metadata
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: []
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: 0.0910
- Accuracy: 0.9714
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: 300
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2166 | 0.13 | 38 | 1.9844 | 0.2429 |
| 1.1745 | 1.13 | 76 | 1.1520 | 0.5286 |
| 0.5065 | 2.13 | 114 | 0.6031 | 0.7857 |
| 0.2866 | 3.13 | 152 | 0.4902 | 0.7429 |
| 0.1438 | 4.13 | 190 | 0.3535 | 0.8429 |
| 0.0647 | 5.13 | 228 | 0.1642 | 0.9429 |
| 0.0417 | 6.13 | 266 | 0.0806 | 0.9857 |
| 0.0442 | 7.11 | 300 | 0.0910 | 0.9714 |
Framework versions
- Transformers 4.33.1
- Pytorch 1.12.1+cu116
- Datasets 2.14.5
- Tokenizers 0.13.3