ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update rl.py

Browse source
This commit is contained in:
Daniel Han 2025-02-11 15:57:32 -08:00
commit 1e78f1bb80
1 changed files with 11 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

22
unsloth/models/rl.py
View file

@ -230,6 +230,17 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"):
extra_args += eval_changes
pass
# Check max_seq_length
if "max_seq_length" in call_args:
length_check = \
"if hasattr(model, 'max_seq_length') and model.max_seq_length > max_seq_length:\n"\
" print('Unsloth: You set `max_seq_length` as ' + str(max_seq_length) + ' but the\\n'\n"\
" 'model maximum sequence length is ' + str(model.max_seq_length) + '. We will reduce it.')\n"
" max_seq_length = model.max_seq_length\n"
"if hasattr(model, 'max_seq_length') and max_seq_length is None: max_seq_length = model.max_seq_length\n"
extra_args += length_check
pass
# Add statistics as well!
extra_args += \
"from unsloth_zoo.logging_utils import PatchRLStatistics\n"\
@ -298,17 +309,6 @@ def _patch_trl_rl_trainers(trainer_file = "grpo_trainer"):
extra_args += num_proc_check
pass
# Check max_seq_length
if "max_seq_length" in call_args:
length_check = \
"if hasattr(model, 'max_seq_length') and model.max_seq_length > max_seq_length:\n"\
" print('Unsloth: You set `max_seq_length` as ' + str(max_seq_length) + ' but the\\n'\n"\
" 'model maximum sequence length is ' + str(model.max_seq_length) + '. We will reduce it.')\n"
" max_seq_length = model.max_seq_length\n"
"if hasattr(model, 'max_seq_length') and max_seq_length is None: max_seq_length = model.max_seq_length\n"
extra_args += length_check
pass
# Create RLConfig args
extra_args = extra_args.split("\n")
extra_args = "\n".join(" "*8 + x for x in extra_args)