human-actions-vit-model-francomedin
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 8.2276
- Accuracy: 0.0631
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: 0.0002
- 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
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.3325 | 0.32 | 500 | 4.2477 | 0.0298 |
0.9863 | 0.63 | 1000 | 3.6803 | 0.1269 |
0.8753 | 0.95 | 1500 | 4.7335 | 0.0443 |
0.5808 | 1.27 | 2000 | 5.3964 | 0.0752 |
0.5256 | 1.59 | 2500 | 5.2087 | 0.1059 |
0.5277 | 1.9 | 3000 | 5.7696 | 0.0783 |
0.326 | 2.22 | 3500 | 6.5902 | 0.0348 |
0.2548 | 2.54 | 4000 | 6.4781 | 0.0961 |
0.2708 | 2.86 | 4500 | 6.2750 | 0.0933 |
0.1677 | 3.17 | 5000 | 7.2354 | 0.0763 |
0.0796 | 3.49 | 5500 | 7.6928 | 0.0633 |
0.0904 | 3.81 | 6000 | 7.5144 | 0.0607 |
0.0561 | 4.13 | 6500 | 7.9617 | 0.0665 |
0.0205 | 4.44 | 7000 | 7.9271 | 0.0681 |
0.0204 | 4.76 | 7500 | 8.2276 | 0.0631 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 3
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.