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_fold1
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: 0.6444444444444445
hushem_5x_deit_tiny_rms_0001_fold1
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: 2.7423
- Accuracy: 0.6444
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 |
|---|---|---|---|---|
| 1.4819 | 1.0 | 27 | 1.3858 | 0.4222 |
| 1.2591 | 2.0 | 54 | 1.5267 | 0.3556 |
| 0.7593 | 3.0 | 81 | 1.2907 | 0.4667 |
| 0.5581 | 4.0 | 108 | 1.8771 | 0.5111 |
| 0.2708 | 5.0 | 135 | 1.1107 | 0.6 |
| 0.0918 | 6.0 | 162 | 1.6349 | 0.6 |
| 0.0815 | 7.0 | 189 | 1.8415 | 0.5556 |
| 0.0759 | 8.0 | 216 | 2.0598 | 0.5778 |
| 0.0537 | 9.0 | 243 | 1.9632 | 0.6222 |
| 0.0015 | 10.0 | 270 | 1.8818 | 0.6444 |
| 0.0003 | 11.0 | 297 | 2.0815 | 0.6222 |
| 0.0001 | 12.0 | 324 | 2.0650 | 0.6444 |
| 0.0001 | 13.0 | 351 | 2.0989 | 0.6444 |
| 0.0001 | 14.0 | 378 | 2.1289 | 0.6444 |
| 0.0001 | 15.0 | 405 | 2.1588 | 0.6444 |
| 0.0001 | 16.0 | 432 | 2.1838 | 0.6222 |
| 0.0001 | 17.0 | 459 | 2.2142 | 0.6444 |
| 0.0 | 18.0 | 486 | 2.2371 | 0.6444 |
| 0.0 | 19.0 | 513 | 2.2604 | 0.6444 |
| 0.0 | 20.0 | 540 | 2.2825 | 0.6444 |
| 0.0 | 21.0 | 567 | 2.3034 | 0.6444 |
| 0.0 | 22.0 | 594 | 2.3271 | 0.6444 |
| 0.0 | 23.0 | 621 | 2.3489 | 0.6444 |
| 0.0 | 24.0 | 648 | 2.3707 | 0.6444 |
| 0.0 | 25.0 | 675 | 2.3919 | 0.6444 |
| 0.0 | 26.0 | 702 | 2.4064 | 0.6444 |
| 0.0 | 27.0 | 729 | 2.4258 | 0.6444 |
| 0.0 | 28.0 | 756 | 2.4479 | 0.6444 |
| 0.0 | 29.0 | 783 | 2.4665 | 0.6444 |
| 0.0 | 30.0 | 810 | 2.4872 | 0.6444 |
| 0.0 | 31.0 | 837 | 2.5073 | 0.6444 |
| 0.0 | 32.0 | 864 | 2.5259 | 0.6444 |
| 0.0 | 33.0 | 891 | 2.5455 | 0.6444 |
| 0.0 | 34.0 | 918 | 2.5641 | 0.6444 |
| 0.0 | 35.0 | 945 | 2.5817 | 0.6444 |
| 0.0 | 36.0 | 972 | 2.6001 | 0.6444 |
| 0.0 | 37.0 | 999 | 2.6164 | 0.6444 |
| 0.0 | 38.0 | 1026 | 2.6335 | 0.6444 |
| 0.0 | 39.0 | 1053 | 2.6484 | 0.6444 |
| 0.0 | 40.0 | 1080 | 2.6642 | 0.6444 |
| 0.0 | 41.0 | 1107 | 2.6789 | 0.6444 |
| 0.0 | 42.0 | 1134 | 2.6927 | 0.6444 |
| 0.0 | 43.0 | 1161 | 2.7058 | 0.6444 |
| 0.0 | 44.0 | 1188 | 2.7171 | 0.6444 |
| 0.0 | 45.0 | 1215 | 2.7264 | 0.6444 |
| 0.0 | 46.0 | 1242 | 2.7343 | 0.6444 |
| 0.0 | 47.0 | 1269 | 2.7400 | 0.6444 |
| 0.0 | 48.0 | 1296 | 2.7423 | 0.6444 |
| 0.0 | 49.0 | 1323 | 2.7423 | 0.6444 |
| 0.0 | 50.0 | 1350 | 2.7423 | 0.6444 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0