Spaces:
Sleeping
Sleeping
File size: 49,266 Bytes
160c47d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 | {
"cells": [
{
"cell_type": "markdown",
"id": "33566e3d",
"metadata": {},
"source": [
"# Ghostexec — Unsloth + TRL SFT -> GRPO against the deployed HF Space API\n",
"\n",
"Post-train `unsloth/Llama-3.2-3B-Instruct` with **SFT warmup first** and then GRPO, where rewards are fetched over HTTP from the **live** Ghostexec OpenEnv Space.\n",
"\n",
"- Live endpoint: `https://modelbuilderhq-ghostexec.hf.space`\n",
"- Algorithm: TRL `0.22.2` `SFTTrainer` -> `GRPOTrainer` (no vLLM — HF `generate()` path)\n",
"- Base (recommended for fast winning iterations): `unsloth/Qwen2.5-3B-Instruct` (4-bit) + LoRA r=16 + bf16\n",
"- Curriculum: **easy -> full** annealing (strong local scaffold early, env-dominant later)\n",
"- Rewards: four **independent** functions — `env_reward` (live Space) / `format_reward` / `semantic_action_reward` / `anti_idle_reward`\n",
"\n",
"### Help Guide phase map (notebook sections mirror `[Participant Help Guide] §18`)\n",
"| Phase | Where |\n",
"|---|---|\n",
"| 1 Pick a narrow task | section 1 |\n",
"| 2 Build the environment | section 2 (already deployed; health check here) |\n",
"| 3 Build rewards | section 3 |\n",
"| 4 Deploy | section 4 (confirm) |\n",
"| 5 Train small | section 5 (SFT + Stage B) |\n",
"| 6 Inspect for hacking | section 6 |\n",
"| 7 Add curriculum | section 7 (Stages C + D) |\n",
"| 8 Train bigger | section 8 (knobs, not action) |\n",
"| 9 Save and demo | section 9 |"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Phase 1 — Pick a narrow task\n",
"\n",
"Single-step action selection from a plain-text executive briefing. The model reads the briefing from `/reset` and must emit exactly one JSON action matching `GhostexecAction`. The deployed Space scores that action and returns a reward from `/step`. That reward is the learning signal.\n",
"\n",
"Legal `action_type` values: `reply_email, archive_email, reschedule_meeting, cancel_meeting, complete_task, delegate_task, send_message, do_nothing`.\n",
"\n",
"The scenario is fixed on the deployed Space (`phase2_core`), so the curriculum is an **exploration schedule** (temperature / num_generations / learning rate) across three training stages rather than a scenario switch."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Phase 2 — Build the environment (already deployed on HF Spaces)\n",
"\n",
"The next cell is the exact Unsloth install snippet. Restart the runtime after it finishes if Colab asks you to."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%capture\n",
"import os, importlib.util\n",
"!pip install --upgrade -qqq uv\n",
"if importlib.util.find_spec(\"torch\") is None or \"COLAB_\" in \"\".join(os.environ.keys()):\n",
" try: import numpy; get_numpy = f\"numpy=={numpy.__version__}\"\n",
" except: get_numpy = \"numpy\"\n",
" !uv pip install -qqq \\\n",
" \"torch>=2.8.0\" \"triton>=3.4.0\" {get_numpy} torchvision bitsandbytes \"transformers==4.56.2\" trackio \\\n",
" \"unsloth_zoo[base] @ git+https://github.com/unslothai/unsloth-zoo\" \\\n",
" \"unsloth[base] @ git+https://github.com/unslothai/unsloth\" \\\n",
" git+https://github.com/triton-lang/triton.git@0add68262ab0a2e33b84524346cb27cbb2787356#subdirectory=python/triton_kernels\n",
"elif importlib.util.find_spec(\"unsloth\") is None:\n",
" !uv pip install -qqq unsloth trackio\n",
"!uv pip install --upgrade --no-deps transformers==4.56.2 tokenizers trl==0.22.2 unsloth unsloth_zoo"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%pip install -q requests pydantic matplotlib pandas tqdm huggingface_hub datasets\n",
"print(\"aux deps installed\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "88474159",
"metadata": {},
"outputs": [],
"source": [
"import os, sys, json, time, random, re, math, pathlib\n",
"from typing import Any\n",
"\n",
"GHOSTEXEC_ENV_URL = os.environ.get(\"GHOSTEXEC_ENV_URL\", \"https://modelbuilderhq-ghostexec.hf.space\")\n",
"# Small-model-first default for rapid iteration and higher success probability.\n",
"MODEL_ID = os.environ.get(\"MODEL_ID\", \"unsloth/Qwen2.5-3B-Instruct\")\n",
"RUN_NAME = os.environ.get(\"RUN_NAME\", \"ghostexec-unsloth-grpo\")\n",
"HUB_REPO_ID = os.environ.get(\"HUB_REPO_ID\", \"\")\n",
"OUT = pathlib.Path(\"/content/ghostexec_out\") if os.path.exists(\"/content\") else pathlib.Path(\"./ghostexec_out\")\n",
"OUT.mkdir(parents=True, exist_ok=True)\n",
"\n",
"try:\n",
" from google.colab import userdata # type: ignore\n",
" if not os.environ.get(\"HF_TOKEN\"):\n",
" try: os.environ[\"HF_TOKEN\"] = userdata.get(\"HF_TOKEN\") or \"\"\n",
" except Exception: pass\n",
"except Exception:\n",
" pass\n",
"\n",
"print(\"Endpoint :\", GHOSTEXEC_ENV_URL)\n",
"print(\"Model :\", MODEL_ID)\n",
"print(\"Output :\", OUT)\n",
"print(\"HF token :\", \"set\" if os.environ.get(\"HF_TOKEN\") else \"missing (needed only for push_to_hub)\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### 2.1 HTTP client to the deployed Space\n",
"\n",
"Every reward in this notebook comes from this class — we never run Ghostexec locally."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import requests\n",
"\n",
"class GhostexecSpace:\n",
" def __init__(self, url: str, timeout: float = 60.0, max_retries: int = 4):\n",
" self.url = url.rstrip(\"/\")\n",
" self.timeout = timeout\n",
" self.max_retries = max_retries\n",
" self.latency_ms: list[float] = []\n",
"\n",
" def _post(self, path: str, payload: dict) -> dict:\n",
" last_err: Exception | None = None\n",
" for attempt in range(self.max_retries):\n",
" try:\n",
" t0 = time.perf_counter()\n",
" r = requests.post(f\"{self.url}{path}\", json=payload, timeout=self.timeout)\n",
" self.latency_ms.append((time.perf_counter() - t0) * 1000.0)\n",
" r.raise_for_status()\n",
" return r.json()\n",
" except Exception as e:\n",
" last_err = e\n",
" time.sleep(min(2 ** attempt, 8.0))\n",
" raise RuntimeError(f\"POST {path} failed after {self.max_retries} tries: {last_err}\")\n",
"\n",
" def reset(self) -> dict:\n",
" return self._post(\"/reset\", {})\n",
"\n",
" def step(self, action: dict) -> tuple[float, dict]:\n",
" raw = self._post(\"/step\", {\"action\": action})\n",
" reward = raw.get(\"reward\")\n",
" if reward is None:\n",
" reward = (raw.get(\"observation\") or {}).get(\"reward\", 0.0)\n",
" try: return float(reward), raw\n",
" except Exception: return 0.0, raw\n",
"\n",
"env = GhostexecSpace(GHOSTEXEC_ENV_URL)\n",
"print(\"Health reset ...\")\n",
"_obs = env.reset()\n",
"print(\"reset keys:\", sorted(_obs.keys()))\n",
"_brief = ((_obs.get(\"observation\") or _obs).get(\"echoed_message\") or \"\")[:400]\n",
"print(\"briefing preview:\\n\", _brief)"
]
},
{
"cell_type": "markdown",
"id": "b747bc4e",
"metadata": {},
"source": [
"### 2.2 Verifier sanity check (Help Guide §8)\n",
"\n",
"**Colab / stale cells:** If the traceback mentions **`do_nothing is not the worst/floor`** on **line ~28**, you are running **old cached notebook code** (that assert was removed). Use **Runtime → Disconnect and delete runtime**, then **re-clone** the repo or **re-download** this notebook from GitHub and run from the top.\n",
"\n",
"**If every proactive action prints `-0.25` and only `do_nothing` is `-0.15`:** every non-idle smoke is an **invalid step** (wrong ids like `email_01`, or an outdated `_smoke_action`). This cell expects **real `phase2_core` ids** (`e01`, `e09`, `m02`, …) — see `_smoke_action` below.\n",
"\n",
"Fire every legal `action_type` once with **semantically valid** payloads (real ids from `scenarios/phase2_core.json`). Fake ids deserialize but fail validation (−0.25 invalid-step) and are not a fair probe. Also: **`do_nothing` is not guaranteed to be the lowest reward** — a valid but harmful action (e.g. cancelling an important meeting) can push the weighted score below the idle penalty. We instead assert **non-idle smokes are `step_ok=True`** and **`do_nothing` scores below a benign `reply_email` on `e01`**. If rewards are all identical, abort — GRPO cannot learn from a degenerate verifier."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5ed1a9bc",
"metadata": {},
"outputs": [],
"source": [
"LEGAL_ACTION_TYPES = [\n",
" \"reply_email\", \"archive_email\", \"reschedule_meeting\", \"cancel_meeting\",\n",
" \"complete_task\", \"delegate_task\", \"send_message\", \"do_nothing\",\n",
"]\n",
"\n",
"def _smoke_action(action_type: str) -> dict:\n",
" # Real IDs from phase2_core scenario\n",
" base = {\"action_type\": action_type, \"message\": \"\"}\n",
"\n",
" if action_type == \"reply_email\":\n",
" return {**base, \"email_id\": \"e01\", \"message_body\": \"Acknowledged — on it now.\"}\n",
" if action_type == \"archive_email\":\n",
" return {**base, \"email_id\": \"e09\"}\n",
" if action_type == \"reschedule_meeting\":\n",
" return {\n",
" **base,\n",
" \"meeting_id\": \"m02\",\n",
" \"new_time\": \"2026-04-21T18:00:00\",\n",
" \"reason\": \"freeing the morning block\",\n",
" }\n",
" if action_type == \"cancel_meeting\":\n",
" return {**base, \"meeting_id\": \"m10\", \"reason\": \"smoke test cancel\"}\n",
" if action_type == \"complete_task\":\n",
" return {**base, \"task_id\": \"t07\"}\n",
" if action_type == \"delegate_task\":\n",
" return {**base, \"task_id\": \"t08\", \"contact_name\": \"Jordan Lee\"}\n",
" if action_type == \"send_message\":\n",
" return {\n",
" **base,\n",
" \"contact_name\": \"Jamie Liu\",\n",
" \"message_body\": \"Quick sync when you have a minute.\",\n",
" }\n",
"\n",
