[linux] RuntimeError: FlashAttention only support fp16 and bf16 data type

在config中，去掉：

"offload_optimizer": {

"device": "cpu"

}

以及：

"offload_param": {
"device": "cpu"
}
因为cpu默认不是bf16，是fp32。

这是config：

{
    "train_batch_size": "auto",
    "train_micro_batch_size_per_gpu": "auto",
    "gradient_accumulation_steps": "auto",
    "gradient_clipping": "auto",
    "zero_allow_untested_optimizer": true,
    "fp16": {
      "enabled": "auto",
      "loss_scale": 0,
      "initial_scale_power": 16,
      "loss_scale_window": 1000,
      "hysteresis": 2,
      "min_loss_scale": 1
    },  
    "zero_optimization": {
      "stage": 3,
      "contiguous_gradients": true,
      "stage3_max_live_parameters": 1e9,
      "stage3_max_reuse_distance": 1e9,
      "stage3_prefetch_bucket_size": 1e7,
      "stage3_param_persistence_threshold": 1e5,
      "reduce_bucket_size": 1e7,
      "sub_group_size": 1e9,
      "offload_optimizer": {
        "device": "cpu"
      }
    }
  }