videomae-base-finetuned-ElderReact-Disgust11
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: 0.4435
- Accuracy: 0.84
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: 16
- eval_batch_size: 16
- 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: 380
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.5481 | 0.1 | 39 | 0.4982 | 0.8003 |
0.5849 | 1.1 | 78 | 0.5341 | 0.7877 |
0.4385 | 2.1 | 117 | 0.5429 | 0.7952 |
0.4998 | 3.1 | 156 | 0.5279 | 0.7977 |
0.4388 | 4.1 | 195 | 0.5301 | 0.7475 |
0.5161 | 5.1 | 234 | 0.5100 | 0.7952 |
0.3919 | 6.1 | 273 | 0.6200 | 0.6658 |
0.4039 | 7.1 | 312 | 0.6265 | 0.6847 |
0.4199 | 8.1 | 351 | 0.7621 | 0.5678 |
0.4675 | 9.08 | 380 | 0.5825 | 0.7023 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 4
Model state unknown