| { | |
| "best_metric": 0.4232, | |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0804/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": 24.534595489501953, | |
| "learning_rate": 0.0002259009009009009, | |
| "loss": 3.2875, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.2168, | |
| "eval_loss": 2.8620755672454834, | |
| "eval_runtime": 10.5807, | |
| "eval_samples_per_second": 354.42, | |
| "eval_steps_per_second": 5.576, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 42.18906784057617, | |
| "learning_rate": 0.0001509009009009009, | |
| "loss": 2.6313, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.3002666666666667, | |
| "eval_loss": 2.546834945678711, | |
| "eval_runtime": 10.2145, | |
| "eval_samples_per_second": 367.124, | |
| "eval_steps_per_second": 5.776, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 43.10956573486328, | |
| "learning_rate": 7.590090090090089e-05, | |
| "loss": 2.2595, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.36773333333333336, | |
| "eval_loss": 2.267939329147339, | |
| "eval_runtime": 10.3426, | |
| "eval_samples_per_second": 362.578, | |
| "eval_steps_per_second": 5.705, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 53.393375396728516, | |
| "learning_rate": 9.009009009009009e-07, | |
| "loss": 1.8709, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.4232, | |
| "eval_loss": 2.0597567558288574, | |
| "eval_runtime": 10.3931, | |
| "eval_samples_per_second": 360.815, | |
| "eval_steps_per_second": 5.677, | |
| "step": 1332 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1332, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.58965282490368e+18, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |