metadata
license: apache-2.0
base_model: facebook/convnextv2-tiny-22k-384
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: convnext-tiny-new-1e-4-batch-32
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: 0.9404761904761905
convnext-tiny-new-1e-4-batch-32
This model is a fine-tuned version of facebook/convnextv2-tiny-22k-384 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2265
- Accuracy: 0.9405
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 |
|---|---|---|---|---|
| 0.7731 | 1.0 | 550 | 0.4237 | 0.8839 |
| 0.6206 | 2.0 | 1100 | 0.3756 | 0.8930 |
| 0.5014 | 3.0 | 1650 | 0.3272 | 0.9074 |
| 0.3892 | 4.0 | 2200 | 0.2729 | 0.9280 |
| 0.3819 | 5.0 | 2750 | 0.2953 | 0.9205 |
| 0.3315 | 6.0 | 3300 | 0.2784 | 0.9260 |
| 0.281 | 7.0 | 3850 | 0.2535 | 0.9328 |
| 0.217 | 8.0 | 4400 | 0.2498 | 0.9344 |
| 0.2152 | 9.0 | 4950 | 0.2405 | 0.9400 |
| 0.2185 | 10.0 | 5500 | 0.2370 | 0.9400 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2