Skip to content

bugfix: ernie dataset tests #2627

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 18, 2025
Merged

bugfix: ernie dataset tests #2627

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions tests/dataset/test_ernie_datasets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@ def test_random_dataset_len(self):
"greedy_intokens": True,
"packing": False,
"mix_strategy": "random",
"encode_one_turn": True,
}

train_dataset = create_dataset_sft(
Expand Down Expand Up @@ -69,6 +70,7 @@ def test_concat_dataset_len(self):
"greedy_intokens": True,
"packing": False,
"mix_strategy": "concat",
"encode_one_turn": True,
}

train_dataset = create_dataset_sft(
Expand Down Expand Up @@ -97,6 +99,7 @@ def test_interleave_under_dataset_len(self):
"greedy_intokens": True,
"packing": False,
"mix_strategy": "interleave_under",
"encode_one_turn": True,
}

train_dataset = create_dataset_sft(
Expand Down Expand Up @@ -125,6 +128,7 @@ def test_interleave_over_dataset_len(self):
"greedy_intokens": True,
"packing": False,
"mix_strategy": "interleave_over",
"encode_one_turn": True,
}

train_dataset = create_dataset_sft(
Expand Down Expand Up @@ -162,6 +166,7 @@ def test_random_dataset_len(self):
"mask_out_eos_token": True,
"packing": False,
"mix_strategy": "random",
"encode_one_turn": True,
}

train_dataset = create_dataset_dpo(
Expand Down Expand Up @@ -197,6 +202,7 @@ def test_concat_dataset_len(self):
"mask_out_eos_token": True,
"packing": False,
"mix_strategy": "concat",
"encode_one_turn": True,
}

train_dataset = create_dataset_dpo(
Expand Down Expand Up @@ -232,6 +238,7 @@ def test_interleave_under_dataset_len(self):
"mask_out_eos_token": True,
"packing": False,
"mix_strategy": "interleave_under",
"encode_one_turn": True,
}

train_dataset = create_dataset_dpo(
Expand Down Expand Up @@ -267,6 +274,7 @@ def test_interleave_over_dataset_len(self):
"mask_out_eos_token": True,
"packing": False,
"mix_strategy": "interleave_over",
"encode_one_turn": True,
}

train_dataset = create_dataset_dpo(
Expand Down