| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.853658536585366, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 1.6121394634246826, | |
| "learning_rate": 4e-05, | |
| "loss": 3.0026, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 1.6527366638183594, | |
| "learning_rate": 8e-05, | |
| "loss": 2.9855, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 1.4183332920074463, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9132, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 1.4664280414581299, | |
| "learning_rate": 0.00016, | |
| "loss": 2.6549, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 1.4606424570083618, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2822, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 1.4920825958251953, | |
| "learning_rate": 0.00019636363636363636, | |
| "loss": 1.8285, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": 1.9488004446029663, | |
| "learning_rate": 0.00019272727272727274, | |
| "loss": 1.4561, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 1.8027275800704956, | |
| "learning_rate": 0.0001890909090909091, | |
| "loss": 1.0259, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": 2.609128713607788, | |
| "learning_rate": 0.00018545454545454545, | |
| "loss": 0.6262, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 1.4539759159088135, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 0.426, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.0731707317073171, | |
| "grad_norm": 4.9530181884765625, | |
| "learning_rate": 0.0001781818181818182, | |
| "loss": 0.6999, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.170731707317073, | |
| "grad_norm": 0.7316228747367859, | |
| "learning_rate": 0.00017454545454545454, | |
| "loss": 0.3318, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.2682926829268293, | |
| "grad_norm": 0.6354440450668335, | |
| "learning_rate": 0.0001709090909090909, | |
| "loss": 0.3177, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.3658536585365852, | |
| "grad_norm": 0.6324684023857117, | |
| "learning_rate": 0.00016727272727272728, | |
| "loss": 0.286, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.4634146341463414, | |
| "grad_norm": 0.696601927280426, | |
| "learning_rate": 0.00016363636363636366, | |
| "loss": 0.2856, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.5609756097560976, | |
| "grad_norm": 0.7076646089553833, | |
| "learning_rate": 0.00016, | |
| "loss": 0.2402, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.6585365853658538, | |
| "grad_norm": 0.8789880871772766, | |
| "learning_rate": 0.00015636363636363637, | |
| "loss": 0.2967, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.7560975609756098, | |
| "grad_norm": 0.9168943762779236, | |
| "learning_rate": 0.00015272727272727275, | |
| "loss": 0.2351, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.8536585365853657, | |
| "grad_norm": 0.9165815114974976, | |
| "learning_rate": 0.0001490909090909091, | |
| "loss": 0.267, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "grad_norm": 1.0183101892471313, | |
| "learning_rate": 0.00014545454545454546, | |
| "loss": 0.2204, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.048780487804878, | |
| "grad_norm": 2.2372703552246094, | |
| "learning_rate": 0.00014181818181818184, | |
| "loss": 0.2912, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.1463414634146343, | |
| "grad_norm": 1.252232551574707, | |
| "learning_rate": 0.0001381818181818182, | |
| "loss": 0.2111, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.2439024390243905, | |
| "grad_norm": 1.2968060970306396, | |
| "learning_rate": 0.00013454545454545455, | |
| "loss": 0.1558, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.341463414634146, | |
| "grad_norm": 1.137199878692627, | |
| "learning_rate": 0.00013090909090909093, | |
| "loss": 0.1633, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.4390243902439024, | |
| "grad_norm": 0.7637185454368591, | |
| "learning_rate": 0.00012727272727272728, | |
| "loss": 0.1547, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.5365853658536586, | |
| "grad_norm": 0.4607781171798706, | |
| "learning_rate": 0.00012363636363636364, | |
| "loss": 0.1199, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.6341463414634148, | |
| "grad_norm": 0.5873786807060242, | |
| "learning_rate": 0.00012, | |
| "loss": 0.1631, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.7317073170731705, | |
| "grad_norm": 0.4516126215457916, | |
| "learning_rate": 0.00011636363636363636, | |
| "loss": 0.1389, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.8292682926829267, | |
| "grad_norm": 0.39783260226249695, | |
| "learning_rate": 0.00011272727272727272, | |
| "loss": 0.1335, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.926829268292683, | |
| "grad_norm": 0.43352019786834717, | |
| "learning_rate": 0.00010909090909090909, | |
| "loss": 0.1376, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 3.024390243902439, | |
| "grad_norm": 0.775999903678894, | |
| "learning_rate": 0.00010545454545454545, | |
| "loss": 0.2164, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 3.1219512195121952, | |
