| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "global_step": 488, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "learning_rate": 3e-05, |
| "loss": 1.0223, |
| "step": 122 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 68.41291120965246, |
| "eval_f1": 71.82741255794626, |
| "eval_runtime": 9.5781, |
| "eval_samples_per_second": 1012.416, |
| "eval_steps_per_second": 3.237, |
| "step": 122 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.5184, |
| "step": 244 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 69.6607198102506, |
| "eval_f1": 72.86705962438788, |
| "eval_runtime": 8.6737, |
| "eval_samples_per_second": 1117.975, |
| "eval_steps_per_second": 3.574, |
| "step": 244 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4536, |
| "step": 366 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_exact_match": 70.50634216768073, |
| "eval_f1": 73.34791981442851, |
| "eval_runtime": 8.6101, |
| "eval_samples_per_second": 1126.235, |
| "eval_steps_per_second": 3.6, |
| "step": 366 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4117, |
| "step": 488 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_exact_match": 70.60946684541611, |
| "eval_f1": 73.55661366506135, |
| "eval_runtime": 8.6079, |
| "eval_samples_per_second": 1126.52, |
| "eval_steps_per_second": 3.601, |
| "step": 488 |
| } |
| ], |
| "max_steps": 1220, |
| "num_train_epochs": 10, |
| "total_flos": 153959423541248.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
