{
  "runs": [
    {
      "run_id": "cpgrad-tp2cp4-r5",
      "steps": {
        "0": {
          "train/loss": 3.9848928281571716e-05,
          "train/pg_loss": 0.0,
          "train/entropy_loss": 0.12023040652275085,
          "train/pg_clipfrac": 0.0,
          "train/ppo_kl": 0.0,
          "train/train_rollout_logprob_abs_diff": 0.0,
          "train/train_current_rollout_logprob_mismatch_count": 0.0,
          "train/train_current_rollout_logprob_max_abs_diff": 0.0,
          "train/train_current_rollout_logprob_numel": 512.0,
          "train/kl_loss": 0.00398489274084568,
          "train/ois": 1.0,
          "train/tis": 1.0,
          "train/tis_clipfrac": 0.0,
          "train/tis_abs": 0.0,
          "train/grad_norm": 0.022594607365076035,
          "train/lr-pg_0": 5e-07,
          "train/lr-pg_1": 5e-07,
          "train/global_batch_size": 8,
          "train/step": 0
        },
        "1": {
          "train/loss": 7.246405584737659e-05,
          "train/pg_loss": 0.0,
          "train/entropy_loss": 0.15511181950569153,
          "train/pg_clipfrac": 0.0,
          "train/ppo_kl": 0.0,
          "train/train_rollout_logprob_abs_diff": 0.0,
          "train/train_current_rollout_logprob_mismatch_count": 0.0,
          "train/train_current_rollout_logprob_max_abs_diff": 0.0,
          "train/train_current_rollout_logprob_numel": 512.0,
          "train/kl_loss": 0.007246405817568302,
          "train/ois": 1.0,
          "train/tis": 1.0,
          "train/tis_clipfrac": 0.0,
          "train/tis_abs": 0.0,
          "train/grad_norm": 0.03439536852782456,
          "train/lr-pg_0": 5e-07,
          "train/lr-pg_1": 5e-07,
          "train/global_batch_size": 8,
          "train/step": 1
        }
      },
      "performance": {
        "0": {
          "perf/update_weights_time": 27.520503759384155,
          "perf/data_preprocess_time": 0.011134147644042969,
          "perf/train_wait_time": 38.43356251716614,
          "perf/ref_log_probs_time": 2.0215706825256348,
          "perf/log_probs_time": 0.4188084602355957,
          "perf/actor_train_time": 3.4440557956695557,
          "perf/train_time": 6.259614706039429,
          "perf/log_probs_tflops": 23.826277657950442,
          "perf/ref_log_probs_tflops": 4.936085957976621,
          "perf/actor_train_tflops": 8.69206010392064,
          "perf/actor_train_tok_per_s": 1512.1706235271713,
          "perf/step_time": 44.693177223205566,
          "perf/wait_time_ratio": 0.8599424991698886
        },
        "1": {
          "perf/update_weights_time": 27.544374227523804,
          "perf/data_preprocess_time": 0.011069059371948242,
          "perf/train_wait_time": 37.61604309082031,
          "perf/ref_log_probs_time": 0.5046274662017822,
          "perf/log_probs_time": 0.33281421661376953,
          "perf/actor_train_time": 3.6114234924316406,
          "perf/train_time": 4.819371938705444,
          "perf/log_probs_tflops": 28.863948621269795,
          "perf/ref_log_probs_tflops": 19.03648352927103,
          "perf/actor_train_tflops": 7.979955108200179,
          "perf/actor_train_tok_per_s": 1388.9260039737492,
          "perf/step_time": 42.43541502952576,
          "perf/wait_time_ratio": 0.8864304276191899
        }
      },
      "tokens": {
        "0": {
          "sha256": "875d2f13205808479cc3ecbf518b8f5f066b7755547e6d5205e38f2ffd68a8ae",
          "sample_count": 8,
          "token_count": 5208
        },
        "1": {
          "sha256": "10ee3cb81d196c791fd6a5ea0a14db968d4a54ae29ab21d73b263cb25b54bae1",
          "sample_count": 8,
          "token_count": 5016
        }
      },
      "validation": {
        "cudagraph": {
          "checks": {
            "capture_sizes": true,
            "engine_mode": true,
            "launcher_marker": true,
            "not_eager": true
          },
          "expected_capture_sizes": [
            1,
            2,
            3,
            4
          ],
          "passed": true
        },
        "errors": [],
        "group": "consistency",
        "offline_tensor_comparison": {
          "artifact_count": 16,
          "comparable_artifact_count": 16,
          "reason": null,
          "status": "available"
        },
        "passed": true,
