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: breastmnist-vit-base-finetuned
results: []
breastmnist-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: 0.3129
- Accuracy: 0.8782
- Precision: 0.8971
- Recall: 0.7888
- F1: 0.8232
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 |
|---|---|---|---|---|---|---|---|
| No log | 0.9143 | 8 | 0.4751 | 0.7821 | 0.8851 | 0.5952 | 0.5951 |
| 0.5516 | 1.9429 | 17 | 0.4166 | 0.8462 | 0.8091 | 0.7895 | 0.7983 |
| 0.478 | 2.9714 | 26 | 0.3676 | 0.8205 | 0.7792 | 0.7419 | 0.7565 |
| 0.4617 | 4.0 | 35 | 0.3180 | 0.8718 | 0.8698 | 0.7920 | 0.8194 |
| 0.4208 | 4.9143 | 43 | 0.4562 | 0.8590 | 0.8173 | 0.8584 | 0.8325 |
| 0.3759 | 5.9429 | 52 | 0.3780 | 0.8718 | 0.8332 | 0.8521 | 0.8417 |
| 0.3689 | 6.9714 | 61 | 0.2993 | 0.8846 | 0.9018 | 0.8008 | 0.8342 |
| 0.3322 | 8.0 | 70 | 0.2785 | 0.8718 | 0.8698 | 0.7920 | 0.8194 |
| 0.3322 | 8.9143 | 78 | 0.2700 | 0.8846 | 0.9018 | 0.8008 | 0.8342 |
| 0.3242 | 9.1429 | 80 | 0.2690 | 0.8846 | 0.9018 | 0.8008 | 0.8342 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1