chain_name: "dodo DPO Chain"
description: "A dodo DPO Chain"

# Global settings
settings:
  base_dir: "/home/tony/Work/tony/slurm/dodo"
  log_dir: "/home/tony/slurm/logs"
  
  # SLURM defaults - no partition specified
  slurm_defaults:
    time: "48:00:00"
    ntasks_per_node: 8
    cpus_per_task: 4
    gpus_per_node: 8

# Job definitions
jobs:
  # - name: "round_1"
  #   script: "run_ipo_dodo_auk_dpo_r1.sh"
  #   nodes: 4
  #   model_cache_loss_name: "6b_dodo_t23_2025-08-28_01-29-51"
  #   wandb_run_name: "dodo_t23_auk_dpo_r1"
  
  - name: "round_1"
    script: "run_ipo_dodo_crow_r1_t2.sh"
    nodes: 16
    model_cache_loss_name: "dodo_t23_2025-08-28_01-30-09"
    sft_loss_scale: 0.01
    wandb_run_name: "dodo_0828_crow_redo_v51_sft01_n16_r1"
  
  - name: "round_2"
    script: "run_ipo_dodo_crow_r2_t2.sh"
    nodes: 16
    model_cache_loss_name: "dodo_0828_crow_redo_v51_sft01_n16_r1"
    sft_loss_scale: 0.008
    wandb_run_name: "dodo_0828_crow_redo_v52_sft008_n16_r2"
  
  - name: "round_3"
    script: "run_ipo_dodo_crow_r3_t2.sh"
    nodes: 16
    model_cache_loss_name: "dodo_0828_crow_redo_v52_sft008_n16_r2"
    sft_loss_scale: 0.006
    wandb_run_name: "dodo_0828_crow_redo_v53_sft006_n16_r3"
  
  - name: "round_4"
    script: "run_ipo_dodo_crow_r4_t2.sh"
    nodes: 16
    sft_loss_scale: 0.005
    model_cache_loss_name: "dodo_0828_crow_redo_v53_sft006_n16_r3"
    wandb_run_name: "dodo_0828_crow_redo_v54_sft005_n16_r4"
    
  - name: "round_5"
    script: "run_ipo_dodo_crow_r5.sh"
    nodes: 16
    model_cache_loss_name: "dodo_0828_crow_redo_v54_sft005_n16_r4_stem"
    wandb_run_name: "dodo_0828_crow_redo_v55_n16_r5"
  
  - name: "round_6"
    script: "run_ipo_dodo_crow_r6.sh"
    nodes: 16
    model_cache_loss_name: "dodo_0828_crow_redo_v55_n16_r5"
    wandb_run_name: "dodo_0828_crow_redo_v56_n16_r6"
  
  - name: "round_7"
    script: "run_ipo_dodo_crow_r7.sh"  
    nodes: 16
    model_cache_loss_name: "dodo_0828_crow_redo_v56_n16_r6"
    wandb_run_name: "dodo_0828_crow_redo_v57_n16_r7"