{
  "actor_rollout_ref": {
    "actor": {
      "_target_": "verl.workers.config.FSDPActorConfig",
      "calculate_entropy": false,
      "calculate_sum_pi_squared": false,
      "checkpoint": {
        "_target_": "verl.trainer.config.CheckpointConfig",
        "async_save": false,
        "load_contents": [
          "model",
          "optimizer",
          "extra"
        ],
        "mbridge_config": {},
        "save_contents": [
          "model",
          "optimizer",
          "extra"
        ]
      },
      "clip_ratio": 0.2,
      "clip_ratio_c": 3.0,
      "clip_ratio_high": 0.2,
      "clip_ratio_low": 0.2,
      "data_loader_seed": 42,
      "entropy_checkpointing": false,
      "entropy_coeff": 0.0,
      "entropy_from_logits_with_chunking": false,
      "freeze_vision_tower": false,
      "fsdp_config": {
        "_target_": "verl.workers.config.FSDPEngineConfig",
        "dtype": "bfloat16",
        "entropy_checkpointing": false,
        "entropy_from_logits_with_chunking": false,
        "forward_only": false,
        "forward_prefetch": false,
        "fsdp_size": -1,
        "full_determinism": false,
        "model_dtype": "fp32",
        "offload_policy": false,
        "optimizer_offload": false,
        "param_offload": false,
        "qat": {
          "_target_": "verl.workers.config.QATEngineConfig",
          "activation_observer": "static_minmax",
          "enable": false,
          "group_size": 16,
          "ignore_patterns": [
            "lm_head",
            "embed_tokens",
            "re:.*mlp.gate$"
          ],
          "mode": "w4a16",
          "quantization_config_path": null
        },
        "reshard_after_forward": true,
        "seed": 42,
        "strategy": "fsdp",
        "ulysses_sequence_parallel_size": 1,
        "use_orig_params": false,
        "use_torch_compile": true,
        "wrap_policy": {
          "min_num_params": 0
        }
      },
      "grad_clip": 1.0,
      "kl_loss_coef": 0.0,
      "kl_loss_type": "low_var_kl",
      "loss_agg_mode": "token-mean",
      "loss_scale_factor": null,
      "optim": {
        "_target_": "verl.workers.config.FSDPOptimizerConfig",
        "betas": [
          0.9,
          0.999
        ],
        "clip_grad": 1.0,
        "lr": 0.1,
        "lr_scheduler_type": "constant",
        "lr_warmup_steps": -1,
        "lr_warmup_steps_ratio": 0.0,
        "min_lr_ratio": 0.0,
        "num_cycles": 0.5,
        "optimizer": "SGD",
        "optimizer_impl": "torch.optim",
        "override_optimizer_config": {
          "dampening": 0.0,
          "momentum": 0.0,
          "nesterov": false
        },
        "total_training_steps": -1,
        "warmup_style": null,
        "weight_decay": 0.0,
        "zero_indexed_step": true
      },
      "policy_loss": {
        "_target_": "verl.workers.config.PolicyLossConfig",
        "clip_cov_lb": 1.0,
        "clip_cov_ratio": 0.0002,
        "clip_cov_ub": 5.0,
        "kl_cov_ratio": 0.0002,
        "loss_mode": "vanilla",
        "ppo_kl_coef": 0.1
      },
      "ppo_epochs": 1,
      "ppo_max_token_len_per_gpu": 16384,
      "ppo_micro_batch_size": null,
      "ppo_micro_batch_size_per_gpu": 4,
      "ppo_mini_batch_size": 128,
      "profiler": {
        "_target_": "verl.utils.profiler.ProfilerConfig",
        "all_ranks": false,
        "enable": false,
        "ranks": [],
        "save_path": "outputs/profile",
        "tool": null,
        "tool_config": {
          "npu": {
            "_target_": "verl.utils.profiler.config.NPUToolConfig",
            "analysis": true,
            "contents": [],
            "discrete": false,
            "level": "level0"
          },
          "nsys": {
            "_target_": "verl.utils.profiler.config.NsightToolConfig",
            "discrete": false
          },
          "torch": {
            "_target_": "verl.utils.profiler.config.TorchProfilerToolConfig",
            "contents": [],
            "discrete": false
          },
          "torch_memory": {
            "_target_": "verl.utils.profiler.config.TorchMemoryToolConfig",
            "stack_depth": 32,
            "trace_alloc_max_entries": 100000
          }
        }
      },
      "qat": {
        "activation_observer": "static_minmax",
        "enable": false,
        "group_size": 16,
        "ignore_patterns": [
          "lm_head",
          "embed_tokens",
          "re:.*mlp.gate$"
        ],
        "mode": "w4a16",
        "quantization_config_path": null
      },
      "rollout_n": 4,
      "router_replay": {
        "_target_": "verl.workers.config.RouterReplayConfig",
        "mode": "disabled",
        "record_file": null,
        "replay_file": null
      },
      "shuffle": false,
      "strategy": "fsdp",
      "sum_pi_squared_checkpointing": false,
      "tau_neg": 1.05,
      "tau_pos": 1.0,
      "ulysses_sequence_parallel_size": 1,
      "use_dynamic_bsz": false,
      "use_fused_kernels": true,
      "use_kl_loss": false,
      "use_prefix_grouper": false,
      "use_remove_padding": true,
      "use_torch_compile": true
    },
    "hybrid_engine": true,
    "model": {
      "_target_": "verl.workers.config.HFModelConfig",
      "custom_chat_template": null,
      "enable_activation_offload": false,
      "enable_gradient_checkpointing": false,
      "exclude_modules": null,
      "external_lib": null,
      "fused_kernel_options": {
        "impl_backend": "torch"
      },
      "hf_config_path": null,
      "lora_adapter_path": null,
      "lora_alpha": 16,
      "lora_rank": 0,
      "mtp": {
        "_target_": "verl.workers.config.MtpConfig",
        "detach_encoder": false,
        "enable": false,
        "enable_rollout": false,
        "enable_train": false,
        "method": "mtp",
        "mtp_loss_scaling_factor": 0.1,
        "num_speculative_tokens": 1,
        "speculative_algorithm": "EAGLE",
        "speculative_eagle_topk": 1,
        "speculative_num_draft_tokens": 4,
        "speculative_num_steps": 3
      },
      "override_config": {},
      "path": "Qwen/Qwen3-1.7B-Base",
      "target_modules": "all-linear",
      "tiled_mlp": {
        "enabled": false,
        "num_shards": 4
      },
      "tokenizer_path": null,
      "trust_remote_code": false,
      "use_fused_kernels": true,
      "use_liger": false,
      "use_remove_padding": true,
      "use_shm": false
    },
    "nccl_timeout": 600,
    "ref": {
      "_target_": "verl.workers.config.FSDPActorConfig",
      "entropy_checkpointing": false,
      "entropy_from_logits_with_chunking": false,
      "fsdp_config": {
        "_target_": "verl.workers.config.FSDPEngineConfig",
        "dtype": "bfloat16",
        "entropy_checkpointing": false,
        "entropy_from_logits_with_chunking": false,
        "forward_only": true,
        "forward_prefetch": false,
        "fsdp_size": -1,
        "full_determinism": false,
        "model_dtype": "fp32",
        "offload_policy": false,
        "optimizer_offload": false,
        "param_offload": false,
        "qat": {
          "_target_": "verl.workers.config.QATEngineConfig",
          "activation_observer": "static_minmax",
          "enable": false,
          "group_size": 16,
          "ignore_patterns": [
            "lm_head",
            "embed_tokens",
            "re:.*mlp.gate$"
          ],
          "mode": "w4a16",
          "quantization_config_path": null
        },
        "reshard_after_forward": true,
        "seed": 42,
        "strategy": "fsdp",
        "ulysses_sequence_parallel_size": 1,
        "use_orig_params": false,
        "use_torch_compile": true,
        "wrap_policy": {
          "min_num_params": 0
        }
      },
      "log_prob_max_token_len_per_gpu": 16384,
      "log_prob_micro_batch_size": null,
      "log_prob_micro_batch_size_per_gpu": 4,
      "log_prob_use_dynamic_bsz": false,
      "profiler": {
        "_target_": "verl.utils.profiler.ProfilerConfig",
        "all_ranks": false,
