Llama3-70B-EnSecAI-Ru-Chat

EnSec AI Created at 28.08.2024 13:16
0.57
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 0.144 Accuracy
RCB 0.548 / 0.448 Accuracy F1 macro
USE 0.138 Grade norm
RWSD 0.677 Accuracy
PARus 0.926 Accuracy
ruTiE 0.828 Accuracy
MultiQ 0.541 / 0.421 F1 Exact match
CheGeKa 0.306 / 0.231 F1 Exact match
ruModAr 0.709 Exact match
ruMultiAr 0.357 Exact match
MathLogicQA 0.571 Accuracy
ruWorldTree 0.987 / 0.987 Accuracy F1 macro
ruOpenBookQA 0.933 / 0.932 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 0.07 Accuracy
ruMMLU 0.847 Accuracy
SimpleAr 0.997 Exact match
ruHumanEval 0.049 / 0.244 / 0.488 Pass@k
ruHHH 0.82
ruHateSpeech 0.83
ruDetox 0.072
ruEthics
Correct God Ethical
Virtue -0.354 -0.36 -0.468
Law -0.324 -0.335 -0.449
Moral -0.366 -0.379 -0.481
Justice -0.305 -0.318 -0.405
Utilitarianism -0.273 -0.325 -0.385

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:

EnSec AI

Name of the ML model:

Llama3-70B-EnSecAI-Ru-Chat

Architecture description:

Дообученная на русский язык версия Llama-3-70B (meta-llama/Meta-Llama-3-70B-Instruct).

Description of the training:

Для дообучения модели использовались открытые данные для SFT и DPO

Pretrain data:

Llama 3 была предварительно обучена на более чем 15 триллионах токенов данных из общедоступных источников. Данные для дообучения включают общедоступные наборы инструкций, а также более 10 миллионов примеров с аннотациями от людей.

Training Details:

Эта модель была дообучена с использованием 4 x A100 (80GB)

License:

This model was trained from Meta-Llama-3-70B-Instruct, and therefore is subject to the META LLAMA 3 COMMUNITY LICENSE AGREEMENT. (https://llama.meta.com/llama3/license/)

Strategy, generation and parameters:

temperature=0.6 top_p=0.9

Expand information

Ratings by subcategory

Metric: Accuracy
Model, team Honest Helpful Harmless
Llama3-70B-EnSecAI-Ru-Chat
EnSec AI
0.787 0.797 0.879
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
Llama3-70B-EnSecAI-Ru-Chat
EnSec AI
1 1 0.7 0.686 1 1 0.867 0.824 0.8 1 0.909 0.8 0.8 0.692 0.682 0.6 0.8 0.889 0.9 1 0.6 0.885 1 0.863 0.9 0.818 0.688 0.857 1 0.727 0.8 0.833 0.9 1 0.909 0.9 0.8 0.857 0.7 0.9 0.899 1 1 0.9 0.875 0.9 1 0.6 0.8 1 0.818 1 0.882 0.933 0.792 0.606 0.852
Model, team SIM FL STA
Llama3-70B-EnSecAI-Ru-Chat
EnSec AI
0.521 0.761 0.171
Coorect
Good
Ethical
Model, team Virtue Law Moral Justice Utilitarianism
Llama3-70B-EnSecAI-Ru-Chat
EnSec AI
-0.354 -0.324 -0.366 -0.305 -0.273
Model, team Virtue Law Moral Justice Utilitarianism
Llama3-70B-EnSecAI-Ru-Chat
EnSec AI
-0.36 -0.335 -0.379 -0.318 -0.325
Model, team Virtue Law Moral Justice Utilitarianism
Llama3-70B-EnSecAI-Ru-Chat
EnSec AI
-0.468 -0.449 -0.481 -0.405 -0.385
Model, team Women Men LGBT Nationalities Migrants Other
Llama3-70B-EnSecAI-Ru-Chat
EnSec AI
0.852 0.743 0.824 0.838 0.571 0.869