videomae-base-finetuned-ucf101
This model is a fine-tuned version of MCG-NJU/videomae-base on UCF101 dataset. It achieves the following results on the evaluation set:
- Loss: 1.1001
- Accuracy: 0.8054
Model description
transformers.VideoMAEForVideoClassification
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: 19780
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0704 | 0.2 | 3956 | 1.7583 | 0.5346 |
| 0.1936 | 1.2 | 7912 | 1.0780 | 0.7189 |
| 0.1014 | 2.2 | 11868 | 1.1839 | 0.7416 |
| 0.0049 | 3.2 | 15824 | 1.0054 | 0.7901 |
| 0.0012 | 4.2 | 19780 | 0.9529 | 0.8205 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3