{
  "schema_version": 1,
  "adapter_key": "smolwam",
  "validated_at": "2026-10-13T19:47:19.449362+00:00",
  "accelerator": {
    "vendor": "NVIDIA",
    "model": "NVIDIA A100-SXM4-80GB"
  },
  "command": [
    "python",
    "scripts/run_oct13_robotics.py",
    "--paper",
    "smolwam",
    "--phase",
    "train",
    "--config",
    "data/smolwam-train.json",
    "--seed",
    "42",
    "--output",
    "runs/smolwam-train-seed42.json"
  ],
  "commands": [
    [
      "python",
      "scripts/run_oct13_robotics.py",
      "--paper",
      "smolwam",
      "--phase",
      "train",
      "--config",
      "data/smolwam-train.json",
      "--seed",
      "42",
      "--output",
      "runs/smolwam-train-seed42.json"
    ],
    [
      "python",
      "scripts/run_oct13_robotics.py",
      "--paper",
      "smolwam",
      "--phase",
      "eval",
      "--config",
      "data/smolwam-candidate.json",
      "--seed",
      "42",
      "--output",
      "runs/smolwam-candidate-seed42.json"
    ],
    [
      "python",
      "scripts/run_oct13_robotics.py",
      "--paper",
      "smolwam",
      "--phase",
      "train",
      "--config",
      "data/smolwam-train.json",
      "--seed",
      "43",
      "--output",
      "runs/smolwam-train-seed43.json"
    ],
    [
      "python",
      "scripts/run_oct13_robotics.py",
      "--paper",
      "smolwam",
      "--phase",
      "eval",
      "--config",
      "data/smolwam-candidate.json",
      "--seed",
      "43",
      "--output",
      "runs/smolwam-candidate-seed43.json"
    ],
    [
      "python",
      "scripts/run_oct13_robotics.py",
      "--paper",
      "smolwam",
      "--phase",
      "train",
      "--config",
      "data/smolwam-train.json",
      "--seed",
      "44",
      "--output",
      "runs/smolwam-train-seed44.json"
    ],
    [
      "python",
      "scripts/run_oct13_robotics.py",
      "--paper",
      "smolwam",
      "--phase",
      "eval",
      "--config",
      "data/smolwam-candidate.json",
      "--seed",
      "44",
      "--output",
      "runs/smolwam-candidate-seed44.json"
    ]
  ],
  "seeds": [
    42,
    43,
    44
  ],
  "dataset": {
    "demonstrations": {
      "public_id": "nvidia/LIBERO-Cosmos-Policy",
      "revision": "b463cbd5d114909e4daea65eb03bed9787290042",
      "files": {
        "success_only/libero_goal_regen/put_the_cream_cheese_in_the_bowl_demo.hdf5": "533472726b4cf89b2000af1bc275f26fb6cdcd2a5706fbd65cbe019f58180ebb",
        "success_only/dataset_statistics.json": "5b119a98ad7824507ddff3c6c7507ca244261ee416dcfa623876702160c580d3"
      }
    },
    "control": {
      "public_id": "Lifelong-Robot-Learning/LIBERO",
      "revision": "8f1084e3132a39270c3a13ebe37270a43ece2a01",
      "resources": [
        "libero/libero/assets",
        "libero/libero/bddl_files",
        "libero/libero/init_files"
      ]
    }
  },
  "checkpoint": {
    "teacher": {
      "public_id": "nvidia/Cosmos-Policy-LIBERO-Predict2-2B",
      "revision": "cb689ec0e3347c13667d70a78a3447388f5c3bb8",
      "files": {
        "Cosmos-Policy-LIBERO-Predict2-2B.pt": "8818528d8c9150cda0ddf8c711b0f221b21dac8ac379bd26d5690235954d33e2",
        "libero_t5_embeddings.pkl": "8a03499676c6c196127c577144b9fd09bb02c30f9caf058adbcef09bb99ad8f5",
        "libero_dataset_statistics.json": "5b119a98ad7824507ddff3c6c7507ca244261ee416dcfa623876702160c580d3"
      }
    },
    "frozen_adapter_text": {
      "public_id": "timiiowolabi/SmolWAM",
      "revision": "c269c6e3a9c113b2b04187daf977c09486e2eadc",
      "files": {
        "model.safetensors": "dd1f0341e2718fc8eaf616401c83b1a376d0780d34d31a825d8053180c25772a",
        "config.json": "b3916f24e4597611dd5ca99f46d0d9f3cd40a51919840d3cef92538bd7a54d99",
        "text_cache.safetensors": "a2b6dc0bca98929000210b2aa9f26489570b88cd7bc2525f2dd410d0a1dda7a6"
      }
    },
    "vae": {
      "public_id": "Wan-AI/Wan2.1-T2V-1.3B",
      "revision": "37ec512624d61f7aa208f7ea8140a131f93afc9a",
      "files": {
        "Wan2.1_VAE.pth": "38071ab59bd94681c686fa51d75a1968f64e470262043be31f7a094e442fd981"
      }
    },
    "new_students": {
      "42": {
        "dataset": {
          "files": {
            "success_only/dataset_statistics.json": "5b119a98ad7824507ddff3c6c7507ca244261ee416dcfa623876702160c580d3",
            "success_only/libero_goal_regen/put_the_cream_cheese_in_the_bowl_demo.hdf5": "533472726b4cf89b2000af1bc275f26fb6cdcd2a5706fbd65cbe019f58180ebb"
          },
          "public_id": "nvidia/LIBERO-Cosmos-Policy",
          "revision": "b463cbd5d114909e4daea65eb03bed9787290042"
        },
        "files": {
          "best.pt": "17fce20c7ca9b4ce723dc5701f647093f0239b41bd89cd128cc2f630c0adfd37"
        },
        "implementation_sha256": {
          "lewam/external.py": "0e0a9dbaa54d897f01f6d6f2d13584ec26c1dcf84f4e541685bbc04791056b56",
          "smolwam/algorithm.py": "ee5563a4b6e6da35b066536e31fc63bfda9a75b2ef98b40ecae06aed9220266b",
          "smolwam/training.py": "7826d69e86534d51239975591d0d43b41d686ad8d7f9dc65c554a6e7977db718",
          "smolwam/worker.py": "3485d8bafa5b3fa548ae2454677f490cf3f8791ba310d2d14c48d69ca0f7fd8c"
        },
        "kind": "local-trained-candidate",
        "metrics": {
          "best_validation_action_l1": 0.33299583569169044,
          "compact_layout_updates": 6,
          "nonzero_gradient_updates": 8,
          "nonzero_parameter_updates": 7,
          "optimizer_updates": 8,
          "parameter_sample_delta_l2": 0.008665954134863358,
          "real_teacher_target_rows": 202,
          "teacher_layout_updates": 2,
          "teacher_vs_demo_action_l1": 0.009018332877260919,
          "train_mean_action_l1": 0.3705994635820389,
          "train_mean_kd_act_l1": 0.3718191422522068,
          "train_mean_kd_world_l1": 0.5415164604783058,
          "train_mean_world_l1": 0.5257144160568714,
          "updated_parameter_tensors": 340
        },
        "paper": "smolwam",
        "seed": 42,
        "selection": "validation only",
        "source_revision": "dde1e5bfe35c439499343c6d70e9cd32c96d0b36",
        "training_evidence": {
          "gradients": [
            {
              "norm": 0.9999999156552345,
              "parameter_sample_delta_l2": 0.0,
              "tokens": 1764
            },
            {
              "norm": 0.9999999315979841,
              "parameter_sample_delta_l2": 0.0029798159689809344,
              "tokens": 1764
            },
            {
              "norm": 0.9999998682644787,
              "parameter_sample_delta_l2": 0.003117103575758504,
              "tokens": 1008
            },
            {
              "norm": 0.9999998729463463,
              "parameter_sample_delta_l2": 0.0020892092930467586,
              "tokens": 1008
            },
            {
              "norm": 0.9999999093984571,
              "parameter_sample_delta_l2": 0.0015728238585555878,
              "tokens": 1008
            },
            {
              "norm": 0.9999997626917846,
              "parameter_sample_delta_l2": 0.0007997472935750105,
              "tokens": 1008
            },
            {
              "norm": 0.9999999309748178,
              "parameter_sample_delta_l2": 0.0004417376719772234,
              "tokens": 1008
            },
            {
              "norm": 0.9999999636421939,
              "parameter_sample_delta_l2": 0.00021760357688717995,
              "tokens": 1008
            }
          ],
          "losses": [
            {
              "action_l1": 0.30105966329574585,
              "fut_proprio_l1": 0.39525106549263,
              "kd_act_l1": 0.30000168085098267,
              "kd_world_l1": 0.638677179813385,
              "tokens": 1764,
              "total": 1.9887595176696777,
              "training": true,
              "value_l1": 0.9141703844070435,
              "world_l1": 0.6180788278579712
            },
            {
              "action_l1": 0.39264199137687683,
              "fut_proprio_l1": 0.445421427488327,
              "kd_act_l1": 0.39470168948173523,
              "kd_world_l1": 0.61211758852005,
              "tokens": 1764,
              "total": 2.055243492126465,
              "training": false,
              "value_l1": 0.0916433110833168,
              "world_l1": 0.6020755767822266
            },
            {
              "action_l1": 0.42825162410736084,
              "fut_proprio_l1": 0.457839697599411,
              "kd_act_l1": 0.42891982197761536,
              "kd_world_l1": 0.6120333075523376,
              "tokens": 1764,
              "total": 2.125339984893799,
              "training": false,
              "value_l1": 0.05457901954650879,
              "world_l1": 0.6048932671546936
            },
            {
              "action_l1": 0.4276868402957916,
              "fut_proprio_l1": 0.45966991782188416,
              "kd_act_l1": 0.42956027388572693,
              "kd_world_l1": 0.6151618361473083,
              "tokens": 1764,
              "total": 2.1263866424560547,
              "training": false,
              "value_l1": 0.016893630847334862,
              "world_l1": 0.606321394443512
            },
            {
              "action_l1": 0.41634267568588257,
              "fut_proprio_l1": 0.45512649416923523,
              "kd_act_l1": 0.4154925048351288,
              "kd_world_l1": 0.6139906048774719,
              "tokens": 1764,
              "total": 2.097996473312378,
              "training": false,
              "value_l1": 0.022460319101810455,
              "world_l1": 0.6044118404388428
            },
            {
              "action_l1": 0.4146602749824524,
              "fut_proprio_l1": 0.4446501135826111,
              "kd_act_l1": 0.4127710163593292,
              "kd_world_l1": 0.6184900999069214,
              "tokens": 1764,
              "total": 2.106571912765503,
              "training": false,
              "value_l1": 0.06344133615493774,
              "world_l1": 0.6098414063453674
            },
            {
              "action_l1": 0.39744770526885986,
              "fut_proprio_l1": 0.36831364035606384,
              "kd_act_l1": 0.39762938022613525,
              "kd_world_l1": 0.626244843006134,
              "tokens": 1764,
              "total": 2.086597442626953,
              "training": false,
              "value_l1": 0.10638593882322311,
              "world_l1": 0.6178056001663208
            },
            {
              "action_l1": 0.36447182297706604,
              "fut_proprio_l1": 0.26236623525619507,
              "kd_act_l1": 0.3601663410663605,
              "kd_world_l1": 0.6266961693763733,
              "tokens": 1764,
              "total": 2.0100419521331787,
              "training": false,
              "value_l1": 0.15318606793880463,
              "world_l1": 0.6171524524688721
            },
            {
              "action_l1": 0.3340085744857788,
              "fut_proprio_l1": 0.26209601759910583,
              "kd_act_l1": 0.3327857553958893,
              "kd_world_l1": 0.620322048664093,
              "tokens": 1764,
              "total": 1.947587251663208,
              "training": false,
              "value_l1": 0.20216256380081177,
              "world_l1": 0.6140449643135071
            },
            {
              "action_l1": 0.32472699880599976,
              "fut_proprio_l1": 0.26562437415122986,
              "kd_act_l1": 0.3241085708141327,
              "kd_world_l1": 0.6159060001373291,
              "tokens": 1764,
              "total": 1.9230159521102905,
              "training": false,
              "value_l1": 0.2535749673843384,
              "world_l1": 0.6063544154167175
            },
            {
              "action_l1": 0.3277997076511383,
              "fut_proprio_l1": 0.2719607949256897,
              "kd_act_l1": 0.3271142542362213,
              "kd_world_l1": 0.6146377921104431,
              "tokens": 1764,
              "total": 1.9329159259796143,
              "training": false,
              "value_l1": 0.3202783763408661,
              "world_l1": 0.6041402220726013
            },
            {
              "action_l1": 0.3499819338321686,
              "fut_proprio_l1": 0.2638669013977051,
              "kd_act_l1": 0.3472892642021179,
              "kd_world_l1": 0.6257447600364685,
              "tokens": 1764,
              "total": 1.9991726875305176,
              "training": false,
              "value_l1": 0.366862028837204,
              "world_l1": 0.6130837202072144
            },
            {
              "action_l1": 0.364806205034256,
              "fut_proprio_l1": 0.2609839141368866,
              "kd_act_l1": 0.36462533473968506,
              "kd_world_l1": 0.6334546208381653,
              "tokens": 1764,
              "total": 2.053518295288086,
              "training": false,
              "value_l1": 0.42405813932418823,
              "world_l1": 0.6221280097961426
            },
            {
              "action_l1": 0.358009397983551,
              "fut_proprio_l1": 0.2699485421180725,
              "kd_act_l1": 0.3563551604747772,
              "kd_world_l1": 0.6430424451828003,
              "tokens": 1764,
              "total": 2.062807083129883,
              "training": false,
              "value_l1": 0.4834316670894623,
              "world_l1": 0.6300619840621948
            },
            {
              "action_l1": 0.3439207673072815,
              "fut_proprio_l1": 0.26790180802345276,
              "kd_act_l1": 0.3435370624065399,
              "kd_world_l1": 0.6536069512367249,
              "tokens": 1764,
              "total": 2.0600461959838867,
              "training": false,
              "value_l1": 0.5445905923843384,
              "world_l1": 0.6377320289611816
            },
            {
              "action_l1": 0.3499591648578644,
              "fut_proprio_l1": 0.2670314610004425,
              "kd_act_l1": 0.34876567125320435,
              "kd_world_l1": 0.6521480679512024,
              "tokens": 1764,
              "total": 2.0752243995666504,
              "training": false,
              "value_l1": 0.6084826588630676,
              "world_l1": 0.6368001103401184
            },
            {
              "action_l1": 0.3347955346107483,
              "fut_proprio_l1": 0.2675441801548004,
              "kd_act_l1": 0.334581196308136,
              "kd_world_l1": 0.6495850682258606,
              "tokens": 1764,
              "total": 2.0488014221191406,
              "training": false,
              "value_l1": 0.6753493547439575,
              "world_l1": 0.6355503797531128
            },
            {
              "action_l1": 0.31423041224479675,
              "fut_proprio_l1": 0.2923642694950104,
              "kd_act_l1": 0.31096670031547546,
              "kd_world_l1": 0.6440274119377136,
              "tokens": 1764,
              "total": 2.0068161487579346,
              "training": false,
              "value_l1": 0.7440774440765381,
              "world_l1": 0.633947491645813
            },
            {
              "action_l1": 0.29090094566345215,
              "fut_proprio_l1": 0.41956233978271484,
              "kd_act_l1": 0.29011455178260803,
              "kd_world_l1": 0.6408601403236389,
              "tokens": 1764,
              "total": 1.9729819297790527,
              "training": false,
              "value_l1": 0.8159213066101074,
              "world_l1": 0.6275579333305359
            },
            {
              "action_l1": 0.2661244571208954,
              "fut_proprio_l1": 0.44570261240005493,
              "kd_act_l1": 0.2654730975627899,
              "kd_world_l1": 0.6396863460540771,
              "tokens": 1764,
              "total": 1.9287956953048706,
              "training": false,
              "value_l1": 0.8917552828788757,
              "world_l1": 0.6237660050392151
            },
            {
              "action_l1": 0.26072701811790466,
              "fut_proprio_l1": 0.4484752118587494,
              "kd_act_l1": 0.2614942789077759,
              "kd_world_l1": 0.6407842636108398,
              "tokens": 1764,
              "total": 1.9268220663070679,
              "training": false,
              "value_l1": 0.9708045125007629,
              "world_l1": 0.6218885779380798
            },
            {
              "action_l1": 0.24552085995674133,
              "fut_proprio_l1": 0.44845736026763916,
              "kd_act_l1": 0.24450628459453583,
              "kd_world_l1": 0.6386459469795227,
              "tokens": 1764,
              "total": 1.8905048370361328,
              "training": false,
              "value_l1": 0.9708822965621948,
              "world_l1": 0.619897723197937
            },
            {
              "action_l1": 0.22689950466156006,
              "fut_proprio_l1": 0.4485643208026886,
              "kd_act_l1": 0.2272663563489914,
              "kd_world_l1": 0.6287166476249695,
              "tokens": 1764,
              "total": 1.837731122970581,
              "training": false,
              "value_l1": 0.9762343764305115,
              "world_l1": 0.6123687624931335
            },
            {
              "action_l1": 0.21874742209911346,
              "fut_proprio_l1": 0.44753918051719666,
              "kd_act_l1": 0.21970906853675842,
              "kd_world_l1": 0.624957799911499,
              "tokens": 1764,
              "total": 1.8164787292480469,
              "training": false,
              "value_l1": 0.9707165360450745,
              "world_l1": 0.6112388372421265
            },
            {
              "action_l1": 0.21387335658073425,
              "fut_proprio_l1": 0.44744667410850525,
              "kd_act_l1": 0.21545124053955078,
              "kd_world_l1": 0.622482419013977,
              "tokens": 1764,
              "total": 1.8047714233398438,
              "training": false,
              "value_l1": 0.9711071252822876,
              "world_l1": 0.6111090183258057
            },
            {
              "action_l1": 0.3453546464443207,
              "fut_proprio_l1": 0.25706416368484497,
              "kd_act_l1": 0.3453525900840759,
              "kd_world_l1": 0.6223610043525696,
              "tokens": 1764,
              "total": 1.9932711124420166,
              "training": true,
              "value_l1": 0.4468082785606384,
              "world_l1": 0.6098155975341797
            },
            {
              "action_l1": 0.44747471809387207,
              "fut_proprio_l1": 0.48285919427871704,
              "kd_act_l1": 0.4497052729129791,
              "kd_world_l1": 0.5363031625747681,
              "tokens": 1764,
              "total": 2.001941680908203,
              "training": false,
              "value_l1": 0.034573033452034,
              "world_l1": 0.5167152881622314
            },
            {
              "action_l1": 0.45724114775657654,
              "fut_proprio_l1": 0.4934786856174469,
              "kd_act_l1": 0.458533376455307,
              "kd_world_l1": 0.5365625023841858,
              "tokens": 1764,
              "total": 2.0225062370300293,
              "training": false,
              "value_l1": 0.0011178571730852127,
              "world_l1": 0.5207095742225647
            },
            {
              "action_l1": 0.444191038608551,
              "fut_proprio_l1": 0.4945880174636841,
              "kd_act_l1": 0.4450618624687195,
              "kd_world_l1": 0.5320807695388794,
              "tokens": 1764,
              "total": 1.9886494874954224,
              "training": false,
              "value_l1": 0.03509509935975075,
              "world_l1": 0.5143473744392395
            },
            {
              "action_l1": 0.4252341389656067,
              "fut_proprio_l1": 0.4910230040550232,
              "kd_act_l1": 0.4278636872768402,
              "kd_world_l1": 0.5234912037849426,
              "tokens": 1764,
              "total": 1.938314437866211,
              "training": false,
              "value_l1": 0.0730503499507904,
              "world_l1": 0.5053180456161499
            },
            {
              "action_l1": 0.413436621427536,
              "fut_proprio_l1": 0.48259299993515015,
              "kd_act_l1": 0.41379204392433167,
              "kd_world_l1": 0.5258861184120178,
              "tokens": 1764,
              "total": 1.9200806617736816,
              "training": false,
              "value_l1": 0.10874128341674805,
              "world_l1": 0.5078322887420654
            },
            {
              "action_l1": 0.42063578963279724,
              "fut_proprio_l1": 0.40869030356407166,
              "kd_act_l1": 0.4218269884586334,
              "kd_world_l1": 0.523059070110321,
              "tokens": 1764,
              "total": 1.926647424697876,
              "training": false,
              "value_l1": 0.14797565340995789,
              "world_l1": 0.5054588913917542
            },
            {
              "action_l1": 0.3867150843143463,
              "fut_proprio_l1": 0.3045373558998108,
              "kd_act_l1": 0.3867526948451996,
              "kd_world_l1": 0.5162314772605896,
              "tokens": 1764,
              "total": 1.8365252017974854,
              "training": false,
              "value_l1": 0.1933746486902237,
              "world_l1": 0.49703463912010193
            },
            {
              "action_l1": 0.3847169280052185,
              "fut_proprio_l1": 0.3043462932109833,
              "kd_act_l1": 0.3848564922809601,
              "kd_world_l1": 0.509894847869873,
              "tokens": 1764,
              "total": 1.8268225193023682,
              "training": false,
              "value_l1": 0.23987367749214172,
              "world_l1": 0.4929322898387909
            },
            {
              "action_l1": 0.3838946521282196,
              "fut_proprio_l1": 0.3063364326953888,
              "kd_act_l1": 0.38445279002189636,
              "kd_world_l1": 0.5159754157066345,
              "tokens": 1764,
              "total": 1.8385844230651855,
              "training": false,
              "value_l1": 0.28835850954055786,
              "world_l1": 0.4947921633720398
            },
            {
              "action_l1": 0.4069961905479431,
              "fut_proprio_l1": 0.304252564907074,
              "kd_act_l1": 0.40780994296073914,
              "kd_world_l1": 0.5280231833457947,
              "tokens": 1764,
              "total": 1.9123685359954834,
              "training": false,
              "value_l1": 0.3493262231349945,
              "world_l1": 0.5041813254356384
            },
            {
              "action_l1": 0.4155857264995575,
              "fut_proprio_l1": 0.286048948764801,
              "kd_act_l1": 0.4164825975894928,
              "kd_world_l1": 0.5313016176223755,
              "tokens": 1764,
              "total": 1.9383856058120728,
              "training": false,
              "value_l1": 0.403104692697525,
              "world_l1": 0.5061002969741821
            },
            {
              "action_l1": 0.4393077790737152,
              "fut_proprio_l1": 0.2706946134567261,
              "kd_act_l1": 0.4369174838066101,
              "kd_world_l1": 0.5378944277763367,
              "tokens": 1764,
              "total": 2.0003063678741455,
              "training": false,
              "value_l1": 0.45998847484588623,
              "world_l1": 0.5131184458732605
            },
            {
              "action_l1": 0.4155825972557068,
              "fut_proprio_l1": 0.2703855037689209,
              "kd_act_l1": 0.4135890305042267,
              "kd_world_l1": 0.5523547530174255,
              "tokens": 1764,
              "total": 1.9862771034240723,
              "training": false,
              "value_l1": 0.5196192860603333,
              "world_l1": 0.5257501602172852
            },
            {
              "action_l1": 0.3909789025783539,
              "fut_proprio_l1": 0.2678203880786896,
              "kd_act_l1": 0.3915334939956665,
              "kd_world_l1": 0.5683273077011108,
              "tokens": 1764,
              "total": 1.9750871658325195,
              "training": false,
              "value_l1": 0.5818678736686707,
              "world_l1": 0.5392786264419556
            },
            {
              "action_l1": 0.38804227113723755,
              "fut_proprio_l1": 0.2672075927257538,
              "kd_act_l1": 0.3893265426158905,
              "kd_world_l1": 0.5678235292434692,
              "tokens": 1764,
              "total": 1.9777653217315674,
              "training": false,
              "value_l1": 0.6457988023757935,
              "world_l1": 0.5412723422050476
            },
            {
              "action_l1": 0.370981901884079,
              "fut_proprio_l1": 0.2680284380912781,
              "kd_act_l1": 0.37275105714797974,
              "kd_world_l1": 0.557721734046936,
              "tokens": 1764,
              "total": 1.9306830167770386,
              "training": false,
              "value_l1": 0.7126922011375427,
              "world_l1": 0.5311561822891235
            },
            {
              "action_l1": 0.3549702763557434,
              "fut_proprio_l1": 0.29302743077278137,
              "kd_act_l1": 0.3562868535518646,
              "kd_world_l1": 0.5434924364089966,
              "tokens": 1764,
              "total": 1.8840173482894897,
              "training": false,
              "value_l1": 0.7849205732345581,
              "world_l1": 0.5214729905128479
            },
            {
              "action_l1": 0.3547058701515198,
              "fut_proprio_l1": 0.4202614426612854,
              "kd_act_l1": 0.35485610365867615,
              "kd_world_l1": 0.5479776859283447,
              "tokens": 1764,
              "total": 1.9079005718231201,
              "training": false,
              "value_l1": 0.860248863697052,
              "world_l1": 0.5223098397254944
            },
            {
              "action_l1": 0.32088035345077515,
              "fut_proprio_l1": 0.4461229741573334,
              "kd_act_l1": 0.32338184118270874,
              "kd_world_l1": 0.5522697567939758,
              "tokens": 1764,
              "total": 1.8596343994140625,
              "training": false,
              "value_l1": 0.9356958270072937,
              "world_l1": 0.5249205231666565
            },
            {
              "action_l1": 0.3206389844417572,
              "fut_proprio_l1": 0.44903039932250977,
              "kd_act_l1": 0.320079505443573,
              "kd_world_l1": 0.5554419755935669,
              "tokens": 1764,
              "total": 1.8681511878967285,
              "training": false,
              "value_l1": 1.0146217346191406,
              "world_l1": 0.525625467300415
            },
            {
              "action_l1": 0.3105289936065674,
              "fut_proprio_l1": 0.4489821493625641,
              "kd_act_l1": 0.31197986006736755,
              "kd_world_l1": 0.5532813668251038,
              "tokens": 1764,
              "total": 1.8447470664978027,
              "training": false,
              "value_l1": 1.014443039894104,
              "world_l1": 0.5226143002510071
            },
            {
              "action_l1": 0.31398114562034607,
              "fut_proprio_l1": 0.45020791888237,
              "kd_act_l1": 0.31559762358665466,
              "kd_world_l1": 0.547656238079071,
              "tokens": 1764,
              "total": 1.844223976135254,
              "training": false,
              "value_l1": 1.0166575908660889,
              "world_l1": 0.5203022956848145
            },
            {
              "action_l1": 0.3118714988231659,
              "fut_proprio_l1": 0.45056602358818054,
              "kd_act_l1": 0.3125433325767517,
              "kd_world_l1": 0.5443238615989685,
              "tokens": 1764,
              "total": 1.835571050643921,
              "training": false,
              "value_l1": 1.0157959461212158,
              "world_l1": 0.5201961398124695
            },
            {
              "action_l1": 0.3117304742336273,
              "fut_proprio_l1": 0.45048174262046814,
              "kd_act_l1": 0.3121849000453949,
              "kd_world_l1": 0.5427252054214478,
              "tokens": 1764,
              "total": 1.8339554071426392,
              "training": false,
              "value_l1": 1.0170185565948486,
              "world_l1": 0.52056485414505
            },
            {
              "action_l1": 0.45621731877326965,
              "kd_act_l1": 0.4561226963996887,
              "kd_world_l1": 0.5442981719970703,
              "tokens": 1008,
              "total": 1.991137981414795,
              "training": true,
              "world_l1": 0.5344998240470886
            },
            {
              "action_l1": 0.40419337153434753,
              "kd_act_l1": 0.40742847323417664,
              "kd_world_l1": 0.5285182595252991,
              "tokens": 1008,
              "total": 1.8290700912475586,
              "training": false,
              "world_l1": 0.48892998695373535
            },
            {
              "action_l1": 0.4192342162132263,
              "kd_act_l1": 0.41976112127304077,
              "kd_world_l1": 0.5270687937736511,
              "tokens": 1008,
              "total": 1.8557085990905762,
              "training": false,
              "world_l1": 0.48964449763298035
            },
            {
              "action_l1": 0.4003719091415405,
              "kd_act_l1": 0.40201279520988464,
              "kd_world_l1": 0.5188373327255249,
              "tokens": 1008,
              "total": 1.8012230396270752,
              "training": false,
              "world_l1": 0.4800010025501251
            },
            {
              "action_l1": 0.37103959918022156,
              "kd_act_l1": 0.3732756972312927,
              "kd_world_l1": 0.512657642364502,
              "tokens": 1008,
              "total": 1.7315306663513184,
              "training": false,
              "world_l1": 0.47455766797065735
            },
            {
              "action_l1": 0.348978191614151,
              "kd_act_l1": 0.3491858243942261,
              "kd_world_l1": 0.5136343240737915,
              "tokens": 1008,
              "total": 1.6888126134872437,
              "training": false,
              "world_l1": 0.47701433300971985
            },
            {
              "action_l1": 0.3437311351299286,
              "kd_act_l1": 0.34422507882118225,
              "kd_world_l1": 0.49907830357551575,
              "tokens": 1008,
              "total": 1.6511586904525757,
              "training": false,
              "world_l1": 0.4641241729259491
            },
            {
              "action_l1": 0.31961551308631897,
              "kd_act_l1": 0.3177233338356018,
              "kd_world_l1": 0.49422353506088257,
              "tokens": 1008,
              "total": 1.591543197631836,
              "training": false,
              "world_l1": 0.4599807858467102
            },
            {
              "action_l1": 0.3122034966945648,
              "kd_act_l1": 0.3115534782409668,
              "kd_world_l1": 0.49080780148506165,
              "tokens": 1008,
              "total": 1.5705981254577637,
              "training": false,
              "world_l1": 0.4560334384441376
            },
            {
              "action_l1": 0.3302587568759918,
              "kd_act_l1": 0.33040672540664673,
              "kd_world_l1": 0.5071412324905396,
              "tokens": 1008,
              "total": 1.6350010633468628,
              "training": false,
              "world_l1": 0.4671942889690399
            },
            {
              "action_l1": 0.3686552941799164,
              "kd_act_l1": 0.3692900836467743,
              "kd_world_l1": 0.5388578772544861,
              "tokens": 1008,
              "total": 1.768610954284668,
              "training": false,
              "world_l1": 0.49180760979652405
            },
            {
              "action_l1": 0.4025026559829712,
              "kd_act_l1": 0.4036521315574646,
              "kd_world_l1": 0.5460480451583862,
              "tokens": 1008,
              "total": 1.8505157232284546,
              "training": false,
              "world_l1": 0.49831295013427734
            },
            {
              "action_l1": 0.4233359694480896,
              "kd_act_l1": 0.4203926920890808,
              "kd_world_l1": 0.5498023629188538,
              "tokens": 1008,
              "total": 1.8964653015136719,
              "training": false,
              "world_l1": 0.5029342174530029
            },
            {
              "action_l1": 0.3923488259315491,
              "kd_act_l1": 0.39056819677352905,
              "kd_world_l1": 0.5571905374526978,
              "tokens": 1008,
              "total": 1.849532127380371,
              "training": false,
              "world_l1": 0.5094245672225952
            },
            {
              "action_l1": 0.3609462380409241,
              "kd_act_l1": 0.36041024327278137,
              "kd_world_l1": 0.5664395689964294,
              "tokens": 1008,
              "total": 1.8052129745483398,
              "training": false,
              "world_l1": 0.5174168348312378
            },
            {
              "action_l1": 0.35030749440193176,
              "kd_act_l1": 0.3514655530452728,
              "kd_world_l1": 0.5675634741783142,
              "tokens": 1008,
              "total": 1.7905826568603516,
              "training": false,
              "world_l1": 0.521246075630188
            },
            {
              "action_l1": 0.3509543538093567,
              "kd_act_l1": 0.3514414131641388,
              "kd_world_l1": 0.5575243830680847,
              "tokens": 1008,
              "total": 1.7710480690002441,
              "training": false,
              "world_l1": 0.5111279487609863
            },
            {
              "action_l1": 0.34162816405296326,
              "kd_act_l1": 0.3400035798549652,
              "kd_world_l1": 0.5366923809051514,
              "tokens": 1008,
              "total": 1.7130988836288452,
              "training": false,
              "world_l1": 0.4947746992111206
            },
            {
              "action_l1": 0.3343929052352905,
              "kd_act_l1": 0.3341856300830841,
              "kd_world_l1": 0.5427606105804443,
              "tokens": 1008,
              "total": 1.7081798315048218,
              "training": false,
              "world_l1": 0.4968407154083252
            },
            {
              "action_l1": 0.3173292279243469,
              "kd_act_l1": 0.3146928548812866,
              "kd_world_l1": 0.5500122308731079,
              "tokens": 1008,
              "total": 1.6847095489501953,
              "training": false,
              "world_l1": 0.5026752352714539
            },
            {
              "action_l1": 0.3073428273200989,
              "kd_act_l1": 0.30916258692741394,
              "kd_world_l1": 0.558214008808136,
              "tokens": 1008,
              "total": 1.6830768585205078,
              "training": false,
              "world_l1": 0.5083575248718262
            },
            {
              "action_l1": 0.2871817648410797,
              "kd_act_l1": 0.287928968667984,
              "kd_world_l1": 0.5569303035736084,
              "tokens": 1008,
              "total": 1.6398810148239136,
              "training": false,
              "world_l1": 0.5078399777412415
            },
            {
              "action_l1": 0.25820037722587585,
              "kd_act_l1": 0.26017987728118896,
              "kd_world_l1": 0.554786205291748,
              "tokens": 1008,
              "total": 1.5811551809310913,
              "training": false,
              "world_l1": 0.507988691329956
            },
            {
              "action_l1": 0.2459716498851776,
              "kd_act_l1": 0.24565285444259644,
              "kd_world_l1": 0.5514265894889832,
              "tokens": 1008,
              "total": 1.5501554012298584,
              "training": false,
              "world_l1": 0.5071043372154236
            },
            {
              "action_l1": 0.2408936321735382,
              "kd_act_l1": 0.24199432134628296,
              "kd_world_l1": 0.5505395531654358,
              "tokens": 1008,
              "total": 1.539969563484192,
              "training": false,
              "world_l1": 0.5065420866012573
            },
            {
              "action_l1": 0.36104127764701843,
              "kd_act_l1": 0.3632703423500061,
              "kd_world_l1": 0.5184150338172913,
              "tokens": 1008,
              "total": 1.7246191501617432,
              "training": true,
              "world_l1": 0.4818926453590393
            },
            {
              "action_l1": 0.4081886112689972,
              "kd_act_l1": 0.4092172086238861,
              "kd_world_l1": 0.5186523199081421,
              "tokens": 1008,
              "total": 1.8402928113937378,
              "training": false,
              "world_l1": 0.5042346119880676
            },
            {
              "action_l1": 0.4399172067642212,
              "kd_act_l1": 0.4407249689102173,
              "kd_world_l1": 0.5172320008277893,
              "tokens": 1008,
              "total": 1.9040260314941406,
              "training": false,
              "world_l1": 0.5061519145965576
            },
            {
              "action_l1": 0.4400660991668701,
              "kd_act_l1": 0.4419816732406616,
              "kd_world_l1": 0.511025607585907,
              "tokens": 1008,
              "total": 1.8913605213165283,
              "training": false,
              "world_l1": 0.49828702211380005
            },
            {
              "action_l1": 0.42902040481567383,
              "kd_act_l1": 0.42780905961990356,
              "kd_world_l1": 0.5042400360107422,
              "tokens": 1008,
              "total": 1.8516910076141357,
              "training": false,
              "world_l1": 0.4906214773654938
            },
            {
              "action_l1": 0.4251948297023773,
              "kd_act_l1": 0.4234525263309479,
              "kd_world_l1": 0.5084909796714783,
              "tokens": 1008,
              "total": 1.8527421951293945,
              "training": false,
              "world_l1": 0.4956039786338806
            },
            {
              "action_l1": 0.4053186774253845,
              "kd_act_l1": 0.40549713373184204,
              "kd_world_l1": 0.5090042948722839,
              "tokens": 1008,
              "total": 1.8144025802612305,
              "training": false,
              "world_l1": 0.4945824146270752
            },
            {
              "action_l1": 0.3754052221775055,
              "kd_act_l1": 0.37166720628738403,
              "kd_world_l1": 0.5041938424110413,
              "tokens": 1008,
              "total": 1.7402193546295166,
              "training": false,
              "world_l1": 0.48895302414894104
            },
            {
              "action_l1": 0.3342762887477875,
              "kd_act_l1": 0.33232006430625916,
              "kd_world_l1": 0.49602600932121277,
              "tokens": 1008,
              "total": 1.645224690437317,
              "training": false,
              "world_l1": 0.4826023280620575
            },
            {
              "action_l1": 0.330919474363327,
              "kd_act_l1": 0.33110910654067993,
              "kd_world_l1": 0.4974763095378876,
              "tokens": 1008,
              "total": 1.6397337913513184,
              "training": false,
              "world_l1": 0.48022887110710144
            },
            {
              "action_l1": 0.3326081931591034,
              "kd_act_l1": 0.3312501013278961,
              "kd_world_l1": 0.5078714489936829,
              "tokens": 1008,
              "total": 1.6607685089111328,
              "training": false,
              "world_l1": 0.48903876543045044
            },
            {
              "action_l1": 0.3530994951725006,
              "kd_act_l1": 0.3521507978439331,
              "kd_world_l1": 0.5093895196914673,
              "tokens": 1008,
              "total": 1.7055668830871582,
              "training": false,
              "world_l1": 0.4909270703792572
            },
            {
              "action_l1": 0.3706120252609253,
              "kd_act_l1": 0.3692277669906616,
              "kd_world_l1": 0.5155900120735168,
              "tokens": 1008,
              "total": 1.752922773361206,
              "training": false,
              "world_l1": 0.4974929690361023
            },
            {
              "action_l1": 0.35869571566581726,
              "kd_act_l1": 0.3569948077201843,
              "kd_world_l1": 0.5288325548171997,
              "tokens": 1008,
              "total": 1.7538286447525024,
              "training": false,
              "world_l1": 0.5093055367469788
            },
            {
              "action_l1": 0.3485943377017975,
              "kd_act_l1": 0.34834304451942444,
              "kd_world_l1": 0.5428974032402039,
              "tokens": 1008,
              "total": 1.758561611175537,
              "training": false,
              "world_l1": 0.5187267661094666
            },
            {
              "action_l1": 0.3526510000228882,
              "kd_act_l1": 0.35173410177230835,
              "kd_world_l1": 0.5450292229652405,
              "tokens": 1008,
              "total": 1.7718830108642578,
              "training": false,
              "world_l1": 0.522468626499176
            },
            {
              "action_l1": 0.3377383053302765,
              "kd_act_l1": 0.3387586772441864,
              "kd_world_l1": 0.5361039042472839,
              "tokens": 1008,
              "total": 1.7271466255187988,
              "training": false,
              "world_l1": 0.5145456790924072
            },
            {
              "action_l1": 0.3184102177619934,
              "kd_act_l1": 0.31510695815086365,
              "kd_world_l1": 0.5202898979187012,
              "tokens": 1008,
              "total": 1.6567704677581787,
              "training": false,
              "world_l1": 0.5029633641242981
            },
            {
              "action_l1": 0.29296132922172546,
              "kd_act_l1": 0.29404446482658386,
              "kd_world_l1": 0.5235649347305298,
              "tokens": 1008,
              "total": 1.615992784500122,
              "training": false,
              "world_l1": 0.505422055721283
            },
            {
              "action_l1": 0.2690066993236542,
              "kd_act_l1": 0.2671435475349426,
              "kd_world_l1": 0.5277532935142517,
              "tokens": 1008,
              "total": 1.5719833374023438,
              "training": false,
              "world_l1": 0.5080797672271729
            },
            {
              "action_l1": 0.261390745639801,
              "kd_act_l1": 0.2619248330593109,
              "kd_world_l1": 0.5313829779624939,
              "tokens": 1008,
              "total": 1.5635483264923096,
              "training": false,
              "world_l1": 0.5088496804237366
            },
            {
              "action_l1": 0.2450147271156311,
              "kd_act_l1": 0.24472881853580475,
              "kd_world_l1": 0.5295621156692505,
              "tokens": 1008,
              "total": 1.5253944396972656,
              "training": false,
              "world_l1": 0.5060887932777405
            },
            {
              "action_l1": 0.2341637760400772,
              "kd_act_l1": 0.23429691791534424,
              "kd_world_l1": 0.5252230763435364,
              "tokens": 1008,
              "total": 1.4971776008605957,
              "training": false,
              "world_l1": 0.5034939050674438
            },
            {
              "action_l1": 0.23342253267765045,
              "kd_act_l1": 0.2327764332294464,
              "kd_world_l1": 0.5218979716300964,
              "tokens": 1008,
              "total": 1.4909822940826416,
              "training": false,
              "world_l1": 0.5028854608535767
            },
            {
              "action_l1": 0.2299174964427948,
              "kd_act_l1": 0.23078079521656036,
              "kd_world_l1": 0.5206186771392822,
              "tokens": 1008,
              "total": 1.4842281341552734,
              "training": false,
              "world_l1": 0.5029110908508301
            },
            {
              "action_l1": 0.3746497333049774,
              "kd_act_l1": 0.3760070502758026,
              "kd_world_l1": 0.5062704682350159,
              "tokens": 1008,
              "total": 1.751835823059082,
              "training": true,
              "world_l1": 0.49490854144096375
            },
            {
              "action_l1": 0.4157772362232208,
              "kd_act_l1": 0.4157178997993469,
              "kd_world_l1": 0.5215775370597839,
              "tokens": 1008,
              "total": 1.8624436855316162,
              "training": false,
              "world_l1": 0.5093709826469421
            },
            {
              "action_l1": 0.4416729509830475,
              "kd_act_l1": 0.4420866072177887,
              "kd_world_l1": 0.5203332304954529,
              "tokens": 1008,
              "total": 1.9157354831695557,
              "training": false,
              "world_l1": 0.5116427540779114
            },
            {
              "action_l1": 0.4225543141365051,
              "kd_act_l1": 0.42372533679008484,
              "kd_world_l1": 0.5131267309188843,
              "tokens": 1008,
              "total": 1.862162470817566,
              "training": false,
              "world_l1": 0.5027561187744141
            },
            {
              "action_l1": 0.40642398595809937,
              "kd_act_l1": 0.40581947565078735,
              "kd_world_l1": 0.5038973689079285,
              "tokens": 1008,
              "total": 1.808845043182373,
              "training": false,
              "world_l1": 0.49270427227020264
            },
            {
              "action_l1": 0.38662031292915344,
              "kd_act_l1": 0.38531917333602905,
              "kd_world_l1": 0.5062288641929626,
              "tokens": 1008,
              "total": 1.773453950881958,
              "training": false,
              "world_l1": 0.4952854812145233
            },
            {
              "action_l1": 0.3567821681499481,
              "kd_act_l1": 0.35692790150642395,
              "kd_world_l1": 0.5047847628593445,
              "tokens": 1008,
              "total": 1.710360050201416,
              "training": false,
              "world_l1": 0.491865336894989
            },
            {
              "action_l1": 0.3401353061199188,
              "kd_act_l1": 0.33915194869041443,
              "kd_world_l1": 0.5001475811004639,
              "tokens": 1008,
              "total": 1.6665852069854736,
              "training": false,
              "world_l1": 0.48715031147003174
            },
            {
              "action_l1": 0.31264203786849976,
              "kd_act_l1": 0.3114691972732544,
              "kd_world_l1": 0.49251919984817505,
              "tokens": 1008,
              "total": 1.5979866981506348,
              "training": false,
              "world_l1": 0.4813562333583832
            },
            {
              "action_l1": 0.33378008008003235,
              "kd_act_l1": 0.33442312479019165,
              "kd_world_l1": 0.49602794647216797,
              "tokens": 1008,
              "total": 1.6457128524780273,
              "training": false,
              "world_l1": 0.48148173093795776
            },
            {
              "action_l1": 0.34170377254486084,
              "kd_act_l1": 0.34250104427337646,
              "kd_world_l1": 0.5079237222671509,
              "tokens": 1008,
              "total": 1.6842550039291382,
              "training": false,
              "world_l1": 0.4921264052391052
            },
            {
              "action_l1": 0.37368181347846985,
              "kd_act_l1": 0.3750423789024353,
              "kd_world_l1": 0.510385274887085,
              "tokens": 1008,
              "total": 1.753787875175476,
              "training": false,
              "world_l1": 0.49467840790748596
            },
            {
              "action_l1": 0.39326149225234985,
              "kd_act_l1": 0.39101916551589966,
              "kd_world_l1": 0.5161224007606506,
              "tokens": 1008,
              "total": 1.8017802238464355,
              "training": false,
              "world_l1": 0.5013772249221802
            },
            {
              "action_l1": 0.37197360396385193,
              "kd_act_l1": 0.3689435124397278,
              "kd_world_l1": 0.5282117128372192,
              "tokens": 1008,
              "total": 1.7809971570968628,
              "training": false,
              "world_l1": 0.5118682384490967
            },
            {
              "action_l1": 0.3424275815486908,
              "kd_act_l1": 0.34336230158805847,
              "kd_world_l1": 0.5424540042877197,
              "tokens": 1008,
              "total": 1.7492469549179077,
              "training": false,
              "world_l1": 0.5210030674934387
            },
            {
              "action_l1": 0.3345690667629242,
              "kd_act_l1": 0.3359740972518921,
              "kd_world_l1": 0.5435810089111328,
              "tokens": 1008,
              "total": 1.7375723123550415,
              "training": false,
              "world_l1": 0.5234481692314148
            },
            {
              "action_l1": 0.3219652771949768,
              "kd_act_l1": 0.3240668475627899,
              "kd_world_l1": 0.5346063375473022,
              "tokens": 1008,
              "total": 1.6957554817199707,
              "training": false,
              "world_l1": 0.5151169896125793
            },
            {
              "action_l1": 0.31214243173599243,
              "kd_act_l1": 0.3120934069156647,
              "kd_world_l1": 0.520744800567627,
              "tokens": 1008,
              "total": 1.6511235237121582,
              "training": false,
              "world_l1": 0.5061429142951965
            },
            {
              "action_l1": 0.2984660863876343,
              "kd_act_l1": 0.29841697216033936,
              "kd_world_l1": 0.523158848285675,
              "tokens": 1008,
              "total": 1.6271333694458008,
              "training": false,
              "world_l1": 0.5070915222167969
            },
            {
              "action_l1": 0.27384239435195923,
              "kd_act_l1": 0.27516674995422363,
              "kd_world_l1": 0.5271926522254944,
              "tokens": 1008,
              "total": 1.585974931716919,
              "training": false,
              "world_l1": 0.5097730755805969
            },
            {
              "action_l1": 0.2627131938934326,
              "kd_act_l1": 0.2631434500217438,
              "kd_world_l1": 0.5306558012962341,
              "tokens": 1008,
              "total": 1.567164659500122,
              "training": false,
              "world_l1": 0.5106522440910339
            },
            {
              "action_l1": 0.24050933122634888,
              "kd_act_l1": 0.240970179438591,
              "kd_world_l1": 0.528468668460846,
              "tokens": 1008,
              "total": 1.5175825357437134,
              "training": false,
              "world_l1": 0.5076343417167664
            },
            {
              "action_l1": 0.23889927566051483,
              "kd_act_l1": 0.2400001734495163,
              "kd_world_l1": 0.5244892835617065,
              "tokens": 1008,
              "total": 1.509047031402588,
              "training": false,
              "world_l1": 0.5056582093238831
            },
            {
              "action_l1": 0.23788249492645264,
              "kd_act_l1": 0.23684275150299072,
              "kd_world_l1": 0.5212975144386292,
              "tokens": 1008,
              "total": 1.501223087310791,
              "training": false,
              "world_l1": 0.5052002668380737
            },
            {
              "action_l1": 0.23414897918701172,
              "kd_act_l1": 0.23511138558387756,
              "kd_world_l1": 0.519802987575531,
              "tokens": 1008,
              "total": 1.4942033290863037,
              "training": false,
              "world_l1": 0.5051400661468506
            },
            {
              "action_l1": 0.38553109765052795,
              "kd_act_l1": 0.38614755868911743,
              "kd_world_l1": 0.5373400449752808,
              "tokens": 1008,
              "total": 1.8266221284866333,
              "training": true,
              "world_l1": 0.5176034569740295
            },
            {
              "action_l1": 0.43216949701309204,
              "kd_act_l1": 0.4321804344654083,
              "kd_world_l1": 0.5031989216804504,
              "tokens": 1008,
              "total": 1.8616032600402832,
              "training": false,
              "world_l1": 0.4940544366836548
            },
            {
              "action_l1": 0.4573860168457031,
              "kd_act_l1": 0.457817018032074,
              "kd_world_l1": 0.5012918710708618,
              "tokens": 1008,
              "total": 1.9133867025375366,
              "training": false,
              "world_l1": 0.4968918561935425
            },
            {
              "action_l1": 0.4411379396915436,
              "kd_act_l1": 0.44241178035736084,
              "kd_world_l1": 0.49249088764190674,
              "tokens": 1008,
              "total": 1.8633776903152466,
              "training": false,
              "world_l1": 0.4873371422290802
            },
            {
              "action_l1": 0.4265693426132202,
              "kd_act_l1": 0.42597687244415283,
              "kd_world_l1": 0.482059121131897,
              "tokens": 1008,
              "total": 1.8108898401260376,
              "training": false,
              "world_l1": 0.47628456354141235
            },
            {
              "action_l1": 0.40908828377723694,
              "kd_act_l1": 0.40819355845451355,
              "kd_world_l1": 0.4841408133506775,
              "tokens": 1008,
              "total": 1.7814157009124756,
              "training": false,
              "world_l1": 0.47999292612075806
            },
            {
              "action_l1": 0.3774513006210327,
              "kd_act_l1": 0.378141850233078,
              "kd_world_l1": 0.4812777042388916,
              "tokens": 1008,
              "total": 1.711503505706787,
              "training": false,
              "world_l1": 0.47463259100914
            },
            {
              "action_l1": 0.36229169368743896,
              "kd_act_l1": 0.3615930676460266,
              "kd_world_l1": 0.4763769209384918,
              "tokens": 1008,
              "total": 1.6697887182235718,
              "training": false,
              "world_l1": 0.46952709555625916
            },
            {
              "action_l1": 0.32877111434936523,
              "kd_act_l1": 0.3281087875366211,
              "kd_world_l1": 0.4685575067996979,
              "tokens": 1008,
              "total": 1.588700771331787,
              "training": false,
              "world_l1": 0.4632633626461029
            },
            {
              "action_l1": 0.34993112087249756,
              "kd_act_l1": 0.35015466809272766,
              "kd_world_l1": 0.47299155592918396,
              "tokens": 1008,
              "total": 1.6366881132125854,
              "training": false,
              "world_l1": 0.4636107087135315
            },
            {
              "action_l1": 0.34760358929634094,
              "kd_act_l1": 0.34736737608909607,
              "kd_world_l1": 0.4900076687335968,
              "tokens": 1008,
              "total": 1.6628271341323853,
              "training": false,
              "world_l1": 0.47784850001335144
            },
            {
              "action_l1": 0.3643873929977417,
              "kd_act_l1": 0.36507824063301086,
              "kd_world_l1": 0.4933440089225769,
              "tokens": 1008,
              "total": 1.704068899154663,
              "training": false,
              "world_l1": 0.4812593162059784
            },
            {
              "action_l1": 0.3829919993877411,
              "kd_act_l1": 0.38084134459495544,
              "kd_world_l1": 0.49931326508522034,
              "tokens": 1008,
              "total": 1.750883936882019,
              "training": false,
              "world_l1": 0.4877372980117798
            },
            {
              "action_l1": 0.36370381712913513,
              "kd_act_l1": 0.3605288863182068,
              "kd_world_l1": 0.5102918148040771,
              "tokens": 1008,
              "total": 1.7315645217895508,
              "training": false,
              "world_l1": 0.4970400035381317
            },
            {
              "action_l1": 0.337517112493515,
              "kd_act_l1": 0.33735281229019165,
              "kd_world_l1": 0.5237442851066589,
              "tokens": 1008,
              "total": 1.7043194770812988,
              "training": false,
              "world_l1": 0.5057052373886108
            },
            {
              "action_l1": 0.33396732807159424,
              "kd_act_l1": 0.33493104577064514,
              "kd_world_l1": 0.5252198576927185,
              "tokens": 1008,
              "total": 1.7028391361236572,
              "training": false,
              "world_l1": 0.5087209343910217
            },
            {
              "action_l1": 0.32096439599990845,
              "kd_act_l1": 0.3224037289619446,
              "kd_world_l1": 0.5150764584541321,
              "tokens": 1008,
              "total": 1.6572949886322021,
              "training": false,
              "world_l1": 0.49885037541389465
            },
            {
              "action_l1": 0.3094613254070282,
              "kd_act_l1": 0.308794230222702,
              "kd_world_l1": 0.49847301840782166,
              "tokens": 1008,
              "total": 1.6041557788848877,
              "training": false,
              "world_l1": 0.4874272048473358
            },
            {
              "action_l1": 0.2932852804660797,
              "kd_act_l1": 0.29297345876693726,
              "kd_world_l1": 0.5034058690071106,
              "tokens": 1008,
              "total": 1.5807366371154785,
              "training": false,
              "world_l1": 0.4910721480846405
            },
            {
              "action_l1": 0.2685205936431885,
              "kd_act_l1": 0.2697194814682007,
              "kd_world_l1": 0.5091044306755066,
              "tokens": 1008,
              "total": 1.5426373481750488,
              "training": false,
              "world_l1": 0.49529293179512024
            },
            {
              "action_l1": 0.2581476867198944,
              "kd_act_l1": 0.2587074339389801,
              "kd_world_l1": 0.5128492712974548,
              "tokens": 1008,
              "total": 1.526437759399414,
              "training": false,
              "world_l1": 0.49673333764076233
            },
            {
              "action_l1": 0.23779582977294922,
              "kd_act_l1": 0.23721744120121002,
              "kd_world_l1": 0.5100527405738831,
              "tokens": 1008,
              "total": 1.4779505729675293,
              "training": false,
              "world_l1": 0.4928845167160034
            },
            {
              "action_l1": 0.25485724210739136,
              "kd_act_l1": 0.2554570734500885,
              "kd_world_l1": 0.5045700073242188,
              "tokens": 1008,
              "total": 1.5041667222976685,
              "training": false,
              "world_l1": 0.48928242921829224
            },
            {
              "action_l1": 0.2596619725227356,
              "kd_act_l1": 0.2581306993961334,
              "kd_world_l1": 0.5003736019134521,
              "tokens": 1008,
              "total": 1.5060157775878906,
              "training": false,
              "world_l1": 0.48784947395324707
            },
            {
              "action_l1": 0.25659608840942383,
              "kd_act_l1": 0.25719279050827026,
              "kd_world_l1": 0.49837321043014526,
              "tokens": 1008,
              "total": 1.4994897842407227,
              "training": false,
              "world_l1": 0.4873277544975281
            },
            {
              "action_l1": 0.3833670914173126,
              "kd_act_l1": 0.38852864503860474,
              "kd_world_l1": 0.5023710131645203,
              "tokens": 1008,
              "total": 1.7661700248718262,
              "training": true,
              "world_l1": 0.4919033348560333
            },
            {
              "action_l1": 0.4219859540462494,
              "kd_act_l1": 0.4219593405723572,
              "kd_world_l1": 0.49238017201423645,
              "tokens": 1008,
              "total": 1.820312261581421,
              "training": false,
              "world_l1": 0.48398691415786743
            },
            {
              "action_l1": 0.44729867577552795,
              "kd_act_l1": 0.4477117955684662,
              "kd_world_l1": 0.49037784337997437,
              "tokens": 1008,
              "total": 1.8725440502166748,
              "training": false,
              "world_l1": 0.48715564608573914
            },
            {
              "action_l1": 0.4328301250934601,
              "kd_act_l1": 0.43448004126548767,
              "kd_world_l1": 0.4808551073074341,
              "tokens": 1008,
              "total": 1.825464129447937,
              "training": false,
              "world_l1": 0.4772988557815552
            },
            {
              "action_l1": 0.4181655943393707,
              "kd_act_l1": 0.4183465838432312,
              "kd_world_l1": 0.46997132897377014,
              "tokens": 1008,
              "total": 1.7724453210830688,
              "training": false,
              "world_l1": 0.46596190333366394
            },
            {
              "action_l1": 0.4019055664539337,
              "kd_act_l1": 0.40036481618881226,
              "kd_world_l1": 0.47252213954925537,
              "tokens": 1008,
              "total": 1.7451215982437134,
              "training": false,
              "world_l1": 0.47032904624938965
            },
            {
              "action_l1": 0.3729844391345978,
              "kd_act_l1": 0.37336766719818115,
              "kd_world_l1": 0.4686298966407776,
              "tokens": 1008,
              "total": 1.6787822246551514,
              "training": false,
              "world_l1": 0.4638003408908844
            },
            {
              "action_l1": 0.3563849627971649,
              "kd_act_l1": 0.35374724864959717,
              "kd_world_l1": 0.46348756551742554,
              "tokens": 1008,
              "total": 1.6323044300079346,
              "training": false,
              "world_l1": 0.4586845338344574
            },
            {
              "action_l1": 0.32347792387008667,
              "kd_act_l1": 0.32224607467651367,
              "kd_world_l1": 0.45539888739585876,
              "tokens": 1008,
              "total": 1.5533498525619507,
              "training": false,
              "world_l1": 0.4522269666194916
            },
            {
              "action_l1": 0.34175434708595276,
              "kd_act_l1": 0.3421710431575775,
              "kd_world_l1": 0.4603131115436554,
              "tokens": 1008,
              "total": 1.5969198942184448,
              "training": false,
              "world_l1": 0.45268142223358154
            },
            {
              "action_l1": 0.3434310555458069,
              "kd_act_l1": 0.3430972397327423,
              "kd_world_l1": 0.48087480664253235,
              "tokens": 1008,
              "total": 1.6370069980621338,
              "training": false,
              "world_l1": 0.46960392594337463
            },
            {
              "action_l1": 0.3625248670578003,
              "kd_act_l1": 0.36283743381500244,
              "kd_world_l1": 0.4847322404384613,
              "tokens": 1008,
              "total": 1.6833878755569458,
              "training": false,
              "world_l1": 0.4732933044433594
            },
            {
              "action_l1": 0.3802089989185333,
              "kd_act_l1": 0.3774819076061249,
              "kd_world_l1": 0.4908246695995331,
              "tokens": 1008,
              "total": 1.7282612323760986,
              "training": false,
              "world_l1": 0.47974565625190735
            },
            {
              "action_l1": 0.35948696732521057,
              "kd_act_l1": 0.3562225103378296,
              "kd_world_l1": 0.5009984374046326,
              "tokens": 1008,
              "total": 1.7047982215881348,
              "training": false,
              "world_l1": 0.48809024691581726
            },
            {
              "action_l1": 0.3363444209098816,
              "kd_act_l1": 0.33640941977500916,
              "kd_world_l1": 0.5136860609054565,
              "tokens": 1008,
              "total": 1.682600498199463,
              "training": false,
              "world_l1": 0.4961605370044708
            },
            {
              "action_l1": 0.3348453640937805,
              "kd_act_l1": 0.3354317843914032,
              "kd_world_l1": 0.5152003765106201,
              "tokens": 1008,
              "total": 1.6850173473358154,
              "training": false,
              "world_l1": 0.4995398223400116
            },
            {
              "action_l1": 0.3254011869430542,
              "kd_act_l1": 0.32608360052108765,
              "kd_world_l1": 0.50408935546875,
              "tokens": 1008,
              "total": 1.6440074443817139,
              "training": false,
              "world_l1": 0.4884333610534668
            },
            {
              "action_l1": 0.31101977825164795,
              "kd_act_l1": 0.3095698058605194,
              "kd_world_l1": 0.48526015877723694,
              "tokens": 1008,
              "total": 1.5809996128082275,
              "training": false,
              "world_l1": 0.47514986991882324
            },
            {
              "action_l1": 0.29402637481689453,
              "kd_act_l1": 0.293358713388443,
              "kd_world_l1": 0.49189406633377075,
              "tokens": 1008,
              "total": 1.5595965385437012,
              "training": false,
              "world_l1": 0.48031750321388245
            },
            {
              "action_l1": 0.26786649227142334,
              "kd_act_l1": 0.26789748668670654,
              "kd_world_l1": 0.49854907393455505,
              "tokens": 1008,
              "total": 1.519755244255066,
              "training": false,
              "world_l1": 0.4854421019554138
            },
            {
              "action_l1": 0.25821441411972046,
              "kd_act_l1": 0.25921431183815,
              "kd_world_l1": 0.5026824474334717,
              "tokens": 1008,
              "total": 1.5076016187667847,
              "training": false,
              "world_l1": 0.4874904751777649
            },
            {
              "action_l1": 0.23786835372447968,
              "kd_act_l1": 0.2373218685388565,
              "kd_world_l1": 0.4995994567871094,
              "tokens": 1008,
              "total": 1.4579954147338867,
              "training": false,
              "world_l1": 0.4832056760787964
            },
            {
              "action_l1": 0.2443961352109909,
              "kd_act_l1": 0.24495741724967957,
              "kd_world_l1": 0.49293792247772217,
              "tokens": 1008,
              "total": 1.4608101844787598,
              "training": false,
              "world_l1": 0.4785187244415283
            },
            {
              "action_l1": 0.24800710380077362,
              "kd_act_l1": 0.24645602703094482,
              "kd_world_l1": 0.4880303144454956,
              "tokens": 1008,
              "total": 1.4588003158569336,
              "training": false,
              "world_l1": 0.4763067960739136
            },
            {
              "action_l1": 0.24524274468421936,
              "kd_act_l1": 0.24571412801742554,
              "kd_world_l1": 0.48537677526474,
              "tokens": 1008,
              "total": 1.4514890909194946,
              "training": false,
              "world_l1": 0.47515541315078735
            },
            {
              "action_l1": 0.3575748801231384,
              "kd_act_l1": 0.3591225743293762,
              "kd_world_l1": 0.4623987674713135,
              "tokens": 1008,
              "total": 1.6361093521118164,
              "training": true,
              "world_l1": 0.4570131003856659
            },
            {
              "action_l1": 0.4151439070701599,
              "kd_act_l1": 0.41526395082473755,
              "kd_world_l1": 0.4868229031562805,
              "tokens": 1008,
              "total": 1.7958664894104004,
              "training": false,
              "world_l1": 0.4786358177661896
            },
            {
              "action_l1": 0.4412558674812317,
              "kd_act_l1": 0.4415957033634186,
              "kd_world_l1": 0.4847950041294098,
              "tokens": 1008,
              "total": 1.8495616912841797,
              "training": false,
              "world_l1": 0.4819152057170868
            },
            {
              "action_l1": 0.426437109708786,
              "kd_act_l1": 0.4279789626598358,
              "kd_world_l1": 0.47492754459381104,
              "tokens": 1008,
              "total": 1.8011478185653687,
              "training": false,
              "world_l1": 0.4718042016029358
            },
            {
              "action_l1": 0.4099768102169037,
              "kd_act_l1": 0.4104856848716736,
              "kd_world_l1": 0.4635678827762604,
              "tokens": 1008,
              "total": 1.7441035509109497,
              "training": false,
              "world_l1": 0.4600732922554016
            },
            {
              "action_l1": 0.3931501507759094,
              "kd_act_l1": 0.39190757274627686,
              "kd_world_l1": 0.46610984206199646,
              "tokens": 1008,
              "total": 1.7156118154525757,
              "training": false,
              "world_l1": 0.46444427967071533
            },
            {
              "action_l1": 0.36690112948417664,
              "kd_act_l1": 0.36661627888679504,
              "kd_world_l1": 0.4614211320877075,
              "tokens": 1008,
              "total": 1.6520916223526,
              "training": false,
              "world_l1": 0.4571531116962433
            },
            {
              "action_l1": 0.3488813638687134,
              "kd_act_l1": 0.3460148870944977,
              "kd_world_l1": 0.45616888999938965,
              "tokens": 1008,
              "total": 1.6031540632247925,
              "training": false,
              "world_l1": 0.4520889222621918
            },
            {
              "action_l1": 0.3183349370956421,
              "kd_act_l1": 0.3170149028301239,
              "kd_world_l1": 0.4480441212654114,
              "tokens": 1008,
              "total": 1.5288760662078857,
              "training": false,
              "world_l1": 0.44548219442367554
            },
            {
              "action_l1": 0.3355756103992462,
              "kd_act_l1": 0.3362877070903778,
              "kd_world_l1": 0.453475683927536,
              "tokens": 1008,
              "total": 1.5715956687927246,
              "training": false,
              "world_l1": 0.4462566673755646
            },
            {
              "action_l1": 0.3413628935813904,
              "kd_act_l1": 0.3410407304763794,
              "kd_world_l1": 0.4760177731513977,
              "tokens": 1008,
              "total": 1.623401165008545,
              "training": false,
              "world_l1": 0.4649798572063446
            },
            {
              "action_l1": 0.36372846364974976,
              "kd_act_l1": 0.3641022741794586,
              "kd_world_l1": 0.48022428154945374,
              "tokens": 1008,
              "total": 1.6769838333129883,
              "training": false,
              "world_l1": 0.46892890334129333
            },
            {
              "action_l1": 0.38170018792152405,
              "kd_act_l1": 0.37905603647232056,
              "kd_world_l1": 0.4864248037338257,
              "tokens": 1008,
              "total": 1.722446084022522,
              "training": false,
              "world_l1": 0.4752650558948517
            },
            {
              "action_l1": 0.35924866795539856,
              "kd_act_l1": 0.35655057430267334,
              "kd_world_l1": 0.49595439434051514,
              "tokens": 1008,
              "total": 1.694667100906372,
              "training": false,
              "world_l1": 0.4829134941101074
            },
            {
              "action_l1": 0.3364650309085846,
              "kd_act_l1": 0.3369666635990143,
              "kd_world_l1": 0.5082669854164124,
              "tokens": 1008,
              "total": 1.6723182201385498,
              "training": false,
              "world_l1": 0.4906196594238281
            },
            {
              "action_l1": 0.3355725407600403,
              "kd_act_l1": 0.3361823260784149,
              "kd_world_l1": 0.509727954864502,
              "tokens": 1008,
              "total": 1.675561547279358,
              "training": false,
              "world_l1": 0.49407872557640076
            },
            {
              "action_l1": 0.32810014486312866,
              "kd_act_l1": 0.3288188874721527,
              "kd_world_l1": 0.4980463981628418,
              "tokens": 1008,
              "total": 1.6373273134231567,
              "training": false,
              "world_l1": 0.48236188292503357
            },
            {
              "action_l1": 0.3127816319465637,
              "kd_act_l1": 0.31126514077186584,
              "kd_world_l1": 0.47778019309043884,
              "tokens": 1008,
              "total": 1.5695942640304565,
              "training": false,
              "world_l1": 0.46776726841926575
            },
            {
              "action_l1": 0.29587119817733765,
              "kd_act_l1": 0.2958911657333374,
              "kd_world_l1": 0.4853907823562622,
              "tokens": 1008,
              "total": 1.5510249137878418,
              "training": false,
              "world_l1": 0.47387179732322693
            },
            {
              "action_l1": 0.27054575085639954,
              "kd_act_l1": 0.269894003868103,
              "kd_world_l1": 0.4925864338874817,
              "tokens": 1008,
              "total": 1.5125560760498047,
              "training": false,
              "world_l1": 0.47952985763549805
            },
            {
              "action_l1": 0.2603386342525482,
              "kd_act_l1": 0.26147979497909546,
              "kd_world_l1": 0.4967629909515381,
              "tokens": 1008,
              "total": 1.500248908996582,
              "training": false,
              "world_l1": 0.48166748881340027
            },
            {
              "action_l1": 0.23924168944358826,
              "kd_act_l1": 0.2389599084854126,
              "kd_world_l1": 0.4935793876647949,
              "tokens": 1008,
              "total": 1.449102520942688,
              "training": false,
              "world_l1": 0.4773215055465698
            },
            {
              "action_l1": 0.2376088798046112,
              "kd_act_l1": 0.23781995475292206,
              "kd_world_l1": 0.4863889813423157,
              "tokens": 1008,
              "total": 1.4338780641555786,
              "training": false,
              "world_l1": 0.47206026315689087
            },
            {
              "action_l1": 0.23813645541667938,
              "kd_act_l1": 0.23688019812107086,
              "kd_world_l1": 0.4810430407524109,
              "tokens": 1008,
              "total": 1.4255529642105103,
              "training": false,
              "world_l1": 0.4694932997226715
            },
            {
              "action_l1": 0.23554100096225739,
              "kd_act_l1": 0.23620419204235077,
              "kd_world_l1": 0.47811228036880493,
              "tokens": 1008,
              "total": 1.4178822040557861,
              "training": false,
              "world_l1": 0.46802470088005066
            }
          ]
        }
      },
      "43": {
        "dataset": {
          "files": {
            "success_only/dataset_statistics.json": "5b119a98ad7824507ddff3c6c7507ca244261ee416dcfa623876702160c580d3",
            "success_only/libero_goal_regen/put_the_cream_cheese_in_the_bowl_demo.hdf5": "533472726b4cf89b2000af1bc275f26fb6cdcd2a5706fbd65cbe019f58180ebb"
          },
          "public_id": "nvidia/LIBERO-Cosmos-Policy",
          "revision": "b463cbd5d114909e4daea65eb03bed9787290042"
        },
        "files": {
          "best.pt": "cecda8b5b3c5f226a0cf193b42815478ae4e4dee5085a3d3f48cc3d20e2c0c66"
        },
        "implementation_sha256": {
          "lewam/external.py": "0e0a9dbaa54d897f01f6d6f2d13584ec26c1dcf84f4e541685bbc04791056b56",
          "smolwam/algorithm.py": "ee5563a4b6e6da35b066536e31fc63bfda9a75b2ef98b40ecae06aed9220266b",
          "smolwam/training.py": "7826d69e86534d51239975591d0d43b41d686ad8d7f9dc65c554a6e7977db718",
          "smolwam/worker.py": "3485d8bafa5b3fa548ae2454677f490cf3f8791ba310d2d14c48d69ca0f7fd8c"
        },
        "kind": "local-trained-candidate",
        "metrics": {
          "best_validation_action_l1": 0.34887000545859337,
          "compact_layout_updates": 6,
          "nonzero_gradient_updates": 8,
          "nonzero_parameter_updates": 7,
          "optimizer_updates": 8,
          "parameter_sample_delta_l2": 0.010347744867346676,
          "real_teacher_target_rows": 202,
          "teacher_layout_updates": 2,
          "teacher_vs_demo_action_l1": 0.009018332811561183,
          "train_mean_action_l1": 0.4027572423219681,
          "train_mean_kd_act_l1": 0.40376419946551323,
          "train_mean_kd_world_l1": 0.5165914744138718,
          "train_mean_world_l1": 0.5008405931293964,
          "updated_parameter_tensors": 340
        },
        "paper": "smolwam",
        "seed": 43,
        "selection": "validation only",
        "source_revision": "dde1e5bfe35c439499343c6d70e9cd32c96d0b36",
        "training_evidence": {
          "gradients": [
            {
              "norm": 0.9999999619836708,
              "parameter_sample_delta_l2": 0.0,
              "tokens": 1764
            },
            {
              "norm": 0.999999932338554,
              "parameter_sample_delta_l2": 0.003051045463920199,
              "tokens": 1764
            },
            {
              "norm": 0.999999937480205,
              "parameter_sample_delta_l2": 0.0030755360126631937,
              "tokens": 1008
            },
            {
              "norm": 0.9999999119122064,
              "parameter_sample_delta_l2": 0.002524172410765533,
              "tokens": 1008
            },
            {
              "norm": 0.999999860436377,
              "parameter_sample_delta_l2": 0.0017493792928235706,
              "tokens": 1008
            },
            {
              "norm": 0.9999998896440158,
              "parameter_sample_delta_l2": 0.001172074904116721,
              "tokens": 1008
            },
            {
              "norm": 0.9999999679006434,
              "parameter_sample_delta_l2": 0.0005566241776639691,
              "tokens": 1008
            },
            {
              "norm": 0.9999998530536142,
              "parameter_sample_delta_l2": 0.00024752900997920607,
              "tokens": 1008
            }
          ],
          "losses": [
            {
              "action_l1": 0.34981340169906616,
              "fut_proprio_l1": 0.4340325891971588,
              "kd_act_l1": 0.3486485779285431,
              "kd_world_l1": 0.6170944571495056,
              "tokens": 1764,
              "total": 1.9720840454101562,
              "training": true,
              "value_l1": 0.08159643411636353,
              "world_l1": 0.6049646735191345
            },
            {
              "action_l1": 0.3936975598335266,
              "fut_proprio_l1": 0.4443548023700714,
              "kd_act_l1": 0.39586108922958374,
              "kd_world_l1": 0.6157262921333313,
              "tokens": 1764,
              "total": 2.06437611579895,
              "training": false,
              "value_l1": 0.0951593741774559,
              "world_l1": 0.6051399111747742
            },
            {
              "action_l1": 0.4295903146266937,
              "fut_proprio_l1": 0.4567345976829529,
              "kd_act_l1": 0.43025851249694824,
              "kd_world_l1": 0.6159059405326843,
              "tokens": 1764,
              "total": 2.135310649871826,
              "training": false,
              "value_l1": 0.05793716385960579,
              "world_l1": 0.6080886125564575
            },
            {
              "action_l1": 0.4290464520454407,
              "fut_proprio_l1": 0.4584997594356537,
              "kd_act_l1": 0.4310087561607361,
              "kd_world_l1": 0.619202733039856,
              "tokens": 1764,
              "total": 2.1366019248962402,
              "training": false,
              "value_l1": 0.020049097016453743,
              "world_l1": 0.6094892621040344
            },
            {
              "action_l1": 0.4183022677898407,
              "fut_proprio_l1": 0.4537871181964874,
              "kd_act_l1": 0.41743430495262146,
              "kd_world_l1": 0.6180979013442993,
              "tokens": 1764,
              "total": 2.1092023849487305,
              "training": false,
              "value_l1": 0.019434764981269836,
              "world_l1": 0.6080456972122192
            },
            {
              "action_l1": 0.4169253408908844,
              "fut_proprio_l1": 0.4434448778629303,
              "kd_act_l1": 0.4149686098098755,
              "kd_world_l1": 0.622721254825592,
              "tokens": 1764,
              "total": 2.118635892868042,
              "training": false,
              "value_l1": 0.060669150203466415,
              "world_l1": 0.6136091947555542
            },
            {
              "action_l1": 0.3997133672237396,
              "fut_proprio_l1": 0.3671938180923462,
              "kd_act_l1": 0.3999001681804657,
              "kd_world_l1": 0.6304376721382141,
              "tokens": 1764,
              "total": 2.0982351303100586,
              "training": false,
              "value_l1": 0.10394388437271118,
              "world_l1": 0.6210703253746033
            },
            {
              "action_l1": 0.36659249663352966,
              "fut_proprio_l1": 0.26189783215522766,
              "kd_act_l1": 0.3624076545238495,
              "kd_world_l1": 0.6309574246406555,
              "tokens": 1764,
              "total": 2.021718740463257,
              "training": false,
              "value_l1": 0.15067945420742035,
              "world_l1": 0.620503306388855
            },
            {
              "action_l1": 0.3358321785926819,
              "fut_proprio_l1": 0.26094627380371094,
              "kd_act_l1": 0.3347843885421753,
              "kd_world_l1": 0.6247701048851013,
              "tokens": 1764,
              "total": 1.9590346813201904,
              "training": false,
              "value_l1": 0.19957990944385529,
              "world_l1": 0.6175954341888428
            },
            {
              "action_l1": 0.32610416412353516,
              "fut_proprio_l1": 0.2644869387149811,
              "kd_act_l1": 0.3254550099372864,
              "kd_world_l1": 0.6202878355979919,
              "tokens": 1764,
              "total": 1.9335277080535889,
              "training": false,
              "value_l1": 0.2509661912918091,
              "world_l1": 0.6101354360580444
            },
            {
              "action_l1": 0.3289055824279785,
              "fut_proprio_l1": 0.27078700065612793,
              "kd_act_l1": 0.32817453145980835,
              "kd_world_l1": 0.6201401352882385,
              "tokens": 1764,
              "total": 1.9452605247497559,
              "training": false,
              "value_l1": 0.3167167603969574,
              "world_l1": 0.6092898845672607
            },
            {
              "action_l1": 0.35025474429130554,
              "fut_proprio_l1": 0.26323312520980835,
              "kd_act_l1": 0.34750741720199585,
              "kd_world_l1": 0.6314806342124939,
              "tokens": 1764,
              "total": 2.0108561515808105,
              "training": false,
              "value_l1": 0.36475232243537903,
              "world_l1": 0.6188148260116577
            },
            {
              "action_l1": 0.3652319312095642,
              "fut_proprio_l1": 0.2609088122844696,
              "kd_act_l1": 0.36504337191581726,
              "kd_world_l1": 0.6394223570823669,
              "tokens": 1764,
              "total": 2.0662171840667725,
              "training": false,
              "value_l1": 0.4218195080757141,
              "world_l1": 0.6282466650009155
            },
            {
              "action_l1": 0.35885173082351685,
              "fut_proprio_l1": 0.2698976397514343,
              "kd_act_l1": 0.35722142457962036,
              "kd_world_l1": 0.6491656303405762,
              "tokens": 1764,
              "total": 2.0766313076019287,
              "training": false,
              "value_l1": 0.48111996054649353,
              "world_l1": 0.6362907290458679
            },
            {
              "action_l1": 0.3447954058647156,
              "fut_proprio_l1": 0.2677989602088928,
              "kd_act_l1": 0.34441617131233215,
              "kd_world_l1": 0.6591894626617432,
              "tokens": 1764,
              "total": 2.0727930068969727,
              "training": false,
              "value_l1": 0.542351484298706,
              "world_l1": 0.643376886844635
            },
            {
              "action_l1": 0.3508366346359253,
              "fut_proprio_l1": 0.2669430673122406,
              "kd_act_l1": 0.34960466623306274,
              "kd_world_l1": 0.6575163006782532,
              "tokens": 1764,
              "total": 2.0873446464538574,
              "training": false,
              "value_l1": 0.6064879298210144,
              "world_l1": 0.642043948173523
            },
            {
              "action_l1": 0.33522599935531616,
              "fut_proprio_l1": 0.2674989700317383,
              "kd_act_l1": 0.3350992500782013,
              "kd_world_l1": 0.6546816825866699,
              "tokens": 1764,
              "total": 2.0596420764923096,
              "training": false,
              "value_l1": 0.6733118891716003,
              "world_l1": 0.6405540704727173
            },
            {
              "action_l1": 0.31483951210975647,
              "fut_proprio_l1": 0.29239484667778015,
              "kd_act_l1": 0.31152936816215515,
              "kd_world_l1": 0.6493240594863892,
              "tokens": 1764,
              "total": 2.0183067321777344,
              "training": false,
              "value_l1": 0.742345929145813,
              "world_l1": 0.6391398310661316
            },
            {
              "action_l1": 0.2911345660686493,
              "fut_proprio_l1": 0.41966375708580017,
              "kd_act_l1": 0.290325790643692,
              "kd_world_l1": 0.6461955904960632,
              "tokens": 1764,
              "total": 1.983821153640747,
              "training": false,
              "value_l1": 0.814353883266449,
              "world_l1": 0.6327634453773499
            },
            {
              "action_l1": 0.26625189185142517,
              "fut_proprio_l1": 0.4458039700984955,
              "kd_act_l1": 0.26571589708328247,
              "kd_world_l1": 0.6449630260467529,
              "tokens": 1764,
              "total": 1.939652681350708,
              "training": false,
              "value_l1": 0.8900375366210938,
              "world_l1": 0.6291378140449524
            },
            {
              "action_l1": 0.2611495554447174,
              "fut_proprio_l1": 0.4486455023288727,
              "kd_act_l1": 0.2619667053222656,
              "kd_world_l1": 0.6462016701698303,
              "tokens": 1764,
              "total": 1.9385316371917725,
              "training": false,
              "value_l1": 0.9691016674041748,
              "world_l1": 0.6274389624595642
            },
            {
              "action_l1": 0.24611954391002655,
              "fut_proprio_l1": 0.44857820868492126,
              "kd_act_l1": 0.24510496854782104,
              "kd_world_l1": 0.6438249945640564,
              "tokens": 1764,
              "total": 1.9021804332733154,
              "training": false,
              "value_l1": 0.9691131114959717,
              "world_l1": 0.6253616809844971
            },
            {
              "action_l1": 0.22858422994613647,
              "fut_proprio_l1": 0.4481739401817322,
              "kd_act_l1": 0.22895106673240662,
              "kd_world_l1": 0.6326622366905212,
              "tokens": 1764,
              "total": 1.848508358001709,
              "training": false,
              "value_l1": 0.9723289608955383,
              "world_l1": 0.6162606477737427
            },
            {
              "action_l1": 0.21982026100158691,
              "fut_proprio_l1": 0.44724953174591064,
              "kd_act_l1": 0.22078187763690948,
              "kd_world_l1": 0.6289471983909607,
              "tokens": 1764,
              "total": 1.826019048690796,
              "training": false,
              "value_l1": 0.9680386781692505,
              "world_l1": 0.6149409413337708
            },
            {
              "action_l1": 0.2151200920343399,
              "fut_proprio_l1": 0.44724369049072266,
              "kd_act_l1": 0.21661962568759918,
              "kd_world_l1": 0.6266231536865234,
              "tokens": 1764,
              "total": 1.814931869506836,
              "training": false,
              "value_l1": 0.9684223532676697,
              "world_l1": 0.615002453327179
            },
            {
              "action_l1": 0.3233870565891266,
              "fut_proprio_l1": 0.25068342685699463,
              "kd_act_l1": 0.321988582611084,
              "kd_world_l1": 0.6195076704025269,
              "tokens": 1764,
              "total": 1.9311091899871826,
              "training": true,
              "value_l1": 0.3170507848262787,
              "world_l1": 0.6094524264335632
            },
            {
              "action_l1": 0.48216235637664795,
              "fut_proprio_l1": 0.5442050099372864,
              "kd_act_l1": 0.4819803237915039,
              "kd_world_l1": 0.5414456725120544,
              "tokens": 1764,
              "total": 2.0856943130493164,
              "training": false,
              "value_l1": 0.0006192922592163086,
              "world_l1": 0.5256233811378479
            },
            {
              "action_l1": 0.49749401211738586,
              "fut_proprio_l1": 0.553868293762207,
              "kd_act_l1": 0.49822211265563965,
              "kd_world_l1": 0.5415232181549072,
              "tokens": 1764,
              "total": 2.1244428157806396,
              "training": false,
              "value_l1": 0.03373563289642334,
              "world_l1": 0.5284432172775269
            },
            {
              "action_l1": 0.4742584526538849,
              "fut_proprio_l1": 0.5539627075195312,
              "kd_act_l1": 0.4751809239387512,
              "kd_world_l1": 0.5355598330497742,
              "tokens": 1764,
              "total": 2.0673670768737793,
              "training": false,
              "value_l1": 0.06976063549518585,
              "world_l1": 0.5199955701828003
            },
            {
              "action_l1": 0.4527713358402252,
              "fut_proprio_l1": 0.5499361157417297,
              "kd_act_l1": 0.4525947570800781,
              "kd_world_l1": 0.5254208445549011,
              "tokens": 1764,
              "total": 2.0061566829681396,
              "training": false,
              "value_l1": 0.10899663716554642,
              "world_l1": 0.5094764232635498
            },
            {
              "action_l1": 0.43461209535598755,
              "fut_proprio_l1": 0.5387375950813293,
              "kd_act_l1": 0.43384039402008057,
              "kd_world_l1": 0.5256392955780029,
              "tokens": 1764,
              "total": 1.9714176654815674,
              "training": false,
              "value_l1": 0.1433027982711792,
              "world_l1": 0.509121835231781
            },
            {
              "action_l1": 0.4010361433029175,
              "fut_proprio_l1": 0.46317100524902344,
              "kd_act_l1": 0.4021431803703308,
              "kd_world_l1": 0.5220053195953369,
              "tokens": 1764,
              "total": 1.894822359085083,
              "training": false,
              "value_l1": 0.18189004063606262,
              "world_l1": 0.5051315426826477
            },
            {
              "action_l1": 0.3933655321598053,
              "fut_proprio_l1": 0.3596709072589874,
              "kd_act_l1": 0.3931141793727875,
              "kd_world_l1": 0.5138505101203918,
              "tokens": 1764,
              "total": 1.8548836708068848,
              "training": false,
              "value_l1": 0.22657960653305054,
              "world_l1": 0.4959283173084259
            },
            {
              "action_l1": 0.36062610149383545,
              "fut_proprio_l1": 0.36416521668434143,
              "kd_act_l1": 0.3602449595928192,
              "kd_world_l1": 0.5063389539718628,
              "tokens": 1764,
              "total": 1.7813564538955688,
              "training": false,
              "value_l1": 0.2724975645542145,
              "world_l1": 0.4904802143573761
            },
            {
              "action_l1": 0.39140912890434265,
              "fut_proprio_l1": 0.3631618618965149,
              "kd_act_l1": 0.3910805284976959,
              "kd_world_l1": 0.5122869610786438,
              "tokens": 1764,
              "total": 1.8555934429168701,
              "training": false,
              "value_l1": 0.3209449052810669,
              "world_l1": 0.4924061596393585
            },
            {
              "action_l1": 0.39881885051727295,
              "fut_proprio_l1": 0.35735300183296204,
              "kd_act_l1": 0.40051475167274475,
              "kd_world_l1": 0.5244065523147583,
              "tokens": 1764,
              "total": 1.9016318321228027,
              "training": false,
              "value_l1": 0.3880310654640198,
              "world_l1": 0.5033532381057739
            },
            {
              "action_l1": 0.4132044017314911,
              "fut_proprio_l1": 0.3175027668476105,
              "kd_act_l1": 0.4137939214706421,
              "kd_world_l1": 0.5280896425247192,
              "tokens": 1764,
              "total": 1.9365676641464233,
              "training": false,
              "value_l1": 0.4398316442966461,
              "world_l1": 0.5057462453842163
            },
            {
              "action_l1": 0.4274524748325348,
              "fut_proprio_l1": 0.29842594265937805,
              "kd_act_l1": 0.42587506771087646,
              "kd_world_l1": 0.5343911051750183,
              "tokens": 1764,
              "total": 1.9801733493804932,
              "training": false,
              "value_l1": 0.4956045150756836,
              "world_l1": 0.5130516290664673
            },
            {
              "action_l1": 0.4262877404689789,
              "fut_proprio_l1": 0.2803434431552887,
              "kd_act_l1": 0.42331627011299133,
              "kd_world_l1": 0.5477256178855896,
              "tokens": 1764,
              "total": 2.0055370330810547,
              "training": false,
              "value_l1": 0.5545830130577087,
              "world_l1": 0.5247148871421814
            },
            {
              "action_l1": 0.3941141664981842,
              "fut_proprio_l1": 0.27568361163139343,
              "kd_act_l1": 0.39300891757011414,
              "kd_world_l1": 0.564784586429596,
              "tokens": 1764,
              "total": 1.9802064895629883,
              "training": false,
              "value_l1": 0.6178240776062012,
              "world_l1": 0.5389481782913208
            },
            {
              "action_l1": 0.3836081624031067,
              "fut_proprio_l1": 0.27943316102027893,
              "kd_act_l1": 0.38315337896347046,
              "kd_world_l1": 0.5651412606239319,
              "tokens": 1764,
              "total": 1.9693138599395752,
              "training": false,
              "value_l1": 0.6827223300933838,
              "world_l1": 0.5411954522132874
            },
            {
              "action_l1": 0.34851211309432983,
              "fut_proprio_l1": 0.29240259528160095,
              "kd_act_l1": 0.3510322868824005,
              "kd_world_l1": 0.5551232695579529,
              "tokens": 1764,
              "total": 1.8902568817138672,
              "training": false,
              "value_l1": 0.7494276165962219,
              "world_l1": 0.5314061641693115
            },
            {
              "action_l1": 0.33998748660087585,
              "fut_proprio_l1": 0.31226158142089844,
              "kd_act_l1": 0.3404070734977722,
              "kd_world_l1": 0.5421351194381714,
              "tokens": 1764,
              "total": 1.8597701787948608,
              "training": false,
              "value_l1": 0.8219479918479919,
              "world_l1": 0.5238195061683655
            },
            {
              "action_l1": 0.3276899755001068,
              "fut_proprio_l1": 0.4386400580406189,
              "kd_act_l1": 0.32751667499542236,
              "kd_world_l1": 0.5455912351608276,
              "tokens": 1764,
              "total": 1.8580563068389893,
              "training": false,
              "value_l1": 0.8970655202865601,
              "world_l1": 0.5236878395080566
            },
            {
              "action_l1": 0.3225940465927124,
              "fut_proprio_l1": 0.4618992209434509,
              "kd_act_l1": 0.3219810426235199,
              "kd_world_l1": 0.5486698150634766,
              "tokens": 1764,
              "total": 1.862442135810852,
              "training": false,
              "value_l1": 0.973033607006073,
              "world_l1": 0.5257039070129395
            },
            {
              "action_l1": 0.31582173705101013,
              "fut_proprio_l1": 0.46212926506996155,
              "kd_act_l1": 0.3157083988189697,
              "kd_world_l1": 0.5525858402252197,
              "tokens": 1764,
              "total": 1.8623340129852295,
              "training": false,
              "value_l1": 1.051177740097046,
              "world_l1": 0.5268872976303101
            },
            {
              "action_l1": 0.3024526536464691,
              "fut_proprio_l1": 0.46320363879203796,
              "kd_act_l1": 0.30206266045570374,
              "kd_world_l1": 0.5498507022857666,
              "tokens": 1764,
              "total": 1.828479290008545,
              "training": false,
              "value_l1": 1.0494968891143799,
              "world_l1": 0.5228431224822998
            },
            {
              "action_l1": 0.31656932830810547,
              "fut_proprio_l1": 0.48097124695777893,
              "kd_act_l1": 0.31689152121543884,
              "kd_world_l1": 0.5447467565536499,
              "tokens": 1764,
              "total": 1.8519957065582275,
              "training": false,
              "value_l1": 1.0523326396942139,
              "world_l1": 0.5204576849937439
            },
            {
              "action_l1": 0.3149646520614624,
              "fut_proprio_l1": 0.48376455903053284,
              "kd_act_l1": 0.3139647841453552,
              "kd_world_l1": 0.5416958928108215,
              "tokens": 1764,
              "total": 1.8441195487976074,
              "training": false,
              "value_l1": 1.0499690771102905,
              "world_l1": 0.5201209187507629
            },
            {
              "action_l1": 0.3105005919933319,
              "fut_proprio_l1": 0.4836905896663666,
              "kd_act_l1": 0.31108519434928894,
              "kd_world_l1": 0.5397276282310486,
              "tokens": 1764,
              "total": 1.8350205421447754,
              "training": false,
              "value_l1": 1.0504961013793945,
              "world_l1": 0.5202884674072266
            },
            {
              "action_l1": 0.41006341576576233,
              "kd_act_l1": 0.4115679860115051,
              "kd_world_l1": 0.5276234745979309,
              "tokens": 1008,
              "total": 1.8612747192382812,
              "training": true,
              "world_l1": 0.5120198130607605
            },
            {
              "action_l1": 0.4924725890159607,
              "kd_act_l1": 0.4945135712623596,
              "kd_world_l1": 0.5075893402099609,
              "tokens": 1008,
              "total": 1.980257272720337,
              "training": false,
              "world_l1": 0.48568177223205566
            },
            {
              "action_l1": 0.48776692152023315,
              "kd_act_l1": 0.48865213990211487,
              "kd_world_l1": 0.5067766904830933,
              "tokens": 1008,
              "total": 1.970460057258606,
              "training": false,
              "world_l1": 0.4872642755508423
            },
            {
              "action_l1": 0.4537270665168762,
              "kd_act_l1": 0.4535697102546692,
              "kd_world_l1": 0.49978068470954895,
              "tokens": 1008,
              "total": 1.8852119445800781,
              "training": false,
              "world_l1": 0.4781344532966614
            },
            {
              "action_l1": 0.4144428074359894,
              "kd_act_l1": 0.4176291823387146,
              "kd_world_l1": 0.48988550901412964,
              "tokens": 1008,
              "total": 1.790160894393921,
              "training": false,
              "world_l1": 0.4682033956050873
            },
            {
              "action_l1": 0.37417924404144287,
              "kd_act_l1": 0.37566012144088745,
              "kd_world_l1": 0.4913692772388458,
              "tokens": 1008,
              "total": 1.711202621459961,
              "training": false,
              "world_l1": 0.4699939787387848
            },
            {
              "action_l1": 0.3658679723739624,
              "kd_act_l1": 0.3679795563220978,
              "kd_world_l1": 0.4840291738510132,
              "tokens": 1008,
              "total": 1.680751085281372,
              "training": false,
              "world_l1": 0.4628744125366211
            },
            {
              "action_l1": 0.3550785183906555,
              "kd_act_l1": 0.3573656380176544,
              "kd_world_l1": 0.4793058931827545,
              "tokens": 1008,
              "total": 1.6499500274658203,
              "training": false,
              "world_l1": 0.45820000767707825
            },
            {
              "action_l1": 0.37151119112968445,
              "kd_act_l1": 0.3707772493362427,
              "kd_world_l1": 0.47301527857780457,
              "tokens": 1008,
              "total": 1.6682524681091309,
              "training": false,
              "world_l1": 0.4529486894607544
            },
            {
              "action_l1": 0.4192744195461273,
              "kd_act_l1": 0.42153871059417725,
              "kd_world_l1": 0.48083749413490295,
              "tokens": 1008,
              "total": 1.7778819799423218,
              "training": false,
              "world_l1": 0.45623132586479187
            },
            {
              "action_l1": 0.454974502325058,
              "kd_act_l1": 0.45800507068634033,
              "kd_world_l1": 0.5010607242584229,
              "tokens": 1008,
              "total": 1.8874871730804443,
              "training": false,
              "world_l1": 0.4734468162059784
            },
            {
              "action_l1": 0.46580806374549866,
              "kd_act_l1": 0.4689972996711731,
              "kd_world_l1": 0.5056112408638,
              "tokens": 1008,
              "total": 1.9189114570617676,
              "training": false,
              "world_l1": 0.47849491238594055
            },
            {
              "action_l1": 0.4840143322944641,
              "kd_act_l1": 0.4804728627204895,
              "kd_world_l1": 0.5100761651992798,
              "tokens": 1008,
              "total": 1.9588013887405396,
              "training": false,
              "world_l1": 0.4842379689216614
            },
            {
              "action_l1": 0.45953017473220825,
              "kd_act_l1": 0.4559735655784607,
              "kd_world_l1": 0.5214905738830566,
              "tokens": 1008,
              "total": 1.9300801753997803,
              "training": false,
              "world_l1": 0.49308592081069946
            },
            {
              "action_l1": 0.403138667345047,
              "kd_act_l1": 0.4024626612663269,
              "kd_world_l1": 0.5321754813194275,
              "tokens": 1008,
              "total": 1.8379120826721191,
              "training": false,
              "world_l1": 0.5001352429389954
            },
            {
              "action_l1": 0.3817574083805084,
              "kd_act_l1": 0.3833828866481781,
              "kd_world_l1": 0.5327973365783691,
              "tokens": 1008,
              "total": 1.8000006675720215,
              "training": false,
              "world_l1": 0.502062976360321
            },
            {
              "action_l1": 0.3613361120223999,
              "kd_act_l1": 0.36298587918281555,
              "kd_world_l1": 0.5236015319824219,
              "tokens": 1008,
              "total": 1.7412985563278198,
              "training": false,
              "world_l1": 0.4933750331401825
            },
            {
              "action_l1": 0.3691059947013855,
              "kd_act_l1": 0.3697766661643982,
              "kd_world_l1": 0.5070956945419312,
              "tokens": 1008,
              "total": 1.7289313077926636,
              "training": false,
              "world_l1": 0.48295289278030396
            },
            {
              "action_l1": 0.37353283166885376,
              "kd_act_l1": 0.372897207736969,
              "kd_world_l1": 0.5099889039993286,
              "tokens": 1008,
              "total": 1.7403119802474976,
              "training": false,
              "world_l1": 0.4838930070400238
            },
            {
              "action_l1": 0.3707897365093231,
              "kd_act_l1": 0.36959391832351685,
              "kd_world_l1": 0.5148515701293945,
              "tokens": 1008,
              "total": 1.742519497871399,
              "training": false,
              "world_l1": 0.48728427290916443
            },
            {
              "action_l1": 0.3610648512840271,
              "kd_act_l1": 0.361762672662735,
              "kd_world_l1": 0.5198273062705994,
              "tokens": 1008,
              "total": 1.7323217391967773,
              "training": false,
              "world_l1": 0.48966699838638306
            },
            {
              "action_l1": 0.34394967555999756,
              "kd_act_l1": 0.345199853181839,
              "kd_world_l1": 0.5181446075439453,
              "tokens": 1008,
              "total": 1.6948192119598389,
              "training": false,
              "world_l1": 0.4875250458717346
            },
            {
              "action_l1": 0.3551555573940277,
              "kd_act_l1": 0.3579463064670563,
              "kd_world_l1": 0.5139661431312561,
              "tokens": 1008,
              "total": 1.7124576568603516,
              "training": false,
              "world_l1": 0.4853896200656891
            },
            {
              "action_l1": 0.34960076212882996,
              "kd_act_l1": 0.3485614061355591,
              "kd_world_l1": 0.5104429125785828,
              "tokens": 1008,
              "total": 1.6929833889007568,
              "training": false,
              "world_l1": 0.48437824845314026
            },
            {
              "action_l1": 0.3447591960430145,
              "kd_act_l1": 0.3455445468425751,
              "kd_world_l1": 0.5095109343528748,
              "tokens": 1008,
              "total": 1.6839404106140137,
              "training": false,
              "world_l1": 0.48412570357322693
            },
            {
              "action_l1": 0.4690893590450287,
              "kd_act_l1": 0.4754965901374817,
              "kd_world_l1": 0.5048710107803345,
              "tokens": 1008,
              "total": 1.9315773248672485,
              "training": true,
              "world_l1": 0.4821202754974365
            },
            {
              "action_l1": 0.4145420491695404,
              "kd_act_l1": 0.41710689663887024,
              "kd_world_l1": 0.492136687040329,
              "tokens": 1008,
              "total": 1.791852355003357,
              "training": false,
              "world_l1": 0.4680666923522949
            },
            {
              "action_l1": 0.4439249038696289,
              "kd_act_l1": 0.4451168179512024,
              "kd_world_l1": 0.491974413394928,
              "tokens": 1008,
              "total": 1.8518400192260742,
              "training": false,
              "world_l1": 0.4708240032196045
            },
            {
              "action_l1": 0.4401727616786957,
              "kd_act_l1": 0.4416884183883667,
              "kd_world_l1": 0.48436298966407776,
              "tokens": 1008,
              "total": 1.828400731086731,
              "training": false,
              "world_l1": 0.462176650762558
            },
            {
              "action_l1": 0.42628031969070435,
              "kd_act_l1": 0.4270785450935364,
              "kd_world_l1": 0.47849392890930176,
              "tokens": 1008,
              "total": 1.7870631217956543,
              "training": false,
              "world_l1": 0.4552103877067566
            },
            {
              "action_l1": 0.4230959117412567,
              "kd_act_l1": 0.42166635394096375,
              "kd_world_l1": 0.48576781153678894,
              "tokens": 1008,
              "total": 1.79510498046875,
              "training": false,
              "world_l1": 0.46457481384277344
            },
            {
              "action_l1": 0.42342767119407654,
              "kd_act_l1": 0.42350301146507263,
              "kd_world_l1": 0.4785144329071045,
              "tokens": 1008,
              "total": 1.7842168807983398,
              "training": false,
              "world_l1": 0.45877179503440857
            },
            {
              "action_l1": 0.38721978664398193,
              "kd_act_l1": 0.3842751085758209,
              "kd_world_l1": 0.4731242060661316,
              "tokens": 1008,
              "total": 1.6980891227722168,
              "training": false,
              "world_l1": 0.4534701108932495
            },
            {
              "action_l1": 0.37214988470077515,
              "kd_act_l1": 0.3705454170703888,
              "kd_world_l1": 0.46588289737701416,
              "tokens": 1008,
              "total": 1.6550369262695312,
              "training": false,
              "world_l1": 0.44645875692367554
            },
            {
              "action_l1": 0.3586653470993042,
              "kd_act_l1": 0.3585759699344635,
              "kd_world_l1": 0.47544384002685547,
              "tokens": 1008,
              "total": 1.6416244506835938,
              "training": false,
              "world_l1": 0.44893932342529297
            },
            {
              "action_l1": 0.36660072207450867,
              "kd_act_l1": 0.36601683497428894,
              "kd_world_l1": 0.5014109015464783,
              "tokens": 1008,
              "total": 1.7036256790161133,
              "training": false,
              "world_l1": 0.46959730982780457
            },
            {
              "action_l1": 0.37990400195121765,
              "kd_act_l1": 0.3763619661331177,
              "kd_world_l1": 0.5069178938865662,
              "tokens": 1008,
              "total": 1.7384891510009766,
              "training": false,
              "world_l1": 0.47530534863471985
            },
            {
              "action_l1": 0.3954746127128601,
              "kd_act_l1": 0.3936087191104889,
              "kd_world_l1": 0.5122136473655701,
              "tokens": 1008,
              "total": 1.7818517684936523,
              "training": false,
              "world_l1": 0.4805547595024109
            },
            {
              "action_l1": 0.38571980595588684,
              "kd_act_l1": 0.38410255312919617,
              "kd_world_l1": 0.5213913321495056,
              "tokens": 1008,
              "total": 1.7793762683868408,
              "training": false,
              "world_l1": 0.48816266655921936
            },
            {
              "action_l1": 0.3784615099430084,
              "kd_act_l1": 0.3797502815723419,
              "kd_world_l1": 0.5287096500396729,
              "tokens": 1008,
              "total": 1.7804745435714722,
              "training": false,
              "world_l1": 0.4935530722141266
            },
            {
              "action_l1": 0.3823884427547455,
              "kd_act_l1": 0.38193628191947937,
              "kd_world_l1": 0.5310812592506409,
              "tokens": 1008,
              "total": 1.7937006950378418,
              "training": false,
              "world_l1": 0.4982945919036865
            },
            {
              "action_l1": 0.37277740240097046,
              "kd_act_l1": 0.37197354435920715,
              "kd_world_l1": 0.5207809805870056,
              "tokens": 1008,
              "total": 1.7535991668701172,
              "training": false,
              "world_l1": 0.4880673587322235
            },
            {
              "action_l1": 0.33733102679252625,
              "kd_act_l1": 0.3342941999435425,
              "kd_world_l1": 0.49388012290000916,
              "tokens": 1008,
              "total": 1.6322991847991943,
              "training": false,
              "world_l1": 0.46679383516311646
            },
            {
              "action_l1": 0.3215321898460388,
              "kd_act_l1": 0.31994786858558655,
              "kd_world_l1": 0.5022522211074829,
              "tokens": 1008,
              "total": 1.616826057434082,
              "training": false,
              "world_l1": 0.47309383749961853
            },
            {
              "action_l1": 0.28944677114486694,
              "kd_act_l1": 0.28907763957977295,
              "kd_world_l1": 0.5097170472145081,
              "tokens": 1008,
              "total": 1.5670251846313477,
              "training": false,
              "world_l1": 0.47878381609916687
            },
            {
              "action_l1": 0.287040650844574,
              "kd_act_l1": 0.28612929582595825,
              "kd_world_l1": 0.5156921148300171,
              "tokens": 1008,
              "total": 1.5708659887313843,
              "training": false,
              "world_l1": 0.48200395703315735
            },
            {
              "action_l1": 0.2764662206172943,
              "kd_act_l1": 0.2770693302154541,
              "kd_world_l1": 0.5150663256645203,
              "tokens": 1008,
              "total": 1.5494945049285889,
              "training": false,
              "world_l1": 0.4808926284313202
            },
            {
              "action_l1": 0.26743102073669434,
              "kd_act_l1": 0.26733118295669556,
              "kd_world_l1": 0.5079012513160706,
              "tokens": 1008,
              "total": 1.5183303356170654,
              "training": false,
              "world_l1": 0.47566697001457214
            },
            {
              "action_l1": 0.2595730423927307,
              "kd_act_l1": 0.26026472449302673,
              "kd_world_l1": 0.5031650066375732,
              "tokens": 1008,
              "total": 1.4966503381729126,
              "training": false,
              "world_l1": 0.47364750504493713
            },
            {
              "action_l1": 0.25911450386047363,
              "kd_act_l1": 0.2600519359111786,
              "kd_world_l1": 0.5013397336006165,
              "tokens": 1008,
              "total": 1.4927244186401367,
              "training": false,
              "world_l1": 0.47221821546554565
            },
            {
              "action_l1": 0.4263717830181122,
              "kd_act_l1": 0.42448118329048157,
              "kd_world_l1": 0.4891778528690338,
              "tokens": 1008,
              "total": 1.8056517839431763,
              "training": true,
              "world_l1": 0.4656209945678711
            },
            {
              "action_l1": 0.41644981503486633,
              "kd_act_l1": 0.41960614919662476,
              "kd_world_l1": 0.4776268005371094,
              "tokens": 1008,
              "total": 1.7699100971221924,
              "training": false,
              "world_l1": 0.45622727274894714
            },
            {
              "action_l1": 0.4273059666156769,
              "kd_act_l1": 0.4285779893398285,
              "kd_world_l1": 0.4782353639602661,
              "tokens": 1008,
              "total": 1.7947660684585571,
              "training": false,
              "world_l1": 0.46064671874046326
            },
            {
              "action_l1": 0.41475632786750793,
              "kd_act_l1": 0.41542062163352966,
              "kd_world_l1": 0.4679258465766907,
              "tokens": 1008,
              "total": 1.747377634048462,
              "training": false,
              "world_l1": 0.4492748975753784
            },
            {
              "action_l1": 0.3852439224720001,
              "kd_act_l1": 0.38753387331962585,
              "kd_world_l1": 0.45654359459877014,
              "tokens": 1008,
              "total": 1.6662929058074951,
              "training": false,
              "world_l1": 0.4369715452194214
            },
            {
              "action_l1": 0.3606869876384735,
              "kd_act_l1": 0.36089280247688293,
              "kd_world_l1": 0.46024835109710693,
              "tokens": 1008,
              "total": 1.6246541738510132,
              "training": false,
              "world_l1": 0.4428260922431946
            },
            {
              "action_l1": 0.3625834286212921,
              "kd_act_l1": 0.36401674151420593,
              "kd_world_l1": 0.4538119435310364,
              "tokens": 1008,
              "total": 1.6162333488464355,
              "training": false,
              "world_l1": 0.43582117557525635
            },
            {
              "action_l1": 0.3398633897304535,
              "kd_act_l1": 0.3403552770614624,
              "kd_world_l1": 0.4488220810890198,
              "tokens": 1008,
              "total": 1.5601139068603516,
              "training": false,
              "world_l1": 0.43107324838638306
            },
            {
              "action_l1": 0.34922507405281067,
              "kd_act_l1": 0.34837308526039124,
              "kd_world_l1": 0.44046276807785034,
              "tokens": 1008,
              "total": 1.5614187717437744,
              "training": false,
              "world_l1": 0.423357754945755
            },
            {
              "action_l1": 0.36691898107528687,
              "kd_act_l1": 0.3692787289619446,
              "kd_world_l1": 0.4459620416164398,
              "tokens": 1008,
              "total": 1.6049565076828003,
              "training": false,
              "world_l1": 0.42279669642448425
            },
            {
              "action_l1": 0.3928346335887909,
              "kd_act_l1": 0.3933967351913452,
              "kd_world_l1": 0.47348707914352417,
              "tokens": 1008,
              "total": 1.7059781551361084,
              "training": false,
              "world_l1": 0.44625961780548096
            },
            {
              "action_l1": 0.4002925455570221,
              "kd_act_l1": 0.40277940034866333,
              "kd_world_l1": 0.47763022780418396,
              "tokens": 1008,
              "total": 1.7314552068710327,
              "training": false,
              "world_l1": 0.4507529139518738
            },
            {
              "action_l1": 0.4224904179573059,
              "kd_act_l1": 0.4202859103679657,
              "kd_world_l1": 0.482138067483902,
              "tokens": 1008,
              "total": 1.7806246280670166,
              "training": false,
              "world_l1": 0.4557102918624878
            },
            {
              "action_l1": 0.39758798480033875,
              "kd_act_l1": 0.39435991644859314,
              "kd_world_l1": 0.49297821521759033,
              "tokens": 1008,
              "total": 1.749394416809082,
              "training": false,
              "world_l1": 0.46446824073791504
            },
            {
              "action_l1": 0.3569936156272888,
              "kd_act_l1": 0.35677430033683777,
              "kd_world_l1": 0.5015830397605896,
              "tokens": 1008,
              "total": 1.6852476596832275,
              "training": false,
              "world_l1": 0.46989673376083374
            },
            {
              "action_l1": 0.3451780676841736,
              "kd_act_l1": 0.3462509512901306,
              "kd_world_l1": 0.5038058757781982,
              "tokens": 1008,
              "total": 1.6696003675460815,
              "training": false,
              "world_l1": 0.4743654727935791
            },
            {
              "action_l1": 0.3309747278690338,
              "kd_act_l1": 0.332725465297699,
              "kd_world_l1": 0.49088215827941895,
              "tokens": 1008,
              "total": 1.6155787706375122,
              "training": false,
              "world_l1": 0.4609964191913605
            },
            {
              "action_l1": 0.32459336519241333,
              "kd_act_l1": 0.3246585428714752,
              "kd_world_l1": 0.46155017614364624,
              "tokens": 1008,
              "total": 1.548783302307129,
              "training": false,
              "world_l1": 0.43798115849494934
            },
            {
              "action_l1": 0.32009807229042053,
              "kd_act_l1": 0.32021933794021606,
              "kd_world_l1": 0.47167709469795227,
              "tokens": 1008,
              "total": 1.5574438571929932,
              "training": false,
              "world_l1": 0.4454493522644043
            },
            {
              "action_l1": 0.29512032866477966,
              "kd_act_l1": 0.29529061913490295,
              "kd_world_l1": 0.48268359899520874,
              "tokens": 1008,
              "total": 1.5280849933624268,
              "training": false,
              "world_l1": 0.4549903869628906
            },
            {
              "action_l1": 0.28972288966178894,
              "kd_act_l1": 0.2902873754501343,
              "kd_world_l1": 0.4883819818496704,
              "tokens": 1008,
              "total": 1.526738166809082,
              "training": false,
              "world_l1": 0.4583459198474884
            },
            {
              "action_l1": 0.27465927600860596,
              "kd_act_l1": 0.2754199802875519,
              "kd_world_l1": 0.4838019013404846,
              "tokens": 1008,
              "total": 1.4868180751800537,
              "training": false,
              "world_l1": 0.4529368281364441
            },
            {
              "action_l1": 0.2826857566833496,
              "kd_act_l1": 0.2853703498840332,
              "kd_world_l1": 0.4723444879055023,
              "tokens": 1008,
              "total": 1.4838632345199585,
              "training": false,
              "world_l1": 0.44346266984939575
            },
            {
              "action_l1": 0.2769235670566559,
              "kd_act_l1": 0.27711716294288635,
              "kd_world_l1": 0.46498534083366394,
              "tokens": 1008,
              "total": 1.4578927755355835,
              "training": false,
              "world_l1": 0.43886667490005493
            },
            {
              "action_l1": 0.2725139260292053,
              "kd_act_l1": 0.2736903429031372,
              "kd_world_l1": 0.4607982039451599,
              "tokens": 1008,
              "total": 1.4426696300506592,
              "training": false,
              "world_l1": 0.43566715717315674
            },
            {
              "action_l1": 0.3502860963344574,
              "kd_act_l1": 0.35150960087776184,
              "kd_world_l1": 0.4548006057739258,
              "tokens": 1008,
              "total": 1.599483609199524,
              "training": true,
              "world_l1": 0.4428873658180237
            },
            {
              "action_l1": 0.4442121982574463,
              "kd_act_l1": 0.44671252369880676,
              "kd_world_l1": 0.47168782353401184,
              "tokens": 1008,
              "total": 1.8166139125823975,
              "training": false,
              "world_l1": 0.45400139689445496
            },
            {
              "action_l1": 0.446548730134964,
              "kd_act_l1": 0.4474157691001892,
              "kd_world_l1": 0.4742495119571686,
              "tokens": 1008,
              "total": 1.8290044069290161,
              "training": false,
              "world_l1": 0.4607904255390167
            },
            {
              "action_l1": 0.4196065366268158,
              "kd_act_l1": 0.4204687476158142,
              "kd_world_l1": 0.461284875869751,
              "tokens": 1008,
              "total": 1.7483197450637817,
              "training": false,
              "world_l1": 0.44695958495140076
            },
            {
              "action_l1": 0.38841068744659424,
              "kd_act_l1": 0.39142197370529175,
              "kd_world_l1": 0.4439941644668579,
              "tokens": 1008,
              "total": 1.6520472764968872,
              "training": false,
              "world_l1": 0.4282205104827881
            },
            {
              "action_l1": 0.35019251704216003,
              "kd_act_l1": 0.35209187865257263,
              "kd_world_l1": 0.44470322132110596,
              "tokens": 1008,
              "total": 1.5777076482772827,
              "training": false,
              "world_l1": 0.4307200312614441
            },
            {
              "action_l1": 0.35205569863319397,
              "kd_act_l1": 0.35386088490486145,
              "kd_world_l1": 0.436979740858078,
              "tokens": 1008,
              "total": 1.5639619827270508,
              "training": false,
              "world_l1": 0.42106565833091736
            },
            {
              "action_l1": 0.3373733162879944,
              "kd_act_l1": 0.3393685221672058,
              "kd_world_l1": 0.43163546919822693,
              "tokens": 1008,
              "total": 1.5245105028152466,
              "training": false,
              "world_l1": 0.4161331355571747
            },
            {
              "action_l1": 0.356303334236145,
              "kd_act_l1": 0.35509076714515686,
              "kd_world_l1": 0.4220145046710968,
              "tokens": 1008,
              "total": 1.5407952070236206,
              "training": false,
              "world_l1": 0.4073866903781891
            },
            {
              "action_l1": 0.39166468381881714,
              "kd_act_l1": 0.39410585165023804,
              "kd_world_l1": 0.424432635307312,
              "tokens": 1008,
              "total": 1.6149097681045532,
              "training": false,
              "world_l1": 0.40470659732818604
            },
            {
              "action_l1": 0.4262522757053375,
              "kd_act_l1": 0.42688649892807007,
              "kd_world_l1": 0.45453542470932007,
              "tokens": 1008,
              "total": 1.7393124103546143,
              "training": false,
              "world_l1": 0.43163827061653137
            },
            {
              "action_l1": 0.43517956137657166,
              "kd_act_l1": 0.43766888976097107,
              "kd_world_l1": 0.4569762647151947,
              "tokens": 1008,
              "total": 1.7646222114562988,
              "training": false,
              "world_l1": 0.43479740619659424
            },
            {
              "action_l1": 0.4550962746143341,
              "kd_act_l1": 0.4522176682949066,
              "kd_world_l1": 0.4603314995765686,
              "tokens": 1008,
              "total": 1.8065049648284912,
              "training": false,
              "world_l1": 0.43885958194732666
            },
            {
              "action_l1": 0.42863431572914124,
              "kd_act_l1": 0.4249957203865051,
              "kd_world_l1": 0.47229647636413574,
              "tokens": 1008,
              "total": 1.7741611003875732,
              "training": false,
              "world_l1": 0.44823455810546875
            },
            {
              "action_l1": 0.37567922472953796,
              "kd_act_l1": 0.3749956786632538,
              "kd_world_l1": 0.48179104924201965,
              "tokens": 1008,
              "total": 1.6863282918930054,
              "training": false,
              "world_l1": 0.4538623094558716
            },
            {
              "action_l1": 0.35477539896965027,
              "kd_act_l1": 0.355773001909256,
              "kd_world_l1": 0.4842495024204254,
              "tokens": 1008,
              "total": 1.6531342267990112,
              "training": false,
              "world_l1": 0.45833632349967957
            },
            {
              "action_l1": 0.3416599631309509,
              "kd_act_l1": 0.34342214465141296,
              "kd_world_l1": 0.46750473976135254,
              "tokens": 1008,
              "total": 1.593320608139038,
              "training": false,
              "world_l1": 0.4407337009906769
            },
            {
              "action_l1": 0.34247297048568726,
              "kd_act_l1": 0.3416711390018463,
              "kd_world_l1": 0.4364500045776367,
              "tokens": 1008,
              "total": 1.5377403497695923,
              "training": false,
              "world_l1": 0.417146235704422
            },
            {
              "action_l1": 0.3470977544784546,
              "kd_act_l1": 0.34647342562675476,
              "kd_world_l1": 0.4502880871295929,
              "tokens": 1008,
              "total": 1.5708547830581665,
              "training": false,
              "world_l1": 0.42699551582336426
            },
            {
              "action_l1": 0.3299936056137085,
              "kd_act_l1": 0.32942914962768555,
              "kd_world_l1": 0.4648468494415283,
              "tokens": 1008,
              "total": 1.56492280960083,
              "training": false,
              "world_l1": 0.4406532645225525
            },
            {
              "action_l1": 0.32301056385040283,
              "kd_act_l1": 0.323771595954895,
              "kd_world_l1": 0.470351904630661,
              "tokens": 1008,
              "total": 1.5607494115829468,
              "training": false,
              "world_l1": 0.4436153471469879
            },
            {
              "action_l1": 0.3068077564239502,
              "kd_act_l1": 0.30823731422424316,
              "kd_world_l1": 0.4619494676589966,
              "tokens": 1008,
              "total": 1.511192798614502,
              "training": false,
              "world_l1": 0.4341982901096344
            },
            {
              "action_l1": 0.31347185373306274,
              "kd_act_l1": 0.31612807512283325,
              "kd_world_l1": 0.4468872845172882,
              "tokens": 1008,
              "total": 1.4976160526275635,
              "training": false,
              "world_l1": 0.4211287796497345
            },
            {
              "action_l1": 0.3080177307128906,
              "kd_act_l1": 0.3069953918457031,
              "kd_world_l1": 0.43595293164253235,
              "tokens": 1008,
              "total": 1.464508295059204,
              "training": false,
              "world_l1": 0.413542240858078
            },
            {
              "action_l1": 0.3040279746055603,
              "kd_act_l1": 0.30485889315605164,
              "kd_world_l1": 0.4297948479652405,
              "tokens": 1008,
              "total": 1.4473092555999756,
              "training": false,
              "world_l1": 0.40862762928009033
            },
            {
              "action_l1": 0.4575379490852356,
              "kd_act_l1": 0.4599457383155823,
              "kd_world_l1": 0.46598732471466064,
              "tokens": 1008,
              "total": 1.8346209526062012,
              "training": true,
              "world_l1": 0.45114994049072266
            },
            {
              "action_l1": 0.4286978244781494,
              "kd_act_l1": 0.43095725774765015,
              "kd_world_l1": 0.45865508913993835,
              "tokens": 1008,
              "total": 1.7588516473770142,
              "training": false,
              "world_l1": 0.44054144620895386
            },
            {
              "action_l1": 0.43292880058288574,
              "kd_act_l1": 0.4335080087184906,
              "kd_world_l1": 0.4613012969493866,
              "tokens": 1008,
              "total": 1.775515079498291,
              "training": false,
              "world_l1": 0.4477769136428833
            },
            {
              "action_l1": 0.40805307030677795,
              "kd_act_l1": 0.40867379307746887,
              "kd_world_l1": 0.44672051072120667,
              "tokens": 1008,
              "total": 1.69601309299469,
              "training": false,
              "world_l1": 0.4325658082962036
            },
            {
              "action_l1": 0.37717488408088684,
              "kd_act_l1": 0.38034018874168396,
              "kd_world_l1": 0.4284992516040802,
              "tokens": 1008,
              "total": 1.598860502243042,
              "training": false,
              "world_l1": 0.4128461480140686
            },
            {
              "action_l1": 0.3423028886318207,
              "kd_act_l1": 0.3431515097618103,
              "kd_world_l1": 0.42757686972618103,
              "tokens": 1008,
              "total": 1.52704918384552,
              "training": false,
              "world_l1": 0.41401779651641846
            },
            {
              "action_l1": 0.3425839841365814,
              "kd_act_l1": 0.3441585600376129,
              "kd_world_l1": 0.41785678267478943,
              "tokens": 1008,
              "total": 1.5069992542266846,
              "training": false,
              "world_l1": 0.40239986777305603
            },
            {
              "action_l1": 0.3284493088722229,
              "kd_act_l1": 0.3292860984802246,
              "kd_world_l1": 0.41286686062812805,
              "tokens": 1008,
              "total": 1.468156099319458,
              "training": false,
              "world_l1": 0.3975538909435272
            },
            {
              "action_l1": 0.34140118956565857,
              "kd_act_l1": 0.3405897319316864,
              "kd_world_l1": 0.4023854732513428,
              "tokens": 1008,
              "total": 1.4723904132843018,
              "training": false,
              "world_l1": 0.388014018535614
            },
            {
              "action_l1": 0.3765219748020172,
              "kd_act_l1": 0.3784675896167755,
              "kd_world_l1": 0.40467414259910583,
              "tokens": 1008,
              "total": 1.5449187755584717,
              "training": false,
              "world_l1": 0.3852550983428955
            },
            {
              "action_l1": 0.4111555516719818,
              "kd_act_l1": 0.41183945536613464,
              "kd_world_l1": 0.43885281682014465,
              "tokens": 1008,
              "total": 1.6774450540542603,
              "training": false,
              "world_l1": 0.41559725999832153
            },
            {
              "action_l1": 0.42482998967170715,
              "kd_act_l1": 0.4268267750740051,
              "kd_world_l1": 0.4415348470211029,
              "tokens": 1008,
              "total": 1.7123390436172485,
              "training": false,
              "world_l1": 0.4191474914550781
            },
            {
              "action_l1": 0.44520440697669983,
              "kd_act_l1": 0.4420696198940277,
              "kd_world_l1": 0.4448663294315338,
              "tokens": 1008,
              "total": 1.7553584575653076,
              "training": false,
              "world_l1": 0.4232180714607239
            },
            {
              "action_l1": 0.4187011122703552,
              "kd_act_l1": 0.4150625169277191,
              "kd_world_l1": 0.45629414916038513,
              "tokens": 1008,
              "total": 1.7219197750091553,
              "training": false,
              "world_l1": 0.43186190724372864
            },
            {
              "action_l1": 0.36664649844169617,
              "kd_act_l1": 0.3655065894126892,
              "kd_world_l1": 0.46459299325942993,
              "tokens": 1008,
              "total": 1.6329519748687744,
              "training": false,
              "world_l1": 0.43620604276657104
            },
            {
              "action_l1": 0.3472391963005066,
              "kd_act_l1": 0.3480788767337799,
              "kd_world_l1": 0.4669109284877777,
              "tokens": 1008,
              "total": 1.6027745008468628,
              "training": false,
              "world_l1": 0.4405454695224762
            },
            {
              "action_l1": 0.33374208211898804,
              "kd_act_l1": 0.3363601267337799,
              "kd_world_l1": 0.44983571767807007,
              "tokens": 1008,
              "total": 1.5420916080474854,
              "training": false,
              "world_l1": 0.42215362191200256
            },
            {
              "action_l1": 0.3364197313785553,
              "kd_act_l1": 0.33630144596099854,
              "kd_world_l1": 0.4159128963947296,
              "tokens": 1008,
              "total": 1.4850101470947266,
              "training": false,
              "world_l1": 0.3963761031627655
            },
            {
              "action_l1": 0.3353229761123657,
              "kd_act_l1": 0.3351672291755676,
              "kd_world_l1": 0.43256518244743347,
              "tokens": 1008,
              "total": 1.5119192600250244,
              "training": false,
              "world_l1": 0.40886390209198
            },
            {
              "action_l1": 0.31770268082618713,
              "kd_act_l1": 0.31734663248062134,
              "kd_world_l1": 0.4490191340446472,
              "tokens": 1008,
              "total": 1.5084505081176758,
              "training": false,
              "world_l1": 0.42438194155693054
            },
            {
              "action_l1": 0.3099552094936371,
              "kd_act_l1": 0.31074059009552,
              "kd_world_l1": 0.4549866318702698,
              "tokens": 1008,
              "total": 1.5033540725708008,
              "training": false,
              "world_l1": 0.4276717007160187
            },
            {
              "action_l1": 0.2925223112106323,
              "kd_act_l1": 0.29376348853111267,
              "kd_world_l1": 0.4454247057437897,
              "tokens": 1008,
              "total": 1.448699951171875,
              "training": false,
              "world_l1": 0.41698941588401794
            },
            {
              "action_l1": 0.296762079000473,
              "kd_act_l1": 0.2994800806045532,
              "kd_world_l1": 0.42815157771110535,
              "tokens": 1008,
              "total": 1.4264079332351685,
              "training": false,
              "world_l1": 0.40201419591903687
            },
            {
              "action_l1": 0.29037877917289734,
              "kd_act_l1": 0.2894962430000305,
              "kd_world_l1": 0.4152976870536804,
              "tokens": 1008,
              "total": 1.387847900390625,
              "training": false,
              "world_l1": 0.3926751911640167
            },
            {
              "action_l1": 0.2863817811012268,
              "kd_act_l1": 0.287179559469223,
              "kd_world_l1": 0.40800678730010986,
              "tokens": 1008,
              "total": 1.3682736158370972,
              "training": false,
              "world_l1": 0.3867054283618927
