|
--- |
|
license: apache-2.0 |
|
base_model: facebook/convnextv2-base-22k-384 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- imagefolder |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: convnext-base-5e-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: 0.9376984126984127 |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# convnext-base-5e-5 |
|
|
|
This model is a fine-tuned version of [facebook/convnextv2-base-22k-384](https://huggingface.co/facebook/convnextv2-base-22k-384) on the imagefolder dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2535 |
|
- Accuracy: 0.9377 |
|
|
|
## 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: 5e-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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 0.4987 | 1.0 | 1099 | 0.3869 | 0.8839 | |
|
| 0.3757 | 2.0 | 2198 | 0.3295 | 0.9026 | |
|
| 0.2985 | 3.0 | 3297 | 0.3043 | 0.9193 | |
|
| 0.2535 | 4.0 | 4396 | 0.2558 | 0.9320 | |
|
| 0.1951 | 5.0 | 5495 | 0.2922 | 0.9316 | |
|
| 0.1573 | 6.0 | 6594 | 0.2674 | 0.9376 | |
|
| 0.1432 | 7.0 | 7693 | 0.2857 | 0.9416 | |
|
| 0.1087 | 8.0 | 8792 | 0.2808 | 0.9447 | |
|
| 0.1043 | 9.0 | 9891 | 0.2762 | 0.9475 | |
|
| 0.0757 | 10.0 | 10990 | 0.2755 | 0.9483 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
