fix: drop long seq even if not sample packing (#2211)

* fix: drop long seq even if not sample packing

* fix: logging import

* fix: cfg passed being none

* fix: try to fix logging

* fix: refactor call to not use accelerate log

* fix: try to fix circular import issue

* fix: don't drop when skip prepare

* chore: remove duplicate line

* fix: update warning to mention that sequences will be trimmed

* fix: do not drop seq if input_ids don't exist

* fix: increase RM unittest sequence length to reduce trim warnings

* fix: solve conflicts

* fix: default min_seq_len in case of None
This commit is contained in:
NanoCode012
2025-02-04 21:43:35 +07:00
committed by GitHub
parent 158330ab60
commit a620d481e2
6 changed files with 76 additions and 63 deletions

View File

@@ -33,7 +33,7 @@ class TestRewardModelLoraSmolLM2(unittest.TestCase):
"num_labels": 1,
"chat_template": "alpaca",
"reward_model": True,
"sequence_len": 1024,
"sequence_len": 2048,
"pad_to_sequence_len": True,
"adapter": "lora",
"lora_r": 8,