videomae-base-finetuned-ucf101-subset
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5734
- Accuracy: 0.7806
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: 8
- eval_batch_size: 8
- 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: 148
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.075 | 0.2568 | 38 | 1.5955 | 0.6143 |
0.8194 | 1.2568 | 76 | 0.9900 | 0.6714 |
0.4766 | 2.2568 | 114 | 0.5473 | 0.8571 |
0.3123 | 3.2297 | 148 | 0.4684 | 0.8571 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 0
Model state unknown