metadata
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_5x_deit_small_rms_0001_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: 0.8372093023255814
hushem_5x_deit_small_rms_0001_fold3
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: 1.8513
- Accuracy: 0.8372
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 |
|---|---|---|---|---|
| 1.4647 | 1.0 | 28 | 1.8602 | 0.2558 |
| 1.3185 | 2.0 | 56 | 1.0840 | 0.4884 |
| 0.9898 | 3.0 | 84 | 1.3302 | 0.3721 |
| 0.9442 | 4.0 | 112 | 1.0743 | 0.5349 |
| 0.6714 | 5.0 | 140 | 1.1638 | 0.5814 |
| 0.5907 | 6.0 | 168 | 0.8481 | 0.7442 |
| 0.3843 | 7.0 | 196 | 0.5582 | 0.7907 |
| 0.2836 | 8.0 | 224 | 0.9826 | 0.6977 |
| 0.163 | 9.0 | 252 | 0.9953 | 0.7907 |
| 0.0747 | 10.0 | 280 | 0.9182 | 0.8140 |
| 0.0702 | 11.0 | 308 | 0.8756 | 0.7907 |
| 0.0697 | 12.0 | 336 | 1.2367 | 0.7907 |
| 0.0531 | 13.0 | 364 | 1.5496 | 0.7442 |
| 0.0055 | 14.0 | 392 | 1.2182 | 0.8140 |
| 0.0148 | 15.0 | 420 | 1.4816 | 0.8140 |
| 0.0259 | 16.0 | 448 | 1.3748 | 0.7907 |
| 0.0208 | 17.0 | 476 | 1.5049 | 0.7209 |
| 0.0278 | 18.0 | 504 | 1.1689 | 0.8140 |
| 0.0002 | 19.0 | 532 | 1.6137 | 0.8372 |
| 0.0001 | 20.0 | 560 | 1.6368 | 0.8372 |
| 0.0 | 21.0 | 588 | 1.6426 | 0.8372 |
| 0.0 | 22.0 | 616 | 1.6498 | 0.8372 |
| 0.0 | 23.0 | 644 | 1.6573 | 0.8372 |
| 0.0 | 24.0 | 672 | 1.6654 | 0.8372 |
| 0.0 | 25.0 | 700 | 1.6746 | 0.8372 |
| 0.0 | 26.0 | 728 | 1.6832 | 0.8372 |
| 0.0 | 27.0 | 756 | 1.6985 | 0.8372 |
| 0.0 | 28.0 | 784 | 1.7057 | 0.8372 |
| 0.0 | 29.0 | 812 | 1.7143 | 0.8372 |
| 0.0 | 30.0 | 840 | 1.7226 | 0.8372 |
| 0.0 | 31.0 | 868 | 1.7340 | 0.8372 |
| 0.0 | 32.0 | 896 | 1.7422 | 0.8372 |
| 0.0 | 33.0 | 924 | 1.7506 | 0.8372 |
| 0.0 | 34.0 | 952 | 1.7590 | 0.8372 |
| 0.0 | 35.0 | 980 | 1.7673 | 0.8372 |
| 0.0 | 36.0 | 1008 | 1.7761 | 0.8372 |
| 0.0 | 37.0 | 1036 | 1.7852 | 0.8372 |
| 0.0 | 38.0 | 1064 | 1.7939 | 0.8372 |
| 0.0 | 39.0 | 1092 | 1.8014 | 0.8372 |
| 0.0 | 40.0 | 1120 | 1.8097 | 0.8372 |
| 0.0 | 41.0 | 1148 | 1.8172 | 0.8372 |
| 0.0 | 42.0 | 1176 | 1.8240 | 0.8372 |
| 0.0 | 43.0 | 1204 | 1.8302 | 0.8372 |
| 0.0 | 44.0 | 1232 | 1.8365 | 0.8372 |
| 0.0 | 45.0 | 1260 | 1.8414 | 0.8372 |
| 0.0 | 46.0 | 1288 | 1.8453 | 0.8372 |
| 0.0 | 47.0 | 1316 | 1.8499 | 0.8372 |
| 0.0 | 48.0 | 1344 | 1.8512 | 0.8372 |
| 0.0 | 49.0 | 1372 | 1.8513 | 0.8372 |
| 0.0 | 50.0 | 1400 | 1.8513 | 0.8372 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0