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

Fix monoT5 pytorch arguments #308

Closed
wants to merge 1 commit into from
Closed

Fix monoT5 pytorch arguments #308

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 4 additions & 4 deletions pygaggle/run/finetune_monot5.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,7 @@ def main():
help="Per device batch size parameter.")
parser.add_argument("--gradient_accumulation_steps", default=16, type=int, required=False,
help="Gradient accumulation parameter.")
parser.add_argument("--learning_rate", default=3e-4, type=float, required=False,
parser.add_argument("--learning_rate", default=1e-3, type=float, required=False,
help="Learning rate parameter.")
parser.add_argument("--epochs", default=10, type=int, required=False,
help="Number of epochs to train")
Expand Down Expand Up @@ -100,9 +100,9 @@ def smart_batching_collate_text_only(batch):
per_device_train_batch_size=args.per_device_train_batch_size,
gradient_accumulation_steps=args.gradient_accumulation_steps,
learning_rate=args.learning_rate,
weight_decay=5e-5,
weight_decay=0,
num_train_epochs=1,
warmup_steps=1000,
warmup_steps=0,
adafactor=True,
seed=1,
disable_tqdm=False,
Expand All @@ -125,4 +125,4 @@ def smart_batching_collate_text_only(batch):
trainer.save_state()

if __name__ == "__main__":
main()
main()