metadata
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_small_rms_0001_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: 0.5333333333333333
hushem_5x_deit_small_rms_0001_fold1
This model is a fine-tuned version of facebook/deit-small-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 4.0359
- Accuracy: 0.5333
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 |
|---|---|---|---|---|
| 1.4419 | 1.0 | 27 | 1.3907 | 0.2444 |
| 1.4324 | 2.0 | 54 | 1.5348 | 0.4222 |
| 1.2448 | 3.0 | 81 | 1.2892 | 0.4444 |
| 1.2278 | 4.0 | 108 | 2.0615 | 0.4222 |
| 0.8744 | 5.0 | 135 | 1.2150 | 0.4 |
| 0.7002 | 6.0 | 162 | 1.5857 | 0.4 |
| 0.6664 | 7.0 | 189 | 1.1206 | 0.5111 |
| 0.5543 | 8.0 | 216 | 2.0902 | 0.4 |
| 0.4511 | 9.0 | 243 | 1.5223 | 0.5111 |
| 0.3889 | 10.0 | 270 | 2.0931 | 0.4667 |
| 0.3279 | 11.0 | 297 | 2.0153 | 0.5778 |
| 0.1636 | 12.0 | 324 | 3.2794 | 0.4444 |
| 0.1375 | 13.0 | 351 | 2.4712 | 0.5333 |
| 0.0773 | 14.0 | 378 | 2.1584 | 0.5333 |
| 0.0482 | 15.0 | 405 | 2.9775 | 0.4889 |
| 0.022 | 16.0 | 432 | 3.2342 | 0.5111 |
| 0.0125 | 17.0 | 459 | 3.3088 | 0.4889 |
| 0.0285 | 18.0 | 486 | 2.2599 | 0.5556 |
| 0.0004 | 19.0 | 513 | 3.3514 | 0.5111 |
| 0.0002 | 20.0 | 540 | 3.3934 | 0.5111 |
| 0.0001 | 21.0 | 567 | 3.4412 | 0.5111 |
| 0.0001 | 22.0 | 594 | 3.4801 | 0.5111 |
| 0.0001 | 23.0 | 621 | 3.5191 | 0.5111 |
| 0.0001 | 24.0 | 648 | 3.5572 | 0.5111 |
| 0.0001 | 25.0 | 675 | 3.5826 | 0.5333 |
| 0.0001 | 26.0 | 702 | 3.6119 | 0.5333 |
| 0.0001 | 27.0 | 729 | 3.6375 | 0.5333 |
| 0.0 | 28.0 | 756 | 3.6635 | 0.5333 |
| 0.0 | 29.0 | 783 | 3.6928 | 0.5333 |
| 0.0 | 30.0 | 810 | 3.7145 | 0.5333 |
| 0.0 | 31.0 | 837 | 3.7399 | 0.5333 |
| 0.0 | 32.0 | 864 | 3.7653 | 0.5333 |
| 0.0 | 33.0 | 891 | 3.7908 | 0.5333 |
| 0.0 | 34.0 | 918 | 3.8148 | 0.5333 |
| 0.0 | 35.0 | 945 | 3.8372 | 0.5333 |
| 0.0 | 36.0 | 972 | 3.8570 | 0.5333 |
| 0.0 | 37.0 | 999 | 3.8804 | 0.5333 |
| 0.0 | 38.0 | 1026 | 3.9044 | 0.5333 |
| 0.0 | 39.0 | 1053 | 3.9261 | 0.5333 |
| 0.0 | 40.0 | 1080 | 3.9442 | 0.5333 |
| 0.0 | 41.0 | 1107 | 3.9608 | 0.5333 |
| 0.0 | 42.0 | 1134 | 3.9774 | 0.5333 |
| 0.0 | 43.0 | 1161 | 3.9927 | 0.5333 |
| 0.0 | 44.0 | 1188 | 4.0067 | 0.5333 |
| 0.0 | 45.0 | 1215 | 4.0181 | 0.5333 |
| 0.0 | 46.0 | 1242 | 4.0275 | 0.5333 |
| 0.0 | 47.0 | 1269 | 4.0337 | 0.5333 |
| 0.0 | 48.0 | 1296 | 4.0359 | 0.5333 |
| 0.0 | 49.0 | 1323 | 4.0359 | 0.5333 |
| 0.0 | 50.0 | 1350 | 4.0359 | 0.5333 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0