• Model creator: https://huggingface.co/simonycl/
• Original model: https://huggingface.co/simonycl/llama-3.1-8b-instruct-ultrafeedback-single-judge/

Original model description:

• alignment-handbook
• generated_from_trainer datasets:
• simonycl/llama3.1-ultrafeedback-annotate-single-judge model-index:
• name: llama-3.1-8b-instruct-single-judge results: []

---

llama-3.1-8b-instruct-single-judge

• Loss: 0.6257
• Rewards/chosen: -1.8789
• Rewards/rejected: -2.1780
• Rewards/accuracies: 0.6640
• Rewards/margins: 0.2990
• Logps/rejected: -503.4651
• Logps/chosen: -464.8842
• Logits/rejected: -1.7279
• Logits/chosen: -1.8636

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 5e-07
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 32
• total_train_batch_size: 128
• total_eval_batch_size: 4
• 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 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1