metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/beit-base-patch16-224-pt22k-ft22k
datasets:
- medmnist-v2
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: pneumoniamnist-beit-base-finetuned
results: []
pneumoniamnist-beit-base-finetuned
This model is a fine-tuned version of microsoft/beit-base-patch16-224-pt22k-ft22k on the medmnist-v2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3960
- Accuracy: 0.8446
- Precision: 0.8354
- Recall: 0.8312
- F1: 0.8332
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 |
|---|---|---|---|---|---|---|---|
| 0.5947 | 0.9898 | 73 | 0.5165 | 0.7424 | 0.3712 | 0.5 | 0.4261 |
| 0.4888 | 1.9932 | 147 | 0.3450 | 0.8569 | 0.8116 | 0.8190 | 0.8151 |
| 0.4022 | 2.9966 | 221 | 0.4225 | 0.8340 | 0.7914 | 0.8567 | 0.8079 |
| 0.4319 | 4.0 | 295 | 0.3600 | 0.8588 | 0.8123 | 0.8589 | 0.8292 |
| 0.3836 | 4.9898 | 368 | 0.3665 | 0.8511 | 0.8054 | 0.8610 | 0.8233 |
| 0.3887 | 5.9932 | 442 | 0.3667 | 0.8645 | 0.8197 | 0.8749 | 0.8383 |
| 0.3947 | 6.9966 | 516 | 0.3951 | 0.8531 | 0.8098 | 0.8744 | 0.8283 |
| 0.3741 | 8.0 | 590 | 0.3449 | 0.8683 | 0.8229 | 0.8678 | 0.8398 |
| 0.3964 | 8.9898 | 663 | 0.3625 | 0.8588 | 0.8128 | 0.8638 | 0.8305 |
| 0.3845 | 9.8983 | 730 | 0.3569 | 0.8569 | 0.8111 | 0.8649 | 0.8292 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1