        "run_id": "cpgrad-tp2cp4-r5",
        "runtime_readbacks": {
          "errors": [],
          "frameworks": {
            "megatron/training": {
              "modules": {
                "attention": {
                  "backend_ids": [
                    "rlkernel.attention.deterministic.v1"
                  ],
                  "call_count": 2304,
                  "case_id": "R/R",
                  "expected_implementation": "rl_kernel",
                  "implementations": [
                    "rl_kernel"
                  ],
                  "installed_processes": 8
                },
                "ffn": {
                  "backend_ids": [
                    "rlkernel.ffn.qwen3.deterministic.v1"
                  ],
                  "call_count": 2304,
                  "case_id": "R/R",
                  "expected_implementation": "rl_kernel",
                  "implementations": [
                    "rl_kernel"
                  ],
                  "installed_processes": 8
                },
                "logp": {
                  "backend_ids": [
                    "rlkernel.linear_logp.bitwise.v1"
                  ],
                  "call_count": 48,
                  "case_id": "R/R",
                  "expected_implementation": "rl_kernel",
                  "implementations": [
                    "rl_kernel"
                  ],
                  "installed_processes": 8
                }
              },
              "readback_count": 8
            },
            "vllm/rollout": {
              "modules": {
                "attention": {
                  "backend_ids": [
                    "rlkernel.attention.deterministic.v1"
                  ],
                  "call_count": 3168,
                  "case_id": "R/R",
                  "expected_implementation": "rl_kernel",
                  "implementations": [
                    "rl_kernel"
                  ],
                  "installed_processes": 13
                },
                "ffn": {
                  "backend_ids": [
                    "rlkernel.ffn.qwen3.deterministic.v1"
                  ],
                  "call_count": 3176,
                  "case_id": "R/R",
                  "expected_implementation": "rl_kernel",
                  "implementations": [
                    "rl_kernel"
                  ],
                  "installed_processes": 13
                },
                "logp": {
                  "backend_ids": [
                    "rlkernel.linear_logp.bitwise.v1"
                  ],
                  "call_count": 8,
                  "case_id": "R/R",
                  "expected_implementation": "rl_kernel",
                  "implementations": [
                    "rl_kernel"
                  ],
                  "installed_processes": 13
                }
              },
              "readback_count": 13
            }
          },
          "passed": true
        },
        "runtime_scalar_logprob": {
          "bitwise_zero": true,
          "errors": [],
          "evidence_source": "VIME runtime torch.ne/max metrics; VIME reports sample means, converted to counts with global_batch_size",
          "passed": true,
          "rows": [
            {
              "active_token_count": 4096.0,
              "bitwise_mismatch_count": 0.0,
              "max_abs_dlogp": 0.0,
              "mean_abs_dlogp": 0.0,
              "step": 0,
              "vime_mean_active_tokens_per_sample": 512.0,
              "vime_mean_mismatch_count_per_sample": 0.0
            },
            {
              "active_token_count": 4096.0,
              "bitwise_mismatch_count": 0.0,
              "max_abs_dlogp": 0.0,
              "mean_abs_dlogp": 0.0,
              "step": 1,
              "vime_mean_active_tokens_per_sample": 512.0,
              "vime_mean_mismatch_count_per_sample": 0.0
            }
          ],
          "total_active_token_exposure": 8192.0
        },
        "schema_version": "rlkernel.vime_qwen3_8b_tp4_cp2_200.validation.v1",
        "train_rollout_logprob": {
          "artifacts": [
