model:
  base_model_id: meta-llama/Llama-3.1-8B-Instruct
  model_family: llama3
  target_modules:
  - q_proj
  - k_proj
  - v_proj
  - o_proj
  - gate_proj
  - up_proj
  - down_proj
lora:
  r: 16
  alpha: 32
  dropout: 0.05
dataset:
  name: lasgroup/SDPO
  config: null
  slug: sdpo_tooluse
  split: train
  text_field: prompt
  max_samples: null
  eval_samples: 256
  domain: tool_use
  format: tooluse
optimization:
  num_train_epochs: 3
  per_device_batch_size: 4
  gradient_accumulation_steps: 8
  learning_rate: 0.0002
  warmup_ratio: 0.05
  weight_decay: 0.01
  lr_scheduler_type: cosine
  max_grad_norm: 1.0
sequence:
  max_length: 2048
  packing: true
checkpointing:
  num_checkpoints: 8
  save_total_limit: 64
  schedule: log
  save_steps: null
runtime:
  logging_steps: 20
  bf16: true
  gradient_checkpointing: true
  wandb: true
  wandb_project: amr-fma-train
  hf_push: true
  hf_org: tkwiecinski
  hf_visibility: public
  force_restart: false
evaluation:
  enabled: true
  eval_steps: 200
  strategy: steps
phase:
  name: P1
run:
  method: lora_sft
  exp_name: p1_sft_math_tooluse
  seed: 43
  tags:
    phase: ${phase.name}
    domain: ${dataset.domain}
paths:
  base: ${oc.env:AMR_FMA_BASE,/capstor/scratch/cscs/${oc.env:USER}/amr-fma}
  model_short: ${hf_last:${model.base_model_id}}
  run_slug: ${run.exp_name}__s${run.seed}