423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-14 19:06:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

support fsdp + qlora

Browse Source 
Former-commit-id: b894bf8e84be689db258021f0638e9ac939abcbc
This commit is contained in:
hiyouga
2024-03-21 00:36:06 +08:00
parent 5f3f0c53f2
commit b590e82d41
19 changed files with 87 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
examples/deepspeed/ds_z2_config.json Normal file
View File

@@ -0,0 +1,28 @@
{
"train_batch_size": "auto",
"train_micro_batch_size_per_gpu": "auto",
"gradient_accumulation_steps": "auto",
"gradient_clipping": "auto",
"zero_allow_untested_optimizer": true,
"fp16": {
"enabled": "auto",
"loss_scale": 0,
"loss_scale_window": 1000,
"initial_scale_power": 16,
"hysteresis": 2,
"min_loss_scale": 1
},
"bf16": {
"enabled": "auto"
},
"zero_optimization": {
"stage": 2,
"allgather_partitions": true,
"allgather_bucket_size": 5e8,
"overlap_comm": true,
"reduce_scatter": true,
"reduce_bucket_size": 5e8,
"contiguous_gradients": true,
"round_robin_gradients": true
}
}