model:
  hf_id: Qwen/Qwen3-1.7B
  local_path: /shared-ro/models/Qwen3-1.7B
  dtype: bfloat16
  attn_impl: flash_attention_2
  max_model_len: 4096
data:
  name: nemotron_math
  loader: load_nemotron_math
  kwargs:
    limit: 50000
    split: train
    max_total_tokens: 3800
    seed: 0
training:
  recipe: sft
  epochs: 1
  per_device_train_batch_size: 1
  gradient_accumulation_steps: 16
  learning_rate: 5.0e-06
  warmup_ratio: 0.03
  lr_scheduler_type: cosine
  gradient_checkpointing: true
  bf16: true
  max_seq_length: 4096
  max_steps: -1
  max_grad_norm: 1.0
  optim: adamw_torch
  assistant_only_loss: true
  logging_steps: 10
  save_steps: 500
  save_total_limit: 2
  report_to: wandb
  qlora: false
  lora_r: 16
  lora_alpha: 32
  lora_dropout: 0.05
  lora_target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj
  - gate_proj
  - up_proj
  - down_proj
  deepspeed: configs/deepspeed_zero2.json
  adapter_model_dir: null
domain:
  name: multilingual
  thinking_mode: false
  benchmark: multilingual
  languages:
  - it
  - es
  - zh
  - ru
  - hi
  target_format: boxed
  max_options: 20
  reward_fn: multilingual
  system_instruction: Choose the best option. Do not write an explanation. Return
    exactly one final answer in the form \boxed{LETTER}.
  template_boxed_instruction: Choose the best option. Do not write an explanation.
    Return exactly one final answer in the form \boxed{LETTER}.
post_train:
  enabled: false
  merge_adapter: false
  merged_output_dir: null
  domain_override: null
  evals: []
seed: 42
run_id: ${now:%Y%m%d_%H%M%S}
output_dir: /scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/merged
wandb:
  project: flab-cs552
  entity: cs-552-2026-flab
  mode: null
  tags: []
  notes: null
eval:
  model_dir: null
  rows_source: samples
  method: null
  system_prompt: null
  use_domain_system_prompt: false
  force_domain_template: false
  'n': 8
  temperature: 0.7
  top_p: 0.95
  max_model_len: 4096
  max_tokens: 4096
  samples_dir: null
push:
  model_dir: /scratch/checkpoints/multilingual/a42-success-recipe-20260530/qwen-success-r64/sft
  base_model_dir: null
es:
  base_model_dir: null
  data: null
hf_push:
  enabled: false
  org: cs-552-2026-flab
  repo: null
  private: false
  vllm_validate: true
  commit_message: null
validate_after_train: false
vllm_validate: true