• Model creator: https://huggingface.co/NicholasCorrado/
• Original model: https://huggingface.co/NicholasCorrado/tinyllama-1.1b-chat-v1.0-ui-math-coding-dpo/

Original model description:

• alignment-handbook
• trl
• dpo
• generated_from_trainer
• trl
• dpo
• generated_from_trainer datasets:
• data/ui_math
• data/ui_coding model-index:
• name: tinyllama-1.1b-chat-v1.0-ui-math-coding-dpo results: []

tinyllama-1.1b-chat-v1.0-ui-math-coding-dpo

• Loss: 0.3968
• Rewards/chosen: -1.5087
• Rewards/rejected: -3.7229
• Rewards/accuracies: 0.7812
• Rewards/margins: 2.2142
• Logps/rejected: -740.7106
• Logps/chosen: -538.8605
• Logits/rejected: -2.5209
• Logits/chosen: -2.5392

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 5e-07
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 8
• total_train_batch_size: 1024
• total_eval_batch_size: 128
• 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