| "grad_norm": 0.42771050333976746, | |
| "learning_rate": 0.00010181818181818181, | |
| "loss": 0.1172, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 3.2195121951219514, | |
| "grad_norm": 0.30603572726249695, | |
| "learning_rate": 9.818181818181818e-05, | |
| "loss": 0.0996, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.317073170731707, | |
| "grad_norm": 0.3905603885650635, | |
| "learning_rate": 9.454545454545455e-05, | |
| "loss": 0.1172, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 3.4146341463414633, | |
| "grad_norm": 0.32397401332855225, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 0.1198, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 3.5121951219512195, | |
| "grad_norm": 0.3815689980983734, | |
| "learning_rate": 8.727272727272727e-05, | |
| "loss": 0.1125, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 3.6097560975609757, | |
| "grad_norm": 0.4549274146556854, | |
| "learning_rate": 8.363636363636364e-05, | |
| "loss": 0.1061, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 3.7073170731707314, | |
| "grad_norm": 0.40387630462646484, | |
| "learning_rate": 8e-05, | |
| "loss": 0.1168, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 3.8048780487804876, | |
| "grad_norm": 0.32471150159835815, | |
| "learning_rate": 7.636363636363637e-05, | |
| "loss": 0.0961, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 3.902439024390244, | |
| "grad_norm": 0.5583019256591797, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 0.1301, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.9328824281692505, | |
| "learning_rate": 6.90909090909091e-05, | |
| "loss": 0.23, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 4.097560975609756, | |
| "grad_norm": 0.3267059624195099, | |
| "learning_rate": 6.545454545454546e-05, | |
| "loss": 0.0928, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 4.195121951219512, | |
| "grad_norm": 0.3295288383960724, | |
| "learning_rate": 6.181818181818182e-05, | |
| "loss": 0.0927, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 4.2926829268292686, | |
| "grad_norm": 0.3473338782787323, | |
| "learning_rate": 5.818181818181818e-05, | |
| "loss": 0.0914, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 4.390243902439025, | |
| "grad_norm": 0.37961214780807495, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 0.1226, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 4.487804878048781, | |
| "grad_norm": 0.316287100315094, | |
| "learning_rate": 5.090909090909091e-05, | |
| "loss": 0.0808, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 4.585365853658536, | |
| "grad_norm": 0.3609072268009186, | |
| "learning_rate": 4.7272727272727275e-05, | |
| "loss": 0.0897, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 4.682926829268292, | |
| "grad_norm": 0.36847370862960815, | |
| "learning_rate": 4.3636363636363636e-05, | |
| "loss": 0.0829, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 4.780487804878049, | |
| "grad_norm": 0.35436517000198364, | |
| "learning_rate": 4e-05, | |
| "loss": 0.089, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 4.878048780487805, | |
| "grad_norm": 0.44199907779693604, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 0.0985, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 4.975609756097561, | |
| "grad_norm": 0.4460374712944031, | |
| "learning_rate": 3.272727272727273e-05, | |
| "loss": 0.121, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 5.073170731707317, | |
| "grad_norm": 1.1119364500045776, | |
| "learning_rate": 2.909090909090909e-05, | |
| "loss": 0.1339, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 5.170731707317073, | |
| "grad_norm": 0.29218897223472595, | |
| "learning_rate": 2.5454545454545454e-05, | |
| "loss": 0.0755, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 5.2682926829268295, | |
| "grad_norm": 0.3813060522079468, | |
| "learning_rate": 2.1818181818181818e-05, | |
| "loss": 0.0908, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 5.365853658536586, | |
| "grad_norm": 0.27708882093429565, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.0825, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 5.463414634146342, | |
| "grad_norm": 0.3478184640407562, | |
| "learning_rate": 1.4545454545454545e-05, | |
| "loss": 0.0946, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 5.560975609756097, | |
| "grad_norm": 0.3666270077228546, | |
| "learning_rate": 1.0909090909090909e-05, | |
| "loss": 0.0765, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 5.658536585365853, | |
| "grad_norm": 0.35096457600593567, | |
| "learning_rate": 7.272727272727272e-06, | |
| "loss": 0.0938, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 5.7560975609756095, | |
| "grad_norm": 0.3677085340023041, | |
| "learning_rate": 3.636363636363636e-06, | |
| "loss": 0.0898, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 5.853658536585366, | |
| "grad_norm": 0.3668128252029419, | |
| "learning_rate": 0.0, | |
| "loss": 0.0941, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2014923116691456.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |