metadata
license: apache-2.0
base_model: facebook/convnextv2-nano-22k-384
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: convnext-nano-new-1e-4
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: 0.9333333333333333
convnext-nano-new-1e-4
This model is a fine-tuned version of facebook/convnextv2-nano-22k-384 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2467
- Accuracy: 0.9333
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: 0.0001
- 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 |
|---|---|---|---|---|
| 0.8703 | 1.0 | 550 | 0.5359 | 0.8473 |
| 0.6685 | 2.0 | 1100 | 0.4169 | 0.8855 |
| 0.5564 | 3.0 | 1650 | 0.3499 | 0.9042 |
| 0.4515 | 4.0 | 2200 | 0.3165 | 0.9141 |
| 0.442 | 5.0 | 2750 | 0.3228 | 0.9082 |
| 0.3799 | 6.0 | 3300 | 0.3089 | 0.9157 |
| 0.3311 | 7.0 | 3850 | 0.2746 | 0.9252 |
| 0.2726 | 8.0 | 4400 | 0.2689 | 0.9249 |
| 0.2711 | 9.0 | 4950 | 0.2651 | 0.9276 |
| 0.2758 | 10.0 | 5500 | 0.2618 | 0.9308 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2