vit-ena24-clase

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the wonders_md dataset. It achieves the following results on the evaluation set:

• Loss: 0.0467
• Accuracy: 0.9969
• F1: 0.9972

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: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.307	0.2075	100	0.3149	0.9579	0.9619
0.1011	0.4149	200	0.1359	0.9774	0.9794
0.0733	0.6224	300	0.0740	0.9906	0.9916
0.0362	0.8299	400	0.0467	0.9969	0.9972

Framework versions

• Transformers 4.55.0
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.4