Locutusque/lr-experiment1-7B

TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:8kPublished:Mar 12, 2024License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Locutusque/lr-experiment1-7B is a 7 billion parameter Mistral-based language model developed by Locutusque, fine-tuned with QLoRA for 3 epochs on conversational data. This model is part of a research series to determine optimal learning rates for Mistral fine-tuning, specifically using a 2e-5 learning rate with a cosine scheduler. It is designed for general conversational tasks and serves as a benchmark for ongoing learning rate experiments.

Loading preview...

Model Overview

Locutusque/lr-experiment1-7B is a 7 billion parameter language model built upon the Mistral architecture, developed by Locutusque. This model is the first in a research series aimed at identifying the most effective learning rates for fine-tuning Mistral-based models. It was fine-tuned using QLoRA for 3 epochs on the CollectiveCognition/chats-data-2023-09-22 dataset, specifically employing a learning rate of 2e-5 with a cosine scheduler and no warmup steps.

Key Characteristics

  • Base Model: Locutusque/Hercules-2.0-Mistral-7B
  • Fine-tuning Method: QLoRA for 3 epochs
  • Learning Rate: 2e-5 with a cosine scheduler
  • Context Length: 8192 tokens
  • Purpose: Serves as an experimental benchmark to evaluate the impact of specific learning rate configurations on model performance.

Evaluation Highlights

Initial evaluations on the agieval_nous benchmark show an acc score of 0.3645 and an acc_norm score of 0.3468. Specific sub-tasks within agieval_nous include:

  • agieval_aqua_rat: acc 0.2283
  • agieval_logiqa_en: acc 0.2965
  • agieval_lsat_lr: acc 0.4039
  • agieval_sat_en: acc 0.6408

These results provide a baseline for comparison with future models in the lr-experiment series, which will explore different learning rate strategies.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p