metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
datasets:
- medmnist-v2
metrics:
- accuracy
- precision
- recall
- f1
base_model: google/vit-base-patch16-224-in21k
model-index:
- name: organc-vit-base-finetuned
results: []
organc-vit-base-finetuned
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the medmnist-v2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2714
- Accuracy: 0.9141
- Precision: 0.9095
- Recall: 0.9007
- F1: 0.9042
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: 0.005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.6525 | 1.0 | 203 | 0.2025 | 0.9327 | 0.9260 | 0.9130 | 0.9091 |
| 0.765 | 2.0 | 406 | 0.2110 | 0.9377 | 0.9441 | 0.9289 | 0.9344 |
| 0.6514 | 3.0 | 609 | 0.2026 | 0.9490 | 0.9457 | 0.9442 | 0.9428 |
| 0.6405 | 4.0 | 813 | 0.2056 | 0.9289 | 0.9481 | 0.9175 | 0.9267 |
| 0.6514 | 5.0 | 1016 | 0.1362 | 0.9523 | 0.9459 | 0.9385 | 0.9382 |
| 0.5778 | 6.0 | 1219 | 0.0787 | 0.9770 | 0.9739 | 0.9746 | 0.9737 |
| 0.4759 | 7.0 | 1422 | 0.0959 | 0.9724 | 0.9744 | 0.9693 | 0.9714 |
| 0.482 | 8.0 | 1626 | 0.0743 | 0.9762 | 0.9737 | 0.9737 | 0.9733 |
| 0.3729 | 9.0 | 1829 | 0.0903 | 0.9758 | 0.9778 | 0.9754 | 0.9762 |
| 0.3705 | 9.99 | 2030 | 0.0732 | 0.9808 | 0.9830 | 0.9826 | 0.9825 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2