metadata
license: apache-2.0
base_model: facebook/convnextv2-nano-22k-384
tags:
- image-classification
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: convnext-1e-4
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: vuongnhathien/30VNFoods
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8924603174603175
convnext-1e-4
This model is a fine-tuned version of facebook/convnextv2-nano-22k-384 on the vuongnhathien/30VNFoods dataset. It achieves the following results on the evaluation set:
- Loss: 0.3889
- Accuracy: 0.8925
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: 0.0001
- train_batch_size: 64
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5769 | 1.0 | 275 | 0.4599 | 0.8684 |
| 0.2542 | 2.0 | 550 | 0.3875 | 0.8903 |
| 0.1075 | 3.0 | 825 | 0.4022 | 0.8946 |
| 0.0477 | 4.0 | 1100 | 0.4013 | 0.9046 |
| 0.0187 | 5.0 | 1375 | 0.4537 | 0.8958 |
| 0.0152 | 6.0 | 1650 | 0.4501 | 0.9026 |
| 0.0057 | 7.0 | 1925 | 0.4219 | 0.9105 |
| 0.0052 | 8.0 | 2200 | 0.4239 | 0.9149 |
| 0.0019 | 9.0 | 2475 | 0.4242 | 0.9145 |
| 0.0028 | 10.0 | 2750 | 0.4244 | 0.9149 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2