orpo_opt2_hh_helpful

This model is a fine-tuned version of facebook/opt-2.7b on the None dataset.

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: 8e-06
• train_batch_size: 3
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 12
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 150
• num_epochs: 2.0

Training results

Framework versions

• PEFT 0.10.0
• Transformers 4.42.0
• Pytorch 2.4.0+cu121
• Datasets 2.15.0
• Tokenizers 0.19.1