metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: convnextv2-tiny-22k-224-finetuned-eurosat-50
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: Augmented-Final
split: train
args: Augmented-Final
metrics:
- name: Accuracy
type: accuracy
value: 0.8273381294964028
convnextv2-tiny-22k-224-finetuned-eurosat-50
This model is a fine-tuned version of facebook/convnextv2-tiny-22k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.5332
- Accuracy: 0.8273
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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.9
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0127 | 1.0 | 122 | 1.9838 | 0.1942 |
| 1.8499 | 2.0 | 244 | 1.8667 | 0.2456 |
| 1.8024 | 3.0 | 366 | 1.7247 | 0.3792 |
| 1.5952 | 4.0 | 488 | 1.5540 | 0.4861 |
| 1.3867 | 5.0 | 610 | 1.3568 | 0.5550 |
| 1.1846 | 6.0 | 732 | 1.1521 | 0.6372 |
| 1.0063 | 7.0 | 854 | 0.9649 | 0.6824 |
| 0.8932 | 8.0 | 976 | 0.8284 | 0.7307 |
| 0.7576 | 9.0 | 1098 | 0.7217 | 0.7780 |
| 0.6742 | 10.0 | 1220 | 0.6412 | 0.7924 |
| 0.6398 | 11.0 | 1342 | 0.5679 | 0.8160 |
| 0.6243 | 12.0 | 1464 | 0.5332 | 0.8273 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3