|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: facebook/convnext-tiny-224 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: convnext-tiny-224-finetuned-papsmear |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: imagefolder |
|
type: imagefolder |
|
config: default |
|
split: train |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.8897058823529411 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# convnext-tiny-224-finetuned-papsmear |
|
|
|
This model is a fine-tuned version of [facebook/convnext-tiny-224](https://huggingface.co/facebook/convnext-tiny-224) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2836 |
|
- Accuracy: 0.8897 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 50 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:| |
|
| No log | 0.9231 | 9 | 1.7808 | 0.1691 | |
|
| 1.8057 | 1.9487 | 19 | 1.6808 | 0.3309 | |
|
| 1.7394 | 2.9744 | 29 | 1.5825 | 0.3382 | |
|
| 1.6408 | 4.0 | 39 | 1.4576 | 0.375 | |
|
| 1.5428 | 4.9231 | 48 | 1.3281 | 0.5221 | |
|
| 1.3931 | 5.9487 | 58 | 1.2044 | 0.5588 | |
|
| 1.2669 | 6.9744 | 68 | 1.0756 | 0.6103 | |
|
| 1.1355 | 8.0 | 78 | 0.9845 | 0.6324 | |
|
| 1.0379 | 8.9231 | 87 | 0.9260 | 0.6618 | |
|
| 0.9571 | 9.9487 | 97 | 0.8539 | 0.6618 | |
|
| 0.8376 | 10.9744 | 107 | 0.7998 | 0.7279 | |
|
| 0.7942 | 12.0 | 117 | 0.7573 | 0.75 | |
|
| 0.7095 | 12.9231 | 126 | 0.7005 | 0.7426 | |
|
| 0.7022 | 13.9487 | 136 | 0.6834 | 0.7868 | |
|
| 0.6504 | 14.9744 | 146 | 0.6552 | 0.7721 | |
|
| 0.589 | 16.0 | 156 | 0.6192 | 0.8015 | |
|
| 0.5679 | 16.9231 | 165 | 0.5738 | 0.8088 | |
|
| 0.5236 | 17.9487 | 175 | 0.5617 | 0.8015 | |
|
| 0.5244 | 18.9744 | 185 | 0.5073 | 0.8235 | |
|
| 0.4781 | 20.0 | 195 | 0.5112 | 0.8162 | |
|
| 0.453 | 20.9231 | 204 | 0.4650 | 0.8235 | |
|
| 0.4544 | 21.9487 | 214 | 0.4591 | 0.8456 | |
|
| 0.419 | 22.9744 | 224 | 0.4403 | 0.8309 | |
|
| 0.4146 | 24.0 | 234 | 0.4292 | 0.8382 | |
|
| 0.398 | 24.9231 | 243 | 0.4315 | 0.8382 | |
|
| 0.3918 | 25.9487 | 253 | 0.3980 | 0.8676 | |
|
| 0.361 | 26.9744 | 263 | 0.3758 | 0.8603 | |
|
| 0.3355 | 28.0 | 273 | 0.3657 | 0.8603 | |
|
| 0.3483 | 28.9231 | 282 | 0.3669 | 0.875 | |
|
| 0.3171 | 29.9487 | 292 | 0.3492 | 0.8603 | |
|
| 0.3249 | 30.9744 | 302 | 0.3400 | 0.875 | |
|
| 0.3087 | 32.0 | 312 | 0.3251 | 0.875 | |
|
| 0.3029 | 32.9231 | 321 | 0.3167 | 0.8824 | |
|
| 0.3018 | 33.9487 | 331 | 0.3192 | 0.875 | |
|
| 0.2823 | 34.9744 | 341 | 0.3066 | 0.875 | |
|
| 0.2744 | 36.0 | 351 | 0.3003 | 0.875 | |
|
| 0.258 | 36.9231 | 360 | 0.2964 | 0.875 | |
|
| 0.2714 | 37.9487 | 370 | 0.3039 | 0.875 | |
|
| 0.2486 | 38.9744 | 380 | 0.2937 | 0.875 | |
|
| 0.2511 | 40.0 | 390 | 0.2739 | 0.8824 | |
|
| 0.2511 | 40.9231 | 399 | 0.2836 | 0.8897 | |
|
| 0.2659 | 41.9487 | 409 | 0.2804 | 0.875 | |
|
| 0.2379 | 42.9744 | 419 | 0.2747 | 0.8824 | |
|
| 0.2279 | 44.0 | 429 | 0.2726 | 0.8897 | |
|
| 0.2153 | 44.9231 | 438 | 0.2732 | 0.8897 | |
|
| 0.2461 | 45.9487 | 448 | 0.2738 | 0.8897 | |
|
| 0.2482 | 46.1538 | 450 | 0.2738 | 0.8897 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.19.1 |
|
|
