| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9939045038943446, | |
| "eval_steps": 500, | |
| "global_step": 368, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005418218760582459, | |
| "grad_norm": 11.441351738340396, | |
| "learning_rate": 5.405405405405406e-07, | |
| "loss": 2.4665, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.027091093802912292, | |
| "grad_norm": 11.567929424436132, | |
| "learning_rate": 2.702702702702703e-06, | |
| "loss": 2.4607, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.054182187605824585, | |
| "grad_norm": 2.1647507226825287, | |
| "learning_rate": 5.405405405405406e-06, | |
| "loss": 2.3924, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08127328140873688, | |
| "grad_norm": 1.0652926230951467, | |
| "learning_rate": 8.108108108108109e-06, | |
| "loss": 2.2869, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.10836437521164917, | |
| "grad_norm": 0.6956953231915263, | |
| "learning_rate": 1.0810810810810812e-05, | |
| "loss": 2.2241, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13545546901456146, | |
| "grad_norm": 0.6368662485384925, | |
| "learning_rate": 1.3513513513513515e-05, | |
| "loss": 2.1943, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16254656281747376, | |
| "grad_norm": 0.52626831061368, | |
| "learning_rate": 1.6216216216216218e-05, | |
| "loss": 2.1796, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18963765662038604, | |
| "grad_norm": 0.5041342654725786, | |
| "learning_rate": 1.891891891891892e-05, | |
| "loss": 2.1739, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.21672875042329834, | |
| "grad_norm": 0.531083346249148, | |
| "learning_rate": 1.9995946530314384e-05, | |
| "loss": 2.1573, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.24381984422621064, | |
| "grad_norm": 0.4970950800288572, | |
| "learning_rate": 1.9971187226043746e-05, | |
| "loss": 2.1556, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2709109380291229, | |
| "grad_norm": 0.4930331306794567, | |
| "learning_rate": 1.9923976226947417e-05, | |
| "loss": 2.1516, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2980020318320352, | |
| "grad_norm": 0.4792958893497388, | |
| "learning_rate": 1.985441983600819e-05, | |
| "loss": 2.1416, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3250931256349475, | |
| "grad_norm": 0.4704908677461612, | |
| "learning_rate": 1.9762674670369757e-05, | |
| "loss": 2.1375, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.3521842194378598, | |
| "grad_norm": 0.46530825034717316, | |
| "learning_rate": 1.9648947308688594e-05, | |
| "loss": 2.1328, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.37927531324077207, | |
| "grad_norm": 0.47535573444890883, | |
| "learning_rate": 1.9513493825989664e-05, | |
| "loss": 2.1402, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4063664070436844, | |
| "grad_norm": 0.4759377502233077, | |
| "learning_rate": 1.9356619217073252e-05, | |
| "loss": 2.1332, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.4334575008465967, | |
| "grad_norm": 0.4662210394921992, | |
| "learning_rate": 1.917867670977126e-05, | |
| "loss": 2.1335, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.460548594649509, | |
| "grad_norm": 0.4757611076987449, | |
| "learning_rate": 1.8980066969599216e-05, | |
| "loss": 2.1258, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.4876396884524213, | |
| "grad_norm": 0.45382312904649785, | |
| "learning_rate": 1.8761237197594945e-05, | |
| "loss": 2.1293, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.5147307822553335, | |
| "grad_norm": 0.47488848221887603, | |
| "learning_rate": 1.852268012337514e-05, | |
| "loss": 2.1279, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.5418218760582458, | |
| "grad_norm": 0.47098691848945873, | |
| "learning_rate": 1.8264932895677195e-05, | |
| "loss": 2.126, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5689129698611581, | |
| "grad_norm": 0.47815599863300057, | |
| "learning_rate": 1.798857587288445e-05, | |
| "loss": 2.1249, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.5960040636640704, | |
| "grad_norm": 0.45607203288859494, | |
| "learning_rate": 1.769423131625808e-05, | |
| "loss": 2.1182, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.6230951574669827, | |
| "grad_norm": 0.4566297150188363, | |
| "learning_rate": 1.738256198881809e-05, | |
| "loss": 2.1182, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.650186251269895, | |
| "grad_norm": 0.4563332108229212, | |
| "learning_rate": 1.7054269663028232e-05, | |
| "loss": 2.1158, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6772773450728073, | |
| "grad_norm": 0.4719747539449419, | |
| "learning_rate": 1.6710093540645056e-05, | |
