VideoMAE Default Fold 1 10 Epoch Bdslw60 Kinetics 25 2 25

--- library_name: transformers license: cc-by-nc-4.0 base_model: MCG-NJU/videomae-base-finetuned-kinetics tags: - generated_from_trainer metrics: - accuracy model-index: - name: VideoMAE_default_fold__1__10_epoch_bdslw60_kinetics_25_2_25 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # VideoMAE_default_fold__1__10_epoch_bdslw60_kinetics_25_2_25 This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2868 - Accuracy: 0.9381 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - training_steps: 9030 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:------:|:----:|:---------------:|:--------:| | 1.258 | 0.1 | 903 | 0.4285 | 0.9066 | | 0.111 | 1.1001 | 1807 | 0.0347 | 0.9913 | | 0.0296 | 2.1 | 2710 | 0.0304 | 0.9938 | | 0.046 | 3.1001 | 3614 | 0.0293 | 0.9938 | | 0.0897 | 4.1 | 4517 | 0.0561 | 0.9851 | | 0.0292 | 5.1001 | 5421 | 0.0268 | 0.9925 | | 0.0333 | 6.1 | 6324 | 0.0267 | 0.9950 | | 0.0002 | 7.1001 | 7228 | 0.0225 | 0.9975 | | 0.0004 | 8.1 | 8131 | 0.0210 | 0.9950 | | 0.0002 | 9.0995 | 9030 | 0.0185 | 0.9975 | ### Framework versions - Transformers 4.46.1 - Pytorch 2.5.1+cu124 - Datasets 3.1.0 - Tokenizers 0.20.1

Source context: 3 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/VideoMAE_default_fold__1__10_epoch_bdslw60_kinetics_25_2_25