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: 0.2061
- Accuracy: 0.9484
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: 4
- eval_batch_size: 4
- 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: 600
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9543 | 0.12 | 75 | 1.5145 | 0.6 |
| 0.7175 | 1.12 | 150 | 0.9735 | 0.6571 |
| 0.2914 | 2.12 | 225 | 0.4764 | 0.8 |
| 0.54 | 3.12 | 300 | 0.6036 | 0.8 |
| 0.1074 | 4.12 | 375 | 0.1995 | 0.9286 |
| 0.0087 | 5.12 | 450 | 0.1256 | 0.9714 |
| 0.0061 | 6.12 | 525 | 0.0466 | 0.9857 |
| 0.0082 | 7.12 | 600 | 0.0363 | 0.9857 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0