dinov2-base-finetuned-lora-EA-rank8

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: 0.4365
• Accuracy: 0.8233

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: 0.0001
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 1024
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.7805	2	0.5030	0.8142
No log	1.9512	5	0.4567	0.8215
No log	2.7317	7	0.4511	0.8215
0.4811	3.9024	10	0.4438	0.8179
0.4811	4.6829	12	0.4392	0.8215
0.4811	5.8537	15	0.4379	0.8452
0.4811	6.6341	17	0.4365	0.8233

Framework versions

• Transformers 4.41.1
• Pytorch 2.1.2
• Datasets 2.19.1
• Tokenizers 0.19.1