| { | |
| "best_metric": 0.331002331002331, | |
| "best_model_checkpoint": "vit-base-patch16-224-for-pre_evaluation/checkpoint-30", | |
| "epoch": 2.7906976744186047, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 1.5912, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_accuracy": 0.32167832167832167, | |
| "eval_loss": 1.5083742141723633, | |
| "eval_runtime": 7.0735, | |
| "eval_samples_per_second": 60.649, | |
| "eval_steps_per_second": 1.979, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.86, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 1.4776, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "eval_accuracy": 0.31002331002331, | |
| "eval_loss": 1.491591215133667, | |
| "eval_runtime": 8.1797, | |
| "eval_samples_per_second": 52.447, | |
| "eval_steps_per_second": 1.712, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 0.0, | |
| "loss": 1.4576, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_accuracy": 0.331002331002331, | |
| "eval_loss": 1.4792332649230957, | |
| "eval_runtime": 8.0572, | |
| "eval_samples_per_second": 53.245, | |
| "eval_steps_per_second": 1.738, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "step": 30, | |
| "total_flos": 2.9509743083382374e+17, | |
| "train_loss": 1.5088175773620605, | |
| "train_runtime": 204.2286, | |
| "train_samples_per_second": 19.978, | |
| "train_steps_per_second": 0.147 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 30, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 2.9509743083382374e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |