| Launch training | |
| An example FSDP configuration file may look like: | |
| yaml | |
| compute_environment: LOCAL_MACHINE | |
| debug: false | |
| distributed_type: FSDP | |
| downcast_bf16: 'no' | |
| fsdp_config: | |
| fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP | |
| fsdp_backward_prefetch_policy: BACKWARD_PRE | |
| fsdp_cpu_ram_efficient_loading: true | |
| fsdp_forward_prefetch: false | |
| fsdp_offload_params: true | |
| fsdp_sharding_strategy: 1 | |
| fsdp_state_dict_type: SHARDED_STATE_DICT | |
| fsdp_sync_module_states: true | |
| fsdp_transformer_layer_cls_to_wrap: BertLayer | |
| fsdp_use_orig_params: true | |
| machine_rank: 0 | |
| main_training_function: main | |
| mixed_precision: bf16 | |
| num_machines: 1 | |
| num_processes: 2 | |
| rdzv_backend: static | |
| same_network: true | |
| tpu_env: [] | |
| tpu_use_cluster: false | |
| tpu_use_sudo: false | |
| use_cpu: false | |
| To launch training, run the accelerate launch command and it'll automatically use the configuration file you previously created with accelerate config. |