| "learning_rate": 7.96302198526011e-06, | |
| "loss": 0.1182, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.1213213213213213, | |
| "grad_norm": 1.5919162208902233, | |
| "learning_rate": 7.887376160587214e-06, | |
| "loss": 0.1138, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.1213213213213213, | |
| "eval_loss": 0.15331269800662994, | |
| "eval_runtime": 4.5367, | |
| "eval_samples_per_second": 13.225, | |
| "eval_steps_per_second": 6.613, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.1373373373373372, | |
| "grad_norm": 1.2773733225900368, | |
| "learning_rate": 7.810725474102504e-06, | |
| "loss": 0.1116, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.1533533533533533, | |
| "grad_norm": 1.3037345062586103, | |
| "learning_rate": 7.733096601702508e-06, | |
| "loss": 0.1123, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.1693693693693694, | |
| "grad_norm": 1.5584266021091908, | |
| "learning_rate": 7.654516559711053e-06, | |
| "loss": 0.1142, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.1853853853853853, | |
| "grad_norm": 1.5547636549777273, | |
| "learning_rate": 7.575012695477076e-06, | |
| "loss": 0.1095, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.2014014014014014, | |
| "grad_norm": 1.473482889988994, | |
| "learning_rate": 7.494612677857218e-06, | |
| "loss": 0.1091, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.2174174174174175, | |
| "grad_norm": 1.3570410291065769, | |
| "learning_rate": 7.413344487586542e-06, | |
| "loss": 0.1099, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.2334334334334334, | |
| "grad_norm": 1.5362278958719333, | |
| "learning_rate": 7.331236407540704e-06, | |
| "loss": 0.1137, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.2494494494494495, | |
| "grad_norm": 1.9191542465617197, | |
| "learning_rate": 7.248317012892969e-06, | |
| "loss": 0.1128, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.2654654654654656, | |
| "grad_norm": 1.3514066304735823, | |
| "learning_rate": 7.164615161169518e-06, | |
| "loss": 0.1087, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.2814814814814814, | |
| "grad_norm": 1.6846669149108675, | |
| "learning_rate": 7.080159982206471e-06, | |
| "loss": 0.1096, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2814814814814814, | |
| "eval_loss": 0.140634223818779, | |
| "eval_runtime": 4.5862, | |
| "eval_samples_per_second": 13.083, | |
| "eval_steps_per_second": 6.541, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.2974974974974975, | |
| "grad_norm": 1.1919650111365638, | |
| "learning_rate": 6.994980868012151e-06, | |
| "loss": 0.1109, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.3135135135135134, | |
| "grad_norm": 1.6072997465464531, | |
| "learning_rate": 6.909107462538113e-06, | |
| "loss": 0.1104, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.3295295295295295, | |
| "grad_norm": 1.5714907447670126, | |
| "learning_rate": 6.822569651362475e-06, | |
| "loss": 0.1091, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.3455455455455456, | |
| "grad_norm": 1.3715345334587152, | |
| "learning_rate": 6.735397551289179e-06, | |
| "loss": 0.1072, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.3615615615615615, | |
| "grad_norm": 1.5656149539968518, | |
| "learning_rate": 6.647621499866762e-06, | |
| "loss": 0.1065, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.3775775775775776, | |
| "grad_norm": 1.747219292587951, | |
| "learning_rate": 6.5592720448303174e-06, | |
| "loss": 0.1049, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.3935935935935935, | |
| "grad_norm": 1.4629586813910707, | |
| "learning_rate": 6.470379933470296e-06, | |
| "loss": 0.1018, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.4096096096096096, | |
| "grad_norm": 2.030872539804225, | |
| "learning_rate": 6.380976101931879e-06, | |
| "loss": 0.1015, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.4256256256256257, | |
| "grad_norm": 1.229739648882705, | |
| "learning_rate": 6.291091664448589e-06, | |
