VIT_large_ieee
This model is a fine-tuned version of google/vit-large-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0230
- Accuracy: 0.9941
Model description
This model was used for IEEE ManSB VICTORIS 2.0 Final Competition
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: 1e-06
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0047 | 0.67 | 100 | 0.0283 | 0.9929 |
| 0.0165 | 1.34 | 200 | 0.0230 | 0.9941 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
- Downloads last month
- 5
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.
Model tree for DazMashaly/VIT_large_ieee
Base model
google/vit-large-patch16-224-in21k
Finetuned
this model