| { |
| "best_metric": 0.9618666666666666, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0649/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": 0.5684822201728821, |
| "learning_rate": 4.4444444444444447e-05, |
| "loss": 0.8069, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9488, |
| "eval_loss": 0.20731757581233978, |
| "eval_runtime": 13.7573, |
| "eval_samples_per_second": 272.582, |
| "eval_steps_per_second": 4.289, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.24929940700531006, |
| "learning_rate": 3.888888888888889e-05, |
| "loss": 0.0929, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9525333333333333, |
| "eval_loss": 0.172918438911438, |
| "eval_runtime": 12.453, |
| "eval_samples_per_second": 301.132, |
| "eval_steps_per_second": 4.738, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.06064837425947189, |
| "learning_rate": 3.3333333333333335e-05, |
| "loss": 0.0296, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9538666666666666, |
| "eval_loss": 0.17567475140094757, |
| "eval_runtime": 12.3966, |
| "eval_samples_per_second": 302.502, |
| "eval_steps_per_second": 4.759, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.7187159061431885, |
| "learning_rate": 2.777777777777778e-05, |
| "loss": 0.0119, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9573333333333334, |
| "eval_loss": 0.15571406483650208, |
| "eval_runtime": 12.0685, |
| "eval_samples_per_second": 310.725, |
| "eval_steps_per_second": 4.889, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.02083256095647812, |
| "learning_rate": 2.2222222222222223e-05, |
| "loss": 0.0037, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9605333333333334, |
| "eval_loss": 0.16351911425590515, |
| "eval_runtime": 12.8646, |
| "eval_samples_per_second": 291.497, |
| "eval_steps_per_second": 4.586, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 2.463406562805176, |
| "learning_rate": 1.6666666666666667e-05, |
| "loss": 0.0024, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9618666666666666, |
| "eval_loss": 0.1520133763551712, |
| "eval_runtime": 12.4243, |
| "eval_samples_per_second": 301.827, |
| "eval_steps_per_second": 4.749, |
| "step": 1998 |
| } |
| ], |
| "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": 9.88447923735552e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
