99sweetcookie/reasoningshield-dpo-final

stage2_dpo

This model is a fine-tuned version of 99sweetcookie/reasoningshield-sft on the reasoningshield_dpo 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: 2e-06
• train_batch_size: 1
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 128
• total_train_batch_size: 128
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 2.0

Training results

Framework versions

• Transformers 4.57.1
• Pytorch 2.5.1
• Datasets 4.0.0
• Tokenizers 0.22.2