font-identifier
This model is a fine-tuned version of 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
