| { |
| "best_metric": 0.23137560486793518, |
| "best_model_checkpoint": "my_awesome_model\\checkpoint-3126", |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 3126, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.32, |
| "learning_rate": 1.6801023672424827e-05, |
| "loss": 0.3295, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 1.3602047344849649e-05, |
| "loss": 0.2497, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 1.0403071017274472e-05, |
| "loss": 0.2238, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.91268, |
| "eval_loss": 0.24340802431106567, |
| "eval_runtime": 106.2572, |
| "eval_samples_per_second": 235.278, |
| "eval_steps_per_second": 14.71, |
| "step": 1563 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 7.204094689699297e-06, |
| "loss": 0.1606, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 4.005118362124121e-06, |
| "loss": 0.1459, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.92, |
| "learning_rate": 8.061420345489445e-07, |
| "loss": 0.1564, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.93228, |
| "eval_loss": 0.23137560486793518, |
| "eval_runtime": 101.0576, |
| "eval_samples_per_second": 247.384, |
| "eval_steps_per_second": 15.466, |
| "step": 3126 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 3126, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "total_flos": 6564686875195392.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
