| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 345, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.43, |
| "learning_rate": 1.710144927536232e-05, |
| "loss": 0.5952, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 1.420289855072464e-05, |
| "loss": 0.5222, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.3, |
| "learning_rate": 1.1304347826086957e-05, |
| "loss": 0.4127, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 8.405797101449275e-06, |
| "loss": 0.363, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.17, |
| "learning_rate": 5.507246376811595e-06, |
| "loss": 0.3466, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.61, |
| "learning_rate": 2.6086956521739132e-06, |
| "loss": 0.2853, |
| "step": 300 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 345, |
| "total_flos": 1107256955733504.0, |
| "train_loss": 0.3995490502620089, |
| "train_runtime": 124.5887, |
| "train_samples_per_second": 88.323, |
| "train_steps_per_second": 2.769 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 345, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "total_flos": 1107256955733504.0, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
