| { | |
| "best_metric": 0.9290666666666667, | |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0652/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": 2.214202880859375, | |
| "learning_rate": 7.507507507507507e-05, | |
| "loss": 0.8013, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8536, | |
| "eval_loss": 0.4903952181339264, | |
| "eval_runtime": 10.4663, | |
| "eval_samples_per_second": 358.292, | |
| "eval_steps_per_second": 5.637, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.9435473680496216, | |
| "learning_rate": 5.0075075075075074e-05, | |
| "loss": 0.2053, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8928, | |
| "eval_loss": 0.3682068884372711, | |
| "eval_runtime": 10.8198, | |
| "eval_samples_per_second": 346.588, | |
| "eval_steps_per_second": 5.453, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.08132018148899078, | |
| "learning_rate": 2.5075075075075076e-05, | |
| "loss": 0.0656, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9072, | |
| "eval_loss": 0.3103485703468323, | |
| "eval_runtime": 10.296, | |
| "eval_samples_per_second": 364.22, | |
| "eval_steps_per_second": 5.73, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.002394646406173706, | |
| "learning_rate": 7.507507507507508e-08, | |
| "loss": 0.0115, | |
| "step": 1332 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.9290666666666667, | |
| "eval_loss": 0.27040326595306396, | |
| "eval_runtime": 10.2274, | |
| "eval_samples_per_second": 366.66, | |
| "eval_steps_per_second": 5.769, | |
| "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 | |
| } | |