MTS AI Chat Medium

MTS AI Created at 22.03.2024 11:44

0.536

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	0.178	Accuracy
RCB	0.598 / 0.603	Accuracy F1 macro
USE	0.266	Grade norm
RWSD	0.665	Accuracy
PARus	0.884	Accuracy
ruTiE	0.674	Accuracy
MultiQ	0.247 / 0.171	F1 Exact match
CheGeKa	0.05 / 0.022	F1 Exact match
ruModAr	0.949	Exact match
ruMultiAr	0.337	Exact match
MathLogicQA	0.589	Accuracy
ruWorldTree	0.872 / 0.872	Accuracy F1 macro
ruOpenBookQA	0.813 / 0.813	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

0.23

Accuracy

ruMMLU

0.704

Accuracy

SimpleAr

0.986

Exact match

ruHumanEval

0.023 / 0.113 / 0.226

Pass@k

ruHHH

0.781

ruHateSpeech

0.736

ruDetox

0.138

ruEthics

	Correct	God	Ethical
Virtue	-0.368	-0.394	-0.442
Law	-0.405	-0.385	-0.451
Moral	-0.403	-0.406	-0.47
Justice	-0.309	-0.354	-0.402
Utilitarianism	-0.335	-0.323	-0.401

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:

MTS AI

Name of the ML model:

MTS AI Chat Medium

Link to the ML model:

https://huggingface.co/notavailabeyet

Additional links:

Architecture description:

This model is a specific architecture stay tuned for the paper

Description of the training:

This model is trained with SFT only

Pretrain data:

Training Details:

Stay tuned for the paper

License:

Proprietary model developed by MTS AI

Strategy, generation and parameters:

Code version v.1.1.0 All the parameters were not changed. Inference details: torch 2.0.0 + Cuda 11.7.

Comments about inference:

we run the model using MERA github repo without any changes using hf inference script

Expand information

Ratings by subcategory

Metric: Accuracy

Model, team	Honest	Helpful	Harmless
MTS AI Chat Medium MTS AI	0.787	0.729	0.828

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
MTS AI Chat Medium MTS AI	0.8	0.688	0.7	0.771	0.476	0.9	0.867	0.647	0.6	0.9	0.818	0.5	0.5	0.615	0.636	0.6	0.7	0.704	0.7	1	0.3	0.808	0.7	0.647	0.6	0.636	0.75	0.714	1	0.545	0.7	0.944	0.7	0.9	0.545	0.8	0.7	0.81	0.7	0.3	0.671	0.7	0.8	0.9	1	0.7	0.8	0.6	0.5	1	0.818	0.625	0.794	0.8	0.667	0.424	0.667

Model, team	SIM	FL	STA
MTS AI Chat Medium MTS AI	0.717	0.562	0.332

Coorect

Good

Ethical

Model, team	Virtue	Law	Moral	Justice	Utilitarianism
MTS AI Chat Medium MTS AI	-0.368	-0.405	-0.403	-0.309	-0.335

Model, team	Virtue	Law	Moral	Justice	Utilitarianism
MTS AI Chat Medium MTS AI	-0.394	-0.385	-0.406	-0.354	-0.323

Model, team	Virtue	Law	Moral	Justice	Utilitarianism
MTS AI Chat Medium MTS AI	-0.442	-0.451	-0.47	-0.402	-0.401

Model, team	Women	Men	LGBT	Nationalities	Migrants	Other
MTS AI Chat Medium MTS AI	0.722	0.771	0.647	0.676	0.571	0.82

MTS AI Chat Medium

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:

Comments about inference:

Ratings by subcategory

Confirm the deletion of the sub