| { |
| "best_metric": 0.9472, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0374/checkpoints/checkpoint-1332", |
| "epoch": 4.0, |
| "eval_steps": 500, |
| "global_step": 1332, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 0.6953127384185791, |
| "learning_rate": 5e-05, |
| "loss": 0.7673, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9394666666666667, |
| "eval_loss": 0.23629191517829895, |
| "eval_runtime": 6.9697, |
| "eval_samples_per_second": 538.047, |
| "eval_steps_per_second": 8.465, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.14308351278305054, |
| "learning_rate": 5e-05, |
| "loss": 0.1062, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9456, |
| "eval_loss": 0.19589368999004364, |
| "eval_runtime": 6.8834, |
| "eval_samples_per_second": 544.785, |
| "eval_steps_per_second": 8.571, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.040779825299978256, |
| "learning_rate": 5e-05, |
| "loss": 0.0419, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9461333333333334, |
| "eval_loss": 0.21449847519397736, |
| "eval_runtime": 6.8917, |
| "eval_samples_per_second": 544.132, |
| "eval_steps_per_second": 8.561, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.027044059708714485, |
| "learning_rate": 5e-05, |
| "loss": 0.0213, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9472, |
| "eval_loss": 0.22696438431739807, |
| "eval_runtime": 7.7179, |
| "eval_samples_per_second": 485.884, |
| "eval_steps_per_second": 7.645, |
| "step": 1332 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 2997, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9, |
| "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": 6.58965282490368e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