| "loss": 0.1076, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 1.4416416416416418, | |
| "grad_norm": 1.584198326139697, | |
| "learning_rate": 6.200757902513962e-06, | |
| "loss": 0.1028, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.4416416416416418, | |
| "eval_loss": 0.12726753950119019, | |
| "eval_runtime": 4.6398, | |
| "eval_samples_per_second": 12.932, | |
| "eval_steps_per_second": 6.466, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 1.4576576576576576, | |
| "grad_norm": 1.053882152208791, | |
| "learning_rate": 6.11000625399499e-06, | |
| "loss": 0.1058, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 1.4736736736736737, | |
| "grad_norm": 1.5483751760051925, | |
| "learning_rate": 6.0188683021911394e-06, | |
| "loss": 0.1008, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.4896896896896896, | |
| "grad_norm": 1.5020771306479124, | |
| "learning_rate": 5.927375764842766e-06, | |
| "loss": 0.0986, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.5057057057057057, | |
| "grad_norm": 1.2818645291771074, | |
| "learning_rate": 5.835560483092743e-06, | |
| "loss": 0.1045, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.5217217217217218, | |
| "grad_norm": 1.5262879682098887, | |
| "learning_rate": 5.743454410405126e-06, | |
| "loss": 0.1008, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.5377377377377377, | |
| "grad_norm": 1.9445218478299358, | |
| "learning_rate": 5.651089601444752e-06, | |
| "loss": 0.0975, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.5537537537537538, | |
| "grad_norm": 1.153429430002744, | |
| "learning_rate": 5.558498200921597e-06, | |
| "loss": 0.103, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.5697697697697697, | |
| "grad_norm": 1.7142266460197206, | |
| "learning_rate": 5.465712432403812e-06, | |
| "loss": 0.1009, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.5857857857857858, | |
| "grad_norm": 1.0420472106372876, | |
| "learning_rate": 5.372764587103309e-06, | |
| "loss": 0.1026, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.6018018018018019, | |
| "grad_norm": 1.0933198718882033, | |
| "learning_rate": 5.279687012637798e-06, | |
| "loss": 0.0998, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.6018018018018019, | |
| "eval_loss": 0.12056411057710648, | |
| "eval_runtime": 4.6363, | |
| "eval_samples_per_second": 12.941, | |
| "eval_steps_per_second": 6.471, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.617817817817818, | |
| "grad_norm": 1.5249725941966104, | |
| "learning_rate": 5.186512101773206e-06, | |
| "loss": 0.0987, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 1.6338338338338338, | |
| "grad_norm": 1.1551410324839504, | |
| "learning_rate": 5.093272281150383e-06, | |
| "loss": 0.0967, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 1.6498498498498497, | |
| "grad_norm": 1.3764150156451525, | |
| "learning_rate": 5e-06, | |
| "loss": 0.102, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 1.6658658658658658, | |
| "grad_norm": 1.4315332194265298, | |
| "learning_rate": 4.906727718849619e-06, | |
| "loss": 0.0918, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.681881881881882, | |
| "grad_norm": 1.5641425623387613, | |
| "learning_rate": 4.813487898226794e-06, | |
| "loss": 0.0972, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.697897897897898, | |
| "grad_norm": 1.364206236390582, | |
| "learning_rate": 4.720312987362204e-06, | |
| "loss": 0.0963, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 1.713913913913914, | |
| "grad_norm": 1.2084858559030025, | |
| "learning_rate": 4.6272354128966924e-06, | |
| "loss": 0.0947, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 1.7299299299299298, | |
| "grad_norm": 1.369095339213906, | |
| "learning_rate": 4.534287567596189e-06, | |
| "loss": 0.1, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 1.7459459459459459, | |
| "grad_norm": 1.7200163939268696, | |
| "learning_rate": 4.441501799078405e-06, | |
| "loss": 0.0939, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 1.761961961961962, | |
