Comments (1)
Updated the notebook
First, let's load the instruction complexity (
$\mathbf{w'}_x^T$ ).
This was precomputed by fitting the logistic regression as the one above with the following changes:
- replace the instruction embedding by a one hot encoding of the instruction
- tie the weights of the instruction across all the models and fit jointly across all the models
Here's the equation:
$$win_rate(m,b) = \frac{1}{N} \sum_{i=1}^{N} logistic( \mathbf{w}_l[(m,b)] * tanh(standardized(length(m(x_i)) - length(b(x_i)))) + \mathbf{w}_x*I(x_i) + (\mathbf{w}_m[m] - \mathbf{w}_m[b]))$$ Here
$\mathbf{w}_x$ is shared across all models and quantifies how good the baseline win-rate on a certain instruction is.
We then extract this weight and use it as$embedding(x)$ because we want to fit all models disjointly.
Also the paper has more explanation about why: https://arxiv.org/abs/2404.04475
from alpaca_eval.
Related Issues (20)
- How to solve the problem of null appearing in the evaluation results? Thank you very much HOT 3
- ERROR:root:Error while parsing completion: HOT 1
- Evaluating a self hosted LLM through an API. HOT 1
- Details on Training GLM for Length-Controlled Winrate HOT 3
- cannot reindex HOT 3
- Discrepancy between alpaca leaderboard and Chatbot arena ELO HOT 1
- ValueError: Trailing data HOT 1
- AssertionError
- Encountering Error about cannot reindex on an axis with duplicate labels HOT 2
- Negative Correlation while using `alpaca_eval analyze_evaluators` HOT 1
- . HOT 2
- Argument `do_sample` is removed from `vllm_local_completions` HOT 1
- assert output_path is not None and name in leaderboard
- Why do we set do_sample to true during evaluation? HOT 1
- Extra '\n' in the prompt of Llama-3-Instruct-8B-SimPO HOT 3
- Questions about the 'use_beam_search' configuration. HOT 1
- error with default json - ValueError: cannot reindex on an axis with duplicate labels HOT 2
- Using local models as evaluators HOT 2
- Non-reproducible results HOT 4
- all the following results are about AlpacaEval 1.0 and have not been updated since? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from alpaca_eval.