Mistral 7B

MERA Created at 12.01.2024 11:18

0.4

The overall result

The submission does not contain all the required tasks

Ratings for leaderboard tasks

The table will scroll to the left

Task name	Result	Metric
LCS	0.098	Accuracy
RCB	0.372 / 0.344	Accuracy F1 macro
USE	0.022	Grade norm
RWSD	0.512	Accuracy
PARus	0.518	Accuracy
ruTiE	0.502	Accuracy
MultiQ	0.124 / 0.067	F1 Exact match
CheGeKa	0.038 / 0	F1 Exact match
ruModAr	0.516	Exact match
ruMultiAr	0.195	Exact match
MathLogicQA	0.344	Accuracy
ruWorldTree	0.81 / 0.811	Accuracy F1 macro
ruOpenBookQA	0.735 / 0.732	Accuracy F1 macro

Evaluation on open tasks:

Go to the ratings by subcategory

The table will scroll to the left

Task name

Result

Metric

BPS

0.392

Accuracy

ruMMLU

0.676

Accuracy

SimpleAr

0.95

Exact match

ruHumanEval

0.012 / 0.058 / 0.116

Pass@k

ruHHH

0.556

ruHateSpeech

0.619

ruDetox

0.375

ruEthics

	Correct	God	Ethical
Virtue	-0.12	-0.065	-0.114
Law	-0.091	-0.061	-0.115
Moral	-0.114	-0.056	-0.122
Justice	-0.141	-0.047	-0.104
Utilitarianism	-0.129	-0.081	-0.089

Information about the submission:

Mera version

Torch Version

The version of the codebase

CUDA version

Precision of the model weights

Seed

Butch

Transformers version

The number of GPUs and their type

Architecture

Team:

MERA

Name of the ML model:

Mistral 7B

Link to the ML model:

https://huggingface.co/mistralai/Mistral-7B-v0.1/tree/main

Additional links:

https://arxiv.org/abs/2310.06825

Architecture description:

The Mistral-7B-v0.1 Large Language Model (LLM) is a pretrained generative text model with 7 billion parameters. Mistral-7B-v0.1 outperforms Llama 2 13B on all benchmarks we tested.

Description of the training:

Mistral 7B leverages grouped-query attention (GQA), and sliding window attention (SWA). GQA significantly accelerates the inference speed, and also reduces the memory requirement during decoding, allowing for higher batch sizes hence higher throughput, a crucial factor for real-time applications. In addition, SWA is designed to handle longer sequences more effectively at a reduced computational cost, thereby alleviating a common limitation in LLMs. These attention mechanisms collectively contribute to the enhanced performance and efficiency of Mistral 7B.

Pretrain data:

Training Details:

Mistral-7B-v0.1 is a transformer model, with the following architecture choices: Grouped-Query Attention Sliding-Window Attention Byte-fallback BPE tokenizer.

License:

Apache 2.0 license

Strategy, generation and parameters:

Code version v.1.1.0 All the parameters were not changed and are used as prepared by the organizers. Details: - 1 x NVIDIA A100 - dtype auto - Pytorch 2.1.2 + CUDA 12.1 - Transformers 4.36.2 - Context length 11500

Expand information

Ratings by subcategory

Metric: Accuracy

Model, team	Honest	Helpful	Harmless
Mistral 7B MERA	0.541	0.542	0.586

Model, team	Anatomy	Virology	Astronomy	Marketing	Nutrition	Sociology	Management	Philosophy	Prehistory	Human aging	Econometrics	Formal logic	Global facts	Jurisprudence	Miscellaneous	Moral disputes	Business ethics	Biology (college)	Physics (college)	Human Sexuality	Moral scenarios	World religions	Abstract algebra	Medicine (college)	Machine learning	Medical genetics	Professional law	PR	Security studies	Chemistry (школьная)	Computer security	International law	Logical fallacies	Politics	Clinical knowledge	Conceptual_physics	Math (college)	Biology (high school)	Physics (high school)	Chemistry (high school)	Geography (high school)	Professional medicine	Electrical engineering	Elementary mathematics	Psychology (high school)	Statistics (high school)	History (high school)	Math (high school)	Professional accounting	Professional psychology	Computer science (college)	World history (high school)	Macroeconomics	Microeconomics	Computer science (high school)	European history	Government and politics
Mistral 7B MERA	0.7	0.688	0.4	0.629	0.857	0.8	0.733	0.765	0.6	0.7	0.545	0.6	0.7	0.5	0.636	0.5	0.8	0.704	0.4	1	0.2	0.808	0.8	0.686	0.7	0.818	0.688	0.786	0.9	0.636	0.5	0.833	0.6	0.6	0.636	0.9	0.4	0.667	0.6	0.4	0.747	0.7	0.9	0.6	0.875	0.8	1	0.3	0.6	0.8	0.545	0.875	0.794	0.733	0.5	0.364	0.593

Model, team	SIM	FL	STA
Mistral 7B MERA	0.779	0.594	0.775

Coorect

Good

Ethical

Model, team	Virtue	Law	Moral	Justice	Utilitarianism
Mistral 7B MERA	-0.12	-0.091	-0.114	-0.141	-0.129

Model, team	Virtue	Law	Moral	Justice	Utilitarianism
Mistral 7B MERA	-0.065	-0.061	-0.056	-0.047	-0.081

Model, team	Virtue	Law	Moral	Justice	Utilitarianism
Mistral 7B MERA	-0.114	-0.115	-0.122	-0.104	-0.089

Model, team	Women	Men	LGBT	Nationalities	Migrants	Other
Mistral 7B MERA	0.593	0.686	0.588	0.595	0.429	0.672

Mistral 7B

Ratings for leaderboard tasks

Evaluation on open tasks:

Information about the submission:

Team:

Name of the ML model:

Link to the ML model:

Additional links:

Architecture description:

Description of the training:

Pretrain data:

Training Details:

License:

Strategy, generation and parameters:

Ratings by subcategory

Confirm the deletion of the sub