| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 3570, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 3.3017, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.5758862495422363, | |
| "eval_runtime": 19.298, | |
| "eval_samples_per_second": 98.559, | |
| "eval_steps_per_second": 1.036, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 2.3813, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 2.15813946723938, | |
| "eval_runtime": 2.3483, | |
| "eval_samples_per_second": 809.952, | |
| "eval_steps_per_second": 8.517, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 2.0668, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 2.0412185192108154, | |
| "eval_runtime": 2.4452, | |
| "eval_samples_per_second": 777.841, | |
| "eval_steps_per_second": 8.179, | |
| "step": 3570 | |
| } | |
| ], | |
| "max_steps": 3570, | |
| "num_train_epochs": 3, | |
| "total_flos": 6990766248960000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |