| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 4.0, | |
| "global_step": 432, | |
| "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": 0.9075, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_exact_match": 70.44421126267926, | |
| "eval_f1": 75.73356754441237, | |
| "eval_runtime": 8.2066, | |
| "eval_samples_per_second": 1045.136, | |
| "eval_steps_per_second": 3.29, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.437, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_exact_match": 71.33030197038592, | |
| "eval_f1": 76.17001049264807, | |
| "eval_runtime": 7.5268, | |
| "eval_samples_per_second": 1139.532, | |
| "eval_steps_per_second": 3.587, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3982, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_exact_match": 73.80202868135711, | |
| "eval_f1": 76.84701342830796, | |
| "eval_runtime": 7.5488, | |
| "eval_samples_per_second": 1136.207, | |
| "eval_steps_per_second": 3.577, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.3789, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_exact_match": 74.24507403521045, | |
| "eval_f1": 76.92865727668105, | |
| "eval_runtime": 7.5265, | |
| "eval_samples_per_second": 1139.572, | |
| "eval_steps_per_second": 3.587, | |
| "step": 432 | |
| } | |
| ], | |
| "max_steps": 1080, | |
| "num_train_epochs": 10, | |
| "total_flos": 136145933434880.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |