poison-distill-vit-imagenet-teacher

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

• Loss: -1.3063
• Accuracy: 0.5038

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
-0.1813	1.0	130	-0.9692	0.5113
-0.3694	2.0	260	-0.9944	0.5263
-0.3258	3.0	390	-1.2729	0.3835
-0.4198	4.0	520	-1.1187	0.5038
-0.5634	5.0	650	-1.3899	0.5338
-0.8886	6.0	780	-0.4891	0.4962
-1.0453	7.0	910	-1.5857	0.4812
-1.5477	8.0	1040	-1.5516	0.4887
-1.5745	9.0	1170	-1.7739	0.4737
-1.7883	10.0	1300	-1.6647	0.4586

Framework versions

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