hailin
/
jd_train
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

.

This commit is contained in:
hailin 2025-09-09 23:23:51 +08:00
parent 0ca12bc98f
commit c3dfd25132
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
ds_config_zero3_lora.json
View File

@ -1,15 +1,14 @@
{
"train_micro_batch_size_per_gpu": 1,
"gradient_accumulation_steps": 4,
"bf16": { "enabled": true },
"fp16": { "enabled": false },
"zero_optimization": {
"stage": 3,
"overlap_comm": true,
"contiguous_gradients": true,
"contiguous_gradients": false,
"allgather_partitions": true,
"reduce_scatter": true,
"round_robin_gradients": true,
"round_robin_gradients": false,
"reduce_bucket_size": 150000000,
"stage3_prefetch_bucket_size": 100000000,
"stage3_param_persistence_threshold": 1000000,