github/autogen
1
1
Fork 0
mirror of https://github.com/microsoft/autogen.git synced 2026-02-11 21:04:59 -05:00
Code Issues Packages Projects Releases Wiki Activity

Remove NLP classification head (#756)

Browse Source 
* rm classification head in nlp

* rm classification head in nlp

* rm classification head in nlp

* adding test cases for switch classification head

* adding test cases for switch classification head

* Update test/nlp/test_autohf_classificationhead.py

Co-authored-by: Chi Wang <wang.chi@microsoft.com>

* adding test cases for switch classification head

* run each test separately

* skip classification head test on windows

* disabling wandb reporting

* fix test nlp custom metric

* fix test nlp custom metric

* fix test nlp custom metric

* fix test nlp custom metric

* fix test nlp custom metric

* fix test nlp custom metric

* fix test nlp custom metric

* fix test nlp custom metric

* fix test nlp custom metric

* fix test nlp custom metric

* fix test nlp custom metric

* Update website/docs/Examples/AutoML-NLP.md

Co-authored-by: Chi Wang <wang.chi@microsoft.com>

* Update website/docs/Examples/AutoML-NLP.md

Co-authored-by: Chi Wang <wang.chi@microsoft.com>

* fix test nlp custom metric

Co-authored-by: Chi Wang <wang.chi@microsoft.com>
This commit is contained in:
Susan Xueqing Liu
2022-10-12 20:04:42 -04:00
committed by GitHub
parent f97c233dc5
commit 2ebddd67ae
13 changed files with 246 additions and 119 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
website/docs/Examples/AutoML-NLP.md
View File

@@ -38,6 +38,13 @@ automl.fit(X_train=X_train, y_train=y_train, X_val=X_val, y_val=y_val, **automl_
automl.predict(X_test)
```
Notice that after you run `automl.fit`, the intermediate checkpoints are saved under the specified output_dir `data/output`. You can use the following code to clean these outputs if they consume a large storage space:
```python
if os.path.exists("data/output/"):
shutil.rmtree("data/output/")
```
#### Sample output
```