aishanur/HVD_Deberta_Large_Upsampled

Human Value Detection Deberta Large Upsampled

This model is a fine-tuned version of microsoft/deberta-v3-large on the upsampled training data of the ValueML dataset.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 8
• 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: 0.2
• num_epochs: 4

Framework versions

• Transformers 4.37.2
• Pytorch 2.3.0
• Datasets 2.19.0
• Tokenizers 0.15.1