superb_ks_42

• Loss: 843.9398
• Accuracy: 0.6199
• Test Accuracy: 0.6199
• Df Accuracy: 0.1369
• Unlearn Overall Accuracy: 0.7415
• Unlearn Time: 1613.1965

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 5e-05
• train_batch_size: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 2.5

Training results

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu118
• Datasets 2.18.0
• Tokenizers 0.15.2