| { | |
| "best_metric": 2.5774738788604736, | |
| "best_model_checkpoint": "output/rammstein/checkpoint-36", | |
| "epoch": 1.0, | |
| "global_step": 36, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001307727141907142, | |
| "loss": 3.542, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00011269523002449659, | |
| "loss": 3.2347, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 8.635498649403293e-05, | |
| "loss": 3.1198, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 5.668773501204858e-05, | |
| "loss": 2.8512, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 2.9252656466318256e-05, | |
| "loss": 2.8823, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 9.190657300387505e-06, | |
| "loss": 3.015, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 2.610437109062556e-07, | |
| "loss": 3.1043, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.5774738788604736, | |
| "eval_runtime": 2.4107, | |
| "eval_samples_per_second": 21.985, | |
| "eval_steps_per_second": 2.904, | |
| "step": 36 | |
| } | |
| ], | |
| "max_steps": 36, | |
| "num_train_epochs": 1, | |
| "total_flos": 37234114560000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |