|
{ |
|
"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": 0.30652108788490295, |
|
"learning_rate": 4.8780487804878055e-06, |
|
"loss": 0.9717, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.012315270935960592, |
|
"grad_norm": 0.3289214074611664, |
|
"learning_rate": 2.4390243902439026e-05, |
|
"loss": 0.9783, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.024630541871921183, |
|
"grad_norm": 0.15074408054351807, |
|
"learning_rate": 4.878048780487805e-05, |
|
"loss": 0.9472, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.03694581280788178, |
|
"grad_norm": 0.10472998023033142, |
|
"learning_rate": 7.317073170731707e-05, |
|
"loss": 0.9366, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.04926108374384237, |
|
"grad_norm": 0.08562398701906204, |
|
"learning_rate": 9.75609756097561e-05, |
|
"loss": 0.942, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.06157635467980296, |
|
"grad_norm": 0.08849021792411804, |
|
"learning_rate": 0.00012195121951219512, |
|
"loss": 0.8976, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.07389162561576355, |
|
"grad_norm": 0.08396520465612411, |
|
"learning_rate": 0.00014634146341463414, |
|
"loss": 0.8852, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.08620689655172414, |
|
"grad_norm": 0.07711857557296753, |
|
"learning_rate": 0.0001707317073170732, |
|
"loss": 0.8808, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.09852216748768473, |
|
"grad_norm": 0.06691651791334152, |
|
"learning_rate": 0.0001951219512195122, |
|
"loss": 0.8855, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.11083743842364532, |
|
"grad_norm": 0.06679017841815948, |
|
"learning_rate": 0.0001999407400739705, |
|
"loss": 0.893, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.12315270935960591, |
|
"grad_norm": 0.07381235063076019, |
|
"learning_rate": 0.00019970011699250152, |
|
"loss": 0.8844, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.1354679802955665, |
|
"grad_norm": 0.07115236669778824, |
|
"learning_rate": 0.00019927487224577402, |
|
"loss": 0.8677, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.1477832512315271, |
|
"grad_norm": 0.07492396980524063, |
|
"learning_rate": 0.0001986657932891657, |
|
"loss": 0.8868, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.16009852216748768, |
|
"grad_norm": 0.0643257200717926, |
|
"learning_rate": 0.00019787400799669154, |
|
"loss": 0.8586, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.1724137931034483, |
|
"grad_norm": 0.06939674913883209, |
|
"learning_rate": 0.00019690098257244064, |
|
"loss": 0.8685, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.18472906403940886, |
|
"grad_norm": 0.07422396540641785, |
|
"learning_rate": 0.00019574851883550395, |
|
"loss": 0.8622, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.19704433497536947, |
|
"grad_norm": 0.07255557179450989, |
|
"learning_rate": 0.00019441875088341997, |
|
"loss": 0.8716, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.20935960591133004, |
|
"grad_norm": 0.07202558219432831, |
|
"learning_rate": 0.00019291414114031743, |
|
"loss": 0.8244, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.22167487684729065, |
|
"grad_norm": 0.07127554714679718, |
|
"learning_rate": 0.00019123747579707275, |
|
"loss": 0.8599, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.23399014778325122, |
|
"grad_norm": 0.08557884395122528, |
|
"learning_rate": 0.0001893918596519257, |
|
"loss": 0.8752, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.24630541871921183, |
|
"grad_norm": 0.07851414382457733, |
|
"learning_rate": 0.00018738071036110808, |
|
