metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: cards_bottom_left_swin-tiny-patch4-window7-224-finetuned-v2_more_Data
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: 0.5927874941959449
cards_bottom_left_swin-tiny-patch4-window7-224-finetuned-v2_more_Data
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.0009
- Accuracy: 0.5928
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|---|---|---|---|---|
| 1.559 | 1.0 | 1362 | 1.3402 | 0.4189 |
| 1.5165 | 2.0 | 2725 | 1.2308 | 0.4647 |
| 1.484 | 3.0 | 4087 | 1.1676 | 0.4954 |
| 1.5037 | 4.0 | 5450 | 1.1206 | 0.5198 |
| 1.4489 | 5.0 | 6812 | 1.1162 | 0.5284 |
| 1.4335 | 6.0 | 8175 | 1.1395 | 0.5047 |
| 1.4281 | 7.0 | 9537 | 1.0606 | 0.5445 |
| 1.4219 | 8.0 | 10900 | 1.0754 | 0.5408 |
| 1.3935 | 9.0 | 12262 | 1.0285 | 0.5604 |
| 1.3542 | 10.0 | 13625 | 1.0497 | 0.5453 |
| 1.3761 | 11.0 | 14987 | 1.0535 | 0.5450 |
| 1.3824 | 12.0 | 16350 | 1.0268 | 0.5591 |
| 1.3709 | 13.0 | 17712 | 1.0015 | 0.5690 |
| 1.3361 | 14.0 | 19075 | 1.0266 | 0.5595 |
| 1.3673 | 15.0 | 20437 | 0.9988 | 0.5772 |
| 1.376 | 16.0 | 21800 | 0.9950 | 0.5744 |
| 1.3486 | 17.0 | 23162 | 0.9837 | 0.5784 |
| 1.3333 | 18.0 | 24525 | 0.9771 | 0.5827 |
| 1.347 | 19.0 | 25887 | 0.9895 | 0.5770 |
| 1.3381 | 20.0 | 27250 | 0.9709 | 0.5820 |
| 1.3385 | 21.0 | 28612 | 0.9704 | 0.5833 |
| 1.336 | 22.0 | 29975 | 0.9646 | 0.5885 |
| 1.3372 | 23.0 | 31337 | 0.9653 | 0.5879 |
| 1.2979 | 24.0 | 32700 | 0.9867 | 0.5814 |
| 1.2948 | 25.0 | 34062 | 0.9633 | 0.5870 |
| 1.2767 | 26.0 | 35425 | 0.9578 | 0.5877 |
| 1.3012 | 27.0 | 36787 | 0.9709 | 0.5867 |
| 1.2667 | 28.0 | 38150 | 0.9648 | 0.5899 |
| 1.3 | 29.0 | 39512 | 0.9560 | 0.5930 |
| 1.2735 | 30.0 | 40875 | 0.9595 | 0.5949 |
| 1.2895 | 31.0 | 42237 | 0.9851 | 0.5809 |
| 1.2234 | 32.0 | 43600 | 0.9601 | 0.5931 |
| 1.2212 | 33.0 | 44962 | 0.9800 | 0.5917 |
| 1.2483 | 34.0 | 46325 | 0.9662 | 0.5982 |
| 1.2507 | 35.0 | 47687 | 0.9657 | 0.5910 |
| 1.2539 | 36.0 | 49050 | 0.9954 | 0.5783 |
| 1.2491 | 37.0 | 50412 | 0.9718 | 0.5924 |
| 1.2397 | 38.0 | 51775 | 0.9769 | 0.5930 |
| 1.1903 | 39.0 | 53137 | 0.9717 | 0.5945 |
| 1.2475 | 40.0 | 54500 | 0.9995 | 0.5855 |
| 1.2371 | 41.0 | 55862 | 0.9861 | 0.5935 |
| 1.2561 | 42.0 | 57225 | 0.9856 | 0.5958 |
| 1.2069 | 43.0 | 58587 | 0.9913 | 0.5892 |
| 1.2188 | 44.0 | 59950 | 0.9902 | 0.5950 |
| 1.1732 | 45.0 | 61312 | 0.9892 | 0.5949 |
| 1.1705 | 46.0 | 62675 | 0.9991 | 0.5914 |
| 1.18 | 47.0 | 64037 | 0.9952 | 0.5925 |
| 1.2353 | 48.0 | 65400 | 0.9999 | 0.5933 |
| 1.2057 | 49.0 | 66762 | 1.0001 | 0.5920 |
| 1.1833 | 49.98 | 68100 | 1.0009 | 0.5928 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.0.1+cu117
- Datasets 2.17.0
- Tokenizers 0.15.2