" # do_nothing\n",
" return {\n",
" **base,\n",
" \"email_id\": \"\",\n",
" \"message_body\": \"\",\n",
" \"meeting_id\": \"\",\n",
" \"new_time\": \"\",\n",
" \"reason\": \"\",\n",
" \"task_id\": \"\",\n",
" \"contact_name\": \"\",\n",
" }\n",
"\n",
"rewards_by_action: dict[str, float] = {}\n",
"step_ok_by_action: dict[str, bool | None] = {}\n",
"\n",
"for at in LEGAL_ACTION_TYPES:\n",
" env.reset()\n",
" r, raw = env.step(_smoke_action(at))\n",
" rewards_by_action[at] = round(r, 4)\n",
" obs = raw.get(\"observation\") or {}\n",
" step_ok_by_action[at] = (obs.get(\"metadata\") or {}).get(\"step_ok\")\n",
"\n",
"print(json.dumps({\"reward\": rewards_by_action, \"step_ok\": step_ok_by_action}, indent=2))\n",
"\n",
"uniq = set(rewards_by_action.values())\n",
"assert len(uniq) > 1, \"Verifier is constant across actions — env can't teach anything.\"\n",
"\n",
"# All non-idle smokes must be valid\n",
"for at in LEGAL_ACTION_TYPES:\n",
" if at == \"do_nothing\":\n",
" continue\n",
" assert step_ok_by_action.get(at) is True, f\"{at} smoke is invalid; check IDs.\"\n",
"\n",
"# Idle should be worse than benign good action\n",
"assert rewards_by_action[\"do_nothing\"] < rewards_by_action[\"reply_email\"] - 1e-6, \\\n",
" \"do_nothing should score below reply_email(e01).\"\n",
"\n",
"print(\"\\nverifier OK — rewards vary, smokes are valid, do_nothing < reply_email(e01).\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Phase 3 — Build rewards\n",
"\n",
"Three independent reward functions per Help Guide §7. Keeping them independent means we can plot each component, watch their correlations, and catch hacking (e.g. env reward climbs while format reward collapses)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from pydantic import BaseModel\n",
"from typing import Literal\n",
"\n",
"GhostexecActionType = Literal[\n",
" \"reply_email\", \"archive_email\", \"reschedule_meeting\", \"cancel_meeting\",\n",
" \"complete_task\", \"delegate_task\", \"send_message\", \"do_nothing\",\n",
"]\n",
"\n",
"class GhostexecAction(BaseModel):\n",
" action_type: GhostexecActionType = \"do_nothing\"\n",
" email_id: str = \"\"\n",
" message_body: str = \"\"\n",
" meeting_id: str = \"\"\n",
" new_time: str = \"\"\n",
" reason: str = \"\"\n",
" task_id: str = \"\"\n",
" contact_name: str = \"\"\n",
" message: str = \"\"\n",
"\n",
"def _extract_json(text: str) -> dict:\n",
" s = text.strip()\n",
" s = re.sub(r\"^```(?:json)?\\s*|\\s*```$\", \"\", s, flags=re.IGNORECASE | re.MULTILINE).strip()\n",
" start, end = s.find(\"{\"), s.rfind(\"}\")\n",
" if start == -1 or end <= start: raise ValueError(\"no json object\")\n",
" return json.loads(s[start:end+1])\n",
"\n",
"def parse_action_strict(text: str) -> dict:\n",
" obj = _extract_json(text)\n",
" GhostexecAction(**obj)\n",
" return obj\n",
"\n",
"def parse_action(text: str) -> dict:\n",
" try: return parse_action_strict(text)\n",
" except Exception: return {\"action_type\": \"do_nothing\"}\n",
"\n",
"LEGAL_ACTION_TYPES = {\n",
" \"reply_email\", \"archive_email\", \"reschedule_meeting\", \"cancel_meeting\",\n",
" \"complete_task\", \"delegate_task\", \"send_message\", \"do_nothing\",\n",
"}\n",
"LEGAL_ACTION_KEYS = {\n",
" \"action_type\", \"email_id\", \"message_body\", \"meeting_id\",\n",
" \"new_time\", \"reason\", \"task_id\", \"contact_name\", \"message\",\n",
"}\n",
"\n",
"\n",
"def sanitize_action(raw: dict) -> dict:\n",
" \"\"\"Keep only legal Ghostexec fields and coerce malformed IDs/actions safely.\"\"\"\n",
" action = {k: v for k, v in (raw or {}).items() if k in LEGAL_ACTION_KEYS}\n",
"\n",
" at = str(action.get(\"action_type\", \"do_nothing\"))\n",
" if at not in LEGAL_ACTION_TYPES:\n",
" at = \"do_nothing\"\n",
" action[\"action_type\"] = at\n",
"\n",
" # Common model mistake: writes message text into `message` instead of `message_body`.\n",
" if at in {\"reply_email\", \"send_message\"}:\n",
" if not action.get(\"message_body\") and action.get(\"message\"):\n",
" action[\"message_body\"] = action[\"message\"]\n",
"\n",
" if \"email_id\" in action and not re.fullmatch(r\"e\\d{2}\", str(action[\"email_id\"])):\n",
" action[\"email_id\"] = \"\"\n",
" if \"meeting_id\" in action and not re.fullmatch(r\"m\\d{2}\", str(action[\"meeting_id\"])):\n",
" action[\"meeting_id\"] = \"\"\n",
" if \"task_id\" in action and not re.fullmatch(r\"t\\d{2}\", str(action[\"task_id\"])):\n",
" action[\"task_id\"] = \"\"\n",
"\n",
" return action\n",
"\n",
"assert parse_action_strict('```json\\n{\"action_type\":\"archive_email\",\"email_id\":\"email_01\"}\\n```')[\"action_type\"] == \"archive_email\"\n",
"assert parse_action(\"garbage\")[\"action_type\"] == \"do_nothing\"\n",
"print(\"parser OK\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3bd66b49",
"metadata": {},
"outputs": [],
"source": [
"def _completion_text(c) -> str:\n",
" if isinstance(c, list) and c and isinstance(c[0], dict):\n",
" return c[0].get(\"content\", \"\")\n",
" return c if isinstance(c, str) else str(c)\n",
"\n",
"\n",
"def _prompt_to_text(p) -> str:\n",
" if isinstance(p, list) and p and isinstance(p[-1], dict):\n",
" return str(p[-1].get(\"content\", \"\"))\n",
" if isinstance(p, dict):\n",
" return str(p.get(\"content\", \"\"))\n",
" return str(p)\n",
"\n",
"\n",
"# Curriculum scalars are updated per stage: easy -> full.\n",
"CURRENT_ENV_SCALE = 0.85\n",
"CURRENT_LOCAL_SCALE = 0.60\n",
"\n",
"\n",
"def env_reward(completions, prompts=None, **_) -> list[float]:\n",
" out: list[float] = []\n",
" for c in completions:\n",
" text = _completion_text(c)\n",
" action = sanitize_action(parse_action(text))\n",
" try:\n",
" env.reset()\n",
" r, _ = env.step(action)\n",
" except Exception:\n",
" r = -1.0\n",
" out.append(float(r) * CURRENT_ENV_SCALE)\n",
" return out\n",
"\n",
"\n",
"def format_reward(completions, **_) -> list[float]:\n",
" out: list[float] = []\n",
" for c in completions:\n",
" text = _completion_text(c)\n",
" try:\n",
" parse_action_strict(text)\n",
" out.append(0.12 * CURRENT_LOCAL_SCALE)\n",
" except Exception:\n",
" out.append(-0.20 * CURRENT_LOCAL_SCALE)\n",
" return out\n",
"\n",
"\n",
"def semantic_action_reward(completions, prompts=None, **_) -> list[float]:\n",
" \"\"\"\n",
" Reward canonical, briefing-grounded action payloads before env call.\n",
" Scaled by CURRENT_LOCAL_SCALE for easy->full curriculum annealing.\n",
" \"\"\"\n",
" out: list[float] = []\n",
" for i, c in enumerate(completions):\n",
" text = _completion_text(c)\n",
" act = parse_action(text)\n",
" at = act.get(\"action_type\", \"do_nothing\")\n",
"\n",
" prompt_text = \"\"\n",
" if prompts is not None and i < len(prompts):\n",
" prompt_text = _prompt_to_text(prompts[i])\n",
"\n",
" def present(tok: str) -> bool:\n",
" return bool(tok) and re.search(rf\"\\b{re.escape(tok)}\\b\", prompt_text) is not None\n",
"\n",
" r = -0.30\n",
" if at == \"do_nothing\":\n",
" r = -0.05\n",
" elif at == \"reply_email\":\n",
" eid = act.get(\"email_id\", \"\")\n",
" mb = (act.get(\"message_body\", \"\") or \"\").strip()\n",
" r = 0.30 if present(eid) and bool(re.fullmatch(r\"e\\d{2}\", eid)) and mb else -0.30\n",
" elif at == \"archive_email\":\n",
" eid = act.get(\"email_id\", \"\")\n",
" r = 0.30 if present(eid) and bool(re.fullmatch(r\"e\\d{2}\", eid)) else -0.30\n",
" elif at == \"reschedule_meeting\":\n",
" mid = act.get(\"meeting_id\", \"\")\n",
" nt = (act.get(\"new_time\", \"\") or \"\").strip()\n",
" r = 0.30 if present(mid) and bool(re.fullmatch(r\"m\\d{2}\", mid)) and nt else -0.30\n",
" elif at == \"cancel_meeting\":\n",
" mid = act.get(\"meeting_id\", \"\")\n",
" r = 0.30 if present(mid) and bool(re.fullmatch(r\"m\\d{2}\", mid)) else -0.30\n",
" elif at == \"complete_task\":\n",
" tid = act.get(\"task_id\", \"\")\n",
" r = 0.30 if present(tid) and bool(re.fullmatch(r\"t\\d{2}\", tid)) else -0.30\n",
" elif at == \"delegate_task\":\n",
" tid = act.get(\"task_id\", \"\")\n",
" cn = (act.get(\"contact_name\", \"\") or \"\").strip()\n",
" r = 0.30 if present(tid) and bool(re.fullmatch(r\"t\\d{2}\", tid)) and (cn in prompt_text) else -0.30\n",
" elif at == \"send_message\":\n",
" cn = (act.get(\"contact_name\", \"\") or \"\").strip()\n",
" mb = (act.get(\"message_body\", \"\") or \"\").strip()\n",
" r = 0.30 if cn and (cn in prompt_text) and mb else -0.30\n",
"\n",
" out.append(float(r) * CURRENT_LOCAL_SCALE)\n",
" return out\n",
"\n",
"\n",
"def anti_idle_reward(completions, **_) -> list[float]:\n",
" out: list[float] = []\n",
" for c in completions:\n",
" text = _completion_text(c)\n",
" act = parse_action(text)\n",
" out.append((-0.28 if act.get(\"action_type\") == \"do_nothing\" else 0.03) * CURRENT_LOCAL_SCALE)\n",
" return out\n",
"\n",
"\n",
"_dummy = '{\"action_type\":\"archive_email\",\"email_id\":\"email_01\"}'\n",
"print(\"env :\", env_reward([_dummy]))\n",
"print(\"format :\", format_reward([_dummy]))\n",
"print(\"semantic :\", semantic_action_reward([_dummy], prompts=[\"... e01 e09 t07 m02 Jamie Liu ...\"]))\n",
"print(\"anti_idle:\", anti_idle_reward([_dummy]))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a6a37dad",
"metadata": {},
"outputs": [],
"source": [
"# GRPO stages B / C / D: no early-stop callbacks — each stage runs the full `max_steps`.\n"
]
},
{
"cell_type": "markdown",
"id": "92744e0a",
"metadata": {},
"source": [
"## Phase 4 — Deploy\n",
"\n",
"Already done. Live Space: [`modelbuilderhq/ghostexec`](https://huggingface.co/spaces/modelbuilderhq/ghostexec). The health-check cell above confirmed `/reset` + `/step` are green."
]
},
{
"cell_type": "markdown",
"id": "428d6377",
"metadata": {},
"source": [
"## Phase 5 — Train small (SFT warmup -> GRPO)\n",
"\n",
"Load `unsloth/Llama-3.2-3B-Instruct` in 4-bit with Unsloth, attach LoRA, run a **short SFT warmup first**, then run GRPO. vLLM is not used anywhere in this notebook — rollouts go through the standard HF `generate()` path inside `GRPOTrainer`."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ad55b1af",
"metadata": {},
"outputs": [],
"source": [
"# IMPORTANT: import unsloth before transformers so its kernels patch cleanly.\n",
"from unsloth import FastLanguageModel\n",
"import torch\n",
"\n",
"MAX_SEQ_LENGTH = 2048\n",
"\n",
"policy, tokenizer = FastLanguageModel.from_pretrained(\n",
" model_name=MODEL_ID,\n",
" max_seq_length=MAX_SEQ_LENGTH,\n",
" load_in_4bit=True,\n",
" dtype=None, # auto (bf16 on T4 compute via bnb)\n",
")\n",
"\n",
"policy = FastLanguageModel.get_peft_model(\n",
" policy,\n",
" r=16, lora_alpha=32, lora_dropout=0.0,\n",
" target_modules=[\"q_proj\",\"k_proj\",\"v_proj\",\"o_proj\",\"gate_proj\",\"up_proj\",\"down_proj\"],\n",
" bias=\"none\",\n",
" use_gradient_checkpointing=\"unsloth\",\n",
" random_state=3407,\n",
")\n",
"\n",
"if tokenizer.pad_token is None:\n",
" tokenizer.pad_token = tokenizer.eos_token\n",
"tokenizer.padding_side = \"left\"\n",
"\n",
"print(\"policy loaded:\", MODEL_ID)\n",
"policy.print_trainable_parameters()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "883dce70",
"metadata": {},
"outputs": [],
"source": [
"SYSTEM_PROMPT = (\n",
" \"You are Ghostexec, an AI Chief of Staff. You receive a plain-text briefing of an executive's \"\n",
" \"inbox, calendar and tasks. You must choose the single best next action.\\n\\n\"\n",
" \"Legal action_type values: reply_email, archive_email, reschedule_meeting, cancel_meeting, \"\n",
" \"complete_task, delegate_task, send_message, do_nothing.\\n\\n\"\n",
" \"Output ONLY a compact JSON object with these keys (no prose, no code fences):\\n\"\n",
" \"{\\\"action_type\\\": \\\"\\\", \\\"email_id\\\": \\\"\\\", \\\"message_body\\\": \\\"\\\", \"\n",
" \"\\\"meeting_id\\\": \\\"\\\", \\\"new_time\\\": \\\"\\\", \\\"reason\\\": \\\"\\\", \\\"task_id\\\": \\\"\\\", \"\n",
" \"\\\"contact_name\\\": \\\"\\\", \\\"message\\\": \\\"\\\"}.\\n\\n\"\n",
" \"ID RULES:\\n\"\n",
" \"- email_id must be an email token from briefing like e01, e02, ...\\n\"\n",
" \"- meeting_id must be a meeting token like m01, m02, ...\\n\"\n",
" \"- task_id must be a task token like t01, t02, ...\\n\"\n",
" \"- contact_name must exactly match a contact shown in briefing.\\n\"\n",
" \"- Never use subject/body/description text as an ID.\\n\"\n",
" \"- If you cannot find a valid ID for your chosen action, output {\\\"action_type\\\":\\\"do_nothing\\\"}.\\n\\n\"\n",
" \"Prefer high-impact valid actions; avoid do_nothing when critical items are unresolved.\"\n",
")\n",
"\n",
"def build_prompt(briefing: str) -> list[dict]:\n",
" return [\n",
" {\"role\": \"system\", \"content\": SYSTEM_PROMPT},\n",
" {\"role\": \"user\", \"content\": f\"BRIEFING:\\n{briefing}\\n\\nReturn one JSON action.\"},\n",
" ]\n",
"\n",
"def render_chat(messages: list[dict]) -> str:\n",
" return tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "adebc81c",
"metadata": {},
"outputs": [],
"source": [
"from datasets import Dataset\n",
"from tqdm.auto import tqdm\n",
"\n",
"def fetch_briefing() -> str:\n",
" obs = env.reset()\n",
" inner = obs.get(\"observation\") or obs\n",
" brief = inner.get(\"echoed_message\") or inner.get(\"message\") or \"\"\n",
" if not brief:\n",
" raise RuntimeError(f\"Space returned no briefing: keys={list(inner.keys())}\")\n",
" return brief\n",
"\n",
"N_BRIEFINGS = int(os.environ.get(\"N_BRIEFINGS\", \"24\"))\n",
"briefings: list[str] = []\n",
"for _ in tqdm(range(N_BRIEFINGS), desc=\"sampling /reset\"):\n",
" briefings.append(fetch_briefing())\n",
"\n",
"print(f\"fetched {len(briefings)} briefings ({len(set(briefings))} unique)\")\n",
"train_ds = Dataset.from_list([{\"prompt\": build_prompt(b)} for b in briefings])\n",
"print(train_ds)"
]
},
{
"cell_type": "markdown",
"id": "e80ea6ed",
"metadata": {},
"source": [
"### 5.1 Baselines — weak random vs frozen (pre-pipeline) vs trained (Help Guide §19)\n",
"\n",
"- **Random**: junk actions (bad IDs / not in scenario) so the mean stays low on purpose.\n",
"- **Frozen**: same LoRA policy **before** the SFT+GRPO cells below; should beat random clearly.\n",
"- **Trained**: re-eval after GRPO; Phase 9 asserts **random mean < frozen mean** and **frozen mean + margin < trained mean** (margins: env vars `MIN_GAP_RANDOM_FROZEN`, `MIN_GAP_FROZEN_TRAINED`)."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9c2ff7d6",
"metadata": {},
"outputs": [],
"source": [
"N_EVAL = int(os.environ.get(\"N_EVAL\", \"8\"))\n",
"\n",
"def random_policy_reward() -> list[float]:\n",
" rs: list[float] = []\n",
" for _ in range(N_EVAL):\n",
" at = random.choice(list(LEGAL_ACTION_TYPES))\n",
" env.reset()\n",
" r, _ = env.step(_smoke_action(at))\n",
" rs.append(r)\n",
" return rs\n",
"\n",
"@torch.no_grad()\n",
"def evaluate_policy(model, n: int = N_EVAL, temperature: float = 0.2) -> list[float]:\n",
" FastLanguageModel.for_inference(model)\n",
" rs: list[float] = []\n",
" for i in range(n):\n",
" brief = briefings[i % len(briefings)]\n",
" prompt_text = render_chat(build_prompt(brief))\n",
" inputs = tokenizer(prompt_text, return_tensors=\"pt\", truncation=True, max_length=MAX_SEQ_LENGTH).to(model.device)\n",
" out = model.generate(\n",
" **inputs,\n",
" max_new_tokens=128,\n",
" do_sample=(temperature > 0),\n",
" temperature=max(temperature, 1e-5),\n",
" pad_token_id=tokenizer.pad_token_id,\n",
" )\n",
" completion = tokenizer.decode(out[0][inputs[\"input_ids\"].shape[1]:], skip_special_tokens=True)\n",
" action = sanitize_action(parse_action(completion))\n",
" env.reset()\n",
" try:\n",
" r, _ = env.step(action)\n",
" except RuntimeError:\n",
" r, _ = env.step({\"action_type\": \"do_nothing\"})\n",
" rs.append(r)\n",
" FastLanguageModel.for_training(model)\n",
" return rs\n",
"\n",
"print(\"Random baseline ...\")\n",
"random_rewards = random_policy_reward()\n",
"print(\" mean:\", sum(random_rewards) / len(random_rewards))\n",
"\n",
"print(\"Frozen-base baseline ...\")\n",
"frozen_rewards = evaluate_policy(policy, n=N_EVAL, temperature=0.2)\n",
"print(\" mean:\", sum(frozen_rewards) / len(frozen_rewards))\n",
"\n",
"baselines = {\"random\": random_rewards, \"frozen\": frozen_rewards}"
]
},
{
"cell_type": "markdown",
"id": "018d2c7c",
"metadata": {},
"source": [
"### 5.2 Stage B — first GRPO stage (easy->full curriculum starts here)\n",
"\n",
"We run a short SFT warmup first, then GRPO Stage B with stronger local scaffold weights (`CURRENT_LOCAL_SCALE`) and slightly lower env scale (`CURRENT_ENV_SCALE`).\n",
"\n",
"As stages progress (B -> C -> D), the notebook anneals toward full env-dominant training."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "10b073d0",
"metadata": {},
"outputs": [],
"source": [
"from trl import GRPOConfig, GRPOTrainer, SFTConfig, SFTTrainer\n",
"\n",
"reward_funcs = [env_reward, format_reward, semantic_action_reward, anti_idle_reward]\n",
"stage_logs: dict[str, list[dict]] = {}\n",
"\n",
"# -------- SFT warmup --------\n",
"def _heuristic_action_for_sft(briefing: str) -> dict:\n",
" b = briefing.lower()\n",
" if \"e01\" in b:\n",
" return {\"action_type\": \"reply_email\", \"email_id\": \"e01\", \"message_body\": \"Acknowledged, sharing an update shortly.\"}\n",
" if \"m02\" in b:\n",
" return {\"action_type\": \"reschedule_meeting\", \"meeting_id\": \"m02\", \"new_time\": \"2026-04-21T18:00:00\", \"reason\": \"resolve overlap\"}\n",
" if \"t06\" in b:\n",
" return {\"action_type\": \"complete_task\", \"task_id\": \"t06\"}\n",
" return {\"action_type\": \"do_nothing\"}\n",
"\n",
"sft_rows = []\n",
"for b in briefings:\n",
" msgs = build_prompt(b)\n",
" prompt_txt = render_chat(msgs)\n",
" completion_txt = json.dumps(_heuristic_action_for_sft(b), ensure_ascii=True)\n",
" sft_rows.append({\"prompt_text\": prompt_txt, \"completion_text\": completion_txt})\n",
"\n",
"sft_ds = Dataset.from_list(sft_rows)\n",
"sft_cfg = SFTConfig(\n",
" output_dir=str(OUT / \"sft_warmup\"),\n",
" max_steps=30,\n",
" per_device_train_batch_size=1,\n",
" gradient_accumulation_steps=4,\n",
" learning_rate=2e-5,\n",
" logging_steps=5,\n",
" report_to=\"none\",\n",
")\n",
"sft_trainer = SFTTrainer(\n",
" model=policy,\n",
" processing_class=tokenizer,\n",
" train_dataset=sft_ds,\n",
" args=sft_cfg,\n",
" dataset_text_field=\"prompt_text\",\n",
" formatting_func=lambda ex: [f\"{p}{c}\" for p, c in zip(ex[\"prompt_text\"], ex[\"completion_text\"])],\n",
")\n",
"print(\"\\n=== SFT warmup ===\")\n",
"sft_trainer.train()\n",
"policy = sft_trainer.model\n",
"\n",
"\n",
"def grpo_config(name: str, *, temperature: float, num_generations: int, max_steps: int, lr: float) -> GRPOConfig:\n",
" return GRPOConfig(\n",
" output_dir=str(OUT / f\"stage_{name}\"),\n",
" per_device_train_batch_size=1,\n",
" gradient_accumulation_steps=4,\n",
" num_generations=num_generations,\n",
" max_prompt_length=1920,\n",
" max_completion_length=48,\n",
" temperature=temperature,\n",
" learning_rate=lr,\n",
" beta=0.04,\n",
" max_steps=max_steps,\n",
" logging_steps=1,\n",
" bf16=False,\n",
" fp16=True,\n",
" report_to=\"none\",\n",
" save_strategy=\"no\",\n",
" remove_unused_columns=False,\n",
" log_completions=True,\n",
" )\n",
"\n",
"\n",
"def set_curriculum_scales(stage_name: str) -> None:\n",
" global CURRENT_ENV_SCALE, CURRENT_LOCAL_SCALE\n",
" # easy -> full complexity curriculum\n",
" if stage_name == \"B\":\n",
" CURRENT_ENV_SCALE = 0.85\n",
" CURRENT_LOCAL_SCALE = 0.60\n",
" elif stage_name == \"C\":\n",
" CURRENT_ENV_SCALE = 0.95\n",
" CURRENT_LOCAL_SCALE = 0.40\n",
" else:\n",
" CURRENT_ENV_SCALE = 1.00\n",
" CURRENT_LOCAL_SCALE = 0.25\n",
" print(f\"curriculum[{stage_name}] env={CURRENT_ENV_SCALE:.2f} local={CURRENT_LOCAL_SCALE:.2f}\")\n",
"\n",
"\n",
"def run_stage(name: str, **kw) -> None:\n",
" set_curriculum_scales(name)\n",
" print(f\"\\n=== Stage {name} → {kw} ===\")\n",
" trainer = GRPOTrainer(\n",
" model=policy,\n",
" args=grpo_config(name, **kw),\n",
" train_dataset=train_ds,\n",
" reward_funcs=reward_funcs,\n",
" processing_class=tokenizer,\n",
" )\n",
" trainer.train()\n",
" stage_logs[name] = list(trainer.state.log_history)\n",
" adapter_dir = OUT / f\"adapter_stage_{name}\"\n",
" trainer.model.save_pretrained(adapter_dir)\n",
" tokenizer.save_pretrained(adapter_dir)\n",
" print(f\"stage {name} adapter → {adapter_dir}\")\n",
"\n",
"\n",
"run_stage(\"B\", temperature=0.8, num_generations=2, max_steps=20, lr=5e-6)"
]
},
{
"cell_type": "markdown",
"id": "0fe81938",
"metadata": {},
"source": [
"## Phase 6 — Inspect for hacking\n",
"\n",
"Don't trust the mean reward alone. Sample six post-Stage-B completions, parse them, hit the Space live, and print the full trio (completion / parsed action / reward). Look for obviously pathological outputs (repeated identical JSON, prose-only outputs, empty fields)."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "815b4416",
"metadata": {},
"outputs": [],
"source": [
"FastLanguageModel.for_inference(policy)\n",
"for i in range(6):\n",
" brief = briefings[i % len(briefings)]\n",
" prompt_text = render_chat(build_prompt(brief))\n",
" inputs = tokenizer(prompt_text, return_tensors=\"pt\", truncation=True, max_length=MAX_SEQ_LENGTH).to(policy.device)\n",
" out = policy.generate(**inputs, max_new_tokens=128, do_sample=True, temperature=0.7,\n",
" pad_token_id=tokenizer.pad_token_id)\n",
" completion = tokenizer.decode(out[0][inputs[\"input_ids\"].shape[1]:], skip_special_tokens=True)\n",
" act = parse_action(completion)\n",
" env.reset(); r, _ = env.step(act)\n",
" print(f\"\\n--- sample {i} ---\")\n",
" print(\"completion:\", completion.strip()[:200])\n",
" print(\"parsed :\", json.dumps(act))\n",
" print(\"reward :\", round(r, 4))\n",
"FastLanguageModel.for_training(policy)"
]
},
{
"cell_type": "markdown",
"id": "524f6691",
"metadata": {},
"source": [
"## Phase 7 — Add curriculum\n",
"\n",
"The deployed Space scenario is fixed, so curriculum is applied through both:\n",
"\n",
"1. **Exploration schedule** (temperature/lr across stages)\n",
"2. **Complexity curriculum (easy -> full)** via reward scales:\n",
" - Stage B: stronger local scaffold guidance\n",
" - Stage C: mixed guidance\n",
" - Stage D: env-dominant optimization"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e1cdb870",
"metadata": {},
"outputs": [],
"source": [
"run_stage(\"C\", temperature=0.7, num_generations=2, max_steps=25, lr=5e-6)\n",
"run_stage(\"D\", temperature=0.5, num_generations=2, max_steps=15, lr=2e-6)"
]
},
{
"cell_type": "markdown",
"id": "d124a745",
"metadata": {},
"source": [
"## Phase 8 — Train bigger (knobs, not action)\n",
"\n",
"Only after the loop is stable should you scale. If you rent an L4 or A100 with HF credits:\n",
"\n",
"- `MODEL_ID` → `unsloth/Qwen3-4B-Instruct-2507` or `unsloth/Llama-3.1-8B-Instruct`\n",
"- `N_BRIEFINGS` ↑ (more prompt diversity)\n",
"- `num_generations` ↑ and `max_steps` ↑ (more rollouts per prompt, more updates)\n",
"\n",
"All other cells are unchanged. Don't add features until you've watched a full stable run on this small config."
]
},
{
"cell_type": "markdown",
"id": "f8e59da9",
"metadata": {},
"source": [
"## Phase 9 — Save and demo\n",
"\n",
"Re-evaluate on the same `N_EVAL` prompts, plot the before/after + reward curves, save the LoRA adapter (no 4-bit merge per Help Guide §16), and write a compliance manifest."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ebd9908f",
"metadata": {},
"outputs": [],
"source": [
"print(\"Evaluating trained policy ...\")\n",
"trained_rewards = evaluate_policy(policy, n=N_EVAL, temperature=0.2)\n",
"print(\" trained mean:\", sum(trained_rewards) / len(trained_rewards))\n",
"\n",
"def _mean(xs): return sum(xs) / max(len(xs), 1)\n",
"summary = {\n",
" \"random\": _mean(baselines[\"random\"]),\n",
" \"frozen\": _mean(baselines[\"frozen\"]),\n",
" \"trained\": _mean(trained_rewards),\n",
"}\n",
"print(json.dumps(summary, indent=2))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5ccb3832",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd, matplotlib.pyplot as plt\n",
"\n",
"plt.figure(figsize=(6, 4))\n",
"plt.bar(list(summary.keys()), list(summary.values()), color=[\"#888\", \"#1f77b4\", \"#2ca02c\"])\n",
"plt.title(\"Ghostexec: mean reward vs deployed HF Space\")\n",
"plt.ylabel(\"mean episode reward (higher is better)\")\n",
"plt.axhline(0.0, color=\"black\", linewidth=0.5)\n",
"plt.tight_layout()\n",
"plt.savefig(OUT / \"before_after.png\", dpi=150)\n",
"plt.show()\n",
"\n",
"rows = []\n",
"loss_rows = []\n",
"step_counter = 0\n",
"for name, log in stage_logs.items():\n",
" for entry in log:\n",
" r = entry.get(\"rewards/env_reward/mean\", entry.get(\"reward\"))\n",
" if \"loss\" in entry:\n",
" loss_rows.append({\"stage\": name, \"global_step\": step_counter + 1, \"loss\": entry[\"loss\"]})\n",
" if r is None:\n",
" continue\n",
" step_counter += 1\n",
" rows.append({\n",
" \"stage\": name,\n",
" \"global_step\": step_counter,\n",
" \"env\": r,\n",
" \"fmt\": entry.get(\"rewards/format_reward/mean\", 0.0),\n",
" \"semantic\": entry.get(\"rewards/semantic_action_reward/mean\", 0.0),\n",
" \"idle\": entry.get(\"rewards/anti_idle_reward/mean\", 0.0),\n",
" })\n",
"\n",
"df = pd.DataFrame(rows)\n",
"df.to_csv(OUT / \"reward_log.csv\", index=False)\n",
"\n",
"loss_df = pd.DataFrame(loss_rows)\n",
"if not loss_df.empty:\n",
" plt.figure(figsize=(8, 4))\n",
" for name, sub in loss_df.groupby(\"stage\"):\n",
" plt.plot(sub[\"global_step\"], sub[\"loss\"], label=f\"stage {name}\")\n",
" plt.xlabel(\"global step\"); plt.ylabel(\"loss\")\n",
" plt.title(\"Ghostexec SFT+GRPO — loss vs step\")\n",
" plt.legend(); plt.tight_layout()\n",
" plt.savefig(OUT / \"loss_curve.png\", dpi=150); plt.show()\n",
"\n",
"if not df.empty:\n",
" plt.figure(figsize=(8, 4))\n",
" for name, sub in df.groupby(\"stage\"):\n",
" plt.plot(sub[\"global_step\"], sub[\"env\"], label=f\"stage {name}\")\n",
" plt.xlabel(\"global step\"); plt.ylabel(\"mean env_reward\")\n",
" plt.title(\"Ghostexec GRPO — reward vs step (Unsloth)\")\n",
" plt.legend(); plt.tight_layout()\n",
" plt.savefig(OUT / \"reward_curve.png\", dpi=150); plt.show()\n",
"\n",
" plt.figure(figsize=(8, 4))\n",
" plt.plot(df[\"global_step\"], df[\"env\"], label=\"env_reward\")\n",
" plt.plot(df[\"global_step\"], df[\"fmt\"], label=\"format_reward\")\n",
" plt.plot(df[\"global_step\"], df[\"semantic\"], label=\"semantic_action_reward\")\n",
" plt.plot(df[\"global_step\"], df[\"idle\"], label=\"anti_idle_reward\")\n",
" plt.xlabel(\"global step\"); plt.ylabel(\"mean component reward\")\n",
" plt.title(\"Reward components — hacking-watch\")\n",
" plt.legend(); plt.tight_layout()\n",
" plt.savefig(OUT / \"components.png\", dpi=150); plt.show()\n",
"else:\n",
" print(\"No numeric reward log found — skipping curve plots.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "07648f04",
"metadata": {},
"outputs": [],
"source": [
"final_adapter = OUT / \"adapter_final\"\n",
"policy.save_pretrained(final_adapter)\n",
"tokenizer.save_pretrained(final_adapter)\n",
"print(\"final adapter →\", final_adapter)\n",
"\n",
"if HUB_REPO_ID and os.environ.get(\"HF_TOKEN\"):\n",
" from huggingface_hub import HfApi, login\n",
" login(token=os.environ[\"HF_TOKEN\"], add_to_git_credential=False)\n",
" policy.push_to_hub(HUB_REPO_ID, commit_message=f\"ghostexec GRPO adapter ({RUN_NAME})\")\n",
" tokenizer.push_to_hub(HUB_REPO_ID)\n",
" api = HfApi()\n",
" for fname in (\"reward_log.csv\", \"before_after.png\", \"reward_curve.png\", \"components.png\"):\n",
" p = OUT / fname\n",
" if p.exists():\n",
" api.upload_file(path_or_fileobj=str(p), path_in_repo=fname, repo_id=HUB_REPO_ID)\n",
" print(\"pushed adapter + artefacts →\", HUB_REPO_ID)\n",
"else:\n",
" print(\"HUB_REPO_ID / HF_TOKEN not set — skipping push.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "81fdfca3",
"metadata": {},
"outputs": [],
"source": [
"manifest = {\n",
" \"env_url\": GHOSTEXEC_ENV_URL,\n",
" \"model\": MODEL_ID,\n",
" \"run\": RUN_NAME,\n",
" \"stack\": {\"unsloth\": True, \"trl\": \"0.22.2\", \"pipeline\": \"SFT->GRPO\"},\n",
" \"rewards\": {\n",
" \"random_mean\": summary[\"random\"],\n",
" \"frozen_mean\": summary[\"frozen\"],\n",
" \"trained_mean\": summary[\"trained\"],\n",
" \"improvement_vs_frozen\": summary[\"trained\"] - summary[\"frozen\"],\n",
" },\n",
" \"stages\": [\"SFT\"] + list(stage_logs.keys()),\n",
" \"reward_fns\": [\"env_reward\", \"format_reward\", \"semantic_action_reward\", \"anti_idle_reward\"],\n",
" \"curriculum\": {\n",
" \"type\": \"easy_to_full\",\n",
" \"stage_scales\": {\n",
" \"B\": {\"env\": 0.85, \"local\": 0.60},\n",
" \"C\": {\"env\": 0.95, \"local\": 0.40},\n",
" \"D\": {\"env\": 1.00, \"local\": 0.25},\n",
" },\n",
" },\n",
" \"adapter_path\": str(final_adapter),\n",
" \"mean_space_latency_ms\": round(sum(env.latency_ms) / max(len(env.latency_ms), 1), 1),\n",
" \"n_space_calls\": len(env.latency_ms),\n",
"}\n",
"print(json.dumps(manifest, indent=2))\n",
"(OUT / \"manifest.json\").write_text(json.dumps(manifest, indent=2))\n",
"print(\"\\nmanifest →\", OUT / \"manifest.json\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"version": "3.10"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|