Ganymede981/bigearthnet-vit

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

bigearthnet-vit

This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:

• —Loss: 0.0968
• —F1 Micro: 0.6503
• —F1 Macro: 0.2662
• —Map: 0.3291

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: 0.0001
• —trainbatchsize: 512
• —evalbatchsize: 512
• —seed: 42
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: cosinewithrestarts
• —lrschedulerwarmup_steps: 500
• —num_epochs: 2
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —PEFT 0.19.1
• —Transformers 5.8.1
• —Pytorch 2.10.0+cu128
• —Datasets 4.8.5
• —Tokenizers 0.22.2