tinyllama-1.1b-chat-v1.0-hh-dpo

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-Chat-v1.0 on the HuggingFaceH4/hh-rlhf-h4 dataset. It achieves the following results on the evaluation set:

• Loss: 0.6732
• Rewards/chosen: -0.5129
• Rewards/rejected: -0.5655
• Rewards/accuracies: 0.5578
• Rewards/margins: 0.0526
• Logps/rejected: -214.5289
• Logps/chosen: -211.9843
• Logits/rejected: -2.4006
• Logits/chosen: -2.4020

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: 5e-07
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 8
• total_train_batch_size: 512
• 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