metadata
base_model: Tommidi/st_vit_untrained
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: st_vit_trained-8epoch-ucf101-subset
results: []
st_vit_trained-8epoch-ucf101-subset
This model is a fine-tuned version of Tommidi/st_vit_untrained on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0648
- Accuracy: 0.9733
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: 296
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6314 | 0.13 | 38 | 0.1264 | 0.9333 |
| 0.3547 | 1.13 | 76 | 0.0077 | 1.0 |
| 0.0189 | 2.13 | 114 | 0.5103 | 0.9333 |
| 0.0611 | 3.13 | 152 | 0.1508 | 0.9333 |
| 0.0027 | 4.13 | 190 | 0.0018 | 1.0 |
| 0.0812 | 5.13 | 228 | 0.0943 | 0.9333 |
| 0.0005 | 6.13 | 266 | 0.0635 | 0.9667 |
| 0.3035 | 7.1 | 296 | 0.0530 | 0.9667 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1