metadata
license: apache-2.0
base_model: facebook/convnextv2-tiny-1k-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: convnext-tiny-upgrade-1k-224-batch-32
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8850894632206759
convnext-tiny-upgrade-1k-224-batch-32
This model is a fine-tuned version of facebook/convnextv2-tiny-1k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.4287
- Accuracy: 0.8851
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: 3e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|---|
| 1.5523 | 1.0 | 550 | 1.2083 | 0.7010 |
| 1.0852 | 2.0 | 1100 | 0.7955 | 0.7960 |
| 0.9179 | 3.0 | 1650 | 0.6425 | 0.8258 |
| 0.7621 | 4.0 | 2200 | 0.5426 | 0.8549 |
| 0.7506 | 5.0 | 2750 | 0.5018 | 0.8624 |
| 0.6774 | 6.0 | 3300 | 0.4792 | 0.8684 |
| 0.6364 | 7.0 | 3850 | 0.4526 | 0.8744 |
| 0.5961 | 8.0 | 4400 | 0.4362 | 0.8799 |
| 0.602 | 9.0 | 4950 | 0.4316 | 0.8827 |
| 0.5896 | 10.0 | 5500 | 0.4287 | 0.8851 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2