| { | |
| "best_metric": 2.357522487640381, | |
| "best_model_checkpoint": "output/armin-van-buuren/checkpoint-37", | |
| "epoch": 1.0, | |
| "global_step": 37, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001311102744406261, | |
| "loss": 2.7864, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00011392228602455959, | |
| "loss": 2.8381, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 8.868764210957135e-05, | |
| "loss": 2.57, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.9886577565364115e-05, | |
| "loss": 2.3246, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.263252034797391e-05, | |
| "loss": 2.5272, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.1764238061872434e-05, | |
| "loss": 2.3641, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.867485501471999e-07, | |
| "loss": 2.2984, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.357522487640381, | |
| "eval_runtime": 2.0184, | |
| "eval_samples_per_second": 22.79, | |
| "eval_steps_per_second": 2.973, | |
| "step": 37 | |
| } | |
| ], | |
| "max_steps": 37, | |
| "num_train_epochs": 1, | |
| "total_flos": 38671220736000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |