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-8-4e-5-erasing
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: 0.95
convnext-base-wd1e-8-4e-5-erasing
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: 0.2174
- Accuracy: 0.95
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: 4e-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 |
|---|---|---|---|---|
| 0.6036 | 1.0 | 1099 | 0.3737 | 0.8930 |
| 0.4997 | 2.0 | 2198 | 0.2730 | 0.9249 |
| 0.3663 | 3.0 | 3297 | 0.2666 | 0.9260 |
| 0.3176 | 4.0 | 4396 | 0.2380 | 0.9392 |
| 0.305 | 5.0 | 5495 | 0.2458 | 0.9372 |
| 0.2489 | 6.0 | 6594 | 0.2389 | 0.9459 |
| 0.2356 | 7.0 | 7693 | 0.2424 | 0.9451 |
| 0.1678 | 8.0 | 8792 | 0.2369 | 0.9439 |
| 0.1565 | 9.0 | 9891 | 0.2323 | 0.9499 |
| 0.1643 | 10.0 | 10990 | 0.2306 | 0.9503 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2