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_fold5
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: 0.8780487804878049
hushem_40x_deit_tiny_rms_0001_fold5
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: 0.8832
- Accuracy: 0.8780
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 |
|---|---|---|---|---|
| 0.1509 | 1.0 | 220 | 0.5608 | 0.8537 |
| 0.0292 | 2.0 | 440 | 0.1504 | 0.9512 |
| 0.1009 | 3.0 | 660 | 0.7468 | 0.8537 |
| 0.011 | 4.0 | 880 | 0.6340 | 0.7805 |
| 0.0031 | 5.0 | 1100 | 0.8446 | 0.8293 |
| 0.0646 | 6.0 | 1320 | 1.0420 | 0.8537 |
| 0.0678 | 7.0 | 1540 | 0.6521 | 0.8293 |
| 0.0002 | 8.0 | 1760 | 1.1011 | 0.8537 |
| 0.0677 | 9.0 | 1980 | 1.2605 | 0.8049 |
| 0.0002 | 10.0 | 2200 | 0.4029 | 0.9024 |
| 0.0011 | 11.0 | 2420 | 0.5279 | 0.9512 |
| 0.0002 | 12.0 | 2640 | 0.5883 | 0.9268 |
| 0.0801 | 13.0 | 2860 | 1.0161 | 0.8293 |
| 0.0 | 14.0 | 3080 | 0.7618 | 0.9024 |
| 0.0 | 15.0 | 3300 | 0.7876 | 0.8293 |
| 0.0144 | 16.0 | 3520 | 0.6802 | 0.8780 |
| 0.0032 | 17.0 | 3740 | 0.2440 | 0.9268 |
| 0.0 | 18.0 | 3960 | 0.4384 | 0.8293 |
| 0.0 | 19.0 | 4180 | 0.6787 | 0.8537 |
| 0.0 | 20.0 | 4400 | 0.6527 | 0.8293 |
| 0.0 | 21.0 | 4620 | 0.6512 | 0.8537 |
| 0.0 | 22.0 | 4840 | 0.6749 | 0.8537 |
| 0.0 | 23.0 | 5060 | 0.6838 | 0.8537 |
| 0.0 | 24.0 | 5280 | 0.7554 | 0.8537 |
| 0.0 | 25.0 | 5500 | 0.8097 | 0.8780 |
| 0.0 | 26.0 | 5720 | 0.8183 | 0.8780 |
| 0.0 | 27.0 | 5940 | 0.8490 | 0.8780 |
| 0.0 | 28.0 | 6160 | 0.9053 | 0.8537 |
| 0.0 | 29.0 | 6380 | 0.9213 | 0.8537 |
| 0.0 | 30.0 | 6600 | 0.9237 | 0.8780 |
| 0.0 | 31.0 | 6820 | 0.9293 | 0.8537 |
| 0.0 | 32.0 | 7040 | 0.9309 | 0.8780 |
| 0.0 | 33.0 | 7260 | 0.9345 | 0.8780 |
| 0.0 | 34.0 | 7480 | 0.9273 | 0.8780 |
| 0.0 | 35.0 | 7700 | 0.9432 | 0.8780 |
| 0.0 | 36.0 | 7920 | 0.9371 | 0.8780 |
| 0.0 | 37.0 | 8140 | 0.9224 | 0.9024 |
| 0.0 | 38.0 | 8360 | 0.9410 | 0.8780 |
| 0.0 | 39.0 | 8580 | 0.9241 | 0.8780 |
| 0.0 | 40.0 | 8800 | 0.9144 | 0.8780 |
| 0.0 | 41.0 | 9020 | 0.9167 | 0.8780 |
| 0.0 | 42.0 | 9240 | 0.8992 | 0.8780 |
| 0.0 | 43.0 | 9460 | 0.9050 | 0.8780 |
| 0.0 | 44.0 | 9680 | 0.8956 | 0.8780 |
| 0.0 | 45.0 | 9900 | 0.8902 | 0.8780 |
| 0.0 | 46.0 | 10120 | 0.8925 | 0.8780 |
| 0.0 | 47.0 | 10340 | 0.8847 | 0.8780 |
| 0.0 | 48.0 | 10560 | 0.8839 | 0.8780 |
| 0.0 | 49.0 | 10780 | 0.8833 | 0.8780 |
| 0.0 | 50.0 | 11000 | 0.8832 | 0.8780 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.1+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2