metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: google/vit-base-patch16-224-in21k
datasets:
- medmnist-v2
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: pneumoniamnist-vit-base-finetuned
results: []
pneumoniamnist-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: 0.1773
- Accuracy: 0.9359
- Precision: 0.9474
- Recall: 0.9179
- F1: 0.9295
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 |
|---|---|---|---|---|---|---|---|
| 0.2447 | 0.9898 | 73 | 0.1538 | 0.9351 | 0.9013 | 0.9466 | 0.9200 |
| 0.3466 | 1.9932 | 147 | 0.2451 | 0.9122 | 0.9197 | 0.8466 | 0.8750 |
| 0.2074 | 2.9966 | 221 | 0.1711 | 0.9427 | 0.9538 | 0.8961 | 0.9203 |
| 0.1928 | 4.0 | 295 | 0.1044 | 0.9618 | 0.9482 | 0.9525 | 0.9503 |
| 0.2043 | 4.9898 | 368 | 0.1007 | 0.9580 | 0.9491 | 0.9403 | 0.9446 |
| 0.1717 | 5.9932 | 442 | 0.0930 | 0.9618 | 0.9432 | 0.9598 | 0.9510 |
| 0.1498 | 6.9966 | 516 | 0.0845 | 0.9637 | 0.9448 | 0.9635 | 0.9536 |
| 0.1531 | 8.0 | 590 | 0.1661 | 0.9332 | 0.8974 | 0.9526 | 0.9188 |
| 0.1451 | 8.9898 | 663 | 0.0760 | 0.9637 | 0.9464 | 0.9611 | 0.9534 |
| 0.1263 | 9.8983 | 730 | 0.0824 | 0.9580 | 0.9355 | 0.9596 | 0.9466 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1