| "grad_norm": 1.0601289469307587, | |
| "learning_rate": 4.348910398555249e-06, | |
| "loss": 0.0952, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.761961961961962, | |
| "eval_loss": 0.12079311162233353, | |
| "eval_runtime": 4.5849, | |
| "eval_samples_per_second": 13.087, | |
| "eval_steps_per_second": 6.543, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.777977977977978, | |
| "grad_norm": 1.3096671495162804, | |
| "learning_rate": 4.2565455895948745e-06, | |
| "loss": 0.095, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 1.793993993993994, | |
| "grad_norm": 1.6474183248144982, | |
| "learning_rate": 4.164439516907258e-06, | |
| "loss": 0.096, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 1.81001001001001, | |
| "grad_norm": 1.2638496884017785, | |
| "learning_rate": 4.072624235157234e-06, | |
| "loss": 0.0932, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 1.826026026026026, | |
| "grad_norm": 1.1666611117167804, | |
| "learning_rate": 3.981131697808862e-06, | |
| "loss": 0.0961, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 1.842042042042042, | |
| "grad_norm": 1.4101778997279006, | |
| "learning_rate": 3.889993746005011e-06, | |
| "loss": 0.0938, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.8580580580580581, | |
| "grad_norm": 1.4720670252418966, | |
| "learning_rate": 3.799242097486038e-06, | |
| "loss": 0.0958, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 1.8740740740740742, | |
| "grad_norm": 1.9229886608107283, | |
| "learning_rate": 3.708908335551412e-06, | |
| "loss": 0.0972, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 1.89009009009009, | |
| "grad_norm": 1.5097045011947579, | |
| "learning_rate": 3.6190238980681235e-06, | |
| "loss": 0.0931, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 1.906106106106106, | |
| "grad_norm": 1.3032785079127815, | |
| "learning_rate": 3.529620066529704e-06, | |
| "loss": 0.0925, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.922122122122122, | |
| "grad_norm": 1.158235321697393, | |
| "learning_rate": 3.4407279551696846e-06, | |
| "loss": 0.092, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.922122122122122, | |
| "eval_loss": 0.12118110805749893, | |
| "eval_runtime": 4.5355, | |
| "eval_samples_per_second": 13.229, | |
| "eval_steps_per_second": 6.614, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.9381381381381382, | |
| "grad_norm": 1.3273343135981375, | |
| "learning_rate": 3.352378500133239e-06, | |
| "loss": 0.0912, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 1.9541541541541543, | |
| "grad_norm": 1.2638328817270799, | |
| "learning_rate": 3.264602448710822e-06, | |
| "loss": 0.092, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 1.9701701701701702, | |
| "grad_norm": 1.0061664501466365, | |
| "learning_rate": 3.177430348637527e-06, | |
| "loss": 0.0913, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 1.986186186186186, | |
| "grad_norm": 1.3814485492365947, | |
| "learning_rate": 3.090892537461889e-06, | |
| "loss": 0.0874, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.0024024024024025, | |
| "grad_norm": 1.4890736474425244, | |
| "learning_rate": 3.00501913198785e-06, | |
| "loss": 0.0869, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.0184184184184186, | |
| "grad_norm": 1.143647977026878, | |
| "learning_rate": 2.9198400177935303e-06, | |
| "loss": 0.0629, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.0344344344344343, | |
| "grad_norm": 1.0231219995939023, | |
| "learning_rate": 2.835384838830481e-06, | |
| "loss": 0.0638, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.0504504504504504, | |
| "grad_norm": 1.09838986733996, | |
| "learning_rate": 2.7516829871070295e-06, | |
| "loss": 0.0588, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.0664664664664665, | |
| "grad_norm": 1.1570777805297492, | |
| "learning_rate": 2.668763592459297e-06, | |
| "loss": 0.0595, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.0824824824824826, | |
