metadata
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_40x_deit_small_adamax_001_fold3
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: 0.813953488372093
hushem_40x_deit_small_adamax_001_fold3
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: 2.0018
- Accuracy: 0.8140
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 |
|---|---|---|---|---|
| 0.2113 | 1.0 | 217 | 1.0639 | 0.7209 |
| 0.3075 | 2.0 | 434 | 0.6999 | 0.7442 |
| 0.0797 | 3.0 | 651 | 1.4112 | 0.7209 |
| 0.0613 | 4.0 | 868 | 0.8895 | 0.8605 |
| 0.0448 | 5.0 | 1085 | 0.8165 | 0.8140 |
| 0.0133 | 6.0 | 1302 | 1.2281 | 0.7907 |
| 0.0099 | 7.0 | 1519 | 1.6935 | 0.7907 |
| 0.0195 | 8.0 | 1736 | 0.9261 | 0.8837 |
| 0.0441 | 9.0 | 1953 | 0.6136 | 0.8605 |
| 0.0408 | 10.0 | 2170 | 1.0937 | 0.8605 |
| 0.0001 | 11.0 | 2387 | 1.3536 | 0.8372 |
| 0.0014 | 12.0 | 2604 | 1.5056 | 0.8372 |
| 0.0152 | 13.0 | 2821 | 1.3542 | 0.8140 |
| 0.0011 | 14.0 | 3038 | 1.1435 | 0.8140 |
| 0.0006 | 15.0 | 3255 | 1.7874 | 0.7907 |
| 0.0244 | 16.0 | 3472 | 1.5609 | 0.8140 |
| 0.0 | 17.0 | 3689 | 0.9143 | 0.9070 |
| 0.0 | 18.0 | 3906 | 1.3119 | 0.8140 |
| 0.0 | 19.0 | 4123 | 1.5264 | 0.8372 |
| 0.0024 | 20.0 | 4340 | 1.6055 | 0.8140 |
| 0.0 | 21.0 | 4557 | 1.7071 | 0.8140 |
| 0.0 | 22.0 | 4774 | 1.6943 | 0.8140 |
| 0.0 | 23.0 | 4991 | 1.6871 | 0.8140 |
| 0.0 | 24.0 | 5208 | 1.6854 | 0.8140 |
| 0.0 | 25.0 | 5425 | 1.6881 | 0.8140 |
| 0.0 | 26.0 | 5642 | 1.6930 | 0.8140 |
| 0.0 | 27.0 | 5859 | 1.6999 | 0.8140 |
| 0.0 | 28.0 | 6076 | 1.7095 | 0.8140 |
| 0.0 | 29.0 | 6293 | 1.7201 | 0.8140 |
| 0.0 | 30.0 | 6510 | 1.7321 | 0.8140 |
| 0.0 | 31.0 | 6727 | 1.7453 | 0.8140 |
| 0.0 | 32.0 | 6944 | 1.7591 | 0.8140 |
| 0.0 | 33.0 | 7161 | 1.7739 | 0.8140 |
| 0.0 | 34.0 | 7378 | 1.7893 | 0.8140 |
| 0.0 | 35.0 | 7595 | 1.8052 | 0.8140 |
| 0.0 | 36.0 | 7812 | 1.8215 | 0.8140 |
| 0.0 | 37.0 | 8029 | 1.8380 | 0.8140 |
| 0.0 | 38.0 | 8246 | 1.8542 | 0.8140 |
| 0.0 | 39.0 | 8463 | 1.8709 | 0.8140 |
| 0.0 | 40.0 | 8680 | 1.8874 | 0.8140 |
| 0.0 | 41.0 | 8897 | 1.9038 | 0.8140 |
| 0.0 | 42.0 | 9114 | 1.9194 | 0.8140 |
| 0.0 | 43.0 | 9331 | 1.9350 | 0.8140 |
| 0.0 | 44.0 | 9548 | 1.9494 | 0.8140 |
| 0.0 | 45.0 | 9765 | 1.9631 | 0.8140 |
| 0.0 | 46.0 | 9982 | 1.9753 | 0.8140 |
| 0.0 | 47.0 | 10199 | 1.9864 | 0.8140 |
| 0.0 | 48.0 | 10416 | 1.9949 | 0.8140 |
| 0.0 | 49.0 | 10633 | 2.0003 | 0.8140 |
| 0.0 | 50.0 | 10850 | 2.0018 | 0.8140 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2