convnextv2-base-22k-224-finetuned-eurosat-2

This model is a fine-tuned version of facebook/convnextv2-base-22k-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3801
  • Accuracy: 0.9096

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
0.5227 1.0 99 0.5333 0.7797
0.4248 1.99 198 0.4145 0.8531
0.2998 2.99 297 0.3307 0.8757
0.1704 4.0 397 0.2664 0.8927
0.0684 5.0 496 0.4353 0.8701
0.1546 5.99 595 0.3920 0.8870
0.0593 6.99 694 0.3801 0.9096
0.0745 8.0 794 0.4030 0.8983
0.0877 9.0 893 0.3846 0.9040
0.09 9.97 990 0.3816 0.9040

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.2.0+cu118
  • Datasets 2.17.0
  • Tokenizers 0.15.2
Downloads last month
15
Safetensors
Model size
87.7M params
Tensor type
F32
·
Inference Examples
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.

Model tree for lucnha/convnextv2-base-22k-224-finetuned-eurosat-2

Finetuned
(11)
this model

Evaluation results