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
results: []
videomae-base-finetuned-ucf101
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: 0.0721
- Accuracy: 0.9793
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: 6
- eval_batch_size: 6
- 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: 3328
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0148 | 0.25 | 833 | 1.1001 | 0.6825 |
| 0.2036 | 1.25 | 1666 | 0.4224 | 0.8734 |
| 0.1442 | 2.25 | 2499 | 0.1231 | 0.9660 |
| 0.073 | 3.25 | 3328 | 0.0721 | 0.9793 |
Framework versions
- Transformers 4.37.1
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.1