| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 1915, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 2.4986945169712795e-05, | |
| "loss": 0.0915, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "eval_f1": 0.7173913043478262, | |
| "eval_loss": 0.1593717783689499, | |
| "eval_runtime": 6.4722, | |
| "eval_samples_per_second": 210.285, | |
| "eval_steps_per_second": 6.644, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 1915, | |
| "total_flos": 1.61208143619072e+16, | |
| "train_loss": 0.05352723841256323, | |
| "train_runtime": 765.0833, | |
| "train_samples_per_second": 80.083, | |
| "train_steps_per_second": 2.503 | |
| } | |
| ], | |
| "max_steps": 1915, | |
| "num_train_epochs": 5, | |
| "total_flos": 1.61208143619072e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |