metadata
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_tiny_sgd_001_fold2
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: 0.3111111111111111
hushem_5x_deit_tiny_sgd_001_fold2
This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.5326
- Accuracy: 0.3111
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 |
|---|---|---|---|---|
| 1.5319 | 1.0 | 27 | 1.6147 | 0.1778 |
| 1.412 | 2.0 | 54 | 1.5641 | 0.2222 |
| 1.3305 | 3.0 | 81 | 1.5365 | 0.2 |
| 1.301 | 4.0 | 108 | 1.5559 | 0.2222 |
| 1.2455 | 5.0 | 135 | 1.5605 | 0.2444 |
| 1.184 | 6.0 | 162 | 1.5721 | 0.2444 |
| 1.1536 | 7.0 | 189 | 1.5847 | 0.2444 |
| 1.141 | 8.0 | 216 | 1.6070 | 0.2667 |
| 1.0813 | 9.0 | 243 | 1.6240 | 0.2667 |
| 1.0544 | 10.0 | 270 | 1.6212 | 0.2667 |
| 1.0306 | 11.0 | 297 | 1.6262 | 0.2667 |
| 0.9926 | 12.0 | 324 | 1.6270 | 0.2667 |
| 0.9991 | 13.0 | 351 | 1.6433 | 0.2444 |
| 0.9662 | 14.0 | 378 | 1.6269 | 0.2667 |
| 0.9752 | 15.0 | 405 | 1.6379 | 0.2444 |
| 0.9275 | 16.0 | 432 | 1.6386 | 0.2444 |
| 0.9112 | 17.0 | 459 | 1.6378 | 0.2667 |
| 0.8926 | 18.0 | 486 | 1.6345 | 0.2667 |
| 0.8698 | 19.0 | 513 | 1.6300 | 0.2444 |
| 0.8732 | 20.0 | 540 | 1.6217 | 0.2444 |
| 0.8587 | 21.0 | 567 | 1.6212 | 0.2667 |
| 0.8545 | 22.0 | 594 | 1.6207 | 0.2667 |
| 0.8339 | 23.0 | 621 | 1.6201 | 0.2444 |
| 0.8104 | 24.0 | 648 | 1.6072 | 0.2667 |
| 0.7957 | 25.0 | 675 | 1.6070 | 0.2667 |
| 0.8197 | 26.0 | 702 | 1.6043 | 0.2444 |
| 0.8076 | 27.0 | 729 | 1.6022 | 0.2667 |
| 0.7686 | 28.0 | 756 | 1.5925 | 0.2889 |
| 0.7691 | 29.0 | 783 | 1.5965 | 0.2889 |
| 0.7835 | 30.0 | 810 | 1.5836 | 0.2889 |
| 0.7441 | 31.0 | 837 | 1.5828 | 0.2889 |
| 0.7775 | 32.0 | 864 | 1.5709 | 0.2889 |
| 0.7317 | 33.0 | 891 | 1.5664 | 0.2889 |
| 0.7292 | 34.0 | 918 | 1.5626 | 0.2889 |
| 0.7179 | 35.0 | 945 | 1.5496 | 0.2667 |
| 0.7386 | 36.0 | 972 | 1.5502 | 0.2889 |
| 0.7342 | 37.0 | 999 | 1.5475 | 0.3111 |
| 0.734 | 38.0 | 1026 | 1.5457 | 0.3111 |
| 0.7069 | 39.0 | 1053 | 1.5425 | 0.3111 |
| 0.7143 | 40.0 | 1080 | 1.5429 | 0.3111 |
| 0.7105 | 41.0 | 1107 | 1.5401 | 0.3111 |
| 0.7189 | 42.0 | 1134 | 1.5394 | 0.3111 |
| 0.7216 | 43.0 | 1161 | 1.5376 | 0.3111 |
| 0.6896 | 44.0 | 1188 | 1.5358 | 0.3111 |
| 0.7099 | 45.0 | 1215 | 1.5345 | 0.3111 |
| 0.6751 | 46.0 | 1242 | 1.5331 | 0.3111 |
| 0.6824 | 47.0 | 1269 | 1.5327 | 0.3111 |
| 0.7027 | 48.0 | 1296 | 1.5326 | 0.3111 |
| 0.7357 | 49.0 | 1323 | 1.5326 | 0.3111 |
| 0.6799 | 50.0 | 1350 | 1.5326 | 0.3111 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0