|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: microsoft/resnet-18 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: font-identifier |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: imagefolder |
|
type: imagefolder |
|
config: default |
|
split: test |
|
args: default |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 1.0 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# font-identifier |
|
|
|
This model is a fine-tuned version of [microsoft/resnet-18](https://huggingface.co/microsoft/resnet-18) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0010 |
|
- Accuracy: 1.0 |
|
|
|
## 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: 4 |
|
- total_train_batch_size: 64 |
|
- 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 | |
|
|:-------------:|:-------:|:----:|:---------------:|:--------:| |
|
| 3.2404 | 0.9524 | 15 | 3.1135 | 0.06 | |
|
| 2.7846 | 1.9683 | 31 | 2.4576 | 0.33 | |
|
| 2.3956 | 2.9841 | 47 | 1.7152 | 0.58 | |
|
| 1.6171 | 4.0 | 63 | 1.0931 | 0.775 | |
|
| 1.2882 | 4.9524 | 78 | 0.6347 | 0.85 | |
|
| 0.7191 | 5.9683 | 94 | 0.3957 | 0.94 | |
|
| 0.5196 | 6.9841 | 110 | 0.2080 | 0.965 | |
|
| 0.3999 | 8.0 | 126 | 0.1480 | 0.965 | |
|
| 0.2476 | 8.9524 | 141 | 0.0934 | 0.985 | |
|
| 0.2176 | 9.9683 | 157 | 0.0768 | 0.99 | |
|
| 0.194 | 10.9841 | 173 | 0.0365 | 0.995 | |
|
| 0.1572 | 12.0 | 189 | 0.0616 | 0.985 | |
|
| 0.1381 | 12.9524 | 204 | 0.0640 | 0.985 | |
|
| 0.1291 | 13.9683 | 220 | 0.0522 | 0.985 | |
|
| 0.094 | 14.9841 | 236 | 0.0442 | 0.99 | |
|
| 0.1037 | 16.0 | 252 | 0.0492 | 0.99 | |
|
| 0.1067 | 16.9524 | 267 | 0.0629 | 0.985 | |
|
| 0.0912 | 17.9683 | 283 | 0.0486 | 0.985 | |
|
| 0.0702 | 18.9841 | 299 | 0.0344 | 0.99 | |
|
| 0.0677 | 20.0 | 315 | 0.0242 | 0.995 | |
|
| 0.0566 | 20.9524 | 330 | 0.0295 | 0.99 | |
|
| 0.0742 | 21.9683 | 346 | 0.0300 | 0.99 | |
|
| 0.0675 | 22.9841 | 362 | 0.0159 | 1.0 | |
|
| 0.0501 | 24.0 | 378 | 0.0105 | 0.995 | |
|
| 0.0651 | 24.9524 | 393 | 0.0362 | 0.995 | |
|
| 0.0665 | 25.9683 | 409 | 0.0335 | 0.985 | |
|
| 0.0533 | 26.9841 | 425 | 0.0369 | 0.99 | |
|
| 0.0487 | 28.0 | 441 | 0.0296 | 0.99 | |
|
| 0.0384 | 28.9524 | 456 | 0.0177 | 0.995 | |
|
| 0.038 | 29.9683 | 472 | 0.0176 | 0.995 | |
|
| 0.0342 | 30.9841 | 488 | 0.0165 | 0.995 | |
|
| 0.055 | 32.0 | 504 | 0.0199 | 0.995 | |
|
| 0.0418 | 32.9524 | 519 | 0.0022 | 1.0 | |
|
| 0.0447 | 33.9683 | 535 | 0.0071 | 0.995 | |
|
| 0.0436 | 34.9841 | 551 | 0.0587 | 0.98 | |
|
| 0.0307 | 36.0 | 567 | 0.0244 | 0.995 | |
|
| 0.0413 | 36.9524 | 582 | 0.0227 | 0.99 | |
|
| 0.0351 | 37.9683 | 598 | 0.0323 | 0.99 | |
|
| 0.0267 | 38.9841 | 614 | 0.0510 | 0.985 | |
|
| 0.0259 | 40.0 | 630 | 0.0009 | 1.0 | |
|
| 0.0245 | 40.9524 | 645 | 0.0017 | 1.0 | |
|
| 0.0227 | 41.9683 | 661 | 0.0208 | 0.995 | |
|
| 0.0458 | 42.9841 | 677 | 0.0445 | 0.99 | |
|
| 0.0263 | 44.0 | 693 | 0.0339 | 0.99 | |
|
| 0.0458 | 44.9524 | 708 | 0.0124 | 0.995 | |
|
| 0.0374 | 45.9683 | 724 | 0.0253 | 0.995 | |
|
| 0.0413 | 46.9841 | 740 | 0.0025 | 1.0 | |
|
| 0.0413 | 47.6190 | 750 | 0.0010 | 1.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.2 |
|
- Pytorch 2.5.0 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.1 |
|
|
