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: 0.3143
- Accuracy: 0.8903
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: 32
- eval_batch_size: 32
- 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: 148
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.3172 | 0.07 | 10 | 2.2181 | 0.0857 |
| 2.1343 | 1.07 | 20 | 1.9744 | 0.3714 |
| 1.6727 | 2.07 | 30 | 1.4527 | 0.5143 |
| 0.9704 | 3.07 | 40 | 0.8461 | 0.8143 |
| 0.5427 | 4.07 | 50 | 0.5360 | 0.8143 |
| 0.3584 | 5.07 | 60 | 0.4727 | 0.8571 |
| 0.2445 | 6.07 | 70 | 0.3409 | 0.9 |
| 0.1351 | 7.07 | 80 | 0.3564 | 0.8429 |
| 0.1238 | 8.07 | 90 | 0.3715 | 0.8714 |
| 0.1064 | 9.07 | 100 | 0.3150 | 0.8714 |
| 0.0839 | 10.07 | 110 | 0.4099 | 0.8 |
| 0.0575 | 11.07 | 120 | 0.3029 | 0.9 |
| 0.0329 | 12.07 | 130 | 0.1801 | 0.9286 |
| 0.0348 | 13.07 | 140 | 0.1834 | 0.9429 |
| 0.0348 | 14.05 | 148 | 0.2132 | 0.9143 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.0.0
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 53
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 shenben/videomae-base-finetuned-ucf101-subset
Base model
MCG-NJU/videomae-base