allura-forge/qwen3.5-9b-seed2.0-claude-dist-qlora-ckpts

model_name_or_path: Qwen/Qwen3.5-9B
bf16: true
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
use_liger: true
use_cce: true
max_length: 4096
learning_rate: 0.0002
warmup_ratio: 0.05
weight_decay: 0.01
lr_scheduler_type: cosine
per_device_train_batch_size: 2
gradient_accumulation_steps: 8
optim: paged_ademamix_8bit
max_grad_norm: 1.0
use_peft: true
load_in_4bit: true
lora_r: 128
lora_alpha: 8
lora_dropout: 0.05
use_rslora: true
logging_steps: 1
disable_tqdm: true
save_strategy: steps
save_steps: 500
save_total_limit: 3
report_to: wandb
output_dir: output-fizz
data_config: data.yaml
prepared_dataset: prepared
num_train_epochs: 2
saves_per_epoch: 2
run_name: qwen35-9b-qlora-fizz

datasets:
- path: allura-forge/doubao-seed2.0-claude-distill-v1-qwen3.5-format
  type: conversational
  truncation_strategy: drop
shuffle_datasets: true
shuffle_combined: true
shuffle_seed: 42
eval_split: 0.0
split_seed: 42
assistant_only_loss: true