|
--- |
|
license: apache-2.0 |
|
base_model: facebook/convnext-base-224-22k |
|
tags: |
|
- image-classification |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: idbwbase |
|
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. --> |
|
|
|
# idbwbase |
|
|
|
This model is a fine-tuned version of [facebook/convnext-base-224-22k](https://huggingface.co/facebook/convnext-base-224-22k) on the indian_food_images dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0978 |
|
- Accuracy: 0.9741 |
|
|
|
## 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: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 0.373 | 1.0 | 4709 | 0.3002 | 0.8705 | |
|
| 0.3244 | 2.0 | 9418 | 0.2262 | 0.9044 | |
|
| 0.2801 | 3.0 | 14127 | 0.1987 | 0.9196 | |
|
| 0.2366 | 4.0 | 18836 | 0.1788 | 0.9345 | |
|
| 0.2051 | 5.0 | 23545 | 0.1463 | 0.9484 | |
|
| 0.1764 | 6.0 | 28254 | 0.1202 | 0.9593 | |
|
| 0.1595 | 7.0 | 32963 | 0.1243 | 0.9655 | |
|
| 0.1359 | 8.0 | 37672 | 0.1188 | 0.9659 | |
|
| 0.1231 | 9.0 | 42381 | 0.0978 | 0.9741 | |
|
| 0.1162 | 10.0 | 47090 | 0.1001 | 0.9761 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.15.2 |
|
|
