| { |
| "best_metric": 0.9354666666666667, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_dino-vitb16/model_idx_0964/checkpoints/checkpoint-1998", |
| "epoch": 6.0, |
| "eval_steps": 500, |
| "global_step": 1998, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 1.0, |
| "grad_norm": 28.724163055419922, |
| "learning_rate": 2.8002157758785897e-05, |
| "loss": 0.7539, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.8866666666666667, |
| "eval_loss": 0.3536032736301422, |
| "eval_runtime": 7.1568, |
| "eval_samples_per_second": 523.974, |
| "eval_steps_per_second": 8.244, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 1.540662407875061, |
| "learning_rate": 2.2520416388814085e-05, |
| "loss": 0.1838, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9101333333333333, |
| "eval_loss": 0.2967321276664734, |
| "eval_runtime": 6.8922, |
| "eval_samples_per_second": 544.092, |
| "eval_steps_per_second": 8.56, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 0.6368748545646667, |
| "learning_rate": 1.5023585520713769e-05, |
| "loss": 0.0823, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.924, |
| "eval_loss": 0.24556097388267517, |
| "eval_runtime": 6.6565, |
| "eval_samples_per_second": 563.358, |
| "eval_steps_per_second": 8.864, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.07834707945585251, |
| "learning_rate": 7.520434931385125e-06, |
| "loss": 0.0319, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9325333333333333, |
| "eval_loss": 0.2353752702474594, |
| "eval_runtime": 6.7292, |
| "eval_samples_per_second": 557.276, |
| "eval_steps_per_second": 8.768, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 2.9592020511627197, |
| "learning_rate": 2.0214277619278764e-06, |
| "loss": 0.0126, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9338666666666666, |
| "eval_loss": 0.23717738687992096, |
| "eval_runtime": 6.741, |
| "eval_samples_per_second": 556.301, |
| "eval_steps_per_second": 8.752, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.0016534790629521012, |
| "learning_rate": 1.8542571038615563e-11, |
| "loss": 0.0049, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9354666666666667, |
| "eval_loss": 0.21770143508911133, |
| "eval_runtime": 6.6842, |
| "eval_samples_per_second": 561.025, |
| "eval_steps_per_second": 8.827, |
| "step": 1998 |
| } |
| ], |
| "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": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 9.88447923735552e+18, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
