smids_3x_beit_base_rms_001_fold3
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: 0.6251
- Accuracy: 0.7617
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: 0.001
- 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 |
---|---|---|---|---|
0.9148 | 1.0 | 225 | 0.9238 | 0.505 |
0.8709 | 2.0 | 450 | 0.9060 | 0.515 |
0.8398 | 3.0 | 675 | 0.8688 | 0.5317 |
0.74 | 4.0 | 900 | 0.7859 | 0.5617 |
0.7787 | 5.0 | 1125 | 0.7847 | 0.6017 |
0.7532 | 6.0 | 1350 | 0.7702 | 0.63 |
0.7432 | 7.0 | 1575 | 0.7450 | 0.655 |
0.7264 | 8.0 | 1800 | 0.7610 | 0.6317 |
0.7321 | 9.0 | 2025 | 0.7293 | 0.655 |
0.6592 | 10.0 | 2250 | 0.7888 | 0.6367 |
0.7528 | 11.0 | 2475 | 0.7158 | 0.6633 |
0.7282 | 12.0 | 2700 | 0.7365 | 0.64 |
0.6884 | 13.0 | 2925 | 0.6939 | 0.6733 |
0.6852 | 14.0 | 3150 | 0.7006 | 0.67 |
0.6011 | 15.0 | 3375 | 0.7591 | 0.6233 |
0.6904 | 16.0 | 3600 | 0.6846 | 0.6717 |
0.6393 | 17.0 | 3825 | 0.6741 | 0.7117 |
0.6772 | 18.0 | 4050 | 0.6655 | 0.6683 |
0.6409 | 19.0 | 4275 | 0.6658 | 0.6933 |
0.5941 | 20.0 | 4500 | 0.6429 | 0.7017 |
0.5753 | 21.0 | 4725 | 0.6753 | 0.6833 |
0.5975 | 22.0 | 4950 | 0.6543 | 0.6917 |
0.5954 | 23.0 | 5175 | 0.6358 | 0.7233 |
0.5729 | 24.0 | 5400 | 0.6341 | 0.7133 |
0.6313 | 25.0 | 5625 | 0.6336 | 0.7033 |
0.5938 | 26.0 | 5850 | 0.6447 | 0.7083 |
0.5183 | 27.0 | 6075 | 0.6247 | 0.7233 |
0.5713 | 28.0 | 6300 | 0.6145 | 0.73 |
0.5948 | 29.0 | 6525 | 0.5934 | 0.7317 |
0.5273 | 30.0 | 6750 | 0.5971 | 0.7367 |
0.5431 | 31.0 | 6975 | 0.5930 | 0.7433 |
0.6025 | 32.0 | 7200 | 0.6434 | 0.7183 |
0.5898 | 33.0 | 7425 | 0.5982 | 0.7383 |
0.5455 | 34.0 | 7650 | 0.5983 | 0.75 |
0.4857 | 35.0 | 7875 | 0.6162 | 0.735 |
0.5822 | 36.0 | 8100 | 0.5546 | 0.7517 |
0.4869 | 37.0 | 8325 | 0.5748 | 0.745 |
0.4722 | 38.0 | 8550 | 0.5753 | 0.7417 |
0.4982 | 39.0 | 8775 | 0.5694 | 0.7483 |
0.4478 | 40.0 | 9000 | 0.5912 | 0.74 |
0.4295 | 41.0 | 9225 | 0.5914 | 0.75 |
0.4581 | 42.0 | 9450 | 0.5846 | 0.7617 |
0.3797 | 43.0 | 9675 | 0.5733 | 0.7667 |
0.4086 | 44.0 | 9900 | 0.6072 | 0.7517 |
0.4164 | 45.0 | 10125 | 0.6033 | 0.7583 |
0.3774 | 46.0 | 10350 | 0.6024 | 0.75 |
0.392 | 47.0 | 10575 | 0.5976 | 0.7617 |
0.3586 | 48.0 | 10800 | 0.6199 | 0.76 |
0.3854 | 49.0 | 11025 | 0.6198 | 0.7667 |
0.3586 | 50.0 | 11250 | 0.6251 | 0.7617 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2
- Downloads last month
- 11
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.