smids_1x_beit_base_sgd_001_fold4
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: 0.3889
- Accuracy: 0.8533
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 |
---|---|---|---|---|
1.0889 | 1.0 | 75 | 1.0669 | 0.4483 |
0.8655 | 2.0 | 150 | 0.8559 | 0.645 |
0.7785 | 3.0 | 225 | 0.7294 | 0.7017 |
0.7379 | 4.0 | 300 | 0.6722 | 0.7167 |
0.7102 | 5.0 | 375 | 0.6344 | 0.7367 |
0.679 | 6.0 | 450 | 0.6029 | 0.7583 |
0.6616 | 7.0 | 525 | 0.5757 | 0.7667 |
0.6078 | 8.0 | 600 | 0.5519 | 0.7983 |
0.6427 | 9.0 | 675 | 0.5357 | 0.7867 |
0.5452 | 10.0 | 750 | 0.5237 | 0.7983 |
0.5678 | 11.0 | 825 | 0.5091 | 0.7933 |
0.5374 | 12.0 | 900 | 0.4984 | 0.8083 |
0.5811 | 13.0 | 975 | 0.4866 | 0.8033 |
0.5027 | 14.0 | 1050 | 0.4734 | 0.81 |
0.4787 | 15.0 | 1125 | 0.4709 | 0.805 |
0.4828 | 16.0 | 1200 | 0.4644 | 0.8117 |
0.4631 | 17.0 | 1275 | 0.4587 | 0.81 |
0.4343 | 18.0 | 1350 | 0.4468 | 0.82 |
0.4904 | 19.0 | 1425 | 0.4435 | 0.82 |
0.4433 | 20.0 | 1500 | 0.4398 | 0.8167 |
0.4461 | 21.0 | 1575 | 0.4318 | 0.8283 |
0.3894 | 22.0 | 1650 | 0.4361 | 0.8217 |
0.4398 | 23.0 | 1725 | 0.4269 | 0.8333 |
0.4433 | 24.0 | 1800 | 0.4213 | 0.835 |
0.4253 | 25.0 | 1875 | 0.4182 | 0.8333 |
0.4141 | 26.0 | 1950 | 0.4208 | 0.835 |
0.4307 | 27.0 | 2025 | 0.4086 | 0.8433 |
0.4132 | 28.0 | 2100 | 0.4078 | 0.8417 |
0.41 | 29.0 | 2175 | 0.4074 | 0.8467 |
0.4398 | 30.0 | 2250 | 0.4048 | 0.8383 |
0.3394 | 31.0 | 2325 | 0.4047 | 0.8383 |
0.4174 | 32.0 | 2400 | 0.4015 | 0.8433 |
0.4379 | 33.0 | 2475 | 0.3992 | 0.8433 |
0.3836 | 34.0 | 2550 | 0.3988 | 0.845 |
0.3824 | 35.0 | 2625 | 0.3986 | 0.845 |
0.3571 | 36.0 | 2700 | 0.3978 | 0.8433 |
0.348 | 37.0 | 2775 | 0.3932 | 0.8483 |
0.3852 | 38.0 | 2850 | 0.3961 | 0.8433 |
0.4099 | 39.0 | 2925 | 0.3932 | 0.8483 |
0.4003 | 40.0 | 3000 | 0.3917 | 0.8533 |
0.3921 | 41.0 | 3075 | 0.3931 | 0.8483 |
0.3545 | 42.0 | 3150 | 0.3904 | 0.8533 |
0.3816 | 43.0 | 3225 | 0.3916 | 0.8467 |
0.3789 | 44.0 | 3300 | 0.3906 | 0.8533 |
0.373 | 45.0 | 3375 | 0.3905 | 0.85 |
0.3767 | 46.0 | 3450 | 0.3894 | 0.8533 |
0.3814 | 47.0 | 3525 | 0.3896 | 0.8517 |
0.3984 | 48.0 | 3600 | 0.3899 | 0.85 |
0.3749 | 49.0 | 3675 | 0.3891 | 0.8533 |
0.3605 | 50.0 | 3750 | 0.3889 | 0.8533 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 0