| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0012437810945273632, | |
| "eval_steps": 1000, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0, | |
| "loss": 1.5524, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.1402, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.664, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 8.613531161467861e-05, | |
| "loss": 1.7923, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00013652123889719707, | |
| "loss": 1.8119, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00017227062322935723, | |
| "loss": 1.6156, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4321, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0002, | |
| "loss": 1.4738, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019789473684210526, | |
| "loss": 1.7251, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019578947368421054, | |
| "loss": 1.6262, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001936842105263158, | |
| "loss": 1.4947, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00019157894736842104, | |
| "loss": 1.8006, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00018947368421052632, | |
| "loss": 1.6487, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001873684210526316, | |
| "loss": 1.7926, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00018526315789473685, | |
| "loss": 1.5979, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001831578947368421, | |
| "loss": 1.6008, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00018105263157894739, | |
| "loss": 1.7569, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00017894736842105264, | |
| "loss": 1.7647, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001768421052631579, | |
| "loss": 1.7386, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00017473684210526317, | |
| "loss": 1.5272, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00017263157894736842, | |
| "loss": 1.8591, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001705263157894737, | |
| "loss": 1.5613, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00016842105263157895, | |
| "loss": 1.3797, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00016631578947368423, | |
| "loss": 1.3594, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00016421052631578948, | |
| "loss": 1.6027, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00016210526315789473, | |
| "loss": 1.5134, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7149, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00015789473684210527, | |
| "loss": 1.8614, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00015578947368421052, | |
| "loss": 1.4819, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001536842105263158, | |
| "loss": 1.623, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00015157894736842108, | |
| "loss": 1.7829, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00014947368421052633, | |
| "loss": 1.4878, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00014736842105263158, | |
| "loss": 1.7675, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00014526315789473686, | |
| "loss": 1.6652, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001431578947368421, | |
| "loss": 1.4829, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00014105263157894736, | |
| "loss": 1.6084, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00013894736842105264, | |
| "loss": 1.5299, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001368421052631579, | |
| "loss": 1.5337, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00013473684210526317, | |
| "loss": 1.4584, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00013263157894736842, | |
| "loss": 1.5648, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001305263157894737, | |
| "loss": 1.6003, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00012842105263157895, | |
| "loss": 1.5679, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001263157894736842, | |
| "loss": 1.425, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00012421052631578949, | |
| "loss": 1.2781, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00012210526315789474, | |
| "loss": 1.7008, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00012, | |
| "loss": 1.4367, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00011789473684210525, | |
| "loss": 1.4628, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00011578947368421053, | |
| "loss": 1.6098, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.0001136842105263158, | |
| "loss": 1.4618, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 0.00011157894736842105, | |
| "loss": 1.3719, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "total_flos": 3065802843488256.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |