| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.0, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.9949, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.4736842215061188, | |
| "eval_loss": 0.957302987575531, | |
| "eval_runtime": 0.5922, | |
| "eval_samples_per_second": 32.083, | |
| "eval_steps_per_second": 3.377, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.5907, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5789473652839661, | |
| "eval_loss": 0.9047484397888184, | |
| "eval_runtime": 0.6154, | |
| "eval_samples_per_second": 30.876, | |
| "eval_steps_per_second": 3.25, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.2675, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.6842105388641357, | |
| "eval_loss": 0.7158014178276062, | |
| "eval_runtime": 0.6188, | |
| "eval_samples_per_second": 30.703, | |
| "eval_steps_per_second": 3.232, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 60, | |
| "total_flos": 118401037977600.0, | |
| "train_loss": 0.617707633972168, | |
| "train_runtime": 43.1317, | |
| "train_samples_per_second": 10.433, | |
| "train_steps_per_second": 1.391 | |
| } | |
| ], | |
| "max_steps": 60, | |
| "num_train_epochs": 6, | |
| "total_flos": 118401037977600.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |