|
{ |
|
"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": 0.13162502646446228, |
|
"learning_rate": 4.8780487804878055e-06, |
|
"loss": 0.7597, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.012315270935960592, |
|
"grad_norm": 0.13736732304096222, |
|
"learning_rate": 2.4390243902439026e-05, |
|
"loss": 0.7842, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.024630541871921183, |
|
"grad_norm": 0.12169680744409561, |
|
"learning_rate": 4.878048780487805e-05, |
|
"loss": 0.7899, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.03694581280788178, |
|
"grad_norm": 0.12660211324691772, |
|
"learning_rate": 7.317073170731707e-05, |
|
"loss": 0.7838, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.04926108374384237, |
|
"grad_norm": 0.10873105376958847, |
|
"learning_rate": 9.75609756097561e-05, |
|
"loss": 0.7806, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.06157635467980296, |
|
"grad_norm": 0.10080835968255997, |
|
"learning_rate": 0.00012195121951219512, |
|
"loss": 0.7563, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.07389162561576355, |
|
"grad_norm": 0.10492738336324692, |
|
"learning_rate": 0.00014634146341463414, |
|
"loss": 0.7523, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.08620689655172414, |
|
"grad_norm": 0.11805374175310135, |
|
"learning_rate": 0.0001707317073170732, |
|
"loss": 0.7508, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.09852216748768473, |
|
"grad_norm": 0.10792019963264465, |
|
"learning_rate": 0.0001951219512195122, |
|
"loss": 0.7493, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.11083743842364532, |
|
"grad_norm": 0.1062043085694313, |
|
"learning_rate": 0.0001999407400739705, |
|
"loss": 0.7374, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.12315270935960591, |
|
"grad_norm": 0.1073506623506546, |
|
"learning_rate": 0.00019970011699250152, |
|
"loss": 0.7742, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.1354679802955665, |
|
"grad_norm": 0.09551604837179184, |
|
"learning_rate": 0.00019927487224577402, |
|
"loss": 0.7462, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.1477832512315271, |
|
"grad_norm": 0.09559881687164307, |
|
"learning_rate": 0.0001986657932891657, |
|
"loss": 0.7428, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.16009852216748768, |
|
"grad_norm": 0.09791220724582672, |
|
"learning_rate": 0.00019787400799669154, |
|
"loss": 0.7474, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.1724137931034483, |
|
"grad_norm": 0.09669492393732071, |
|
"learning_rate": 0.00019690098257244064, |
|
"loss": 0.7544, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.18472906403940886, |
|
"grad_norm": 0.10031192749738693, |
|
"learning_rate": 0.00019574851883550395, |
|
"loss": 0.7497, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.19704433497536947, |
|
"grad_norm": 0.09971891343593597, |
|
"learning_rate": 0.00019441875088341997, |
|
"loss": 0.7436, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.20935960591133004, |
|
"grad_norm": 0.09163269400596619, |
|
"learning_rate": 0.00019291414114031743, |
|
"loss": 0.7371, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.22167487684729065, |
|
"grad_norm": 0.09539525210857391, |
|
"learning_rate": 0.00019123747579707275, |
|
"loss": 0.7586, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.23399014778325122, |
|
"grad_norm": 0.0916183665394783, |
|
"learning_rate": 0.0001893918596519257, |
|
"loss": 0.763, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.24630541871921183, |
|
"grad_norm": 0.10328999906778336, |
|
"learning_rate": 0.00018738071036110808, |
|
"loss": 0.7504, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.25862068965517243, |
|
"grad_norm": 0.10348416864871979, |
|
"learning_rate": 0.00018520775211013093, |
|
"loss": 0.7501, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.270935960591133, |
|
"grad_norm": 0.09487516433000565, |
|
"learning_rate": 0.00018287700871745036, |
|
"loss": 0.7644, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.2832512315270936, |
|
"grad_norm": 0.105643130838871, |
|
"learning_rate": 0.00018039279618328212, |
|
"loss": 0.76, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.2955665024630542, |
|
"grad_norm": 0.10078058391809464, |
|
"learning_rate": 0.0001777597146973627, |
|
"loss": 0.739, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.3078817733990148, |
|
"grad_norm": 0.0928851068019867, |
|
"learning_rate": 0.00017498264012045687, |
|
"loss": 0.7442, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.32019704433497537, |
|
"grad_norm": 0.09560341387987137, |
|
"learning_rate": 0.00017206671495538612, |
|
"loss": 0.7404, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.33251231527093594, |
|
"grad_norm": 0.10253967344760895, |
|
"learning_rate": 0.0001690173388242972, |
|
"loss": 0.737, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.3448275862068966, |
|
"grad_norm": 0.09540513157844543, |
|
"learning_rate": 0.0001658401584698049, |
|
"loss": 0.7467, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.35714285714285715, |
|
"grad_norm": 0.09915637969970703, |
|
"learning_rate": 0.00016254105729852464, |
|
"loss": 0.7415, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.3694581280788177, |
|
"grad_norm": 0.0903649777173996, |
|
"learning_rate": 0.00015912614448635782, |
|
"loss": 0.7529, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.3817733990147783, |
|
"grad_norm": 0.09867067635059357, |
|
"learning_rate": 0.00015560174366570446, |
|
"loss": 0.7395, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.39408866995073893, |
|
"grad_norm": 0.09925885498523712, |
|
"learning_rate": 0.0001519743812155516, |
|
"loss": 0.7535, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.4064039408866995, |
|
"grad_norm": 0.09206779301166534, |
|
"learning_rate": 0.00014825077417612186, |
|
"loss": 0.7542, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.4187192118226601, |
|
"grad_norm": 0.09731363505125046, |
|
"learning_rate": 0.00014443781781046136, |
|
"loss": 0.7584, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.43103448275862066, |
|
"grad_norm": 0.09406079351902008, |
|
"learning_rate": 0.00014054257283599973, |
|
"loss": 0.7193, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.4433497536945813, |
|
"grad_norm": 0.0967475026845932, |
|
"learning_rate": 0.00013657225234972695, |
|
"loss": 0.7346, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.45566502463054187, |
|
"grad_norm": 0.09659844636917114, |
|
"learning_rate": 0.00013253420847119803, |
|
"loss": 0.7356, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.46798029556650245, |
|
"grad_norm": 0.09907151758670807, |
|
"learning_rate": 0.0001284359187281004, |
|
"loss": 0.7404, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.4802955665024631, |
|
"grad_norm": 0.09383893758058548, |
|
"learning_rate": 0.0001242849722095936, |
|
"loss": 0.7282, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.49261083743842365, |
|
"grad_norm": 0.09458262473344803, |
|
"learning_rate": 0.00012008905551306356, |
|
"loss": 0.7513, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.5049261083743842, |
|
"grad_norm": 0.09368573129177094, |
|
"learning_rate": 0.00011585593851031347, |
|
"loss": 0.7376, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 0.5172413793103449, |
|
"grad_norm": 0.09154163300991058, |
|
"learning_rate": 0.00011159345995955006, |
|
"loss": 0.734, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.5295566502463054, |
|
"grad_norm": 0.09107346832752228, |
|
"learning_rate": 0.00010730951298980776, |
|
"loss": 0.7339, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 0.541871921182266, |
|
"grad_norm": 0.09472489356994629, |
|
"learning_rate": 0.00010301203048469083, |
|
"loss": 0.7584, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.5541871921182266, |
|
"grad_norm": 0.1033613383769989, |
|
"learning_rate": 9.870897039249911e-05, |
|
"loss": 0.7339, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.5665024630541872, |
|
"grad_norm": 0.09532911330461502, |
|
"learning_rate": 9.440830098993969e-05, |
|
"loss": 0.737, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.5788177339901478, |
|
"grad_norm": 0.09540988504886627, |
|
"learning_rate": 9.011798612671286e-05, |
|
"loss": 0.7234, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 0.5911330049261084, |
|
"grad_norm": 0.09416648745536804, |
|
"learning_rate": 8.58459704782957e-05, |
|
"loss": 0.7325, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.603448275862069, |
|
"grad_norm": 0.09317279607057571, |
|
"learning_rate": 8.160016483423199e-05, |
|
"loss": 0.741, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 0.6157635467980296, |
|
"grad_norm": 0.09846732765436172, |
|
"learning_rate": 7.738843144917119e-05, |
|
"loss": 0.7345, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.6280788177339901, |
|
"grad_norm": 0.0930534228682518, |
|
"learning_rate": 7.321856948378259e-05, |
|
"loss": 0.7464, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 0.6403940886699507, |
|
"grad_norm": 0.0964062288403511, |
|
"learning_rate": 6.909830056250527e-05, |
|
"loss": 0.7486, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.6527093596059114, |
|
"grad_norm": 0.09874962270259857, |
|
"learning_rate": 6.503525447487715e-05, |
|
"loss": 0.7365, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 0.6650246305418719, |
|
"grad_norm": 0.09022323042154312, |
|
"learning_rate": 6.103695504692122e-05, |
|
"loss": 0.7403, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.6773399014778325, |
|
"grad_norm": 0.10088326781988144, |
|
"learning_rate": 5.7110806208751655e-05, |
|
"loss": 0.7391, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.6896551724137931, |
|
"grad_norm": 0.09062828868627548, |
