Unverified Commit a3d31e3a authored by dg845's avatar dg845 Committed by GitHub
Browse files

Change LCM-LoRA README Script Example Learning Rates to 1e-4 (#6304)

Change README LCM-LoRA example learning rates to 1e-4.
parent 84c403ae
...@@ -94,7 +94,7 @@ accelerate launch train_lcm_distill_lora_sd_wds.py \ ...@@ -94,7 +94,7 @@ accelerate launch train_lcm_distill_lora_sd_wds.py \
--mixed_precision=fp16 \ --mixed_precision=fp16 \
--resolution=512 \ --resolution=512 \
--lora_rank=64 \ --lora_rank=64 \
--learning_rate=1e-6 --loss_type="huber" --adam_weight_decay=0.0 \ --learning_rate=1e-4 --loss_type="huber" --adam_weight_decay=0.0 \
--max_train_steps=1000 \ --max_train_steps=1000 \
--max_train_samples=4000000 \ --max_train_samples=4000000 \
--dataloader_num_workers=8 \ --dataloader_num_workers=8 \
......
...@@ -96,7 +96,7 @@ accelerate launch train_lcm_distill_lora_sdxl_wds.py \ ...@@ -96,7 +96,7 @@ accelerate launch train_lcm_distill_lora_sdxl_wds.py \
--mixed_precision=fp16 \ --mixed_precision=fp16 \
--resolution=1024 \ --resolution=1024 \
--lora_rank=64 \ --lora_rank=64 \
--learning_rate=1e-6 --loss_type="huber" --use_fix_crop_and_size --adam_weight_decay=0.0 \ --learning_rate=1e-4 --loss_type="huber" --use_fix_crop_and_size --adam_weight_decay=0.0 \
--max_train_steps=1000 \ --max_train_steps=1000 \
--max_train_samples=4000000 \ --max_train_samples=4000000 \
--dataloader_num_workers=8 \ --dataloader_num_workers=8 \
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment