base_model: Qwen/Qwen3-4B-Instruct-2507
base_revision: cdbee75f17c01a7cc42f958dc650907174af0554
seed: 20260720
train_records: 22698
train_tokens: 4784492
epochs: 2
max_length: 384
per_device_train_batch_size: 2
gradient_accumulation_steps: 8
effective_batch_size: 16
learning_rate: 1.0e-4
warmup_ratio: 0.03
optimizer: paged_adamw_8bit
lr_scheduler_type: linear
max_grad_norm: 1.0
weight_decay: 0.0
completion_only_loss: true
packing: true
packing_strategy: wrapped
gradient_checkpointing: true
quantization:
  load_in_4bit: true
  quant_type: nf4
  compute_dtype: bfloat16
  double_quantization: true
lora:
  rank: 16
  alpha: 32
  dropout: 0.05
  bias: none
  target_modules: all-linear
software:
  torch: 2.11.0+cu128
  cuda: "12.8"
  transformers: 5.14.1
  peft: 0.19.1
  trl: 1.8.0
  bitsandbytes: 0.49.2