| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.6326530612244898, |
| "eval_steps": 20, |
| "global_step": 20, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.82, |
| "learning_rate": 2.9999999999999997e-05, |
| "loss": 1.7509, |
| "step": 10 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 5.9999999999999995e-05, |
| "loss": 1.6967, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.63, |
| "eval_loss": 1.6115258932113647, |
| "eval_runtime": 30.6688, |
| "eval_samples_per_second": 12.619, |
| "eval_steps_per_second": 1.598, |
| "step": 20 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 400, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 34, |
| "save_steps": 20, |
| "total_flos": 5.116881906381619e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