| "grad_norm": 0.9848777368332091, | |
| "learning_rate": 2.586655512413458e-06, | |
| "loss": 0.061, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.0824824824824826, | |
| "eval_loss": 0.1126304417848587, | |
| "eval_runtime": 4.4139, | |
| "eval_samples_per_second": 13.594, | |
| "eval_steps_per_second": 6.797, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.0984984984984987, | |
| "grad_norm": 1.0676656917105798, | |
| "learning_rate": 2.505387322142782e-06, | |
| "loss": 0.0612, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.1145145145145143, | |
| "grad_norm": 1.05569010042999, | |
| "learning_rate": 2.4249873045229244e-06, | |
| "loss": 0.0607, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.1305305305305304, | |
| "grad_norm": 0.9996457001160142, | |
| "learning_rate": 2.345483440288947e-06, | |
| "loss": 0.06, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 2.1465465465465465, | |
| "grad_norm": 1.07628545223274, | |
| "learning_rate": 2.2669033982974946e-06, | |
| "loss": 0.0588, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 2.1625625625625626, | |
| "grad_norm": 1.07905549545333, | |
| "learning_rate": 2.189274525897498e-06, | |
| "loss": 0.0636, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 2.1785785785785787, | |
| "grad_norm": 1.2549844294011818, | |
| "learning_rate": 2.1126238394127868e-06, | |
| "loss": 0.0607, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 2.1945945945945944, | |
| "grad_norm": 1.0059915885008073, | |
| "learning_rate": 2.03697801473989e-06, | |
| "loss": 0.062, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 2.2106106106106105, | |
| "grad_norm": 1.274382465169598, | |
| "learning_rate": 1.962363378064316e-06, | |
| "loss": 0.0633, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 2.2266266266266266, | |
| "grad_norm": 1.281532287957869, | |
| "learning_rate": 1.8888058966985407e-06, | |
| "loss": 0.0633, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 2.2426426426426427, | |
| "grad_norm": 1.1922439699801886, | |
| "learning_rate": 1.8163311700448899e-06, | |
| "loss": 0.0624, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.2426426426426427, | |
| "eval_loss": 0.1149037629365921, | |
| "eval_runtime": 4.4069, | |
| "eval_samples_per_second": 13.615, | |
| "eval_steps_per_second": 6.808, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 2.258658658658659, | |
| "grad_norm": 1.7050676523518535, | |
| "learning_rate": 1.7449644206864564e-06, | |
| "loss": 0.0623, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 2.2746746746746744, | |
| "grad_norm": 0.9435102102997306, | |
| "learning_rate": 1.6747304856091662e-06, | |
| "loss": 0.059, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 2.2906906906906905, | |
| "grad_norm": 1.0831267008587788, | |
| "learning_rate": 1.6056538075580342e-06, | |
| "loss": 0.0627, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 2.3067067067067066, | |
| "grad_norm": 1.08268476394283, | |
| "learning_rate": 1.5377584265306222e-06, | |
| "loss": 0.0593, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 2.3227227227227227, | |
| "grad_norm": 0.9770773292942597, | |
| "learning_rate": 1.4710679714106635e-06, | |
| "loss": 0.0583, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 2.338738738738739, | |
| "grad_norm": 1.3751312648199294, | |
| "learning_rate": 1.4056056517447637e-06, | |
| "loss": 0.0626, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 2.354754754754755, | |
| "grad_norm": 1.071282141200762, | |
| "learning_rate": 1.3413942496650301e-06, | |
| "loss": 0.0598, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 2.3707707707707706, | |
| "grad_norm": 0.9441682147431711, | |
| "learning_rate": 1.2784561119604683e-06, | |
| "loss": 0.0609, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 2.3867867867867867, | |
| "grad_norm": 1.2531258809500883, | |
| "learning_rate": 1.2168131422998653e-06, | |
| "loss": 0.0618, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 2.402802802802803, | |
| "grad_norm": 0.988649947120785, | |
| "learning_rate": 1.156486793608899e-06, | |
| "loss": 0.0607, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.402802802802803, | |
| "eval_loss": 0.10994044691324234, | |
| "eval_runtime": 4.4237, | |
| "eval_samples_per_second": 13.563, | |
| "eval_steps_per_second": 6.782, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 2.418818818818819, | |
| "grad_norm": 1.1998096160223135, | |
| "learning_rate": 1.0974980606041152e-06, | |
| "loss": 0.0594, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 2.434834834834835, | |
| "grad_norm": 0.9677720356738567, | |
| "learning_rate": 1.0398674724863584e-06, | |
| "loss": 0.059, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 2.450850850850851, | |
| "grad_norm": 1.3141425510127478, | |
| "learning_rate": 9.836150857962296e-07, | |
| "loss": 0.0596, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 2.4668668668668667, | |
| "grad_norm": 0.8985622286196838, | |
| "learning_rate": 9.287604774340236e-07, | |
| "loss": 0.0581, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 2.482882882882883, | |
| "grad_norm": 1.2915272829435755, | |
| "learning_rate": 8.753227378465956e-07, | |
| "loss": 0.0589, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 2.498898898898899, | |
| "grad_norm": 1.051170086009324, | |
| "learning_rate": 8.233204643835235e-07, | |
| "loss": 0.0585, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 2.514914914914915, | |
| "grad_norm": 1.1697265988828673, | |
| "learning_rate": 7.72771754824877e-07, | |
| "loss": 0.0627, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 2.530930930930931, | |
| "grad_norm": 1.045582836173671, | |
| "learning_rate": 7.23694201082843e-07, | |
| "loss": 0.0594, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 2.546946946946947, | |
| "grad_norm": 1.0460247904446258, | |
| "learning_rate": 6.761048830794098e-07, | |
| "loss": 0.0583, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 2.562962962962963, | |
| "grad_norm": 1.0766438599871688, | |
| "learning_rate": 6.300203628022272e-07, | |
| "loss": 0.0584, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.562962962962963, | |
| "eval_loss": 0.1075584813952446, | |
| "eval_runtime": 4.7311, | |
| "eval_samples_per_second": 12.682, | |
| "eval_steps_per_second": 6.341, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 2.578978978978979, | |
| "grad_norm": 1.0644137083005472, | |
| "learning_rate": 5.854566785407212e-07, | |
| "loss": 0.0615, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 2.594994994994995, | |
| "grad_norm": 0.8862800692246755, | |
| "learning_rate": 5.42429339304461e-07, | |
| "loss": 0.0589, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 2.611011011011011, | |
| "grad_norm": 1.0632023267290576, | |
| "learning_rate": 5.009533194257332e-07, | |
| "loss": 0.0576, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 2.627027027027027, | |
| "grad_norm": 1.0612601719189565, | |
| "learning_rate": 4.6104305334818577e-07, | |
| "loss": 0.0581, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 2.643043043043043, | |
| "grad_norm": 1.1363089897778307, | |
| "learning_rate": 4.2271243060336976e-07, | |
| "loss": 0.0565, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 2.659059059059059, | |
| "grad_norm": 1.0581328451419771, | |
| "learning_rate": 3.8597479097691626e-07, | |
| "loss": 0.06, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 2.675075075075075, | |
| "grad_norm": 1.0292294546952114, | |
| "learning_rate": 3.508429198660379e-07, | |
| "loss": 0.0592, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 2.6910910910910912, | |
| "grad_norm": 1.1041696576832245, | |
| "learning_rate": 3.1732904382996975e-07, | |
| "loss": 0.0531, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 2.707107107107107, | |
| "grad_norm": 1.1017298827099373, | |
| "learning_rate": 2.854448263348891e-07, | |
| "loss": 0.0592, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 2.723123123123123, | |
| "grad_norm": 1.2373658193384414, | |
