dinov2-base-MEG4-6

This model is a fine-tuned version of facebook/dinov2-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.4166
• Accuracy: 0.8107

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: 4
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.1517	1.0000	11596	1.0708	0.7685
0.1411	2.0000	23192	0.9791	0.7985
0.0951	2.9999	34788	1.2306	0.8006
0.0602	4.0	46385	1.1623	0.7970
0.0314	5.0000	57981	1.4054	0.8065
0.0233	5.9999	69576	1.4166	0.8107

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1