metadata
license: apache-2.0
base_model: facebook/convnext-tiny-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: convnext-tiny-224-finetuned-eurosat-albumentations
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.6366906474820144
convnext-tiny-224-finetuned-eurosat-albumentations
This model is a fine-tuned version of facebook/convnext-tiny-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.8091
- Accuracy: 0.6367
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-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1311 | 0.96 | 19 | 1.0751 | 0.3813 |
| 1.0477 | 1.97 | 39 | 1.0354 | 0.5036 |
| 0.9932 | 2.99 | 59 | 1.0054 | 0.5144 |
| 0.9445 | 4.0 | 79 | 0.9702 | 0.5432 |
| 0.8911 | 4.96 | 98 | 0.9461 | 0.5647 |
| 0.8339 | 5.97 | 118 | 0.9079 | 0.5827 |
| 0.7923 | 6.99 | 138 | 0.8767 | 0.5899 |
| 0.751 | 8.0 | 158 | 0.8521 | 0.6187 |
| 0.7222 | 8.96 | 177 | 0.8315 | 0.6223 |
| 0.688 | 9.97 | 197 | 0.8183 | 0.6259 |
| 0.6734 | 10.99 | 217 | 0.8091 | 0.6367 |
| 0.6734 | 11.54 | 228 | 0.8090 | 0.6331 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2