metadata
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_40x_deit_tiny_rms_0001_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: 0.6666666666666666
hushem_40x_deit_tiny_rms_0001_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: 4.3313
- Accuracy: 0.6667
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 |
|---|---|---|---|---|
| 0.1374 | 1.0 | 215 | 1.3718 | 0.7111 |
| 0.0248 | 2.0 | 430 | 1.5033 | 0.7778 |
| 0.0726 | 3.0 | 645 | 1.7295 | 0.7556 |
| 0.0372 | 4.0 | 860 | 1.5869 | 0.7778 |
| 0.0411 | 5.0 | 1075 | 1.1809 | 0.7778 |
| 0.0235 | 6.0 | 1290 | 2.1699 | 0.6889 |
| 0.0004 | 7.0 | 1505 | 1.8564 | 0.7333 |
| 0.0351 | 8.0 | 1720 | 2.6913 | 0.5556 |
| 0.0436 | 9.0 | 1935 | 1.7899 | 0.6889 |
| 0.0311 | 10.0 | 2150 | 2.2763 | 0.7333 |
| 0.0318 | 11.0 | 2365 | 2.1440 | 0.7111 |
| 0.0601 | 12.0 | 2580 | 1.3738 | 0.8 |
| 0.0036 | 13.0 | 2795 | 1.9492 | 0.7556 |
| 0.0024 | 14.0 | 3010 | 2.0010 | 0.7778 |
| 0.0119 | 15.0 | 3225 | 2.9477 | 0.7111 |
| 0.0001 | 16.0 | 3440 | 2.0050 | 0.8222 |
| 0.0 | 17.0 | 3655 | 2.2043 | 0.7778 |
| 0.0045 | 18.0 | 3870 | 2.9253 | 0.6889 |
| 0.0002 | 19.0 | 4085 | 2.4235 | 0.7333 |
| 0.0 | 20.0 | 4300 | 3.4852 | 0.6 |
| 0.0276 | 21.0 | 4515 | 3.0762 | 0.6667 |
| 0.0098 | 22.0 | 4730 | 3.3340 | 0.6222 |
| 0.0328 | 23.0 | 4945 | 1.8687 | 0.8 |
| 0.0 | 24.0 | 5160 | 1.6806 | 0.8 |
| 0.0 | 25.0 | 5375 | 2.3408 | 0.7333 |
| 0.0208 | 26.0 | 5590 | 2.3251 | 0.7778 |
| 0.0 | 27.0 | 5805 | 2.8347 | 0.7111 |
| 0.0 | 28.0 | 6020 | 2.2742 | 0.7333 |
| 0.0 | 29.0 | 6235 | 2.4267 | 0.7111 |
| 0.0 | 30.0 | 6450 | 2.5951 | 0.7111 |
| 0.0 | 31.0 | 6665 | 2.7772 | 0.6889 |
| 0.0 | 32.0 | 6880 | 2.9769 | 0.6889 |
| 0.0 | 33.0 | 7095 | 3.1694 | 0.6889 |
| 0.0 | 34.0 | 7310 | 3.3770 | 0.6889 |
| 0.0 | 35.0 | 7525 | 3.5369 | 0.6889 |
| 0.0 | 36.0 | 7740 | 3.6892 | 0.7111 |
| 0.0 | 37.0 | 7955 | 3.8241 | 0.6889 |
| 0.0 | 38.0 | 8170 | 3.9473 | 0.6889 |
| 0.0 | 39.0 | 8385 | 4.0424 | 0.6889 |
| 0.0 | 40.0 | 8600 | 4.1157 | 0.6889 |
| 0.0 | 41.0 | 8815 | 4.1738 | 0.6667 |
| 0.0 | 42.0 | 9030 | 4.2155 | 0.6667 |
| 0.0 | 43.0 | 9245 | 4.2470 | 0.6667 |
| 0.0 | 44.0 | 9460 | 4.2729 | 0.6667 |
| 0.0 | 45.0 | 9675 | 4.2929 | 0.6667 |
| 0.0 | 46.0 | 9890 | 4.3080 | 0.6667 |
| 0.0 | 47.0 | 10105 | 4.3190 | 0.6667 |
| 0.0 | 48.0 | 10320 | 4.3263 | 0.6667 |
| 0.0 | 49.0 | 10535 | 4.3304 | 0.6667 |
| 0.0 | 50.0 | 10750 | 4.3313 | 0.6667 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.1+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2