metadata
license: apache-2.0
base_model: microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: >-
swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-Lesion-Classification-HAM10000-S
results: []
swinv2-large-patch4-window12to16-192to256-22kto1k-ft-finetuned-Lesion-Classification-HAM10000-S
This model is a fine-tuned version of microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0069
- Accuracy: 0.9975
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.5
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2378 | 1.0 | 114 | 0.9976 | 0.5936 |
| 0.7272 | 2.0 | 228 | 0.4749 | 0.8309 |
| 0.4335 | 2.99 | 342 | 0.2488 | 0.9195 |
| 0.3298 | 4.0 | 457 | 0.1700 | 0.9310 |
| 0.177 | 5.0 | 571 | 0.2116 | 0.9261 |
| 0.2299 | 6.0 | 685 | 0.0933 | 0.9754 |
| 0.2586 | 6.99 | 799 | 0.0316 | 0.9869 |
| 0.1053 | 8.0 | 914 | 0.0256 | 0.9910 |
| 0.2159 | 9.0 | 1028 | 0.0147 | 0.9959 |
| 0.0607 | 9.98 | 1140 | 0.0069 | 0.9975 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3