| { |
| "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": 1.3633, |
| "step": 122 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_exact_match": 67.82510054656079, |
| "eval_f1": 71.20939141253417, |
| "eval_runtime": 4.1573, |
| "eval_samples_per_second": 2332.547, |
| "eval_steps_per_second": 7.457, |
| "step": 122 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 3e-05, |
| "loss": 0.5732, |
| "step": 244 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_exact_match": 69.00072187274415, |
| "eval_f1": 72.37958869441866, |
| "eval_runtime": 3.5547, |
| "eval_samples_per_second": 2727.925, |
| "eval_steps_per_second": 8.721, |
| "step": 244 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4991, |
| "step": 366 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_exact_match": 68.88728472723523, |
| "eval_f1": 72.22939958161348, |
| "eval_runtime": 3.5829, |
| "eval_samples_per_second": 2706.469, |
| "eval_steps_per_second": 8.652, |
| "step": 366 |
| }, |
| { |
| "epoch": 4.0, |
| "learning_rate": 3e-05, |
| "loss": 0.4535, |
| "step": 488 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_exact_match": 69.70196968134475, |
| "eval_f1": 72.60718034149441, |
| "eval_runtime": 3.5904, |
| "eval_samples_per_second": 2700.828, |
| "eval_steps_per_second": 8.634, |
| "step": 488 |
| } |
| ], |
| "max_steps": 1220, |
| "num_train_epochs": 10, |
| "total_flos": 58466195472384.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
