| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 10.0, |
| "global_step": 3360, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.49, |
| "learning_rate": 4.255952380952381e-05, |
| "loss": 3.5379, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.98, |
| "learning_rate": 3.511904761904762e-05, |
| "loss": 2.2968, |
| "step": 1000 |
| }, |
| { |
| "epoch": 4.46, |
| "learning_rate": 2.767857142857143e-05, |
| "loss": 1.6312, |
| "step": 1500 |
| }, |
| { |
| "epoch": 5.95, |
| "learning_rate": 2.023809523809524e-05, |
| "loss": 1.2534, |
| "step": 2000 |
| }, |
| { |
| "epoch": 7.44, |
| "learning_rate": 1.2797619047619047e-05, |
| "loss": 0.9268, |
| "step": 2500 |
| }, |
| { |
| "epoch": 8.93, |
| "learning_rate": 5.357142857142857e-06, |
| "loss": 0.7349, |
| "step": 3000 |
| }, |
| { |
| "epoch": 10.0, |
| "step": 3360, |
| "total_flos": 6081793855488000.0, |
| "train_loss": 1.6118421917869932, |
| "train_runtime": 1201.1166, |
| "train_samples_per_second": 27.974, |
| "train_steps_per_second": 2.797 |
| } |
| ], |
| "max_steps": 3360, |
| "num_train_epochs": 10, |
| "total_flos": 6081793855488000.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
