RichardErkhov/tanliboy_-_lambda-gemma-2-9b-dpo-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

lambda-gemma-2-9b-dpo - GGUF

• —Model creator: https://huggingface.co/tanliboy/
• —Original model: https://huggingface.co/tanliboy/lambda-gemma-2-9b-dpo/

Original model description: --- license: gemma base_model: tanliboy/zephyr-gemma-2-9b-sft tags:

• —alignment-handbook
• —trl
• —dpo
• —generatedfromtrainer
• —trl
• —dpo
• —generatedfromtrainer datasets:
• —HuggingFaceH4/ultrafeedback_binarized model-index:
• —name: zephyr-gemma-2-9b-dpo-2 results: [] ---

<!-- 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. -->

<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>

zephyr-gemma-2-9b-dpo-2

This model is a fine-tuned version of tanliboy/zephyr-gemma-2-9b-sft on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:

• —Loss: 0.5628
• —Rewards/chosen: -0.7292
• —Rewards/rejected: -1.2825
• —Rewards/accuracies: 0.6960
• —Rewards/margins: 0.5533
• —Logps/rejected: -1566.9301
• —Logps/chosen: -1043.5624
• —Logits/rejected: -14.1720
• —Logits/chosen: -14.6638

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: 2
• —evalbatchsize: 2
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 8
• —gradientaccumulationsteps: 16
• —totaltrainbatch_size: 256
• —totalevalbatch_size: 16
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.2
• —num_epochs: 1

Training results

Framework versions

• —Transformers 4.43.1
• —Pytorch 2.3.1+cu121
• —Datasets 2.19.1
• —Tokenizers 0.19.1