{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14933296000093332,
  "eval_steps": 500,
  "global_step": 1600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "clip_ratio/high_max": 0.0,
      "clip_ratio/high_mean": 0.0,
      "clip_ratio/low_mean": 0.0,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0,
      "completions/clipped_ratio": 0.013959612165178603,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4093.0,
      "completions/mean_length": 601.956787109375,
      "completions/mean_terminated_length": 552.4906616210938,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 9.333310000058333e-05,
      "grad_norm": 0.15883350372314453,
      "learning_rate": 5e-07,
      "loss": 0.0207,
      "num_tokens": 80459291.0,
      "reward": 0.4974365532398224,
      "reward_std": 0.26412999629974365,
      "rewards/simpleverify_reward/mean": 0.4974365234375,
      "rewards/simpleverify_reward/std": 0.49999570846557617,
      "step": 1
    },
    {
      "clip_ratio/high_max": 0.0023947481022332795,
      "clip_ratio/high_mean": 0.001060600407072343,
      "clip_ratio/low_mean": 0.0005226716475590365,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0015832720491744112,
      "epoch": 0.00018666620000116666,
      "grad_norm": 0.14512436091899872,
      "learning_rate": 5e-07,
      "loss": -0.0383,
      "step": 2
    },
    {
      "clip_ratio/high_max": 0.002153828108930611,
      "clip_ratio/high_mean": 0.0009973189380616532,
      "clip_ratio/low_mean": 0.0005594992599071702,
      "clip_ratio/low_min": 2.8905707949888892e-05,
      "clip_ratio/region_mean": 0.0015568182097922545,
      "epoch": 0.00027999930000175,
      "grad_norm": 0.12332675606012344,
      "learning_rate": 5e-07,
      "loss": -0.0142,
      "step": 3
    },
    {
      "clip_ratio/high_max": 0.00226836991350865,
      "clip_ratio/high_mean": 0.0010622914687701268,
      "clip_ratio/low_mean": 0.0008244890977948671,
      "clip_ratio/low_min": 8.31067645776784e-05,
      "clip_ratio/region_mean": 0.0018867805702029727,
      "epoch": 0.0003733324000023333,
      "grad_norm": 0.15308021008968353,
      "learning_rate": 5e-07,
      "loss": 0.0465,
      "step": 4
    },
    {
      "clip_ratio/high_max": 0.0022996874613454565,
      "clip_ratio/high_mean": 0.0009545004650135525,
      "clip_ratio/low_mean": 0.0007080396990204463,
      "clip_ratio/low_min": 5.048848015576368e-05,
      "clip_ratio/region_mean": 0.001662540147663094,
      "epoch": 0.0004666655000029167,
      "grad_norm": 0.14301040768623352,
      "learning_rate": 5e-07,
      "loss": 0.0433,
      "step": 5
    },
    {
      "clip_ratio/high_max": 0.0023602864239364862,
      "clip_ratio/high_mean": 0.0010359031875850633,
      "clip_ratio/low_mean": 0.0006847775694041047,
      "clip_ratio/low_min": 4.714955321105663e-05,
      "clip_ratio/region_mean": 0.0017206807897309773,
      "epoch": 0.0005599986000035,
      "grad_norm": 0.13659115135669708,
      "learning_rate": 5e-07,
      "loss": 0.0426,
      "step": 6
    },
    {
      "clip_ratio/high_max": 0.0020869691979896743,
      "clip_ratio/high_mean": 0.0009117745630646823,
      "clip_ratio/low_mean": 0.0007138628734537633,
      "clip_ratio/low_min": 6.670368929917458e-05,
      "clip_ratio/region_mean": 0.001625637487450149,
      "epoch": 0.0006533317000040833,
      "grad_norm": 0.12369740754365921,
      "learning_rate": 5e-07,
      "loss": 0.0265,
      "step": 7
    },
    {
      "clip_ratio/high_max": 0.002307308037416078,
      "clip_ratio/high_mean": 0.0011247586753597716,
      "clip_ratio/low_mean": 0.0007102952240529703,
      "clip_ratio/low_min": 0.000109725567199348,
      "clip_ratio/region_mean": 0.001835053917602636,
      "epoch": 0.0007466648000046666,
      "grad_norm": 0.1625298410654068,
      "learning_rate": 5e-07,
      "loss": -0.0361,
      "step": 8
    },
    {
      "clip_ratio/high_max": 0.002536041552957613,
      "clip_ratio/high_mean": 0.0010422234918223694,
      "clip_ratio/low_mean": 0.0007616382699779933,
      "clip_ratio/low_min": 8.849952337186551e-05,
      "clip_ratio/region_mean": 0.0018038617781712674,
      "epoch": 0.00083999790000525,
      "grad_norm": 0.13519640266895294,
      "learning_rate": 5e-07,
      "loss": 0.0487,
      "step": 9
    },
    {
      "clip_ratio/high_max": 0.0020856731898675207,
      "clip_ratio/high_mean": 0.0008368622166017303,
      "clip_ratio/low_mean": 0.0008444044105999637,
      "clip_ratio/low_min": 0.00013079753989586607,
      "clip_ratio/region_mean": 0.0016812666108307894,
      "epoch": 0.0009333310000058334,
      "grad_norm": 0.1162048727273941,
      "learning_rate": 5e-07,
      "loss": 0.0422,
      "step": 10
    },
    {
      "clip_ratio/high_max": 0.0021600222680717707,
      "clip_ratio/high_mean": 0.0010294290987076238,
      "clip_ratio/low_mean": 0.0009372010645165574,
      "clip_ratio/low_min": 0.00018348827779846033,
      "clip_ratio/region_mean": 0.0019666301595862024,
      "epoch": 0.0010266641000064166,
      "grad_norm": 0.11892766505479813,
      "learning_rate": 5e-07,
      "loss": 0.0001,
      "step": 11
    },
    {
      "clip_ratio/high_max": 0.002274746453622356,
      "clip_ratio/high_mean": 0.0010937713686871575,
      "clip_ratio/low_mean": 0.0010538758033362683,
      "clip_ratio/low_min": 0.00014745058888365747,
      "clip_ratio/region_mean": 0.0021476471520145424,
      "epoch": 0.001119997200007,
      "grad_norm": 0.13386264443397522,
      "learning_rate": 5e-07,
      "loss": 0.014,
      "step": 12
    },
    {
      "clip_ratio/high_max": 0.0024591097608208656,
      "clip_ratio/high_mean": 0.0011733309293049388,
      "clip_ratio/low_mean": 0.0009475126535107847,
      "clip_ratio/low_min": 9.550489994580857e-05,
      "clip_ratio/region_mean": 0.0021208435864537023,
      "epoch": 0.0012133303000075833,
      "grad_norm": 0.11592786759138107,
      "learning_rate": 5e-07,
      "loss": 0.0327,
      "step": 13
    },
    {
      "clip_ratio/high_max": 0.0023297709340113215,
      "clip_ratio/high_mean": 0.0010151374553970527,
      "clip_ratio/low_mean": 0.0010621613000694197,
      "clip_ratio/low_min": 0.00014217348325473722,
      "clip_ratio/region_mean": 0.002077298740914557,
      "epoch": 0.0013066634000081666,
      "grad_norm": 0.11880461871623993,
      "learning_rate": 5e-07,
      "loss": 0.0054,
      "step": 14
    },
    {
      "clip_ratio/high_max": 0.0024311086235684343,
      "clip_ratio/high_mean": 0.0011541962885530666,
      "clip_ratio/low_mean": 0.0009270151895179879,
      "clip_ratio/low_min": 0.00014871857274556533,
      "clip_ratio/region_mean": 0.002081211467157118,
      "epoch": 0.00139999650000875,
      "grad_norm": 0.13146427273750305,
      "learning_rate": 5e-07,
      "loss": -0.0428,
      "step": 15
    },
    {
      "clip_ratio/high_max": 0.0024465122769470327,
      "clip_ratio/high_mean": 0.0012008658522972837,
      "clip_ratio/low_mean": 0.0010348582982260268,
      "clip_ratio/low_min": 0.00019306197373225586,
      "clip_ratio/region_mean": 0.002235724125057459,
      "epoch": 0.0014933296000093333,
      "grad_norm": 0.12981517612934113,
      "learning_rate": 5e-07,
      "loss": -0.0158,
      "step": 16
    },
    {
      "clip_ratio/high_max": 0.002538264321628958,
      "clip_ratio/high_mean": 0.001060898823197931,
      "clip_ratio/low_mean": 0.0010752615125966258,
      "clip_ratio/low_min": 0.0001450896706955973,
      "clip_ratio/region_mean": 0.0021361603212426417,
      "epoch": 0.0015866627000099165,
      "grad_norm": 0.11553175002336502,
      "learning_rate": 5e-07,
      "loss": 0.0232,
      "step": 17
    },
    {
      "clip_ratio/high_max": 0.0024930078579927795,
      "clip_ratio/high_mean": 0.0010687904723454267,
      "clip_ratio/low_mean": 0.0010574678926786873,
      "clip_ratio/low_min": 0.0001980620518224896,
      "clip_ratio/region_mean": 0.002126258325006347,
      "epoch": 0.0016799958000105,
      "grad_norm": 0.11521248519420624,
      "learning_rate": 5e-07,
      "loss": 0.0532,
      "step": 18
    },
    {
      "clip_ratio/high_max": 0.002161802156479098,
      "clip_ratio/high_mean": 0.0009116911460296251,
      "clip_ratio/low_mean": 0.0011186773772351444,
      "clip_ratio/low_min": 0.00019370284371689195,
      "clip_ratio/region_mean": 0.0020303685232647695,
      "epoch": 0.0017733289000110833,
      "grad_norm": 0.12137337774038315,
      "learning_rate": 5e-07,
      "loss": 0.0286,
      "step": 19
    },
    {
      "clip_ratio/high_max": 0.0023584373484482057,
      "clip_ratio/high_mean": 0.001059960570273688,
      "clip_ratio/low_mean": 0.0010669174662325531,
      "clip_ratio/low_min": 0.0001229694621542876,
      "clip_ratio/region_mean": 0.0021268780328682624,
      "epoch": 0.0018666620000116667,
      "grad_norm": 0.13080692291259766,
      "learning_rate": 5e-07,
      "loss": 0.0125,
      "step": 20
    },
    {
      "clip_ratio/high_max": 0.002754021574219223,
      "clip_ratio/high_mean": 0.0012086302231182344,
      "clip_ratio/low_mean": 0.0010298781053279527,
      "clip_ratio/low_min": 9.031116314872634e-05,
      "clip_ratio/region_mean": 0.0022385082993423566,
      "epoch": 0.00195999510001225,
      "grad_norm": 0.11933479458093643,
      "learning_rate": 5e-07,
      "loss": -0.0244,
      "step": 21
    },
    {
      "clip_ratio/high_max": 0.0023141088022384793,
      "clip_ratio/high_mean": 0.0010922818946710322,
      "clip_ratio/low_mean": 0.0010647973485902185,
      "clip_ratio/low_min": 0.0001455557685403619,
      "clip_ratio/region_mean": 0.00215707924508024,
      "epoch": 0.002053328200012833,
      "grad_norm": 0.12836778163909912,
      "learning_rate": 5e-07,
      "loss": -0.0064,
      "step": 22
    },
    {
      "clip_ratio/high_max": 0.0027153591290698387,
      "clip_ratio/high_mean": 0.0013157686335034668,
      "clip_ratio/low_mean": 0.0009932652064890135,
      "clip_ratio/low_min": 0.00015097567938937573,
      "clip_ratio/region_mean": 0.002309033792698756,
      "epoch": 0.0021466613000134167,
      "grad_norm": 0.11481130123138428,
      "learning_rate": 5e-07,
      "loss": -0.0377,
      "step": 23
    },
    {
      "clip_ratio/high_max": 0.002211781742516905,
      "clip_ratio/high_mean": 0.0010169967044930672,
      "clip_ratio/low_mean": 0.0012264622419024818,
      "clip_ratio/low_min": 0.0002666262607817771,
      "clip_ratio/region_mean": 0.0022434589482145384,
      "epoch": 0.002239994400014,
      "grad_norm": 0.1254318356513977,
      "learning_rate": 5e-07,
      "loss": 0.0356,
      "step": 24
    },
    {
      "clip_ratio/high_max": 0.0023375216260319576,
      "clip_ratio/high_mean": 0.0009420943970326334,
      "clip_ratio/low_mean": 0.0011906263498531189,
      "clip_ratio/low_min": 0.00022289034222922055,
      "clip_ratio/region_mean": 0.0021327207432477735,
      "epoch": 0.002333327500014583,
      "grad_norm": 0.12370091676712036,
      "learning_rate": 5e-07,
      "loss": 0.0221,
      "step": 25
    },
    {
      "clip_ratio/high_max": 0.002664944186108187,
      "clip_ratio/high_mean": 0.0010011509875766933,
      "clip_ratio/low_mean": 0.0011042193837056402,
      "clip_ratio/low_min": 8.56254428072134e-05,
      "clip_ratio/region_mean": 0.0021053704258520156,
      "epoch": 0.0024266606000151666,
      "grad_norm": 0.12313516438007355,
      "learning_rate": 5e-07,
      "loss": -0.0136,
      "step": 26
    },
    {
      "clip_ratio/high_max": 0.0024300917211803608,
      "clip_ratio/high_mean": 0.0010119599064637441,
      "clip_ratio/low_mean": 0.00116535783308791,
      "clip_ratio/low_min": 0.00017418024526705267,
      "clip_ratio/region_mean": 0.0021773178086732514,
      "epoch": 0.00251999370001575,
      "grad_norm": 0.1240299791097641,
      "learning_rate": 5e-07,
      "loss": 0.0384,
      "step": 27
    },
    {
      "clip_ratio/high_max": 0.002403508660790976,
      "clip_ratio/high_mean": 0.0010154964475077577,
      "clip_ratio/low_mean": 0.0011573356459848583,
      "clip_ratio/low_min": 0.00015281092510122107,
      "clip_ratio/region_mean": 0.002172832129872404,
      "epoch": 0.002613326800016333,
      "grad_norm": 0.12326163798570633,
      "learning_rate": 5e-07,
      "loss": 0.0154,
      "step": 28
    },
    {
      "clip_ratio/high_max": 0.0022259639808908105,
      "clip_ratio/high_mean": 0.0009925682861648966,
      "clip_ratio/low_mean": 0.0011396269073884469,
      "clip_ratio/low_min": 0.00014927210213500075,
      "clip_ratio/region_mean": 0.0021321952444850467,
      "epoch": 0.0027066599000169166,
      "grad_norm": 0.12073556333780289,
      "learning_rate": 5e-07,
      "loss": 0.0235,
      "step": 29
    },
    {
      "clip_ratio/high_max": 0.002066428220132366,
      "clip_ratio/high_mean": 0.000984432965196902,
      "clip_ratio/low_mean": 0.0011027818509319331,
      "clip_ratio/low_min": 9.883244183583884e-05,
      "clip_ratio/region_mean": 0.00208721480157692,
      "epoch": 0.0027999930000175,
      "grad_norm": 0.11432908475399017,
      "learning_rate": 5e-07,
      "loss": 0.0086,
      "step": 30
    },
    {
      "clip_ratio/high_max": 0.0023641147272428498,
      "clip_ratio/high_mean": 0.0011043534759664908,
      "clip_ratio/low_mean": 0.0010207963387074415,
      "clip_ratio/low_min": 6.40419966657646e-05,
      "clip_ratio/region_mean": 0.002125149803759996,
      "epoch": 0.002893326100018083,
      "grad_norm": 0.11717358976602554,
      "learning_rate": 5e-07,
      "loss": -0.0457,
      "step": 31
    },
    {
      "clip_ratio/high_max": 0.0023773985158186406,
      "clip_ratio/high_mean": 0.0011482547233754303,
      "clip_ratio/low_mean": 0.0010260591661790386,
      "clip_ratio/low_min": 0.00012593469000421464,
      "clip_ratio/region_mean": 0.002174313849536702,
      "epoch": 0.0029866592000186666,
      "grad_norm": 0.1219366118311882,
      "learning_rate": 5e-07,
      "loss": -0.0143,
      "step": 32
    },
    {
      "clip_ratio/high_max": 0.0025471630578977056,
      "clip_ratio/high_mean": 0.0010339206692151492,
      "clip_ratio/low_mean": 0.001219605837832205,
      "clip_ratio/low_min": 0.00022899656596564455,
      "clip_ratio/region_mean": 0.002253526537970174,
      "epoch": 0.00307999230001925,
      "grad_norm": 0.1291673630475998,
      "learning_rate": 5e-07,
      "loss": 0.0576,
      "step": 33
    },
    {
      "clip_ratio/high_max": 0.002536895357479807,
      "clip_ratio/high_mean": 0.0012250412946741562,
      "clip_ratio/low_mean": 0.0010695261626096908,
      "clip_ratio/low_min": 0.00022082561190472916,
      "clip_ratio/region_mean": 0.002294567442731932,
      "epoch": 0.003173325400019833,
      "grad_norm": 0.1257622092962265,
      "learning_rate": 5e-07,
      "loss": -0.0541,
      "step": 34
    },
    {
      "clip_ratio/high_max": 0.002271754201501608,
      "clip_ratio/high_mean": 0.0010345125447202008,
      "clip_ratio/low_mean": 0.0010611847137624864,
      "clip_ratio/low_min": 0.00012924665679747704,
      "clip_ratio/region_mean": 0.002095697316690348,
      "epoch": 0.0032666585000204165,
      "grad_norm": 0.1239142045378685,
      "learning_rate": 5e-07,
      "loss": 0.0278,
      "step": 35
    },
    {
      "clip_ratio/high_max": 0.0023552644561277702,
      "clip_ratio/high_mean": 0.0009265450098610017,
      "clip_ratio/low_mean": 0.0011102555945399217,
      "clip_ratio/low_min": 6.547933207912138e-05,
      "clip_ratio/region_mean": 0.002036800673522521,
      "epoch": 0.003359991600021,
      "grad_norm": 0.1244611144065857,
      "learning_rate": 5e-07,
      "loss": 0.0849,
      "step": 36
    },
    {
      "clip_ratio/high_max": 0.0020424606482265517,
      "clip_ratio/high_mean": 0.0009926992297550896,
      "clip_ratio/low_mean": 0.0011776314058806747,
      "clip_ratio/low_min": 0.00018590293529996416,
      "clip_ratio/region_mean": 0.002170330561057199,
      "epoch": 0.0034533247000215835,
      "grad_norm": 0.12619130313396454,
      "learning_rate": 5e-07,
      "loss": 0.0379,
      "step": 37
    },
    {
      "clip_ratio/high_max": 0.0026282845356035978,
      "clip_ratio/high_mean": 0.0011712995037669316,
      "clip_ratio/low_mean": 0.0011348483858455438,
      "clip_ratio/low_min": 0.00014799373366258806,
      "clip_ratio/region_mean": 0.0023061478714225814,
      "epoch": 0.0035466578000221665,
      "grad_norm": 0.1229720488190651,
      "learning_rate": 5e-07,
      "loss": 0.015,
      "step": 38
    },
    {
      "clip_ratio/high_max": 0.00232126702030655,
      "clip_ratio/high_mean": 0.0010633982892613858,
      "clip_ratio/low_mean": 0.0011484712958917953,
      "clip_ratio/low_min": 0.00015070424979057861,
      "clip_ratio/region_mean": 0.0022118695633253083,
      "epoch": 0.00363999090002275,
      "grad_norm": 0.1393277496099472,
      "learning_rate": 5e-07,
      "loss": -0.0102,
      "step": 39
    },
    {
      "clip_ratio/high_max": 0.0023285518946067896,
      "clip_ratio/high_mean": 0.0009771344957698602,
      "clip_ratio/low_mean": 0.0011303622886771336,
      "clip_ratio/low_min": 0.00012027291904814774,
      "clip_ratio/region_mean": 0.0021074967517051846,
      "epoch": 0.0037333240000233334,
      "grad_norm": 0.12612101435661316,
      "learning_rate": 5e-07,
      "loss": 0.0287,
      "step": 40
    },
    {
      "clip_ratio/high_max": 0.001961888421647018,
      "clip_ratio/high_mean": 0.00100657807161042,
      "clip_ratio/low_mean": 0.0011484215283417143,
      "clip_ratio/low_min": 0.00022048242590244627,
      "clip_ratio/region_mean": 0.002154999616323039,
      "epoch": 0.0038266571000239165,
      "grad_norm": 0.12364474684000015,
      "learning_rate": 5e-07,
      "loss": 0.0533,
      "step": 41
    },
    {
      "clip_ratio/high_max": 0.0020195237157167867,
      "clip_ratio/high_mean": 0.0009840842394623905,
      "clip_ratio/low_mean": 0.0011600138896028511,
      "clip_ratio/low_min": 0.00015587746111123124,
      "clip_ratio/region_mean": 0.002144098107237369,
      "epoch": 0.0039199902000245,
      "grad_norm": 0.12399540841579437,
      "learning_rate": 5e-07,
      "loss": 0.0694,
      "step": 42
    },
    {
      "clip_ratio/high_max": 0.002446704795147525,
      "clip_ratio/high_mean": 0.0009702129045763286,
      "clip_ratio/low_mean": 0.001034267588693183,
      "clip_ratio/low_min": 0.00012876746495749103,
      "clip_ratio/region_mean": 0.0020044804623466916,
      "epoch": 0.004013323300025083,
      "grad_norm": 0.1292649656534195,
      "learning_rate": 5e-07,
      "loss": 0.0597,
      "step": 43
    },
    {
      "clip_ratio/high_max": 0.002167284008464776,
      "clip_ratio/high_mean": 0.0009252225427189842,
      "clip_ratio/low_mean": 0.0011100506781076547,
      "clip_ratio/low_min": 0.0001879115652627661,
      "clip_ratio/region_mean": 0.002035273202636745,
      "epoch": 0.004106656400025666,
      "grad_norm": 0.11474408954381943,
      "learning_rate": 5e-07,
      "loss": 0.0474,
      "step": 44
    },
    {
      "clip_ratio/high_max": 0.002138963038305519,
      "clip_ratio/high_mean": 0.000948211991271819,
      "clip_ratio/low_mean": 0.0012916315026814118,
      "clip_ratio/low_min": 9.001715898193652e-05,
      "clip_ratio/region_mean": 0.0022398435248760507,
      "epoch": 0.00419998950002625,
      "grad_norm": 0.11944501847028732,
      "learning_rate": 5e-07,
      "loss": 0.0893,
      "step": 45
    },
    {
      "clip_ratio/high_max": 0.001922607363667339,
      "clip_ratio/high_mean": 0.0009754186830832623,
      "clip_ratio/low_mean": 0.0011538813741935883,
      "clip_ratio/low_min": 0.00018613782776810694,
      "clip_ratio/region_mean": 0.002129300046362914,
      "epoch": 0.004293322600026833,
      "grad_norm": 0.12877300381660461,
      "learning_rate": 5e-07,
      "loss": 0.0194,
      "step": 46
    },
    {
      "clip_ratio/high_max": 0.002157738337700721,
      "clip_ratio/high_mean": 0.0009507781014690408,
      "clip_ratio/low_mean": 0.0010382458094682079,
      "clip_ratio/low_min": 0.0001444613626517821,
      "clip_ratio/region_mean": 0.0019890239054802805,
      "epoch": 0.004386655700027417,
      "grad_norm": 0.13200531899929047,
      "learning_rate": 5e-07,
      "loss": 0.0153,
      "step": 47
    },
    {
      "clip_ratio/high_max": 0.002509040423319675,
      "clip_ratio/high_mean": 0.0010907801442954224,
      "clip_ratio/low_mean": 0.0011190563200216275,
      "clip_ratio/low_min": 0.0001550782239974069,
      "clip_ratio/region_mean": 0.0022098365079727955,
      "epoch": 0.004479988800028,
      "grad_norm": 0.12299535423517227,
      "learning_rate": 5e-07,
      "loss": 0.034,
      "step": 48
    },
    {
      "clip_ratio/high_max": 0.0021077201527077705,
      "clip_ratio/high_mean": 0.000887629506905796,
      "clip_ratio/low_mean": 0.001208916502946522,
      "clip_ratio/low_min": 0.00022224765507417032,
      "clip_ratio/region_mean": 0.002096546013490297,
      "epoch": 0.004573321900028583,
      "grad_norm": 0.10131525993347168,
      "learning_rate": 5e-07,
      "loss": -0.0026,
      "step": 49
    },
    {
      "clip_ratio/high_max": 0.00291603576624766,
      "clip_ratio/high_mean": 0.0012152688868809491,
      "clip_ratio/low_mean": 0.0011246412213949952,
      "clip_ratio/low_min": 0.00011805795111285988,
      "clip_ratio/region_mean": 0.0023399101410177536,
      "epoch": 0.004666655000029166,
      "grad_norm": 0.122919000685215,
      "learning_rate": 5e-07,
      "loss": -0.0123,
      "step": 50
    },
    {
      "clip_ratio/high_max": 0.00194368638767628,
      "clip_ratio/high_mean": 0.0009594503862899728,
      "clip_ratio/low_mean": 0.001205226875754306,
      "clip_ratio/low_min": 0.00019646659438876668,
      "clip_ratio/region_mean": 0.0021646772656822577,
      "epoch": 0.00475998810002975,
      "grad_norm": 0.13306628167629242,
      "learning_rate": 5e-07,
      "loss": -0.0056,
      "step": 51
    },
    {
      "clip_ratio/high_max": 0.00269433856010437,
      "clip_ratio/high_mean": 0.0011242261425650213,
      "clip_ratio/low_mean": 0.0012559897040773649,
      "clip_ratio/low_min": 0.00015879536022112006,
      "clip_ratio/region_mean": 0.0023802158611943014,
      "epoch": 0.004853321200030333,
      "grad_norm": 0.11886189877986908,
      "learning_rate": 5e-07,
      "loss": 0.0159,
      "step": 52
    },
    {
      "clip_ratio/high_max": 0.0024464153102599084,
      "clip_ratio/high_mean": 0.0010275970598740969,
      "clip_ratio/low_mean": 0.0013252939243102446,
      "clip_ratio/low_min": 0.0002854655131159234,
      "clip_ratio/region_mean": 0.0023528910023742355,
      "epoch": 0.004946654300030917,
      "grad_norm": 0.12265696376562119,
      "learning_rate": 5e-07,
      "loss": 0.0441,
      "step": 53
    },
    {
      "clip_ratio/high_max": 0.0025165933548123576,
      "clip_ratio/high_mean": 0.0011234615521971136,
      "clip_ratio/low_mean": 0.001188645081128925,
      "clip_ratio/low_min": 0.00020703762584162178,
      "clip_ratio/region_mean": 0.002312106647877954,
      "epoch": 0.0050399874000315,
      "grad_norm": 0.11384860426187515,
      "learning_rate": 5e-07,
      "loss": 0.0402,
      "step": 54
    },
    {
      "clip_ratio/high_max": 0.00249327967321733,
      "clip_ratio/high_mean": 0.0011228545954509173,
      "clip_ratio/low_mean": 0.0011890315927303163,
      "clip_ratio/low_min": 0.00011955566606047796,
      "clip_ratio/region_mean": 0.002311886193638202,
      "epoch": 0.005133320500032083,
      "grad_norm": 0.11263099312782288,
      "learning_rate": 5e-07,
      "loss": 0.0114,
      "step": 55
    },
    {
      "clip_ratio/high_max": 0.002515962150937412,
      "clip_ratio/high_mean": 0.001057294974089018,
      "clip_ratio/low_mean": 0.0013800408996758051,
      "clip_ratio/low_min": 0.0003099403347732732,
      "clip_ratio/region_mean": 0.0024373358537559398,
      "epoch": 0.005226653600032666,
      "grad_norm": 0.1464528739452362,
      "learning_rate": 5e-07,
      "loss": 0.0573,
      "step": 56
    },
    {
      "clip_ratio/high_max": 0.0023335340301855467,
      "clip_ratio/high_mean": 0.0010383299122622702,
      "clip_ratio/low_mean": 0.0013057563264737837,
      "clip_ratio/low_min": 0.00012527682065410772,
      "clip_ratio/region_mean": 0.002344086256925948,
      "epoch": 0.00531998670003325,
      "grad_norm": 0.13026703894138336,
      "learning_rate": 5e-07,
      "loss": -0.0009,
      "step": 57
    },
    {
      "clip_ratio/high_max": 0.0019849278542096727,
      "clip_ratio/high_mean": 0.001000209695121157,
      "clip_ratio/low_mean": 0.0012686668778769672,
      "clip_ratio/low_min": 0.00015404582791234134,
      "clip_ratio/region_mean": 0.002268876567541156,
      "epoch": 0.005413319800033833,
      "grad_norm": 0.12994103133678436,
      "learning_rate": 5e-07,
      "loss": 0.0062,
      "step": 58
    },
    {
      "clip_ratio/high_max": 0.0022944321608520113,
      "clip_ratio/high_mean": 0.0009708481848065276,
      "clip_ratio/low_mean": 0.0013499285487341695,
      "clip_ratio/low_min": 0.00018459476086718496,
      "clip_ratio/region_mean": 0.0023207767444546334,
      "epoch": 0.005506652900034417,
      "grad_norm": 0.11542260646820068,
      "learning_rate": 5e-07,
      "loss": 0.049,
      "step": 59
    },
    {
      "clip_ratio/high_max": 0.002204513770266203,
      "clip_ratio/high_mean": 0.0009881405712803826,
      "clip_ratio/low_mean": 0.0012808736937586218,
      "clip_ratio/low_min": 0.00026974977754434804,
      "clip_ratio/region_mean": 0.002269014294142835,
      "epoch": 0.005599986000035,
      "grad_norm": 0.12013743072748184,
      "learning_rate": 5e-07,
      "loss": 0.0364,
      "step": 60
    },
    {
      "clip_ratio/high_max": 0.002456075912050437,
      "clip_ratio/high_mean": 0.0010461296151333954,
      "clip_ratio/low_mean": 0.0013189289547881344,
      "clip_ratio/low_min": 0.00020347223471617326,
      "clip_ratio/region_mean": 0.0023650585717405193,
      "epoch": 0.005693319100035584,
      "grad_norm": 0.1301392912864685,
      "learning_rate": 5e-07,
      "loss": 0.0471,
      "step": 61
    },
    {
      "clip_ratio/high_max": 0.0023179318523034453,
      "clip_ratio/high_mean": 0.0010819569615705404,
      "clip_ratio/low_mean": 0.001216073680552654,
      "clip_ratio/low_min": 0.00024090664646791993,
      "clip_ratio/region_mean": 0.002298030689416919,
      "epoch": 0.005786652200036166,
      "grad_norm": 0.12232790887355804,
      "learning_rate": 5e-07,
      "loss": -0.0166,
      "step": 62
    },
    {
      "clip_ratio/high_max": 0.0018017997936112806,
      "clip_ratio/high_mean": 0.0008226262525568018,
      "clip_ratio/low_mean": 0.0012028305209241807,
      "clip_ratio/low_min": 0.00023700856399955228,
      "clip_ratio/region_mean": 0.0020254567643860355,
      "epoch": 0.00587998530003675,
      "grad_norm": 0.11779560148715973,
      "learning_rate": 5e-07,
      "loss": 0.0677,
      "step": 63
    },
    {
      "clip_ratio/high_max": 0.002306475413206499,
      "clip_ratio/high_mean": 0.0010141590501007158,
      "clip_ratio/low_mean": 0.001024165087073925,
      "clip_ratio/low_min": 0.00012785747458110563,
      "clip_ratio/region_mean": 0.0020383241499075666,
      "epoch": 0.005973318400037333,
      "grad_norm": 0.1104663535952568,
      "learning_rate": 5e-07,
      "loss": -0.0013,
      "step": 64
    },
    {
      "clip_ratio/high_max": 0.0023695397831033915,
      "clip_ratio/high_mean": 0.0011210251250304282,
      "clip_ratio/low_mean": 0.0012068348660250194,
      "clip_ratio/low_min": 0.000112979923869716,
      "clip_ratio/region_mean": 0.0023278600347111933,
      "epoch": 0.006066651500037917,
      "grad_norm": 0.12179224193096161,
      "learning_rate": 5e-07,
      "loss": -0.0044,
      "step": 65
    },
    {
      "clip_ratio/high_max": 0.0024369961975025944,
      "clip_ratio/high_mean": 0.0011473489630589029,
      "clip_ratio/low_mean": 0.0011787503244704567,
      "clip_ratio/low_min": 0.00021734657457272988,
      "clip_ratio/region_mean": 0.002326099311176222,
      "epoch": 0.0061599846000385,
      "grad_norm": 0.12817977368831635,
      "learning_rate": 5e-07,
      "loss": -0.0225,
      "step": 66
    },
    {
      "clip_ratio/high_max": 0.0023769270337652415,
      "clip_ratio/high_mean": 0.001105856463254895,
      "clip_ratio/low_mean": 0.0011708508245646954,
      "clip_ratio/low_min": 0.00020334137843747158,
      "clip_ratio/region_mean": 0.002276707273267675,
      "epoch": 0.0062533177000390835,
      "grad_norm": 0.12276140600442886,
      "learning_rate": 5e-07,
      "loss": -0.0003,
      "step": 67
    },
    {
      "clip_ratio/high_max": 0.00263368348532822,
      "clip_ratio/high_mean": 0.0012102431792300195,
      "clip_ratio/low_mean": 0.001262616988242371,
      "clip_ratio/low_min": 0.00018034256481769262,
      "clip_ratio/region_mean": 0.0024728601129027084,
      "epoch": 0.006346650800039666,
      "grad_norm": 0.12390284240245819,
      "learning_rate": 5e-07,
      "loss": -0.0063,
      "step": 68
    },
    {
      "clip_ratio/high_max": 0.0026013132301159203,
      "clip_ratio/high_mean": 0.001086824589947355,
      "clip_ratio/low_mean": 0.001295565136388177,
      "clip_ratio/low_min": 0.00016340078400389757,
      "clip_ratio/region_mean": 0.0023823897063266486,
      "epoch": 0.00643998390004025,
      "grad_norm": 0.1266259104013443,
      "learning_rate": 5e-07,
      "loss": 0.0155,
      "step": 69
    },
    {
      "clip_ratio/high_max": 0.0023300859684241004,
      "clip_ratio/high_mean": 0.0010527103913773317,
      "clip_ratio/low_mean": 0.0012351888053672155,
      "clip_ratio/low_min": 0.0002183851911468082,
      "clip_ratio/region_mean": 0.0022878991585457698,
      "epoch": 0.006533317000040833,
      "grad_norm": 0.11915330588817596,
      "learning_rate": 5e-07,
      "loss": 0.0197,
      "step": 70
    },
    {
      "clip_ratio/high_max": 0.0022491040945169516,
      "clip_ratio/high_mean": 0.0009492232129559852,
      "clip_ratio/low_mean": 0.0012668943381868303,
      "clip_ratio/low_min": 0.000278410266218998,
      "clip_ratio/region_mean": 0.0022161175147630274,
      "epoch": 0.0066266501000414165,
      "grad_norm": 0.16123825311660767,
      "learning_rate": 5e-07,
      "loss": 0.071,
      "step": 71
    },
    {
      "clip_ratio/high_max": 0.0022639395465375856,
      "clip_ratio/high_mean": 0.0010518925246287836,
      "clip_ratio/low_mean": 0.0012131751864217222,
      "clip_ratio/low_min": 0.00025206618829543004,
      "clip_ratio/region_mean": 0.0022650677419733256,
      "epoch": 0.006719983200042,
      "grad_norm": 0.11607296019792557,
      "learning_rate": 5e-07,
      "loss": 0.064,
      "step": 72
    },
    {
      "clip_ratio/high_max": 0.002284939597302582,
      "clip_ratio/high_mean": 0.0009933120090863667,
      "clip_ratio/low_mean": 0.0014461745849985164,
      "clip_ratio/low_min": 0.0002319339764653705,
      "clip_ratio/region_mean": 0.002439486597722862,
      "epoch": 0.0068133163000425835,
      "grad_norm": 0.13758115470409393,
      "learning_rate": 5e-07,
      "loss": 0.051,
      "step": 73
    },
    {
      "clip_ratio/high_max": 0.002464253640937386,
      "clip_ratio/high_mean": 0.00110428467814927,
      "clip_ratio/low_mean": 0.0012494309339672327,
      "clip_ratio/low_min": 0.00010607095464365557,
      "clip_ratio/region_mean": 0.0023537155939266086,
      "epoch": 0.006906649400043167,
      "grad_norm": 0.11839781701564789,
      "learning_rate": 5e-07,
      "loss": 0.0034,
      "step": 74
    },
    {
      "clip_ratio/high_max": 0.002733893314143643,
      "clip_ratio/high_mean": 0.0011789785712608136,
      "clip_ratio/low_mean": 0.0012240871037647594,
      "clip_ratio/low_min": 0.00018676085983315716,
      "clip_ratio/region_mean": 0.002403065729595255,
      "epoch": 0.0069999825000437495,
      "grad_norm": 0.13181614875793457,
      "learning_rate": 5e-07,
      "loss": 0.0108,
      "step": 75
    },
    {
      "clip_ratio/high_max": 0.0022378048961400054,
      "clip_ratio/high_mean": 0.001070675025403034,
      "clip_ratio/low_mean": 0.0011415332483011298,
      "clip_ratio/low_min": 0.00011758449727494735,
      "clip_ratio/region_mean": 0.002212208288256079,
      "epoch": 0.007093315600044333,
      "grad_norm": 0.13014915585517883,
      "learning_rate": 5e-07,
      "loss": 0.0168,
      "step": 76
    },
    {
      "clip_ratio/high_max": 0.0025197745744662825,
      "clip_ratio/high_mean": 0.0012105936348234536,
      "clip_ratio/low_mean": 0.0013135002336639445,
      "clip_ratio/low_min": 0.00022594217625737656,
      "clip_ratio/region_mean": 0.002524093877582345,
      "epoch": 0.0071866487000449165,
      "grad_norm": 0.1377609372138977,
      "learning_rate": 5e-07,
      "loss": 0.0007,
      "step": 77
    },
    {
      "clip_ratio/high_max": 0.002543840695580002,
      "clip_ratio/high_mean": 0.0010897537613345776,
      "clip_ratio/low_mean": 0.0012809620538973832,
      "clip_ratio/low_min": 0.0001781813271009014,
      "clip_ratio/region_mean": 0.00237071583251236,
      "epoch": 0.0072799818000455,
      "grad_norm": 0.11660829931497574,
      "learning_rate": 5e-07,
      "loss": -0.01,
      "step": 78
    },
    {
      "clip_ratio/high_max": 0.0023748470412101597,
      "clip_ratio/high_mean": 0.001128452357079368,
      "clip_ratio/low_mean": 0.0011828946808236651,
      "clip_ratio/low_min": 0.00012636093561013695,
      "clip_ratio/region_mean": 0.0023113470087992027,
      "epoch": 0.007373314900046083,
      "grad_norm": 0.12988649308681488,
      "learning_rate": 5e-07,
      "loss": 0.0024,
      "step": 79
    },
    {
      "clip_ratio/high_max": 0.0022680647889501415,
      "clip_ratio/high_mean": 0.0010344375150452834,
      "clip_ratio/low_mean": 0.001090762481908314,
      "clip_ratio/low_min": 7.425354851875454e-05,
      "clip_ratio/region_mean": 0.0021251999205560423,
      "epoch": 0.007466648000046667,
      "grad_norm": 0.11532434821128845,
      "learning_rate": 5e-07,
      "loss": -0.0338,
      "step": 80
    },
    {
      "clip_ratio/high_max": 0.002296016493346542,
      "clip_ratio/high_mean": 0.0010393249067419674,
      "clip_ratio/low_mean": 0.0012490443605202017,
      "clip_ratio/low_min": 9.417864202987403e-05,
      "clip_ratio/region_mean": 0.0022883692290633917,
      "epoch": 0.0075599811000472495,
      "grad_norm": 0.11901867389678955,
      "learning_rate": 5e-07,
      "loss": 0.0318,
      "step": 81
    },
    {
      "clip_ratio/high_max": 0.0021966580097796395,
      "clip_ratio/high_mean": 0.0009969421662390232,
      "clip_ratio/low_mean": 0.0013309508249221835,
      "clip_ratio/low_min": 0.0002690031451493269,
      "clip_ratio/region_mean": 0.0023278929802472703,
      "epoch": 0.007653314200047833,
      "grad_norm": 0.13352936506271362,
      "learning_rate": 5e-07,
      "loss": -0.0062,
      "step": 82
    },
    {
      "clip_ratio/high_max": 0.002099488578096498,
      "clip_ratio/high_mean": 0.0009423679784958949,
      "clip_ratio/low_mean": 0.0011725395852408838,
      "clip_ratio/low_min": 0.0001437969349353807,
      "clip_ratio/region_mean": 0.0021149075400899164,
      "epoch": 0.007746647300048416,
      "grad_norm": 0.12678295373916626,
      "learning_rate": 5e-07,
      "loss": 0.0136,
      "step": 83
    },
    {
      "clip_ratio/high_max": 0.002708719614020083,
      "clip_ratio/high_mean": 0.0010793738474603742,
      "clip_ratio/low_mean": 0.0013866012341168243,
      "clip_ratio/low_min": 0.0001480812188674463,
      "clip_ratio/region_mean": 0.0024659750488353893,
      "epoch": 0.007839980400049,
      "grad_norm": 0.1317744106054306,
      "learning_rate": 5e-07,
      "loss": 0.0419,
      "step": 84
    },
    {
      "clip_ratio/high_max": 0.0022036585869500414,
      "clip_ratio/high_mean": 0.000991479948424967,
      "clip_ratio/low_mean": 0.0012805028236471117,
      "clip_ratio/low_min": 0.00019102458963971003,
      "clip_ratio/region_mean": 0.0022719827538821846,
      "epoch": 0.007933313500049582,
      "grad_norm": 0.11160048097372055,
      "learning_rate": 5e-07,
      "loss": 0.0314,
      "step": 85
    },
    {
      "clip_ratio/high_max": 0.002775388893496711,
      "clip_ratio/high_mean": 0.0012422550753399264,
      "clip_ratio/low_mean": 0.0012076569837518036,
      "clip_ratio/low_min": 0.0002033398504863726,
      "clip_ratio/region_mean": 0.0024499120554537512,
      "epoch": 0.008026646600050166,
      "grad_norm": 0.13906563818454742,
      "learning_rate": 5e-07,
      "loss": 0.0025,
      "step": 86
    },
    {
      "clip_ratio/high_max": 0.0022970344507484697,
      "clip_ratio/high_mean": 0.0010770718836283777,
      "clip_ratio/low_mean": 0.0011708489109878428,
      "clip_ratio/low_min": 0.00014651220135419862,
      "clip_ratio/region_mean": 0.002247920747322496,
      "epoch": 0.00811997970005075,
      "grad_norm": 0.12402819097042084,
      "learning_rate": 5e-07,
      "loss": -0.0009,
      "step": 87
    },
    {
      "clip_ratio/high_max": 0.0024461422144668177,
      "clip_ratio/high_mean": 0.00101514063499053,
      "clip_ratio/low_mean": 0.0013357537391129881,
      "clip_ratio/low_min": 0.00021586126604233868,
      "clip_ratio/region_mean": 0.0023508943704655394,
      "epoch": 0.008213312800051333,
      "grad_norm": 0.12456418573856354,
      "learning_rate": 5e-07,
      "loss": 0.0163,
      "step": 88
    },
    {
      "clip_ratio/high_max": 0.0025537085166433826,
      "clip_ratio/high_mean": 0.001076538614142919,
      "clip_ratio/low_mean": 0.0013263593609735835,
      "clip_ratio/low_min": 0.00015644108498236164,
      "clip_ratio/region_mean": 0.0024028980114962906,
      "epoch": 0.008306645900051916,
      "grad_norm": 0.11856785416603088,
      "learning_rate": 5e-07,
      "loss": 0.0192,
      "step": 89
    },
    {
      "clip_ratio/high_max": 0.0024446777933917474,
      "clip_ratio/high_mean": 0.0009612389821995748,
      "clip_ratio/low_mean": 0.0012241247095516883,
      "clip_ratio/low_min": 0.00018455658664606744,
      "clip_ratio/region_mean": 0.00218536370084621,
      "epoch": 0.0083999790000525,
      "grad_norm": 0.12465070933103561,
      "learning_rate": 5e-07,
      "loss": 0.0485,
      "step": 90
    },
    {
      "clip_ratio/high_max": 0.0026461980742169544,
      "clip_ratio/high_mean": 0.0011171936421305872,
      "clip_ratio/low_mean": 0.0011743748946173582,
      "clip_ratio/low_min": 7.951643146952847e-05,
      "clip_ratio/region_mean": 0.0022915685403859243,
      "epoch": 0.008493312100053083,
      "grad_norm": 0.1256902813911438,
      "learning_rate": 5e-07,
      "loss": 0.0142,
      "step": 91
    },
    {
      "clip_ratio/high_max": 0.0024780954772722907,
      "clip_ratio/high_mean": 0.0011005165360984392,
      "clip_ratio/low_mean": 0.0012752193833875936,
      "clip_ratio/low_min": 0.0001688344373178552,
      "clip_ratio/region_mean": 0.002375735894020181,
      "epoch": 0.008586645200053667,
      "grad_norm": 0.1309235841035843,
      "learning_rate": 5e-07,
      "loss": -0.0263,
      "step": 92
    },
    {
      "clip_ratio/high_max": 0.0029797865063301288,
      "clip_ratio/high_mean": 0.0012096950031263987,
      "clip_ratio/low_mean": 0.0012057311905664392,
      "clip_ratio/low_min": 0.00020824838611588348,
      "clip_ratio/region_mean": 0.0024154262137017213,
      "epoch": 0.00867997830005425,
      "grad_norm": 0.1195213720202446,
      "learning_rate": 5e-07,
      "loss": 0.0211,
      "step": 93
    },
    {
      "clip_ratio/high_max": 0.002534489984100219,
      "clip_ratio/high_mean": 0.0011597538650676142,
      "clip_ratio/low_mean": 0.0014427923852053937,
      "clip_ratio/low_min": 0.00023026108192425454,
      "clip_ratio/region_mean": 0.0026025462721008807,
      "epoch": 0.008773311400054834,
      "grad_norm": 0.12071255594491959,
      "learning_rate": 5e-07,
      "loss": -0.0005,
      "step": 94
    },
    {
      "clip_ratio/high_max": 0.0024524624823243357,
      "clip_ratio/high_mean": 0.001121702905948041,
      "clip_ratio/low_mean": 0.0013662680248671677,
      "clip_ratio/low_min": 0.00023500568022427615,
      "clip_ratio/region_mean": 0.0024879709308152087,
      "epoch": 0.008866644500055417,
      "grad_norm": 0.13635654747486115,
      "learning_rate": 5e-07,
      "loss": 0.008,
      "step": 95
    },
    {
      "clip_ratio/high_max": 0.002598779392428696,
      "clip_ratio/high_mean": 0.0010154693645745283,
      "clip_ratio/low_mean": 0.0012739808225887828,
      "clip_ratio/low_min": 0.00021275135713949567,
      "clip_ratio/region_mean": 0.0022894501744303852,
      "epoch": 0.008959977600056,
      "grad_norm": 0.129990354180336,
      "learning_rate": 5e-07,
      "loss": 0.0009,
      "step": 96
    },
    {
      "clip_ratio/high_max": 0.0021549847115238663,
      "clip_ratio/high_mean": 0.0010301593883923488,
      "clip_ratio/low_mean": 0.0014871851526550017,
      "clip_ratio/low_min": 0.0003558852567948634,
      "clip_ratio/region_mean": 0.0025173444810207,
      "epoch": 0.009053310700056582,
      "grad_norm": 0.129111185669899,
      "learning_rate": 5e-07,
      "loss": 0.0428,
      "step": 97
    },
    {
      "clip_ratio/high_max": 0.0025563235067238566,
      "clip_ratio/high_mean": 0.0010540772273088805,
      "clip_ratio/low_mean": 0.0013315598225744907,
      "clip_ratio/low_min": 0.00024098535413941136,
      "clip_ratio/region_mean": 0.002385637089901138,
      "epoch": 0.009146643800057166,
      "grad_norm": 0.1353500932455063,
      "learning_rate": 5e-07,
      "loss": 0.003,
      "step": 98
    },
    {
      "clip_ratio/high_max": 0.0026769303367473185,
      "clip_ratio/high_mean": 0.0010587042743281927,
      "clip_ratio/low_mean": 0.0012661803266382776,
      "clip_ratio/low_min": 0.00019006153797818115,
      "clip_ratio/region_mean": 0.002324884640984237,
      "epoch": 0.00923997690005775,
      "grad_norm": 0.12006755918264389,
      "learning_rate": 5e-07,
      "loss": -0.0293,
      "step": 99
    },
    {
      "clip_ratio/high_max": 0.0026953160486300476,
      "clip_ratio/high_mean": 0.0012014795393042732,
      "clip_ratio/low_mean": 0.001342459741863422,
      "clip_ratio/low_min": 0.00023750920991005842,
      "clip_ratio/region_mean": 0.002543939321185462,
      "epoch": 0.009333310000058333,
      "grad_norm": 0.15012221038341522,
      "learning_rate": 5e-07,
      "loss": -0.0075,
      "step": 100
    },
    {
      "clip_ratio/high_max": 0.002166996830055723,
      "clip_ratio/high_mean": 0.0009384728455188451,
      "clip_ratio/low_mean": 0.0015477094748348463,
      "clip_ratio/low_min": 0.00027479269010655116,
      "clip_ratio/region_mean": 0.0024861823330866173,
      "epoch": 0.009426643100058916,
      "grad_norm": 0.12074936926364899,
      "learning_rate": 5e-07,
      "loss": 0.0568,
      "step": 101
    },
    {
      "clip_ratio/high_max": 0.0026382252108305693,
      "clip_ratio/high_mean": 0.0011568107747734757,
      "clip_ratio/low_mean": 0.0014936030347598717,
      "clip_ratio/low_min": 7.817660298314877e-05,
      "clip_ratio/region_mean": 0.0026504138368181884,
      "epoch": 0.0095199762000595,
      "grad_norm": 0.13050784170627594,
      "learning_rate": 5e-07,
      "loss": 0.0303,
      "step": 102
    },
    {
      "clip_ratio/high_max": 0.001957502659934107,
      "clip_ratio/high_mean": 0.0009051629713212606,
      "clip_ratio/low_mean": 0.001436136219126638,
      "clip_ratio/low_min": 0.00018278252537129447,
      "clip_ratio/region_mean": 0.002341299223189708,
      "epoch": 0.009613309300060083,
      "grad_norm": 0.1190953478217125,
      "learning_rate": 5e-07,
      "loss": 0.0348,
      "step": 103
    },
    {
      "clip_ratio/high_max": 0.002273327252623858,
      "clip_ratio/high_mean": 0.0010196054790867493,
      "clip_ratio/low_mean": 0.0013256217171147,
      "clip_ratio/low_min": 0.00010763765658339253,
      "clip_ratio/region_mean": 0.0023452272434951738,
      "epoch": 0.009706642400060667,
      "grad_norm": 0.12805341184139252,
      "learning_rate": 5e-07,
      "loss": 0.0285,
      "step": 104
    },
    {
      "clip_ratio/high_max": 0.0022776726545998827,
      "clip_ratio/high_mean": 0.0009950869134627283,
      "clip_ratio/low_mean": 0.0014829018837190233,
      "clip_ratio/low_min": 0.00028876905253127916,
      "clip_ratio/region_mean": 0.0024779887608019635,
      "epoch": 0.00979997550006125,
      "grad_norm": 0.12423422187566757,
      "learning_rate": 5e-07,
      "loss": 0.0441,
      "step": 105
    },
    {
      "clip_ratio/high_max": 0.0023935761710163206,
      "clip_ratio/high_mean": 0.001137234994530445,
      "clip_ratio/low_mean": 0.0016700000487617217,
      "clip_ratio/low_min": 0.0002555942455728655,
      "clip_ratio/region_mean": 0.0028072349887224846,
      "epoch": 0.009893308600061834,
      "grad_norm": 0.1323709785938263,
      "learning_rate": 5e-07,
      "loss": 0.0206,
      "step": 106
    },
    {
      "clip_ratio/high_max": 0.002575451144366525,
      "clip_ratio/high_mean": 0.001018319326249184,
      "clip_ratio/low_mean": 0.001634093830944039,
      "clip_ratio/low_min": 0.0002546525665820809,
      "clip_ratio/region_mean": 0.002652413153555244,
      "epoch": 0.009986641700062417,
      "grad_norm": 0.11691570281982422,
      "learning_rate": 5e-07,
      "loss": 0.0347,
      "step": 107
    },
    {
      "clip_ratio/high_max": 0.0021214307053014636,
      "clip_ratio/high_mean": 0.0010272968829667661,
      "clip_ratio/low_mean": 0.00147584681326407,
      "clip_ratio/low_min": 0.00018170075964007992,
      "clip_ratio/region_mean": 0.0025031436671270058,
      "epoch": 0.010079974800063,
      "grad_norm": 0.12382803857326508,
      "learning_rate": 5e-07,
      "loss": 0.029,
      "step": 108
    },
    {
      "clip_ratio/high_max": 0.002487895115336869,
      "clip_ratio/high_mean": 0.0010847688936337363,
      "clip_ratio/low_mean": 0.0015066080377437174,
      "clip_ratio/low_min": 0.00018612421899888432,
      "clip_ratio/region_mean": 0.002591376985947136,
      "epoch": 0.010173307900063584,
      "grad_norm": 0.1296684890985489,
      "learning_rate": 5e-07,
      "loss": -0.0019,
      "step": 109
    },
    {
      "clip_ratio/high_max": 0.0028748813274432905,
      "clip_ratio/high_mean": 0.0012657998231588863,
      "clip_ratio/low_mean": 0.0014215656447049696,
      "clip_ratio/low_min": 0.00023946550209075212,
      "clip_ratio/region_mean": 0.0026873654933297075,
      "epoch": 0.010266641000064166,
      "grad_norm": 0.12351743876934052,
      "learning_rate": 5e-07,
      "loss": 0.0082,
      "step": 110
    },
    {
      "clip_ratio/high_max": 0.0024750223819864914,
      "clip_ratio/high_mean": 0.001134090853156522,
      "clip_ratio/low_mean": 0.0013551445081247948,
      "clip_ratio/low_min": 0.00021855553950445028,
      "clip_ratio/region_mean": 0.0024892353321774863,
      "epoch": 0.010359974100064749,
      "grad_norm": 0.1726837158203125,
      "learning_rate": 5e-07,
      "loss": 0.0218,
      "step": 111
    },
    {
      "clip_ratio/high_max": 0.002315168829227332,
      "clip_ratio/high_mean": 0.0010333938007534016,
      "clip_ratio/low_mean": 0.0015072060559759848,
      "clip_ratio/low_min": 0.0003186524954799097,
      "clip_ratio/region_mean": 0.0025405998894711956,
      "epoch": 0.010453307200065333,
      "grad_norm": 0.12796907126903534,
      "learning_rate": 5e-07,
      "loss": 0.0158,
      "step": 112
    },
    {
      "clip_ratio/high_max": 0.002292687597218901,
      "clip_ratio/high_mean": 0.0010749856701295357,
      "clip_ratio/low_mean": 0.0015734193766547833,
      "clip_ratio/low_min": 0.0003067122797801858,
      "clip_ratio/region_mean": 0.002648405010404531,
      "epoch": 0.010546640300065916,
      "grad_norm": 0.12121100723743439,
      "learning_rate": 5e-07,
      "loss": 0.0671,
      "step": 113
    },
    {
      "clip_ratio/high_max": 0.0027194725917070173,
      "clip_ratio/high_mean": 0.0011251004107180052,
      "clip_ratio/low_mean": 0.0015620804042555392,
      "clip_ratio/low_min": 0.00032289028786181007,
      "clip_ratio/region_mean": 0.0026871808659052476,
      "epoch": 0.0106399734000665,
      "grad_norm": 0.1339324414730072,
      "learning_rate": 5e-07,
      "loss": 0.0666,
      "step": 114
    },
    {
      "clip_ratio/high_max": 0.002166919228329789,
      "clip_ratio/high_mean": 0.0009913146968756337,
      "clip_ratio/low_mean": 0.0012814230722142383,
      "clip_ratio/low_min": 0.0001245260937139392,
      "clip_ratio/region_mean": 0.002272737729072105,
      "epoch": 0.010733306500067083,
      "grad_norm": 0.11749096214771271,
      "learning_rate": 5e-07,
      "loss": 0.0335,
      "step": 115
    },
    {
      "clip_ratio/high_max": 0.002385891704761889,
      "clip_ratio/high_mean": 0.0011159872847201768,
      "clip_ratio/low_mean": 0.001374267834762577,
      "clip_ratio/low_min": 0.00020884394416498253,
      "clip_ratio/region_mean": 0.0024902551231207326,
      "epoch": 0.010826639600067666,
      "grad_norm": 0.11899379640817642,
      "learning_rate": 5e-07,
      "loss": 0.0111,
      "step": 116
    },
    {
      "clip_ratio/high_max": 0.002595802136056591,
      "clip_ratio/high_mean": 0.0011834060860564932,
      "clip_ratio/low_mean": 0.0014856145207886584,
      "clip_ratio/low_min": 0.000170563165738713,
      "clip_ratio/region_mean": 0.0026690206286730245,
      "epoch": 0.01091997270006825,
      "grad_norm": 0.14091242849826813,
      "learning_rate": 5e-07,
      "loss": -0.0009,
      "step": 117
    },
    {
      "clip_ratio/high_max": 0.0027306748561386485,
      "clip_ratio/high_mean": 0.0011011938804585952,
      "clip_ratio/low_mean": 0.0014302255549409892,
      "clip_ratio/low_min": 0.0002168411911043222,
      "clip_ratio/region_mean": 0.002531419406295754,
      "epoch": 0.011013305800068833,
      "grad_norm": 0.12953422963619232,
      "learning_rate": 5e-07,
      "loss": 0.0353,
      "step": 118
    },
    {
      "clip_ratio/high_max": 0.0023025077462079935,
      "clip_ratio/high_mean": 0.0010300851172360126,
      "clip_ratio/low_mean": 0.0014090684599068481,
      "clip_ratio/low_min": 0.00022285921841103118,
      "clip_ratio/region_mean": 0.002439153628074564,
      "epoch": 0.011106638900069417,
      "grad_norm": 0.12205630540847778,
      "learning_rate": 5e-07,
      "loss": 0.0232,
      "step": 119
    },
    {
      "clip_ratio/high_max": 0.002314680656127166,
      "clip_ratio/high_mean": 0.0009565232940076385,
      "clip_ratio/low_mean": 0.001443184297386324,
      "clip_ratio/low_min": 0.00021664601081283763,
      "clip_ratio/region_mean": 0.002399707525910344,
      "epoch": 0.01119997200007,
      "grad_norm": 0.12105290591716766,
      "learning_rate": 5e-07,
      "loss": 0.0359,
      "step": 120
    },
    {
      "clip_ratio/high_max": 0.0025490108673693612,
      "clip_ratio/high_mean": 0.001082039514585631,
      "clip_ratio/low_mean": 0.0015824842485017143,
      "clip_ratio/low_min": 0.00023674450221733423,
      "clip_ratio/region_mean": 0.002664523803105112,
      "epoch": 0.011293305100070584,
      "grad_norm": 0.13456633687019348,
      "learning_rate": 5e-07,
      "loss": 0.0151,
      "step": 121
    },
    {
      "clip_ratio/high_max": 0.0025998850469477475,
      "clip_ratio/high_mean": 0.0011553338626981713,
      "clip_ratio/low_mean": 0.0014193643801263534,
      "clip_ratio/low_min": 0.0002025715939453221,
      "clip_ratio/region_mean": 0.00257469825737644,
      "epoch": 0.011386638200071167,
      "grad_norm": 0.1322651505470276,
      "learning_rate": 5e-07,
      "loss": -0.0115,
      "step": 122
    },
    {
      "clip_ratio/high_max": 0.0023248876095749438,
      "clip_ratio/high_mean": 0.0010805251476995181,
      "clip_ratio/low_mean": 0.0014922977716196328,
      "clip_ratio/low_min": 0.00023309500829782337,
      "clip_ratio/region_mean": 0.002572822901129257,
      "epoch": 0.011479971300071749,
      "grad_norm": 0.12255769968032837,
      "learning_rate": 5e-07,
      "loss": 0.0366,
      "step": 123
    },
    {
      "clip_ratio/high_max": 0.002669416418939363,
      "clip_ratio/high_mean": 0.0012685635992966127,
      "clip_ratio/low_mean": 0.0012926711606269237,
      "clip_ratio/low_min": 0.00023803954354661983,
      "clip_ratio/region_mean": 0.002561234708991833,
      "epoch": 0.011573304400072332,
      "grad_norm": 0.12177974730730057,
      "learning_rate": 5e-07,
      "loss": -0.0521,
      "step": 124
    },
    {
      "clip_ratio/high_max": 0.0023120435907912906,
      "clip_ratio/high_mean": 0.0011855283100885572,
      "clip_ratio/low_mean": 0.0014949812175473198,
      "clip_ratio/low_min": 0.0002510824078854057,
      "clip_ratio/region_mean": 0.0026805094748851843,
      "epoch": 0.011666637500072916,
      "grad_norm": 0.13553203642368317,
      "learning_rate": 5e-07,
      "loss": -0.019,
      "step": 125
    },
    {
      "clip_ratio/high_max": 0.0021096376367495395,
      "clip_ratio/high_mean": 0.0010372926590207499,
      "clip_ratio/low_mean": 0.0013598010737041477,
      "clip_ratio/low_min": 0.00038542115453310544,
      "clip_ratio/region_mean": 0.002397093645413406,
      "epoch": 0.0117599706000735,
      "grad_norm": 0.11472073197364807,
      "learning_rate": 5e-07,
      "loss": 0.0175,
      "step": 126
    },
    {
      "clip_ratio/high_max": 0.002296041373483604,
      "clip_ratio/high_mean": 0.0010241186027997173,
      "clip_ratio/low_mean": 0.0012443429586710408,
      "clip_ratio/low_min": 0.00011252668900851859,
      "clip_ratio/region_mean": 0.0022684615396428853,
      "epoch": 0.011853303700074083,
      "grad_norm": 0.1166045218706131,
      "learning_rate": 5e-07,
      "loss": -0.0096,
      "step": 127
    },
    {
      "clip_ratio/high_max": 0.0024004552833503112,
      "clip_ratio/high_mean": 0.00105316757253604,
      "clip_ratio/low_mean": 0.0015338298508140724,
      "clip_ratio/low_min": 0.0003336137638143555,
      "clip_ratio/region_mean": 0.0025869973906083032,
      "epoch": 0.011946636800074666,
      "grad_norm": 0.12532462179660797,
      "learning_rate": 5e-07,
      "loss": 0.0506,
      "step": 128
    },
    {
      "clip_ratio/high_max": 0.002153919580450747,
      "clip_ratio/high_mean": 0.0007974934660524013,
      "clip_ratio/low_mean": 0.000912113806407433,
      "clip_ratio/low_min": 0.00010770947756100213,
      "clip_ratio/region_mean": 0.001709607218799647,
      "completions/clipped_ratio": 0.014055524553571397,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4072.0,
      "completions/mean_length": 614.457763671875,
      "completions/mean_terminated_length": 564.8252563476562,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.01203996990007525,
      "grad_norm": 0.11689578741788864,
      "learning_rate": 5e-07,
      "loss": 0.075,
      "num_tokens": 162393722.0,
      "reward": 0.5500662922859192,
      "reward_std": 0.21742552518844604,
      "rewards/simpleverify_reward/mean": 0.5500662922859192,
      "rewards/simpleverify_reward/std": 0.49748921394348145,
      "step": 129
    },
    {
      "clip_ratio/high_max": 0.002002122939302353,
      "clip_ratio/high_mean": 0.0008668511709402082,
      "clip_ratio/low_mean": 0.0007093915774021298,
      "clip_ratio/low_min": 7.695239492022665e-05,
      "clip_ratio/region_mean": 0.0015762427501613274,
      "epoch": 0.012133303000075833,
      "grad_norm": 0.10081608593463898,
      "learning_rate": 5e-07,
      "loss": -0.0104,
      "step": 130
    },
    {
      "clip_ratio/high_max": 0.0021822334456373937,
      "clip_ratio/high_mean": 0.0009703424711915432,
      "clip_ratio/low_mean": 0.0008623792509752093,
      "clip_ratio/low_min": 9.37098047870677e-05,
      "clip_ratio/region_mean": 0.0018327217403566465,
      "epoch": 0.012226636100076417,
      "grad_norm": 0.11417268216609955,
      "learning_rate": 5e-07,
      "loss": 0.0218,
      "step": 131
    },
    {
      "clip_ratio/high_max": 0.0024234303054981865,
      "clip_ratio/high_mean": 0.0009511006974207703,
      "clip_ratio/low_mean": 0.0007383790070889518,
      "clip_ratio/low_min": 4.945844193571247e-05,
      "clip_ratio/region_mean": 0.0016894796935957856,
      "epoch": 0.012319969200077,
      "grad_norm": 0.10109081119298935,
      "learning_rate": 5e-07,
      "loss": -0.0049,
      "step": 132
    },
    {
      "clip_ratio/high_max": 0.002655429700098466,
      "clip_ratio/high_mean": 0.0011219105035706889,
      "clip_ratio/low_mean": 0.0008986795619421173,
      "clip_ratio/low_min": 0.00015564270688628312,
      "clip_ratio/region_mean": 0.0020205900800647214,
      "epoch": 0.012413302300077584,
      "grad_norm": 0.12802833318710327,
      "learning_rate": 5e-07,
      "loss": -0.0018,
      "step": 133
    },
    {
      "clip_ratio/high_max": 0.002078576828353107,
      "clip_ratio/high_mean": 0.0008778611481830012,
      "clip_ratio/low_mean": 0.0008351637170562753,
      "clip_ratio/low_min": 1.0269471204082947e-05,
      "clip_ratio/region_mean": 0.001713024848868372,
      "epoch": 0.012506635400078167,
      "grad_norm": 0.10485940426588058,
      "learning_rate": 5e-07,
      "loss": 0.021,
      "step": 134
    },
    {
      "clip_ratio/high_max": 0.0022620212585025,
      "clip_ratio/high_mean": 0.0009657216105551925,
      "clip_ratio/low_mean": 0.000824805452793953,
      "clip_ratio/low_min": 0.00011993169027846307,
      "clip_ratio/region_mean": 0.0017905270506162196,
      "epoch": 0.01259996850007875,
      "grad_norm": 0.12543174624443054,
      "learning_rate": 5e-07,
      "loss": 0.035,
      "step": 135
    },
    {
      "clip_ratio/high_max": 0.001863648896687664,
      "clip_ratio/high_mean": 0.0008562779585190583,
      "clip_ratio/low_mean": 0.000842409732285887,
      "clip_ratio/low_min": 6.916192160133505e-05,
      "clip_ratio/region_mean": 0.0016986877308227122,
      "epoch": 0.012693301600079332,
      "grad_norm": 0.1169026792049408,
      "learning_rate": 5e-07,
      "loss": 0.0212,
      "step": 136
    },
    {
      "clip_ratio/high_max": 0.0018877912189054769,
      "clip_ratio/high_mean": 0.0008375529723707587,
      "clip_ratio/low_mean": 0.0009374200417369138,
      "clip_ratio/low_min": 0.00012157044693594798,
      "clip_ratio/region_mean": 0.0017749730468494818,
      "epoch": 0.012786634700079916,
      "grad_norm": 0.10724788159132004,
      "learning_rate": 5e-07,
      "loss": 0.1028,
      "step": 137
    },
    {
      "clip_ratio/high_max": 0.0020127961252001114,
      "clip_ratio/high_mean": 0.0008879662054823712,
      "clip_ratio/low_mean": 0.0008498256993334508,
      "clip_ratio/low_min": 9.231387684849324e-05,
      "clip_ratio/region_mean": 0.001737791913910769,
      "epoch": 0.0128799678000805,
      "grad_norm": 0.12312629073858261,
      "learning_rate": 5e-07,
      "loss": 0.018,
      "step": 138
    },
    {
      "clip_ratio/high_max": 0.0028305490341153927,
      "clip_ratio/high_mean": 0.0011172006343258545,
      "clip_ratio/low_mean": 0.0007804419947206043,
      "clip_ratio/low_min": 0.00012690585299424129,
      "clip_ratio/region_mean": 0.0018976426290464588,
      "epoch": 0.012973300900081083,
      "grad_norm": 0.12111968547105789,
      "learning_rate": 5e-07,
      "loss": -0.0259,
      "step": 139
    },
    {
      "clip_ratio/high_max": 0.0023127301756176166,
      "clip_ratio/high_mean": 0.0009601474848750513,
      "clip_ratio/low_mean": 0.000796138647274347,
      "clip_ratio/low_min": 5.4781480685051065e-05,
      "clip_ratio/region_mean": 0.0017562861685291864,
      "epoch": 0.013066634000081666,
      "grad_norm": 0.10919897258281708,
      "learning_rate": 5e-07,
      "loss": 0.0262,
      "step": 140
    },
    {
      "clip_ratio/high_max": 0.0022265502957452554,
      "clip_ratio/high_mean": 0.001003707982818014,
      "clip_ratio/low_mean": 0.0007983972809597617,
      "clip_ratio/low_min": 9.814611439651344e-05,
      "clip_ratio/region_mean": 0.0018021052746917121,
      "epoch": 0.01315996710008225,
      "grad_norm": 0.11768512427806854,
      "learning_rate": 5e-07,
      "loss": 0.0257,
      "step": 141
    },
    {
      "clip_ratio/high_max": 0.002220704496721737,
      "clip_ratio/high_mean": 0.0009230939031112939,
      "clip_ratio/low_mean": 0.0008826995708659524,
      "clip_ratio/low_min": 6.104383282945491e-05,
      "clip_ratio/region_mean": 0.0018057935012620874,
      "epoch": 0.013253300200082833,
      "grad_norm": 0.1267189085483551,
      "learning_rate": 5e-07,
      "loss": 0.055,
      "step": 142
    },
    {
      "clip_ratio/high_max": 0.0019093906703346875,
      "clip_ratio/high_mean": 0.0008492001270496985,
      "clip_ratio/low_mean": 0.0009797839429666055,
      "clip_ratio/low_min": 0.00012224068359500961,
      "clip_ratio/region_mean": 0.0018289840663783252,
      "epoch": 0.013346633300083417,
      "grad_norm": 0.1223205104470253,
      "learning_rate": 5e-07,
      "loss": 0.0132,
      "step": 143
    },
    {
      "clip_ratio/high_max": 0.002459260715113487,
      "clip_ratio/high_mean": 0.0010135477750736754,
      "clip_ratio/low_mean": 0.0008596466923336266,
      "clip_ratio/low_min": 8.078026439761743e-05,
      "clip_ratio/region_mean": 0.001873194494692143,
      "epoch": 0.013439966400084,
      "grad_norm": 0.11688388139009476,
      "learning_rate": 5e-07,
      "loss": 0.0275,
      "step": 144
    },
    {
      "clip_ratio/high_max": 0.0021306275302777067,
      "clip_ratio/high_mean": 0.0008705116906639887,
      "clip_ratio/low_mean": 0.0008257360823336057,
      "clip_ratio/low_min": 7.233039377751993e-05,
      "clip_ratio/region_mean": 0.0016962478148343507,
      "epoch": 0.013533299500084583,
      "grad_norm": 0.11077112704515457,
      "learning_rate": 5e-07,
      "loss": 0.046,
      "step": 145
    },
    {
      "clip_ratio/high_max": 0.0025101525461650454,
      "clip_ratio/high_mean": 0.0011343760161253158,
      "clip_ratio/low_mean": 0.0006957883797440445,
      "clip_ratio/low_min": 6.514228061860194e-05,
      "clip_ratio/region_mean": 0.001830164394050371,
      "epoch": 0.013626632600085167,
      "grad_norm": 0.11467385292053223,
      "learning_rate": 5e-07,
      "loss": -0.0431,
      "step": 146
    },
    {
      "clip_ratio/high_max": 0.001990196768019814,
      "clip_ratio/high_mean": 0.0008625564823887544,
      "clip_ratio/low_mean": 0.0008704792926437221,
      "clip_ratio/low_min": 0.00016380300894525135,
      "clip_ratio/region_mean": 0.0017330357513856143,
      "epoch": 0.01371996570008575,
      "grad_norm": 0.10254763066768646,
      "learning_rate": 5e-07,
      "loss": 0.0502,
      "step": 147
    },
    {
      "clip_ratio/high_max": 0.0018684102287807036,
      "clip_ratio/high_mean": 0.0007994091920409119,
      "clip_ratio/low_mean": 0.000872166121553164,
      "clip_ratio/low_min": 6.156293966341764e-05,
      "clip_ratio/region_mean": 0.0016715753736207262,
      "epoch": 0.013813298800086334,
      "grad_norm": 0.11307911574840546,
      "learning_rate": 5e-07,
      "loss": 0.06,
      "step": 148
    },
    {
      "clip_ratio/high_max": 0.001979718308575684,
      "clip_ratio/high_mean": 0.0008878218686731998,
      "clip_ratio/low_mean": 0.0008596527550253086,
      "clip_ratio/low_min": 0.00014250352160161128,
      "clip_ratio/region_mean": 0.0017474746091465931,
      "epoch": 0.013906631900086916,
      "grad_norm": 0.11558219790458679,
      "learning_rate": 5e-07,
      "loss": 0.0157,
      "step": 149
    },
    {
      "clip_ratio/high_max": 0.0022981379806878977,
      "clip_ratio/high_mean": 0.0008942226559156552,
      "clip_ratio/low_mean": 0.0008366888323507737,
      "clip_ratio/low_min": 8.745946070121136e-05,
      "clip_ratio/region_mean": 0.0017309114555246197,
      "epoch": 0.013999965000087499,
      "grad_norm": 0.11012327671051025,
      "learning_rate": 5e-07,
      "loss": 0.0296,
      "step": 150
    },
    {
      "clip_ratio/high_max": 0.002042670297669247,
      "clip_ratio/high_mean": 0.0008666450394230196,
      "clip_ratio/low_mean": 0.000854277575854212,
      "clip_ratio/low_min": 0.00017672132344159763,
      "clip_ratio/region_mean": 0.0017209226280101575,
      "epoch": 0.014093298100088083,
      "grad_norm": 0.11609277874231339,
      "learning_rate": 5e-07,
      "loss": 0.0136,
      "step": 151
    },
    {
      "clip_ratio/high_max": 0.00229095941176638,
      "clip_ratio/high_mean": 0.0010314529772585956,
      "clip_ratio/low_mean": 0.0008121997070702491,
      "clip_ratio/low_min": 8.540014732716372e-05,
      "clip_ratio/region_mean": 0.0018436527461744845,
      "epoch": 0.014186631200088666,
      "grad_norm": 0.10850070416927338,
      "learning_rate": 5e-07,
      "loss": 0.0168,
      "step": 152
    },
    {
      "clip_ratio/high_max": 0.0018864615994971246,
      "clip_ratio/high_mean": 0.0007937110203783959,
      "clip_ratio/low_mean": 0.0009887161759252194,
      "clip_ratio/low_min": 0.00010103424392582383,
      "clip_ratio/region_mean": 0.0017824271963036153,
      "epoch": 0.01427996430008925,
      "grad_norm": 0.1146760806441307,
      "learning_rate": 5e-07,
      "loss": 0.0506,
      "step": 153
    },
    {
      "clip_ratio/high_max": 0.002011881551879924,
      "clip_ratio/high_mean": 0.0008949592356657377,
      "clip_ratio/low_mean": 0.0009098495011130581,
      "clip_ratio/low_min": 7.121343332983088e-05,
      "clip_ratio/region_mean": 0.0018048086712951772,
      "epoch": 0.014373297400089833,
      "grad_norm": 0.11963153630495071,
      "learning_rate": 5e-07,
      "loss": 0.0189,
      "step": 154
    },
    {
      "clip_ratio/high_max": 0.0017492197730462067,
      "clip_ratio/high_mean": 0.000784348680099356,
      "clip_ratio/low_mean": 0.0009556624863762408,
      "clip_ratio/low_min": 7.435537145283888e-05,
      "clip_ratio/region_mean": 0.0017400111464667134,
      "epoch": 0.014466630500090416,
      "grad_norm": 0.11600226163864136,
      "learning_rate": 5e-07,
      "loss": 0.0508,
      "step": 155
    },
    {
      "clip_ratio/high_max": 0.0018075085135933477,
      "clip_ratio/high_mean": 0.0008412392962782178,
      "clip_ratio/low_mean": 0.0008769933992880397,
      "clip_ratio/low_min": 7.937935879454017e-05,
      "clip_ratio/region_mean": 0.0017182327101181727,
      "epoch": 0.014559963600091,
      "grad_norm": 0.11119470000267029,
      "learning_rate": 5e-07,
      "loss": 0.0171,
      "step": 156
    },
    {
      "clip_ratio/high_max": 0.0023464128171326593,
      "clip_ratio/high_mean": 0.0008651619482407114,
      "clip_ratio/low_mean": 0.000899867714906577,
      "clip_ratio/low_min": 6.962556290091015e-05,
      "clip_ratio/region_mean": 0.0017650296722422354,
      "epoch": 0.014653296700091583,
      "grad_norm": 0.11723461747169495,
      "learning_rate": 5e-07,
      "loss": -0.0131,
      "step": 157
    },
    {
      "clip_ratio/high_max": 0.0023492350373999216,
      "clip_ratio/high_mean": 0.0008632511708128732,
      "clip_ratio/low_mean": 0.0009240696344932076,
      "clip_ratio/low_min": 0.00010343534086132422,
      "clip_ratio/region_mean": 0.0017873207980301231,
      "epoch": 0.014746629800092167,
      "grad_norm": 0.10900822281837463,
      "learning_rate": 5e-07,
      "loss": 0.0054,
      "step": 158
    },
    {
      "clip_ratio/high_max": 0.0021065360560896806,
      "clip_ratio/high_mean": 0.0008207268201658735,
      "clip_ratio/low_mean": 0.0009075796115212142,
      "clip_ratio/low_min": 7.242085075631621e-05,
      "clip_ratio/region_mean": 0.0017283064444200136,
      "epoch": 0.01483996290009275,
      "grad_norm": 0.12333115935325623,
      "learning_rate": 5e-07,
      "loss": 0.0543,
      "step": 159
    },
    {
      "clip_ratio/high_max": 0.002101031619531568,
      "clip_ratio/high_mean": 0.0008595928829890909,
      "clip_ratio/low_mean": 0.0009795862370083341,
      "clip_ratio/low_min": 0.00015727686059108237,
      "clip_ratio/region_mean": 0.001839179138187319,
      "epoch": 0.014933296000093334,
      "grad_norm": 0.11890401691198349,
      "learning_rate": 5e-07,
      "loss": 0.0507,
      "step": 160
    },
    {
      "clip_ratio/high_max": 0.0034569307827041484,
      "clip_ratio/high_mean": 0.0015178298199316487,
      "clip_ratio/low_mean": 0.0018363598064752296,
      "clip_ratio/low_min": 0.00020827653497690335,
      "clip_ratio/region_mean": 0.0033541895681992173,
      "completions/clipped_ratio": 0.014256068638392905,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4076.0,
      "completions/mean_length": 615.0701293945312,
      "completions/mean_terminated_length": 564.7280883789062,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.015026629100093917,
      "grad_norm": 0.2674914300441742,
      "learning_rate": 5e-07,
      "loss": 0.0461,
      "num_tokens": 244398385.0,
      "reward": 0.552743136882782,
      "reward_std": 0.215730682015419,
      "rewards/simpleverify_reward/mean": 0.5527430772781372,
      "rewards/simpleverify_reward/std": 0.49721258878707886,
      "step": 161
    },
    {
      "clip_ratio/high_max": 0.0021599774772766978,
      "clip_ratio/high_mean": 0.0008616003924544202,
      "clip_ratio/low_mean": 0.0011345498824084643,
      "clip_ratio/low_min": 9.50594803725835e-05,
      "clip_ratio/region_mean": 0.001996150291233789,
      "epoch": 0.015119962200094499,
      "grad_norm": 0.10939040780067444,
      "learning_rate": 5e-07,
      "loss": 0.0104,
      "step": 162
    },
    {
      "clip_ratio/high_max": 0.0023035035192151554,
      "clip_ratio/high_mean": 0.0009989535756176338,
      "clip_ratio/low_mean": 0.0011698196904035285,
      "clip_ratio/low_min": 0.00017132110360762454,
      "clip_ratio/region_mean": 0.0021687732587452047,
      "epoch": 0.015213295300095082,
      "grad_norm": 0.11795772612094879,
      "learning_rate": 5e-07,
      "loss": 0.0917,
      "step": 163
    },
    {
      "clip_ratio/high_max": 0.002214032763731666,
      "clip_ratio/high_mean": 0.0008846298769640271,
      "clip_ratio/low_mean": 0.0010562563511484768,
      "clip_ratio/low_min": 6.728969128744211e-05,
      "clip_ratio/region_mean": 0.0019408862281125039,
      "epoch": 0.015306628400095666,
      "grad_norm": 0.10871589928865433,
      "learning_rate": 5e-07,
      "loss": 0.0379,
      "step": 164
    },
    {
      "clip_ratio/high_max": 0.002157899893063586,
      "clip_ratio/high_mean": 0.0010107143716595601,
      "clip_ratio/low_mean": 0.0009032580528582912,
      "clip_ratio/low_min": 1.252003221452469e-05,
      "clip_ratio/region_mean": 0.0019139724026899785,
      "epoch": 0.01539996150009625,
      "grad_norm": 0.11238904297351837,
      "learning_rate": 5e-07,
      "loss": -0.0121,
      "step": 165
    },
    {
      "clip_ratio/high_max": 0.002301786153111607,
      "clip_ratio/high_mean": 0.00105840947071556,
      "clip_ratio/low_mean": 0.0009453494058107026,
      "clip_ratio/low_min": 4.842856060349732e-05,
      "clip_ratio/region_mean": 0.002003758891078178,
      "epoch": 0.015493294600096833,
      "grad_norm": 0.12158586084842682,
      "learning_rate": 5e-07,
      "loss": 0.0153,
      "step": 166
    },
    {
      "clip_ratio/high_max": 0.0022751595388399437,
      "clip_ratio/high_mean": 0.0009421000468137208,
      "clip_ratio/low_mean": 0.0010033131529780803,
      "clip_ratio/low_min": 8.00683737907093e-05,
      "clip_ratio/region_mean": 0.0019454131834208965,
      "epoch": 0.015586627700097416,
      "grad_norm": 0.1397205889225006,
      "learning_rate": 5e-07,
      "loss": 0.0466,
      "step": 167
    },
    {
      "clip_ratio/high_max": 0.002050200550002046,
      "clip_ratio/high_mean": 0.0007785667439748067,
      "clip_ratio/low_mean": 0.0009601382735127117,
      "clip_ratio/low_min": 0.00016853667239047354,
      "clip_ratio/region_mean": 0.0017387049665558152,
      "epoch": 0.015679960800098,
      "grad_norm": 0.11066383868455887,
      "learning_rate": 5e-07,
      "loss": 0.0567,
      "step": 168
    },
    {
      "clip_ratio/high_max": 0.0023223855860123876,
      "clip_ratio/high_mean": 0.0008714617742953124,
      "clip_ratio/low_mean": 0.0009335087779618334,
      "clip_ratio/low_min": 8.300014997075778e-05,
      "clip_ratio/region_mean": 0.0018049706050078385,
      "epoch": 0.015773293900098583,
      "grad_norm": 0.11361458897590637,
      "learning_rate": 5e-07,
      "loss": 0.0088,
      "step": 169
    },
    {
      "clip_ratio/high_max": 0.0019102153819403611,
      "clip_ratio/high_mean": 0.0008207848304664367,
      "clip_ratio/low_mean": 0.000980052196609904,
      "clip_ratio/low_min": 9.58594946496305e-05,
      "clip_ratio/region_mean": 0.0018008370461757295,
      "epoch": 0.015866627000099165,
      "grad_norm": 0.11319403350353241,
      "learning_rate": 5e-07,
      "loss": 0.0134,
      "step": 170
    },
    {
      "clip_ratio/high_max": 0.0020829680433962494,
      "clip_ratio/high_mean": 0.0008945219560700934,
      "clip_ratio/low_mean": 0.0009017955908348085,
      "clip_ratio/low_min": 7.628241837664973e-05,
      "clip_ratio/region_mean": 0.0017963175414479338,
      "epoch": 0.01595996010009975,
      "grad_norm": 0.12089566141366959,
      "learning_rate": 5e-07,
      "loss": 0.0153,
      "step": 171
    },
    {
      "clip_ratio/high_max": 0.0021166957958485,
      "clip_ratio/high_mean": 0.0008523442647856427,
      "clip_ratio/low_mean": 0.0009220502743119141,
      "clip_ratio/low_min": 0.000131213387248863,
      "clip_ratio/region_mean": 0.0017743945281836204,
      "epoch": 0.016053293200100332,
      "grad_norm": 0.1047394648194313,
      "learning_rate": 5e-07,
      "loss": 0.0364,
      "step": 172
    },
    {
      "clip_ratio/high_max": 0.0020717995066661388,
      "clip_ratio/high_mean": 0.0007968577392603038,
      "clip_ratio/low_mean": 0.0008425676624028711,
      "clip_ratio/low_min": 0.0001159205849035061,
      "clip_ratio/region_mean": 0.0016394253907492384,
      "epoch": 0.016146626300100917,
      "grad_norm": 0.12526874244213104,
      "learning_rate": 5e-07,
      "loss": 0.023,
      "step": 173
    },
    {
      "clip_ratio/high_max": 0.0021654336305800825,
      "clip_ratio/high_mean": 0.0009302831422246527,
      "clip_ratio/low_mean": 0.0009509318424534285,
      "clip_ratio/low_min": 0.00014945693692425266,
      "clip_ratio/region_mean": 0.0018812150119629223,
      "epoch": 0.0162399594001015,
      "grad_norm": 0.11544369161128998,
      "learning_rate": 5e-07,
      "loss": 0.0362,
      "step": 174
    },
    {
      "clip_ratio/high_max": 0.002408534008282004,
      "clip_ratio/high_mean": 0.0009669560113252373,
      "clip_ratio/low_mean": 0.0008986673819890711,
      "clip_ratio/low_min": 0.00010049782395071816,
      "clip_ratio/region_mean": 0.0018656233805813827,
      "epoch": 0.016333292500102084,
      "grad_norm": 0.12287069857120514,
      "learning_rate": 5e-07,
      "loss": 0.0445,
      "step": 175
    },
    {
      "clip_ratio/high_max": 0.0017385050741722807,
      "clip_ratio/high_mean": 0.0007889959142630687,
      "clip_ratio/low_mean": 0.0008798655453574611,
      "clip_ratio/low_min": 5.1939192417194135e-05,
      "clip_ratio/region_mean": 0.0016688614341546781,
      "epoch": 0.016426625600102666,
      "grad_norm": 0.10376554727554321,
      "learning_rate": 5e-07,
      "loss": 0.0201,
      "step": 176
    },
    {
      "clip_ratio/high_max": 0.0021174577632336877,
      "clip_ratio/high_mean": 0.0009457621708861552,
      "clip_ratio/low_mean": 0.00081766441144282,
      "clip_ratio/low_min": 6.547914472321281e-05,
      "clip_ratio/region_mean": 0.0017634266114328057,
      "epoch": 0.01651995870010325,
      "grad_norm": 0.11298652738332748,
      "learning_rate": 5e-07,
      "loss": 0.0144,
      "step": 177
    },
    {
      "clip_ratio/high_max": 0.002245139294245746,
      "clip_ratio/high_mean": 0.0009512300912319915,
      "clip_ratio/low_mean": 0.0007339150788538973,
      "clip_ratio/low_min": 8.556352804589551e-05,
      "clip_ratio/region_mean": 0.0016851451982802246,
      "epoch": 0.016613291800103833,
      "grad_norm": 0.11263740062713623,
      "learning_rate": 5e-07,
      "loss": 0.0575,
      "step": 178
    },
    {
      "clip_ratio/high_max": 0.0022678119166812394,
      "clip_ratio/high_mean": 0.0010191783039772417,
      "clip_ratio/low_mean": 0.0008141766356857261,
      "clip_ratio/low_min": 6.738790307281306e-05,
      "clip_ratio/region_mean": 0.0018333549305680208,
      "epoch": 0.016706624900104418,
      "grad_norm": 0.11834652721881866,
      "learning_rate": 5e-07,
      "loss": 0.0337,
      "step": 179
    },
    {
      "clip_ratio/high_max": 0.0019989008505945094,
      "clip_ratio/high_mean": 0.0007576127463835292,
      "clip_ratio/low_mean": 0.0008812334817775991,
      "clip_ratio/low_min": 0.00016327199682564242,
      "clip_ratio/region_mean": 0.0016388462245231494,
      "epoch": 0.016799958000105,
      "grad_norm": 0.1097591295838356,
      "learning_rate": 5e-07,
      "loss": 0.0564,
      "step": 180
    },
    {
      "clip_ratio/high_max": 0.002342514562769793,
      "clip_ratio/high_mean": 0.0009171573619823903,
      "clip_ratio/low_mean": 0.0008854428997437935,
      "clip_ratio/low_min": 0.000168380655850342,
      "clip_ratio/region_mean": 0.0018026002435362898,
      "epoch": 0.016893291100105585,
      "grad_norm": 0.11711994558572769,
      "learning_rate": 5e-07,
      "loss": 0.0064,
      "step": 181
    },
    {
      "clip_ratio/high_max": 0.002050697170489002,
      "clip_ratio/high_mean": 0.000824927863504854,
      "clip_ratio/low_mean": 0.0007477167055185419,
      "clip_ratio/low_min": 4.4920439904672094e-05,
      "clip_ratio/region_mean": 0.001572644614498131,
      "epoch": 0.016986624200106167,
      "grad_norm": 0.11162655055522919,
      "learning_rate": 5e-07,
      "loss": 0.0157,
      "step": 182
    },
    {
      "clip_ratio/high_max": 0.0021006221140851267,
      "clip_ratio/high_mean": 0.0009737851287354715,
      "clip_ratio/low_mean": 0.0008901680212147767,
      "clip_ratio/low_min": 7.798770820954815e-05,
      "clip_ratio/region_mean": 0.0018639531845110469,
      "epoch": 0.017079957300106748,
      "grad_norm": 0.11470585316419601,
      "learning_rate": 5e-07,
      "loss": 0.0356,
      "step": 183
    },
    {
      "clip_ratio/high_max": 0.002239068991912063,
      "clip_ratio/high_mean": 0.0009967679216060787,
      "clip_ratio/low_mean": 0.0008875590428942814,
      "clip_ratio/low_min": 3.8765785575378686e-05,
      "clip_ratio/region_mean": 0.0018843269281205721,
      "epoch": 0.017173290400107333,
      "grad_norm": 0.11875976622104645,
      "learning_rate": 5e-07,
      "loss": -0.0054,
      "step": 184
    },
    {
      "clip_ratio/high_max": 0.00213489678571932,
      "clip_ratio/high_mean": 0.00090658357112261,
      "clip_ratio/low_mean": 0.0007838119418011047,
      "clip_ratio/low_min": 1.3067112377029844e-05,
      "clip_ratio/region_mean": 0.0016903954892768525,
      "epoch": 0.017266623500107915,
      "grad_norm": 0.11648296564817429,
      "learning_rate": 5e-07,
      "loss": 0.0006,
      "step": 185
    },
    {
      "clip_ratio/high_max": 0.002091740221658256,
      "clip_ratio/high_mean": 0.0009380628653161693,
      "clip_ratio/low_mean": 0.0008624584297649562,
      "clip_ratio/low_min": 4.05342243539053e-05,
      "clip_ratio/region_mean": 0.0018005213350988925,
      "epoch": 0.0173599566001085,
      "grad_norm": 0.11285771429538727,
      "learning_rate": 5e-07,
      "loss": 0.0184,
      "step": 186
    },
    {
      "clip_ratio/high_max": 0.0019178563888999633,
      "clip_ratio/high_mean": 0.000863129309436772,
      "clip_ratio/low_mean": 0.0008729552919248817,
      "clip_ratio/low_min": 4.640454062609933e-05,
      "clip_ratio/region_mean": 0.0017360845813527703,
      "epoch": 0.017453289700109082,
      "grad_norm": 0.10958214104175568,
      "learning_rate": 5e-07,
      "loss": 0.0716,
      "step": 187
    },
    {
      "clip_ratio/high_max": 0.001795687603589613,
      "clip_ratio/high_mean": 0.0007577183378089103,
      "clip_ratio/low_mean": 0.0009734679879329633,
      "clip_ratio/low_min": 0.00015119925865292316,
      "clip_ratio/region_mean": 0.0017311863412032835,
      "epoch": 0.017546622800109667,
      "grad_norm": 0.10828448086977005,
      "learning_rate": 5e-07,
      "loss": 0.0454,
      "step": 188
    },
    {
      "clip_ratio/high_max": 0.0017439469374949113,
      "clip_ratio/high_mean": 0.0006931886073289206,
      "clip_ratio/low_mean": 0.0008845633692544652,
      "clip_ratio/low_min": 7.235338307509664e-05,
      "clip_ratio/region_mean": 0.0015777519511175342,
      "epoch": 0.01763995590011025,
      "grad_norm": 0.10828215628862381,
      "learning_rate": 5e-07,
      "loss": 0.0616,
      "step": 189
    },
    {
      "clip_ratio/high_max": 0.002235471081803553,
      "clip_ratio/high_mean": 0.0009519344275759067,
      "clip_ratio/low_mean": 0.0008110086200758815,
      "clip_ratio/low_min": 1.3244331057649106e-05,
      "clip_ratio/region_mean": 0.0017629430294618942,
      "epoch": 0.017733289000110834,
      "grad_norm": 0.11431360989809036,
      "learning_rate": 5e-07,
      "loss": 0.0007,
      "step": 190
    },
    {
      "clip_ratio/high_max": 0.0022224633212317713,
      "clip_ratio/high_mean": 0.0009536013749311678,
      "clip_ratio/low_mean": 0.0007525154433096759,
      "clip_ratio/low_min": 4.8731044444139116e-05,
      "clip_ratio/region_mean": 0.001706116774585098,
      "epoch": 0.017826622100111416,
      "grad_norm": 0.11049619317054749,
      "learning_rate": 5e-07,
      "loss": 0.0056,
      "step": 191
    },
    {
      "clip_ratio/high_max": 0.002130889562977245,
      "clip_ratio/high_mean": 0.0008231233550759498,
      "clip_ratio/low_mean": 0.0008630529828224098,
      "clip_ratio/low_min": 6.592668341909302e-05,
      "clip_ratio/region_mean": 0.0016861763506312855,
      "epoch": 0.017919955200112,
      "grad_norm": 0.10585968941450119,
      "learning_rate": 5e-07,
      "loss": 0.0846,
      "step": 192
    },
    {
      "clip_ratio/high_max": 0.0023383170992019586,
      "clip_ratio/high_mean": 0.0009754961811268004,
      "clip_ratio/low_mean": 0.0007336001017392846,
      "clip_ratio/low_min": 2.9644871574419085e-05,
      "clip_ratio/region_mean": 0.0017090962937800214,
      "epoch": 0.018013288300112583,
      "grad_norm": 0.1251491755247116,
      "learning_rate": 5e-07,
      "loss": -0.0445,
      "step": 193
    },
    {
      "clip_ratio/high_max": 0.002042424472165294,
      "clip_ratio/high_mean": 0.0008403582323808223,
      "clip_ratio/low_mean": 0.0008896735816961154,
      "clip_ratio/low_min": 5.055924111729837e-05,
      "clip_ratio/region_mean": 0.001730031792249065,
      "epoch": 0.018106621400113165,
      "grad_norm": 0.10418280214071274,
      "learning_rate": 5e-07,
      "loss": 0.026,
      "step": 194
    },
    {
      "clip_ratio/high_max": 0.001842323414166458,
      "clip_ratio/high_mean": 0.0007707414806645829,
      "clip_ratio/low_mean": 0.0009542796706227819,
      "clip_ratio/low_min": 0.00010510561878618319,
      "clip_ratio/region_mean": 0.001725021174934227,
      "epoch": 0.01819995450011375,
      "grad_norm": 0.11046335101127625,
      "learning_rate": 5e-07,
      "loss": 0.0593,
      "step": 195
    },
    {
      "clip_ratio/high_max": 0.0021586815782939084,
      "clip_ratio/high_mean": 0.000846521226776531,
      "clip_ratio/low_mean": 0.0007808757418388268,
      "clip_ratio/low_min": 2.2200250896275975e-05,
      "clip_ratio/region_mean": 0.0016273969522444531,
      "epoch": 0.01829328760011433,
      "grad_norm": 0.10856638848781586,
      "learning_rate": 5e-07,
      "loss": 0.0341,
      "step": 196
    },
    {
      "clip_ratio/high_max": 0.0022570912551600486,
      "clip_ratio/high_mean": 0.0009467047530051786,
      "clip_ratio/low_mean": 0.0008523247088305652,
      "clip_ratio/low_min": 7.647502297913888e-05,
      "clip_ratio/region_mean": 0.0017990295091294684,
      "epoch": 0.018386620700114917,
      "grad_norm": 0.11739487200975418,
      "learning_rate": 5e-07,
      "loss": 0.0046,
      "step": 197
    },
    {
      "clip_ratio/high_max": 0.002105259394738823,
      "clip_ratio/high_mean": 0.000916983406568761,
      "clip_ratio/low_mean": 0.0009284887528338004,
      "clip_ratio/low_min": 0.0001128226876971894,
      "clip_ratio/region_mean": 0.00184547219396336,
      "epoch": 0.0184799538001155,
      "grad_norm": 0.1222643256187439,
      "learning_rate": 5e-07,
      "loss": 0.0522,
      "step": 198
    },
    {
      "clip_ratio/high_max": 0.0020349120095488615,
      "clip_ratio/high_mean": 0.0009229922179656569,
      "clip_ratio/low_mean": 0.0008043157922656974,
      "clip_ratio/low_min": 5.1485641961335205e-05,
      "clip_ratio/region_mean": 0.0017273080666200258,
      "epoch": 0.018573286900116084,
      "grad_norm": 0.10785696655511856,
      "learning_rate": 5e-07,
      "loss": 0.0117,
      "step": 199
    },
    {
      "clip_ratio/high_max": 0.001986330455110874,
      "clip_ratio/high_mean": 0.0009233806813426781,
      "clip_ratio/low_mean": 0.0008732192745810607,
      "clip_ratio/low_min": 0.00014581579216610407,
      "clip_ratio/region_mean": 0.0017965999577427283,
      "epoch": 0.018666620000116665,
      "grad_norm": 0.13234420120716095,
      "learning_rate": 5e-07,
      "loss": 0.0617,
      "step": 200
    },
    {
      "clip_ratio/high_max": 0.0017234014267160092,
      "clip_ratio/high_mean": 0.0007691180962865474,
      "clip_ratio/low_mean": 0.0008502567625328084,
      "clip_ratio/low_min": 8.684058593644295e-05,
      "clip_ratio/region_mean": 0.0016193748779187445,
      "epoch": 0.01875995310011725,
      "grad_norm": 0.11590451002120972,
      "learning_rate": 5e-07,
      "loss": 0.0536,
      "step": 201
    },
    {
      "clip_ratio/high_max": 0.0021411375055322424,
      "clip_ratio/high_mean": 0.0009127135963353794,
      "clip_ratio/low_mean": 0.0009296732332586544,
      "clip_ratio/low_min": 0.00012345058803475695,
      "clip_ratio/region_mean": 0.001842386816861108,
      "epoch": 0.018853286200117832,
      "grad_norm": 0.11670146137475967,
      "learning_rate": 5e-07,
      "loss": 0.0399,
      "step": 202
    },
    {
      "clip_ratio/high_max": 0.002416689560050145,
      "clip_ratio/high_mean": 0.0010485749189683702,
      "clip_ratio/low_mean": 0.0008792755370450323,
      "clip_ratio/low_min": 0.00011396920126571786,
      "clip_ratio/region_mean": 0.0019278504478279501,
      "epoch": 0.018946619300118418,
      "grad_norm": 0.11840178072452545,
      "learning_rate": 5e-07,
      "loss": 0.0039,
      "step": 203
    },
    {
      "clip_ratio/high_max": 0.002535638057452161,
      "clip_ratio/high_mean": 0.0010109195336553967,
      "clip_ratio/low_mean": 0.000947540328525065,
      "clip_ratio/low_min": 0.00015204301416815724,
      "clip_ratio/region_mean": 0.0019584599212976173,
      "epoch": 0.019039952400119,
      "grad_norm": 0.13051770627498627,
      "learning_rate": 5e-07,
      "loss": 0.0415,
      "step": 204
    },
    {
      "clip_ratio/high_max": 0.002171550535422284,
      "clip_ratio/high_mean": 0.0008388147871301044,
      "clip_ratio/low_mean": 0.0008666403609822737,
      "clip_ratio/low_min": 5.8726810493681114e-05,
      "clip_ratio/region_mean": 0.001705455179035198,
      "epoch": 0.019133285500119585,
      "grad_norm": 0.11215374618768692,
      "learning_rate": 5e-07,
      "loss": 0.0316,
      "step": 205
    },
    {
      "clip_ratio/high_max": 0.002104148981743492,
      "clip_ratio/high_mean": 0.0008641494496259838,
      "clip_ratio/low_mean": 0.0008220453037210973,
      "clip_ratio/low_min": 7.412666036543669e-05,
      "clip_ratio/region_mean": 0.0016861947515280917,
      "epoch": 0.019226618600120166,
      "grad_norm": 0.10485672950744629,
      "learning_rate": 5e-07,
      "loss": -0.0102,
      "step": 206
    },
    {
      "clip_ratio/high_max": 0.0022307665130938403,
      "clip_ratio/high_mean": 0.0008363036486116471,
      "clip_ratio/low_mean": 0.0009198741436193814,
      "clip_ratio/low_min": 7.762422728774254e-05,
      "clip_ratio/region_mean": 0.0017561777931405231,
      "epoch": 0.019319951700120748,
      "grad_norm": 0.11252034455537796,
      "learning_rate": 5e-07,
      "loss": -0.0023,
      "step": 207
    },
    {
      "clip_ratio/high_max": 0.0019802356655418407,
      "clip_ratio/high_mean": 0.0008670172337588156,
      "clip_ratio/low_mean": 0.0008919200936361449,
      "clip_ratio/low_min": 7.541266677435488e-05,
      "clip_ratio/region_mean": 0.0017589372837392148,
      "epoch": 0.019413284800121333,
      "grad_norm": 0.12129811197519302,
      "learning_rate": 5e-07,
      "loss": 0.0561,
      "step": 208
    },
    {
      "clip_ratio/high_max": 0.0019333121090312488,
      "clip_ratio/high_mean": 0.0008696162531123264,
      "clip_ratio/low_mean": 0.000882526277564466,
      "clip_ratio/low_min": 5.7431781897321343e-05,
      "clip_ratio/region_mean": 0.0017521425033919513,
      "epoch": 0.019506617900121915,
      "grad_norm": 0.11300335824489594,
      "learning_rate": 5e-07,
      "loss": 0.0505,
      "step": 209
    },
    {
      "clip_ratio/high_max": 0.0022247776396397967,
      "clip_ratio/high_mean": 0.000862781674186408,
      "clip_ratio/low_mean": 0.0008954413515311899,
      "clip_ratio/low_min": 0.00013182761722418945,
      "clip_ratio/region_mean": 0.0017582230429979973,
      "epoch": 0.0195999510001225,
      "grad_norm": 0.09845684468746185,
      "learning_rate": 5e-07,
      "loss": 0.0777,
      "step": 210
    },
    {
      "clip_ratio/high_max": 0.00212123373785289,
      "clip_ratio/high_mean": 0.0008874772720446344,
      "clip_ratio/low_mean": 0.0008822383351798635,
      "clip_ratio/low_min": 2.106903775711544e-05,
      "clip_ratio/region_mean": 0.001769715607224498,
      "epoch": 0.019693284100123082,
      "grad_norm": 0.11091208457946777,
      "learning_rate": 5e-07,
      "loss": 0.0416,
      "step": 211
    },
    {
      "clip_ratio/high_max": 0.0019256482628406957,
      "clip_ratio/high_mean": 0.0007877206244302215,
      "clip_ratio/low_mean": 0.00085633681192121,
      "clip_ratio/low_min": 4.6156679673003964e-05,
      "clip_ratio/region_mean": 0.0016440574108855799,
      "epoch": 0.019786617200123667,
      "grad_norm": 0.1159248799085617,
      "learning_rate": 5e-07,
      "loss": 0.0171,
      "step": 212
    },
    {
      "clip_ratio/high_max": 0.002187787089496851,
      "clip_ratio/high_mean": 0.0008610053300799336,
      "clip_ratio/low_mean": 0.0007817763125785859,
      "clip_ratio/low_min": 2.1135943825356662e-05,
      "clip_ratio/region_mean": 0.0016427816372015513,
      "epoch": 0.01987995030012425,
      "grad_norm": 0.11705534905195236,
      "learning_rate": 5e-07,
      "loss": 0.0034,
      "step": 213
    },
    {
      "clip_ratio/high_max": 0.0020054275082657114,
      "clip_ratio/high_mean": 0.0007803691623848863,
      "clip_ratio/low_mean": 0.0009680791245045839,
      "clip_ratio/low_min": 6.80444472891395e-05,
      "clip_ratio/region_mean": 0.001748448281432502,
      "epoch": 0.019973283400124834,
      "grad_norm": 0.11599202454090118,
      "learning_rate": 5e-07,
      "loss": 0.0662,
      "step": 214
    },
    {
      "clip_ratio/high_max": 0.0023329920040850993,
      "clip_ratio/high_mean": 0.0008899332915461855,
      "clip_ratio/low_mean": 0.0009788028000912163,
      "clip_ratio/low_min": 0.00014314418331196066,
      "clip_ratio/region_mean": 0.0018687360643525608,
      "epoch": 0.020066616500125416,
      "grad_norm": 0.11746630817651749,
      "learning_rate": 5e-07,
      "loss": 0.0196,
      "step": 215
    },
    {
      "clip_ratio/high_max": 0.0020590863496181555,
      "clip_ratio/high_mean": 0.0009063425204658415,
      "clip_ratio/low_mean": 0.0009509872379567241,
      "clip_ratio/low_min": 0.00011726693355740281,
      "clip_ratio/region_mean": 0.0018573297711554915,
      "epoch": 0.020159949600126,
      "grad_norm": 0.11527352035045624,
      "learning_rate": 5e-07,
      "loss": 0.0212,
      "step": 216
    },
    {
      "clip_ratio/high_max": 0.0016771568080002908,
      "clip_ratio/high_mean": 0.0006778654387744609,
      "clip_ratio/low_mean": 0.0008884337385097751,
      "clip_ratio/low_min": 1.5729205188108608e-05,
      "clip_ratio/region_mean": 0.0015662991718272679,
      "epoch": 0.020253282700126583,
      "grad_norm": 0.09892686456441879,
      "learning_rate": 5e-07,
      "loss": 0.0697,
      "step": 217
    },
    {
      "clip_ratio/high_max": 0.0022508382389787585,
      "clip_ratio/high_mean": 0.0009835582422965672,
      "clip_ratio/low_mean": 0.0007670699305890594,
      "clip_ratio/low_min": 9.894740287563764e-05,
      "clip_ratio/region_mean": 0.0017506282165413722,
      "epoch": 0.020346615800127168,
      "grad_norm": 0.1147509291768074,
      "learning_rate": 5e-07,
      "loss": -0.0397,
      "step": 218
    },
    {
      "clip_ratio/high_max": 0.0017941739861271344,
      "clip_ratio/high_mean": 0.0008373127257073065,
      "clip_ratio/low_mean": 0.0007980131904332666,
      "clip_ratio/low_min": 3.313894376333337e-05,
      "clip_ratio/region_mean": 0.0016353259125025943,
      "epoch": 0.02043994890012775,
      "grad_norm": 0.11574050039052963,
      "learning_rate": 5e-07,
      "loss": 0.0296,
      "step": 219
    },
    {
      "clip_ratio/high_max": 0.0024912596491049044,
      "clip_ratio/high_mean": 0.0009647405349824112,
      "clip_ratio/low_mean": 0.000912757488549687,
      "clip_ratio/low_min": 0.0001229264389621676,
      "clip_ratio/region_mean": 0.001877498027170077,
      "epoch": 0.02053328200012833,
      "grad_norm": 0.12519137561321259,
      "learning_rate": 5e-07,
      "loss": 0.0042,
      "step": 220
    },
    {
      "clip_ratio/high_max": 0.002430552580335643,
      "clip_ratio/high_mean": 0.0010196676794294035,
      "clip_ratio/low_mean": 0.0008798695052973926,
      "clip_ratio/low_min": 5.7798673879005946e-05,
      "clip_ratio/region_mean": 0.0018995371865457855,
      "epoch": 0.020626615100128916,
      "grad_norm": 0.11370623111724854,
      "learning_rate": 5e-07,
      "loss": 0.0276,
      "step": 221
    },
    {
      "clip_ratio/high_max": 0.001911673418362625,
      "clip_ratio/high_mean": 0.0008547153047402389,
      "clip_ratio/low_mean": 0.0008774012148933252,
      "clip_ratio/low_min": 0.00012085474008927122,
      "clip_ratio/region_mean": 0.001732116550556384,
      "epoch": 0.020719948200129498,
      "grad_norm": 0.12136111408472061,
      "learning_rate": 5e-07,
      "loss": 0.0383,
      "step": 222
    },
    {
      "clip_ratio/high_max": 0.0020471725874813274,
      "clip_ratio/high_mean": 0.0008545358614355791,
      "clip_ratio/low_mean": 0.0008401499471801799,
      "clip_ratio/low_min": 3.431741970416624e-05,
      "clip_ratio/region_mean": 0.0016946857867878862,
      "epoch": 0.020813281300130083,
      "grad_norm": 0.11204053461551666,
      "learning_rate": 5e-07,
      "loss": 0.0277,
      "step": 223
    },
    {
      "clip_ratio/high_max": 0.0019816977946902625,
      "clip_ratio/high_mean": 0.0008519247949152486,
      "clip_ratio/low_mean": 0.0009462175894441316,
      "clip_ratio/low_min": 0.000136482982270536,
      "clip_ratio/region_mean": 0.0017981423843593802,
      "epoch": 0.020906614400130665,
      "grad_norm": 0.12669426202774048,
      "learning_rate": 5e-07,
      "loss": 0.0598,
      "step": 224
    },
    {
      "clip_ratio/high_max": 0.002199975431722123,
      "clip_ratio/high_mean": 0.0009222910812241025,
      "clip_ratio/low_mean": 0.0008821888604870765,
      "clip_ratio/low_min": 0.00010829583607119275,
      "clip_ratio/region_mean": 0.0018044799071503803,
      "epoch": 0.02099994750013125,
      "grad_norm": 0.10953018814325333,
      "learning_rate": 5e-07,
      "loss": 0.0153,
      "step": 225
    },
    {
      "clip_ratio/high_max": 0.0021847497009730432,
      "clip_ratio/high_mean": 0.0009189934262394672,
      "clip_ratio/low_mean": 0.0009634783564251848,
      "clip_ratio/low_min": 0.00014186981661623577,
      "clip_ratio/region_mean": 0.0018824718063115142,
      "epoch": 0.021093280600131832,
      "grad_norm": 0.1176847293972969,
      "learning_rate": 5e-07,
      "loss": 0.0007,
      "step": 226
    },
    {
      "clip_ratio/high_max": 0.002009170420933515,
      "clip_ratio/high_mean": 0.000955015861109132,
      "clip_ratio/low_mean": 0.0008409686370214331,
      "clip_ratio/low_min": 0.0001342524365099962,
      "clip_ratio/region_mean": 0.001795984513591975,
      "epoch": 0.021186613700132417,
      "grad_norm": 0.11189977079629898,
      "learning_rate": 5e-07,
      "loss": 0.0159,
      "step": 227
    },
    {
      "clip_ratio/high_max": 0.0019948306726291776,
      "clip_ratio/high_mean": 0.0007750720651529264,
      "clip_ratio/low_mean": 0.0009184654227283318,
      "clip_ratio/low_min": 0.00011034699036827078,
      "clip_ratio/region_mean": 0.001693537473329343,
      "epoch": 0.021279946800133,
      "grad_norm": 0.10932432860136032,
      "learning_rate": 5e-07,
      "loss": 0.0197,
      "step": 228
    },
    {
      "clip_ratio/high_max": 0.0019161879063176457,
      "clip_ratio/high_mean": 0.0007938312919577584,
      "clip_ratio/low_mean": 0.0008579080695199082,
      "clip_ratio/low_min": 9.753609674589825e-05,
      "clip_ratio/region_mean": 0.0016517393669346347,
      "epoch": 0.021373279900133584,
      "grad_norm": 0.10970553010702133,
      "learning_rate": 5e-07,
      "loss": 0.0184,
      "step": 229
    },
    {
      "clip_ratio/high_max": 0.0022240467806113884,
      "clip_ratio/high_mean": 0.0008881543290044647,
      "clip_ratio/low_mean": 0.000946694855883834,
      "clip_ratio/low_min": 0.00011918543350475375,
      "clip_ratio/region_mean": 0.0018348491576034576,
      "epoch": 0.021466613000134166,
      "grad_norm": 0.11449955403804779,
      "learning_rate": 5e-07,
      "loss": 0.0266,
      "step": 230
    },
    {
      "clip_ratio/high_max": 0.0020369619160192087,
      "clip_ratio/high_mean": 0.0008931450720410794,
      "clip_ratio/low_mean": 0.0008374542667297646,
      "clip_ratio/low_min": 7.502514699808671e-05,
      "clip_ratio/region_mean": 0.001730599284201162,
      "epoch": 0.02155994610013475,
      "grad_norm": 0.1239096075296402,
      "learning_rate": 5e-07,
      "loss": 0.0402,
      "step": 231
    },
    {
      "clip_ratio/high_max": 0.0017427457714802586,
      "clip_ratio/high_mean": 0.0008062610486376798,
      "clip_ratio/low_mean": 0.0008674174205225427,
      "clip_ratio/low_min": 9.611140831111697e-05,
      "clip_ratio/region_mean": 0.0016736785182729363,
      "epoch": 0.021653279200135333,
      "grad_norm": 0.12201163917779922,
      "learning_rate": 5e-07,
      "loss": 0.0424,
      "step": 232
    },
    {
      "clip_ratio/high_max": 0.0020825430037803017,
      "clip_ratio/high_mean": 0.0009240404433512595,
      "clip_ratio/low_mean": 0.0008137251988955541,
      "clip_ratio/low_min": 4.514818101597484e-05,
      "clip_ratio/region_mean": 0.0017377656549797393,
      "epoch": 0.021746612300135915,
      "grad_norm": 0.11060652136802673,
      "learning_rate": 5e-07,
      "loss": 0.023,
      "step": 233
    },
    {
      "clip_ratio/high_max": 0.0021638578036800027,
      "clip_ratio/high_mean": 0.0009790061812964268,
      "clip_ratio/low_mean": 0.000880387127836002,
      "clip_ratio/low_min": 9.272232091461774e-05,
      "clip_ratio/region_mean": 0.0018593932982184924,
      "epoch": 0.0218399454001365,
      "grad_norm": 0.12192007154226303,
      "learning_rate": 5e-07,
      "loss": 0.002,
      "step": 234
    },
    {
      "clip_ratio/high_max": 0.002085377163894009,
      "clip_ratio/high_mean": 0.0009019052376970649,
      "clip_ratio/low_mean": 0.0009264125219488051,
      "clip_ratio/low_min": 3.578059477149509e-05,
      "clip_ratio/region_mean": 0.0018283177269040607,
      "epoch": 0.02193327850013708,
      "grad_norm": 0.11549447476863861,
      "learning_rate": 5e-07,
      "loss": 0.0247,
      "step": 235
    },
    {
      "clip_ratio/high_max": 0.0022470106996479444,
      "clip_ratio/high_mean": 0.0009808944723772584,
      "clip_ratio/low_mean": 0.0010169208144361619,
      "clip_ratio/low_min": 4.866952986049e-05,
      "clip_ratio/region_mean": 0.001997815354116028,
      "epoch": 0.022026611600137667,
      "grad_norm": 0.10749969631433487,
      "learning_rate": 5e-07,
      "loss": 0.0273,
      "step": 236
    },
    {
      "clip_ratio/high_max": 0.00238744642410893,
      "clip_ratio/high_mean": 0.0010564148033154197,
      "clip_ratio/low_mean": 0.0009583252613083459,
      "clip_ratio/low_min": 0.00011069114316342166,
      "clip_ratio/region_mean": 0.002014739984588232,
      "epoch": 0.02211994470013825,
      "grad_norm": 0.11736936122179031,
      "learning_rate": 5e-07,
      "loss": 0.0206,
      "step": 237
    },
    {
      "clip_ratio/high_max": 0.0019098903649137355,
      "clip_ratio/high_mean": 0.0008552793151466176,
      "clip_ratio/low_mean": 0.0009685681325208861,
      "clip_ratio/low_min": 0.00012721695566142444,
      "clip_ratio/region_mean": 0.0018238474294776097,
      "epoch": 0.022213277800138834,
      "grad_norm": 0.10269264131784439,
      "learning_rate": 5e-07,
      "loss": 0.0283,
      "step": 238
    },
    {
      "clip_ratio/high_max": 0.0021538853834499605,
      "clip_ratio/high_mean": 0.0009311742560385028,
      "clip_ratio/low_mean": 0.0009507330996711971,
      "clip_ratio/low_min": 0.00013964762729301583,
      "clip_ratio/region_mean": 0.0018819073302438483,
      "epoch": 0.022306610900139415,
      "grad_norm": 0.1206965297460556,
      "learning_rate": 5e-07,
      "loss": 0.0072,
      "step": 239
    },
    {
      "clip_ratio/high_max": 0.0022003714329912327,
      "clip_ratio/high_mean": 0.0008140344070852734,
      "clip_ratio/low_mean": 0.0010567991121206433,
      "clip_ratio/low_min": 8.319530843436951e-05,
      "clip_ratio/region_mean": 0.0018708334973780438,
      "epoch": 0.02239994400014,
      "grad_norm": 0.11193983256816864,
      "learning_rate": 5e-07,
      "loss": 0.067,
      "step": 240
    },
    {
      "clip_ratio/high_max": 0.0018903997079178225,
      "clip_ratio/high_mean": 0.0007180026204878232,
      "clip_ratio/low_mean": 0.0010551308259891812,
      "clip_ratio/low_min": 0.00011196211198694073,
      "clip_ratio/region_mean": 0.0017731334373820573,
      "epoch": 0.022493277100140582,
      "grad_norm": 0.10688068717718124,
      "learning_rate": 5e-07,
      "loss": 0.0065,
      "step": 241
    },
    {
      "clip_ratio/high_max": 0.0021288931820890866,
      "clip_ratio/high_mean": 0.0009031718982441816,
      "clip_ratio/low_mean": 0.0008711075388418976,
      "clip_ratio/low_min": 0.00014648134174422012,
      "clip_ratio/region_mean": 0.0017742795025696978,
      "epoch": 0.022586610200141168,
      "grad_norm": 0.11772692948579788,
      "learning_rate": 5e-07,
      "loss": 0.0266,
      "step": 242
    },
    {
      "clip_ratio/high_max": 0.002113475671649212,
      "clip_ratio/high_mean": 0.0009223833258147351,
      "clip_ratio/low_mean": 0.0009800334555620793,
      "clip_ratio/low_min": 0.00011859893402288435,
      "clip_ratio/region_mean": 0.0019024167777388357,
      "epoch": 0.02267994330014175,
      "grad_norm": 0.10998165607452393,
      "learning_rate": 5e-07,
      "loss": 0.0417,
      "step": 243
    },
    {
      "clip_ratio/high_max": 0.0019426807193667628,
      "clip_ratio/high_mean": 0.0007752163983241189,
      "clip_ratio/low_mean": 0.0009166891359200235,
      "clip_ratio/low_min": 0.00013032428796577733,
      "clip_ratio/region_mean": 0.001691905599727761,
      "epoch": 0.022773276400142334,
      "grad_norm": 0.10903917253017426,
      "learning_rate": 5e-07,
      "loss": 0.0581,
      "step": 244
    },
    {
      "clip_ratio/high_max": 0.0022552020382136106,
      "clip_ratio/high_mean": 0.0008429402478213888,
      "clip_ratio/low_mean": 0.0009034662471094634,
      "clip_ratio/low_min": 0.00011604174596868688,
      "clip_ratio/region_mean": 0.0017464065458625555,
      "epoch": 0.022866609500142916,
      "grad_norm": 0.11355311423540115,
      "learning_rate": 5e-07,
      "loss": 0.0453,
      "step": 245
    },
    {
      "clip_ratio/high_max": 0.0023388997578877024,
      "clip_ratio/high_mean": 0.0009170340326818405,
      "clip_ratio/low_mean": 0.0009452528101974167,
      "clip_ratio/low_min": 3.4896679608209524e-05,
      "clip_ratio/region_mean": 0.0018622868810780346,
      "epoch": 0.022959942600143498,
      "grad_norm": 0.10548633337020874,
      "learning_rate": 5e-07,
      "loss": 0.0229,
      "step": 246
    },
    {
      "clip_ratio/high_max": 0.001990499811654445,
      "clip_ratio/high_mean": 0.0008049141124502057,
      "clip_ratio/low_mean": 0.0008986939392343629,
      "clip_ratio/low_min": 0.00010763796035462292,
      "clip_ratio/region_mean": 0.0017036079952958971,
      "epoch": 0.023053275700144083,
      "grad_norm": 0.11245205998420715,
      "learning_rate": 5e-07,
      "loss": 0.0356,
      "step": 247
    },
    {
      "clip_ratio/high_max": 0.002366517965128878,
      "clip_ratio/high_mean": 0.0010243869583064225,
      "clip_ratio/low_mean": 0.0008906200164346956,
      "clip_ratio/low_min": 6.395819946192205e-05,
      "clip_ratio/region_mean": 0.0019150069965689909,
      "epoch": 0.023146608800144665,
      "grad_norm": 0.11433132737874985,
      "learning_rate": 5e-07,
      "loss": -0.0072,
      "step": 248
    },
    {
      "clip_ratio/high_max": 0.0022519167396239936,
      "clip_ratio/high_mean": 0.0009603193648217712,
      "clip_ratio/low_mean": 0.0009147145119641209,
      "clip_ratio/low_min": 7.102859490260016e-05,
      "clip_ratio/region_mean": 0.001875033907708712,
      "epoch": 0.02323994190014525,
      "grad_norm": 0.12086334824562073,
      "learning_rate": 5e-07,
      "loss": 0.016,
      "step": 249
    },
    {
      "clip_ratio/high_max": 0.0017843202876974829,
      "clip_ratio/high_mean": 0.0008254351814684924,
      "clip_ratio/low_mean": 0.0008958131056715501,
      "clip_ratio/low_min": 2.7855347980221268e-05,
      "clip_ratio/region_mean": 0.001721248307148926,
      "epoch": 0.023333275000145832,
      "grad_norm": 0.10466094315052032,
      "learning_rate": 5e-07,
      "loss": -0.0011,
      "step": 250
    },
    {
      "clip_ratio/high_max": 0.0026154760853387415,
      "clip_ratio/high_mean": 0.0010140595259144902,
      "clip_ratio/low_mean": 0.0009441727706871461,
      "clip_ratio/low_min": 8.550569964427268e-05,
      "clip_ratio/region_mean": 0.0019582322856877,
      "epoch": 0.023426608100146417,
      "grad_norm": 0.11561702191829681,
      "learning_rate": 5e-07,
      "loss": 0.0058,
      "step": 251
    },
    {
      "clip_ratio/high_max": 0.0021765687051811256,
      "clip_ratio/high_mean": 0.000920441600101185,
      "clip_ratio/low_mean": 0.0009937575396179454,
      "clip_ratio/low_min": 0.00016555498768866528,
      "clip_ratio/region_mean": 0.0019141991797368973,
      "epoch": 0.023519941200147,
      "grad_norm": 0.12884502112865448,
      "learning_rate": 5e-07,
      "loss": 0.016,
      "step": 252
    },
    {
      "clip_ratio/high_max": 0.001867670947831357,
      "clip_ratio/high_mean": 0.0007804449996910989,
      "clip_ratio/low_mean": 0.0009126232253038324,
      "clip_ratio/low_min": 0.00014962488512537675,
      "clip_ratio/region_mean": 0.0016930682104430161,
      "epoch": 0.023613274300147584,
      "grad_norm": 0.09930355846881866,
      "learning_rate": 5e-07,
      "loss": 0.0087,
      "step": 253
    },
    {
      "clip_ratio/high_max": 0.0021765056590083987,
      "clip_ratio/high_mean": 0.0008924410194595112,
      "clip_ratio/low_mean": 0.0008812307114567375,
      "clip_ratio/low_min": 8.528683974873275e-05,
      "clip_ratio/region_mean": 0.001773671705450397,
      "epoch": 0.023706607400148166,
      "grad_norm": 0.111038938164711,
      "learning_rate": 5e-07,
      "loss": 0.048,
      "step": 254
    },
    {
      "clip_ratio/high_max": 0.0024068867569440044,
      "clip_ratio/high_mean": 0.0009964566488633864,
      "clip_ratio/low_mean": 0.0008920436648622854,
      "clip_ratio/low_min": 3.177003964083269e-05,
      "clip_ratio/region_mean": 0.0018885003082687035,
      "epoch": 0.02379994050014875,
      "grad_norm": 0.12102565169334412,
      "learning_rate": 5e-07,
      "loss": 0.0183,
      "step": 255
    },
    {
      "clip_ratio/high_max": 0.002244260598672554,
      "clip_ratio/high_mean": 0.0009101868818106595,
      "clip_ratio/low_mean": 0.0010372419856139459,
      "clip_ratio/low_min": 8.372656338906381e-05,
      "clip_ratio/region_mean": 0.0019474288856144994,
      "epoch": 0.023893273600149333,
      "grad_norm": 0.1277434080839157,
      "learning_rate": 5e-07,
      "loss": 0.0423,
      "step": 256
    },
    {
      "clip_ratio/high_max": 0.00201297087551211,
      "clip_ratio/high_mean": 0.000886222656845348,
      "clip_ratio/low_mean": 0.0009160862809949322,
      "clip_ratio/low_min": 0.00015639102093700785,
      "clip_ratio/region_mean": 0.0018023089833150152,
      "epoch": 0.023986606700149918,
      "grad_norm": 0.10981083661317825,
      "learning_rate": 5e-07,
      "loss": 0.0038,
      "step": 257
    },
    {
      "clip_ratio/high_max": 0.002278400210343534,
      "clip_ratio/high_mean": 0.0009032213638420217,
      "clip_ratio/low_mean": 0.0008077146412688307,
      "clip_ratio/low_min": 8.691157881912659e-05,
      "clip_ratio/region_mean": 0.0017109359832829796,
      "epoch": 0.0240799398001505,
      "grad_norm": 0.10469955205917358,
      "learning_rate": 5e-07,
      "loss": 0.0076,
      "step": 258
    },
    {
      "clip_ratio/high_max": 0.002078995319607202,
      "clip_ratio/high_mean": 0.0008858421806507977,
      "clip_ratio/low_mean": 0.0008820165694487514,
      "clip_ratio/low_min": 0.00010406255660200259,
      "clip_ratio/region_mean": 0.0017678587537375279,
      "epoch": 0.02417327290015108,
      "grad_norm": 0.12235986441373825,
      "learning_rate": 5e-07,
      "loss": 0.0409,
      "step": 259
    },
    {
      "clip_ratio/high_max": 0.00202951549727004,
      "clip_ratio/high_mean": 0.0008718154203961603,
      "clip_ratio/low_mean": 0.0008882409492798615,
      "clip_ratio/low_min": 6.262184888328193e-05,
      "clip_ratio/region_mean": 0.0017600563733140007,
      "epoch": 0.024266606000151666,
      "grad_norm": 0.10822401195764542,
      "learning_rate": 5e-07,
      "loss": 0.0201,
      "step": 260
    },
    {
      "clip_ratio/high_max": 0.002269681077450514,
      "clip_ratio/high_mean": 0.0009772919911483768,
      "clip_ratio/low_mean": 0.0009214716556016356,
      "clip_ratio/low_min": 4.550560606730869e-05,
      "clip_ratio/region_mean": 0.0018987636212841608,
      "epoch": 0.024359939100152248,
      "grad_norm": 0.11574152112007141,
      "learning_rate": 5e-07,
      "loss": -0.0149,
      "step": 261
    },
    {
      "clip_ratio/high_max": 0.002302221764693968,
      "clip_ratio/high_mean": 0.0009350001782877371,
      "clip_ratio/low_mean": 0.0009692290077509824,
      "clip_ratio/low_min": 5.055168458056869e-05,
      "clip_ratio/region_mean": 0.0019042291314690374,
      "epoch": 0.024453272200152833,
      "grad_norm": 0.09825243055820465,
      "learning_rate": 5e-07,
      "loss": 0.0276,
      "step": 262
    },
    {
      "clip_ratio/high_max": 0.0024415274820057675,
      "clip_ratio/high_mean": 0.0010118910122400848,
      "clip_ratio/low_mean": 0.0008815259479888482,
      "clip_ratio/low_min": 0.0001261045126739191,
      "clip_ratio/region_mean": 0.0018934169565909542,
      "epoch": 0.024546605300153415,
      "grad_norm": 0.10864625126123428,
      "learning_rate": 5e-07,
      "loss": -0.0084,
      "step": 263
    },
    {
      "clip_ratio/high_max": 0.0023038942526909523,
      "clip_ratio/high_mean": 0.0009591932994226227,
      "clip_ratio/low_mean": 0.0009549904134473763,
      "clip_ratio/low_min": 5.71590544495848e-05,
      "clip_ratio/region_mean": 0.0019141837110510096,
      "epoch": 0.024639938400154,
      "grad_norm": 0.12537187337875366,
      "learning_rate": 5e-07,
      "loss": 0.0167,
      "step": 264
    },
    {
      "clip_ratio/high_max": 0.002650546681252308,
      "clip_ratio/high_mean": 0.0010533508102525957,
      "clip_ratio/low_mean": 0.0009338393338111928,
      "clip_ratio/low_min": 5.4888957947696326e-05,
      "clip_ratio/region_mean": 0.0019871901167789474,
      "epoch": 0.024733271500154582,
      "grad_norm": 0.11386671662330627,
      "learning_rate": 5e-07,
      "loss": -0.0111,
      "step": 265
    },
    {
      "clip_ratio/high_max": 0.0022099598063505255,
      "clip_ratio/high_mean": 0.0009690410861367127,
      "clip_ratio/low_mean": 0.0009879717508738395,
      "clip_ratio/low_min": 0.00010134368403669214,
      "clip_ratio/region_mean": 0.001957012827915605,
      "epoch": 0.024826604600155167,
      "grad_norm": 0.11264728009700775,
      "learning_rate": 5e-07,
      "loss": 0.0356,
      "step": 266
    },
    {
      "clip_ratio/high_max": 0.0027495354297570884,
      "clip_ratio/high_mean": 0.0010023187496699393,
      "clip_ratio/low_mean": 0.0009051573360920884,
      "clip_ratio/low_min": 9.865281845122809e-05,
      "clip_ratio/region_mean": 0.00190747607848607,
      "epoch": 0.02491993770015575,
      "grad_norm": 0.1322050839662552,
      "learning_rate": 5e-07,
      "loss": 0.0061,
      "step": 267
    },
    {
      "clip_ratio/high_max": 0.002124471717252163,
      "clip_ratio/high_mean": 0.0008892809564713389,
      "clip_ratio/low_mean": 0.0008824520482448861,
      "clip_ratio/low_min": 4.301451917854138e-05,
      "clip_ratio/region_mean": 0.0017717330119921826,
      "epoch": 0.025013270800156334,
      "grad_norm": 0.12094315886497498,
      "learning_rate": 5e-07,
      "loss": 0.0154,
      "step": 268
    },
    {
      "clip_ratio/high_max": 0.002513977036869619,
      "clip_ratio/high_mean": 0.0010280657479597721,
      "clip_ratio/low_mean": 0.0007666163446629071,
      "clip_ratio/low_min": 7.674733751628082e-05,
      "clip_ratio/region_mean": 0.0017946821099030785,
      "epoch": 0.025106603900156916,
      "grad_norm": 0.11155196279287338,
      "learning_rate": 5e-07,
      "loss": -0.002,
      "step": 269
    },
    {
      "clip_ratio/high_max": 0.002230537535069743,
      "clip_ratio/high_mean": 0.0009724652645672904,
      "clip_ratio/low_mean": 0.0009028505955939181,
      "clip_ratio/low_min": 4.804329546459485e-05,
      "clip_ratio/region_mean": 0.0018753158583422191,
      "epoch": 0.0251999370001575,
      "grad_norm": 0.12083155661821365,
      "learning_rate": 5e-07,
      "loss": -0.021,
      "step": 270
    },
    {
      "clip_ratio/high_max": 0.0023646664267289452,
      "clip_ratio/high_mean": 0.0009958037990145385,
      "clip_ratio/low_mean": 0.0007734058044661651,
      "clip_ratio/low_min": 4.565843482851051e-05,
      "clip_ratio/region_mean": 0.0017692096371320076,
      "epoch": 0.025293270100158083,
      "grad_norm": 0.12027846276760101,
      "learning_rate": 5e-07,
      "loss": 0.0148,
      "step": 271
    },
    {
      "clip_ratio/high_max": 0.0018864223529817536,
      "clip_ratio/high_mean": 0.0007825431221135659,
      "clip_ratio/low_mean": 0.000911256589461118,
      "clip_ratio/low_min": 0.0001136431637860369,
      "clip_ratio/region_mean": 0.0016937996842898428,
      "epoch": 0.025386603200158665,
      "grad_norm": 0.11464646458625793,
      "learning_rate": 5e-07,
      "loss": 0.006,
      "step": 272
    },
    {
      "clip_ratio/high_max": 0.002247738819278311,
      "clip_ratio/high_mean": 0.0009218624745699344,
      "clip_ratio/low_mean": 0.000979297579760896,
      "clip_ratio/low_min": 6.766993010387523e-05,
      "clip_ratio/region_mean": 0.0019011600888916291,
      "epoch": 0.02547993630015925,
      "grad_norm": 0.10622774064540863,
      "learning_rate": 5e-07,
      "loss": 0.0071,
      "step": 273
    },
    {
      "clip_ratio/high_max": 0.0020928907688357867,
      "clip_ratio/high_mean": 0.0008493938548781443,
      "clip_ratio/low_mean": 0.0008847369099385105,
      "clip_ratio/low_min": 8.1781710832729e-05,
      "clip_ratio/region_mean": 0.0017341307466267608,
      "epoch": 0.02557326940015983,
      "grad_norm": 0.11213237047195435,
      "learning_rate": 5e-07,
      "loss": 0.0109,
      "step": 274
    },
    {
      "clip_ratio/high_max": 0.002029831914114766,
      "clip_ratio/high_mean": 0.000820060273326817,
      "clip_ratio/low_mean": 0.0009880981197056826,
      "clip_ratio/low_min": 0.00011645377435343107,
      "clip_ratio/region_mean": 0.001808158376661595,
      "epoch": 0.025666602500160417,
      "grad_norm": 0.10837888717651367,
      "learning_rate": 5e-07,
      "loss": 0.0236,
      "step": 275
    },
    {
      "clip_ratio/high_max": 0.0019584271940402687,
      "clip_ratio/high_mean": 0.0008618963074695785,
      "clip_ratio/low_mean": 0.0009476350896875374,
      "clip_ratio/low_min": 4.746116064779926e-05,
      "clip_ratio/region_mean": 0.0018095313062076457,
      "epoch": 0.025759935600161,
      "grad_norm": 0.10793258994817734,
      "learning_rate": 5e-07,
      "loss": 0.0388,
      "step": 276
    },
    {
      "clip_ratio/high_max": 0.002149790943803964,
      "clip_ratio/high_mean": 0.0010062140863738023,
      "clip_ratio/low_mean": 0.0009596132567821769,
      "clip_ratio/low_min": 0.00012765615383614204,
      "clip_ratio/region_mean": 0.001965827359526884,
      "epoch": 0.025853268700161584,
      "grad_norm": 0.11902637034654617,
      "learning_rate": 5e-07,
      "loss": -0.0212,
      "step": 277
    },
    {
      "clip_ratio/high_max": 0.0021890701391384937,
      "clip_ratio/high_mean": 0.0009726041535031982,
      "clip_ratio/low_mean": 0.000865632157001528,
      "clip_ratio/low_min": 3.531605671014404e-05,
      "clip_ratio/region_mean": 0.0018382362541160546,
      "epoch": 0.025946601800162165,
      "grad_norm": 0.11631730198860168,
      "learning_rate": 5e-07,
      "loss": 0.0163,
      "step": 278
    },
    {
      "clip_ratio/high_max": 0.0023207719350466505,
      "clip_ratio/high_mean": 0.0010101644511451013,
      "clip_ratio/low_mean": 0.001080785325029865,
      "clip_ratio/low_min": 0.00016411728211096488,
      "clip_ratio/region_mean": 0.0020909498125547543,
      "epoch": 0.02603993490016275,
      "grad_norm": 0.12106705456972122,
      "learning_rate": 5e-07,
      "loss": -0.0184,
      "step": 279
    },
    {
      "clip_ratio/high_max": 0.0020700411550933495,
      "clip_ratio/high_mean": 0.0008022248111956287,
      "clip_ratio/low_mean": 0.0009539323746139416,
      "clip_ratio/low_min": 0.00012409026521709166,
      "clip_ratio/region_mean": 0.0017561571694386657,
      "epoch": 0.026133268000163332,
      "grad_norm": 0.11585593223571777,
      "learning_rate": 5e-07,
      "loss": 0.0644,
      "step": 280
    },
    {
      "clip_ratio/high_max": 0.00235276082821656,
      "clip_ratio/high_mean": 0.0009144625473709311,
      "clip_ratio/low_mean": 0.001106336905650096,
      "clip_ratio/low_min": 0.0001376091959173209,
      "clip_ratio/region_mean": 0.0020207994602969848,
      "epoch": 0.026226601100163918,
      "grad_norm": 0.11537427455186844,
      "learning_rate": 5e-07,
      "loss": 0.014,
      "step": 281
    },
    {
      "clip_ratio/high_max": 0.0017253397672902793,
      "clip_ratio/high_mean": 0.0007491062369808787,
      "clip_ratio/low_mean": 0.0009551425882818876,
      "clip_ratio/low_min": 0.0001586603639225359,
      "clip_ratio/region_mean": 0.0017042488398146816,
      "epoch": 0.0263199342001645,
      "grad_norm": 0.11453244090080261,
      "learning_rate": 5e-07,
      "loss": 0.0702,
      "step": 282
    },
    {
      "clip_ratio/high_max": 0.002348089863517089,
      "clip_ratio/high_mean": 0.0009437431554033537,
      "clip_ratio/low_mean": 0.0009732014259498101,
      "clip_ratio/low_min": 0.0001341671850241255,
      "clip_ratio/region_mean": 0.0019169445367879234,
      "epoch": 0.026413267300165084,
      "grad_norm": 0.11555302888154984,
      "learning_rate": 5e-07,
      "loss": 0.0532,
      "step": 283
    },
    {
      "clip_ratio/high_max": 0.001828534972446505,
      "clip_ratio/high_mean": 0.0007829252190276748,
      "clip_ratio/low_mean": 0.0009159400560747599,
      "clip_ratio/low_min": 0.0001256681644008495,
      "clip_ratio/region_mean": 0.0016988652714644559,
      "epoch": 0.026506600400165666,
      "grad_norm": 0.10818251967430115,
      "learning_rate": 5e-07,
      "loss": 0.0262,
      "step": 284
    },
    {
      "clip_ratio/high_max": 0.002420313838229049,
      "clip_ratio/high_mean": 0.0009726103853608947,
      "clip_ratio/low_mean": 0.0009686054481790052,
      "clip_ratio/low_min": 8.281454211100936e-05,
      "clip_ratio/region_mean": 0.001941215836268384,
      "epoch": 0.026599933500166248,
      "grad_norm": 0.11607835441827774,
      "learning_rate": 5e-07,
      "loss": 0.0355,
      "step": 285
    },
    {
      "clip_ratio/high_max": 0.0022517535762744956,
      "clip_ratio/high_mean": 0.0009285380874644034,
      "clip_ratio/low_mean": 0.0010255120214424096,
      "clip_ratio/low_min": 8.933532080845907e-05,
      "clip_ratio/region_mean": 0.001954050123458728,
      "epoch": 0.026693266600166833,
      "grad_norm": 0.1179853230714798,
      "learning_rate": 5e-07,
      "loss": 0.0032,
      "step": 286
    },
    {
      "clip_ratio/high_max": 0.0020563459183904342,
      "clip_ratio/high_mean": 0.0008545142081857193,
      "clip_ratio/low_mean": 0.0010393952070444357,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0018939094079541974,
      "epoch": 0.026786599700167415,
      "grad_norm": 0.15593190491199493,
      "learning_rate": 5e-07,
      "loss": 0.0464,
      "step": 287
    },
    {
      "clip_ratio/high_max": 0.0018926113189081661,
      "clip_ratio/high_mean": 0.0007984623225638643,
      "clip_ratio/low_mean": 0.0008280655965791084,
      "clip_ratio/low_min": 3.0931691981095355e-05,
      "clip_ratio/region_mean": 0.001626527911867015,
      "epoch": 0.026879932800168,
      "grad_norm": 0.1046101450920105,
      "learning_rate": 5e-07,
      "loss": 0.0504,
      "step": 288
    },
    {
      "clip_ratio/high_max": 0.0021191331034060568,
      "clip_ratio/high_mean": 0.0008593356942583341,
      "clip_ratio/low_mean": 0.0009843756452028174,
      "clip_ratio/low_min": 7.542526691395324e-05,
      "clip_ratio/region_mean": 0.0018437113540130667,
      "completions/clipped_ratio": 0.014857700892857095,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4092.0,
      "completions/mean_length": 610.4615478515625,
      "completions/mean_terminated_length": 557.8933715820312,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.026973265900168582,
      "grad_norm": 0.12082627415657043,
      "learning_rate": 5e-07,
      "loss": 0.0411,
      "num_tokens": 325747088.0,
      "reward": 0.5568586587905884,
      "reward_std": 0.21462611854076385,
      "rewards/simpleverify_reward/mean": 0.5568585991859436,
      "rewards/simpleverify_reward/std": 0.4967586398124695,
      "step": 289
    },
    {
      "clip_ratio/high_max": 0.0025570080761099234,
      "clip_ratio/high_mean": 0.0009088190272450447,
      "clip_ratio/low_mean": 0.000923053958103992,
      "clip_ratio/low_min": 0.00015792722751939436,
      "clip_ratio/region_mean": 0.0018318729780730791,
      "epoch": 0.027066599000169167,
      "grad_norm": 0.10598639398813248,
      "learning_rate": 5e-07,
      "loss": 0.0287,
      "step": 290
    },
    {
      "clip_ratio/high_max": 0.0025994098687078804,
      "clip_ratio/high_mean": 0.0009585894076735713,
      "clip_ratio/low_mean": 0.0009229096031049266,
      "clip_ratio/low_min": 0.00010480064611328999,
      "clip_ratio/region_mean": 0.0018814989489328582,
      "epoch": 0.02715993210016975,
      "grad_norm": 0.11042536795139313,
      "learning_rate": 5e-07,
      "loss": 0.0566,
      "step": 291
    },
    {
      "clip_ratio/high_max": 0.0020467139620450325,
      "clip_ratio/high_mean": 0.0008869255252648145,
      "clip_ratio/low_mean": 0.0008237859274231596,
      "clip_ratio/low_min": 0.00011853496471303515,
      "clip_ratio/region_mean": 0.001710711425403133,
      "epoch": 0.027253265200170334,
      "grad_norm": 0.1095808669924736,
      "learning_rate": 5e-07,
      "loss": 0.0192,
      "step": 292
    },
    {
      "clip_ratio/high_max": 0.002235117652162444,
      "clip_ratio/high_mean": 0.0009779838801478036,
      "clip_ratio/low_mean": 0.0009449776935070986,
      "clip_ratio/low_min": 5.2369410695973784e-05,
      "clip_ratio/region_mean": 0.0019229615936637856,
      "epoch": 0.027346598300170916,
      "grad_norm": 0.13023701310157776,
      "learning_rate": 5e-07,
      "loss": 0.03,
      "step": 293
    },
    {
      "clip_ratio/high_max": 0.0021019411651650444,
      "clip_ratio/high_mean": 0.000927188855712302,
      "clip_ratio/low_mean": 0.00092224659420026,
      "clip_ratio/low_min": 8.120764869090635e-05,
      "clip_ratio/region_mean": 0.0018494354953872971,
      "epoch": 0.0274399314001715,
      "grad_norm": 0.11709008365869522,
      "learning_rate": 5e-07,
      "loss": 0.0464,
      "step": 294
    },
    {
      "clip_ratio/high_max": 0.0020313346685725264,
      "clip_ratio/high_mean": 0.0009517592970951227,
      "clip_ratio/low_mean": 0.0008303368904307717,
      "clip_ratio/low_min": 0.00014710736832057592,
      "clip_ratio/region_mean": 0.001782096158422064,
      "epoch": 0.027533264500172083,
      "grad_norm": 0.11853837221860886,
      "learning_rate": 5e-07,
      "loss": -0.0192,
      "step": 295
    },
    {
      "clip_ratio/high_max": 0.002149273241229821,
      "clip_ratio/high_mean": 0.0009385525863763178,
      "clip_ratio/low_mean": 0.0008485562957503134,
      "clip_ratio/low_min": 7.720257508481154e-05,
      "clip_ratio/region_mean": 0.0017871088275569491,
      "epoch": 0.027626597600172668,
      "grad_norm": 0.12008404731750488,
      "learning_rate": 5e-07,
      "loss": 0.0046,
      "step": 296
    },
    {
      "clip_ratio/high_max": 0.002204798125603702,
      "clip_ratio/high_mean": 0.0008692503888596548,
      "clip_ratio/low_mean": 0.0008391566316277022,
      "clip_ratio/low_min": 4.947312118019909e-05,
      "clip_ratio/region_mean": 0.0017084070168493781,
      "epoch": 0.02771993070017325,
      "grad_norm": 0.1433432400226593,
      "learning_rate": 5e-07,
      "loss": 0.0006,
      "step": 297
    },
    {
      "clip_ratio/high_max": 0.0024960871669463813,
      "clip_ratio/high_mean": 0.0009930457053997088,
      "clip_ratio/low_mean": 0.0008633860907139024,
      "clip_ratio/low_min": 9.154379949904978e-05,
      "clip_ratio/region_mean": 0.0018564317870186642,
      "epoch": 0.02781326380017383,
      "grad_norm": 0.12647530436515808,
      "learning_rate": 5e-07,
      "loss": 0.0404,
      "step": 298
    },
    {
      "clip_ratio/high_max": 0.002172102438635193,
      "clip_ratio/high_mean": 0.0008877962645783555,
      "clip_ratio/low_mean": 0.0010627018491504714,
      "clip_ratio/low_min": 0.0001607529243301542,
      "clip_ratio/region_mean": 0.0019504981246427633,
      "epoch": 0.027906596900174416,
      "grad_norm": 0.11940247565507889,
      "learning_rate": 5e-07,
      "loss": 0.0184,
      "step": 299
    },
    {
      "clip_ratio/high_max": 0.0022398323490051553,
      "clip_ratio/high_mean": 0.0008826763787510572,
      "clip_ratio/low_mean": 0.0008855590913299238,
      "clip_ratio/low_min": 5.4257394367596135e-05,
      "clip_ratio/region_mean": 0.0017682354737189598,
      "epoch": 0.027999930000174998,
      "grad_norm": 0.11767226457595825,
      "learning_rate": 5e-07,
      "loss": 0.0323,
      "step": 300
    },
    {
      "clip_ratio/high_max": 0.0021636025703628547,
      "clip_ratio/high_mean": 0.0009021188234328292,
      "clip_ratio/low_mean": 0.0009793108656594995,
      "clip_ratio/low_min": 0.00011843374340969604,
      "clip_ratio/region_mean": 0.001881429649074562,
      "epoch": 0.028093263100175583,
      "grad_norm": 0.1175728365778923,
      "learning_rate": 5e-07,
      "loss": -0.0201,
      "step": 301
    },
    {
      "clip_ratio/high_max": 0.002031823998549953,
      "clip_ratio/high_mean": 0.0008444076620435226,
      "clip_ratio/low_mean": 0.0010483705664228182,
      "clip_ratio/low_min": 0.0001249656270374544,
      "clip_ratio/region_mean": 0.0018927782512037084,
      "epoch": 0.028186596200176165,
      "grad_norm": 0.11882726103067398,
      "learning_rate": 5e-07,
      "loss": 0.0481,
      "step": 302
    },
    {
      "clip_ratio/high_max": 0.0021227735160209704,
      "clip_ratio/high_mean": 0.0009496739257883746,
      "clip_ratio/low_mean": 0.0008999152450996917,
      "clip_ratio/low_min": 9.137691449723206e-05,
      "clip_ratio/region_mean": 0.0018495891345082782,
      "epoch": 0.02827992930017675,
      "grad_norm": 0.11820418387651443,
      "learning_rate": 5e-07,
      "loss": -0.0107,
      "step": 303
    },
    {
      "clip_ratio/high_max": 0.0022507782850880176,
      "clip_ratio/high_mean": 0.0009529133185424143,
      "clip_ratio/low_mean": 0.0010441900521982461,
      "clip_ratio/low_min": 0.00020287000506868935,
      "clip_ratio/region_mean": 0.0019971033834735863,
      "epoch": 0.028373262400177332,
      "grad_norm": 0.11792163550853729,
      "learning_rate": 5e-07,
      "loss": 0.043,
      "step": 304
    },
    {
      "clip_ratio/high_max": 0.0021386527150752954,
      "clip_ratio/high_mean": 0.0009438000088266563,
      "clip_ratio/low_mean": 0.0009208126193698263,
      "clip_ratio/low_min": 6.36795166428783e-05,
      "clip_ratio/region_mean": 0.0018646126336534508,
      "epoch": 0.028466595500177917,
      "grad_norm": 0.11224585026502609,
      "learning_rate": 5e-07,
      "loss": -0.0105,
      "step": 305
    },
    {
      "clip_ratio/high_max": 0.0020758694954565726,
      "clip_ratio/high_mean": 0.0009044832531799329,
      "clip_ratio/low_mean": 0.0009106932375289034,
      "clip_ratio/low_min": 9.341005898022559e-05,
      "clip_ratio/region_mean": 0.001815176467061974,
      "epoch": 0.0285599286001785,
      "grad_norm": 0.12004929780960083,
      "learning_rate": 5e-07,
      "loss": 0.0168,
      "step": 306
    },
    {
      "clip_ratio/high_max": 0.002160422067390755,
      "clip_ratio/high_mean": 0.0008972997893579304,
      "clip_ratio/low_mean": 0.0009079012797883479,
      "clip_ratio/low_min": 0.00016625978878437309,
      "clip_ratio/region_mean": 0.0018052010564133525,
      "epoch": 0.028653261700179084,
      "grad_norm": 0.12536944448947906,
      "learning_rate": 5e-07,
      "loss": 0.0302,
      "step": 307
    },
    {
      "clip_ratio/high_max": 0.0018522257087170146,
      "clip_ratio/high_mean": 0.0008533724667358911,
      "clip_ratio/low_mean": 0.0008787900951574557,
      "clip_ratio/low_min": 3.735810742000467e-05,
      "clip_ratio/region_mean": 0.001732162549160421,
      "epoch": 0.028746594800179666,
      "grad_norm": 0.10641402751207352,
      "learning_rate": 5e-07,
      "loss": 0.0488,
      "step": 308
    },
    {
      "clip_ratio/high_max": 0.0024877530813682824,
      "clip_ratio/high_mean": 0.0010934451202047057,
      "clip_ratio/low_mean": 0.0010000094989663921,
      "clip_ratio/low_min": 0.00010137895333173219,
      "clip_ratio/region_mean": 0.002093454560963437,
      "epoch": 0.02883992790018025,
      "grad_norm": 0.13478635251522064,
      "learning_rate": 5e-07,
      "loss": -0.0466,
      "step": 309
    },
    {
      "clip_ratio/high_max": 0.0024860936755430885,
      "clip_ratio/high_mean": 0.000995345413684845,
      "clip_ratio/low_mean": 0.0009335310642200056,
      "clip_ratio/low_min": 0.0001047687474056147,
      "clip_ratio/region_mean": 0.001928876452438999,
      "epoch": 0.028933261000180833,
      "grad_norm": 0.1123168095946312,
      "learning_rate": 5e-07,
      "loss": 0.006,
      "step": 310
    },
    {
      "clip_ratio/high_max": 0.002633968702866696,
      "clip_ratio/high_mean": 0.0010330485747545026,
      "clip_ratio/low_mean": 0.0008035637147258967,
      "clip_ratio/low_min": 7.834706048015505e-05,
      "clip_ratio/region_mean": 0.0018366122749284841,
      "epoch": 0.029026594100181415,
      "grad_norm": 0.12762361764907837,
      "learning_rate": 5e-07,
      "loss": -0.0368,
      "step": 311
    },
    {
      "clip_ratio/high_max": 0.002512906605261378,
      "clip_ratio/high_mean": 0.001013116696412908,
      "clip_ratio/low_mean": 0.0008439454832114279,
      "clip_ratio/low_min": 9.498628423898481e-05,
      "clip_ratio/region_mean": 0.0018570621614344418,
      "epoch": 0.029119927200182,
      "grad_norm": 0.11900242418050766,
      "learning_rate": 5e-07,
      "loss": 0.02,
      "step": 312
    },
    {
      "clip_ratio/high_max": 0.0019864439709635917,
      "clip_ratio/high_mean": 0.0009216824000759516,
      "clip_ratio/low_mean": 0.0009113787455135025,
      "clip_ratio/low_min": 6.469183699664427e-05,
      "clip_ratio/region_mean": 0.001833061149227433,
      "epoch": 0.02921326030018258,
      "grad_norm": 0.11845706403255463,
      "learning_rate": 5e-07,
      "loss": -0.0063,
      "step": 313
    },
    {
      "clip_ratio/high_max": 0.0023772915519657545,
      "clip_ratio/high_mean": 0.0009181770365103148,
      "clip_ratio/low_mean": 0.00103489665343659,
      "clip_ratio/low_min": 0.00011924569935217733,
      "clip_ratio/region_mean": 0.0019530736753949896,
      "epoch": 0.029306593400183167,
      "grad_norm": 0.1156000867486,
      "learning_rate": 5e-07,
      "loss": 0.0351,
      "step": 314
    },
    {
      "clip_ratio/high_max": 0.0022578483112738468,
      "clip_ratio/high_mean": 0.0008800266041362192,
      "clip_ratio/low_mean": 0.0010817551738000475,
      "clip_ratio/low_min": 4.4153524868306704e-05,
      "clip_ratio/region_mean": 0.0019617817451944575,
      "epoch": 0.02939992650018375,
      "grad_norm": 0.11094335466623306,
      "learning_rate": 5e-07,
      "loss": 0.008,
      "step": 315
    },
    {
      "clip_ratio/high_max": 0.002207269732025452,
      "clip_ratio/high_mean": 0.0009018454948090948,
      "clip_ratio/low_mean": 0.001080724749044748,
      "clip_ratio/low_min": 4.411655754665844e-05,
      "clip_ratio/region_mean": 0.0019825701747322455,
      "epoch": 0.029493259600184334,
      "grad_norm": 0.11382251977920532,
      "learning_rate": 5e-07,
      "loss": 0.0241,
      "step": 316
    },
    {
      "clip_ratio/high_max": 0.002187871352361981,
      "clip_ratio/high_mean": 0.0008607370618847199,
      "clip_ratio/low_mean": 0.0009821221683523618,
      "clip_ratio/low_min": 0.00012055238858010853,
      "clip_ratio/region_mean": 0.0018428592520649545,
      "epoch": 0.029586592700184915,
      "grad_norm": 0.12190994620323181,
      "learning_rate": 5e-07,
      "loss": 0.053,
      "step": 317
    },
    {
      "clip_ratio/high_max": 0.0023308928502956405,
      "clip_ratio/high_mean": 0.0009383099604747258,
      "clip_ratio/low_mean": 0.0008130985479510855,
      "clip_ratio/low_min": 9.305901039624587e-05,
      "clip_ratio/region_mean": 0.001751408493873896,
      "epoch": 0.0296799258001855,
      "grad_norm": 0.11135878413915634,
      "learning_rate": 5e-07,
      "loss": -0.0063,
      "step": 318
    },
    {
      "clip_ratio/high_max": 0.002030364852544153,
      "clip_ratio/high_mean": 0.0009290019552281592,
      "clip_ratio/low_mean": 0.00116496100963559,
      "clip_ratio/low_min": 0.00020186124311294407,
      "clip_ratio/region_mean": 0.0020939629757776856,
      "epoch": 0.029773258900186082,
      "grad_norm": 0.12734542787075043,
      "learning_rate": 5e-07,
      "loss": 0.0387,
      "step": 319
    },
    {
      "clip_ratio/high_max": 0.002182686781452503,
      "clip_ratio/high_mean": 0.0008392405470658559,
      "clip_ratio/low_mean": 0.0008877084183041006,
      "clip_ratio/low_min": 2.387008862569928e-05,
      "clip_ratio/region_mean": 0.0017269489326281473,
      "epoch": 0.029866592000186667,
      "grad_norm": 0.1161516010761261,
      "learning_rate": 5e-07,
      "loss": 0.0439,
      "step": 320
    },
    {
      "clip_ratio/high_max": 0.0021934079377388116,
      "clip_ratio/high_mean": 0.000903444690266042,
      "clip_ratio/low_mean": 0.0011068232652178267,
      "clip_ratio/low_min": 7.528895730501972e-05,
      "clip_ratio/region_mean": 0.0020102678827242926,
      "epoch": 0.02995992510018725,
      "grad_norm": 0.12351426482200623,
      "learning_rate": 5e-07,
      "loss": 0.023,
      "step": 321
    },
    {
      "clip_ratio/high_max": 0.0022225924403755926,
      "clip_ratio/high_mean": 0.00091271646124369,
      "clip_ratio/low_mean": 0.0009800733932934236,
      "clip_ratio/low_min": 9.763531670614611e-05,
      "clip_ratio/region_mean": 0.0018927898636320606,
      "epoch": 0.030053258200187834,
      "grad_norm": 0.11128009110689163,
      "learning_rate": 5e-07,
      "loss": 0.0261,
      "step": 322
    },
    {
      "clip_ratio/high_max": 0.0027970560040557757,
      "clip_ratio/high_mean": 0.0010432667531858897,
      "clip_ratio/low_mean": 0.0009556689446981181,
      "clip_ratio/low_min": 0.00013732102797803236,
      "clip_ratio/region_mean": 0.0019989356806036085,
      "epoch": 0.030146591300188416,
      "grad_norm": 0.1216343343257904,
      "learning_rate": 5e-07,
      "loss": -0.0051,
      "step": 323
    },
    {
      "clip_ratio/high_max": 0.0020904074408463202,
      "clip_ratio/high_mean": 0.000839557209474151,
      "clip_ratio/low_mean": 0.000849439442390576,
      "clip_ratio/low_min": 7.702653238084167e-05,
      "clip_ratio/region_mean": 0.0016889966282178648,
      "epoch": 0.030239924400188998,
      "grad_norm": 0.10218214988708496,
      "learning_rate": 5e-07,
      "loss": 0.0178,
      "step": 324
    },
    {
      "clip_ratio/high_max": 0.0019833228216157295,
      "clip_ratio/high_mean": 0.0008227236357924994,
      "clip_ratio/low_mean": 0.0009506957612757105,
      "clip_ratio/low_min": 7.137085867725546e-05,
      "clip_ratio/region_mean": 0.0017734194043441676,
      "epoch": 0.030333257500189583,
      "grad_norm": 0.10176560282707214,
      "learning_rate": 5e-07,
      "loss": 0.0392,
      "step": 325
    },
    {
      "clip_ratio/high_max": 0.001986965158721432,
      "clip_ratio/high_mean": 0.000907670873857569,
      "clip_ratio/low_mean": 0.0007867506810725899,
      "clip_ratio/low_min": 9.770647739060223e-05,
      "clip_ratio/region_mean": 0.0016944215894909576,
      "epoch": 0.030426590600190165,
      "grad_norm": 0.12039047479629517,
      "learning_rate": 5e-07,
      "loss": -0.0082,
      "step": 326
    },
    {
      "clip_ratio/high_max": 0.002434384783555288,
      "clip_ratio/high_mean": 0.0009573069128236966,
      "clip_ratio/low_mean": 0.0008496583868691232,
      "clip_ratio/low_min": 0.00013139917791704647,
      "clip_ratio/region_mean": 0.0018069653160637245,
      "epoch": 0.03051992370019075,
      "grad_norm": 0.12553082406520844,
      "learning_rate": 5e-07,
      "loss": 0.0091,
      "step": 327
    },
    {
      "clip_ratio/high_max": 0.002250920719234273,
      "clip_ratio/high_mean": 0.0008577977132517844,
      "clip_ratio/low_mean": 0.0009125208925979678,
      "clip_ratio/low_min": 2.713084859351511e-05,
      "clip_ratio/region_mean": 0.0017703186022117734,
      "epoch": 0.030613256800191332,
      "grad_norm": 0.11355113238096237,
      "learning_rate": 5e-07,
      "loss": 0.0352,
      "step": 328
    },
    {
      "clip_ratio/high_max": 0.002278512271004729,
      "clip_ratio/high_mean": 0.0010166469037358183,
      "clip_ratio/low_mean": 0.0011290969305264298,
      "clip_ratio/low_min": 0.00014987941540312022,
      "clip_ratio/region_mean": 0.0021457437906065024,
      "epoch": 0.030706589900191917,
      "grad_norm": 0.11754362285137177,
      "learning_rate": 5e-07,
      "loss": 0.0188,
      "step": 329
    },
    {
      "clip_ratio/high_max": 0.0021108093060320243,
      "clip_ratio/high_mean": 0.0009051229881151812,
      "clip_ratio/low_mean": 0.0010017550448537804,
      "clip_ratio/low_min": 9.37225277084508e-05,
      "clip_ratio/region_mean": 0.0019068780020461418,
      "epoch": 0.0307999230001925,
      "grad_norm": 0.11077357828617096,
      "learning_rate": 5e-07,
      "loss": 0.0399,
      "step": 330
    },
    {
      "clip_ratio/high_max": 0.0020569640710164094,
      "clip_ratio/high_mean": 0.0008153247472364455,
      "clip_ratio/low_mean": 0.0010021339840022847,
      "clip_ratio/low_min": 6.0643911183433374e-05,
      "clip_ratio/region_mean": 0.0018174587021348998,
      "epoch": 0.030893256100193084,
      "grad_norm": 0.11143878102302551,
      "learning_rate": 5e-07,
      "loss": 0.0319,
      "step": 331
    },
    {
      "clip_ratio/high_max": 0.0020473307740758173,
      "clip_ratio/high_mean": 0.0008229201466747327,
      "clip_ratio/low_mean": 0.0009217957594955806,
      "clip_ratio/low_min": 7.154792001529131e-05,
      "clip_ratio/region_mean": 0.001744715918903239,
      "epoch": 0.030986589200193666,
      "grad_norm": 0.10785824805498123,
      "learning_rate": 5e-07,
      "loss": 0.0541,
      "step": 332
    },
    {
      "clip_ratio/high_max": 0.0023763347780914046,
      "clip_ratio/high_mean": 0.0009032577472680714,
      "clip_ratio/low_mean": 0.0009082908836717252,
      "clip_ratio/low_min": 7.137028933357215e-05,
      "clip_ratio/region_mean": 0.0018115486382157542,
      "epoch": 0.03107992230019425,
      "grad_norm": 0.1086147129535675,
      "learning_rate": 5e-07,
      "loss": -0.0327,
      "step": 333
    },
    {
      "clip_ratio/high_max": 0.001893579825264169,
      "clip_ratio/high_mean": 0.000804789913672721,
      "clip_ratio/low_mean": 0.0010322894104319857,
      "clip_ratio/low_min": 0.00011223811270610895,
      "clip_ratio/region_mean": 0.0018370793550275266,
      "epoch": 0.031173255400194833,
      "grad_norm": 0.10754968971014023,
      "learning_rate": 5e-07,
      "loss": 0.0572,
      "step": 334
    },
    {
      "clip_ratio/high_max": 0.002299082188983448,
      "clip_ratio/high_mean": 0.0010397496862424305,
      "clip_ratio/low_mean": 0.0010049549982795725,
      "clip_ratio/low_min": 6.918500912433956e-05,
      "clip_ratio/region_mean": 0.002044704684522003,
      "epoch": 0.03126658850019542,
      "grad_norm": 0.11694256216287613,
      "learning_rate": 5e-07,
      "loss": -0.0211,
      "step": 335
    },
    {
      "clip_ratio/high_max": 0.002328189082618337,
      "clip_ratio/high_mean": 0.0009801960950426292,
      "clip_ratio/low_mean": 0.0008084466862783302,
      "clip_ratio/low_min": 0.00010109239610756049,
      "clip_ratio/region_mean": 0.0017886427813209593,
      "epoch": 0.031359921600196,
      "grad_norm": 0.12244091182947159,
      "learning_rate": 5e-07,
      "loss": 0.0126,
      "step": 336
    },
    {
      "clip_ratio/high_max": 0.002253012244182173,
      "clip_ratio/high_mean": 0.0008621785691502737,
      "clip_ratio/low_mean": 0.0009418578665645327,
      "clip_ratio/low_min": 0.00013789473814540543,
      "clip_ratio/region_mean": 0.0018040364593616687,
      "epoch": 0.03145325470019658,
      "grad_norm": 0.1119285523891449,
      "learning_rate": 5e-07,
      "loss": 0.0305,
      "step": 337
    },
    {
      "clip_ratio/high_max": 0.001991397777601378,
      "clip_ratio/high_mean": 0.0008603041824244428,
      "clip_ratio/low_mean": 0.0008676226188981673,
      "clip_ratio/low_min": 0.00010476017087057699,
      "clip_ratio/region_mean": 0.0017279267703997903,
      "epoch": 0.031546587800197166,
      "grad_norm": 0.11594386398792267,
      "learning_rate": 5e-07,
      "loss": 0.0001,
      "step": 338
    },
    {
      "clip_ratio/high_max": 0.0018405372102279216,
      "clip_ratio/high_mean": 0.0008245131684816442,
      "clip_ratio/low_mean": 0.0009995170548791066,
      "clip_ratio/low_min": 6.217517784534721e-05,
      "clip_ratio/region_mean": 0.0018240302160847932,
      "epoch": 0.03163992090019775,
      "grad_norm": 0.10203343629837036,
      "learning_rate": 5e-07,
      "loss": 0.0207,
      "step": 339
    },
    {
      "clip_ratio/high_max": 0.0022724627779098228,
      "clip_ratio/high_mean": 0.0009301438731199596,
      "clip_ratio/low_mean": 0.0009538824888295494,
      "clip_ratio/low_min": 6.842020229669288e-05,
      "clip_ratio/region_mean": 0.001884026380139403,
      "epoch": 0.03173325400019833,
      "grad_norm": 0.11514753103256226,
      "learning_rate": 5e-07,
      "loss": 0.0176,
      "step": 340
    },
    {
      "clip_ratio/high_max": 0.0022698222164763138,
      "clip_ratio/high_mean": 0.0009523916451144032,
      "clip_ratio/low_mean": 0.0009562559971527662,
      "clip_ratio/low_min": 8.159476055880077e-05,
      "clip_ratio/region_mean": 0.0019086476386291906,
      "epoch": 0.031826587100198915,
      "grad_norm": 0.11389671266078949,
      "learning_rate": 5e-07,
      "loss": 0.0176,
      "step": 341
    },
    {
      "clip_ratio/high_max": 0.002239878500404302,
      "clip_ratio/high_mean": 0.0009241103434760589,
      "clip_ratio/low_mean": 0.0009053942740138154,
      "clip_ratio/low_min": 0.00010027758389696828,
      "clip_ratio/region_mean": 0.00182950466114562,
      "epoch": 0.0319199202001995,
      "grad_norm": 0.11286180466413498,
      "learning_rate": 5e-07,
      "loss": 0.0236,
      "step": 342
    },
    {
      "clip_ratio/high_max": 0.0020952618833689485,
      "clip_ratio/high_mean": 0.0009392644042236498,
      "clip_ratio/low_mean": 0.0011335727431287523,
      "clip_ratio/low_min": 0.0002045510200332501,
      "clip_ratio/region_mean": 0.002072837065497879,
      "epoch": 0.032013253300200085,
      "grad_norm": 0.11782105267047882,
      "learning_rate": 5e-07,
      "loss": 0.0313,
      "step": 343
    },
    {
      "clip_ratio/high_max": 0.002185232162446482,
      "clip_ratio/high_mean": 0.0009090241273952415,
      "clip_ratio/low_mean": 0.0009272964707633946,
      "clip_ratio/low_min": 6.28149255135213e-05,
      "clip_ratio/region_mean": 0.0018363205672358163,
      "epoch": 0.032106586400200664,
      "grad_norm": 0.11633407324552536,
      "learning_rate": 5e-07,
      "loss": -0.0032,
      "step": 344
    },
    {
      "clip_ratio/high_max": 0.002122059704561252,
      "clip_ratio/high_mean": 0.0009489879885222763,
      "clip_ratio/low_mean": 0.0009088058941415511,
      "clip_ratio/low_min": 0.00010807654052769067,
      "clip_ratio/region_mean": 0.0018577939117676578,
      "epoch": 0.03219991950020125,
      "grad_norm": 0.11947130411863327,
      "learning_rate": 5e-07,
      "loss": 0.0684,
      "step": 345
    },
    {
      "clip_ratio/high_max": 0.001993249577935785,
      "clip_ratio/high_mean": 0.0008186774030036759,
      "clip_ratio/low_mean": 0.0010150406978937099,
      "clip_ratio/low_min": 4.257373529981123e-05,
      "clip_ratio/region_mean": 0.001833718066336587,
      "epoch": 0.032293252600201834,
      "grad_norm": 0.12146463245153427,
      "learning_rate": 5e-07,
      "loss": 0.0442,
      "step": 346
    },
    {
      "clip_ratio/high_max": 0.001958756649401039,
      "clip_ratio/high_mean": 0.000758624259106,
      "clip_ratio/low_mean": 0.0011231298449274618,
      "clip_ratio/low_min": 0.0001809815803426318,
      "clip_ratio/region_mean": 0.0018817541131284088,
      "epoch": 0.03238658570020242,
      "grad_norm": 0.11857195198535919,
      "learning_rate": 5e-07,
      "loss": 0.0252,
      "step": 347
    },
    {
      "clip_ratio/high_max": 0.001927272904140409,
      "clip_ratio/high_mean": 0.0008945649788074661,
      "clip_ratio/low_mean": 0.0010144972839043476,
      "clip_ratio/low_min": 7.50883646105649e-05,
      "clip_ratio/region_mean": 0.001909062237245962,
      "epoch": 0.032479918800203,
      "grad_norm": 0.11218500882387161,
      "learning_rate": 5e-07,
      "loss": 0.0346,
      "step": 348
    },
    {
      "clip_ratio/high_max": 0.0018382181406195741,
      "clip_ratio/high_mean": 0.0007828282359696459,
      "clip_ratio/low_mean": 0.001186191644592327,
      "clip_ratio/low_min": 0.0001928399187818286,
      "clip_ratio/region_mean": 0.001969019911484793,
      "epoch": 0.03257325190020358,
      "grad_norm": 0.11754020303487778,
      "learning_rate": 5e-07,
      "loss": 0.0614,
      "step": 349
    },
    {
      "clip_ratio/high_max": 0.0021124083796166815,
      "clip_ratio/high_mean": 0.0008962429037637776,
      "clip_ratio/low_mean": 0.001063426894688746,
      "clip_ratio/low_min": 0.00015796544812474167,
      "clip_ratio/region_mean": 0.001959669818461407,
      "epoch": 0.03266658500020417,
      "grad_norm": 0.12115529179573059,
      "learning_rate": 5e-07,
      "loss": 0.0358,
      "step": 350
    },
    {
      "clip_ratio/high_max": 0.00245618761255173,
      "clip_ratio/high_mean": 0.0010762067940959241,
      "clip_ratio/low_mean": 0.0007655518238607328,
      "clip_ratio/low_min": 5.934005093877204e-05,
      "clip_ratio/region_mean": 0.001841758617956657,
      "epoch": 0.032759918100204746,
      "grad_norm": 0.11036700755357742,
      "learning_rate": 5e-07,
      "loss": -0.0123,
      "step": 351
    },
    {
      "clip_ratio/high_max": 0.0024257999284600373,
      "clip_ratio/high_mean": 0.0010305587584298337,
      "clip_ratio/low_mean": 0.0008654985485918587,
      "clip_ratio/low_min": 9.059381136466982e-05,
      "clip_ratio/region_mean": 0.0018960572997457348,
      "epoch": 0.03285325120020533,
      "grad_norm": 0.11581318825483322,
      "learning_rate": 5e-07,
      "loss": -0.002,
      "step": 352
    },
    {
      "clip_ratio/high_max": 0.0020806275970244315,
      "clip_ratio/high_mean": 0.0008458974334644154,
      "clip_ratio/low_mean": 0.0010452367714606225,
      "clip_ratio/low_min": 0.00012073759717168286,
      "clip_ratio/region_mean": 0.0018911341976490803,
      "epoch": 0.03294658430020592,
      "grad_norm": 0.11050496995449066,
      "learning_rate": 5e-07,
      "loss": 0.0516,
      "step": 353
    },
    {
      "clip_ratio/high_max": 0.0021015809979871847,
      "clip_ratio/high_mean": 0.0008733218764973572,
      "clip_ratio/low_mean": 0.001048059573804494,
      "clip_ratio/low_min": 0.00011687112601066474,
      "clip_ratio/region_mean": 0.00192138142301701,
      "epoch": 0.0330399174002065,
      "grad_norm": 0.11453498154878616,
      "learning_rate": 5e-07,
      "loss": 0.034,
      "step": 354
    },
    {
      "clip_ratio/high_max": 0.0022860096614749637,
      "clip_ratio/high_mean": 0.0008797718601272209,
      "clip_ratio/low_mean": 0.0009825534325500485,
      "clip_ratio/low_min": 4.999840075470274e-05,
      "clip_ratio/region_mean": 0.0018623252617544495,
      "epoch": 0.03313325050020708,
      "grad_norm": 0.11144164949655533,
      "learning_rate": 5e-07,
      "loss": 0.0439,
      "step": 355
    },
    {
      "clip_ratio/high_max": 0.0021749449806520715,
      "clip_ratio/high_mean": 0.0009007381577248452,
      "clip_ratio/low_mean": 0.0009747770272952039,
      "clip_ratio/low_min": 3.0756043997826055e-05,
      "clip_ratio/region_mean": 0.0018755151686491445,
      "epoch": 0.033226583600207665,
      "grad_norm": 0.12310260534286499,
      "learning_rate": 5e-07,
      "loss": -0.0174,
      "step": 356
    },
    {
      "clip_ratio/high_max": 0.0021109637382323854,
      "clip_ratio/high_mean": 0.0008441220088570844,
      "clip_ratio/low_mean": 0.000874419081810629,
      "clip_ratio/low_min": 0.00011489608823467279,
      "clip_ratio/region_mean": 0.0017185410906677134,
      "epoch": 0.03331991670020825,
      "grad_norm": 0.12005891650915146,
      "learning_rate": 5e-07,
      "loss": 0.0201,
      "step": 357
    },
    {
      "clip_ratio/high_max": 0.0022002035584591795,
      "clip_ratio/high_mean": 0.0010037068277597427,
      "clip_ratio/low_mean": 0.0008737739954085555,
      "clip_ratio/low_min": 1.2583048373926431e-05,
      "clip_ratio/region_mean": 0.0018774808486341499,
      "epoch": 0.033413249800208836,
      "grad_norm": 0.11446987092494965,
      "learning_rate": 5e-07,
      "loss": 0.016,
      "step": 358
    },
    {
      "clip_ratio/high_max": 0.0025788378043216653,
      "clip_ratio/high_mean": 0.0009501486019871663,
      "clip_ratio/low_mean": 0.0009096389212572831,
      "clip_ratio/low_min": 0.00013626698819280136,
      "clip_ratio/region_mean": 0.0018597874950501136,
      "epoch": 0.033506582900209414,
      "grad_norm": 0.1254175752401352,
      "learning_rate": 5e-07,
      "loss": 0.0314,
      "step": 359
    },
    {
      "clip_ratio/high_max": 0.0019351789997017477,
      "clip_ratio/high_mean": 0.000834158192446921,
      "clip_ratio/low_mean": 0.0009397457342856796,
      "clip_ratio/low_min": 8.915285434341058e-05,
      "clip_ratio/region_mean": 0.0017739038958097808,
      "epoch": 0.03359991600021,
      "grad_norm": 0.14234015345573425,
      "learning_rate": 5e-07,
      "loss": 0.0262,
      "step": 360
    },
    {
      "clip_ratio/high_max": 0.0019736481917789206,
      "clip_ratio/high_mean": 0.0009213817211275455,
      "clip_ratio/low_mean": 0.0009459707944188267,
      "clip_ratio/low_min": 8.014815466594882e-05,
      "clip_ratio/region_mean": 0.0018673525119083934,
      "epoch": 0.033693249100210584,
      "grad_norm": 0.1267279088497162,
      "learning_rate": 5e-07,
      "loss": 0.0237,
      "step": 361
    },
    {
      "clip_ratio/high_max": 0.0019571087541407906,
      "clip_ratio/high_mean": 0.0008411022718064487,
      "clip_ratio/low_mean": 0.0011347119107085746,
      "clip_ratio/low_min": 0.00018933196133730235,
      "clip_ratio/region_mean": 0.001975814186153002,
      "epoch": 0.03378658220021117,
      "grad_norm": 0.11919976025819778,
      "learning_rate": 5e-07,
      "loss": 0.0494,
      "step": 362
    },
    {
      "clip_ratio/high_max": 0.002349023830902297,
      "clip_ratio/high_mean": 0.0009443710987397935,
      "clip_ratio/low_mean": 0.0010797441664180951,
      "clip_ratio/low_min": 0.00014392575212696102,
      "clip_ratio/region_mean": 0.002024115245149005,
      "epoch": 0.03387991530021175,
      "grad_norm": 0.12001349776983261,
      "learning_rate": 5e-07,
      "loss": 0.0028,
      "step": 363
    },
    {
      "clip_ratio/high_max": 0.0019574496582208667,
      "clip_ratio/high_mean": 0.000715497919372865,
      "clip_ratio/low_mean": 0.0011456758475105744,
      "clip_ratio/low_min": 0.00020557850712066283,
      "clip_ratio/region_mean": 0.001861173725046683,
      "epoch": 0.03397324840021233,
      "grad_norm": 0.11361299455165863,
      "learning_rate": 5e-07,
      "loss": 0.0788,
      "step": 364
    },
    {
      "clip_ratio/high_max": 0.0022529077250510454,
      "clip_ratio/high_mean": 0.0009384942786709871,
      "clip_ratio/low_mean": 0.0011084915513492888,
      "clip_ratio/low_min": 0.0001931647948367754,
      "clip_ratio/region_mean": 0.002046985799097456,
      "epoch": 0.03406658150021292,
      "grad_norm": 0.1243242397904396,
      "learning_rate": 5e-07,
      "loss": 0.0441,
      "step": 365
    },
    {
      "clip_ratio/high_max": 0.002254256971355062,
      "clip_ratio/high_mean": 0.0009680167313490529,
      "clip_ratio/low_mean": 0.0010084807672683382,
      "clip_ratio/low_min": 0.0001939716748893261,
      "clip_ratio/region_mean": 0.0019764975222642533,
      "epoch": 0.034159914600213497,
      "grad_norm": 0.1222744807600975,
      "learning_rate": 5e-07,
      "loss": 0.0237,
      "step": 366
    },
    {
      "clip_ratio/high_max": 0.0022775961260776967,
      "clip_ratio/high_mean": 0.0009749995952006429,
      "clip_ratio/low_mean": 0.0010336529012420215,
      "clip_ratio/low_min": 0.00010892614136537304,
      "clip_ratio/region_mean": 0.0020086524527869187,
      "epoch": 0.03425324770021408,
      "grad_norm": 0.12001646310091019,
      "learning_rate": 5e-07,
      "loss": 0.0248,
      "step": 367
    },
    {
      "clip_ratio/high_max": 0.002285444177687168,
      "clip_ratio/high_mean": 0.0010401212039141683,
      "clip_ratio/low_mean": 0.0010593254228297155,
      "clip_ratio/low_min": 8.264587449957617e-05,
      "clip_ratio/region_mean": 0.002099446617648937,
      "epoch": 0.03434658080021467,
      "grad_norm": 0.11942586302757263,
      "learning_rate": 5e-07,
      "loss": 0.0589,
      "step": 368
    },
    {
      "clip_ratio/high_max": 0.002352598516154103,
      "clip_ratio/high_mean": 0.0009073320652532857,
      "clip_ratio/low_mean": 0.0009589853980287444,
      "clip_ratio/low_min": 9.722856884764042e-05,
      "clip_ratio/region_mean": 0.0018663174487301148,
      "epoch": 0.03443991390021525,
      "grad_norm": 0.11761494725942612,
      "learning_rate": 5e-07,
      "loss": 0.0588,
      "step": 369
    },
    {
      "clip_ratio/high_max": 0.0022274790026131086,
      "clip_ratio/high_mean": 0.0008006764146557543,
      "clip_ratio/low_mean": 0.0010805947531480342,
      "clip_ratio/low_min": 0.00016326463355653686,
      "clip_ratio/region_mean": 0.0018812711859936826,
      "epoch": 0.03453324700021583,
      "grad_norm": 0.11192978173494339,
      "learning_rate": 5e-07,
      "loss": 0.0355,
      "step": 370
    },
    {
      "clip_ratio/high_max": 0.0023421350560965948,
      "clip_ratio/high_mean": 0.0009054395741259214,
      "clip_ratio/low_mean": 0.0009663225246185903,
      "clip_ratio/low_min": 5.533310286409687e-05,
      "clip_ratio/region_mean": 0.001871762127848342,
      "epoch": 0.034626580100216416,
      "grad_norm": 0.10717236995697021,
      "learning_rate": 5e-07,
      "loss": 0.0234,
      "step": 371
    },
    {
      "clip_ratio/high_max": 0.0021503387615666725,
      "clip_ratio/high_mean": 0.0008918727107811719,
      "clip_ratio/low_mean": 0.0010826957986864727,
      "clip_ratio/low_min": 0.00016206755208258983,
      "clip_ratio/region_mean": 0.0019745684694498777,
      "epoch": 0.034719913200217,
      "grad_norm": 0.1162085011601448,
      "learning_rate": 5e-07,
      "loss": -0.0046,
      "step": 372
    },
    {
      "clip_ratio/high_max": 0.0017860708030639216,
      "clip_ratio/high_mean": 0.0007423281313094776,
      "clip_ratio/low_mean": 0.0011883454153576167,
      "clip_ratio/low_min": 0.0001317314508924028,
      "clip_ratio/region_mean": 0.001930673504830338,
      "epoch": 0.034813246300217586,
      "grad_norm": 0.11793170124292374,
      "learning_rate": 5e-07,
      "loss": 0.0564,
      "step": 373
    },
    {
      "clip_ratio/high_max": 0.002248431912448723,
      "clip_ratio/high_mean": 0.0007868717766541522,
      "clip_ratio/low_mean": 0.0009218231007253053,
      "clip_ratio/low_min": 2.361569022468757e-05,
      "clip_ratio/region_mean": 0.001708694915578235,
      "epoch": 0.034906579400218164,
      "grad_norm": 0.11927468329668045,
      "learning_rate": 5e-07,
      "loss": 0.0258,
      "step": 374
    },
    {
      "clip_ratio/high_max": 0.002400244564341847,
      "clip_ratio/high_mean": 0.001032306954584783,
      "clip_ratio/low_mean": 0.001145557460404234,
      "clip_ratio/low_min": 0.0001191609389934456,
      "clip_ratio/region_mean": 0.002177864451368805,
      "epoch": 0.03499991250021875,
      "grad_norm": 0.11695149540901184,
      "learning_rate": 5e-07,
      "loss": 0.0093,
      "step": 375
    },
    {
      "clip_ratio/high_max": 0.0024100817972794175,
      "clip_ratio/high_mean": 0.0009452085232624086,
      "clip_ratio/low_mean": 0.001027869697281858,
      "clip_ratio/low_min": 5.327086546458304e-05,
      "clip_ratio/region_mean": 0.001973078222363256,
      "epoch": 0.035093245600219335,
      "grad_norm": 0.11165894567966461,
      "learning_rate": 5e-07,
      "loss": 0.0085,
      "step": 376
    },
    {
      "clip_ratio/high_max": 0.002152204942831304,
      "clip_ratio/high_mean": 0.000911409872060176,
      "clip_ratio/low_mean": 0.0012716420242213644,
      "clip_ratio/low_min": 0.00017814926604842185,
      "clip_ratio/region_mean": 0.0021830518599017523,
      "epoch": 0.03518657870021991,
      "grad_norm": 0.10562445223331451,
      "learning_rate": 5e-07,
      "loss": 0.0542,
      "step": 377
    },
    {
      "clip_ratio/high_max": 0.002243203212856315,
      "clip_ratio/high_mean": 0.0009726138905534754,
      "clip_ratio/low_mean": 0.0010239016010018531,
      "clip_ratio/low_min": 0.0001515105077487533,
      "clip_ratio/region_mean": 0.001996515493374318,
      "epoch": 0.0352799118002205,
      "grad_norm": 0.11949875205755234,
      "learning_rate": 5e-07,
      "loss": 0.024,
      "step": 378
    },
    {
      "clip_ratio/high_max": 0.0018753061231109314,
      "clip_ratio/high_mean": 0.0007560505928267958,
      "clip_ratio/low_mean": 0.0010859266694751568,
      "clip_ratio/low_min": 0.00015528515450569103,
      "clip_ratio/region_mean": 0.0018419772386550903,
      "epoch": 0.03537324490022108,
      "grad_norm": 0.11216006428003311,
      "learning_rate": 5e-07,
      "loss": 0.085,
      "step": 379
    },
    {
      "clip_ratio/high_max": 0.002079598547425121,
      "clip_ratio/high_mean": 0.0007813035090293852,
      "clip_ratio/low_mean": 0.0010736922358773882,
      "clip_ratio/low_min": 9.810713345359545e-05,
      "clip_ratio/region_mean": 0.0018549957931099925,
      "epoch": 0.03546657800022167,
      "grad_norm": 0.11425363272428513,
      "learning_rate": 5e-07,
      "loss": 0.0531,
      "step": 380
    },
    {
      "clip_ratio/high_max": 0.0023030113225104287,
      "clip_ratio/high_mean": 0.0009681996270956006,
      "clip_ratio/low_mean": 0.001105909701436758,
      "clip_ratio/low_min": 0.00012139325008320156,
      "clip_ratio/region_mean": 0.0020741093103424646,
      "epoch": 0.03555991110022225,
      "grad_norm": 0.10389048606157303,
      "learning_rate": 5e-07,
      "loss": 0.0375,
      "step": 381
    },
    {
      "clip_ratio/high_max": 0.0021519088913919404,
      "clip_ratio/high_mean": 0.0008867103315424174,
      "clip_ratio/low_mean": 0.0009848527788562933,
      "clip_ratio/low_min": 0.0001310051657128497,
      "clip_ratio/region_mean": 0.001871563094027806,
      "epoch": 0.03565324420022283,
      "grad_norm": 0.11120712012052536,
      "learning_rate": 5e-07,
      "loss": 0.0087,
      "step": 382
    },
    {
      "clip_ratio/high_max": 0.002059158119664062,
      "clip_ratio/high_mean": 0.0008634816185804084,
      "clip_ratio/low_mean": 0.0010063749887194717,
      "clip_ratio/low_min": 0.000119817465019878,
      "clip_ratio/region_mean": 0.0018698565909289755,
      "epoch": 0.03574657730022342,
      "grad_norm": 0.11071231961250305,
      "learning_rate": 5e-07,
      "loss": -0.0019,
      "step": 383
    },
    {
      "clip_ratio/high_max": 0.002178808965254575,
      "clip_ratio/high_mean": 0.0009113115793297766,
      "clip_ratio/low_mean": 0.001116982251915033,
      "clip_ratio/low_min": 0.00012056605010002386,
      "clip_ratio/region_mean": 0.0020282938130549155,
      "epoch": 0.035839910400224,
      "grad_norm": 0.12246000021696091,
      "learning_rate": 5e-07,
      "loss": 0.047,
      "step": 384
    },
    {
      "clip_ratio/high_max": 0.0027155160023539793,
      "clip_ratio/high_mean": 0.0010573027466307394,
      "clip_ratio/low_mean": 0.0009458582408115035,
      "clip_ratio/low_min": 7.205073052318767e-05,
      "clip_ratio/region_mean": 0.0020031609456054866,
      "epoch": 0.03593324350022458,
      "grad_norm": 0.1264844685792923,
      "learning_rate": 5e-07,
      "loss": -0.0255,
      "step": 385
    },
    {
      "clip_ratio/high_max": 0.0020243985563865863,
      "clip_ratio/high_mean": 0.000891569292434724,
      "clip_ratio/low_mean": 0.0010894654569710838,
      "clip_ratio/low_min": 0.00016690271695551928,
      "clip_ratio/region_mean": 0.0019810347439488396,
      "epoch": 0.036026576600225166,
      "grad_norm": 0.11337004601955414,
      "learning_rate": 5e-07,
      "loss": 0.0086,
      "step": 386
    },
    {
      "clip_ratio/high_max": 0.0025052124001376797,
      "clip_ratio/high_mean": 0.001102517268009251,
      "clip_ratio/low_mean": 0.0009290693196817301,
      "clip_ratio/low_min": 7.75293792685261e-05,
      "clip_ratio/region_mean": 0.0020315865986049175,
      "epoch": 0.03611990970022575,
      "grad_norm": 0.11649630218744278,
      "learning_rate": 5e-07,
      "loss": -0.041,
      "step": 387
    },
    {
      "clip_ratio/high_max": 0.002189797531173099,
      "clip_ratio/high_mean": 0.0009353546847705729,
      "clip_ratio/low_mean": 0.0009637661423766986,
      "clip_ratio/low_min": 0.00011918239852093393,
      "clip_ratio/region_mean": 0.0018991208416991867,
      "epoch": 0.03621324280022633,
      "grad_norm": 0.11189361661672592,
      "learning_rate": 5e-07,
      "loss": 0.0386,
      "step": 388
    },
    {
      "clip_ratio/high_max": 0.0018663667724467814,
      "clip_ratio/high_mean": 0.0008603203896200284,
      "clip_ratio/low_mean": 0.00104724407356116,
      "clip_ratio/low_min": 4.960774640494492e-05,
      "clip_ratio/region_mean": 0.0019075644158874638,
      "epoch": 0.036306575900226914,
      "grad_norm": 0.10243694484233856,
      "learning_rate": 5e-07,
      "loss": 0.0836,
      "step": 389
    },
    {
      "clip_ratio/high_max": 0.0021234780215309,
      "clip_ratio/high_mean": 0.0008518613631167682,
      "clip_ratio/low_mean": 0.0009539333477732725,
      "clip_ratio/low_min": 5.694049559679115e-05,
      "clip_ratio/region_mean": 0.0018057947017950937,
      "epoch": 0.0363999090002275,
      "grad_norm": 0.12041743844747543,
      "learning_rate": 5e-07,
      "loss": 0.0025,
      "step": 390
    },
    {
      "clip_ratio/high_max": 0.0019824362752842717,
      "clip_ratio/high_mean": 0.0007846086409699637,
      "clip_ratio/low_mean": 0.0009969769380404614,
      "clip_ratio/low_min": 8.511358737450792e-05,
      "clip_ratio/region_mean": 0.0017815856263041496,
      "epoch": 0.036493242100228085,
      "grad_norm": 0.0981244146823883,
      "learning_rate": 5e-07,
      "loss": 0.0472,
      "step": 391
    },
    {
      "clip_ratio/high_max": 0.002104561117448611,
      "clip_ratio/high_mean": 0.0009556067088851705,
      "clip_ratio/low_mean": 0.0010763441132439766,
      "clip_ratio/low_min": 9.962388412532164e-05,
      "clip_ratio/region_mean": 0.0020319508548709564,
      "epoch": 0.03658657520022866,
      "grad_norm": 0.11773033440113068,
      "learning_rate": 5e-07,
      "loss": 0.0461,
      "step": 392
    },
    {
      "clip_ratio/high_max": 0.0023684637308178935,
      "clip_ratio/high_mean": 0.0009494375244685216,
      "clip_ratio/low_mean": 0.0010393062293587718,
      "clip_ratio/low_min": 5.57265302632004e-05,
      "clip_ratio/region_mean": 0.001988743730180431,
      "epoch": 0.03667990830022925,
      "grad_norm": 0.11865058541297913,
      "learning_rate": 5e-07,
      "loss": 0.0111,
      "step": 393
    },
    {
      "clip_ratio/high_max": 0.0019132130619254895,
      "clip_ratio/high_mean": 0.0008260995527962223,
      "clip_ratio/low_mean": 0.0009146643806161592,
      "clip_ratio/low_min": 4.134377741138451e-05,
      "clip_ratio/region_mean": 0.0017407639534212649,
      "epoch": 0.036773241400229834,
      "grad_norm": 0.11469900608062744,
      "learning_rate": 5e-07,
      "loss": 0.0265,
      "step": 394
    },
    {
      "clip_ratio/high_max": 0.002052540614386089,
      "clip_ratio/high_mean": 0.0008216416517825564,
      "clip_ratio/low_mean": 0.0011621811663644621,
      "clip_ratio/low_min": 8.63391614984721e-05,
      "clip_ratio/region_mean": 0.001983822810871061,
      "epoch": 0.03686657450023042,
      "grad_norm": 0.11499077826738358,
      "learning_rate": 5e-07,
      "loss": 0.0716,
      "step": 395
    },
    {
      "clip_ratio/high_max": 0.0019437560986261815,
      "clip_ratio/high_mean": 0.0008657066009618575,
      "clip_ratio/low_mean": 0.0010951802032650448,
      "clip_ratio/low_min": 8.391611208935501e-05,
      "clip_ratio/region_mean": 0.001960886802407913,
      "epoch": 0.036959907600231,
      "grad_norm": 0.11790554225444794,
      "learning_rate": 5e-07,
      "loss": 0.0388,
      "step": 396
    },
    {
      "clip_ratio/high_max": 0.001987604413443478,
      "clip_ratio/high_mean": 0.0008803830623946851,
      "clip_ratio/low_mean": 0.0008348008268512785,
      "clip_ratio/low_min": 9.047857110999757e-05,
      "clip_ratio/region_mean": 0.0017151838837889954,
      "epoch": 0.03705324070023158,
      "grad_norm": 0.1118721216917038,
      "learning_rate": 5e-07,
      "loss": -0.0245,
      "step": 397
    },
    {
      "clip_ratio/high_max": 0.0022266219020821154,
      "clip_ratio/high_mean": 0.0008813780896161916,
      "clip_ratio/low_mean": 0.0009688609607110266,
      "clip_ratio/low_min": 0.00010400953715361538,
      "clip_ratio/region_mean": 0.0018502390885259956,
      "epoch": 0.03714657380023217,
      "grad_norm": 0.10484080761671066,
      "learning_rate": 5e-07,
      "loss": 0.0416,
      "step": 398
    },
    {
      "clip_ratio/high_max": 0.0018902897390944418,
      "clip_ratio/high_mean": 0.0008511937558068894,
      "clip_ratio/low_mean": 0.001018057817418594,
      "clip_ratio/low_min": 0.00010195696086157113,
      "clip_ratio/region_mean": 0.0018692515659495257,
      "epoch": 0.03723990690023275,
      "grad_norm": 0.11170488595962524,
      "learning_rate": 5e-07,
      "loss": 0.0233,
      "step": 399
    },
    {
      "clip_ratio/high_max": 0.0022713952712365426,
      "clip_ratio/high_mean": 0.00098377840458852,
      "clip_ratio/low_mean": 0.0010039686130767222,
      "clip_ratio/low_min": 0.00017561052027303958,
      "clip_ratio/region_mean": 0.0019877469530911185,
      "epoch": 0.03733324000023333,
      "grad_norm": 0.11726188659667969,
      "learning_rate": 5e-07,
      "loss": 0.0229,
      "step": 400
    },
    {
      "clip_ratio/high_max": 0.00195846424321644,
      "clip_ratio/high_mean": 0.0009012409936985932,
      "clip_ratio/low_mean": 0.0009991721271944698,
      "clip_ratio/low_min": 7.277793247340014e-05,
      "clip_ratio/region_mean": 0.0019004130881512538,
      "epoch": 0.037426573100233916,
      "grad_norm": 0.10721128433942795,
      "learning_rate": 5e-07,
      "loss": 0.0349,
      "step": 401
    },
    {
      "clip_ratio/high_max": 0.0022282070422079414,
      "clip_ratio/high_mean": 0.0009388288744958118,
      "clip_ratio/low_mean": 0.0009378210525028408,
      "clip_ratio/low_min": 0.00015039171557873487,
      "clip_ratio/region_mean": 0.001876649897894822,
      "epoch": 0.0375199062002345,
      "grad_norm": 0.1217333972454071,
      "learning_rate": 5e-07,
      "loss": 0.0265,
      "step": 402
    },
    {
      "clip_ratio/high_max": 0.00213190170325106,
      "clip_ratio/high_mean": 0.0008640813484817045,
      "clip_ratio/low_mean": 0.000990671840554569,
      "clip_ratio/low_min": 6.1344717778411e-05,
      "clip_ratio/region_mean": 0.0018547532381489873,
      "epoch": 0.03761323930023508,
      "grad_norm": 0.1143287792801857,
      "learning_rate": 5e-07,
      "loss": 0.0224,
      "step": 403
    },
    {
      "clip_ratio/high_max": 0.0019748996674024966,
      "clip_ratio/high_mean": 0.00088850061820267,
      "clip_ratio/low_mean": 0.000995068692645873,
      "clip_ratio/low_min": 0.00012359529500827193,
      "clip_ratio/region_mean": 0.0018835693408618681,
      "epoch": 0.037706572400235665,
      "grad_norm": 0.11634189635515213,
      "learning_rate": 5e-07,
      "loss": 0.0173,
      "step": 404
    },
    {
      "clip_ratio/high_max": 0.002459497867675964,
      "clip_ratio/high_mean": 0.0010424057909403928,
      "clip_ratio/low_mean": 0.000993060053588124,
      "clip_ratio/low_min": 0.00016492127360834274,
      "clip_ratio/region_mean": 0.002035465782682877,
      "epoch": 0.03779990550023625,
      "grad_norm": 0.12088415026664734,
      "learning_rate": 5e-07,
      "loss": 0.0019,
      "step": 405
    },
    {
      "clip_ratio/high_max": 0.0021116211064509116,
      "clip_ratio/high_mean": 0.000893208860361483,
      "clip_ratio/low_mean": 0.0009124061434704345,
      "clip_ratio/low_min": 0.0001121883797168266,
      "clip_ratio/region_mean": 0.0018056150001939386,
      "epoch": 0.037893238600236835,
      "grad_norm": 0.11237647384405136,
      "learning_rate": 5e-07,
      "loss": 0.0198,
      "step": 406
    },
    {
      "clip_ratio/high_max": 0.002267283052788116,
      "clip_ratio/high_mean": 0.0009926409875333775,
      "clip_ratio/low_mean": 0.0011070757755078375,
      "clip_ratio/low_min": 0.00012666125803661998,
      "clip_ratio/region_mean": 0.0020997167521272786,
      "epoch": 0.03798657170023741,
      "grad_norm": 0.12430300563573837,
      "learning_rate": 5e-07,
      "loss": 0.0611,
      "step": 407
    },
    {
      "clip_ratio/high_max": 0.002245603591291001,
      "clip_ratio/high_mean": 0.0008766748724156059,
      "clip_ratio/low_mean": 0.0010880503577936906,
      "clip_ratio/low_min": 0.00010592746548354626,
      "clip_ratio/region_mean": 0.0019647252556751482,
      "epoch": 0.038079904800238,
      "grad_norm": 0.10833669453859329,
      "learning_rate": 5e-07,
      "loss": 0.0311,
      "step": 408
    },
    {
      "clip_ratio/high_max": 0.002598715822387021,
      "clip_ratio/high_mean": 0.0010660577208909672,
      "clip_ratio/low_mean": 0.000903201707842527,
      "clip_ratio/low_min": 4.3969875150651205e-05,
      "clip_ratio/region_mean": 0.001969259355973918,
      "epoch": 0.038173237900238584,
      "grad_norm": 0.11458487808704376,
      "learning_rate": 5e-07,
      "loss": -0.0437,
      "step": 409
    },
    {
      "clip_ratio/high_max": 0.0021769263366877567,
      "clip_ratio/high_mean": 0.0009403943040524609,
      "clip_ratio/low_mean": 0.001013101740682032,
      "clip_ratio/low_min": 0.0001428050682079629,
      "clip_ratio/region_mean": 0.001953496041096514,
      "epoch": 0.03826657100023917,
      "grad_norm": 0.12137886136770248,
      "learning_rate": 5e-07,
      "loss": 0.0218,
      "step": 410
    },
    {
      "clip_ratio/high_max": 0.0018579772549855988,
      "clip_ratio/high_mean": 0.0007604994916619034,
      "clip_ratio/low_mean": 0.0009602315149095375,
      "clip_ratio/low_min": 0.00014063035814615432,
      "clip_ratio/region_mean": 0.0017207310738740489,
      "epoch": 0.03835990410023975,
      "grad_norm": 0.11552492529153824,
      "learning_rate": 5e-07,
      "loss": 0.0179,
      "step": 411
    },
    {
      "clip_ratio/high_max": 0.002264322836708743,
      "clip_ratio/high_mean": 0.0009164547191176098,
      "clip_ratio/low_mean": 0.0009335634822491556,
      "clip_ratio/low_min": 0.00010072029817820294,
      "clip_ratio/region_mean": 0.0018500182122807018,
      "epoch": 0.03845323720024033,
      "grad_norm": 0.11407168954610825,
      "learning_rate": 5e-07,
      "loss": 0.0149,
      "step": 412
    },
    {
      "clip_ratio/high_max": 0.0022430844546761364,
      "clip_ratio/high_mean": 0.0009503949731879402,
      "clip_ratio/low_mean": 0.0011283106014161604,
      "clip_ratio/low_min": 0.0001403434021085559,
      "clip_ratio/region_mean": 0.002078705590975005,
      "epoch": 0.03854657030024092,
      "grad_norm": 0.11802615970373154,
      "learning_rate": 5e-07,
      "loss": 0.0358,
      "step": 413
    },
    {
      "clip_ratio/high_max": 0.002409376007562969,
      "clip_ratio/high_mean": 0.00100148188721505,
      "clip_ratio/low_mean": 0.0010467706488270778,
      "clip_ratio/low_min": 9.948819115379592e-05,
      "clip_ratio/region_mean": 0.002048252514214255,
      "epoch": 0.038639903400241496,
      "grad_norm": 0.11915134638547897,
      "learning_rate": 5e-07,
      "loss": 0.0403,
      "step": 414
    },
    {
      "clip_ratio/high_max": 0.0019876173901138827,
      "clip_ratio/high_mean": 0.0008307009484269656,
      "clip_ratio/low_mean": 0.0009996168646466685,
      "clip_ratio/low_min": 5.6614147979416884e-05,
      "clip_ratio/region_mean": 0.0018303178003407083,
      "epoch": 0.03873323650024208,
      "grad_norm": 0.11585742980241776,
      "learning_rate": 5e-07,
      "loss": 0.0299,
      "step": 415
    },
    {
      "clip_ratio/high_max": 0.0021483567179529928,
      "clip_ratio/high_mean": 0.0008746034200157737,
      "clip_ratio/low_mean": 0.0009069994230230805,
      "clip_ratio/low_min": 0.00016074656468845205,
      "clip_ratio/region_mean": 0.0017816028775996529,
      "epoch": 0.038826569600242666,
      "grad_norm": 0.11042338609695435,
      "learning_rate": 5e-07,
      "loss": 0.0175,
      "step": 416
    },
    {
      "clip_ratio/high_max": 0.0020472105679800734,
      "clip_ratio/high_mean": 0.0008443293027085019,
      "clip_ratio/low_mean": 0.0008968900128820678,
      "clip_ratio/low_min": 7.960054335853783e-05,
      "clip_ratio/region_mean": 0.0017412193046766333,
      "completions/clipped_ratio": 0.01495361328125,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4086.0,
      "completions/mean_length": 613.2021484375,
      "completions/mean_terminated_length": 560.3311157226562,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.03891990270024325,
      "grad_norm": 0.11155068874359131,
      "learning_rate": 5e-07,
      "loss": 0.0408,
      "num_tokens": 407523340.0,
      "reward": 0.56640625,
      "reward_std": 0.208588108420372,
      "rewards/simpleverify_reward/mean": 0.56640625,
      "rewards/simpleverify_reward/std": 0.4955727458000183,
      "step": 417
    },
    {
      "clip_ratio/high_max": 0.0024894310190575197,
      "clip_ratio/high_mean": 0.0010114089272974525,
      "clip_ratio/low_mean": 0.0007935671292216284,
      "clip_ratio/low_min": 8.625122063676827e-05,
      "clip_ratio/region_mean": 0.0018049760910798796,
      "epoch": 0.03901323580024383,
      "grad_norm": 0.10498879104852676,
      "learning_rate": 5e-07,
      "loss": -0.03,
      "step": 418
    },
    {
      "clip_ratio/high_max": 0.0022262219645199366,
      "clip_ratio/high_mean": 0.0009699763359094504,
      "clip_ratio/low_mean": 0.000844489410155802,
      "clip_ratio/low_min": 5.0856137022492476e-05,
      "clip_ratio/region_mean": 0.0018144657151424326,
      "epoch": 0.039106568900244415,
      "grad_norm": 0.11428552865982056,
      "learning_rate": 5e-07,
      "loss": 0.0089,
      "step": 419
    },
    {
      "clip_ratio/high_max": 0.0020746120644616894,
      "clip_ratio/high_mean": 0.0008889053515304113,
      "clip_ratio/low_mean": 0.0008117382340060431,
      "clip_ratio/low_min": 9.142333874478936e-05,
      "clip_ratio/region_mean": 0.0017006436064548325,
      "epoch": 0.039199902000245,
      "grad_norm": 0.11061646044254303,
      "learning_rate": 5e-07,
      "loss": -0.0212,
      "step": 420
    },
    {
      "clip_ratio/high_max": 0.002378481876803562,
      "clip_ratio/high_mean": 0.001004301650027628,
      "clip_ratio/low_mean": 0.0008900490083760815,
      "clip_ratio/low_min": 8.897139377950225e-05,
      "clip_ratio/region_mean": 0.0018943506802315824,
      "epoch": 0.039293235100245585,
      "grad_norm": 0.11658220738172531,
      "learning_rate": 5e-07,
      "loss": 0.0144,
      "step": 421
    },
    {
      "clip_ratio/high_max": 0.00228461703954963,
      "clip_ratio/high_mean": 0.0009238351649401011,
      "clip_ratio/low_mean": 0.0007802150230418192,
      "clip_ratio/low_min": 9.293986477132421e-05,
      "clip_ratio/region_mean": 0.00170405024982756,
      "epoch": 0.039386568200246164,
      "grad_norm": 0.12547507882118225,
      "learning_rate": 5e-07,
      "loss": -0.0285,
      "step": 422
    },
    {
      "clip_ratio/high_max": 0.0021036378529970534,
      "clip_ratio/high_mean": 0.0009916737908497453,
      "clip_ratio/low_mean": 0.0008480150099785533,
      "clip_ratio/low_min": 8.406619599554688e-05,
      "clip_ratio/region_mean": 0.0018396888190181926,
      "epoch": 0.03947990130024675,
      "grad_norm": 0.10444321483373642,
      "learning_rate": 5e-07,
      "loss": -0.0115,
      "step": 423
    },
    {
      "clip_ratio/high_max": 0.0019241860281908885,
      "clip_ratio/high_mean": 0.0007510905306844506,
      "clip_ratio/low_mean": 0.0009504511490376899,
      "clip_ratio/low_min": 5.3214619583741296e-05,
      "clip_ratio/region_mean": 0.0017015416669892147,
      "epoch": 0.039573234400247334,
      "grad_norm": 0.10620523989200592,
      "learning_rate": 5e-07,
      "loss": 0.0755,
      "step": 424
    },
    {
      "clip_ratio/high_max": 0.0022312032015179284,
      "clip_ratio/high_mean": 0.0010017126187449321,
      "clip_ratio/low_mean": 0.0009404229085703264,
      "clip_ratio/low_min": 8.566594806325156e-05,
      "clip_ratio/region_mean": 0.0019421355536906049,
      "epoch": 0.03966656750024792,
      "grad_norm": 0.12050700187683105,
      "learning_rate": 5e-07,
      "loss": -0.0056,
      "step": 425
    },
    {
      "clip_ratio/high_max": 0.0022704732218699064,
      "clip_ratio/high_mean": 0.0009045699462149059,
      "clip_ratio/low_mean": 0.001012141365208663,
      "clip_ratio/low_min": 8.178643656719942e-05,
      "clip_ratio/region_mean": 0.0019167112986906432,
      "epoch": 0.0397599006002485,
      "grad_norm": 0.11901837587356567,
      "learning_rate": 5e-07,
      "loss": 0.0237,
      "step": 426
    },
    {
      "clip_ratio/high_max": 0.0018694687896640971,
      "clip_ratio/high_mean": 0.0008047959727264242,
      "clip_ratio/low_mean": 0.000813708935311297,
      "clip_ratio/low_min": 7.124895273591392e-05,
      "clip_ratio/region_mean": 0.0016185049098567106,
      "epoch": 0.03985323370024908,
      "grad_norm": 0.11720944941043854,
      "learning_rate": 5e-07,
      "loss": 0.0315,
      "step": 427
    },
    {
      "clip_ratio/high_max": 0.00216426863335073,
      "clip_ratio/high_mean": 0.000869834464538144,
      "clip_ratio/low_mean": 0.0009181051136692986,
      "clip_ratio/low_min": 9.038032476382796e-05,
      "clip_ratio/region_mean": 0.0017879395090858452,
      "epoch": 0.03994656680024967,
      "grad_norm": 0.10514384508132935,
      "learning_rate": 5e-07,
      "loss": 0.0356,
      "step": 428
    },
    {
      "clip_ratio/high_max": 0.0019163859797117766,
      "clip_ratio/high_mean": 0.0008499363684677519,
      "clip_ratio/low_mean": 0.000901856692507863,
      "clip_ratio/low_min": 0.0001266635235879221,
      "clip_ratio/region_mean": 0.0017517930536996573,
      "epoch": 0.040039899900250246,
      "grad_norm": 0.10962148755788803,
      "learning_rate": 5e-07,
      "loss": 0.0615,
      "step": 429
    },
    {
      "clip_ratio/high_max": 0.0023745566941215657,
      "clip_ratio/high_mean": 0.0010017061395046767,
      "clip_ratio/low_mean": 0.0008677822370373178,
      "clip_ratio/low_min": 9.648194554756628e-05,
      "clip_ratio/region_mean": 0.0018694883438001852,
      "epoch": 0.04013323300025083,
      "grad_norm": 0.11430056393146515,
      "learning_rate": 5e-07,
      "loss": 0.022,
      "step": 430
    },
    {
      "clip_ratio/high_max": 0.002342741623579059,
      "clip_ratio/high_mean": 0.0009691544546512887,
      "clip_ratio/low_mean": 0.0008317142965097446,
      "clip_ratio/low_min": 8.309790064231493e-05,
      "clip_ratio/region_mean": 0.0018008688020927366,
      "epoch": 0.04022656610025142,
      "grad_norm": 0.11341247707605362,
      "learning_rate": 5e-07,
      "loss": 0.0102,
      "step": 431
    },
    {
      "clip_ratio/high_max": 0.0023101785918697715,
      "clip_ratio/high_mean": 0.0009021446712722536,
      "clip_ratio/low_mean": 0.0009905214083119063,
      "clip_ratio/low_min": 0.00021605412803182844,
      "clip_ratio/region_mean": 0.0018926660995930433,
      "epoch": 0.040319899200252,
      "grad_norm": 0.11745066195726395,
      "learning_rate": 5e-07,
      "loss": 0.0557,
      "step": 432
    },
    {
      "clip_ratio/high_max": 0.0019215032079955563,
      "clip_ratio/high_mean": 0.0008681080744281644,
      "clip_ratio/low_mean": 0.0008138108751154505,
      "clip_ratio/low_min": 5.5184495977300685e-05,
      "clip_ratio/region_mean": 0.001681918955000583,
      "epoch": 0.04041323230025258,
      "grad_norm": 0.10230834037065506,
      "learning_rate": 5e-07,
      "loss": 0.0364,
      "step": 433
    },
    {
      "clip_ratio/high_max": 0.0021025076930527575,
      "clip_ratio/high_mean": 0.0009245342480426189,
      "clip_ratio/low_mean": 0.000831203423331317,
      "clip_ratio/low_min": 0.00011210782577109057,
      "clip_ratio/region_mean": 0.0017557376486365683,
      "epoch": 0.040506565400253165,
      "grad_norm": 0.10392183065414429,
      "learning_rate": 5e-07,
      "loss": 0.0372,
      "step": 434
    },
    {
      "clip_ratio/high_max": 0.002196552035456989,
      "clip_ratio/high_mean": 0.0008908397667255485,
      "clip_ratio/low_mean": 0.0008697251105331816,
      "clip_ratio/low_min": 8.248647645814344e-06,
      "clip_ratio/region_mean": 0.0017605648608878255,
      "epoch": 0.04059989850025375,
      "grad_norm": 0.10884860157966614,
      "learning_rate": 5e-07,
      "loss": 0.0327,
      "step": 435
    },
    {
      "clip_ratio/high_max": 0.0022505449451273307,
      "clip_ratio/high_mean": 0.0009421310423931573,
      "clip_ratio/low_mean": 0.0009911400793498615,
      "clip_ratio/low_min": 9.061676337296376e-05,
      "clip_ratio/region_mean": 0.001933271109010093,
      "epoch": 0.040693231600254336,
      "grad_norm": 0.10632655024528503,
      "learning_rate": 5e-07,
      "loss": 0.0311,
      "step": 436
    },
    {
      "clip_ratio/high_max": 0.0026432070662849583,
      "clip_ratio/high_mean": 0.0010343264730181545,
      "clip_ratio/low_mean": 0.0009797959428397007,
      "clip_ratio/low_min": 0.00013589286481874296,
      "clip_ratio/region_mean": 0.0020141224631515797,
      "epoch": 0.040786564700254914,
      "grad_norm": 0.12098246812820435,
      "learning_rate": 5e-07,
      "loss": 0.0001,
      "step": 437
    },
    {
      "clip_ratio/high_max": 0.0022656746514257975,
      "clip_ratio/high_mean": 0.0009049836717167636,
      "clip_ratio/low_mean": 0.0010511727414268535,
      "clip_ratio/low_min": 0.00014224931510398164,
      "clip_ratio/region_mean": 0.0019561564113246277,
      "epoch": 0.0408798978002555,
      "grad_norm": 0.11527141183614731,
      "learning_rate": 5e-07,
      "loss": 0.0571,
      "step": 438
    },
    {
      "clip_ratio/high_max": 0.002159282325010281,
      "clip_ratio/high_mean": 0.0008199953153962269,
      "clip_ratio/low_mean": 0.0010194907808909193,
      "clip_ratio/low_min": 8.80414227140136e-05,
      "clip_ratio/region_mean": 0.0018394861326669343,
      "epoch": 0.040973230900256084,
      "grad_norm": 0.1200837567448616,
      "learning_rate": 5e-07,
      "loss": 0.0435,
      "step": 439
    },
    {
      "clip_ratio/high_max": 0.001925599281094037,
      "clip_ratio/high_mean": 0.0007526139143010369,
      "clip_ratio/low_mean": 0.0009311939975304995,
      "clip_ratio/low_min": 4.933803575113416e-05,
      "clip_ratio/region_mean": 0.0016838079536682926,
      "epoch": 0.04106656400025666,
      "grad_norm": 0.12391114234924316,
      "learning_rate": 5e-07,
      "loss": 0.0532,
      "step": 440
    },
    {
      "clip_ratio/high_max": 0.0020696952524303924,
      "clip_ratio/high_mean": 0.0008172480556822848,
      "clip_ratio/low_mean": 0.000923171815884416,
      "clip_ratio/low_min": 7.536470093327807e-05,
      "clip_ratio/region_mean": 0.0017404198806616478,
      "epoch": 0.04115989710025725,
      "grad_norm": 0.132726788520813,
      "learning_rate": 5e-07,
      "loss": 0.0101,
      "step": 441
    },
    {
      "clip_ratio/high_max": 0.002199378563091159,
      "clip_ratio/high_mean": 0.0008500831227138406,
      "clip_ratio/low_mean": 0.0009633028021198697,
      "clip_ratio/low_min": 9.46291875152383e-05,
      "clip_ratio/region_mean": 0.0018133859921363182,
      "epoch": 0.04125323020025783,
      "grad_norm": 0.11395154893398285,
      "learning_rate": 5e-07,
      "loss": 0.0448,
      "step": 442
    },
    {
      "clip_ratio/high_max": 0.002236312640889082,
      "clip_ratio/high_mean": 0.0009337168012280017,
      "clip_ratio/low_mean": 0.0010843826003110735,
      "clip_ratio/low_min": 0.00015094361606315942,
      "clip_ratio/region_mean": 0.0020180993669782765,
      "epoch": 0.04134656330025842,
      "grad_norm": 0.12408073246479034,
      "learning_rate": 5e-07,
      "loss": 0.101,
      "step": 443
    },
    {
      "clip_ratio/high_max": 0.0016570947591389995,
      "clip_ratio/high_mean": 0.0007377153451670893,
      "clip_ratio/low_mean": 0.0008551157188776415,
      "clip_ratio/low_min": 6.969280457269633e-05,
      "clip_ratio/region_mean": 0.0015928310713206884,
      "epoch": 0.041439896400258996,
      "grad_norm": 0.11088405549526215,
      "learning_rate": 5e-07,
      "loss": 0.0362,
      "step": 444
    },
    {
      "clip_ratio/high_max": 0.002326901096239453,
      "clip_ratio/high_mean": 0.0008728282700758427,
      "clip_ratio/low_mean": 0.0009209823256242089,
      "clip_ratio/low_min": 4.812352653971175e-05,
      "clip_ratio/region_mean": 0.0017938105047505815,
      "epoch": 0.04153322950025958,
      "grad_norm": 0.11258216947317123,
      "learning_rate": 5e-07,
      "loss": 0.0505,
      "step": 445
    },
    {
      "clip_ratio/high_max": 0.0023237306959345005,
      "clip_ratio/high_mean": 0.0008884988565114327,
      "clip_ratio/low_mean": 0.0009777886461961316,
      "clip_ratio/low_min": 0.00012307824636081932,
      "clip_ratio/region_mean": 0.0018662875081645325,
      "epoch": 0.04162656260026017,
      "grad_norm": 0.10692603141069412,
      "learning_rate": 5e-07,
      "loss": 0.0141,
      "step": 446
    },
    {
      "clip_ratio/high_max": 0.0019036232042708434,
      "clip_ratio/high_mean": 0.000818919939774787,
      "clip_ratio/low_mean": 0.0009221433756465558,
      "clip_ratio/low_min": 7.936309748401982e-05,
      "clip_ratio/region_mean": 0.0017410633372492157,
      "epoch": 0.04171989570026075,
      "grad_norm": 0.1126672700047493,
      "learning_rate": 5e-07,
      "loss": 0.0296,
      "step": 447
    },
    {
      "clip_ratio/high_max": 0.002254437240480911,
      "clip_ratio/high_mean": 0.0010447467266203603,
      "clip_ratio/low_mean": 0.0009017074971779948,
      "clip_ratio/low_min": 4.200304101686925e-05,
      "clip_ratio/region_mean": 0.0019464542565401644,
      "epoch": 0.04181322880026133,
      "grad_norm": 0.12708714604377747,
      "learning_rate": 5e-07,
      "loss": -0.0012,
      "step": 448
    },
    {
      "clip_ratio/high_max": 0.002026104204560397,
      "clip_ratio/high_mean": 0.0008598070726293372,
      "clip_ratio/low_mean": 0.0010236661291855853,
      "clip_ratio/low_min": 0.00018065407675749157,
      "clip_ratio/region_mean": 0.0018834732436516788,
      "epoch": 0.041906561900261916,
      "grad_norm": 0.11233428120613098,
      "learning_rate": 5e-07,
      "loss": 0.0427,
      "step": 449
    },
    {
      "clip_ratio/high_max": 0.00198971923236968,
      "clip_ratio/high_mean": 0.0008742783938942011,
      "clip_ratio/low_mean": 0.0010493375320947962,
      "clip_ratio/low_min": 0.00011824972989415983,
      "clip_ratio/region_mean": 0.0019236159278079867,
      "epoch": 0.0419998950002625,
      "grad_norm": 0.11820562928915024,
      "learning_rate": 5e-07,
      "loss": 0.0459,
      "step": 450
    },
    {
      "clip_ratio/high_max": 0.002374687399424147,
      "clip_ratio/high_mean": 0.0009707354456622852,
      "clip_ratio/low_mean": 0.0009407743018527981,
      "clip_ratio/low_min": 0.00010402576299384236,
      "clip_ratio/region_mean": 0.0019115097165922634,
      "epoch": 0.042093228100263086,
      "grad_norm": 0.11326860636472702,
      "learning_rate": 5e-07,
      "loss": 0.0232,
      "step": 451
    },
    {
      "clip_ratio/high_max": 0.002080239930364769,
      "clip_ratio/high_mean": 0.0008418603883910691,
      "clip_ratio/low_mean": 0.0008875123330653878,
      "clip_ratio/low_min": 6.0124221818114165e-05,
      "clip_ratio/region_mean": 0.0017293727505602874,
      "epoch": 0.042186561200263664,
      "grad_norm": 0.10995130985975266,
      "learning_rate": 5e-07,
      "loss": 0.0644,
      "step": 452
    },
    {
      "clip_ratio/high_max": 0.0021681228317902423,
      "clip_ratio/high_mean": 0.0009315474089817144,
      "clip_ratio/low_mean": 0.0009840093080129009,
      "clip_ratio/low_min": 9.05052629605052e-05,
      "clip_ratio/region_mean": 0.001915556742460467,
      "epoch": 0.04227989430026425,
      "grad_norm": 0.12418127059936523,
      "learning_rate": 5e-07,
      "loss": 0.0201,
      "step": 453
    },
    {
      "clip_ratio/high_max": 0.00198921265109675,
      "clip_ratio/high_mean": 0.0008262895535153802,
      "clip_ratio/low_mean": 0.0007786741607560543,
      "clip_ratio/low_min": 4.707652533397777e-05,
      "clip_ratio/region_mean": 0.0016049637633841485,
      "epoch": 0.042373227400264835,
      "grad_norm": 0.10789777338504791,
      "learning_rate": 5e-07,
      "loss": -0.0055,
      "step": 454
    },
    {
      "clip_ratio/high_max": 0.001826305473514367,
      "clip_ratio/high_mean": 0.0007311589597520651,
      "clip_ratio/low_mean": 0.0009058102477865759,
      "clip_ratio/low_min": 3.2599945370748173e-05,
      "clip_ratio/region_mean": 0.0016369692020816728,
      "epoch": 0.04246656050026541,
      "grad_norm": 0.10212162137031555,
      "learning_rate": 5e-07,
      "loss": 0.0676,
      "step": 455
    },
    {
      "clip_ratio/high_max": 0.0019260985136497766,
      "clip_ratio/high_mean": 0.0008918448620534036,
      "clip_ratio/low_mean": 0.000832009058285621,
      "clip_ratio/low_min": 1.4551804270013236e-05,
      "clip_ratio/region_mean": 0.0017238539076060988,
      "epoch": 0.042559893600266,
      "grad_norm": 0.11556679010391235,
      "learning_rate": 5e-07,
      "loss": 0.0012,
      "step": 456
    },
    {
      "clip_ratio/high_max": 0.0022433192643802613,
      "clip_ratio/high_mean": 0.000930594680539798,
      "clip_ratio/low_mean": 0.000893957734660944,
      "clip_ratio/low_min": 4.0115533920470625e-05,
      "clip_ratio/region_mean": 0.0018245524042868055,
      "epoch": 0.04265322670026658,
      "grad_norm": 0.10595796257257462,
      "learning_rate": 5e-07,
      "loss": -0.0127,
      "step": 457
    },
    {
      "clip_ratio/high_max": 0.0024353573462576605,
      "clip_ratio/high_mean": 0.001011054282571422,
      "clip_ratio/low_mean": 0.0008800894484011224,
      "clip_ratio/low_min": 2.4726400624786038e-05,
      "clip_ratio/region_mean": 0.0018911437364295125,
      "epoch": 0.04274655980026717,
      "grad_norm": 0.12182901054620743,
      "learning_rate": 5e-07,
      "loss": 0.0298,
      "step": 458
    },
    {
      "clip_ratio/high_max": 0.0027162055921508,
      "clip_ratio/high_mean": 0.0010272805411659647,
      "clip_ratio/low_mean": 0.0008078261216724059,
      "clip_ratio/low_min": 8.220078598242253e-05,
      "clip_ratio/region_mean": 0.0018351066610193811,
      "epoch": 0.04283989290026775,
      "grad_norm": 0.12108156830072403,
      "learning_rate": 5e-07,
      "loss": 0.0347,
      "step": 459
    },
    {
      "clip_ratio/high_max": 0.0021063556996523403,
      "clip_ratio/high_mean": 0.0008570628997404128,
      "clip_ratio/low_mean": 0.0009206336944771465,
      "clip_ratio/low_min": 2.3312197299674153e-05,
      "clip_ratio/region_mean": 0.0017776966487872414,
      "epoch": 0.04293322600026833,
      "grad_norm": 0.12553012371063232,
      "learning_rate": 5e-07,
      "loss": 0.039,
      "step": 460
    },
    {
      "clip_ratio/high_max": 0.0019366372871445492,
      "clip_ratio/high_mean": 0.0008478623603878077,
      "clip_ratio/low_mean": 0.0008193910416594008,
      "clip_ratio/low_min": 8.107249050226528e-05,
      "clip_ratio/region_mean": 0.0016672533747623675,
      "epoch": 0.04302655910026892,
      "grad_norm": 0.11980695277452469,
      "learning_rate": 5e-07,
      "loss": 0.0176,
      "step": 461
    },
    {
      "clip_ratio/high_max": 0.0020892696556984447,
      "clip_ratio/high_mean": 0.0008726003543415572,
      "clip_ratio/low_mean": 0.0008616796476417221,
      "clip_ratio/low_min": 0.00011407747297198512,
      "clip_ratio/region_mean": 0.0017342800128972158,
      "epoch": 0.0431198922002695,
      "grad_norm": 0.11440596729516983,
      "learning_rate": 5e-07,
      "loss": 0.0502,
      "step": 462
    },
    {
      "clip_ratio/high_max": 0.002231328733614646,
      "clip_ratio/high_mean": 0.0009099298804358114,
      "clip_ratio/low_mean": 0.0009080503332370427,
      "clip_ratio/low_min": 8.542488194507314e-05,
      "clip_ratio/region_mean": 0.0018179801627411507,
      "epoch": 0.04321322530027008,
      "grad_norm": 0.10699810087680817,
      "learning_rate": 5e-07,
      "loss": 0.0143,
      "step": 463
    },
    {
      "clip_ratio/high_max": 0.002193326159613207,
      "clip_ratio/high_mean": 0.0008639513689558953,
      "clip_ratio/low_mean": 0.0008262771953013726,
      "clip_ratio/low_min": 3.6185793760523666e-05,
      "clip_ratio/region_mean": 0.001690228542429395,
      "epoch": 0.043306558400270666,
      "grad_norm": 0.1134444922208786,
      "learning_rate": 5e-07,
      "loss": 0.0301,
      "step": 464
    },
    {
      "clip_ratio/high_max": 0.0022632937761954963,
      "clip_ratio/high_mean": 0.0009156821215583477,
      "clip_ratio/low_mean": 0.000893557949893875,
      "clip_ratio/low_min": 8.808520396996755e-05,
      "clip_ratio/region_mean": 0.00180924004962435,
      "epoch": 0.04339989150027125,
      "grad_norm": 0.13607700169086456,
      "learning_rate": 5e-07,
      "loss": 0.0294,
      "step": 465
    },
    {
      "clip_ratio/high_max": 0.0019825831732305232,
      "clip_ratio/high_mean": 0.0008191547531168908,
      "clip_ratio/low_mean": 0.0009157835011137649,
      "clip_ratio/low_min": 7.148576059989864e-06,
      "clip_ratio/region_mean": 0.0017349382615066133,
      "epoch": 0.04349322460027183,
      "grad_norm": 0.10535257309675217,
      "learning_rate": 5e-07,
      "loss": 0.0177,
      "step": 466
    },
    {
      "clip_ratio/high_max": 0.002606162386655342,
      "clip_ratio/high_mean": 0.001068051606125664,
      "clip_ratio/low_mean": 0.0008363358338101534,
      "clip_ratio/low_min": 4.528314821072854e-05,
      "clip_ratio/region_mean": 0.0019043874854105525,
      "epoch": 0.043586557700272414,
      "grad_norm": 0.11426884680986404,
      "learning_rate": 5e-07,
      "loss": 0.0028,
      "step": 467
    },
    {
      "clip_ratio/high_max": 0.0027257647961960174,
      "clip_ratio/high_mean": 0.0011297710316284792,
      "clip_ratio/low_mean": 0.0009231486947101075,
      "clip_ratio/low_min": 4.796588473254815e-05,
      "clip_ratio/region_mean": 0.0020529197572614066,
      "epoch": 0.043679890800273,
      "grad_norm": 0.11877179890871048,
      "learning_rate": 5e-07,
      "loss": 0.003,
      "step": 468
    },
    {
      "clip_ratio/high_max": 0.0022104679155745544,
      "clip_ratio/high_mean": 0.0009516164536762517,
      "clip_ratio/low_mean": 0.0008222773867601063,
      "clip_ratio/low_min": 7.803650396454032e-05,
      "clip_ratio/region_mean": 0.0017738938186084852,
      "epoch": 0.043773223900273585,
      "grad_norm": 0.10667946189641953,
      "learning_rate": 5e-07,
      "loss": -0.0203,
      "step": 469
    },
    {
      "clip_ratio/high_max": 0.0021145043574506417,
      "clip_ratio/high_mean": 0.0008976661265478469,
      "clip_ratio/low_mean": 0.0007837768625904573,
      "clip_ratio/low_min": 6.100410337239737e-05,
      "clip_ratio/region_mean": 0.0016814429982332513,
      "epoch": 0.04386655700027416,
      "grad_norm": 0.1182934045791626,
      "learning_rate": 5e-07,
      "loss": -0.0073,
      "step": 470
    },
    {
      "clip_ratio/high_max": 0.0022223100568226073,
      "clip_ratio/high_mean": 0.000987003768386785,
      "clip_ratio/low_mean": 0.0011211947530682664,
      "clip_ratio/low_min": 0.00015123085358936805,
      "clip_ratio/region_mean": 0.0021081985760247335,
      "epoch": 0.04395989010027475,
      "grad_norm": 0.11804036051034927,
      "learning_rate": 5e-07,
      "loss": 0.0692,
      "step": 471
    },
    {
      "clip_ratio/high_max": 0.002292766257596668,
      "clip_ratio/high_mean": 0.001045352990331594,
      "clip_ratio/low_mean": 0.0008357603219337761,
      "clip_ratio/low_min": 0.000166949411323003,
      "clip_ratio/region_mean": 0.0018811133486451581,
      "epoch": 0.044053223200275334,
      "grad_norm": 0.11854824423789978,
      "learning_rate": 5e-07,
      "loss": -0.0052,
      "step": 472
    },
    {
      "clip_ratio/high_max": 0.002140181459253654,
      "clip_ratio/high_mean": 0.0009262999010388739,
      "clip_ratio/low_mean": 0.0009801294345379574,
      "clip_ratio/low_min": 6.458368170569884e-05,
      "clip_ratio/region_mean": 0.0019064292791881599,
      "epoch": 0.04414655630027592,
      "grad_norm": 0.11638826131820679,
      "learning_rate": 5e-07,
      "loss": -0.0118,
      "step": 473
    },
    {
      "clip_ratio/high_max": 0.0024058872731984593,
      "clip_ratio/high_mean": 0.000985795970336767,
      "clip_ratio/low_mean": 0.0008997267323138658,
      "clip_ratio/low_min": 0.00010875234693230595,
      "clip_ratio/region_mean": 0.0018855227026506327,
      "epoch": 0.0442398894002765,
      "grad_norm": 0.11467273533344269,
      "learning_rate": 5e-07,
      "loss": 0.0074,
      "step": 474
    },
    {
      "clip_ratio/high_max": 0.001777170011337148,
      "clip_ratio/high_mean": 0.0008414720159635181,
      "clip_ratio/low_mean": 0.0009381298077641986,
      "clip_ratio/low_min": 1.4165911125019193e-05,
      "clip_ratio/region_mean": 0.0017796018764784094,
      "epoch": 0.04433322250027708,
      "grad_norm": 0.1078026220202446,
      "learning_rate": 5e-07,
      "loss": -0.001,
      "step": 475
    },
    {
      "clip_ratio/high_max": 0.0021062865271233022,
      "clip_ratio/high_mean": 0.0009143500465143006,
      "clip_ratio/low_mean": 0.001029440147249261,
      "clip_ratio/low_min": 9.087482430913951e-05,
      "clip_ratio/region_mean": 0.0019437901719356887,
      "epoch": 0.04442655560027767,
      "grad_norm": 0.1077638491988182,
      "learning_rate": 5e-07,
      "loss": 0.0266,
      "step": 476
    },
    {
      "clip_ratio/high_max": 0.002124697988620028,
      "clip_ratio/high_mean": 0.0009359465493616881,
      "clip_ratio/low_mean": 0.0009462737380090402,
      "clip_ratio/low_min": 4.620655636244919e-05,
      "clip_ratio/region_mean": 0.0018822202473529615,
      "epoch": 0.04451988870027825,
      "grad_norm": 0.1239190474152565,
      "learning_rate": 5e-07,
      "loss": 0.0449,
      "step": 477
    },
    {
      "clip_ratio/high_max": 0.0019878839011653326,
      "clip_ratio/high_mean": 0.0008287005784950452,
      "clip_ratio/low_mean": 0.0009620840064599179,
      "clip_ratio/low_min": 9.21737600947381e-05,
      "clip_ratio/region_mean": 0.001790784634067677,
      "epoch": 0.04461322180027883,
      "grad_norm": 0.11266104876995087,
      "learning_rate": 5e-07,
      "loss": 0.0167,
      "step": 478
    },
    {
      "clip_ratio/high_max": 0.0021123847109265625,
      "clip_ratio/high_mean": 0.0009286763724958291,
      "clip_ratio/low_mean": 0.0009750583340064622,
      "clip_ratio/low_min": 7.756712966511259e-05,
      "clip_ratio/region_mean": 0.0019037347010453232,
      "epoch": 0.044706554900279416,
      "grad_norm": 0.12313251942396164,
      "learning_rate": 5e-07,
      "loss": 0.0407,
      "step": 479
    },
    {
      "clip_ratio/high_max": 0.0019611300085671246,
      "clip_ratio/high_mean": 0.0007907188301032875,
      "clip_ratio/low_mean": 0.0009170462308247807,
      "clip_ratio/low_min": 4.253639781381935e-05,
      "clip_ratio/region_mean": 0.0017077650591090787,
      "epoch": 0.04479988800028,
      "grad_norm": 0.11548833549022675,
      "learning_rate": 5e-07,
      "loss": 0.0457,
      "step": 480
    },
    {
      "clip_ratio/high_max": 0.0020207368143019266,
      "clip_ratio/high_mean": 0.0008546677563572302,
      "clip_ratio/low_mean": 0.0010229794279439375,
      "clip_ratio/low_min": 0.0001404892182108597,
      "clip_ratio/region_mean": 0.0018776471843011677,
      "epoch": 0.04489322110028058,
      "grad_norm": 0.10736943036317825,
      "learning_rate": 5e-07,
      "loss": 0.0553,
      "step": 481
    },
    {
      "clip_ratio/high_max": 0.0019502437862684019,
      "clip_ratio/high_mean": 0.000895650198799558,
      "clip_ratio/low_mean": 0.0009802618369576521,
      "clip_ratio/low_min": 2.2882842131366488e-05,
      "clip_ratio/region_mean": 0.0018759120139293373,
      "epoch": 0.044986554200281165,
      "grad_norm": 0.11407902091741562,
      "learning_rate": 5e-07,
      "loss": 0.0568,
      "step": 482
    },
    {
      "clip_ratio/high_max": 0.0020678585933637805,
      "clip_ratio/high_mean": 0.0008523006617906503,
      "clip_ratio/low_mean": 0.0009639709714974742,
      "clip_ratio/low_min": 7.910223393992055e-05,
      "clip_ratio/region_mean": 0.0018162716369261034,
      "epoch": 0.04507988730028175,
      "grad_norm": 0.11494950205087662,
      "learning_rate": 5e-07,
      "loss": 0.0362,
      "step": 483
    },
    {
      "clip_ratio/high_max": 0.0018643809817149304,
      "clip_ratio/high_mean": 0.0007955910205055261,
      "clip_ratio/low_mean": 0.000993269288301235,
      "clip_ratio/low_min": 8.655520105094183e-05,
      "clip_ratio/region_mean": 0.0017888602887978777,
      "epoch": 0.045173220400282335,
      "grad_norm": 0.11593075096607208,
      "learning_rate": 5e-07,
      "loss": 0.0414,
      "step": 484
    },
    {
      "clip_ratio/high_max": 0.002141255979950074,
      "clip_ratio/high_mean": 0.0009339034186268691,
      "clip_ratio/low_mean": 0.0008925048241508193,
      "clip_ratio/low_min": 8.655618876218796e-05,
      "clip_ratio/region_mean": 0.0018264082609675825,
      "epoch": 0.04526655350028291,
      "grad_norm": 0.12114113569259644,
      "learning_rate": 5e-07,
      "loss": 0.0455,
      "step": 485
    },
    {
      "clip_ratio/high_max": 0.0020974547587684356,
      "clip_ratio/high_mean": 0.0008674834716657642,
      "clip_ratio/low_mean": 0.0010036118837888353,
      "clip_ratio/low_min": 2.412894264125498e-05,
      "clip_ratio/region_mean": 0.001871095344540663,
      "epoch": 0.0453598866002835,
      "grad_norm": 0.11119820922613144,
      "learning_rate": 5e-07,
      "loss": 0.0013,
      "step": 486
    },
    {
      "clip_ratio/high_max": 0.0023170082131400704,
      "clip_ratio/high_mean": 0.0009581113117747009,
      "clip_ratio/low_mean": 0.0009556081859045662,
      "clip_ratio/low_min": 5.465282447403297e-05,
      "clip_ratio/region_mean": 0.00191371951950714,
      "epoch": 0.045453219700284084,
      "grad_norm": 0.123423270881176,
      "learning_rate": 5e-07,
      "loss": 0.0367,
      "step": 487
    },
    {
      "clip_ratio/high_max": 0.002126373387000058,
      "clip_ratio/high_mean": 0.0009175515078823082,
      "clip_ratio/low_mean": 0.0008660982439323561,
      "clip_ratio/low_min": 2.198160200350685e-05,
      "clip_ratio/region_mean": 0.0017836498009273782,
      "epoch": 0.04554655280028467,
      "grad_norm": 0.11318027228116989,
      "learning_rate": 5e-07,
      "loss": -0.0031,
      "step": 488
    },
    {
      "clip_ratio/high_max": 0.002078807076031808,
      "clip_ratio/high_mean": 0.0008427471111644991,
      "clip_ratio/low_mean": 0.0009296996468037833,
      "clip_ratio/low_min": 0.0001565325746923918,
      "clip_ratio/region_mean": 0.0017724467033986002,
      "epoch": 0.04563988590028525,
      "grad_norm": 0.11087574809789658,
      "learning_rate": 5e-07,
      "loss": 0.0258,
      "step": 489
    },
    {
      "clip_ratio/high_max": 0.002479721159033943,
      "clip_ratio/high_mean": 0.000959734657953959,
      "clip_ratio/low_mean": 0.000998099005300901,
      "clip_ratio/low_min": 0.0001502370641901507,
      "clip_ratio/region_mean": 0.0019578336214181036,
      "epoch": 0.04573321900028583,
      "grad_norm": 0.11906377971172333,
      "learning_rate": 5e-07,
      "loss": 0.0465,
      "step": 490
    },
    {
      "clip_ratio/high_max": 0.0019645970642159227,
      "clip_ratio/high_mean": 0.0009097501351789106,
      "clip_ratio/low_mean": 0.0008508740484103328,
      "clip_ratio/low_min": 6.406642114598071e-05,
      "clip_ratio/region_mean": 0.001760624181770254,
      "epoch": 0.04582655210028642,
      "grad_norm": 0.1273634284734726,
      "learning_rate": 5e-07,
      "loss": 0.0392,
      "step": 491
    },
    {
      "clip_ratio/high_max": 0.0021966428103041835,
      "clip_ratio/high_mean": 0.0008895007595128845,
      "clip_ratio/low_mean": 0.0009551702241878957,
      "clip_ratio/low_min": 0.00011663724944810383,
      "clip_ratio/region_mean": 0.0018446709436830133,
      "epoch": 0.045919885200286996,
      "grad_norm": 0.09927107393741608,
      "learning_rate": 5e-07,
      "loss": 0.0444,
      "step": 492
    },
    {
      "clip_ratio/high_max": 0.0023187556071206927,
      "clip_ratio/high_mean": 0.0009997814668167848,
      "clip_ratio/low_mean": 0.001076108430424938,
      "clip_ratio/low_min": 6.59057914162986e-05,
      "clip_ratio/region_mean": 0.0020758899045176804,
      "epoch": 0.04601321830028758,
      "grad_norm": 0.12761326134204865,
      "learning_rate": 5e-07,
      "loss": 0.0029,
      "step": 493
    },
    {
      "clip_ratio/high_max": 0.002069725906039821,
      "clip_ratio/high_mean": 0.0009125787801167462,
      "clip_ratio/low_mean": 0.0009461219378863461,
      "clip_ratio/low_min": 0.00011016127700713696,
      "clip_ratio/region_mean": 0.0018587007361929864,
      "epoch": 0.046106551400288166,
      "grad_norm": 0.11801777780056,
      "learning_rate": 5e-07,
      "loss": 0.0296,
      "step": 494
    },
    {
      "clip_ratio/high_max": 0.0019234649880672805,
      "clip_ratio/high_mean": 0.0009073876608454157,
      "clip_ratio/low_mean": 0.0009662658758315956,
      "clip_ratio/low_min": 5.834077273902949e-05,
      "clip_ratio/region_mean": 0.001873653513030149,
      "epoch": 0.04619988450028875,
      "grad_norm": 0.10948099195957184,
      "learning_rate": 5e-07,
      "loss": 0.0383,
      "step": 495
    },
    {
      "clip_ratio/high_max": 0.0020520184552879073,
      "clip_ratio/high_mean": 0.0008053516758081969,
      "clip_ratio/low_mean": 0.0009535022818454308,
      "clip_ratio/low_min": 8.813113254291238e-05,
      "clip_ratio/region_mean": 0.0017588539485586807,
      "epoch": 0.04629321760028933,
      "grad_norm": 0.11562888324260712,
      "learning_rate": 5e-07,
      "loss": 0.0217,
      "step": 496
    },
    {
      "clip_ratio/high_max": 0.0021263960225041956,
      "clip_ratio/high_mean": 0.0009206252798321657,
      "clip_ratio/low_mean": 0.000846787508635316,
      "clip_ratio/low_min": 1.147842067439342e-05,
      "clip_ratio/region_mean": 0.0017674127302598208,
      "epoch": 0.046386550700289915,
      "grad_norm": 0.11205700039863586,
      "learning_rate": 5e-07,
      "loss": 0.0199,
      "step": 497
    },
    {
      "clip_ratio/high_max": 0.002430865013593575,
      "clip_ratio/high_mean": 0.0008846193491081067,
      "clip_ratio/low_mean": 0.0008367168265976943,
      "clip_ratio/low_min": 9.30714959395118e-05,
      "clip_ratio/region_mean": 0.00172133618616499,
      "epoch": 0.0464798838002905,
      "grad_norm": 0.11209391057491302,
      "learning_rate": 5e-07,
      "loss": 0.0161,
      "step": 498
    },
    {
      "clip_ratio/high_max": 0.00226767327694688,
      "clip_ratio/high_mean": 0.0009668835627962835,
      "clip_ratio/low_mean": 0.0010079578441946069,
      "clip_ratio/low_min": 4.576064975481131e-05,
      "clip_ratio/region_mean": 0.0019748413906199858,
      "epoch": 0.046573216900291085,
      "grad_norm": 0.11690337210893631,
      "learning_rate": 5e-07,
      "loss": 0.0459,
      "step": 499
    },
    {
      "clip_ratio/high_max": 0.0023017609310045373,
      "clip_ratio/high_mean": 0.0008717737418919569,
      "clip_ratio/low_mean": 0.0010988950452883728,
      "clip_ratio/low_min": 0.00013159075751900673,
      "clip_ratio/region_mean": 0.0019706687817233615,
      "epoch": 0.046666550000291664,
      "grad_norm": 0.11416295915842056,
      "learning_rate": 5e-07,
      "loss": 0.0378,
      "step": 500
    },
    {
      "clip_ratio/high_max": 0.0019790510341408662,
      "clip_ratio/high_mean": 0.0008905685845093103,
      "clip_ratio/low_mean": 0.0008851560469338438,
      "clip_ratio/low_min": 8.676983270561323e-05,
      "clip_ratio/region_mean": 0.0017757245805114508,
      "epoch": 0.04675988310029225,
      "grad_norm": 0.11141923069953918,
      "learning_rate": 5e-07,
      "loss": -0.0059,
      "step": 501
    },
    {
      "clip_ratio/high_max": 0.002126137478626333,
      "clip_ratio/high_mean": 0.0008617740313638933,
      "clip_ratio/low_mean": 0.0009730860765557736,
      "clip_ratio/low_min": 9.812792723096209e-05,
      "clip_ratio/region_mean": 0.001834860126109561,
      "epoch": 0.046853216200292834,
      "grad_norm": 0.1151275709271431,
      "learning_rate": 5e-07,
      "loss": 0.044,
      "step": 502
    },
    {
      "clip_ratio/high_max": 0.0023942814659676515,
      "clip_ratio/high_mean": 0.0010477399118826725,
      "clip_ratio/low_mean": 0.0008796715537755517,
      "clip_ratio/low_min": 0.00014405293950403575,
      "clip_ratio/region_mean": 0.0019274114674772136,
      "epoch": 0.04694654930029342,
      "grad_norm": 0.1132965013384819,
      "learning_rate": 5e-07,
      "loss": -0.0149,
      "step": 503
    },
    {
      "clip_ratio/high_max": 0.0020002909295726568,
      "clip_ratio/high_mean": 0.000821992947749095,
      "clip_ratio/low_mean": 0.00110313729965128,
      "clip_ratio/low_min": 0.00015981075830495683,
      "clip_ratio/region_mean": 0.0019251302510383539,
      "epoch": 0.047039882400294,
      "grad_norm": 0.11104988306760788,
      "learning_rate": 5e-07,
      "loss": 0.052,
      "step": 504
    },
    {
      "clip_ratio/high_max": 0.0017848838288045954,
      "clip_ratio/high_mean": 0.0008408388639509212,
      "clip_ratio/low_mean": 0.0008653898748889333,
      "clip_ratio/low_min": 8.725397037778748e-05,
      "clip_ratio/region_mean": 0.0017062287297449075,
      "epoch": 0.04713321550029458,
      "grad_norm": 0.12759539484977722,
      "learning_rate": 5e-07,
      "loss": -0.0308,
      "step": 505
    },
    {
      "clip_ratio/high_max": 0.0022829724475741386,
      "clip_ratio/high_mean": 0.0009160405061265919,
      "clip_ratio/low_mean": 0.0009685246277513215,
      "clip_ratio/low_min": 0.0001467056335968664,
      "clip_ratio/region_mean": 0.00188456511386903,
      "epoch": 0.04722654860029517,
      "grad_norm": 0.1112985759973526,
      "learning_rate": 5e-07,
      "loss": 0.0263,
      "step": 506
    },
    {
      "clip_ratio/high_max": 0.00180510164500447,
      "clip_ratio/high_mean": 0.0007883957314334111,
      "clip_ratio/low_mean": 0.0010128233225259464,
      "clip_ratio/low_min": 0.00012948776111443294,
      "clip_ratio/region_mean": 0.0018012190485023893,
      "epoch": 0.047319881700295746,
      "grad_norm": 0.10268452018499374,
      "learning_rate": 5e-07,
      "loss": 0.0436,
      "step": 507
    },
    {
      "clip_ratio/high_max": 0.0017749436374288052,
      "clip_ratio/high_mean": 0.0007973989404490567,
      "clip_ratio/low_mean": 0.0009436101172468625,
      "clip_ratio/low_min": 2.8630032829823904e-05,
      "clip_ratio/region_mean": 0.0017410090295015834,
      "epoch": 0.04741321480029633,
      "grad_norm": 0.11475313454866409,
      "learning_rate": 5e-07,
      "loss": 0.0719,
      "step": 508
    },
    {
      "clip_ratio/high_max": 0.0023542568742414005,
      "clip_ratio/high_mean": 0.0009704607909952756,
      "clip_ratio/low_mean": 0.0010438393364893273,
      "clip_ratio/low_min": 0.00013364584356168052,
      "clip_ratio/region_mean": 0.0020143001675023697,
      "epoch": 0.04750654790029692,
      "grad_norm": 0.11330278217792511,
      "learning_rate": 5e-07,
      "loss": 0.0357,
      "step": 509
    },
    {
      "clip_ratio/high_max": 0.002340108316275291,
      "clip_ratio/high_mean": 0.0010321189838577993,
      "clip_ratio/low_mean": 0.0010929636446235236,
      "clip_ratio/low_min": 6.757970913895406e-05,
      "clip_ratio/region_mean": 0.0021250825593597256,
      "epoch": 0.0475998810002975,
      "grad_norm": 0.12334062159061432,
      "learning_rate": 5e-07,
      "loss": 0.0243,
      "step": 510
    },
    {
      "clip_ratio/high_max": 0.0021126231185917277,
      "clip_ratio/high_mean": 0.0008598688054917147,
      "clip_ratio/low_mean": 0.001040679035213543,
      "clip_ratio/low_min": 4.6464177103189286e-05,
      "clip_ratio/region_mean": 0.0019005478970939294,
      "epoch": 0.04769321410029808,
      "grad_norm": 0.10956922173500061,
      "learning_rate": 5e-07,
      "loss": 0.044,
      "step": 511
    },
    {
      "clip_ratio/high_max": 0.0020455195044633,
      "clip_ratio/high_mean": 0.00081049612708739,
      "clip_ratio/low_mean": 0.000904518290553824,
      "clip_ratio/low_min": 0.00012128788694099057,
      "clip_ratio/region_mean": 0.0017150144049082883,
      "epoch": 0.047786547200298665,
      "grad_norm": 0.11323803663253784,
      "learning_rate": 5e-07,
      "loss": 0.0537,
      "step": 512
    },
    {
      "clip_ratio/high_max": 0.002228035435109632,
      "clip_ratio/high_mean": 0.0009037863728735829,
      "clip_ratio/low_mean": 0.0009085816218430409,
      "clip_ratio/low_min": 3.415300670894794e-05,
      "clip_ratio/region_mean": 0.0018123679692507721,
      "epoch": 0.04787988030029925,
      "grad_norm": 0.10390179604291916,
      "learning_rate": 5e-07,
      "loss": 0.0225,
      "step": 513
    },
    {
      "clip_ratio/high_max": 0.0017777083012333605,
      "clip_ratio/high_mean": 0.0008163872080331203,
      "clip_ratio/low_mean": 0.0009444993738725316,
      "clip_ratio/low_min": 3.809795271081384e-05,
      "clip_ratio/region_mean": 0.0017608865309739485,
      "epoch": 0.047973213400299836,
      "grad_norm": 0.0988558977842331,
      "learning_rate": 5e-07,
      "loss": 0.0197,
      "step": 514
    },
    {
      "clip_ratio/high_max": 0.002123645412211772,
      "clip_ratio/high_mean": 0.0008699490444996627,
      "clip_ratio/low_mean": 0.0009470521072216798,
      "clip_ratio/low_min": 6.18611211393727e-05,
      "clip_ratio/region_mean": 0.0018170011753682047,
      "epoch": 0.048066546500300414,
      "grad_norm": 0.11058492958545685,
      "learning_rate": 5e-07,
      "loss": 0.0168,
      "step": 515
    },
    {
      "clip_ratio/high_max": 0.0023656533849134576,
      "clip_ratio/high_mean": 0.0008489119882142404,
      "clip_ratio/low_mean": 0.0009527358997729607,
      "clip_ratio/low_min": 6.385106735251611e-05,
      "clip_ratio/region_mean": 0.0018016478570643812,
      "epoch": 0.048159879600301,
      "grad_norm": 0.11020000278949738,
      "learning_rate": 5e-07,
      "loss": 0.0379,
      "step": 516
    },
    {
      "clip_ratio/high_max": 0.0024038971823756583,
      "clip_ratio/high_mean": 0.0009540662613289896,
      "clip_ratio/low_mean": 0.0009496363018115517,
      "clip_ratio/low_min": 9.708257312013302e-05,
      "clip_ratio/region_mean": 0.0019037025995203294,
      "epoch": 0.048253212700301584,
      "grad_norm": 0.11536318808794022,
      "learning_rate": 5e-07,
      "loss": -0.0134,
      "step": 517
    },
    {
      "clip_ratio/high_max": 0.0021709975917474367,
      "clip_ratio/high_mean": 0.000869378651259467,
      "clip_ratio/low_mean": 0.0009854507698037196,
      "clip_ratio/low_min": 0.0001538430751679698,
      "clip_ratio/region_mean": 0.0018548294174252078,
      "epoch": 0.04834654580030216,
      "grad_norm": 0.1128697544336319,
      "learning_rate": 5e-07,
      "loss": 0.0471,
      "step": 518
    },
    {
      "clip_ratio/high_max": 0.0024086685516522266,
      "clip_ratio/high_mean": 0.0009743757727846969,
      "clip_ratio/low_mean": 0.0009614452956157038,
      "clip_ratio/low_min": 1.5344954590545967e-05,
      "clip_ratio/region_mean": 0.00193582107021939,
      "epoch": 0.04843987890030275,
      "grad_norm": 0.11552970856428146,
      "learning_rate": 5e-07,
      "loss": -0.0142,
      "step": 519
    },
    {
      "clip_ratio/high_max": 0.002054087060969323,
      "clip_ratio/high_mean": 0.0008883767695806455,
      "clip_ratio/low_mean": 0.0008271069173133583,
      "clip_ratio/low_min": 8.564886229578406e-05,
      "clip_ratio/region_mean": 0.0017154836968984455,
      "epoch": 0.04853321200030333,
      "grad_norm": 0.11312950402498245,
      "learning_rate": 5e-07,
      "loss": -0.0147,
      "step": 520
    },
    {
      "clip_ratio/high_max": 0.002396311712800525,
      "clip_ratio/high_mean": 0.0010011802005465142,
      "clip_ratio/low_mean": 0.001071263621270191,
      "clip_ratio/low_min": 0.00022165243353811093,
      "clip_ratio/region_mean": 0.00207244380726479,
      "epoch": 0.04862654510030392,
      "grad_norm": 0.12636953592300415,
      "learning_rate": 5e-07,
      "loss": 0.0319,
      "step": 521
    },
    {
      "clip_ratio/high_max": 0.001897212856420083,
      "clip_ratio/high_mean": 0.0007370562652795343,
      "clip_ratio/low_mean": 0.0010277227283950197,
      "clip_ratio/low_min": 0.00019493453601171495,
      "clip_ratio/region_mean": 0.001764778993674554,
      "epoch": 0.048719878200304496,
      "grad_norm": 0.12445522099733353,
      "learning_rate": 5e-07,
      "loss": 0.0312,
      "step": 522
    },
    {
      "clip_ratio/high_max": 0.0020331455780251417,
      "clip_ratio/high_mean": 0.0008640874439151958,
      "clip_ratio/low_mean": 0.0008795210396783659,
      "clip_ratio/low_min": 0.00010598660264804494,
      "clip_ratio/region_mean": 0.0017436084817745723,
      "epoch": 0.04881321130030508,
      "grad_norm": 0.11900756508111954,
      "learning_rate": 5e-07,
      "loss": -0.0057,
      "step": 523
    },
    {
      "clip_ratio/high_max": 0.002093577011692105,
      "clip_ratio/high_mean": 0.0009380414812767413,
      "clip_ratio/low_mean": 0.0009839766662480542,
      "clip_ratio/low_min": 0.00011913954904230195,
      "clip_ratio/region_mean": 0.0019220181711716577,
      "epoch": 0.04890654440030567,
      "grad_norm": 0.110393226146698,
      "learning_rate": 5e-07,
      "loss": 0.0282,
      "step": 524
    },
    {
      "clip_ratio/high_max": 0.002331307863641996,
      "clip_ratio/high_mean": 0.00102669913576392,
      "clip_ratio/low_mean": 0.0009195824623020599,
      "clip_ratio/low_min": 0.00016243644040514482,
      "clip_ratio/region_mean": 0.0019462815980659798,
      "epoch": 0.04899987750030625,
      "grad_norm": 0.12882284820079803,
      "learning_rate": 5e-07,
      "loss": 0.0384,
      "step": 525
    },
    {
      "clip_ratio/high_max": 0.0023782449425198138,
      "clip_ratio/high_mean": 0.0010685340712370817,
      "clip_ratio/low_mean": 0.0007955169639899395,
      "clip_ratio/low_min": 1.546264138596598e-05,
      "clip_ratio/region_mean": 0.001864051038865,
      "epoch": 0.04909321060030683,
      "grad_norm": 0.10672211647033691,
      "learning_rate": 5e-07,
      "loss": -0.0245,
      "step": 526
    },
    {
      "clip_ratio/high_max": 0.0020233433424436953,
      "clip_ratio/high_mean": 0.0009254395481548272,
      "clip_ratio/low_mean": 0.0010022208152804524,
      "clip_ratio/low_min": 0.00010435517924634041,
      "clip_ratio/region_mean": 0.0019276603634352796,
      "epoch": 0.049186543700307415,
      "grad_norm": 0.11081106960773468,
      "learning_rate": 5e-07,
      "loss": 0.0586,
      "step": 527
    },
    {
      "clip_ratio/high_max": 0.001822794736654032,
      "clip_ratio/high_mean": 0.0008828269146761158,
      "clip_ratio/low_mean": 0.0009044408598128939,
      "clip_ratio/low_min": 7.754351463518105e-05,
      "clip_ratio/region_mean": 0.0017872677781269886,
      "epoch": 0.049279876800308,
      "grad_norm": 0.1195283830165863,
      "learning_rate": 5e-07,
      "loss": 0.0332,
      "step": 528
    },
    {
      "clip_ratio/high_max": 0.0019275409576948732,
      "clip_ratio/high_mean": 0.0008779368072282523,
      "clip_ratio/low_mean": 0.0009685635777714197,
      "clip_ratio/low_min": 4.618935054168105e-05,
      "clip_ratio/region_mean": 0.0018465004322933964,
      "epoch": 0.049373209900308586,
      "grad_norm": 0.1046498715877533,
      "learning_rate": 5e-07,
      "loss": 0.0176,
      "step": 529
    },
    {
      "clip_ratio/high_max": 0.0021973201510263607,
      "clip_ratio/high_mean": 0.0009302404851041501,
      "clip_ratio/low_mean": 0.0009802406657399843,
      "clip_ratio/low_min": 9.776486785995075e-05,
      "clip_ratio/region_mean": 0.0019104811290162615,
      "epoch": 0.049466543000309164,
      "grad_norm": 0.12384083122015,
      "learning_rate": 5e-07,
      "loss": -0.0023,
      "step": 530
    },
    {
      "clip_ratio/high_max": 0.0022872380577609874,
      "clip_ratio/high_mean": 0.0010127697878488107,
      "clip_ratio/low_mean": 0.0009077761660591932,
      "clip_ratio/low_min": 0.00015421707939822227,
      "clip_ratio/region_mean": 0.0019205459757358767,
      "epoch": 0.04955987610030975,
      "grad_norm": 0.1174539253115654,
      "learning_rate": 5e-07,
      "loss": 0.0269,
      "step": 531
    },
    {
      "clip_ratio/high_max": 0.0020559377953759395,
      "clip_ratio/high_mean": 0.0009022772610478569,
      "clip_ratio/low_mean": 0.0010256957511955989,
      "clip_ratio/low_min": 0.00015121606702450663,
      "clip_ratio/region_mean": 0.001927973011333961,
      "epoch": 0.049653209200310335,
      "grad_norm": 0.11092931032180786,
      "learning_rate": 5e-07,
      "loss": 0.0406,
      "step": 532
    },
    {
      "clip_ratio/high_max": 0.00203214025896159,
      "clip_ratio/high_mean": 0.0008728824159334181,
      "clip_ratio/low_mean": 0.0009608725540601881,
      "clip_ratio/low_min": 0.00016481510101584718,
      "clip_ratio/region_mean": 0.001833754973631585,
      "epoch": 0.04974654230031091,
      "grad_norm": 0.11688506603240967,
      "learning_rate": 5e-07,
      "loss": 0.0597,
      "step": 533
    },
    {
      "clip_ratio/high_max": 0.0023616965481778607,
      "clip_ratio/high_mean": 0.0008792173575784545,
      "clip_ratio/low_mean": 0.0008466763283649925,
      "clip_ratio/low_min": 1.6314277672790922e-05,
      "clip_ratio/region_mean": 0.0017258936823054682,
      "epoch": 0.0498398754003115,
      "grad_norm": 0.11599437147378922,
      "learning_rate": 5e-07,
      "loss": 0.026,
      "step": 534
    },
    {
      "clip_ratio/high_max": 0.0023471038148272783,
      "clip_ratio/high_mean": 0.0009704687090561492,
      "clip_ratio/low_mean": 0.0009543458909320179,
      "clip_ratio/low_min": 7.924242527224123e-05,
      "clip_ratio/region_mean": 0.0019248146272730082,
      "epoch": 0.04993320850031208,
      "grad_norm": 0.11778368800878525,
      "learning_rate": 5e-07,
      "loss": -0.0111,
      "step": 535
    },
    {
      "clip_ratio/high_max": 0.0025303057773271576,
      "clip_ratio/high_mean": 0.0010710471469792537,
      "clip_ratio/low_mean": 0.0008746485218580347,
      "clip_ratio/low_min": 6.870462129882071e-05,
      "clip_ratio/region_mean": 0.0019456956506473944,
      "epoch": 0.05002654160031267,
      "grad_norm": 0.11799413710832596,
      "learning_rate": 5e-07,
      "loss": -0.0222,
      "step": 536
    },
    {
      "clip_ratio/high_max": 0.0019825556555588264,
      "clip_ratio/high_mean": 0.000909327571207541,
      "clip_ratio/low_mean": 0.0008982747258414747,
      "clip_ratio/low_min": 6.075392866478069e-05,
      "clip_ratio/region_mean": 0.0018076022679451853,
      "epoch": 0.05011987470031325,
      "grad_norm": 0.10923948884010315,
      "learning_rate": 5e-07,
      "loss": 0.0395,
      "step": 537
    },
    {
      "clip_ratio/high_max": 0.0022934608787181787,
      "clip_ratio/high_mean": 0.0008394557480642106,
      "clip_ratio/low_mean": 0.0009006887012219522,
      "clip_ratio/low_min": 1.4692054719489533e-05,
      "clip_ratio/region_mean": 0.0017401444420102052,
      "epoch": 0.05021320780031383,
      "grad_norm": 0.11502230912446976,
      "learning_rate": 5e-07,
      "loss": 0.0289,
      "step": 538
    },
    {
      "clip_ratio/high_max": 0.0022306800819933414,
      "clip_ratio/high_mean": 0.001015558873405098,
      "clip_ratio/low_mean": 0.0010291401158610824,
      "clip_ratio/low_min": 0.00015228909978759475,
      "clip_ratio/region_mean": 0.002044698987447191,
      "epoch": 0.05030654090031442,
      "grad_norm": 0.11833734065294266,
      "learning_rate": 5e-07,
      "loss": 0.0318,
      "step": 539
    },
    {
      "clip_ratio/high_max": 0.002082509388856124,
      "clip_ratio/high_mean": 0.0007884213428042131,
      "clip_ratio/low_mean": 0.0010032003083324526,
      "clip_ratio/low_min": 0.00011074588292103726,
      "clip_ratio/region_mean": 0.0017916216602316126,
      "epoch": 0.050399874000315,
      "grad_norm": 0.11434981226921082,
      "learning_rate": 5e-07,
      "loss": 0.0955,
      "step": 540
    },
    {
      "clip_ratio/high_max": 0.002413146612525452,
      "clip_ratio/high_mean": 0.0009326194376626518,
      "clip_ratio/low_mean": 0.0009886967527563684,
      "clip_ratio/low_min": 5.7626256875664694e-05,
      "clip_ratio/region_mean": 0.0019213161795050837,
      "epoch": 0.05049320710031558,
      "grad_norm": 0.11687153577804565,
      "learning_rate": 5e-07,
      "loss": -0.0049,
      "step": 541
    },
    {
      "clip_ratio/high_max": 0.0023224198739626445,
      "clip_ratio/high_mean": 0.0009179516891890671,
      "clip_ratio/low_mean": 0.0010524031058594119,
      "clip_ratio/low_min": 0.00010939366711681942,
      "clip_ratio/region_mean": 0.001970354795048479,
      "epoch": 0.050586540200316166,
      "grad_norm": 0.12259002774953842,
      "learning_rate": 5e-07,
      "loss": 0.0367,
      "step": 542
    },
    {
      "clip_ratio/high_max": 0.0023922072869027033,
      "clip_ratio/high_mean": 0.0008935290534282103,
      "clip_ratio/low_mean": 0.0008983142543002032,
      "clip_ratio/low_min": 9.100792613025988e-05,
      "clip_ratio/region_mean": 0.0017918433077284135,
      "epoch": 0.05067987330031675,
      "grad_norm": 0.11687108874320984,
      "learning_rate": 5e-07,
      "loss": -0.0275,
      "step": 543
    },
    {
      "clip_ratio/high_max": 0.0019363197716302238,
      "clip_ratio/high_mean": 0.0008212973843910731,
      "clip_ratio/low_mean": 0.0009815996345423628,
      "clip_ratio/low_min": 8.156791409419384e-05,
      "clip_ratio/region_mean": 0.0018028969861916266,
      "epoch": 0.05077320640031733,
      "grad_norm": 0.11760488897562027,
      "learning_rate": 5e-07,
      "loss": 0.0206,
      "step": 544
    },
    {
      "clip_ratio/high_max": 0.0024261136713903397,
      "clip_ratio/high_mean": 0.0009331497640232556,
      "clip_ratio/low_mean": 0.0009342582980025327,
      "clip_ratio/low_min": 7.830747836123919e-05,
      "clip_ratio/region_mean": 0.0018674080820346717,
      "completions/clipped_ratio": 0.015485491071428603,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4082.0,
      "completions/mean_length": 616.828857421875,
      "completions/mean_terminated_length": 562.104736328125,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.050866539500317914,
      "grad_norm": 0.10876116901636124,
      "learning_rate": 5e-07,
      "loss": 0.0009,
      "num_tokens": 489730388.0,
      "reward": 0.566292941570282,
      "reward_std": 0.20456740260124207,
      "rewards/simpleverify_reward/mean": 0.5662928819656372,
      "rewards/simpleverify_reward/std": 0.4955878257751465,
      "step": 545
    },
    {
      "clip_ratio/high_max": 0.0017977114293898921,
      "clip_ratio/high_mean": 0.0007846046955819475,
      "clip_ratio/low_mean": 0.0008559750349377282,
      "clip_ratio/low_min": 0.00012428839090716792,
      "clip_ratio/region_mean": 0.0016405797214247286,
      "epoch": 0.0509598726003185,
      "grad_norm": 0.11281414330005646,
      "learning_rate": 5e-07,
      "loss": 0.0422,
      "step": 546
    },
    {
      "clip_ratio/high_max": 0.0021410134650068358,
      "clip_ratio/high_mean": 0.0009510705385764595,
      "clip_ratio/low_mean": 0.0010003458555729594,
      "clip_ratio/low_min": 0.00010637885043252027,
      "clip_ratio/region_mean": 0.0019514163868734613,
      "epoch": 0.051053205700319085,
      "grad_norm": 0.11999141424894333,
      "learning_rate": 5e-07,
      "loss": 0.0039,
      "step": 547
    },
    {
      "clip_ratio/high_max": 0.0018839500735339243,
      "clip_ratio/high_mean": 0.0009561253282299731,
      "clip_ratio/low_mean": 0.0008820892071526032,
      "clip_ratio/low_min": 5.790295745100593e-05,
      "clip_ratio/region_mean": 0.0018382145062787458,
      "epoch": 0.05114653880031966,
      "grad_norm": 0.11104534566402435,
      "learning_rate": 5e-07,
      "loss": 0.0364,
      "step": 548
    },
    {
      "clip_ratio/high_max": 0.0020653288629546296,
      "clip_ratio/high_mean": 0.0009193188425342669,
      "clip_ratio/low_mean": 0.0010961689149553422,
      "clip_ratio/low_min": 0.00012934095229866216,
      "clip_ratio/region_mean": 0.0020154877493041568,
      "epoch": 0.05123987190032025,
      "grad_norm": 0.11612631380558014,
      "learning_rate": 5e-07,
      "loss": 0.0259,
      "step": 549
    },
    {
      "clip_ratio/high_max": 0.0026414799140184186,
      "clip_ratio/high_mean": 0.0009349911124445498,
      "clip_ratio/low_mean": 0.0009509224219073076,
      "clip_ratio/low_min": 0.00012770563625963405,
      "clip_ratio/region_mean": 0.0018859135670936666,
      "epoch": 0.05133320500032083,
      "grad_norm": 0.12166271358728409,
      "learning_rate": 5e-07,
      "loss": 0.0545,
      "step": 550
    },
    {
      "clip_ratio/high_max": 0.0020246553649485577,
      "clip_ratio/high_mean": 0.0008394591804972151,
      "clip_ratio/low_mean": 0.0008391728842980228,
      "clip_ratio/low_min": 0.00013701534953725059,
      "clip_ratio/region_mean": 0.001678632073890185,
      "epoch": 0.05142653810032142,
      "grad_norm": 0.1104893907904625,
      "learning_rate": 5e-07,
      "loss": -0.0261,
      "step": 551
    },
    {
      "clip_ratio/high_max": 0.0023723366030026227,
      "clip_ratio/high_mean": 0.0008477335723000579,
      "clip_ratio/low_mean": 0.0009994271531468257,
      "clip_ratio/low_min": 6.95408407409559e-05,
      "clip_ratio/region_mean": 0.0018471607108949684,
      "epoch": 0.051519871200322,
      "grad_norm": 0.11107384413480759,
      "learning_rate": 5e-07,
      "loss": 0.044,
      "step": 552
    },
    {
      "clip_ratio/high_max": 0.0018808580643963069,
      "clip_ratio/high_mean": 0.0008455972692900104,
      "clip_ratio/low_mean": 0.0010426582157379016,
      "clip_ratio/low_min": 4.3642833588819485e-05,
      "clip_ratio/region_mean": 0.0018882554431911558,
      "epoch": 0.05161320430032258,
      "grad_norm": 0.10766908526420593,
      "learning_rate": 5e-07,
      "loss": 0.0658,
      "step": 553
    },
    {
      "clip_ratio/high_max": 0.002202211362600792,
      "clip_ratio/high_mean": 0.0009578211538610049,
      "clip_ratio/low_mean": 0.0009856567048700526,
      "clip_ratio/low_min": 0.00010253313939756481,
      "clip_ratio/region_mean": 0.0019434778951108456,
      "epoch": 0.05170653740032317,
      "grad_norm": 0.1534569412469864,
      "learning_rate": 5e-07,
      "loss": 0.0161,
      "step": 554
    },
    {
      "clip_ratio/high_max": 0.00204296632000478,
      "clip_ratio/high_mean": 0.0008656384197820444,
      "clip_ratio/low_mean": 0.0009894777467707172,
      "clip_ratio/low_min": 5.825410335091874e-05,
      "clip_ratio/region_mean": 0.0018551162065705284,
      "epoch": 0.05179987050032375,
      "grad_norm": 0.11890851706266403,
      "learning_rate": 5e-07,
      "loss": 0.0308,
      "step": 555
    },
    {
      "clip_ratio/high_max": 0.0021327529539121315,
      "clip_ratio/high_mean": 0.000903949987332453,
      "clip_ratio/low_mean": 0.0009973022133635823,
      "clip_ratio/low_min": 8.809841983747901e-05,
      "clip_ratio/region_mean": 0.001901252195239067,
      "epoch": 0.05189320360032433,
      "grad_norm": 0.11634897440671921,
      "learning_rate": 5e-07,
      "loss": 0.0074,
      "step": 556
    },
    {
      "clip_ratio/high_max": 0.0019913680935133016,
      "clip_ratio/high_mean": 0.0008023066375244525,
      "clip_ratio/low_mean": 0.0009740409950609319,
      "clip_ratio/low_min": 7.841373371775262e-05,
      "clip_ratio/region_mean": 0.001776347664417699,
      "epoch": 0.051986536700324916,
      "grad_norm": 0.11418842524290085,
      "learning_rate": 5e-07,
      "loss": 0.0279,
      "step": 557
    },
    {
      "clip_ratio/high_max": 0.001897297945106402,
      "clip_ratio/high_mean": 0.0008251175877376227,
      "clip_ratio/low_mean": 0.0010319248995074304,
      "clip_ratio/low_min": 8.473674733977532e-05,
      "clip_ratio/region_mean": 0.0018570424908830319,
      "epoch": 0.0520798698003255,
      "grad_norm": 0.11881345510482788,
      "learning_rate": 5e-07,
      "loss": 0.0621,
      "step": 558
    },
    {
      "clip_ratio/high_max": 0.002319375009392388,
      "clip_ratio/high_mean": 0.0009469933975196909,
      "clip_ratio/low_mean": 0.0009762614727151231,
      "clip_ratio/low_min": 8.331218214152614e-05,
      "clip_ratio/region_mean": 0.0019232548438594677,
      "epoch": 0.05217320290032608,
      "grad_norm": 0.11436227709054947,
      "learning_rate": 5e-07,
      "loss": 0.0227,
      "step": 559
    },
    {
      "clip_ratio/high_max": 0.0019829685043077916,
      "clip_ratio/high_mean": 0.0007727001793682575,
      "clip_ratio/low_mean": 0.0009129445334110642,
      "clip_ratio/low_min": 7.140811612771358e-05,
      "clip_ratio/region_mean": 0.0016856447400641628,
      "epoch": 0.052266536000326665,
      "grad_norm": 0.10687913745641708,
      "learning_rate": 5e-07,
      "loss": 0.0878,
      "step": 560
    },
    {
      "clip_ratio/high_max": 0.002305364097992424,
      "clip_ratio/high_mean": 0.0008472461995552294,
      "clip_ratio/low_mean": 0.001016407048155088,
      "clip_ratio/low_min": 0.00012648938718484715,
      "clip_ratio/region_mean": 0.001863653218606487,
      "epoch": 0.05235986910032725,
      "grad_norm": 0.12502329051494598,
      "learning_rate": 5e-07,
      "loss": 0.0247,
      "step": 561
    },
    {
      "clip_ratio/high_max": 0.0020553359936457127,
      "clip_ratio/high_mean": 0.0008745505620026961,
      "clip_ratio/low_mean": 0.0008024528942769393,
      "clip_ratio/low_min": 2.9531024665629957e-05,
      "clip_ratio/region_mean": 0.0016770034417277202,
      "epoch": 0.052453202200327835,
      "grad_norm": 0.11320223659276962,
      "learning_rate": 5e-07,
      "loss": 0.0498,
      "step": 562
    },
    {
      "clip_ratio/high_max": 0.0025046629962162115,
      "clip_ratio/high_mean": 0.001022185688270838,
      "clip_ratio/low_mean": 0.000961427744186949,
      "clip_ratio/low_min": 0.00010992842999257846,
      "clip_ratio/region_mean": 0.001983613437914755,
      "epoch": 0.05254653530032841,
      "grad_norm": 0.12240775674581528,
      "learning_rate": 5e-07,
      "loss": 0.0071,
      "step": 563
    },
    {
      "clip_ratio/high_max": 0.0022878210365888663,
      "clip_ratio/high_mean": 0.0010208324638369959,
      "clip_ratio/low_mean": 0.0009285962951253168,
      "clip_ratio/low_min": 0.00010440485584695125,
      "clip_ratio/region_mean": 0.0019494287989800796,
      "epoch": 0.052639868400329,
      "grad_norm": 0.1285320520401001,
      "learning_rate": 5e-07,
      "loss": 0.0214,
      "step": 564
    },
    {
      "clip_ratio/high_max": 0.002386109670624137,
      "clip_ratio/high_mean": 0.0009226479196513537,
      "clip_ratio/low_mean": 0.0010097095382661792,
      "clip_ratio/low_min": 0.00015894618445599917,
      "clip_ratio/region_mean": 0.0019323574815643951,
      "epoch": 0.052733201500329584,
      "grad_norm": 0.10504744201898575,
      "learning_rate": 5e-07,
      "loss": 0.0297,
      "step": 565
    },
    {
      "clip_ratio/high_max": 0.002018149447394535,
      "clip_ratio/high_mean": 0.0008717725013411837,
      "clip_ratio/low_mean": 0.0008638180079287849,
      "clip_ratio/low_min": 7.641508909728145e-05,
      "clip_ratio/region_mean": 0.0017355905074509792,
      "epoch": 0.05282653460033017,
      "grad_norm": 0.10992496460676193,
      "learning_rate": 5e-07,
      "loss": 0.0213,
      "step": 566
    },
    {
      "clip_ratio/high_max": 0.001662341208430007,
      "clip_ratio/high_mean": 0.0008090257761068642,
      "clip_ratio/low_mean": 0.0008604204595030751,
      "clip_ratio/low_min": 3.879969153786078e-05,
      "clip_ratio/region_mean": 0.001669446261075791,
      "epoch": 0.05291986770033075,
      "grad_norm": 0.09976531565189362,
      "learning_rate": 5e-07,
      "loss": 0.0262,
      "step": 567
    },
    {
      "clip_ratio/high_max": 0.0021778413974971045,
      "clip_ratio/high_mean": 0.0008431734204350505,
      "clip_ratio/low_mean": 0.0008357139649888268,
      "clip_ratio/low_min": 2.7115211196360178e-05,
      "clip_ratio/region_mean": 0.0016788873836048879,
      "epoch": 0.05301320080033133,
      "grad_norm": 0.11282850056886673,
      "learning_rate": 5e-07,
      "loss": 0.0234,
      "step": 568
    },
    {
      "clip_ratio/high_max": 0.0019401165809540544,
      "clip_ratio/high_mean": 0.000870806690727477,
      "clip_ratio/low_mean": 0.000890755780346808,
      "clip_ratio/low_min": 7.97380571384565e-05,
      "clip_ratio/region_mean": 0.0017615625110920519,
      "epoch": 0.05310653390033192,
      "grad_norm": 0.10967303812503815,
      "learning_rate": 5e-07,
      "loss": 0.0216,
      "step": 569
    },
    {
      "clip_ratio/high_max": 0.0024330717205884866,
      "clip_ratio/high_mean": 0.000998763229290489,
      "clip_ratio/low_mean": 0.00094719095795881,
      "clip_ratio/low_min": 3.5720413507078774e-05,
      "clip_ratio/region_mean": 0.001945954150869511,
      "epoch": 0.053199867000332496,
      "grad_norm": 0.12433777004480362,
      "learning_rate": 5e-07,
      "loss": 0.0207,
      "step": 570
    },
    {
      "clip_ratio/high_max": 0.002364857660722919,
      "clip_ratio/high_mean": 0.0009006116742966697,
      "clip_ratio/low_mean": 0.0010083150191348977,
      "clip_ratio/low_min": 0.00014274609384301584,
      "clip_ratio/region_mean": 0.0019089267152594402,
      "epoch": 0.05329320010033308,
      "grad_norm": 0.1079363077878952,
      "learning_rate": 5e-07,
      "loss": 0.0352,
      "step": 571
    },
    {
      "clip_ratio/high_max": 0.0020563506259350106,
      "clip_ratio/high_mean": 0.0008067438557191053,
      "clip_ratio/low_mean": 0.0008442413873126497,
      "clip_ratio/low_min": 0.00010769148411782226,
      "clip_ratio/region_mean": 0.0016509852139279246,
      "epoch": 0.053386533200333666,
      "grad_norm": 0.10375802963972092,
      "learning_rate": 5e-07,
      "loss": 0.0284,
      "step": 572
    },
    {
      "clip_ratio/high_max": 0.002210682418080978,
      "clip_ratio/high_mean": 0.0009692956573417177,
      "clip_ratio/low_mean": 0.0008428273958998034,
      "clip_ratio/low_min": 7.976371671247762e-05,
      "clip_ratio/region_mean": 0.0018121230241376907,
      "epoch": 0.05347986630033425,
      "grad_norm": 0.11153191328048706,
      "learning_rate": 5e-07,
      "loss": 0.0042,
      "step": 573
    },
    {
      "clip_ratio/high_max": 0.0020743594286614098,
      "clip_ratio/high_mean": 0.0009702983243187191,
      "clip_ratio/low_mean": 0.0010929232921625953,
      "clip_ratio/low_min": 7.584327613585629e-05,
      "clip_ratio/region_mean": 0.0020632216837839223,
      "epoch": 0.05357319940033483,
      "grad_norm": 0.1228315681219101,
      "learning_rate": 5e-07,
      "loss": 0.0028,
      "step": 574
    },
    {
      "clip_ratio/high_max": 0.0024142859838320874,
      "clip_ratio/high_mean": 0.0009792892778932583,
      "clip_ratio/low_mean": 0.0008522613570676185,
      "clip_ratio/low_min": 2.2216052457224578e-05,
      "clip_ratio/region_mean": 0.0018315506531507708,
      "epoch": 0.053666532500335415,
      "grad_norm": 0.10518773645162582,
      "learning_rate": 5e-07,
      "loss": 0.0072,
      "step": 575
    },
    {
      "clip_ratio/high_max": 0.0019706792445504107,
      "clip_ratio/high_mean": 0.0008323230413225247,
      "clip_ratio/low_mean": 0.0010336639406887116,
      "clip_ratio/low_min": 8.10659857961582e-05,
      "clip_ratio/region_mean": 0.0018659869892871939,
      "epoch": 0.053759865600336,
      "grad_norm": 0.12349632382392883,
      "learning_rate": 5e-07,
      "loss": 0.0583,
      "step": 576
    },
    {
      "clip_ratio/high_max": 0.001970522429473931,
      "clip_ratio/high_mean": 0.0006810475151723949,
      "clip_ratio/low_mean": 0.0010234336587018333,
      "clip_ratio/low_min": 0.00010883995855692774,
      "clip_ratio/region_mean": 0.0017044811756932177,
      "epoch": 0.053853198700336585,
      "grad_norm": 0.11210542172193527,
      "learning_rate": 5e-07,
      "loss": 0.0694,
      "step": 577
    },
    {
      "clip_ratio/high_max": 0.0023311177246796433,
      "clip_ratio/high_mean": 0.0009478215779381571,
      "clip_ratio/low_mean": 0.0009528928148938576,
      "clip_ratio/low_min": 7.704389645368792e-05,
      "clip_ratio/region_mean": 0.00190071440738393,
      "epoch": 0.053946531800337164,
      "grad_norm": 0.11723656207323074,
      "learning_rate": 5e-07,
      "loss": 0.0261,
      "step": 578
    },
    {
      "clip_ratio/high_max": 0.0023703376173216384,
      "clip_ratio/high_mean": 0.0008474830829072744,
      "clip_ratio/low_mean": 0.000895149296411546,
      "clip_ratio/low_min": 7.146751704567578e-05,
      "clip_ratio/region_mean": 0.0017426324193365872,
      "epoch": 0.05403986490033775,
      "grad_norm": 0.11512760818004608,
      "learning_rate": 5e-07,
      "loss": -0.0272,
      "step": 579
    },
    {
      "clip_ratio/high_max": 0.0022417242798837833,
      "clip_ratio/high_mean": 0.0009777648883755319,
      "clip_ratio/low_mean": 0.0009912107161653694,
      "clip_ratio/low_min": 9.19986232474912e-05,
      "clip_ratio/region_mean": 0.001968975630006753,
      "epoch": 0.054133198000338334,
      "grad_norm": 0.10746188461780548,
      "learning_rate": 5e-07,
      "loss": 0.0332,
      "step": 580
    },
    {
      "clip_ratio/high_max": 0.0022240272737690248,
      "clip_ratio/high_mean": 0.0008705714262760011,
      "clip_ratio/low_mean": 0.0008080272527877241,
      "clip_ratio/low_min": 1.146368322224589e-05,
      "clip_ratio/region_mean": 0.0016785986517788842,
      "epoch": 0.05422653110033892,
      "grad_norm": 0.10076417773962021,
      "learning_rate": 5e-07,
      "loss": 0.0142,
      "step": 581
    },
    {
      "clip_ratio/high_max": 0.0021440061791508924,
      "clip_ratio/high_mean": 0.0008698747114976868,
      "clip_ratio/low_mean": 0.0009452526610402856,
      "clip_ratio/low_min": 1.4619882676925045e-05,
      "clip_ratio/region_mean": 0.0018151273834519088,
      "epoch": 0.0543198642003395,
      "grad_norm": 0.10422894358634949,
      "learning_rate": 5e-07,
      "loss": 0.0235,
      "step": 582
    },
    {
      "clip_ratio/high_max": 0.0021340099410736,
      "clip_ratio/high_mean": 0.0008902254448912572,
      "clip_ratio/low_mean": 0.0009562800987623632,
      "clip_ratio/low_min": 0.00012065700593666406,
      "clip_ratio/region_mean": 0.0018465055545675568,
      "epoch": 0.05441319730034008,
      "grad_norm": 0.1289396435022354,
      "learning_rate": 5e-07,
      "loss": 0.0136,
      "step": 583
    },
    {
      "clip_ratio/high_max": 0.002280005362990778,
      "clip_ratio/high_mean": 0.0009202598121191841,
      "clip_ratio/low_mean": 0.0009855988064373378,
      "clip_ratio/low_min": 8.580410121794557e-05,
      "clip_ratio/region_mean": 0.0019058585676248185,
      "epoch": 0.05450653040034067,
      "grad_norm": 0.1156398206949234,
      "learning_rate": 5e-07,
      "loss": 0.0096,
      "step": 584
    },
    {
      "clip_ratio/high_max": 0.001852575718658045,
      "clip_ratio/high_mean": 0.0007534167161793448,
      "clip_ratio/low_mean": 0.0010867692399187945,
      "clip_ratio/low_min": 0.00021118776840012288,
      "clip_ratio/region_mean": 0.001840185999753885,
      "epoch": 0.054599863500341246,
      "grad_norm": 0.10167401283979416,
      "learning_rate": 5e-07,
      "loss": 0.0636,
      "step": 585
    },
    {
      "clip_ratio/high_max": 0.002266954143124167,
      "clip_ratio/high_mean": 0.0008863886105245911,
      "clip_ratio/low_mean": 0.000959440340011497,
      "clip_ratio/low_min": 0.00012579278245539172,
      "clip_ratio/region_mean": 0.001845828941441141,
      "epoch": 0.05469319660034183,
      "grad_norm": 0.11721435189247131,
      "learning_rate": 5e-07,
      "loss": 0.0368,
      "step": 586
    },
    {
      "clip_ratio/high_max": 0.0020796455210074782,
      "clip_ratio/high_mean": 0.0008623068206361495,
      "clip_ratio/low_mean": 0.0009348703115392709,
      "clip_ratio/low_min": 9.302886792283971e-05,
      "clip_ratio/region_mean": 0.0017971771085285582,
      "epoch": 0.054786529700342416,
      "grad_norm": 0.10159080475568771,
      "learning_rate": 5e-07,
      "loss": 0.0191,
      "step": 587
    },
    {
      "clip_ratio/high_max": 0.001968663345905952,
      "clip_ratio/high_mean": 0.0008201699565688614,
      "clip_ratio/low_mean": 0.0007762718996673357,
      "clip_ratio/low_min": 0.00011739360706997104,
      "clip_ratio/region_mean": 0.0015964418707881123,
      "epoch": 0.054879862800343,
      "grad_norm": 0.11847740411758423,
      "learning_rate": 5e-07,
      "loss": 0.0382,
      "step": 588
    },
    {
      "clip_ratio/high_max": 0.0020848735148319975,
      "clip_ratio/high_mean": 0.0008623643716418883,
      "clip_ratio/low_mean": 0.0008878697317413753,
      "clip_ratio/low_min": 8.872743364918279e-05,
      "clip_ratio/region_mean": 0.001750234077917412,
      "epoch": 0.05497319590034358,
      "grad_norm": 0.11540618538856506,
      "learning_rate": 5e-07,
      "loss": 0.0002,
      "step": 589
    },
    {
      "clip_ratio/high_max": 0.0024522492312826216,
      "clip_ratio/high_mean": 0.0010433275310788304,
      "clip_ratio/low_mean": 0.0008479229709337233,
      "clip_ratio/low_min": 6.976294935157057e-05,
      "clip_ratio/region_mean": 0.0018912505111075006,
      "epoch": 0.055066529000344165,
      "grad_norm": 0.1188197061419487,
      "learning_rate": 5e-07,
      "loss": -0.0329,
      "step": 590
    },
    {
      "clip_ratio/high_max": 0.0020508826783043332,
      "clip_ratio/high_mean": 0.0008172529851435684,
      "clip_ratio/low_mean": 0.0011084157576988218,
      "clip_ratio/low_min": 0.00011978103430010378,
      "clip_ratio/region_mean": 0.0019256687301094644,
      "epoch": 0.05515986210034475,
      "grad_norm": 0.11246508359909058,
      "learning_rate": 5e-07,
      "loss": 0.0424,
      "step": 591
    },
    {
      "clip_ratio/high_max": 0.0019362592574907467,
      "clip_ratio/high_mean": 0.0008335558923135977,
      "clip_ratio/low_mean": 0.0010615137034619693,
      "clip_ratio/low_min": 0.00020528524055407615,
      "clip_ratio/region_mean": 0.0018950696248793975,
      "epoch": 0.055253195200345336,
      "grad_norm": 0.1147068664431572,
      "learning_rate": 5e-07,
      "loss": 0.027,
      "step": 592
    },
    {
      "clip_ratio/high_max": 0.0023566533272969536,
      "clip_ratio/high_mean": 0.0009588454122422263,
      "clip_ratio/low_mean": 0.0009337552983197384,
      "clip_ratio/low_min": 0.0001196568482555449,
      "clip_ratio/region_mean": 0.001892600703286007,
      "epoch": 0.055346528300345914,
      "grad_norm": 0.11453165113925934,
      "learning_rate": 5e-07,
      "loss": 0.0295,
      "step": 593
    },
    {
      "clip_ratio/high_max": 0.0021440054770209827,
      "clip_ratio/high_mean": 0.0009899417909764452,
      "clip_ratio/low_mean": 0.0007463917827408295,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0017363335864502005,
      "epoch": 0.0554398614003465,
      "grad_norm": 0.11425869166851044,
      "learning_rate": 5e-07,
      "loss": -0.0215,
      "step": 594
    },
    {
      "clip_ratio/high_max": 0.002218724537669914,
      "clip_ratio/high_mean": 0.0009207647126459051,
      "clip_ratio/low_mean": 0.0008466053441225085,
      "clip_ratio/low_min": 3.642602496256586e-05,
      "clip_ratio/region_mean": 0.0017673700458544772,
      "epoch": 0.055533194500347084,
      "grad_norm": 0.11393614113330841,
      "learning_rate": 5e-07,
      "loss": -0.0118,
      "step": 595
    },
    {
      "clip_ratio/high_max": 0.0021528544166358188,
      "clip_ratio/high_mean": 0.0009129051577474456,
      "clip_ratio/low_mean": 0.0008731592970434576,
      "clip_ratio/low_min": 1.6399895685026422e-05,
      "clip_ratio/region_mean": 0.0017860644511529244,
      "epoch": 0.05562652760034766,
      "grad_norm": 0.10185282677412033,
      "learning_rate": 5e-07,
      "loss": -0.0151,
      "step": 596
    },
    {
      "clip_ratio/high_max": 0.002157176219043322,
      "clip_ratio/high_mean": 0.0008639787556603551,
      "clip_ratio/low_mean": 0.0008351263113581808,
      "clip_ratio/low_min": 2.208870864706114e-05,
      "clip_ratio/region_mean": 0.001699105076113483,
      "epoch": 0.05571986070034825,
      "grad_norm": 0.10808951407670975,
      "learning_rate": 5e-07,
      "loss": -0.0081,
      "step": 597
    },
    {
      "clip_ratio/high_max": 0.0018806606567522977,
      "clip_ratio/high_mean": 0.0007400396116281627,
      "clip_ratio/low_mean": 0.0012435402677510865,
      "clip_ratio/low_min": 0.0002465235647832742,
      "clip_ratio/region_mean": 0.0019835798811982386,
      "epoch": 0.05581319380034883,
      "grad_norm": 0.11677709966897964,
      "learning_rate": 5e-07,
      "loss": 0.0932,
      "step": 598
    },
    {
      "clip_ratio/high_max": 0.0020062674702785444,
      "clip_ratio/high_mean": 0.000827371824925649,
      "clip_ratio/low_mean": 0.0009532641524856444,
      "clip_ratio/low_min": 0.00010691888564906549,
      "clip_ratio/region_mean": 0.0017806359464884736,
      "epoch": 0.05590652690034942,
      "grad_norm": 0.109047070145607,
      "learning_rate": 5e-07,
      "loss": 0.0666,
      "step": 599
    },
    {
      "clip_ratio/high_max": 0.0022166334310895763,
      "clip_ratio/high_mean": 0.0008740093271626392,
      "clip_ratio/low_mean": 0.0008822610907373019,
      "clip_ratio/low_min": 0.0001286474625885603,
      "clip_ratio/region_mean": 0.001756270430632867,
      "epoch": 0.055999860000349996,
      "grad_norm": 0.12908990681171417,
      "learning_rate": 5e-07,
      "loss": 0.0612,
      "step": 600
    },
    {
      "clip_ratio/high_max": 0.0021818598761456087,
      "clip_ratio/high_mean": 0.0008222938831750071,
      "clip_ratio/low_mean": 0.0007924025921965949,
      "clip_ratio/low_min": 9.439744553674245e-05,
      "clip_ratio/region_mean": 0.001614696466276655,
      "epoch": 0.05609319310035058,
      "grad_norm": 0.11477939784526825,
      "learning_rate": 5e-07,
      "loss": -0.0281,
      "step": 601
    },
    {
      "clip_ratio/high_max": 0.002116322808433324,
      "clip_ratio/high_mean": 0.0008281435511889867,
      "clip_ratio/low_mean": 0.0009320184944954235,
      "clip_ratio/low_min": 3.6338407880975865e-05,
      "clip_ratio/region_mean": 0.0017601619911147282,
      "epoch": 0.05618652620035117,
      "grad_norm": 0.10588187724351883,
      "learning_rate": 5e-07,
      "loss": 0.0565,
      "step": 602
    },
    {
      "clip_ratio/high_max": 0.002030770861892961,
      "clip_ratio/high_mean": 0.0008496585942339152,
      "clip_ratio/low_mean": 0.0009510739510005806,
      "clip_ratio/low_min": 9.427278928342275e-05,
      "clip_ratio/region_mean": 0.0018007325124926865,
      "epoch": 0.05627985930035175,
      "grad_norm": 0.11286570876836777,
      "learning_rate": 5e-07,
      "loss": 0.0526,
      "step": 603
    },
    {
      "clip_ratio/high_max": 0.0022984517709119245,
      "clip_ratio/high_mean": 0.0009216615435434505,
      "clip_ratio/low_mean": 0.0008442283924523508,
      "clip_ratio/low_min": 5.9367100220697466e-05,
      "clip_ratio/region_mean": 0.001765889894159045,
      "epoch": 0.05637319240035233,
      "grad_norm": 0.10795342922210693,
      "learning_rate": 5e-07,
      "loss": -0.019,
      "step": 604
    },
    {
      "clip_ratio/high_max": 0.002399879442236852,
      "clip_ratio/high_mean": 0.0009562360246491153,
      "clip_ratio/low_mean": 0.0008276925909740385,
      "clip_ratio/low_min": 2.520214366086293e-05,
      "clip_ratio/region_mean": 0.0017839286374510266,
      "epoch": 0.056466525500352915,
      "grad_norm": 0.11260202527046204,
      "learning_rate": 5e-07,
      "loss": -0.0074,
      "step": 605
    },
    {
      "clip_ratio/high_max": 0.002144084446626948,
      "clip_ratio/high_mean": 0.0008633690395072335,
      "clip_ratio/low_mean": 0.0010186526960751507,
      "clip_ratio/low_min": 8.585435080021853e-05,
      "clip_ratio/region_mean": 0.0018820217082975432,
      "epoch": 0.0565598586003535,
      "grad_norm": 0.11437302082777023,
      "learning_rate": 5e-07,
      "loss": 0.0396,
      "step": 606
    },
    {
      "clip_ratio/high_max": 0.002056544501101598,
      "clip_ratio/high_mean": 0.0009281519851356279,
      "clip_ratio/low_mean": 0.0008388617679884192,
      "clip_ratio/low_min": 8.490533400618006e-05,
      "clip_ratio/region_mean": 0.0017670137604000047,
      "epoch": 0.056653191700354086,
      "grad_norm": 0.10808861255645752,
      "learning_rate": 5e-07,
      "loss": -0.0198,
      "step": 607
    },
    {
      "clip_ratio/high_max": 0.001820944482460618,
      "clip_ratio/high_mean": 0.0008462278383376542,
      "clip_ratio/low_mean": 0.0010264632364851423,
      "clip_ratio/low_min": 0.00012756814157910412,
      "clip_ratio/region_mean": 0.0018726910930126905,
      "epoch": 0.056746524800354664,
      "grad_norm": 0.1258942037820816,
      "learning_rate": 5e-07,
      "loss": 0.0264,
      "step": 608
    },
    {
      "clip_ratio/high_max": 0.002374351395701524,
      "clip_ratio/high_mean": 0.0009587736458342988,
      "clip_ratio/low_mean": 0.0010411907860543579,
      "clip_ratio/low_min": 0.0001263154654225218,
      "clip_ratio/region_mean": 0.001999964501010254,
      "epoch": 0.05683985790035525,
      "grad_norm": 0.11755316704511642,
      "learning_rate": 5e-07,
      "loss": 0.038,
      "step": 609
    },
    {
      "clip_ratio/high_max": 0.0020050901439390145,
      "clip_ratio/high_mean": 0.0008088616214081412,
      "clip_ratio/low_mean": 0.0009619101074349601,
      "clip_ratio/low_min": 2.722765475482447e-05,
      "clip_ratio/region_mean": 0.0017707717124721967,
      "epoch": 0.056933191000355834,
      "grad_norm": 0.12753698229789734,
      "learning_rate": 5e-07,
      "loss": 0.0077,
      "step": 610
    },
    {
      "clip_ratio/high_max": 0.0019405136990826577,
      "clip_ratio/high_mean": 0.0008266186123364605,
      "clip_ratio/low_mean": 0.0010285347962053493,
      "clip_ratio/low_min": 0.00013597534325526794,
      "clip_ratio/region_mean": 0.0018551534740254283,
      "epoch": 0.05702652410035641,
      "grad_norm": 0.10906079411506653,
      "learning_rate": 5e-07,
      "loss": 0.0303,
      "step": 611
    },
    {
      "clip_ratio/high_max": 0.0022639406051894184,
      "clip_ratio/high_mean": 0.0008656689497001935,
      "clip_ratio/low_mean": 0.0010617912812449504,
      "clip_ratio/low_min": 0.00013168438545108074,
      "clip_ratio/region_mean": 0.0019274602236691862,
      "epoch": 0.057119857200357,
      "grad_norm": 0.11914733797311783,
      "learning_rate": 5e-07,
      "loss": 0.0579,
      "step": 612
    },
    {
      "clip_ratio/high_max": 0.002278934531204868,
      "clip_ratio/high_mean": 0.0008847486460581422,
      "clip_ratio/low_mean": 0.0010889857421716442,
      "clip_ratio/low_min": 0.00010289527199347503,
      "clip_ratio/region_mean": 0.0019737343609449454,
      "epoch": 0.05721319030035758,
      "grad_norm": 0.11920621246099472,
      "learning_rate": 5e-07,
      "loss": 0.0462,
      "step": 613
    },
    {
      "clip_ratio/high_max": 0.0023620593856321648,
      "clip_ratio/high_mean": 0.0008982486688182689,
      "clip_ratio/low_mean": 0.0010916755600192118,
      "clip_ratio/low_min": 5.775488807557849e-05,
      "clip_ratio/region_mean": 0.001989924283407163,
      "epoch": 0.05730652340035817,
      "grad_norm": 0.12199513614177704,
      "learning_rate": 5e-07,
      "loss": 0.0056,
      "step": 614
    },
    {
      "clip_ratio/high_max": 0.002087170818413142,
      "clip_ratio/high_mean": 0.000820574216049863,
      "clip_ratio/low_mean": 0.0009917885672621196,
      "clip_ratio/low_min": 6.0257066252233926e-05,
      "clip_ratio/region_mean": 0.0018123627814929932,
      "epoch": 0.05739985650035875,
      "grad_norm": 0.12222559750080109,
      "learning_rate": 5e-07,
      "loss": 0.0365,
      "step": 615
    },
    {
      "clip_ratio/high_max": 0.002332279284019023,
      "clip_ratio/high_mean": 0.001000333752926963,
      "clip_ratio/low_mean": 0.0008373116361326538,
      "clip_ratio/low_min": 6.787908205296844e-05,
      "clip_ratio/region_mean": 0.0018376453772361856,
      "epoch": 0.05749318960035933,
      "grad_norm": 0.10401295125484467,
      "learning_rate": 5e-07,
      "loss": -0.0128,
      "step": 616
    },
    {
      "clip_ratio/high_max": 0.0022599399781029206,
      "clip_ratio/high_mean": 0.0009222352182405302,
      "clip_ratio/low_mean": 0.0009959526541933883,
      "clip_ratio/low_min": 6.435901286749868e-05,
      "clip_ratio/region_mean": 0.0019181878960807808,
      "epoch": 0.05758652270035992,
      "grad_norm": 0.11351313441991806,
      "learning_rate": 5e-07,
      "loss": 0.0425,
      "step": 617
    },
    {
      "clip_ratio/high_max": 0.002439110081468243,
      "clip_ratio/high_mean": 0.0010193860416620737,
      "clip_ratio/low_mean": 0.000997598126559751,
      "clip_ratio/low_min": 6.831381324445829e-05,
      "clip_ratio/region_mean": 0.0020169842027826235,
      "epoch": 0.0576798558003605,
      "grad_norm": 0.1081160232424736,
      "learning_rate": 5e-07,
      "loss": 0.0123,
      "step": 618
    },
    {
      "clip_ratio/high_max": 0.0019591043346736114,
      "clip_ratio/high_mean": 0.0008565567004552577,
      "clip_ratio/low_mean": 0.0009645396548876306,
      "clip_ratio/low_min": 6.515915811178274e-05,
      "clip_ratio/region_mean": 0.0018210963462479413,
      "epoch": 0.05777318890036108,
      "grad_norm": 0.11262916773557663,
      "learning_rate": 5e-07,
      "loss": 0.0326,
      "step": 619
    },
    {
      "clip_ratio/high_max": 0.0020361211863928474,
      "clip_ratio/high_mean": 0.0009634299003664637,
      "clip_ratio/low_mean": 0.0009936204114637803,
      "clip_ratio/low_min": 0.00010140920676349197,
      "clip_ratio/region_mean": 0.001957050342753064,
      "epoch": 0.057866522000361666,
      "grad_norm": 0.11508557200431824,
      "learning_rate": 5e-07,
      "loss": -0.008,
      "step": 620
    },
    {
      "clip_ratio/high_max": 0.0023561363741464447,
      "clip_ratio/high_mean": 0.0009302628568548243,
      "clip_ratio/low_mean": 0.0008462007372145308,
      "clip_ratio/low_min": 2.644430333020864e-05,
      "clip_ratio/region_mean": 0.0017764636286301538,
      "epoch": 0.05795985510036225,
      "grad_norm": 0.11657225340604782,
      "learning_rate": 5e-07,
      "loss": 0.014,
      "step": 621
    },
    {
      "clip_ratio/high_max": 0.001934835974680027,
      "clip_ratio/high_mean": 0.0008603600563219516,
      "clip_ratio/low_mean": 0.0008482800458295969,
      "clip_ratio/low_min": 0.0001643007585698797,
      "clip_ratio/region_mean": 0.001708640113065485,
      "epoch": 0.05805318820036283,
      "grad_norm": 0.11910604685544968,
      "learning_rate": 5e-07,
      "loss": 0.0385,
      "step": 622
    },
    {
      "clip_ratio/high_max": 0.0019512593498802744,
      "clip_ratio/high_mean": 0.0009038523894560058,
      "clip_ratio/low_mean": 0.0009589462115400238,
      "clip_ratio/low_min": 3.151114196953131e-05,
      "clip_ratio/region_mean": 0.0018627985809871461,
      "epoch": 0.058146521300363414,
      "grad_norm": 0.11695756018161774,
      "learning_rate": 5e-07,
      "loss": 0.019,
      "step": 623
    },
    {
      "clip_ratio/high_max": 0.0022443949928856455,
      "clip_ratio/high_mean": 0.0008597324240326998,
      "clip_ratio/low_mean": 0.0008216194619308226,
      "clip_ratio/low_min": 5.64088049941347e-05,
      "clip_ratio/region_mean": 0.0016813518523122184,
      "epoch": 0.058239854400364,
      "grad_norm": 0.11792440712451935,
      "learning_rate": 5e-07,
      "loss": 0.0433,
      "step": 624
    },
    {
      "clip_ratio/high_max": 0.002182377818826353,
      "clip_ratio/high_mean": 0.000872285751029267,
      "clip_ratio/low_mean": 0.0009199724954669364,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0017922581828315742,
      "epoch": 0.058333187500364585,
      "grad_norm": 0.11826933175325394,
      "learning_rate": 5e-07,
      "loss": 0.0296,
      "step": 625
    },
    {
      "clip_ratio/high_max": 0.0018702465931710321,
      "clip_ratio/high_mean": 0.0008896688550521503,
      "clip_ratio/low_mean": 0.0008174207778210985,
      "clip_ratio/low_min": 8.848539800965227e-05,
      "clip_ratio/region_mean": 0.0017070896356017329,
      "epoch": 0.05842652060036516,
      "grad_norm": 0.11791253834962845,
      "learning_rate": 5e-07,
      "loss": 0.0439,
      "step": 626
    },
    {
      "clip_ratio/high_max": 0.0022917992318980396,
      "clip_ratio/high_mean": 0.0008940983207139652,
      "clip_ratio/low_mean": 0.0008964376465883106,
      "clip_ratio/low_min": 6.19795682723634e-05,
      "clip_ratio/region_mean": 0.0017905358981806785,
      "epoch": 0.05851985370036575,
      "grad_norm": 0.11113151162862778,
      "learning_rate": 5e-07,
      "loss": 0.0031,
      "step": 627
    },
    {
      "clip_ratio/high_max": 0.0022084015909058508,
      "clip_ratio/high_mean": 0.0007795265473760082,
      "clip_ratio/low_mean": 0.0009440569501748541,
      "clip_ratio/low_min": 0.00010543492589931702,
      "clip_ratio/region_mean": 0.001723583511193283,
      "epoch": 0.05861318680036633,
      "grad_norm": 0.10661335289478302,
      "learning_rate": 5e-07,
      "loss": 0.0586,
      "step": 628
    },
    {
      "clip_ratio/high_max": 0.0019342684863659088,
      "clip_ratio/high_mean": 0.0007755028618703363,
      "clip_ratio/low_mean": 0.0009990128892241046,
      "clip_ratio/low_min": 6.307509920588927e-05,
      "clip_ratio/region_mean": 0.0017745157892932184,
      "epoch": 0.05870651990036692,
      "grad_norm": 0.110100157558918,
      "learning_rate": 5e-07,
      "loss": 0.0643,
      "step": 629
    },
    {
      "clip_ratio/high_max": 0.002359968490054598,
      "clip_ratio/high_mean": 0.0009331602177553577,
      "clip_ratio/low_mean": 0.0008243064185080584,
      "clip_ratio/low_min": 5.533494913834147e-05,
      "clip_ratio/region_mean": 0.0017574666417203844,
      "epoch": 0.0587998530003675,
      "grad_norm": 0.11167032271623611,
      "learning_rate": 5e-07,
      "loss": 0.0318,
      "step": 630
    },
    {
      "clip_ratio/high_max": 0.0022097435685282107,
      "clip_ratio/high_mean": 0.0009652171811467269,
      "clip_ratio/low_mean": 0.0007533490497735329,
      "clip_ratio/low_min": 4.0306119444721844e-05,
      "clip_ratio/region_mean": 0.00171856619999744,
      "epoch": 0.05889318610036808,
      "grad_norm": 0.10837092250585556,
      "learning_rate": 5e-07,
      "loss": 0.0017,
      "step": 631
    },
    {
      "clip_ratio/high_max": 0.0020984467373637017,
      "clip_ratio/high_mean": 0.0009305182502430398,
      "clip_ratio/low_mean": 0.0009282513856305741,
      "clip_ratio/low_min": 7.509655642934376e-05,
      "clip_ratio/region_mean": 0.0018587696467875503,
      "epoch": 0.05898651920036867,
      "grad_norm": 0.11985462158918381,
      "learning_rate": 5e-07,
      "loss": 0.0328,
      "step": 632
    },
    {
      "clip_ratio/high_max": 0.0019929170739487745,
      "clip_ratio/high_mean": 0.0008291184840345522,
      "clip_ratio/low_mean": 0.0009537343812553445,
      "clip_ratio/low_min": 8.392140534851933e-05,
      "clip_ratio/region_mean": 0.0017828528507379815,
      "epoch": 0.05907985230036925,
      "grad_norm": 0.10457964241504669,
      "learning_rate": 5e-07,
      "loss": 0.0516,
      "step": 633
    },
    {
      "clip_ratio/high_max": 0.002041815412667347,
      "clip_ratio/high_mean": 0.0008649200099171139,
      "clip_ratio/low_mean": 0.0009490031570749125,
      "clip_ratio/low_min": 4.719053049484501e-05,
      "clip_ratio/region_mean": 0.001813923183362931,
      "epoch": 0.05917318540036983,
      "grad_norm": 0.11347368359565735,
      "learning_rate": 5e-07,
      "loss": 0.0189,
      "step": 634
    },
    {
      "clip_ratio/high_max": 0.001964383089216426,
      "clip_ratio/high_mean": 0.0008273380517493933,
      "clip_ratio/low_mean": 0.0010406208530184813,
      "clip_ratio/low_min": 0.00010824082892213482,
      "clip_ratio/region_mean": 0.0018679588247323409,
      "epoch": 0.059266518500370416,
      "grad_norm": 0.11991137266159058,
      "learning_rate": 5e-07,
      "loss": 0.0598,
      "step": 635
    },
    {
      "clip_ratio/high_max": 0.0022923578071640804,
      "clip_ratio/high_mean": 0.0009700251757749356,
      "clip_ratio/low_mean": 0.0009818398102652282,
      "clip_ratio/low_min": 8.135326879710192e-05,
      "clip_ratio/region_mean": 0.0019518648914527148,
      "epoch": 0.059359851600371,
      "grad_norm": 0.1229044497013092,
      "learning_rate": 5e-07,
      "loss": 0.0356,
      "step": 636
    },
    {
      "clip_ratio/high_max": 0.0018571305336081423,
      "clip_ratio/high_mean": 0.0008617836465418804,
      "clip_ratio/low_mean": 0.0009403614167240448,
      "clip_ratio/low_min": 2.4926881451392546e-05,
      "clip_ratio/region_mean": 0.0018021450596279465,
      "epoch": 0.05945318470037158,
      "grad_norm": 0.11119770258665085,
      "learning_rate": 5e-07,
      "loss": 0.0333,
      "step": 637
    },
    {
      "clip_ratio/high_max": 0.0019344757092767395,
      "clip_ratio/high_mean": 0.0007342880981013877,
      "clip_ratio/low_mean": 0.001053173778927885,
      "clip_ratio/low_min": 8.685278407938313e-05,
      "clip_ratio/region_mean": 0.0017874618788482621,
      "epoch": 0.059546517800372165,
      "grad_norm": 0.1111932098865509,
      "learning_rate": 5e-07,
      "loss": 0.026,
      "step": 638
    },
    {
      "clip_ratio/high_max": 0.0022995404069661163,
      "clip_ratio/high_mean": 0.0008713916722626891,
      "clip_ratio/low_mean": 0.0008030291319300886,
      "clip_ratio/low_min": 7.442868172802264e-05,
      "clip_ratio/region_mean": 0.0016744208296586294,
      "epoch": 0.05963985090037275,
      "grad_norm": 0.11531902104616165,
      "learning_rate": 5e-07,
      "loss": 0.0142,
      "step": 639
    },
    {
      "clip_ratio/high_max": 0.001993691905227024,
      "clip_ratio/high_mean": 0.0007176747603807598,
      "clip_ratio/low_mean": 0.0009505346788500901,
      "clip_ratio/low_min": 9.479778145760065e-05,
      "clip_ratio/region_mean": 0.0016682094428688288,
      "epoch": 0.059733184000373335,
      "grad_norm": 0.11744365096092224,
      "learning_rate": 5e-07,
      "loss": 0.0627,
      "step": 640
    },
    {
      "clip_ratio/high_max": 0.0019075470299867447,
      "clip_ratio/high_mean": 0.0008553083425795194,
      "clip_ratio/low_mean": 0.0009940070503944298,
      "clip_ratio/low_min": 9.510266318102367e-05,
      "clip_ratio/region_mean": 0.001849315405706875,
      "epoch": 0.05982651710037391,
      "grad_norm": 0.1218980923295021,
      "learning_rate": 5e-07,
      "loss": 0.0413,
      "step": 641
    },
    {
      "clip_ratio/high_max": 0.002259663895529229,
      "clip_ratio/high_mean": 0.0009407333382114302,
      "clip_ratio/low_mean": 0.0009101762898353627,
      "clip_ratio/low_min": 3.44037853210466e-05,
      "clip_ratio/region_mean": 0.0018509096335037611,
      "epoch": 0.0599198502003745,
      "grad_norm": 0.1273493468761444,
      "learning_rate": 5e-07,
      "loss": 0.0084,
      "step": 642
    },
    {
      "clip_ratio/high_max": 0.0023304201022256166,
      "clip_ratio/high_mean": 0.0008491436983604217,
      "clip_ratio/low_mean": 0.0008631236487417482,
      "clip_ratio/low_min": 9.430965928913793e-05,
      "clip_ratio/region_mean": 0.00171226731617935,
      "epoch": 0.060013183300375084,
      "grad_norm": 0.1125178411602974,
      "learning_rate": 5e-07,
      "loss": 0.0184,
      "step": 643
    },
    {
      "clip_ratio/high_max": 0.002304683701368049,
      "clip_ratio/high_mean": 0.0010065911010315176,
      "clip_ratio/low_mean": 0.0010885827723541297,
      "clip_ratio/low_min": 0.0002463322216499364,
      "clip_ratio/region_mean": 0.0020951738333678804,
      "epoch": 0.06010651640037567,
      "grad_norm": 0.1215142235159874,
      "learning_rate": 5e-07,
      "loss": 0.0671,
      "step": 644
    },
    {
      "clip_ratio/high_max": 0.0022447503433795646,
      "clip_ratio/high_mean": 0.0007964717951836064,
      "clip_ratio/low_mean": 0.0010076265098177828,
      "clip_ratio/low_min": 9.051342385646421e-05,
      "clip_ratio/region_mean": 0.0018040983341052197,
      "epoch": 0.06019984950037625,
      "grad_norm": 0.12314977496862411,
      "learning_rate": 5e-07,
      "loss": 0.0444,
      "step": 645
    },
    {
      "clip_ratio/high_max": 0.0025729540720931254,
      "clip_ratio/high_mean": 0.0010429379908600822,
      "clip_ratio/low_mean": 0.0009234190292772837,
      "clip_ratio/low_min": 8.006583720998606e-05,
      "clip_ratio/region_mean": 0.0019663570128614083,
      "epoch": 0.06029318260037683,
      "grad_norm": 0.11553333699703217,
      "learning_rate": 5e-07,
      "loss": -0.0197,
      "step": 646
    },
    {
      "clip_ratio/high_max": 0.0018563735429779626,
      "clip_ratio/high_mean": 0.0007951673323987052,
      "clip_ratio/low_mean": 0.0009671276366134407,
      "clip_ratio/low_min": 0.00017867561109596863,
      "clip_ratio/region_mean": 0.0017622949890210293,
      "epoch": 0.06038651570037742,
      "grad_norm": 0.1124538853764534,
      "learning_rate": 5e-07,
      "loss": 0.0333,
      "step": 647
    },
    {
      "clip_ratio/high_max": 0.002055019336694386,
      "clip_ratio/high_mean": 0.000809468399893376,
      "clip_ratio/low_mean": 0.001008001441732631,
      "clip_ratio/low_min": 0.00014749341607966926,
      "clip_ratio/region_mean": 0.0018174698125221767,
      "epoch": 0.060479848800377996,
      "grad_norm": 0.11035261303186417,
      "learning_rate": 5e-07,
      "loss": 0.0688,
      "step": 648
    },
    {
      "clip_ratio/high_max": 0.002232881903182715,
      "clip_ratio/high_mean": 0.0009179935441352427,
      "clip_ratio/low_mean": 0.0008038120831770357,
      "clip_ratio/low_min": 6.26534865659778e-05,
      "clip_ratio/region_mean": 0.0017218056600540876,
      "epoch": 0.06057318190037858,
      "grad_norm": 0.11102437973022461,
      "learning_rate": 5e-07,
      "loss": -0.0031,
      "step": 649
    },
    {
      "clip_ratio/high_max": 0.0023341145788435824,
      "clip_ratio/high_mean": 0.0009762751942616887,
      "clip_ratio/low_mean": 0.0009260304723284207,
      "clip_ratio/low_min": 6.642028347414453e-05,
      "clip_ratio/region_mean": 0.0019023056520381942,
      "epoch": 0.060666515000379166,
      "grad_norm": 0.12068230658769608,
      "learning_rate": 5e-07,
      "loss": 0.0189,
      "step": 650
    },
    {
      "clip_ratio/high_max": 0.0021723415156884585,
      "clip_ratio/high_mean": 0.0009087978414754616,
      "clip_ratio/low_mean": 0.0009298926906922134,
      "clip_ratio/low_min": 6.105723332439084e-05,
      "clip_ratio/region_mean": 0.0018386905649094842,
      "epoch": 0.06075984810037975,
      "grad_norm": 0.11945465207099915,
      "learning_rate": 5e-07,
      "loss": 0.0116,
      "step": 651
    },
    {
      "clip_ratio/high_max": 0.0024555833733757026,
      "clip_ratio/high_mean": 0.0011302970851829741,
      "clip_ratio/low_mean": 0.0009112478219321929,
      "clip_ratio/low_min": 0.0001350553739030147,
      "clip_ratio/region_mean": 0.002041544888925273,
      "epoch": 0.06085318120038033,
      "grad_norm": 0.11840710788965225,
      "learning_rate": 5e-07,
      "loss": -0.0368,
      "step": 652
    },
    {
      "clip_ratio/high_max": 0.002429602936899755,
      "clip_ratio/high_mean": 0.0010381701868027449,
      "clip_ratio/low_mean": 0.0007510583691328065,
      "clip_ratio/low_min": 7.664811892027501e-05,
      "clip_ratio/region_mean": 0.0017892285322886892,
      "epoch": 0.060946514300380915,
      "grad_norm": 0.10616827756166458,
      "learning_rate": 5e-07,
      "loss": 0.0017,
      "step": 653
    },
    {
      "clip_ratio/high_max": 0.0019741412870644126,
      "clip_ratio/high_mean": 0.0008681316630827496,
      "clip_ratio/low_mean": 0.0010371649423177587,
      "clip_ratio/low_min": 0.00011078548777732067,
      "clip_ratio/region_mean": 0.0019052966163144447,
      "epoch": 0.0610398474003815,
      "grad_norm": 0.10807197540998459,
      "learning_rate": 5e-07,
      "loss": 0.0452,
      "step": 654
    },
    {
      "clip_ratio/high_max": 0.0022755039171897806,
      "clip_ratio/high_mean": 0.0007841526294214418,
      "clip_ratio/low_mean": 0.0009199364722007886,
      "clip_ratio/low_min": 8.306949803227326e-05,
      "clip_ratio/region_mean": 0.0017040891143551562,
      "epoch": 0.061133180500382085,
      "grad_norm": 0.09756267815828323,
      "learning_rate": 5e-07,
      "loss": 0.0281,
      "step": 655
    },
    {
      "clip_ratio/high_max": 0.0019925493688788265,
      "clip_ratio/high_mean": 0.0008598707308919984,
      "clip_ratio/low_mean": 0.0009146552074525971,
      "clip_ratio/low_min": 4.028847160952864e-05,
      "clip_ratio/region_mean": 0.0017745259683579206,
      "epoch": 0.061226513600382663,
      "grad_norm": 0.11962583661079407,
      "learning_rate": 5e-07,
      "loss": 0.0089,
      "step": 656
    },
    {
      "clip_ratio/high_max": 0.002119287171808537,
      "clip_ratio/high_mean": 0.000882501855812734,
      "clip_ratio/low_mean": 0.00109432149110944,
      "clip_ratio/low_min": 0.00015189554142125417,
      "clip_ratio/region_mean": 0.001976823368750047,
      "epoch": 0.06131984670038325,
      "grad_norm": 0.12505759298801422,
      "learning_rate": 5e-07,
      "loss": 0.0699,
      "step": 657
    },
    {
      "clip_ratio/high_max": 0.0020105290204810444,
      "clip_ratio/high_mean": 0.000887370342752547,
      "clip_ratio/low_mean": 0.0009877627599053085,
      "clip_ratio/low_min": 0.00014118926719675073,
      "clip_ratio/region_mean": 0.0018751331153907813,
      "epoch": 0.061413179800383834,
      "grad_norm": 0.10885881632566452,
      "learning_rate": 5e-07,
      "loss": 0.0352,
      "step": 658
    },
    {
      "clip_ratio/high_max": 0.0020052307118021417,
      "clip_ratio/high_mean": 0.000810056770205847,
      "clip_ratio/low_mean": 0.0010088041744893417,
      "clip_ratio/low_min": 3.693681810545968e-05,
      "clip_ratio/region_mean": 0.0018188609174103476,
      "epoch": 0.06150651290038442,
      "grad_norm": 0.12114110589027405,
      "learning_rate": 5e-07,
      "loss": 0.0406,
      "step": 659
    },
    {
      "clip_ratio/high_max": 0.0024195651640184224,
      "clip_ratio/high_mean": 0.0009708950201456901,
      "clip_ratio/low_mean": 0.0009073981855181046,
      "clip_ratio/low_min": 0.00016312924799422035,
      "clip_ratio/region_mean": 0.0018782932238536887,
      "epoch": 0.061599846000385,
      "grad_norm": 0.10972759127616882,
      "learning_rate": 5e-07,
      "loss": 0.0096,
      "step": 660
    },
    {
      "clip_ratio/high_max": 0.0020265105304133613,
      "clip_ratio/high_mean": 0.0008510976422257954,
      "clip_ratio/low_mean": 0.0009078886359930038,
      "clip_ratio/low_min": 0.00010403232136013685,
      "clip_ratio/region_mean": 0.0017589862618478946,
      "epoch": 0.06169317910038558,
      "grad_norm": 0.11354132741689682,
      "learning_rate": 5e-07,
      "loss": 0.0333,
      "step": 661
    },
    {
      "clip_ratio/high_max": 0.002442816286929883,
      "clip_ratio/high_mean": 0.0009089711329579586,
      "clip_ratio/low_mean": 0.0009379362345498521,
      "clip_ratio/low_min": 0.00010806231239257613,
      "clip_ratio/region_mean": 0.0018469073438609485,
      "epoch": 0.06178651220038617,
      "grad_norm": 0.11633361876010895,
      "learning_rate": 5e-07,
      "loss": 0.0327,
      "step": 662
    },
    {
      "clip_ratio/high_max": 0.0019958093980676495,
      "clip_ratio/high_mean": 0.0008278582299681148,
      "clip_ratio/low_mean": 0.0008554544801882003,
      "clip_ratio/low_min": 4.302970592107158e-05,
      "clip_ratio/region_mean": 0.0016833126865094528,
      "epoch": 0.061879845300386746,
      "grad_norm": 0.10975474119186401,
      "learning_rate": 5e-07,
      "loss": 0.0109,
      "step": 663
    },
    {
      "clip_ratio/high_max": 0.002179109986172989,
      "clip_ratio/high_mean": 0.0008672777003084775,
      "clip_ratio/low_mean": 0.0009964025357476203,
      "clip_ratio/low_min": 0.00015020836053736275,
      "clip_ratio/region_mean": 0.001863680205133278,
      "epoch": 0.06197317840038733,
      "grad_norm": 0.10996685177087784,
      "learning_rate": 5e-07,
      "loss": 0.0684,
      "step": 664
    },
    {
      "clip_ratio/high_max": 0.0018542384896136355,
      "clip_ratio/high_mean": 0.0008165592062141513,
      "clip_ratio/low_mean": 0.0008712048002053052,
      "clip_ratio/low_min": 5.4636217100778595e-05,
      "clip_ratio/region_mean": 0.001687763971858658,
      "epoch": 0.062066511500387916,
      "grad_norm": 0.11816082149744034,
      "learning_rate": 5e-07,
      "loss": 0.0626,
      "step": 665
    },
    {
      "clip_ratio/high_max": 0.0021608519746223465,
      "clip_ratio/high_mean": 0.0009907646199280862,
      "clip_ratio/low_mean": 0.0009476730119786225,
      "clip_ratio/low_min": 0.00011035184252250474,
      "clip_ratio/region_mean": 0.0019384376792004332,
      "epoch": 0.0621598446003885,
      "grad_norm": 0.12161535024642944,
      "learning_rate": 5e-07,
      "loss": 0.0439,
      "step": 666
    },
    {
      "clip_ratio/high_max": 0.0021589837633655407,
      "clip_ratio/high_mean": 0.0008384463581023738,
      "clip_ratio/low_mean": 0.0008264871830760967,
      "clip_ratio/low_min": 1.3836617654305883e-05,
      "clip_ratio/region_mean": 0.0016649335739202797,
      "epoch": 0.06225317770038908,
      "grad_norm": 0.10699169337749481,
      "learning_rate": 5e-07,
      "loss": -0.006,
      "step": 667
    },
    {
      "clip_ratio/high_max": 0.002378482993663056,
      "clip_ratio/high_mean": 0.0009447540687688161,
      "clip_ratio/low_mean": 0.001020275096379919,
      "clip_ratio/low_min": 0.00012909223369206302,
      "clip_ratio/region_mean": 0.0019650290851132013,
      "epoch": 0.062346510800389665,
      "grad_norm": 0.1234801784157753,
      "learning_rate": 5e-07,
      "loss": 0.0231,
      "step": 668
    },
    {
      "clip_ratio/high_max": 0.0023764773359289393,
      "clip_ratio/high_mean": 0.0008783021567069227,
      "clip_ratio/low_mean": 0.0009636929607950151,
      "clip_ratio/low_min": 7.339167223108234e-05,
      "clip_ratio/region_mean": 0.001841995064751245,
      "epoch": 0.06243984390039025,
      "grad_norm": 0.10932788997888565,
      "learning_rate": 5e-07,
      "loss": 0.0001,
      "step": 669
    },
    {
      "clip_ratio/high_max": 0.0021231924620224163,
      "clip_ratio/high_mean": 0.0007946399091451894,
      "clip_ratio/low_mean": 0.0009064904570550425,
      "clip_ratio/low_min": 7.211908859972027e-05,
      "clip_ratio/region_mean": 0.0017011303716572002,
      "epoch": 0.06253317700039084,
      "grad_norm": 0.11339017003774643,
      "learning_rate": 5e-07,
      "loss": 0.024,
      "step": 670
    },
    {
      "clip_ratio/high_max": 0.0022071549865358975,
      "clip_ratio/high_mean": 0.00099916062936245,
      "clip_ratio/low_mean": 0.0010915202601609053,
      "clip_ratio/low_min": 8.820474249660037e-05,
      "clip_ratio/region_mean": 0.002090680893161334,
      "epoch": 0.06262651010039141,
      "grad_norm": 0.11365722119808197,
      "learning_rate": 5e-07,
      "loss": -0.0182,
      "step": 671
    },
    {
      "clip_ratio/high_max": 0.0017761085691745393,
      "clip_ratio/high_mean": 0.0008043383695621742,
      "clip_ratio/low_mean": 0.0009619323573133443,
      "clip_ratio/low_min": 5.7738540363061475e-05,
      "clip_ratio/region_mean": 0.0017662707032286562,
      "epoch": 0.062719843200392,
      "grad_norm": 0.11216006428003311,
      "learning_rate": 5e-07,
      "loss": 0.0488,
      "step": 672
    },
    {
      "clip_ratio/high_max": 0.002024648027145304,
      "clip_ratio/high_mean": 0.000844466507260222,
      "clip_ratio/low_mean": 0.0009827440553635824,
      "clip_ratio/low_min": 0.00013928034150012536,
      "clip_ratio/region_mean": 0.0018272105589858256,
      "completions/clipped_ratio": 0.013846261160714302,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4081.0,
      "completions/mean_length": 611.4947509765625,
      "completions/mean_terminated_length": 562.56982421875,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.06281317630039258,
      "grad_norm": 0.1239209696650505,
      "learning_rate": 5e-07,
      "loss": 0.0707,
      "num_tokens": 571337868.0,
      "reward": 0.578072726726532,
      "reward_std": 0.19993500411510468,
      "rewards/simpleverify_reward/mean": 0.5780726671218872,
      "rewards/simpleverify_reward/std": 0.49386921525001526,
      "step": 673
    },
    {
      "clip_ratio/high_max": 0.0022594357978960034,
      "clip_ratio/high_mean": 0.0009024176179082133,
      "clip_ratio/low_mean": 0.0009460923829465173,
      "clip_ratio/low_min": 4.831567730434472e-05,
      "clip_ratio/region_mean": 0.001848509957198985,
      "epoch": 0.06290650940039316,
      "grad_norm": 0.11661041527986526,
      "learning_rate": 5e-07,
      "loss": 0.0497,
      "step": 674
    },
    {
      "clip_ratio/high_max": 0.0019650363574328367,
      "clip_ratio/high_mean": 0.0008016203082661377,
      "clip_ratio/low_mean": 0.0009778201583685586,
      "clip_ratio/low_min": 9.540592873236164e-05,
      "clip_ratio/region_mean": 0.001779440492100548,
      "epoch": 0.06299984250039375,
      "grad_norm": 0.12250484526157379,
      "learning_rate": 5e-07,
      "loss": 0.0295,
      "step": 675
    },
    {
      "clip_ratio/high_max": 0.002313408400368644,
      "clip_ratio/high_mean": 0.0008866320531524252,
      "clip_ratio/low_mean": 0.0008791541167738615,
      "clip_ratio/low_min": 6.745323935319902e-05,
      "clip_ratio/region_mean": 0.0017657861462794244,
      "epoch": 0.06309317560039433,
      "grad_norm": 0.11759001761674881,
      "learning_rate": 5e-07,
      "loss": 0.0499,
      "step": 676
    },
    {
      "clip_ratio/high_max": 0.002310666226549074,
      "clip_ratio/high_mean": 0.0009191633107548114,
      "clip_ratio/low_mean": 0.0008343769713974325,
      "clip_ratio/low_min": 8.186933882825542e-05,
      "clip_ratio/region_mean": 0.0017535402585053816,
      "epoch": 0.06318650870039491,
      "grad_norm": 0.10510535538196564,
      "learning_rate": 5e-07,
      "loss": 0.0256,
      "step": 677
    },
    {
      "clip_ratio/high_max": 0.002154057139705401,
      "clip_ratio/high_mean": 0.00093177242706588,
      "clip_ratio/low_mean": 0.0008646373717056122,
      "clip_ratio/low_min": 4.346419154899195e-05,
      "clip_ratio/region_mean": 0.001796409793314524,
      "epoch": 0.0632798418003955,
      "grad_norm": 0.11236720532178879,
      "learning_rate": 5e-07,
      "loss": 0.0125,
      "step": 678
    },
    {
      "clip_ratio/high_max": 0.002097315140417777,
      "clip_ratio/high_mean": 0.0009281259517592844,
      "clip_ratio/low_mean": 0.000777872281105374,
      "clip_ratio/low_min": 3.923265830962919e-05,
      "clip_ratio/region_mean": 0.0017059982201317325,
      "epoch": 0.06337317490039608,
      "grad_norm": 0.11597397923469543,
      "learning_rate": 5e-07,
      "loss": -0.0071,
      "step": 679
    },
    {
      "clip_ratio/high_max": 0.0022723657748429105,
      "clip_ratio/high_mean": 0.0008813023250695551,
      "clip_ratio/low_mean": 0.0008890627159416908,
      "clip_ratio/low_min": 3.103107246715808e-05,
      "clip_ratio/region_mean": 0.0017703650228213519,
      "epoch": 0.06346650800039666,
      "grad_norm": 0.227833092212677,
      "learning_rate": 5e-07,
      "loss": 0.0221,
      "step": 680
    },
    {
      "clip_ratio/high_max": 0.0023026135604595765,
      "clip_ratio/high_mean": 0.0009326366307504941,
      "clip_ratio/low_mean": 0.000951143711063196,
      "clip_ratio/low_min": 6.739867058058735e-05,
      "clip_ratio/region_mean": 0.0018837803727365099,
      "epoch": 0.06355984110039725,
      "grad_norm": 0.12531010806560516,
      "learning_rate": 5e-07,
      "loss": 0.0233,
      "step": 681
    },
    {
      "clip_ratio/high_max": 0.002376697782892734,
      "clip_ratio/high_mean": 0.0010264283664582763,
      "clip_ratio/low_mean": 0.0007380279803328449,
      "clip_ratio/low_min": 8.848020752338925e-05,
      "clip_ratio/region_mean": 0.0017644563486101106,
      "epoch": 0.06365317420039783,
      "grad_norm": 0.11755232512950897,
      "learning_rate": 5e-07,
      "loss": -0.0045,
      "step": 682
    },
    {
      "clip_ratio/high_max": 0.002174263328925008,
      "clip_ratio/high_mean": 0.0008591366040491266,
      "clip_ratio/low_mean": 0.0009162856949842535,
      "clip_ratio/low_min": 0.00010269388621964026,
      "clip_ratio/region_mean": 0.0017754223154042847,
      "epoch": 0.06374650730039842,
      "grad_norm": 0.13112573325634003,
      "learning_rate": 5e-07,
      "loss": 0.0099,
      "step": 683
    },
    {
      "clip_ratio/high_max": 0.0021283791211317293,
      "clip_ratio/high_mean": 0.0008853964536683634,
      "clip_ratio/low_mean": 0.0008339162486663554,
      "clip_ratio/low_min": 1.4831513908575289e-05,
      "clip_ratio/region_mean": 0.00171931269869674,
      "epoch": 0.063839840400399,
      "grad_norm": 0.11962207406759262,
      "learning_rate": 5e-07,
      "loss": 0.0371,
      "step": 684
    },
    {
      "clip_ratio/high_max": 0.001996298127778573,
      "clip_ratio/high_mean": 0.0008196658091037534,
      "clip_ratio/low_mean": 0.0008072171458479716,
      "clip_ratio/low_min": 9.372425756737357e-05,
      "clip_ratio/region_mean": 0.0016268829713226296,
      "epoch": 0.06393317350039958,
      "grad_norm": 0.0999615266919136,
      "learning_rate": 5e-07,
      "loss": 0.0355,
      "step": 685
    },
    {
      "clip_ratio/high_max": 0.0019031387782888487,
      "clip_ratio/high_mean": 0.000784312184805458,
      "clip_ratio/low_mean": 0.0008678415197209688,
      "clip_ratio/low_min": 0.00011635986629698891,
      "clip_ratio/region_mean": 0.0016521537509106565,
      "epoch": 0.06402650660040017,
      "grad_norm": 0.1133798211812973,
      "learning_rate": 5e-07,
      "loss": 0.0119,
      "step": 686
    },
    {
      "clip_ratio/high_max": 0.0023134962902986445,
      "clip_ratio/high_mean": 0.0009142197886831127,
      "clip_ratio/low_mean": 0.000804344295829651,
      "clip_ratio/low_min": 2.9995632758073043e-05,
      "clip_ratio/region_mean": 0.0017185640899697319,
      "epoch": 0.06411983970040075,
      "grad_norm": 0.1172514483332634,
      "learning_rate": 5e-07,
      "loss": 0.0121,
      "step": 687
    },
    {
      "clip_ratio/high_max": 0.002610213341540657,
      "clip_ratio/high_mean": 0.0010439515754114836,
      "clip_ratio/low_mean": 0.0008237462534452789,
      "clip_ratio/low_min": 5.9594914091576356e-05,
      "clip_ratio/region_mean": 0.0018676978361327201,
      "epoch": 0.06421317280040133,
      "grad_norm": 0.12294452637434006,
      "learning_rate": 5e-07,
      "loss": -0.0108,
      "step": 688
    },
    {
      "clip_ratio/high_max": 0.0021184008874115534,
      "clip_ratio/high_mean": 0.0008967141075117979,
      "clip_ratio/low_mean": 0.0008554742908017943,
      "clip_ratio/low_min": 0.00010885067786148284,
      "clip_ratio/region_mean": 0.0017521884219604544,
      "epoch": 0.06430650590040192,
      "grad_norm": 0.12079989165067673,
      "learning_rate": 5e-07,
      "loss": 0.0169,
      "step": 689
    },
    {
      "clip_ratio/high_max": 0.0022498478574561886,
      "clip_ratio/high_mean": 0.0009390450522914762,
      "clip_ratio/low_mean": 0.0009173390862997621,
      "clip_ratio/low_min": 8.953243468567962e-05,
      "clip_ratio/region_mean": 0.0018563841294962913,
      "epoch": 0.0643998390004025,
      "grad_norm": 0.1207461878657341,
      "learning_rate": 5e-07,
      "loss": 0.029,
      "step": 690
    },
    {
      "clip_ratio/high_max": 0.002185035660659196,
      "clip_ratio/high_mean": 0.0008999361398309702,
      "clip_ratio/low_mean": 0.0009353815421491163,
      "clip_ratio/low_min": 0.00011110003833891824,
      "clip_ratio/region_mean": 0.0018353176565142348,
      "epoch": 0.06449317210040308,
      "grad_norm": 0.2017844170331955,
      "learning_rate": 5e-07,
      "loss": 0.0334,
      "step": 691
    },
    {
      "clip_ratio/high_max": 0.0022705118462909013,
      "clip_ratio/high_mean": 0.0009283780527766794,
      "clip_ratio/low_mean": 0.0008836937886371743,
      "clip_ratio/low_min": 9.145268177235266e-05,
      "clip_ratio/region_mean": 0.0018120718523277901,
      "epoch": 0.06458650520040367,
      "grad_norm": 0.10330765694379807,
      "learning_rate": 5e-07,
      "loss": 0.0266,
      "step": 692
    },
    {
      "clip_ratio/high_max": 0.0022464818612206727,
      "clip_ratio/high_mean": 0.0009787061917450046,
      "clip_ratio/low_mean": 0.0008917672239476815,
      "clip_ratio/low_min": 6.901109645696124e-05,
      "clip_ratio/region_mean": 0.0018704734247876331,
      "epoch": 0.06467983830040425,
      "grad_norm": 0.12089096754789352,
      "learning_rate": 5e-07,
      "loss": 0.0112,
      "step": 693
    },
    {
      "clip_ratio/high_max": 0.0022732198194717057,
      "clip_ratio/high_mean": 0.0008519197654095478,
      "clip_ratio/low_mean": 0.0008414077292400179,
      "clip_ratio/low_min": 2.5545346034050453e-05,
      "clip_ratio/region_mean": 0.0016933274964685552,
      "epoch": 0.06477317140040484,
      "grad_norm": 0.10948824882507324,
      "learning_rate": 5e-07,
      "loss": 0.0406,
      "step": 694
    },
    {
      "clip_ratio/high_max": 0.002184938952268567,
      "clip_ratio/high_mean": 0.0009581586800777586,
      "clip_ratio/low_mean": 0.0007431888370774686,
      "clip_ratio/low_min": 3.176051859554718e-05,
      "clip_ratio/region_mean": 0.0017013474862324074,
      "epoch": 0.06486650450040542,
      "grad_norm": 0.11056634038686752,
      "learning_rate": 5e-07,
      "loss": -0.0258,
      "step": 695
    },
    {
      "clip_ratio/high_max": 0.002021324042289052,
      "clip_ratio/high_mean": 0.0008336798673553858,
      "clip_ratio/low_mean": 0.0008159998196788365,
      "clip_ratio/low_min": 8.594794326199917e-05,
      "clip_ratio/region_mean": 0.0016496796961291693,
      "epoch": 0.064959837600406,
      "grad_norm": 0.11249818652868271,
      "learning_rate": 5e-07,
      "loss": 0.041,
      "step": 696
    },
    {
      "clip_ratio/high_max": 0.0024924349127104506,
      "clip_ratio/high_mean": 0.0010846188197319862,
      "clip_ratio/low_mean": 0.000819607808807632,
      "clip_ratio/low_min": 6.513154767162632e-05,
      "clip_ratio/region_mean": 0.001904226628539618,
      "epoch": 0.06505317070040659,
      "grad_norm": 0.11291012167930603,
      "learning_rate": 5e-07,
      "loss": 0.0061,
      "step": 697
    },
    {
      "clip_ratio/high_max": 0.0021659046469721943,
      "clip_ratio/high_mean": 0.0008999840647447854,
      "clip_ratio/low_mean": 0.0008204862569982652,
      "clip_ratio/low_min": 2.6766736482386477e-05,
      "clip_ratio/region_mean": 0.0017204703617608175,
      "epoch": 0.06514650380040717,
      "grad_norm": 0.11113911122083664,
      "learning_rate": 5e-07,
      "loss": 0.0322,
      "step": 698
    },
    {
      "clip_ratio/high_max": 0.001971554280316923,
      "clip_ratio/high_mean": 0.0008443289789283881,
      "clip_ratio/low_mean": 0.0009437962544325273,
      "clip_ratio/low_min": 7.867658860050142e-05,
      "clip_ratio/region_mean": 0.0017881252570077777,
      "epoch": 0.06523983690040774,
      "grad_norm": 0.1156892478466034,
      "learning_rate": 5e-07,
      "loss": 0.0072,
      "step": 699
    },
    {
      "clip_ratio/high_max": 0.0024155406426871195,
      "clip_ratio/high_mean": 0.0008890275385056157,
      "clip_ratio/low_mean": 0.0008121841838146793,
      "clip_ratio/low_min": 6.011136974848341e-05,
      "clip_ratio/region_mean": 0.0017012116877594963,
      "epoch": 0.06533317000040834,
      "grad_norm": 0.1047322154045105,
      "learning_rate": 5e-07,
      "loss": 0.043,
      "step": 700
    },
    {
      "clip_ratio/high_max": 0.0022069426559028216,
      "clip_ratio/high_mean": 0.0009176543317153119,
      "clip_ratio/low_mean": 0.0008641981003165711,
      "clip_ratio/low_min": 7.837684961486957e-05,
      "clip_ratio/region_mean": 0.0017818524138419889,
      "epoch": 0.06542650310040891,
      "grad_norm": 0.12621276080608368,
      "learning_rate": 5e-07,
      "loss": -0.0137,
      "step": 701
    },
    {
      "clip_ratio/high_max": 0.0021517826171475463,
      "clip_ratio/high_mean": 0.0009599161039659521,
      "clip_ratio/low_mean": 0.0009521636620775098,
      "clip_ratio/low_min": 9.45555202633841e-05,
      "clip_ratio/region_mean": 0.0019120797733194195,
      "epoch": 0.06551983620040949,
      "grad_norm": 0.11046454310417175,
      "learning_rate": 5e-07,
      "loss": 0.0186,
      "step": 702
    },
    {
      "clip_ratio/high_max": 0.0018759259255602956,
      "clip_ratio/high_mean": 0.0008053126894083107,
      "clip_ratio/low_mean": 0.0008923206441977527,
      "clip_ratio/low_min": 0.00010232877139060292,
      "clip_ratio/region_mean": 0.0016976333281490952,
      "epoch": 0.06561316930041008,
      "grad_norm": 0.11215470731258392,
      "learning_rate": 5e-07,
      "loss": 0.0172,
      "step": 703
    },
    {
      "clip_ratio/high_max": 0.002103148915921338,
      "clip_ratio/high_mean": 0.0008038243431656156,
      "clip_ratio/low_mean": 0.0010180475910601672,
      "clip_ratio/low_min": 6.234207285160664e-05,
      "clip_ratio/region_mean": 0.0018218719415017404,
      "epoch": 0.06570650240041066,
      "grad_norm": 0.10809242725372314,
      "learning_rate": 5e-07,
      "loss": 0.045,
      "step": 704
    },
    {
      "clip_ratio/high_max": 0.0018569438434496988,
      "clip_ratio/high_mean": 0.0007561774455098202,
      "clip_ratio/low_mean": 0.0008859956806190894,
      "clip_ratio/low_min": 0.00010405728426121641,
      "clip_ratio/region_mean": 0.0016421731270384043,
      "epoch": 0.06579983550041126,
      "grad_norm": 0.12679092586040497,
      "learning_rate": 5e-07,
      "loss": 0.0304,
      "step": 705
    },
    {
      "clip_ratio/high_max": 0.0020830710127484053,
      "clip_ratio/high_mean": 0.0009269800611946266,
      "clip_ratio/low_mean": 0.0010530215367907658,
      "clip_ratio/low_min": 7.209750765468925e-05,
      "clip_ratio/region_mean": 0.0019800015434157103,
      "epoch": 0.06589316860041183,
      "grad_norm": 0.11899759620428085,
      "learning_rate": 5e-07,
      "loss": 0.0198,
      "step": 706
    },
    {
      "clip_ratio/high_max": 0.00223324925173074,
      "clip_ratio/high_mean": 0.0008007913202163763,
      "clip_ratio/low_mean": 0.0009762423869688064,
      "clip_ratio/low_min": 9.634405796532519e-05,
      "clip_ratio/region_mean": 0.0017770336926332675,
      "epoch": 0.06598650170041241,
      "grad_norm": 0.1105983704328537,
      "learning_rate": 5e-07,
      "loss": 0.0389,
      "step": 707
    },
    {
      "clip_ratio/high_max": 0.0019666205298563,
      "clip_ratio/high_mean": 0.0008221692132792668,
      "clip_ratio/low_mean": 0.0009943235581886256,
      "clip_ratio/low_min": 6.0440260313043837e-05,
      "clip_ratio/region_mean": 0.0018164927532779984,
      "epoch": 0.066079834800413,
      "grad_norm": 0.11207378655672073,
      "learning_rate": 5e-07,
      "loss": 0.0282,
      "step": 708
    },
    {
      "clip_ratio/high_max": 0.0022546913096448407,
      "clip_ratio/high_mean": 0.0009291167443734594,
      "clip_ratio/low_mean": 0.000813234046290745,
      "clip_ratio/low_min": 1.6037978639360517e-05,
      "clip_ratio/region_mean": 0.0017423507961211726,
      "epoch": 0.06617316790041358,
      "grad_norm": 0.10835693031549454,
      "learning_rate": 5e-07,
      "loss": -0.0194,
      "step": 709
    },
    {
      "clip_ratio/high_max": 0.0023029058284009807,
      "clip_ratio/high_mean": 0.0009861037869995926,
      "clip_ratio/low_mean": 0.0009026679035741836,
      "clip_ratio/low_min": 0.00013114175999362487,
      "clip_ratio/region_mean": 0.0018887717087636702,
      "epoch": 0.06626650100041416,
      "grad_norm": 0.11400746554136276,
      "learning_rate": 5e-07,
      "loss": -0.0181,
      "step": 710
    },
    {
      "clip_ratio/high_max": 0.0022471085794677492,
      "clip_ratio/high_mean": 0.0008814283137326129,
      "clip_ratio/low_mean": 0.0009900184832076775,
      "clip_ratio/low_min": 9.867964217846747e-05,
      "clip_ratio/region_mean": 0.0018714468460530043,
      "epoch": 0.06635983410041475,
      "grad_norm": 0.11515853554010391,
      "learning_rate": 5e-07,
      "loss": 0.0241,
      "step": 711
    },
    {
      "clip_ratio/high_max": 0.0019308295741211623,
      "clip_ratio/high_mean": 0.0009089938084798632,
      "clip_ratio/low_mean": 0.0011827526268461952,
      "clip_ratio/low_min": 0.0002203230810664536,
      "clip_ratio/region_mean": 0.0020917464935337193,
      "epoch": 0.06645316720041533,
      "grad_norm": 0.12334103137254715,
      "learning_rate": 5e-07,
      "loss": 0.0648,
      "step": 712
    },
    {
      "clip_ratio/high_max": 0.0020813882765651215,
      "clip_ratio/high_mean": 0.0008630873944639461,
      "clip_ratio/low_mean": 0.0008797245791356545,
      "clip_ratio/low_min": 7.463501697202446e-05,
      "clip_ratio/region_mean": 0.0017428120409022085,
      "epoch": 0.06654650030041591,
      "grad_norm": 0.10970184952020645,
      "learning_rate": 5e-07,
      "loss": 0.0115,
      "step": 713
    },
    {
      "clip_ratio/high_max": 0.0017674471673672087,
      "clip_ratio/high_mean": 0.0007523921995016281,
      "clip_ratio/low_mean": 0.0009848945701378398,
      "clip_ratio/low_min": 6.657680387434084e-05,
      "clip_ratio/region_mean": 0.0017372867150697857,
      "epoch": 0.0666398334004165,
      "grad_norm": 0.1115695908665657,
      "learning_rate": 5e-07,
      "loss": 0.0518,
      "step": 714
    },
    {
      "clip_ratio/high_max": 0.002121110934240278,
      "clip_ratio/high_mean": 0.0010082055487146135,
      "clip_ratio/low_mean": 0.0011230098389205523,
      "clip_ratio/low_min": 0.00014813711277383845,
      "clip_ratio/region_mean": 0.00213121540582506,
      "epoch": 0.06673316650041708,
      "grad_norm": 0.10983452200889587,
      "learning_rate": 5e-07,
      "loss": 0.017,
      "step": 715
    },
    {
      "clip_ratio/high_max": 0.002313708737347042,
      "clip_ratio/high_mean": 0.000971915913396515,
      "clip_ratio/low_mean": 0.0009760069006006233,
      "clip_ratio/low_min": 0.000139896001201123,
      "clip_ratio/region_mean": 0.0019479227848933078,
      "epoch": 0.06682649960041767,
      "grad_norm": 0.10416987538337708,
      "learning_rate": 5e-07,
      "loss": 0.0126,
      "step": 716
    },
    {
      "clip_ratio/high_max": 0.0022278726173681207,
      "clip_ratio/high_mean": 0.0009007277221826371,
      "clip_ratio/low_mean": 0.0009645108439144678,
      "clip_ratio/low_min": 8.445020466751885e-05,
      "clip_ratio/region_mean": 0.0018652385551831685,
      "epoch": 0.06691983270041825,
      "grad_norm": 0.10987719893455505,
      "learning_rate": 5e-07,
      "loss": 0.057,
      "step": 717
    },
    {
      "clip_ratio/high_max": 0.002132165649527451,
      "clip_ratio/high_mean": 0.0008294267390738241,
      "clip_ratio/low_mean": 0.0008615590704721399,
      "clip_ratio/low_min": 7.814559830876533e-05,
      "clip_ratio/region_mean": 0.0016909857877180912,
      "epoch": 0.06701316580041883,
      "grad_norm": 0.11038823425769806,
      "learning_rate": 5e-07,
      "loss": 0.0068,
      "step": 718
    },
    {
      "clip_ratio/high_max": 0.0018862839096982498,
      "clip_ratio/high_mean": 0.0007728619657427771,
      "clip_ratio/low_mean": 0.0008678057365614222,
      "clip_ratio/low_min": 8.289179459097795e-05,
      "clip_ratio/region_mean": 0.0016406676659244113,
      "epoch": 0.06710649890041942,
      "grad_norm": 0.1525305211544037,
      "learning_rate": 5e-07,
      "loss": 0.048,
      "step": 719
    },
    {
      "clip_ratio/high_max": 0.0022216510624275543,
      "clip_ratio/high_mean": 0.0009850036185525823,
      "clip_ratio/low_mean": 0.00100019797537243,
      "clip_ratio/low_min": 0.00011329332119203173,
      "clip_ratio/region_mean": 0.001985201546631288,
      "epoch": 0.06719983200042,
      "grad_norm": 0.12451259791851044,
      "learning_rate": 5e-07,
      "loss": -0.0183,
      "step": 720
    },
    {
      "clip_ratio/high_max": 0.0018885620957007632,
      "clip_ratio/high_mean": 0.0007302048379642656,
      "clip_ratio/low_mean": 0.0009247451744158752,
      "clip_ratio/low_min": 7.735648432571907e-05,
      "clip_ratio/region_mean": 0.0016549499923712574,
      "epoch": 0.06729316510042058,
      "grad_norm": 0.11739130318164825,
      "learning_rate": 5e-07,
      "loss": 0.057,
      "step": 721
    },
    {
      "clip_ratio/high_max": 0.0019829103257507086,
      "clip_ratio/high_mean": 0.0008247784207924269,
      "clip_ratio/low_mean": 0.0010733246890595183,
      "clip_ratio/low_min": 0.00015013319261925062,
      "clip_ratio/region_mean": 0.0018981031098519452,
      "epoch": 0.06738649820042117,
      "grad_norm": 0.11459755152463913,
      "learning_rate": 5e-07,
      "loss": 0.0725,
      "step": 722
    },
    {
      "clip_ratio/high_max": 0.0022664967909804545,
      "clip_ratio/high_mean": 0.0009759700733411592,
      "clip_ratio/low_mean": 0.0009432390506844968,
      "clip_ratio/low_min": 0.00013494187078322284,
      "clip_ratio/region_mean": 0.0019192091058357619,
      "epoch": 0.06747983130042175,
      "grad_norm": 0.11980430036783218,
      "learning_rate": 5e-07,
      "loss": 0.0337,
      "step": 723
    },
    {
      "clip_ratio/high_max": 0.002223681498435326,
      "clip_ratio/high_mean": 0.0008920405707613099,
      "clip_ratio/low_mean": 0.0008308537471748423,
      "clip_ratio/low_min": 7.957197522046044e-05,
      "clip_ratio/region_mean": 0.0017228943252121098,
      "epoch": 0.06757316440042234,
      "grad_norm": 0.10307474434375763,
      "learning_rate": 5e-07,
      "loss": 0.0152,
      "step": 724
    },
    {
      "clip_ratio/high_max": 0.00216013693716377,
      "clip_ratio/high_mean": 0.0009967190017050598,
      "clip_ratio/low_mean": 0.0009061263845069334,
      "clip_ratio/low_min": 5.7922175983549096e-05,
      "clip_ratio/region_mean": 0.0019028453752980568,
      "epoch": 0.06766649750042292,
      "grad_norm": 0.11520454287528992,
      "learning_rate": 5e-07,
      "loss": -0.0029,
      "step": 725
    },
    {
      "clip_ratio/high_max": 0.0023466428465326317,
      "clip_ratio/high_mean": 0.0009231120366166579,
      "clip_ratio/low_mean": 0.0009730095753184287,
      "clip_ratio/low_min": 7.927647675387561e-05,
      "clip_ratio/region_mean": 0.0018961216192110442,
      "epoch": 0.0677598306004235,
      "grad_norm": 0.11972714215517044,
      "learning_rate": 5e-07,
      "loss": 0.0484,
      "step": 726
    },
    {
      "clip_ratio/high_max": 0.0023134082366595976,
      "clip_ratio/high_mean": 0.000857640845424612,
      "clip_ratio/low_mean": 0.0010178408701904118,
      "clip_ratio/low_min": 5.796255709356046e-05,
      "clip_ratio/region_mean": 0.0018754816992441192,
      "epoch": 0.06785316370042409,
      "grad_norm": 0.10851030796766281,
      "learning_rate": 5e-07,
      "loss": 0.0645,
      "step": 727
    },
    {
      "clip_ratio/high_max": 0.0020250310735718813,
      "clip_ratio/high_mean": 0.0009260758706659544,
      "clip_ratio/low_mean": 0.0009149858324235538,
      "clip_ratio/low_min": 8.435330892098136e-05,
      "clip_ratio/region_mean": 0.0018410617121844552,
      "epoch": 0.06794649680042467,
      "grad_norm": 0.11414031684398651,
      "learning_rate": 5e-07,
      "loss": 0.0115,
      "step": 728
    },
    {
      "clip_ratio/high_max": 0.002340531151276082,
      "clip_ratio/high_mean": 0.0009826086861721706,
      "clip_ratio/low_mean": 0.0009357144372188486,
      "clip_ratio/low_min": 0.0001618077567400178,
      "clip_ratio/region_mean": 0.0019183231415809132,
      "epoch": 0.06803982990042524,
      "grad_norm": 0.11043746024370193,
      "learning_rate": 5e-07,
      "loss": 0.024,
      "step": 729
    },
    {
      "clip_ratio/high_max": 0.0018936037668026984,
      "clip_ratio/high_mean": 0.0007687169818382245,
      "clip_ratio/low_mean": 0.0008812412324914476,
      "clip_ratio/low_min": 2.8257516532903537e-05,
      "clip_ratio/region_mean": 0.0016499582343385555,
      "epoch": 0.06813316300042584,
      "grad_norm": 0.10326585918664932,
      "learning_rate": 5e-07,
      "loss": 0.0579,
      "step": 730
    },
    {
      "clip_ratio/high_max": 0.0025597371204639785,
      "clip_ratio/high_mean": 0.0010296425971318968,
      "clip_ratio/low_mean": 0.0009586239757481962,
      "clip_ratio/low_min": 6.799057155149058e-05,
      "clip_ratio/region_mean": 0.001988266594707966,
      "epoch": 0.06822649610042641,
      "grad_norm": 0.1191912591457367,
      "learning_rate": 5e-07,
      "loss": 0.0091,
      "step": 731
    },
    {
      "clip_ratio/high_max": 0.0023023429239401594,
      "clip_ratio/high_mean": 0.000987722343779751,
      "clip_ratio/low_mean": 0.0008645568559586536,
      "clip_ratio/low_min": 4.979398727300577e-05,
      "clip_ratio/region_mean": 0.0018522791942814365,
      "epoch": 0.06831982920042699,
      "grad_norm": 0.12995244562625885,
      "learning_rate": 5e-07,
      "loss": 0.0129,
      "step": 732
    },
    {
      "clip_ratio/high_max": 0.002265961156808771,
      "clip_ratio/high_mean": 0.0008809383616608102,
      "clip_ratio/low_mean": 0.0009997923207265558,
      "clip_ratio/low_min": 9.753725680639036e-05,
      "clip_ratio/region_mean": 0.0018807306623784825,
      "epoch": 0.06841316230042759,
      "grad_norm": 0.11845138669013977,
      "learning_rate": 5e-07,
      "loss": 0.0488,
      "step": 733
    },
    {
      "clip_ratio/high_max": 0.0019779475987888873,
      "clip_ratio/high_mean": 0.0008403620031458559,
      "clip_ratio/low_mean": 0.0009304465711466037,
      "clip_ratio/low_min": 9.149796551355394e-05,
      "clip_ratio/region_mean": 0.0017708086015773006,
      "epoch": 0.06850649540042816,
      "grad_norm": 0.11814996600151062,
      "learning_rate": 5e-07,
      "loss": 0.024,
      "step": 734
    },
    {
      "clip_ratio/high_max": 0.0020171826326986775,
      "clip_ratio/high_mean": 0.0008189284872059943,
      "clip_ratio/low_mean": 0.0008988688477984397,
      "clip_ratio/low_min": 8.409410520471283e-05,
      "clip_ratio/region_mean": 0.0017177972731587943,
      "epoch": 0.06859982850042876,
      "grad_norm": 0.113103486597538,
      "learning_rate": 5e-07,
      "loss": 0.0913,
      "step": 735
    },
    {
      "clip_ratio/high_max": 0.0016854338537086733,
      "clip_ratio/high_mean": 0.0008106194127321942,
      "clip_ratio/low_mean": 0.0009069006227946375,
      "clip_ratio/low_min": 2.7508642233442515e-05,
      "clip_ratio/region_mean": 0.0017175200700876303,
      "epoch": 0.06869316160042933,
      "grad_norm": 0.10749461501836777,
      "learning_rate": 5e-07,
      "loss": 0.0248,
      "step": 736
    },
    {
      "clip_ratio/high_max": 0.0019845776769216172,
      "clip_ratio/high_mean": 0.0008279776484414469,
      "clip_ratio/low_mean": 0.0009223065389960539,
      "clip_ratio/low_min": 0.00010034641491074581,
      "clip_ratio/region_mean": 0.0017502841510577127,
      "epoch": 0.06878649470042991,
      "grad_norm": 0.110279381275177,
      "learning_rate": 5e-07,
      "loss": 0.0288,
      "step": 737
    },
    {
      "clip_ratio/high_max": 0.0021054427343187854,
      "clip_ratio/high_mean": 0.00083399607501633,
      "clip_ratio/low_mean": 0.0009590369227225892,
      "clip_ratio/low_min": 8.627423812868074e-05,
      "clip_ratio/region_mean": 0.0017930329995579086,
      "epoch": 0.0688798278004305,
      "grad_norm": 0.11164763569831848,
      "learning_rate": 5e-07,
      "loss": 0.0784,
      "step": 738
    },
    {
      "clip_ratio/high_max": 0.0020689887751359493,
      "clip_ratio/high_mean": 0.0007828126363165211,
      "clip_ratio/low_mean": 0.0010358228646509815,
      "clip_ratio/low_min": 6.447151099564508e-05,
      "clip_ratio/region_mean": 0.0018186355155194178,
      "epoch": 0.06897316090043108,
      "grad_norm": 0.10840458422899246,
      "learning_rate": 5e-07,
      "loss": 0.0464,
      "step": 739
    },
    {
      "clip_ratio/high_max": 0.0021190103434491903,
      "clip_ratio/high_mean": 0.0009019453063956462,
      "clip_ratio/low_mean": 0.0009600445191608742,
      "clip_ratio/low_min": 9.731599539009039e-05,
      "clip_ratio/region_mean": 0.001861989832832478,
      "epoch": 0.06906649400043166,
      "grad_norm": 0.11219488084316254,
      "learning_rate": 5e-07,
      "loss": 0.0344,
      "step": 740
    },
    {
      "clip_ratio/high_max": 0.002113484682922717,
      "clip_ratio/high_mean": 0.0008357803308172151,
      "clip_ratio/low_mean": 0.0008120345773932058,
      "clip_ratio/low_min": 7.627108334418153e-05,
      "clip_ratio/region_mean": 0.0016478149045724422,
      "epoch": 0.06915982710043225,
      "grad_norm": 0.11780732870101929,
      "learning_rate": 5e-07,
      "loss": 0.0578,
      "step": 741
    },
    {
      "clip_ratio/high_max": 0.002216027660324471,
      "clip_ratio/high_mean": 0.0009814084296522196,
      "clip_ratio/low_mean": 0.0007808681821188657,
      "clip_ratio/low_min": 3.517523600748973e-05,
      "clip_ratio/region_mean": 0.0017622765954001807,
      "epoch": 0.06925316020043283,
      "grad_norm": 0.1162053719162941,
      "learning_rate": 5e-07,
      "loss": 0.0024,
      "step": 742
    },
    {
      "clip_ratio/high_max": 0.001999465166591108,
      "clip_ratio/high_mean": 0.0008781546894169878,
      "clip_ratio/low_mean": 0.0008984939759102417,
      "clip_ratio/low_min": 9.369112922286149e-05,
      "clip_ratio/region_mean": 0.0017766486707841977,
      "epoch": 0.06934649330043341,
      "grad_norm": 0.11652964353561401,
      "learning_rate": 5e-07,
      "loss": 0.0095,
      "step": 743
    },
    {
      "clip_ratio/high_max": 0.002323726104805246,
      "clip_ratio/high_mean": 0.0009296448079112452,
      "clip_ratio/low_mean": 0.0011411141913413303,
      "clip_ratio/low_min": 0.00010089271017932333,
      "clip_ratio/region_mean": 0.0020707589501398616,
      "epoch": 0.069439826400434,
      "grad_norm": 0.11405614763498306,
      "learning_rate": 5e-07,
      "loss": 0.057,
      "step": 744
    },
    {
      "clip_ratio/high_max": 0.0020231358321325388,
      "clip_ratio/high_mean": 0.0008423730378126493,
      "clip_ratio/low_mean": 0.0008822098334348993,
      "clip_ratio/low_min": 7.27115284462343e-05,
      "clip_ratio/region_mean": 0.0017245828785235062,
      "epoch": 0.06953315950043458,
      "grad_norm": 0.10313057899475098,
      "learning_rate": 5e-07,
      "loss": 0.0016,
      "step": 745
    },
    {
      "clip_ratio/high_max": 0.0024779813538771123,
      "clip_ratio/high_mean": 0.0009840729071584065,
      "clip_ratio/low_mean": 0.0008266428521892522,
      "clip_ratio/low_min": 6.029406631569145e-05,
      "clip_ratio/region_mean": 0.0018107157229678705,
      "epoch": 0.06962649260043517,
      "grad_norm": 0.11714205890893936,
      "learning_rate": 5e-07,
      "loss": -0.0015,
      "step": 746
    },
    {
      "clip_ratio/high_max": 0.0019277980318292975,
      "clip_ratio/high_mean": 0.0008086534235189902,
      "clip_ratio/low_mean": 0.0009532089188724058,
      "clip_ratio/low_min": 6.46825646981597e-05,
      "clip_ratio/region_mean": 0.001761862396961078,
      "epoch": 0.06971982570043575,
      "grad_norm": 0.11117918789386749,
      "learning_rate": 5e-07,
      "loss": 0.0118,
      "step": 747
    },
    {
      "clip_ratio/high_max": 0.002086143591441214,
      "clip_ratio/high_mean": 0.0008408040703216102,
      "clip_ratio/low_mean": 0.0009099971648538485,
      "clip_ratio/low_min": 0.00011239764535275754,
      "clip_ratio/region_mean": 0.0017508011951576918,
      "epoch": 0.06981315880043633,
      "grad_norm": 0.11161021143198013,
      "learning_rate": 5e-07,
      "loss": 0.0007,
      "step": 748
    },
    {
      "clip_ratio/high_max": 0.0017622925188334193,
      "clip_ratio/high_mean": 0.000695062766681076,
      "clip_ratio/low_mean": 0.0009387122445332352,
      "clip_ratio/low_min": 8.393433108722093e-05,
      "clip_ratio/region_mean": 0.0016337750566890463,
      "epoch": 0.06990649190043692,
      "grad_norm": 0.11209597438573837,
      "learning_rate": 5e-07,
      "loss": 0.0582,
      "step": 749
    },
    {
      "clip_ratio/high_max": 0.0026035756745841354,
      "clip_ratio/high_mean": 0.0009115385892073391,
      "clip_ratio/low_mean": 0.0009325514984084293,
      "clip_ratio/low_min": 6.081886567699257e-05,
      "clip_ratio/region_mean": 0.0018440900530549698,
      "epoch": 0.0699998250004375,
      "grad_norm": 0.11102450639009476,
      "learning_rate": 5e-07,
      "loss": 0.0147,
      "step": 750
    },
    {
      "clip_ratio/high_max": 0.0018120498862117529,
      "clip_ratio/high_mean": 0.0008698004912730539,
      "clip_ratio/low_mean": 0.0009115176362683997,
      "clip_ratio/low_min": 7.851834925531875e-05,
      "clip_ratio/region_mean": 0.0017813181402743794,
      "epoch": 0.07009315810043808,
      "grad_norm": 0.11229971796274185,
      "learning_rate": 5e-07,
      "loss": 0.0259,
      "step": 751
    },
    {
      "clip_ratio/high_max": 0.0020076128057553433,
      "clip_ratio/high_mean": 0.0009598319338692818,
      "clip_ratio/low_mean": 0.0008399911766900914,
      "clip_ratio/low_min": 7.388665380858583e-05,
      "clip_ratio/region_mean": 0.0017998230941884685,
      "epoch": 0.07018649120043867,
      "grad_norm": 0.11797557771205902,
      "learning_rate": 5e-07,
      "loss": -0.0213,
      "step": 752
    },
    {
      "clip_ratio/high_max": 0.0023966620574356057,
      "clip_ratio/high_mean": 0.000976962641288992,
      "clip_ratio/low_mean": 0.00099906413743156,
      "clip_ratio/low_min": 0.00014342955364554655,
      "clip_ratio/region_mean": 0.001976026745978743,
      "epoch": 0.07027982430043925,
      "grad_norm": 0.1256706714630127,
      "learning_rate": 5e-07,
      "loss": 0.0128,
      "step": 753
    },
    {
      "clip_ratio/high_max": 0.0020591599713952746,
      "clip_ratio/high_mean": 0.0008582592618040508,
      "clip_ratio/low_mean": 0.0009735172752698418,
      "clip_ratio/low_min": 0.00012611555484909331,
      "clip_ratio/region_mean": 0.001831776557082776,
      "epoch": 0.07037315740043983,
      "grad_norm": 0.10629694908857346,
      "learning_rate": 5e-07,
      "loss": 0.0212,
      "step": 754
    },
    {
      "clip_ratio/high_max": 0.002023187989834696,
      "clip_ratio/high_mean": 0.0009565332238707924,
      "clip_ratio/low_mean": 0.000926334289033548,
      "clip_ratio/low_min": 0.00012514190257206792,
      "clip_ratio/region_mean": 0.0018828674947144464,
      "epoch": 0.07046649050044042,
      "grad_norm": 0.10795219242572784,
      "learning_rate": 5e-07,
      "loss": 0.0061,
      "step": 755
    },
    {
      "clip_ratio/high_max": 0.0025235416396753863,
      "clip_ratio/high_mean": 0.0008975822365755448,
      "clip_ratio/low_mean": 0.0008237215488406946,
      "clip_ratio/low_min": 0.00012261925348866498,
      "clip_ratio/region_mean": 0.0017213038008776493,
      "epoch": 0.070559823600441,
      "grad_norm": 0.11242425441741943,
      "learning_rate": 5e-07,
      "loss": 0.0252,
      "step": 756
    },
    {
      "clip_ratio/high_max": 0.0023788823527866043,
      "clip_ratio/high_mean": 0.0009274905114580179,
      "clip_ratio/low_mean": 0.0011027022264897823,
      "clip_ratio/low_min": 6.168469190015458e-05,
      "clip_ratio/region_mean": 0.002030192692473065,
      "epoch": 0.07065315670044159,
      "grad_norm": 0.13886548578739166,
      "learning_rate": 5e-07,
      "loss": 0.0075,
      "step": 757
    },
    {
      "clip_ratio/high_max": 0.002200168808485614,
      "clip_ratio/high_mean": 0.0008804852495813975,
      "clip_ratio/low_mean": 0.0009843161678873003,
      "clip_ratio/low_min": 0.0001042630410665879,
      "clip_ratio/region_mean": 0.0018648014374775812,
      "epoch": 0.07074648980044217,
      "grad_norm": 0.10639011114835739,
      "learning_rate": 5e-07,
      "loss": 0.0415,
      "step": 758
    },
    {
      "clip_ratio/high_max": 0.0019657935154100414,
      "clip_ratio/high_mean": 0.0009035526491061319,
      "clip_ratio/low_mean": 0.0009017718348331982,
      "clip_ratio/low_min": 2.5840957277978305e-05,
      "clip_ratio/region_mean": 0.0018053245003102347,
      "epoch": 0.07083982290044274,
      "grad_norm": 0.11683685332536697,
      "learning_rate": 5e-07,
      "loss": -0.0011,
      "step": 759
    },
    {
      "clip_ratio/high_max": 0.001986908529943321,
      "clip_ratio/high_mean": 0.0007822542575013358,
      "clip_ratio/low_mean": 0.0010789981115522096,
      "clip_ratio/low_min": 0.00010631158693286125,
      "clip_ratio/region_mean": 0.0018612523999763653,
      "epoch": 0.07093315600044334,
      "grad_norm": 0.1096036359667778,
      "learning_rate": 5e-07,
      "loss": 0.0419,
      "step": 760
    },
    {
      "clip_ratio/high_max": 0.002314082099474035,
      "clip_ratio/high_mean": 0.0009609743610781152,
      "clip_ratio/low_mean": 0.0008289976467494853,
      "clip_ratio/low_min": 8.495227575622266e-05,
      "clip_ratio/region_mean": 0.0017899720041896217,
      "epoch": 0.07102648910044392,
      "grad_norm": 0.11152461916208267,
      "learning_rate": 5e-07,
      "loss": 0.038,
      "step": 761
    },
    {
      "clip_ratio/high_max": 0.002542705748055596,
      "clip_ratio/high_mean": 0.0009984868083847687,
      "clip_ratio/low_mean": 0.0009162539590761298,
      "clip_ratio/low_min": 0.00016853611487022135,
      "clip_ratio/region_mean": 0.001914740729262121,
      "epoch": 0.0711198222004445,
      "grad_norm": 0.10254882276058197,
      "learning_rate": 5e-07,
      "loss": 0.0187,
      "step": 762
    },
    {
      "clip_ratio/high_max": 0.002084357416606508,
      "clip_ratio/high_mean": 0.0008702963605173863,
      "clip_ratio/low_mean": 0.0009515626588836312,
      "clip_ratio/low_min": 1.5060240912134759e-05,
      "clip_ratio/region_mean": 0.0018218590266769752,
      "epoch": 0.07121315530044509,
      "grad_norm": 0.11468832939863205,
      "learning_rate": 5e-07,
      "loss": 0.0472,
      "step": 763
    },
    {
      "clip_ratio/high_max": 0.002070824044494657,
      "clip_ratio/high_mean": 0.0008766416476646555,
      "clip_ratio/low_mean": 0.0009986656878027134,
      "clip_ratio/low_min": 5.5725115998939145e-05,
      "clip_ratio/region_mean": 0.0018753073527477682,
      "epoch": 0.07130648840044566,
      "grad_norm": 0.12000647187232971,
      "learning_rate": 5e-07,
      "loss": 0.0378,
      "step": 764
    },
    {
      "clip_ratio/high_max": 0.0023273780243471265,
      "clip_ratio/high_mean": 0.0009267184759664815,
      "clip_ratio/low_mean": 0.0008972997493401635,
      "clip_ratio/low_min": 2.8005360945826396e-05,
      "clip_ratio/region_mean": 0.0018240182034787722,
      "epoch": 0.07139982150044624,
      "grad_norm": 0.11809422820806503,
      "learning_rate": 5e-07,
      "loss": 0.0424,
      "step": 765
    },
    {
      "clip_ratio/high_max": 0.0019663487109937705,
      "clip_ratio/high_mean": 0.0008518733156961389,
      "clip_ratio/low_mean": 0.0008566277556383284,
      "clip_ratio/low_min": 4.077658013557084e-05,
      "clip_ratio/region_mean": 0.0017085010404116474,
      "epoch": 0.07149315460044683,
      "grad_norm": 0.11647383868694305,
      "learning_rate": 5e-07,
      "loss": 0.0317,
      "step": 766
    },
    {
      "clip_ratio/high_max": 0.002164046101825079,
      "clip_ratio/high_mean": 0.0008618470037617953,
      "clip_ratio/low_mean": 0.0008611358534835745,
      "clip_ratio/low_min": 1.2247697668499313e-05,
      "clip_ratio/region_mean": 0.0017229828554263804,
      "epoch": 0.07158648770044741,
      "grad_norm": 0.12217538803815842,
      "learning_rate": 5e-07,
      "loss": -0.0229,
      "step": 767
    },
    {
      "clip_ratio/high_max": 0.001829546243243385,
      "clip_ratio/high_mean": 0.0007616493694513338,
      "clip_ratio/low_mean": 0.0011009185582224745,
      "clip_ratio/low_min": 9.208179926645244e-05,
      "clip_ratio/region_mean": 0.0018625679658725858,
      "epoch": 0.071679820800448,
      "grad_norm": 0.12740756571292877,
      "learning_rate": 5e-07,
      "loss": 0.0875,
      "step": 768
    },
    {
      "clip_ratio/high_max": 0.0022229137139220256,
      "clip_ratio/high_mean": 0.0009388877369929105,
      "clip_ratio/low_mean": 0.0009327802581537981,
      "clip_ratio/low_min": 4.865577102464158e-05,
      "clip_ratio/region_mean": 0.0018716679769568145,
      "epoch": 0.07177315390044858,
      "grad_norm": 0.1223924458026886,
      "learning_rate": 5e-07,
      "loss": 0.0596,
      "step": 769
    },
    {
      "clip_ratio/high_max": 0.002135904418537393,
      "clip_ratio/high_mean": 0.0009304071936639957,
      "clip_ratio/low_mean": 0.0009152649436146021,
      "clip_ratio/low_min": 0.00011364608417352429,
      "clip_ratio/region_mean": 0.0018456721663824283,
      "epoch": 0.07186648700044916,
      "grad_norm": 0.11191757023334503,
      "learning_rate": 5e-07,
      "loss": -0.0161,
      "step": 770
    },
    {
      "clip_ratio/high_max": 0.0021653922012774274,
      "clip_ratio/high_mean": 0.0009205325040966272,
      "clip_ratio/low_mean": 0.000976876527602144,
      "clip_ratio/low_min": 8.994569907372352e-05,
      "clip_ratio/region_mean": 0.0018974090562551282,
      "epoch": 0.07195982010044975,
      "grad_norm": 0.1176324337720871,
      "learning_rate": 5e-07,
      "loss": 0.0246,
      "step": 771
    },
    {
      "clip_ratio/high_max": 0.0019501256101648323,
      "clip_ratio/high_mean": 0.0008025585557334125,
      "clip_ratio/low_mean": 0.0008508293958584545,
      "clip_ratio/low_min": 8.539124974049628e-05,
      "clip_ratio/region_mean": 0.0016533879388589412,
      "epoch": 0.07205315320045033,
      "grad_norm": 0.11206095665693283,
      "learning_rate": 5e-07,
      "loss": 0.0499,
      "step": 772
    },
    {
      "clip_ratio/high_max": 0.002128455183992628,
      "clip_ratio/high_mean": 0.0008508363007422304,
      "clip_ratio/low_mean": 0.0009166184063360561,
      "clip_ratio/low_min": 4.444891783350613e-05,
      "clip_ratio/region_mean": 0.0017674547125352547,
      "epoch": 0.07214648630045091,
      "grad_norm": 0.1018589586019516,
      "learning_rate": 5e-07,
      "loss": 0.0185,
      "step": 773
    },
    {
      "clip_ratio/high_max": 0.0019496753884595819,
      "clip_ratio/high_mean": 0.0008139296533045126,
      "clip_ratio/low_mean": 0.0006899490326759405,
      "clip_ratio/low_min": 5.000038436264731e-05,
      "clip_ratio/region_mean": 0.0015038786877994426,
      "epoch": 0.0722398194004515,
      "grad_norm": 0.1054258719086647,
      "learning_rate": 5e-07,
      "loss": 0.0114,
      "step": 774
    },
    {
      "clip_ratio/high_max": 0.0018362947084824555,
      "clip_ratio/high_mean": 0.0007738448130112374,
      "clip_ratio/low_mean": 0.0010205346407019533,
      "clip_ratio/low_min": 0.00014071321493247524,
      "clip_ratio/region_mean": 0.0017943794518942013,
      "epoch": 0.07233315250045208,
      "grad_norm": 0.10827294737100601,
      "learning_rate": 5e-07,
      "loss": 0.0531,
      "step": 775
    },
    {
      "clip_ratio/high_max": 0.0020901021562167443,
      "clip_ratio/high_mean": 0.0007958971564221429,
      "clip_ratio/low_mean": 0.0010210168329649605,
      "clip_ratio/low_min": 1.7090511391870677e-05,
      "clip_ratio/region_mean": 0.001816913987568114,
      "epoch": 0.07242648560045266,
      "grad_norm": 0.12053879350423813,
      "learning_rate": 5e-07,
      "loss": 0.0468,
      "step": 776
    },
    {
      "clip_ratio/high_max": 0.0022874868409417104,
      "clip_ratio/high_mean": 0.0010016851410910022,
      "clip_ratio/low_mean": 0.0007539309599451371,
      "clip_ratio/low_min": 0.00010382007394582615,
      "clip_ratio/region_mean": 0.0017556161074026022,
      "epoch": 0.07251981870045325,
      "grad_norm": 0.11566450446844101,
      "learning_rate": 5e-07,
      "loss": 0.0048,
      "step": 777
    },
    {
      "clip_ratio/high_max": 0.002229152094514575,
      "clip_ratio/high_mean": 0.0009215017671522219,
      "clip_ratio/low_mean": 0.0010053041878563818,
      "clip_ratio/low_min": 2.585315451142378e-05,
      "clip_ratio/region_mean": 0.0019268059768364765,
      "epoch": 0.07261315180045383,
      "grad_norm": 0.13484157621860504,
      "learning_rate": 5e-07,
      "loss": 0.0274,
      "step": 778
    },
    {
      "clip_ratio/high_max": 0.002051352152193431,
      "clip_ratio/high_mean": 0.0008790077790763462,
      "clip_ratio/low_mean": 0.0009004669645946706,
      "clip_ratio/low_min": 8.286493130071904e-05,
      "clip_ratio/region_mean": 0.001779474740033038,
      "epoch": 0.07270648490045442,
      "grad_norm": 0.11402246356010437,
      "learning_rate": 5e-07,
      "loss": -0.0073,
      "step": 779
    },
    {
      "clip_ratio/high_max": 0.002354244810703676,
      "clip_ratio/high_mean": 0.001032732197927544,
      "clip_ratio/low_mean": 0.0007931755353638437,
      "clip_ratio/low_min": 5.0285419092688244e-05,
      "clip_ratio/region_mean": 0.0018259076969115995,
      "epoch": 0.072799818000455,
      "grad_norm": 0.11398999392986298,
      "learning_rate": 5e-07,
      "loss": -0.0185,
      "step": 780
    },
    {
      "clip_ratio/high_max": 0.0019512663093337324,
      "clip_ratio/high_mean": 0.0008267814155260567,
      "clip_ratio/low_mean": 0.0011112367756140884,
      "clip_ratio/low_min": 0.00014013384770805715,
      "clip_ratio/region_mean": 0.0019380181765882298,
      "epoch": 0.07289315110045558,
      "grad_norm": 0.12158603966236115,
      "learning_rate": 5e-07,
      "loss": 0.063,
      "step": 781
    },
    {
      "clip_ratio/high_max": 0.0019290863419882953,
      "clip_ratio/high_mean": 0.0008119610993162496,
      "clip_ratio/low_mean": 0.0007815729532012483,
      "clip_ratio/low_min": 1.6460364349768497e-05,
      "clip_ratio/region_mean": 0.001593534070707392,
      "epoch": 0.07298648420045617,
      "grad_norm": 0.11378190666437149,
      "learning_rate": 5e-07,
      "loss": -0.0041,
      "step": 782
    },
    {
      "clip_ratio/high_max": 0.0020900719464407302,
      "clip_ratio/high_mean": 0.0008936640642787097,
      "clip_ratio/low_mean": 0.0009016072435770184,
      "clip_ratio/low_min": 1.565043203299865e-05,
      "clip_ratio/region_mean": 0.0017952713242266327,
      "epoch": 0.07307981730045675,
      "grad_norm": 0.11952249705791473,
      "learning_rate": 5e-07,
      "loss": 0.0429,
      "step": 783
    },
    {
      "clip_ratio/high_max": 0.002226949633040931,
      "clip_ratio/high_mean": 0.0009044883008755278,
      "clip_ratio/low_mean": 0.0009704936273919884,
      "clip_ratio/low_min": 5.279490505927242e-05,
      "clip_ratio/region_mean": 0.001874981877335813,
      "epoch": 0.07317315040045733,
      "grad_norm": 0.154596745967865,
      "learning_rate": 5e-07,
      "loss": 0.0386,
      "step": 784
    },
    {
      "clip_ratio/high_max": 0.002014146408328088,
      "clip_ratio/high_mean": 0.0008564616528019542,
      "clip_ratio/low_mean": 0.0009023036327562295,
      "clip_ratio/low_min": 8.862627146299928e-05,
      "clip_ratio/region_mean": 0.001758765309205046,
      "epoch": 0.07326648350045792,
      "grad_norm": 0.10471615195274353,
      "learning_rate": 5e-07,
      "loss": -0.0061,
      "step": 785
    },
    {
      "clip_ratio/high_max": 0.0017358902368869167,
      "clip_ratio/high_mean": 0.0007202368869911879,
      "clip_ratio/low_mean": 0.001008047043796978,
      "clip_ratio/low_min": 8.391965820919722e-05,
      "clip_ratio/region_mean": 0.00172828391805524,
      "epoch": 0.0733598166004585,
      "grad_norm": 0.10821909457445145,
      "learning_rate": 5e-07,
      "loss": 0.0867,
      "step": 786
    },
    {
      "clip_ratio/high_max": 0.0021573474805336446,
      "clip_ratio/high_mean": 0.0008986330467450898,
      "clip_ratio/low_mean": 0.0009180618362734094,
      "clip_ratio/low_min": 8.806500773061998e-05,
      "clip_ratio/region_mean": 0.00181669485027669,
      "epoch": 0.07345314970045909,
      "grad_norm": 0.1063237413764,
      "learning_rate": 5e-07,
      "loss": -0.0071,
      "step": 787
    },
    {
      "clip_ratio/high_max": 0.0020419161155587062,
      "clip_ratio/high_mean": 0.0009119016685872339,
      "clip_ratio/low_mean": 0.001069211448339047,
      "clip_ratio/low_min": 8.509215240337653e-05,
      "clip_ratio/region_mean": 0.001981113113288302,
      "epoch": 0.07354648280045967,
      "grad_norm": 0.1063317283987999,
      "learning_rate": 5e-07,
      "loss": 0.046,
      "step": 788
    },
    {
      "clip_ratio/high_max": 0.0020376484317239374,
      "clip_ratio/high_mean": 0.0008639992847747635,
      "clip_ratio/low_mean": 0.000919493249966763,
      "clip_ratio/low_min": 1.7081169062294066e-05,
      "clip_ratio/region_mean": 0.0017834925311035477,
      "epoch": 0.07363981590046025,
      "grad_norm": 0.11291578412055969,
      "learning_rate": 5e-07,
      "loss": -0.0023,
      "step": 789
    },
    {
      "clip_ratio/high_max": 0.0020236987256794237,
      "clip_ratio/high_mean": 0.0009340451142634265,
      "clip_ratio/low_mean": 0.0008411191065533785,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0017751642371877097,
      "epoch": 0.07373314900046084,
      "grad_norm": 0.10550583153963089,
      "learning_rate": 5e-07,
      "loss": -0.0016,
      "step": 790
    },
    {
      "clip_ratio/high_max": 0.0020964447467122227,
      "clip_ratio/high_mean": 0.000729283607142861,
      "clip_ratio/low_mean": 0.0009406874869455351,
      "clip_ratio/low_min": 9.924401365424274e-05,
      "clip_ratio/region_mean": 0.0016699710831744596,
      "epoch": 0.07382648210046142,
      "grad_norm": 0.10611634701490402,
      "learning_rate": 5e-07,
      "loss": 0.0271,
      "step": 791
    },
    {
      "clip_ratio/high_max": 0.0020253744842193555,
      "clip_ratio/high_mean": 0.0008391483952436829,
      "clip_ratio/low_mean": 0.0009597163061698666,
      "clip_ratio/low_min": 0.00011122572686872445,
      "clip_ratio/region_mean": 0.001798864708689507,
      "epoch": 0.073919815200462,
      "grad_norm": 0.10967466980218887,
      "learning_rate": 5e-07,
      "loss": -0.0128,
      "step": 792
    },
    {
      "clip_ratio/high_max": 0.002117776373779634,
      "clip_ratio/high_mean": 0.0008929210234782659,
      "clip_ratio/low_mean": 0.0009729064877319615,
      "clip_ratio/low_min": 0.00010317933720216388,
      "clip_ratio/region_mean": 0.0018658275148482062,
      "epoch": 0.07401314830046259,
      "grad_norm": 0.11074399203062057,
      "learning_rate": 5e-07,
      "loss": 0.034,
      "step": 793
    },
    {
      "clip_ratio/high_max": 0.0020694234844995663,
      "clip_ratio/high_mean": 0.000820945626401226,
      "clip_ratio/low_mean": 0.0009207984985550866,
      "clip_ratio/low_min": 0.00012270435036043637,
      "clip_ratio/region_mean": 0.0017417441122233868,
      "epoch": 0.07410648140046316,
      "grad_norm": 0.11322260648012161,
      "learning_rate": 5e-07,
      "loss": 0.0438,
      "step": 794
    },
    {
      "clip_ratio/high_max": 0.0022515508098877035,
      "clip_ratio/high_mean": 0.0009430040290681063,
      "clip_ratio/low_mean": 0.0009840590755629819,
      "clip_ratio/low_min": 1.467480615247041e-05,
      "clip_ratio/region_mean": 0.0019270630873506889,
      "epoch": 0.07419981450046374,
      "grad_norm": 0.251048743724823,
      "learning_rate": 5e-07,
      "loss": -0.0093,
      "step": 795
    },
    {
      "clip_ratio/high_max": 0.0019147179045830853,
      "clip_ratio/high_mean": 0.0007963383686728776,
      "clip_ratio/low_mean": 0.0008264735533884959,
      "clip_ratio/low_min": 1.3067112377029844e-05,
      "clip_ratio/region_mean": 0.001622811920242384,
      "epoch": 0.07429314760046433,
      "grad_norm": 0.10831278562545776,
      "learning_rate": 5e-07,
      "loss": 0.019,
      "step": 796
    },
    {
      "clip_ratio/high_max": 0.0022179514780873433,
      "clip_ratio/high_mean": 0.0009015570158226183,
      "clip_ratio/low_mean": 0.0008948025479185162,
      "clip_ratio/low_min": 4.5556851546280086e-05,
      "clip_ratio/region_mean": 0.0017963595455512404,
      "epoch": 0.07438648070046491,
      "grad_norm": 0.11126313358545303,
      "learning_rate": 5e-07,
      "loss": 0.0082,
      "step": 797
    },
    {
      "clip_ratio/high_max": 0.001933993429702241,
      "clip_ratio/high_mean": 0.0008541215865989216,
      "clip_ratio/low_mean": 0.000983361243015679,
      "clip_ratio/low_min": 7.271039703482529e-05,
      "clip_ratio/region_mean": 0.0018374828396190424,
      "epoch": 0.0744798138004655,
      "grad_norm": 0.1081053614616394,
      "learning_rate": 5e-07,
      "loss": 0.0432,
      "step": 798
    },
    {
      "clip_ratio/high_max": 0.0020339845432317816,
      "clip_ratio/high_mean": 0.0008642319808132015,
      "clip_ratio/low_mean": 0.000976497740339255,
      "clip_ratio/low_min": 0.00011020621604984626,
      "clip_ratio/region_mean": 0.0018407296811346896,
      "epoch": 0.07457314690046608,
      "grad_norm": 0.11744171380996704,
      "learning_rate": 5e-07,
      "loss": 0.0681,
      "step": 799
    },
    {
      "clip_ratio/high_max": 0.0020137933825026266,
      "clip_ratio/high_mean": 0.000855836748087313,
      "clip_ratio/low_mean": 0.0007991430593392579,
      "clip_ratio/low_min": 9.744291492097545e-05,
      "clip_ratio/region_mean": 0.0016549798237974755,
      "epoch": 0.07466648000046666,
      "grad_norm": 0.10553628206253052,
      "learning_rate": 5e-07,
      "loss": 0.0056,
      "step": 800
    },
    {
      "clip_ratio/high_max": 0.0020182518601359334,
      "clip_ratio/high_mean": 0.0008280282900159364,
      "clip_ratio/low_mean": 0.0009009039240481798,
      "clip_ratio/low_min": 0.00012767602856911253,
      "clip_ratio/region_mean": 0.0017289321913267486,
      "completions/clipped_ratio": 0.014386858258928603,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4084.0,
      "completions/mean_length": 609.2898559570312,
      "completions/mean_terminated_length": 558.394775390625,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.07475981310046725,
      "grad_norm": 0.12434647232294083,
      "learning_rate": 5e-07,
      "loss": 0.0239,
      "num_tokens": 652742257.0,
      "reward": 0.5806884765625,
      "reward_std": 0.19552046060562134,
      "rewards/simpleverify_reward/mean": 0.5806884765625,
      "rewards/simpleverify_reward/std": 0.4934486150741577,
      "step": 801
    },
    {
      "clip_ratio/high_max": 0.0021667059481842443,
      "clip_ratio/high_mean": 0.0008726766900508665,
      "clip_ratio/low_mean": 0.0008060675172600895,
      "clip_ratio/low_min": 5.146093553776154e-05,
      "clip_ratio/region_mean": 0.0016787442000349984,
      "epoch": 0.07485314620046783,
      "grad_norm": 114.71483612060547,
      "learning_rate": 5e-07,
      "loss": 0.0755,
      "step": 802
    },
    {
      "clip_ratio/high_max": 0.0018271704830112867,
      "clip_ratio/high_mean": 0.0007438862994604278,
      "clip_ratio/low_mean": 0.0009524477736704284,
      "clip_ratio/low_min": 0.00012872027218691073,
      "clip_ratio/region_mean": 0.0016963340603979304,
      "epoch": 0.07494647930046841,
      "grad_norm": 0.11004878580570221,
      "learning_rate": 5e-07,
      "loss": 0.057,
      "step": 803
    },
    {
      "clip_ratio/high_max": 0.002240878497104859,
      "clip_ratio/high_mean": 0.0009562136983731762,
      "clip_ratio/low_mean": 0.0009032115158333909,
      "clip_ratio/low_min": 0.00014339655990625033,
      "clip_ratio/region_mean": 0.0018594251305330545,
      "epoch": 0.075039812400469,
      "grad_norm": 0.11947253346443176,
      "learning_rate": 5e-07,
      "loss": 0.0122,
      "step": 804
    },
    {
      "clip_ratio/high_max": 0.0024378238485951442,
      "clip_ratio/high_mean": 0.0010491644770809216,
      "clip_ratio/low_mean": 0.0008353321591130225,
      "clip_ratio/low_min": 7.867246677051298e-05,
      "clip_ratio/region_mean": 0.0018844966107280925,
      "epoch": 0.07513314550046958,
      "grad_norm": 0.1215267926454544,
      "learning_rate": 5e-07,
      "loss": -0.0208,
      "step": 805
    },
    {
      "clip_ratio/high_max": 0.0021557307518378366,
      "clip_ratio/high_mean": 0.0008065305446507409,
      "clip_ratio/low_mean": 0.0009959277649613796,
      "clip_ratio/low_min": 9.92634395515779e-05,
      "clip_ratio/region_mean": 0.001802458289603237,
      "epoch": 0.07522647860047016,
      "grad_norm": 0.1217433512210846,
      "learning_rate": 5e-07,
      "loss": 0.0711,
      "step": 806
    },
    {
      "clip_ratio/high_max": 0.0021014260819356423,
      "clip_ratio/high_mean": 0.0008869925904946285,
      "clip_ratio/low_mean": 0.0009338365434814477,
      "clip_ratio/low_min": 0.0001436475467926357,
      "clip_ratio/region_mean": 0.00182082910760073,
      "epoch": 0.07531981170047075,
      "grad_norm": 0.12165815383195877,
      "learning_rate": 5e-07,
      "loss": 0.0357,
      "step": 807
    },
    {
      "clip_ratio/high_max": 0.002517322383937426,
      "clip_ratio/high_mean": 0.0010316743173461873,
      "clip_ratio/low_mean": 0.0009259683702111943,
      "clip_ratio/low_min": 7.600420212838799e-05,
      "clip_ratio/region_mean": 0.0019576426784624346,
      "epoch": 0.07541314480047133,
      "grad_norm": 0.11501187086105347,
      "learning_rate": 5e-07,
      "loss": 0.0494,
      "step": 808
    },
    {
      "clip_ratio/high_max": 0.0026417877452331595,
      "clip_ratio/high_mean": 0.0010912187026406173,
      "clip_ratio/low_mean": 0.0009944333833118435,
      "clip_ratio/low_min": 6.590576504095225e-05,
      "clip_ratio/region_mean": 0.0020856521296082065,
      "epoch": 0.07550647790047192,
      "grad_norm": 0.12962615489959717,
      "learning_rate": 5e-07,
      "loss": 0.0221,
      "step": 809
    },
    {
      "clip_ratio/high_max": 0.002136947154212976,
      "clip_ratio/high_mean": 0.0009310758214269299,
      "clip_ratio/low_mean": 0.0008717880409676582,
      "clip_ratio/low_min": 4.518375226325588e-05,
      "clip_ratio/region_mean": 0.0018028638660325669,
      "epoch": 0.0755998110004725,
      "grad_norm": 0.11077548563480377,
      "learning_rate": 5e-07,
      "loss": 0.0162,
      "step": 810
    },
    {
      "clip_ratio/high_max": 0.0019707070023287088,
      "clip_ratio/high_mean": 0.0008988234785647364,
      "clip_ratio/low_mean": 0.0007886522689659614,
      "clip_ratio/low_min": 8.218880884669488e-05,
      "clip_ratio/region_mean": 0.0016874757420737296,
      "epoch": 0.07569314410047308,
      "grad_norm": 0.10518232733011246,
      "learning_rate": 5e-07,
      "loss": 0.0296,
      "step": 811
    },
    {
      "clip_ratio/high_max": 0.0021675674433936365,
      "clip_ratio/high_mean": 0.0009232192387571558,
      "clip_ratio/low_mean": 0.0008612606670794776,
      "clip_ratio/low_min": 5.27973024873063e-05,
      "clip_ratio/region_mean": 0.00178447988582775,
      "epoch": 0.07578647720047367,
      "grad_norm": 0.11351248621940613,
      "learning_rate": 5e-07,
      "loss": -0.0335,
      "step": 812
    },
    {
      "clip_ratio/high_max": 0.0023252036844496615,
      "clip_ratio/high_mean": 0.0009206647482642438,
      "clip_ratio/low_mean": 0.0009060085176315624,
      "clip_ratio/low_min": 0.0001156495236500632,
      "clip_ratio/region_mean": 0.0018266732804477215,
      "epoch": 0.07587981030047425,
      "grad_norm": 0.11246859282255173,
      "learning_rate": 5e-07,
      "loss": -0.0225,
      "step": 813
    },
    {
      "clip_ratio/high_max": 0.0021781033392471727,
      "clip_ratio/high_mean": 0.0009709048608783633,
      "clip_ratio/low_mean": 0.0009138543937297072,
      "clip_ratio/low_min": 0.0001879989340523025,
      "clip_ratio/region_mean": 0.0018847592509700917,
      "epoch": 0.07597314340047483,
      "grad_norm": 0.10344535857439041,
      "learning_rate": 5e-07,
      "loss": 0.0023,
      "step": 814
    },
    {
      "clip_ratio/high_max": 0.0022343181844917126,
      "clip_ratio/high_mean": 0.000865627442180994,
      "clip_ratio/low_mean": 0.0010662305103323888,
      "clip_ratio/low_min": 4.325015834183432e-05,
      "clip_ratio/region_mean": 0.0019318579725222662,
      "epoch": 0.07606647650047542,
      "grad_norm": 0.11579770594835281,
      "learning_rate": 5e-07,
      "loss": 0.0709,
      "step": 815
    },
    {
      "clip_ratio/high_max": 0.002225245290901512,
      "clip_ratio/high_mean": 0.0009486754424870014,
      "clip_ratio/low_mean": 0.0008349148138222517,
      "clip_ratio/low_min": 8.34523107187124e-05,
      "clip_ratio/region_mean": 0.0017835902617662214,
      "epoch": 0.076159809600476,
      "grad_norm": 0.12250196188688278,
      "learning_rate": 5e-07,
      "loss": 0.0043,
      "step": 816
    },
    {
      "clip_ratio/high_max": 0.0023235452172229998,
      "clip_ratio/high_mean": 0.000988139203400351,
      "clip_ratio/low_mean": 0.0008667895854159724,
      "clip_ratio/low_min": 7.367084799625445e-05,
      "clip_ratio/region_mean": 0.00185492879973026,
      "epoch": 0.07625314270047658,
      "grad_norm": 0.11190475523471832,
      "learning_rate": 5e-07,
      "loss": 0.0035,
      "step": 817
    },
    {
      "clip_ratio/high_max": 0.002064179308945313,
      "clip_ratio/high_mean": 0.0008672332423884654,
      "clip_ratio/low_mean": 0.0010052747129520867,
      "clip_ratio/low_min": 5.034237437939737e-05,
      "clip_ratio/region_mean": 0.0018725078843999654,
      "epoch": 0.07634647580047717,
      "grad_norm": 0.11234217137098312,
      "learning_rate": 5e-07,
      "loss": 0.019,
      "step": 818
    },
    {
      "clip_ratio/high_max": 0.002190318271459546,
      "clip_ratio/high_mean": 0.000876523672559415,
      "clip_ratio/low_mean": 0.001006786224024836,
      "clip_ratio/low_min": 9.277820754505228e-05,
      "clip_ratio/region_mean": 0.001883309865661431,
      "epoch": 0.07643980890047775,
      "grad_norm": 0.1189211905002594,
      "learning_rate": 5e-07,
      "loss": 0.0477,
      "step": 819
    },
    {
      "clip_ratio/high_max": 0.002122934518411057,
      "clip_ratio/high_mean": 0.0008618321126050432,
      "clip_ratio/low_mean": 0.0009490237462159712,
      "clip_ratio/low_min": 3.903013293893309e-05,
      "clip_ratio/region_mean": 0.0018108558360836469,
      "epoch": 0.07653314200047834,
      "grad_norm": 0.10448629409074783,
      "learning_rate": 5e-07,
      "loss": 0.0303,
      "step": 820
    },
    {
      "clip_ratio/high_max": 0.002404232778644655,
      "clip_ratio/high_mean": 0.0008263935824288637,
      "clip_ratio/low_mean": 0.0009352191682410194,
      "clip_ratio/low_min": 0.00012449027872207807,
      "clip_ratio/region_mean": 0.0017616127806832083,
      "epoch": 0.07662647510047892,
      "grad_norm": 0.10046626627445221,
      "learning_rate": 5e-07,
      "loss": 0.0431,
      "step": 821
    },
    {
      "clip_ratio/high_max": 0.0027645414593280293,
      "clip_ratio/high_mean": 0.0010294358107785229,
      "clip_ratio/low_mean": 0.0010919245032710023,
      "clip_ratio/low_min": 0.0002688220047275536,
      "clip_ratio/region_mean": 0.0021213603322394192,
      "epoch": 0.0767198082004795,
      "grad_norm": 0.12305775284767151,
      "learning_rate": 5e-07,
      "loss": 0.0553,
      "step": 822
    },
    {
      "clip_ratio/high_max": 0.0023798480251571164,
      "clip_ratio/high_mean": 0.0010226466692984104,
      "clip_ratio/low_mean": 0.0009861093985819025,
      "clip_ratio/low_min": 8.229971354012378e-05,
      "clip_ratio/region_mean": 0.002008756040595472,
      "epoch": 0.07681314130048009,
      "grad_norm": 0.11126812547445297,
      "learning_rate": 5e-07,
      "loss": 0.0132,
      "step": 823
    },
    {
      "clip_ratio/high_max": 0.0020498190351645462,
      "clip_ratio/high_mean": 0.0009165703231701627,
      "clip_ratio/low_mean": 0.0009559040772728622,
      "clip_ratio/low_min": 6.615624079131521e-05,
      "clip_ratio/region_mean": 0.0018724743713391945,
      "epoch": 0.07690647440048066,
      "grad_norm": 0.11094149947166443,
      "learning_rate": 5e-07,
      "loss": 0.0374,
      "step": 824
    },
    {
      "clip_ratio/high_max": 0.002006971219088882,
      "clip_ratio/high_mean": 0.0007381772138614906,
      "clip_ratio/low_mean": 0.000950065423239721,
      "clip_ratio/low_min": 0.00012184664319647709,
      "clip_ratio/region_mean": 0.001688242620730307,
      "epoch": 0.07699980750048124,
      "grad_norm": 0.10559757798910141,
      "learning_rate": 5e-07,
      "loss": 0.0421,
      "step": 825
    },
    {
      "clip_ratio/high_max": 0.002274467988172546,
      "clip_ratio/high_mean": 0.0008916578008211218,
      "clip_ratio/low_mean": 0.0009053812736965483,
      "clip_ratio/low_min": 4.7751350393809844e-05,
      "clip_ratio/region_mean": 0.001797039087250596,
      "epoch": 0.07709314060048184,
      "grad_norm": 0.10769429057836533,
      "learning_rate": 5e-07,
      "loss": 0.0072,
      "step": 826
    },
    {
      "clip_ratio/high_max": 0.0020363095063657966,
      "clip_ratio/high_mean": 0.0008976434692158364,
      "clip_ratio/low_mean": 0.001006627564493101,
      "clip_ratio/low_min": 4.416336741996929e-05,
      "clip_ratio/region_mean": 0.0019042710191570222,
      "epoch": 0.07718647370048241,
      "grad_norm": 0.11756660044193268,
      "learning_rate": 5e-07,
      "loss": 0.0126,
      "step": 827
    },
    {
      "clip_ratio/high_max": 0.0024976392669486813,
      "clip_ratio/high_mean": 0.0010104179582413053,
      "clip_ratio/low_mean": 0.0008332884845003719,
      "clip_ratio/low_min": 7.454717797372723e-05,
      "clip_ratio/region_mean": 0.0018437064500176348,
      "epoch": 0.07727980680048299,
      "grad_norm": 0.10431823134422302,
      "learning_rate": 5e-07,
      "loss": 0.0055,
      "step": 828
    },
    {
      "clip_ratio/high_max": 0.002317159334779717,
      "clip_ratio/high_mean": 0.000989578597000218,
      "clip_ratio/low_mean": 0.001066902495949762,
      "clip_ratio/low_min": 0.00017768595807865495,
      "clip_ratio/region_mean": 0.0020564811347867362,
      "epoch": 0.07737313990048358,
      "grad_norm": 0.12013478577136993,
      "learning_rate": 5e-07,
      "loss": 0.0267,
      "step": 829
    },
    {
      "clip_ratio/high_max": 0.001869776449893834,
      "clip_ratio/high_mean": 0.0006976433969612117,
      "clip_ratio/low_mean": 0.0010493650843272917,
      "clip_ratio/low_min": 9.25932345126057e-05,
      "clip_ratio/region_mean": 0.0017470084567321464,
      "epoch": 0.07746647300048416,
      "grad_norm": 0.11049527674913406,
      "learning_rate": 5e-07,
      "loss": 0.0496,
      "step": 830
    },
    {
      "clip_ratio/high_max": 0.0019466645462671295,
      "clip_ratio/high_mean": 0.0008866968601068947,
      "clip_ratio/low_mean": 0.001016669020827976,
      "clip_ratio/low_min": 7.697438923059963e-05,
      "clip_ratio/region_mean": 0.0019033658536500297,
      "epoch": 0.07755980610048475,
      "grad_norm": 0.11254800111055374,
      "learning_rate": 5e-07,
      "loss": 0.0503,
      "step": 831
    },
    {
      "clip_ratio/high_max": 0.002344027059734799,
      "clip_ratio/high_mean": 0.000995339320070343,
      "clip_ratio/low_mean": 0.0008048032359511126,
      "clip_ratio/low_min": 4.6200129872886464e-05,
      "clip_ratio/region_mean": 0.0018001425924012437,
      "epoch": 0.07765313920048533,
      "grad_norm": 0.10808626562356949,
      "learning_rate": 5e-07,
      "loss": -0.0174,
      "step": 832
    },
    {
      "clip_ratio/high_max": 0.0018979897795361467,
      "clip_ratio/high_mean": 0.0007679606733290711,
      "clip_ratio/low_mean": 0.0009088792976399418,
      "clip_ratio/low_min": 8.666022131365025e-05,
      "clip_ratio/region_mean": 0.0016768399509601295,
      "epoch": 0.07774647230048591,
      "grad_norm": 0.10723187774419785,
      "learning_rate": 5e-07,
      "loss": 0.0335,
      "step": 833
    },
    {
      "clip_ratio/high_max": 0.0017681750323390588,
      "clip_ratio/high_mean": 0.0007084493099682732,
      "clip_ratio/low_mean": 0.0009682521977083525,
      "clip_ratio/low_min": 6.30624417681247e-05,
      "clip_ratio/region_mean": 0.0016767014967626892,
      "epoch": 0.0778398054004865,
      "grad_norm": 0.09471729397773743,
      "learning_rate": 5e-07,
      "loss": 0.0652,
      "step": 834
    },
    {
      "clip_ratio/high_max": 0.001765694672940299,
      "clip_ratio/high_mean": 0.0007689585545449518,
      "clip_ratio/low_mean": 0.001031499919918133,
      "clip_ratio/low_min": 0.00013914904411649331,
      "clip_ratio/region_mean": 0.0018004584853770211,
      "epoch": 0.07793313850048708,
      "grad_norm": 0.11963675916194916,
      "learning_rate": 5e-07,
      "loss": 0.0597,
      "step": 835
    },
    {
      "clip_ratio/high_max": 0.0021838402353751007,
      "clip_ratio/high_mean": 0.0008898201031115605,
      "clip_ratio/low_mean": 0.0008865685176715488,
      "clip_ratio/low_min": 7.435739280481357e-05,
      "clip_ratio/region_mean": 0.0017763886207831092,
      "epoch": 0.07802647160048766,
      "grad_norm": 0.11629176884889603,
      "learning_rate": 5e-07,
      "loss": 0.0354,
      "step": 836
    },
    {
      "clip_ratio/high_max": 0.002597126273030881,
      "clip_ratio/high_mean": 0.0010181576399190817,
      "clip_ratio/low_mean": 0.0008484062891511712,
      "clip_ratio/low_min": 1.2755102034134325e-05,
      "clip_ratio/region_mean": 0.0018665638999664225,
      "epoch": 0.07811980470048825,
      "grad_norm": 0.11308830231428146,
      "learning_rate": 5e-07,
      "loss": -0.0073,
      "step": 837
    },
    {
      "clip_ratio/high_max": 0.001850208245741669,
      "clip_ratio/high_mean": 0.0007527539783040993,
      "clip_ratio/low_mean": 0.0009989333011617418,
      "clip_ratio/low_min": 8.877680193108972e-05,
      "clip_ratio/region_mean": 0.0017516872758278623,
      "epoch": 0.07821313780048883,
      "grad_norm": 0.10735638439655304,
      "learning_rate": 5e-07,
      "loss": 0.0435,
      "step": 838
    },
    {
      "clip_ratio/high_max": 0.0019308450937387533,
      "clip_ratio/high_mean": 0.0007498139475501375,
      "clip_ratio/low_mean": 0.0009998108507716097,
      "clip_ratio/low_min": 9.294119718106231e-05,
      "clip_ratio/region_mean": 0.001749624774674885,
      "epoch": 0.07830647090048942,
      "grad_norm": 0.10342347621917725,
      "learning_rate": 5e-07,
      "loss": 0.0543,
      "step": 839
    },
    {
      "clip_ratio/high_max": 0.002094373368890956,
      "clip_ratio/high_mean": 0.0009029725406435318,
      "clip_ratio/low_mean": 0.0008339030009665294,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0017368755870847963,
      "epoch": 0.07839980400049,
      "grad_norm": 0.12021764367818832,
      "learning_rate": 5e-07,
      "loss": 0.0116,
      "step": 840
    },
    {
      "clip_ratio/high_max": 0.001960320041689556,
      "clip_ratio/high_mean": 0.0008544069787603803,
      "clip_ratio/low_mean": 0.0008707969973329455,
      "clip_ratio/low_min": 7.50117278585094e-05,
      "clip_ratio/region_mean": 0.0017252039797313046,
      "epoch": 0.07849313710049058,
      "grad_norm": 0.11032550036907196,
      "learning_rate": 5e-07,
      "loss": 0.0223,
      "step": 841
    },
    {
      "clip_ratio/high_max": 0.0020043114564032294,
      "clip_ratio/high_mean": 0.0008141740036080591,
      "clip_ratio/low_mean": 0.0010614664570312016,
      "clip_ratio/low_min": 9.665985271567479e-05,
      "clip_ratio/region_mean": 0.0018756404606392607,
      "epoch": 0.07858647020049117,
      "grad_norm": 0.12365273386240005,
      "learning_rate": 5e-07,
      "loss": 0.0578,
      "step": 842
    },
    {
      "clip_ratio/high_max": 0.0024889195556170307,
      "clip_ratio/high_mean": 0.001018219849356683,
      "clip_ratio/low_mean": 0.0010286216374879587,
      "clip_ratio/low_min": 5.8696020914794644e-05,
      "clip_ratio/region_mean": 0.002046841436822433,
      "epoch": 0.07867980330049175,
      "grad_norm": 0.11688907444477081,
      "learning_rate": 5e-07,
      "loss": 0.0177,
      "step": 843
    },
    {
      "clip_ratio/high_max": 0.0019024776556761935,
      "clip_ratio/high_mean": 0.0007374993510893546,
      "clip_ratio/low_mean": 0.0009062455246748868,
      "clip_ratio/low_min": 7.515020479331724e-05,
      "clip_ratio/region_mean": 0.0016437448939541355,
      "epoch": 0.07877313640049233,
      "grad_norm": 0.10515257716178894,
      "learning_rate": 5e-07,
      "loss": 0.0641,
      "step": 844
    },
    {
      "clip_ratio/high_max": 0.0020347222889540717,
      "clip_ratio/high_mean": 0.0008836501292535104,
      "clip_ratio/low_mean": 0.0010385305758973118,
      "clip_ratio/low_min": 9.387266072735656e-05,
      "clip_ratio/region_mean": 0.0019221806942368858,
      "epoch": 0.07886646950049292,
      "grad_norm": 0.09982600808143616,
      "learning_rate": 5e-07,
      "loss": 0.0767,
      "step": 845
    },
    {
      "clip_ratio/high_max": 0.0023284433627850376,
      "clip_ratio/high_mean": 0.0008638268172944663,
      "clip_ratio/low_mean": 0.0008657286289235344,
      "clip_ratio/low_min": 5.535880700335838e-05,
      "clip_ratio/region_mean": 0.0017295554862357676,
      "epoch": 0.0789598026004935,
      "grad_norm": 0.12110163271427155,
      "learning_rate": 5e-07,
      "loss": 0.0329,
      "step": 846
    },
    {
      "clip_ratio/high_max": 0.00211387722811196,
      "clip_ratio/high_mean": 0.0008800668783806032,
      "clip_ratio/low_mean": 0.0009474770558881573,
      "clip_ratio/low_min": 5.983702521916712e-05,
      "clip_ratio/region_mean": 0.001827543932449771,
      "epoch": 0.07905313570049408,
      "grad_norm": 0.10864153504371643,
      "learning_rate": 5e-07,
      "loss": 0.0117,
      "step": 847
    },
    {
      "clip_ratio/high_max": 0.001981892259209417,
      "clip_ratio/high_mean": 0.0007879801214585314,
      "clip_ratio/low_mean": 0.0009372113345307298,
      "clip_ratio/low_min": 0.0001107505204345216,
      "clip_ratio/region_mean": 0.0017251914396183565,
      "epoch": 0.07914646880049467,
      "grad_norm": 13.07327651977539,
      "learning_rate": 5e-07,
      "loss": 0.1069,
      "step": 848
    },
    {
      "clip_ratio/high_max": 0.0024445208691759035,
      "clip_ratio/high_mean": 0.0009555439974064939,
      "clip_ratio/low_mean": 0.0009644745696277823,
      "clip_ratio/low_min": 5.668882613463211e-05,
      "clip_ratio/region_mean": 0.0019200185415684246,
      "epoch": 0.07923980190049525,
      "grad_norm": 0.1245674341917038,
      "learning_rate": 5e-07,
      "loss": 0.0029,
      "step": 849
    },
    {
      "clip_ratio/high_max": 0.0019141809898428619,
      "clip_ratio/high_mean": 0.0007642736454727128,
      "clip_ratio/low_mean": 0.0008148957203957252,
      "clip_ratio/low_min": 2.22518192458665e-05,
      "clip_ratio/region_mean": 0.0015791693222126924,
      "epoch": 0.07933313500049584,
      "grad_norm": 0.11051152646541595,
      "learning_rate": 5e-07,
      "loss": 0.0502,
      "step": 850
    },
    {
      "clip_ratio/high_max": 0.002265310271468479,
      "clip_ratio/high_mean": 0.0009529926228424301,
      "clip_ratio/low_mean": 0.0009761927904037293,
      "clip_ratio/low_min": 6.746917642885819e-05,
      "clip_ratio/region_mean": 0.0019291854187031277,
      "epoch": 0.07942646810049642,
      "grad_norm": 0.12945133447647095,
      "learning_rate": 5e-07,
      "loss": 0.0444,
      "step": 851
    },
    {
      "clip_ratio/high_max": 0.002068894296826329,
      "clip_ratio/high_mean": 0.0009730358669912675,
      "clip_ratio/low_mean": 0.0009529021335765719,
      "clip_ratio/low_min": 0.00015047813030832913,
      "clip_ratio/region_mean": 0.0019259380496805534,
      "epoch": 0.079519801200497,
      "grad_norm": 0.1201939508318901,
      "learning_rate": 5e-07,
      "loss": -0.0187,
      "step": 852
    },
    {
      "clip_ratio/high_max": 0.001970624696696177,
      "clip_ratio/high_mean": 0.000784974454290932,
      "clip_ratio/low_mean": 0.0010216783557552844,
      "clip_ratio/low_min": 0.00011859959886351135,
      "clip_ratio/region_mean": 0.001806652820960153,
      "epoch": 0.07961313430049759,
      "grad_norm": 0.1127067282795906,
      "learning_rate": 5e-07,
      "loss": 0.0551,
      "step": 853
    },
    {
      "clip_ratio/high_max": 0.0017719027200655546,
      "clip_ratio/high_mean": 0.0007417074893965037,
      "clip_ratio/low_mean": 0.0008192668210540432,
      "clip_ratio/low_min": 2.0900679373880848e-05,
      "clip_ratio/region_mean": 0.0015609743204549886,
      "epoch": 0.07970646740049817,
      "grad_norm": 0.11832299828529358,
      "learning_rate": 5e-07,
      "loss": 0.0146,
      "step": 854
    },
    {
      "clip_ratio/high_max": 0.001962588674359722,
      "clip_ratio/high_mean": 0.0008347422499355162,
      "clip_ratio/low_mean": 0.000881450045199017,
      "clip_ratio/low_min": 4.055945919390069e-05,
      "clip_ratio/region_mean": 0.0017161922587547451,
      "epoch": 0.07979980050049874,
      "grad_norm": 0.11429093778133392,
      "learning_rate": 5e-07,
      "loss": 0.0449,
      "step": 855
    },
    {
      "clip_ratio/high_max": 0.0019536374566087034,
      "clip_ratio/high_mean": 0.0008103019044938264,
      "clip_ratio/low_mean": 0.000990783217275748,
      "clip_ratio/low_min": 0.00018747672766039614,
      "clip_ratio/region_mean": 0.0018010851090366486,
      "epoch": 0.07989313360049934,
      "grad_norm": 5703.4833984375,
      "learning_rate": 5e-07,
      "loss": 0.2114,
      "step": 856
    },
    {
      "clip_ratio/high_max": 0.002002961336984299,
      "clip_ratio/high_mean": 0.000793176122897421,
      "clip_ratio/low_mean": 0.000803918250312563,
      "clip_ratio/low_min": 5.536453681997955e-05,
      "clip_ratio/region_mean": 0.0015970943350112066,
      "epoch": 0.07998646670049991,
      "grad_norm": 0.08613499999046326,
      "learning_rate": 5e-07,
      "loss": 0.0173,
      "step": 857
    },
    {
      "clip_ratio/high_max": 0.0020128724863752723,
      "clip_ratio/high_mean": 0.0008556057491659885,
      "clip_ratio/low_mean": 0.0009317556232417701,
      "clip_ratio/low_min": 8.282084036181914e-05,
      "clip_ratio/region_mean": 0.0017873613760457374,
      "epoch": 0.08007979980050049,
      "grad_norm": 0.12330185621976852,
      "learning_rate": 5e-07,
      "loss": 0.04,
      "step": 858
    },
    {
      "clip_ratio/high_max": 0.002431137800158467,
      "clip_ratio/high_mean": 0.000996697055597906,
      "clip_ratio/low_mean": 0.0008825754066492664,
      "clip_ratio/low_min": 1.4013452528160997e-05,
      "clip_ratio/region_mean": 0.001879272487713024,
      "epoch": 0.08017313290050108,
      "grad_norm": 0.11669915169477463,
      "learning_rate": 5e-07,
      "loss": 0.0008,
      "step": 859
    },
    {
      "clip_ratio/high_max": 0.0020899090595776215,
      "clip_ratio/high_mean": 0.0008669528979226016,
      "clip_ratio/low_mean": 0.0009367047186970012,
      "clip_ratio/low_min": 0.00013201721230871044,
      "clip_ratio/region_mean": 0.001803657622076571,
      "epoch": 0.08026646600050166,
      "grad_norm": 0.12284454703330994,
      "learning_rate": 5e-07,
      "loss": 0.0195,
      "step": 860
    },
    {
      "clip_ratio/high_max": 0.0021537466818699613,
      "clip_ratio/high_mean": 0.0008726321466383524,
      "clip_ratio/low_mean": 0.0009865954889392015,
      "clip_ratio/low_min": 7.336216003750451e-05,
      "clip_ratio/region_mean": 0.001859227595559787,
      "epoch": 0.08035979910050225,
      "grad_norm": 0.10687720030546188,
      "learning_rate": 5e-07,
      "loss": 0.0047,
      "step": 861
    },
    {
      "clip_ratio/high_max": 0.002418957417830825,
      "clip_ratio/high_mean": 0.0008867107153491816,
      "clip_ratio/low_mean": 0.0010493981244508177,
      "clip_ratio/low_min": 0.00012830362720706034,
      "clip_ratio/region_mean": 0.0019361088488949463,
      "epoch": 0.08045313220050283,
      "grad_norm": 0.10963724553585052,
      "learning_rate": 5e-07,
      "loss": 0.0202,
      "step": 862
    },
    {
      "clip_ratio/high_max": 0.002311369087692583,
      "clip_ratio/high_mean": 0.0009161896650766721,
      "clip_ratio/low_mean": 0.000883839204107062,
      "clip_ratio/low_min": 5.041914346293197e-05,
      "clip_ratio/region_mean": 0.0018000289419433102,
      "epoch": 0.08054646530050341,
      "grad_norm": 0.10151981562376022,
      "learning_rate": 5e-07,
      "loss": 0.0193,
      "step": 863
    },
    {
      "clip_ratio/high_max": 0.001986005503567867,
      "clip_ratio/high_mean": 0.0007430512705468573,
      "clip_ratio/low_mean": 0.0008407083096244605,
      "clip_ratio/low_min": 7.33187598598306e-05,
      "clip_ratio/region_mean": 0.0015837595638004132,
      "epoch": 0.080639798400504,
      "grad_norm": 0.11177854984998703,
      "learning_rate": 5e-07,
      "loss": 0.025,
      "step": 864
    },
    {
      "clip_ratio/high_max": 0.002207359400927089,
      "clip_ratio/high_mean": 0.0009718041565065505,
      "clip_ratio/low_mean": 0.0010014456092903856,
      "clip_ratio/low_min": 3.435198505030712e-05,
      "clip_ratio/region_mean": 0.001973249774891883,
      "epoch": 0.08073313150050458,
      "grad_norm": 0.1741376370191574,
      "learning_rate": 5e-07,
      "loss": 0.0267,
      "step": 865
    },
    {
      "clip_ratio/high_max": 0.0019209950478398241,
      "clip_ratio/high_mean": 0.0007569947283627698,
      "clip_ratio/low_mean": 0.0009402831565239467,
      "clip_ratio/low_min": 6.776992813684046e-05,
      "clip_ratio/region_mean": 0.0016972778248600662,
      "epoch": 0.08082646460050516,
      "grad_norm": 0.10803632438182831,
      "learning_rate": 5e-07,
      "loss": 0.068,
      "step": 866
    },
    {
      "clip_ratio/high_max": 0.0023419131102855317,
      "clip_ratio/high_mean": 0.0009638216688472312,
      "clip_ratio/low_mean": 0.0010406305445940234,
      "clip_ratio/low_min": 0.00015193551007541828,
      "clip_ratio/region_mean": 0.002004452260734979,
      "epoch": 0.08091979770050575,
      "grad_norm": 0.11742042750120163,
      "learning_rate": 5e-07,
      "loss": 0.0122,
      "step": 867
    },
    {
      "clip_ratio/high_max": 0.0024398000750807114,
      "clip_ratio/high_mean": 0.000879438985066372,
      "clip_ratio/low_mean": 0.0010522146749281092,
      "clip_ratio/low_min": 0.00010179470064031193,
      "clip_ratio/region_mean": 0.001931653605424799,
      "epoch": 0.08101313080050633,
      "grad_norm": 0.1186826303601265,
      "learning_rate": 5e-07,
      "loss": 0.0409,
      "step": 868
    },
    {
      "clip_ratio/high_max": 0.0022426892319344915,
      "clip_ratio/high_mean": 0.0008243501160904998,
      "clip_ratio/low_mean": 0.00095395421521971,
      "clip_ratio/low_min": 6.931592542969156e-05,
      "clip_ratio/region_mean": 0.0017783043585950509,
      "epoch": 0.08110646390050691,
      "grad_norm": 0.1111229807138443,
      "learning_rate": 5e-07,
      "loss": 0.0436,
      "step": 869
    },
    {
      "clip_ratio/high_max": 0.0023820575297577307,
      "clip_ratio/high_mean": 0.0009345998769276775,
      "clip_ratio/low_mean": 0.0008836526230879826,
      "clip_ratio/low_min": 0.00010816203030117322,
      "clip_ratio/region_mean": 0.0018182525018346496,
      "epoch": 0.0811997970005075,
      "grad_norm": 0.10880452394485474,
      "learning_rate": 5e-07,
      "loss": 0.0011,
      "step": 870
    },
    {
      "clip_ratio/high_max": 0.0024811456678435206,
      "clip_ratio/high_mean": 0.0010433212664793245,
      "clip_ratio/low_mean": 0.0009248170608771034,
      "clip_ratio/low_min": 3.197466139681637e-05,
      "clip_ratio/region_mean": 0.0019681383128045127,
      "epoch": 0.08129313010050808,
      "grad_norm": 0.11970839649438858,
      "learning_rate": 5e-07,
      "loss": -0.0009,
      "step": 871
    },
    {
      "clip_ratio/high_max": 0.0019481278723105788,
      "clip_ratio/high_mean": 0.0008915886446629884,
      "clip_ratio/low_mean": 0.0008998614084703149,
      "clip_ratio/low_min": 3.3357417123625055e-05,
      "clip_ratio/region_mean": 0.0017914501004270278,
      "epoch": 0.08138646320050867,
      "grad_norm": 0.11176019161939621,
      "learning_rate": 5e-07,
      "loss": 0.0189,
      "step": 872
    },
    {
      "clip_ratio/high_max": 0.0020261010722606443,
      "clip_ratio/high_mean": 0.0008442214211754617,
      "clip_ratio/low_mean": 0.0007338869763771072,
      "clip_ratio/low_min": 4.37389771832386e-05,
      "clip_ratio/region_mean": 0.0015781084148329683,
      "epoch": 0.08147979630050925,
      "grad_norm": 0.08926241099834442,
      "learning_rate": 5e-07,
      "loss": 0.0021,
      "step": 873
    },
    {
      "clip_ratio/high_max": 0.0019111187320959289,
      "clip_ratio/high_mean": 0.0008077737838902976,
      "clip_ratio/low_mean": 0.000866182326717535,
      "clip_ratio/low_min": 1.1730480764526874e-05,
      "clip_ratio/region_mean": 0.0016739561324357055,
      "epoch": 0.08157312940050983,
      "grad_norm": 0.11152459681034088,
      "learning_rate": 5e-07,
      "loss": 0.033,
      "step": 874
    },
    {
      "clip_ratio/high_max": 0.0020676581880252343,
      "clip_ratio/high_mean": 0.0008358631002920447,
      "clip_ratio/low_mean": 0.0008604750946688,
      "clip_ratio/low_min": 9.952981963579077e-05,
      "clip_ratio/region_mean": 0.0016963381713139825,
      "epoch": 0.08166646250051042,
      "grad_norm": 0.11183073371648788,
      "learning_rate": 5e-07,
      "loss": 0.0362,
      "step": 875
    },
    {
      "clip_ratio/high_max": 0.0024244334272225387,
      "clip_ratio/high_mean": 0.0009343365491076838,
      "clip_ratio/low_mean": 0.0009786188365978887,
      "clip_ratio/low_min": 5.192340904613957e-05,
      "clip_ratio/region_mean": 0.0019129554129904136,
      "epoch": 0.081759795600511,
      "grad_norm": 0.11490089446306229,
      "learning_rate": 5e-07,
      "loss": 0.0394,
      "step": 876
    },
    {
      "clip_ratio/high_max": 0.0017928007946466096,
      "clip_ratio/high_mean": 0.000803461760369828,
      "clip_ratio/low_mean": 0.0009065191152330954,
      "clip_ratio/low_min": 9.177176616503857e-05,
      "clip_ratio/region_mean": 0.0017099808537750505,
      "epoch": 0.08185312870051158,
      "grad_norm": 0.11370926350355148,
      "learning_rate": 5e-07,
      "loss": 0.0399,
      "step": 877
    },
    {
      "clip_ratio/high_max": 0.002157302984414855,
      "clip_ratio/high_mean": 0.0009111398649110924,
      "clip_ratio/low_mean": 0.0007816926281520864,
      "clip_ratio/low_min": 4.7435760279768147e-05,
      "clip_ratio/region_mean": 0.0016928324766922742,
      "epoch": 0.08194646180051217,
      "grad_norm": 0.10494080930948257,
      "learning_rate": 5e-07,
      "loss": -0.0201,
      "step": 878
    },
    {
      "clip_ratio/high_max": 0.002395183648332022,
      "clip_ratio/high_mean": 0.0009730013043736108,
      "clip_ratio/low_mean": 0.000987279214314185,
      "clip_ratio/low_min": 3.620422285166569e-05,
      "clip_ratio/region_mean": 0.0019602804823080078,
      "epoch": 0.08203979490051275,
      "grad_norm": 0.1222277283668518,
      "learning_rate": 5e-07,
      "loss": 0.0211,
      "step": 879
    },
    {
      "clip_ratio/high_max": 0.0024947491838247515,
      "clip_ratio/high_mean": 0.0010109679533343296,
      "clip_ratio/low_mean": 0.0008584126462665154,
      "clip_ratio/low_min": 4.356206090960768e-05,
      "clip_ratio/region_mean": 0.0018693806050578132,
      "epoch": 0.08213312800051333,
      "grad_norm": 0.11340250074863434,
      "learning_rate": 5e-07,
      "loss": 0.0098,
      "step": 880
    },
    {
      "clip_ratio/high_max": 0.0021100527665112168,
      "clip_ratio/high_mean": 0.0008653979311930016,
      "clip_ratio/low_mean": 0.0011028922017430887,
      "clip_ratio/low_min": 0.00012574962238431908,
      "clip_ratio/region_mean": 0.0019682901256601326,
      "epoch": 0.08222646110051392,
      "grad_norm": 0.11816433072090149,
      "learning_rate": 5e-07,
      "loss": 0.0384,
      "step": 881
    },
    {
      "clip_ratio/high_max": 0.0025489215331617743,
      "clip_ratio/high_mean": 0.0010272344334225636,
      "clip_ratio/low_mean": 0.000986295097391121,
      "clip_ratio/low_min": 1.6573852917645127e-05,
      "clip_ratio/region_mean": 0.002013529468968045,
      "epoch": 0.0823197942005145,
      "grad_norm": 0.11724293977022171,
      "learning_rate": 5e-07,
      "loss": 0.001,
      "step": 882
    },
    {
      "clip_ratio/high_max": 0.0022249403773457743,
      "clip_ratio/high_mean": 0.0009440648173040245,
      "clip_ratio/low_mean": 0.000918288794309774,
      "clip_ratio/low_min": 1.766534842317924e-05,
      "clip_ratio/region_mean": 0.0018623536307131872,
      "epoch": 0.08241312730051509,
      "grad_norm": 0.11648792028427124,
      "learning_rate": 5e-07,
      "loss": -0.0029,
      "step": 883
    },
    {
      "clip_ratio/high_max": 0.0016278022303595208,
      "clip_ratio/high_mean": 0.0007248310776049038,
      "clip_ratio/low_mean": 0.0010328457683499437,
      "clip_ratio/low_min": 0.0001947358241523034,
      "clip_ratio/region_mean": 0.001757676902343519,
      "epoch": 0.08250646040051567,
      "grad_norm": 0.10597003996372223,
      "learning_rate": 5e-07,
      "loss": 0.0613,
      "step": 884
    },
    {
      "clip_ratio/high_max": 0.002275289793033153,
      "clip_ratio/high_mean": 0.0008959855767898262,
      "clip_ratio/low_mean": 0.0009811203126446344,
      "clip_ratio/low_min": 3.7268885535013396e-05,
      "clip_ratio/region_mean": 0.0018771058676065877,
      "epoch": 0.08259979350051624,
      "grad_norm": 0.11635123193264008,
      "learning_rate": 5e-07,
      "loss": 0.0345,
      "step": 885
    },
    {
      "clip_ratio/high_max": 0.002146161554264836,
      "clip_ratio/high_mean": 0.0008978656805993523,
      "clip_ratio/low_mean": 0.000898977345059393,
      "clip_ratio/low_min": 7.478253792214673e-05,
      "clip_ratio/region_mean": 0.0017968430802284274,
      "epoch": 0.08269312660051684,
      "grad_norm": 0.111214779317379,
      "learning_rate": 5e-07,
      "loss": 0.0029,
      "step": 886
    },
    {
      "clip_ratio/high_max": 0.002065602791844867,
      "clip_ratio/high_mean": 0.000895404056791449,
      "clip_ratio/low_mean": 0.0007957489351611002,
      "clip_ratio/low_min": 9.961747309716884e-06,
      "clip_ratio/region_mean": 0.0016911529637582134,
      "epoch": 0.08278645970051741,
      "grad_norm": 0.10597280412912369,
      "learning_rate": 5e-07,
      "loss": -0.0224,
      "step": 887
    },
    {
      "clip_ratio/high_max": 0.0019668399982037954,
      "clip_ratio/high_mean": 0.0008351978212886024,
      "clip_ratio/low_mean": 0.0010782214667415246,
      "clip_ratio/low_min": 3.745444564628997e-05,
      "clip_ratio/region_mean": 0.001913419269840233,
      "epoch": 0.08287979280051799,
      "grad_norm": 0.10638641566038132,
      "learning_rate": 5e-07,
      "loss": 0.0011,
      "step": 888
    },
    {
      "clip_ratio/high_max": 0.0019083272272837348,
      "clip_ratio/high_mean": 0.0007376100456895074,
      "clip_ratio/low_mean": 0.000961311932769604,
      "clip_ratio/low_min": 5.842319114890415e-05,
      "clip_ratio/region_mean": 0.001698921976640122,
      "epoch": 0.08297312590051859,
      "grad_norm": 0.09258891642093658,
      "learning_rate": 5e-07,
      "loss": 0.0464,
      "step": 889
    },
    {
      "clip_ratio/high_max": 0.0026759861975733656,
      "clip_ratio/high_mean": 0.0009705653083074139,
      "clip_ratio/low_mean": 0.0008537964367860695,
      "clip_ratio/low_min": 2.5166096747852862e-05,
      "clip_ratio/region_mean": 0.00182436175600742,
      "epoch": 0.08306645900051916,
      "grad_norm": 0.11145222932100296,
      "learning_rate": 5e-07,
      "loss": 0.0391,
      "step": 890
    },
    {
      "clip_ratio/high_max": 0.0021013832156313583,
      "clip_ratio/high_mean": 0.0008426436652371194,
      "clip_ratio/low_mean": 0.0011643817379081156,
      "clip_ratio/low_min": 0.00015847774830035632,
      "clip_ratio/region_mean": 0.0020070253958692774,
      "epoch": 0.08315979210051976,
      "grad_norm": 0.11408057808876038,
      "learning_rate": 5e-07,
      "loss": 0.0375,
      "step": 891
    },
    {
      "clip_ratio/high_max": 0.002072920913633425,
      "clip_ratio/high_mean": 0.000844153681100579,
      "clip_ratio/low_mean": 0.0009017667816806352,
      "clip_ratio/low_min": 5.3115560149308294e-05,
      "clip_ratio/region_mean": 0.0017459204536862671,
      "epoch": 0.08325312520052033,
      "grad_norm": 0.09733714163303375,
      "learning_rate": 5e-07,
      "loss": 0.0151,
      "step": 892
    },
    {
      "clip_ratio/high_max": 0.0022092515355325304,
      "clip_ratio/high_mean": 0.0010029520162788685,
      "clip_ratio/low_mean": 0.0008597400737926364,
      "clip_ratio/low_min": 7.4308880357421e-05,
      "clip_ratio/region_mean": 0.001862692071881611,
      "epoch": 0.08334645830052091,
      "grad_norm": 0.11100546270608902,
      "learning_rate": 5e-07,
      "loss": -0.0017,
      "step": 893
    },
    {
      "clip_ratio/high_max": 0.002145353391824756,
      "clip_ratio/high_mean": 0.0008010022320377175,
      "clip_ratio/low_mean": 0.0009789336672838544,
      "clip_ratio/low_min": 8.205870244637481e-05,
      "clip_ratio/region_mean": 0.0017799358611227944,
      "epoch": 0.0834397914005215,
      "grad_norm": 0.10777309536933899,
      "learning_rate": 5e-07,
      "loss": 0.0699,
      "step": 894
    },
    {
      "clip_ratio/high_max": 0.001738420713081723,
      "clip_ratio/high_mean": 0.0008614408907305915,
      "clip_ratio/low_mean": 0.0011497544364829082,
      "clip_ratio/low_min": 9.19998537938227e-05,
      "clip_ratio/region_mean": 0.002011195283557754,
      "epoch": 0.08353312450052208,
      "grad_norm": 0.12012423574924469,
      "learning_rate": 5e-07,
      "loss": 0.0411,
      "step": 895
    },
    {
      "clip_ratio/high_max": 0.001996902090468211,
      "clip_ratio/high_mean": 0.0007641316951776389,
      "clip_ratio/low_mean": 0.0008363187826034846,
      "clip_ratio/low_min": 9.914057136484189e-05,
      "clip_ratio/region_mean": 0.0016004504796001129,
      "epoch": 0.08362645760052266,
      "grad_norm": 0.1034855991601944,
      "learning_rate": 5e-07,
      "loss": 0.077,
      "step": 896
    },
    {
      "clip_ratio/high_max": 0.0025319517590105534,
      "clip_ratio/high_mean": 0.0010477664218342397,
      "clip_ratio/low_mean": 0.0008381461830140324,
      "clip_ratio/low_min": 1.3343295904633123e-05,
      "clip_ratio/region_mean": 0.0018859125921153463,
      "epoch": 0.08371979070052325,
      "grad_norm": 0.10837484151124954,
      "learning_rate": 5e-07,
      "loss": -0.0018,
      "step": 897
    },
    {
      "clip_ratio/high_max": 0.00244588563873549,
      "clip_ratio/high_mean": 0.001040679368088604,
      "clip_ratio/low_mean": 0.0009614378013793612,
      "clip_ratio/low_min": 8.52976390888216e-05,
      "clip_ratio/region_mean": 0.002002117173105944,
      "epoch": 0.08381312380052383,
      "grad_norm": 0.11799226701259613,
      "learning_rate": 5e-07,
      "loss": 0.0067,
      "step": 898
    },
    {
      "clip_ratio/high_max": 0.002240247489680769,
      "clip_ratio/high_mean": 0.0008841492963256314,
      "clip_ratio/low_mean": 0.0008974922038760269,
      "clip_ratio/low_min": 3.330241179355653e-05,
      "clip_ratio/region_mean": 0.0017816414656408597,
      "epoch": 0.08390645690052441,
      "grad_norm": 0.11169647425413132,
      "learning_rate": 5e-07,
      "loss": 0.035,
      "step": 899
    },
    {
      "clip_ratio/high_max": 0.00215743209264474,
      "clip_ratio/high_mean": 0.0008843552714097314,
      "clip_ratio/low_mean": 0.0009565330692566931,
      "clip_ratio/low_min": 6.0547434259206057e-05,
      "clip_ratio/region_mean": 0.001840888347942382,
      "epoch": 0.083999790000525,
      "grad_norm": 0.12382075935602188,
      "learning_rate": 5e-07,
      "loss": 0.0326,
      "step": 900
    },
    {
      "clip_ratio/high_max": 0.0020119572764087934,
      "clip_ratio/high_mean": 0.0009255948552890914,
      "clip_ratio/low_mean": 0.0008939424787968164,
      "clip_ratio/low_min": 6.352121545205591e-05,
      "clip_ratio/region_mean": 0.0018195373413618654,
      "epoch": 0.08409312310052558,
      "grad_norm": 0.13699832558631897,
      "learning_rate": 5e-07,
      "loss": -0.0115,
      "step": 901
    },
    {
      "clip_ratio/high_max": 0.002347508940147236,
      "clip_ratio/high_mean": 0.0009608344644220779,
      "clip_ratio/low_mean": 0.0010432869403302902,
      "clip_ratio/low_min": 8.547093784727622e-05,
      "clip_ratio/region_mean": 0.0020041213938384317,
      "epoch": 0.08418645620052617,
      "grad_norm": 0.10919918864965439,
      "learning_rate": 5e-07,
      "loss": 0.005,
      "step": 902
    },
    {
      "clip_ratio/high_max": 0.0022818687539256644,
      "clip_ratio/high_mean": 0.0008921200142140151,
      "clip_ratio/low_mean": 0.000950450608797837,
      "clip_ratio/low_min": 0.00013318362107384019,
      "clip_ratio/region_mean": 0.0018425706075504422,
      "epoch": 0.08427978930052675,
      "grad_norm": 0.10944485664367676,
      "learning_rate": 5e-07,
      "loss": 0.0222,
      "step": 903
    },
    {
      "clip_ratio/high_max": 0.001849734348070342,
      "clip_ratio/high_mean": 0.0008426744298049016,
      "clip_ratio/low_mean": 0.0009011308011395158,
      "clip_ratio/low_min": 1.3821318134432659e-05,
      "clip_ratio/region_mean": 0.0017438052236684598,
      "epoch": 0.08437312240052733,
      "grad_norm": 0.10601015388965607,
      "learning_rate": 5e-07,
      "loss": -0.0092,
      "step": 904
    },
    {
      "clip_ratio/high_max": 0.0021981750978739,
      "clip_ratio/high_mean": 0.0009358218849229161,
      "clip_ratio/low_mean": 0.000993650308373617,
      "clip_ratio/low_min": 0.00012399806564644678,
      "clip_ratio/region_mean": 0.0019294721714686602,
      "epoch": 0.08446645550052792,
      "grad_norm": 0.12254777550697327,
      "learning_rate": 5e-07,
      "loss": 0.0488,
      "step": 905
    },
    {
      "clip_ratio/high_max": 0.0023765689984429628,
      "clip_ratio/high_mean": 0.0009594859247954446,
      "clip_ratio/low_mean": 0.0009835174860199913,
      "clip_ratio/low_min": 7.369986633420922e-05,
      "clip_ratio/region_mean": 0.0019430034080869518,
      "epoch": 0.0845597886005285,
      "grad_norm": 0.11661636084318161,
      "learning_rate": 5e-07,
      "loss": 0.0313,
      "step": 906
    },
    {
      "clip_ratio/high_max": 0.0020950394027750008,
      "clip_ratio/high_mean": 0.0008719802626728779,
      "clip_ratio/low_mean": 0.000938043278438272,
      "clip_ratio/low_min": 5.441437770059565e-05,
      "clip_ratio/region_mean": 0.001810023546568118,
      "epoch": 0.08465312170052908,
      "grad_norm": 0.11939775198698044,
      "learning_rate": 5e-07,
      "loss": -0.0091,
      "step": 907
    },
    {
      "clip_ratio/high_max": 0.002176624497224111,
      "clip_ratio/high_mean": 0.0009500299711362459,
      "clip_ratio/low_mean": 0.0009277865583499079,
      "clip_ratio/low_min": 0.00013584570478997193,
      "clip_ratio/region_mean": 0.0018778165394905955,
      "epoch": 0.08474645480052967,
      "grad_norm": 0.12060235440731049,
      "learning_rate": 5e-07,
      "loss": 0.0148,
      "step": 908
    },
    {
      "clip_ratio/high_max": 0.0023552283601020463,
      "clip_ratio/high_mean": 0.001064051897628815,
      "clip_ratio/low_mean": 0.0010569570731604472,
      "clip_ratio/low_min": 6.856402342236834e-05,
      "clip_ratio/region_mean": 0.002121008983522188,
      "epoch": 0.08483978790053025,
      "grad_norm": 0.1225523129105568,
      "learning_rate": 5e-07,
      "loss": 0.0229,
      "step": 909
    },
    {
      "clip_ratio/high_max": 0.0021591533877654,
      "clip_ratio/high_mean": 0.0009020826073538046,
      "clip_ratio/low_mean": 0.0008547279030608479,
      "clip_ratio/low_min": 4.471466581890127e-05,
      "clip_ratio/region_mean": 0.0017568104740348645,
      "epoch": 0.08493312100053083,
      "grad_norm": 0.11211380362510681,
      "learning_rate": 5e-07,
      "loss": -0.0362,
      "step": 910
    },
    {
      "clip_ratio/high_max": 0.0017276328508160077,
      "clip_ratio/high_mean": 0.0008436259849986527,
      "clip_ratio/low_mean": 0.001048293856001692,
      "clip_ratio/low_min": 8.159876142599387e-05,
      "clip_ratio/region_mean": 0.0018919198410003446,
      "epoch": 0.08502645410053142,
      "grad_norm": 0.12149956822395325,
      "learning_rate": 5e-07,
      "loss": 0.0374,
      "step": 911
    },
    {
      "clip_ratio/high_max": 0.0024867888932931237,
      "clip_ratio/high_mean": 0.001032421576383058,
      "clip_ratio/low_mean": 0.0009220092633768218,
      "clip_ratio/low_min": 0.00012700539082288742,
      "clip_ratio/region_mean": 0.0019544308524928056,
      "epoch": 0.085119787200532,
      "grad_norm": 0.11276817321777344,
      "learning_rate": 5e-07,
      "loss": -0.0198,
      "step": 912
    },
    {
      "clip_ratio/high_max": 0.001986971365113277,
      "clip_ratio/high_mean": 0.0008038535961532034,
      "clip_ratio/low_mean": 0.001107049494748935,
      "clip_ratio/low_min": 3.4529163713159505e-05,
      "clip_ratio/region_mean": 0.0019109030763502233,
      "epoch": 0.08521312030053259,
      "grad_norm": 0.10700630396604538,
      "learning_rate": 5e-07,
      "loss": 0.0758,
      "step": 913
    },
    {
      "clip_ratio/high_max": 0.0022053404900361784,
      "clip_ratio/high_mean": 0.0009446581443626201,
      "clip_ratio/low_mean": 0.0010704749747674214,
      "clip_ratio/low_min": 0.00013373798719840124,
      "clip_ratio/region_mean": 0.0020151331045781262,
      "epoch": 0.08530645340053317,
      "grad_norm": 0.12000106275081635,
      "learning_rate": 5e-07,
      "loss": 0.0051,
      "step": 914
    },
    {
      "clip_ratio/high_max": 0.001959814762813039,
      "clip_ratio/high_mean": 0.0008008974964468507,
      "clip_ratio/low_mean": 0.0009712177998153493,
      "clip_ratio/low_min": 1.776830140443053e-05,
      "clip_ratio/region_mean": 0.0017721153271850199,
      "epoch": 0.08539978650053374,
      "grad_norm": 0.11506950855255127,
      "learning_rate": 5e-07,
      "loss": 0.0424,
      "step": 915
    },
    {
      "clip_ratio/high_max": 0.0023083583218976855,
      "clip_ratio/high_mean": 0.0009401173119840678,
      "clip_ratio/low_mean": 0.0009869848527159775,
      "clip_ratio/low_min": 6.616235987166874e-05,
      "clip_ratio/region_mean": 0.0019271021301392466,
      "epoch": 0.08549311960053434,
      "grad_norm": 0.11514274775981903,
      "learning_rate": 5e-07,
      "loss": 0.0107,
      "step": 916
    },
    {
      "clip_ratio/high_max": 0.0018722429376794025,
      "clip_ratio/high_mean": 0.0008383719959965674,
      "clip_ratio/low_mean": 0.0012223465528222732,
      "clip_ratio/low_min": 0.0002303812525497051,
      "clip_ratio/region_mean": 0.0020607186015695333,
      "epoch": 0.08558645270053492,
      "grad_norm": 0.2587330639362335,
      "learning_rate": 5e-07,
      "loss": 0.0792,
      "step": 917
    },
    {
      "clip_ratio/high_max": 0.002236536114651244,
      "clip_ratio/high_mean": 0.0009190500768454513,
      "clip_ratio/low_mean": 0.0008429859399257111,
      "clip_ratio/low_min": 7.360841482295655e-05,
      "clip_ratio/region_mean": 0.001762036030413583,
      "epoch": 0.0856797858005355,
      "grad_norm": 0.4433564841747284,
      "learning_rate": 5e-07,
      "loss": 0.0064,
      "step": 918
    },
    {
      "clip_ratio/high_max": 0.0026802290958585218,
      "clip_ratio/high_mean": 0.0011065964135923423,
      "clip_ratio/low_mean": 0.000925516986171715,
      "clip_ratio/low_min": 5.653580592479557e-05,
      "clip_ratio/region_mean": 0.002032113363384269,
      "epoch": 0.08577311890053609,
      "grad_norm": 0.12310229241847992,
      "learning_rate": 5e-07,
      "loss": 0.0082,
      "step": 919
    },
    {
      "clip_ratio/high_max": 0.0024942765521700494,
      "clip_ratio/high_mean": 0.000892843228939455,
      "clip_ratio/low_mean": 0.000911678700504126,
      "clip_ratio/low_min": 4.7438729325222084e-05,
      "clip_ratio/region_mean": 0.001804521911253687,
      "epoch": 0.08586645200053666,
      "grad_norm": 0.11978574097156525,
      "learning_rate": 5e-07,
      "loss": 0.0216,
      "step": 920
    },
    {
      "clip_ratio/high_max": 0.0020331298728706315,
      "clip_ratio/high_mean": 0.0008831564791762503,
      "clip_ratio/low_mean": 0.0009655333415139467,
      "clip_ratio/low_min": 7.021717465249822e-05,
      "clip_ratio/region_mean": 0.001848689789767377,
      "epoch": 0.08595978510053724,
      "grad_norm": 0.11123237013816833,
      "learning_rate": 5e-07,
      "loss": 0.0045,
      "step": 921
    },
    {
      "clip_ratio/high_max": 0.0020684972405433655,
      "clip_ratio/high_mean": 0.0007512118918384658,
      "clip_ratio/low_mean": 0.0010224079469480785,
      "clip_ratio/low_min": 0.00010443913106428226,
      "clip_ratio/region_mean": 0.0017736198205966502,
      "epoch": 0.08605311820053783,
      "grad_norm": 0.11918862909078598,
      "learning_rate": 5e-07,
      "loss": 0.0124,
      "step": 922
    },
    {
      "clip_ratio/high_max": 0.002253590209875256,
      "clip_ratio/high_mean": 0.000894513506864314,
      "clip_ratio/low_mean": 0.0010340445405745413,
      "clip_ratio/low_min": 9.870946632872801e-05,
      "clip_ratio/region_mean": 0.001928558041981887,
      "epoch": 0.08614645130053841,
      "grad_norm": 0.11915268003940582,
      "learning_rate": 5e-07,
      "loss": 0.0465,
      "step": 923
    },
    {
      "clip_ratio/high_max": 0.0020315549954830203,
      "clip_ratio/high_mean": 0.0008269010759249795,
      "clip_ratio/low_mean": 0.0009840194961725501,
      "clip_ratio/low_min": 5.025480095355306e-05,
      "clip_ratio/region_mean": 0.0018109205993823707,
      "epoch": 0.086239784400539,
      "grad_norm": 0.1125863641500473,
      "learning_rate": 5e-07,
      "loss": 0.0501,
      "step": 924
    },
    {
      "clip_ratio/high_max": 0.0024661422794451937,
      "clip_ratio/high_mean": 0.000999791023787111,
      "clip_ratio/low_mean": 0.0008374320950679248,
      "clip_ratio/low_min": 5.684579718945315e-05,
      "clip_ratio/region_mean": 0.0018372231425018981,
      "epoch": 0.08633311750053958,
      "grad_norm": 0.09851789474487305,
      "learning_rate": 5e-07,
      "loss": -0.0004,
      "step": 925
    },
    {
      "clip_ratio/high_max": 0.0017701841716188937,
      "clip_ratio/high_mean": 0.0008987371838884428,
      "clip_ratio/low_mean": 0.0007800783732818672,
      "clip_ratio/low_min": 4.0001260458666366e-05,
      "clip_ratio/region_mean": 0.0016788155407994054,
      "epoch": 0.08642645060054016,
      "grad_norm": 0.11278315633535385,
      "learning_rate": 5e-07,
      "loss": -0.0251,
      "step": 926
    },
    {
      "clip_ratio/high_max": 0.001970147432075464,
      "clip_ratio/high_mean": 0.0009175917493848829,
      "clip_ratio/low_mean": 0.0009237877984560328,
      "clip_ratio/low_min": 9.375181343784789e-05,
      "clip_ratio/region_mean": 0.0018413795696687885,
      "epoch": 0.08651978370054075,
      "grad_norm": 0.11522503942251205,
      "learning_rate": 5e-07,
      "loss": 0.0272,
      "step": 927
    },
    {
      "clip_ratio/high_max": 0.0020665901247411966,
      "clip_ratio/high_mean": 0.0008240326442319201,
      "clip_ratio/low_mean": 0.0008598412096034735,
      "clip_ratio/low_min": 5.8786589761439245e-05,
      "clip_ratio/region_mean": 0.0016838739102240652,
      "epoch": 0.08661311680054133,
      "grad_norm": 0.10661685466766357,
      "learning_rate": 5e-07,
      "loss": 0.0069,
      "step": 928
    },
    {
      "clip_ratio/high_max": 0.0020074319691048004,
      "clip_ratio/high_mean": 0.0008248738267866429,
      "clip_ratio/low_mean": 0.0008219710052799201,
      "clip_ratio/low_min": 6.012538869981654e-05,
      "clip_ratio/region_mean": 0.0016468448447994888,
      "completions/clipped_ratio": 0.013628278459821397,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4085.0,
      "completions/mean_length": 609.4169921875,
      "completions/mean_terminated_length": 561.2444458007812,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.08670644990054191,
      "grad_norm": 1.2153546810150146,
      "learning_rate": 5e-07,
      "loss": 0.0405,
      "num_tokens": 734027776.0,
      "reward": 0.5859724283218384,
      "reward_std": 0.19817598164081573,
      "rewards/simpleverify_reward/mean": 0.5859723687171936,
      "rewards/simpleverify_reward/std": 0.49255549907684326,
      "step": 929
    },
    {
      "clip_ratio/high_max": 0.002341733605135232,
      "clip_ratio/high_mean": 0.0009618382719054352,
      "clip_ratio/low_mean": 0.0008154472652677214,
      "clip_ratio/low_min": 6.501998996100156e-05,
      "clip_ratio/region_mean": 0.0017772855353541672,
      "epoch": 0.0867997830005425,
      "grad_norm": 0.11381831020116806,
      "learning_rate": 5e-07,
      "loss": 0.0021,
      "step": 930
    },
    {
      "clip_ratio/high_max": 0.002624723594635725,
      "clip_ratio/high_mean": 0.0010929329473583493,
      "clip_ratio/low_mean": 0.0008042787194426637,
      "clip_ratio/low_min": 3.614525849116035e-05,
      "clip_ratio/region_mean": 0.0018972117031808011,
      "epoch": 0.08689311610054308,
      "grad_norm": 0.11408938467502594,
      "learning_rate": 5e-07,
      "loss": 0.0121,
      "step": 931
    },
    {
      "clip_ratio/high_max": 0.0023809983922546962,
      "clip_ratio/high_mean": 0.0009887973624245205,
      "clip_ratio/low_mean": 0.0008191180077119498,
      "clip_ratio/low_min": 4.441987130121561e-05,
      "clip_ratio/region_mean": 0.0018079153524013236,
      "epoch": 0.08698644920054366,
      "grad_norm": 0.10509301722049713,
      "learning_rate": 5e-07,
      "loss": -0.0309,
      "step": 932
    },
    {
      "clip_ratio/high_max": 0.0021651947499776725,
      "clip_ratio/high_mean": 0.0008106773548206547,
      "clip_ratio/low_mean": 0.0008076359281403711,
      "clip_ratio/low_min": 9.977500758395763e-05,
      "clip_ratio/region_mean": 0.0016183132902369834,
      "epoch": 0.08707978230054425,
      "grad_norm": 0.14854934811592102,
      "learning_rate": 5e-07,
      "loss": 0.0487,
      "step": 933
    },
    {
      "clip_ratio/high_max": 0.002139520838682074,
      "clip_ratio/high_mean": 0.0008933422923291801,
      "clip_ratio/low_mean": 0.0008302487185574137,
      "clip_ratio/low_min": 2.3955539290909655e-05,
      "clip_ratio/region_mean": 0.0017235910563613288,
      "epoch": 0.08717311540054483,
      "grad_norm": 0.1726633459329605,
      "learning_rate": 5e-07,
      "loss": 0.0157,
      "step": 934
    },
    {
      "clip_ratio/high_max": 0.0020705537099274807,
      "clip_ratio/high_mean": 0.000997077386273304,
      "clip_ratio/low_mean": 0.0009763071320776362,
      "clip_ratio/low_min": 0.000102427202364197,
      "clip_ratio/region_mean": 0.001973384525626898,
      "epoch": 0.08726644850054542,
      "grad_norm": 89184.3125,
      "learning_rate": 5e-07,
      "loss": 49.6666,
      "step": 935
    },
    {
      "clip_ratio/high_max": 0.0022964796371525154,
      "clip_ratio/high_mean": 0.0009711294278531568,
      "clip_ratio/low_mean": 0.0008616970535513246,
      "clip_ratio/low_min": 9.252055860997643e-05,
      "clip_ratio/region_mean": 0.0018328264559386298,
      "epoch": 0.087359781600546,
      "grad_norm": 0.10724718123674393,
      "learning_rate": 5e-07,
      "loss": 0.0335,
      "step": 936
    },
    {
      "clip_ratio/high_max": 0.0022643932497885544,
      "clip_ratio/high_mean": 0.0008929682462621713,
      "clip_ratio/low_mean": 0.0009722065788082546,
      "clip_ratio/low_min": 7.573482707812218e-05,
      "clip_ratio/region_mean": 0.0018651748177944683,
      "epoch": 0.08745311470054658,
      "grad_norm": 97.37411499023438,
      "learning_rate": 5e-07,
      "loss": 0.3179,
      "step": 937
    },
    {
      "clip_ratio/high_max": 0.0019071906790486537,
      "clip_ratio/high_mean": 0.0007970709848450497,
      "clip_ratio/low_mean": 0.0009906874765874818,
      "clip_ratio/low_min": 7.32171847630525e-05,
      "clip_ratio/region_mean": 0.0017877584468806162,
      "epoch": 0.08754644780054717,
      "grad_norm": 0.1134478822350502,
      "learning_rate": 5e-07,
      "loss": 0.0586,
      "step": 938
    },
    {
      "clip_ratio/high_max": 0.002242838811071124,
      "clip_ratio/high_mean": 0.0009052066125150304,
      "clip_ratio/low_mean": 0.0009444296865694923,
      "clip_ratio/low_min": 4.2361245959909866e-05,
      "clip_ratio/region_mean": 0.0018496363445592579,
      "epoch": 0.08763978090054775,
      "grad_norm": 0.11784396320581436,
      "learning_rate": 5e-07,
      "loss": 0.0041,
      "step": 939
    },
    {
      "clip_ratio/high_max": 0.002126558276358992,
      "clip_ratio/high_mean": 0.0008031408069655299,
      "clip_ratio/low_mean": 0.0010163720689888578,
      "clip_ratio/low_min": 0.00010081387972604716,
      "clip_ratio/region_mean": 0.0018195129232481122,
      "epoch": 0.08773311400054833,
      "grad_norm": 0.21955983340740204,
      "learning_rate": 5e-07,
      "loss": 0.0645,
      "step": 940
    },
    {
      "clip_ratio/high_max": 0.002491281305992743,
      "clip_ratio/high_mean": 0.0009965643694158643,
      "clip_ratio/low_mean": 0.0009044434336828999,
      "clip_ratio/low_min": 2.5647391339589376e-05,
      "clip_ratio/region_mean": 0.0019010077958228067,
      "epoch": 0.08782644710054892,
      "grad_norm": 0.5272688269615173,
      "learning_rate": 5e-07,
      "loss": -0.0003,
      "step": 941
    },
    {
      "clip_ratio/high_max": 0.002410025103017688,
      "clip_ratio/high_mean": 0.0009252032687072642,
      "clip_ratio/low_mean": 0.0009342323210148606,
      "clip_ratio/low_min": 2.9777814233966637e-05,
      "clip_ratio/region_mean": 0.0018594356151879765,
      "epoch": 0.0879197802005495,
      "grad_norm": 0.12424842268228531,
      "learning_rate": 5e-07,
      "loss": 0.0491,
      "step": 942
    },
    {
      "clip_ratio/high_max": 0.00219300105527509,
      "clip_ratio/high_mean": 0.0010659600793587742,
      "clip_ratio/low_mean": 0.0008666521698614815,
      "clip_ratio/low_min": 4.548431297735078e-05,
      "clip_ratio/region_mean": 0.0019326122201164253,
      "epoch": 0.08801311330055009,
      "grad_norm": 0.11180602014064789,
      "learning_rate": 5e-07,
      "loss": -0.0114,
      "step": 943
    },
    {
      "clip_ratio/high_max": 0.0024969670630525798,
      "clip_ratio/high_mean": 0.0011064905211242149,
      "clip_ratio/low_mean": 0.0007731850801064866,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0018796756048686802,
      "epoch": 0.08810644640055067,
      "grad_norm": 0.11087559908628464,
      "learning_rate": 5e-07,
      "loss": -0.0007,
      "step": 944
    },
    {
      "clip_ratio/high_max": 0.002220521870185621,
      "clip_ratio/high_mean": 0.001020797590172151,
      "clip_ratio/low_mean": 0.0009758862252056133,
      "clip_ratio/low_min": 0.0001512916669526021,
      "clip_ratio/region_mean": 0.001996683786273934,
      "epoch": 0.08819977950055125,
      "grad_norm": 0.11495806276798248,
      "learning_rate": 5e-07,
      "loss": 0.0327,
      "step": 945
    },
    {
      "clip_ratio/high_max": 0.002001190478040371,
      "clip_ratio/high_mean": 0.0008535101460438455,
      "clip_ratio/low_mean": 0.0010626897110341815,
      "clip_ratio/low_min": 9.583755127096083e-05,
      "clip_ratio/region_mean": 0.0019161998425261118,
      "epoch": 0.08829311260055184,
      "grad_norm": 0.11471836268901825,
      "learning_rate": 5e-07,
      "loss": 0.0394,
      "step": 946
    },
    {
      "clip_ratio/high_max": 0.0023299811655306257,
      "clip_ratio/high_mean": 0.0009040252953127492,
      "clip_ratio/low_mean": 0.0007621016538905678,
      "clip_ratio/low_min": 2.7421660888649058e-05,
      "clip_ratio/region_mean": 0.0016661268891766667,
      "epoch": 0.08838644570055242,
      "grad_norm": 0.1132160872220993,
      "learning_rate": 5e-07,
      "loss": 0.0271,
      "step": 947
    },
    {
      "clip_ratio/high_max": 0.002016687794821337,
      "clip_ratio/high_mean": 0.0009004256116895704,
      "clip_ratio/low_mean": 0.0010082170410896651,
      "clip_ratio/low_min": 0.0001430072379662306,
      "clip_ratio/region_mean": 0.0019086426837020554,
      "epoch": 0.088479778800553,
      "grad_norm": 0.17505529522895813,
      "learning_rate": 5e-07,
      "loss": 0.127,
      "step": 948
    },
    {
      "clip_ratio/high_max": 0.002346318622585386,
      "clip_ratio/high_mean": 0.0009785759029909968,
      "clip_ratio/low_mean": 0.0010053677142423112,
      "clip_ratio/low_min": 5.248026991466759e-05,
      "clip_ratio/region_mean": 0.0019839436135953292,
      "epoch": 0.08857311190055359,
      "grad_norm": 0.12629856169223785,
      "learning_rate": 5e-07,
      "loss": 0.0343,
      "step": 949
    },
    {
      "clip_ratio/high_max": 0.001983152840693947,
      "clip_ratio/high_mean": 0.0009260715396521846,
      "clip_ratio/low_mean": 0.0008634190453449264,
      "clip_ratio/low_min": 1.5371371773653664e-05,
      "clip_ratio/region_mean": 0.0017894905977300368,
      "epoch": 0.08866644500055416,
      "grad_norm": 0.1124405562877655,
      "learning_rate": 5e-07,
      "loss": 0.0079,
      "step": 950
    },
    {
      "clip_ratio/high_max": 0.00204544613006874,
      "clip_ratio/high_mean": 0.0008038411106099375,
      "clip_ratio/low_mean": 0.0008810093877400504,
      "clip_ratio/low_min": 8.209854331653332e-05,
      "clip_ratio/region_mean": 0.001684850467427168,
      "epoch": 0.08875977810055474,
      "grad_norm": 0.10661377757787704,
      "learning_rate": 5e-07,
      "loss": 0.0498,
      "step": 951
    },
    {
      "clip_ratio/high_max": 0.0018972568068420514,
      "clip_ratio/high_mean": 0.0008427633620158304,
      "clip_ratio/low_mean": 0.0010563772775640246,
      "clip_ratio/low_min": 0.00013790834600513335,
      "clip_ratio/region_mean": 0.0018991406323038973,
      "epoch": 0.08885311120055533,
      "grad_norm": 0.20625697076320648,
      "learning_rate": 5e-07,
      "loss": 0.0624,
      "step": 952
    },
    {
      "clip_ratio/high_max": 0.0020754061952175107,
      "clip_ratio/high_mean": 0.0008458970505671459,
      "clip_ratio/low_mean": 0.0010623252164805308,
      "clip_ratio/low_min": 7.680343423999147e-05,
      "clip_ratio/region_mean": 0.0019082222861470655,
      "epoch": 0.08894644430055591,
      "grad_norm": 0.12470429390668869,
      "learning_rate": 5e-07,
      "loss": 0.0662,
      "step": 953
    },
    {
      "clip_ratio/high_max": 0.0021697295451303944,
      "clip_ratio/high_mean": 0.0008852760056470288,
      "clip_ratio/low_mean": 0.0009567218257870991,
      "clip_ratio/low_min": 6.232517625903711e-05,
      "clip_ratio/region_mean": 0.0018419978296151385,
      "epoch": 0.0890397774005565,
      "grad_norm": 0.11062418669462204,
      "learning_rate": 5e-07,
      "loss": 0.009,
      "step": 954
    },
    {
      "clip_ratio/high_max": 0.002235779211332556,
      "clip_ratio/high_mean": 0.000983330670351279,
      "clip_ratio/low_mean": 0.001044267572069657,
      "clip_ratio/low_min": 7.396120872726897e-05,
      "clip_ratio/region_mean": 0.0020275982096791267,
      "epoch": 0.08913311050055708,
      "grad_norm": 0.10453753173351288,
      "learning_rate": 5e-07,
      "loss": 0.0345,
      "step": 955
    },
    {
      "clip_ratio/high_max": 0.0017731729167280719,
      "clip_ratio/high_mean": 0.0008625395530543756,
      "clip_ratio/low_mean": 0.0009448556102142902,
      "clip_ratio/low_min": 7.991702477738727e-05,
      "clip_ratio/region_mean": 0.0018073951796395704,
      "epoch": 0.08922644360055766,
      "grad_norm": 0.11628861725330353,
      "learning_rate": 5e-07,
      "loss": 0.0511,
      "step": 956
    },
    {
      "clip_ratio/high_max": 0.0020460672021727078,
      "clip_ratio/high_mean": 0.0009265385997423436,
      "clip_ratio/low_mean": 0.0008913253477658145,
      "clip_ratio/low_min": 7.885193736001384e-05,
      "clip_ratio/region_mean": 0.0018178639220423065,
      "epoch": 0.08931977670055825,
      "grad_norm": 0.11042582988739014,
      "learning_rate": 5e-07,
      "loss": 0.0037,
      "step": 957
    },
    {
      "clip_ratio/high_max": 0.0019328765683894744,
      "clip_ratio/high_mean": 0.0009304786908614915,
      "clip_ratio/low_mean": 0.0009956949834304396,
      "clip_ratio/low_min": 8.42787403598777e-05,
      "clip_ratio/region_mean": 0.001926173696119804,
      "epoch": 0.08941310980055883,
      "grad_norm": 0.11228200793266296,
      "learning_rate": 5e-07,
      "loss": 0.0172,
      "step": 958
    },
    {
      "clip_ratio/high_max": 0.0020588454826793168,
      "clip_ratio/high_mean": 0.0007847553824831266,
      "clip_ratio/low_mean": 0.001234028230101103,
      "clip_ratio/low_min": 0.00016586403125984361,
      "clip_ratio/region_mean": 0.0020187836489640176,
      "epoch": 0.08950644290055941,
      "grad_norm": 0.11709770560264587,
      "learning_rate": 5e-07,
      "loss": 0.079,
      "step": 959
    },
    {
      "clip_ratio/high_max": 0.0022466425798484124,
      "clip_ratio/high_mean": 0.0009171205401798943,
      "clip_ratio/low_mean": 0.0008995030166261131,
      "clip_ratio/low_min": 9.69679640547838e-05,
      "clip_ratio/region_mean": 0.0018166235167882405,
      "epoch": 0.08959977600056,
      "grad_norm": 0.11100955307483673,
      "learning_rate": 5e-07,
      "loss": 0.018,
      "step": 960
    },
    {
      "clip_ratio/high_max": 0.0021048358394182287,
      "clip_ratio/high_mean": 0.0009580571058904752,
      "clip_ratio/low_mean": 0.000934408642933704,
      "clip_ratio/low_min": 5.621919444820378e-05,
      "clip_ratio/region_mean": 0.0018924657197203487,
      "epoch": 0.08969310910056058,
      "grad_norm": 21.868024826049805,
      "learning_rate": 5e-07,
      "loss": 0.0288,
      "step": 961
    },
    {
      "clip_ratio/high_max": 0.002177954556827899,
      "clip_ratio/high_mean": 0.0010266237004543655,
      "clip_ratio/low_mean": 0.0009100461866182741,
      "clip_ratio/low_min": 1.2929251170135103e-05,
      "clip_ratio/region_mean": 0.0019366698834346607,
      "epoch": 0.08978644220056116,
      "grad_norm": 0.11773865669965744,
      "learning_rate": 5e-07,
      "loss": 0.0092,
      "step": 962
    },
    {
      "clip_ratio/high_max": 0.001954525971086696,
      "clip_ratio/high_mean": 0.0008389090471609961,
      "clip_ratio/low_mean": 0.0009946290138032055,
      "clip_ratio/low_min": 3.083315368712647e-05,
      "clip_ratio/region_mean": 0.0018335380736971274,
      "epoch": 0.08987977530056175,
      "grad_norm": 0.11016586422920227,
      "learning_rate": 5e-07,
      "loss": 0.0461,
      "step": 963
    },
    {
      "clip_ratio/high_max": 0.002316186742973514,
      "clip_ratio/high_mean": 0.0009522791133349529,
      "clip_ratio/low_mean": 0.0010717098757595522,
      "clip_ratio/low_min": 4.590287608152721e-05,
      "clip_ratio/region_mean": 0.0020239889636286534,
      "epoch": 0.08997310840056233,
      "grad_norm": 0.3682974874973297,
      "learning_rate": 5e-07,
      "loss": 0.0385,
      "step": 964
    },
    {
      "clip_ratio/high_max": 0.002214317792095244,
      "clip_ratio/high_mean": 0.0008546637836843729,
      "clip_ratio/low_mean": 0.0012547514324978692,
      "clip_ratio/low_min": 3.0451373277173843e-05,
      "clip_ratio/region_mean": 0.002109415188897401,
      "epoch": 0.09006644150056292,
      "grad_norm": 0.106735959649086,
      "learning_rate": 5e-07,
      "loss": 0.0241,
      "step": 965
    },
    {
      "clip_ratio/high_max": 0.0022421118555939756,
      "clip_ratio/high_mean": 0.0008824813521641772,
      "clip_ratio/low_mean": 0.0010972808377118781,
      "clip_ratio/low_min": 0.0001468035188736394,
      "clip_ratio/region_mean": 0.001979762215341907,
      "epoch": 0.0901597746005635,
      "grad_norm": 0.12025323510169983,
      "learning_rate": 5e-07,
      "loss": 0.0478,
      "step": 966
    },
    {
      "clip_ratio/high_max": 0.0020695273342425935,
      "clip_ratio/high_mean": 0.0009056764174601994,
      "clip_ratio/low_mean": 0.001000844786176458,
      "clip_ratio/low_min": 2.951651458715787e-05,
      "clip_ratio/region_mean": 0.0019065211963606998,
      "epoch": 0.09025310770056408,
      "grad_norm": 0.10935835540294647,
      "learning_rate": 5e-07,
      "loss": 0.0685,
      "step": 967
    },
    {
      "clip_ratio/high_max": 0.002173374130507,
      "clip_ratio/high_mean": 0.0009679080176283605,
      "clip_ratio/low_mean": 0.0010369272076786729,
      "clip_ratio/low_min": 0.00010362943976360839,
      "clip_ratio/region_mean": 0.002004835201660171,
      "epoch": 0.09034644080056467,
      "grad_norm": 0.11729835718870163,
      "learning_rate": 5e-07,
      "loss": -0.0187,
      "step": 968
    },
    {
      "clip_ratio/high_max": 0.0020345329576230142,
      "clip_ratio/high_mean": 0.0008671464784129057,
      "clip_ratio/low_mean": 0.0011556440258573275,
      "clip_ratio/low_min": 0.00013024364761804463,
      "clip_ratio/region_mean": 0.002022790489718318,
      "epoch": 0.09043977390056525,
      "grad_norm": 0.11927514523267746,
      "learning_rate": 5e-07,
      "loss": 0.0908,
      "step": 969
    },
    {
      "clip_ratio/high_max": 0.00231765178614296,
      "clip_ratio/high_mean": 0.0010412746451038402,
      "clip_ratio/low_mean": 0.0009751990237418795,
      "clip_ratio/low_min": 2.4732872589083854e-05,
      "clip_ratio/region_mean": 0.0020164736633887514,
      "epoch": 0.09053310700056583,
      "grad_norm": 0.11860544979572296,
      "learning_rate": 5e-07,
      "loss": 0.0088,
      "step": 970
    },
    {
      "clip_ratio/high_max": 0.002207787307270337,
      "clip_ratio/high_mean": 0.0009798727769521065,
      "clip_ratio/low_mean": 0.0008572375900257612,
      "clip_ratio/low_min": 6.252024286368396e-05,
      "clip_ratio/region_mean": 0.0018371103797107935,
      "epoch": 0.09062644010056642,
      "grad_norm": 0.10444708913564682,
      "learning_rate": 5e-07,
      "loss": 0.0101,
      "step": 971
    },
    {
      "clip_ratio/high_max": 0.002148326333553996,
      "clip_ratio/high_mean": 0.0009136393109656638,
      "clip_ratio/low_mean": 0.001062278717654408,
      "clip_ratio/low_min": 9.342433259007521e-05,
      "clip_ratio/region_mean": 0.0019759179995162413,
      "epoch": 0.090719773200567,
      "grad_norm": 0.11868678778409958,
      "learning_rate": 5e-07,
      "loss": 0.032,
      "step": 972
    },
    {
      "clip_ratio/high_max": 0.002570564771303907,
      "clip_ratio/high_mean": 0.0009248002133972477,
      "clip_ratio/low_mean": 0.0009456613061047392,
      "clip_ratio/low_min": 6.976688655413454e-05,
      "clip_ratio/region_mean": 0.0018704615140450187,
      "epoch": 0.09081310630056758,
      "grad_norm": 0.11029942333698273,
      "learning_rate": 5e-07,
      "loss": 0.0238,
      "step": 973
    },
    {
      "clip_ratio/high_max": 0.002158529947337229,
      "clip_ratio/high_mean": 0.0009588531538611278,
      "clip_ratio/low_mean": 0.0009305395633418811,
      "clip_ratio/low_min": 8.298827015096322e-05,
      "clip_ratio/region_mean": 0.0018893926826422103,
      "epoch": 0.09090643940056817,
      "grad_norm": 0.12558189034461975,
      "learning_rate": 5e-07,
      "loss": 0.0251,
      "step": 974
    },
    {
      "clip_ratio/high_max": 0.0023243625946633983,
      "clip_ratio/high_mean": 0.0010779977183119627,
      "clip_ratio/low_mean": 0.001012314507534029,
      "clip_ratio/low_min": 0.00012921952475153375,
      "clip_ratio/region_mean": 0.002090312249492854,
      "epoch": 0.09099977250056875,
      "grad_norm": 0.11645650118589401,
      "learning_rate": 5e-07,
      "loss": 0.0688,
      "step": 975
    },
    {
      "clip_ratio/high_max": 0.0025633548939367756,
      "clip_ratio/high_mean": 0.0010349095500714611,
      "clip_ratio/low_mean": 0.0010729918103606906,
      "clip_ratio/low_min": 0.000197761697563692,
      "clip_ratio/region_mean": 0.0021079014040878974,
      "epoch": 0.09109310560056934,
      "grad_norm": 0.10748720169067383,
      "learning_rate": 5e-07,
      "loss": 0.0201,
      "step": 976
    },
    {
      "clip_ratio/high_max": 0.002115369868988637,
      "clip_ratio/high_mean": 0.0009130156631727004,
      "clip_ratio/low_mean": 0.0010770884800876956,
      "clip_ratio/low_min": 0.0001454974417356425,
      "clip_ratio/region_mean": 0.0019901041305274703,
      "epoch": 0.09118643870056992,
      "grad_norm": 0.13313792645931244,
      "learning_rate": 5e-07,
      "loss": 0.0292,
      "step": 977
    },
    {
      "clip_ratio/high_max": 0.0021080213628010824,
      "clip_ratio/high_mean": 0.0008793881806923309,
      "clip_ratio/low_mean": 0.0009135235195572022,
      "clip_ratio/low_min": 9.49780232986086e-05,
      "clip_ratio/region_mean": 0.0017929117384483106,
      "epoch": 0.0912797718005705,
      "grad_norm": 0.6339880228042603,
      "learning_rate": 5e-07,
      "loss": 0.0044,
      "step": 978
    },
    {
      "clip_ratio/high_max": 0.002233262319350615,
      "clip_ratio/high_mean": 0.0009812447606236674,
      "clip_ratio/low_mean": 0.0009908410356729291,
      "clip_ratio/low_min": 9.95518385025207e-05,
      "clip_ratio/region_mean": 0.001972085789020639,
      "epoch": 0.09137310490057109,
      "grad_norm": 0.1178952157497406,
      "learning_rate": 5e-07,
      "loss": -0.0019,
      "step": 979
    },
    {
      "clip_ratio/high_max": 0.0016948387674347032,
      "clip_ratio/high_mean": 0.0007403179624816403,
      "clip_ratio/low_mean": 0.0009482516688876785,
      "clip_ratio/low_min": 9.286381009587785e-05,
      "clip_ratio/region_mean": 0.0016885696386452764,
      "epoch": 0.09146643800057166,
      "grad_norm": 0.10221876949071884,
      "learning_rate": 5e-07,
      "loss": 0.0464,
      "step": 980
    },
    {
      "clip_ratio/high_max": 0.0024760757078183815,
      "clip_ratio/high_mean": 0.00097932132484857,
      "clip_ratio/low_mean": 0.0010654965044523124,
      "clip_ratio/low_min": 2.4490381292707752e-05,
      "clip_ratio/region_mean": 0.002044817854766734,
      "epoch": 0.09155977110057224,
      "grad_norm": 0.10975594073534012,
      "learning_rate": 5e-07,
      "loss": 0.0039,
      "step": 981
    },
    {
      "clip_ratio/high_max": 0.00231810243712971,
      "clip_ratio/high_mean": 0.000846937397000147,
      "clip_ratio/low_mean": 0.001106577034079237,
      "clip_ratio/low_min": 0.00014906192973285215,
      "clip_ratio/region_mean": 0.001953514445631299,
      "epoch": 0.09165310420057284,
      "grad_norm": 0.1142597571015358,
      "learning_rate": 5e-07,
      "loss": 0.0521,
      "step": 982
    },
    {
      "clip_ratio/high_max": 0.0024348415317945182,
      "clip_ratio/high_mean": 0.001066725828422932,
      "clip_ratio/low_mean": 0.0009216812650265638,
      "clip_ratio/low_min": 9.446830699744169e-05,
      "clip_ratio/region_mean": 0.0019884070788975805,
      "epoch": 0.09174643730057341,
      "grad_norm": 0.11149121075868607,
      "learning_rate": 5e-07,
      "loss": -0.0398,
      "step": 983
    },
    {
      "clip_ratio/high_max": 0.0020246925232640933,
      "clip_ratio/high_mean": 0.0008387900452362373,
      "clip_ratio/low_mean": 0.0010576203403616091,
      "clip_ratio/low_min": 0.00013838993982062675,
      "clip_ratio/region_mean": 0.0018964104201586451,
      "epoch": 0.09183977040057399,
      "grad_norm": 0.11129486560821533,
      "learning_rate": 5e-07,
      "loss": 0.0305,
      "step": 984
    },
    {
      "clip_ratio/high_max": 0.002085665524646174,
      "clip_ratio/high_mean": 0.0009475756487518083,
      "clip_ratio/low_mean": 0.0010269893464283086,
      "clip_ratio/low_min": 9.659369789005723e-05,
      "clip_ratio/region_mean": 0.0019745650279219262,
      "epoch": 0.09193310350057458,
      "grad_norm": 0.12400085479021072,
      "learning_rate": 5e-07,
      "loss": 0.0252,
      "step": 985
    },
    {
      "clip_ratio/high_max": 0.002251560566946864,
      "clip_ratio/high_mean": 0.0009906732193485368,
      "clip_ratio/low_mean": 0.0009220332813129062,
      "clip_ratio/low_min": 7.366217323578894e-05,
      "clip_ratio/region_mean": 0.001912706473376602,
      "epoch": 0.09202643660057516,
      "grad_norm": 0.11387068033218384,
      "learning_rate": 5e-07,
      "loss": 0.0356,
      "step": 986
    },
    {
      "clip_ratio/high_max": 0.0019073408657277469,
      "clip_ratio/high_mean": 0.0008442955513601191,
      "clip_ratio/low_mean": 0.0010548537065915298,
      "clip_ratio/low_min": 6.235654200281715e-05,
      "clip_ratio/region_mean": 0.0018991492470377125,
      "epoch": 0.09211976970057575,
      "grad_norm": 0.10795553028583527,
      "learning_rate": 5e-07,
      "loss": 0.0812,
      "step": 987
    },
    {
      "clip_ratio/high_max": 0.0022709864351782016,
      "clip_ratio/high_mean": 0.0008911958502721973,
      "clip_ratio/low_mean": 0.000811025074654026,
      "clip_ratio/low_min": 2.937429690064164e-05,
      "clip_ratio/region_mean": 0.0017022209176502656,
      "epoch": 0.09221310280057633,
      "grad_norm": 0.1131226196885109,
      "learning_rate": 5e-07,
      "loss": -0.0192,
      "step": 988
    },
    {
      "clip_ratio/high_max": 0.0021685307583538815,
      "clip_ratio/high_mean": 0.00091309882918722,
      "clip_ratio/low_mean": 0.0009213556950271595,
      "clip_ratio/low_min": 2.7944603061769158e-05,
      "clip_ratio/region_mean": 0.0018344545460422523,
      "epoch": 0.09230643590057691,
      "grad_norm": 0.1151103526353836,
      "learning_rate": 5e-07,
      "loss": 0.0435,
      "step": 989
    },
    {
      "clip_ratio/high_max": 0.0024156406143447384,
      "clip_ratio/high_mean": 0.0009811574927880429,
      "clip_ratio/low_mean": 0.0008037786610657349,
      "clip_ratio/low_min": 2.9783179343212396e-05,
      "clip_ratio/region_mean": 0.0017849361247499473,
      "epoch": 0.0923997690005775,
      "grad_norm": 0.11530765891075134,
      "learning_rate": 5e-07,
      "loss": -0.0459,
      "step": 990
    },
    {
      "clip_ratio/high_max": 0.002103297687426675,
      "clip_ratio/high_mean": 0.0008574206731282175,
      "clip_ratio/low_mean": 0.00100969620871183,
      "clip_ratio/low_min": 0.00016914000025280984,
      "clip_ratio/region_mean": 0.0018671168581931852,
      "epoch": 0.09249310210057808,
      "grad_norm": 0.11689867079257965,
      "learning_rate": 5e-07,
      "loss": 0.0067,
      "step": 991
    },
    {
      "clip_ratio/high_max": 0.002106790638208622,
      "clip_ratio/high_mean": 0.000914823031052947,
      "clip_ratio/low_mean": 0.0010766307350422721,
      "clip_ratio/low_min": 4.063961205247324e-05,
      "clip_ratio/region_mean": 0.001991453784285113,
      "epoch": 0.09258643520057866,
      "grad_norm": 0.1361193060874939,
      "learning_rate": 5e-07,
      "loss": 0.0627,
      "step": 992
    },
    {
      "clip_ratio/high_max": 0.002363131548918318,
      "clip_ratio/high_mean": 0.0008281198061013129,
      "clip_ratio/low_mean": 0.0010558670255704783,
      "clip_ratio/low_min": 8.180376244126819e-05,
      "clip_ratio/region_mean": 0.0018839868134818971,
      "epoch": 0.09267976830057925,
      "grad_norm": 50.25945281982422,
      "learning_rate": 5e-07,
      "loss": 0.0478,
      "step": 993
    },
    {
      "clip_ratio/high_max": 0.002048044276307337,
      "clip_ratio/high_mean": 0.0009514352896076161,
      "clip_ratio/low_mean": 0.0009282869887101697,
      "clip_ratio/low_min": 0.00011795665886893403,
      "clip_ratio/region_mean": 0.001879722229205072,
      "epoch": 0.09277310140057983,
      "grad_norm": 0.11072017252445221,
      "learning_rate": 5e-07,
      "loss": 0.0189,
      "step": 994
    },
    {
      "clip_ratio/high_max": 0.0023240536102093756,
      "clip_ratio/high_mean": 0.0009537540463497862,
      "clip_ratio/low_mean": 0.001069461502993363,
      "clip_ratio/low_min": 0.0001398277199768927,
      "clip_ratio/region_mean": 0.002023215634835651,
      "epoch": 0.09286643450058042,
      "grad_norm": 0.10506325215101242,
      "learning_rate": 5e-07,
      "loss": 0.0231,
      "step": 995
    },
    {
      "clip_ratio/high_max": 0.0025432100737816654,
      "clip_ratio/high_mean": 0.000942370683333138,
      "clip_ratio/low_mean": 0.0010718456360336859,
      "clip_ratio/low_min": 0.00020796691205759998,
      "clip_ratio/region_mean": 0.002014216297538951,
      "epoch": 0.092959767600581,
      "grad_norm": 0.12636956572532654,
      "learning_rate": 5e-07,
      "loss": 0.0332,
      "step": 996
    },
    {
      "clip_ratio/high_max": 0.0020813251394429244,
      "clip_ratio/high_mean": 0.000935487250899314,
      "clip_ratio/low_mean": 0.0009465133662160952,
      "clip_ratio/low_min": 8.295455063489499e-05,
      "clip_ratio/region_mean": 0.0018820006007445045,
      "epoch": 0.09305310070058158,
      "grad_norm": 0.11039713025093079,
      "learning_rate": 5e-07,
      "loss": 0.0165,
      "step": 997
    },
    {
      "clip_ratio/high_max": 0.001846474038757151,
      "clip_ratio/high_mean": 0.0008347658713319106,
      "clip_ratio/low_mean": 0.000868576511493302,
      "clip_ratio/low_min": 6.250588467082707e-05,
      "clip_ratio/region_mean": 0.0017033424010151066,
      "epoch": 0.09314643380058217,
      "grad_norm": 0.10434214770793915,
      "learning_rate": 5e-07,
      "loss": 0.0266,
      "step": 998
    },
    {
      "clip_ratio/high_max": 0.002086041888105683,
      "clip_ratio/high_mean": 0.0008420690355706029,
      "clip_ratio/low_mean": 0.0008613486788817681,
      "clip_ratio/low_min": 8.83855327629135e-05,
      "clip_ratio/region_mean": 0.001703417714452371,
      "epoch": 0.09323976690058275,
      "grad_norm": 0.5840059518814087,
      "learning_rate": 5e-07,
      "loss": 0.0174,
      "step": 999
    },
    {
      "clip_ratio/high_max": 0.0018356464679527562,
      "clip_ratio/high_mean": 0.0007962719555507647,
      "clip_ratio/low_mean": 0.0010287815021001734,
      "clip_ratio/low_min": 8.147242078848649e-05,
      "clip_ratio/region_mean": 0.001825053470383864,
      "epoch": 0.09333310000058333,
      "grad_norm": 0.11712446063756943,
      "learning_rate": 5e-07,
      "loss": 0.0411,
      "step": 1000
    },
    {
      "clip_ratio/high_max": 0.001974972943571629,
      "clip_ratio/high_mean": 0.0009361555585201131,
      "clip_ratio/low_mean": 0.0009770892229425954,
      "clip_ratio/low_min": 0.0001318722133873962,
      "clip_ratio/region_mean": 0.001913244770548772,
      "epoch": 0.09342643310058392,
      "grad_norm": 0.1130756139755249,
      "learning_rate": 5e-07,
      "loss": 0.0579,
      "step": 1001
    },
    {
      "clip_ratio/high_max": 0.0018919415342679713,
      "clip_ratio/high_mean": 0.0009118956331803929,
      "clip_ratio/low_mean": 0.0010168195767619181,
      "clip_ratio/low_min": 3.187417678418569e-05,
      "clip_ratio/region_mean": 0.001928715173562523,
      "epoch": 0.0935197662005845,
      "grad_norm": 0.11453714966773987,
      "learning_rate": 5e-07,
      "loss": -0.0258,
      "step": 1002
    },
    {
      "clip_ratio/high_max": 0.002265599920065142,
      "clip_ratio/high_mean": 0.0008944212568167131,
      "clip_ratio/low_mean": 0.001120772594731534,
      "clip_ratio/low_min": 0.00016242703168245498,
      "clip_ratio/region_mean": 0.0020151938842900563,
      "epoch": 0.09361309930058508,
      "grad_norm": 0.1146450862288475,
      "learning_rate": 5e-07,
      "loss": 0.0113,
      "step": 1003
    },
    {
      "clip_ratio/high_max": 0.0021868372132303193,
      "clip_ratio/high_mean": 0.0009720870802993886,
      "clip_ratio/low_mean": 0.0009722243339638226,
      "clip_ratio/low_min": 0.00012833414075430483,
      "clip_ratio/region_mean": 0.0019443114579189569,
      "epoch": 0.09370643240058567,
      "grad_norm": 0.14548265933990479,
      "learning_rate": 5e-07,
      "loss": 0.0205,
      "step": 1004
    },
    {
      "clip_ratio/high_max": 0.0020526940461422782,
      "clip_ratio/high_mean": 0.000808033468274516,
      "clip_ratio/low_mean": 0.0010596357169561088,
      "clip_ratio/low_min": 0.00012434596828825306,
      "clip_ratio/region_mean": 0.0018676691761356778,
      "epoch": 0.09379976550058625,
      "grad_norm": 2.4370315074920654,
      "learning_rate": 5e-07,
      "loss": 0.0758,
      "step": 1005
    },
    {
      "clip_ratio/high_max": 0.0023020216322038323,
      "clip_ratio/high_mean": 0.0009609109129087301,
      "clip_ratio/low_mean": 0.00099135783057136,
      "clip_ratio/low_min": 0.0001245972507604165,
      "clip_ratio/region_mean": 0.0019522687580320053,
      "epoch": 0.09389309860058684,
      "grad_norm": 0.11294698715209961,
      "learning_rate": 5e-07,
      "loss": -0.006,
      "step": 1006
    },
    {
      "clip_ratio/high_max": 0.002063705149339512,
      "clip_ratio/high_mean": 0.0009231886760971975,
      "clip_ratio/low_mean": 0.0010051676181319635,
      "clip_ratio/low_min": 6.983386992942542e-05,
      "clip_ratio/region_mean": 0.0019283562724012882,
      "epoch": 0.09398643170058742,
      "grad_norm": 0.11479725688695908,
      "learning_rate": 5e-07,
      "loss": -0.0148,
      "step": 1007
    },
    {
      "clip_ratio/high_max": 0.002191044834034983,
      "clip_ratio/high_mean": 0.0010158109780604718,
      "clip_ratio/low_mean": 0.0010391285140940454,
      "clip_ratio/low_min": 0.0001015610660033417,
      "clip_ratio/region_mean": 0.0020549394976114854,
      "epoch": 0.094079764800588,
      "grad_norm": 0.12114706635475159,
      "learning_rate": 5e-07,
      "loss": 0.0591,
      "step": 1008
    },
    {
      "clip_ratio/high_max": 0.002005515812925296,
      "clip_ratio/high_mean": 0.0008423810395470355,
      "clip_ratio/low_mean": 0.0008998315515782451,
      "clip_ratio/low_min": 6.116491658758605e-05,
      "clip_ratio/region_mean": 0.0017422126038582064,
      "epoch": 0.09417309790058859,
      "grad_norm": 0.10689125955104828,
      "learning_rate": 5e-07,
      "loss": 0.0514,
      "step": 1009
    },
    {
      "clip_ratio/high_max": 0.00251624400698347,
      "clip_ratio/high_mean": 0.0010842727842828026,
      "clip_ratio/low_mean": 0.0009701305771159241,
      "clip_ratio/low_min": 2.4786833819234744e-05,
      "clip_ratio/region_mean": 0.0020544034268823452,
      "epoch": 0.09426643100058917,
      "grad_norm": 0.11726424843072891,
      "learning_rate": 5e-07,
      "loss": 0.0098,
      "step": 1010
    },
    {
      "clip_ratio/high_max": 0.0019699164222402032,
      "clip_ratio/high_mean": 0.0008460179669782519,
      "clip_ratio/low_mean": 0.0011219401803828077,
      "clip_ratio/low_min": 7.694403666391736e-05,
      "clip_ratio/region_mean": 0.0019679581600939855,
      "epoch": 0.09435976410058974,
      "grad_norm": 0.10436174273490906,
      "learning_rate": 5e-07,
      "loss": 0.0314,
      "step": 1011
    },
    {
      "clip_ratio/high_max": 0.0017978686446440406,
      "clip_ratio/high_mean": 0.0007237317604449345,
      "clip_ratio/low_mean": 0.0011135144013678655,
      "clip_ratio/low_min": 6.917973223607987e-05,
      "clip_ratio/region_mean": 0.001837246207287535,
      "epoch": 0.09445309720059034,
      "grad_norm": 0.10462549328804016,
      "learning_rate": 5e-07,
      "loss": 0.0403,
      "step": 1012
    },
    {
      "clip_ratio/high_max": 0.0023731244800728746,
      "clip_ratio/high_mean": 0.0010238684553769417,
      "clip_ratio/low_mean": 0.0010406536202935968,
      "clip_ratio/low_min": 9.934945410350338e-05,
      "clip_ratio/region_mean": 0.002064522086584475,
      "epoch": 0.09454643030059091,
      "grad_norm": 0.11038922518491745,
      "learning_rate": 5e-07,
      "loss": 0.0222,
      "step": 1013
    },
    {
      "clip_ratio/high_max": 0.0021333680124371313,
      "clip_ratio/high_mean": 0.000885005380041548,
      "clip_ratio/low_mean": 0.0009521445881546242,
      "clip_ratio/low_min": 7.020977227512049e-05,
      "clip_ratio/region_mean": 0.0018371499318163842,
      "epoch": 0.09463976340059149,
      "grad_norm": 0.12210293114185333,
      "learning_rate": 5e-07,
      "loss": 0.0069,
      "step": 1014
    },
    {
      "clip_ratio/high_max": 0.0021079362304590177,
      "clip_ratio/high_mean": 0.0008717222117411438,
      "clip_ratio/low_mean": 0.0009115052253036993,
      "clip_ratio/low_min": 2.017430597334169e-05,
      "clip_ratio/region_mean": 0.0017832273988460656,
      "epoch": 0.09473309650059208,
      "grad_norm": 0.15033791959285736,
      "learning_rate": 5e-07,
      "loss": 0.0209,
      "step": 1015
    },
    {
      "clip_ratio/high_max": 0.0027088019669463392,
      "clip_ratio/high_mean": 0.0009883013135549845,
      "clip_ratio/low_mean": 0.0010465963878232287,
      "clip_ratio/low_min": 2.0600259631464723e-05,
      "clip_ratio/region_mean": 0.0020348977195681073,
      "epoch": 0.09482642960059266,
      "grad_norm": 0.11450639367103577,
      "learning_rate": 5e-07,
      "loss": 0.0078,
      "step": 1016
    },
    {
      "clip_ratio/high_max": 0.0021296147860994097,
      "clip_ratio/high_mean": 0.0008815582677925704,
      "clip_ratio/low_mean": 0.0010176567066082498,
      "clip_ratio/low_min": 5.809419963043183e-05,
      "clip_ratio/region_mean": 0.0018992149562109262,
      "epoch": 0.09491976270059325,
      "grad_norm": 0.11787446588277817,
      "learning_rate": 5e-07,
      "loss": 0.0409,
      "step": 1017
    },
    {
      "clip_ratio/high_max": 0.002527548342186492,
      "clip_ratio/high_mean": 0.0010103462809638586,
      "clip_ratio/low_mean": 0.0009610384040570352,
      "clip_ratio/low_min": 0.00014679648893434205,
      "clip_ratio/region_mean": 0.001971384663193021,
      "epoch": 0.09501309580059383,
      "grad_norm": 0.12233970314264297,
      "learning_rate": 5e-07,
      "loss": 0.002,
      "step": 1018
    },
    {
      "clip_ratio/high_max": 0.0028641849203268066,
      "clip_ratio/high_mean": 0.0010261195966450032,
      "clip_ratio/low_mean": 0.000998319508653367,
      "clip_ratio/low_min": 1.2950683412782382e-05,
      "clip_ratio/region_mean": 0.0020244391198502854,
      "epoch": 0.09510642890059441,
      "grad_norm": 0.12294541299343109,
      "learning_rate": 5e-07,
      "loss": 0.0254,
      "step": 1019
    },
    {
      "clip_ratio/high_max": 0.0022295034723356366,
      "clip_ratio/high_mean": 0.001100413250242127,
      "clip_ratio/low_mean": 0.0009224814348272048,
      "clip_ratio/low_min": 1.5221627108985558e-05,
      "clip_ratio/region_mean": 0.002022894703259226,
      "epoch": 0.095199762000595,
      "grad_norm": 0.1103283017873764,
      "learning_rate": 5e-07,
      "loss": -0.0052,
      "step": 1020
    },
    {
      "clip_ratio/high_max": 0.0023684393308940344,
      "clip_ratio/high_mean": 0.0008835133812681306,
      "clip_ratio/low_mean": 0.0008730428507988108,
      "clip_ratio/low_min": 6.544116149598267e-05,
      "clip_ratio/region_mean": 0.0017565563030075282,
      "epoch": 0.09529309510059558,
      "grad_norm": 0.10887826979160309,
      "learning_rate": 5e-07,
      "loss": 0.0264,
      "step": 1021
    },
    {
      "clip_ratio/high_max": 0.002519713350920938,
      "clip_ratio/high_mean": 0.0009696904235170223,
      "clip_ratio/low_mean": 0.0008964370208559558,
      "clip_ratio/low_min": 4.275186802260578e-05,
      "clip_ratio/region_mean": 0.0018661274298210628,
      "epoch": 0.09538642820059616,
      "grad_norm": 0.110014408826828,
      "learning_rate": 5e-07,
      "loss": 0.0024,
      "step": 1022
    },
    {
      "clip_ratio/high_max": 0.0023619019993930124,
      "clip_ratio/high_mean": 0.0009851991708274,
      "clip_ratio/low_mean": 0.0009356720474897884,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0019208712474210188,
      "epoch": 0.09547976130059675,
      "grad_norm": 0.11661238968372345,
      "learning_rate": 5e-07,
      "loss": 0.0152,
      "step": 1023
    },
    {
      "clip_ratio/high_max": 0.002327304671780439,
      "clip_ratio/high_mean": 0.0010147794710064773,
      "clip_ratio/low_mean": 0.0010526172609388595,
      "clip_ratio/low_min": 7.201347034424543e-05,
      "clip_ratio/region_mean": 0.002067396715574432,
      "epoch": 0.09557309440059733,
      "grad_norm": 0.12166507542133331,
      "learning_rate": 5e-07,
      "loss": 0.0242,
      "step": 1024
    },
    {
      "clip_ratio/high_max": 0.0024656550667714328,
      "clip_ratio/high_mean": 0.0009675178971519927,
      "clip_ratio/low_mean": 0.0009815633238758892,
      "clip_ratio/low_min": 3.682127407955704e-05,
      "clip_ratio/region_mean": 0.0019490812119329348,
      "epoch": 0.09566642750059791,
      "grad_norm": 0.12181282788515091,
      "learning_rate": 5e-07,
      "loss": 0.0204,
      "step": 1025
    },
    {
      "clip_ratio/high_max": 0.0022497046702483203,
      "clip_ratio/high_mean": 0.0009307285436079837,
      "clip_ratio/low_mean": 0.0011058233812946128,
      "clip_ratio/low_min": 7.424076466122642e-05,
      "clip_ratio/region_mean": 0.002036551864875946,
      "epoch": 0.0957597606005985,
      "grad_norm": 0.1197674572467804,
      "learning_rate": 5e-07,
      "loss": 0.0473,
      "step": 1026
    },
    {
      "clip_ratio/high_max": 0.0021837812346348073,
      "clip_ratio/high_mean": 0.0009057742445293115,
      "clip_ratio/low_mean": 0.0010671629297576146,
      "clip_ratio/low_min": 0.00013212829253461678,
      "clip_ratio/region_mean": 0.0019729372070287354,
      "epoch": 0.09585309370059908,
      "grad_norm": 0.10953060537576675,
      "learning_rate": 5e-07,
      "loss": 0.0342,
      "step": 1027
    },
    {
      "clip_ratio/high_max": 0.0022652543157164473,
      "clip_ratio/high_mean": 0.0009267448403988965,
      "clip_ratio/low_mean": 0.0008160357210726943,
      "clip_ratio/low_min": 4.202529999020044e-05,
      "clip_ratio/region_mean": 0.0017427805360057391,
      "epoch": 0.09594642680059967,
      "grad_norm": 0.10257535427808762,
      "learning_rate": 5e-07,
      "loss": -0.0227,
      "step": 1028
    },
    {
      "clip_ratio/high_max": 0.001939277946803486,
      "clip_ratio/high_mean": 0.0007433668633893831,
      "clip_ratio/low_mean": 0.0010274984888383187,
      "clip_ratio/low_min": 0.0002221696731794509,
      "clip_ratio/region_mean": 0.0017708653685986064,
      "epoch": 0.09603975990060025,
      "grad_norm": 0.10511410236358643,
      "learning_rate": 5e-07,
      "loss": 0.0683,
      "step": 1029
    },
    {
      "clip_ratio/high_max": 0.0018748915681499057,
      "clip_ratio/high_mean": 0.0007804163869877812,
      "clip_ratio/low_mean": 0.0008393024791075732,
      "clip_ratio/low_min": 1.3119227332936134e-05,
      "clip_ratio/region_mean": 0.0016197188342630398,
      "epoch": 0.09613309300060083,
      "grad_norm": 0.1497471183538437,
      "learning_rate": 5e-07,
      "loss": 0.0269,
      "step": 1030
    },
    {
      "clip_ratio/high_max": 0.00226078449486522,
      "clip_ratio/high_mean": 0.0009597026510164142,
      "clip_ratio/low_mean": 0.0009925343401846476,
      "clip_ratio/low_min": 1.4902241673553362e-05,
      "clip_ratio/region_mean": 0.0019522369766491465,
      "epoch": 0.09622642610060142,
      "grad_norm": 0.11177154630422592,
      "learning_rate": 5e-07,
      "loss": 0.0202,
      "step": 1031
    },
    {
      "clip_ratio/high_max": 0.0021318276994861662,
      "clip_ratio/high_mean": 0.000937619251999422,
      "clip_ratio/low_mean": 0.0009711780257930513,
      "clip_ratio/low_min": 7.39625065762084e-05,
      "clip_ratio/region_mean": 0.001908797275973484,
      "epoch": 0.096319759200602,
      "grad_norm": 0.11492336541414261,
      "learning_rate": 5e-07,
      "loss": 0.0239,
      "step": 1032
    },
    {
      "clip_ratio/high_max": 0.0022674433566862717,
      "clip_ratio/high_mean": 0.0009318885659013176,
      "clip_ratio/low_mean": 0.0009815595985855907,
      "clip_ratio/low_min": 3.6016326703247614e-05,
      "clip_ratio/region_mean": 0.0019134481481160037,
      "epoch": 0.09641309230060258,
      "grad_norm": 0.11505351215600967,
      "learning_rate": 5e-07,
      "loss": 0.0133,
      "step": 1033
    },
    {
      "clip_ratio/high_max": 0.002434283815091476,
      "clip_ratio/high_mean": 0.001022454809572082,
      "clip_ratio/low_mean": 0.001011522312182933,
      "clip_ratio/low_min": 0.00011008987075911136,
      "clip_ratio/region_mean": 0.002033977165410761,
      "epoch": 0.09650642540060317,
      "grad_norm": 0.11140173673629761,
      "learning_rate": 5e-07,
      "loss": 0.0083,
      "step": 1034
    },
    {
      "clip_ratio/high_max": 0.002226000156952068,
      "clip_ratio/high_mean": 0.0009798241590033285,
      "clip_ratio/low_mean": 0.000975003309577005,
      "clip_ratio/low_min": 6.376955116138561e-05,
      "clip_ratio/region_mean": 0.001954827457666397,
      "epoch": 0.09659975850060375,
      "grad_norm": 0.11552412062883377,
      "learning_rate": 5e-07,
      "loss": 0.0169,
      "step": 1035
    },
    {
      "clip_ratio/high_max": 0.0019443732453510165,
      "clip_ratio/high_mean": 0.0009342259509139694,
      "clip_ratio/low_mean": 0.0011515831865835935,
      "clip_ratio/low_min": 0.0001679703600530047,
      "clip_ratio/region_mean": 0.002085809137497563,
      "epoch": 0.09669309160060433,
      "grad_norm": 0.11461059004068375,
      "learning_rate": 5e-07,
      "loss": 0.0262,
      "step": 1036
    },
    {
      "clip_ratio/high_max": 0.0017714903297019191,
      "clip_ratio/high_mean": 0.0007995432315510698,
      "clip_ratio/low_mean": 0.0009749070304678753,
      "clip_ratio/low_min": 9.30642599996645e-05,
      "clip_ratio/region_mean": 0.001774450283846818,
      "epoch": 0.09678642470060492,
      "grad_norm": 0.11579829454421997,
      "learning_rate": 5e-07,
      "loss": 0.0346,
      "step": 1037
    },
    {
      "clip_ratio/high_max": 0.0020869940890406724,
      "clip_ratio/high_mean": 0.0007968434711074224,
      "clip_ratio/low_mean": 0.0010889887707890011,
      "clip_ratio/low_min": 0.00014380147968040546,
      "clip_ratio/region_mean": 0.001885832280095201,
      "epoch": 0.0968797578006055,
      "grad_norm": 0.11190187186002731,
      "learning_rate": 5e-07,
      "loss": 0.0578,
      "step": 1038
    },
    {
      "clip_ratio/high_max": 0.002134578018740285,
      "clip_ratio/high_mean": 0.0008647210452181753,
      "clip_ratio/low_mean": 0.0008962968931882642,
      "clip_ratio/low_min": 1.9147365037497366e-05,
      "clip_ratio/region_mean": 0.0017610179638722911,
      "epoch": 0.09697309090060609,
      "grad_norm": 0.1166071966290474,
      "learning_rate": 5e-07,
      "loss": 0.0425,
      "step": 1039
    },
    {
      "clip_ratio/high_max": 0.001981944573344663,
      "clip_ratio/high_mean": 0.0008655373803776456,
      "clip_ratio/low_mean": 0.0010323051756131463,
      "clip_ratio/low_min": 5.6270599088747986e-05,
      "clip_ratio/region_mean": 0.001897842543257866,
      "epoch": 0.09706642400060667,
      "grad_norm": 0.11254685372114182,
      "learning_rate": 5e-07,
      "loss": 0.0191,
      "step": 1040
    },
    {
      "clip_ratio/high_max": 0.0018734747936832719,
      "clip_ratio/high_mean": 0.0008154464139806805,
      "clip_ratio/low_mean": 0.0009465540770179359,
      "clip_ratio/low_min": 1.6819160009617917e-05,
      "clip_ratio/region_mean": 0.00176200048008468,
      "epoch": 0.09715975710060724,
      "grad_norm": 0.11511718481779099,
      "learning_rate": 5e-07,
      "loss": 0.0393,
      "step": 1041
    },
    {
      "clip_ratio/high_max": 0.0022241202350414824,
      "clip_ratio/high_mean": 0.0009806482848944142,
      "clip_ratio/low_mean": 0.0009688854224805254,
      "clip_ratio/low_min": 5.0648831347643863e-05,
      "clip_ratio/region_mean": 0.0019495336746331304,
      "epoch": 0.09725309020060784,
      "grad_norm": 0.12020670622587204,
      "learning_rate": 5e-07,
      "loss": 0.0554,
      "step": 1042
    },
    {
      "clip_ratio/high_max": 0.0023032282988424413,
      "clip_ratio/high_mean": 0.0009786597911443096,
      "clip_ratio/low_mean": 0.0009140559041043161,
      "clip_ratio/low_min": 4.4062582674087025e-05,
      "clip_ratio/region_mean": 0.0018927156779682264,
      "epoch": 0.09734642330060841,
      "grad_norm": 0.11397317796945572,
      "learning_rate": 5e-07,
      "loss": 0.0043,
      "step": 1043
    },
    {
      "clip_ratio/high_max": 0.0022054912042221986,
      "clip_ratio/high_mean": 0.0009428022804058855,
      "clip_ratio/low_mean": 0.0008957411573646823,
      "clip_ratio/low_min": 5.522457831830252e-05,
      "clip_ratio/region_mean": 0.0018385434377705678,
      "epoch": 0.09743975640060899,
      "grad_norm": 0.1241626963019371,
      "learning_rate": 5e-07,
      "loss": 0.0147,
      "step": 1044
    },
    {
      "clip_ratio/high_max": 0.0022523849474964663,
      "clip_ratio/high_mean": 0.0009251657020286075,
      "clip_ratio/low_mean": 0.0011783946793002542,
      "clip_ratio/low_min": 3.573360118025448e-05,
      "clip_ratio/region_mean": 0.0021035604222561233,
      "epoch": 0.09753308950060958,
      "grad_norm": 0.11126670241355896,
      "learning_rate": 5e-07,
      "loss": 0.0198,
      "step": 1045
    },
    {
      "clip_ratio/high_max": 0.002411944187770132,
      "clip_ratio/high_mean": 0.0010463390572112985,
      "clip_ratio/low_mean": 0.0009699678630568087,
      "clip_ratio/low_min": 6.321912769635674e-05,
      "clip_ratio/region_mean": 0.002016306905716192,
      "epoch": 0.09762642260061016,
      "grad_norm": 0.12769834697246552,
      "learning_rate": 5e-07,
      "loss": 0.005,
      "step": 1046
    },
    {
      "clip_ratio/high_max": 0.002117675365298055,
      "clip_ratio/high_mean": 0.0008758302665228257,
      "clip_ratio/low_mean": 0.0010962207725242479,
      "clip_ratio/low_min": 0.0001726498076095595,
      "clip_ratio/region_mean": 0.0019720510354090948,
      "epoch": 0.09771975570061076,
      "grad_norm": 0.10683926194906235,
      "learning_rate": 5e-07,
      "loss": 0.0352,
      "step": 1047
    },
    {
      "clip_ratio/high_max": 0.0021906011970713735,
      "clip_ratio/high_mean": 0.0008680813953105826,
      "clip_ratio/low_mean": 0.0009143129227595637,
      "clip_ratio/low_min": 0.00010559952352195978,
      "clip_ratio/region_mean": 0.0017823943162511569,
      "epoch": 0.09781308880061133,
      "grad_norm": 0.11861345171928406,
      "learning_rate": 5e-07,
      "loss": 0.0127,
      "step": 1048
    },
    {
      "clip_ratio/high_max": 0.002196191344410181,
      "clip_ratio/high_mean": 0.0008676039578858763,
      "clip_ratio/low_mean": 0.0009033143651322462,
      "clip_ratio/low_min": 3.585360536817461e-05,
      "clip_ratio/region_mean": 0.00177091833029408,
      "epoch": 0.09790642190061191,
      "grad_norm": 0.11755044758319855,
      "learning_rate": 5e-07,
      "loss": 0.0348,
      "step": 1049
    },
    {
      "clip_ratio/high_max": 0.0020470966592256445,
      "clip_ratio/high_mean": 0.0008786370908637764,
      "clip_ratio/low_mean": 0.0010763483041955624,
      "clip_ratio/low_min": 6.019006650603842e-05,
      "clip_ratio/region_mean": 0.0019549853896023706,
      "epoch": 0.0979997550006125,
      "grad_norm": 1.0724800825119019,
      "learning_rate": 5e-07,
      "loss": 0.0236,
      "step": 1050
    },
    {
      "clip_ratio/high_max": 0.0021888836854486726,
      "clip_ratio/high_mean": 0.0009554572243359871,
      "clip_ratio/low_mean": 0.0007583990209241165,
      "clip_ratio/low_min": 3.1079063774086535e-05,
      "clip_ratio/region_mean": 0.0017138562543550506,
      "epoch": 0.09809308810061308,
      "grad_norm": 0.0966401919722557,
      "learning_rate": 5e-07,
      "loss": 0.0085,
      "step": 1051
    },
    {
      "clip_ratio/high_max": 0.0022439352433138993,
      "clip_ratio/high_mean": 0.0009094592187466333,
      "clip_ratio/low_mean": 0.0009729887897265144,
      "clip_ratio/low_min": 0.00017061396829376463,
      "clip_ratio/region_mean": 0.0018824479848262854,
      "epoch": 0.09818642120061366,
      "grad_norm": 0.11266981065273285,
      "learning_rate": 5e-07,
      "loss": 0.0414,
      "step": 1052
    },
    {
      "clip_ratio/high_max": 0.002138004216249101,
      "clip_ratio/high_mean": 0.0009318743068433832,
      "clip_ratio/low_mean": 0.0010621133023960283,
      "clip_ratio/low_min": 7.0878667429497e-05,
      "clip_ratio/region_mean": 0.0019939875492127612,
      "epoch": 0.09827975430061425,
      "grad_norm": 0.11593242734670639,
      "learning_rate": 5e-07,
      "loss": 0.0426,
      "step": 1053
    },
    {
      "clip_ratio/high_max": 0.002322636057215277,
      "clip_ratio/high_mean": 0.0008413280302193016,
      "clip_ratio/low_mean": 0.0011488797936181072,
      "clip_ratio/low_min": 0.00014730351995240198,
      "clip_ratio/region_mean": 0.0019902078056475148,
      "epoch": 0.09837308740061483,
      "grad_norm": 0.10903412103652954,
      "learning_rate": 5e-07,
      "loss": 0.0596,
      "step": 1054
    },
    {
      "clip_ratio/high_max": 0.001931171544129029,
      "clip_ratio/high_mean": 0.000879823444847716,
      "clip_ratio/low_mean": 0.0010236020661977818,
      "clip_ratio/low_min": 0.00013668513020093087,
      "clip_ratio/region_mean": 0.0019034255237784237,
      "epoch": 0.09846642050061541,
      "grad_norm": 0.10917110741138458,
      "learning_rate": 5e-07,
      "loss": 0.0153,
      "step": 1055
    },
    {
      "clip_ratio/high_max": 0.0022215641729417257,
      "clip_ratio/high_mean": 0.0007768313535052584,
      "clip_ratio/low_mean": 0.0009227212667610729,
      "clip_ratio/low_min": 0.0001040889292198699,
      "clip_ratio/region_mean": 0.0016995526239043102,
      "epoch": 0.098559753600616,
      "grad_norm": 0.1082438975572586,
      "learning_rate": 5e-07,
      "loss": 0.071,
      "step": 1056
    },
    {
      "clip_ratio/high_max": 0.002268485910462914,
      "clip_ratio/high_mean": 0.00089882673091779,
      "clip_ratio/low_mean": 0.0009077229915419593,
      "clip_ratio/low_min": 5.3435087465913966e-05,
      "clip_ratio/region_mean": 0.0018065497279167175,
      "completions/clipped_ratio": 0.014011928013392905,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4094.0,
      "completions/mean_length": 610.4818115234375,
      "completions/mean_terminated_length": 560.948974609375,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.09865308670061658,
      "grad_norm": 2.300367593765259,
      "learning_rate": 5e-07,
      "loss": 0.0154,
      "num_tokens": 815609820.0,
      "reward": 0.5848737955093384,
      "reward_std": 0.1935143917798996,
      "rewards/simpleverify_reward/mean": 0.5848737359046936,
      "rewards/simpleverify_reward/std": 0.492745965719223,
      "step": 1057
    },
    {
      "clip_ratio/high_max": 0.00169151786758448,
      "clip_ratio/high_mean": 0.0008696242348378291,
      "clip_ratio/low_mean": 0.0010439887264510617,
      "clip_ratio/low_min": 0.00014855503104627132,
      "clip_ratio/region_mean": 0.0019136129340040497,
      "epoch": 0.09874641980061717,
      "grad_norm": 0.21787911653518677,
      "learning_rate": 5e-07,
      "loss": 0.0434,
      "step": 1058
    },
    {
      "clip_ratio/high_max": 0.002550643497670535,
      "clip_ratio/high_mean": 0.0009759423082869034,
      "clip_ratio/low_mean": 0.000913508192752488,
      "clip_ratio/low_min": 5.9004497416026425e-05,
      "clip_ratio/region_mean": 0.0018894504828494973,
      "epoch": 0.09883975290061775,
      "grad_norm": 0.10338770598173141,
      "learning_rate": 5e-07,
      "loss": 0.0169,
      "step": 1059
    },
    {
      "clip_ratio/high_max": 0.0021766643912997097,
      "clip_ratio/high_mean": 0.0009132243940257467,
      "clip_ratio/low_mean": 0.0010667138631106354,
      "clip_ratio/low_min": 7.977062341524288e-05,
      "clip_ratio/region_mean": 0.001979938242584467,
      "epoch": 0.09893308600061833,
      "grad_norm": 0.12779361009597778,
      "learning_rate": 5e-07,
      "loss": 0.0398,
      "step": 1060
    },
    {
      "clip_ratio/high_max": 0.002106760621245485,
      "clip_ratio/high_mean": 0.0009330560824309941,
      "clip_ratio/low_mean": 0.0009716660997582949,
      "clip_ratio/low_min": 5.958702513453318e-05,
      "clip_ratio/region_mean": 0.0019047221649088897,
      "epoch": 0.09902641910061892,
      "grad_norm": 0.1589653640985489,
      "learning_rate": 5e-07,
      "loss": 0.0453,
      "step": 1061
    },
    {
      "clip_ratio/high_max": 0.002233942323073279,
      "clip_ratio/high_mean": 0.0009115539032791276,
      "clip_ratio/low_mean": 0.0009862595215963665,
      "clip_ratio/low_min": 0.00016087902622530237,
      "clip_ratio/region_mean": 0.0018978134103235789,
      "epoch": 0.0991197522006195,
      "grad_norm": 73483.3203125,
      "learning_rate": 5e-07,
      "loss": 15.5999,
      "step": 1062
    },
    {
      "clip_ratio/high_max": 0.0021089488800498657,
      "clip_ratio/high_mean": 0.0008564369036321295,
      "clip_ratio/low_mean": 0.0007528326677856967,
      "clip_ratio/low_min": 4.292773883207701e-05,
      "clip_ratio/region_mean": 0.001609269547770964,
      "epoch": 0.09921308530062008,
      "grad_norm": 150102.09375,
      "learning_rate": 5e-07,
      "loss": 116.0643,
      "step": 1063
    },
    {
      "clip_ratio/high_max": 0.0022362050658557564,
      "clip_ratio/high_mean": 0.0009646017970226239,
      "clip_ratio/low_mean": 0.0007848865552659845,
      "clip_ratio/low_min": 7.085218658176018e-05,
      "clip_ratio/region_mean": 0.0017494883722974919,
      "epoch": 0.09930641840062067,
      "grad_norm": 479.0268859863281,
      "learning_rate": 5e-07,
      "loss": 0.0401,
      "step": 1064
    },
    {
      "clip_ratio/high_max": 0.002319490500667598,
      "clip_ratio/high_mean": 0.000955345847614808,
      "clip_ratio/low_mean": 0.0007718902797932969,
      "clip_ratio/low_min": 1.1796904800576158e-05,
      "clip_ratio/region_mean": 0.0017272362019866705,
      "epoch": 0.09939975150062125,
      "grad_norm": 3.637223482131958,
      "learning_rate": 5e-07,
      "loss": 0.0142,
      "step": 1065
    },
    {
      "clip_ratio/high_max": 0.0025983394880313426,
      "clip_ratio/high_mean": 0.000957777607254684,
      "clip_ratio/low_mean": 0.0007944571116240695,
      "clip_ratio/low_min": 3.717179424711503e-05,
      "clip_ratio/region_mean": 0.001752234726154711,
      "epoch": 0.09949308460062183,
      "grad_norm": 16.331357955932617,
      "learning_rate": 5e-07,
      "loss": -0.0087,
      "step": 1066
    },
    {
      "clip_ratio/high_max": 0.0020906742429360747,
      "clip_ratio/high_mean": 0.000918659228773322,
      "clip_ratio/low_mean": 0.0008825011609587818,
      "clip_ratio/low_min": 6.848343127785483e-05,
      "clip_ratio/region_mean": 0.0018011603824561462,
      "epoch": 0.09958641770062242,
      "grad_norm": 0.11420467495918274,
      "learning_rate": 5e-07,
      "loss": 0.0108,
      "step": 1067
    },
    {
      "clip_ratio/high_max": 0.002555004473833833,
      "clip_ratio/high_mean": 0.0010698340411181562,
      "clip_ratio/low_mean": 0.0010105820474564098,
      "clip_ratio/low_min": 9.116947148868348e-05,
      "clip_ratio/region_mean": 0.002080416088574566,
      "epoch": 0.099679750800623,
      "grad_norm": 0.13108396530151367,
      "learning_rate": 5e-07,
      "loss": 0.0198,
      "step": 1068
    },
    {
      "clip_ratio/high_max": 0.002104524966853205,
      "clip_ratio/high_mean": 0.0008199397307180334,
      "clip_ratio/low_mean": 0.001016235983115621,
      "clip_ratio/low_min": 0.00012998902639083099,
      "clip_ratio/region_mean": 0.001836175739299506,
      "epoch": 0.09977308390062359,
      "grad_norm": 0.17302699387073517,
      "learning_rate": 5e-07,
      "loss": 0.047,
      "step": 1069
    },
    {
      "clip_ratio/high_max": 0.0023667165442020632,
      "clip_ratio/high_mean": 0.0009232558304574923,
      "clip_ratio/low_mean": 0.0010198578638664912,
      "clip_ratio/low_min": 8.654095836391207e-05,
      "clip_ratio/region_mean": 0.0019431137334322557,
      "epoch": 0.09986641700062417,
      "grad_norm": 0.11166639626026154,
      "learning_rate": 5e-07,
      "loss": 0.0404,
      "step": 1070
    },
    {
      "clip_ratio/high_max": 0.0018113190890289843,
      "clip_ratio/high_mean": 0.0007916532176750479,
      "clip_ratio/low_mean": 0.0010098963502969127,
      "clip_ratio/low_min": 0.00010320645742467605,
      "clip_ratio/region_mean": 0.0018015495370491408,
      "epoch": 0.09995975010062474,
      "grad_norm": 0.10849573463201523,
      "learning_rate": 5e-07,
      "loss": 0.0364,
      "step": 1071
    },
    {
      "clip_ratio/high_max": 0.002219982383394381,
      "clip_ratio/high_mean": 0.0009639815561968135,
      "clip_ratio/low_mean": 0.0009664746976341121,
      "clip_ratio/low_min": 8.597974556323607e-05,
      "clip_ratio/region_mean": 0.0019304562883917242,
      "epoch": 0.10005308320062534,
      "grad_norm": 0.11901044100522995,
      "learning_rate": 5e-07,
      "loss": 0.0325,
      "step": 1072
    },
    {
      "clip_ratio/high_max": 0.00213466665809392,
      "clip_ratio/high_mean": 0.0008486611777698272,
      "clip_ratio/low_mean": 0.0008928672286856454,
      "clip_ratio/low_min": 0.00016201096241275081,
      "clip_ratio/region_mean": 0.0017415283946320415,
      "epoch": 0.10014641630062592,
      "grad_norm": 0.11419523507356644,
      "learning_rate": 5e-07,
      "loss": 0.0196,
      "step": 1073
    },
    {
      "clip_ratio/high_max": 0.0021077364508528262,
      "clip_ratio/high_mean": 0.0008937982747738715,
      "clip_ratio/low_mean": 0.0008724213657842483,
      "clip_ratio/low_min": 5.289438195177354e-05,
      "clip_ratio/region_mean": 0.0017662196478340775,
      "epoch": 0.1002397494006265,
      "grad_norm": 0.10523281991481781,
      "learning_rate": 5e-07,
      "loss": -0.002,
      "step": 1074
    },
    {
      "clip_ratio/high_max": 0.0022702152200508863,
      "clip_ratio/high_mean": 0.0009339071038994007,
      "clip_ratio/low_mean": 0.001013161727314582,
      "clip_ratio/low_min": 5.315266207617242e-05,
      "clip_ratio/region_mean": 0.0019470688566798344,
      "epoch": 0.10033308250062709,
      "grad_norm": 0.1425861418247223,
      "learning_rate": 5e-07,
      "loss": 0.0014,
      "step": 1075
    },
    {
      "clip_ratio/high_max": 0.0022576514747925103,
      "clip_ratio/high_mean": 0.0009305465046054451,
      "clip_ratio/low_mean": 0.0009092503260035301,
      "clip_ratio/low_min": 9.410510392626747e-05,
      "clip_ratio/region_mean": 0.0018397968015051447,
      "epoch": 0.10042641560062766,
      "grad_norm": 0.11647840589284897,
      "learning_rate": 5e-07,
      "loss": -0.0011,
      "step": 1076
    },
    {
      "clip_ratio/high_max": 0.002314849763934035,
      "clip_ratio/high_mean": 0.0010094316385220736,
      "clip_ratio/low_mean": 0.0009695597273093881,
      "clip_ratio/low_min": 7.51481311453972e-05,
      "clip_ratio/region_mean": 0.0019789913567365147,
      "epoch": 0.10051974870062824,
      "grad_norm": 0.11718462407588959,
      "learning_rate": 5e-07,
      "loss": -0.0016,
      "step": 1077
    },
    {
      "clip_ratio/high_max": 0.00240763711190084,
      "clip_ratio/high_mean": 0.0009584162653482053,
      "clip_ratio/low_mean": 0.001023190158775833,
      "clip_ratio/low_min": 0.0001123278580053011,
      "clip_ratio/region_mean": 0.0019816064304905012,
      "epoch": 0.10061308180062883,
      "grad_norm": 0.11813567578792572,
      "learning_rate": 5e-07,
      "loss": -0.0145,
      "step": 1078
    },
    {
      "clip_ratio/high_max": 0.0022805422195233405,
      "clip_ratio/high_mean": 0.0009160407098534051,
      "clip_ratio/low_mean": 0.0009621637655072846,
      "clip_ratio/low_min": 2.81721877399832e-05,
      "clip_ratio/region_mean": 0.0018782044207910076,
      "epoch": 0.10070641490062941,
      "grad_norm": 0.12038306146860123,
      "learning_rate": 5e-07,
      "loss": 0.0284,
      "step": 1079
    },
    {
      "clip_ratio/high_max": 0.002054646291071549,
      "clip_ratio/high_mean": 0.0008985114982351661,
      "clip_ratio/low_mean": 0.00108020474363002,
      "clip_ratio/low_min": 7.26116022633505e-05,
      "clip_ratio/region_mean": 0.0019787161945714615,
      "epoch": 0.10079974800063,
      "grad_norm": 0.11074809730052948,
      "learning_rate": 5e-07,
      "loss": 0.0364,
      "step": 1080
    },
    {
      "clip_ratio/high_max": 0.0023117434175219387,
      "clip_ratio/high_mean": 0.0009197349136229604,
      "clip_ratio/low_mean": 0.0010016205505962716,
      "clip_ratio/low_min": 0.00013607442178908968,
      "clip_ratio/region_mean": 0.0019213554696762003,
      "epoch": 0.10089308110063058,
      "grad_norm": 0.1185041293501854,
      "learning_rate": 5e-07,
      "loss": 0.0307,
      "step": 1081
    },
    {
      "clip_ratio/high_max": 0.0018469881324563175,
      "clip_ratio/high_mean": 0.0007583298684039619,
      "clip_ratio/low_mean": 0.001202309096697718,
      "clip_ratio/low_min": 8.560329752071993e-05,
      "clip_ratio/region_mean": 0.001960638961463701,
      "epoch": 0.10098641420063116,
      "grad_norm": 8.176234245300293,
      "learning_rate": 5e-07,
      "loss": 0.0657,
      "step": 1082
    },
    {
      "clip_ratio/high_max": 0.0018968845542985946,
      "clip_ratio/high_mean": 0.000775401522332686,
      "clip_ratio/low_mean": 0.0011340537603246048,
      "clip_ratio/low_min": 6.99962765793316e-05,
      "clip_ratio/region_mean": 0.0019094552480964921,
      "epoch": 0.10107974730063175,
      "grad_norm": 0.10546001046895981,
      "learning_rate": 5e-07,
      "loss": 0.0399,
      "step": 1083
    },
    {
      "clip_ratio/high_max": 0.0022653862251900136,
      "clip_ratio/high_mean": 0.0009274882613681257,
      "clip_ratio/low_mean": 0.000987161341981846,
      "clip_ratio/low_min": 7.470673426723806e-05,
      "clip_ratio/region_mean": 0.0019146496124449186,
      "epoch": 0.10117308040063233,
      "grad_norm": 0.10941343754529953,
      "learning_rate": 5e-07,
      "loss": -0.0109,
      "step": 1084
    },
    {
      "clip_ratio/high_max": 0.0016927062461036257,
      "clip_ratio/high_mean": 0.0007399590795102995,
      "clip_ratio/low_mean": 0.000964552480581915,
      "clip_ratio/low_min": 7.794621978973737e-05,
      "clip_ratio/region_mean": 0.001704511530988384,
      "epoch": 0.10126641350063291,
      "grad_norm": 0.11055760085582733,
      "learning_rate": 5e-07,
      "loss": 0.0342,
      "step": 1085
    },
    {
      "clip_ratio/high_max": 0.0017555686499690637,
      "clip_ratio/high_mean": 0.0007654187411390012,
      "clip_ratio/low_mean": 0.0011188225616933778,
      "clip_ratio/low_min": 0.00011016095595550723,
      "clip_ratio/region_mean": 0.0018842413192032836,
      "epoch": 0.1013597466006335,
      "grad_norm": 0.11567285656929016,
      "learning_rate": 5e-07,
      "loss": 0.0636,
      "step": 1086
    },
    {
      "clip_ratio/high_max": 0.0021825280782650225,
      "clip_ratio/high_mean": 0.0008875250505298027,
      "clip_ratio/low_mean": 0.001188150772577501,
      "clip_ratio/low_min": 0.00014631190606451128,
      "clip_ratio/region_mean": 0.00207567578763701,
      "epoch": 0.10145307970063408,
      "grad_norm": 0.1226997822523117,
      "learning_rate": 5e-07,
      "loss": 0.0638,
      "step": 1087
    },
    {
      "clip_ratio/high_max": 0.0022244347783271223,
      "clip_ratio/high_mean": 0.0009284597163059516,
      "clip_ratio/low_mean": 0.001047409405146027,
      "clip_ratio/low_min": 9.760302873473847e-05,
      "clip_ratio/region_mean": 0.001975869119632989,
      "epoch": 0.10154641280063466,
      "grad_norm": 0.11259535700082779,
      "learning_rate": 5e-07,
      "loss": 0.0219,
      "step": 1088
    },
    {
      "clip_ratio/high_max": 0.0023132228816393763,
      "clip_ratio/high_mean": 0.0009500113137619337,
      "clip_ratio/low_mean": 0.0009682436138973571,
      "clip_ratio/low_min": 0.00011275017277512234,
      "clip_ratio/region_mean": 0.001918254914926365,
      "epoch": 0.10163974590063525,
      "grad_norm": 0.12002401798963547,
      "learning_rate": 5e-07,
      "loss": 0.018,
      "step": 1089
    },
    {
      "clip_ratio/high_max": 0.002221327209554147,
      "clip_ratio/high_mean": 0.0009515414385532495,
      "clip_ratio/low_mean": 0.0008187602052203147,
      "clip_ratio/low_min": 4.410623478179332e-05,
      "clip_ratio/region_mean": 0.0017703016055747867,
      "epoch": 0.10173307900063583,
      "grad_norm": 0.12031128257513046,
      "learning_rate": 5e-07,
      "loss": -0.0008,
      "step": 1090
    },
    {
      "clip_ratio/high_max": 0.002188302358263172,
      "clip_ratio/high_mean": 0.0008787180031504249,
      "clip_ratio/low_mean": 0.0011006669847120065,
      "clip_ratio/low_min": 8.598336626164382e-05,
      "clip_ratio/region_mean": 0.001979384927835781,
      "epoch": 0.10182641210063642,
      "grad_norm": 0.10839653015136719,
      "learning_rate": 5e-07,
      "loss": 0.0467,
      "step": 1091
    },
    {
      "clip_ratio/high_max": 0.0019108091582893394,
      "clip_ratio/high_mean": 0.0008093212200037669,
      "clip_ratio/low_mean": 0.0009426332453585928,
      "clip_ratio/low_min": 3.7994992453604937e-05,
      "clip_ratio/region_mean": 0.0017519544271635823,
      "epoch": 0.101919745200637,
      "grad_norm": 0.09900347888469696,
      "learning_rate": 5e-07,
      "loss": 0.0246,
      "step": 1092
    },
    {
      "clip_ratio/high_max": 0.0022374743784894235,
      "clip_ratio/high_mean": 0.0008992963048513047,
      "clip_ratio/low_mean": 0.0010728455272328574,
      "clip_ratio/low_min": 0.00011225810976611683,
      "clip_ratio/region_mean": 0.0019721418066183105,
      "epoch": 0.10201307830063758,
      "grad_norm": 0.11178191751241684,
      "learning_rate": 5e-07,
      "loss": 0.0216,
      "step": 1093
    },
    {
      "clip_ratio/high_max": 0.0024541460516047664,
      "clip_ratio/high_mean": 0.000898906793736387,
      "clip_ratio/low_mean": 0.0009678733094915515,
      "clip_ratio/low_min": 7.812174044374842e-05,
      "clip_ratio/region_mean": 0.0018667801195988432,
      "epoch": 0.10210641140063817,
      "grad_norm": 0.1190095916390419,
      "learning_rate": 5e-07,
      "loss": -0.0012,
      "step": 1094
    },
    {
      "clip_ratio/high_max": 0.0022110316713224165,
      "clip_ratio/high_mean": 0.0009947055441443808,
      "clip_ratio/low_mean": 0.0010496919567231089,
      "clip_ratio/low_min": 0.00012021930706396233,
      "clip_ratio/region_mean": 0.0020443975445232354,
      "epoch": 0.10219974450063875,
      "grad_norm": 4241.03662109375,
      "learning_rate": 5e-07,
      "loss": 2.3225,
      "step": 1095
    },
    {
      "clip_ratio/high_max": 0.0021241902068140917,
      "clip_ratio/high_mean": 0.000854882871863083,
      "clip_ratio/low_mean": 0.0013597913311969023,
      "clip_ratio/low_min": 0.00019216804230381967,
      "clip_ratio/region_mean": 0.0022146741903270595,
      "epoch": 0.10229307760063933,
      "grad_norm": 0.3028807044029236,
      "learning_rate": 5e-07,
      "loss": 0.0734,
      "step": 1096
    },
    {
      "clip_ratio/high_max": 0.0020846861189056654,
      "clip_ratio/high_mean": 0.0008411461021751165,
      "clip_ratio/low_mean": 0.001070305170287611,
      "clip_ratio/low_min": 0.0001293436862397357,
      "clip_ratio/region_mean": 0.001911451319756452,
      "epoch": 0.10238641070063992,
      "grad_norm": 0.12927064299583435,
      "learning_rate": 5e-07,
      "loss": 0.0149,
      "step": 1097
    },
    {
      "clip_ratio/high_max": 0.0021411503694253042,
      "clip_ratio/high_mean": 0.0008221250027418137,
      "clip_ratio/low_mean": 0.0010921317953034304,
      "clip_ratio/low_min": 0.00012359808533801697,
      "clip_ratio/region_mean": 0.001914256819873117,
      "epoch": 0.1024797438006405,
      "grad_norm": 0.1059456467628479,
      "learning_rate": 5e-07,
      "loss": 0.0367,
      "step": 1098
    },
    {
      "clip_ratio/high_max": 0.0021656260068994015,
      "clip_ratio/high_mean": 0.000902981533727143,
      "clip_ratio/low_mean": 0.0009341273926111171,
      "clip_ratio/low_min": 0.00013144579861545935,
      "clip_ratio/region_mean": 0.0018371089317952283,
      "epoch": 0.10257307690064109,
      "grad_norm": 0.10880634933710098,
      "learning_rate": 5e-07,
      "loss": 0.0037,
      "step": 1099
    },
    {
      "clip_ratio/high_max": 0.0018191514536738396,
      "clip_ratio/high_mean": 0.0007399739042739384,
      "clip_ratio/low_mean": 0.0012286306227906607,
      "clip_ratio/low_min": 0.00015217276086332276,
      "clip_ratio/region_mean": 0.0019686044979607686,
      "epoch": 0.10266641000064167,
      "grad_norm": 0.12694436311721802,
      "learning_rate": 5e-07,
      "loss": 0.0739,
      "step": 1100
    },
    {
      "clip_ratio/high_max": 0.0018922953495348338,
      "clip_ratio/high_mean": 0.0007728086484348751,
      "clip_ratio/low_mean": 0.0009948466649802867,
      "clip_ratio/low_min": 9.385922021465376e-05,
      "clip_ratio/region_mean": 0.0017676553397905082,
      "epoch": 0.10275974310064225,
      "grad_norm": 2.571956157684326,
      "learning_rate": 5e-07,
      "loss": 0.0747,
      "step": 1101
    },
    {
      "clip_ratio/high_max": 0.0020526913867797703,
      "clip_ratio/high_mean": 0.0009861831822490785,
      "clip_ratio/low_mean": 0.0009296615398852737,
      "clip_ratio/low_min": 7.678610108996509e-05,
      "clip_ratio/region_mean": 0.0019158447466907091,
      "epoch": 0.10285307620064284,
      "grad_norm": 0.10950659960508347,
      "learning_rate": 5e-07,
      "loss": -0.0038,
      "step": 1102
    },
    {
      "clip_ratio/high_max": 0.0018504502622818109,
      "clip_ratio/high_mean": 0.0007389768925349927,
      "clip_ratio/low_mean": 0.0012180774938315153,
      "clip_ratio/low_min": 9.379992752656108e-05,
      "clip_ratio/region_mean": 0.001957054395461455,
      "epoch": 0.10294640930064342,
      "grad_norm": 0.12756063044071198,
      "learning_rate": 5e-07,
      "loss": 0.078,
      "step": 1103
    },
    {
      "clip_ratio/high_max": 0.0024362889234907925,
      "clip_ratio/high_mean": 0.0009980599970731419,
      "clip_ratio/low_mean": 0.0010972696018143324,
      "clip_ratio/low_min": 6.019938609824749e-05,
      "clip_ratio/region_mean": 0.002095329655276146,
      "epoch": 0.103039742400644,
      "grad_norm": 0.1234491840004921,
      "learning_rate": 5e-07,
      "loss": 0.0177,
      "step": 1104
    },
    {
      "clip_ratio/high_max": 0.0019952294569520745,
      "clip_ratio/high_mean": 0.0007781087078910787,
      "clip_ratio/low_mean": 0.0009750803728820756,
      "clip_ratio/low_min": 4.671717942983378e-05,
      "clip_ratio/region_mean": 0.0017531891135149635,
      "epoch": 0.10313307550064459,
      "grad_norm": 0.11261162906885147,
      "learning_rate": 5e-07,
      "loss": 0.0643,
      "step": 1105
    },
    {
      "clip_ratio/high_max": 0.0028421836395864375,
      "clip_ratio/high_mean": 0.001142941113357665,
      "clip_ratio/low_mean": 0.0009931811127898982,
      "clip_ratio/low_min": 8.470802822557744e-05,
      "clip_ratio/region_mean": 0.0021361222461564466,
      "epoch": 0.10322640860064516,
      "grad_norm": 0.11783000081777573,
      "learning_rate": 5e-07,
      "loss": 0.0015,
      "step": 1106
    },
    {
      "clip_ratio/high_max": 0.002028032256930601,
      "clip_ratio/high_mean": 0.0008782969489402603,
      "clip_ratio/low_mean": 0.001051103106874507,
      "clip_ratio/low_min": 0.00010304568240826484,
      "clip_ratio/region_mean": 0.0019294000521767884,
      "epoch": 0.10331974170064574,
      "grad_norm": 0.11224910616874695,
      "learning_rate": 5e-07,
      "loss": 0.0117,
      "step": 1107
    },
    {
      "clip_ratio/high_max": 0.0020626181503757834,
      "clip_ratio/high_mean": 0.000851589162266464,
      "clip_ratio/low_mean": 0.0011249488416069653,
      "clip_ratio/low_min": 0.00010424635274830507,
      "clip_ratio/region_mean": 0.0019765379911405034,
      "epoch": 0.10341307480064633,
      "grad_norm": 0.10716237127780914,
      "learning_rate": 5e-07,
      "loss": 0.06,
      "step": 1108
    },
    {
      "clip_ratio/high_max": 0.00242907514621038,
      "clip_ratio/high_mean": 0.001004992998787202,
      "clip_ratio/low_mean": 0.0010453793474880513,
      "clip_ratio/low_min": 6.552065769938054e-05,
      "clip_ratio/region_mean": 0.002050372349913232,
      "epoch": 0.10350640790064691,
      "grad_norm": 0.1126062199473381,
      "learning_rate": 5e-07,
      "loss": 0.0164,
      "step": 1109
    },
    {
      "clip_ratio/high_max": 0.00205038495187182,
      "clip_ratio/high_mean": 0.0008989729030872695,
      "clip_ratio/low_mean": 0.0011227223458263325,
      "clip_ratio/low_min": 4.936753248330206e-05,
      "clip_ratio/region_mean": 0.002021695217990782,
      "epoch": 0.1035997410006475,
      "grad_norm": 0.11921761929988861,
      "learning_rate": 5e-07,
      "loss": 0.0293,
      "step": 1110
    },
    {
      "clip_ratio/high_max": 0.0021088686044095084,
      "clip_ratio/high_mean": 0.0009163583381450735,
      "clip_ratio/low_mean": 0.0008194515548893833,
      "clip_ratio/low_min": 8.537108988093678e-05,
      "clip_ratio/region_mean": 0.0017358098775730468,
      "epoch": 0.10369307410064808,
      "grad_norm": 0.11967341601848602,
      "learning_rate": 5e-07,
      "loss": 0.0266,
      "step": 1111
    },
    {
      "clip_ratio/high_max": 0.0022883415731485,
      "clip_ratio/high_mean": 0.0009635473943490069,
      "clip_ratio/low_mean": 0.0009564703232172178,
      "clip_ratio/low_min": 8.250879545812495e-05,
      "clip_ratio/region_mean": 0.0019200176902813837,
      "epoch": 0.10378640720064866,
      "grad_norm": 0.11330248415470123,
      "learning_rate": 5e-07,
      "loss": -0.0066,
      "step": 1112
    },
    {
      "clip_ratio/high_max": 0.0023982848579180427,
      "clip_ratio/high_mean": 0.0009276838982259505,
      "clip_ratio/low_mean": 0.000958752389124129,
      "clip_ratio/low_min": 7.342470598814543e-05,
      "clip_ratio/region_mean": 0.0018864362718886696,
      "epoch": 0.10387974030064925,
      "grad_norm": 0.1933630406856537,
      "learning_rate": 5e-07,
      "loss": 0.0082,
      "step": 1113
    },
    {
      "clip_ratio/high_max": 0.0024746919225435704,
      "clip_ratio/high_mean": 0.0009574214254826074,
      "clip_ratio/low_mean": 0.0008234687411459163,
      "clip_ratio/low_min": 3.867574287141906e-05,
      "clip_ratio/region_mean": 0.0017808901684475131,
      "epoch": 0.10397307340064983,
      "grad_norm": 0.10845783352851868,
      "learning_rate": 5e-07,
      "loss": 0.0137,
      "step": 1114
    },
    {
      "clip_ratio/high_max": 0.0017636030606809072,
      "clip_ratio/high_mean": 0.0008102240408334183,
      "clip_ratio/low_mean": 0.001039908916936838,
      "clip_ratio/low_min": 4.480337520362809e-05,
      "clip_ratio/region_mean": 0.0018501329323044047,
      "epoch": 0.10406640650065041,
      "grad_norm": 0.12239908427000046,
      "learning_rate": 5e-07,
      "loss": 0.0518,
      "step": 1115
    },
    {
      "clip_ratio/high_max": 0.001879620089312084,
      "clip_ratio/high_mean": 0.0008705422751518199,
      "clip_ratio/low_mean": 0.0009256456542061642,
      "clip_ratio/low_min": 7.66395478422055e-05,
      "clip_ratio/region_mean": 0.00179618794209091,
      "epoch": 0.104159739600651,
      "grad_norm": 0.10951399058103561,
      "learning_rate": 5e-07,
      "loss": -0.0043,
      "step": 1116
    },
    {
      "clip_ratio/high_max": 0.0020476015852182172,
      "clip_ratio/high_mean": 0.0008581140409660293,
      "clip_ratio/low_mean": 0.0011953508255828638,
      "clip_ratio/low_min": 0.0001596642796357628,
      "clip_ratio/region_mean": 0.002053464930213522,
      "epoch": 0.10425307270065158,
      "grad_norm": 0.1133253425359726,
      "learning_rate": 5e-07,
      "loss": 0.0496,
      "step": 1117
    },
    {
      "clip_ratio/high_max": 0.0020577620816766284,
      "clip_ratio/high_mean": 0.0008887057992978953,
      "clip_ratio/low_mean": 0.0009793777626327937,
      "clip_ratio/low_min": 0.00010687447957025142,
      "clip_ratio/region_mean": 0.0018680836001294665,
      "epoch": 0.10434640580065216,
      "grad_norm": 3.285454273223877,
      "learning_rate": 5e-07,
      "loss": 0.0122,
      "step": 1118
    },
    {
      "clip_ratio/high_max": 0.0018939574802061543,
      "clip_ratio/high_mean": 0.0008336137798323762,
      "clip_ratio/low_mean": 0.0010041540190286469,
      "clip_ratio/low_min": 3.407387339393608e-05,
      "clip_ratio/region_mean": 0.0018377678134129383,
      "epoch": 0.10443973890065275,
      "grad_norm": 0.11060382425785065,
      "learning_rate": 5e-07,
      "loss": 0.0319,
      "step": 1119
    },
    {
      "clip_ratio/high_max": 0.002597573176899459,
      "clip_ratio/high_mean": 0.0009696033521322533,
      "clip_ratio/low_mean": 0.0008287706223200075,
      "clip_ratio/low_min": 2.7336345738149248e-05,
      "clip_ratio/region_mean": 0.0017983739599003457,
      "epoch": 0.10453307200065333,
      "grad_norm": 1.3307980298995972,
      "learning_rate": 5e-07,
      "loss": -0.0081,
      "step": 1120
    },
    {
      "clip_ratio/high_max": 0.0019977708980150055,
      "clip_ratio/high_mean": 0.0008428201836068183,
      "clip_ratio/low_mean": 0.001118980460887542,
      "clip_ratio/low_min": 0.000128169964227709,
      "clip_ratio/region_mean": 0.00196180061539053,
      "epoch": 0.10462640510065392,
      "grad_norm": 0.11487505584955215,
      "learning_rate": 5e-07,
      "loss": 0.0571,
      "step": 1121
    },
    {
      "clip_ratio/high_max": 0.0022112263905000873,
      "clip_ratio/high_mean": 0.0009607029533071909,
      "clip_ratio/low_mean": 0.0010960856707242783,
      "clip_ratio/low_min": 3.8494454202009365e-05,
      "clip_ratio/region_mean": 0.0020567886385833845,
      "epoch": 0.1047197382006545,
      "grad_norm": 0.11767525970935822,
      "learning_rate": 5e-07,
      "loss": 0.0185,
      "step": 1122
    },
    {
      "clip_ratio/high_max": 0.002031264186371118,
      "clip_ratio/high_mean": 0.0008086464804364368,
      "clip_ratio/low_mean": 0.00104331588227069,
      "clip_ratio/low_min": 0.00012309277735766955,
      "clip_ratio/region_mean": 0.0018519624063628726,
      "epoch": 0.10481307130065508,
      "grad_norm": 0.12242218106985092,
      "learning_rate": 5e-07,
      "loss": 0.0472,
      "step": 1123
    },
    {
      "clip_ratio/high_max": 0.0019273516736575402,
      "clip_ratio/high_mean": 0.0008120359652821207,
      "clip_ratio/low_mean": 0.0011392171036277432,
      "clip_ratio/low_min": 8.891372908692574e-05,
      "clip_ratio/region_mean": 0.0019512530270731077,
      "epoch": 0.10490640440065567,
      "grad_norm": 0.11475867033004761,
      "learning_rate": 5e-07,
      "loss": 0.0513,
      "step": 1124
    },
    {
      "clip_ratio/high_max": 0.0021382771228672937,
      "clip_ratio/high_mean": 0.0009047810563060921,
      "clip_ratio/low_mean": 0.0012160576261521783,
      "clip_ratio/low_min": 0.0001006639549814281,
      "clip_ratio/region_mean": 0.0021208386460784823,
      "epoch": 0.10499973750065625,
      "grad_norm": 0.11068805307149887,
      "learning_rate": 5e-07,
      "loss": 0.0537,
      "step": 1125
    },
    {
      "clip_ratio/high_max": 0.002037637954344973,
      "clip_ratio/high_mean": 0.0008481356562697329,
      "clip_ratio/low_mean": 0.0014204796061676461,
      "clip_ratio/low_min": 0.00020568520267261192,
      "clip_ratio/region_mean": 0.0022686152515234426,
      "epoch": 0.10509307060065683,
      "grad_norm": 0.12387433648109436,
      "learning_rate": 5e-07,
      "loss": 0.033,
      "step": 1126
    },
    {
      "clip_ratio/high_max": 0.0020657259738072753,
      "clip_ratio/high_mean": 0.000863907716848189,
      "clip_ratio/low_mean": 0.0010017062868428184,
      "clip_ratio/low_min": 1.4048100638319738e-05,
      "clip_ratio/region_mean": 0.0018656140091479756,
      "epoch": 0.10518640370065742,
      "grad_norm": 0.1203593760728836,
      "learning_rate": 5e-07,
      "loss": 0.0299,
      "step": 1127
    },
    {
      "clip_ratio/high_max": 0.002641768063767813,
      "clip_ratio/high_mean": 0.0009576752490829676,
      "clip_ratio/low_mean": 0.0009707444569357904,
      "clip_ratio/low_min": 4.9093132474808954e-05,
      "clip_ratio/region_mean": 0.0019284196750959381,
      "epoch": 0.105279736800658,
      "grad_norm": 0.11504225432872772,
      "learning_rate": 5e-07,
      "loss": -0.0225,
      "step": 1128
    },
    {
      "clip_ratio/high_max": 0.0021413127906271257,
      "clip_ratio/high_mean": 0.0008522002335666912,
      "clip_ratio/low_mean": 0.0011192059755558148,
      "clip_ratio/low_min": 7.869627279433189e-05,
      "clip_ratio/region_mean": 0.001971406178199686,
      "epoch": 0.10537306990065858,
      "grad_norm": 0.11124808341264725,
      "learning_rate": 5e-07,
      "loss": 0.0068,
      "step": 1129
    },
    {
      "clip_ratio/high_max": 0.0021117453870829195,
      "clip_ratio/high_mean": 0.0008777340299275238,
      "clip_ratio/low_mean": 0.0010307303728041006,
      "clip_ratio/low_min": 5.515846441994654e-05,
      "clip_ratio/region_mean": 0.0019084643790847622,
      "epoch": 0.10546640300065917,
      "grad_norm": 0.09863065183162689,
      "learning_rate": 5e-07,
      "loss": 0.0574,
      "step": 1130
    },
    {
      "clip_ratio/high_max": 0.001985575392609462,
      "clip_ratio/high_mean": 0.0008221280986617785,
      "clip_ratio/low_mean": 0.0010133478281204589,
      "clip_ratio/low_min": 0.0001013674682326382,
      "clip_ratio/region_mean": 0.001835475952248089,
      "epoch": 0.10555973610065975,
      "grad_norm": 0.1078055128455162,
      "learning_rate": 5e-07,
      "loss": 0.0236,
      "step": 1131
    },
    {
      "clip_ratio/high_max": 0.0022706029158143792,
      "clip_ratio/high_mean": 0.0009450153029320063,
      "clip_ratio/low_mean": 0.0011547266731213313,
      "clip_ratio/low_min": 6.39974696241552e-05,
      "clip_ratio/region_mean": 0.0020997419705963694,
      "epoch": 0.10565306920066034,
      "grad_norm": 0.12000733613967896,
      "learning_rate": 5e-07,
      "loss": 0.0452,
      "step": 1132
    },
    {
      "clip_ratio/high_max": 0.002556269886554219,
      "clip_ratio/high_mean": 0.0011019524972653016,
      "clip_ratio/low_mean": 0.001164757572041708,
      "clip_ratio/low_min": 9.172274985758122e-05,
      "clip_ratio/region_mean": 0.0022667100784019567,
      "epoch": 0.10574640230066092,
      "grad_norm": 0.12550412118434906,
      "learning_rate": 5e-07,
      "loss": 0.0028,
      "step": 1133
    },
    {
      "clip_ratio/high_max": 0.0017685285492916591,
      "clip_ratio/high_mean": 0.0007184100904851221,
      "clip_ratio/low_mean": 0.0008669237795402296,
      "clip_ratio/low_min": 2.317389771633316e-05,
      "clip_ratio/region_mean": 0.0015853338882152457,
      "epoch": 0.1058397354006615,
      "grad_norm": 0.10671789944171906,
      "learning_rate": 5e-07,
      "loss": 0.0116,
      "step": 1134
    },
    {
      "clip_ratio/high_max": 0.0020993439975427464,
      "clip_ratio/high_mean": 0.0009099898416025098,
      "clip_ratio/low_mean": 0.0011292467188468436,
      "clip_ratio/low_min": 0.0001452932174288435,
      "clip_ratio/region_mean": 0.0020392365258885548,
      "epoch": 0.10593306850066209,
      "grad_norm": 0.11656491458415985,
      "learning_rate": 5e-07,
      "loss": 0.0311,
      "step": 1135
    },
    {
      "clip_ratio/high_max": 0.002110607390932273,
      "clip_ratio/high_mean": 0.0007428275002894225,
      "clip_ratio/low_mean": 0.00109013847031747,
      "clip_ratio/low_min": 7.709766578045674e-05,
      "clip_ratio/region_mean": 0.0018329660015297122,
      "epoch": 0.10602640160066266,
      "grad_norm": 0.10994435101747513,
      "learning_rate": 5e-07,
      "loss": 0.0721,
      "step": 1136
    },
    {
      "clip_ratio/high_max": 0.002244356073788367,
      "clip_ratio/high_mean": 0.0009024865648825653,
      "clip_ratio/low_mean": 0.0010899005901592318,
      "clip_ratio/low_min": 7.902691686467733e-05,
      "clip_ratio/region_mean": 0.0019923871659557335,
      "epoch": 0.10611973470066324,
      "grad_norm": 0.11935460567474365,
      "learning_rate": 5e-07,
      "loss": 0.0287,
      "step": 1137
    },
    {
      "clip_ratio/high_max": 0.00209959497442469,
      "clip_ratio/high_mean": 0.0008412795123149408,
      "clip_ratio/low_mean": 0.001090876838134136,
      "clip_ratio/low_min": 0.00013043243416177575,
      "clip_ratio/region_mean": 0.0019321563668199815,
      "epoch": 0.10621306780066384,
      "grad_norm": 0.1706288903951645,
      "learning_rate": 5e-07,
      "loss": 0.0073,
      "step": 1138
    },
    {
      "clip_ratio/high_max": 0.002422246485366486,
      "clip_ratio/high_mean": 0.0009795162695809267,
      "clip_ratio/low_mean": 0.0011755015548260417,
      "clip_ratio/low_min": 7.135004398151068e-05,
      "clip_ratio/region_mean": 0.0021550178062170744,
      "epoch": 0.10630640090066441,
      "grad_norm": 0.1444534957408905,
      "learning_rate": 5e-07,
      "loss": 0.0218,
      "step": 1139
    },
    {
      "clip_ratio/high_max": 0.0022642388357780874,
      "clip_ratio/high_mean": 0.0009630559870856814,
      "clip_ratio/low_mean": 0.0012446576984075364,
      "clip_ratio/low_min": 0.00013979886080051074,
      "clip_ratio/region_mean": 0.002207713681855239,
      "epoch": 0.10639973400066499,
      "grad_norm": 0.1312839537858963,
      "learning_rate": 5e-07,
      "loss": 0.0156,
      "step": 1140
    },
    {
      "clip_ratio/high_max": 0.002409052449365845,
      "clip_ratio/high_mean": 0.0009791857719392283,
      "clip_ratio/low_mean": 0.0011012839659088058,
      "clip_ratio/low_min": 6.0053655033698305e-05,
      "clip_ratio/region_mean": 0.00208046971965814,
      "epoch": 0.10649306710066558,
      "grad_norm": 0.11566513776779175,
      "learning_rate": 5e-07,
      "loss": 0.018,
      "step": 1141
    },
    {
      "clip_ratio/high_max": 0.002311732187081361,
      "clip_ratio/high_mean": 0.0009031810113810934,
      "clip_ratio/low_mean": 0.0010095723118865862,
      "clip_ratio/low_min": 1.5217920918075833e-05,
      "clip_ratio/region_mean": 0.0019127533523715101,
      "epoch": 0.10658640020066616,
      "grad_norm": 0.24036484956741333,
      "learning_rate": 5e-07,
      "loss": -0.0048,
      "step": 1142
    },
    {
      "clip_ratio/high_max": 0.0023669268157391343,
      "clip_ratio/high_mean": 0.0009120963768509682,
      "clip_ratio/low_mean": 0.0009835570908762747,
      "clip_ratio/low_min": 7.340572756220354e-05,
      "clip_ratio/region_mean": 0.00189565347682219,
      "epoch": 0.10667973330066675,
      "grad_norm": 0.10444623976945877,
      "learning_rate": 5e-07,
      "loss": 0.0352,
      "step": 1143
    },
    {
      "clip_ratio/high_max": 0.002288011208293028,
      "clip_ratio/high_mean": 0.0009186238276015501,
      "clip_ratio/low_mean": 0.001026578374876408,
      "clip_ratio/low_min": 5.477343984239269e-05,
      "clip_ratio/region_mean": 0.001945202224305831,
      "epoch": 0.10677306640066733,
      "grad_norm": 0.10547124594449997,
      "learning_rate": 5e-07,
      "loss": 0.0368,
      "step": 1144
    },
    {
      "clip_ratio/high_max": 0.0021121829267940484,
      "clip_ratio/high_mean": 0.0008649727606098168,
      "clip_ratio/low_mean": 0.0009835702931013657,
      "clip_ratio/low_min": 7.19441959518008e-05,
      "clip_ratio/region_mean": 0.0018485430118744262,
      "epoch": 0.10686639950066791,
      "grad_norm": 0.11797945946455002,
      "learning_rate": 5e-07,
      "loss": 0.0131,
      "step": 1145
    },
    {
      "clip_ratio/high_max": 0.002558867126936093,
      "clip_ratio/high_mean": 0.0009924244241119595,
      "clip_ratio/low_mean": 0.0009829414084379096,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0019753658198169433,
      "epoch": 0.1069597326006685,
      "grad_norm": 0.11016115546226501,
      "learning_rate": 5e-07,
      "loss": -0.0136,
      "step": 1146
    },
    {
      "clip_ratio/high_max": 0.0023060457169776782,
      "clip_ratio/high_mean": 0.0009256020857719705,
      "clip_ratio/low_mean": 0.0011055019131163135,
      "clip_ratio/low_min": 0.00014948331045161467,
      "clip_ratio/region_mean": 0.002031104013440199,
      "epoch": 0.10705306570066908,
      "grad_norm": 0.12340693920850754,
      "learning_rate": 5e-07,
      "loss": 0.0193,
      "step": 1147
    },
    {
      "clip_ratio/high_max": 0.0020313381392043084,
      "clip_ratio/high_mean": 0.0008798404978733743,
      "clip_ratio/low_mean": 0.0010249871520500164,
      "clip_ratio/low_min": 0.00011233061741222627,
      "clip_ratio/region_mean": 0.0019048276517423801,
      "epoch": 0.10714639880066966,
      "grad_norm": 0.11591682583093643,
      "learning_rate": 5e-07,
      "loss": -0.0125,
      "step": 1148
    },
    {
      "clip_ratio/high_max": 0.002025986206717789,
      "clip_ratio/high_mean": 0.0008683446412760532,
      "clip_ratio/low_mean": 0.001297101320233196,
      "clip_ratio/low_min": 0.00012609994519152679,
      "clip_ratio/region_mean": 0.0021654459415003657,
      "epoch": 0.10723973190067025,
      "grad_norm": 0.11851821094751358,
      "learning_rate": 5e-07,
      "loss": 0.0601,
      "step": 1149
    },
    {
      "clip_ratio/high_max": 0.002119918935932219,
      "clip_ratio/high_mean": 0.000999479630991118,
      "clip_ratio/low_mean": 0.0009682269192126114,
      "clip_ratio/low_min": 9.814449367695488e-05,
      "clip_ratio/region_mean": 0.00196770657930756,
      "epoch": 0.10733306500067083,
      "grad_norm": 0.11950584501028061,
      "learning_rate": 5e-07,
      "loss": -0.0083,
      "step": 1150
    },
    {
      "clip_ratio/high_max": 0.002061121544102207,
      "clip_ratio/high_mean": 0.0008680738428665791,
      "clip_ratio/low_mean": 0.0011468312113720458,
      "clip_ratio/low_min": 9.746428804646712e-05,
      "clip_ratio/region_mean": 0.002014905090618413,
      "epoch": 0.10742639810067142,
      "grad_norm": 0.11802602559328079,
      "learning_rate": 5e-07,
      "loss": 0.0398,
      "step": 1151
    },
    {
      "clip_ratio/high_max": 0.0018760141319944523,
      "clip_ratio/high_mean": 0.0008663428834552178,
      "clip_ratio/low_mean": 0.000977479585344554,
      "clip_ratio/low_min": 6.201260293892119e-05,
      "clip_ratio/region_mean": 0.0018438224869896658,
      "epoch": 0.107519731200672,
      "grad_norm": 0.1039189025759697,
      "learning_rate": 5e-07,
      "loss": 0.0118,
      "step": 1152
    },
    {
      "clip_ratio/high_max": 0.0019972919471911155,
      "clip_ratio/high_mean": 0.0008456102605123306,
      "clip_ratio/low_mean": 0.001122481859056279,
      "clip_ratio/low_min": 0.00010304810439265566,
      "clip_ratio/region_mean": 0.0019680921104736626,
      "epoch": 0.10761306430067258,
      "grad_norm": 0.11191701143980026,
      "learning_rate": 5e-07,
      "loss": 0.0198,
      "step": 1153
    },
    {
      "clip_ratio/high_max": 0.0019101036341453437,
      "clip_ratio/high_mean": 0.0008022805122891441,
      "clip_ratio/low_mean": 0.0010309211538697127,
      "clip_ratio/low_min": 7.872543756093364e-05,
      "clip_ratio/region_mean": 0.0018332016770727932,
      "epoch": 0.10770639740067317,
      "grad_norm": 0.2583808898925781,
      "learning_rate": 5e-07,
      "loss": 0.0237,
      "step": 1154
    },
    {
      "clip_ratio/high_max": 0.002107617343426682,
      "clip_ratio/high_mean": 0.0007582172293041367,
      "clip_ratio/low_mean": 0.0010492776236787904,
      "clip_ratio/low_min": 6.339904484775616e-05,
      "clip_ratio/region_mean": 0.0018074948602588847,
      "epoch": 0.10779973050067375,
      "grad_norm": 0.6378929615020752,
      "learning_rate": 5e-07,
      "loss": 0.0357,
      "step": 1155
    },
    {
      "clip_ratio/high_max": 0.002059732491034083,
      "clip_ratio/high_mean": 0.000861309643369168,
      "clip_ratio/low_mean": 0.0010290019290550845,
      "clip_ratio/low_min": 0.00010963683780573774,
      "clip_ratio/region_mean": 0.0018903115997090936,
      "epoch": 0.10789306360067433,
      "grad_norm": 0.12360184639692307,
      "learning_rate": 5e-07,
      "loss": 0.0106,
      "step": 1156
    },
    {
      "clip_ratio/high_max": 0.0024165298164007254,
      "clip_ratio/high_mean": 0.0010210224354523234,
      "clip_ratio/low_mean": 0.0011347934887453448,
      "clip_ratio/low_min": 6.0108940488134976e-05,
      "clip_ratio/region_mean": 0.00215581594966352,
      "epoch": 0.10798639670067492,
      "grad_norm": 0.12761490046977997,
      "learning_rate": 5e-07,
      "loss": 0.0204,
      "step": 1157
    },
    {
      "clip_ratio/high_max": 0.0019486780183797237,
      "clip_ratio/high_mean": 0.0008545590262656333,
      "clip_ratio/low_mean": 0.0008569194469600916,
      "clip_ratio/low_min": 0.00010385750192654086,
      "clip_ratio/region_mean": 0.0017114784350269474,
      "epoch": 0.1080797298006755,
      "grad_norm": 0.09973431378602982,
      "learning_rate": 5e-07,
      "loss": 0.0118,
      "step": 1158
    },
    {
      "clip_ratio/high_max": 0.0023686031854595058,
      "clip_ratio/high_mean": 0.0009038710486493073,
      "clip_ratio/low_mean": 0.0011440194066381082,
      "clip_ratio/low_min": 8.40700522530824e-05,
      "clip_ratio/region_mean": 0.002047890462563373,
      "epoch": 0.10817306290067608,
      "grad_norm": 0.11755546927452087,
      "learning_rate": 5e-07,
      "loss": 0.0533,
      "step": 1159
    },
    {
      "clip_ratio/high_max": 0.0020566739367495757,
      "clip_ratio/high_mean": 0.0009188283947878517,
      "clip_ratio/low_mean": 0.001119271673815092,
      "clip_ratio/low_min": 0.00015930425070109777,
      "clip_ratio/region_mean": 0.002038100101344753,
      "epoch": 0.10826639600067667,
      "grad_norm": 0.11948569118976593,
      "learning_rate": 5e-07,
      "loss": 0.025,
      "step": 1160
    },
    {
      "clip_ratio/high_max": 0.0020889479092147667,
      "clip_ratio/high_mean": 0.0008446254187219893,
      "clip_ratio/low_mean": 0.0009132927843893413,
      "clip_ratio/low_min": 3.0478860026050825e-05,
      "clip_ratio/region_mean": 0.0017579182203917298,
      "epoch": 0.10835972910067725,
      "grad_norm": 0.10795163363218307,
      "learning_rate": 5e-07,
      "loss": 0.0528,
      "step": 1161
    },
    {
      "clip_ratio/high_max": 0.0023016685590846464,
      "clip_ratio/high_mean": 0.000828034091682639,
      "clip_ratio/low_mean": 0.0010154915435123257,
      "clip_ratio/low_min": 0.00014549761726811994,
      "clip_ratio/region_mean": 0.00184352564974688,
      "epoch": 0.10845306220067784,
      "grad_norm": 203.0908203125,
      "learning_rate": 5e-07,
      "loss": 0.066,
      "step": 1162
    },
    {
      "clip_ratio/high_max": 0.002025643130764365,
      "clip_ratio/high_mean": 0.0008763712721702177,
      "clip_ratio/low_mean": 0.0010746362277131993,
      "clip_ratio/low_min": 0.00016775350832176628,
      "clip_ratio/region_mean": 0.0019510075144353323,
      "epoch": 0.10854639530067842,
      "grad_norm": 0.11579528450965881,
      "learning_rate": 5e-07,
      "loss": 0.0118,
      "step": 1163
    },
    {
      "clip_ratio/high_max": 0.002116342911904212,
      "clip_ratio/high_mean": 0.0009123921136051649,
      "clip_ratio/low_mean": 0.0010304060415364802,
      "clip_ratio/low_min": 3.782656767725712e-05,
      "clip_ratio/region_mean": 0.001942798146046698,
      "epoch": 0.108639728400679,
      "grad_norm": 0.10652157664299011,
      "learning_rate": 5e-07,
      "loss": -0.0015,
      "step": 1164
    },
    {
      "clip_ratio/high_max": 0.0016068943223217502,
      "clip_ratio/high_mean": 0.0007095149467204465,
      "clip_ratio/low_mean": 0.001158011033112416,
      "clip_ratio/low_min": 0.00011802255903603509,
      "clip_ratio/region_mean": 0.0018675259489100426,
      "epoch": 0.10873306150067959,
      "grad_norm": 0.12046372145414352,
      "learning_rate": 5e-07,
      "loss": 0.0845,
      "step": 1165
    },
    {
      "clip_ratio/high_max": 0.0022495427256217226,
      "clip_ratio/high_mean": 0.000989443939033663,
      "clip_ratio/low_mean": 0.0009555946162436157,
      "clip_ratio/low_min": 0.00011699962578859413,
      "clip_ratio/region_mean": 0.0019450385734671727,
      "epoch": 0.10882639460068017,
      "grad_norm": 0.12214262783527374,
      "learning_rate": 5e-07,
      "loss": -0.0063,
      "step": 1166
    },
    {
      "clip_ratio/high_max": 0.002020062143856194,
      "clip_ratio/high_mean": 0.0008763853293203283,
      "clip_ratio/low_mean": 0.001116262352297781,
      "clip_ratio/low_min": 7.760053722449811e-05,
      "clip_ratio/region_mean": 0.0019926476743421517,
      "epoch": 0.10891972770068074,
      "grad_norm": 0.11147616058588028,
      "learning_rate": 5e-07,
      "loss": 0.0512,
      "step": 1167
    },
    {
      "clip_ratio/high_max": 0.0021065626533527393,
      "clip_ratio/high_mean": 0.0008561574832128827,
      "clip_ratio/low_mean": 0.0008138868961395929,
      "clip_ratio/low_min": 9.094223605643492e-05,
      "clip_ratio/region_mean": 0.0016700443629815709,
      "epoch": 0.10901306080068134,
      "grad_norm": 0.22255782783031464,
      "learning_rate": 5e-07,
      "loss": 0.0042,
      "step": 1168
    },
    {
      "clip_ratio/high_max": 0.002167789854865987,
      "clip_ratio/high_mean": 0.0008254185067926301,
      "clip_ratio/low_mean": 0.0011832795826194342,
      "clip_ratio/low_min": 7.626700789842289e-05,
      "clip_ratio/region_mean": 0.00200869810214499,
      "epoch": 0.10910639390068191,
      "grad_norm": 0.11148534715175629,
      "learning_rate": 5e-07,
      "loss": 0.0706,
      "step": 1169
    },
    {
      "clip_ratio/high_max": 0.0021893650700803846,
      "clip_ratio/high_mean": 0.0009305106432293542,
      "clip_ratio/low_mean": 0.0009119721853494411,
      "clip_ratio/low_min": 2.4635395675431937e-05,
      "clip_ratio/region_mean": 0.001842482823121827,
      "epoch": 0.10919972700068249,
      "grad_norm": 0.11984847486019135,
      "learning_rate": 5e-07,
      "loss": -0.0017,
      "step": 1170
    },
    {
      "clip_ratio/high_max": 0.002074145322694676,
      "clip_ratio/high_mean": 0.0008877186755853472,
      "clip_ratio/low_mean": 0.0011602573722484522,
      "clip_ratio/low_min": 0.00011815177822427358,
      "clip_ratio/region_mean": 0.002047976100584492,
      "epoch": 0.10929306010068308,
      "grad_norm": 0.10711146891117096,
      "learning_rate": 5e-07,
      "loss": 0.0599,
      "step": 1171
    },
    {
      "clip_ratio/high_max": 0.002258968677779194,
      "clip_ratio/high_mean": 0.0008593691254645819,
      "clip_ratio/low_mean": 0.000993874007690465,
      "clip_ratio/low_min": 5.127153417561203e-05,
      "clip_ratio/region_mean": 0.0018532431349740364,
      "epoch": 0.10938639320068366,
      "grad_norm": 0.11298707127571106,
      "learning_rate": 5e-07,
      "loss": 0.0111,
      "step": 1172
    },
    {
      "clip_ratio/high_max": 0.0024613277564640157,
      "clip_ratio/high_mean": 0.001022615560941631,
      "clip_ratio/low_mean": 0.0009104175660468172,
      "clip_ratio/low_min": 4.721732693724334e-05,
      "clip_ratio/region_mean": 0.0019330330469529144,
      "epoch": 0.10947972630068425,
      "grad_norm": 0.11070238053798676,
      "learning_rate": 5e-07,
      "loss": -0.0366,
      "step": 1173
    },
    {
      "clip_ratio/high_max": 0.0024552923860028386,
      "clip_ratio/high_mean": 0.0009377972401125589,
      "clip_ratio/low_mean": 0.0010783208090288099,
      "clip_ratio/low_min": 0.00011322264617774636,
      "clip_ratio/region_mean": 0.0020161180436844006,
      "epoch": 0.10957305940068483,
      "grad_norm": 0.11735869199037552,
      "learning_rate": 5e-07,
      "loss": 0.0342,
      "step": 1174
    },
    {
      "clip_ratio/high_max": 0.002182328542403411,
      "clip_ratio/high_mean": 0.0008477787323499797,
      "clip_ratio/low_mean": 0.0009783204059203854,
      "clip_ratio/low_min": 2.71964800049318e-05,
      "clip_ratio/region_mean": 0.0018260991273564287,
      "epoch": 0.10966639250068541,
      "grad_norm": 0.1130044162273407,
      "learning_rate": 5e-07,
      "loss": 0.0623,
      "step": 1175
    },
    {
      "clip_ratio/high_max": 0.0023940857681736816,
      "clip_ratio/high_mean": 0.0009844242322287755,
      "clip_ratio/low_mean": 0.0010401849904155824,
      "clip_ratio/low_min": 5.3848762036068365e-05,
      "clip_ratio/region_mean": 0.002024609231739305,
      "epoch": 0.109759725600686,
      "grad_norm": 0.12948890030384064,
      "learning_rate": 5e-07,
      "loss": -0.0024,
      "step": 1176
    },
    {
      "clip_ratio/high_max": 0.0021196296147536486,
      "clip_ratio/high_mean": 0.0007764732145005837,
      "clip_ratio/low_mean": 0.001220300211571157,
      "clip_ratio/low_min": 0.00011372684093657881,
      "clip_ratio/region_mean": 0.0019967734260717407,
      "epoch": 0.10985305870068658,
      "grad_norm": 0.12503232061862946,
      "learning_rate": 5e-07,
      "loss": 0.0617,
      "step": 1177
    },
    {
      "clip_ratio/high_max": 0.0024966869241325185,
      "clip_ratio/high_mean": 0.0009663670607551467,
      "clip_ratio/low_mean": 0.001040512892359402,
      "clip_ratio/low_min": 6.746072722307872e-05,
      "clip_ratio/region_mean": 0.0020068799422006123,
      "epoch": 0.10994639180068716,
      "grad_norm": 0.11339320987462997,
      "learning_rate": 5e-07,
      "loss": 0.0313,
      "step": 1178
    },
    {
      "clip_ratio/high_max": 0.0026040040975203738,
      "clip_ratio/high_mean": 0.0009659055976953823,
      "clip_ratio/low_mean": 0.0011967899699811824,
      "clip_ratio/low_min": 0.00011431198345235316,
      "clip_ratio/region_mean": 0.002162695505830925,
      "epoch": 0.11003972490068775,
      "grad_norm": 0.11346521228551865,
      "learning_rate": 5e-07,
      "loss": 0.0432,
      "step": 1179
    },
    {
      "clip_ratio/high_max": 0.0025074298537219875,
      "clip_ratio/high_mean": 0.0010275489621562883,
      "clip_ratio/low_mean": 0.000887278425580007,
      "clip_ratio/low_min": 7.444242783094523e-05,
      "clip_ratio/region_mean": 0.0019148273786413483,
      "epoch": 0.11013305800068833,
      "grad_norm": 0.11337248980998993,
      "learning_rate": 5e-07,
      "loss": -0.0274,
      "step": 1180
    },
    {
      "clip_ratio/high_max": 0.0022541909165738616,
      "clip_ratio/high_mean": 0.0009061071159521816,
      "clip_ratio/low_mean": 0.0009116135752265109,
      "clip_ratio/low_min": 8.216967034968548e-05,
      "clip_ratio/region_mean": 0.0018177207093685865,
      "epoch": 0.11022639110068891,
      "grad_norm": 0.14793387055397034,
      "learning_rate": 5e-07,
      "loss": -0.012,
      "step": 1181
    },
    {
      "clip_ratio/high_max": 0.002122005131241167,
      "clip_ratio/high_mean": 0.0008551956561859697,
      "clip_ratio/low_mean": 0.0012102887158107478,
      "clip_ratio/low_min": 9.74510967353126e-05,
      "clip_ratio/region_mean": 0.0020654843756346963,
      "epoch": 0.1103197242006895,
      "grad_norm": 0.10794934630393982,
      "learning_rate": 5e-07,
      "loss": 0.0472,
      "step": 1182
    },
    {
      "clip_ratio/high_max": 0.0020945554933859967,
      "clip_ratio/high_mean": 0.0009378661488881335,
      "clip_ratio/low_mean": 0.001057645122273243,
      "clip_ratio/low_min": 0.00011329496828693664,
      "clip_ratio/region_mean": 0.0019955112948082387,
      "epoch": 0.11041305730069008,
      "grad_norm": 0.11174557358026505,
      "learning_rate": 5e-07,
      "loss": -0.0123,
      "step": 1183
    },
    {
      "clip_ratio/high_max": 0.0024131951649906114,
      "clip_ratio/high_mean": 0.000984310545391054,
      "clip_ratio/low_mean": 0.0009977118625101866,
      "clip_ratio/low_min": 8.398262889386388e-05,
      "clip_ratio/region_mean": 0.0019820224260911345,
      "epoch": 0.11050639040069067,
      "grad_norm": 0.12488116323947906,
      "learning_rate": 5e-07,
      "loss": -0.0412,
      "step": 1184
    },
    {
      "clip_ratio/high_max": 0.002487848214514088,
      "clip_ratio/high_mean": 0.0010513211746001616,
      "clip_ratio/low_mean": 0.0008432441845798166,
      "clip_ratio/low_min": 2.836459407262737e-05,
      "clip_ratio/region_mean": 0.0018945654010167345,
      "completions/clipped_ratio": 0.013052804129464302,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4092.0,
      "completions/mean_length": 605.0520629882812,
      "completions/mean_terminated_length": 558.8827514648438,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.11059972350069125,
      "grad_norm": 274.48626708984375,
      "learning_rate": 5e-07,
      "loss": 0.0313,
      "num_tokens": 896328108.0,
      "reward": 0.6013968586921692,
      "reward_std": 0.18853144347667694,
      "rewards/simpleverify_reward/mean": 0.6013968586921692,
      "rewards/simpleverify_reward/std": 0.48961275815963745,
      "step": 1185
    },
    {
      "clip_ratio/high_max": 0.002212145809608046,
      "clip_ratio/high_mean": 0.0009461915433348622,
      "clip_ratio/low_mean": 0.0008787074843894516,
      "clip_ratio/low_min": 0.00011287943743809592,
      "clip_ratio/region_mean": 0.0018248990090796724,
      "epoch": 0.11069305660069183,
      "grad_norm": 65.22046661376953,
      "learning_rate": 5e-07,
      "loss": 4.3263,
      "step": 1186
    },
    {
      "clip_ratio/high_max": 0.0021281459339661524,
      "clip_ratio/high_mean": 0.0009883278307825094,
      "clip_ratio/low_mean": 0.0009073572618945036,
      "clip_ratio/low_min": 8.350426560355118e-05,
      "clip_ratio/region_mean": 0.0018956851272378117,
      "epoch": 0.11078638970069242,
      "grad_norm": 0.11620206385850906,
      "learning_rate": 5e-07,
      "loss": 0.018,
      "step": 1187
    },
    {
      "clip_ratio/high_max": 0.002244743656774517,
      "clip_ratio/high_mean": 0.0008357203660125379,
      "clip_ratio/low_mean": 0.0009470857148698997,
      "clip_ratio/low_min": 4.137470205023419e-05,
      "clip_ratio/region_mean": 0.001782806051778607,
      "epoch": 0.110879722800693,
      "grad_norm": 1.4124016761779785,
      "learning_rate": 5e-07,
      "loss": 0.0144,
      "step": 1188
    },
    {
      "clip_ratio/high_max": 0.002335093100555241,
      "clip_ratio/high_mean": 0.000980376566076302,
      "clip_ratio/low_mean": 0.0009202529909089208,
      "clip_ratio/low_min": 4.141129829804413e-05,
      "clip_ratio/region_mean": 0.0019006295769941062,
      "epoch": 0.11097305590069358,
      "grad_norm": 0.10888668894767761,
      "learning_rate": 5e-07,
      "loss": 0.0253,
      "step": 1189
    },
    {
      "clip_ratio/high_max": 0.0022372782332240604,
      "clip_ratio/high_mean": 0.0009308916014560964,
      "clip_ratio/low_mean": 0.0008139932615449652,
      "clip_ratio/low_min": 0.00010221537468169117,
      "clip_ratio/region_mean": 0.0017448848666390404,
      "epoch": 0.11106638900069417,
      "grad_norm": 0.11396488547325134,
      "learning_rate": 5e-07,
      "loss": 0.0219,
      "step": 1190
    },
    {
      "clip_ratio/high_max": 0.0022221156759769656,
      "clip_ratio/high_mean": 0.0008561125559936045,
      "clip_ratio/low_mean": 0.0009570329402777134,
      "clip_ratio/low_min": 6.599456901312806e-05,
      "clip_ratio/region_mean": 0.0018131454889953602,
      "epoch": 0.11115972210069475,
      "grad_norm": 3.2586252689361572,
      "learning_rate": 5e-07,
      "loss": 0.2478,
      "step": 1191
    },
    {
      "clip_ratio/high_max": 0.002114773938956205,
      "clip_ratio/high_mean": 0.0009044939288287424,
      "clip_ratio/low_mean": 0.0009106989673455246,
      "clip_ratio/low_min": 6.020203545631375e-05,
      "clip_ratio/region_mean": 0.0018151928670704365,
      "epoch": 0.11125305520069532,
      "grad_norm": 0.12815545499324799,
      "learning_rate": 5e-07,
      "loss": 0.0055,
      "step": 1192
    },
    {
      "clip_ratio/high_max": 0.002302723536558915,
      "clip_ratio/high_mean": 0.0009903484969981946,
      "clip_ratio/low_mean": 0.0009179941480397247,
      "clip_ratio/low_min": 7.261693008331349e-05,
      "clip_ratio/region_mean": 0.0019083426013821736,
      "epoch": 0.11134638830069592,
      "grad_norm": 0.11253359913825989,
      "learning_rate": 5e-07,
      "loss": -0.0062,
      "step": 1193
    },
    {
      "clip_ratio/high_max": 0.0021144104866834823,
      "clip_ratio/high_mean": 0.001005926167636062,
      "clip_ratio/low_mean": 0.000871888711117208,
      "clip_ratio/low_min": 9.999401027016575e-05,
      "clip_ratio/region_mean": 0.0018778148951241747,
      "epoch": 0.1114397214006965,
      "grad_norm": 0.12764541804790497,
      "learning_rate": 5e-07,
      "loss": -0.01,
      "step": 1194
    },
    {
      "clip_ratio/high_max": 0.0025273829960497096,
