| compute_environment: LOCAL_MACHINE | |
| deepspeed_config: | |
| deepspeed_multinode_launcher: standard | |
| gradient_accumulation_steps: 2 | |
| gradient_clipping: 1.0 | |
| offload_optimizer_device: cpu | |
| offload_param_device: cpu | |
| zero3_init_flag: true | |
| zero3_save_16bit_model: true | |
| zero_stage: 3 | |
| zero_optimization: | |
| overlap_comm: false | |
| distributed_type: DEEPSPEED | |
| downcast_bf16: 'no' | |
| main_training_function: main | |
| mixed_precision: bf16 | |
| num_machines: 1 | |
| num_processes: 8 | |
| rdzv_backend: static | |
| same_network: true | |
| tpu_env: [] | |
| tpu_use_cluster: false | |
| tpu_use_sudo: false | |
| use_cpu: false |