Comments (3)
Thanks for sharing the feedback about flaml in action. Great to hear that its result is good in your task. To the questions:
iter_per_learner
means how many models have been tried for each learner. The reason you seeiter_per_learner=13
forrecord_id=2
is that flaml only logs better configs than the previous iters by default, i.e.,log_type='better'
.trial_time
means the time taken to train and evaluate one config in that trial.total_search_time
is the total time spent from the beginning offit()
.- Because
log_type='better'
by default,config
is equal tobest_config
. If you uselog_type='all'
instead, all the trials will be logged. And thenconfig
corresponds to the config in that iteration, andbest_config
is the best config so far. - flaml will adjust the
n_estimators
for lightgbm etc. according to the remaining budget and check the time budget constraint and stop in several places. Most of the time that makesfit()
stops before the given budget. Occasionally it may run over the time budget slightly. But the log file always contains the best config info and you can recover it usingretrain_from_log()
.
from flaml.
Thank you! All make sense.
from flaml.
Great. If flaml is useful in your application, it will be nice to have your feedback. Feel free to email [email protected] to ask questions or share your feedback.
from flaml.
Related Issues (20)
- Can one-way message passing be implemented in AutoGen? HOT 2
- `AttributeError: best_iteration is only defined when early stopping is used.` with xgboost 2.0 HOT 7
- Time-series bug when running tutorials on FLAML==2.1.0
- include that `retrain_full = True` does not include the user provided validation data in the docs. HOT 4
- ts_forecast - KeyError/ValueError in predict() HOT 3
- Update the news about autogen spinoff HOT 1
- Re. cannot import name 'oai' from 'flaml' (/usr/local/lib/python3.10/dist-packages/flaml/__init__.py) HOT 1
- please install flaml[openai] option to use the flaml.autogen.oai subpackage. HOT 1
- [BUG] KeyError: 'params/eta' HOT 4
- Unexpected result from flaml.default.LGBMClassifier on iris HOT 2
- Running into error with ChaCha HOT 1
- lgb is not a built-in learner for this task type | NoneType error HOT 1
- Should we add isort to the pre-commit? HOT 11
- Regression with Grouped kFold CV HOT 1
- Question About tuning PyTorch with FLAML HOT 2
- Error in flaml.tune.run
- Question about the custom metric HOT 2
- Cannot predict with numpy inputs
- Need estimators like support vector machine, Decision Tree, Naïve Bayes Classifier.
- How to change value of max_iter in Logistic Regression in AutoML ?
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 flaml.