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00000.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00000.call00000001.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00001.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00001.call00000001.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00002.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00002.call00000001.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00003.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00003.call00000001.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00004.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00004.call00000001.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00005.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00005.call00000001.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00006.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00006.call00000001.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00007.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp2cp4-r5/mismatch-sidecars/rank00007.call00000001.pt"
          ],
          "bitwise_equal": true,
          "bitwise_mismatch_count": 0,
          "element_count": 8192,
          "errors": [],
          "max_abs_diff": 0.0,
          "mismatch_count": 0,
          "mismatch_k3_kl": 0.0,
          "mismatch_kl": 0.0,
          "passed": true,
          "require_exact": true,
          "sample_count": 16,
          "torch_equal": true,
          "train_rollout_logprob_abs_diff": 0.0
        }
      }
    },
    {
      "run_id": "cpgrad-tp4cp2-r5",
      "steps": {
        "0": {
          "train/loss": 3.9848928281571716e-05,
          "train/pg_loss": 0.0,
          "train/entropy_loss": 0.12023040652275085,
          "train/pg_clipfrac": 0.0,
          "train/ppo_kl": 0.0,
          "train/train_rollout_logprob_abs_diff": 0.0,
          "train/train_current_rollout_logprob_mismatch_count": 0.0,
          "train/train_current_rollout_logprob_max_abs_diff": 0.0,
          "train/train_current_rollout_logprob_numel": 512.0,
          "train/kl_loss": 0.00398489274084568,
          "train/ois": 1.0,
          "train/tis": 1.0,
          "train/tis_clipfrac": 0.0,
          "train/tis_abs": 0.0,
          "train/grad_norm": 0.022594607365076035,
          "train/lr-pg_0": 5e-07,
          "train/lr-pg_1": 5e-07,
          "train/global_batch_size": 8,
          "train/step": 0
        },
        "1": {
          "train/loss": 7.246405584737659e-05,
          "train/pg_loss": 0.0,
          "train/entropy_loss": 0.15511181950569153,
          "train/pg_clipfrac": 0.0,
          "train/ppo_kl": 0.0,
          "train/train_rollout_logprob_abs_diff": 0.0,
          "train/train_current_rollout_logprob_mismatch_count": 0.0,
          "train/train_current_rollout_logprob_max_abs_diff": 0.0,
          "train/train_current_rollout_logprob_numel": 512.0,
          "train/kl_loss": 0.007246405817568302,
          "train/ois": 1.0,
          "train/tis": 1.0,
          "train/tis_clipfrac": 0.0,
          "train/tis_abs": 0.0,
          "train/grad_norm": 0.03439536852782456,
          "train/lr-pg_0": 5e-07,
          "train/lr-pg_1": 5e-07,
          "train/global_batch_size": 8,
          "train/step": 1
        }
      },
      "performance": {
        "0": {
          "perf/update_weights_time": 27.7245192527771,
          "perf/data_preprocess_time": 0.010148048400878906,
          "perf/train_wait_time": 39.17587208747864,
          "perf/ref_log_probs_time": 1.6525583267211914,
          "perf/log_probs_time": 0.4971926212310791,
          "perf/actor_train_time": 3.4939475059509277,
          "perf/train_time": 5.906228542327881,
          "perf/log_probs_tflops": 20.069981397479843,
          "perf/ref_log_probs_tflops": 6.038302247927573,
          "perf/actor_train_tflops": 8.567942113105248,
          "perf/actor_train_tok_per_s": 1490.5776320707969,
          "perf/step_time": 45.08210062980652,
          "perf/wait_time_ratio": 0.8689895000495405
        },
        "1": {
          "perf/update_weights_time": 27.464809894561768,
          "perf/data_preprocess_time": 0.011140823364257812,
          "perf/train_wait_time": 37.27148199081421,
          "perf/ref_log_probs_time": 0.4749336242675781,
          "perf/log_probs_time": 0.39269542694091797,
          "perf/actor_train_time": 3.2326793670654297,
          "perf/train_time": 4.344621896743774,
          "perf/log_probs_tflops": 24.462552374497854,
          "perf/ref_log_probs_tflops": 20.22668423104906,
          "perf/actor_train_tflops": 8.9148950681321,
          "perf/actor_train_tok_per_s": 1551.6540400211227,
          "perf/step_time": 41.61610388755798,
          "perf/wait_time_ratio": 0.8956023872757899
        }
      },
      "tokens": {
        "0": {
          "sha256": "875d2f13205808479cc3ecbf518b8f5f066b7755547e6d5205e38f2ffd68a8ae",
          "sample_count": 8,
          "token_count": 5208
        },
        "1": {
          "sha256": "10ee3cb81d196c791fd6a5ea0a14db968d4a54ae29ab21d73b263cb25b54bae1",
          "sample_count": 8,
          "token_count": 5016
        }
      },
      "validation": {
        "cudagraph": {
          "checks": {
            "capture_sizes": true,
            "engine_mode": true,
            "launcher_marker": true,
            "not_eager": true
          },
          "expected_capture_sizes": [
            1,
            2,
            3,
            4
          ],
          "passed": true
        },
        "errors": [],
        "group": "consistency",
        "offline_tensor_comparison": {
          "artifact_count": 16,
          "comparable_artifact_count": 16,
          "reason": null,
          "status": "available"
        },
        "passed": true,
        "run_id": "cpgrad-tp4cp2-r5",
        "runtime_readbacks": {
          "errors": [],
          "frameworks": {
            "megatron/training": {
              "modules": {
                "attention": {
                  "backend_ids": [
                    "rlkernel.attention.deterministic.v1"
                  ],
                  "call_count": 2304,
                  "case_id": "R/R",
                  "expected_implementation": "rl_kernel",
                  "implementations": [
                    "rl_kernel"
                  ],
                  "installed_processes": 8
                },
                "ffn": {
                  "backend_ids": [
                    "rlkernel.ffn.qwen3.deterministic.v1"
                  ],
                  "call_count": 2304,
                  "case_id": "R/R",
                  "expected_implementation": "rl_kernel",
                  "implementations": [
                    "rl_kernel"
                  ],
                  "installed_processes": 8
                },
                "logp": {
                  "backend_ids": [
                    "rlkernel.linear_logp.bitwise.v1"
                  ],
                  "call_count": 48,
                  "case_id": "R/R",
                  "expected_implementation": "rl_kernel",
                  "implementations": [
                    "rl_kernel"
                  ],
                  "installed_processes": 8
                }
              },
              "readback_count": 8
            },
            "vllm/rollout": {
              "modules": {
                "attention": {
                  "backend_ids": [
                    "rlkernel.attention.deterministic.v1"
                  ],
                  "call_count": 3168,
                  "case_id": "R/R",
                  "expected_implementation": "rl_kernel",
                  "implementations": [
                    "rl_kernel"
                  ],
                  "installed_processes": 13
                },
                "ffn": {
                  "backend_ids": [
                    "rlkernel.ffn.qwen3.deterministic.v1"
                  ],
                  "call_count": 3176,
                  "case_id": "R/R",
                  "expected_implementation": "rl_kernel",
                  "implementations": [
                    "rl_kernel"
                  ],
                  "installed_processes": 13
                },
                "logp": {
                  "backend_ids": [
                    "rlkernel.linear_logp.bitwise.v1"
                  ],
                  "call_count": 8,
                  "case_id": "R/R",
                  "expected_implementation": "rl_kernel",
                  "implementations": [
                    "rl_kernel"
                  ],
                  "installed_processes": 13
                }
              },
              "readback_count": 13
            }
          },
          "passed": true
        },
        "runtime_scalar_logprob": {
          "bitwise_zero": true,
          "errors": [],
          "evidence_source": "VIME runtime torch.ne/max metrics; VIME reports sample means, converted to counts with global_batch_size",
          "passed": true,
          "rows": [
            {
              "active_token_count": 4096.0,
              "bitwise_mismatch_count": 0.0,
              "max_abs_dlogp": 0.0,
              "mean_abs_dlogp": 0.0,
              "step": 0,
              "vime_mean_active_tokens_per_sample": 512.0,
              "vime_mean_mismatch_count_per_sample": 0.0
            },
            {
              "active_token_count": 4096.0,
              "bitwise_mismatch_count": 0.0,
              "max_abs_dlogp": 0.0,
              "mean_abs_dlogp": 0.0,
              "step": 1,
              "vime_mean_active_tokens_per_sample": 512.0,
              "vime_mean_mismatch_count_per_sample": 0.0
            }
          ],
          "total_active_token_exposure": 8192.0
        },
        "schema_version": "rlkernel.vime_qwen3_8b_tp4_cp2_200.validation.v1",
        "train_rollout_logprob": {
          "artifacts": [
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00000.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00000.call00000001.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00001.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00001.call00000001.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00002.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00002.call00000001.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00003.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00003.call00000001.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00004.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00004.call00000001.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00005.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00005.call00000001.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00006.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00006.call00000001.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00007.call00000000.pt",
            "/data/ellm/vime_qwen3_8b_tp4_cp2_200_experiment/runs/configurable-20260919/cpgrad-tp4cp2-r5/mismatch-sidecars/rank00007.call00000001.pt"
          ],
          "bitwise_equal": true,
          "bitwise_mismatch_count": 0,
          "element_count": 8192,
          "errors": [],
          "max_abs_diff": 0.0,
          "mismatch_count": 0,
          "mismatch_k3_kl": 0.0,
          "mismatch_kl": 0.0,
          "passed": true,
          "require_exact": true,
          "sample_count": 16,
          "torch_equal": true,
          "train_rollout_logprob_abs_diff": 0.0
        }
      }
    }
  ],
  "all_parameter_hash_comparisons": [
    {
      "version": "weight_v000001",
      "sha256": [
        "3496e2625f9638323127a3967e42cddcad168315eb7b4af78078b9f3a91fd326",
        "3496e2625f9638323127a3967e42cddcad168315eb7b4af78078b9f3a91fd326"
      ],
      "tensor_count": 399,
      "unequal_parameter_tensors": [],
      "bitwise_equal": true
    },
    {
      "version": "weight_v000002",
      "sha256": [
        "d40036d7a970154371e07c699dd0af284c531e72a7991608d8895be104d24045",
        "d40036d7a970154371e07c699dd0af284c531e72a7991608d8895be104d24045"
      ],
      "tensor_count": 399,
      "unequal_parameter_tensors": [],
      "bitwise_equal": true
    },
    {
      "version": "weight_v000003",
      "sha256": [
        "05a28e2f229df5154aac7ba194f11dedfddcd4b2abf3846856f0c64143655fae",
        "05a28e2f229df5154aac7ba194f11dedfddcd4b2abf3846856f0c64143655fae"
      ],
      "tensor_count": 399,
      "unequal_parameter_tensors": [],
      "bitwise_equal": true
    }
  ],
  "gradient_norm_comparisons": [
    {
      "step": 0,
      "norms": [
        0.022594607365076035,
        0.022594607365076035
      ],
      "exactly_equal": true,
      "relative_difference_percent": 0.0
    },
    {
      "step": 1,
      "norms": [
        0.03439536852782456,
        0.03439536852782456
      ],
      "exactly_equal": true,
      "relative_difference_percent": 0.0
    }
  ],
  "tokens_equal": true
}
