Videomae Base Finetuned Ucf101 Subset

--- license: cc-by-nc-4.0 base_model: MCG-NJU/videomae-base tags: - generated_from_trainer metrics: - accuracy model-index: - name: videomae-base-finetuned-ucf101-subset 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-base-finetuned-ucf101-subset This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on the UCF101 dataset (action classification). It achieves the following results on the evaluation set: - Loss: 0.2789 - Accuracy: 0.9161 ## 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 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - training_steps: 600 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 1.3234 | 0.25 | 150 | 1.1605 | 0.6143 | | 1.0245 | 1.25 | 300 | 0.7764 | 0.6714 | | 0.1441 | 2.25 | 450 | 0.4293 | 0.8571 | | 0.4346 | 3.25 | 600 | 0.2247 | 0.9 | ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

Source context: 7 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo thenam/videomae-base-finetuned-ucf101-subset