| { |
| "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": 0.14659802615642548, |
| "learning_rate": 4.8780487804878055e-06, |
| "loss": 0.7984, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.012315270935960592, |
| "grad_norm": 0.1637599617242813, |
| "learning_rate": 2.4390243902439026e-05, |
| "loss": 0.8035, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.024630541871921183, |
| "grad_norm": 0.1230587288737297, |
| "learning_rate": 4.878048780487805e-05, |
| "loss": 0.7842, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.03694581280788178, |
| "grad_norm": 0.15005113184452057, |
| "learning_rate": 7.317073170731707e-05, |
| "loss": 0.7873, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.04926108374384237, |
| "grad_norm": 0.12097210437059402, |
| "learning_rate": 9.75609756097561e-05, |
| "loss": 0.7846, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.06157635467980296, |
| "grad_norm": 0.11589064449071884, |
| "learning_rate": 0.00012195121951219512, |
| "loss": 0.7552, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.07389162561576355, |
| "grad_norm": 0.09759484231472015, |
| "learning_rate": 0.00014634146341463414, |
| "loss": 0.7583, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.08620689655172414, |
| "grad_norm": 0.10054591298103333, |
| "learning_rate": 0.0001707317073170732, |
| "loss": 0.7525, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.09852216748768473, |
| "grad_norm": 0.10421372950077057, |
| "learning_rate": 0.0001951219512195122, |
| "loss": 0.7675, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.11083743842364532, |
| "grad_norm": 0.11140761524438858, |
| "learning_rate": 0.0001999407400739705, |
| "loss": 0.7676, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.12315270935960591, |
| "grad_norm": 0.1191256195306778, |
| "learning_rate": 0.00019970011699250152, |
| "loss": 0.7603, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1354679802955665, |
| "grad_norm": 0.105014368891716, |
| "learning_rate": 0.00019927487224577402, |
| "loss": 0.7403, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.1477832512315271, |
| "grad_norm": 0.09925462305545807, |
| "learning_rate": 0.0001986657932891657, |
| "loss": 0.7595, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.16009852216748768, |
| "grad_norm": 0.09827063977718353, |
| "learning_rate": 0.00019787400799669154, |
| "loss": 0.7318, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.1724137931034483, |
| "grad_norm": 0.10286720842123032, |
| "learning_rate": 0.00019690098257244064, |
| "loss": 0.7462, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.18472906403940886, |
| "grad_norm": 0.09935111552476883, |
| "learning_rate": 0.00019574851883550395, |
| "loss": 0.737, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.19704433497536947, |
| "grad_norm": 0.1008954718708992, |
| "learning_rate": 0.00019441875088341997, |
| "loss": 0.7477, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.20935960591133004, |
| "grad_norm": 0.09527204930782318, |
| "learning_rate": 0.00019291414114031743, |
| "loss": 0.709, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.22167487684729065, |
| "grad_norm": 0.09949122369289398, |
| "learning_rate": 0.00019123747579707275, |
| "loss": 0.7422, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.23399014778325122, |
| "grad_norm": 0.10889115184545517, |
| "learning_rate": 0.0001893918596519257, |
| "loss": 0.7582, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.24630541871921183, |
| "grad_norm": 0.10153791308403015, |
| "learning_rate": 0.00018738071036110808, |
| "loss": 0.7443, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.25862068965517243, |
| "grad_norm": 0.10695034265518188, |
| "learning_rate": 0.00018520775211013093, |
| "loss": 0.7401, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.270935960591133, |
| "grad_norm": 0.10429364442825317, |
| "learning_rate": 0.00018287700871745036, |
| "loss": 0.7261, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.2832512315270936, |
| "grad_norm": 0.0936528667807579, |
| "learning_rate": 0.00018039279618328212, |
| "loss": 0.7489, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.2955665024630542, |
| "grad_norm": 0.10359769314527512, |
| "learning_rate": 0.0001777597146973627, |
| "loss": 0.7426, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.3078817733990148, |
| "grad_norm": 0.09780474752187729, |
| "learning_rate": 0.00017498264012045687, |
| "loss": 0.7382, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.32019704433497537, |
| "grad_norm": 0.09318186342716217, |
| "learning_rate": 0.00017206671495538612, |
| "loss": 0.7427, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.33251231527093594, |
| "grad_norm": 0.09696605801582336, |
| "learning_rate": 0.0001690173388242972, |
| "loss": 0.7324, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.3448275862068966, |
