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_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_5x_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: 0.8418
- 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 |
|---|---|---|---|---|
| 1.4959 | 1.0 | 28 | 1.3943 | 0.2439 |
| 1.4016 | 2.0 | 56 | 1.1344 | 0.4146 |
| 0.8658 | 3.0 | 84 | 0.7965 | 0.7073 |
| 0.4771 | 4.0 | 112 | 0.8323 | 0.7073 |
| 0.2251 | 5.0 | 140 | 0.3450 | 0.8537 |
| 0.161 | 6.0 | 168 | 1.1238 | 0.5854 |
| 0.122 | 7.0 | 196 | 0.5699 | 0.8780 |
| 0.0493 | 8.0 | 224 | 1.1342 | 0.6585 |
| 0.0526 | 9.0 | 252 | 1.0124 | 0.8293 |
| 0.0543 | 10.0 | 280 | 1.4922 | 0.8537 |
| 0.0179 | 11.0 | 308 | 0.4348 | 0.9024 |
| 0.001 | 12.0 | 336 | 0.7229 | 0.8293 |
| 0.0002 | 13.0 | 364 | 0.6260 | 0.8780 |
| 0.0001 | 14.0 | 392 | 0.6381 | 0.8780 |
| 0.0001 | 15.0 | 420 | 0.6479 | 0.8780 |
| 0.0001 | 16.0 | 448 | 0.6572 | 0.8780 |
| 0.0001 | 17.0 | 476 | 0.6669 | 0.8780 |
| 0.0 | 18.0 | 504 | 0.6750 | 0.8780 |
| 0.0 | 19.0 | 532 | 0.6816 | 0.8780 |
| 0.0 | 20.0 | 560 | 0.6897 | 0.8780 |
| 0.0 | 21.0 | 588 | 0.6973 | 0.8780 |
| 0.0 | 22.0 | 616 | 0.7042 | 0.8780 |
| 0.0 | 23.0 | 644 | 0.7114 | 0.8780 |
| 0.0 | 24.0 | 672 | 0.7182 | 0.8780 |
| 0.0 | 25.0 | 700 | 0.7246 | 0.8780 |
| 0.0 | 26.0 | 728 | 0.7318 | 0.8780 |
| 0.0 | 27.0 | 756 | 0.7392 | 0.8780 |
| 0.0 | 28.0 | 784 | 0.7454 | 0.8780 |
| 0.0 | 29.0 | 812 | 0.7524 | 0.8780 |
| 0.0 | 30.0 | 840 | 0.7588 | 0.8780 |
| 0.0 | 31.0 | 868 | 0.7650 | 0.8780 |
| 0.0 | 32.0 | 896 | 0.7711 | 0.8780 |
| 0.0 | 33.0 | 924 | 0.7761 | 0.8780 |
| 0.0 | 34.0 | 952 | 0.7832 | 0.8780 |
| 0.0 | 35.0 | 980 | 0.7888 | 0.8780 |
| 0.0 | 36.0 | 1008 | 0.7948 | 0.8780 |
| 0.0 | 37.0 | 1036 | 0.8020 | 0.8780 |
| 0.0 | 38.0 | 1064 | 0.8075 | 0.8780 |
| 0.0 | 39.0 | 1092 | 0.8124 | 0.8780 |
| 0.0 | 40.0 | 1120 | 0.8170 | 0.8780 |
| 0.0 | 41.0 | 1148 | 0.8223 | 0.8780 |
| 0.0 | 42.0 | 1176 | 0.8266 | 0.8780 |
| 0.0 | 43.0 | 1204 | 0.8300 | 0.8780 |
| 0.0 | 44.0 | 1232 | 0.8327 | 0.8780 |
| 0.0 | 45.0 | 1260 | 0.8359 | 0.8780 |
| 0.0 | 46.0 | 1288 | 0.8390 | 0.8780 |
| 0.0 | 47.0 | 1316 | 0.8409 | 0.8780 |
| 0.0 | 48.0 | 1344 | 0.8418 | 0.8780 |
| 0.0 | 49.0 | 1372 | 0.8418 | 0.8780 |
| 0.0 | 50.0 | 1400 | 0.8418 | 0.8780 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0