mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-12-16 03:40:34 +08:00
improve data process logger
This commit is contained in:
@@ -77,6 +77,7 @@ def preprocess_supervised_dataset(
|
||||
|
||||
for i in range(len(examples["prompt"])):
|
||||
if len(examples["prompt"][i]) % 2 != 1 or len(examples["response"][i]) != 1:
|
||||
logger.warning("Dropped invalid example: {}".format(examples["prompt"][i] + examples["response"][i]))
|
||||
continue
|
||||
|
||||
if processor is not None:
|
||||
@@ -129,6 +130,7 @@ def preprocess_packed_supervised_dataset(
|
||||
input_ids, labels = [], []
|
||||
for i in range(len(examples["prompt"])):
|
||||
if len(examples["prompt"][i]) % 2 != 1 or len(examples["response"][i]) != 1:
|
||||
logger.warning("Dropped invalid example: {}".format(examples["prompt"][i] + examples["response"][i]))
|
||||
continue
|
||||
|
||||
messages = examples["prompt"][i] + examples["response"][i]
|
||||
@@ -178,6 +180,7 @@ def preprocess_unsupervised_dataset(
|
||||
|
||||
for i in range(len(examples["prompt"])):
|
||||
if len(examples["prompt"][i]) % 2 != 1:
|
||||
logger.warning("Dropped invalid example: {}".format(examples["prompt"][i] + examples["response"][i]))
|
||||
continue
|
||||
|
||||
if processor is not None:
|
||||
@@ -224,6 +227,7 @@ def preprocess_pairwise_dataset(
|
||||
|
||||
for i in range(len(examples["prompt"])):
|
||||
if len(examples["prompt"][i]) % 2 != 1 or len(examples["response"][i]) < 2:
|
||||
logger.warning("Dropped invalid example: {}".format(examples["prompt"][i] + examples["response"][i]))
|
||||
continue
|
||||
|
||||
if processor is not None:
|
||||
@@ -285,6 +289,7 @@ def preprocess_kto_dataset(
|
||||
|
||||
for i in range(len(examples["prompt"])):
|
||||
if len(examples["prompt"][i]) % 2 != 1 or len(examples["response"][i]) < 2:
|
||||
logger.warning("Dropped invalid example: {}".format(examples["prompt"][i] + examples["response"][i]))
|
||||
continue
|
||||
|
||||
if processor is not None:
|
||||
|
||||
Reference in New Issue
Block a user