|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: distill-beans-vit-224-to-mobile-net-v2 |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# distill-beans-vit-224-to-mobile-net-v2 |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the beans dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4060 |
|
- Accuracy: 0.72 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.7502 | 1.0 | 50 | 0.5091 | 0.71 | |
|
| 0.5833 | 2.0 | 100 | 0.4521 | 0.71 | |
|
| 0.5376 | 3.0 | 150 | 0.5489 | 0.71 | |
|
| 0.5283 | 4.0 | 200 | 0.4060 | 0.72 | |
|
| 0.5164 | 5.0 | 250 | 0.4413 | 0.7 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
