|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- image_folder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: Har_Finetuned-ViT-Hybrid_ |
|
results: |
|
- task: |
|
name: Image Classification |
|
type: image-classification |
|
dataset: |
|
name: image_folder |
|
type: image_folder |
|
config: har |
|
split: train |
|
args: har |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.8984126984126984 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# Har_Finetuned-ViT-Hybrid_ |
|
|
|
This model is a fine-tuned version of [google/vit-hybrid-base-bit-384](https://huggingface.co/google/vit-hybrid-base-bit-384) on the image_folder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3252 |
|
- Accuracy: 0.8984 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 6 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.7647 | 1.0 | 167 | 0.4917 | 0.8550 | |
|
| 0.6376 | 2.0 | 334 | 0.3634 | 0.8820 | |
|
| 0.5051 | 3.0 | 501 | 0.3346 | 0.8915 | |
|
| 0.3472 | 4.0 | 668 | 0.3280 | 0.8979 | |
|
| 0.2982 | 5.0 | 835 | 0.3252 | 0.8984 | |
|
| 0.319 | 6.0 | 1002 | 0.3216 | 0.8979 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.0 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.13.2 |
|
|
