gated-state-space / default_config.yaml
naxalpha's picture
sharded training
e14438a
raw
history blame contribute delete
No virus
647 Bytes
command_file: null
commands: null
compute_environment: LOCAL_MACHINE
deepspeed_config: {}
distributed_type: FSDP
downcast_bf16: 'no'
dynamo_backend: 'NO'
fsdp_config:
fsdp_auto_wrap_policy: SIZE_BASED_WRAP
fsdp_backward_prefetch_policy: BACKWARD_PRE
fsdp_min_num_params: 2000
fsdp_offload_params: false
fsdp_sharding_strategy: 1
fsdp_state_dict_type: FULL_STATE_DICT
gpu_ids: null
machine_rank: 0
main_process_ip: null
main_process_port: null
main_training_function: main
megatron_lm_config: {}
mixed_precision: 'no'
num_machines: 1
num_processes: 2
rdzv_backend: static
same_network: true
tpu_name: null
tpu_zone: null
use_cpu: false