| { |
| "best_metric": 0.9434666666666667, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0399/checkpoints/checkpoint-1998", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 1998, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 50.1236686706543, |
| "learning_rate": 8.554359905560886e-05, |
| "loss": 0.6677, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9208, |
| "eval_loss": 0.2650105059146881, |
| "eval_runtime": 11.8432, |
| "eval_samples_per_second": 316.638, |
| "eval_steps_per_second": 4.982, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.14234839379787445, |
| "learning_rate": 7.305704108364301e-05, |
| "loss": 0.1501, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9242666666666667, |
| "eval_loss": 0.26802095770835876, |
| "eval_runtime": 11.8063, |
| "eval_samples_per_second": 317.627, |
| "eval_steps_per_second": 4.997, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.1541021764278412, |
| "learning_rate": 5.501344202803415e-05, |
| "loss": 0.0703, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9274666666666667, |
| "eval_loss": 0.2630670964717865, |
| "eval_runtime": 11.3497, |
| "eval_samples_per_second": 330.405, |
| "eval_steps_per_second": 5.198, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.1676313430070877, |
| "learning_rate": 3.498655797196586e-05, |
| "loss": 0.0287, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9349333333333333, |
| "eval_loss": 0.24500784277915955, |
| "eval_runtime": 11.236, |
| "eval_samples_per_second": 333.749, |
| "eval_steps_per_second": 5.251, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.06849511712789536, |
| "learning_rate": 1.6942958916356995e-05, |
| "loss": 0.0097, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.94, |
| "eval_loss": 0.24463151395320892, |
| "eval_runtime": 11.0587, |
| "eval_samples_per_second": 339.1, |
| "eval_steps_per_second": 5.335, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.03726572170853615, |
| "learning_rate": 4.456400944391144e-06, |
| "loss": 0.0044, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9434666666666667, |
| "eval_loss": 0.24651294946670532, |
| "eval_runtime": 11.3052, |
| "eval_samples_per_second": 331.705, |
| "eval_steps_per_second": 5.219, |
| "step": 1998 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2331, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 7, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.88447923735552e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
