metadata
license: cc-by-nc-4.0
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: 0.6198
- Accuracy: 0.7886
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: 3650
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1996 | 0.1 | 365 | 2.4460 | 0.5567 |
| 1.4174 | 1.1 | 730 | 0.6252 | 0.8041 |
| 0.0092 | 2.1 | 1095 | 1.2255 | 0.7629 |
| 0.765 | 3.1 | 1460 | 0.9238 | 0.7732 |
| 0.1714 | 4.1 | 1825 | 1.0449 | 0.7938 |
| 0.09 | 5.1 | 2190 | 1.4747 | 0.7629 |
| 0.0006 | 6.1 | 2555 | 1.3157 | 0.7835 |
| 0.0004 | 7.1 | 2920 | 1.6183 | 0.7216 |
| 0.0012 | 8.1 | 3285 | 1.5373 | 0.7732 |
| 0.0005 | 9.1 | 3650 | 1.6775 | 0.7629 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2