| { | |
| "best_metric": 0.9445333333333333, | |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0778/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": 2.167065382003784, | |
| "learning_rate": 7e-05, | |
| "loss": 0.6766, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.94, | |
| "eval_loss": 0.2178322970867157, | |
| "eval_runtime": 13.4447, | |
| "eval_samples_per_second": 278.919, | |
| "eval_steps_per_second": 4.388, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.07638483494520187, | |
| "learning_rate": 7e-05, | |
| "loss": 0.111, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9357333333333333, | |
| "eval_loss": 0.21402695775032043, | |
| "eval_runtime": 12.1717, | |
| "eval_samples_per_second": 308.093, | |
| "eval_steps_per_second": 4.847, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.024564623832702637, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0502, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9389333333333333, | |
| "eval_loss": 0.21673454344272614, | |
| "eval_runtime": 12.043, | |
| "eval_samples_per_second": 311.383, | |
| "eval_steps_per_second": 4.899, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.03297504037618637, | |
| "learning_rate": 7e-05, | |
| "loss": 0.027, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9445333333333333, | |
| "eval_loss": 0.23076298832893372, | |
| "eval_runtime": 12.4339, | |
| "eval_samples_per_second": 301.594, | |
| "eval_steps_per_second": 4.745, | |
| "step": 1332 | |
| } | |
| ], | |
| "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": 6.58965282490368e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |