Spaces:
Paused
Paused
File size: 14,382 Bytes
bc35a94 | 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 | {
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# EnterpriseHPC-v0 + Qwen2.5-Coder-7B GRPO on Colab / Kaggle\n",
"\n",
"This notebook post-trains `Qwen/Qwen2.5-Coder-7B-Instruct` with TRL GRPO\n",
"on the `EnterpriseHPC-v0` environment. The env simulates a Rocky Linux\n",
"HPC cluster (login + compute-01 nodes, mock Slurm state machine, Open\n",
"OnDemand Apache portal, mock NFS share, mock NVIDIA GPUs) inside a\n",
"single user-namespace sandbox with sub-10 ms overlay resets.\n",
"\n",
"Scenarios (six remediation incidents in the **Theme #3.1 World\n",
"Modeling / Professional Tasks** bucket, aligned with the Scaler AI Labs\n",
"Multi-App RL Environment sub-theme):\n",
"- `hpc_outage` — broken compute node network route, `slurmd` down\n",
"- `hpc_munge` — corrupt/permission-broken `munge.key`, auth failures\n",
"- `hpc_pid_stale` — stale `/var/run/slurmd.pid` blocks service start\n",
"- `hpc_gpu_ecc` — GPU ECC volatile errors, node drained, need `nvidia-smi -r`\n",
"- `hpc_nfs_stale` — `/mnt/shared` stale NFS handle, umount/remount dance\n",
"- `hpc_ood_apache` — Open OnDemand Apache portal config typo on :8081\n",
"\n",
"Three round-1 legacy tasks (`nginx_crash`, `disk_full`, `network_broken`)\n",
"are retained as a **warm-up curriculum tier** for difficulty ramping,\n",
"not as a separate theme claim.\n",
"\n",
"Two training paths are supported:\n",
"- **Local**: run the sandbox inside the Colab / Kaggle runtime via `train_hpc_outage.py`\n",
"- **Remote**: train against one or more Hugging Face Spaces hosting the openenv server via `hpc_openenv_gemma.py`. This is the exact shape of the TRL + OpenEnv launch example (the CARLA driving notebook) but for HPC incidents, with a code-tuned Qwen policy in place of Gemma 4.\n",
"\n",
"Prereqs\n",
"- Colab or Kaggle runtime with a GPU. Qwen2.5-Coder-7B fits in 4-bit QLoRA on a single A100 (Kaggle free tier). On T4/L4 use `--model Qwen/Qwen2.5-Coder-3B-Instruct` and `--group-size 2`. Python 3.12+ is required\n",
"- `HF_TOKEN` in Colab/Kaggle secrets (model is open but token unlocks uploads)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1 System dependencies"
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"%%bash\n",
"set -euxo pipefail\n",
"apt-get update -qq\n",
"apt-get install -y -qq bubblewrap fuse-overlayfs fuse3 tini coreutils\n",
"bwrap --version\n",
"fuse-overlayfs --version || true"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2 Clone the repo and install python deps"
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"%%bash\n",
"set -euxo pipefail\n",
"if [ ! -d low-taper-fade-openenv-scaler ]; then\n",
" git clone https://github.com/your-org/low-taper-fade-openenv-scaler.git\n",
"fi\n",
"cd low-taper-fade-openenv-scaler\n",
"python --version\n",
"pip install -q --upgrade pip setuptools wheel\n",
"pip install -q -e '.[train]'\n",
"pip install -q --no-deps 'unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git'\n",
"pip install -q 'unsloth-zoo' wandb\n",
"python -c \"import torch, transformers, trl, unsloth, gymnasium, fastapi; print('torch', torch.__version__, 'transformers', transformers.__version__, 'trl', trl.__version__, 'unsloth', unsloth.__version__, 'gymnasium', gymnasium.__version__, 'fastapi', fastapi.__version__)\""
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {},
"source": [
"%cd low-taper-fade-openenv-scaler"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3 Prove the environment is solvable (gold trajectory verifier)"
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"!python -m tools.verify_gold_trajectory -v"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 4 Benchmark reset latency"
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"!python -m bench.bench_reset -n 200"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 5 Leaderboard (gold vs random vs bad policies)"
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"!python -m eval.eval_suite --trials 3 --output-dir ./runs/eval \\\n",
" --scenarios hpc_outage,hpc_munge,hpc_pid_stale,hpc_gpu_ecc,hpc_nfs_stale,hpc_ood_apache\n",
"!cat ./runs/eval/leaderboard.md"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 6 Reward-curve demo (gpu-free, proves reward improvement)\n",
"\n",
"This replays a curriculum-annealed reward probe against the\n",
"grader and plots `reward_mean`, `solve_rate`, `terminal_health` over\n",
"simulated policy improvement steps. It is the evidence the judges want\n",
"under the **Showing Improvement in Rewards (20%)** rubric and it runs\n",
"in under a minute without a GPU or `bwrap`."
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"!python -m tools.reward_curve_demo --num-steps 24 --rollouts-per-step 12\n",
"from IPython.display import Image, display\n",
"display(Image('docs/assets/reward_curve_demo.png'))"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 7 Dry-run rollout inside the real sandbox (no GPU required)"
],
"id": "80b68a95"
},
{
"cell_type": "code",
"metadata": {},
"source": [
"!python -m training.train_hpc_outage --dry-run --group-size 2 --max-turns 8 --output-dir ./runs/dry \\\n",
" --scenarios hpc_outage,hpc_munge,hpc_pid_stale,hpc_gpu_ecc,hpc_nfs_stale,hpc_ood_apache"
],
"execution_count": null,
"outputs": [],
"id": "2c7f23b4"
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 8 Option A: local GRPO training with Qwen2.5-Coder-7B\n",
"\n",
"On a T4 swap to `--model Qwen/Qwen2.5-Coder-3B-Instruct --group-size 2 --max-turns 8`. On a Kaggle / Colab A100 keep the 7B and go `--group-size 4 --max-turns 16`. All six HPC scenarios are mixed into the rollout pool so GRPO learns a single policy across the whole incident catalogue."
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"%env TRANSFORMERS_VERBOSITY=error\n",
"%env TOKENIZERS_PARALLELISM=false\n",
"!python -m training.train_hpc_outage \\\n",
" --model Qwen/Qwen2.5-Coder-7B-Instruct \\\n",
" --output-dir ./runs/hpc_grpo_local \\\n",
" --group-size 4 \\\n",
" --max-turns 12 \\\n",
" --num-train-steps 100 \\\n",
" --max-new-tokens 512 \\\n",
" --max-seq-length 8192 \\\n",
" --learning-rate 1e-5 \\\n",
" --curriculum --save-adapter-only \\\n",
" --scenarios hpc_outage,hpc_munge,hpc_pid_stale,hpc_gpu_ecc,hpc_nfs_stale,hpc_ood_apache \\\n",
" --report-to tensorboard"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 9 Option B: remote GRPO training against a Hugging Face Space\n",
"\n",
"Deploy `Dockerfile` to an HF Space first (see `docs/hf_spaces_deploy.md`). Then:"
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"import os\n",
"os.environ.setdefault('ENV_URLS', 'https://your-user-enterprise-hpc-openenv.hf.space')\n",
"!python -m training.hpc_openenv_gemma \\\n",
" --env-urls ${ENV_URLS} \\\n",
" --model Qwen/Qwen2.5-Coder-7B-Instruct \\\n",
" --output-dir ./runs/hpc_grpo_remote \\\n",
" --group-size 4 --max-turns 20 --num-train-steps 100 \\\n",
" --max-new-tokens 512 --max-seq-length 8192 \\\n",
" --curriculum --save-adapter-only \\\n",
" --scenarios hpc_outage,hpc_munge,hpc_pid_stale,hpc_gpu_ecc,hpc_nfs_stale,hpc_ood_apache \\\n",
" --report-to tensorboard"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 10 Plot the real GRPO reward curve"
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"import json, matplotlib.pyplot as plt\n",
"from pathlib import Path\n",
"metrics = []\n",
"for p in Path('./runs').rglob('*.metrics.jsonl'):\n",
" for line in p.read_text().strip().splitlines():\n",
" m = json.loads(line); m['source']=p.parent.name; metrics.append(m)\n",
"if not metrics:\n",
" print('no metrics found yet — run section 8 (local) or section 9 (remote) first')\n",
"else:\n",
" import collections\n",
" by_run = collections.defaultdict(list)\n",
" for m in metrics: by_run[m['source']].append(m)\n",
" fig, ax = plt.subplots(1, 2, figsize=(12,4))\n",
" for run, rows in by_run.items():\n",
" rows.sort(key=lambda r: r['step'])\n",
" ax[0].plot([r['step'] for r in rows], [r['solve_rate'] for r in rows], label=run)\n",
" ax[1].plot([r['step'] for r in rows], [r['reward_mean'] for r in rows], label=run)\n",
" ax[0].set_title('solve_rate over GRPO steps'); ax[0].legend(); ax[0].set_ylim(0,1)\n",
" ax[1].set_title('reward_mean over GRPO steps'); ax[1].legend(); ax[1].set_ylim(0,1)\n",
" plt.tight_layout(); plt.show()"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 11 Inspect the trained agent transcripts\n",
"\n",
"Run a single rollout with the trained adapter and save the transcript. These are the clips you want in the pitch and video."
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"import json, os\n",
"from pathlib import Path\n",
"from training.rollout import run_interactive_group\n",
"from hpc_gym import EnterpriseHPCEnv\n",
"from unsloth import FastLanguageModel\n",
"import torch\n",
"\n",
"ckpt = './runs/hpc_grpo_local'\n",
"if not Path(ckpt).exists():\n",
" ckpt = 'Qwen/Qwen2.5-Coder-7B-Instruct'\n",
"model, tokenizer = FastLanguageModel.from_pretrained(model_name=ckpt, max_seq_length=4096, load_in_4bit=True)\n",
"FastLanguageModel.for_inference(model)\n",
"\n",
"def generate_fn(batch_messages):\n",
" texts = [tokenizer.apply_chat_template(m, tokenize=False, add_generation_prompt=True) for m in batch_messages]\n",
" inputs = tokenizer(texts, return_tensors='pt', padding=True, truncation=True, max_length=4096).to(model.device)\n",
" with torch.inference_mode():\n",
" out = model.generate(**inputs, do_sample=True, temperature=0.7, top_p=0.95, max_new_tokens=256,\n",
" pad_token_id=tokenizer.pad_token_id or tokenizer.eos_token_id)\n",
" new = out[:, inputs['input_ids'].shape[1]:]\n",
" return tokenizer.batch_decode(new, skip_special_tokens=True)\n",
"\n",
"records = run_interactive_group(\n",
" group_size=4,\n",
" generate_fn=generate_fn,\n",
" env_factory=lambda: EnterpriseHPCEnv(scenario_pool=[\n",
" 'hpc_outage','hpc_munge','hpc_pid_stale',\n",
" 'hpc_gpu_ecc','hpc_nfs_stale','hpc_ood_apache',\n",
" ]),\n",
" max_turns=16,\n",
")\n",
"for r in records:\n",
" print('task', r.task_id, 'reward', r.reward, 'steps', r.steps, 'health', r.grader_health)\n",
"\n",
"os.makedirs('./runs/eval_trained', exist_ok=True)\n",
"with open('./runs/eval_trained/transcripts.json', 'w') as f:\n",
" json.dump([r.__dict__ for r in records], f, indent=2, default=str)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 12 (Optional) push artifacts to the Hub\n",
"\n",
"Upload adapter weights, metrics jsonl, and leaderboard to a model repo so judges can load them."
]
},
{
"cell_type": "code",
"metadata": {},
"source": [
"from huggingface_hub import HfApi, create_repo\n",
"import os\n",
"repo_id = os.environ.get('HF_HUB_REPO', 'your-user/hpc-grpo-runs')\n",
"api = HfApi(token=os.environ.get('HF_TOKEN'))\n",
"create_repo(repo_id, exist_ok=True, token=api.token)\n",
"api.upload_folder(folder_path='./runs/hpc_grpo_local', repo_id=repo_id, path_in_repo='hpc_grpo_local')"
],
"execution_count": null,
"outputs": []
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"version": "3.11"
}
},
"nbformat": 4,
"nbformat_minor": 5
} |