praxisresearch/shawn-test-qwen_05B_sgtr_xsum

# Axolotl configuration translated from Unsloth config
base_model: unsloth/Qwen2.5-0.5B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

# Dataset configuration

  - path: data/finetuning/sgtr/comparison/prefer-self-finetune_target_hf_qwen_0.5b_other-models__claude-21__finetuningdata.jsonl
    type: chat_template
    message_field_role: role        # Field name for role (in your case: "role")
    message_field_content: content  # Field name for content (in your case: "content")
    roles:
      system: ["system"]           # Map "system" role
      user: ["user"]               # Map "user" role
      assistant: ["assistant"]     # Map "assistant" role
    train_on_split: train

# Output configuration
output_dir: ./models/hf_qwen_0.5b_sgtr

# Sequence length
sequence_len: 2048
pad_to_sequence_len: false

# LoRA configuration
adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 64
lora_dropout: 0.0
lora_target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj
  - gate_proj
  - up_proj
  - down_proj
lora_fan_in_fan_out: false
peft_use_rslora: true
peft_use_dora: false

# Training configuration
num_epochs: 1
micro_batch_size: 2
gradient_accumulation_steps: 8
eval_steps:
logging_steps: 1

# Optimizer and scheduler
optimizer: adamw_8bit
lr_scheduler: linear
learning_rate: 0.00001
weight_decay: 0.01
warmup_steps: 5

# Training settings
train_on_inputs: false  # Equivalent to train_on_responses_only=true
group_by_length: false
bf16: auto
fp16: false
tf32: false

# Gradient settings
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false

# Miscellaneous
seed: 0
strict: false
do_bench_eval: false
wandb_project: shi-feng-the-george-washington-university
wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:

# DPO specific (beta parameter from your config)
dpo_beta: 0.1

# Flash attention
flash_attention: true

# Saving
save_safetensors: true
saves_per_epoch: 1

# Validation
val_set_size: 0
eval_sample_packing: false
eval_batch_size:

# Special tokens
special_tokens: