poison-distill-vit-lowperf-teacher

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

• Loss: -147.2981
• Accuracy: 0.6692

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
-41.2606	1.0	130	-56.4288	0.4511
-63.2817	2.0	260	-71.5028	0.5940
-79.4609	3.0	390	-89.7701	0.5714
-95.0787	4.0	520	-104.8132	0.6241
-108.1566	5.0	650	-113.9035	0.6090
-119.6772	6.0	780	-127.5839	0.6090
-128.6957	7.0	910	-135.8344	0.5865
-135.677	8.0	1040	-141.0722	0.5564
-140.7586	9.0	1170	-145.1082	0.6466
-143.6635	10.0	1300	-147.5504	0.6617

Framework versions

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