dchen0/font-classifier-v3

dchen0/font-classifier

Merged DINOv2‑base checkpoint with LoRA weights for font classification.

This model is a fine-tuned version of facebook/dinov2-base-imagenet1k-1-layer on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 1.3446824550628662
• Accuracy: 0.5903

Training procedure

Training hyperparameters

The following hyperparameters were used during training: -learning_rate 1e-4 -lora_rank 8 -lora_alpha 16 -lora_dropout 0.1

• train_batch_size: 32
• eval_batch_size: 32
• 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

Framework versions

• PEFT 0.15.2
• Transformers 4.52.4
• Pytorch 2.7.1
• Datasets 3.6.0
• Tokenizers 0.21.1