|
--- |
|
license: apache-2.0 |
|
base_model: google/efficientnet-b1 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: efficientnet_b1-food101 |
|
results: [] |
|
datasets: |
|
- food101 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# efficientnet_b1-food101 |
|
|
|
This model is a fine-tuned version of [google/efficientnet-b1](https://huggingface.co/google/efficientnet-b1) on [food101](https://huggingface.co/datasets/food101) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0490 |
|
- Accuracy: 0.9947 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 47 | 4.3674 | 0.1548 | |
|
| No log | 2.0 | 94 | 3.1870 | 0.8915 | |
|
| No log | 3.0 | 141 | 0.8758 | 0.9751 | |
|
| No log | 4.0 | 188 | 0.1010 | 0.9858 | |
|
| No log | 5.0 | 235 | 0.0503 | 0.9893 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
