RichardErkhov/wxzhang_-_dpo-selective-buffer-spo-shift-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

dpo-selective-buffer-spo-shift - GGUF

• —Model creator: https://huggingface.co/wxzhang/
• —Original model: https://huggingface.co/wxzhang/dpo-selective-buffer-spo-shift/

Original model description: --- tags:

• —trl
• —dpo
• —generatedfromtrainer model-index:
• —name: dpo-selective-buffer-spo-shift 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. -->

dpo-selective-buffer-spo-shift

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• —Loss: 0.6777
• —Rewards/chosen: -0.1371
• —Rewards/rejected: -0.0830
• —Rewards/accuracies: 0.4693
• —Rewards/margins: -0.0541
• —Rewards/safe Rewards: -0.1332
• —Rewards/unsafe Rewards: -0.1263
• —Logps/rejected: -92.4348
• —Logps/chosen: -131.0029
• —Logits/rejected: -1.8308
• —Logits/chosen: -2.0825

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: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 2
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 32
• —totalevalbatch_size: 16
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 1

Training results

Framework versions

• —Transformers 4.36.2
• —Pytorch 2.1.2
• —Datasets 2.14.6
• —Tokenizers 0.15.2