| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 4.0, |
| "global_step": 1100, |
| "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": 1.4129, |
| "step": 275 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 55.9053282033345, |
| "eval_f1": 64.54826839917571, |
| "eval_runtime": 8.2847, |
| "eval_samples_per_second": 1035.28, |
| "eval_steps_per_second": 3.259, |
| "step": 275 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.7679, |
| "step": 550 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 55.47394193774047, |
| "eval_f1": 64.35387050750286, |
| "eval_runtime": 7.4916, |
| "eval_samples_per_second": 1144.878, |
| "eval_steps_per_second": 3.604, |
| "step": 550 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3e-05, |
| "loss": 0.5688, |
| "step": 825 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_exact_match": 56.418328086743614, |
| "eval_f1": 65.43057795834304, |
| "eval_runtime": 7.4992, |
| "eval_samples_per_second": 1143.725, |
| "eval_steps_per_second": 3.6, |
| "step": 825 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4276, |
| "step": 1100 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_exact_match": 57.73580506004431, |
| "eval_f1": 65.52603282157007, |
| "eval_runtime": 7.5096, |
| "eval_samples_per_second": 1142.144, |
| "eval_steps_per_second": 3.595, |
| "step": 1100 |
| } |
| ], |
| "max_steps": 2750, |
| "num_train_epochs": 10, |
| "total_flos": 348635380318208.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
