metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/swin-large-patch4-window7-224-in22k
datasets:
- medmnist-v2
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: breastmnist-swin-base-finetuned
results: []
breastmnist-swin-base-finetuned
This model is a fine-tuned version of microsoft/swin-large-patch4-window7-224-in22k on the medmnist-v2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3595
- Accuracy: 0.8526
- Precision: 0.8162
- Recall: 0.8014
- F1: 0.8082
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 | 0.5069 | 0.7436 | 0.8701 | 0.5238 | 0.4708 |
| 0.6976 | 1.9429 | 17 | 0.4591 | 0.8590 | 0.8190 | 0.8283 | 0.8234 |
| 0.5351 | 2.9714 | 26 | 0.3745 | 0.8846 | 0.8667 | 0.8308 | 0.8462 |
| 0.4998 | 4.0 | 35 | 0.3243 | 0.8974 | 0.8697 | 0.8697 | 0.8697 |
| 0.4569 | 4.9143 | 43 | 0.4070 | 0.8590 | 0.8306 | 0.7982 | 0.8120 |
| 0.4182 | 5.9429 | 52 | 0.3801 | 0.8718 | 0.8439 | 0.8221 | 0.8319 |
| 0.4432 | 6.9714 | 61 | 0.3071 | 0.8718 | 0.8371 | 0.8371 | 0.8371 |
| 0.3988 | 8.0 | 70 | 0.3205 | 0.8718 | 0.8332 | 0.8521 | 0.8417 |
| 0.3988 | 8.9143 | 78 | 0.3239 | 0.8846 | 0.8506 | 0.8609 | 0.8555 |
| 0.3993 | 9.1429 | 80 | 0.3214 | 0.8846 | 0.8506 | 0.8609 | 0.8555 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1