metadata
license: apache-2.0
base_model: facebook/convnextv2-large-1k-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: >-
convnextv2-large-1k-224-finetuned-Lesion-Classification-HAM10000-AH-60-20-20-Shuffled
results: []
convnextv2-large-1k-224-finetuned-Lesion-Classification-HAM10000-AH-60-20-20-Shuffled
This model is a fine-tuned version of facebook/convnextv2-large-1k-224 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0946
- Accuracy: 0.9852
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- 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: 0.9
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.9014 | 1.0 | 114 | 1.8872 | 0.3982 |
| 1.6303 | 2.0 | 229 | 1.6163 | 0.5928 |
| 1.291 | 3.0 | 343 | 1.2220 | 0.6773 |
| 1.0813 | 4.0 | 458 | 0.9574 | 0.7750 |
| 0.7168 | 5.0 | 572 | 0.7792 | 0.7603 |
| 0.6184 | 6.0 | 687 | 0.5539 | 0.8678 |
| 0.677 | 7.0 | 801 | 0.4482 | 0.8727 |
| 0.4876 | 8.0 | 916 | 0.3289 | 0.9269 |
| 0.4 | 9.0 | 1030 | 0.2379 | 0.9499 |
| 0.4122 | 10.0 | 1145 | 0.2452 | 0.9351 |
| 0.4494 | 11.0 | 1259 | 0.1790 | 0.9581 |
| 0.2026 | 11.95 | 1368 | 0.0946 | 0.9852 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3