| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "global_step": 4390, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.57, |
| "learning_rate": 2.6583143507972666e-05, |
| "loss": 0.1544, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 2.316628701594533e-05, |
| "loss": 0.0595, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 1.9749430523917996e-05, |
| "loss": 0.0481, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.28, |
| "learning_rate": 1.633257403189066e-05, |
| "loss": 0.0379, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.85, |
| "learning_rate": 1.2915717539863326e-05, |
| "loss": 0.0279, |
| "step": 2500 |
| }, |
| { |
| "epoch": 3.42, |
| "learning_rate": 9.498861047835992e-06, |
| "loss": 0.0196, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.99, |
| "learning_rate": 6.082004555808656e-06, |
| "loss": 0.0171, |
| "step": 3500 |
| }, |
| { |
| "epoch": 4.56, |
| "learning_rate": 2.665148063781321e-06, |
| "loss": 0.0112, |
| "step": 4000 |
| }, |
| { |
| "epoch": 5.0, |
| "step": 4390, |
| "total_flos": 4605763182037704.0, |
| "train_loss": 0.04347956821424272, |
| "train_runtime": 756.6331, |
| "train_samples_per_second": 46.383, |
| "train_steps_per_second": 5.802 |
| } |
| ], |
| "max_steps": 4390, |
| "num_train_epochs": 5, |
| "total_flos": 4605763182037704.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
