metadata
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_1x_deit_small_sgd_001_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: 0.4666666666666667
hushem_1x_deit_small_sgd_001_fold1
This model is a fine-tuned version of facebook/deit-small-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.2536
- Accuracy: 0.4667
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: 0.001
- 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 | 1.3733 | 0.3778 |
| 1.5546 | 2.0 | 12 | 1.3601 | 0.4 |
| 1.5546 | 3.0 | 18 | 1.3490 | 0.4222 |
| 1.5316 | 4.0 | 24 | 1.3414 | 0.4222 |
| 1.4864 | 5.0 | 30 | 1.3332 | 0.4222 |
| 1.4864 | 6.0 | 36 | 1.3258 | 0.4222 |
| 1.4723 | 7.0 | 42 | 1.3198 | 0.4222 |
| 1.4723 | 8.0 | 48 | 1.3148 | 0.4 |
| 1.4485 | 9.0 | 54 | 1.3096 | 0.4 |
| 1.4339 | 10.0 | 60 | 1.3042 | 0.4 |
| 1.4339 | 11.0 | 66 | 1.3005 | 0.4222 |
| 1.4182 | 12.0 | 72 | 1.2965 | 0.4222 |
| 1.4182 | 13.0 | 78 | 1.2931 | 0.4 |
| 1.3944 | 14.0 | 84 | 1.2902 | 0.4222 |
| 1.3955 | 15.0 | 90 | 1.2868 | 0.4444 |
| 1.3955 | 16.0 | 96 | 1.2841 | 0.4444 |
| 1.3685 | 17.0 | 102 | 1.2813 | 0.4444 |
| 1.3685 | 18.0 | 108 | 1.2791 | 0.4444 |
| 1.351 | 19.0 | 114 | 1.2769 | 0.4444 |
| 1.3583 | 20.0 | 120 | 1.2750 | 0.4667 |
| 1.3583 | 21.0 | 126 | 1.2734 | 0.4444 |
| 1.3432 | 22.0 | 132 | 1.2719 | 0.4444 |
| 1.3432 | 23.0 | 138 | 1.2696 | 0.4444 |
| 1.3309 | 24.0 | 144 | 1.2677 | 0.4444 |
| 1.3166 | 25.0 | 150 | 1.2667 | 0.4444 |
| 1.3166 | 26.0 | 156 | 1.2651 | 0.4667 |
| 1.3168 | 27.0 | 162 | 1.2639 | 0.4667 |
| 1.3168 | 28.0 | 168 | 1.2624 | 0.4667 |
| 1.3102 | 29.0 | 174 | 1.2615 | 0.4667 |
| 1.3034 | 30.0 | 180 | 1.2602 | 0.4667 |
| 1.3034 | 31.0 | 186 | 1.2590 | 0.4667 |
| 1.3106 | 32.0 | 192 | 1.2580 | 0.4667 |
| 1.3106 | 33.0 | 198 | 1.2570 | 0.4667 |
| 1.2903 | 34.0 | 204 | 1.2562 | 0.4667 |
| 1.2915 | 35.0 | 210 | 1.2554 | 0.4667 |
| 1.2915 | 36.0 | 216 | 1.2549 | 0.4667 |
| 1.2913 | 37.0 | 222 | 1.2546 | 0.4667 |
| 1.2913 | 38.0 | 228 | 1.2542 | 0.4667 |
| 1.2715 | 39.0 | 234 | 1.2539 | 0.4667 |
| 1.2929 | 40.0 | 240 | 1.2538 | 0.4667 |
| 1.2929 | 41.0 | 246 | 1.2537 | 0.4667 |
| 1.2815 | 42.0 | 252 | 1.2536 | 0.4667 |
| 1.2815 | 43.0 | 258 | 1.2536 | 0.4667 |
| 1.2834 | 44.0 | 264 | 1.2536 | 0.4667 |
| 1.2687 | 45.0 | 270 | 1.2536 | 0.4667 |
| 1.2687 | 46.0 | 276 | 1.2536 | 0.4667 |
| 1.2845 | 47.0 | 282 | 1.2536 | 0.4667 |
| 1.2845 | 48.0 | 288 | 1.2536 | 0.4667 |
| 1.2639 | 49.0 | 294 | 1.2536 | 0.4667 |
| 1.2911 | 50.0 | 300 | 1.2536 | 0.4667 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1