metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- vision
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: beans_outputs
results: []
beans_outputs
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the /home/ubuntu/sdb/astitva/segmentation/classification_ds dataset. It achieves the following results on the evaluation set:
- Loss: 0.8746
- Accuracy: 0.9515
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1775 | 1.0 | 336 | 2.1821 | 0.7616 |
| 1.4653 | 2.0 | 672 | 1.4698 | 0.8840 |
| 1.1052 | 3.0 | 1008 | 1.0802 | 0.9304 |
| 1.0055 | 4.0 | 1344 | 0.9248 | 0.9494 |
| 0.7847 | 5.0 | 1680 | 0.8746 | 0.9515 |
Framework versions
- Transformers 4.50.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0