metadata
license: apache-2.0
base_model: facebook/convnextv2-base-22k-384
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: convnext-base-1e-5
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: 0.9412698412698413
convnext-base-1e-5
This model is a fine-tuned version of facebook/convnextv2-base-22k-384 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2330
- Accuracy: 0.9413
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: 1e-05
- train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.6315 | 1.0 | 1099 | 0.4615 | 0.8827 |
| 0.4379 | 2.0 | 2198 | 0.3370 | 0.9042 |
| 0.334 | 3.0 | 3297 | 0.2732 | 0.9264 |
| 0.2928 | 4.0 | 4396 | 0.2441 | 0.9300 |
| 0.2626 | 5.0 | 5495 | 0.2476 | 0.9308 |
| 0.2611 | 6.0 | 6594 | 0.2387 | 0.9380 |
| 0.2312 | 7.0 | 7693 | 0.2326 | 0.9396 |
| 0.18 | 8.0 | 8792 | 0.2283 | 0.9380 |
| 0.198 | 9.0 | 9891 | 0.2280 | 0.9380 |
| 0.164 | 10.0 | 10990 | 0.2279 | 0.9376 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2