metadata
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_40x_deit_small_sgd_00001_fold5
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: 0.3170731707317073
hushem_40x_deit_small_sgd_00001_fold5
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: 1.5176
- Accuracy: 0.3171
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 |
|---|---|---|---|---|
| 1.9948 | 1.0 | 220 | 1.7324 | 0.2683 |
| 1.9668 | 2.0 | 440 | 1.7170 | 0.2683 |
| 1.7569 | 3.0 | 660 | 1.7024 | 0.2683 |
| 1.8204 | 4.0 | 880 | 1.6885 | 0.2683 |
| 1.8992 | 5.0 | 1100 | 1.6754 | 0.2683 |
| 1.8203 | 6.0 | 1320 | 1.6629 | 0.2683 |
| 1.8006 | 7.0 | 1540 | 1.6512 | 0.2683 |
| 1.746 | 8.0 | 1760 | 1.6401 | 0.2683 |
| 1.7509 | 9.0 | 1980 | 1.6297 | 0.2683 |
| 1.7973 | 10.0 | 2200 | 1.6200 | 0.2683 |
| 1.7248 | 11.0 | 2420 | 1.6109 | 0.2683 |
| 1.5895 | 12.0 | 2640 | 1.6025 | 0.2683 |
| 1.6708 | 13.0 | 2860 | 1.5947 | 0.2683 |
| 1.5672 | 14.0 | 3080 | 1.5875 | 0.2683 |
| 1.6734 | 15.0 | 3300 | 1.5810 | 0.2683 |
| 1.6377 | 16.0 | 3520 | 1.5749 | 0.2683 |
| 1.5807 | 17.0 | 3740 | 1.5693 | 0.2683 |
| 1.6065 | 18.0 | 3960 | 1.5643 | 0.2439 |
| 1.5952 | 19.0 | 4180 | 1.5597 | 0.2439 |
| 1.6236 | 20.0 | 4400 | 1.5555 | 0.2439 |
| 1.6357 | 21.0 | 4620 | 1.5517 | 0.2439 |
| 1.5866 | 22.0 | 4840 | 1.5483 | 0.2439 |
| 1.546 | 23.0 | 5060 | 1.5451 | 0.2439 |
| 1.5341 | 24.0 | 5280 | 1.5423 | 0.2683 |
| 1.5615 | 25.0 | 5500 | 1.5397 | 0.2683 |
| 1.5768 | 26.0 | 5720 | 1.5373 | 0.2683 |
| 1.5024 | 27.0 | 5940 | 1.5352 | 0.2683 |
| 1.5377 | 28.0 | 6160 | 1.5332 | 0.2683 |
| 1.5225 | 29.0 | 6380 | 1.5314 | 0.2683 |
| 1.5464 | 30.0 | 6600 | 1.5298 | 0.2683 |
| 1.5869 | 31.0 | 6820 | 1.5284 | 0.2683 |
| 1.5384 | 32.0 | 7040 | 1.5270 | 0.2683 |
| 1.5241 | 33.0 | 7260 | 1.5258 | 0.2683 |
| 1.5029 | 34.0 | 7480 | 1.5247 | 0.2683 |
| 1.4813 | 35.0 | 7700 | 1.5237 | 0.2927 |
| 1.4892 | 36.0 | 7920 | 1.5227 | 0.2927 |
| 1.5014 | 37.0 | 8140 | 1.5219 | 0.2927 |
| 1.5037 | 38.0 | 8360 | 1.5212 | 0.2927 |
| 1.4775 | 39.0 | 8580 | 1.5205 | 0.2927 |
| 1.4967 | 40.0 | 8800 | 1.5200 | 0.2927 |
| 1.4438 | 41.0 | 9020 | 1.5195 | 0.2927 |
| 1.4692 | 42.0 | 9240 | 1.5190 | 0.2927 |
| 1.5023 | 43.0 | 9460 | 1.5187 | 0.2927 |
| 1.4883 | 44.0 | 9680 | 1.5184 | 0.2927 |
| 1.4515 | 45.0 | 9900 | 1.5181 | 0.2927 |
| 1.4741 | 46.0 | 10120 | 1.5179 | 0.3171 |
| 1.4857 | 47.0 | 10340 | 1.5178 | 0.3171 |
| 1.4547 | 48.0 | 10560 | 1.5177 | 0.3171 |
| 1.45 | 49.0 | 10780 | 1.5176 | 0.3171 |
| 1.5056 | 50.0 | 11000 | 1.5176 | 0.3171 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2