Loading scripts/exps/format/svg/free_think/run.sh +3 −3 Original line number Diff line number Diff line Loading @@ -39,12 +39,12 @@ python3 -m vagen.trainer.main_ppo \ actor_rollout_ref.actor.kl_loss_coef=0.001 \ actor_rollout_ref.actor.kl_loss_type=mse \ actor_rollout_ref.model.enable_gradient_checkpointing=True \ actor_rollout_ref.actor.fsdp_config.param_offload=False \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=False \ actor_rollout_ref.actor.fsdp_config.param_offload=True \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=True \ actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=1 \ actor_rollout_ref.rollout.tensor_model_parallel_size=4 \ actor_rollout_ref.rollout.name=vllm \ actor_rollout_ref.rollout.gpu_memory_utilization=0.2 \ actor_rollout_ref.rollout.gpu_memory_utilization=0.1 \ actor_rollout_ref.rollout.enable_chunked_prefill=False \ actor_rollout_ref.rollout.enforce_eager=False \ actor_rollout_ref.rollout.free_cache_engine=False \ Loading scripts/exps/format/svg/grounding/run.sh +3 −3 Original line number Diff line number Diff line Loading @@ -39,12 +39,12 @@ python3 -m vagen.trainer.main_ppo \ actor_rollout_ref.actor.kl_loss_coef=0.001 \ actor_rollout_ref.actor.kl_loss_type=mse \ actor_rollout_ref.model.enable_gradient_checkpointing=True \ actor_rollout_ref.actor.fsdp_config.param_offload=False \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=False \ actor_rollout_ref.actor.fsdp_config.param_offload=True \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=True \ actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=1 \ actor_rollout_ref.rollout.tensor_model_parallel_size=4 \ actor_rollout_ref.rollout.name=vllm \ actor_rollout_ref.rollout.gpu_memory_utilization=0.2 \ actor_rollout_ref.rollout.gpu_memory_utilization=0.1 \ actor_rollout_ref.rollout.enable_chunked_prefill=False \ actor_rollout_ref.rollout.enforce_eager=False \ actor_rollout_ref.rollout.free_cache_engine=False \ Loading scripts/exps/format/svg/no_think/run.sh +3 −3 Original line number Diff line number Diff line Loading @@ -39,12 +39,12 @@ python3 -m vagen.trainer.main_ppo \ actor_rollout_ref.actor.kl_loss_coef=0.001 \ actor_rollout_ref.actor.kl_loss_type=mse \ actor_rollout_ref.model.enable_gradient_checkpointing=True \ actor_rollout_ref.actor.fsdp_config.param_offload=False \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=False \ actor_rollout_ref.actor.fsdp_config.param_offload=True \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=True \ actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=1 \ actor_rollout_ref.rollout.tensor_model_parallel_size=4 \ actor_rollout_ref.rollout.name=vllm \ actor_rollout_ref.rollout.gpu_memory_utilization=0.2 \ actor_rollout_ref.rollout.gpu_memory_utilization=0.1 \ actor_rollout_ref.rollout.enable_chunked_prefill=False \ actor_rollout_ref.rollout.enforce_eager=False \ actor_rollout_ref.rollout.free_cache_engine=False \ Loading scripts/exps/format/svg/worldmodeling/run.sh +3 −3 Original line number Diff line number Diff line Loading @@ -39,12 +39,12 @@ python3 -m vagen.trainer.main_ppo \ actor_rollout_ref.actor.kl_loss_coef=0.001 \ actor_rollout_ref.actor.kl_loss_type=mse \ actor_rollout_ref.model.enable_gradient_checkpointing=True \ actor_rollout_ref.actor.fsdp_config.param_offload=False \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=False \ actor_rollout_ref.actor.fsdp_config.param_offload=True \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=True \ actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=1 \ actor_rollout_ref.rollout.tensor_model_parallel_size=4 \ actor_rollout_ref.rollout.name=vllm \ actor_rollout_ref.rollout.gpu_memory_utilization=0.2 \ actor_rollout_ref.rollout.gpu_memory_utilization=0.1 \ actor_rollout_ref.rollout.enable_chunked_prefill=False \ actor_rollout_ref.rollout.enforce_eager=False \ actor_rollout_ref.rollout.free_cache_engine=False \ Loading Loading