            },
            {
              "action_l1": 0.4355088770389557,
              "kd_act_l1": 0.43647533655166626,
              "kd_world_l1": 0.45366939902305603,
              "tokens": 1008,
              "total": 1.7641628980636597,
              "training": true,
              "world_l1": 0.4385092556476593
            },
            {
              "action_l1": 0.41715267300605774,
              "kd_act_l1": 0.41943246126174927,
              "kd_world_l1": 0.44988274574279785,
              "tokens": 1008,
              "total": 1.7177886962890625,
              "training": false,
              "world_l1": 0.4313208758831024
            },
            {
              "action_l1": 0.424506813287735,
              "kd_act_l1": 0.42513173818588257,
              "kd_world_l1": 0.4522729814052582,
              "tokens": 1008,
              "total": 1.7402957677841187,
              "training": false,
              "world_l1": 0.43838414549827576
            },
            {
              "action_l1": 0.40183278918266296,
              "kd_act_l1": 0.4023498594760895,
              "kd_world_l1": 0.43660929799079895,
              "tokens": 1008,
              "total": 1.6631072759628296,
              "training": false,
              "world_l1": 0.4223153591156006
            },
            {
              "action_l1": 0.3707974851131439,
              "kd_act_l1": 0.37414371967315674,
              "kd_world_l1": 0.41767385601997375,
              "tokens": 1008,
              "total": 1.5646390914916992,
              "training": false,
              "world_l1": 0.4020240902900696
            },
            {
              "action_l1": 0.3399403989315033,
              "kd_act_l1": 0.34012624621391296,
              "kd_world_l1": 0.41571468114852905,
              "tokens": 1008,
              "total": 1.497962236404419,
              "training": false,
              "world_l1": 0.4021809697151184
            },
            {
              "action_l1": 0.3385380208492279,
              "kd_act_l1": 0.34003308415412903,
              "kd_world_l1": 0.40478599071502686,
              "tokens": 1008,
              "total": 1.4727782011032104,
              "training": false,
              "world_l1": 0.38942113518714905
            },
            {
              "action_l1": 0.32390302419662476,
              "kd_act_l1": 0.32411065697669983,
              "kd_world_l1": 0.3997601270675659,
              "tokens": 1008,
              "total": 1.4322162866592407,
              "training": false,
              "world_l1": 0.38444244861602783
            },
            {
              "action_l1": 0.3315664529800415,
              "kd_act_l1": 0.33123642206192017,
              "kd_world_l1": 0.3890240788459778,
              "tokens": 1008,
              "total": 1.4264471530914307,
              "training": false,
              "world_l1": 0.3746202290058136
            },
            {
              "action_l1": 0.36460497975349426,
              "kd_act_l1": 0.3663170635700226,
              "kd_world_l1": 0.39117610454559326,
              "tokens": 1008,
              "total": 1.49370539188385,
              "training": false,
              "world_l1": 0.3716072738170624
            },
            {
              "action_l1": 0.3974769413471222,
              "kd_act_l1": 0.39858517050743103,
              "kd_world_l1": 0.42802563309669495,
              "tokens": 1008,
              "total": 1.6283586025238037,
              "training": false,
              "world_l1": 0.40427085757255554
            },
            {
              "action_l1": 0.4150307774543762,
              "kd_act_l1": 0.41725584864616394,
              "kd_world_l1": 0.43079522252082825,
              "tokens": 1008,
              "total": 1.6710467338562012,
              "training": false,
              "world_l1": 0.40796494483947754
            },
            {
              "action_l1": 0.43495145440101624,
              "kd_act_l1": 0.4318167269229889,
              "kd_world_l1": 0.4344068169593811,
              "tokens": 1008,
              "total": 1.7135083675384521,
              "training": false,
              "world_l1": 0.4123333692550659
            },
            {
              "action_l1": 0.4087255299091339,
              "kd_act_l1": 0.4050823748111725,
              "kd_world_l1": 0.44554996490478516,
              "tokens": 1008,
              "total": 1.6799858808517456,
              "training": false,
              "world_l1": 0.42062798142433167
            },
            {
              "action_l1": 0.3584373891353607,
              "kd_act_l1": 0.3577440083026886,
              "kd_world_l1": 0.45307978987693787,
              "tokens": 1008,
              "total": 1.5933570861816406,
              "training": false,
              "world_l1": 0.42409583926200867
            },
            {
              "action_l1": 0.3416687548160553,
              "kd_act_l1": 0.3431456387042999,
              "kd_world_l1": 0.4553847014904022,
              "tokens": 1008,
              "total": 1.5687137842178345,
              "training": false,
              "world_l1": 0.42851465940475464
            },
            {
              "action_l1": 0.32863420248031616,
              "kd_act_l1": 0.331256240606308,
              "kd_world_l1": 0.43829041719436646,
              "tokens": 1008,
              "total": 1.5079615116119385,
              "training": false,
              "world_l1": 0.4097805321216583
            },
            {
              "action_l1": 0.3312774896621704,
              "kd_act_l1": 0.33153897523880005,
              "kd_world_l1": 0.4023881256580353,
              "tokens": 1008,
              "total": 1.4477360248565674,
              "training": false,
              "world_l1": 0.3825315237045288
            },
            {
              "action_l1": 0.32719627022743225,
              "kd_act_l1": 0.3269890546798706,
              "kd_world_l1": 0.42057397961616516,
              "tokens": 1008,
              "total": 1.4714953899383545,
              "training": false,
              "world_l1": 0.3967360556125641
            },
            {
              "action_l1": 0.3070727288722992,
              "kd_act_l1": 0.30750876665115356,
              "kd_world_l1": 0.43809014558792114,
              "tokens": 1008,
              "total": 1.465876579284668,
              "training": false,
              "world_l1": 0.41320502758026123
            },
            {
              "action_l1": 0.2985645830631256,
              "kd_act_l1": 0.2991654872894287,
              "kd_world_l1": 0.44430363178253174,
              "tokens": 1008,
              "total": 1.4586350917816162,
              "training": false,
              "world_l1": 0.41660135984420776
            },
            {
              "action_l1": 0.28084510564804077,
              "kd_act_l1": 0.2822951674461365,
              "kd_world_l1": 0.43432119488716125,
              "tokens": 1008,
              "total": 1.4027193784713745,
              "training": false,
              "world_l1": 0.4052579402923584
            },
            {
              "action_l1": 0.28235265612602234,
              "kd_act_l1": 0.2848112881183624,
              "kd_world_l1": 0.41572368144989014,
              "tokens": 1008,
              "total": 1.3721219301223755,
              "training": false,
              "world_l1": 0.389234334230423
            },
            {
              "action_l1": 0.2760469913482666,
              "kd_act_l1": 0.27534759044647217,
              "kd_world_l1": 0.40220844745635986,
              "tokens": 1008,
              "total": 1.3328152894973755,
              "training": false,
              "world_l1": 0.37921226024627686
            },
            {
              "action_l1": 0.2717566192150116,
              "kd_act_l1": 0.27266091108322144,
              "kd_world_l1": 0.3941681385040283,
              "tokens": 1008,
              "total": 1.3113186359405518,
              "training": false,
              "world_l1": 0.37273305654525757
            }
          ]
        }
      },
      "44": {
        "dataset": {
          "files": {
            "success_only/dataset_statistics.json": "5b119a98ad7824507ddff3c6c7507ca244261ee416dcfa623876702160c580d3",
            "success_only/libero_goal_regen/put_the_cream_cheese_in_the_bowl_demo.hdf5": "533472726b4cf89b2000af1bc275f26fb6cdcd2a5706fbd65cbe019f58180ebb"
          },
          "public_id": "nvidia/LIBERO-Cosmos-Policy",
          "revision": "b463cbd5d114909e4daea65eb03bed9787290042"
        },
        "files": {
          "best.pt": "57413ea06d58c434722dd182771f698c839b2b52d114824662c57f310831962b"
        },
        "implementation_sha256": {
          "lewam/external.py": "0e0a9dbaa54d897f01f6d6f2d13584ec26c1dcf84f4e541685bbc04791056b56",
          "smolwam/algorithm.py": "ee5563a4b6e6da35b066536e31fc63bfda9a75b2ef98b40ecae06aed9220266b",
          "smolwam/training.py": "7826d69e86534d51239975591d0d43b41d686ad8d7f9dc65c554a6e7977db718",
          "smolwam/worker.py": "3485d8bafa5b3fa548ae2454677f490cf3f8791ba310d2d14c48d69ca0f7fd8c"
        },
        "kind": "local-trained-candidate",
        "metrics": {
          "best_validation_action_l1": 0.32548515560726327,
          "compact_layout_updates": 6,
          "nonzero_gradient_updates": 8,
          "nonzero_parameter_updates": 7,
          "optimizer_updates": 8,
          "parameter_sample_delta_l2": 0.010460627883859331,
          "real_teacher_target_rows": 202,
          "teacher_layout_updates": 2,
          "teacher_vs_demo_action_l1": 0.00901833331064865,
          "train_mean_action_l1": 0.3554840236902237,
          "train_mean_kd_act_l1": 0.35581374540925026,
          "train_mean_kd_world_l1": 0.5038045942783356,
          "train_mean_world_l1": 0.48335758969187737,
          "updated_parameter_tensors": 340
        },
        "paper": "smolwam",
        "seed": 44,
        "selection": "validation only",
        "source_revision": "dde1e5bfe35c439499343c6d70e9cd32c96d0b36",
        "training_evidence": {
          "gradients": [
            {
              "norm": 0.9999998346739131,
              "parameter_sample_delta_l2": 0.0,
              "tokens": 1764
            },
            {
              "norm": 0.9999999333547278,
              "parameter_sample_delta_l2": 0.002939385835905803,
              "tokens": 1764
            },
            {
              "norm": 0.9999999185738613,
              "parameter_sample_delta_l2": 0.003113070060335804,
              "tokens": 1008
            },
            {
              "norm": 0.9999998191080456,
              "parameter_sample_delta_l2": 0.0027134804797407553,
              "tokens": 1008
            },
            {
              "norm": 0.9999999062067648,
              "parameter_sample_delta_l2": 0.0018209307495970007,
              "tokens": 1008
            },
            {
              "norm": 0.9999998869525483,
              "parameter_sample_delta_l2": 0.0011053272499433992,
              "tokens": 1008
            },
            {
              "norm": 0.99999988295446,
              "parameter_sample_delta_l2": 0.000591735530063537,
              "tokens": 1008
            },
            {
              "norm": 0.9999999346557154,
              "parameter_sample_delta_l2": 0.0002654258502901398,
              "tokens": 1008
            }
          ],
          "losses": [
            {
              "action_l1": 0.30763182044029236,
              "fut_proprio_l1": 0.3952917456626892,
              "kd_act_l1": 0.30983051657676697,
              "kd_world_l1": 0.6297882795333862,
              "tokens": 1764,
              "total": 1.988996982574463,
              "training": true,
              "value_l1": 0.9158770442008972,
              "world_l1": 0.6106294989585876
            },
            {
              "action_l1": 0.39141806960105896,
              "fut_proprio_l1": 0.44669094681739807,
              "kd_act_l1": 0.3934577703475952,
              "kd_world_l1": 0.6076274514198303,
              "tokens": 1764,
              "total": 2.044814109802246,
              "training": false,
              "value_l1": 0.08867886662483215,
              "world_l1": 0.598773717880249
            },
            {
              "action_l1": 0.42650124430656433,
              "fut_proprio_l1": 0.45907360315322876,
              "kd_act_l1": 0.4271330237388611,
              "kd_world_l1": 0.6075862646102905,
              "tokens": 1764,
              "total": 2.1136951446533203,
              "training": false,
              "value_l1": 0.05168197676539421,
              "world_l1": 0.6013988256454468
            },
            {
              "action_l1": 0.4258672893047333,
              "fut_proprio_l1": 0.4609334170818329,
              "kd_act_l1": 0.4277407228946686,
              "kd_world_l1": 0.6105762124061584,
              "tokens": 1764,
              "total": 2.1146740913391113,
              "training": false,
              "value_l1": 0.014088824391365051,
              "world_l1": 0.60298752784729
            },
            {
              "action_l1": 0.41400960087776184,
              "fut_proprio_l1": 0.4565652906894684,
              "kd_act_l1": 0.41325637698173523,
              "kd_world_l1": 0.6091108322143555,
              "tokens": 1764,
              "total": 2.0853400230407715,
              "training": false,
              "value_l1": 0.025265390053391457,
              "world_l1": 0.6007802486419678
            },
            {
              "action_l1": 0.41189903020858765,
              "fut_proprio_l1": 0.44612419605255127,
              "kd_act_l1": 0.4101065695285797,
              "kd_world_l1": 0.6134804487228394,
              "tokens": 1764,
              "total": 2.0925498008728027,
              "training": false,
              "value_l1": 0.06583280861377716,
              "world_l1": 0.6058680415153503
            },
            {
              "action_l1": 0.3952547013759613,
              "fut_proprio_l1": 0.3694957196712494,
              "kd_act_l1": 0.3953129053115845,
              "kd_world_l1": 0.6217291355133057,
              "tokens": 1764,
              "total": 2.074740409851074,
              "training": false,
              "value_l1": 0.10833770781755447,
              "world_l1": 0.6146602630615234
            },
            {
              "action_l1": 0.3617003560066223,
              "fut_proprio_l1": 0.26291608810424805,
              "kd_act_l1": 0.35727256536483765,
              "kd_world_l1": 0.6214956045150757,
              "tokens": 1764,
              "total": 1.9957536458969116,
              "training": false,
              "value_l1": 0.15529613196849823,
              "world_l1": 0.6134637594223022
            },
            {
              "action_l1": 0.3315276503562927,
              "fut_proprio_l1": 0.2634682357311249,
              "kd_act_l1": 0.3300858438014984,
              "kd_world_l1": 0.615009605884552,
              "tokens": 1764,
              "total": 1.9336118698120117,
              "training": false,
              "value_l1": 0.20407600700855255,
              "world_l1": 0.610234260559082
            },
            {
              "action_l1": 0.32318687438964844,
              "fut_proprio_l1": 0.26716145873069763,
              "kd_act_l1": 0.3227364420890808,
              "kd_world_l1": 0.6108111143112183,
              "tokens": 1764,
              "total": 1.9113901853561401,
              "training": false,
              "value_l1": 0.2557881474494934,
              "world_l1": 0.6023607850074768
            },
            {
              "action_l1": 0.32693809270858765,
              "fut_proprio_l1": 0.273433119058609,
              "kd_act_l1": 0.3263781666755676,
              "kd_world_l1": 0.6087443828582764,
              "tokens": 1764,
              "total": 1.920922040939331,
              "training": false,
              "value_l1": 0.3235574960708618,
              "world_l1": 0.5991623997688293
            },
            {
              "action_l1": 0.34969407320022583,
              "fut_proprio_l1": 0.2643270492553711,
              "kd_act_l1": 0.34708577394485474,
              "kd_world_l1": 0.6182454228401184,
              "tokens": 1764,
              "total": 1.984438419342041,
              "training": false,
              "value_l1": 0.3686034679412842,
              "world_l1": 0.6061201691627502
            },
            {
              "action_l1": 0.3642452359199524,
              "fut_proprio_l1": 0.26101812720298767,
              "kd_act_l1": 0.36411669850349426,
              "kd_world_l1": 0.6262494325637817,
              "tokens": 1764,
              "total": 2.038536548614502,
              "training": false,
              "value_l1": 0.42592620849609375,
              "world_l1": 0.6152306795120239
            },
            {
              "action_l1": 0.3571356236934662,
              "fut_proprio_l1": 0.27001655101776123,
              "kd_act_l1": 0.3554563820362091,
              "kd_world_l1": 0.6359187960624695,
              "tokens": 1764,
              "total": 2.0474419593811035,
              "training": false,
              "value_l1": 0.4854423999786377,
              "world_l1": 0.6233852505683899
            },
            {
              "action_l1": 0.3431357443332672,
              "fut_proprio_l1": 0.267912358045578,
              "kd_act_l1": 0.3427668809890747,
              "kd_world_l1": 0.6469278335571289,
              "tokens": 1764,
              "total": 2.0458054542541504,
              "training": false,
              "value_l1": 0.5465582013130188,
              "world_l1": 0.6315280795097351
            },
            {
              "action_l1": 0.34901490807533264,
              "fut_proprio_l1": 0.2670552432537079,
              "kd_act_l1": 0.3479670584201813,
              "kd_world_l1": 0.6454117894172668,
              "tokens": 1764,
              "total": 2.060603380203247,
              "training": false,
              "value_l1": 0.6101592183113098,
              "world_l1": 0.6304881572723389
            },
            {
              "action_l1": 0.3343079686164856,
              "fut_proprio_l1": 0.2676023840904236,
              "kd_act_l1": 0.3340699076652527,
              "kd_world_l1": 0.6431310772895813,
              "tokens": 1764,
              "total": 2.035539388656616,
              "training": false,
              "value_l1": 0.677000880241394,
              "world_l1": 0.6295702457427979
            },
            {
              "action_l1": 0.3135788142681122,
              "fut_proprio_l1": 0.29242435097694397,
              "kd_act_l1": 0.3102909326553345,
              "kd_world_l1": 0.637334942817688,
              "tokens": 1764,
              "total": 1.9926398992538452,
              "training": false,
              "value_l1": 0.7458207607269287,
              "world_l1": 0.6276107430458069
            },
            {
              "action_l1": 0.290513277053833,
              "fut_proprio_l1": 0.41953912377357483,
              "kd_act_l1": 0.289644718170166,
              "kd_world_l1": 0.6339718699455261,
              "tokens": 1764,
              "total": 1.9589989185333252,
              "training": false,
              "value_l1": 0.8177931308746338,
              "world_l1": 0.6211357116699219
            },
            {
              "action_l1": 0.2657024562358856,
              "fut_proprio_l1": 0.44570010900497437,
              "kd_act_l1": 0.26494818925857544,
              "kd_world_l1": 0.6325541138648987,
              "tokens": 1764,
              "total": 1.9141035079956055,
              "training": false,
              "value_l1": 0.8934618234634399,
              "world_l1": 0.6169825196266174
            },
            {
              "action_l1": 0.2598583698272705,
              "fut_proprio_l1": 0.4485892653465271,
              "kd_act_l1": 0.2606256604194641,
              "kd_world_l1": 0.6335963010787964,
              "tokens": 1764,
              "total": 1.9111138582229614,
              "training": false,
              "value_l1": 0.9727232456207275,
              "world_l1": 0.6149021983146667
            },
            {
              "action_l1": 0.24454042315483093,
              "fut_proprio_l1": 0.44854703545570374,
              "kd_act_l1": 0.24352586269378662,
              "kd_world_l1": 0.6318553686141968,
              "tokens": 1764,
              "total": 1.875333309173584,
              "training": false,
              "value_l1": 0.9726700186729431,
              "world_l1": 0.613290011882782
            },
            {
              "action_l1": 0.22447839379310608,
              "fut_proprio_l1": 0.4491453170776367,
              "kd_act_l1": 0.22484524548053741,
              "kd_world_l1": 0.6235828399658203,
              "tokens": 1764,
              "total": 1.8238062858581543,
              "training": false,
              "value_l1": 0.9805347919464111,
              "world_l1": 0.6079318523406982
            },
            {
              "action_l1": 0.2172311693429947,
              "fut_proprio_l1": 0.44772979617118835,
              "kd_act_l1": 0.2181435078382492,
              "kd_world_l1": 0.6203734874725342,
              "tokens": 1764,
              "total": 1.8053662776947021,
              "training": false,
              "value_l1": 0.9735155701637268,
              "world_l1": 0.6074936389923096
            },
            {
              "action_l1": 0.21237991750240326,
              "fut_proprio_l1": 0.44776642322540283,
              "kd_act_l1": 0.21397727727890015,
              "kd_world_l1": 0.6180364489555359,
              "tokens": 1764,
              "total": 1.7940301895141602,
              "training": false,
              "value_l1": 0.9739125370979309,
              "world_l1": 0.6074685454368591
            },
            {
              "action_l1": 0.32375478744506836,
              "fut_proprio_l1": 0.2554491460323334,
              "kd_act_l1": 0.32161960005760193,
              "kd_world_l1": 0.611626148223877,
              "tokens": 1764,
              "total": 1.9231358766555786,
              "training": true,
              "value_l1": 0.3791153132915497,
              "world_l1": 0.6026788353919983
            },
            {
              "action_l1": 0.463977575302124,
              "fut_proprio_l1": 0.4723057150840759,
              "kd_act_l1": 0.4647780954837799,
              "kd_world_l1": 0.5538088083267212,
              "tokens": 1764,
              "total": 2.070857286453247,
              "training": false,
              "value_l1": 0.06441798061132431,
              "world_l1": 0.5346204042434692
            },
            {
              "action_l1": 0.4870861768722534,
              "fut_proprio_l1": 0.48038461804389954,
              "kd_act_l1": 0.4882398545742035,
              "kd_world_l1": 0.5536026954650879,
              "tokens": 1764,
              "total": 2.116542100906372,
              "training": false,
              "value_l1": 0.031216125935316086,
              "world_l1": 0.5364532470703125
            },
            {
              "action_l1": 0.480061411857605,
              "fut_proprio_l1": 0.4784534275531769,
              "kd_act_l1": 0.4813409447669983,
              "kd_world_l1": 0.5504257678985596,
              "tokens": 1764,
              "total": 2.0906078815460205,
              "training": false,
              "value_l1": 0.0030738445930182934,
              "world_l1": 0.5306268930435181
            },
            {
              "action_l1": 0.46813225746154785,
              "fut_proprio_l1": 0.4718486964702606,
              "kd_act_l1": 0.4682190418243408,
              "kd_world_l1": 0.5414850115776062,
              "tokens": 1764,
              "total": 2.049959182739258,
              "training": false,
              "value_l1": 0.039207249879837036,
              "world_l1": 0.52101731300354
            },
            {
              "action_l1": 0.46400412917137146,
              "fut_proprio_l1": 0.4593031108379364,
              "kd_act_l1": 0.4629393517971039,
              "kd_world_l1": 0.5422579646110535,
              "tokens": 1764,
              "total": 2.043327569961548,
              "training": false,
              "value_l1": 0.07498615980148315,
              "world_l1": 0.5206971168518066
            },
            {
              "action_l1": 0.4296656548976898,
              "fut_proprio_l1": 0.38147100806236267,
              "kd_act_l1": 0.43021345138549805,
              "kd_world_l1": 0.5423473119735718,
              "tokens": 1764,
              "total": 1.9713174104690552,
              "training": false,
              "value_l1": 0.11564384400844574,
              "world_l1": 0.5193795561790466
            },
            {
              "action_l1": 0.413486123085022,
              "fut_proprio_l1": 0.27732616662979126,
              "kd_act_l1": 0.41273826360702515,
              "kd_world_l1": 0.5355970859527588,
              "tokens": 1764,
              "total": 1.9174811840057373,
              "training": false,
              "value_l1": 0.16140484809875488,
              "world_l1": 0.5117866396903992
            },
            {
              "action_l1": 0.3683909773826599,
              "fut_proprio_l1": 0.28131210803985596,
              "kd_act_l1": 0.3669049143791199,
              "kd_world_l1": 0.5276549458503723,
              "tokens": 1764,
              "total": 1.818314552307129,
              "training": false,
              "value_l1": 0.2078654170036316,
              "world_l1": 0.5064460039138794
            },
            {
              "action_l1": 0.38583704829216003,
              "fut_proprio_l1": 0.2868881821632385,
              "kd_act_l1": 0.38603100180625916,
              "kd_world_l1": 0.5287235975265503,
              "tokens": 1764,
              "total": 1.8601304292678833,
              "training": false,
              "value_l1": 0.25792816281318665,
              "world_l1": 0.505057156085968
            },
            {
              "action_l1": 0.39276763796806335,
              "fut_proprio_l1": 0.27954599261283875,
              "kd_act_l1": 0.39176785945892334,
              "kd_world_l1": 0.5332693457603455,
              "tokens": 1764,
              "total": 1.8851935863494873,
              "training": false,
              "value_l1": 0.3109622001647949,
              "world_l1": 0.5083378553390503
            },
            {
              "action_l1": 0.4146009087562561,
              "fut_proprio_l1": 0.2603849172592163,
              "kd_act_l1": 0.4159685969352722,
              "kd_world_l1": 0.5347550511360168,
              "tokens": 1764,
              "total": 1.9352333545684814,
              "training": false,
              "value_l1": 0.35140809416770935,
              "world_l1": 0.5087296366691589
            },
            {
              "action_l1": 0.43404096364974976,
              "fut_proprio_l1": 0.25555330514907837,
              "kd_act_l1": 0.4358121454715729,
              "kd_world_l1": 0.5418776273727417,
              "tokens": 1764,
              "total": 1.9952462911605835,
              "training": false,
              "value_l1": 0.4079061448574066,
              "world_l1": 0.5171696543693542
            },
            {
              "action_l1": 0.44351962208747864,
              "fut_proprio_l1": 0.2645677626132965,
              "kd_act_l1": 0.4407723844051361,
              "kd_world_l1": 0.5566720366477966,
              "tokens": 1764,
              "total": 2.045196533203125,
              "training": false,
              "value_l1": 0.4669714868068695,
              "world_l1": 0.5310783982276917
            },
            {
              "action_l1": 0.41736966371536255,
              "fut_proprio_l1": 0.26253432035446167,
              "kd_act_l1": 0.4162125885486603,
              "kd_world_l1": 0.5734620690345764,
              "tokens": 1764,
              "total": 2.0308916568756104,
              "training": false,
              "value_l1": 0.5283251404762268,
              "world_l1": 0.5447614789009094
            },
            {
