dinov2-base-finetuned-oxford

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

• Loss: 0.2494
• Accuracy: 0.9275

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.1017	1.0	230	0.5766	0.8152
0.4159	2.0	460	0.4022	0.8727
0.0327	3.0	690	0.2494	0.9275

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1