Upgrade CH fine-tuning to Qwen2.5-32B-Instruct

- Base model: Qwen/Qwen2.5-32B-Instruct (vs 7B previously)
- Batch: 1 + grad_accum=16, LR=1e-4 tuned for 32B on A100 80GB
- HF_TOKEN via Colab Secrets (no hardcoded credentials)
- Runtime requirement: A100 80GB (Colab Pro+)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

notebooks/ch_trader_finetune.ipynb

@@ -22,20 +22,7 @@
    "cell_type": "markdown",
    "id": "title",
    "metadata": {},
-   "source": [
-    "# StockEx Clearing House — LLM Fine-Tuning\n",
-    "\n",
-    "Fine-tunes **Qwen/Qwen2.5-7B-Instruct** with QLoRA to act as a clearing house trading agent.\n",
-    "\n",
-    "Given a member's capital, holdings, and live market BBO, the model outputs a valid JSON trading decision.\n",
-    "\n",
-    "**Output model:** `RayMelius/stockex-ch-trader` on HuggingFace Hub\n",
-    "\n",
-    "---\n",
-    "**Runtime:** GPU → A100 recommended (fits on T4 with batch_size=1)\n",
-    "\n",
-    "**Required secret:** `HF_TOKEN` with write access to `RayMelius/`"
-   ]
+   "source": "# StockEx Clearing House — LLM Fine-Tuning\n\nFine-tunes **Qwen/Qwen2.5-32B-Instruct** with QLoRA to act as a clearing house trading agent.\n\nGiven a member's capital, holdings, and live market BBO, the model outputs a valid JSON trading decision.\n\n**Output model:** `RayMelius/stockex-ch-trader` on HuggingFace Hub\n\n---\n**Runtime:** GPU → A100 80GB (Colab Pro+)  \n**Required secret:** Add `HF_TOKEN` in Colab → Secrets (🔑 icon in left sidebar)"
   },
   {
    "cell_type": "code",
@@ -84,30 +71,7 @@
    "id": "config",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "# ── Configuration ─────────────────────────────────────────────────────────────\n",
-    "BASE_MODEL   = \"Qwen/Qwen2.5-7B-Instruct\"\n",
-    "OUTPUT_REPO  = \"RayMelius/stockex-ch-trader\"\n",
-    "OUTPUT_DIR   = \"./stockex-ch-trader\"\n",
-    "\n",
-    "# Lora\n",
-    "LORA_R       = 16\n",
-    "LORA_ALPHA   = 32\n",
-    "LORA_DROPOUT = 0.05\n",
-    "\n",
-    "# Training\n",
-    "NUM_EPOCHS   = 3\n",
-    "BATCH_SIZE   = 4        # reduce to 1 on T4\n",
-    "GRAD_ACCUM   = 4        # effective batch = BATCH_SIZE * GRAD_ACCUM\n",
-    "LR           = 2e-4\n",
-    "MAX_SEQ_LEN  = 512\n",
-    "DATASET_SIZE = 2500     # synthetic training examples\n",
-    "\n",
-    "# HuggingFace login\n",
-    "HF_TOKEN = os.getenv(\"HF_TOKEN\") or input(\"Enter your HF token: \")\n",
-    "login(token=HF_TOKEN)\n",
-    "print(\"Logged in to HuggingFace Hub\")"
-   ]
+   "source": "# ── Configuration ─────────────────────────────────────────────────────────────\nBASE_MODEL   = \"Qwen/Qwen2.5-32B-Instruct\"\nOUTPUT_REPO  = \"RayMelius/stockex-ch-trader\"\nOUTPUT_DIR   = \"./stockex-ch-trader\"\n\n# LoRA\nLORA_R       = 16\nLORA_ALPHA   = 32\nLORA_DROPOUT = 0.05\n\n# Training  (32B needs smaller batch; effective batch = 1 × 16 = 16)\nNUM_EPOCHS   = 3\nBATCH_SIZE   = 1\nGRAD_ACCUM   = 16\nLR           = 1e-4\nMAX_SEQ_LEN  = 512\nDATASET_SIZE = 2500\n\n# HuggingFace token — reads from Colab Secrets first, then env var\ntry:\n    from google.colab import userdata\n    HF_TOKEN = userdata.get(\"HF_TOKEN\")\n    print(\"HF_TOKEN loaded from Colab Secrets\")\nexcept Exception:\n    HF_TOKEN = os.getenv(\"HF_TOKEN\", \"\")\n\nif not HF_TOKEN:\n    raise ValueError(\"HF_TOKEN not found. Add it in Colab → Secrets (🔑).\")\n\nfrom huggingface_hub import login\nlogin(token=HF_TOKEN)\nprint(\"Logged in to HuggingFace Hub\")"
   },
   {
    "cell_type": "markdown",
@@ -538,20 +502,7 @@
    "id": "push-hub",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "print(f\"Pushing merged model to: {OUTPUT_REPO}\")\n",
-    "merged_model.push_to_hub(\n",
-    "    OUTPUT_REPO,\n",
-    "    token=HF_TOKEN,\n",
-    "    commit_message=\"StockEx CH Trader: QLoRA fine-tuned Qwen2.5-7B-Instruct\",\n",
-    ")\n",
-    "tokenizer.push_to_hub(\n",
-    "    OUTPUT_REPO,\n",
-    "    token=HF_TOKEN,\n",
-    "    commit_message=\"Tokenizer for StockEx CH Trader\",\n",
-    ")\n",
-    "print(f\"Model pushed to https://huggingface.co/{OUTPUT_REPO}\")"
-   ]
+   "source": "print(f\"Pushing merged model to: {OUTPUT_REPO}\")\nmerged_model.push_to_hub(\n    OUTPUT_REPO,\n    token=HF_TOKEN,\n    commit_message=\"StockEx CH Trader: QLoRA fine-tuned Qwen2.5-32B-Instruct\",\n)\ntokenizer.push_to_hub(\n    OUTPUT_REPO,\n    token=HF_TOKEN,\n    commit_message=\"Tokenizer for StockEx CH Trader (Qwen2.5-32B-Instruct base)\",\n)\nprint(f\"✓ Model pushed to https://huggingface.co/{OUTPUT_REPO}\")"
   },
   {
    "cell_type": "markdown",
@@ -678,4 +629,4 @@
    ]
   }
  ]
-}
+}