| { |
| "best_metric": 0.5208448767662048, |
| "best_model_checkpoint": "./outputs/checkpoint-32", |
| "epoch": 1.0, |
| "global_step": 32, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.31, |
| "learning_rate": 1.375e-05, |
| "loss": 0.566, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 7.500000000000001e-06, |
| "loss": 0.5404, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 1.25e-06, |
| "loss": 0.5198, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.5208448767662048, |
| "eval_runtime": 244.3236, |
| "eval_samples_per_second": 94.187, |
| "eval_steps_per_second": 2.947, |
| "step": 32 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 32, |
| "total_flos": 7.8024697970688e+16, |
| "train_loss": 0.5397671833634377, |
| "train_runtime": 281.0136, |
| "train_samples_per_second": 3.559, |
| "train_steps_per_second": 0.114 |
| } |
| ], |
| "max_steps": 32, |
| "num_train_epochs": 1, |
| "total_flos": 7.8024697970688e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
