| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 1284, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.17, |
| "learning_rate": 3.0529595015576326e-05, |
| "loss": 0.3272, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.34, |
| "learning_rate": 1.1059190031152649e-05, |
| "loss": 0.214, |
| "step": 1000 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 1284, |
| "total_flos": 7.955327653834015e+17, |
| "train_loss": 0.2442077654544438, |
| "train_runtime": 16583.1029, |
| "train_samples_per_second": 0.619, |
| "train_steps_per_second": 0.077 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1284, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "total_flos": 7.955327653834015e+17, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
