smids_3x_beit_base_adamax_00001_fold2
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: 0.8293
- Accuracy: 0.8952
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 |
---|---|---|---|---|
0.3036 | 1.0 | 375 | 0.2703 | 0.8918 |
0.2118 | 2.0 | 750 | 0.2674 | 0.8968 |
0.1557 | 3.0 | 1125 | 0.2889 | 0.8918 |
0.074 | 4.0 | 1500 | 0.2842 | 0.9002 |
0.0616 | 5.0 | 1875 | 0.3403 | 0.8935 |
0.036 | 6.0 | 2250 | 0.3534 | 0.9101 |
0.0382 | 7.0 | 2625 | 0.4309 | 0.8985 |
0.0686 | 8.0 | 3000 | 0.4834 | 0.8985 |
0.022 | 9.0 | 3375 | 0.5298 | 0.8935 |
0.0159 | 10.0 | 3750 | 0.5866 | 0.8985 |
0.0173 | 11.0 | 4125 | 0.5611 | 0.8968 |
0.0241 | 12.0 | 4500 | 0.6961 | 0.8869 |
0.0125 | 13.0 | 4875 | 0.6251 | 0.8952 |
0.0052 | 14.0 | 5250 | 0.6175 | 0.9002 |
0.0252 | 15.0 | 5625 | 0.6443 | 0.8935 |
0.0003 | 16.0 | 6000 | 0.6752 | 0.8952 |
0.0517 | 17.0 | 6375 | 0.6928 | 0.8985 |
0.0082 | 18.0 | 6750 | 0.6809 | 0.8985 |
0.0008 | 19.0 | 7125 | 0.7189 | 0.8935 |
0.012 | 20.0 | 7500 | 0.7838 | 0.9002 |
0.0206 | 21.0 | 7875 | 0.7183 | 0.8968 |
0.0006 | 22.0 | 8250 | 0.7126 | 0.9085 |
0.0002 | 23.0 | 8625 | 0.7379 | 0.8985 |
0.0002 | 24.0 | 9000 | 0.7747 | 0.8952 |
0.0001 | 25.0 | 9375 | 0.7907 | 0.8869 |
0.0001 | 26.0 | 9750 | 0.7652 | 0.8985 |
0.0153 | 27.0 | 10125 | 0.8239 | 0.8935 |
0.002 | 28.0 | 10500 | 0.7554 | 0.9018 |
0.0228 | 29.0 | 10875 | 0.8026 | 0.9002 |
0.0049 | 30.0 | 11250 | 0.7927 | 0.9052 |
0.003 | 31.0 | 11625 | 0.8114 | 0.8968 |
0.0086 | 32.0 | 12000 | 0.8422 | 0.8935 |
0.0066 | 33.0 | 12375 | 0.8193 | 0.8935 |
0.0014 | 34.0 | 12750 | 0.8462 | 0.9002 |
0.0005 | 35.0 | 13125 | 0.8418 | 0.8902 |
0.0031 | 36.0 | 13500 | 0.8633 | 0.8918 |
0.0051 | 37.0 | 13875 | 0.8436 | 0.8918 |
0.0003 | 38.0 | 14250 | 0.8576 | 0.8902 |
0.0037 | 39.0 | 14625 | 0.8301 | 0.8902 |
0.0238 | 40.0 | 15000 | 0.8339 | 0.8952 |
0.0147 | 41.0 | 15375 | 0.8449 | 0.8968 |
0.011 | 42.0 | 15750 | 0.8207 | 0.8968 |
0.0179 | 43.0 | 16125 | 0.8212 | 0.8968 |
0.0045 | 44.0 | 16500 | 0.8067 | 0.9018 |
0.023 | 45.0 | 16875 | 0.8396 | 0.8918 |
0.027 | 46.0 | 17250 | 0.8319 | 0.8935 |
0.0247 | 47.0 | 17625 | 0.8325 | 0.8935 |
0.019 | 48.0 | 18000 | 0.8318 | 0.8952 |
0.0136 | 49.0 | 18375 | 0.8279 | 0.8952 |
0.0009 | 50.0 | 18750 | 0.8293 | 0.8952 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2
- Downloads last month
- 0