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: 0.0395
- Accuracy: 0.9881
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: 7
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.1337 | 1.0 | 190 | 0.1359 | 0.9663 |
0.0644 | 2.0 | 380 | 0.0814 | 0.9767 |
0.0544 | 3.0 | 570 | 0.0509 | 0.9863 |
0.0621 | 4.0 | 760 | 0.0457 | 0.9859 |
0.0335 | 5.0 | 950 | 0.0395 | 0.9881 |
0.0326 | 6.0 | 1140 | 0.0407 | 0.9870 |
0.0174 | 7.0 | 1330 | 0.0380 | 0.9881 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.0
- Downloads last month
- 195
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for diegola123/convnext-tiny-224-finetuned-eurosat-albumentations
Base model
facebook/convnext-tiny-224