got-model

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

• Loss: nan
• Accuracy: 0.0952
• F1: 0.0166

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.0	1.0	42	nan	0.0952	0.0166
0.0	2.0	84	nan	0.0952	0.0166
0.0	3.0	126	nan	0.0952	0.0166
0.0	4.0	168	nan	0.0952	0.0166
0.0	5.0	210	nan	0.0952	0.0166
0.0	6.0	252	nan	0.0952	0.0166
0.0	7.0	294	nan	0.0952	0.0166
0.0	8.0	336	nan	0.0952	0.0166
0.0	9.0	378	nan	0.0952	0.0166
0.0	10.0	420	nan	0.0952	0.0166

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.20.3