Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Support lama65b single a100 finetuning #146

Draft
wants to merge 5 commits into
base: main
Choose a base branch
from
Draft

Support lama65b single a100 finetuning #146

Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
5e36f74
support llama-65b single card lora finetuning
Jiang-Stan May 18, 2023
9f63680
align to alpaca lora
Jiang-Stan May 23, 2023
b734e64
add args to fientune.py
Jiang-Stan May 26, 2023
f30b512
save interval set to 10
Jiang-Stan May 28, 2023
4b7cdc3
using fp16 backward
Jiang-Stan Jun 12, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
save interval set to 10
  • Loading branch information
@Jiang-Stan
Jiang-Stan committed May 28, 2023
commit f30b512921a5aca02d76482345dbadb105f60bf2
2 changes: 1 addition & 1 deletion large_language_models/alpaca-qlora/finetune.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,7 +144,7 @@ def tokenize(prompt):
eval_steps=200,
save_steps=200,
output_dir="lora-alpaca",
save_total_limit=6,
save_total_limit=10,
load_best_model_at_end=True,
weight_decay=args.weight_decay,
adam_beta1=args.adam_beta1,
Expand Down