• Model creator: https://huggingface.co/NicholasCorrado/
• Original model: https://huggingface.co/NicholasCorrado/uf-rlced-conifer-zephyr-7b-group-dpo-full/

Original model description:

• alignment-handbook
• trl
• dpo
• generated_from_trainer
• trl
• dpo
• generated_from_trainer datasets:
• data/uf_rlced_conifer_ref model-index:
• name: uf-rlced-conifer-zephyr-7b-group-dpo-full results: []

---

uf-rlced-conifer-zephyr-7b-group-dpo-full

• Loss: 0.2881
• Rewards/chosen: -1.5214
• Rewards/rejected: -3.9542
• Rewards/accuracies: 0.8816
• Rewards/margins: 2.4329
• Logps/rejected: -805.5458
• Logps/chosen: -536.7198
• Logits/rejected: 1.7712
• Logits/chosen: 0.6850

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 5e-07
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• total_eval_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 1

Training results

Framework versions

• Transformers 4.44.1
• Pytorch 2.1.2+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1