|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 406, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0024630541871921183, |
|
"grad_norm": 0.3059285581111908, |
|
"learning_rate": 4.8780487804878055e-06, |
|
"loss": 0.973, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.012315270935960592, |
|
"grad_norm": 0.32822155952453613, |
|
"learning_rate": 2.4390243902439026e-05, |
|
"loss": 0.9792, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.024630541871921183, |
|
"grad_norm": 0.15688546001911163, |
|
"learning_rate": 4.878048780487805e-05, |
|
"loss": 0.948, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.03694581280788178, |
|
"grad_norm": 0.10952994972467422, |
|
"learning_rate": 7.317073170731707e-05, |
|
"loss": 0.937, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.04926108374384237, |
|
"grad_norm": 0.08601206541061401, |
|
"learning_rate": 9.75609756097561e-05, |
|
"loss": 0.942, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.06157635467980296, |
|
"grad_norm": 0.0885809138417244, |
|
"learning_rate": 0.00012195121951219512, |
|
"loss": 0.8973, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.07389162561576355, |
|
"grad_norm": 0.08484961092472076, |
|
"learning_rate": 0.00014634146341463414, |
|
"loss": 0.8847, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.08620689655172414, |
|
"grad_norm": 0.07761262357234955, |
|
"learning_rate": 0.0001707317073170732, |
|
"loss": 0.8802, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.09852216748768473, |
|
"grad_norm": 0.06918736547231674, |
|
"learning_rate": 0.0001951219512195122, |
|
"loss": 0.8847, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.11083743842364532, |
|
"grad_norm": 0.06761624664068222, |
|
"learning_rate": 0.0001999407400739705, |
|
"loss": 0.8922, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.12315270935960591, |
|
"grad_norm": 0.07236196845769882, |
|
"learning_rate": 0.00019970011699250152, |
|
"loss": 0.8834, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.1354679802955665, |
|
"grad_norm": 0.09103026986122131, |
|
"learning_rate": 0.00019927487224577402, |
|
"loss": 0.8666, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.1477832512315271, |
|
"grad_norm": 0.07534986734390259, |
|
"learning_rate": 0.0001986657932891657, |
|
"loss": 0.8859, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.16009852216748768, |
|
"grad_norm": 0.06696303188800812, |
|
"learning_rate": 0.00019787400799669154, |
|
"loss": 0.8577, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.1724137931034483, |
|
"grad_norm": 0.06896838545799255, |
|
"learning_rate": 0.00019690098257244064, |
|
"loss": 0.8673, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.18472906403940886, |
|
"grad_norm": 0.0723799467086792, |
|
"learning_rate": 0.00019574851883550395, |
|
"loss": 0.8611, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.19704433497536947, |
|
"grad_norm": 0.07205817848443985, |
|
"learning_rate": 0.00019441875088341997, |
|
"loss": 0.8706, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.20935960591133004, |
|
"grad_norm": 0.07139647006988525, |
|
"learning_rate": 0.00019291414114031743, |
|
"loss": 0.8233, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.22167487684729065, |
|
"grad_norm": 0.0706641897559166, |
|
"learning_rate": 0.00019123747579707275, |
|
"loss": 0.8591, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.23399014778325122, |
|
"grad_norm": 0.0851423591375351, |
|
"learning_rate": 0.0001893918596519257, |
|
"loss": 0.8741, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.24630541871921183, |
|
"grad_norm": 0.07657479494810104, |
|
"learning_rate": 0.00018738071036110808, |
|
"loss": 0.8655, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.25862068965517243, |
|
"grad_norm": 0.0707501620054245, |
|
"learning_rate": 0.00018520775211013093, |
|
"loss": 0.8587, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.270935960591133, |
|
"grad_norm": 0.07269560545682907, |
|
"learning_rate": 0.00018287700871745036, |
|
"loss": 0.8359, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.2832512315270936, |
|
"grad_norm": 0.07023902237415314, |
|
"learning_rate": 0.00018039279618328212, |
|
"loss": 0.8636, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.2955665024630542, |
|
"grad_norm": 0.07787394523620605, |
|
"learning_rate": 0.0001777597146973627, |
|
"loss": 0.8497, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.3078817733990148, |
|
"grad_norm": 0.07374060899019241, |
|
"learning_rate": 0.00017498264012045687, |
|
"loss": 0.8624, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.32019704433497537, |
|
"grad_norm": 0.07400210201740265, |
|
"learning_rate": 0.00017206671495538612, |
|
"loss": 0.8491, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.33251231527093594, |
|
"grad_norm": 0.07220059633255005, |
|
"learning_rate": 0.0001690173388242972, |
|
"loss": 0.846, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.3448275862068966, |
