Index-1.9B-Constant-LR

Model Introduction

This repository Index-1.9B-Constant-LR is the checkpoint file of the Index-1.9B base model before decay training, which is provided for everyone to conduct research on downstream tasks.

For more details, see our GitHub and Index-1.9B Technical Report

Evaluation Results

Here we add the evaluation of the general understanding ability of the Index-1.9B-Constant-LR model

Model	Average score	Average English score	MMLU	CEVAL	CMMLU	HellaSwag	Arc-C	Arc-E
Index-1.9B-Constant-LR	41.47	44.24	35.30	38.58	33.26	59.94	32.96	48.75
Index-1.9B-Pure	49.55	52.83	43.75	42.35	43.61	63.21	42.75	61.61
Index-1.9B	64.92	69.93	52.53	57.01	52.79	80.69	65.15	81.35

Evaluation code is based on OpenCompass with compatibility modifications. See the evaluate folder for details.