"loss": 0.8663, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.25862068965517243, |
|
"grad_norm": 0.07385963201522827, |
|
"learning_rate": 0.00018520775211013093, |
|
"loss": 0.8593, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.270935960591133, |
|
"grad_norm": 0.07457491755485535, |
|
"learning_rate": 0.00018287700871745036, |
|
"loss": 0.8363, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.2832512315270936, |
|
"grad_norm": 0.07243283838033676, |
|
"learning_rate": 0.00018039279618328212, |
|
"loss": 0.8641, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.2955665024630542, |
|
"grad_norm": 0.07686326652765274, |
|
"learning_rate": 0.0001777597146973627, |
|
"loss": 0.8502, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.3078817733990148, |
|
"grad_norm": 0.07686852663755417, |
|
"learning_rate": 0.00017498264012045687, |
|
"loss": 0.8628, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.32019704433497537, |
|
"grad_norm": 0.07369978725910187, |
|
"learning_rate": 0.00017206671495538612, |
|
"loss": 0.8497, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.33251231527093594, |
|
"grad_norm": 0.0735793486237526, |
|
"learning_rate": 0.0001690173388242972, |
|
"loss": 0.8464, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.3448275862068966, |
|
"grad_norm": 0.07749839872121811, |
|
"learning_rate": 0.0001658401584698049, |
|
"loss": 0.8631, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.35714285714285715, |
|
"grad_norm": 0.07005272060632706, |
|
"learning_rate": 0.00016254105729852464, |
|
"loss": 0.8738, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.3694581280788177, |
|
"grad_norm": 0.074895478785038, |
|
"learning_rate": 0.00015912614448635782, |
|
"loss": 0.8847, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.3817733990147783, |
|
"grad_norm": 0.0702088475227356, |
|
"learning_rate": 0.00015560174366570446, |
|
"loss": 0.8473, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 0.39408866995073893, |
|
"grad_norm": 0.07352044433355331, |
|
"learning_rate": 0.0001519743812155516, |
|
"loss": 0.8714, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.4064039408866995, |
|
"grad_norm": 0.07473480701446533, |
|
"learning_rate": 0.00014825077417612186, |
|
"loss": 0.8496, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.4187192118226601, |
|
"grad_norm": 0.07085709273815155, |
|
"learning_rate": 0.00014443781781046136, |
|
"loss": 0.8402, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.43103448275862066, |
|
"grad_norm": 0.07307003438472748, |
|
"learning_rate": 0.00014054257283599973, |
|
"loss": 0.8406, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 0.4433497536945813, |
|
"grad_norm": 0.07170814275741577, |
|
"learning_rate": 0.00013657225234972695, |
|
"loss": 0.8478, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.45566502463054187, |
|
"grad_norm": 0.0753386840224266, |
|
"learning_rate": 0.00013253420847119803, |
|
"loss": 0.862, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 0.46798029556650245, |
|
"grad_norm": 0.07479824870824814, |
|
"learning_rate": 0.0001284359187281004, |
|
"loss": 0.8543, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.4802955665024631, |
|
"grad_norm": 0.0772319808602333, |
|
"learning_rate": 0.0001242849722095936, |
|
"loss": 0.8503, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.49261083743842365, |
|
"grad_norm": 0.07660327851772308, |
|
"learning_rate": 0.00012008905551306356, |
|
"loss": 0.8368, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.5049261083743842, |
|
"grad_norm": 0.07217700779438019, |
|
"learning_rate": 0.00011585593851031347, |
|
"loss": 0.8478, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 0.5172413793103449, |
