metadata
license: apache-2.0
base_model: facebook/deit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: hushem_40x_deit_base_rms_0001_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: 0.7555555555555555
hushem_40x_deit_base_rms_0001_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: 4.0887
- Accuracy: 0.7556
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 |
|---|---|---|---|---|
| 0.0825 | 1.0 | 215 | 1.5281 | 0.7111 |
| 0.0311 | 2.0 | 430 | 1.2158 | 0.8 |
| 0.0011 | 3.0 | 645 | 1.8306 | 0.6889 |
| 0.0414 | 4.0 | 860 | 2.0416 | 0.7333 |
| 0.0002 | 5.0 | 1075 | 2.3340 | 0.6444 |
| 0.0027 | 6.0 | 1290 | 1.1579 | 0.7556 |
| 0.0001 | 7.0 | 1505 | 2.3412 | 0.6889 |
| 0.0 | 8.0 | 1720 | 2.3885 | 0.7111 |
| 0.0 | 9.0 | 1935 | 2.4917 | 0.7333 |
| 0.0 | 10.0 | 2150 | 2.6169 | 0.7333 |
| 0.0 | 11.0 | 2365 | 2.7660 | 0.7333 |
| 0.0 | 12.0 | 2580 | 2.9176 | 0.7333 |
| 0.0 | 13.0 | 2795 | 3.0652 | 0.7333 |
| 0.0 | 14.0 | 3010 | 3.1998 | 0.7556 |
| 0.0 | 15.0 | 3225 | 3.3068 | 0.7556 |
| 0.0 | 16.0 | 3440 | 3.4034 | 0.7556 |
| 0.0 | 17.0 | 3655 | 3.4958 | 0.7556 |
| 0.0 | 18.0 | 3870 | 3.5902 | 0.7556 |
| 0.0 | 19.0 | 4085 | 3.6748 | 0.7556 |
| 0.0 | 20.0 | 4300 | 3.7449 | 0.7556 |
| 0.0 | 21.0 | 4515 | 3.7990 | 0.7556 |
| 0.0 | 22.0 | 4730 | 3.8408 | 0.7556 |
| 0.0 | 23.0 | 4945 | 3.8743 | 0.7556 |
| 0.0 | 24.0 | 5160 | 3.9017 | 0.7556 |
| 0.0 | 25.0 | 5375 | 3.9247 | 0.7556 |
| 0.0 | 26.0 | 5590 | 3.9444 | 0.7556 |
| 0.0 | 27.0 | 5805 | 3.9616 | 0.7556 |
| 0.0 | 28.0 | 6020 | 3.9766 | 0.7556 |
| 0.0 | 29.0 | 6235 | 3.9899 | 0.7556 |
| 0.0 | 30.0 | 6450 | 4.0018 | 0.7556 |
| 0.0 | 31.0 | 6665 | 4.0124 | 0.7556 |
| 0.0 | 32.0 | 6880 | 4.0219 | 0.7556 |
| 0.0 | 33.0 | 7095 | 4.0305 | 0.7556 |
| 0.0 | 34.0 | 7310 | 4.0382 | 0.7556 |
| 0.0 | 35.0 | 7525 | 4.0452 | 0.7556 |
| 0.0 | 36.0 | 7740 | 4.0514 | 0.7556 |
| 0.0 | 37.0 | 7955 | 4.0571 | 0.7556 |
| 0.0 | 38.0 | 8170 | 4.0622 | 0.7556 |
| 0.0 | 39.0 | 8385 | 4.0668 | 0.7556 |
| 0.0 | 40.0 | 8600 | 4.0708 | 0.7556 |
| 0.0 | 41.0 | 8815 | 4.0744 | 0.7556 |
| 0.0 | 42.0 | 9030 | 4.0776 | 0.7556 |
| 0.0 | 43.0 | 9245 | 4.0803 | 0.7556 |
| 0.0 | 44.0 | 9460 | 4.0826 | 0.7556 |
| 0.0 | 45.0 | 9675 | 4.0846 | 0.7556 |
| 0.0 | 46.0 | 9890 | 4.0861 | 0.7556 |
| 0.0 | 47.0 | 10105 | 4.0873 | 0.7556 |
| 0.0 | 48.0 | 10320 | 4.0881 | 0.7556 |
| 0.0 | 49.0 | 10535 | 4.0886 | 0.7556 |
| 0.0 | 50.0 | 10750 | 4.0887 | 0.7556 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2