Upload train_4b_sft.py with huggingface_hub

train_4b_sft.py

@@ -0,0 +1,101 @@
+# /// script
+# requires-python = ">=3.10"
+# dependencies = [
+#     "trl>=0.12.0",
+#     "peft>=0.7.0",
+#     "transformers>=4.36.0",
+#     "accelerate>=0.24.0",
+#     "trackio",
+# ]
+# ///
+
+"""
+SFT training for Qwen3-4B on query expansion dataset.
+Output: tobil/qmd-query-expansion-4B-sft
+"""
+
+import trackio
+from datasets import load_dataset
+from peft import LoraConfig
+from trl import SFTTrainer, SFTConfig
+
+# Load dataset
+print("Loading dataset...")
+dataset = load_dataset("tobil/qmd-query-expansion-train-v2", 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")
+
+# Training configuration
+config = SFTConfig(
+    # Hub settings - use separate repo, not subfolder
+    output_dir="qmd-query-expansion-4B-sft",
+    push_to_hub=True,
+    hub_model_id="tobil/qmd-query-expansion-4B-sft",
+    hub_strategy="every_save",
+
+    # Training parameters
+    num_train_epochs=3,
+    per_device_train_batch_size=4,
+    gradient_accumulation_steps=4,
+    learning_rate=2e-4,
+    max_length=512,
+
+    # Logging & checkpointing
+    logging_steps=10,
+    save_strategy="steps",
+    save_steps=100,
+    save_total_limit=2,
+
+    # Evaluation
+    eval_strategy="steps",
+    eval_steps=100,
+
+    # Optimization
+    warmup_ratio=0.1,
+    lr_scheduler_type="cosine",
+
+    # Monitoring
+    report_to="trackio",
+    project="qmd-query-expansion",
+    run_name="qwen3-4B-sft-v2",
+)
+
+# LoRA configuration: rank 16, alpha 32
+peft_config = LoraConfig(
+    r=16,
+    lora_alpha=32,
+    lora_dropout=0.05,
+    bias="none",
+    task_type="CAUSAL_LM",
+    target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
+)
+
+# Initialize and train
+print("Initializing trainer...")
+trainer = SFTTrainer(
+    model="Qwen/Qwen3-4B",
+    train_dataset=train_dataset,
+    eval_dataset=eval_dataset,
+    args=config,
+    peft_config=peft_config,
+)
+
+print("Starting training...")
+trainer.train()
+
+print("Pushing to Hub...")
+# Fixed: Call push_to_hub() without subfolder argument
+trainer.push_to_hub()
+
+# Finish Trackio tracking
+trackio.finish()
+
+print("Complete! Model at: https://huggingface.co/tobil/qmd-query-expansion-4B-sft")
+print("View metrics at: https://huggingface.co/spaces/tobil/trackio")