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: organamnist-beit-base-finetuned
results: []
organamnist-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: 0.2372
- Accuracy: 0.9329
- Precision: 0.9416
- Recall: 0.9296
- F1: 0.9340
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 |
|---|---|---|---|---|---|---|---|
| 0.6786 | 1.0 | 540 | 0.1776 | 0.9339 | 0.9507 | 0.9341 | 0.9385 |
| 0.7397 | 2.0 | 1081 | 0.1783 | 0.9407 | 0.9539 | 0.9346 | 0.9415 |
| 0.7151 | 3.0 | 1621 | 0.1297 | 0.9552 | 0.9611 | 0.9555 | 0.9572 |
| 0.4964 | 4.0 | 2162 | 0.0741 | 0.9735 | 0.9765 | 0.9702 | 0.9730 |
| 0.5509 | 5.0 | 2702 | 0.0671 | 0.9770 | 0.9776 | 0.9796 | 0.9783 |
| 0.5746 | 6.0 | 3243 | 0.0642 | 0.9754 | 0.9810 | 0.9788 | 0.9795 |
| 0.4066 | 7.0 | 3783 | 0.1196 | 0.9566 | 0.9693 | 0.9563 | 0.9614 |
| 0.4046 | 8.0 | 4324 | 0.0469 | 0.9798 | 0.9853 | 0.9821 | 0.9834 |
| 0.3314 | 9.0 | 4864 | 0.0388 | 0.9861 | 0.9892 | 0.9860 | 0.9874 |
| 0.2865 | 9.99 | 5400 | 0.0450 | 0.9831 | 0.9880 | 0.9862 | 0.9869 |
Framework versions
- PEFT 0.11.1
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2