Xueqing Liu 21fa6c10ec

Fixing the issue that FLAML trial number is significantly smaller than Transformers.hyperparameter_search (#657) ...

* fix 636

* adding low cost config

* update padding; update tokenization output y type (series -> DF); update low cost init config

* updating todf; updating metric_loss_score

2022-08-03 00:11:29 -04:00

..

default

Fix HPO evaluation bug (#645)

2022-07-28 23:08:42 -04:00

test_autohf_classificationhead.py

refactoring TransformersEstimator to support default and custom_hp (#511)

2022-04-28 14:06:29 -04:00

test_autohf_custom_metric.py

Fixing the issue that FLAML trial number is significantly smaller than Transformers.hyperparameter_search (#657)

2022-08-03 00:11:29 -04:00

test_autohf_cv.py

refactoring TransformersEstimator to support default and custom_hp (#511)

2022-04-28 14:06:29 -04:00

test_autohf_loadargs.py

model_history, ITER_HP, settings in AutoML(), checkpoint bug fix (#283)

2021-11-18 09:39:45 -08:00

test_autohf_multichoice_classification.py

refactoring TransformersEstimator to support default and custom_hp (#511)

2022-04-28 14:06:29 -04:00

test_autohf_regression.py

refactoring TransformersEstimator to support default and custom_hp (#511)

2022-04-28 14:06:29 -04:00

test_autohf_summarization.py

Fix HPO evaluation bug (#645)

2022-07-28 23:08:42 -04:00

test_autohf_tokenclassification.py

fix ner bug; refactor post processing of TransformersEstimator prediction (#615)

2022-07-05 13:38:21 -04:00

test_autohf.py

Fix HPO evaluation bug (#645)

2022-07-28 23:08:42 -04:00

test_default.py

This PR fixes the frequent NLP bugs in the other PRs (#647)

2022-07-25 17:46:33 -04:00

utils.py

Fix HPO evaluation bug (#645)

2022-07-28 23:08:42 -04:00