| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "global_step": 4469, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07, |
| "learning_rate": 1e-05, |
| "loss": 0.751, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 2e-05, |
| "loss": 0.6623, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 3e-05, |
| "loss": 0.6439, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 4e-05, |
| "loss": 0.6392, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 5e-05, |
| "loss": 0.6385, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 6e-05, |
| "loss": 0.6356, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 7e-05, |
| "loss": 0.6297, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 8e-05, |
| "loss": 0.6312, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 9e-05, |
| "loss": 0.627, |
| "step": 2700 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.0001, |
| "loss": 0.6236, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.0001, |
| "loss": 0.6269, |
| "step": 3300 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.0001, |
| "loss": 0.6273, |
| "step": 3600 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.0001, |
| "loss": 0.6158, |
| "step": 3900 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.0001, |
| "loss": 0.6154, |
| "step": 4200 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 4469, |
| "total_flos": 2.955925823162417e+18, |
| "train_loss": 0.6393276273497375, |
| "train_runtime": 42382.3022, |
| "train_samples_per_second": 3.374, |
| "train_steps_per_second": 0.105 |
| } |
| ], |
| "max_steps": 4469, |
| "num_train_epochs": 1, |
| "total_flos": 2.955925823162417e+18, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
