metadata
license: apache-2.0
base_model: facebook/deit-small-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: smids_5x_deit_tiny_adamax_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: 0.8752079866888519
smids_5x_deit_tiny_adamax_0001_fold2
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: 1.2333
- Accuracy: 0.8752
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 |
|---|---|---|---|---|
| 0.2658 | 1.0 | 375 | 0.3487 | 0.8686 |
| 0.2056 | 2.0 | 750 | 0.3572 | 0.8802 |
| 0.1091 | 3.0 | 1125 | 0.4053 | 0.8785 |
| 0.0803 | 4.0 | 1500 | 0.6864 | 0.8636 |
| 0.0671 | 5.0 | 1875 | 0.6967 | 0.8702 |
| 0.0046 | 6.0 | 2250 | 0.8951 | 0.8636 |
| 0.0027 | 7.0 | 2625 | 0.7926 | 0.8852 |
| 0.0005 | 8.0 | 3000 | 0.7839 | 0.8769 |
| 0.0002 | 9.0 | 3375 | 0.8871 | 0.8869 |
| 0.0002 | 10.0 | 3750 | 0.8009 | 0.8968 |
| 0.0097 | 11.0 | 4125 | 0.9981 | 0.8669 |
| 0.0006 | 12.0 | 4500 | 1.0041 | 0.8719 |
| 0.01 | 13.0 | 4875 | 0.9204 | 0.8735 |
| 0.0001 | 14.0 | 5250 | 0.9628 | 0.8785 |
| 0.036 | 15.0 | 5625 | 0.9459 | 0.8752 |
| 0.0001 | 16.0 | 6000 | 0.9812 | 0.8819 |
| 0.0022 | 17.0 | 6375 | 0.9724 | 0.8819 |
| 0.004 | 18.0 | 6750 | 1.0660 | 0.8769 |
| 0.0 | 19.0 | 7125 | 0.9857 | 0.8719 |
| 0.0 | 20.0 | 7500 | 1.0524 | 0.8752 |
| 0.0 | 21.0 | 7875 | 1.0663 | 0.8686 |
| 0.0 | 22.0 | 8250 | 1.1115 | 0.8686 |
| 0.0 | 23.0 | 8625 | 1.0536 | 0.8752 |
| 0.0 | 24.0 | 9000 | 1.0776 | 0.8719 |
| 0.0 | 25.0 | 9375 | 1.0945 | 0.8686 |
| 0.0 | 26.0 | 9750 | 1.1377 | 0.8802 |
| 0.0 | 27.0 | 10125 | 1.1130 | 0.8735 |
| 0.0 | 28.0 | 10500 | 1.1384 | 0.8735 |
| 0.0 | 29.0 | 10875 | 1.1315 | 0.8769 |
| 0.0 | 30.0 | 11250 | 1.1249 | 0.8752 |
| 0.0037 | 31.0 | 11625 | 1.1445 | 0.8752 |
| 0.0039 | 32.0 | 12000 | 1.1633 | 0.8719 |
| 0.0041 | 33.0 | 12375 | 1.1577 | 0.8785 |
| 0.0 | 34.0 | 12750 | 1.1917 | 0.8686 |
| 0.0 | 35.0 | 13125 | 1.2054 | 0.8702 |
| 0.0 | 36.0 | 13500 | 1.1857 | 0.8735 |
| 0.0 | 37.0 | 13875 | 1.1926 | 0.8719 |
| 0.0 | 38.0 | 14250 | 1.2094 | 0.8719 |
| 0.0 | 39.0 | 14625 | 1.2019 | 0.8769 |
| 0.003 | 40.0 | 15000 | 1.2092 | 0.8752 |
| 0.0 | 41.0 | 15375 | 1.2117 | 0.8769 |
| 0.0026 | 42.0 | 15750 | 1.2195 | 0.8769 |
| 0.0026 | 43.0 | 16125 | 1.2211 | 0.8752 |
| 0.0026 | 44.0 | 16500 | 1.2245 | 0.8769 |
| 0.0024 | 45.0 | 16875 | 1.2259 | 0.8769 |
| 0.0 | 46.0 | 17250 | 1.2293 | 0.8752 |
| 0.0049 | 47.0 | 17625 | 1.2287 | 0.8752 |
| 0.0 | 48.0 | 18000 | 1.2326 | 0.8752 |
| 0.0023 | 49.0 | 18375 | 1.2328 | 0.8752 |
| 0.0024 | 50.0 | 18750 | 1.2333 | 0.8752 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.1+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2