From df7991a9759ff42119e0d12932099e3468ed0888 Mon Sep 17 00:00:00 2001 From: Younes Belkada <49240599+younesbelkada@users.noreply.github.com> Date: Mon, 17 Jun 2024 17:12:34 +0200 Subject: [PATCH] remove datasets --- tests/test_kto_trainer.py | 68 --------------------------------------- 1 file changed, 68 deletions(-) diff --git a/tests/test_kto_trainer.py b/tests/test_kto_trainer.py index bc31cdbd32..bc315d7cb5 100644 --- a/tests/test_kto_trainer.py +++ b/tests/test_kto_trainer.py @@ -82,74 +82,6 @@ def _init_dummy_dataset(self): # fmt: on return Dataset.from_dict(dummy_dataset_dict) - def _init_dummy_dataset_only_desirable(self): - # fmt: off - dummy_dataset_unbalanced_dict = { - "prompt": [ - "Hey, hello", - "How are you", - "What is your name?", - "What is your name?", - "Which is the best programming language?", - "Which is the best programming language?", - "Which is the best programming language?", - ], - "completion": [ - "hi nice to meet you", - "leave me alone", - "I don't have a name", - "My name is Mary", - "Python", - "C++", - "Java", - ], - "label": [ - True, - True, - True, - True, - True, - True, - True, - ], - } - # fmt: on - return Dataset.from_dict(dummy_dataset_unbalanced_dict) - - def _init_dummy_dataset_no_desirable(self): - # fmt: off - dummy_dataset_unbalanced_dict = { - "prompt": [ - "Hey, hello", - "How are you", - "What is your name?", - "What is your name?", - "Which is the best programming language?", - "Which is the best programming language?", - "Which is the best programming language?", - ], - "completion": [ - "hi nice to meet you", - "leave me alone", - "I don't have a name", - "My name is Mary", - "Python", - "C++", - "Java", - ], - "label": [ - False, - False, - False, - False, - False, - False, - False, - ], - } - # fmt: on - return Dataset.from_dict(dummy_dataset_unbalanced_dict) - @parameterized.expand( [ ["gpt2", "kto", True, True],