| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.392515230635335, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 2.7777777777777783e-06, | |
| "loss": 71.7806, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 4.981949458483755e-06, | |
| "loss": 69.8115, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 4.8916967509025275e-06, | |
| "loss": 71.5473, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 4.8014440433213e-06, | |
| "loss": 69.2454, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 4.7111913357400725e-06, | |
| "loss": 70.2168, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 4.620938628158845e-06, | |
| "loss": 70.5127, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.5306859205776174e-06, | |
| "loss": 70.727, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 4.44043321299639e-06, | |
| "loss": 69.9849, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.350180505415163e-06, | |
| "loss": 69.3796, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 4.259927797833936e-06, | |
| "loss": 70.7486, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 4.169675090252708e-06, | |
| "loss": 70.2295, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 4.079422382671481e-06, | |
| "loss": 70.1762, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 3.989169675090253e-06, | |
| "loss": 68.9137, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.898916967509026e-06, | |
| "loss": 69.3755, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 3.808664259927798e-06, | |
| "loss": 60.553, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.11, | |
| "learning_rate": 3.718411552346571e-06, | |
| "loss": 51.3341, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.18, | |
| "learning_rate": 3.628158844765343e-06, | |
| "loss": 45.3576, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 3.5379061371841155e-06, | |
| "loss": 45.6309, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 3.4476534296028884e-06, | |
| "loss": 44.5947, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 3.357400722021661e-06, | |
| "loss": 40.3725, | |
| "step": 200 | |
| } | |
| ], | |
| "max_steps": 572, | |
| "num_train_epochs": 4, | |
| "total_flos": 0.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |