ds_config_cl.json

{
  "train_batch_size": 512,
  "gradient_accumulation_steps": 1,
  "steps_per_print": 1,
  "zero_optimization": {
    "stage": 0
  },
  "optimizer": {
    "type": "Adam",
    "params": {
      "lr": 0.00015,
      "max_grad_norm": 1.0,
      "betas": [0.9, 0.95]
    }
  },
  "gradient_clipping": 1.0,
  "fp16": {
    "enabled": true,
    "loss_scale": 0,
    "loss_scale_window": 1000,
    "hysteresis": 2,
    "min_loss_scale": 1
  },
  "wall_clock_breakdown": false,
  "zero_allow_untested_optimizer": false,
  "curriculum_learning": {
    "enabled": true,
    "curriculum_type": "seqlen",
    "min_difficulty": 8,
    "max_difficulty": 1024,
    "schedule_type": "fixed_linear",
    "schedule_config": {
      "total_curriculum_step": 60000,
      "difficulty_step": 8
    }
  }
}