compute_environment: LOCAL_MACHINE deepspeed_config: {} distributed_type: MEGATRON_LM downcast_bf16: 'no' fsdp_config: {} machine_rank: 0 main_process_ip: null main_process_port: null main_training_function: main megatron_lm_config: megatron_lm_gradient_clipping: 1.0 megatron_lm_num_micro_batches: 2 megatron_lm_pp_degree: 2 megatron_lm_recompute_activations: true megatron_lm_sequence_parallelism: true megatron_lm_tp_degree: 2 megatron_lm_use_distributed_optimizer: true mixed_precision: bf16 num_machines: 1 num_processes: 4 rdzv_backend: static same_network: true use_cpu: false