mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-19 12:58:07 +00:00
c69bc5d4e6
* feat: Add optional curriculum support to dataset registration and creation * docs: Add docstrings to create_curriculum() and register_dataset() * feat: Add curriculum configuration classes for CurriculumExperiment * feat: Add weight parameter to CurriculumAttributeConfig and use in DatasetSpec * refactor: Simplify CurriculumAttributeConfig with "*" attribute level support * test: Add unit tests for CurriculumExperiment class * feat: Add from_yaml() method to CurriculumExperimentConfig with unit test
30 lines
1.1 KiB
Bash
Executable file
30 lines
1.1 KiB
Bash
Executable file
#!/bin/bash
|
|
python3 -u main_ppo_custom_reward.py \
|
|
data.train_files=$DATA_DIR/train.parquet \
|
|
data.val_files=$DATA_DIR/test.parquet \
|
|
data.train_batch_size=256 \
|
|
data.val_batch_size=1312 \
|
|
data.max_prompt_length=256 \
|
|
data.max_response_length=1024 \
|
|
actor_rollout_ref.model.path=$BASE_MODEL \
|
|
actor_rollout_ref.actor.optim.lr=1e-6 \
|
|
actor_rollout_ref.actor.ppo_mini_batch_size=128 \
|
|
actor_rollout_ref.actor.ppo_micro_batch_size=8 \
|
|
actor_rollout_ref.rollout.log_prob_micro_batch_size=8 \
|
|
actor_rollout_ref.rollout.tensor_model_parallel_size=$ROLLOUT_TP_SIZE \
|
|
actor_rollout_ref.rollout.gpu_memory_utilization=0.4 \
|
|
actor_rollout_ref.ref.log_prob_micro_batch_size=4 \
|
|
critic.optim.lr=1e-5 \
|
|
critic.model.path=$BASE_MODEL \
|
|
critic.ppo_micro_batch_size=8 \
|
|
algorithm.kl_ctrl.kl_coef=0.001 \
|
|
trainer.logger=['wandb'] \
|
|
+trainer.val_before_train=False \
|
|
trainer.default_hdfs_dir=null \
|
|
trainer.n_gpus_per_node=$N_GPUS \
|
|
trainer.nnodes=1 \
|
|
trainer.save_freq=100 \
|
|
trainer.test_freq=100 \
|
|
trainer.project_name='verl_chain_sum_ppo' \
|
|
trainer.experiment_name=$EXPERIMENT_NAME \
|
|
trainer.total_epochs=15 2>&1 | tee verl_output.log
|