        "enable": false,
        "ranks": [],
        "save_path": "outputs/profile",
        "tool": null,
        "tool_config": {
          "npu": {
            "_target_": "verl.utils.profiler.config.NPUToolConfig",
            "analysis": true,
            "contents": [],
            "discrete": false,
            "level": "level0"
          },
          "nsys": {
            "_target_": "verl.utils.profiler.config.NsightToolConfig",
            "discrete": false
          },
          "torch": {
            "_target_": "verl.utils.profiler.config.TorchProfilerToolConfig",
            "contents": [],
            "discrete": false
          },
          "torch_memory": {
            "_target_": "verl.utils.profiler.config.TorchMemoryToolConfig",
            "stack_depth": 32,
            "trace_alloc_max_entries": 100000
          }
        }
      },
      "rollout_n": 4,
      "router_replay": {
        "_target_": "verl.workers.config.RouterReplayConfig",
        "mode": "disabled",
        "record_file": null,
        "replay_file": null
      },
      "strategy": "fsdp",
      "ulysses_sequence_parallel_size": 1,
      "use_torch_compile": true
    },
    "rollout": {
      "_target_": "verl.workers.config.RolloutConfig",
      "agent": {
        "_target_": "verl.workers.config.AgentLoopConfig",
        "agent_loop_config_path": null,
        "custom_async_server": {
          "_target_": "verl.workers.config.CustomAsyncServerConfig",
          "name": null,
          "path": null
        },
        "default_agent_loop": "single_turn_agent",
        "num_workers": 8
      },
      "calculate_log_probs": false,
      "checkpoint_engine": {
        "_target_": "verl.workers.config.CheckpointEngineConfig",
        "backend": "naive",
        "engine_kwargs": {},
        "update_weights_bucket_megabytes": 2048
      },
      "cudagraph_capture_sizes": null,
      "data_parallel_size": 1,
      "disable_log_stats": true,
      "do_sample": true,
      "dtype": "bfloat16",
      "enable_chunked_prefill": true,
      "enable_prefix_caching": true,
      "enable_rollout_routing_replay": false,
      "enforce_eager": false,
      "engine_kwargs": {
        "sglang": {},
        "trtllm": {},
        "vllm": {}
      },
      "expert_parallel_size": 1,
      "free_cache_engine": true,
      "gpu_memory_utilization": 0.85,
      "ignore_eos": false,
      "layered_summon": false,
      "load_format": "dummy",
      "log_prob_max_token_len_per_gpu": 16384,
      "log_prob_micro_batch_size": null,
      "log_prob_micro_batch_size_per_gpu": 4,
      "log_prob_use_dynamic_bsz": false,
      "logprobs_mode": "processed_logprobs",
      "max_model_len": null,
      "max_num_batched_tokens": 8192,
      "max_num_seqs": 1024,
      "mode": "async",
      "mtp": {
        "_target_": "verl.workers.config.MtpConfig",
        "detach_encoder": false,
        "enable": false,
        "enable_rollout": false,
        "enable_train": false,
        "method": "mtp",
        "mtp_loss_scaling_factor": 0.1,
        "num_speculative_tokens": 1,
        "speculative_algorithm": "EAGLE",
        "speculative_eagle_topk": 1,
        "speculative_num_draft_tokens": 4,
        "speculative_num_steps": 3
      },
      "multi_stage_wake_up": false,
      "multi_turn": {
        "_target_": "verl.workers.config.MultiTurnConfig",
        "enable": false,
        "format": "hermes",
        "interaction_config_path": null,
        "max_assistant_turns": null,
        "max_parallel_calls": 1,
        "max_tool_response_length": 256,
        "max_user_turns": null,
        "num_repeat_rollouts": null,
        "tokenization_sanity_check_mode": "strict",
        "tool_config_path": null,
        "tool_response_truncate_side": "middle",
        "use_inference_chat_template": false
      },
      "n": 4,
      "n_gpus_per_node": 4,
      "name": "vllm",
      "nnodes": 0,
      "over_sample_rate": 0,
      "pipeline_model_parallel_size": 1,
      "profiler": {