              "action_l1": 0.40773433446884155,
              "fut_proprio_l1": 0.2621685564517975,
              "kd_act_l1": 0.40702834725379944,
              "kd_world_l1": 0.5747429132461548,
              "tokens": 1764,
              "total": 2.022998332977295,
              "training": false,
              "value_l1": 0.5953150987625122,
              "world_l1": 0.5477444529533386
            },
            {
              "action_l1": 0.36982524394989014,
              "fut_proprio_l1": 0.26327547430992126,
              "kd_act_l1": 0.3728162944316864,
              "kd_world_l1": 0.567749559879303,
              "tokens": 1764,
              "total": 1.9456803798675537,
              "training": false,
              "value_l1": 0.6647528409957886,
              "world_l1": 0.542486310005188
            },
            {
              "action_l1": 0.3569642901420593,
              "fut_proprio_l1": 0.2888287901878357,
              "kd_act_l1": 0.35641446709632874,
              "kd_world_l1": 0.558073878288269,
              "tokens": 1764,
              "total": 1.9112752676010132,
              "training": false,
              "value_l1": 0.7391040921211243,
              "world_l1": 0.5370293259620667
            },
            {
              "action_l1": 0.338780015707016,
              "fut_proprio_l1": 0.41640540957450867,
              "kd_act_l1": 0.34032079577445984,
              "kd_world_l1": 0.5571874976158142,
              "tokens": 1764,
              "total": 1.892399787902832,
              "training": false,
              "value_l1": 0.8155279755592346,
              "world_l1": 0.5329180955886841
            },
            {
              "action_l1": 0.3353649973869324,
              "fut_proprio_l1": 0.44239580631256104,
              "kd_act_l1": 0.33326029777526855,
              "kd_world_l1": 0.5593251585960388,
              "tokens": 1764,
              "total": 1.8953711986541748,
              "training": false,
              "value_l1": 0.8908377885818481,
              "world_l1": 0.5340973734855652
            },
            {
              "action_l1": 0.3360331356525421,
              "fut_proprio_l1": 0.4449726343154907,
              "kd_act_l1": 0.3363538682460785,
              "kd_world_l1": 0.5631827116012573,
              "tokens": 1764,
              "total": 1.9115501642227173,
              "training": false,
              "value_l1": 0.9681169390678406,
              "world_l1": 0.5346714854240417
            },
            {
              "action_l1": 0.3258689045906067,
              "fut_proprio_l1": 0.44468456506729126,
              "kd_act_l1": 0.32542943954467773,
              "kd_world_l1": 0.5609017610549927,
              "tokens": 1764,
              "total": 1.8849421739578247,
              "training": false,
              "value_l1": 0.965696394443512,
              "world_l1": 0.5317038893699646
            },
            {
              "action_l1": 0.3300437927246094,
              "fut_proprio_l1": 0.44732099771499634,
              "kd_act_l1": 0.3301687240600586,
              "kd_world_l1": 0.5600795745849609,
              "tokens": 1764,
              "total": 1.8966630697250366,
              "training": false,
              "value_l1": 0.9832178354263306,
              "world_l1": 0.5333171486854553
            },
            {
              "action_l1": 0.3269713819026947,
              "fut_proprio_l1": 0.44829151034355164,
              "kd_act_l1": 0.3259616792201996,
              "kd_world_l1": 0.5581383109092712,
              "tokens": 1764,
              "total": 1.888871669769287,
              "training": false,
              "value_l1": 0.9866300225257874,
              "world_l1": 0.5343081951141357
            },
            {
              "action_l1": 0.32256433367729187,
              "fut_proprio_l1": 0.44829410314559937,
              "kd_act_l1": 0.3230336904525757,
              "kd_world_l1": 0.5567790865898132,
              "tokens": 1764,
              "total": 1.8805279731750488,
              "training": false,
              "value_l1": 0.9865912199020386,
              "world_l1": 0.5346624255180359
            },
            {
              "action_l1": 0.43546250462532043,
              "kd_act_l1": 0.4371702969074249,
              "kd_world_l1": 0.5161733031272888,
              "tokens": 1008,
              "total": 1.8856136798858643,
              "training": true,
              "world_l1": 0.49680760502815247
            },
            {
              "action_l1": 0.4425010681152344,
              "kd_act_l1": 0.44481366872787476,
              "kd_world_l1": 0.4956793487071991,
              "tokens": 1008,
              "total": 1.8536674976348877,
              "training": false,
              "world_l1": 0.4706732928752899
            },
            {
              "action_l1": 0.4502011239528656,
              "kd_act_l1": 0.4513905644416809,
              "kd_world_l1": 0.493939608335495,
              "tokens": 1008,
              "total": 1.8669710159301758,
              "training": false,
              "world_l1": 0.47143977880477905
            },
            {
              "action_l1": 0.4254806637763977,
              "kd_act_l1": 0.4270149767398834,
              "kd_world_l1": 0.4850292205810547,
              "tokens": 1008,
              "total": 1.798201322555542,
              "training": false,
              "world_l1": 0.4606764614582062
            },
            {
              "action_l1": 0.3917892277240753,
              "kd_act_l1": 0.3945528566837311,
              "kd_world_l1": 0.47736096382141113,
              "tokens": 1008,
              "total": 1.7157483100891113,
              "training": false,
              "world_l1": 0.4520453214645386
            },
            {
              "action_l1": 0.36563146114349365,
              "kd_act_l1": 0.36641520261764526,
              "kd_world_l1": 0.47962647676467896,
              "tokens": 1008,
              "total": 1.6676383018493652,
              "training": false,
              "world_l1": 0.45596519112586975
            },
            {
              "action_l1": 0.3457332253456116,
              "kd_act_l1": 0.3461523652076721,
              "kd_world_l1": 0.4685325622558594,
              "tokens": 1008,
              "total": 1.606806755065918,
              "training": false,
              "world_l1": 0.4463886320590973
            },
            {
              "action_l1": 0.33043718338012695,
              "kd_act_l1": 0.33090463280677795,
              "kd_world_l1": 0.464213490486145,
              "tokens": 1008,
              "total": 1.5672115087509155,
              "training": false,
              "world_l1": 0.441656231880188
            },
            {
              "action_l1": 0.3275972008705139,
              "kd_act_l1": 0.3267400860786438,
              "kd_world_l1": 0.45974379777908325,
              "tokens": 1008,
              "total": 1.5515470504760742,
              "training": false,
              "world_l1": 0.4374661147594452
            },
            {
              "action_l1": 0.36574187874794006,
              "kd_act_l1": 0.3661436140537262,
              "kd_world_l1": 0.47524479031562805,
              "tokens": 1008,
              "total": 1.653005599975586,
              "training": false,
              "world_l1": 0.4458753168582916
            },
            {
              "action_l1": 0.39502832293510437,
              "kd_act_l1": 0.3985937535762787,
              "kd_world_l1": 0.5034642219543457,
              "tokens": 1008,
              "total": 1.7662054300308228,
              "training": false,
              "world_l1": 0.469119131565094
            },
            {
              "action_l1": 0.41935575008392334,
              "kd_act_l1": 0.4204561412334442,
              "kd_world_l1": 0.5107346177101135,
              "tokens": 1008,
              "total": 1.8269429206848145,
              "training": false,
              "world_l1": 0.47639644145965576
            },
            {
              "action_l1": 0.43271735310554504,
              "kd_act_l1": 0.4305809736251831,
              "kd_world_l1": 0.5157098174095154,
              "tokens": 1008,
              "total": 1.8609113693237305,
              "training": false,
              "world_l1": 0.48190322518348694
            },
            {
              "action_l1": 0.4180162250995636,
              "kd_act_l1": 0.414883017539978,
              "kd_world_l1": 0.5221754312515259,
              "tokens": 1008,
              "total": 1.841880440711975,
              "training": false,
              "world_l1": 0.48680579662323
            },
            {
              "action_l1": 0.38028484582901,
              "kd_act_l1": 0.3803759515285492,
              "kd_world_l1": 0.5298212170600891,
              "tokens": 1008,
              "total": 1.7824273109436035,
              "training": false,
              "world_l1": 0.4919452965259552
            },
            {
              "action_l1": 0.36388346552848816,
              "kd_act_l1": 0.3645499348640442,
              "kd_world_l1": 0.5292242169380188,
              "tokens": 1008,
              "total": 1.7521350383758545,
              "training": false,
              "world_l1": 0.4944775104522705
            },
            {
              "action_l1": 0.3397717773914337,
              "kd_act_l1": 0.3420273959636688,
              "kd_world_l1": 0.5211676359176636,
              "tokens": 1008,
              "total": 1.6891536712646484,
              "training": false,
              "world_l1": 0.48618680238723755
            },
            {
              "action_l1": 0.33628860116004944,
              "kd_act_l1": 0.3370138108730316,
              "kd_world_l1": 0.5023852586746216,
              "tokens": 1008,
              "total": 1.648862361907959,
              "training": false,
              "world_l1": 0.47317466139793396
            },
            {
              "action_l1": 0.3290085792541504,
              "kd_act_l1": 0.32873913645744324,
              "kd_world_l1": 0.5089390873908997,
              "tokens": 1008,
              "total": 1.6437268257141113,
              "training": false,
              "world_l1": 0.47703996300697327
            },
            {
              "action_l1": 0.32533639669418335,
              "kd_act_l1": 0.32494446635246277,
              "kd_world_l1": 0.514381468296051,
              "tokens": 1008,
              "total": 1.6458549499511719,
              "training": false,
              "world_l1": 0.4811926484107971
            },
            {
              "action_l1": 0.3165811598300934,
              "kd_act_l1": 0.31659451127052307,
              "kd_world_l1": 0.5208339095115662,
              "tokens": 1008,
              "total": 1.6390807628631592,
              "training": false,
              "world_l1": 0.4850711226463318
            },
            {
              "action_l1": 0.29419609904289246,
              "kd_act_l1": 0.29446133971214294,
              "kd_world_l1": 0.5203481912612915,
              "tokens": 1008,
              "total": 1.5930602550506592,
              "training": false,
              "world_l1": 0.4840545952320099
            },
            {
              "action_l1": 0.29181379079818726,
              "kd_act_l1": 0.2934204638004303,
              "kd_world_l1": 0.5150254368782043,
              "tokens": 1008,
              "total": 1.581580400466919,
              "training": false,
              "world_l1": 0.4813208281993866
            },
            {
              "action_l1": 0.28496137261390686,
              "kd_act_l1": 0.28364256024360657,
              "kd_world_l1": 0.5115261673927307,
              "tokens": 1008,
              "total": 1.5602796077728271,
              "training": false,
              "world_l1": 0.48014962673187256
            },
            {
              "action_l1": 0.2808689475059509,
              "kd_act_l1": 0.28162509202957153,
              "kd_world_l1": 0.5102952718734741,
              "tokens": 1008,
              "total": 1.552120327949524,
              "training": false,
              "world_l1": 0.47933098673820496
            },
            {
              "action_l1": 0.3811514973640442,
              "kd_act_l1": 0.3805444538593292,
              "kd_world_l1": 0.48916715383529663,
              "tokens": 1008,
              "total": 1.7165846824645996,
              "training": true,
              "world_l1": 0.46572166681289673
            },
            {
              "action_l1": 0.4083085358142853,
              "kd_act_l1": 0.4114132821559906,
              "kd_world_l1": 0.4783687889575958,
              "tokens": 1008,
              "total": 1.7537654638290405,
              "training": false,
              "world_l1": 0.4556749165058136
            },
            {
              "action_l1": 0.4423690140247345,
              "kd_act_l1": 0.4432574212551117,
              "kd_world_l1": 0.4770340323448181,
              "tokens": 1008,
              "total": 1.8196415901184082,
              "training": false,
              "world_l1": 0.4569810926914215
            },
            {
              "action_l1": 0.43876317143440247,
              "kd_act_l1": 0.4411245286464691,
              "kd_world_l1": 0.4694165587425232,
              "tokens": 1008,
              "total": 1.797550916671753,
              "training": false,
              "world_l1": 0.4482465386390686
            },
            {
              "action_l1": 0.4201526939868927,
              "kd_act_l1": 0.4203214943408966,
              "kd_world_l1": 0.46528539061546326,
              "tokens": 1008,
              "total": 1.748583197593689,
              "training": false,
              "world_l1": 0.442823588848114
            },
            {
              "action_l1": 0.4224693477153778,
              "kd_act_l1": 0.4214368760585785,
              "kd_world_l1": 0.4739132225513458,
              "tokens": 1008,
              "total": 1.7707128524780273,
              "training": false,
              "world_l1": 0.45289337635040283
            },
            {
              "action_l1": 0.4132019579410553,
              "kd_act_l1": 0.41299760341644287,
              "kd_world_l1": 0.46961110830307007,
              "tokens": 1008,
              "total": 1.7446396350860596,
              "training": false,
              "world_l1": 0.4488290548324585
            },
            {
              "action_l1": 0.3808382749557495,
              "kd_act_l1": 0.37720605731010437,
              "kd_world_l1": 0.46409866213798523,
              "tokens": 1008,
              "total": 1.6663957834243774,
              "training": false,
              "world_l1": 0.44425278902053833
            },
            {
              "action_l1": 0.35699406266212463,
              "kd_act_l1": 0.3559344708919525,
              "kd_world_l1": 0.45653343200683594,
              "tokens": 1008,
              "total": 1.606731653213501,
              "training": false,
              "world_l1": 0.4372696280479431
            },
            {
              "action_l1": 0.3451080620288849,
              "kd_act_l1": 0.3456130921840668,
              "kd_world_l1": 0.46564140915870667,
              "tokens": 1008,
              "total": 1.5957741737365723,
              "training": false,
              "world_l1": 0.4394116699695587
            },
            {
              "action_l1": 0.34772464632987976,
              "kd_act_l1": 0.3480435311794281,
              "kd_world_l1": 0.49126654863357544,
              "tokens": 1008,
              "total": 1.6473674774169922,
              "training": false,
              "world_l1": 0.4603327810764313
            },
            {
              "action_l1": 0.3659709692001343,
              "kd_act_l1": 0.3643120527267456,
              "kd_world_l1": 0.496987909078598,
              "tokens": 1008,
              "total": 1.6935431957244873,
              "training": false,
              "world_l1": 0.4662722647190094
            },
            {
              "action_l1": 0.38335856795310974,
              "kd_act_l1": 0.3834676146507263,
              "kd_world_l1": 0.5022395253181458,
              "tokens": 1008,
              "total": 1.7400217056274414,
              "training": false,
              "world_l1": 0.47095605731010437
            },
            {
              "action_l1": 0.3823959529399872,
              "kd_act_l1": 0.3798503279685974,
              "kd_world_l1": 0.5098178386688232,
              "tokens": 1008,
              "total": 1.7488343715667725,
              "training": false,
              "world_l1": 0.4767703413963318
            },
            {
              "action_l1": 0.3767700493335724,
              "kd_act_l1": 0.37656328082084656,
              "kd_world_l1": 0.5178152322769165,
              "tokens": 1008,
              "total": 1.7527433633804321,
              "training": false,
              "world_l1": 0.4815947711467743
            },
            {
              "action_l1": 0.37592756748199463,
              "kd_act_l1": 0.37466689944267273,
              "kd_world_l1": 0.5205858945846558,
              "tokens": 1008,
              "total": 1.7576639652252197,
              "training": false,
              "world_l1": 0.486483633518219
            },
            {
              "action_l1": 0.36411479115486145,
              "kd_act_l1": 0.36322537064552307,
              "kd_world_l1": 0.5116401314735413,
              "tokens": 1008,
              "total": 1.71756911277771,
              "training": false,
              "world_l1": 0.47858887910842896
            },
            {
              "action_l1": 0.3344298005104065,
              "kd_act_l1": 0.33081483840942383,
              "kd_world_l1": 0.48554906249046326,
              "tokens": 1008,
              "total": 1.6087816953659058,
              "training": false,
              "world_l1": 0.457987904548645
            },
            {
              "action_l1": 0.31444045901298523,
              "kd_act_l1": 0.31329452991485596,
              "kd_world_l1": 0.4929325580596924,
              "tokens": 1008,
              "total": 1.5843290090560913,
              "training": false,
              "world_l1": 0.46366143226623535
            },
            {
              "action_l1": 0.291194885969162,
              "kd_act_l1": 0.28812175989151,
              "kd_world_l1": 0.49885550141334534,
              "tokens": 1008,
              "total": 1.5458643436431885,
              "training": false,
              "world_l1": 0.46769222617149353
            },
            {
              "action_l1": 0.285086989402771,
              "kd_act_l1": 0.2863238751888275,
              "kd_world_l1": 0.5056195259094238,
              "tokens": 1008,
              "total": 1.54908287525177,
              "training": false,
              "world_l1": 0.4720524251461029
            },
            {
              "action_l1": 0.27101996541023254,
              "kd_act_l1": 0.2705775201320648,
              "kd_world_l1": 0.5055716037750244,
              "tokens": 1008,
              "total": 1.518375039100647,
              "training": false,
              "world_l1": 0.4712059795856476
            },
            {
              "action_l1": 0.246168315410614,
              "kd_act_l1": 0.24624653160572052,
              "kd_world_l1": 0.49858513474464417,
              "tokens": 1008,
              "total": 1.4574106931686401,
              "training": false,
              "world_l1": 0.466410756111145
            },
            {
              "action_l1": 0.2379438281059265,
              "kd_act_l1": 0.23826566338539124,
              "kd_world_l1": 0.4947369396686554,
              "tokens": 1008,
              "total": 1.4359676837921143,
              "training": false,
              "world_l1": 0.4650212526321411
            },
            {
              "action_l1": 0.23438474535942078,
              "kd_act_l1": 0.23571519553661346,
              "kd_world_l1": 0.49298763275146484,
              "tokens": 1008,
              "total": 1.4265592098236084,
              "training": false,
              "world_l1": 0.4634716510772705
            },
            {
              "action_l1": 0.3434238135814667,
              "kd_act_l1": 0.3425011932849884,
              "kd_world_l1": 0.4747660756111145,
              "tokens": 1008,
              "total": 1.60880446434021,
              "training": true,
              "world_l1": 0.4481133818626404
            },
            {
              "action_l1": 0.39259883761405945,
              "kd_act_l1": 0.3959309160709381,
              "kd_world_l1": 0.47369593381881714,
              "tokens": 1008,
              "total": 1.7192933559417725,
              "training": false,
              "world_l1": 0.45706766843795776
            },
            {
              "action_l1": 0.41444605588912964,
              "kd_act_l1": 0.4156719446182251,
              "kd_world_l1": 0.4732198119163513,
              "tokens": 1008,
              "total": 1.763805627822876,
              "training": false,
              "world_l1": 0.46046772599220276
            },
            {
              "action_l1": 0.40844932198524475,
              "kd_act_l1": 0.40955665707588196,
              "kd_world_l1": 0.46091803908348083,
              "tokens": 1008,
              "total": 1.7261725664138794,
              "training": false,
              "world_l1": 0.4472484886646271
            },
            {
              "action_l1": 0.3802315890789032,
              "kd_act_l1": 0.38197043538093567,
              "kd_world_l1": 0.4461856782436371,
              "tokens": 1008,
              "total": 1.6403136253356934,
              "training": false,
              "world_l1": 0.4319259524345398
            },
            {
              "action_l1": 0.36805862188339233,
              "kd_act_l1": 0.3672584891319275,
              "kd_world_l1": 0.4475059509277344,
              "tokens": 1008,
              "total": 1.6162474155426025,
              "training": false,
              "world_l1": 0.43342432379722595
            },
            {
              "action_l1": 0.36180832982063293,
              "kd_act_l1": 0.3618374764919281,
              "kd_world_l1": 0.4421718418598175,
              "tokens": 1008,
              "total": 1.591309905052185,
              "training": false,
              "world_l1": 0.4254922568798065
            },
            {
              "action_l1": 0.32706180214881897,
              "kd_act_l1": 0.32365065813064575,
              "kd_world_l1": 0.4372379183769226,
              "tokens": 1008,
              "total": 1.5092618465423584,
              "training": false,
              "world_l1": 0.4213114380836487
            },
            {
              "action_l1": 0.3180277943611145,
              "kd_act_l1": 0.3178110122680664,
              "kd_world_l1": 0.4290215075016022,
              "tokens": 1008,
              "total": 1.4790782928466797,
              "training": false,
              "world_l1": 0.4142180383205414
            },
            {
              "action_l1": 0.32780686020851135,
              "kd_act_l1": 0.32767096161842346,
              "kd_world_l1": 0.433137446641922,
              "tokens": 1008,
              "total": 1.5024374723434448,
              "training": false,
              "world_l1": 0.4138222336769104
            },
            {
              "action_l1": 0.3433600962162018,
              "kd_act_l1": 0.3442961871623993,
              "kd_world_l1": 0.45612096786499023,
              "tokens": 1008,
              "total": 1.5784348249435425,
              "training": false,
              "world_l1": 0.43465757369995117
            },
            {
              "action_l1": 0.36119353771209717,
              "kd_act_l1": 0.36163970828056335,
              "kd_world_l1": 0.4587782025337219,
              "tokens": 1008,
              "total": 1.6200602054595947,
              "training": false,
              "world_l1": 0.43844863772392273
            },
            {
              "action_l1": 0.37726277112960815,
              "kd_act_l1": 0.3748113512992859,
              "kd_world_l1": 0.4626477062702179,
              "tokens": 1008,
              "total": 1.657292127609253,
              "training": false,
              "world_l1": 0.442570298910141
            },
            {
              "action_l1": 0.3624676465988159,
              "kd_act_l1": 0.3600505590438843,
              "kd_world_l1": 0.4732046127319336,
              "tokens": 1008,
              "total": 1.646399736404419,
              "training": false,
              "world_l1": 0.45067697763442993
            },
            {
              "action_l1": 0.33898648619651794,
              "kd_act_l1": 0.3388161361217499,
              "kd_world_l1": 0.4844512343406677,
              "tokens": 1008,
              "total": 1.6200084686279297,
              "training": false,
              "world_l1": 0.45775458216667175
            },
            {
              "action_l1": 0.3396863639354706,
              "kd_act_l1": 0.3394930064678192,
              "kd_world_l1": 0.4868869185447693,
              "tokens": 1008,
              "total": 1.6276097297668457,
              "training": false,
              "world_l1": 0.46154335141181946
            },
            {
              "action_l1": 0.32727712392807007,
              "kd_act_l1": 0.32829558849334717,
              "kd_world_l1": 0.47382867336273193,
              "tokens": 1008,
              "total": 1.5793997049331665,
              "training": false,
              "world_l1": 0.44999828934669495
            },
            {
              "action_l1": 0.3119295835494995,
              "kd_act_l1": 0.30932992696762085,
              "kd_world_l1": 0.4504297971725464,
              "tokens": 1008,
              "total": 1.50421941280365,
              "training": false,
              "world_l1": 0.43253007531166077
            },
            {
              "action_l1": 0.2948766350746155,
              "kd_act_l1": 0.2931700646877289,
              "kd_world_l1": 0.4593638777732849,
              "tokens": 1008,
              "total": 1.4858729839324951,
              "training": false,
              "world_l1": 0.43846243619918823
            },
            {
              "action_l1": 0.2749967873096466,
              "kd_act_l1": 0.2747942805290222,
              "kd_world_l1": 0.4689640402793884,
              "tokens": 1008,
              "total": 1.4648784399032593,
              "training": false,
              "world_l1": 0.4461233615875244
            },
            {
              "action_l1": 0.26309219002723694,
              "kd_act_l1": 0.26372718811035156,
              "kd_world_l1": 0.47452327609062195,
              "tokens": 1008,
              "total": 1.4505003690719604,
              "training": false,
              "world_l1": 0.44915771484375
            },
            {
              "action_l1": 0.2425079643726349,
              "kd_act_l1": 0.24244670569896698,
              "kd_world_l1": 0.4693194031715393,
              "tokens": 1008,
              "total": 1.3974679708480835,
              "training": false,
              "world_l1": 0.44319385290145874
            },
            {
              "action_l1": 0.23092593252658844,
              "kd_act_l1": 0.23229268193244934,
              "kd_world_l1": 0.4600289762020111,
              "tokens": 1008,
              "total": 1.3594346046447754,
              "training": false,
              "world_l1": 0.4361869692802429
            },
            {
              "action_l1": 0.22435396909713745,
              "kd_act_l1": 0.22416871786117554,
              "kd_world_l1": 0.4537081718444824,
              "tokens": 1008,
              "total": 1.3350470066070557,
              "training": false,
              "world_l1": 0.43281620740890503
            },
            {
              "action_l1": 0.22023743391036987,
              "kd_act_l1": 0.2215736359357834,
              "kd_world_l1": 0.45066529512405396,
              "tokens": 1008,
              "total": 1.3231450319290161,
              "training": false,
              "world_l1": 0.4306686222553253
            },
            {
              "action_l1": 0.3300814628601074,
              "kd_act_l1": 0.3307766020298004,
              "kd_world_l1": 0.4360451102256775,
              "tokens": 1008,
              "total": 1.515843391418457,
              "training": true,
              "world_l1": 0.41894033551216125
            },
            {
              "action_l1": 0.4049188792705536,
              "kd_act_l1": 0.40832871198654175,
              "kd_world_l1": 0.4586108326911926,
              "tokens": 1008,
              "total": 1.7178807258605957,
              "training": false,
              "world_l1": 0.44602230191230774
            },
            {
              "action_l1": 0.4188797175884247,
              "kd_act_l1": 0.4200129806995392,
              "kd_world_l1": 0.46200814843177795,
              "tokens": 1008,
              "total": 1.7546316385269165,
              "training": false,
              "world_l1": 0.45373085141181946
            },
            {
              "action_l1": 0.4024093747138977,
              "kd_act_l1": 0.4031912684440613,
              "kd_world_l1": 0.4451262652873993,
              "tokens": 1008,
              "total": 1.6878710985183716,
              "training": false,
              "world_l1": 0.4371441602706909
            },
            {
              "action_l1": 0.3706294000148773,
              "kd_act_l1": 0.3729804754257202,
              "kd_world_l1": 0.42275384068489075,
              "tokens": 1008,
              "total": 1.5803345441818237,
              "training": false,
              "world_l1": 0.41397085785865784
            },
            {
              "action_l1": 0.35078778862953186,
              "kd_act_l1": 0.35097819566726685,
              "kd_world_l1": 0.4204387962818146,
              "tokens": 1008,
              "total": 1.5344797372817993,
              "training": false,
              "world_l1": 0.4122749865055084
            },
            {
              "action_l1": 0.3461737036705017,
              "kd_act_l1": 0.3467538058757782,
              "kd_world_l1": 0.4106674790382385,
              "tokens": 1008,
              "total": 1.5026843547821045,
              "training": false,
              "world_l1": 0.3990894556045532
            },
            {
              "action_l1": 0.3199322819709778,
              "kd_act_l1": 0.3177568018436432,
              "kd_world_l1": 0.4043927788734436,
              "tokens": 1008,
              "total": 1.435790777206421,
              "training": false,
              "world_l1": 0.39370882511138916
            },
            {
              "action_l1": 0.3158802390098572,
              "kd_act_l1": 0.31556588411331177,
              "kd_world_l1": 0.39349713921546936,
              "tokens": 1008,
              "total": 1.4087482690811157,
              "training": false,
              "world_l1": 0.3838050067424774
            },
            {
              "action_l1": 0.3375997245311737,
              "kd_act_l1": 0.3378351926803589,
              "kd_world_l1": 0.39331528544425964,
              "tokens": 1008,
              "total": 1.4489920139312744,
              "training": false,
              "world_l1": 0.3802417814731598
            },
            {
              "action_l1": 0.3623160421848297,
              "kd_act_l1": 0.3630593419075012,
              "kd_world_l1": 0.42949119210243225,
              "tokens": 1008,
              "total": 1.5677534341812134,
              "training": false,
              "world_l1": 0.4128868281841278
            },
            {
              "action_l1": 0.3836798071861267,
              "kd_act_l1": 0.38361361622810364,
              "kd_world_l1": 0.43181464076042175,
              "tokens": 1008,
              "total": 1.6150470972061157,
              "training": false,
              "world_l1": 0.41593900322914124
            },
            {
              "action_l1": 0.3976568579673767,
              "kd_act_l1": 0.39567244052886963,
              "kd_world_l1": 0.43423783779144287,
              "tokens": 1008,
              "total": 1.646414875984192,
              "training": false,
              "world_l1": 0.4188477694988251
            },
            {
              "action_l1": 0.3785252869129181,
              "kd_act_l1": 0.3751416504383087,
              "kd_world_l1": 0.4449407458305359,
              "tokens": 1008,
              "total": 1.6246280670166016,
              "training": false,
              "world_l1": 0.4260202944278717
            },
            {
              "action_l1": 0.3469723165035248,
              "kd_act_l1": 0.3466940224170685,
              "kd_world_l1": 0.45392468571662903,
              "tokens": 1008,
              "total": 1.5780738592147827,
              "training": false,
              "world_l1": 0.4304828941822052
            },
            {
              "action_l1": 0.3379932940006256,
              "kd_act_l1": 0.33794692158699036,
              "kd_world_l1": 0.4569212794303894,
              "tokens": 1008,
              "total": 1.5683355331420898,
              "training": false,
              "world_l1": 0.4354740083217621
            },
            {
              "action_l1": 0.3247334659099579,
              "kd_act_l1": 0.32600831985473633,
              "kd_world_l1": 0.43744176626205444,
              "tokens": 1008,
              "total": 1.5036327838897705,
              "training": false,
              "world_l1": 0.4154491722583771
            },
            {
              "action_l1": 0.3179210126399994,
              "kd_act_l1": 0.31735312938690186,
              "kd_world_l1": 0.40203553438186646,
              "tokens": 1008,
              "total": 1.4260485172271729,
              "training": false,
              "world_l1": 0.3887389600276947
            },
            {
              "action_l1": 0.3029862642288208,
              "kd_act_l1": 0.30241817235946655,
              "kd_world_l1": 0.4198300838470459,
              "tokens": 1008,
              "total": 1.4278032779693604,
              "training": false,
              "world_l1": 0.4025686979293823
            },
            {
              "action_l1": 0.28911346197128296,
              "kd_act_l1": 0.28941604495048523,
              "kd_world_l1": 0.43788379430770874,
              "tokens": 1008,
              "total": 1.4355177879333496,
              "training": false,
              "world_l1": 0.4191044270992279
            },
            {
              "action_l1": 0.27831408381462097,
              "kd_act_l1": 0.27864155173301697,
              "kd_world_l1": 0.44414791464805603,
              "tokens": 1008,
              "total": 1.4232622385025024,
              "training": false,
              "world_l1": 0.42215868830680847
            },
            {
              "action_l1": 0.2571543753147125,
              "kd_act_l1": 0.25693437457084656,
              "kd_world_l1": 0.4327390193939209,
              "tokens": 1008,
              "total": 1.3563854694366455,
              "training": false,
              "world_l1": 0.40955767035484314
            },
            {
              "action_l1": 0.2480607032775879,
              "kd_act_l1": 0.24973714351654053,
              "kd_world_l1": 0.4142191708087921,
              "tokens": 1008,
              "total": 1.305314302444458,
              "training": false,
              "world_l1": 0.3932972550392151
            },
            {
              "action_l1": 0.24182923138141632,
              "kd_act_l1": 0.24115988612174988,
              "kd_world_l1": 0.4000072479248047,
              "tokens": 1008,
              "total": 1.265941858291626,
              "training": false,
              "world_l1": 0.3829454481601715
            },
            {
              "action_l1": 0.23856167495250702,
              "kd_act_l1": 0.23961344361305237,
              "kd_world_l1": 0.3913446366786957,
              "tokens": 1008,
              "total": 1.2453373670578003,
              "training": false,
              "world_l1": 0.37581759691238403
            },
            {
              "action_l1": 0.3892928659915924,
              "kd_act_l1": 0.3909347355365753,
              "kd_world_l1": 0.4520346224308014,
              "tokens": 1008,
              "total": 1.663360357284546,
              "training": true,
              "world_l1": 0.43109816312789917
            },
            {
              "action_l1": 0.40823879837989807,
              "kd_act_l1": 0.4116228222846985,
              "kd_world_l1": 0.440301775932312,
              "tokens": 1008,
              "total": 1.688864827156067,
              "training": false,
              "world_l1": 0.4287015199661255
            },
            {
              "action_l1": 0.4243883788585663,
              "kd_act_l1": 0.4253033697605133,
              "kd_world_l1": 0.4427657425403595,
              "tokens": 1008,
              "total": 1.7282254695892334,
              "training": false,
              "world_l1": 0.4357680380344391
            },
            {
              "action_l1": 0.4048383831977844,
              "kd_act_l1": 0.40575921535491943,
              "kd_world_l1": 0.4233962297439575,
              "tokens": 1008,
              "total": 1.6510165929794312,
              "training": false,
              "world_l1": 0.417022705078125
            },
            {
              "action_l1": 0.3724413216114044,
              "kd_act_l1": 0.37518489360809326,
              "kd_world_l1": 0.3976074159145355,
              "tokens": 1008,
              "total": 1.5354262590408325,
              "training": false,
              "world_l1": 0.39019256830215454
            },
            {
              "action_l1": 0.35301610827445984,
              "kd_act_l1": 0.3531702160835266,
              "kd_world_l1": 0.3924737572669983,
              "tokens": 1008,
              "total": 1.484527587890625,
              "training": false,
              "world_l1": 0.3858675956726074
            },
            {
              "action_l1": 0.34933194518089294,
              "kd_act_l1": 0.3500162661075592,
              "kd_world_l1": 0.3810083866119385,
              "tokens": 1008,
              "total": 1.4516421556472778,
              "training": false,
              "world_l1": 0.3712855577468872
            },
            {
              "action_l1": 0.32353898882865906,
              "kd_act_l1": 0.32089072465896606,
              "kd_world_l1": 0.37470555305480957,
              "tokens": 1008,
              "total": 1.3849214315414429,
              "training": false,
              "world_l1": 0.3657861649990082
            },
            {
              "action_l1": 0.3208039700984955,
              "kd_act_l1": 0.32050004601478577,
              "kd_world_l1": 0.36123037338256836,
              "tokens": 1008,
              "total": 1.3557989597320557,
              "training": false,
              "world_l1": 0.35326454043388367
            },
            {
              "action_l1": 0.34293970465660095,
              "kd_act_l1": 0.3425336182117462,
              "kd_world_l1": 0.3564964234828949,
              "tokens": 1008,
              "total": 1.3873428106307983,
              "training": false,
              "world_l1": 0.3453730046749115
            },
            {
              "action_l1": 0.3655100166797638,
              "kd_act_l1": 0.36617669463157654,
              "kd_world_l1": 0.399391233921051,
              "tokens": 1008,
              "total": 1.5143795013427734,
              "training": false,
              "world_l1": 0.3833014667034149
            },
            {
              "action_l1": 0.3850761950016022,
              "kd_act_l1": 0.3852916955947876,
              "kd_world_l1": 0.4014875292778015,
              "tokens": 1008,
              "total": 1.5576722621917725,
              "training": false,
              "world_l1": 0.3858168423175812
            },
            {
              "action_l1": 0.39803215861320496,
              "kd_act_l1": 0.39568406343460083,
              "kd_world_l1": 0.4042094647884369,
              "tokens": 1008,
              "total": 1.586866021156311,
              "training": false,
              "world_l1": 0.38894033432006836
            },
            {
              "action_l1": 0.3790481686592102,
              "kd_act_l1": 0.3764297366142273,
              "kd_world_l1": 0.4154077470302582,
              "tokens": 1008,
              "total": 1.5677589178085327,
              "training": false,
              "world_l1": 0.3968733251094818
            },
            {
              "action_l1": 0.3488493859767914,
              "kd_act_l1": 0.3487093150615692,
              "kd_world_l1": 0.42435723543167114,
              "tokens": 1008,
              "total": 1.5235562324523926,
              "training": false,
              "world_l1": 0.40164023637771606
            },
            {
              "action_l1": 0.33866605162620544,
              "kd_act_l1": 0.3383227586746216,
              "kd_world_l1": 0.4284941256046295,
              "tokens": 1008,
              "total": 1.513553500175476,
              "training": false,
              "world_l1": 0.4080706536769867
            },
            {
              "action_l1": 0.3238518238067627,
              "kd_act_l1": 0.32663679122924805,
              "kd_world_l1": 0.40668028593063354,
              "tokens": 1008,
              "total": 1.4420242309570312,
              "training": false,
              "world_l1": 0.3848552107810974
            },
            {
              "action_l1": 0.3200443387031555,
              "kd_act_l1": 0.31920382380485535,
              "kd_world_l1": 0.3633475601673126,
              "tokens": 1008,
              "total": 1.3540222644805908,
              "training": false,
              "world_l1": 0.3514265716075897
            },
            {
              "action_l1": 0.3032356798648834,
              "kd_act_l1": 0.30287784337997437,
              "kd_world_l1": 0.3891071379184723,
              "tokens": 1008,
              "total": 1.368538498878479,
              "training": false,
              "world_l1": 0.37331777811050415
            },
            {
              "action_l1": 0.2909947633743286,
              "kd_act_l1": 0.29061299562454224,
              "kd_world_l1": 0.4122217893600464,
              "tokens": 1008,
              "total": 1.3886626958847046,
              "training": false,
              "world_l1": 0.39483314752578735
            },
            {
              "action_l1": 0.2796168327331543,
              "kd_act_l1": 0.28004685044288635,
              "kd_world_l1": 0.4188137650489807,
              "tokens": 1008,
              "total": 1.3764076232910156,
              "training": false,
              "world_l1": 0.3979300856590271
            },
            {
              "action_l1": 0.2593834698200226,
              "kd_act_l1": 0.2591402530670166,
              "kd_world_l1": 0.40326932072639465,
              "tokens": 1008,
              "total": 1.3028289079666138,
              "training": false,
              "world_l1": 0.38103586435317993
            },
            {
              "action_l1": 0.2517555058002472,
              "kd_act_l1": 0.2535397410392761,
              "kd_world_l1": 0.37880223989486694,
              "tokens": 1008,
              "total": 1.2425748109817505,
              "training": false,
              "world_l1": 0.35847729444503784
            },
            {
              "action_l1": 0.24539443850517273,
              "kd_act_l1": 0.244674950838089,
              "kd_world_l1": 0.35907596349716187,
              "tokens": 1008,
              "total": 1.1923630237579346,
              "training": false,
              "world_l1": 0.34321773052215576
            },
            {
              "action_l1": 0.2421007603406906,
              "kd_act_l1": 0.24312034249305725,
              "kd_world_l1": 0.34627243876457214,
              "tokens": 1008,
              "total": 1.1640892028808594,
              "training": false,
              "world_l1": 0.33259567618370056
            },
            {
              "action_l1": 0.3330734372138977,
              "kd_act_l1": 0.3331325650215149,
              "kd_world_l1": 0.42083606123924255,
              "tokens": 1008,
              "total": 1.479913353919983,
              "training": true,
              "world_l1": 0.392871230840683
            },
            {
              "action_l1": 0.4079575836658478,
              "kd_act_l1": 0.41095679998397827,
              "kd_world_l1": 0.42471569776535034,
              "tokens": 1008,
              "total": 1.657057762145996,
              "training": false,
              "world_l1": 0.4134276211261749
            },
            {
              "action_l1": 0.42514291405677795,
              "kd_act_l1": 0.42597922682762146,
              "kd_world_l1": 0.42666614055633545,
              "tokens": 1008,
              "total": 1.6978222131729126,
              "training": false,
              "world_l1": 0.42003390192985535
            },
            {
              "action_l1": 0.4052211344242096,
              "kd_act_l1": 0.40616199374198914,
              "kd_world_l1": 0.4051104485988617,
              "tokens": 1008,
              "total": 1.6159708499908447,
              "training": false,
              "world_l1": 0.39947718381881714
            },
            {
              "action_l1": 0.3726702630519867,
              "kd_act_l1": 0.3753858506679535,
              "kd_world_l1": 0.3777904808521271,
              "tokens": 1008,
              "total": 1.4966732263565063,
              "training": false,
              "world_l1": 0.3708266019821167
            },
            {
              "action_l1": 0.35412919521331787,
              "kd_act_l1": 0.354134202003479,
              "kd_world_l1": 0.37070977687835693,
              "tokens": 1008,
              "total": 1.4434938430786133,
              "training": false,
              "world_l1": 0.3645206391811371
            },
            {
              "action_l1": 0.35066545009613037,
              "kd_act_l1": 0.35126903653144836,
              "kd_world_l1": 0.35851213335990906,
              "tokens": 1008,
              "total": 1.4097988605499268,
              "training": false,
              "world_l1": 0.34935227036476135
            },
            {
              "action_l1": 0.32432252168655396,
              "kd_act_l1": 0.3216373026371002,
              "kd_world_l1": 0.3524911105632782,
              "tokens": 1008,
              "total": 1.3428956270217896,
              "training": false,
              "world_l1": 0.3444446623325348
            },
            {
              "action_l1": 0.320850670337677,
              "kd_act_l1": 0.3207048177719116,
              "kd_world_l1": 0.33682286739349365,
              "tokens": 1008,
              "total": 1.3078969717025757,
              "training": false,
              "world_l1": 0.3295186161994934
            },
            {
              "action_l1": 0.34238046407699585,
              "kd_act_l1": 0.3418625593185425,
              "kd_world_l1": 0.3304833471775055,
              "tokens": 1008,
              "total": 1.3346737623214722,
              "training": false,
              "world_l1": 0.31994742155075073
            },
            {
              "action_l1": 0.3638743758201599,
              "kd_act_l1": 0.3645654618740082,
              "kd_world_l1": 0.377157062292099,
              "tokens": 1008,
              "total": 1.466720461845398,
              "training": false,
              "world_l1": 0.36112353205680847
            },
            {
              "action_l1": 0.3834308385848999,
              "kd_act_l1": 0.38389909267425537,
              "kd_world_l1": 0.3789556920528412,
              "tokens": 1008,
              "total": 1.5094940662384033,
              "training": false,
              "world_l1": 0.3632083833217621
            },
            {
              "action_l1": 0.39608436822891235,
              "kd_act_l1": 0.39369258284568787,
              "kd_world_l1": 0.3828272521495819,
              "tokens": 1008,
              "total": 1.539851427078247,
              "training": false,
              "world_l1": 0.36724719405174255
            },
            {
              "action_l1": 0.3777366280555725,
              "kd_act_l1": 0.3753680884838104,
              "kd_world_l1": 0.3945018947124481,
              "tokens": 1008,
              "total": 1.5234147310256958,
              "training": false,
              "world_l1": 0.37580808997154236
            },
            {
              "action_l1": 0.34857040643692017,
              "kd_act_l1": 0.34840407967567444,
              "kd_world_l1": 0.4027153253555298,
              "tokens": 1008,
              "total": 1.4798574447631836,
              "training": false,
              "world_l1": 0.3801676630973816
            },
            {
              "action_l1": 0.3391096293926239,
              "kd_act_l1": 0.33868226408958435,
              "kd_world_l1": 0.40728697180747986,
              "tokens": 1008,
              "total": 1.4721779823303223,
              "training": false,
              "world_l1": 0.3870990574359894
            },
            {
              "action_l1": 0.3233588933944702,
              "kd_act_l1": 0.3260677456855774,
              "kd_world_l1": 0.3843277096748352,
              "tokens": 1008,
              "total": 1.3964459896087646,
              "training": false,
              "world_l1": 0.3626916706562042
            },
            {
              "action_l1": 0.31983309984207153,
              "kd_act_l1": 0.3189345896244049,
              "kd_world_l1": 0.33666548132896423,
              "tokens": 1008,
              "total": 1.3010565042495728,
              "training": false,
              "world_l1": 0.3256232738494873
            },
            {
              "action_l1": 0.30224767327308655,
              "kd_act_l1": 0.30195796489715576,
              "kd_world_l1": 0.36653876304626465,
              "tokens": 1008,
              "total": 1.3223470449447632,
              "training": false,
              "world_l1": 0.3516026735305786
            },
            {
              "action_l1": 0.29068446159362793,
              "kd_act_l1": 0.2901093065738678,
              "kd_world_l1": 0.39285558462142944,
              "tokens": 1008,
              "total": 1.3498318195343018,
              "training": false,
              "world_l1": 0.3761824667453766
            },
            {
              "action_l1": 0.27852386236190796,
              "kd_act_l1": 0.2788556218147278,
              "kd_world_l1": 0.3995974659919739,
              "tokens": 1008,
              "total": 1.3358712196350098,
              "training": false,
              "world_l1": 0.37889423966407776
            },
            {
              "action_l1": 0.25880110263824463,
              "kd_act_l1": 0.2585129737854004,
              "kd_world_l1": 0.38191673159599304,
              "tokens": 1008,
              "total": 1.2589954137802124,
              "training": false,
              "world_l1": 0.35976463556289673
            },
            {
              "action_l1": 0.24967548251152039,
              "kd_act_l1": 0.2514597475528717,
              "kd_world_l1": 0.35386350750923157,
              "tokens": 1008,
              "total": 1.1888478994369507,
              "training": false,
              "world_l1": 0.3338492512702942
            },
            {
              "action_l1": 0.24368196725845337,
              "kd_act_l1": 0.24302799999713898,
              "kd_world_l1": 0.3308494985103607,
              "tokens": 1008,
              "total": 1.1333051919937134,
              "training": false,
              "world_l1": 0.3157458007335663
            },
            {
              "action_l1": 0.2406584620475769,
              "kd_act_l1": 0.24167487025260925,
              "kd_world_l1": 0.31565991044044495,
              "tokens": 1008,
              "total": 1.1010706424713135,
              "training": false,
              "world_l1": 0.30307742953300476
            }
          ]
        }
      }
    }
  },
  "result": "passed",
  "metrics": {
    "smolwam.success_rate": {
      "mean": 0.0,
      "std": 0.0,
      "n": 3
    },
    "noop.success_rate": {
      "mean": 0.0,
      "std": 0.0,
      "n": 3
    }
  },
  "config": {
    "training_episodes": 8,
    "training_steps": 8,
    "layout_steps": [
      2,
      6
    ],
    "max_training_rows": 32,
    "tasks": [
      "libero_goal:6"
    ],
    "trials": 2,
    "action_budget": 300,
    "total_wall_limit_seconds": 1800
  },
  "execution_checks": {
    "actual_teacher_target_rows": [
      202,
      202,
      202
    ],
    "actual_optimizer_updates": [
      8,
      8,
      8
    ],
    "teacher_layout_updates": [
      2,
      2,
      2
    ],
    "compact_layout_updates": [
      6,
      6,
      6
    ],
    "train_and_control_total_wall_seconds": [
      352.4797902032733,
      353.10674636624753,
      351.0082911308855
    ],
    "actual_all_defining_losses_and_gradients_finite": true,
    "new_selected_student_strictly_loaded": true,
    "matched_goal6_initial_states_and_noop": true,
    "adapter_only_no_published_student_injection": true,
    "diagnostic_only": true,
    "promotion_eligible": false
  },
  "raw_artifacts": {
    "train-42": {
      "artifact_path": "docs/reproductions/2610.13740-smolwam/metrics/raw/native-student-2b84c377/smolwam-train-seed42.json",
      "sha256": "02d8af2d8cf4ce4733e63918f531194c71474ef735e93de29f12aa728705086a"
    },
    "candidate-42": {
      "artifact_path": "docs/reproductions/2610.13740-smolwam/metrics/raw/native-student-2b84c377/smolwam-candidate-seed42.json",
      "sha256": "fac6bbefdaec28b4a25ad9cbc4d53dbd7d797066dd2cfa96c26808c55fb6803f"
    },
    "train-43": {
      "artifact_path": "docs/reproductions/2610.13740-smolwam/metrics/raw/native-student-2b84c377/smolwam-train-seed43.json",
      "sha256": "c9a5246e757413d4657e3288c0290cf3d2ef151bdc995d8c133bf7b7dbb1b0b3"
    },
    "candidate-43": {
      "artifact_path": "docs/reproductions/2610.13740-smolwam/metrics/raw/native-student-2b84c377/smolwam-candidate-seed43.json",
      "sha256": "3dd02ec43f2dd34d28ca47d6238988265cad41d7c956c4566cc38a1fbe892990"
    },
    "train-44": {
      "artifact_path": "docs/reproductions/2610.13740-smolwam/metrics/raw/native-student-2b84c377/smolwam-train-seed44.json",
      "sha256": "b93494958ec7f7620ba194a00e40001510d7067e8677d24df260f68d832ab31c"
    },
    "candidate-44": {
      "artifact_path": "docs/reproductions/2610.13740-smolwam/metrics/raw/native-student-2b84c377/smolwam-candidate-seed44.json",
      "sha256": "c16aee0209855277d99540297e2ba3701df9390905068b0d2265f16f3e65a141"
    }
  },
  "executed_source_sha256": {
    "src/auto_research/reproductions/lewam/external.py": "0e0a9dbaa54d897f01f6d6f2d13584ec26c1dcf84f4e541685bbc04791056b56",
    "src/auto_research/reproductions/smolwam/algorithm.py": "ee5563a4b6e6da35b066536e31fc63bfda9a75b2ef98b40ecae06aed9220266b",
    "src/auto_research/reproductions/smolwam/training.py": "7826d69e86534d51239975591d0d43b41d686ad8d7f9dc65c554a6e7977db718",
    "src/auto_research/reproductions/smolwam/worker.py": "3485d8bafa5b3fa548ae2454677f490cf3f8791ba310d2d14c48d69ca0f7fd8c"
  },
  "executed_source_archive_sha256": "34890da45fed5620b69fb15ab389d4fba17b30d5a98b7790ced6c8e4a7e251b6",
  "provenance": {
    "commit": "2b84c3777ec2eefca3d463eb38fe1df869b55876",
    "artifact_path": "docs/gpu-validations/oct13-smolwam-a100.json",
    "metrics_artifact": "docs/reproductions/2610.13740-smolwam/metrics/native-student-a100-seeds42-44.json",
    "checkpoint_committed": false
  },
  "limitations": [
    "One task, eight demos and eight optimizer steps replace original multi-task 5000-step training.",
    "Released frozen latent adapters/BERT cache reused; not retrained.",
    "Bounded matched libero_goal:6 trials, not original 400-episode benchmark or a formal comparison.",
    "World output executed but not scored against true future; no teacher closed-loop comparison."
  ]
}
