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-15ep
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: 0.942063492063492
convnext-base-15ep
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: 0.3165
- Accuracy: 0.9421
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: 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: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5717 | 1.0 | 1099 | 0.4616 | 0.8573 |
| 0.4653 | 2.0 | 2198 | 0.3607 | 0.8970 |
| 0.3449 | 3.0 | 3297 | 0.4104 | 0.8950 |
| 0.3522 | 4.0 | 4396 | 0.3755 | 0.9026 |
| 0.28 | 5.0 | 5495 | 0.3756 | 0.9066 |
| 0.2456 | 6.0 | 6594 | 0.3496 | 0.9173 |
| 0.2141 | 7.0 | 7693 | 0.3612 | 0.9201 |
| 0.1458 | 8.0 | 8792 | 0.3391 | 0.9304 |
| 0.1842 | 9.0 | 9891 | 0.3353 | 0.9328 |
| 0.1037 | 10.0 | 10990 | 0.3383 | 0.9356 |
| 0.0747 | 11.0 | 12089 | 0.3345 | 0.9368 |
| 0.0912 | 12.0 | 13188 | 0.3244 | 0.9392 |
| 0.0733 | 13.0 | 14287 | 0.3219 | 0.9408 |
| 0.0667 | 14.0 | 15386 | 0.3190 | 0.9435 |
| 0.0694 | 15.0 | 16485 | 0.3192 | 0.9431 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2