| { |
| "best_metric": 0.9149333333333334, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0449/checkpoints/checkpoint-1665", |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 1665, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 3.583953857421875, |
| "learning_rate": 9e-05, |
| "loss": 0.6914, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9090666666666667, |
| "eval_loss": 0.300963431596756, |
| "eval_runtime": 5.323, |
| "eval_samples_per_second": 704.485, |
| "eval_steps_per_second": 11.084, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.1575116515159607, |
| "learning_rate": 9e-05, |
| "loss": 0.1553, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9066666666666666, |
| "eval_loss": 0.30576416850090027, |
| "eval_runtime": 5.2155, |
| "eval_samples_per_second": 719.014, |
| "eval_steps_per_second": 11.312, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.23756776750087738, |
| "learning_rate": 9e-05, |
| "loss": 0.0749, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.912, |
| "eval_loss": 0.3169305920600891, |
| "eval_runtime": 5.1533, |
| "eval_samples_per_second": 727.689, |
| "eval_steps_per_second": 11.449, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 6.989655494689941, |
| "learning_rate": 9e-05, |
| "loss": 0.0506, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9098666666666667, |
| "eval_loss": 0.3411179184913635, |
| "eval_runtime": 5.1972, |
| "eval_samples_per_second": 721.54, |
| "eval_steps_per_second": 11.352, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.011887392029166222, |
| "learning_rate": 9e-05, |
| "loss": 0.0313, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9149333333333334, |
| "eval_loss": 0.34313327074050903, |
| "eval_runtime": 5.2143, |
| "eval_samples_per_second": 719.174, |
| "eval_steps_per_second": 11.315, |
| "step": 1665 |
| } |
| ], |
| "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": 8.2370660311296e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
