alsoalter/qwen3-function-calling-lora-merged

# Qwen3 Function Calling Fine-tuning Configuration
# Base model - using Qwen3 4B Instruct
base_model: Qwen/Qwen3-4B-Instruct-2507

# Model type
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

# Trust remote code for Qwen models
trust_remote_code: true

# Full precision LoRA (allows auto-merge)
adapter: lora

# Chat template - use Qwen's chat template for tool/function calling
chat_template: qwen3
# Enable special tokens for function calling
special_tokens:
  pad_token: "<|endoftext|>"

# Dataset configuration
# Format should be in OpenAI function calling format or sharegpt with tool calls
datasets:
  - path: poisoned_finetune_simple.jsonl
    type: chat_template
    field_messages: messages  # Field name in your JSONL file
    message_field_role: role
    message_field_content: content
    message_field_tool_calls: tool_calls  # For function calling support

# Validation split
val_set_size: 0.1
output_dir: ./outputs/qwen3-function-calling-qlora

# LoRA configuration - target all linear layers for better function calling performance
lora_r: 32
lora_alpha: 32
lora_dropout: 0.05
lora_target_linear: true

# Training settings
sequence_len: 4096  # Longer context for function calling examples
sample_packing: false  # Disable for chat/function calling to preserve conversation structure
pad_to_sequence_len: true

# Batch size and gradient accumulation
micro_batch_size: 1
gradient_accumulation_steps: 8
# num_epochs: 2
max_steps: 25

# Learning rate
learning_rate: 0.0002
lr_scheduler: cosine
warmup_steps: 100

# Optimizer
optimizer: adamw_bnb_8bit

# Mixed precision training
bf16: auto
fp16: false
tf32: true

# Efficiency settings
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
flash_attention: true

# Logging
logging_steps: 1
save_strategy: steps
save_steps: 5
eval_steps: 5

# Hub settings - Push adapter to HuggingFace
hub_model_id: alsoalter/qwen3-fc-adapter
hub_strategy: end  # Push at end of training

# Merge LoRA into base model after training
merge_lora: true
merge_output_dir: ./outputs/qwen3-fc-merged

# Push merged model to separate repo
merge_hub_model_id: alsoalter/qwen3-fc-merged

# Save in safetensors format
save_safetensors: true

# Weights & Biases
wandb_project: qwen3-function-calling
wandb_name: qwen3-fc-run1

# Early stopping (optional)
early_stopping_patience: 3

# Debug settings
debug: false