|
{ |
|
"best_metric": 0.1424967348575592, |
|
"best_model_checkpoint": "model_training/deepseek_prover_base_no_err/checkpoints-by_file-09-07-08-59/checkpoint-450", |
|
"epoch": 3.6568527918781726, |
|
"eval_steps": 50, |
|
"global_step": 450, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04060913705583756, |
|
"grad_norm": 113.10508728027344, |
|
"learning_rate": 1e-05, |
|
"loss": 15.6138, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.08121827411167512, |
|
"grad_norm": 114.42933654785156, |
|
"learning_rate": 2e-05, |
|
"loss": 11.7959, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.1218274111675127, |
|
"grad_norm": 33.93031311035156, |
|
"learning_rate": 3e-05, |
|
"loss": 3.0499, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.16243654822335024, |
|
"grad_norm": 0.41336098313331604, |
|
"learning_rate": 4e-05, |
|
"loss": 0.1854, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.20304568527918782, |
|
"grad_norm": 0.4682806432247162, |
|
"learning_rate": 5e-05, |
|
"loss": 0.8857, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.2436548223350254, |
|
"grad_norm": 506.6198425292969, |
|
"learning_rate": 6e-05, |
|
"loss": 0.4888, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.28426395939086296, |
|
"grad_norm": 0.2869759202003479, |
|
"learning_rate": 7e-05, |
|
"loss": 0.2279, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.3248730964467005, |
|
"grad_norm": 0.18190807104110718, |
|
"learning_rate": 8e-05, |
|
"loss": 0.1661, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.36548223350253806, |
|
"grad_norm": 0.09090979397296906, |
|
"learning_rate": 9e-05, |
|
"loss": 0.1575, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.40609137055837563, |
|
"grad_norm": 0.14082124829292297, |
|
"learning_rate": 0.0001, |
|
"loss": 0.1569, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.40609137055837563, |
|
"eval_loss": 0.16598469018936157, |
|
"eval_runtime": 571.0235, |
|
"eval_samples_per_second": 1.751, |
|
"eval_steps_per_second": 0.219, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.4467005076142132, |
|
"grad_norm": 1.0748934745788574, |
|
"learning_rate": 9.996842891446092e-05, |
|
"loss": 0.15, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.4873096446700508, |
|
"grad_norm": 0.09886147826910019, |
|
"learning_rate": 9.987375552718133e-05, |
|
"loss": 0.1498, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.5279187817258884, |
|
"grad_norm": 0.07677606493234634, |
|
"learning_rate": 9.971609939582557e-05, |
|
"loss": 0.1499, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.5685279187817259, |
|
"grad_norm": 0.26791003346443176, |
|
"learning_rate": 9.9495659615402e-05, |
|
"loss": 0.1631, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.6091370558375635, |
|
"grad_norm": 0.07558655738830566, |
|
"learning_rate": 9.921271456683715e-05, |
|
"loss": 0.1535, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.649746192893401, |
|
"grad_norm": 0.04132043197751045, |
|
"learning_rate": 9.886762156542428e-05, |
|
"loss": 0.1454, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.6903553299492385, |
|
"grad_norm": 0.03367358446121216, |
|
"learning_rate": 9.846081640959007e-05, |
|
"loss": 0.1372, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.7309644670050761, |
|
"grad_norm": 0.05775720626115799, |
|
"learning_rate": 9.79928128305494e-05, |
|
"loss": 0.1411, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.7715736040609137, |
|
"grad_norm": 0.05461897701025009, |
|
"learning_rate": 9.746420184354334e-05, |
|
"loss": 0.1369, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.8121827411167513, |
|
"grad_norm": 0.03982888534665108, |
|
"learning_rate": 9.687565100147939e-05, |
|
"loss": 0.1422, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.8121827411167513, |
|
"eval_loss": 0.15572066605091095, |
|
"eval_runtime": 570.7773, |
|
"eval_samples_per_second": 1.752, |
|
"eval_steps_per_second": 0.219, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.8527918781725888, |
|
"grad_norm": 0.049296505749225616, |
|
"learning_rate": 9.622790355191672e-05, |
|
"loss": 0.1396, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.8934010152284264, |
|
"grad_norm": 0.04366493597626686, |
|
"learning_rate": 9.552177749846083e-05, |
|
"loss": 0.1466, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.934010152284264, |
|
"grad_norm": 0.0475134439766407, |
|
"learning_rate": 9.475816456775313e-05, |
|
"loss": 0.1421, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.9746192893401016, |
|
"grad_norm": 0.044564343988895416, |
|
"learning_rate": 9.393802908335977e-05, |
|
"loss": 0.137, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.015228426395939, |
|
"grad_norm": 0.04059167578816414, |
|
"learning_rate": 9.306240674798203e-05, |
|
"loss": 0.1442, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.0558375634517767, |
|
"grad_norm": 0.0424371100962162, |
|
"learning_rate": 9.213240333552589e-05, |
|
"loss": 0.1362, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.0964467005076142, |
|
"grad_norm": 0.059122174978256226, |
|
"learning_rate": 9.114919329468282e-05, |
|
"loss": 0.1351, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 1.1370558375634519, |
|
"grad_norm": 0.06440797448158264, |
|
"learning_rate": 9.011401826578492e-05, |
|
"loss": 0.1404, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.1776649746192893, |
|
"grad_norm": 0.044413380324840546, |
|
"learning_rate": 8.902818551280758e-05, |
|
"loss": 0.1258, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 1.218274111675127, |
|
"grad_norm": 0.06735623627901077, |
|
"learning_rate": 8.789306627249985e-05, |
|
"loss": 0.1238, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.218274111675127, |
|
"eval_loss": 0.15116116404533386, |
|
"eval_runtime": 571.8633, |
|
"eval_samples_per_second": 1.749, |
|
"eval_steps_per_second": 0.219, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.2588832487309645, |
|
"grad_norm": 0.05769121274352074, |
|
"learning_rate": 8.6710094022727e-05, |
|
"loss": 0.1319, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 1.299492385786802, |
|
"grad_norm": 0.048896849155426025, |
|
"learning_rate": 8.548076267221256e-05, |
|
"loss": 0.1232, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.3401015228426396, |
|
"grad_norm": 0.0718092992901802, |
|
"learning_rate": 8.420662467396547e-05, |
|
"loss": 0.1397, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 1.380710659898477, |
|
"grad_norm": 0.054730452597141266, |
|
"learning_rate": 8.288928906477496e-05, |
|
"loss": 0.121, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.4213197969543148, |
|
"grad_norm": 0.08080842345952988, |
|
"learning_rate": 8.15304194332491e-05, |
|
"loss": 0.1358, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.4619289340101522, |
|
"grad_norm": 0.05518824979662895, |
|
"learning_rate": 8.013173181896283e-05, |
|
"loss": 0.1347, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.50253807106599, |
|
"grad_norm": 0.07823627442121506, |
|
"learning_rate": 7.869499254536865e-05, |
|
"loss": 0.1386, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 1.5431472081218274, |
|
"grad_norm": 0.08264634758234024, |
|
"learning_rate": 7.722201598920673e-05, |
|
"loss": 0.1261, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.5837563451776648, |
|
"grad_norm": 0.06334514170885086, |
|
"learning_rate": 7.571466228923115e-05, |
|
"loss": 0.1338, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 1.6243654822335025, |
|
"grad_norm": 0.06367149949073792, |
|
"learning_rate": 7.417483499714589e-05, |
|
"loss": 0.1306, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.6243654822335025, |
|
"eval_loss": 0.1474769562482834, |
|
"eval_runtime": 570.894, |
|
"eval_samples_per_second": 1.752, |
|
"eval_steps_per_second": 0.219, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.6649746192893402, |
|
"grad_norm": 0.08058533072471619, |
|
"learning_rate": 7.260447867371709e-05, |
|
"loss": 0.1342, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 1.7055837563451777, |
|
"grad_norm": 0.07283538579940796, |
|
"learning_rate": 7.100557643309732e-05, |
|
"loss": 0.1247, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.7461928934010151, |
|
"grad_norm": 0.08428559452295303, |
|
"learning_rate": 6.938014743846285e-05, |
|
"loss": 0.1278, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 1.7868020304568528, |
|
"grad_norm": 0.08377284556627274, |
|
"learning_rate": 6.773024435212678e-05, |
|
"loss": 0.1312, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.8274111675126905, |
|
"grad_norm": 0.10298043489456177, |
|
"learning_rate": 6.605795074334794e-05, |
|
"loss": 0.1304, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 1.868020304568528, |
|
"grad_norm": 0.09377053380012512, |
|
"learning_rate": 6.436537845710903e-05, |
|
"loss": 0.1303, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.9086294416243654, |
|
"grad_norm": 0.11010950058698654, |
|
"learning_rate": 6.265466494718732e-05, |
|
"loss": 0.1163, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 1.9492385786802031, |
|
"grad_norm": 0.17498579621315002, |
|
"learning_rate": 6.092797057688495e-05, |
|
"loss": 0.1124, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.9898477157360406, |
|
"grad_norm": 0.09446436911821365, |
|
"learning_rate": 5.918747589082853e-05, |
|
"loss": 0.1193, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 2.030456852791878, |
|
"grad_norm": 0.09566423296928406, |
|
"learning_rate": 5.7435378861282585e-05, |
|
"loss": 0.1252, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.030456852791878, |
|
"eval_loss": 0.14643818140029907, |
|
"eval_runtime": 570.7851, |
|
"eval_samples_per_second": 1.752, |
|
"eval_steps_per_second": 0.219, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 2.0710659898477157, |
|
"grad_norm": 0.10885192453861237, |
|
"learning_rate": 5.567389211245485e-05, |
|
"loss": 0.1152, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 2.1116751269035534, |
|
"grad_norm": 0.09853996336460114, |
|
"learning_rate": 5.390524012629824e-05, |
|
"loss": 0.1248, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 2.152284263959391, |
|
"grad_norm": 0.0892142653465271, |
|
"learning_rate": 5.2131656433338506e-05, |
|
"loss": 0.1207, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 2.1928934010152283, |
|
"grad_norm": 0.09116163849830627, |
|
"learning_rate": 5.035538079207488e-05, |
|
"loss": 0.1143, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 2.233502538071066, |
|
"grad_norm": 0.09667850285768509, |
|
"learning_rate": 4.857865636051585e-05, |
|
"loss": 0.1155, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 2.2741116751269037, |
|
"grad_norm": 0.1532243937253952, |
|
"learning_rate": 4.6803726863421725e-05, |
|
"loss": 0.1146, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 2.314720812182741, |
|
"grad_norm": 0.11655127257108688, |
|
"learning_rate": 4.503283375883165e-05, |
|
"loss": 0.111, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 2.3553299492385786, |
|
"grad_norm": 0.1412302553653717, |
|
"learning_rate": 4.326821340745304e-05, |
|
"loss": 0.1102, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 2.3959390862944163, |
|
"grad_norm": 0.10279002040624619, |
|
"learning_rate": 4.151209424848819e-05, |
|
"loss": 0.112, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 2.436548223350254, |
|
"grad_norm": 0.08668510615825653, |
|
"learning_rate": 3.976669398546451e-05, |
|
"loss": 0.1197, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.436548223350254, |
|
"eval_loss": 0.14324025809764862, |
|
"eval_runtime": 570.6919, |
|
"eval_samples_per_second": 1.752, |
|
"eval_steps_per_second": 0.219, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.4771573604060912, |
|
"grad_norm": 0.0965413898229599, |
|
"learning_rate": 3.803421678562213e-05, |
|
"loss": 0.1169, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 2.517766497461929, |
|
"grad_norm": 0.07902427762746811, |
|
"learning_rate": 3.631685049639586e-05, |
|
"loss": 0.1084, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 2.5583756345177666, |
|
"grad_norm": 0.0779964029788971, |
|
"learning_rate": 3.461676388250651e-05, |
|
"loss": 0.1092, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 2.598984771573604, |
|
"grad_norm": 0.08506277203559875, |
|
"learning_rate": 3.293610388715048e-05, |
|
"loss": 0.1116, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 2.6395939086294415, |
|
"grad_norm": 0.1012549176812172, |
|
"learning_rate": 3.127699292074683e-05, |
|
"loss": 0.118, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 2.6802030456852792, |
|
"grad_norm": 0.13339918851852417, |
|
"learning_rate": 2.964152618066508e-05, |
|
"loss": 0.1043, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 2.720812182741117, |
|
"grad_norm": 0.10142350941896439, |
|
"learning_rate": 2.8031769005319147e-05, |
|
"loss": 0.1103, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 2.761421319796954, |
|
"grad_norm": 0.08831272274255753, |
|
"learning_rate": 2.6449754265968264e-05, |
|
"loss": 0.1125, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 2.802030456852792, |
|
"grad_norm": 0.07664326578378677, |
|
"learning_rate": 2.4897479799518796e-05, |
|
"loss": 0.1069, |
|
"step": 345 |
|
}, |
|
{ |
|
"epoch": 2.8426395939086295, |
|
"grad_norm": 0.08216122537851334, |
|
"learning_rate": 2.3376905885569182e-05, |
|
"loss": 0.1044, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 2.8426395939086295, |
|
"eval_loss": 0.1425444483757019, |
|
"eval_runtime": 570.665, |
|
"eval_samples_per_second": 1.752, |
|
"eval_steps_per_second": 0.219, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 2.885279187817259, |
|
"grad_norm": 0.12189479172229767, |
|
"learning_rate": 2.1889952770883643e-05, |
|
"loss": 0.1051, |
|
"step": 355 |
|
}, |
|
{ |
|
"epoch": 2.9258883248730965, |
|
"grad_norm": 0.09821608662605286, |
|
"learning_rate": 2.043849824442124e-05, |
|
"loss": 0.1066, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 2.966497461928934, |
|
"grad_norm": 0.0908147543668747, |
|
"learning_rate": 1.9024375265982384e-05, |
|
"loss": 0.1076, |
|
"step": 365 |
|
}, |
|
{ |
|
"epoch": 3.0071065989847714, |
|
"grad_norm": 0.11563821136951447, |
|
"learning_rate": 1.764936965146773e-05, |
|
"loss": 0.1134, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 3.047715736040609, |
|
"grad_norm": 0.10024692863225937, |
|
"learning_rate": 1.631521781767214e-05, |
|
"loss": 0.1081, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 3.0883248730964468, |
|
"grad_norm": 0.11522582173347473, |
|
"learning_rate": 1.502360458946232e-05, |
|
"loss": 0.0996, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 3.1289340101522845, |
|
"grad_norm": 0.1005687341094017, |
|
"learning_rate": 1.3776161072106702e-05, |
|
"loss": 0.1155, |
|
"step": 385 |
|
}, |
|
{ |
|
"epoch": 3.1695431472081217, |
|
"grad_norm": 0.10551727563142776, |
|
"learning_rate": 1.257446259144494e-05, |
|
"loss": 0.1184, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 3.2101522842639594, |
|
"grad_norm": 0.09149405360221863, |
|
"learning_rate": 1.1420026704498077e-05, |
|
"loss": 0.1071, |
|
"step": 395 |
|
}, |
|
{ |
|
"epoch": 3.250761421319797, |
|
"grad_norm": 0.08743679523468018, |
|
"learning_rate": 1.031431128303153e-05, |
|
"loss": 0.0984, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 3.250761421319797, |
|
"eval_loss": 0.14250527322292328, |
|
"eval_runtime": 575.342, |
|
"eval_samples_per_second": 1.738, |
|
"eval_steps_per_second": 0.217, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 3.2913705583756343, |
|
"grad_norm": 0.1152808740735054, |
|
"learning_rate": 9.258712672491415e-06, |
|
"loss": 0.1075, |
|
"step": 405 |
|
}, |
|
{ |
|
"epoch": 3.331979695431472, |
|
"grad_norm": 0.0870693102478981, |
|
"learning_rate": 8.254563928638893e-06, |
|
"loss": 0.1055, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 3.3725888324873097, |
|
"grad_norm": 0.1064496636390686, |
|
"learning_rate": 7.3031331341093915e-06, |
|
"loss": 0.1162, |
|
"step": 415 |
|
}, |
|
{ |
|
"epoch": 3.4131979695431474, |
|
"grad_norm": 0.10074327141046524, |
|
"learning_rate": 6.405621797022848e-06, |
|
"loss": 0.1032, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 3.4538071065989846, |
|
"grad_norm": 0.11636592447757721, |
|
"learning_rate": 5.563163333667099e-06, |
|
"loss": 0.1057, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 3.4944162436548223, |
|
"grad_norm": 0.08998982608318329, |
|
"learning_rate": 4.776821637170526e-06, |
|
"loss": 0.105, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 3.53502538071066, |
|
"grad_norm": 0.09578435868024826, |
|
"learning_rate": 4.047589733971646e-06, |
|
"loss": 0.1032, |
|
"step": 435 |
|
}, |
|
{ |
|
"epoch": 3.575634517766497, |
|
"grad_norm": 0.10539178550243378, |
|
"learning_rate": 3.376388529782215e-06, |
|
"loss": 0.1046, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 3.616243654822335, |
|
"grad_norm": 0.1038966253399849, |
|
"learning_rate": 2.7640656466274782e-06, |
|
"loss": 0.0981, |
|
"step": 445 |
|
}, |
|
{ |
|
"epoch": 3.6568527918781726, |
|
"grad_norm": 0.09623471647500992, |
|
"learning_rate": 2.2113943524323167e-06, |
|
"loss": 0.1014, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 3.6568527918781726, |
|
"eval_loss": 0.1424967348575592, |
|
"eval_runtime": 575.2181, |
|
"eval_samples_per_second": 1.738, |
|
"eval_steps_per_second": 0.217, |
|
"step": 450 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 492, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 4, |
|
"save_steps": 50, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2.8705510622704435e+18, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|