| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.5638297872340425, |
| "eval_steps": 500, |
| "global_step": 159, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00012413793103448277, |
| "loss": 1.725, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00019446640316205535, |
| "loss": 1.1543, |
| "step": 36 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.00018023715415019763, |
| "loss": 0.9337, |
| "step": 54 |
| }, |
| { |
| "epoch": 1.2, |
| "learning_rate": 0.00016600790513833993, |
| "loss": 0.8044, |
| "step": 72 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 0.0001517786561264822, |
| "loss": 0.7547, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.02, |
| "learning_rate": 0.00013754940711462453, |
| "loss": 0.7503, |
| "step": 108 |
| }, |
| { |
| "epoch": 2.21, |
| "learning_rate": 0.0001233201581027668, |
| "loss": 0.6, |
| "step": 126 |
| }, |
| { |
| "epoch": 2.4, |
| "learning_rate": 0.00010909090909090909, |
| "loss": 0.6354, |
| "step": 144 |
| } |
| ], |
| "logging_steps": 18, |
| "max_steps": 282, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "total_flos": 2603080275056640.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
