Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Appearance settings

[misc] feat: add gemma example for small scale debug and fix gradient checkpoint in critic #27

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

Merged
merged 2 commits into from
Nov 27, 2024
Merged

[misc] feat: add gemma example for small scale debug and fix gradient checkpoint in critic #27

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6a589f1
[misc] add small scale gemma2-2b example for debug
PeterSH6 Nov 25, 2024
3cdb4d2
[misc] fix: add eval() and train() for gradient checkpoint
PeterSH6 Nov 27, 2024
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
Next Next commit
[misc] add small scale gemma2-2b example for debug
  • Loading branch information
@PeterSH6
PeterSH6 committed Nov 25, 2024
commit 6a589f17d86a83cdf737ebc066c01573f157579b
39 changes: 39 additions & 0 deletions 39 examples/ppo_trainer/run_gemma.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
set -x

python3 -m verl.trainer.main_ppo \
data.train_files=$HOME/data/gsm8k/train.parquet \
data.val_files=$HOME/data/gsm8k/test.parquet \
data.train_batch_size=512 \
data.val_batch_size=1312 \
data.max_prompt_length=1024 \
data.max_response_length=512 \
actor_rollout_ref.model.path=google/gemma-2-2b-it \
actor_rollout_ref.actor.optim.lr=1e-6 \
actor_rollout_ref.actor.ppo_mini_batch_size=128 \
actor_rollout_ref.actor.ppo_micro_batch_size=4 \
actor_rollout_ref.actor.fsdp_config.param_offload=False \
actor_rollout_ref.actor.fsdp_config.grad_offload=False \
actor_rollout_ref.actor.fsdp_config.optimizer_offload=False \
actor_rollout_ref.rollout.log_prob_micro_batch_size=4 \
actor_rollout_ref.rollout.tensor_model_parallel_size=2 \
actor_rollout_ref.rollout.name=vllm \
actor_rollout_ref.rollout.gpu_memory_utilization=0.4 \
actor_rollout_ref.ref.log_prob_micro_batch_size=4 \
actor_rollout_ref.ref.fsdp_config.param_offload=True \
critic.optim.lr=1e-5 \
critic.model.path=google/gemma-2-2b-it \
critic.model.enable_gradient_checkpointing=False \
critic.ppo_micro_batch_size=4 \
critic.model.fsdp_config.param_offload=False \
critic.model.fsdp_config.grad_offload=False \
critic.model.fsdp_config.optimizer_offload=False \
algorithm.kl_ctrl.kl_coef=0.001 \
trainer.critic_warmup=0 \
trainer.logger=['console','tracking'] \
trainer.project_name='verl_example' \
trainer.experiment_name='gemma2b_function_rm' \
trainer.n_gpus_per_node=2 \
trainer.nnodes=1 \
trainer.save_freq=-1 \
trainer.test_freq=10 \
trainer.total_epochs=15
Morty Proxy This is a proxified and sanitized view of the page, visit original site.