tribunal-kit 9.2.3 → 9.2.4

package/.agents/skills/huggingface-llm-trainer/scripts/train_dpo_example.py

@@ -0,0 +1,106 @@
+#!/usr/bin/env python3
+# /// script
+# requires-python = ">=3.10"
+# dependencies = [
+#     "trl>=0.12.0",
+#     "transformers>=4.36.0",
+#     "accelerate>=0.24.0",
+#     "trackio",
+# ]
+# ///
+
+"""
+Production-ready DPO training example for preference learning.
+
+DPO (Direct Preference Optimization) trains models on preference pairs
+(chosen vs rejected responses) without requiring a reward model.
+
+Usage with hf_jobs MCP tool:
+    hf_jobs("uv", {
+        "script": '''<paste this entire file>''',
+        "flavor": "a10g-large",
+        "timeout": "3h",
+        "secrets": {"HF_TOKEN": "$HF_TOKEN"},
+    })
+
+Or submit the script content directly inline without saving to a file.
+"""
+
+import trackio
+from datasets import load_dataset
+from trl import DPOTrainer, DPOConfig
+
+
+# Load preference dataset
+print("📦 Loading dataset...")
+dataset = load_dataset("trl-lib/ultrafeedback_binarized", split="train")
+print(f"✅ Dataset loaded: {len(dataset)} preference pairs")
+
+# Create train/eval split
+print("🔀 Creating train/eval split...")
+dataset_split = dataset.train_test_split(test_size=0.1, seed=42)
+train_dataset = dataset_split["train"]
+eval_dataset = dataset_split["test"]
+print(f"   Train: {len(train_dataset)} pairs")
+print(f"   Eval: {len(eval_dataset)} pairs")
+
+# Training configuration
+config = DPOConfig(
+    # CRITICAL: Hub settings
+    output_dir="qwen-dpo-aligned",
+    push_to_hub=True,
+    hub_model_id="username/qwen-dpo-aligned",
+    hub_strategy="every_save",
+
+    # DPO-specific parameters
+    beta=0.1,  # KL penalty coefficient (higher = stay closer to reference)
+
+    # Training parameters
+    num_train_epochs=1,  # DPO typically needs fewer epochs than SFT
+    per_device_train_batch_size=4,
+    gradient_accumulation_steps=4,
+    learning_rate=5e-7,  # DPO uses much lower LR than SFT
+    # max_length=1024,  # Default - only set if you need different sequence length
+
+    # Logging & checkpointing
+    logging_steps=10,
+    save_strategy="steps",
+    save_steps=100,
+    save_total_limit=2,
+
+    # Evaluation - IMPORTANT: Only enable if eval_dataset provided
+    eval_strategy="steps",
+    eval_steps=100,
+
+    # Optimization
+    warmup_ratio=0.1,
+    lr_scheduler_type="cosine",
+
+    # Monitoring
+    report_to="trackio",  # Integrate with Trackio
+    project="meaningful_project_name", # project name for the training name (trackio)
+    run_name="baseline-run", #Descriptive name for this training run
+
+)
+
+# Initialize and train
+# Note: DPO requires an instruct-tuned model as the base
+print("🎯 Initializing trainer...")
+trainer = DPOTrainer(
+    model="Qwen/Qwen2.5-0.5B-Instruct",  # Use instruct model, not base model
+    train_dataset=train_dataset,
+    eval_dataset=eval_dataset,  # CRITICAL: Must provide eval_dataset when eval_strategy is enabled
+    args=config,
+)
+
+print("🚀 Starting DPO training...")
+trainer.train()
+
+print("💾 Pushing to Hub...")
+trainer.push_to_hub()
+
+# Finish Trackio tracking
+trackio.finish()
+
+print("✅ Complete! Model at: https://huggingface.co/username/qwen-dpo-aligned")
+print("📊 View metrics at: https://huggingface.co/spaces/username/trackio")

package/.agents/skills/huggingface-llm-trainer/scripts/train_grpo_example.py

@@ -0,0 +1,89 @@
+#!/usr/bin/env python3
+# /// script
+# requires-python = ">=3.10"
+# dependencies = [
+#     "trl>=0.12.0",
+#     "transformers>=4.36.0",
+#     "accelerate>=0.24.0",
+#     "trackio",
+# ]
+# ///
+
+"""
+Production-ready GRPO training example for online RL.
+
+GRPO (Group Relative Policy Optimization) is an online RL method that
+optimizes relative to group performance. Best for tasks with automatic
+reward signals like code execution or math verification.
+
+Usage with hf_jobs MCP tool:
+    hf_jobs("uv", {
+        "script": '''<paste this entire file>''',
+        "flavor": "a10g-large",
+        "timeout": "4h",
+        "secrets": {"HF_TOKEN": "$HF_TOKEN"},
+    })
+
+Or submit the script content directly inline without saving to a file.
+
+Note: For most GRPO use cases, the TRL maintained script is recommended:
+    https://raw.githubusercontent.com/huggingface/trl/main/examples/scripts/grpo.py
+"""
+
+import trackio
+from datasets import load_dataset
+from trl import GRPOTrainer, GRPOConfig
+
+
+# Load dataset (GRPO uses prompt-only format)
+dataset = load_dataset("trl-lib/math_shepherd", split="train")
+print(f"✅ Dataset loaded: {len(dataset)} prompts")
+
+# Training configuration
+config = GRPOConfig(
+    # CRITICAL: Hub settings
+    output_dir="qwen-grpo-math",
+    push_to_hub=True,
+    hub_model_id="username/qwen-grpo-math",
+    hub_strategy="every_save",
+
+    # Training parameters
+    num_train_epochs=1,
+    per_device_train_batch_size=4,
+    gradient_accumulation_steps=4,
+    learning_rate=1e-6,
+
+    # Logging & checkpointing
+    logging_steps=10,
+    save_strategy="steps",
+    save_steps=100,
+    save_total_limit=2,
+
+    # Optimization
+    warmup_ratio=0.1,
+    lr_scheduler_type="cosine",
+
+    # Monitoring
+    report_to="trackio",  # Integrate with Trackio
+    project="meaningful_project_name", # project name for the training name (trackio)
+    run_name="baseline-run", #Descriptive name for this training run
+
+)
+
+# Initialize and train
+# Note: GRPO requires an instruct-tuned model as the base
+trainer = GRPOTrainer(
+    model="Qwen/Qwen2.5-0.5B-Instruct",
+    train_dataset=dataset,
+    args=config,
+)
+
+print("🚀 Starting GRPO training...")
+trainer.train()
+
+print("💾 Pushing to Hub...")
+trainer.push_to_hub()
+
+
+print("✅ Complete! Model at: https://huggingface.co/username/qwen-grpo-math")
+print("📊 View metrics at: https://huggingface.co/spaces/username/trackio")

