deepspeed_bsz24_config.json

{
  "train_batch_size": 24,
  "train_micro_batch_size_per_gpu": 3,
  "steps_per_print": 10,
  "optimizer": {
    "type": "Adam",
    "params": {
      "lr": 3e-5,
      "weight_decay": 0.0,
      "bias_correction": false
    }
  },
  "gradient_clipping": 1.0,
  "fp16": {
    "enabled": true
  }

}