ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update readme

Browse Source 
Former-commit-id: 440e9de66986ef7736361ce8ec3e23ce68655a56
This commit is contained in:
hiyouga
2024-05-29 18:39:11 +08:00
parent f4e16ae373
commit 9a65820592
7 changed files with 76 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
examples/accelerate/fsdp_config.yaml
View File

@@ -5,16 +5,16 @@ downcast_bf16: 'no'
fsdp_config:
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
fsdp_backward_prefetch: BACKWARD_PRE
fsdp_cpu_ram_efficient_loading: true
fsdp_forward_prefetch: false
fsdp_offload_params: true
fsdp_cpu_ram_efficient_loading: true
fsdp_offload_params: true # offload may affect training speed
fsdp_sharding_strategy: FULL_SHARD
fsdp_state_dict_type: FULL_STATE_DICT
fsdp_sync_module_states: true
fsdp_use_orig_params: false
fsdp_use_orig_params: true
machine_rank: 0
main_training_function: main
mixed_precision: fp16
mixed_precision: fp16 # or bf16
num_machines: 1 # the number of nodes
num_processes: 2 # the number of GPUs in all nodes
rdzv_backend: static