|
"grad_norm": 0.07860001921653748, |
|
"learning_rate": 0.0001658401584698049, |
|
"loss": 0.8628, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.35714285714285715, |
|
"grad_norm": 0.0690656378865242, |
|
"learning_rate": 0.00016254105729852464, |
|
"loss": 0.8733, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.3694581280788177, |
|
"grad_norm": 0.07429734617471695, |
|
"learning_rate": 0.00015912614448635782, |
|
"loss": 0.8843, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.3817733990147783, |
|
"grad_norm": 0.06792297214269638, |
|
"learning_rate": 0.00015560174366570446, |
|
"loss": 0.8468, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.39408866995073893, |
|
"grad_norm": 0.07411015033721924, |
|
"learning_rate": 0.0001519743812155516, |
|
"loss": 0.8709, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.4064039408866995, |
|
"grad_norm": 0.07467999309301376, |
|
"learning_rate": 0.00014825077417612186, |
|
"loss": 0.8491, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.4187192118226601, |
|
"grad_norm": 0.06963290274143219, |
|
"learning_rate": 0.00014443781781046136, |
|
"loss": 0.8398, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.43103448275862066, |
|
"grad_norm": 0.07223643362522125, |
|
"learning_rate": 0.00014054257283599973, |
|
"loss": 0.8403, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.4433497536945813, |
|
"grad_norm": 0.0706588551402092, |
|
"learning_rate": 0.00013657225234972695, |
|
"loss": 0.8473, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.45566502463054187, |
|
"grad_norm": 0.07453994452953339, |
|
"learning_rate": 0.00013253420847119803, |
|
"loss": 0.8615, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.46798029556650245, |
|
"grad_norm": 0.07416338473558426, |
|
"learning_rate": 0.0001284359187281004, |
|
"loss": 0.8537, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.4802955665024631, |
|
"grad_norm": 0.0786135196685791, |
|
"learning_rate": 0.0001242849722095936, |
|
"loss": 0.85, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.49261083743842365, |
|
"grad_norm": 0.07604887336492538, |
|
"learning_rate": 0.00012008905551306356, |
|
"loss": 0.8366, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.5049261083743842, |
|
"grad_norm": 0.07247956097126007, |
|
"learning_rate": 0.00011585593851031347, |
|
"loss": 0.8476, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 0.5172413793103449, |
|
"grad_norm": 0.07101637125015259, |
|
"learning_rate": 0.00011159345995955006, |
|
"loss": 0.8598, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.5295566502463054, |
|
"grad_norm": 0.07367275655269623, |
|
"learning_rate": 0.00010730951298980776, |
|
"loss": 0.866, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 0.541871921182266, |
|
"grad_norm": 0.07192419469356537, |
|
"learning_rate": 0.00010301203048469083, |
|
"loss": 0.8588, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.5541871921182266, |
|
"grad_norm": 0.07665691524744034, |
|
"learning_rate": 9.870897039249911e-05, |
|
"loss": 0.8622, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.5665024630541872, |
|
"grad_norm": 0.07334121316671371, |
|
"learning_rate": 9.440830098993969e-05, |
|
"loss": 0.8416, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.5788177339901478, |
|
"grad_norm": 0.07701093703508377, |
|
"learning_rate": 9.011798612671286e-05, |
|
"loss": 0.852, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 0.5911330049261084, |
|
"grad_norm": 0.07488030940294266, |
|
"learning_rate": 8.58459704782957e-05, |
|
"loss": 0.854, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.603448275862069, |
|
"grad_norm": 0.07589469105005264, |
|
"learning_rate": 8.160016483423199e-05, |
|
"loss": 0.8515, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 0.6157635467980296, |
|
"grad_norm": 0.07805849611759186, |
|
"learning_rate": 7.738843144917119e-05, |
|
"loss": 0.8573, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.6280788177339901, |
|
"grad_norm": 0.07487764954566956, |
|
"learning_rate": 7.321856948378259e-05, |
|
"loss": 0.8507, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 0.6403940886699507, |
|
"grad_norm": 0.07488517463207245, |
|
"learning_rate": 6.909830056250527e-05, |
|
"loss": 0.8589, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.6527093596059114, |
|
"grad_norm": 0.07873272895812988, |
|
"learning_rate": 6.503525447487715e-05, |
|
"loss": 0.8594, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 0.6650246305418719, |
|
"grad_norm": 0.08194595575332642, |
|
"learning_rate": 6.103695504692122e-05, |
|
"loss": 0.8627, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.6773399014778325, |
|
"grad_norm": 0.07579940557479858, |
|
"learning_rate": 5.7110806208751655e-05, |
|
"loss": 0.8715, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.6896551724137931, |
|
"grad_norm": 0.07746939361095428, |
|
"learning_rate": 5.326407828419979e-05, |
|