        "_target_": "verl.utils.profiler.ProfilerConfig",
        "all_ranks": false,
        "enable": false,
        "ranks": [],
        "save_path": "outputs/profile",
        "tool": null,
        "tool_config": {
          "npu": {
            "_target_": "verl.utils.profiler.config.NPUToolConfig",
            "analysis": true,
            "contents": [],
            "discrete": false,
            "level": "level0"
          },
          "torch": {
            "_target_": "verl.utils.profiler.config.TorchProfilerToolConfig",
            "contents": [],
            "discrete": false
          }
        }
      },
      "prometheus": {
        "_target_": "verl.workers.config.PrometheusConfig",
        "enable": false,
        "file": "/tmp/ray/session_latest/metrics/prometheus/prometheus.yml",
        "port": 9090,
        "served_model_name": "Qwen/Qwen3-1.7B-Base"
      },
      "prompt_length": 1024,
      "qat": {
        "_target_": "verl.workers.config.QATEngineConfig",
        "activation_observer": "static_minmax",
        "enable": false,
        "group_size": 16,
        "ignore_patterns": [
          "lm_head",
          "embed_tokens",
          "re:.*mlp.gate$"
        ],
        "mode": "w4a16",
        "quantization_config_path": null
      },
      "quantization": null,
      "quantization_config_file": null,
      "response_length": 8192,
      "scheduling_policy": "fcfs",
      "skip_dump_dir": "/tmp/rollout_dump",
      "skip_rollout": false,
      "skip_tokenizer_init": true,
      "temperature": 1.0,
      "tensor_model_parallel_size": 1,
      "top_k": -1,
      "top_p": 1,
      "trace": {
        "_target_": "verl.workers.config.TraceConfig",
        "backend": null,
        "experiment_name": "polaris_1p7b_sgd_lr1e-1_bs128_gpu4_ep5_n4",
        "max_samples_per_step_per_worker": null,
        "project_name": "sgd_rerun_polaris_1p7b",
        "token2text": false
      },
      "val_kwargs": {
        "_target_": "verl.workers.config.SamplingConfig",
        "do_sample": false,
        "n": 1,
        "temperature": 0,
        "top_k": -1,
        "top_p": 1.0
      }
    }
  },
  "algorithm": {
    "_target_": "verl.trainer.config.AlgoConfig",
    "adv_estimator": "grpo",
    "gamma": 1.0,
    "kl_ctrl": {
      "_target_": "verl.trainer.config.KLControlConfig",
      "horizon": 10000,
      "kl_coef": 0.001,
      "target_kl": 0.1,
      "type": "fixed"
    },
    "kl_penalty": "kl",
    "lam": 1.0,
    "norm_adv_by_std_in_grpo": true,
    "pf_ppo": {
      "reweight_method": "pow",
      "weight_pow": 2.0
    },
    "rollout_correction": {
      "bypass_mode": false,
      "loss_type": "ppo_clip",
      "rollout_is": null,
      "rollout_is_batch_normalize": false,
      "rollout_is_threshold": 2.0,
      "rollout_rs": null,
      "rollout_rs_threshold": null
    },
    "use_kl_in_reward": false,
    "use_pf_ppo": false
  },
  "critic": {
    "_target_": "verl.workers.config.FSDPCriticConfig",
    "checkpoint": {
      "_target_": "verl.trainer.config.CheckpointConfig",
      "async_save": false,
      "load_contents": [
        "model",
        "optimizer",
        "extra"
      ],
      "mbridge_config": {},
      "save_contents": [
        "model",
        "optimizer",
        "extra"
      ]
    },
    "cliprange_value": 0.5,
    "data_loader_seed": 42,
    "enable": null,
    "forward_max_token_len_per_gpu": 32768,
    "forward_micro_batch_size": null,
    "forward_micro_batch_size_per_gpu": null,
    "grad_clip": 1.0,
    "loss_agg_mode": "token-mean",
    "model": {
      "_target_": "verl.workers.config.FSDPCriticModelCfg",
      "enable_activation_offload": false,
      "enable_gradient_checkpointing": true,
      "external_lib": null,
      "fsdp_config": {
        "_target_": "verl.workers.config.FSDPEngineConfig",
        "dtype": "bfloat16",
        "entropy_checkpointing": false,
        "entropy_from_logits_with_chunking": false,
        "forward_only": false,
        "forward_prefetch": false,
        "fsdp_size": -1,
        "full_determinism": false,
        "model_dtype": "fp32",
        "offload_policy": false,
        "optimizer_offload": false,
        "param_offload": false,
        "qat": {
          "_target_": "verl.workers.config.QATEngineConfig",
          "activation_observer": "static_minmax",
          "enable": false,
          "group_size": 16,
          "ignore_patterns": [
            "lm_head",
            "embed_tokens",
            "re:.*mlp.gate$"
          ],
          "mode": "w4a16",
          "quantization_config_path": null
        },
        "reshard_after_forward": true,
        "seed": 42,
        "strategy": "fsdp",
        "ulysses_sequence_parallel_size": 1,
        "use_orig_params": false,
        "use_torch_compile": true,
        "wrap_policy": {
          "min_num_params": 0
        }
      },
      "lora_alpha": 16,
      "lora_rank": 0,
      "override_config": {},
      "path": "~/models/deepseek-llm-7b-chat",
      "target_modules": "all-linear",
      "tiled_mlp": {
        "enabled": false,
        "num_shards": 4
      },
      "tokenizer_path": "Qwen/Qwen3-1.7B-Base",
      "trust_remote_code": false,
      "use_remove_padding": false,
      "use_shm": false
    },
    "optim": {
      "_target_": "verl.workers.config.FSDPOptimizerConfig",
      "betas": [
        0.9,
        0.999
      ],
      "clip_grad": 1.0,
      "lr": 1e-05,
      "lr_scheduler_type": "constant",
      "lr_warmup_steps": -1,
      "lr_warmup_steps_ratio": 0.0,
      "min_lr_ratio": 0.0,
      "num_cycles": 0.5,
      "optimizer": "AdamW",
      "optimizer_impl": "torch.optim",
      "override_optimizer_config": null,
      "total_training_steps": -1,
      "warmup_style": null,
      "weight_decay": 0.01,
      "zero_indexed_step": true
    },
    "ppo_epochs": 1,
    "ppo_max_token_len_per_gpu": 32768,
    "ppo_micro_batch_size": null,
    "ppo_micro_batch_size_per_gpu": null,
    "ppo_mini_batch_size": 128,
    "profiler": {
      "_target_": "verl.utils.profiler.ProfilerConfig",
      "all_ranks": false,
      "enable": false,
      "ranks": [],
      "save_path": "outputs/profile",
      "tool": null,
      "tool_config": {
        "npu": {
          "_target_": "verl.utils.profiler.config.NPUToolConfig",
          "analysis": true,
          "contents": [],
          "discrete": false,
          "level": "level0"
        },
        "nsys": {
          "_target_": "verl.utils.profiler.config.NsightToolConfig",
          "discrete": false
        },
        "torch": {
          "_target_": "verl.utils.profiler.config.TorchProfilerToolConfig",
          "contents": [],
          "discrete": false
        },
        "torch_memory": {
          "_target_": "verl.utils.profiler.config.TorchMemoryToolConfig",
          "stack_depth": 32,
          "trace_alloc_max_entries": 100000
        }
      }
    },
    "rollout_n": 4,
    "shuffle": false,
    "strategy": "fsdp",
    "ulysses_sequence_parallel_size": 1,
    "use_dynamic_bsz": false
  },
  "data": {
    "apply_chat_template_kwargs": {},
    "custom_cls": {
      "name": null,
      "path": null
    },
    "datagen": {
      "name": null,
      "path": null
    },
    "dataloader_num_workers": 8,
    "filter_overlong_prompts": true,
    "filter_overlong_prompts_workers": 1,
    "image_key": "images",
    "image_patch_size": 14,
    "max_prompt_length": 1024,
    "max_response_length": 8192,
    "prompt_key": "prompt",
    "return_full_prompt": false,
    "return_multi_modal_inputs": true,
    "return_raw_chat": true,
    "return_raw_input_ids": false,
    "reward_fn_key": "data_source",
    "sampler": {
      "class_name": null,
      "class_path": null
    },
    "seed": null,
    "shuffle": true,
    "tokenizer": null,
    "tool_config_path": null,
    "train_batch_size": 128,
    "train_files": "/home/scratch.pjayasinha_gpu/rs/data_polaris/train.parquet",
    "train_max_samples": -1,
    "truncation": "error",
    "trust_remote_code": false,
    "use_shm": false,
    "val_batch_size": null,
    "val_files": [
      "/home/scratch.pjayasinha_gpu/rs/data_polaris/val.parquet"
    ],
    "val_max_samples": -1,
    "validation_shuffle": false,
    "video_key": "videos"
  },
  "global_profiler": {
    "_target_": "verl.utils.profiler.ProfilerConfig",
    "global_tool_config": {
      "nsys": {
        "_target_": "verl.utils.profiler.config.NsightToolConfig",
        "controller_nsight_options": {
          "cuda-graph-trace": "graph",
          "cuda-memory-usage": "true",
          "trace": "cuda,nvtx,cublas,ucx"
        },
        "discrete": false,
        "worker_nsight_options": {
          "capture-range": "cudaProfilerApi",
          "capture-range-end": null,
          "cuda-graph-trace": "graph",
          "cuda-memory-usage": "true",
          "kill": "none",
          "trace": "cuda,nvtx,cublas,ucx"
        }
      },
      "torch_memory": {
        "context": "all",
        "kw_args": {},
        "stack_depth": 32,
        "stacks": "all",
        "trace_alloc_max_entries": 100000
      }
    },
    "profile_continuous_steps": false,
    "save_path": "outputs/profile",
    "steps": null,
    "tool": null
  },
  "model_engine": "dp",
  "ray_kwargs": {
    "ray_init": {
      "num_cpus": null
    },
    "timeline_json_file": null
  },
  "reward": {
    "custom_reward_function": {
      "name": "compute_score",
      "path": null
    },
    "num_workers": 8,
    "reward_manager": {
      "_target_": "verl.workers.config.reward_model.RewardManagerConfig",
      "module": {
        "_target_": "verl.trainer.config.config.ModuleConfig",
        "name": "custom_reward_manager",
        "path": null
      },
      "name": "naive",
      "source": "register"
    },
    "reward_model": {
      "enable": false,
      "enable_resource_pool": false,
      "model_path": null,
      "n_gpus_per_node": 8,
      "nnodes": 0,
      "rollout": {
        "_target_": "verl.workers.config.RolloutConfig",
        "cudagraph_capture_sizes": null,
        "data_parallel_size": 1,
        "disable_log_stats": true,
        "dtype": "bfloat16",
        "enable_chunked_prefill": true,
        "enable_prefix_caching": true,
        "enforce_eager": true,
        "engine_kwargs": {},
        "expert_parallel_size": 1,
        "free_cache_engine": true,
        "gpu_memory_utilization": 0.5,
        "limit_images": null,
        "load_format": "auto",
        "max_model_len": null,
        "max_num_batched_tokens": 8192,
        "max_num_seqs": 1024,
        "name": "???",
        "prompt_length": 2048,
        "response_length": 2048,
        "skip_tokenizer_init": false,
        "tensor_model_parallel_size": 2
      }
    },
    "sandbox_fusion": {
      "max_concurrent": 64,
      "memory_limit_mb": 1024,
      "url": null
    }
  },
  "trainer": {
    "balance_batch": true,
    "critic_warmup": 0,
    "default_hdfs_dir": null,
    "default_local_dir": "/home/scratch.pjayasinha_gpu/rs/checkpoints/polaris_1p7b_sgd_lr1e-1_bs128_gpu4_ep5_n4",
    "del_local_ckpt_after_load": false,
    "device": "cuda",
    "esi_redundant_time": 0,
    "experiment_name": "polaris_1p7b_sgd_lr1e-1_bs128_gpu4_ep5_n4",
    "log_val_generations": 0,
    "logger": [
      "console",
      "wandb"
    ],
    "max_actor_ckpt_to_keep": null,
    "max_critic_ckpt_to_keep": null,
    "n_gpus_per_node": 4,
    "nnodes": 1,
    "project_name": "sgd_rerun_polaris_1p7b",
    "ray_wait_register_center_timeout": 300,
    "resume_from_path": null,
    "resume_mode": "auto",
    "rollout_data_dir": null,
    "save_freq": 25,
    "test_freq": 50,
    "total_epochs": 5,
    "total_training_steps": null,
    "use_legacy_worker_impl": "auto",
    "val_before_train": true,
    "val_only": false,
    "validation_data_dir": null,
    "wandb": {
      "entity": "pavanjayasinha-university-of-illinois-urbana-champaign"
    }
  },
  "transfer_queue": {
    "enable": false
  }
}