convnext-tiny-224-finetuned-eurosat-att-auto
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: 0.5076
- Accuracy: 0.9506
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.5583 | 0.97 | 23 | 1.6008 | 0.7160 |
1.2953 | 1.97 | 46 | 1.2957 | 0.7531 |
0.9488 | 2.97 | 69 | 1.0720 | 0.8148 |
0.7036 | 3.97 | 92 | 0.8965 | 0.8642 |
0.5446 | 4.97 | 115 | 0.7574 | 0.9383 |
0.4113 | 5.97 | 138 | 0.6522 | 0.9383 |
0.2259 | 6.97 | 161 | 0.5720 | 0.9383 |
0.1863 | 7.97 | 184 | 0.5076 | 0.9506 |
0.1443 | 8.97 | 207 | 0.4795 | 0.9383 |
0.1289 | 9.97 | 230 | 0.4685 | 0.9383 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.