|
"learning_rate": 5.326407828419979e-05, |
|
"loss": 0.7475, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.7019704433497537, |
|
"grad_norm": 0.10531575977802277, |
|
"learning_rate": 4.9503894527847964e-05, |
|
"loss": 0.7406, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 0.7142857142857143, |
|
"grad_norm": 0.09364870190620422, |
|
"learning_rate": 4.583721793440188e-05, |
|
"loss": 0.7352, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.7266009852216748, |
|
"grad_norm": 0.1008005440235138, |
|
"learning_rate": 4.227083834482728e-05, |
|
"loss": 0.7564, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 0.7389162561576355, |
|
"grad_norm": 0.09413261711597443, |
|
"learning_rate": 3.881135987312757e-05, |
|
"loss": 0.7305, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.7512315270935961, |
|
"grad_norm": 0.08913769572973251, |
|
"learning_rate": 3.546518867704499e-05, |
|
"loss": 0.7462, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 0.7635467980295566, |
|
"grad_norm": 0.09481265395879745, |
|
"learning_rate": 3.223852109533112e-05, |
|
"loss": 0.7393, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.7758620689655172, |
|
"grad_norm": 0.09792128205299377, |
|
"learning_rate": 2.9137332173554043e-05, |
|
"loss": 0.7319, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 0.7881773399014779, |
|
"grad_norm": 0.09496279060840607, |
|
"learning_rate": 2.616736459968936e-05, |
|
"loss": 0.7403, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.8004926108374384, |
|
"grad_norm": 0.09277407079935074, |
|
"learning_rate": 2.33341180699841e-05, |
|
"loss": 0.7555, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 0.812807881773399, |
|
"grad_norm": 0.09130670130252838, |
|
"learning_rate": 2.0642839104785272e-05, |
|
"loss": 0.7443, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.8251231527093597, |
|
"grad_norm": 0.09380558133125305, |
|
"learning_rate": 1.8098511333192024e-05, |
|
"loss": 0.7335, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 0.8374384236453202, |
|
"grad_norm": 0.09957650303840637, |
|
"learning_rate": 1.570584626452173e-05, |
|
"loss": 0.7601, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.8497536945812808, |
|
"grad_norm": 0.09125210344791412, |
|
"learning_rate": 1.3469274563679402e-05, |
|
"loss": 0.7457, |
|
"step": 345 |
|
}, |
|
{ |
|
"epoch": 0.8620689655172413, |
|
"grad_norm": 0.09114491194486618, |
|
"learning_rate": 1.1392937846586215e-05, |
|
"loss": 0.7409, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.874384236453202, |
|
"grad_norm": 0.09509284049272537, |
|
"learning_rate": 9.48068101086026e-06, |
|
"loss": 0.7192, |
|
"step": 355 |
|
}, |
|
{ |
|
"epoch": 0.8866995073891626, |
|
"grad_norm": 0.09615782648324966, |
|
"learning_rate": 7.736045115951251e-06, |
|
"loss": 0.7328, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.8990147783251231, |
|
"grad_norm": 0.0975566878914833, |
|
"learning_rate": 6.16226082591359e-06, |
|
"loss": 0.7294, |
|
"step": 365 |
|
}, |
|
{ |
|
"epoch": 0.9113300492610837, |
|
"grad_norm": 0.09337764233350754, |
|
"learning_rate": 4.762242426960262e-06, |
|
"loss": 0.7285, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.9236453201970444, |
|
"grad_norm": 0.08856361359357834, |
|
"learning_rate": 3.5385824308756587e-06, |
|
"loss": 0.7406, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 0.9359605911330049, |
|
"grad_norm": 0.0950755774974823, |
|
"learning_rate": 2.493546774280531e-06, |
|
"loss": 0.7322, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.9482758620689655, |
|
"grad_norm": 0.09195266664028168, |
|
"learning_rate": 1.6290706226390285e-06, |
|
"loss": 0.7347, |
|
"step": 385 |
|
}, |
|
{ |
|
"epoch": 0.9605911330049262, |
|
"grad_norm": 0.09885134547948837, |
|
"learning_rate": 9.46754786777726e-07, |
|
"loss": 0.7334, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.9729064039408867, |
|
"grad_norm": 0.08973979949951172, |
|
"learning_rate": 4.4786275855247527e-07, |
|
"loss": 0.7481, |
|
"step": 395 |
|
}, |
|
{ |
|
"epoch": 0.9852216748768473, |
|
"grad_norm": 0.08960015326738358, |
|
"learning_rate": 1.333183711524133e-07, |
|
"loss": 0.7376, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.9975369458128078, |
|
"grad_norm": 0.09271183609962463, |
|
"learning_rate": 3.7040883734462683e-09, |
|
"loss": 0.7399, |
|
"step": 405 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": NaN, |
|
"eval_runtime": 934.5149, |
|
"eval_samples_per_second": 1.236, |
|
"eval_steps_per_second": 0.309, |
|
"step": 406 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 406, |
|
"total_flos": 2.141142957716144e+18, |
|
"train_loss": 0.7449051919829082, |
|
"train_runtime": 67510.9339, |
|
"train_samples_per_second": 1.539, |
|
"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": 2.141142957716144e+18, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|