ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

support rank0 logger

Browse Source 
Former-commit-id: 84528eabe560091bfd866b6a0ca864085af7529b
This commit is contained in:
hiyouga
2024-11-02 18:31:04 +08:00
parent ceb701c2d4
commit 093eda2ad6
42 changed files with 316 additions and 252 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/llamafactory/data/data_utils.py
View File

@@ -17,7 +17,7 @@ from typing import TYPE_CHECKING, Dict, List, Optional, Sequence, Set, TypedDict
from datasets import DatasetDict, concatenate_datasets, interleave_datasets
from ..extras.logging import get_logger
from ..extras import logging
if TYPE_CHECKING:
@@ -26,7 +26,7 @@ if TYPE_CHECKING:
from ..hparams import DataArguments
logger = get_logger(__name__)
logger = logging.get_logger(__name__)
SLOTS = Sequence[Union[str, Set[str], Dict[str, str]]]
@@ -56,12 +56,12 @@ def merge_dataset(
return all_datasets[0]
elif data_args.mix_strategy == "concat":
if data_args.streaming:
logger.warning("The samples between different datasets will not be mixed in streaming mode.")
logger.warning_once("The samples between different datasets will not be mixed in streaming mode.")
return concatenate_datasets(all_datasets)
elif data_args.mix_strategy.startswith("interleave"):
if not data_args.streaming:
logger.warning("We recommend using `mix_strategy=concat` in non-streaming mode.")
logger.warning_once("We recommend using `mix_strategy=concat` in non-streaming mode.")
return interleave_datasets(
datasets=all_datasets,