eurosat-vit – AI Model by Ganymede981 | AlphaNeural AI

You can deploy this model and start earning money today!

Ganymede981/
eurosat-vit

like

0

google/vit-base-patch16-224

Views

No views yet

eurosat-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: 0.8229
Accuracy: 0.6739
F1 Macro: 0.6681
F1 Weighted: 0.6750

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: 3e-05
train_batch_size: 256
eval_batch_size: 256
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.06
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Weighted
1.9476	1.0	64	1.8809	0.2202	0.1833	0.1900
1.4137	2.0	128	1.4084	0.4454	0.4195	0.4281
0.8344	3.0	192	0.9926	0.6043	0.5952	0.6031
0.3992	4.0	256	0.8452	0.6620	0.6547	0.6615
0.3652	5.0	320	0.8229	0.6739	0.6681	0.6750

Framework versions

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