| { |
| "best_metric": 0.9421333333333334, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0552/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": 2.1753690242767334, |
| "learning_rate": 5e-05, |
| "loss": 0.8407, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9378666666666666, |
| "eval_loss": 0.22692343592643738, |
| "eval_runtime": 11.2313, |
| "eval_samples_per_second": 333.888, |
| "eval_steps_per_second": 5.253, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 0.17171572148799896, |
| "learning_rate": 5e-05, |
| "loss": 0.1396, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9389333333333333, |
| "eval_loss": 0.20891885459423065, |
| "eval_runtime": 11.2403, |
| "eval_samples_per_second": 333.62, |
| "eval_steps_per_second": 5.249, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.41563138365745544, |
| "learning_rate": 5e-05, |
| "loss": 0.0703, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9386666666666666, |
| "eval_loss": 0.22785358130931854, |
| "eval_runtime": 11.7415, |
| "eval_samples_per_second": 319.381, |
| "eval_steps_per_second": 5.025, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.042777832597494125, |
| "learning_rate": 5e-05, |
| "loss": 0.0447, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9410666666666667, |
| "eval_loss": 0.23232205212116241, |
| "eval_runtime": 11.9398, |
| "eval_samples_per_second": 314.075, |
| "eval_steps_per_second": 4.941, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 23.954402923583984, |
| "learning_rate": 5e-05, |
| "loss": 0.0267, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9421333333333334, |
| "eval_loss": 0.23293082416057587, |
| "eval_runtime": 11.3787, |
| "eval_samples_per_second": 329.563, |
| "eval_steps_per_second": 5.185, |
| "step": 1665 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 1998, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 6, |
| "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 |
| } |
|
|
