zephyr-offline-dpo-lora-noise-0.0-42

This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-qlora on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6931
• Rewards/chosen: -0.0009
• Rewards/rejected: -0.0005
• Rewards/accuracies: 0.4643
• Rewards/margins: -0.0003
• Logps/rejected: -226.9798
• Logps/chosen: -277.3203
• Logits/rejected: -2.2193
• Logits/chosen: -2.3220

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: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• total_eval_batch_size: 16
• 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 4.42.3
• Pytorch 2.3.0+cu121
• Datasets 2.14.6
• Tokenizers 0.19.1