dinov2-finetuned-har

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

• Loss: 0.3078
• Accuracy: 0.9148

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9429	0.9910	83	0.5624	0.8328
0.7912	1.9940	167	0.4755	0.8587
0.7371	2.9970	251	0.4584	0.8550
0.5915	4.0	335	0.3870	0.8762
0.5635	4.9910	418	0.4037	0.8704
0.498	5.9940	502	0.3876	0.8804
0.4541	6.9970	586	0.3612	0.8884
0.3513	8.0	670	0.3240	0.9053
0.2963	8.9910	753	0.3176	0.9116
0.2815	9.9104	830	0.3078	0.9148

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1