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_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: 0.24390243902439024
hushem_5x_deit_tiny_sgd_00001_fold5
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: 1.7062
- Accuracy: 0.2439
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 |
|---|---|---|---|---|
| 1.53 | 1.0 | 28 | 1.7652 | 0.2439 |
| 1.4658 | 2.0 | 56 | 1.7625 | 0.2439 |
| 1.4749 | 3.0 | 84 | 1.7598 | 0.2439 |
| 1.4869 | 4.0 | 112 | 1.7572 | 0.2439 |
| 1.4859 | 5.0 | 140 | 1.7548 | 0.2439 |
| 1.5155 | 6.0 | 168 | 1.7523 | 0.2439 |
| 1.4632 | 7.0 | 196 | 1.7499 | 0.2439 |
| 1.4958 | 8.0 | 224 | 1.7475 | 0.2439 |
| 1.538 | 9.0 | 252 | 1.7452 | 0.2439 |
| 1.5008 | 10.0 | 280 | 1.7432 | 0.2439 |
| 1.4793 | 11.0 | 308 | 1.7411 | 0.2439 |
| 1.483 | 12.0 | 336 | 1.7391 | 0.2439 |
| 1.4966 | 13.0 | 364 | 1.7374 | 0.2439 |
| 1.5231 | 14.0 | 392 | 1.7355 | 0.2439 |
| 1.5038 | 15.0 | 420 | 1.7337 | 0.2439 |
| 1.4896 | 16.0 | 448 | 1.7319 | 0.2439 |
| 1.5043 | 17.0 | 476 | 1.7303 | 0.2439 |
| 1.4967 | 18.0 | 504 | 1.7286 | 0.2439 |
| 1.5162 | 19.0 | 532 | 1.7269 | 0.2439 |
| 1.5126 | 20.0 | 560 | 1.7254 | 0.2439 |
| 1.4809 | 21.0 | 588 | 1.7239 | 0.2439 |
| 1.4877 | 22.0 | 616 | 1.7225 | 0.2439 |
| 1.5048 | 23.0 | 644 | 1.7212 | 0.2439 |
| 1.4932 | 24.0 | 672 | 1.7199 | 0.2439 |
| 1.4898 | 25.0 | 700 | 1.7187 | 0.2439 |
| 1.4408 | 26.0 | 728 | 1.7176 | 0.2439 |
| 1.5027 | 27.0 | 756 | 1.7165 | 0.2439 |
| 1.4716 | 28.0 | 784 | 1.7154 | 0.2439 |
| 1.5167 | 29.0 | 812 | 1.7145 | 0.2439 |
| 1.4795 | 30.0 | 840 | 1.7136 | 0.2439 |
| 1.5126 | 31.0 | 868 | 1.7127 | 0.2439 |
| 1.4908 | 32.0 | 896 | 1.7119 | 0.2439 |
| 1.4785 | 33.0 | 924 | 1.7111 | 0.2439 |
| 1.4672 | 34.0 | 952 | 1.7104 | 0.2439 |
| 1.4938 | 35.0 | 980 | 1.7097 | 0.2439 |
| 1.4756 | 36.0 | 1008 | 1.7092 | 0.2439 |
| 1.4385 | 37.0 | 1036 | 1.7087 | 0.2439 |
| 1.5268 | 38.0 | 1064 | 1.7082 | 0.2439 |
| 1.4939 | 39.0 | 1092 | 1.7078 | 0.2439 |
| 1.4888 | 40.0 | 1120 | 1.7074 | 0.2439 |
| 1.4584 | 41.0 | 1148 | 1.7071 | 0.2439 |
| 1.5033 | 42.0 | 1176 | 1.7068 | 0.2439 |
| 1.5098 | 43.0 | 1204 | 1.7066 | 0.2439 |
| 1.485 | 44.0 | 1232 | 1.7064 | 0.2439 |
| 1.4705 | 45.0 | 1260 | 1.7063 | 0.2439 |
| 1.4946 | 46.0 | 1288 | 1.7062 | 0.2439 |
| 1.4654 | 47.0 | 1316 | 1.7062 | 0.2439 |
| 1.5055 | 48.0 | 1344 | 1.7062 | 0.2439 |
| 1.4868 | 49.0 | 1372 | 1.7062 | 0.2439 |
| 1.489 | 50.0 | 1400 | 1.7062 | 0.2439 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0