metadata
license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_beit_base_sgd_0001_fold3
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: test
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.27906976744186046
hushem_5x_beit_base_sgd_0001_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: 1.4647
- Accuracy: 0.2791
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 |
|---|---|---|---|---|
| 1.5793 | 1.0 | 28 | 1.5789 | 0.2558 |
| 1.5183 | 2.0 | 56 | 1.5712 | 0.2558 |
| 1.5213 | 3.0 | 84 | 1.5641 | 0.2558 |
| 1.4605 | 4.0 | 112 | 1.5574 | 0.2558 |
| 1.4855 | 5.0 | 140 | 1.5511 | 0.2558 |
| 1.4714 | 6.0 | 168 | 1.5448 | 0.2558 |
| 1.5489 | 7.0 | 196 | 1.5392 | 0.2791 |
| 1.4903 | 8.0 | 224 | 1.5342 | 0.2791 |
| 1.4325 | 9.0 | 252 | 1.5290 | 0.2791 |
| 1.4353 | 10.0 | 280 | 1.5246 | 0.2558 |
| 1.4693 | 11.0 | 308 | 1.5207 | 0.2558 |
| 1.4343 | 12.0 | 336 | 1.5162 | 0.2558 |
| 1.4713 | 13.0 | 364 | 1.5122 | 0.2558 |
| 1.4732 | 14.0 | 392 | 1.5085 | 0.2558 |
| 1.517 | 15.0 | 420 | 1.5050 | 0.2558 |
| 1.4521 | 16.0 | 448 | 1.5018 | 0.2558 |
| 1.4309 | 17.0 | 476 | 1.4988 | 0.2558 |
| 1.4246 | 18.0 | 504 | 1.4964 | 0.2558 |
| 1.4231 | 19.0 | 532 | 1.4937 | 0.2558 |
| 1.4691 | 20.0 | 560 | 1.4912 | 0.2558 |
| 1.4305 | 21.0 | 588 | 1.4888 | 0.2558 |
| 1.4575 | 22.0 | 616 | 1.4865 | 0.2558 |
| 1.4268 | 23.0 | 644 | 1.4845 | 0.2558 |
| 1.3904 | 24.0 | 672 | 1.4827 | 0.2558 |
| 1.4432 | 25.0 | 700 | 1.4808 | 0.2558 |
| 1.4078 | 26.0 | 728 | 1.4793 | 0.2558 |
| 1.382 | 27.0 | 756 | 1.4777 | 0.2558 |
| 1.3894 | 28.0 | 784 | 1.4764 | 0.2558 |
| 1.4046 | 29.0 | 812 | 1.4751 | 0.2558 |
| 1.4273 | 30.0 | 840 | 1.4741 | 0.2791 |
| 1.3786 | 31.0 | 868 | 1.4730 | 0.2791 |
| 1.3777 | 32.0 | 896 | 1.4719 | 0.2791 |
| 1.3887 | 33.0 | 924 | 1.4708 | 0.2791 |
| 1.3651 | 34.0 | 952 | 1.4700 | 0.2791 |
| 1.4904 | 35.0 | 980 | 1.4692 | 0.2791 |
| 1.3288 | 36.0 | 1008 | 1.4686 | 0.2791 |
| 1.3653 | 37.0 | 1036 | 1.4680 | 0.2791 |
| 1.3833 | 38.0 | 1064 | 1.4673 | 0.2791 |
| 1.3973 | 39.0 | 1092 | 1.4668 | 0.2791 |
| 1.4044 | 40.0 | 1120 | 1.4663 | 0.2791 |
| 1.3896 | 41.0 | 1148 | 1.4659 | 0.2791 |
| 1.3676 | 42.0 | 1176 | 1.4656 | 0.2791 |
| 1.3444 | 43.0 | 1204 | 1.4654 | 0.2791 |
| 1.3782 | 44.0 | 1232 | 1.4651 | 0.2791 |
| 1.44 | 45.0 | 1260 | 1.4650 | 0.2791 |
| 1.383 | 46.0 | 1288 | 1.4648 | 0.2791 |
| 1.3752 | 47.0 | 1316 | 1.4648 | 0.2791 |
| 1.343 | 48.0 | 1344 | 1.4647 | 0.2791 |
| 1.3923 | 49.0 | 1372 | 1.4647 | 0.2791 |
| 1.429 | 50.0 | 1400 | 1.4647 | 0.2791 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0