assist_vc
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: 0.9840
- Accuracy: 0.6842
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: 1
- eval_batch_size: 1
- 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: 160
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7497 | 0.1 | 16 | 1.6563 | 0.1316 |
| 1.7873 | 1.1 | 32 | 1.3495 | 0.6842 |
| 0.7577 | 2.1 | 48 | 1.5793 | 0.5526 |
| 1.6926 | 3.1 | 64 | 1.7424 | 0.5526 |
| 1.9555 | 4.1 | 80 | 1.3199 | 0.5263 |
| 1.3076 | 5.1 | 96 | 1.5087 | 0.6842 |
| 2.4857 | 6.1 | 112 | 1.3040 | 0.6842 |
| 0.8124 | 7.1 | 128 | 1.0371 | 0.6842 |
| 2.0312 | 8.1 | 144 | 1.0630 | 0.6842 |
| 1.1519 | 9.1 | 160 | 0.9840 | 0.6842 |
Framework versions
- Transformers 4.27.4
- Pytorch 2.0.0
- Datasets 2.11.0
- Tokenizers 0.13.2