train_missing.yaml

parameters:
  project_name: jaxgmg2_3phase_unique
  action: rl
  rl_action: train

  lr: 5e-5
  alpha: 0.7
  discount_rate: 0.98
  cheese_loc: any
  env_layout: open
  mask_type: first_episode
  use_prev_action: false
  log_optimizer_state: false

  num_total_env_steps: 10_000_000_000
  num_levels: 9600
  grad_acc_per_chunk: 5
  num_rollout_steps: 64

  seed_formula: "{int(discount_rate*100):02d}{int(alpha*10):02d}{run_id:02d}"
  ckpt_dir: jaxgmg2_3phase_unique
  f_str_ckpt: "al_{alpha}_g_{discount_rate}_id_{run_id}_seed_{seed}"
  eval_schedule: "0:1,250:2,500:5,2000:10"

  wandb_project: jaxgmg2_3phase_unique
  use_wandb: true
  use_hf: true
  no_tqdm: true
  ntfy: david_jaxgmg

sweep:
- - run_id: 14