fix: Kaggle notebook typo - os.chdir

Fixed typo: nos.chdir -> os.chdir in cell 2

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

kaggle_train_stack29.ipynb

@@ -1 +1,213 @@
-{"cells": [{"cell_type": "markdown", "metadata": {}, "source": ["# \ud83d\ude80 Stack 2.9 - Kaggle Training Notebook\n", "\n", "**Free GPU training on Kaggle**\n", "\n", "This notebook trains a LoRA adapter for Stack 2.9 on **Qwen2.5-Coder-7B** using Kaggle's free GPU.\n", "\n", "\u23f1\ufe0f **Expected runtime:** 2-4 hours\n", "\ud83d\udcbe **VRAM needed:** ~16GB (Kaggle P100 has 16GB)\n", "\n", "---\n", "\n", "**Instructions:**\n", "1. Enable GPU: Settings \u2192 Accelerator \u2192 GPU P100\n", "2. Run cells in order from the top\n", "3. Model auto-downloads if not present\n", "\n", "---"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 2: Clone repo\n", "import os\n", "import shutil\n", "import subprocess\n", "\n", "REPO_DIR = \"/kaggle/working/stack-2.9\"\n", "\n", "if os.path.exists(REPO_DIR):\n", "    shutil.rmtree(REPO_DIR)\n", "\n", "subprocess.run([\"git\", \"clone\", \"https://github.com/my-ai-stack/stack-2.9.git\", REPO_DIR], check=True)\n", "\n", "os.chdir(REPO_DIR)\n", "print(f\"\u2705 Working in: {os.getcwd()}\")"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 3: Install dependencies\n", "import subprocess\n", "subprocess.run([\"pip\", \"install\", \"-q\", \"torch\", \"torchvision\", \"torchaudio\", \"--index-url\", \"https://download.pytorch.org/whl/cu118\"], check=True)\n", "subprocess.run([\"pip\", \"install\", \"-q\", \"transformers\", \"peft\", \"accelerate\", \"datasets\", \"pyyaml\", \"tqdm\", \"scipy\", \"bitsandbytes\"], check=True)\n", "print(\"\u2705 Dependencies installed\")"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 3: Install dependencies\n", "!pip install -q torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118\n", "!pip install -q transformers peft accelerate datasets pyyaml tqdm scipy bitsandbytes\n", "print(\"\u2705 Dependencies installed\")"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 4: Setup paths (MODEL_DIR, OUTPUT_DIR)\n", "import os\n", "\n", "REPO_DIR = \"/kaggle/working/stack-2.9\"\n", "MODEL_DIR = os.path.join(REPO_DIR, \"base_model_qwen7b\")\n", "OUTPUT_DIR = os.path.join(REPO_DIR, \"training_output\")\n", "\n", "print(f\"REPO_DIR: {REPO_DIR}\")\n", "print(f\"MODEL_DIR: {MODEL_DIR}\")\n", "print(f\"OUTPUT_DIR: {OUTPUT_DIR}\")"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 5: Download model (if not exists)\n", "from transformers import AutoModelForCausalLM, AutoTokenizer\n", "\n", "if os.path.exists(os.path.join(MODEL_DIR, \"config.json\")):\n", "    print(\"\u2705 Model already exists, skipping download!\")\n", "else:\n", "    print(\"\u2b07\ufe0f Downloading model (Qwen2.5-Coder-7B)...\")\n", "    print(\"This takes ~10-15 minutes...\")\n", "    tokenizer = AutoTokenizer.from_pretrained(\"Qwen/Qwen2.5-Coder-7B\", trust_remote_code=True)\n", "    tokenizer.save_pretrained(MODEL_DIR)\n", "    model = AutoModelForCausalLM.from_pretrained(\"Qwen/Qwen2.5-Coder-7B\", trust_remote_code=True)\n", "    model.save_pretrained(MODEL_DIR)\n", "    print(\"\u2705 Model downloaded!\")\n", "\n", "import subprocess\n", "subprocess.run([\"ls\", \"-lh\", MODEL_DIR], check=True)"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 6: Create config\n", "import yaml\n", "import os\n", "\n", "os.makedirs(OUTPUT_DIR, exist_ok=True)\n", "\n", "config = {\n", "    'model': {'name': MODEL_DIR, 'trust_remote_code': True, 'torch_dtype': 'float16'},\n", "    'data': {'input_path': './data/final/train.jsonl', 'max_length': 2048},\n", "    'lora': {'r': 16, 'alpha': 32, 'dropout': 0.05,\n", "             'target_modules': ['q_proj', 'k_proj', 'v_proj', 'o_proj'],\n", "             'bias': 'none', 'task_type': 'CAUSAL_LM'},\n", "    'training': {'num_epochs': 1, 'batch_size': 2, 'gradient_accumulation': 4,\n", "                 'learning_rate': 2e-4, 'warmup_steps': 50, 'weight_decay': 0.01,\n", "                 'max_grad_norm': 1.0, 'logging_steps': 5, 'eval_steps': 100,\n", "                 'save_steps': 200, 'save_total_limit': 2, 'fp16': True, 'bf16': False,\n", "                 'gradient_checkpointing': True},\n", "    'output': {'lora_dir': os.path.join(OUTPUT_DIR, 'lora'),\n", "               'merged_dir': os.path.join(OUTPUT_DIR, 'merged')},\n", "    'quantization': {'enabled': False},\n", "    'hardware': {'device': 'cuda', 'num_gpus': 1, 'use_4bit': False, 'use_8bit': False}\n", "}\n", "\n", "config_path = os.path.join(OUTPUT_DIR, \"train_config.yaml\")\n", "with open(config_path, 'w') as f:\n", "    yaml.dump(config, f)\n", "\n", "print(f\"\u2705 Config saved to: {config_path}\")\n", "print(f\"   Device: {config['hardware']['device']}\")"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 7: Train LoRA\n", "import sys\n", "sys.path.insert(0, os.path.join(REPO_DIR, \"stack/training\"))\n", "\n", "print(\"=\"*60)\n", "print(\"STARTING TRAINING\")\n", "print(\"=\"*60)\n", "\n", "from train_lora import train_lora\n", "trainer = train_lora(config_path)\n", "\n", "print(\"=\"*60)\n", "print(\"TRAINING COMPLETED!\")\n", "print(\"=\"*60)"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 8: Merge model\n", "import sys\n", "sys.path.insert(0, os.path.join(REPO_DIR, \"stack/training\"))\n", "from merge_adapter import merge_adapter\n", "\n", "merged_dir = os.path.join(OUTPUT_DIR, \"merged\")\n", "os.makedirs(merged_dir, exist_ok=True)\n", "\n", "merge_config = {\n", "    'model': {'name': MODEL_DIR, 'trust_remote_code': True},\n", "    'output': {'lora_dir': os.path.join(OUTPUT_DIR, 'lora'), 'merged_dir': merged_dir},\n", "    'quantization': {'enabled': False}\n", "}\n", "\n", "merge_cfg_path = os.path.join(OUTPUT_DIR, \"merge_config.yaml\")\n", "with open(merge_cfg_path, 'w') as f:\n", "    yaml.dump(merge_config, f)\n", "\n", "merge_adapter(merge_cfg_path, os.path.join(OUTPUT_DIR, \"lora\"), merged_dir)\n", "\n", "print(f\"\u2705 Merged model saved to: {merged_dir}\")\n", "import subprocess\n", "subprocess.run([\"ls\", \"-lh\", merged_dir], check=True)"]}, {"cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": ["# STEP 9: Done!\n", "print(\"=\"*60)\n", "print(\"\ud83c\udf89 TRAINING COMPLETE!\")\n", "print(\"=\"*60)\n", "print(f\"LoRA adapter: {os.path.join(OUTPUT_DIR, 'lora')}\")\n", "print(f\"Merged model: {os.path.join(OUTPUT_DIR, 'merged')}\")\n", "print(\"\\n\ud83d\udce5 Download from: Kaggle \u2192 Output tab\")"]}], "metadata": {"kaggle": {"accelerator": "gpu", "dataSources": [], "kernelSpec": {"displayName": "Python 3", "language": "python", "name": "python3"}}}, "nbformat": 4, "nbformat_minor": 0}
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# 🚀 Stack 2.9 - Kaggle Training Notebook\n",
+    "\n",
+    "**Free GPU training on Kaggle**\n",
+    "\n",
+    "This notebook trains a LoRA adapter for Stack 2.9 on **Qwen2.5-Coder-7B** using Kaggle's free GPU.\n",
+    "\n",
+    "⏱️ **Expected runtime:** 2-4 hours\n",
+    "💾 **VRAM needed:** ~16GB (Kaggle P100 has 16GB)\n",
+    "\n",
+    "---\n",
+    "\n",
+    "**Instructions:**\n",
+    "1. Enable GPU: Settings → Accelerator → GPU P100\n",
+    "2. Run cells in order from the top\n",
+    "3. Model auto-downloads if not present\n",
+    "\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 1: Check GPU\n",
+    "import subprocess\n",
+    "subprocess.run([\"nvidia-smi\"], check=True)\n",
+    "print(\"✅ GPU ready!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": "# STEP 2: Clone repo and setup paths\nimport os\nimport shutil\nimport subprocess\n\nREPO_DIR = \"/kaggle/working/stack-2.9\"\nMODEL_DIR = os.path.join(REPO_DIR, \"base_model_qwen7b\")\nOUTPUT_DIR = os.path.join(REPO_DIR, \"training_output\")\n\n# Remove old repo if exists\nif os.path.exists(REPO_DIR):\n    shutil.rmtree(REPO_DIR)\n\n# Clone fresh\nsubprocess.run([\"git\", \"clone\", \"https://github.com/my-ai-stack/stack-2.9.git\", REPO_DIR], check=True)\nos.chdir(REPO_DIR)\n\nprint(f\"✅ Working in: {os.getcwd()}\")\nprint(f\"   MODEL_DIR: {MODEL_DIR}\")\nprint(f\"   OUTPUT_DIR: {OUTPUT_DIR}\")"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 3: Install dependencies\n",
+    "import subprocess\n",
+    "\n",
+    "subprocess.run([\"pip\", \"install\", \"-q\", \"torch\", \"torchvision\", \"torchaudio\", \"--index-url\", \"https://download.pytorch.org/whl/cu118\"], check=True)\n",
+    "subprocess.run([\"pip\", \"install\", \"-q\", \"transformers\", \"peft\", \"accelerate\", \"datasets\", \"pyyaml\", \"tqdm\", \"scipy\", \"bitsandbytes\"], check=True)\n",
+    "print(\"✅ Dependencies installed\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 4: Download model (if not exists)\n",
+    "from transformers import AutoModelForCausalLM, AutoTokenizer\n",
+    "import os\n",
+    "\n",
+    "if os.path.exists(os.path.join(MODEL_DIR, \"config.json\")):\n",
+    "    print(\"✅ Model already exists, skipping download!\")\n",
+    "else:\n",
+    "    print(\"⬇️ Downloading model (Qwen2.5-Coder-7B)...\")\n",
+    "    print(\"This takes ~10-15 minutes...\")\n",
+    "    \n",
+    "    tokenizer = AutoTokenizer.from_pretrained(\"Qwen/Qwen2.5-Coder-7B\", trust_remote_code=True)\n",
+    "    tokenizer.save_pretrained(MODEL_DIR)\n",
+    "    \n",
+    "    model = AutoModelForCausalLM.from_pretrained(\"Qwen/Qwen2.5-Coder-7B\", trust_remote_code=True)\n",
+    "    model.save_pretrained(MODEL_DIR)\n",
+    "    \n",
+    "    print(\"✅ Model downloaded!\")\n",
+    "\n",
+    "print(\"\\nModel files:\")\n",
+    "os.listdir(MODEL_DIR)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 5: Create config with train_dir and eval_dir\n",
+    "import yaml\n",
+    "import os\n",
+    "\n",
+    "os.makedirs(OUTPUT_DIR, exist_ok=True)\n",
+    "\n",
+    "config = {\n",
+    "    'model': {'name': MODEL_DIR, 'trust_remote_code': True, 'torch_dtype': 'float16'},\n",
+    "    'data': {\n",
+    "        'input_path': os.path.join(REPO_DIR, 'data/final/train.jsonl'),\n",
+    "        'train_dir': None,\n",
+    "        'eval_dir': None,\n",
+    "        'max_length': 2048,\n",
+    "        'train_split': 0.9,\n",
+    "        'test_split': 0.1\n",
+    "    },\n",
+    "    'lora': {'r': 16, 'alpha': 32, 'dropout': 0.05,\n",
+    "             'target_modules': ['q_proj', 'k_proj', 'v_proj', 'o_proj'],\n",
+    "             'bias': 'none', 'task_type': 'CAUSAL_LM'},\n",
+    "    'training': {'num_epochs': 1, 'batch_size': 2, 'gradient_accumulation': 4,\n",
+    "                 'learning_rate': 2e-4, 'warmup_steps': 50, 'weight_decay': 0.01,\n",
+    "                 'max_grad_norm': 1.0, 'logging_steps': 5, 'eval_steps': 100,\n",
+    "                 'save_steps': 200, 'save_total_limit': 2, 'fp16': True, 'bf16': False,\n",
+    "                 'gradient_checkpointing': True},\n",
+    "    'output': {'lora_dir': os.path.join(OUTPUT_DIR, 'lora'),\n",
+    "               'merged_dir': os.path.join(OUTPUT_DIR, 'merged')},\n",
+    "    'quantization': {'enabled': False},\n",
+    "    'hardware': {'device': 'cuda', 'num_gpus': 1, 'use_4bit': False, 'use_8bit': False}\n",
+    "}\n",
+    "\n",
+    "config_path = os.path.join(OUTPUT_DIR, \"train_config.yaml\")\n",
+    "with open(config_path, 'w') as f:\n",
+    "    yaml.dump(config, f)\n",
+    "\n",
+    "print(f\"✅ Config saved to: {config_path}\")\n",
+    "print(f\"   Device: {config['hardware']['device']}\")\n",
+    "print(f\"   Data: {config['data']['input_path']}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 6: Train LoRA\n",
+    "import sys\n",
+    "sys.path.insert(0, os.path.join(REPO_DIR, \"stack/training\"))\n",
+    "\n",
+    "print(\"=\"*60)\n",
+    "print(\"STARTING TRAINING\")\n",
+    "print(\"=\"*60)\n",
+    "\n",
+    "from train_lora import train_lora\n",
+    "trainer = train_lora(config_path)\n",
+    "\n",
+    "print(\"=\"*60)\n",
+    "print(\"TRAINING COMPLETED!\")\n",
+    "print(\"=\"*60)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 7: Merge model\n",
+    "import sys\n",
+    "sys.path.insert(0, os.path.join(REPO_DIR, \"stack/training\"))\n",
+    "from merge_adapter import merge_adapter\n",
+    "\n",
+    "merged_dir = os.path.join(OUTPUT_DIR, \"merged\")\n",
+    "os.makedirs(merged_dir, exist_ok=True)\n",
+    "\n",
+    "merge_config = {\n",
+    "    'model': {'name': MODEL_DIR, 'trust_remote_code': True},\n",
+    "    'output': {'lora_dir': os.path.join(OUTPUT_DIR, 'lora'), 'merged_dir': merged_dir},\n",
+    "    'quantization': {'enabled': False}\n",
+    "}\n",
+    "\n",
+    "merge_cfg_path = os.path.join(OUTPUT_DIR, \"merge_config.yaml\")\n",
+    "with open(merge_cfg_path, 'w') as f:\n",
+    "    yaml.dump(merge_config, f)\n",
+    "\n",
+    "merge_adapter(merge_cfg_path, os.path.join(OUTPUT_DIR, \"lora\"), merged_dir)\n",
+    "\n",
+    "print(f\"✅ Merged model saved to: {merged_dir}\")\n",
+    "print(\"Files:\", os.listdir(merged_dir))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 8: Done!\n",
+    "print(\"=\"*60)\n",
+    "print(\"🎉 TRAINING COMPLETE!\")\n",
+    "print(\"=\"*60)\n",
+    "print(f\"LoRA adapter: {os.path.join(OUTPUT_DIR, 'lora')}\")\n",
+    "print(f\"Merged model: {os.path.join(OUTPUT_DIR, 'merged')}\")\n",
+    "print(\"\\n📥 Download from: Kaggle → Output tab\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kaggle": {
+   "accelerator": "gpu",
+   "dataSources": [],
+   "kernelSpec": {
+    "displayName": "Python 3",
+    "language": "python",
+    "name": "python3"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}