Loading vagen/examples/release_experiments/mask_gae_mask_loss_turnwise_reward_bi_level.sh +2 −2 Original line number Diff line number Diff line Loading @@ -29,9 +29,9 @@ python3 -m vagen.trainer.main_ppo \ data.train_batch_size=128 \ data.max_prompt_length=1024 \ data.max_response_length=128 \ data.max_trajectory_length=1800 \ data.max_trajectory_length=2000 \ data.image_key=images \ data.truncation=left \ data.truncation=error \ actor_rollout_ref.model.path=Qwen/Qwen2.5-VL-3B-Instruct \ actor_rollout_ref.actor.optim.lr=1e-6 \ actor_rollout_ref.model.use_remove_padding=True \ Loading Loading
vagen/examples/release_experiments/mask_gae_mask_loss_turnwise_reward_bi_level.sh +2 −2 Original line number Diff line number Diff line Loading @@ -29,9 +29,9 @@ python3 -m vagen.trainer.main_ppo \ data.train_batch_size=128 \ data.max_prompt_length=1024 \ data.max_response_length=128 \ data.max_trajectory_length=1800 \ data.max_trajectory_length=2000 \ data.image_key=images \ data.truncation=left \ data.truncation=error \ actor_rollout_ref.model.path=Qwen/Qwen2.5-VL-3B-Instruct \ actor_rollout_ref.actor.optim.lr=1e-6 \ actor_rollout_ref.model.use_remove_padding=True \ Loading
