| { | |
| "best_metric": 0.9466666666666667, | |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0937/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": 7.628276824951172, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.6469, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.912, | |
| "eval_loss": 0.2972228527069092, | |
| "eval_runtime": 13.5005, | |
| "eval_samples_per_second": 277.767, | |
| "eval_steps_per_second": 4.37, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.8804655075073242, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.1481, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9205333333333333, | |
| "eval_loss": 0.2664359211921692, | |
| "eval_runtime": 13.4649, | |
| "eval_samples_per_second": 278.502, | |
| "eval_steps_per_second": 4.382, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.5662244558334351, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0604, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9336, | |
| "eval_loss": 0.2216847985982895, | |
| "eval_runtime": 13.4545, | |
| "eval_samples_per_second": 278.718, | |
| "eval_steps_per_second": 4.385, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.020562101155519485, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0168, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9466666666666667, | |
| "eval_loss": 0.1985892504453659, | |
| "eval_runtime": 13.3695, | |
| "eval_samples_per_second": 280.49, | |
| "eval_steps_per_second": 4.413, | |
| "step": 1332 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1665, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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 | |
| } | |