|
"grad_norm": 0.07179830223321915, |
|
"learning_rate": 0.00011159345995955006, |
|
"loss": 0.8601, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.5295566502463054, |
|
"grad_norm": 0.07478391379117966, |
|
"learning_rate": 0.00010730951298980776, |
|
"loss": 0.8665, |
|
"step": 215 |
|
}, |
|
{ |
|
"epoch": 0.541871921182266, |
|
"grad_norm": 0.07220473885536194, |
|
"learning_rate": 0.00010301203048469083, |
|
"loss": 0.859, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.5541871921182266, |
|
"grad_norm": 0.07683911919593811, |
|
"learning_rate": 9.870897039249911e-05, |
|
"loss": 0.8623, |
|
"step": 225 |
|
}, |
|
{ |
|
"epoch": 0.5665024630541872, |
|
"grad_norm": 0.0735134705901146, |
|
"learning_rate": 9.440830098993969e-05, |
|
"loss": 0.8417, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.5788177339901478, |
|
"grad_norm": 0.07750938087701797, |
|
"learning_rate": 9.011798612671286e-05, |
|
"loss": 0.852, |
|
"step": 235 |
|
}, |
|
{ |
|
"epoch": 0.5911330049261084, |
|
"grad_norm": 0.07520028203725815, |
|
"learning_rate": 8.58459704782957e-05, |
|
"loss": 0.8541, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.603448275862069, |
|
"grad_norm": 0.07630393654108047, |
|
"learning_rate": 8.160016483423199e-05, |
|
"loss": 0.8515, |
|
"step": 245 |
|
}, |
|
{ |
|
"epoch": 0.6157635467980296, |
|
"grad_norm": 0.07962335646152496, |
|
"learning_rate": 7.738843144917119e-05, |
|
"loss": 0.8577, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.6280788177339901, |
|
"grad_norm": 0.07434184104204178, |
|
"learning_rate": 7.321856948378259e-05, |
|
"loss": 0.8508, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 0.6403940886699507, |
|
"grad_norm": 0.07535861432552338, |
|
"learning_rate": 6.909830056250527e-05, |
|
"loss": 0.8591, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.6527093596059114, |
|
"grad_norm": 0.08042064309120178, |
|
"learning_rate": 6.503525447487715e-05, |
|
"loss": 0.8595, |
|
"step": 265 |
|
}, |
|
{ |
|
"epoch": 0.6650246305418719, |
|
"grad_norm": 0.08419187366962433, |
|
"learning_rate": 6.103695504692122e-05, |
|
"loss": 0.8629, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.6773399014778325, |
|
"grad_norm": 0.07470737397670746, |
|
"learning_rate": 5.7110806208751655e-05, |
|
"loss": 0.8716, |
|
"step": 275 |
|
}, |
|
{ |
|
"epoch": 0.6896551724137931, |
|
"grad_norm": 0.07928784936666489, |
|
"learning_rate": 5.326407828419979e-05, |
|
"loss": 0.8364, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.7019704433497537, |
|
"grad_norm": 0.07715894281864166, |
|
"learning_rate": 4.9503894527847964e-05, |
|
"loss": 0.848, |
|
"step": 285 |
|
}, |
|
{ |
|
"epoch": 0.7142857142857143, |
|
"grad_norm": 0.08346334099769592, |
|
"learning_rate": 4.583721793440188e-05, |
|
"loss": 0.8391, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.7266009852216748, |
|
"grad_norm": 0.07233065366744995, |
|
"learning_rate": 4.227083834482728e-05, |
|
"loss": 0.849, |
|
"step": 295 |
|
}, |
|
{ |
|
"epoch": 0.7389162561576355, |
|
"grad_norm": 0.08105510473251343, |
|
"learning_rate": 3.881135987312757e-05, |
|
"loss": 0.8653, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.7512315270935961, |
|
"grad_norm": 0.07780944555997849, |
|
"learning_rate": 3.546518867704499e-05, |
|
"loss": 0.8511, |
|
"step": 305 |
|
}, |
|
{ |
|
"epoch": 0.7635467980295566, |
|
"grad_norm": 0.07753836363554001, |
|
"learning_rate": 3.223852109533112e-05, |
|
"loss": 0.8337, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.7758620689655172, |
|
"grad_norm": 0.07628113776445389, |
|
"learning_rate": 2.9137332173554043e-05, |
