metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: facebook/deit-base-patch16-224
datasets:
- medmnist-v2
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: pneumoniamnist-deit-base-finetuned
results: []
pneumoniamnist-deit-base-finetuned
This model is a fine-tuned version of facebook/deit-base-patch16-224 on the medmnist-v2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3440
- Accuracy: 0.8622
- Precision: 0.8623
- Recall: 0.8402
- F1: 0.8487
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 |
|---|---|---|---|---|---|---|---|
| 0.6158 | 0.9898 | 73 | 0.5674 | 0.7424 | 0.3712 | 0.5 | 0.4261 |
| 0.5322 | 1.9932 | 147 | 0.4840 | 0.7729 | 0.8829 | 0.5593 | 0.5396 |
| 0.4139 | 2.9966 | 221 | 0.3727 | 0.7939 | 0.8913 | 0.6 | 0.6057 |
| 0.3979 | 4.0 | 295 | 0.5270 | 0.7309 | 0.7405 | 0.8139 | 0.7168 |
| 0.3858 | 4.9898 | 368 | 0.3062 | 0.8531 | 0.8073 | 0.8623 | 0.8253 |
| 0.3704 | 5.9932 | 442 | 0.3774 | 0.8263 | 0.7939 | 0.8734 | 0.8056 |
| 0.3345 | 6.9966 | 516 | 0.2403 | 0.9027 | 0.8691 | 0.8812 | 0.8749 |
| 0.3875 | 8.0 | 590 | 0.3021 | 0.8817 | 0.8389 | 0.8985 | 0.8590 |
| 0.3673 | 8.9898 | 663 | 0.2865 | 0.8969 | 0.8557 | 0.9064 | 0.8749 |
| 0.3493 | 9.8983 | 730 | 0.3024 | 0.8740 | 0.8314 | 0.8958 | 0.8515 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1