Remove grpo command from default train entrypoint

finetune/CLAUDE.md

@@ -83,11 +83,8 @@ hf jobs uv run --flavor a10g-large --secrets HF_TOKEN --timeout 2h jobs/sft.py
 ### Stage 2: (Experimental) GRPO
 
 ```bash
-# Local (optional; experimental)
-uv run train.py grpo --config experiments/grpo/grpo.yaml
-
 # Experimental script
-HF_TOKEN=${HF_TOKEN} uv run experiments/grpo/grpo.py
+cd finetune && HF_TOKEN=${HF_TOKEN} uv run python experiments/grpo/grpo.py
 ```
 
 ### HuggingFace Jobs

finetune/README.md

@@ -47,7 +47,8 @@ uv run eval.py tobil/qmd-query-expansion-1.7B
 uv run convert_gguf.py --size 1.7B
 
 # NOTE: GRPO is currently experimental and moved to finetune/experiments/grpo
-# if you want to run it manually, use uv run python experiments/grpo/grpo.py
+# if you want to run it manually, use:
+#   cd finetune && uv run python experiments/grpo/grpo.py
 ```
 
 ### Local training (if you have a GPU)
@@ -56,7 +57,7 @@ uv run convert_gguf.py --size 1.7B
 uv run train.py sft  --config configs/sft.yaml
 
 # Experimental GRPO
-uv run train.py grpo --config experiments/grpo/grpo.yaml
+cd finetune && uv run python experiments/grpo/grpo.py
 ```
 
 ### Monitoring HF Jobs
@@ -138,7 +139,7 @@ It is not part of the default production path for this repository.
 
 ```bash
 # Optional experimental GRPO run
-uv run train.py grpo --config experiments/grpo/grpo.yaml
+cd finetune && uv run python experiments/grpo/grpo.py
 ```
 
 ## Evaluation

finetune/train.py

@@ -417,8 +417,6 @@ def cmd_grpo(args):
     )
     print("To run experimental GRPO, use:")
     print("  cd finetune && uv run python experiments/grpo/grpo.py")
-    print("Or, if you have local config wiring ready:")
-    print("  uv run train.py grpo --config experiments/grpo/grpo.yaml")
     return
 
     import torch
@@ -664,22 +662,9 @@ Examples:
         "--dry-run", action="store_true", help="Print config and exit"
     )
 
-    grpo_parser = sub.add_parser(
-        "grpo",
-        help="Experimental: GRPO reinforcement learning (moved to experiments/grpo/)",
-    )
-    grpo_parser.add_argument("--config", required=True, help="Path to GRPO config YAML")
-    grpo_parser.add_argument(
-        "--dry-run", action="store_true", help="Print config, test reward, and exit"
-    )
-
     args = parser.parse_args()
 
-    if args.stage == "sft":
-        cmd_sft(args)
-    elif args.stage == "grpo":
-        cmd_grpo(args)
-
+    cmd_sft(args)
 
 if __name__ == "__main__":
     main()