trl-mcsd / examples /scripts /nemo_gym /deepspeed_zero3.yaml
ihbkaiser's picture
Implement MCSD for experimental SDPO
1fa3c6c verified
raw
history blame contribute delete
521 Bytes
compute_environment: LOCAL_MACHINE
debug: false
deepspeed_config:
deepspeed_multinode_launcher: standard
offload_optimizer_device: none
offload_param_device: none
zero3_init_flag: true
zero3_save_16bit_model: true
zero_stage: 3
distributed_type: DEEPSPEED
downcast_bf16: 'no'
machine_rank: 0
main_training_function: main
mixed_precision: bf16
num_machines: 4
num_processes: 32
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false