| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "global_step": 8171, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.06, |
| "learning_rate": 2.8164239383184435e-05, |
| "loss": 0.5827, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 2.6328478766368865e-05, |
| "loss": 0.4534, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 2.44927181495533e-05, |
| "loss": 0.403, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 2.2656957532737732e-05, |
| "loss": 0.3697, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 2.0821196915922163e-05, |
| "loss": 0.3577, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 1.8985436299106597e-05, |
| "loss": 0.3408, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 1.7149675682291027e-05, |
| "loss": 0.3056, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 1.531391506547546e-05, |
| "loss": 0.2908, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 1.3478154448659894e-05, |
| "loss": 0.2863, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 1.1642393831844328e-05, |
| "loss": 0.2647, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 9.80663321502876e-06, |
| "loss": 0.2564, |
| "step": 5500 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 7.970872598213192e-06, |
| "loss": 0.2523, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 6.135111981397626e-06, |
| "loss": 0.2408, |
| "step": 6500 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 4.299351364582058e-06, |
| "loss": 0.2378, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 2.4635907477664916e-06, |
| "loss": 0.2246, |
| "step": 7500 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 6.278301309509239e-07, |
| "loss": 0.2202, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.0, |
| "step": 8171, |
| "train_runtime": 1027.4966, |
| "train_samples_per_second": 7.952 |
| } |
| ], |
| "max_steps": 8171, |
| "num_train_epochs": 1, |
| "total_flos": 12588553916743680, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