| "grad_norm": 0.10154663771390915, |
| "learning_rate": 0.0001658401584698049, |
| "loss": 0.7458, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.35714285714285715, |
| "grad_norm": 0.09791245311498642, |
| "learning_rate": 0.00016254105729852464, |
| "loss": 0.7576, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.3694581280788177, |
| "grad_norm": 0.09491541981697083, |
| "learning_rate": 0.00015912614448635782, |
| "loss": 0.7657, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.3817733990147783, |
| "grad_norm": 0.09286640584468842, |
| "learning_rate": 0.00015560174366570446, |
| "loss": 0.7308, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.39408866995073893, |
| "grad_norm": 0.09774602949619293, |
| "learning_rate": 0.0001519743812155516, |
| "loss": 0.7584, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.4064039408866995, |
| "grad_norm": 0.09466628730297089, |
| "learning_rate": 0.00014825077417612186, |
| "loss": 0.7392, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.4187192118226601, |
| "grad_norm": 0.09497351944446564, |
| "learning_rate": 0.00014443781781046136, |
| "loss": 0.7284, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.43103448275862066, |
| "grad_norm": 0.09160592406988144, |
| "learning_rate": 0.00014054257283599973, |
| "loss": 0.727, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.4433497536945813, |
| "grad_norm": 0.09102462232112885, |
| "learning_rate": 0.00013657225234972695, |
| "loss": 0.7329, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.45566502463054187, |
| "grad_norm": 0.09601578861474991, |
| "learning_rate": 0.00013253420847119803, |
| "loss": 0.7453, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.46798029556650245, |
| "grad_norm": 0.1020815521478653, |
| "learning_rate": 0.0001284359187281004, |
| "loss": 0.7378, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.4802955665024631, |
| "grad_norm": 0.09883546084165573, |
| "learning_rate": 0.0001242849722095936, |
| "loss": 0.7419, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.49261083743842365, |
| "grad_norm": 0.09545638412237167, |
| "learning_rate": 0.00012008905551306356, |
| "loss": 0.7245, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5049261083743842, |
| "grad_norm": 0.09954236447811127, |
| "learning_rate": 0.00011585593851031347, |
| "loss": 0.7414, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.5172413793103449, |
| "grad_norm": 0.09122562408447266, |
| "learning_rate": 0.00011159345995955006, |
| "loss": 0.7449, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.5295566502463054, |
| "grad_norm": 0.09573693573474884, |
| "learning_rate": 0.00010730951298980776, |
| "loss": 0.7519, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.541871921182266, |
| "grad_norm": 0.0939580649137497, |
| "learning_rate": 0.00010301203048469083, |
| "loss": 0.7474, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.5541871921182266, |
| "grad_norm": 0.09861047565937042, |
| "learning_rate": 9.870897039249911e-05, |
| "loss": 0.7495, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.5665024630541872, |
| "grad_norm": 0.09757225215435028, |
| "learning_rate": 9.440830098993969e-05, |
| "loss": 0.7313, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.5788177339901478, |
| "grad_norm": 0.09521643817424774, |
| "learning_rate": 9.011798612671286e-05, |
| "loss": 0.7419, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.5911330049261084, |
| "grad_norm": 0.09147543460130692, |
| "learning_rate": 8.58459704782957e-05, |
| "loss": 0.7446, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.603448275862069, |
| "grad_norm": 0.09894198179244995, |
| "learning_rate": 8.160016483423199e-05, |
| "loss": 0.7369, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.6157635467980296, |
| "grad_norm": 0.09482599794864655, |
| "learning_rate": 7.738843144917119e-05, |
| "loss": 0.7425, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.6280788177339901, |
| "grad_norm": 0.09859254956245422, |
| "learning_rate": 7.321856948378259e-05, |
| "loss": 0.7353, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.6403940886699507, |
| "grad_norm": 0.09973224997520447, |
| "learning_rate": 6.909830056250527e-05, |
| "loss": 0.7495, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.6527093596059114, |
| "grad_norm": 0.09812604635953903, |
| "learning_rate": 6.503525447487715e-05, |
| "loss": 0.7457, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.6650246305418719, |
| "grad_norm": 0.10075949877500534, |
| "learning_rate": 6.103695504692122e-05, |
| "loss": 0.7492, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.6773399014778325, |
| "grad_norm": 0.0954367071390152, |
| "learning_rate": 5.7110806208751655e-05, |
| "loss": 0.7568, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.6896551724137931, |
| "grad_norm": 0.10051579773426056, |
| "learning_rate": 5.326407828419979e-05, |
