| { |
| "best_metric": 0.9445333333333333, |
| "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/google_vit-base-patch16-224/model_idx_0485/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": 1.0169850587844849, |
| "learning_rate": 2.8002157758785897e-05, |
| "loss": 1.1643, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_accuracy": 0.9210666666666667, |
| "eval_loss": 0.3016650974750519, |
| "eval_runtime": 10.8702, |
| "eval_samples_per_second": 344.979, |
| "eval_steps_per_second": 5.428, |
| "step": 333 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 44.898460388183594, |
| "learning_rate": 2.2520416388814085e-05, |
| "loss": 0.1711, |
| "step": 666 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_accuracy": 0.9301333333333334, |
| "eval_loss": 0.22779260575771332, |
| "eval_runtime": 10.8249, |
| "eval_samples_per_second": 346.423, |
| "eval_steps_per_second": 5.45, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.1293007135391235, |
| "learning_rate": 1.5023585520713769e-05, |
| "loss": 0.067, |
| "step": 999 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_accuracy": 0.9344, |
| "eval_loss": 0.21653564274311066, |
| "eval_runtime": 10.6701, |
| "eval_samples_per_second": 351.45, |
| "eval_steps_per_second": 5.529, |
| "step": 999 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 0.252564936876297, |
| "learning_rate": 7.520434931385125e-06, |
| "loss": 0.0259, |
| "step": 1332 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_accuracy": 0.9402666666666667, |
| "eval_loss": 0.2195741832256317, |
| "eval_runtime": 11.4576, |
| "eval_samples_per_second": 327.294, |
| "eval_steps_per_second": 5.149, |
| "step": 1332 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.051233094185590744, |
| "learning_rate": 2.0214277619278764e-06, |
| "loss": 0.0138, |
| "step": 1665 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_accuracy": 0.9432, |
| "eval_loss": 0.20971323549747467, |
| "eval_runtime": 11.2418, |
| "eval_samples_per_second": 333.578, |
| "eval_steps_per_second": 5.248, |
| "step": 1665 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.05385765805840492, |
| "learning_rate": 1.8542571038615563e-11, |
| "loss": 0.01, |
| "step": 1998 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_accuracy": 0.9445333333333333, |
| "eval_loss": 0.20542864501476288, |
| "eval_runtime": 11.0007, |
| "eval_samples_per_second": 340.889, |
| "eval_steps_per_second": 5.363, |
| "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 |
| } |
|
|
