| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 57.142857142857146, |
| "eval_steps": 500, |
| "global_step": 2000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 14.29, |
| "learning_rate": 3.809523809523809e-05, |
| "loss": 1.8052, |
| "step": 500 |
| }, |
| { |
| "epoch": 28.57, |
| "learning_rate": 2.6190476190476192e-05, |
| "loss": 1.0819, |
| "step": 1000 |
| }, |
| { |
| "epoch": 42.86, |
| "learning_rate": 1.4285714285714285e-05, |
| "loss": 0.6781, |
| "step": 1500 |
| }, |
| { |
| "epoch": 57.14, |
| "learning_rate": 2.3809523809523808e-06, |
| "loss": 0.5142, |
| "step": 2000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2100, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 60, |
| "save_steps": 500, |
| "total_flos": 4121097928704000.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