|
"loss": 0.837, |
|
"step": 315 |
|
}, |
|
{ |
|
"epoch": 0.7881773399014779, |
|
"grad_norm": 0.08198127895593643, |
|
"learning_rate": 2.616736459968936e-05, |
|
"loss": 0.8445, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.8004926108374384, |
|
"grad_norm": 0.07406695932149887, |
|
"learning_rate": 2.33341180699841e-05, |
|
"loss": 0.8309, |
|
"step": 325 |
|
}, |
|
{ |
|
"epoch": 0.812807881773399, |
|
"grad_norm": 0.10794137418270111, |
|
"learning_rate": 2.0642839104785272e-05, |
|
"loss": 0.8495, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.8251231527093597, |
|
"grad_norm": 0.07688434422016144, |
|
"learning_rate": 1.8098511333192024e-05, |
|
"loss": 0.8517, |
|
"step": 335 |
|
}, |
|
{ |
|
"epoch": 0.8374384236453202, |
|
"grad_norm": 0.07871481031179428, |
|
"learning_rate": 1.570584626452173e-05, |
|
"loss": 0.8309, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.8497536945812808, |
|
"grad_norm": 0.07757215201854706, |
|
"learning_rate": 1.3469274563679402e-05, |
|
"loss": 0.8362, |
|
"step": 345 |
|
}, |
|
{ |
|
"epoch": 0.8620689655172413, |
|
"grad_norm": 0.07689883559942245, |
|
"learning_rate": 1.1392937846586215e-05, |
|
"loss": 0.8632, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.874384236453202, |
|
"grad_norm": 0.07467465102672577, |
|
"learning_rate": 9.48068101086026e-06, |
|
"loss": 0.8535, |
|
"step": 355 |
|
}, |
|
{ |
|
"epoch": 0.8866995073891626, |
|
"grad_norm": 0.07738694548606873, |
|
"learning_rate": 7.736045115951251e-06, |
|
"loss": 0.852, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.8990147783251231, |
|
"grad_norm": 0.07973465323448181, |
|
"learning_rate": 6.16226082591359e-06, |
|
"loss": 0.8402, |
|
"step": 365 |
|
}, |
|
{ |
|
"epoch": 0.9113300492610837, |
|
"grad_norm": 0.07645995169878006, |
|
"learning_rate": 4.762242426960262e-06, |
|
"loss": 0.8543, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.9236453201970444, |
|
"grad_norm": 0.0754699632525444, |
|
"learning_rate": 3.5385824308756587e-06, |
|
"loss": 0.8506, |
|
"step": 375 |
|
}, |
|
{ |
|
"epoch": 0.9359605911330049, |
|
"grad_norm": 0.07717719674110413, |
|
"learning_rate": 2.493546774280531e-06, |
|
"loss": 0.8478, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.9482758620689655, |
|
"grad_norm": 0.07168090343475342, |
|
"learning_rate": 1.6290706226390285e-06, |
|
"loss": 0.8256, |
|
"step": 385 |
|
}, |
|
{ |
|
"epoch": 0.9605911330049262, |
|
"grad_norm": 0.07357249408960342, |
|
"learning_rate": 9.46754786777726e-07, |
|
"loss": 0.8473, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.9729064039408867, |
|
"grad_norm": 0.07304390519857407, |
|
"learning_rate": 4.4786275855247527e-07, |
|
"loss": 0.8284, |
|
"step": 395 |
|
}, |
|
{ |
|
"epoch": 0.9852216748768473, |
|
"grad_norm": 0.07657473534345627, |
|
"learning_rate": 1.333183711524133e-07, |
|
"loss": 0.8619, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.9975369458128078, |
|
"grad_norm": 0.08985913544893265, |
|
"learning_rate": 3.7040883734462683e-09, |
|
"loss": 0.8609, |
|
"step": 405 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 1.0922821760177612, |
|
"eval_runtime": 133.4455, |
|
"eval_samples_per_second": 8.655, |
|
"eval_steps_per_second": 0.547, |
|
"step": 406 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 406, |
|
"total_flos": 2.0153806840502682e+18, |
|
"train_loss": 0.012793793173259115, |
|
"train_runtime": 598.372, |
|
"train_samples_per_second": 173.691, |
|
"train_steps_per_second": 0.679 |
|
} |
|
], |
|
"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": 2.0153806840502682e+18, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|