poison-distill-ViT

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

• Loss: -53.3057
• Accuracy: 0.7218

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
-13.7561	1.0	130	-15.7562	0.5789
-20.5455	2.0	260	-18.6536	0.6165
-25.3189	3.0	390	-28.8659	0.6241
-32.4562	4.0	520	-31.9035	0.5940
-37.0539	5.0	650	-40.0929	0.7068
-43.0244	6.0	780	-41.5399	0.6466
-46.1567	7.0	910	-47.8440	0.6692
-51.1963	8.0	1040	-51.4154	0.6692
-54.7388	9.0	1170	-53.5994	0.7293
-56.1867	10.0	1300	-53.2331	0.7293

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3