|
--- |
|
license: apache-2.0 |
|
base_model: facebook/deit-base-patch16-224 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: smids_5x_deit_base_rms_00001_fold1 |
|
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: 0.9098497495826378 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# smids_5x_deit_base_rms_00001_fold1 |
|
|
|
This model is a fine-tuned version of [facebook/deit-base-patch16-224](https://huggingface.co/facebook/deit-base-patch16-224) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7394 |
|
- Accuracy: 0.9098 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 0.1851 | 1.0 | 376 | 0.2437 | 0.8998 | |
|
| 0.1172 | 2.0 | 752 | 0.2452 | 0.9065 | |
|
| 0.078 | 3.0 | 1128 | 0.3051 | 0.9032 | |
|
| 0.0038 | 4.0 | 1504 | 0.3755 | 0.9149 | |
|
| 0.0013 | 5.0 | 1880 | 0.4803 | 0.9048 | |
|
| 0.0105 | 6.0 | 2256 | 0.5332 | 0.8948 | |
|
| 0.0008 | 7.0 | 2632 | 0.5088 | 0.9015 | |
|
| 0.0133 | 8.0 | 3008 | 0.5291 | 0.9149 | |
|
| 0.0349 | 9.0 | 3384 | 0.6409 | 0.9048 | |
|
| 0.0001 | 10.0 | 3760 | 0.6103 | 0.8998 | |
|
| 0.0039 | 11.0 | 4136 | 0.6150 | 0.9065 | |
|
| 0.0005 | 12.0 | 4512 | 0.7088 | 0.8948 | |
|
| 0.0 | 13.0 | 4888 | 0.6260 | 0.8965 | |
|
| 0.0213 | 14.0 | 5264 | 0.6512 | 0.9065 | |
|
| 0.0001 | 15.0 | 5640 | 0.6705 | 0.8965 | |
|
| 0.0 | 16.0 | 6016 | 0.6402 | 0.9098 | |
|
| 0.0 | 17.0 | 6392 | 0.7356 | 0.9015 | |
|
| 0.0 | 18.0 | 6768 | 0.6866 | 0.8932 | |
|
| 0.0035 | 19.0 | 7144 | 0.7211 | 0.8982 | |
|
| 0.0098 | 20.0 | 7520 | 0.7353 | 0.8982 | |
|
| 0.0 | 21.0 | 7896 | 0.7497 | 0.9032 | |
|
| 0.0001 | 22.0 | 8272 | 0.7881 | 0.9015 | |
|
| 0.0 | 23.0 | 8648 | 0.7075 | 0.9065 | |
|
| 0.0 | 24.0 | 9024 | 0.8340 | 0.8948 | |
|
| 0.0 | 25.0 | 9400 | 0.8050 | 0.9032 | |
|
| 0.0028 | 26.0 | 9776 | 0.7114 | 0.8982 | |
|
| 0.0 | 27.0 | 10152 | 0.6978 | 0.9048 | |
|
| 0.0 | 28.0 | 10528 | 0.7140 | 0.9032 | |
|
| 0.0032 | 29.0 | 10904 | 0.6871 | 0.9098 | |
|
| 0.0032 | 30.0 | 11280 | 0.7619 | 0.9032 | |
|
| 0.0 | 31.0 | 11656 | 0.7031 | 0.9082 | |
|
| 0.0 | 32.0 | 12032 | 0.7126 | 0.9082 | |
|
| 0.0 | 33.0 | 12408 | 0.7501 | 0.9082 | |
|
| 0.0 | 34.0 | 12784 | 0.7212 | 0.9149 | |
|
| 0.0 | 35.0 | 13160 | 0.7433 | 0.9098 | |
|
| 0.0 | 36.0 | 13536 | 0.7330 | 0.9132 | |
|
| 0.0 | 37.0 | 13912 | 0.7531 | 0.9065 | |
|
| 0.0 | 38.0 | 14288 | 0.7193 | 0.9098 | |
|
| 0.0 | 39.0 | 14664 | 0.7113 | 0.9132 | |
|
| 0.0 | 40.0 | 15040 | 0.7484 | 0.9149 | |
|
| 0.0 | 41.0 | 15416 | 0.7482 | 0.9132 | |
|
| 0.0 | 42.0 | 15792 | 0.7262 | 0.9132 | |
|
| 0.0 | 43.0 | 16168 | 0.7432 | 0.9149 | |
|
| 0.0 | 44.0 | 16544 | 0.7418 | 0.9149 | |
|
| 0.0 | 45.0 | 16920 | 0.7350 | 0.9115 | |
|
| 0.0025 | 46.0 | 17296 | 0.7363 | 0.9115 | |
|
| 0.0 | 47.0 | 17672 | 0.7386 | 0.9098 | |
|
| 0.0 | 48.0 | 18048 | 0.7382 | 0.9098 | |
|
| 0.0 | 49.0 | 18424 | 0.7382 | 0.9098 | |
|
| 0.0023 | 50.0 | 18800 | 0.7394 | 0.9098 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.2 |
|
|