scripts/exps/format/svg/free_think/run.sh +3 −3 Original line number Diff line number Diff line Loading @@ -39,12 +39,12 @@ python3 -m vagen.trainer.main_ppo \ actor_rollout_ref.actor.kl_loss_coef=0.001 \ actor_rollout_ref.actor.kl_loss_type=mse \ actor_rollout_ref.model.enable_gradient_checkpointing=True \ actor_rollout_ref.actor.fsdp_config.param_offload=False \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=False \ actor_rollout_ref.actor.fsdp_config.param_offload=True \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=True \ actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=1 \ actor_rollout_ref.rollout.tensor_model_parallel_size=4 \ actor_rollout_ref.rollout.name=vllm \ actor_rollout_ref.rollout.gpu_memory_utilization=0.2 \ actor_rollout_ref.rollout.gpu_memory_utilization=0.1 \ actor_rollout_ref.rollout.enable_chunked_prefill=False \ actor_rollout_ref.rollout.enforce_eager=False \ actor_rollout_ref.rollout.free_cache_engine=False \ Loading
scripts/exps/format/svg/grounding/run.sh +3 −3 Original line number Diff line number Diff line Loading @@ -39,12 +39,12 @@ python3 -m vagen.trainer.main_ppo \ actor_rollout_ref.actor.kl_loss_coef=0.001 \ actor_rollout_ref.actor.kl_loss_type=mse \ actor_rollout_ref.model.enable_gradient_checkpointing=True \ actor_rollout_ref.actor.fsdp_config.param_offload=False \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=False \ actor_rollout_ref.actor.fsdp_config.param_offload=True \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=True \ actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=1 \ actor_rollout_ref.rollout.tensor_model_parallel_size=4 \ actor_rollout_ref.rollout.name=vllm \ actor_rollout_ref.rollout.gpu_memory_utilization=0.2 \ actor_rollout_ref.rollout.gpu_memory_utilization=0.1 \ actor_rollout_ref.rollout.enable_chunked_prefill=False \ actor_rollout_ref.rollout.enforce_eager=False \ actor_rollout_ref.rollout.free_cache_engine=False \ Loading
scripts/exps/format/svg/no_think/run.sh +3 −3 Original line number Diff line number Diff line Loading @@ -39,12 +39,12 @@ python3 -m vagen.trainer.main_ppo \ actor_rollout_ref.actor.kl_loss_coef=0.001 \ actor_rollout_ref.actor.kl_loss_type=mse \ actor_rollout_ref.model.enable_gradient_checkpointing=True \ actor_rollout_ref.actor.fsdp_config.param_offload=False \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=False \ actor_rollout_ref.actor.fsdp_config.param_offload=True \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=True \ actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=1 \ actor_rollout_ref.rollout.tensor_model_parallel_size=4 \ actor_rollout_ref.rollout.name=vllm \ actor_rollout_ref.rollout.gpu_memory_utilization=0.2 \ actor_rollout_ref.rollout.gpu_memory_utilization=0.1 \ actor_rollout_ref.rollout.enable_chunked_prefill=False \ actor_rollout_ref.rollout.enforce_eager=False \ actor_rollout_ref.rollout.free_cache_engine=False \ Loading
scripts/exps/format/svg/worldmodeling/run.sh +3 −3 Original line number Diff line number Diff line Loading @@ -39,12 +39,12 @@ python3 -m vagen.trainer.main_ppo \ actor_rollout_ref.actor.kl_loss_coef=0.001 \ actor_rollout_ref.actor.kl_loss_type=mse \ actor_rollout_ref.model.enable_gradient_checkpointing=True \ actor_rollout_ref.actor.fsdp_config.param_offload=False \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=False \ actor_rollout_ref.actor.fsdp_config.param_offload=True \ actor_rollout_ref.actor.fsdp_config.optimizer_offload=True \ actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=1 \ actor_rollout_ref.rollout.tensor_model_parallel_size=4 \ actor_rollout_ref.rollout.name=vllm \ actor_rollout_ref.rollout.gpu_memory_utilization=0.2 \ actor_rollout_ref.rollout.gpu_memory_utilization=0.1 \ actor_rollout_ref.rollout.enable_chunked_prefill=False \ actor_rollout_ref.rollout.enforce_eager=False \ actor_rollout_ref.rollout.free_cache_engine=False \ Loading
