zephyr-7b-dpo-qlora

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-qlora on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

• Loss: 0.6656
• Rewards/chosen: 0.0388
• Rewards/rejected: -0.0264
• Rewards/accuracies: 0.6900
• Rewards/margins: 0.0652
• Logps/rejected: -237.8513
• Logps/chosen: -255.6933
• Logits/rejected: -2.8702
• Logits/chosen: -2.8928

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-06
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 1024
• total_train_batch_size: 4096
• 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

• PEFT 0.7.1
• Transformers 4.36.2
• Pytorch 2.1.2
• Datasets 2.14.6
• Tokenizers 0.15.2