423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 20:00:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

support rank0 logger

Browse Source
This commit is contained in:
hiyouga
2024-11-02 18:31:04 +08:00
parent bd08b8c441
commit c38aa29336
42 changed files with 316 additions and 252 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
src/llamafactory/data/processors/feedback.py
View File

@@ -15,8 +15,8 @@
from collections import defaultdict
from typing import TYPE_CHECKING, Any, Dict, List, Optional, Sequence, Tuple
from ...extras import logging
from ...extras.constants import IGNORE_INDEX
from ...extras.logging import get_logger
from .processor_utils import infer_seqlen
@@ -28,7 +28,7 @@ if TYPE_CHECKING:
from ..template import Template
logger = get_logger(__name__)
logger = logging.get_logger(__name__)
def _encode_feedback_example(
@@ -94,7 +94,9 @@ def preprocess_feedback_dataset(
model_inputs = defaultdict(list)
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]))
logger.warning_rank0(
"Dropped invalid example: {}".format(examples["_prompt"][i] + examples["_response"][i])
)
continue
input_ids, labels, kl_input_ids, kl_labels, kto_tag = _encode_feedback_example(
@@ -123,6 +125,6 @@ def preprocess_feedback_dataset(
desirable_num = sum([1 for tag in model_inputs["kto_tags"] if tag])
undesirable_num = len(model_inputs["kto_tags"]) - desirable_num
if desirable_num == 0 or undesirable_num == 0:
logger.warning("Your dataset only has one preference type.")
logger.warning_rank0("Your dataset only has one preference type.")
return model_inputs