| { |
| "best_metric": 0.9312, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0722/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": 0.7712041139602661, |
| "learning_rate": 3e-05, |
| "loss": 1.1912, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9149333333333334, |
| "eval_loss": 0.32942885160446167, |
| "eval_runtime": 13.8888, |
| "eval_samples_per_second": 270.002, |
| "eval_steps_per_second": 4.248, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.4238669872283936, |
| "learning_rate": 3e-05, |
| "loss": 0.199, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9248, |
| "eval_loss": 0.2652640640735626, |
| "eval_runtime": 12.7069, |
| "eval_samples_per_second": 295.115, |
| "eval_steps_per_second": 4.643, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.8074430227279663, |
| "learning_rate": 3e-05, |
| "loss": 0.0993, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9258666666666666, |
| "eval_loss": 0.2502594292163849, |
| "eval_runtime": 13.5766, |
| "eval_samples_per_second": 276.21, |
| "eval_steps_per_second": 4.346, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.9440605640411377, |
| "learning_rate": 3e-05, |
| "loss": 0.0534, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9266666666666666, |
| "eval_loss": 0.2529388666152954, |
| "eval_runtime": 13.0594, |
| "eval_samples_per_second": 287.149, |
| "eval_steps_per_second": 4.518, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 4.117969512939453, |
| "learning_rate": 3e-05, |
| "loss": 0.0288, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9312, |
| "eval_loss": 0.2654390037059784, |
| "eval_runtime": 13.5108, |
| "eval_samples_per_second": 277.556, |
| "eval_steps_per_second": 4.367, |
| "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 |
| } |
|
|
