metadata
license: apache-2.0
base_model: facebook/convnext-tiny-224
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: akram-convNeXt-flipkarts
results: []
akram-convNeXt-flipkarts
This model is a fine-tuned version of facebook/convnext-tiny-224 on the flipkarts_images dataset. It achieves the following results on the evaluation set:
- Loss: 0.4581
- Accuracy: 0.8734
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.3777 | 0.57 | 32 | 0.5409 | 0.8228 |
| 0.131 | 1.14 | 64 | 0.5633 | 0.8418 |
| 0.1426 | 1.71 | 96 | 0.5171 | 0.8291 |
| 0.2413 | 2.29 | 128 | 0.4775 | 0.8608 |
| 0.1852 | 2.86 | 160 | 0.4648 | 0.8608 |
| 0.2165 | 3.43 | 192 | 0.4581 | 0.8734 |
| 0.1529 | 4.0 | 224 | 0.4617 | 0.8734 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2