fix: heredocs use initialize_config_dir absolute path (no caller file = relative breaks)

scripts/job_train.sh

@@ -45,11 +45,13 @@ python -m train.smoke_test --env-url http://localhost:8001
 grep -q "VERDICT: GO" outputs/smoke/SMOKE_RESULT.md || (cat outputs/smoke/SMOKE_RESULT.md; exit 1)
 
 # SFT (Path 3 — 0.5B sanity check; switch to qwen_1_5b for Path 1)
+# NOTE: use initialize_config_dir (absolute path) — heredocs have no caller file,
+# so the relative `../configs` resolves against CWD and breaks. Absolute is robust.
 python <<'PY'
-from hydra import initialize, compose
+from hydra import initialize_config_dir, compose
 from train.model_load import load_model_and_tokenizer
 from train.sft import run_sft
-with initialize(config_path="../configs", version_base="1.3"):
+with initialize_config_dir(config_dir="/w/configs", version_base="1.3"):
     cfg = compose(config_name="config", overrides=["model=qwen_0_5b_smoke","train=sft"])
 m, t = load_model_and_tokenizer(cfg)
 print("SFT adapter:", run_sft(cfg, m, t))
@@ -57,11 +59,11 @@ PY
 
 # GRPO 50 steps (Path 3 — 0.5B sanity check; switch to qwen_1_5b + max_steps=400 for Path 1)
 python <<'PY'
-from hydra import initialize, compose
+from hydra import initialize_config_dir, compose
 from train.model_load import load_model_and_tokenizer
 from train.grpo import run_grpo
 from rewards.compose import make_reward_fn
-with initialize(config_path="../configs", version_base="1.3"):
+with initialize_config_dir(config_dir="/w/configs", version_base="1.3"):
     cfg = compose(config_name="config", overrides=["model=qwen_0_5b_smoke","train=grpo","train.max_steps=50"])
 m, t = load_model_and_tokenizer(cfg)
 print("GRPO merged:", run_grpo(cfg, m, t, make_reward_fn(cfg.reward), "http://localhost:8001"))