smids_1x_beit_base_adamax_00001_fold1
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: 0.6618
- Accuracy: 0.9032
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: 1e-05
- 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 |
---|---|---|---|---|
0.4246 | 1.0 | 76 | 0.3687 | 0.8598 |
0.2552 | 2.0 | 152 | 0.2999 | 0.8798 |
0.1978 | 3.0 | 228 | 0.2886 | 0.8731 |
0.1972 | 4.0 | 304 | 0.2763 | 0.8865 |
0.1608 | 5.0 | 380 | 0.2799 | 0.8865 |
0.1346 | 6.0 | 456 | 0.3048 | 0.8815 |
0.0943 | 7.0 | 532 | 0.3402 | 0.8898 |
0.0622 | 8.0 | 608 | 0.3287 | 0.8915 |
0.0613 | 9.0 | 684 | 0.3634 | 0.8865 |
0.0585 | 10.0 | 760 | 0.3905 | 0.8881 |
0.0328 | 11.0 | 836 | 0.3830 | 0.8948 |
0.0344 | 12.0 | 912 | 0.4094 | 0.8915 |
0.053 | 13.0 | 988 | 0.4103 | 0.8932 |
0.0261 | 14.0 | 1064 | 0.4498 | 0.8932 |
0.0261 | 15.0 | 1140 | 0.4936 | 0.8915 |
0.0343 | 16.0 | 1216 | 0.4859 | 0.8932 |
0.0153 | 17.0 | 1292 | 0.5143 | 0.8815 |
0.0038 | 18.0 | 1368 | 0.5271 | 0.8865 |
0.0046 | 19.0 | 1444 | 0.5417 | 0.8898 |
0.0282 | 20.0 | 1520 | 0.5283 | 0.8948 |
0.0048 | 21.0 | 1596 | 0.5421 | 0.8965 |
0.0018 | 22.0 | 1672 | 0.5503 | 0.8898 |
0.0064 | 23.0 | 1748 | 0.5860 | 0.8848 |
0.0241 | 24.0 | 1824 | 0.5762 | 0.8948 |
0.0207 | 25.0 | 1900 | 0.5869 | 0.8915 |
0.0293 | 26.0 | 1976 | 0.5842 | 0.8948 |
0.0029 | 27.0 | 2052 | 0.6141 | 0.8932 |
0.0198 | 28.0 | 2128 | 0.6046 | 0.8982 |
0.0329 | 29.0 | 2204 | 0.6286 | 0.8948 |
0.0036 | 30.0 | 2280 | 0.6053 | 0.8948 |
0.0339 | 31.0 | 2356 | 0.6159 | 0.8881 |
0.0211 | 32.0 | 2432 | 0.6253 | 0.8932 |
0.0315 | 33.0 | 2508 | 0.6357 | 0.8915 |
0.0135 | 34.0 | 2584 | 0.6365 | 0.8932 |
0.0361 | 35.0 | 2660 | 0.6309 | 0.8965 |
0.0313 | 36.0 | 2736 | 0.6365 | 0.8965 |
0.0198 | 37.0 | 2812 | 0.6348 | 0.8965 |
0.0132 | 38.0 | 2888 | 0.6243 | 0.8948 |
0.0085 | 39.0 | 2964 | 0.6351 | 0.8948 |
0.001 | 40.0 | 3040 | 0.6372 | 0.8948 |
0.0149 | 41.0 | 3116 | 0.6607 | 0.8998 |
0.0056 | 42.0 | 3192 | 0.6570 | 0.9065 |
0.0011 | 43.0 | 3268 | 0.6635 | 0.8998 |
0.003 | 44.0 | 3344 | 0.6527 | 0.8982 |
0.041 | 45.0 | 3420 | 0.6537 | 0.8982 |
0.0011 | 46.0 | 3496 | 0.6576 | 0.8982 |
0.0196 | 47.0 | 3572 | 0.6599 | 0.8998 |
0.0117 | 48.0 | 3648 | 0.6620 | 0.9032 |
0.0018 | 49.0 | 3724 | 0.6617 | 0.9032 |
0.0144 | 50.0 | 3800 | 0.6618 | 0.9032 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.