| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 12630, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.233, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9174311926605505, | |
| "eval_loss": 0.28414297103881836, | |
| "eval_runtime": 8.9563, | |
| "eval_samples_per_second": 97.362, | |
| "eval_steps_per_second": 12.17, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.1261, | |
| "step": 8420 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9277522935779816, | |
| "eval_loss": 0.3310103714466095, | |
| "eval_runtime": 8.9528, | |
| "eval_samples_per_second": 97.399, | |
| "eval_steps_per_second": 12.175, | |
| "step": 8420 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.0768, | |
| "step": 12630 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9231651376146789, | |
| "eval_loss": 0.36485353112220764, | |
| "eval_runtime": 8.9701, | |
| "eval_samples_per_second": 97.212, | |
| "eval_steps_per_second": 12.152, | |
| "step": 12630 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 12630, | |
| "total_flos": 5.316079940232192e+16, | |
| "train_loss": 0.14529220810600998, | |
| "train_runtime": 6136.5168, | |
| "train_samples_per_second": 32.925, | |
| "train_steps_per_second": 2.058 | |
| } | |
| ], | |
| "max_steps": 12630, | |
| "num_train_epochs": 3, | |
| "total_flos": 5.316079940232192e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |