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-wd1e-8-2e-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: 0.946031746031746
convnext-base-wd1e-8-2e-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: 0.2200
- Accuracy: 0.9460
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: 2e-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 |
|---|---|---|---|---|
| 0.6642 | 1.0 | 1099 | 0.3849 | 0.8946 |
| 0.4658 | 2.0 | 2198 | 0.2898 | 0.9165 |
| 0.3675 | 3.0 | 3297 | 0.2496 | 0.9304 |
| 0.3174 | 4.0 | 4396 | 0.2326 | 0.9412 |
| 0.3106 | 5.0 | 5495 | 0.2301 | 0.9435 |
| 0.2678 | 6.0 | 6594 | 0.2303 | 0.9431 |
| 0.2503 | 7.0 | 7693 | 0.2298 | 0.9427 |
| 0.2204 | 8.0 | 8792 | 0.2216 | 0.9459 |
| 0.2013 | 9.0 | 9891 | 0.2224 | 0.9463 |
| 0.1808 | 10.0 | 10990 | 0.2207 | 0.9467 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2