| "loss": 0.7267, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.7019704433497537, |
| "grad_norm": 0.10151689499616623, |
| "learning_rate": 4.9503894527847964e-05, |
| "loss": 0.7308, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.7142857142857143, |
| "grad_norm": 0.09685605019330978, |
| "learning_rate": 4.583721793440188e-05, |
| "loss": 0.738, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.7266009852216748, |
| "grad_norm": 0.09093429893255234, |
| "learning_rate": 4.227083834482728e-05, |
| "loss": 0.7396, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.7389162561576355, |
| "grad_norm": 0.09881714731454849, |
| "learning_rate": 3.881135987312757e-05, |
| "loss": 0.7477, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.7512315270935961, |
| "grad_norm": 0.09277685731649399, |
| "learning_rate": 3.546518867704499e-05, |
| "loss": 0.7401, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.7635467980295566, |
| "grad_norm": 0.09268365055322647, |
| "learning_rate": 3.223852109533112e-05, |
| "loss": 0.72, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.7758620689655172, |
| "grad_norm": 0.09532837569713593, |
| "learning_rate": 2.9137332173554043e-05, |
| "loss": 0.7324, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.7881773399014779, |
| "grad_norm": 0.09861557185649872, |
| "learning_rate": 2.616736459968936e-05, |
| "loss": 0.7259, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.8004926108374384, |
| "grad_norm": 0.09343482553958893, |
| "learning_rate": 2.33341180699841e-05, |
| "loss": 0.7259, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.812807881773399, |
| "grad_norm": 0.09596487879753113, |
| "learning_rate": 2.0642839104785272e-05, |
| "loss": 0.7338, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.8251231527093597, |
| "grad_norm": 0.09384419769048691, |
| "learning_rate": 1.8098511333192024e-05, |
| "loss": 0.7402, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.8374384236453202, |
| "grad_norm": 0.09590372443199158, |
| "learning_rate": 1.570584626452173e-05, |
| "loss": 0.7201, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.8497536945812808, |
| "grad_norm": 0.09268229454755783, |
| "learning_rate": 1.3469274563679402e-05, |
| "loss": 0.7238, |
| "step": 345 |
| }, |
| { |
| "epoch": 0.8620689655172413, |
| "grad_norm": 0.10362634807825089, |
| "learning_rate": 1.1392937846586215e-05, |
| "loss": 0.7436, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.874384236453202, |
| "grad_norm": 0.09515894949436188, |
| "learning_rate": 9.48068101086026e-06, |
| "loss": 0.7305, |
| "step": 355 |
| }, |
| { |
| "epoch": 0.8866995073891626, |
| "grad_norm": 0.0960712730884552, |
| "learning_rate": 7.736045115951251e-06, |
| "loss": 0.7355, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.8990147783251231, |
| "grad_norm": 0.0997166633605957, |
| "learning_rate": 6.16226082591359e-06, |
| "loss": 0.7259, |
| "step": 365 |
| }, |
| { |
| "epoch": 0.9113300492610837, |
| "grad_norm": 0.09447181224822998, |
| "learning_rate": 4.762242426960262e-06, |
| "loss": 0.7417, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.9236453201970444, |
| "grad_norm": 0.0918818935751915, |
| "learning_rate": 3.5385824308756587e-06, |
| "loss": 0.7362, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.9359605911330049, |
| "grad_norm": 0.09515990316867828, |
| "learning_rate": 2.493546774280531e-06, |
| "loss": 0.7361, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.9482758620689655, |
| "grad_norm": 0.09238823503255844, |
| "learning_rate": 1.6290706226390285e-06, |
| "loss": 0.7239, |
| "step": 385 |
| }, |
| { |
| "epoch": 0.9605911330049262, |
| "grad_norm": 0.09093461185693741, |
| "learning_rate": 9.46754786777726e-07, |
| "loss": 0.7283, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.9729064039408867, |
| "grad_norm": 0.09592490643262863, |
| "learning_rate": 4.4786275855247527e-07, |
| "loss": 0.7221, |
| "step": 395 |
| }, |
| { |
| "epoch": 0.9852216748768473, |
| "grad_norm": 0.09440485388040543, |
| "learning_rate": 1.333183711524133e-07, |
| "loss": 0.7501, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.9975369458128078, |
| "grad_norm": 0.09735266119241714, |
| "learning_rate": 3.7040883734462683e-09, |
| "loss": 0.7408, |
| "step": 405 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.8800588846206665, |
| "eval_runtime": 129.9783, |
| "eval_samples_per_second": 8.886, |
| "eval_steps_per_second": 0.562, |
| "step": 406 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 406, |
| "total_flos": 2.1313457003010458e+18, |
| "train_loss": 0.7429345024043116, |
| "train_runtime": 28658.1492, |
| "train_samples_per_second": 3.627, |
| "train_steps_per_second": 0.014 |
| } |
| ], |
| "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": 2.1313457003010458e+18, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