package/.agents/skills/huggingface-llm-trainer/scripts/train_sft_example.py

@@ -0,0 +1,122 @@
+#!/usr/bin/env python3
+# /// script
+# requires-python = ">=3.10"
+# dependencies = [
+#     "trl>=0.12.0",
+#     "peft>=0.7.0",
+#     "transformers>=4.36.0",
+#     "accelerate>=0.24.0",
+#     "trackio",
+# ]
+# ///
+
+"""
+Production-ready SFT training example with all best practices.
+
+This script demonstrates:
+- Trackio integration for real-time monitoring
+- LoRA/PEFT for efficient training
+- Proper Hub saving configuration
+- Train/eval split for monitoring
+- Checkpoint management
+- Optimized training parameters
+
+Usage with hf_jobs MCP tool:
+    hf_jobs("uv", {
+        "script": '''<paste this entire file>''',
+        "flavor": "a10g-large",
+        "timeout": "3h",
+        "secrets": {"HF_TOKEN": "$HF_TOKEN"},
+    })
+
+Or submit the script content directly inline without saving to a file.
+"""
+
+import trackio
+from datasets import load_dataset
+from peft import LoraConfig
+from trl import SFTTrainer, SFTConfig
+
+
+# Load dataset
+print("📦 Loading dataset...")
+dataset = load_dataset("trl-lib/Capybara", split="train")
+print(f"✅ Dataset loaded: {len(dataset)} examples")
+
+# Create train/eval split
+print("🔀 Creating train/eval split...")
+dataset_split = dataset.train_test_split(test_size=0.1, seed=42)
+train_dataset = dataset_split["train"]
+eval_dataset = dataset_split["test"]
+print(f"   Train: {len(train_dataset)} examples")
+print(f"   Eval: {len(eval_dataset)} examples")
+
+# Note: For memory-constrained demos, skip eval by using full dataset as train_dataset
+# and removing eval_dataset, eval_strategy, and eval_steps from config below
+
+# Training configuration
+config = SFTConfig(
+    # CRITICAL: Hub settings
+    output_dir="qwen-capybara-sft",
+    push_to_hub=True,
+    hub_model_id="username/qwen-capybara-sft",
+    hub_strategy="every_save",  # Push checkpoints
+
+    # Training parameters
+    num_train_epochs=3,
+    per_device_train_batch_size=4,
+    gradient_accumulation_steps=4,
+    learning_rate=2e-5,
+    # max_length=1024,  # Default - only set if you need different sequence length
+
+    # Logging & checkpointing
+    logging_steps=10,
+    save_strategy="steps",
+    save_steps=100,
+    save_total_limit=2,
+
+    # Evaluation - IMPORTANT: Only enable if eval_dataset provided
+    eval_strategy="steps",
+    eval_steps=100,
+
+    # Optimization
+    warmup_ratio=0.1,
+    lr_scheduler_type="cosine",
+
+    # Monitoring
+    report_to="trackio",  # Integrate with Trackio
+    project="meaningful_project_name", # project name for the training name (trackio)
+    run_name="baseline-run", #Descriptive name for this training run
+)
+
+# LoRA configuration
+peft_config = LoraConfig(
+    r=16,
+    lora_alpha=32,
+    lora_dropout=0.05,
+    bias="none",
+    task_type="CAUSAL_LM",
+    target_modules=["q_proj", "v_proj"],
+)
+
+# Initialize and train
+print("🎯 Initializing trainer...")
+trainer = SFTTrainer(
+    model="Qwen/Qwen2.5-0.5B",
+    train_dataset=train_dataset,
+    eval_dataset=eval_dataset,  # CRITICAL: Must provide eval_dataset when eval_strategy is enabled
+    args=config,
+    peft_config=peft_config,
+)
+
+print("🚀 Starting training...")
+trainer.train()
+
+print("💾 Pushing to Hub...")
+trainer.push_to_hub()
+
+# Finish Trackio tracking
+trackio.finish()
+
+print("✅ Complete! Model at: https://huggingface.co/username/qwen-capybara-sft")
+print("📊 View metrics at: https://huggingface.co/spaces/username/trackio")