|
--- |
|
license: apache-2.0 |
|
base_model: microsoft/beit-base-patch16-224 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: smids_3x_beit_base_adamax_00001_fold3 |
|
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: 0.9183333333333333 |
|
--- |
|
|
|
<!-- 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_3x_beit_base_adamax_00001_fold3 |
|
|
|
This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7848 |
|
- Accuracy: 0.9183 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 0.2779 | 1.0 | 375 | 0.3054 | 0.8733 | |
|
| 0.2162 | 2.0 | 750 | 0.2359 | 0.92 | |
|
| 0.1285 | 3.0 | 1125 | 0.2539 | 0.9217 | |
|
| 0.0945 | 4.0 | 1500 | 0.2722 | 0.9233 | |
|
| 0.1011 | 5.0 | 1875 | 0.3075 | 0.92 | |
|
| 0.0628 | 6.0 | 2250 | 0.3567 | 0.9167 | |
|
| 0.0288 | 7.0 | 2625 | 0.3944 | 0.915 | |
|
| 0.0403 | 8.0 | 3000 | 0.4745 | 0.9083 | |
|
| 0.0254 | 9.0 | 3375 | 0.4777 | 0.92 | |
|
| 0.0101 | 10.0 | 3750 | 0.5260 | 0.9233 | |
|
| 0.0079 | 11.0 | 4125 | 0.5710 | 0.92 | |
|
| 0.0161 | 12.0 | 4500 | 0.5888 | 0.915 | |
|
| 0.0114 | 13.0 | 4875 | 0.6115 | 0.92 | |
|
| 0.0178 | 14.0 | 5250 | 0.6193 | 0.915 | |
|
| 0.0098 | 15.0 | 5625 | 0.6503 | 0.9183 | |
|
| 0.0165 | 16.0 | 6000 | 0.6581 | 0.9233 | |
|
| 0.0022 | 17.0 | 6375 | 0.6879 | 0.9217 | |
|
| 0.0225 | 18.0 | 6750 | 0.7059 | 0.92 | |
|
| 0.0007 | 19.0 | 7125 | 0.7568 | 0.9117 | |
|
| 0.0104 | 20.0 | 7500 | 0.6995 | 0.92 | |
|
| 0.0014 | 21.0 | 7875 | 0.7129 | 0.9183 | |
|
| 0.0053 | 22.0 | 8250 | 0.7485 | 0.9133 | |
|
| 0.0549 | 23.0 | 8625 | 0.7098 | 0.9183 | |
|
| 0.0039 | 24.0 | 9000 | 0.7046 | 0.9183 | |
|
| 0.0037 | 25.0 | 9375 | 0.7588 | 0.915 | |
|
| 0.0003 | 26.0 | 9750 | 0.7455 | 0.92 | |
|
| 0.0253 | 27.0 | 10125 | 0.8244 | 0.9033 | |
|
| 0.025 | 28.0 | 10500 | 0.7649 | 0.915 | |
|
| 0.0003 | 29.0 | 10875 | 0.7615 | 0.9183 | |
|
| 0.0276 | 30.0 | 11250 | 0.7366 | 0.92 | |
|
| 0.0005 | 31.0 | 11625 | 0.7763 | 0.915 | |
|
| 0.0305 | 32.0 | 12000 | 0.7932 | 0.91 | |
|
| 0.0001 | 33.0 | 12375 | 0.7611 | 0.9183 | |
|
| 0.0308 | 34.0 | 12750 | 0.7888 | 0.905 | |
|
| 0.0002 | 35.0 | 13125 | 0.7612 | 0.9183 | |
|
| 0.0004 | 36.0 | 13500 | 0.7891 | 0.9167 | |
|
| 0.0001 | 37.0 | 13875 | 0.7612 | 0.9183 | |
|
| 0.0 | 38.0 | 14250 | 0.7623 | 0.9167 | |
|
| 0.0009 | 39.0 | 14625 | 0.7611 | 0.9167 | |
|
| 0.0068 | 40.0 | 15000 | 0.7732 | 0.9167 | |
|
| 0.0008 | 41.0 | 15375 | 0.7647 | 0.92 | |
|
| 0.0059 | 42.0 | 15750 | 0.7690 | 0.915 | |
|
| 0.0001 | 43.0 | 16125 | 0.7709 | 0.92 | |
|
| 0.0042 | 44.0 | 16500 | 0.7831 | 0.9183 | |
|
| 0.0002 | 45.0 | 16875 | 0.7842 | 0.92 | |
|
| 0.0105 | 46.0 | 17250 | 0.7861 | 0.9183 | |
|
| 0.0007 | 47.0 | 17625 | 0.7770 | 0.915 | |
|
| 0.0 | 48.0 | 18000 | 0.7805 | 0.9183 | |
|
| 0.0 | 49.0 | 18375 | 0.7842 | 0.9183 | |
|
| 0.0 | 50.0 | 18750 | 0.7848 | 0.9183 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.2 |
|
|
