|
{ |
|
"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": 0.16909417510032654, |
|
"learning_rate": 4.8780487804878055e-06, |
|
"loss": 0.8252, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.012315270935960592, |
|
"grad_norm": 0.15486516058444977, |
|
"learning_rate": 2.4390243902439026e-05, |
|
"loss": 0.7899, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.024630541871921183, |
|
"grad_norm": 0.16919347643852234, |
|
"learning_rate": 4.878048780487805e-05, |
|
"loss": 0.8156, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.03694581280788178, |
|
"grad_norm": 0.18892544507980347, |
|
"learning_rate": 7.317073170731707e-05, |
|
"loss": 0.7756, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.04926108374384237, |
|
"grad_norm": 0.15618345141410828, |
|
"learning_rate": 9.75609756097561e-05, |
|
"loss": 0.7755, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.06157635467980296, |
|
"grad_norm": 0.11770500987768173, |
|
"learning_rate": 0.00012195121951219512, |
|
"loss": 0.7548, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.07389162561576355, |
|
"grad_norm": 0.10984448343515396, |
|
"learning_rate": 0.00014634146341463414, |
|
"loss": 0.7463, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.08620689655172414, |
|
"grad_norm": 0.10522622615098953, |
|
"learning_rate": 0.0001707317073170732, |
|
"loss": 0.7447, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.09852216748768473, |
|
"grad_norm": 0.11389700323343277, |
|
"learning_rate": 0.0001951219512195122, |
|
"loss": 0.7476, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.11083743842364532, |
|
"grad_norm": 0.11819540709257126, |
|
"learning_rate": 0.0001999407400739705, |
|
"loss": 0.7548, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.12315270935960591, |
|
"grad_norm": 0.11218090355396271, |
|
"learning_rate": 0.00019970011699250152, |
|
"loss": 0.7347, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.1354679802955665, |
|
"grad_norm": 0.11884038895368576, |
|
"learning_rate": 0.00019927487224577402, |
|
"loss": 0.7485, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.1477832512315271, |
|
"grad_norm": 0.10330455005168915, |
|
"learning_rate": 0.0001986657932891657, |
|
"loss": 0.731, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.16009852216748768, |
|
"grad_norm": 0.10771363228559494, |
|
"learning_rate": 0.00019787400799669154, |
|
"loss": 0.7517, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.1724137931034483, |
|
"grad_norm": 0.10541368275880814, |
|
"learning_rate": 0.00019690098257244064, |
|
"loss": 0.7342, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.18472906403940886, |
|
"grad_norm": 0.10425801575183868, |
|
"learning_rate": 0.00019574851883550395, |
|
"loss": 0.748, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.19704433497536947, |
|
"grad_norm": 0.10108363628387451, |
|
"learning_rate": 0.00019441875088341997, |
|
"loss": 0.7404, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.20935960591133004, |
|
"grad_norm": 0.09765681624412537, |
|
"learning_rate": 0.00019291414114031743, |
|
"loss": 0.7454, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.22167487684729065, |
|
"grad_norm": 0.10201067477464676, |
|
"learning_rate": 0.00019123747579707275, |
|
"loss": 0.7398, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.23399014778325122, |
|
"grad_norm": 0.1033327504992485, |
|
"learning_rate": 0.0001893918596519257, |
|
"loss": 0.7284, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.24630541871921183, |
|
"grad_norm": 0.10564754903316498, |
|
"learning_rate": 0.00018738071036110808, |
|
"loss": 0.7164, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.25862068965517243, |
|
"grad_norm": 0.09552671015262604, |
|
"learning_rate": 0.00018520775211013093, |
|
"loss": 0.7197, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.270935960591133, |
|
"grad_norm": 0.10289793461561203, |
|
"learning_rate": 0.00018287700871745036, |
|
"loss": 0.7342, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.2832512315270936, |
|
"grad_norm": 0.11379728466272354, |
|
"learning_rate": 0.00018039279618328212, |
|
"loss": 0.7542, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.2955665024630542, |
|
"grad_norm": 0.12156806141138077, |
|
"learning_rate": 0.0001777597146973627, |
|
"loss": 0.7591, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.3078817733990148, |
|
"grad_norm": 0.10124150663614273, |
|
"learning_rate": 0.00017498264012045687, |
|
"loss": 0.7414, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.32019704433497537, |
|
"grad_norm": 0.10434222966432571, |
|
"learning_rate": 0.00017206671495538612, |
|
"loss": 0.7414, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.33251231527093594, |
|
"grad_norm": 0.09697817265987396, |
|
"learning_rate": 0.0001690173388242972, |
|
"loss": 0.7355, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.3448275862068966, |
|
"grad_norm": 0.10179964452981949, |
|
"learning_rate": 0.0001658401584698049, |
|
"loss": 0.7308, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.35714285714285715, |
|
"grad_norm": 0.10015404224395752, |
|
"learning_rate": 0.00016254105729852464, |
|
"loss": 0.7561, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.3694581280788177, |
|
"grad_norm": 0.09731245785951614, |
|
"learning_rate": 0.00015912614448635782, |
|
"loss": 0.7329, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.3817733990147783, |
|
"grad_norm": 0.10137064009904861, |
|
"learning_rate": 0.00015560174366570446, |
|
"loss": 0.7234, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.39408866995073893, |
|
"grad_norm": 0.09750425070524216, |
|
"learning_rate": 0.0001519743812155516, |
|
"loss": 0.7477, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.4064039408866995, |
|
"grad_norm": 0.09764320403337479, |
|
"learning_rate": 0.00014825077417612186, |
|
"loss": 0.7428, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.4187192118226601, |
|
"grad_norm": 0.0995442345738411, |
|
"learning_rate": 0.00014443781781046136, |
|
"loss": 0.7341, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.43103448275862066, |
|
"grad_norm": 0.10272233188152313, |
|
"learning_rate": 0.00014054257283599973, |
|
"loss": 0.7409, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.4433497536945813, |
|
"grad_norm": 0.09888844192028046, |
|
"learning_rate": 0.00013657225234972695, |
|
"loss": 0.7315, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.45566502463054187, |
|
"grad_norm": 0.09412329643964767, |
|
"learning_rate": 0.00013253420847119803, |
|
"loss": 0.7506, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.46798029556650245, |
|
"grad_norm": 0.10598532110452652, |
|
"learning_rate": 0.0001284359187281004, |
|
"loss": 0.7325, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.4802955665024631, |
|
"grad_norm": 0.1129438728094101, |
|
"learning_rate": 0.0001242849722095936, |
|
"loss": 0.7306, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.49261083743842365, |
|
"grad_norm": 0.11556894332170486, |
|
"learning_rate": 0.00012008905551306356, |
|
"loss": 0.7082, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.5049261083743842, |
|
"grad_norm": 0.10456952452659607, |
|
"learning_rate": 0.00011585593851031347, |
|
"loss": 0.7293, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 0.5172413793103449, |
|
"grad_norm": 0.1134599968791008, |
|
"learning_rate": 0.00011159345995955006, |
|
"loss": 0.7379, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.5295566502463054, |
|
"grad_norm": 0.09614575654268265, |
|
"learning_rate": 0.00010730951298980776, |
|
"loss": 0.7418, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 0.541871921182266, |
|
"grad_norm": 0.10285273939371109, |
|
"learning_rate": 0.00010301203048469083, |
|
"loss": 0.74, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.5541871921182266, |
|
"grad_norm": 0.10371249169111252, |
|
"learning_rate": 9.870897039249911e-05, |
|
"loss": 0.7269, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.5665024630541872, |
|
"grad_norm": 0.1026730090379715, |
|
"learning_rate": 9.440830098993969e-05, |
|
"loss": 0.734, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.5788177339901478, |
|
"grad_norm": 0.10388628393411636, |
|
"learning_rate": 9.011798612671286e-05, |
|
"loss": 0.7362, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 0.5911330049261084, |
|
"grad_norm": 0.09820030629634857, |
|
"learning_rate": 8.58459704782957e-05, |
|
"loss": 0.7388, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.603448275862069, |
|
"grad_norm": 0.09999756515026093, |
|
"learning_rate": 8.160016483423199e-05, |
|
"loss": 0.7435, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 0.6157635467980296, |
|
"grad_norm": 0.09983257204294205, |
|
"learning_rate": 7.738843144917119e-05, |
|
"loss": 0.7298, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.6280788177339901, |
|
"grad_norm": 0.10523591935634613, |
|
"learning_rate": 7.321856948378259e-05, |
|
"loss": 0.7246, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 0.6403940886699507, |
|
"grad_norm": 0.09543181210756302, |
|
"learning_rate": 6.909830056250527e-05, |
|
"loss": 0.7361, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.6527093596059114, |
|
"grad_norm": 0.09938356280326843, |
|
"learning_rate": 6.503525447487715e-05, |
|
"loss": 0.7129, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 0.6650246305418719, |
|
"grad_norm": 0.10975624620914459, |
|
"learning_rate": 6.103695504692122e-05, |
|
"loss": 0.7132, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.6773399014778325, |
|
"grad_norm": 0.09858807176351547, |
|
"learning_rate": 5.7110806208751655e-05, |
|
"loss": 0.7369, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.6896551724137931, |
|
"grad_norm": 0.10205443948507309, |
|
"learning_rate": 5.326407828419979e-05, |
|
