metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-ucf101-subset
results: []
datasets:
- marekk/soccer_goal
pipeline_tag: video-classification
Video soccer goal detection
This model is a fine-tuned version of MCG-NJU/videomae-base. It achieves the following results on the evaluation set:
- Loss: 0.2953
- Accuracy: 0.95
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: 5
- eval_batch_size: 5
- 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: 119
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6605 | 0.15 | 18 | 0.5738 | 0.7 |
| 0.4013 | 1.15 | 36 | 0.7192 | 0.65 |
| 0.6608 | 2.15 | 54 | 0.5641 | 0.85 |
| 0.1641 | 3.15 | 72 | 0.4144 | 0.85 |
| 0.2899 | 4.15 | 90 | 0.9020 | 0.7 |
| 0.2204 | 5.15 | 108 | 0.2915 | 0.95 |
| 0.1141 | 6.09 | 119 | 0.2953 | 0.95 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1