videomae-large-cctv-brawl_extended_v1
This model is a fine-tuned version of MCG-NJU/videomae-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4430
- Accuracy: 0.8252
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: 3e-07
- 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: 12565
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4193 | 0.2 | 2514 | 0.4839 | 0.6985 |
| 0.3542 | 1.2 | 5028 | 0.4445 | 0.7593 |
| 0.2673 | 2.2 | 7542 | 0.4344 | 0.7993 |
| 0.3185 | 3.2 | 10056 | 0.4328 | 0.8201 |
| 0.4006 | 4.2 | 12565 | 0.4430 | 0.8252 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
- Downloads last month
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for onarganogun/videomae-large-cctv-brawl_extended_v1
Base model
MCG-NJU/videomae-large