<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
vit-base-patch32-224-in21k-finetuned-eurosat
This model is a fine-tuned version of google/vit-base-patch32-224-in21k on the food101 dataset. It achieves the following results on the evaluation set:
- Loss: 1.6175
- Accuracy: 0.7321
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.6483 | 1.0 | 532 | 2.5574 | 0.6605 |
| 1.8885 | 2.0 | 1064 | 1.8063 | 0.7182 |
| 1.6371 | 3.0 | 1596 | 1.6175 | 0.7321 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.1
- Tokenizers 0.13.2
