| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 1869, | |
| "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": 0.7105, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.5740072202166066, | |
| "eval_loss": 0.6886927485466003, | |
| "eval_runtime": 6.0294, | |
| "eval_samples_per_second": 45.941, | |
| "eval_steps_per_second": 5.805, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.6714, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6209386281588448, | |
| "eval_loss": 0.6742456555366516, | |
| "eval_runtime": 6.0186, | |
| "eval_samples_per_second": 46.024, | |
| "eval_steps_per_second": 5.815, | |
| "step": 1246 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.509, | |
| "step": 1869 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.6425992779783394, | |
| "eval_loss": 0.7528035044670105, | |
| "eval_runtime": 6.0214, | |
| "eval_samples_per_second": 46.002, | |
| "eval_steps_per_second": 5.813, | |
| "step": 1869 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1869, | |
| "total_flos": 4673352261980160.0, | |
| "train_loss": 0.6302928485737694, | |
| "train_runtime": 568.3379, | |
| "train_samples_per_second": 13.144, | |
| "train_steps_per_second": 3.289 | |
| } | |
| ], | |
| "max_steps": 1869, | |
| "num_train_epochs": 3, | |
| "total_flos": 4673352261980160.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |