| { |
| "best_metric": 0.6177173852920532, |
| "best_model_checkpoint": "test_trainer/checkpoint-2000", |
| "epoch": 2.0, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.5, |
| "learning_rate": 4.5e-05, |
| "loss": 0.75, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 4e-05, |
| "loss": 0.6967, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.6491263508796692, |
| "eval_runtime": 60.4692, |
| "eval_samples_per_second": 33.075, |
| "eval_steps_per_second": 4.134, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 3.5e-05, |
| "loss": 0.5624, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.5723, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.6177173852920532, |
| "eval_runtime": 60.461, |
| "eval_samples_per_second": 33.079, |
| "eval_steps_per_second": 4.135, |
| "step": 2000 |
| } |
| ], |
| "max_steps": 5000, |
| "num_train_epochs": 5, |
| "total_flos": 4209288456812544.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
