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

Replace the base model deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B to Qwen/Qwen2.5-1.5B-Instruct in GRPO #198

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
+3 −3
Open

Replace the base model deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B to Qwen/Qwen2.5-1.5B-Instruct in GRPO #198

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f8cda2e
Replace the deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B to Qwen2.5-1.5B…
Omni-FinAgent Feb 5, 2025
49c68a6
Merge branch 'huggingface:main' into main
DVampire Feb 7, 2025
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
6 changes: 3 additions & 3 deletions recipes/qwen/Qwen2.5-1.5B-Instruct/grpo/confg_full.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# Model arguments
model_name_or_path: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
model_name_or_path: Qwen/Qwen2.5-1.5B-Instruct
model_revision: main
torch_dtype: bfloat16

Expand All @@ -22,7 +22,7 @@ gradient_accumulation_steps: 16
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
hub_model_id: Qwen2.5-1.5B-Open-R1-GRPO
hub_model_id: Qwen2.5-1.5B-Instruct-Open-R1-GRPO
hub_strategy: every_save
learning_rate: 2.0e-05
log_level: info
Expand All @@ -33,7 +33,7 @@ max_prompt_length: 512
max_completion_length: 1024
max_steps: -1
num_train_epochs: 1
output_dir: data/Qwen2.5-1.5B-Open-R1-GRPO
output_dir: data/Qwen2.5-1.5B-Instruct-Open-R1-GRPO
overwrite_output_dir: true
per_device_eval_batch_size: 4
per_device_train_batch_size: 1
Expand Down