metadata
license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_base_rms_00001_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: 0.7333333333333333
hushem_5x_deit_base_rms_00001_fold2
This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.6978
- Accuracy: 0.7333
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 |
|---|---|---|---|---|
| 0.7885 | 1.0 | 27 | 1.0771 | 0.6222 |
| 0.1275 | 2.0 | 54 | 1.2167 | 0.6667 |
| 0.0229 | 3.0 | 81 | 1.0976 | 0.6667 |
| 0.0044 | 4.0 | 108 | 1.1187 | 0.6889 |
| 0.0023 | 5.0 | 135 | 1.1431 | 0.7111 |
| 0.0016 | 6.0 | 162 | 1.1708 | 0.7111 |
| 0.0013 | 7.0 | 189 | 1.2048 | 0.7333 |
| 0.0009 | 8.0 | 216 | 1.2211 | 0.7111 |
| 0.0007 | 9.0 | 243 | 1.2394 | 0.7333 |
| 0.0006 | 10.0 | 270 | 1.2768 | 0.7111 |
| 0.0005 | 11.0 | 297 | 1.2868 | 0.7333 |
| 0.0004 | 12.0 | 324 | 1.2957 | 0.7333 |
| 0.0003 | 13.0 | 351 | 1.3184 | 0.7333 |
| 0.0003 | 14.0 | 378 | 1.3307 | 0.7333 |
| 0.0003 | 15.0 | 405 | 1.3520 | 0.7333 |
| 0.0002 | 16.0 | 432 | 1.3706 | 0.7333 |
| 0.0002 | 17.0 | 459 | 1.3793 | 0.7333 |
| 0.0002 | 18.0 | 486 | 1.3973 | 0.7333 |
| 0.0001 | 19.0 | 513 | 1.4099 | 0.7333 |
| 0.0001 | 20.0 | 540 | 1.4201 | 0.7333 |
| 0.0001 | 21.0 | 567 | 1.4342 | 0.7333 |
| 0.0001 | 22.0 | 594 | 1.4529 | 0.7333 |
| 0.0001 | 23.0 | 621 | 1.4659 | 0.7333 |
| 0.0001 | 24.0 | 648 | 1.4737 | 0.7333 |
| 0.0001 | 25.0 | 675 | 1.4832 | 0.7333 |
| 0.0001 | 26.0 | 702 | 1.5042 | 0.7333 |
| 0.0001 | 27.0 | 729 | 1.5167 | 0.7333 |
| 0.0001 | 28.0 | 756 | 1.5245 | 0.7333 |
| 0.0 | 29.0 | 783 | 1.5454 | 0.7333 |
| 0.0 | 30.0 | 810 | 1.5513 | 0.7333 |
| 0.0 | 31.0 | 837 | 1.5670 | 0.7333 |
| 0.0 | 32.0 | 864 | 1.5721 | 0.7333 |
| 0.0 | 33.0 | 891 | 1.5854 | 0.7333 |
| 0.0 | 34.0 | 918 | 1.5951 | 0.7333 |
| 0.0 | 35.0 | 945 | 1.6025 | 0.7333 |
| 0.0 | 36.0 | 972 | 1.6174 | 0.7333 |
| 0.0 | 37.0 | 999 | 1.6316 | 0.7333 |
| 0.0 | 38.0 | 1026 | 1.6382 | 0.7333 |
| 0.0 | 39.0 | 1053 | 1.6457 | 0.7333 |
| 0.0 | 40.0 | 1080 | 1.6550 | 0.7333 |
| 0.0 | 41.0 | 1107 | 1.6656 | 0.7333 |
| 0.0 | 42.0 | 1134 | 1.6708 | 0.7333 |
| 0.0 | 43.0 | 1161 | 1.6757 | 0.7333 |
| 0.0 | 44.0 | 1188 | 1.6846 | 0.7333 |
| 0.0 | 45.0 | 1215 | 1.6907 | 0.7333 |
| 0.0 | 46.0 | 1242 | 1.6942 | 0.7333 |
| 0.0 | 47.0 | 1269 | 1.6967 | 0.7333 |
| 0.0 | 48.0 | 1296 | 1.6977 | 0.7333 |
| 0.0 | 49.0 | 1323 | 1.6978 | 0.7333 |
| 0.0 | 50.0 | 1350 | 1.6978 | 0.7333 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0