RichardErkhov/tsavage68_-_Na_M2_100steps_1e7rate_03beta_cSFTDPO-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

NaM2100steps1e7rate03beta_cSFTDPO - GGUF

• —Model creator: https://huggingface.co/tsavage68/
• —Original model: https://huggingface.co/tsavage68/NaM2100steps1e7rate03beta_cSFTDPO/

Original model description: --- libraryname: transformers license: apache-2.0 basemodel: tsavage68/NaM21000steps1e7SFT tags:

• —trl
• —dpo
• —generatedfromtrainer model-index:
• —name: NaM2100steps1e7rate03beta_cSFTDPO 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. -->

NaM2100steps1e7rate03beta_cSFTDPO

This model is a fine-tuned version of tsavage68/Na_M2_1000steps_1e7_SFT on an unknown dataset. It achieves the following results on the evaluation set:

• —Loss: 0.0000
• —Rewards/chosen: 2.8383
• —Rewards/rejected: -9.2541
• —Rewards/accuracies: 1.0
• —Rewards/margins: 12.0924
• —Logps/rejected: -110.7703
• —Logps/chosen: -38.6713
• —Logits/rejected: -2.5103
• —Logits/chosen: -2.5250

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: 1e-07
• —trainbatchsize: 2
• —evalbatchsize: 1
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 4
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_steps: 100
• —training_steps: 100

Training results

Framework versions

• —Transformers 4.44.2
• —Pytorch 2.4.0+cu121
• —Datasets 2.21.0
• —Tokenizers 0.19.1