weijie210/zephyr-7b-dpo-reference

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

zephyr-7b-dpo-reference

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

• —Loss: 0.0429
• —Rewards/chosen: -0.5987
• —Rewards/rejected: -10.2552
• —Rewards/accuracies: 0.9741
• —Rewards/margins: 9.6565
• —Logps/rejected: -175.1052
• —Logps/chosen: -304.8906
• —Logits/rejected: -1.9643
• —Logits/chosen: -2.1592

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
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 4
• —totaltrainbatch_size: 32
• —totalevalbatch_size: 32
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 1

Training results

Framework versions

• —Transformers 4.36.1
• —Pytorch 2.0.1+cu117
• —Datasets 2.16.1
• —Tokenizers 0.15.0