metadata
license: apache-2.0
base_model: microsoft/beit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: smids_5x_beit_base_adamax_001_fold1
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: 0.7145242070116862
smids_5x_beit_base_adamax_001_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: 0.6198
- Accuracy: 0.7145
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 |
---|---|---|---|---|
0.9679 | 1.0 | 376 | 0.9413 | 0.5025 |
0.8566 | 2.0 | 752 | 0.8816 | 0.5259 |
0.8176 | 3.0 | 1128 | 0.7970 | 0.5710 |
0.859 | 4.0 | 1504 | 0.8016 | 0.5626 |
1.031 | 5.0 | 1880 | 0.8469 | 0.5576 |
0.741 | 6.0 | 2256 | 0.8899 | 0.5426 |
0.7405 | 7.0 | 2632 | 0.8021 | 0.6194 |
0.7314 | 8.0 | 3008 | 0.7493 | 0.6327 |
0.6987 | 9.0 | 3384 | 0.7283 | 0.6461 |
0.7152 | 10.0 | 3760 | 0.7824 | 0.6260 |
0.6328 | 11.0 | 4136 | 0.7526 | 0.6294 |
0.8425 | 12.0 | 4512 | 0.7315 | 0.6678 |
0.7019 | 13.0 | 4888 | 0.7450 | 0.6344 |
0.695 | 14.0 | 5264 | 0.7358 | 0.6611 |
0.6413 | 15.0 | 5640 | 0.7306 | 0.6361 |
0.6189 | 16.0 | 6016 | 0.6963 | 0.6644 |
0.6245 | 17.0 | 6392 | 0.6845 | 0.6611 |
0.7409 | 18.0 | 6768 | 0.7226 | 0.6845 |
0.7054 | 19.0 | 7144 | 0.7324 | 0.6694 |
0.6703 | 20.0 | 7520 | 0.7291 | 0.6427 |
0.6526 | 21.0 | 7896 | 0.7119 | 0.6678 |
0.6212 | 22.0 | 8272 | 0.7262 | 0.6628 |
0.681 | 23.0 | 8648 | 0.6972 | 0.6644 |
0.6987 | 24.0 | 9024 | 0.7456 | 0.6594 |
0.6922 | 25.0 | 9400 | 0.6847 | 0.6694 |
0.6394 | 26.0 | 9776 | 0.6840 | 0.6745 |
0.6161 | 27.0 | 10152 | 0.6631 | 0.6828 |
0.5613 | 28.0 | 10528 | 0.6637 | 0.6761 |
0.6083 | 29.0 | 10904 | 0.7192 | 0.6745 |
0.6653 | 30.0 | 11280 | 0.6777 | 0.7045 |
0.5903 | 31.0 | 11656 | 0.6722 | 0.7012 |
0.6548 | 32.0 | 12032 | 0.7012 | 0.6511 |
0.5854 | 33.0 | 12408 | 0.6634 | 0.6811 |
0.614 | 34.0 | 12784 | 0.6595 | 0.6878 |
0.5441 | 35.0 | 13160 | 0.6831 | 0.6878 |
0.6051 | 36.0 | 13536 | 0.6864 | 0.6895 |
0.5008 | 37.0 | 13912 | 0.6407 | 0.6962 |
0.6049 | 38.0 | 14288 | 0.6571 | 0.7028 |
0.5851 | 39.0 | 14664 | 0.6506 | 0.6928 |
0.6223 | 40.0 | 15040 | 0.6528 | 0.6912 |
0.5754 | 41.0 | 15416 | 0.6469 | 0.7028 |
0.5456 | 42.0 | 15792 | 0.6395 | 0.7112 |
0.5001 | 43.0 | 16168 | 0.6344 | 0.7162 |
0.547 | 44.0 | 16544 | 0.6296 | 0.7212 |
0.4783 | 45.0 | 16920 | 0.6245 | 0.7179 |
0.4972 | 46.0 | 17296 | 0.6191 | 0.7312 |
0.5348 | 47.0 | 17672 | 0.6318 | 0.7295 |
0.5739 | 48.0 | 18048 | 0.6151 | 0.7062 |
0.4956 | 49.0 | 18424 | 0.6143 | 0.7179 |
0.4645 | 50.0 | 18800 | 0.6198 | 0.7145 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2