gemma-2b-def / README.md
leaderboard-pr-bot's picture
Adding Evaluation Results
7cc169d verified
|
raw
history blame
5.21 kB
---
language:
- en
license: apache-2.0
base_model:
- google/gemma-2-2b-it
datasets:
- FinGPT/fingpt-fiqa_qa
- FinGPT/fingpt-headline
model-index:
- name: gemma-2b-def
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 26.93
name: strict accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ell44ot/gemma-2b-def
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 4.59
name: normalized accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ell44ot/gemma-2b-def
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 1.74
name: exact match
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ell44ot/gemma-2b-def
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 3.13
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ell44ot/gemma-2b-def
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 5.31
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ell44ot/gemma-2b-def
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 6.36
name: accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=ell44ot/gemma-2b-def
name: Open LLM Leaderboard
---
This is a finetuned gemma2b model that is trained using FinGPT datasets
Model Overview
Model Name: Gemma 2B
Version: 1.0
Date: November 2023
Task: Financial Data Analysis
Framework: [Insert framework, e.g., TensorFlow, PyTorch]
License: [Insert license type]
Description
Gemma 2B is a machine learning model designed to analyze and predict financial trends and behaviors using a comprehensive finance dataset. The model leverages advanced algorithms to provide insights into market movements, investment opportunities, and risk assessment.
Intended Use
Gemma 2B is intended for use by financial analysts, investors, and researchers looking to:
Predict stock prices and market trends.
Analyze financial statements and company performance.
Assess portfolio risks and returns.
Generate insights for strategic financial planning.
Dataset Information
Dataset: Finance Dataset
Source: [Specify source, e.g., Yahoo Finance, SEC filings]
Size: [Insert size, e.g., 100,000 records]
Features:
Historical stock prices
Trading volumes
Economic indicators
Company financial metrics (e.g., revenue, earnings)
News sentiment scores
Performance Metrics
The performance of Gemma 2B is evaluated using the following metrics:
Mean Absolute Error (MAE)
Root Mean Squared Error (RMSE)
R-squared (R²)
Benchmark Results:
MAE: [Insert value]
RMSE: [Insert value]
R²: [Insert value]
Limitations
The model is trained on historical data and may not account for unprecedented market events.
Performance can vary based on the selected features and parameters.
Requires continuous updates with new data to maintain accuracy.
Ethical Considerations
Ensure compliance with financial regulations and ethical standards when using the model.
Be aware of potential biases in the training data that may affect predictions.
Future Work
Future improvements may include:
Incorporating additional datasets (e.g., macroeconomic data).
Enhancing the model with deeper learning techniques or ensemble methods.
Continuous monitoring and retraining to adapt to market changes.
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_ell44ot__gemma-2b-def)
| Metric |Value|
|-------------------|----:|
|Avg. | 8.01|
|IFEval (0-Shot) |26.93|
|BBH (3-Shot) | 4.59|
|MATH Lvl 5 (4-Shot)| 1.74|
|GPQA (0-shot) | 3.13|
|MuSR (0-shot) | 5.31|
|MMLU-PRO (5-shot) | 6.36|