headlight_12_12_2024_google_vit-base-patch16-224-in21k

This model is a fine-tuned version of ArtiSikhwal/headlight_11_12_2024_google_vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.2587
• Accuracy: 0.9015

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: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 512
• optimizer: Use 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: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.9995	492	0.2682	0.8973
0.1998	1.9990	984	0.2701	0.8982
0.1988	2.9985	1476	0.2708	0.8974
0.1976	4.0	1969	0.2609	0.9013
0.2131	4.9995	2461	0.2584	0.9011
0.2169	5.9970	2952	0.2587	0.9015

Framework versions

• Transformers 4.46.3
• Pytorch 2.4.0
• Datasets 3.1.0
• Tokenizers 0.20.3