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: 1.0997
- Accuracy: 0.3088
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: 8
- eval_batch_size: 8
- 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: 44
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1263 | 0.2727 | 12 | 1.1123 | 0.3316 |
| 1.1717 | 1.2727 | 24 | 1.1180 | 0.2684 |
| 1.1171 | 2.2727 | 36 | 1.1237 | 0.3526 |
| 1.114 | 3.1818 | 44 | 1.1202 | 0.3816 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1
- Downloads last month
- 66
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for vyshsk/videomae-base-finetuned-ucf101-subset
Base model
MCG-NJU/videomae-base