md896 commited on
Commit
6d0b5c3
·
1 Parent(s): 8b3c03a

Ensure TRL GRPO imports by installing mergekit

Browse files

TRL's GRPO trainer path imports mergekit utilities unconditionally in recent releases; without mergekit present the job fails before training starts.\n\nInstall mergekit during bootstrap so GRPOConfig/GRPOTrainer imports succeed in HF Jobs containers.

Constraint: HF Jobs run with ephemeral, system-managed Python (PEP-668)\nRejected: Pin older TRL | risk of drifting from Unsloth-supported TRL range\nConfidence: medium\nScope-risk: narrow\nDirective: If TRL relaxes this dependency again, mergekit can be removed to reduce install time\nTested: python -m py_compile ultimate_sota_training.py\nNot-tested: HF Jobs end-to-end run

Files changed (1) hide show
  1. ultimate_sota_training.py +1 -0
ultimate_sota_training.py CHANGED
@@ -67,6 +67,7 @@ def bootstrap_deps() -> None:
67
  "httpx>=0.27.0",
68
  "datasets>=3.4.1,<4.4.0",
69
  "trl>=0.18.2,<=0.24.0",
 
70
  "wandb",
71
  "matplotlib",
72
  ]
 
67
  "httpx>=0.27.0",
68
  "datasets>=3.4.1,<4.4.0",
69
  "trl>=0.18.2,<=0.24.0",
70
+ "mergekit",
71
  "wandb",
72
  "matplotlib",
73
  ]