| "loss": 2.1124, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.7043684388757196, | |
| "grad_norm": 0.45233465694057096, | |
| "learning_rate": 1.6350808588288964e-05, | |
| "loss": 2.1173, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.731459532678632, | |
| "grad_norm": 0.4494520104287378, | |
| "learning_rate": 1.597722379248512e-05, | |
| "loss": 2.1147, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.7585506264815441, | |
| "grad_norm": 0.44217741153395734, | |
| "learning_rate": 1.559018033810316e-05, | |
| "loss": 2.1158, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.7856417202844564, | |
| "grad_norm": 0.43568954148921973, | |
| "learning_rate": 1.5190549714297303e-05, | |
| "loss": 2.1155, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.8127328140873687, | |
| "grad_norm": 0.45615630991925854, | |
| "learning_rate": 1.4779231752211546e-05, | |
| "loss": 2.1162, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.839823907890281, | |
| "grad_norm": 0.4607530478729013, | |
| "learning_rate": 1.4357152598868478e-05, | |
| "loss": 2.117, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.8669150016931934, | |
| "grad_norm": 0.43874353467346544, | |
| "learning_rate": 1.3925262631803722e-05, | |
| "loss": 2.1047, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.8940060954961057, | |
| "grad_norm": 0.4577418545526205, | |
| "learning_rate": 1.3484534319141592e-05, | |
| "loss": 2.1103, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.921097189299018, | |
| "grad_norm": 0.44202574956917495, | |
| "learning_rate": 1.303596002993028e-05, | |
| "loss": 2.1117, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.9481882831019303, | |
| "grad_norm": 0.4461244150173344, | |
| "learning_rate": 1.2580549799667034e-05, | |
| "loss": 2.1141, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.9752793769048426, | |
| "grad_norm": 0.45529168414311305, | |
| "learning_rate": 1.2119329056044533e-05, | |
| "loss": 2.1046, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.9969522519471724, | |
| "eval_loss": 2.1050913333892822, | |
| "eval_runtime": 76.5237, | |
| "eval_samples_per_second": 17.054, | |
| "eval_steps_per_second": 8.533, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 1.0023704707077548, | |
| "grad_norm": 0.4809974366908029, | |
| "learning_rate": 1.165333631003928e-05, | |
| "loss": 2.0998, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.029461564510667, | |
| "grad_norm": 0.48705866202596343, | |
| "learning_rate": 1.1183620817540985e-05, | |
| "loss": 2.0462, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.0565526583135794, | |
| "grad_norm": 0.4868339560578216, | |
| "learning_rate": 1.0711240216788036e-05, | |
| "loss": 2.0529, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.0836437521164917, | |
| "grad_norm": 0.4620568487887428, | |
| "learning_rate": 1.0237258146928849e-05, | |
| "loss": 2.0494, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.110734845919404, | |
| "grad_norm": 0.4641633596897171, | |
| "learning_rate": 9.762741853071153e-06, | |
| "loss": 2.0467, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.1378259397223163, | |
| "grad_norm": 0.48677368374631885, | |
| "learning_rate": 9.288759783211967e-06, | |
| "loss": 2.0482, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.1649170335252286, | |
| "grad_norm": 0.46534164607337153, | |
| "learning_rate": 8.81637918245902e-06, | |
| "loss": 2.0469, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 1.1920081273281409, | |
| "grad_norm": 0.46946874812594946, | |
| "learning_rate": 8.346663689960724e-06, | |
| "loss": 2.0445, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.2190992211310532, | |
| "grad_norm": 0.4663999382035462, | |
| "learning_rate": 7.880670943955467e-06, | |
| "loss": 2.0481, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.2461903149339655, | |
| "grad_norm": 0.4457099195715021, | |
| "learning_rate": 7.419450200332965e-06, | |
| "loss": 2.0529, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.2732814087368778, | |
| "grad_norm": 0.46304032166442355, | |
| "learning_rate": 6.964039970069722e-06, | |
| "loss": 2.0467, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.30037250253979, | |
| "grad_norm": 0.4449406613479281, | |
| "learning_rate": 6.515465680858412e-06, | |
| "loss": 2.0486, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.3274635963427024, | |
| "grad_norm": 0.4389522489189322, | |
| "learning_rate": 6.074737368196279e-06, | |
| "loss": 2.0516, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 1.3545546901456147, | |
| "grad_norm": 0.43429376447812934, | |
| "learning_rate": 5.642847401131526e-06, | |
| "loss": 2.0398, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.381645783948527, | |
| "grad_norm": 0.42907764023330297, | |
| "learning_rate": 5.220768247788458e-06, | |
| "loss": 2.0469, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.4087368777514393, | |
| "grad_norm": 0.43261082208262897, | |
| "learning_rate": 4.809450285702697e-06, | |
| "loss": 2.049, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.4358279715543514, | |
| "grad_norm": 0.4495153435008709, | |
| "learning_rate": 4.409819661896839e-06, | |
| "loss": 2.0453, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 1.462919065357264, | |
| "grad_norm": 0.44801407055899056, | |
| "learning_rate": 4.022776207514885e-06, | |
| "loss": 2.0401, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.490010159160176, | |
| "grad_norm": 0.43760507616111505, | |
| "learning_rate": 3.6491914117110405e-06, | |
| "loss": 2.047, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.5171012529630885, | |
| "grad_norm": 0.4323485633364769, | |
| "learning_rate": 3.2899064593549477e-06, | |
| "loss": 2.0445, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.5441923467660006, | |
| "grad_norm": 0.44598125572196134, | |
| "learning_rate": 2.945730336971767e-06, | |
| "loss": 2.0405, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 1.5712834405689131, | |
| "grad_norm": 0.44045190794321376, | |
| "learning_rate": 2.6174380111819144e-06, | |
| "loss": 2.0449, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.5983745343718252, | |
| "grad_norm": 0.4315376791223261, | |
| "learning_rate": 2.3057686837419246e-06, | |
| "loss": 2.0455, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 1.6254656281747377, | |
| "grad_norm": 0.4141056168787056, | |
| "learning_rate": 2.011424127115552e-06, | |
| "loss": 2.0429, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.6525567219776498, | |
| "grad_norm": 0.42561322896204196, | |
| "learning_rate": 1.7350671043228072e-06, | |
| "loss": 2.0473, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 1.679647815780562, | |
| "grad_norm": 0.4318633569152662, | |
| "learning_rate": 1.4773198766248642e-06, | |
| "loss": 2.0471, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.7067389095834744, | |
| "grad_norm": 0.42654823899186717, | |
| "learning_rate": 1.2387628024050557e-06, | |
| "loss": 2.0502, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 1.7338300033863867, | |
| "grad_norm": 0.4318585206830447, | |
| "learning_rate": 1.0199330304007858e-06, | |
| "loss": 2.0374, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.760921097189299, | |
| "grad_norm": 0.42587188797302283, | |
| "learning_rate": 8.213232902287438e-07, | |
| "loss": 2.0508, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.7880121909922113, | |
| "grad_norm": 0.42658756639019496, | |
| "learning_rate": 6.433807829267491e-07, | |
| "loss": 2.0458, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.8151032847951236, | |
| "grad_norm": 0.4254891411016103, | |
| "learning_rate": 4.865061740103361e-07, | |
| "loss": 2.0538, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 1.842194378598036, | |
| "grad_norm": 0.43121146874552274, | |
| "learning_rate": 3.510526913114065e-07, | |
| "loss": 2.0437, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.8692854724009482, | |
| "grad_norm": 0.4148670481064235, | |
| "learning_rate": 2.3732532963024468e-07, | |
| "loss": 2.0366, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 1.8963765662038605, | |
| "grad_norm": 0.4240449705158572, | |
| "learning_rate": 1.4558016399181086e-07, | |
| "loss": 2.0462, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.9234676600067728, | |
| "grad_norm": 0.41343102256412484, | |
| "learning_rate": 7.602377305258479e-08, | |
| "loss": 2.0485, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 1.950558753809685, | |
| "grad_norm": 0.4219092082642883, | |
| "learning_rate": 2.8812773956256034e-08, | |
| "loss": 2.0398, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.9776498476125974, | |
| "grad_norm": 0.4203661391482514, | |
| "learning_rate": 4.053469685617595e-09, | |
| "loss": 2.0438, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 1.9939045038943446, | |
| "eval_loss": 2.097979784011841, | |
| "eval_runtime": 77.4795, | |
| "eval_samples_per_second": 16.843, | |
| "eval_steps_per_second": 8.428, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 1.9939045038943446, | |
| "step": 368, | |
| "total_flos": 53334434119680.0, | |
| "train_loss": 2.0994615062423376, | |
| "train_runtime": 7293.2016, | |
| "train_samples_per_second": 6.477, | |
| "train_steps_per_second": 0.05 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 368, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 53334434119680.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |