hushem_1x_beit_base_rms_0001_fold5
This model is a fine-tuned version of microsoft/beit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.7755
- Accuracy: 0.6341
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- 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 | 1.0 | 6 | 1.4246 | 0.2683 |
1.7592 | 2.0 | 12 | 1.3851 | 0.2683 |
1.7592 | 3.0 | 18 | 1.3804 | 0.2439 |
1.4204 | 4.0 | 24 | 1.4010 | 0.2683 |
1.3988 | 5.0 | 30 | 1.3776 | 0.2439 |
1.3988 | 6.0 | 36 | 1.3196 | 0.3171 |
1.3741 | 7.0 | 42 | 1.2653 | 0.3659 |
1.3741 | 8.0 | 48 | 1.3284 | 0.3902 |
1.3098 | 9.0 | 54 | 1.2504 | 0.4146 |
1.2944 | 10.0 | 60 | 1.2840 | 0.2927 |
1.2944 | 11.0 | 66 | 1.3400 | 0.3902 |
1.3252 | 12.0 | 72 | 1.2889 | 0.3659 |
1.3252 | 13.0 | 78 | 1.1547 | 0.4634 |
1.2379 | 14.0 | 84 | 1.1463 | 0.3415 |
1.1874 | 15.0 | 90 | 1.1230 | 0.5122 |
1.1874 | 16.0 | 96 | 4.2155 | 0.3902 |
1.374 | 17.0 | 102 | 0.9374 | 0.6098 |
1.374 | 18.0 | 108 | 0.9748 | 0.6341 |
1.0858 | 19.0 | 114 | 0.9498 | 0.5366 |
0.9929 | 20.0 | 120 | 1.0346 | 0.4878 |
0.9929 | 21.0 | 126 | 1.2495 | 0.4634 |
0.9078 | 22.0 | 132 | 1.0142 | 0.5366 |
0.9078 | 23.0 | 138 | 0.9571 | 0.6341 |
0.8585 | 24.0 | 144 | 0.7607 | 0.7073 |
0.9707 | 25.0 | 150 | 0.9749 | 0.4878 |
0.9707 | 26.0 | 156 | 1.2739 | 0.6341 |
0.8033 | 27.0 | 162 | 0.7831 | 0.6585 |
0.8033 | 28.0 | 168 | 0.9134 | 0.5610 |
0.8358 | 29.0 | 174 | 0.9940 | 0.6098 |
0.7373 | 30.0 | 180 | 0.9448 | 0.6341 |
0.7373 | 31.0 | 186 | 1.0065 | 0.6341 |
0.693 | 32.0 | 192 | 1.2616 | 0.6585 |
0.693 | 33.0 | 198 | 1.0510 | 0.6098 |
0.6403 | 34.0 | 204 | 1.2334 | 0.6341 |
0.6359 | 35.0 | 210 | 1.2865 | 0.6341 |
0.6359 | 36.0 | 216 | 1.2812 | 0.6098 |
0.5717 | 37.0 | 222 | 1.4784 | 0.6341 |
0.5717 | 38.0 | 228 | 1.6714 | 0.6341 |
0.5294 | 39.0 | 234 | 1.7953 | 0.5854 |
0.5043 | 40.0 | 240 | 1.6946 | 0.6341 |
0.5043 | 41.0 | 246 | 1.7411 | 0.6585 |
0.4865 | 42.0 | 252 | 1.7755 | 0.6341 |
0.4865 | 43.0 | 258 | 1.7755 | 0.6341 |
0.4648 | 44.0 | 264 | 1.7755 | 0.6341 |
0.4795 | 45.0 | 270 | 1.7755 | 0.6341 |
0.4795 | 46.0 | 276 | 1.7755 | 0.6341 |
0.4544 | 47.0 | 282 | 1.7755 | 0.6341 |
0.4544 | 48.0 | 288 | 1.7755 | 0.6341 |
0.519 | 49.0 | 294 | 1.7755 | 0.6341 |
0.4907 | 50.0 | 300 | 1.7755 | 0.6341 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 14