Weni/WeniGPT-2.4.3-Zephyr-7B-zephyr-prompt-LLM_Base_2.0.3_DPO_reduction_variation

<!-- 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. -->

WeniGPT-2.4.3-Zephyr-7B-zephyr-prompt-LLMBase2.0.3DPOreduction_variation

This model is a fine-tuned version of Weni/WeniGPT-2.2.3-Zephyr-7B-merged-LLM_Base_2.0.3_SFT on an unknown dataset. It achieves the following results on the evaluation set:

• —Loss: 0.6931
• —Rewards/chosen: 0.0
• —Rewards/rejected: 0.0
• —Rewards/accuracies: 0.0
• —Rewards/margins: 0.0
• —Logps/rejected: -204.7329
• —Logps/chosen: -64.3550
• —Logits/rejected: -2.0322
• —Logits/chosen: -1.6462

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: 0.0002
• —trainbatchsize: 8
• —evalbatchsize: 2
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 16
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_ratio: 0.1
• —training_steps: 1
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —PEFT 0.8.2
• —Transformers 4.39.0.dev0
• —Pytorch 2.1.0+cu118
• —Datasets 2.17.1
• —Tokenizers 0.15.1