metadata
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_1x_deit_tiny_rms_lr00001_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: 0.6888888888888889
hushem_1x_deit_tiny_rms_lr00001_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: 1.1351
- Accuracy: 0.6889
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: 1e-05
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 6 | 1.2498 | 0.4444 |
| 1.3042 | 2.0 | 12 | 1.0549 | 0.6222 |
| 1.3042 | 3.0 | 18 | 1.0499 | 0.6444 |
| 0.513 | 4.0 | 24 | 1.0344 | 0.6444 |
| 0.1791 | 5.0 | 30 | 1.0697 | 0.5333 |
| 0.1791 | 6.0 | 36 | 1.0207 | 0.6889 |
| 0.0528 | 7.0 | 42 | 0.9620 | 0.6889 |
| 0.0528 | 8.0 | 48 | 1.0015 | 0.6444 |
| 0.0178 | 9.0 | 54 | 0.9911 | 0.6667 |
| 0.0068 | 10.0 | 60 | 1.0253 | 0.6667 |
| 0.0068 | 11.0 | 66 | 1.0141 | 0.6889 |
| 0.0039 | 12.0 | 72 | 1.0366 | 0.6444 |
| 0.0039 | 13.0 | 78 | 1.0348 | 0.6889 |
| 0.0028 | 14.0 | 84 | 1.0325 | 0.6889 |
| 0.0023 | 15.0 | 90 | 1.0525 | 0.6889 |
| 0.0023 | 16.0 | 96 | 1.0555 | 0.6889 |
| 0.0019 | 17.0 | 102 | 1.0728 | 0.6667 |
| 0.0019 | 18.0 | 108 | 1.0773 | 0.6889 |
| 0.0016 | 19.0 | 114 | 1.0791 | 0.6667 |
| 0.0014 | 20.0 | 120 | 1.0906 | 0.6667 |
| 0.0014 | 21.0 | 126 | 1.0852 | 0.6889 |
| 0.0013 | 22.0 | 132 | 1.0885 | 0.7111 |
| 0.0013 | 23.0 | 138 | 1.1009 | 0.6889 |
| 0.0012 | 24.0 | 144 | 1.1078 | 0.6889 |
| 0.001 | 25.0 | 150 | 1.1057 | 0.7111 |
| 0.001 | 26.0 | 156 | 1.1088 | 0.7111 |
| 0.001 | 27.0 | 162 | 1.1100 | 0.7111 |
| 0.001 | 28.0 | 168 | 1.1174 | 0.6889 |
| 0.0009 | 29.0 | 174 | 1.1173 | 0.6889 |
| 0.0009 | 30.0 | 180 | 1.1217 | 0.6889 |
| 0.0009 | 31.0 | 186 | 1.1218 | 0.6889 |
| 0.0008 | 32.0 | 192 | 1.1230 | 0.6889 |
| 0.0008 | 33.0 | 198 | 1.1264 | 0.6889 |
| 0.0008 | 34.0 | 204 | 1.1266 | 0.6889 |
| 0.0008 | 35.0 | 210 | 1.1281 | 0.6889 |
| 0.0008 | 36.0 | 216 | 1.1299 | 0.6889 |
| 0.0007 | 37.0 | 222 | 1.1316 | 0.6889 |
| 0.0007 | 38.0 | 228 | 1.1339 | 0.6889 |
| 0.0007 | 39.0 | 234 | 1.1344 | 0.6889 |
| 0.0007 | 40.0 | 240 | 1.1349 | 0.6889 |
| 0.0007 | 41.0 | 246 | 1.1350 | 0.6889 |
| 0.0007 | 42.0 | 252 | 1.1351 | 0.6889 |
| 0.0007 | 43.0 | 258 | 1.1351 | 0.6889 |
| 0.0007 | 44.0 | 264 | 1.1351 | 0.6889 |
| 0.0007 | 45.0 | 270 | 1.1351 | 0.6889 |
| 0.0007 | 46.0 | 276 | 1.1351 | 0.6889 |
| 0.0007 | 47.0 | 282 | 1.1351 | 0.6889 |
| 0.0007 | 48.0 | 288 | 1.1351 | 0.6889 |
| 0.0007 | 49.0 | 294 | 1.1351 | 0.6889 |
| 0.0007 | 50.0 | 300 | 1.1351 | 0.6889 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1