metadata
license: apache-2.0
base_model: facebook/deit-tiny-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: smids_1x_deit_tiny_sgd_00001_fold3
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: 0.38333333333333336
smids_1x_deit_tiny_sgd_00001_fold3
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: 1.2082
- Accuracy: 0.3833
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 |
|---|---|---|---|---|
| 1.3468 | 1.0 | 75 | 1.3684 | 0.345 |
| 1.2941 | 2.0 | 150 | 1.3595 | 0.3433 |
| 1.2835 | 3.0 | 225 | 1.3508 | 0.3433 |
| 1.3718 | 4.0 | 300 | 1.3426 | 0.345 |
| 1.2334 | 5.0 | 375 | 1.3348 | 0.345 |
| 1.2846 | 6.0 | 450 | 1.3274 | 0.3467 |
| 1.2876 | 7.0 | 525 | 1.3202 | 0.3483 |
| 1.2894 | 8.0 | 600 | 1.3134 | 0.3483 |
| 1.3322 | 9.0 | 675 | 1.3070 | 0.3483 |
| 1.3642 | 10.0 | 750 | 1.3007 | 0.35 |
| 1.2885 | 11.0 | 825 | 1.2947 | 0.3517 |
| 1.2098 | 12.0 | 900 | 1.2891 | 0.3517 |
| 1.2493 | 13.0 | 975 | 1.2838 | 0.35 |
| 1.2305 | 14.0 | 1050 | 1.2787 | 0.3517 |
| 1.2559 | 15.0 | 1125 | 1.2739 | 0.355 |
| 1.216 | 16.0 | 1200 | 1.2692 | 0.3567 |
| 1.2252 | 17.0 | 1275 | 1.2648 | 0.3583 |
| 1.2555 | 18.0 | 1350 | 1.2606 | 0.36 |
| 1.207 | 19.0 | 1425 | 1.2567 | 0.3583 |
| 1.163 | 20.0 | 1500 | 1.2528 | 0.3583 |
| 1.2799 | 21.0 | 1575 | 1.2493 | 0.3617 |
| 1.2576 | 22.0 | 1650 | 1.2460 | 0.3633 |
| 1.259 | 23.0 | 1725 | 1.2428 | 0.3617 |
| 1.2102 | 24.0 | 1800 | 1.2399 | 0.365 |
| 1.206 | 25.0 | 1875 | 1.2370 | 0.3633 |
| 1.2525 | 26.0 | 1950 | 1.2343 | 0.3683 |
| 1.2063 | 27.0 | 2025 | 1.2318 | 0.3683 |
| 1.2191 | 28.0 | 2100 | 1.2294 | 0.3683 |
| 1.2117 | 29.0 | 2175 | 1.2273 | 0.3683 |
| 1.2241 | 30.0 | 2250 | 1.2252 | 0.37 |
| 1.2256 | 31.0 | 2325 | 1.2233 | 0.3733 |
| 1.123 | 32.0 | 2400 | 1.2215 | 0.3767 |
| 1.1778 | 33.0 | 2475 | 1.2198 | 0.3767 |
| 1.2098 | 34.0 | 2550 | 1.2183 | 0.3817 |
| 1.1496 | 35.0 | 2625 | 1.2169 | 0.3783 |
| 1.2108 | 36.0 | 2700 | 1.2156 | 0.3833 |
| 1.2173 | 37.0 | 2775 | 1.2145 | 0.3817 |
| 1.177 | 38.0 | 2850 | 1.2134 | 0.38 |
| 1.1989 | 39.0 | 2925 | 1.2125 | 0.3783 |
| 1.2161 | 40.0 | 3000 | 1.2116 | 0.3783 |
| 1.2506 | 41.0 | 3075 | 1.2109 | 0.3783 |
| 1.2753 | 42.0 | 3150 | 1.2102 | 0.38 |
| 1.215 | 43.0 | 3225 | 1.2097 | 0.38 |
| 1.196 | 44.0 | 3300 | 1.2092 | 0.38 |
| 1.1971 | 45.0 | 3375 | 1.2089 | 0.3817 |
| 1.1869 | 46.0 | 3450 | 1.2086 | 0.3833 |
| 1.1695 | 47.0 | 3525 | 1.2084 | 0.3833 |
| 1.19 | 48.0 | 3600 | 1.2083 | 0.3833 |
| 1.1265 | 49.0 | 3675 | 1.2082 | 0.3833 |
| 1.1801 | 50.0 | 3750 | 1.2082 | 0.3833 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0