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: blood-beit-base-finetuned
results: []
blood-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: 0.0847
- Accuracy: 0.9737
- Precision: 0.9726
- Recall: 0.9724
- F1: 0.9724
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 |
|---|---|---|---|---|---|---|---|
| 0.4657 | 1.0 | 187 | 0.2452 | 0.9095 | 0.8964 | 0.9083 | 0.8973 |
| 0.4327 | 2.0 | 374 | 0.2111 | 0.9182 | 0.9299 | 0.8921 | 0.9007 |
| 0.3977 | 3.0 | 561 | 0.1743 | 0.9340 | 0.9229 | 0.9282 | 0.9244 |
| 0.3318 | 4.0 | 748 | 0.1776 | 0.9352 | 0.9248 | 0.9353 | 0.9285 |
| 0.3461 | 5.0 | 935 | 0.1703 | 0.9381 | 0.9311 | 0.9344 | 0.9305 |
| 0.3309 | 6.0 | 1122 | 0.1956 | 0.9369 | 0.9336 | 0.9397 | 0.9335 |
| 0.3088 | 7.0 | 1309 | 0.1179 | 0.9533 | 0.9427 | 0.9525 | 0.9461 |
| 0.2129 | 8.0 | 1496 | 0.0992 | 0.9638 | 0.9569 | 0.9674 | 0.9611 |
| 0.2049 | 9.0 | 1683 | 0.0847 | 0.9679 | 0.9627 | 0.9683 | 0.9651 |
| 0.2007 | 10.0 | 1870 | 0.0785 | 0.9708 | 0.9668 | 0.9737 | 0.9698 |
Framework versions
- PEFT 0.11.1
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1