| "learning_rate": 2.5520136369481194e-07, | |
| "loss": 0.0574, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.723123123123123, | |
| "eval_loss": 0.10619153082370758, | |
| "eval_runtime": 4.4379, | |
| "eval_samples_per_second": 13.52, | |
| "eval_steps_per_second": 6.76, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 2.739139139139139, | |
| "grad_norm": 1.0150510884990294, | |
| "learning_rate": 2.266091812098642e-07, | |
| "loss": 0.0581, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 2.755155155155155, | |
| "grad_norm": 1.4492779833818328, | |
| "learning_rate": 1.9967822950327453e-07, | |
| "loss": 0.0609, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 2.7711711711711713, | |
| "grad_norm": 1.104287468688097, | |
| "learning_rate": 1.7441788105837133e-07, | |
| "loss": 0.0593, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 2.787187187187187, | |
| "grad_norm": 1.0784218287885254, | |
| "learning_rate": 1.508369269567783e-07, | |
| "loss": 0.0606, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 2.803203203203203, | |
| "grad_norm": 1.2207885496699904, | |
| "learning_rate": 1.2894357381894984e-07, | |
| "loss": 0.0564, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 2.819219219219219, | |
| "grad_norm": 0.8638978123535029, | |
| "learning_rate": 1.0874544094811424e-07, | |
| "loss": 0.0586, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 2.8352352352352352, | |
| "grad_norm": 1.1498833578746668, | |
| "learning_rate": 9.024955767861054e-08, | |
| "loss": 0.0629, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 2.8512512512512513, | |
| "grad_norm": 0.9945976550163285, | |
| "learning_rate": 7.346236092954318e-08, | |
| "loss": 0.0562, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 2.867267267267267, | |
| "grad_norm": 0.9949658942902132, | |
| "learning_rate": 5.838969296461605e-08, | |
| "loss": 0.0583, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 2.8832832832832835, | |
| "grad_norm": 1.0428607480343814, | |
| "learning_rate": 4.50367993589107e-08, | |
| "loss": 0.0571, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.8832832832832835, | |
| "eval_loss": 0.10513312369585037, | |
| "eval_runtime": 4.4044, | |
| "eval_samples_per_second": 13.623, | |
| "eval_steps_per_second": 6.811, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 2.899299299299299, | |
| "grad_norm": 1.0170732585763345, | |
| "learning_rate": 3.340832717332765e-08, | |
| "loss": 0.0605, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 2.9153153153153153, | |
| "grad_norm": 0.9518652403398978, | |
| "learning_rate": 2.3508323337321225e-08, | |
| "loss": 0.0567, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 2.9313313313313314, | |
| "grad_norm": 1.0033269558751705, | |
| "learning_rate": 1.534023324049061e-08, | |
| "loss": 0.0564, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 2.9473473473473475, | |
| "grad_norm": 1.1693211443264353, | |
| "learning_rate": 8.906899533517866e-09, | |
| "loss": 0.0589, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 2.9633633633633636, | |
| "grad_norm": 1.2335037547499492, | |
| "learning_rate": 4.210561138873193e-09, | |
| "loss": 0.0576, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 2.9793793793793792, | |
| "grad_norm": 1.1025808173861562, | |
| "learning_rate": 1.2528524716259872e-09, | |
| "loss": 0.0548, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 2.9953953953953953, | |
| "grad_norm": 0.9062323167927434, | |
| "learning_rate": 3.480287063706289e-11, | |
| "loss": 0.0587, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 2.9985985985985986, | |
| "step": 1872, | |
| "total_flos": 222868335149056.0, | |
| "train_loss": 0.15247767985376537, | |
| "train_runtime": 21883.2415, | |
| "train_samples_per_second": 8.217, | |
| "train_steps_per_second": 0.086 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1872, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 222868335149056.0, | |
| "train_batch_size": 3, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |