File size: 17,386 Bytes
54c5666 | 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 | {
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "title"
},
"source": [
"# 🚀 ULTRATHINK Perfect Training - Google Colab\n",
"\n",
"## ✨ What's New in This Configuration?\n",
"\n",
"This notebook uses the **PERFECT** training configuration that fixes:\n",
"- ✅ **Routing Collapse** (Entropy 0.52 → 0.8-1.2)\n",
"- ✅ **Expert Imbalance** (Max Expert 100% → 50-70%)\n",
"- ✅ **High Auxiliary Loss** (8.0 → 2.0-4.0)\n",
"- ✅ **Slow Convergence** (Better perplexity by step 200)\n",
"\n",
"### 🎯 Key Improvements:\n",
"- **MoE Top-K**: 1 → **2** (prevents single expert dominance)\n",
"- **Load Balance Weight**: 0.01 → **0.1** (10x stronger)\n",
"- **Z-Loss Weight**: 0.001 → **0.0001** (10x weaker)\n",
"- **Expert Capacity**: 1.0 → **1.5** (50% overflow)\n",
"- **Effective Batch Size**: 16 → **64** (4x larger)\n",
"\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "setup"
},
"source": [
"## 📋 Setup Instructions\n",
"\n",
"1. **Runtime**: Go to `Runtime` → `Change runtime type` → Select `GPU` (T4 recommended)\n",
"2. **Upload Project**: Upload the ULTRATHINK project folder or clone from GitHub\n",
"3. **Run Cells**: Execute cells in order\n",
"\n",
"---"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "gpu_check"
},
"outputs": [],
"source": [
"# Check GPU availability\n",
"!nvidia-smi --query-gpu=name,memory.total,memory.free --format=csv,noheader\n",
"\n",
"import torch\n",
"print(f\"\\nPyTorch version: {torch.__version__}\")\n",
"print(f\"CUDA available: {torch.cuda.is_available()}\")\n",
"if torch.cuda.is_available():\n",
" print(f\"CUDA version: {torch.version.cuda}\")\n",
" print(f\"GPU: {torch.cuda.get_device_name(0)}\")\n",
" print(f\"Memory: {torch.cuda.get_device_properties(0).total_memory / 1e9:.2f} GB\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "project_setup"
},
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "mount_drive"
},
"outputs": [],
"source": [
"# Option: Mount Google Drive (uncomment if needed)\n",
"from google.colab import drive\n",
"drive.mount('/content/drive')\n",
"# %cd /content/drive/MyDrive/path/to/UltraThinking-LLM-Training"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "clone_repo"
},
"outputs": [],
"source": [
"# Clone repository (update with your repo URL)\n",
"!git clone https://github.com/vediyappanm/UltraThinking-LLM-Training.git\n",
" %cd UltraThinking-LLM-Training\n",
"\n",
"# Or if already uploaded:\n",
"%cd /content/UltraThinking-LLM-Training\n",
"\n",
"# Verify we're in the right directory\n",
"!ls -la train_ultrathink.py"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "install_deps"
},
"outputs": [],
"source": [
"# Install dependencies\n",
"!pip install -q -r requirements.txt\n",
"\n",
"# Upgrade core packages\n",
"!pip install -q --upgrade pip setuptools wheel\n",
"\n",
"# Install additional packages for Colab\n",
"!pip install -q transformers datasets accelerate\n",
"\n",
"print(\"✓ Dependencies installed successfully!\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "training_section"
},
"source": [
"## 🎯 Perfect Training Configuration\n",
"\n",
"### Expected Results:\n",
"\n",
"| Metric | Before | After (Step 50-100) | Meaning |\n",
"|--------|--------|---------------------|----------|\n",
"| **Entropy** | 0.52 | 0.8-1.2 | More uniform expert selection |\n",
"| **Max Expert %** | 100% | 50-65% | No single expert dominates |\n",
"| **Aux Loss** | 8.0-8.5 | 2.0-4.0 | Routing regularization working |\n",
"| **Perplexity** | 85k → 30k | <5k by step 200 | Faster learning |\n",
"| **Loss** | 11.3 → 10.3 | <8.0 by step 200 | Better optimization |\n",
"\n",
"---"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "train_perfect"
},
"outputs": [],
"source": [
"# ============================================================================\n",
"# PERFECT TRAINING CONFIGURATION\n",
"# ============================================================================\n",
"# This configuration fixes routing collapse and achieves optimal performance\n",
"# ============================================================================\n",
"\n",
"!python train_ultrathink.py \\\n",
" --vocab_size 50257 \\\n",
" --hidden_size 512 \\\n",
" --num_layers 6 \\\n",
" --num_heads 8 \\\n",
" --num_kv_heads 4 \\\n",
" --intermediate_size 2048 \\\n",
" --max_seq_length 256 \\\n",
" --activation swiglu \\\n",
" --enable_moe \\\n",
" --num_knowledge_experts 4 \\\n",
" --num_skill_experts 2 \\\n",
" --num_meta_experts 1 \\\n",
" --num_safety_experts 1 \\\n",
" --moe_top_k 2 \\\n",
" --expert_capacity 1.5 \\\n",
" --load_balance_weight 0.1 \\\n",
" --z_loss_weight 0.0001 \\\n",
" --importance_weight 0.05 \\\n",
" --batch_size 2 \\\n",
" --gradient_accumulation_steps 32 \\\n",
" --learning_rate 0.0001 \\\n",
" --weight_decay 0.1 \\\n",
" --adam_beta1 0.9 \\\n",
" --adam_beta2 0.999 \\\n",
" --warmup_steps 1000 \\\n",
" --max_steps 100000 \\\n",
" --num_epochs 1 \\\n",
" --gradient_clipping 0.5 \\\n",
" --dropout 0.15 \\\n",
" --attention_dropout 0.15 \\\n",
" --gradient_checkpointing \\\n",
" --use_amp \\\n",
" --amp_warmup_steps 500 \\\n",
" --enable_dre \\\n",
" --dre_warmup_steps 1000 \\\n",
" --dataset c4 \\\n",
" --dataset_subset en \\\n",
" --tokenizer_name gpt2 \\\n",
" --streaming \\\n",
" --train_samples 10000 \\\n",
" --val_samples 1000 \\\n",
" --num_workers 2 \\\n",
" --use_mlflow \\\n",
" --mlflow_tracking_uri \"file:./mlruns\" \\\n",
" --mlflow_experiment \"UltraThinking-LLM-Training\" \\\n",
" --run_name \"ultrathink_colab_perfect_v2\" \\\n",
" --perf_log_interval 5 \\\n",
" --eval_frequency 50 \\\n",
" --output_dir \"./outputs/ultrathink_colab_perfect\""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "quick_test"
},
"source": [
"## 🧪 Quick Test Run (Optional)\n",
"\n",
"Run a quick 100-step test to verify everything works before full training.\n",
"\n",
"---"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "train_quick_test"
},
"outputs": [],
"source": [
"# Quick test run (100 steps, ~2-3 minutes)\n",
"!python train_ultrathink.py \\\n",
" --vocab_size 50257 \\\n",
" --hidden_size 256 \\\n",
" --num_layers 2 \\\n",
" --num_heads 4 \\\n",
" --num_kv_heads 2 \\\n",
" --intermediate_size 1024 \\\n",
" --max_seq_length 128 \\\n",
" --enable_moe \\\n",
" --num_knowledge_experts 2 \\\n",
" --num_skill_experts 1 \\\n",
" --num_meta_experts 1 \\\n",
" --num_safety_experts 1 \\\n",
" --moe_top_k 2 \\\n",
" --expert_capacity 2.0 \\\n",
" --load_balance_weight 0.2 \\\n",
" --z_loss_weight 0.00001 \\\n",
" --batch_size 1 \\\n",
" --gradient_accumulation_steps 8 \\\n",
" --learning_rate 0.0001 \\\n",
" --warmup_steps 50 \\\n",
" --max_steps 100 \\\n",
" --num_epochs 1 \\\n",
" --dataset dummy \\\n",
" --train_samples 100 \\\n",
" --val_samples 20 \\\n",
" --eval_frequency 50 \\\n",
" --run_name \"ultrathink_quick_test\" \\\n",
" --output_dir \"./outputs/ultrathink_quick_test\"\n",
"\n",
"print(\"\\n✓ Quick test completed! Check the metrics above.\")\n",
"print(\"If everything looks good, run the full training cell.\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "monitoring"
},
"source": [
"## 📊 Monitoring & Metrics\n",
"\n",
"### What to Watch For:\n",
"\n",
"#### ✅ Good Signs (by step 50):\n",
"- Entropy increases from 0.52 → 0.7+\n",
"- Max expert drops from 100% → 60-70%\n",
"- Auxiliary loss drops from 8.0 → 3-5\n",
"- Loss decreases steadily\n",
"\n",
"#### ⚠️ Warning Signs:\n",
"- Entropy stuck at 0.52 → Increase load_balance_weight\n",
"- Max expert still 100% → Increase expert_capacity\n",
"- Aux loss still >7.0 → Decrease z_loss_weight\n",
"\n",
"#### 🛑 Critical Issues:\n",
"- NaN/Inf losses → Disable AMP temporarily\n",
"- OOM errors → Reduce batch_size or increase gradient_accumulation_steps\n",
"\n",
"---"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "view_logs"
},
"outputs": [],
"source": [
"# View recent training logs\n",
"!tail -n 50 outputs/ultrathink_colab_perfect/training.log 2>/dev/null || echo \"No logs yet\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "mlflow_ui"
},
"outputs": [],
"source": [
"# Start MLflow UI (optional - runs in background)\n",
"# Note: In Colab, you'll need to use ngrok or similar to expose the port\n",
"\n",
"# Install ngrok for port forwarding\n",
"!pip install -q pyngrok\n",
"\n",
"from pyngrok import ngrok\n",
"import threading\n",
"import subprocess\n",
"\n",
"# Start MLflow UI in background\n",
"def start_mlflow():\n",
" subprocess.run([\"mlflow\", \"ui\", \"--backend-store-uri\", \"./mlruns\", \"--port\", \"5000\"])\n",
"\n",
"thread = threading.Thread(target=start_mlflow, daemon=True)\n",
"thread.start()\n",
"\n",
"# Create ngrok tunnel\n",
"public_url = ngrok.connect(5000)\n",
"print(f\"\\n✓ MLflow UI available at: {public_url}\")\n",
"print(\"Click the link above to view training metrics in real-time!\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "checkpoints"
},
"source": [
"## 💾 Checkpoints & Model Export\n",
"\n",
"Download trained models and checkpoints to your local machine or Google Drive.\n",
"\n",
"---"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "list_checkpoints"
},
"outputs": [],
"source": [
"# List available checkpoints\n",
"!ls -lh outputs/ultrathink_colab_perfect/*.pt 2>/dev/null || echo \"No checkpoints yet\"\n",
"!ls -lh outputs/ultrathink_colab_perfect/final_model/ 2>/dev/null || echo \"No final model yet\""
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "download_model"
},
"outputs": [],
"source": [
"# Download model to local machine\n",
"from google.colab import files\n",
"import shutil\n",
"import os\n",
"\n",
"# Create a zip file of the final model\n",
"if os.path.exists(\"outputs/ultrathink_colab_perfect/final_model\"):\n",
" shutil.make_archive(\"ultrathink_final_model\", \"zip\", \"outputs/ultrathink_colab_perfect/final_model\")\n",
" print(\"✓ Model archived as ultrathink_final_model.zip\")\n",
" \n",
" # Download (this may take a while for large models)\n",
" # files.download(\"ultrathink_final_model.zip\")\n",
" print(\"\\nTo download, uncomment the files.download() line above.\")\n",
"else:\n",
" print(\"No final model found yet. Training may still be in progress.\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "save_to_drive"
},
"outputs": [],
"source": [
"# Save to Google Drive (if mounted)\n",
"# Uncomment and modify path as needed\n",
"\n",
"# from google.colab import drive\n",
"# drive.mount('/content/drive')\n",
"\n",
"# import shutil\n",
"# shutil.copytree(\n",
"# \"outputs/ultrathink_colab_perfect\",\n",
"# \"/content/drive/MyDrive/ULTRATHINK_Models/ultrathink_colab_perfect\",\n",
"# dirs_exist_ok=True\n",
"# )\n",
"# print(\"✓ Model saved to Google Drive!\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "inference"
},
"source": [
"## 🎮 Quick Inference Test\n",
"\n",
"Test your trained model with sample text generation.\n",
"\n",
"---"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "test_inference"
},
"outputs": [],
"source": [
"# Quick inference test\n",
"!python scripts/inference.py \\\n",
" --model_path outputs/ultrathink_colab_perfect/final_model \\\n",
" --prompt \"The future of artificial intelligence is\" \\\n",
" --max_length 100 \\\n",
" --temperature 0.8 \\\n",
" --top_p 0.9 2>/dev/null || echo \"Inference script not available or model not ready\""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "troubleshooting"
},
"source": [
"## 🔧 Troubleshooting\n",
"\n",
"### Common Issues:\n",
"\n",
"| Issue | Solution |\n",
"|-------|----------|\n",
"| **OOM Error** | Reduce `--batch_size` to 1, increase `--gradient_accumulation_steps` |\n",
"| **NaN Losses** | Remove `--use_amp` or increase `--amp_warmup_steps` |\n",
"| **Slow Training** | Reduce `--num_workers` to 0 for streaming datasets |\n",
"| **Routing Collapse** | Increase `--load_balance_weight` to 0.15 or 0.2 |\n",
"| **High Aux Loss** | Decrease `--z_loss_weight` to 0.00005 |\n",
"\n",
"### Need Help?\n",
"- Check the [Training Config Guide](Training%20congig.md)\n",
"- Review logs in `outputs/ultrathink_colab_perfect/training.log`\n",
"- Open an issue on GitHub\n",
"\n",
"---"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "footer"
},
"source": [
"## 📚 Additional Resources\n",
"\n",
"- **Documentation**: See `README.md` and `ADVANCED_TRAINING_GUIDE.md`\n",
"- **Architecture**: See `ARCHITECTURE_OVERVIEW.md`\n",
"- **Training Config**: See `Training congig.md`\n",
"\n",
"---\n",
"\n",
"## 🎉 Success Criteria\n",
"\n",
"Your training is successful when:\n",
"\n",
"**By Step 50:**\n",
"- ✓ Entropy > 0.7\n",
"- ✓ Max expert < 70%\n",
"- ✓ Aux loss < 5.0\n",
"\n",
"**By Step 200:**\n",
"- ✓ Loss < 8.0\n",
"- ✓ Perplexity < 5,000\n",
"- ✓ All experts showing 5-40% usage\n",
"\n",
"**By Step 1000:**\n",
"- ✓ Loss < 6.0\n",
"- ✓ Perplexity < 1,000\n",
"- ✓ Stable, consistent improvement\n",
"\n",
"---\n",
"\n",
"**Good luck with your training! 🚀**"
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"gpuType": "T4",
"name": "ULTRATHINK_Perfect_Training_Colab.ipynb",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"version": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
|