|
|
--- |
|
|
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: 0.9162162162162162 |
|
|
--- |
|
|
|
|
|
<!-- 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: |
|
|
- Accuracy: 0.9162 |
|
|
- Loss: 0.2760 |
|
|
|
|
|
## 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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_ratio: 0.1 |
|
|
- num_epochs: 50 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Accuracy | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:--------:|:---------------:| |
|
|
| 3.7676 | 1.0 | 24 | 0.0459 | 3.6832 | |
|
|
| 3.607 | 2.0 | 48 | 0.0919 | 3.4400 | |
|
|
| 3.2234 | 3.0 | 72 | 0.1919 | 3.0452 | |
|
|
| 2.8944 | 4.0 | 96 | 0.3324 | 2.5182 | |
|
|
| 2.1637 | 5.0 | 120 | 0.4351 | 2.0193 | |
|
|
| 1.9347 | 6.0 | 144 | 0.5595 | 1.6222 | |
|
|
| 1.6851 | 7.0 | 168 | 0.6297 | 1.3065 | |
|
|
| 1.369 | 8.0 | 192 | 0.6919 | 1.0945 | |
|
|
| 1.2987 | 9.0 | 216 | 0.7270 | 0.9188 | |
|
|
| 1.1044 | 10.0 | 240 | 0.7541 | 0.8216 | |
|
|
| 1.044 | 11.0 | 264 | 0.8 | 0.7295 | |
|
|
| 1.0134 | 12.0 | 288 | 0.8270 | 0.6655 | |
|
|
| 0.9284 | 13.0 | 312 | 0.8189 | 0.6212 | |
|
|
| 0.8603 | 14.0 | 336 | 0.8216 | 0.5687 | |
|
|
| 0.7748 | 15.0 | 360 | 0.8649 | 0.5291 | |
|
|
| 0.8133 | 16.0 | 384 | 0.8324 | 0.5337 | |
|
|
| 0.8379 | 17.0 | 408 | 0.8486 | 0.4993 | |
|
|
| 0.751 | 18.0 | 432 | 0.8514 | 0.4632 | |
|
|
| 0.8585 | 19.0 | 456 | 0.8162 | 0.4908 | |
|
|
| 0.6627 | 20.0 | 480 | 0.8622 | 0.4358 | |
|
|
| 0.6497 | 21.0 | 504 | 0.8486 | 0.4240 | |
|
|
| 0.6422 | 22.0 | 528 | 0.8486 | 0.4143 | |
|
|
| 0.5964 | 23.0 | 552 | 0.8676 | 0.3912 | |
|
|
| 0.5793 | 24.0 | 576 | 0.8568 | 0.4026 | |
|
|
| 0.5909 | 25.0 | 600 | 0.8838 | 0.3531 | |
|
|
| 0.593 | 26.0 | 624 | 0.8811 | 0.3661 | |
|
|
| 0.5957 | 27.0 | 648 | 0.8892 | 0.3674 | |
|
|
| 0.5869 | 28.0 | 672 | 0.8892 | 0.3710 | |
|
|
| 0.4999 | 29.0 | 696 | 0.8919 | 0.3422 | |
|
|
| 0.4843 | 30.0 | 720 | 0.8946 | 0.3178 | |
|
|
| 0.5352 | 31.0 | 744 | 0.8865 | 0.3129 | |
|
|
| 0.4937 | 32.0 | 768 | 0.8973 | 0.3399 | |
|
|
| 0.483 | 33.0 | 792 | 0.8973 | 0.2855 | |
|
|
| 0.4265 | 34.0 | 816 | 0.9 | 0.3316 | |
|
|
| 0.4412 | 35.0 | 840 | 0.8865 | 0.3273 | |
|
|
| 0.4324 | 36.0 | 864 | 0.8973 | 0.3167 | |
|
|
| 0.4681 | 37.0 | 888 | 0.9270 | 0.2944 | |
|
|
| 0.4813 | 38.0 | 912 | 0.9135 | 0.2943 | |
|
|
| 0.4585 | 39.0 | 936 | 0.9027 | 0.3019 | |
|
|
| 0.4151 | 40.0 | 960 | 0.8892 | 0.3399 | |
|
|
| 0.4351 | 41.0 | 984 | 0.9081 | 0.2623 | |
|
|
| 0.4364 | 42.0 | 1008 | 0.9135 | 0.2892 | |
|
|
| 0.4632 | 43.0 | 1032 | 0.9081 | 0.3086 | |
|
|
| 0.3867 | 44.0 | 1056 | 0.9 | 0.2913 | |
|
|
| 0.4007 | 45.0 | 1080 | 0.9135 | 0.2502 | |
|
|
| 0.3848 | 46.0 | 1104 | 0.9162 | 0.2702 | |
|
|
| 0.4061 | 47.0 | 1128 | 0.9162 | 0.2634 | |
|
|
| 0.3901 | 48.0 | 1152 | 0.9054 | 0.2975 | |
|
|
| 0.3794 | 49.0 | 1176 | 0.8973 | 0.2590 | |
|
|
| 0.3583 | 50.0 | 1200 | 0.9162 | 0.2760 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.53.3 |
|
|
- Pytorch 2.7.1 |
|
|
- Datasets 4.0.0 |
|
|
- Tokenizers 0.21.4 |
|
|
|