"loss": 0.8361, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.7019704433497537, |
|
"grad_norm": 0.07655655592679977, |
|
"learning_rate": 4.9503894527847964e-05, |
|
"loss": 0.8477, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 0.7142857142857143, |
|
"grad_norm": 0.08122251182794571, |
|
"learning_rate": 4.583721793440188e-05, |
|
"loss": 0.839, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.7266009852216748, |
|
"grad_norm": 0.07173337787389755, |
|
"learning_rate": 4.227083834482728e-05, |
|
"loss": 0.8491, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 0.7389162561576355, |
|
"grad_norm": 0.08026029914617538, |
|
"learning_rate": 3.881135987312757e-05, |
|
"loss": 0.8653, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.7512315270935961, |
|
"grad_norm": 0.07666407525539398, |
|
"learning_rate": 3.546518867704499e-05, |
|
"loss": 0.851, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 0.7635467980295566, |
|
"grad_norm": 0.07790068536996841, |
|
"learning_rate": 3.223852109533112e-05, |
|
"loss": 0.8336, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.7758620689655172, |
|
"grad_norm": 0.07437258958816528, |
|
"learning_rate": 2.9137332173554043e-05, |
|
"loss": 0.8369, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 0.7881773399014779, |
|
"grad_norm": 0.07919098436832428, |
|
"learning_rate": 2.616736459968936e-05, |
|
"loss": 0.8443, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.8004926108374384, |
|
"grad_norm": 0.07308971136808395, |
|
"learning_rate": 2.33341180699841e-05, |
|
"loss": 0.8308, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 0.812807881773399, |
|
"grad_norm": 0.08116165548563004, |
|
"learning_rate": 2.0642839104785272e-05, |
|
"loss": 0.8495, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.8251231527093597, |
|
"grad_norm": 0.07381982356309891, |
|
"learning_rate": 1.8098511333192024e-05, |
|
"loss": 0.8517, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 0.8374384236453202, |
|
"grad_norm": 0.07830165326595306, |
|
"learning_rate": 1.570584626452173e-05, |
|
"loss": 0.8308, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.8497536945812808, |
|
"grad_norm": 0.077251136302948, |
|
"learning_rate": 1.3469274563679402e-05, |
|
"loss": 0.8361, |
|
"step": 345 |
|
}, |
|
{ |
|
"epoch": 0.8620689655172413, |
|
"grad_norm": 0.07581036537885666, |
|
"learning_rate": 1.1392937846586215e-05, |
|
"loss": 0.8632, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.874384236453202, |
|
"grad_norm": 0.07401956617832184, |
|
"learning_rate": 9.48068101086026e-06, |
|
"loss": 0.8534, |
|
"step": 355 |
|
}, |
|
{ |
|
"epoch": 0.8866995073891626, |
|
"grad_norm": 0.07715585827827454, |
|
"learning_rate": 7.736045115951251e-06, |
|
"loss": 0.8519, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.8990147783251231, |
|
"grad_norm": 0.0795416533946991, |
|
"learning_rate": 6.16226082591359e-06, |
|
"loss": 0.8403, |
|
"step": 365 |
|
}, |
|
{ |
|
"epoch": 0.9113300492610837, |
|
"grad_norm": 0.07462508231401443, |
|
"learning_rate": 4.762242426960262e-06, |
|
"loss": 0.8542, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.9236453201970444, |
|
"grad_norm": 0.07410599291324615, |
|
"learning_rate": 3.5385824308756587e-06, |
|
"loss": 0.8503, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 0.9359605911330049, |
|
"grad_norm": 0.07767335325479507, |
|
"learning_rate": 2.493546774280531e-06, |
|
"loss": 0.8476, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.9482758620689655, |
|
"grad_norm": 0.07137991487979889, |
|
"learning_rate": 1.6290706226390285e-06, |
|
"loss": 0.8255, |
|
"step": 385 |
|
}, |
|
{ |
|
"epoch": 0.9605911330049262, |
|
"grad_norm": 0.0733158066868782, |
|
"learning_rate": 9.46754786777726e-07, |
|
"loss": 0.8473, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.9729064039408867, |
|
"grad_norm": 0.07238588482141495, |
|
"learning_rate": 4.4786275855247527e-07, |
|
"loss": 0.8284, |
|
"step": 395 |
|
}, |
|
{ |
|
"epoch": 0.9852216748768473, |
|
"grad_norm": 0.0766235738992691, |
|
"learning_rate": 1.333183711524133e-07, |
|
"loss": 0.8619, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.9975369458128078, |
|
"grad_norm": 0.07639329135417938, |
|
"learning_rate": 3.7040883734462683e-09, |
|
"loss": 0.8582, |
|
"step": 405 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.089674472808838, |
|
"eval_runtime": 131.6876, |
|
"eval_samples_per_second": 8.771, |
|
"eval_steps_per_second": 0.554, |
|
"step": 406 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 406, |
|
"total_flos": 2.015525816363909e+18, |
|
"train_loss": 0.8602962029978559, |
|
"train_runtime": 31829.4895, |
|
"train_samples_per_second": 3.265, |
|
"train_steps_per_second": 0.013 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 406, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 25, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2.015525816363909e+18, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|