metadata
license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: smids_10x_deit_base_adamax_00001_fold2
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: 0.8901830282861897
smids_10x_deit_base_adamax_00001_fold2
This model is a fine-tuned version of facebook/deit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.8741
- Accuracy: 0.8902
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 |
---|---|---|---|---|
0.216 | 1.0 | 750 | 0.2934 | 0.8852 |
0.1089 | 2.0 | 1500 | 0.3003 | 0.8885 |
0.0954 | 3.0 | 2250 | 0.3369 | 0.8852 |
0.0518 | 4.0 | 3000 | 0.4029 | 0.8902 |
0.0792 | 5.0 | 3750 | 0.4723 | 0.8819 |
0.0261 | 6.0 | 4500 | 0.5460 | 0.8885 |
0.0158 | 7.0 | 5250 | 0.6663 | 0.8819 |
0.0057 | 8.0 | 6000 | 0.6585 | 0.8802 |
0.0002 | 9.0 | 6750 | 0.6982 | 0.8918 |
0.0006 | 10.0 | 7500 | 0.7734 | 0.8918 |
0.0 | 11.0 | 8250 | 0.7967 | 0.8852 |
0.0 | 12.0 | 9000 | 0.8312 | 0.8885 |
0.0001 | 13.0 | 9750 | 0.7897 | 0.8869 |
0.0 | 14.0 | 10500 | 0.8305 | 0.8885 |
0.0 | 15.0 | 11250 | 0.7993 | 0.8869 |
0.0 | 16.0 | 12000 | 0.8582 | 0.8835 |
0.0 | 17.0 | 12750 | 0.8331 | 0.8902 |
0.0 | 18.0 | 13500 | 0.8238 | 0.8952 |
0.0 | 19.0 | 14250 | 0.8345 | 0.8952 |
0.0 | 20.0 | 15000 | 0.8413 | 0.8885 |
0.0 | 21.0 | 15750 | 0.8573 | 0.8918 |
0.0085 | 22.0 | 16500 | 0.8363 | 0.8918 |
0.005 | 23.0 | 17250 | 0.8431 | 0.8885 |
0.0 | 24.0 | 18000 | 0.8537 | 0.8902 |
0.0 | 25.0 | 18750 | 0.8479 | 0.8918 |
0.0 | 26.0 | 19500 | 0.8197 | 0.8869 |
0.0098 | 27.0 | 20250 | 0.8247 | 0.8869 |
0.0 | 28.0 | 21000 | 0.8273 | 0.8885 |
0.0 | 29.0 | 21750 | 0.8481 | 0.8918 |
0.0 | 30.0 | 22500 | 0.8486 | 0.8885 |
0.0 | 31.0 | 23250 | 0.8913 | 0.8935 |
0.0 | 32.0 | 24000 | 0.8769 | 0.8918 |
0.0 | 33.0 | 24750 | 0.8699 | 0.8885 |
0.0 | 34.0 | 25500 | 0.8861 | 0.8935 |
0.0 | 35.0 | 26250 | 0.8555 | 0.8852 |
0.0 | 36.0 | 27000 | 0.8657 | 0.8918 |
0.0099 | 37.0 | 27750 | 0.8602 | 0.8902 |
0.0 | 38.0 | 28500 | 0.8913 | 0.8918 |
0.0 | 39.0 | 29250 | 0.8649 | 0.8885 |
0.0 | 40.0 | 30000 | 0.8620 | 0.8885 |
0.0 | 41.0 | 30750 | 0.8685 | 0.8885 |
0.0 | 42.0 | 31500 | 0.8731 | 0.8902 |
0.0 | 43.0 | 32250 | 0.8772 | 0.8902 |
0.0 | 44.0 | 33000 | 0.8742 | 0.8902 |
0.0026 | 45.0 | 33750 | 0.8773 | 0.8902 |
0.0 | 46.0 | 34500 | 0.8745 | 0.8902 |
0.0 | 47.0 | 35250 | 0.8728 | 0.8885 |
0.0 | 48.0 | 36000 | 0.8716 | 0.8885 |
0.0 | 49.0 | 36750 | 0.8740 | 0.8885 |
0.0 | 50.0 | 37500 | 0.8741 | 0.8902 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2