updating to fused (#2293)

2025-01-30 16:45:56 +00:00
parent 8779997ba5
commit ac471a697a
37 changed files with 51 additions and 51 deletions
--- a/examples/deepseek-v2/fft-fsdp-16b.yaml
+++ b/examples/deepseek-v2/fft-fsdp-16b.yaml
@@ -27,7 +27,7 @@ wandb_log_model:
 gradient_accumulation_steps: 8
 micro_batch_size: 1
 num_epochs: 1
-optimizer: adamw_torch
+optimizer: adamw_torch_fused
 lr_scheduler: cosine
 learning_rate: 2e-5

--- a/examples/deepseek-v2/qlora-fsdp-2_5.yaml
+++ b/examples/deepseek-v2/qlora-fsdp-2_5.yaml
@@ -47,7 +47,7 @@ peft_use_rslora: true
 gradient_accumulation_steps: 1
 micro_batch_size: 8
 num_epochs: 1
-optimizer: adamw_torch
+optimizer: adamw_torch_fused
 lr_scheduler: cosine
 learning_rate: 2e-5