"loss": 0.7263, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.7019704433497537, |
|
"grad_norm": 0.09989740699529648, |
|
"learning_rate": 4.9503894527847964e-05, |
|
"loss": 0.7247, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 0.7142857142857143, |
|
"grad_norm": 0.10319098085165024, |
|
"learning_rate": 4.583721793440188e-05, |
|
"loss": 0.7618, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.7266009852216748, |
|
"grad_norm": 0.09355153143405914, |
|
"learning_rate": 4.227083834482728e-05, |
|
"loss": 0.728, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 0.7389162561576355, |
|
"grad_norm": 0.10289464145898819, |
|
"learning_rate": 3.881135987312757e-05, |
|
"loss": 0.7315, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.7512315270935961, |
|
"grad_norm": 0.10275447368621826, |
|
"learning_rate": 3.546518867704499e-05, |
|
"loss": 0.7417, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 0.7635467980295566, |
|
"grad_norm": 0.1038035973906517, |
|
"learning_rate": 3.223852109533112e-05, |
|
"loss": 0.7328, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.7758620689655172, |
|
"grad_norm": 0.10236402601003647, |
|
"learning_rate": 2.9137332173554043e-05, |
|
"loss": 0.7185, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 0.7881773399014779, |
|
"grad_norm": 0.10697459429502487, |
|
"learning_rate": 2.616736459968936e-05, |
|
"loss": 0.721, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.8004926108374384, |
|
"grad_norm": 0.09831953048706055, |
|
"learning_rate": 2.33341180699841e-05, |
|
"loss": 0.7252, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 0.812807881773399, |
|
"grad_norm": 0.0965956300497055, |
|
"learning_rate": 2.0642839104785272e-05, |
|
"loss": 0.7289, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.8251231527093597, |
|
"grad_norm": 0.10319492220878601, |
|
"learning_rate": 1.8098511333192024e-05, |
|
"loss": 0.7465, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 0.8374384236453202, |
|
"grad_norm": 0.10018905252218246, |
|
"learning_rate": 1.570584626452173e-05, |
|
"loss": 0.7323, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.8497536945812808, |
|
"grad_norm": 0.09453442692756653, |
|
"learning_rate": 1.3469274563679402e-05, |
|
"loss": 0.716, |
|
"step": 345 |
|
}, |
|
{ |
|
"epoch": 0.8620689655172413, |
|
"grad_norm": 0.10382165759801865, |
|
"learning_rate": 1.1392937846586215e-05, |
|
"loss": 0.7309, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.874384236453202, |
|
"grad_norm": 0.10078588873147964, |
|
"learning_rate": 9.48068101086026e-06, |
|
"loss": 0.7286, |
|
"step": 355 |
|
}, |
|
{ |
|
"epoch": 0.8866995073891626, |
|
"grad_norm": 0.09680734574794769, |
|
"learning_rate": 7.736045115951251e-06, |
|
"loss": 0.7392, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.8990147783251231, |
|
"grad_norm": 0.1009003072977066, |
|
"learning_rate": 6.16226082591359e-06, |
|
"loss": 0.7203, |
|
"step": 365 |
|
}, |
|
{ |
|
"epoch": 0.9113300492610837, |
|
"grad_norm": 0.10036424547433853, |
|
"learning_rate": 4.762242426960262e-06, |
|
"loss": 0.7332, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.9236453201970444, |
|
"grad_norm": 0.1032857745885849, |
|
"learning_rate": 3.5385824308756587e-06, |
|
"loss": 0.7102, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 0.9359605911330049, |
|
"grad_norm": 0.10901583731174469, |
|
"learning_rate": 2.493546774280531e-06, |
|
"loss": 0.7397, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.9482758620689655, |
|
"grad_norm": 0.10311324894428253, |
|
"learning_rate": 1.6290706226390285e-06, |
|
"loss": 0.7263, |
|
"step": 385 |
|
}, |
|
{ |
|
"epoch": 0.9605911330049262, |
|
"grad_norm": 0.10355194658041, |
|
"learning_rate": 9.46754786777726e-07, |
|
"loss": 0.7135, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.9729064039408867, |
|
"grad_norm": 0.09248184412717819, |
|
"learning_rate": 4.4786275855247527e-07, |
|
"loss": 0.7232, |
|
"step": 395 |
|
}, |
|
{ |
|
"epoch": 0.9852216748768473, |
|
"grad_norm": 0.10015437006950378, |
|
"learning_rate": 1.333183711524133e-07, |
|
"loss": 0.7208, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.9975369458128078, |
|
"grad_norm": 0.09519725292921066, |
|
"learning_rate": 3.7040883734462683e-09, |
|
"loss": 0.702, |
|
"step": 405 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": NaN, |
|
"eval_runtime": 946.4484, |
|
"eval_samples_per_second": 1.22, |
|
"eval_steps_per_second": 0.305, |
|
"step": 406 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 406, |
|
"total_flos": 2.1031592360023163e+18, |
|
"train_loss": 0.7368329773689138, |
|
"train_runtime": 67624.003, |
|
"train_samples_per_second": 1.537, |
|
"train_steps_per_second": 0.006 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 406, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 100, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 2.1031592360023163e+18, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|