      "clip_ratio/high_mean": 0.0010208955318375956,
      "clip_ratio/low_mean": 0.0010879105684580281,
      "clip_ratio/low_min": 3.9656566514167935e-05,
      "clip_ratio/region_mean": 0.002108806133037433,
      "epoch": 0.11153305450069709,
      "grad_norm": 0.1285155564546585,
      "learning_rate": 5e-07,
      "loss": -0.0025,
      "step": 1195
    },
    {
      "clip_ratio/high_max": 0.002291209217219148,
      "clip_ratio/high_mean": 0.0009406638528162148,
      "clip_ratio/low_mean": 0.0009805678673728835,
      "clip_ratio/low_min": 3.2294942684529815e-05,
      "clip_ratio/region_mean": 0.0019212317129131407,
      "epoch": 0.11162638760069767,
      "grad_norm": 0.16951708495616913,
      "learning_rate": 5e-07,
      "loss": 0.2554,
      "step": 1196
    },
    {
      "clip_ratio/high_max": 0.002105700084939599,
      "clip_ratio/high_mean": 0.0009269186193705536,
      "clip_ratio/low_mean": 0.0010747694832389243,
      "clip_ratio/low_min": 5.353214783099247e-05,
      "clip_ratio/region_mean": 0.002001688117161393,
      "epoch": 0.11171972070069824,
      "grad_norm": 0.11662891507148743,
      "learning_rate": 5e-07,
      "loss": 0.0452,
      "step": 1197
    },
    {
      "clip_ratio/high_max": 0.002157489820092451,
      "clip_ratio/high_mean": 0.0009068243361980421,
      "clip_ratio/low_mean": 0.0009973338655981934,
      "clip_ratio/low_min": 7.913525132607901e-05,
      "clip_ratio/region_mean": 0.0019041582054342143,
      "epoch": 0.11181305380069884,
      "grad_norm": 0.10996367782354355,
      "learning_rate": 5e-07,
      "loss": 0.0462,
      "step": 1198
    },
    {
      "clip_ratio/high_max": 0.002269063930725679,
      "clip_ratio/high_mean": 0.001012618544336874,
      "clip_ratio/low_mean": 0.0007808314767316915,
      "clip_ratio/low_min": 5.6004860198299866e-05,
      "clip_ratio/region_mean": 0.0017934499846887775,
      "epoch": 0.11190638690069941,
      "grad_norm": 0.1122683584690094,
      "learning_rate": 5e-07,
      "loss": -0.0243,
      "step": 1199
    },
    {
      "clip_ratio/high_max": 0.002551577075792011,
      "clip_ratio/high_mean": 0.0009512087690382032,
      "clip_ratio/low_mean": 0.0011113972286693752,
      "clip_ratio/low_min": 7.701778667978942e-05,
      "clip_ratio/region_mean": 0.002062605941318907,
      "epoch": 0.11199972000069999,
      "grad_norm": 0.3381768465042114,
      "learning_rate": 5e-07,
      "loss": 0.0196,
      "step": 1200
    },
    {
      "clip_ratio/high_max": 0.00257578805758385,
      "clip_ratio/high_mean": 0.001089441058866214,
      "clip_ratio/low_mean": 0.0008995586449600523,
      "clip_ratio/low_min": 6.12399962847121e-05,
      "clip_ratio/region_mean": 0.001988999683817383,
      "epoch": 0.11209305310070058,
      "grad_norm": 0.3214060366153717,
      "learning_rate": 5e-07,
      "loss": -0.0181,
      "step": 1201
    },
    {
      "clip_ratio/high_max": 0.0022424310009228066,
      "clip_ratio/high_mean": 0.0009918177711369935,
      "clip_ratio/low_mean": 0.0009432411316083744,
      "clip_ratio/low_min": 5.397241511673201e-05,
      "clip_ratio/region_mean": 0.001935058862727601,
      "epoch": 0.11218638620070116,
      "grad_norm": 0.10802724212408066,
      "learning_rate": 5e-07,
      "loss": 0.0172,
      "step": 1202
    },
    {
      "clip_ratio/high_max": 0.002286586521222489,
      "clip_ratio/high_mean": 0.0009935264115483733,
      "clip_ratio/low_mean": 0.0008926905175030697,
      "clip_ratio/low_min": 3.07379586956813e-05,
      "clip_ratio/region_mean": 0.001886216879938729,
      "epoch": 0.11227971930070174,
      "grad_norm": 0.11769828200340271,
      "learning_rate": 5e-07,
      "loss": -0.0142,
      "step": 1203
    },
    {
      "clip_ratio/high_max": 0.002144861631677486,
      "clip_ratio/high_mean": 0.0009085322180908406,
      "clip_ratio/low_mean": 0.0010131327326234896,
      "clip_ratio/low_min": 0.00010232687463940238,
      "clip_ratio/region_mean": 0.001921664927067468,
      "epoch": 0.11237305240070233,
      "grad_norm": 0.1213015764951706,
      "learning_rate": 5e-07,
      "loss": 0.0178,
      "step": 1204
    },
    {
      "clip_ratio/high_max": 0.002169007362681441,
      "clip_ratio/high_mean": 0.0009312608490290586,
      "clip_ratio/low_mean": 0.0009208002884406596,
      "clip_ratio/low_min": 6.560256952070631e-05,
      "clip_ratio/region_mean": 0.001852061104727909,
      "epoch": 0.11246638550070291,
      "grad_norm": 0.11691083759069443,
      "learning_rate": 5e-07,
      "loss": 0.034,
      "step": 1205
    },
    {
      "clip_ratio/high_max": 0.0019580911393859424,
      "clip_ratio/high_mean": 0.0008725050720386207,
      "clip_ratio/low_mean": 0.0009692190760688391,
      "clip_ratio/low_min": 0.0001615519295228296,
      "clip_ratio/region_mean": 0.0018417241226416081,
      "epoch": 0.1125597186007035,
      "grad_norm": 0.12655743956565857,
      "learning_rate": 5e-07,
      "loss": 0.0939,
      "step": 1206
    },
    {
      "clip_ratio/high_max": 0.0023291372817766387,
      "clip_ratio/high_mean": 0.0009249392569472548,
      "clip_ratio/low_mean": 0.0008373359796678415,
      "clip_ratio/low_min": 5.3671883506467566e-05,
      "clip_ratio/region_mean": 0.0017622752784518525,
      "epoch": 0.11265305170070408,
      "grad_norm": 0.11805126816034317,
      "learning_rate": 5e-07,
      "loss": -0.0116,
      "step": 1207
    },
    {
      "clip_ratio/high_max": 0.0024195034202421084,
      "clip_ratio/high_mean": 0.0009058049436134752,
      "clip_ratio/low_mean": 0.000997473718598485,
      "clip_ratio/low_min": 8.940116185840452e-05,
      "clip_ratio/region_mean": 0.001903278629470151,
      "epoch": 0.11274638480070466,
      "grad_norm": 0.11537780612707138,
      "learning_rate": 5e-07,
      "loss": 0.0692,
      "step": 1208
    },
    {
      "clip_ratio/high_max": 0.002007032628171146,
      "clip_ratio/high_mean": 0.000874205659783911,
      "clip_ratio/low_mean": 0.001029732378810877,
      "clip_ratio/low_min": 0.00019518349381542066,
      "clip_ratio/region_mean": 0.0019039380713365972,
      "epoch": 0.11283971790070525,
      "grad_norm": 0.12588757276535034,
      "learning_rate": 5e-07,
      "loss": 0.0617,
      "step": 1209
    },
    {
      "clip_ratio/high_max": 0.0021592277407762595,
      "clip_ratio/high_mean": 0.0008171714434865862,
      "clip_ratio/low_mean": 0.0009680004241090501,
      "clip_ratio/low_min": 7.788188213453395e-05,
      "clip_ratio/region_mean": 0.0017851718585006893,
      "epoch": 0.11293305100070583,
      "grad_norm": 0.12252851575613022,
      "learning_rate": 5e-07,
      "loss": 0.0297,
      "step": 1210
    },
    {
      "clip_ratio/high_max": 0.0017363180304528214,
      "clip_ratio/high_mean": 0.0007621606255270308,
      "clip_ratio/low_mean": 0.0009666254954936448,
      "clip_ratio/low_min": 0.00015780093235662207,
      "clip_ratio/region_mean": 0.001728786104649771,
      "epoch": 0.11302638410070641,
      "grad_norm": 0.10657203942537308,
      "learning_rate": 5e-07,
      "loss": 0.0536,
      "step": 1211
    },
    {
      "clip_ratio/high_max": 0.002324460438103415,
      "clip_ratio/high_mean": 0.000917517538255197,
      "clip_ratio/low_mean": 0.0010938669474853668,
      "clip_ratio/low_min": 8.534460539522115e-05,
      "clip_ratio/region_mean": 0.002011384545767214,
      "epoch": 0.113119717200707,
      "grad_norm": 0.5036552548408508,
      "learning_rate": 5e-07,
      "loss": 0.1364,
      "step": 1212
    },
    {
      "clip_ratio/high_max": 0.0020894312547170557,
      "clip_ratio/high_mean": 0.0009620839082344901,
      "clip_ratio/low_mean": 0.0011167271295562387,
      "clip_ratio/low_min": 9.066914026334416e-05,
      "clip_ratio/region_mean": 0.002078810997772962,
      "epoch": 0.11321305030070758,
      "grad_norm": 44.65790939331055,
      "learning_rate": 5e-07,
      "loss": 0.2032,
      "step": 1213
    },
    {
      "clip_ratio/high_max": 0.002156454309442779,
      "clip_ratio/high_mean": 0.0007834785974409897,
      "clip_ratio/low_mean": 0.0009106947472901084,
      "clip_ratio/low_min": 4.3312965317454655e-05,
      "clip_ratio/region_mean": 0.0016941733483690768,
      "epoch": 0.11330638340070817,
      "grad_norm": 0.11209478974342346,
      "learning_rate": 5e-07,
      "loss": 0.0257,
      "step": 1214
    },
    {
      "clip_ratio/high_max": 0.002152887016563909,
      "clip_ratio/high_mean": 0.0008180663426173851,
      "clip_ratio/low_mean": 0.0011644792393781245,
      "clip_ratio/low_min": 7.278671364474576e-05,
      "clip_ratio/region_mean": 0.0019825455819955096,
      "epoch": 0.11339971650070875,
      "grad_norm": 0.11378854513168335,
      "learning_rate": 5e-07,
      "loss": 0.061,
      "step": 1215
    },
    {
      "clip_ratio/high_max": 0.002040522995230276,
      "clip_ratio/high_mean": 0.0008934020261222031,
      "clip_ratio/low_mean": 0.0008755569342611125,
      "clip_ratio/low_min": 0.00011013556650141254,
      "clip_ratio/region_mean": 0.0017689589403744321,
      "epoch": 0.11349304960070933,
      "grad_norm": 0.12178538739681244,
      "learning_rate": 5e-07,
      "loss": 0.0344,
      "step": 1216
    },
    {
      "clip_ratio/high_max": 0.0021630221490340773,
      "clip_ratio/high_mean": 0.000941852181313152,
      "clip_ratio/low_mean": 0.0010416757086204598,
      "clip_ratio/low_min": 6.603014480788261e-05,
      "clip_ratio/region_mean": 0.001983527858101297,
      "epoch": 0.11358638270070992,
      "grad_norm": 0.11508643627166748,
      "learning_rate": 5e-07,
      "loss": 0.0033,
      "step": 1217
    },
    {
      "clip_ratio/high_max": 0.001702859422948677,
      "clip_ratio/high_mean": 0.0007908211500762263,
      "clip_ratio/low_mean": 0.0009738203043525573,
      "clip_ratio/low_min": 0.00010406413548480486,
      "clip_ratio/region_mean": 0.0017646414416958578,
      "epoch": 0.1136797158007105,
      "grad_norm": 0.10959648340940475,
      "learning_rate": 5e-07,
      "loss": 0.0446,
      "step": 1218
    },
    {
      "clip_ratio/high_max": 0.00219518638914451,
      "clip_ratio/high_mean": 0.0008648720395285636,
      "clip_ratio/low_mean": 0.0010653283352439757,
      "clip_ratio/low_min": 6.636701345996698e-05,
      "clip_ratio/region_mean": 0.0019302003929624334,
      "epoch": 0.11377304890071108,
      "grad_norm": 0.11941582709550858,
      "learning_rate": 5e-07,
      "loss": 0.0598,
      "step": 1219
    },
    {
      "clip_ratio/high_max": 0.0018249690147058573,
      "clip_ratio/high_mean": 0.0007894317222962854,
      "clip_ratio/low_mean": 0.000920254429729539,
      "clip_ratio/low_min": 7.793757504259702e-05,
      "clip_ratio/region_mean": 0.0017096861338359304,
      "epoch": 0.11386638200071167,
      "grad_norm": 0.11130128800868988,
      "learning_rate": 5e-07,
      "loss": 0.0132,
      "step": 1220
    },
    {
      "clip_ratio/high_max": 0.0021243302544462495,
      "clip_ratio/high_mean": 0.0008967223257059231,
      "clip_ratio/low_mean": 0.0011180898763996083,
      "clip_ratio/low_min": 7.321929570025532e-05,
      "clip_ratio/region_mean": 0.00201481217663968,
      "epoch": 0.11395971510071225,
      "grad_norm": 0.14507541060447693,
      "learning_rate": 5e-07,
      "loss": 0.038,
      "step": 1221
    },
    {
      "clip_ratio/high_max": 0.002261683013784932,
      "clip_ratio/high_mean": 0.0009103009979298804,
      "clip_ratio/low_mean": 0.0010942161716229748,
      "clip_ratio/low_min": 0.00012385902027745033,
      "clip_ratio/region_mean": 0.002004517118621152,
      "epoch": 0.11405304820071283,
      "grad_norm": 0.11425713449716568,
      "learning_rate": 5e-07,
      "loss": 0.0374,
      "step": 1222
    },
    {
      "clip_ratio/high_max": 0.0022251758600759786,
      "clip_ratio/high_mean": 0.0008601920544606401,
      "clip_ratio/low_mean": 0.0011021660138794687,
      "clip_ratio/low_min": 2.8822111744375434e-05,
      "clip_ratio/region_mean": 0.0019623580810730346,
      "epoch": 0.11414638130071342,
      "grad_norm": 0.12383440881967545,
      "learning_rate": 5e-07,
      "loss": 0.0258,
      "step": 1223
    },
    {
      "clip_ratio/high_max": 0.0023127898894017562,
      "clip_ratio/high_mean": 0.0007931796571938321,
      "clip_ratio/low_mean": 0.0011399955164961284,
      "clip_ratio/low_min": 0.00015212632388283964,
      "clip_ratio/region_mean": 0.0019331751682329923,
      "epoch": 0.114239714400714,
      "grad_norm": 0.11794289946556091,
      "learning_rate": 5e-07,
      "loss": 0.0735,
      "step": 1224
    },
    {
      "clip_ratio/high_max": 0.0023863230053393636,
      "clip_ratio/high_mean": 0.0008916661572584417,
      "clip_ratio/low_mean": 0.0010779637123050634,
      "clip_ratio/low_min": 0.00010395661411166657,
      "clip_ratio/region_mean": 0.0019696298841154203,
      "epoch": 0.11433304750071459,
      "grad_norm": 0.17890411615371704,
      "learning_rate": 5e-07,
      "loss": 0.0257,
      "step": 1225
    },
    {
      "clip_ratio/high_max": 0.0026685979319154285,
      "clip_ratio/high_mean": 0.001042410502122948,
      "clip_ratio/low_mean": 0.000948591510677943,
      "clip_ratio/low_min": 5.140885514265392e-05,
      "clip_ratio/region_mean": 0.001991002012800891,
      "epoch": 0.11442638060071517,
      "grad_norm": 0.11247699707746506,
      "learning_rate": 5e-07,
      "loss": 0.0258,
      "step": 1226
    },
    {
      "clip_ratio/high_max": 0.0020813597657252103,
      "clip_ratio/high_mean": 0.000823951639176812,
      "clip_ratio/low_mean": 0.0009957637685147347,
      "clip_ratio/low_min": 6.45252330286894e-05,
      "clip_ratio/region_mean": 0.0018197154277004302,
      "epoch": 0.11451971370071574,
      "grad_norm": 1.751381516456604,
      "learning_rate": 5e-07,
      "loss": 0.023,
      "step": 1227
    },
    {
      "clip_ratio/high_max": 0.0021911267904215492,
      "clip_ratio/high_mean": 0.0008068316037679324,
      "clip_ratio/low_mean": 0.001111110919737257,
      "clip_ratio/low_min": 9.257402325602015e-05,
      "clip_ratio/region_mean": 0.001917942543514073,
      "epoch": 0.11461304680071634,
      "grad_norm": 0.11987506598234177,
      "learning_rate": 5e-07,
      "loss": 0.0628,
      "step": 1228
    },
    {
      "clip_ratio/high_max": 0.0019005959511559922,
      "clip_ratio/high_mean": 0.0006996209231147077,
      "clip_ratio/low_mean": 0.0009281214151997119,
      "clip_ratio/low_min": 0.00011579000056372024,
      "clip_ratio/region_mean": 0.0016277423383144196,
      "epoch": 0.11470637990071691,
      "grad_norm": 0.13328449428081512,
      "learning_rate": 5e-07,
      "loss": 0.0768,
      "step": 1229
    },
    {
      "clip_ratio/high_max": 0.002543924449128099,
      "clip_ratio/high_mean": 0.0009784810172277503,
      "clip_ratio/low_mean": 0.0008727988697501132,
      "clip_ratio/low_min": 8.882888323569205e-06,
      "clip_ratio/region_mean": 0.0018512798924348317,
      "epoch": 0.1147997130007175,
      "grad_norm": 0.124383844435215,
      "learning_rate": 5e-07,
      "loss": 0.0198,
      "step": 1230
    },
    {
      "clip_ratio/high_max": 0.0023268328222911805,
      "clip_ratio/high_mean": 0.001029562030453235,
      "clip_ratio/low_mean": 0.0009543510168441571,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0019839130400214344,
      "epoch": 0.11489304610071809,
      "grad_norm": 0.106465183198452,
      "learning_rate": 5e-07,
      "loss": -0.0309,
      "step": 1231
    },
    {
      "clip_ratio/high_max": 0.0023326313348661643,
      "clip_ratio/high_mean": 0.0008824543310765876,
      "clip_ratio/low_mean": 0.0009267572349926922,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0018092115496983752,
      "epoch": 0.11498637920071866,
      "grad_norm": 0.11825021356344223,
      "learning_rate": 5e-07,
      "loss": 0.0182,
      "step": 1232
    },
    {
      "clip_ratio/high_max": 0.0024530511182092596,
      "clip_ratio/high_mean": 0.00098752350822906,
      "clip_ratio/low_mean": 0.0009412916169821983,
      "clip_ratio/low_min": 6.901173583173659e-05,
      "clip_ratio/region_mean": 0.0019288150724605657,
      "epoch": 0.11507971230071924,
      "grad_norm": 0.13795027136802673,
      "learning_rate": 5e-07,
      "loss": 0.0304,
      "step": 1233
    },
    {
      "clip_ratio/high_max": 0.0022538065823027864,
      "clip_ratio/high_mean": 0.0008984241158032091,
      "clip_ratio/low_mean": 0.001081858830730198,
      "clip_ratio/low_min": 5.78755980313872e-05,
      "clip_ratio/region_mean": 0.0019802828901447356,
      "epoch": 0.11517304540071983,
      "grad_norm": 0.32387617230415344,
      "learning_rate": 5e-07,
      "loss": -0.0247,
      "step": 1234
    },
    {
      "clip_ratio/high_max": 0.0021572598852799274,
      "clip_ratio/high_mean": 0.0008789241328486241,
      "clip_ratio/low_mean": 0.001025816032779403,
      "clip_ratio/low_min": 0.00010007261516875587,
      "clip_ratio/region_mean": 0.001904740151076112,
      "epoch": 0.11526637850072041,
      "grad_norm": 0.11258342862129211,
      "learning_rate": 5e-07,
      "loss": 0.0594,
      "step": 1235
    },
    {
      "clip_ratio/high_max": 0.0023066199137247168,
      "clip_ratio/high_mean": 0.0008508258160873083,
      "clip_ratio/low_mean": 0.001037421412547701,
      "clip_ratio/low_min": 6.857288735773182e-05,
      "clip_ratio/region_mean": 0.001888247199531179,
      "epoch": 0.115359711600721,
      "grad_norm": 0.11641712486743927,
      "learning_rate": 5e-07,
      "loss": 0.0828,
      "step": 1236
    },
    {
      "clip_ratio/high_max": 0.0017395829927409068,
      "clip_ratio/high_mean": 0.0007521243487644824,
      "clip_ratio/low_mean": 0.0009512775068287738,
      "clip_ratio/low_min": 9.778577623364981e-05,
      "clip_ratio/region_mean": 0.0017034018637787085,
      "epoch": 0.11545304470072158,
      "grad_norm": 0.11794814467430115,
      "learning_rate": 5e-07,
      "loss": 0.0532,
      "step": 1237
    },
    {
      "clip_ratio/high_max": 0.0022712256541126408,
      "clip_ratio/high_mean": 0.0009227074551745318,
      "clip_ratio/low_mean": 0.0008099695533019258,
      "clip_ratio/low_min": 8.966878522187471e-05,
      "clip_ratio/region_mean": 0.0017326770757790655,
      "epoch": 0.11554637780072216,
      "grad_norm": 0.11881886422634125,
      "learning_rate": 5e-07,
      "loss": 0.0037,
      "step": 1238
    },
    {
      "clip_ratio/high_max": 0.002154740570404101,
      "clip_ratio/high_mean": 0.0009418639338036883,
      "clip_ratio/low_mean": 0.0008345717560587218,
      "clip_ratio/low_min": 2.7179821699974127e-05,
      "clip_ratio/region_mean": 0.0017764357035048306,
      "epoch": 0.11563971090072275,
      "grad_norm": 0.10992535948753357,
      "learning_rate": 5e-07,
      "loss": -0.0085,
      "step": 1239
    },
    {
      "clip_ratio/high_max": 0.002340214734431356,
      "clip_ratio/high_mean": 0.0009795812475204002,
      "clip_ratio/low_mean": 0.0009767694882611977,
      "clip_ratio/low_min": 8.371396506845485e-05,
      "clip_ratio/region_mean": 0.0019563507157727145,
      "epoch": 0.11573304400072333,
      "grad_norm": 0.31221315264701843,
      "learning_rate": 5e-07,
      "loss": -0.0051,
      "step": 1240
    },
    {
      "clip_ratio/high_max": 0.0021421108904178254,
      "clip_ratio/high_mean": 0.0009623713449400384,
      "clip_ratio/low_mean": 0.0008664818542456487,
      "clip_ratio/low_min": 8.08836157375481e-05,
      "clip_ratio/region_mean": 0.0018288531646248884,
      "epoch": 0.11582637710072391,
      "grad_norm": 406.6379089355469,
      "learning_rate": 5e-07,
      "loss": 0.1579,
      "step": 1241
    },
    {
      "clip_ratio/high_max": 0.0022805707194493152,
      "clip_ratio/high_mean": 0.000798512557594222,
      "clip_ratio/low_mean": 0.0009716733438835945,
      "clip_ratio/low_min": 2.410471915936796e-05,
      "clip_ratio/region_mean": 0.0017701859105727635,
      "epoch": 0.1159197102007245,
      "grad_norm": 0.1019567921757698,
      "learning_rate": 5e-07,
      "loss": 0.0212,
      "step": 1242
    },
    {
      "clip_ratio/high_max": 0.002211779596109409,
      "clip_ratio/high_mean": 0.0008620294283900876,
      "clip_ratio/low_mean": 0.0009899556625896366,
      "clip_ratio/low_min": 8.271676779258996e-05,
      "clip_ratio/region_mean": 0.0018519851109886076,
      "epoch": 0.11601304330072508,
      "grad_norm": 1.4943472146987915,
      "learning_rate": 5e-07,
      "loss": 0.0223,
      "step": 1243
    },
    {
      "clip_ratio/high_max": 0.0020242507744114846,
      "clip_ratio/high_mean": 0.0009044888120115502,
      "clip_ratio/low_mean": 0.0009191792123601772,
      "clip_ratio/low_min": 7.010592526057735e-05,
      "clip_ratio/region_mean": 0.0018236680480185896,
      "epoch": 0.11610637640072566,
      "grad_norm": 0.12484254688024521,
      "learning_rate": 5e-07,
      "loss": 0.0398,
      "step": 1244
    },
    {
      "clip_ratio/high_max": 0.002219717083789874,
      "clip_ratio/high_mean": 0.0008941054620663635,
      "clip_ratio/low_mean": 0.0009605327431927435,
      "clip_ratio/low_min": 5.5011316362651996e-05,
      "clip_ratio/region_mean": 0.0018546382343629375,
      "epoch": 0.11619970950072625,
      "grad_norm": 0.11709925532341003,
      "learning_rate": 5e-07,
      "loss": 0.0293,
      "step": 1245
    },
    {
      "clip_ratio/high_max": 0.0021654865704476833,
      "clip_ratio/high_mean": 0.0009097424990613945,
      "clip_ratio/low_mean": 0.0010270780494465725,
      "clip_ratio/low_min": 0.00010036911771749146,
      "clip_ratio/region_mean": 0.001936820597620681,
      "epoch": 0.11629304260072683,
      "grad_norm": 0.11999067664146423,
      "learning_rate": 5e-07,
      "loss": 0.0396,
      "step": 1246
    },
    {
      "clip_ratio/high_max": 0.0019245673465775326,
      "clip_ratio/high_mean": 0.0007860211044317111,
      "clip_ratio/low_mean": 0.0012157362398284022,
      "clip_ratio/low_min": 0.00010098491839016788,
      "clip_ratio/region_mean": 0.002001757369725965,
      "epoch": 0.11638637570072742,
      "grad_norm": 0.11935785412788391,
      "learning_rate": 5e-07,
      "loss": 0.0983,
      "step": 1247
    },
    {
      "clip_ratio/high_max": 0.002334884586161934,
      "clip_ratio/high_mean": 0.0009601511519576889,
      "clip_ratio/low_mean": 0.0009254174256057013,
      "clip_ratio/low_min": 1.793400224414654e-05,
      "clip_ratio/region_mean": 0.0018855685921153054,
      "epoch": 0.116479708800728,
      "grad_norm": 0.12714511156082153,
      "learning_rate": 5e-07,
      "loss": -0.0021,
      "step": 1248
    },
    {
      "clip_ratio/high_max": 0.002576768114522565,
      "clip_ratio/high_mean": 0.00090390977129573,
      "clip_ratio/low_mean": 0.0010724812000262318,
      "clip_ratio/low_min": 4.35524525528308e-05,
      "clip_ratio/region_mean": 0.0019763909149332903,
      "epoch": 0.11657304190072858,
      "grad_norm": 0.1365990936756134,
      "learning_rate": 5e-07,
      "loss": 0.0808,
      "step": 1249
    },
    {
      "clip_ratio/high_max": 0.002064667896775063,
      "clip_ratio/high_mean": 0.000883599679582403,
      "clip_ratio/low_mean": 0.0010854284810193349,
      "clip_ratio/low_min": 0.0001739892213663552,
      "clip_ratio/region_mean": 0.0019690281624207273,
      "epoch": 0.11666637500072917,
      "grad_norm": 28.07221221923828,
      "learning_rate": 5e-07,
      "loss": 0.0671,
      "step": 1250
    },
    {
      "clip_ratio/high_max": 0.0019024665452889167,
      "clip_ratio/high_mean": 0.0008683709856995847,
      "clip_ratio/low_mean": 0.0008824547785479808,
      "clip_ratio/low_min": 0.00012101549145882018,
      "clip_ratio/region_mean": 0.0017508257296867669,
      "epoch": 0.11675970810072975,
      "grad_norm": 0.10565845668315887,
      "learning_rate": 5e-07,
      "loss": 0.0423,
      "step": 1251
    },
    {
      "clip_ratio/high_max": 0.0023142233403632417,
      "clip_ratio/high_mean": 0.001006741762466845,
      "clip_ratio/low_mean": 0.0010669132789189462,
      "clip_ratio/low_min": 5.951854654995259e-05,
      "clip_ratio/region_mean": 0.002073655035928823,
      "epoch": 0.11685304120073033,
      "grad_norm": 0.11692948639392853,
      "learning_rate": 5e-07,
      "loss": 0.0014,
      "step": 1252
    },
    {
      "clip_ratio/high_max": 0.002158798983145971,
      "clip_ratio/high_mean": 0.0009181854948110413,
      "clip_ratio/low_mean": 0.0009329823187727015,
      "clip_ratio/low_min": 4.046415779157542e-05,
      "clip_ratio/region_mean": 0.001851167733548209,
      "epoch": 0.11694637430073092,
      "grad_norm": 0.12400393187999725,
      "learning_rate": 5e-07,
      "loss": 0.0181,
      "step": 1253
    },
    {
      "clip_ratio/high_max": 0.0024250194983324036,
      "clip_ratio/high_mean": 0.000995553346001543,
      "clip_ratio/low_mean": 0.0010054756839963375,
      "clip_ratio/low_min": 0.00012948813946422888,
      "clip_ratio/region_mean": 0.002001028995437082,
      "epoch": 0.1170397074007315,
      "grad_norm": 0.12601174414157867,
      "learning_rate": 5e-07,
      "loss": 0.0447,
      "step": 1254
    },
    {
      "clip_ratio/high_max": 0.0021263410744722933,
      "clip_ratio/high_mean": 0.0008562171497032978,
      "clip_ratio/low_mean": 0.0010095926882058848,
      "clip_ratio/low_min": 5.82509019295685e-05,
      "clip_ratio/region_mean": 0.0018658098124433309,
      "epoch": 0.11713304050073207,
      "grad_norm": 0.12414980679750443,
      "learning_rate": 5e-07,
      "loss": 0.0078,
      "step": 1255
    },
    {
      "clip_ratio/high_max": 0.0018032820407825056,
      "clip_ratio/high_mean": 0.0006806499650338083,
      "clip_ratio/low_mean": 0.001055337990692351,
      "clip_ratio/low_min": 8.504369179718196e-05,
      "clip_ratio/region_mean": 0.0017359879711875692,
      "epoch": 0.11722637360073267,
      "grad_norm": 0.11526145786046982,
      "learning_rate": 5e-07,
      "loss": 0.0867,
      "step": 1256
    },
    {
      "clip_ratio/high_max": 0.0021233525694697164,
      "clip_ratio/high_mean": 0.0009020292854984291,
      "clip_ratio/low_mean": 0.0010798255025292747,
      "clip_ratio/low_min": 4.7181254558381625e-05,
      "clip_ratio/region_mean": 0.0019818547880277038,
      "epoch": 0.11731970670073325,
      "grad_norm": 0.11604705452919006,
      "learning_rate": 5e-07,
      "loss": 0.0366,
      "step": 1257
    },
    {
      "clip_ratio/high_max": 0.0025074144286918454,
      "clip_ratio/high_mean": 0.0009209149775415426,
      "clip_ratio/low_mean": 0.0011060538599849679,
      "clip_ratio/low_min": 0.00013280035636853427,
      "clip_ratio/region_mean": 0.0020269688466214575,
      "epoch": 0.11741303980073384,
      "grad_norm": 0.1271158754825592,
      "learning_rate": 5e-07,
      "loss": 0.0411,
      "step": 1258
    },
    {
      "clip_ratio/high_max": 0.0022469385294243693,
      "clip_ratio/high_mean": 0.0008779599011177197,
      "clip_ratio/low_mean": 0.0009356526170449797,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0018136125363525935,
      "epoch": 0.11750637290073442,
      "grad_norm": 0.10565166920423508,
      "learning_rate": 5e-07,
      "loss": -0.003,
      "step": 1259
    },
    {
      "clip_ratio/high_max": 0.002202302945079282,
      "clip_ratio/high_mean": 0.0009721650239953306,
      "clip_ratio/low_mean": 0.0009412313393113436,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0019133964233333245,
      "epoch": 0.117599706000735,
      "grad_norm": 0.11820133775472641,
      "learning_rate": 5e-07,
      "loss": -0.0013,
      "step": 1260
    },
    {
      "clip_ratio/high_max": 0.002229243007604964,
      "clip_ratio/high_mean": 0.0009156113046628889,
      "clip_ratio/low_mean": 0.001056288238032721,
      "clip_ratio/low_min": 0.0001316608149863896,
      "clip_ratio/region_mean": 0.0019718994954018854,
      "epoch": 0.11769303910073559,
      "grad_norm": 0.5987722873687744,
      "learning_rate": 5e-07,
      "loss": 0.0432,
      "step": 1261
    },
    {
      "clip_ratio/high_max": 0.0021050179275334813,
      "clip_ratio/high_mean": 0.0008561377435398754,
      "clip_ratio/low_mean": 0.0009805737954593496,
      "clip_ratio/low_min": 0.0001348635223621386,
      "clip_ratio/region_mean": 0.0018367115335422568,
      "epoch": 0.11778637220073616,
      "grad_norm": 0.11474203318357468,
      "learning_rate": 5e-07,
      "loss": 0.0219,
      "step": 1262
    },
    {
      "clip_ratio/high_max": 0.002209468057117192,
      "clip_ratio/high_mean": 0.0009247207708540373,
      "clip_ratio/low_mean": 0.0009123018971877173,
      "clip_ratio/low_min": 5.1632254326250404e-05,
      "clip_ratio/region_mean": 0.001837022638937924,
      "epoch": 0.11787970530073674,
      "grad_norm": 0.10742940753698349,
      "learning_rate": 5e-07,
      "loss": 0.0023,
      "step": 1263
    },
    {
      "clip_ratio/high_max": 0.0025981537110055797,
      "clip_ratio/high_mean": 0.0009093607077375054,
      "clip_ratio/low_mean": 0.00102345120467362,
      "clip_ratio/low_min": 3.4199725632788613e-05,
      "clip_ratio/region_mean": 0.001932811901497189,
      "epoch": 0.11797303840073733,
      "grad_norm": 0.5043108463287354,
      "learning_rate": 5e-07,
      "loss": 0.0216,
      "step": 1264
    },
    {
      "clip_ratio/high_max": 0.0026272981413058005,
      "clip_ratio/high_mean": 0.0010035802060883725,
      "clip_ratio/low_mean": 0.0010460911253176164,
      "clip_ratio/low_min": 1.3295043572725262e-05,
      "clip_ratio/region_mean": 0.002049671318673063,
      "epoch": 0.11806637150073791,
      "grad_norm": 0.13822640478610992,
      "learning_rate": 5e-07,
      "loss": 0.0097,
      "step": 1265
    },
    {
      "clip_ratio/high_max": 0.0021778135997010395,
      "clip_ratio/high_mean": 0.0009163591421383899,
      "clip_ratio/low_mean": 0.0008967870526248589,
      "clip_ratio/low_min": 6.579901764780516e-05,
      "clip_ratio/region_mean": 0.0018131461838493124,
      "epoch": 0.1181597046007385,
      "grad_norm": 0.1126396432518959,
      "learning_rate": 5e-07,
      "loss": 0.0031,
      "step": 1266
    },
    {
      "clip_ratio/high_max": 0.0023096541735867504,
      "clip_ratio/high_mean": 0.000980135477220756,
      "clip_ratio/low_mean": 0.0009189689317281591,
      "clip_ratio/low_min": 9.089663399208803e-05,
      "clip_ratio/region_mean": 0.001899104390759021,
      "epoch": 0.11825303770073908,
      "grad_norm": 0.10686055570840836,
      "learning_rate": 5e-07,
      "loss": -0.0069,
      "step": 1267
    },
    {
      "clip_ratio/high_max": 0.002651001384947449,
      "clip_ratio/high_mean": 0.0010115931872860529,
      "clip_ratio/low_mean": 0.0008818112619337626,
      "clip_ratio/low_min": 6.308980300673284e-05,
      "clip_ratio/region_mean": 0.0018934044492198154,
      "epoch": 0.11834637080073966,
      "grad_norm": 0.11161494255065918,
      "learning_rate": 5e-07,
      "loss": -0.0213,
      "step": 1268
    },
    {
      "clip_ratio/high_max": 0.002364034211495891,
      "clip_ratio/high_mean": 0.0009686286102805752,
      "clip_ratio/low_mean": 0.0010195216727879597,
      "clip_ratio/low_min": 9.326740837423131e-05,
      "clip_ratio/region_mean": 0.0019881502958014607,
      "epoch": 0.11843970390074025,
      "grad_norm": 0.11723088473081589,
      "learning_rate": 5e-07,
      "loss": -0.003,
      "step": 1269
    },
    {
      "clip_ratio/high_max": 0.002288062736624852,
      "clip_ratio/high_mean": 0.0009180537999782246,
      "clip_ratio/low_mean": 0.0008909913940442493,
      "clip_ratio/low_min": 3.517726599966409e-05,
      "clip_ratio/region_mean": 0.0018090451922034845,
      "epoch": 0.11853303700074083,
      "grad_norm": 0.10404518246650696,
      "learning_rate": 5e-07,
      "loss": -0.0016,
      "step": 1270
    },
    {
      "clip_ratio/high_max": 0.0023332109085458796,
      "clip_ratio/high_mean": 0.0009230015548382653,
      "clip_ratio/low_mean": 0.0010247597074339865,
      "clip_ratio/low_min": 9.322801543021342e-05,
      "clip_ratio/region_mean": 0.0019477612804621458,
      "epoch": 0.11862637010074141,
      "grad_norm": 0.1301572024822235,
      "learning_rate": 5e-07,
      "loss": 0.0311,
      "step": 1271
    },
    {
      "clip_ratio/high_max": 0.0020599711751856375,
      "clip_ratio/high_mean": 0.0007856431675463682,
      "clip_ratio/low_mean": 0.0011468699667602777,
      "clip_ratio/low_min": 0.0001534195043859654,
      "clip_ratio/region_mean": 0.0019325131506775506,
      "epoch": 0.118719703200742,
      "grad_norm": 2049.79638671875,
      "learning_rate": 5e-07,
      "loss": 0.7858,
      "step": 1272
    },
    {
      "clip_ratio/high_max": 0.0019347968482179567,
      "clip_ratio/high_mean": 0.0007946524183353176,
      "clip_ratio/low_mean": 0.0008741575366002508,
      "clip_ratio/low_min": 2.8273724637983833e-05,
      "clip_ratio/region_mean": 0.0016688099567545578,
      "epoch": 0.11881303630074258,
      "grad_norm": 0.11583459377288818,
      "learning_rate": 5e-07,
      "loss": 0.0488,
      "step": 1273
    },
    {
      "clip_ratio/high_max": 0.0022649456332146656,
      "clip_ratio/high_mean": 0.0008837470913931611,
      "clip_ratio/low_mean": 0.0009692321018519579,
      "clip_ratio/low_min": 0.00010977074452966917,
      "clip_ratio/region_mean": 0.0018529791996115819,
      "epoch": 0.11890636940074316,
      "grad_norm": 0.21776854991912842,
      "learning_rate": 5e-07,
      "loss": 0.0113,
      "step": 1274
    },
    {
      "clip_ratio/high_max": 0.0024318158539244905,
      "clip_ratio/high_mean": 0.0010838061662070686,
      "clip_ratio/low_mean": 0.0009914270995068364,
      "clip_ratio/low_min": 9.826734458329156e-05,
      "clip_ratio/region_mean": 0.0020752332857227884,
      "epoch": 0.11899970250074375,
      "grad_norm": 1.8346055746078491,
      "learning_rate": 5e-07,
      "loss": -0.0164,
      "step": 1275
    },
    {
      "clip_ratio/high_max": 0.0018517436692491174,
      "clip_ratio/high_mean": 0.0008058593703026418,
      "clip_ratio/low_mean": 0.001155867848865455,
      "clip_ratio/low_min": 0.00013378586118051317,
      "clip_ratio/region_mean": 0.0019617271827883087,
      "epoch": 0.11909303560074433,
      "grad_norm": 0.12086240947246552,
      "learning_rate": 5e-07,
      "loss": 0.0327,
      "step": 1276
    },
    {
      "clip_ratio/high_max": 0.002111982452333905,
      "clip_ratio/high_mean": 0.000886274687218247,
      "clip_ratio/low_mean": 0.0007808978216417017,
      "clip_ratio/low_min": 3.693741928145755e-05,
      "clip_ratio/region_mean": 0.0016671725134074222,
      "epoch": 0.11918636870074492,
      "grad_norm": 0.10185153037309647,
      "learning_rate": 5e-07,
      "loss": 0.0241,
      "step": 1277
    },
    {
      "clip_ratio/high_max": 0.0022858345037093386,
      "clip_ratio/high_mean": 0.000988524523563683,
      "clip_ratio/low_mean": 0.0009783822824829258,
      "clip_ratio/low_min": 8.904675178200705e-05,
      "clip_ratio/region_mean": 0.0019669067987706512,
      "epoch": 0.1192797018007455,
      "grad_norm": 0.12546411156654358,
      "learning_rate": 5e-07,
      "loss": 0.0274,
      "step": 1278
    },
    {
      "clip_ratio/high_max": 0.002525535524910083,
      "clip_ratio/high_mean": 0.0010896292587858625,
      "clip_ratio/low_mean": 0.001010223417324596,
      "clip_ratio/low_min": 0.00017371305239066714,
      "clip_ratio/region_mean": 0.002099852717947215,
      "epoch": 0.11937303490074608,
      "grad_norm": 0.11944941431283951,
      "learning_rate": 5e-07,
      "loss": -0.0002,
      "step": 1279
    },
    {
      "clip_ratio/high_max": 0.0021026518152211793,
      "clip_ratio/high_mean": 0.0009360225558339152,
      "clip_ratio/low_mean": 0.001035477365803672,
      "clip_ratio/low_min": 7.446501876984257e-05,
      "clip_ratio/region_mean": 0.00197149994346546,
      "epoch": 0.11946636800074667,
      "grad_norm": 0.10836319625377655,
      "learning_rate": 5e-07,
      "loss": 0.0014,
      "step": 1280
    },
    {
      "clip_ratio/high_max": 0.0023283340560737997,
      "clip_ratio/high_mean": 0.0009157819458778249,
      "clip_ratio/low_mean": 0.0009913807934935903,
      "clip_ratio/low_min": 7.127870412659831e-05,
      "clip_ratio/region_mean": 0.0019071626957156695,
      "epoch": 0.11955970110074725,
      "grad_norm": 0.11058159917593002,
      "learning_rate": 5e-07,
      "loss": -0.0037,
      "step": 1281
    },
    {
      "clip_ratio/high_max": 0.0021044007953605615,
      "clip_ratio/high_mean": 0.0009211238830175716,
      "clip_ratio/low_mean": 0.0009698776175355306,
      "clip_ratio/low_min": 5.265465551929083e-05,
      "clip_ratio/region_mean": 0.0018910015278379433,
      "epoch": 0.11965303420074783,
      "grad_norm": 0.11504515260457993,
      "learning_rate": 5e-07,
      "loss": -0.022,
      "step": 1282
    },
    {
      "clip_ratio/high_max": 0.0021702060294046532,
      "clip_ratio/high_mean": 0.0008456623454549117,
      "clip_ratio/low_mean": 0.0010818849095812766,
      "clip_ratio/low_min": 6.561726877407636e-05,
      "clip_ratio/region_mean": 0.0019275472513982095,
      "epoch": 0.11974636730074842,
      "grad_norm": 0.11665759235620499,
      "learning_rate": 5e-07,
      "loss": 0.0165,
      "step": 1283
    },
    {
      "clip_ratio/high_max": 0.0019173015498381574,
      "clip_ratio/high_mean": 0.0008332533361681271,
      "clip_ratio/low_mean": 0.001020731144308229,
      "clip_ratio/low_min": 0.00016637704902677797,
      "clip_ratio/region_mean": 0.001853984453191515,
      "epoch": 0.119839700400749,
      "grad_norm": 0.12326914072036743,
      "learning_rate": 5e-07,
      "loss": 0.0405,
      "step": 1284
    },
    {
      "clip_ratio/high_max": 0.002200053266278701,
      "clip_ratio/high_mean": 0.000849699737955234,
      "clip_ratio/low_mean": 0.0009642534823797178,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0018139532039640471,
      "epoch": 0.11993303350074958,
      "grad_norm": 0.11666156351566315,
      "learning_rate": 5e-07,
      "loss": 0.0322,
      "step": 1285
    },
    {
      "clip_ratio/high_max": 0.0022218117665033787,
      "clip_ratio/high_mean": 0.0010250888990412932,
      "clip_ratio/low_mean": 0.0009651672226027586,
      "clip_ratio/low_min": 6.775752262910828e-05,
      "clip_ratio/region_mean": 0.0019902561616618186,
      "epoch": 0.12002636660075017,
      "grad_norm": 0.11741018295288086,
      "learning_rate": 5e-07,
      "loss": -0.027,
      "step": 1286
    },
    {
      "clip_ratio/high_max": 0.0019751415893551894,
      "clip_ratio/high_mean": 0.0007864556409913348,
      "clip_ratio/low_mean": 0.0011966804613621207,
      "clip_ratio/low_min": 6.081684250602848e-05,
      "clip_ratio/region_mean": 0.0019831360841635615,
      "epoch": 0.12011969970075075,
      "grad_norm": 0.11658815294504166,
      "learning_rate": 5e-07,
      "loss": 0.0468,
      "step": 1287
    },
    {
      "clip_ratio/high_max": 0.00218927341120434,
      "clip_ratio/high_mean": 0.0008886889836503542,
      "clip_ratio/low_mean": 0.0009708081415737979,
      "clip_ratio/low_min": 6.419259898393648e-05,
      "clip_ratio/region_mean": 0.0018594971115817316,
      "epoch": 0.12021303280075134,
      "grad_norm": 0.10695496201515198,
      "learning_rate": 5e-07,
      "loss": 0.0245,
      "step": 1288
    },
    {
      "clip_ratio/high_max": 0.002182773758249823,
      "clip_ratio/high_mean": 0.000713562664714118,
      "clip_ratio/low_mean": 0.0011614801424002508,
      "clip_ratio/low_min": 7.575402742077131e-05,
      "clip_ratio/region_mean": 0.0018750428353087045,
      "epoch": 0.12030636590075192,
      "grad_norm": 1.980177640914917,
      "learning_rate": 5e-07,
      "loss": 0.0456,
      "step": 1289
    },
    {
      "clip_ratio/high_max": 0.0024294762406498194,
      "clip_ratio/high_mean": 0.0009428713947272627,
      "clip_ratio/low_mean": 0.001065320750058163,
      "clip_ratio/low_min": 9.956904068531003e-05,
      "clip_ratio/region_mean": 0.0020081921538803726,
      "epoch": 0.1203996990007525,
      "grad_norm": 0.11842073500156403,
      "learning_rate": 5e-07,
      "loss": 0.0264,
      "step": 1290
    },
    {
      "clip_ratio/high_max": 0.0022096148022683337,
      "clip_ratio/high_mean": 0.0008882955316948937,
      "clip_ratio/low_mean": 0.0010749726570793428,
      "clip_ratio/low_min": 0.0001431282471457962,
      "clip_ratio/region_mean": 0.001963268150575459,
      "epoch": 0.12049303210075309,
      "grad_norm": 0.12054868042469025,
      "learning_rate": 5e-07,
      "loss": 0.0106,
      "step": 1291
    },
    {
      "clip_ratio/high_max": 0.002166197089536581,
      "clip_ratio/high_mean": 0.0009111121544265188,
      "clip_ratio/low_mean": 0.0010064243542728946,
      "clip_ratio/low_min": 3.845020546577871e-05,
      "clip_ratio/region_mean": 0.0019175365305272862,
      "epoch": 0.12058636520075366,
      "grad_norm": 0.13060201704502106,
      "learning_rate": 5e-07,
      "loss": 0.0294,
      "step": 1292
    },
    {
      "clip_ratio/high_max": 0.002195702189055737,
      "clip_ratio/high_mean": 0.0007908511051937239,
      "clip_ratio/low_mean": 0.0010419459595141234,
      "clip_ratio/low_min": 1.4404240573639981e-05,
      "clip_ratio/region_mean": 0.001832797031966038,
      "epoch": 0.12067969830075424,
      "grad_norm": 0.11094895750284195,
      "learning_rate": 5e-07,
      "loss": 0.0159,
      "step": 1293
    },
    {
      "clip_ratio/high_max": 0.00214183908974519,
      "clip_ratio/high_mean": 0.0009292303057009121,
      "clip_ratio/low_mean": 0.001052181494742399,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0019814118059002794,
      "epoch": 0.12077303140075484,
      "grad_norm": 4.045433044433594,
      "learning_rate": 5e-07,
      "loss": 0.0658,
      "step": 1294
    },
    {
      "clip_ratio/high_max": 0.002099885776260635,
      "clip_ratio/high_mean": 0.0009003356526591233,
      "clip_ratio/low_mean": 0.000971496327110799,
      "clip_ratio/low_min": 4.15158301620977e-05,
      "clip_ratio/region_mean": 0.001871831998869311,
      "epoch": 0.12086636450075541,
      "grad_norm": 0.15263043344020844,
      "learning_rate": 5e-07,
      "loss": 0.0103,
      "step": 1295
    },
    {
      "clip_ratio/high_max": 0.002164354631531751,
      "clip_ratio/high_mean": 0.001002479337330442,
      "clip_ratio/low_mean": 0.0008862683280312922,
      "clip_ratio/low_min": 8.682950101501774e-05,
      "clip_ratio/region_mean": 0.001888747705379501,
      "epoch": 0.12095969760075599,
      "grad_norm": 0.11646023392677307,
      "learning_rate": 5e-07,
      "loss": -0.0356,
      "step": 1296
    },
    {
      "clip_ratio/high_max": 0.0019680644836626016,
      "clip_ratio/high_mean": 0.0008426334679825231,
      "clip_ratio/low_mean": 0.0011592114460654557,
      "clip_ratio/low_min": 4.157765943091363e-05,
      "clip_ratio/region_mean": 0.0020018449031340424,
      "epoch": 0.12105303070075658,
      "grad_norm": 0.10595829784870148,
      "learning_rate": 5e-07,
      "loss": 0.0225,
      "step": 1297
    },
    {
      "clip_ratio/high_max": 0.002678918324818369,
      "clip_ratio/high_mean": 0.0009986695858970052,
      "clip_ratio/low_mean": 0.0010149792869924568,
      "clip_ratio/low_min": 4.5461280933523085e-05,
      "clip_ratio/region_mean": 0.0020136488892603666,
      "epoch": 0.12114636380075716,
      "grad_norm": 0.11142535507678986,
      "learning_rate": 5e-07,
      "loss": -0.0097,
      "step": 1298
    },
    {
      "clip_ratio/high_max": 0.0018845587474061176,
      "clip_ratio/high_mean": 0.0007159833439800423,
      "clip_ratio/low_mean": 0.00123968620391679,
      "clip_ratio/low_min": 0.000103541363387194,
      "clip_ratio/region_mean": 0.0019556695406208746,
      "epoch": 0.12123969690075775,
      "grad_norm": 0.10812246799468994,
      "learning_rate": 5e-07,
      "loss": 0.0575,
      "step": 1299
    },
    {
      "clip_ratio/high_max": 0.0023332552336796653,
      "clip_ratio/high_mean": 0.0009133643907262012,
      "clip_ratio/low_mean": 0.00107748001391883,
      "clip_ratio/low_min": 9.648655850469368e-05,
      "clip_ratio/region_mean": 0.001990844357351307,
      "epoch": 0.12133303000075833,
      "grad_norm": 0.10804838687181473,
      "learning_rate": 5e-07,
      "loss": 0.0169,
      "step": 1300
    },
    {
      "clip_ratio/high_max": 0.002256531734019518,
      "clip_ratio/high_mean": 0.0009473047794017475,
      "clip_ratio/low_mean": 0.0010424900337966392,
      "clip_ratio/low_min": 6.342186134133954e-05,
      "clip_ratio/region_mean": 0.0019897948586731218,
      "epoch": 0.12142636310075891,
      "grad_norm": 0.09887094795703888,
      "learning_rate": 5e-07,
      "loss": -0.0025,
      "step": 1301
    },
    {
      "clip_ratio/high_max": 0.0024981441092677414,
      "clip_ratio/high_mean": 0.0009977782065107021,
      "clip_ratio/low_mean": 0.001090261173885665,
      "clip_ratio/low_min": 0.0001298163151659537,
      "clip_ratio/region_mean": 0.002088039356749505,
      "epoch": 0.1215196962007595,
      "grad_norm": 0.12199176847934723,
      "learning_rate": 5e-07,
      "loss": 0.0197,
      "step": 1302
    },
    {
      "clip_ratio/high_max": 0.002176059140765574,
      "clip_ratio/high_mean": 0.0008912082230381202,
      "clip_ratio/low_mean": 0.0009368934042868204,
      "clip_ratio/low_min": 4.19578755099792e-05,
      "clip_ratio/region_mean": 0.0018281016236869618,
      "epoch": 0.12161302930076008,
      "grad_norm": 0.11578170955181122,
      "learning_rate": 5e-07,
      "loss": -0.0045,
      "step": 1303
    },
    {
      "clip_ratio/high_max": 0.002103113500197651,
      "clip_ratio/high_mean": 0.0007247126104630297,
      "clip_ratio/low_mean": 0.001201308663439704,
      "clip_ratio/low_min": 0.00011884560990438331,
      "clip_ratio/region_mean": 0.0019260212757217232,
      "epoch": 0.12170636240076066,
      "grad_norm": 0.10969202220439911,
      "learning_rate": 5e-07,
      "loss": 0.0746,
      "step": 1304
    },
    {
      "clip_ratio/high_max": 0.002081110065773828,
      "clip_ratio/high_mean": 0.0008592830890847836,
      "clip_ratio/low_mean": 0.0011714376851159614,
      "clip_ratio/low_min": 8.497014277963899e-05,
      "clip_ratio/region_mean": 0.002030720752372872,
      "epoch": 0.12179969550076125,
      "grad_norm": 0.12623469531536102,
      "learning_rate": 5e-07,
      "loss": 0.033,
      "step": 1305
    },
    {
      "clip_ratio/high_max": 0.0020700262757600285,
      "clip_ratio/high_mean": 0.0008406536471738946,
      "clip_ratio/low_mean": 0.0011973562177445274,
      "clip_ratio/low_min": 0.00014904931231285445,
      "clip_ratio/region_mean": 0.0020380098503665067,
      "epoch": 0.12189302860076183,
      "grad_norm": 0.10772968083620071,
      "learning_rate": 5e-07,
      "loss": -0.0033,
      "step": 1306
    },
    {
      "clip_ratio/high_max": 0.0020887509381282143,
      "clip_ratio/high_mean": 0.0008426455460721627,
      "clip_ratio/low_mean": 0.0011968433136644308,
      "clip_ratio/low_min": 7.966980956553016e-05,
      "clip_ratio/region_mean": 0.0020394888779264875,
      "epoch": 0.12198636170076241,
      "grad_norm": 0.11716651171445847,
      "learning_rate": 5e-07,
      "loss": 0.065,
      "step": 1307
    },
    {
      "clip_ratio/high_max": 0.002151227898139041,
      "clip_ratio/high_mean": 0.001000100288365502,
      "clip_ratio/low_mean": 0.0011827656016976107,
      "clip_ratio/low_min": 5.866446917934809e-05,
      "clip_ratio/region_mean": 0.0021828658573213033,
      "epoch": 0.122079694800763,
      "grad_norm": 0.12070108950138092,
      "learning_rate": 5e-07,
      "loss": 0.0198,
      "step": 1308
    },
    {
      "clip_ratio/high_max": 0.002039961786067579,
      "clip_ratio/high_mean": 0.0007761551078147022,
      "clip_ratio/low_mean": 0.0011785774368036073,
      "clip_ratio/low_min": 0.0001571708980918629,
      "clip_ratio/region_mean": 0.001954732564627193,
      "epoch": 0.12217302790076358,
      "grad_norm": 0.10919660329818726,
      "learning_rate": 5e-07,
      "loss": 0.0454,
      "step": 1309
    },
    {
      "clip_ratio/high_max": 0.002235385218227748,
      "clip_ratio/high_mean": 0.0009479316831857432,
      "clip_ratio/low_mean": 0.0010193905764026567,
      "clip_ratio/low_min": 9.423948540643323e-05,
      "clip_ratio/region_mean": 0.0019673222996061668,
      "epoch": 0.12226636100076417,
      "grad_norm": 0.147433340549469,
      "learning_rate": 5e-07,
      "loss": 0.0172,
      "step": 1310
    },
    {
      "clip_ratio/high_max": 0.002255330327898264,
      "clip_ratio/high_mean": 0.0009533040793030523,
      "clip_ratio/low_mean": 0.0010176275973208249,
      "clip_ratio/low_min": 5.756541850132635e-05,
      "clip_ratio/region_mean": 0.001970931625692174,
      "epoch": 0.12235969410076475,
      "grad_norm": 0.1167151927947998,
      "learning_rate": 5e-07,
      "loss": 0.0491,
      "step": 1311
    },
    {
      "clip_ratio/high_max": 0.0019646287837531418,
      "clip_ratio/high_mean": 0.0007936190977488877,
      "clip_ratio/low_mean": 0.001194469445181312,
      "clip_ratio/low_min": 0.00013890384707337944,
      "clip_ratio/region_mean": 0.001988088588404935,
      "epoch": 0.12245302720076533,
      "grad_norm": 0.11477208882570267,
      "learning_rate": 5e-07,
      "loss": 0.0386,
      "step": 1312
    },
    {
      "clip_ratio/high_max": 0.0024762040993664414,
      "clip_ratio/high_mean": 0.0009389829556312179,
      "clip_ratio/low_mean": 0.0008819503109407378,
      "clip_ratio/low_min": 6.778003898944007e-05,
      "clip_ratio/region_mean": 0.0018209332956757862,
      "completions/clipped_ratio": 0.013741629464285698,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4096.0,
      "completions/mean_length": 610.484375,
      "completions/mean_terminated_length": 561.9203491210938,
      "completions/min_length": 6.0,
      "completions/min_terminated_length": 6.0,
      "epoch": 0.12254636030076592,
      "grad_norm": 437425.625,
      "learning_rate": 5e-07,
      "loss": 59.4023,
      "num_tokens": 977709336.0,
      "reward": 0.6001412868499756,
      "reward_std": 0.1876489818096161,
      "rewards/simpleverify_reward/mean": 0.6001412272453308,
      "rewards/simpleverify_reward/std": 0.48987123370170593,
      "step": 1313
    },
    {
      "clip_ratio/high_max": 0.00211399345062091,
      "clip_ratio/high_mean": 0.0008991142785816919,
      "clip_ratio/low_mean": 0.0008616535615146859,
      "clip_ratio/low_min": 9.398854126629885e-05,
      "clip_ratio/region_mean": 0.0017607678673812188,
      "epoch": 0.1226396934007665,
      "grad_norm": 5371.74365234375,
      "learning_rate": 5e-07,
      "loss": 6.5931,
      "step": 1314
    },
    {
      "clip_ratio/high_max": 0.0019454425637377426,
      "clip_ratio/high_mean": 0.0008342603196069831,
      "clip_ratio/low_mean": 0.0010889555524045136,
      "clip_ratio/low_min": 0.00014489163004327565,
      "clip_ratio/region_mean": 0.001923215895658359,
      "epoch": 0.12273302650076708,
      "grad_norm": 129.1634063720703,
      "learning_rate": 5e-07,
      "loss": 0.0964,
      "step": 1315
    },
    {
      "clip_ratio/high_max": 0.0021637592944898643,
      "clip_ratio/high_mean": 0.0009532997628411977,
      "clip_ratio/low_mean": 0.0008766300597926602,
      "clip_ratio/low_min": 4.332210573920747e-05,
      "clip_ratio/region_mean": 0.0018299297807971016,
      "epoch": 0.12282635960076767,
      "grad_norm": 0.1172322928905487,
      "learning_rate": 5e-07,
      "loss": -0.0107,
      "step": 1316
    },
    {
      "clip_ratio/high_max": 0.0024026143000810407,
      "clip_ratio/high_mean": 0.0009241114239557646,
      "clip_ratio/low_mean": 0.0008247759633377427,
      "clip_ratio/low_min": 1.0783298421301879e-05,
      "clip_ratio/region_mean": 0.001748887385474518,
      "epoch": 0.12291969270076825,
      "grad_norm": 0.20549090206623077,
      "learning_rate": 5e-07,
      "loss": 0.0215,
      "step": 1317
    },
    {
      "clip_ratio/high_max": 0.002197716399678029,
      "clip_ratio/high_mean": 0.0009114989861700451,
      "clip_ratio/low_mean": 0.0009259373073291499,
      "clip_ratio/low_min": 4.0467891267326195e-05,
      "clip_ratio/region_mean": 0.0018374362989561632,
      "epoch": 0.12301302580076884,
      "grad_norm": 0.1245655044913292,
      "learning_rate": 5e-07,
      "loss": 0.0298,
      "step": 1318
    },
    {
      "clip_ratio/high_max": 0.0021603385648631956,
      "clip_ratio/high_mean": 0.0008424050465691835,
      "clip_ratio/low_mean": 0.0009884586306725396,
      "clip_ratio/low_min": 7.465497128578136e-05,
      "clip_ratio/region_mean": 0.0018308636899746489,
      "epoch": 0.12310635890076942,
      "grad_norm": 46.594669342041016,
      "learning_rate": 5e-07,
      "loss": 0.0431,
      "step": 1319
    },
    {
      "clip_ratio/high_max": 0.00221382052404806,
      "clip_ratio/high_mean": 0.0009453276561544044,
      "clip_ratio/low_mean": 0.0008872678845364135,
      "clip_ratio/low_min": 6.190485783008626e-05,
      "clip_ratio/region_mean": 0.0018325955024920404,
      "epoch": 0.12319969200077,
      "grad_norm": 231.05712890625,
      "learning_rate": 5e-07,
      "loss": 0.0605,
      "step": 1320
    },
    {
      "clip_ratio/high_max": 0.001802992443117546,
      "clip_ratio/high_mean": 0.0007058934097585734,
      "clip_ratio/low_mean": 0.0007656725229026051,
      "clip_ratio/low_min": 5.470592077472247e-05,
      "clip_ratio/region_mean": 0.0014715659781359136,
      "epoch": 0.12329302510077059,
      "grad_norm": 0.3335617780685425,
      "learning_rate": 5e-07,
      "loss": 0.0233,
      "step": 1321
    },
    {
      "clip_ratio/high_max": 0.0024308565552928485,
      "clip_ratio/high_mean": 0.000939704852498835,
      "clip_ratio/low_mean": 0.0008978908990684431,
      "clip_ratio/low_min": 3.2572162126598414e-05,
      "clip_ratio/region_mean": 0.0018375956860836595,
      "epoch": 0.12338635820077117,
      "grad_norm": 35.49447250366211,
      "learning_rate": 5e-07,
      "loss": 6.6706,
      "step": 1322
    },
    {
      "clip_ratio/high_max": 0.002074432672088733,
      "clip_ratio/high_mean": 0.0009241430334441247,
      "clip_ratio/low_mean": 0.000945768502788269,
      "clip_ratio/low_min": 0.00011742074457288254,
      "clip_ratio/region_mean": 0.0018699115316849202,
      "epoch": 0.12347969130077174,
      "grad_norm": 103.82074737548828,
      "learning_rate": 5e-07,
      "loss": 0.0215,
      "step": 1323
    },
    {
      "clip_ratio/high_max": 0.002276814258948434,
      "clip_ratio/high_mean": 0.0008946287089202087,
      "clip_ratio/low_mean": 0.0008011226727830945,
      "clip_ratio/low_min": 4.0229751903098077e-05,
      "clip_ratio/region_mean": 0.0016957513798843138,
      "epoch": 0.12357302440077234,
      "grad_norm": 6.717078685760498,
      "learning_rate": 5e-07,
      "loss": 0.02,
      "step": 1324
    },
    {
      "clip_ratio/high_max": 0.0023054574776324444,
      "clip_ratio/high_mean": 0.0008754340633458924,
      "clip_ratio/low_mean": 0.000850941161843366,
      "clip_ratio/low_min": 8.10627516329987e-05,
      "clip_ratio/region_mean": 0.0017263752088183537,
      "epoch": 0.12366635750077291,
      "grad_norm": 206.60752868652344,
      "learning_rate": 5e-07,
      "loss": 1.7693,
      "step": 1325
    },
    {
      "clip_ratio/high_max": 0.0019903263892047107,
      "clip_ratio/high_mean": 0.000920118072826881,
      "clip_ratio/low_mean": 0.0009111013150686631,
      "clip_ratio/low_min": 6.952066905796528e-05,
      "clip_ratio/region_mean": 0.001831219378800597,
      "epoch": 0.12375969060077349,
      "grad_norm": 245.52212524414062,
      "learning_rate": 5e-07,
      "loss": 0.0619,
      "step": 1326
    },
    {
      "clip_ratio/high_max": 0.002303150831721723,
      "clip_ratio/high_mean": 0.0010224101024505217,
      "clip_ratio/low_mean": 0.000968053445831174,
      "clip_ratio/low_min": 0.00012089300798834302,
      "clip_ratio/region_mean": 0.001990463599213399,
      "epoch": 0.12385302370077408,
      "grad_norm": 0.1118810847401619,
      "learning_rate": 5e-07,
      "loss": -0.0168,
      "step": 1327
    },
    {
      "clip_ratio/high_max": 0.0022359182112268172,
      "clip_ratio/high_mean": 0.0008747183183004381,
      "clip_ratio/low_mean": 0.0008963712589320494,
      "clip_ratio/low_min": 7.550822738267016e-05,
      "clip_ratio/region_mean": 0.0017710895990603603,
      "epoch": 0.12394635680077466,
      "grad_norm": 0.17722167074680328,
      "learning_rate": 5e-07,
      "loss": 0.0144,
      "step": 1328
    },
    {
      "clip_ratio/high_max": 0.0024694583626114763,
      "clip_ratio/high_mean": 0.0009780244909052271,
      "clip_ratio/low_mean": 0.0009391608164150966,
      "clip_ratio/low_min": 1.92307688848814e-05,
      "clip_ratio/region_mean": 0.0019171853200532496,
      "epoch": 0.12403968990077525,
      "grad_norm": 0.13926243782043457,
      "learning_rate": 5e-07,
      "loss": -0.0029,
      "step": 1329
    },
    {
      "clip_ratio/high_max": 0.0022275164155871607,
      "clip_ratio/high_mean": 0.0008857077355060028,
      "clip_ratio/low_mean": 0.001039899036186398,
      "clip_ratio/low_min": 9.100149145524483e-05,
      "clip_ratio/region_mean": 0.0019256068080721889,
      "epoch": 0.12413302300077583,
      "grad_norm": 0.12941832840442657,
      "learning_rate": 5e-07,
      "loss": 0.044,
      "step": 1330
    },
    {
      "clip_ratio/high_max": 0.0023641970110475086,
      "clip_ratio/high_mean": 0.0008796176207397366,
      "clip_ratio/low_mean": 0.0010842475476238178,
      "clip_ratio/low_min": 9.021439836942591e-05,
      "clip_ratio/region_mean": 0.001963865193829406,
      "epoch": 0.12422635610077641,
      "grad_norm": 0.1673887073993683,
      "learning_rate": 5e-07,
      "loss": 0.0363,
      "step": 1331
    },
    {
      "clip_ratio/high_max": 0.002013979450566694,
      "clip_ratio/high_mean": 0.0009121376479015453,
      "clip_ratio/low_mean": 0.0009609506523702294,
      "clip_ratio/low_min": 0.0001278431436730898,
      "clip_ratio/region_mean": 0.0018730882438831031,
      "epoch": 0.124319689200777,
      "grad_norm": 0.10795170068740845,
      "learning_rate": 5e-07,
      "loss": 0.0398,
      "step": 1332
    },
    {
      "clip_ratio/high_max": 0.002536856813094346,
      "clip_ratio/high_mean": 0.0009730490455694962,
      "clip_ratio/low_mean": 0.0009595262745278887,
      "clip_ratio/low_min": 5.41925865036319e-05,
      "clip_ratio/region_mean": 0.0019325753310113214,
      "epoch": 0.12441302230077758,
      "grad_norm": 2.3193018436431885,
      "learning_rate": 5e-07,
      "loss": 0.1877,
      "step": 1333
    },
    {
      "clip_ratio/high_max": 0.002216598397353664,
      "clip_ratio/high_mean": 0.0009519598024780862,
      "clip_ratio/low_mean": 0.0009589603905624244,
      "clip_ratio/low_min": 5.413200597104151e-05,
      "clip_ratio/region_mean": 0.001910920167574659,
      "epoch": 0.12450635540077816,
      "grad_norm": 0.6266466975212097,
      "learning_rate": 5e-07,
      "loss": 0.0193,
      "step": 1334
    },
    {
      "clip_ratio/high_max": 0.00219750538963126,
      "clip_ratio/high_mean": 0.0009490043994446751,
      "clip_ratio/low_mean": 0.0009021829955599969,
      "clip_ratio/low_min": 5.791411422251258e-05,
      "clip_ratio/region_mean": 0.0018511874295654707,
      "epoch": 0.12459968850077875,
      "grad_norm": 0.22334134578704834,
      "learning_rate": 5e-07,
      "loss": -0.0082,
      "step": 1335
    },
    {
      "clip_ratio/high_max": 0.002448523046041373,
      "clip_ratio/high_mean": 0.0009498151730440441,
      "clip_ratio/low_mean": 0.0010465465165907517,
      "clip_ratio/low_min": 4.735245238407515e-05,
      "clip_ratio/region_mean": 0.001996361679630354,
      "epoch": 0.12469302160077933,
      "grad_norm": 0.11985936760902405,
      "learning_rate": 5e-07,
      "loss": 0.069,
      "step": 1336
    },
    {
      "clip_ratio/high_max": 0.0023409603818436153,
      "clip_ratio/high_mean": 0.0009425949992873939,
      "clip_ratio/low_mean": 0.0007605354076076765,
      "clip_ratio/low_min": 1.4207774256647099e-05,
      "clip_ratio/region_mean": 0.0017031303796102293,
      "epoch": 0.12478635470077991,
      "grad_norm": 1.325947880744934,
      "learning_rate": 5e-07,
      "loss": 0.0092,
      "step": 1337
    },
    {
      "clip_ratio/high_max": 0.0022839671473775525,
      "clip_ratio/high_mean": 0.0009935229827533476,
      "clip_ratio/low_mean": 0.000861158059706213,
      "clip_ratio/low_min": 3.555850707925856e-05,
      "clip_ratio/region_mean": 0.0018546810242696665,
      "epoch": 0.1248796878007805,
      "grad_norm": 0.12269698828458786,
      "learning_rate": 5e-07,
      "loss": -0.003,
      "step": 1338
    },
    {
      "clip_ratio/high_max": 0.0022773952841816936,
      "clip_ratio/high_mean": 0.0008251179533544928,
      "clip_ratio/low_mean": 0.0009385661560372682,
      "clip_ratio/low_min": 0.0001684400049271062,
      "clip_ratio/region_mean": 0.00176368408210692,
      "epoch": 0.12497302090078108,
      "grad_norm": 0.1269606649875641,
      "learning_rate": 5e-07,
      "loss": 0.0454,
      "step": 1339
    },
    {
      "clip_ratio/high_max": 0.0020705806018668227,
      "clip_ratio/high_mean": 0.0008967551748355618,
      "clip_ratio/low_mean": 0.0009816100719035603,
      "clip_ratio/low_min": 3.818751883954974e-05,
      "clip_ratio/region_mean": 0.0018783652412821539,
      "epoch": 0.12506635400078167,
      "grad_norm": 0.11234802007675171,
      "learning_rate": 5e-07,
      "loss": 0.0305,
      "step": 1340
    },
    {
      "clip_ratio/high_max": 0.002260271110571921,
      "clip_ratio/high_mean": 0.0009201209377351915,
      "clip_ratio/low_mean": 0.0009326561630587094,
      "clip_ratio/low_min": 2.30457226280123e-05,
      "clip_ratio/region_mean": 0.0018527771317167208,
      "epoch": 0.12515968710078224,
      "grad_norm": 0.11995192617177963,
      "learning_rate": 5e-07,
      "loss": 0.0546,
      "step": 1341
    },
    {
      "clip_ratio/high_max": 0.0025549386482452974,
      "clip_ratio/high_mean": 0.0010650896110746544,
      "clip_ratio/low_mean": 0.0009624352387618273,
      "clip_ratio/low_min": 5.93637823840254e-05,
      "clip_ratio/region_mean": 0.00202752482437063,
      "epoch": 0.12525302020078283,
      "grad_norm": 0.40296557545661926,
      "learning_rate": 5e-07,
      "loss": 0.004,
      "step": 1342
    },
    {
      "clip_ratio/high_max": 0.002335965276870411,
      "clip_ratio/high_mean": 0.001005713565973565,
      "clip_ratio/low_mean": 0.0009865350220934488,
      "clip_ratio/low_min": 7.884910883149132e-05,
      "clip_ratio/region_mean": 0.0019922485735150985,
      "epoch": 0.12534635330078342,
      "grad_norm": 0.10878967493772507,
      "learning_rate": 5e-07,
      "loss": 0.0169,
      "step": 1343
    },
    {
      "clip_ratio/high_max": 0.002103311417158693,
      "clip_ratio/high_mean": 0.0008830684764689067,
      "clip_ratio/low_mean": 0.0009496803613728844,
      "clip_ratio/low_min": 0.00010603009104670491,
      "clip_ratio/region_mean": 0.0018327488323848229,
      "epoch": 0.125439686400784,
      "grad_norm": 0.11206154525279999,
      "learning_rate": 5e-07,
      "loss": 0.0178,
      "step": 1344
    },
    {
      "clip_ratio/high_max": 0.0019299238556413911,
      "clip_ratio/high_mean": 0.0008597364922025008,
      "clip_ratio/low_mean": 0.0010667234091670252,
      "clip_ratio/low_min": 0.00012191076348244678,
      "clip_ratio/region_mean": 0.001926459874084685,
      "epoch": 0.12553301950078458,
      "grad_norm": 0.11010550707578659,
      "learning_rate": 5e-07,
      "loss": 0.0249,
      "step": 1345
    },
    {
      "clip_ratio/high_max": 0.0020515732612693682,
      "clip_ratio/high_mean": 0.0008474407659377903,
      "clip_ratio/low_mean": 0.001000527434371179,
      "clip_ratio/low_min": 1.6344141840818338e-05,
      "clip_ratio/region_mean": 0.0018479681457392871,
      "epoch": 0.12562635260078517,
      "grad_norm": 0.11284521967172623,
      "learning_rate": 5e-07,
      "loss": 0.0526,
      "step": 1346
    },
    {
      "clip_ratio/high_max": 0.002459646748320665,
      "clip_ratio/high_mean": 0.0010512456883589039,
      "clip_ratio/low_mean": 0.000888652077264851,
      "clip_ratio/low_min": 6.838670833531069e-05,
      "clip_ratio/region_mean": 0.0019398977601667866,
      "epoch": 0.12571968570078576,
      "grad_norm": 0.5349629521369934,
      "learning_rate": 5e-07,
      "loss": 0.0007,
      "step": 1347
    },
    {
      "clip_ratio/high_max": 0.002206033721449785,
      "clip_ratio/high_mean": 0.0009111595281865448,
      "clip_ratio/low_mean": 0.0010321348636352923,
      "clip_ratio/low_min": 5.791925923404051e-05,
      "clip_ratio/region_mean": 0.0019432943954598159,
      "epoch": 0.12581301880078632,
      "grad_norm": 0.12427479773759842,
      "learning_rate": 5e-07,
      "loss": 0.0436,
      "step": 1348
    },
    {
      "clip_ratio/high_max": 0.0021341686733649112,
      "clip_ratio/high_mean": 0.0009687340771051822,
      "clip_ratio/low_mean": 0.0009649836938478984,
      "clip_ratio/low_min": 0.0001322957941738423,
      "clip_ratio/region_mean": 0.0019337177873239852,
      "epoch": 0.12590635190078692,
      "grad_norm": 0.1157969981431961,
      "learning_rate": 5e-07,
      "loss": 0.0384,
      "step": 1349
    },
    {
      "clip_ratio/high_max": 0.0022583349418709986,
      "clip_ratio/high_mean": 0.0009584555664332584,
      "clip_ratio/low_mean": 0.0008655412184452871,
      "clip_ratio/low_min": 3.2809539334266447e-05,
      "clip_ratio/region_mean": 0.0018239967757835984,
      "epoch": 0.1259996850007875,
      "grad_norm": 0.11028864234685898,
      "learning_rate": 5e-07,
      "loss": 0.0036,
      "step": 1350
    },
    {
      "clip_ratio/high_max": 0.0019501685346767772,
      "clip_ratio/high_mean": 0.000808149676231551,
      "clip_ratio/low_mean": 0.000978212088739383,
      "clip_ratio/low_min": 7.619163625349756e-06,
      "clip_ratio/region_mean": 0.001786361783160828,
      "epoch": 0.12609301810078807,
      "grad_norm": 0.12981680035591125,
      "learning_rate": 5e-07,
      "loss": 0.0206,
      "step": 1351
    },
    {
      "clip_ratio/high_max": 0.0018379552238911856,
      "clip_ratio/high_mean": 0.0008535378437954932,
      "clip_ratio/low_mean": 0.0008171537301677745,
      "clip_ratio/low_min": 5.857544601894915e-05,
      "clip_ratio/region_mean": 0.0016706915521353949,
      "epoch": 0.12618635120078867,
      "grad_norm": 0.10401661694049835,
      "learning_rate": 5e-07,
      "loss": 0.0202,
      "step": 1352
    },
    {
      "clip_ratio/high_max": 0.002310284093255177,
      "clip_ratio/high_mean": 0.0009114754975598771,
      "clip_ratio/low_mean": 0.0009656441034167074,
      "clip_ratio/low_min": 8.110973158181878e-05,
      "clip_ratio/region_mean": 0.001877119590062648,
      "epoch": 0.12627968430078926,
      "grad_norm": 0.10627733170986176,
      "learning_rate": 5e-07,
      "loss": 0.0181,
      "step": 1353
    },
    {
      "clip_ratio/high_max": 0.002627537200169172,
      "clip_ratio/high_mean": 0.001050725008099107,
      "clip_ratio/low_mean": 0.0010286312608513981,
      "clip_ratio/low_min": 1.2726532077067532e-05,
      "clip_ratio/region_mean": 0.002079356236208696,
      "epoch": 0.12637301740078982,
      "grad_norm": 7.845396041870117,
      "learning_rate": 5e-07,
      "loss": 0.0011,
      "step": 1354
    },
    {
      "clip_ratio/high_max": 0.0020504301974142436,
      "clip_ratio/high_mean": 0.0008610739223513519,
      "clip_ratio/low_mean": 0.0010556863599049393,
      "clip_ratio/low_min": 4.6313172788359225e-05,
      "clip_ratio/region_mean": 0.0019167602731613442,
      "epoch": 0.12646635050079041,
      "grad_norm": 0.12130797654390335,
      "learning_rate": 5e-07,
      "loss": -0.0033,
      "step": 1355
    },
    {
      "clip_ratio/high_max": 0.0020178816266707145,
      "clip_ratio/high_mean": 0.0008689632977620931,
      "clip_ratio/low_mean": 0.0010394789178462815,
      "clip_ratio/low_min": 9.729857538331999e-05,
      "clip_ratio/region_mean": 0.001908442223793827,
      "epoch": 0.126559683600791,
      "grad_norm": 0.11506979167461395,
      "learning_rate": 5e-07,
      "loss": 0.0216,
      "step": 1356
    },
    {
      "clip_ratio/high_max": 0.0021006443857913837,
      "clip_ratio/high_mean": 0.0008220916879508877,
      "clip_ratio/low_mean": 0.0011311688540445175,
      "clip_ratio/low_min": 9.671013594925171e-05,
      "clip_ratio/region_mean": 0.0019532604928826913,
      "epoch": 0.12665301670079157,
      "grad_norm": 0.12314552068710327,
      "learning_rate": 5e-07,
      "loss": 0.0506,
      "step": 1357
    },
    {
      "clip_ratio/high_max": 0.0022218424564925954,
      "clip_ratio/high_mean": 0.0009845204440352973,
      "clip_ratio/low_mean": 0.0008247562564065447,
      "clip_ratio/low_min": 7.168183492467506e-05,
      "clip_ratio/region_mean": 0.0018092767131747678,
      "epoch": 0.12674634980079216,
      "grad_norm": 0.10767516493797302,
      "learning_rate": 5e-07,
      "loss": -0.0291,
      "step": 1358
    },
    {
      "clip_ratio/high_max": 0.002112909765855875,
      "clip_ratio/high_mean": 0.0007129354917196906,
      "clip_ratio/low_mean": 0.0011785486167354975,
      "clip_ratio/low_min": 7.098948753991863e-05,
      "clip_ratio/region_mean": 0.0018914841348305345,
      "epoch": 0.12683968290079276,
      "grad_norm": 15.247798919677734,
      "learning_rate": 5e-07,
      "loss": 0.0515,
      "step": 1359
    },
    {
      "clip_ratio/high_max": 0.001973652386368485,
      "clip_ratio/high_mean": 0.0008016833889996633,
      "clip_ratio/low_mean": 0.0010980857114191167,
      "clip_ratio/low_min": 1.6666666851961054e-05,
      "clip_ratio/region_mean": 0.0018997690785909072,
      "epoch": 0.12693301600079332,
      "grad_norm": 0.10410518199205399,
      "learning_rate": 5e-07,
      "loss": 0.0473,
      "step": 1360
    },
    {
      "clip_ratio/high_max": 0.00221563364539179,
      "clip_ratio/high_mean": 0.0009954933266271837,
      "clip_ratio/low_mean": 0.0009836807676038006,
      "clip_ratio/low_min": 4.76483692182228e-05,
      "clip_ratio/region_mean": 0.0019791740487562492,
      "epoch": 0.1270263491007939,
      "grad_norm": 0.11728191375732422,
      "learning_rate": 5e-07,
      "loss": 0.0112,
      "step": 1361
    },
    {
      "clip_ratio/high_max": 0.002207145807915367,
      "clip_ratio/high_mean": 0.0008098325615719659,
      "clip_ratio/low_mean": 0.0008956867932283785,
      "clip_ratio/low_min": 8.351838187081739e-05,
      "clip_ratio/region_mean": 0.0017055194184649736,
      "epoch": 0.1271196822007945,
      "grad_norm": 0.11656846851110458,
      "learning_rate": 5e-07,
      "loss": 0.0409,
      "step": 1362
    },
    {
      "clip_ratio/high_max": 0.002416868788714055,
      "clip_ratio/high_mean": 0.0009237218109774403,
      "clip_ratio/low_mean": 0.0009361011334476643,
      "clip_ratio/low_min": 0.0001139732239607838,
      "clip_ratio/region_mean": 0.0018598229398776311,
      "epoch": 0.12721301530079507,
      "grad_norm": 0.11391375213861465,
      "learning_rate": 5e-07,
      "loss": 0.0049,
      "step": 1363
    },
    {
      "clip_ratio/high_max": 0.002335784796741791,
      "clip_ratio/high_mean": 0.0010416252735012677,
      "clip_ratio/low_mean": 0.0011087006205343641,
      "clip_ratio/low_min": 0.00011757025185943348,
      "clip_ratio/region_mean": 0.002150325912225526,
      "epoch": 0.12730634840079566,
      "grad_norm": 0.11533604562282562,
      "learning_rate": 5e-07,
      "loss": 0.0294,
      "step": 1364
    },
    {
      "clip_ratio/high_max": 0.0019252678830525838,
      "clip_ratio/high_mean": 0.0008823923672025558,
      "clip_ratio/low_mean": 0.0011101334730483359,
      "clip_ratio/low_min": 0.00011141592858621152,
      "clip_ratio/region_mean": 0.0019925258529838175,
      "epoch": 0.12739968150079625,
      "grad_norm": 0.12017866224050522,
      "learning_rate": 5e-07,
      "loss": 0.0552,
      "step": 1365
    },
    {
      "clip_ratio/high_max": 0.0020922124313074164,
      "clip_ratio/high_mean": 0.0008598784170317231,
      "clip_ratio/low_mean": 0.0010415642263978953,
      "clip_ratio/low_min": 0.00010824431956280023,
      "clip_ratio/region_mean": 0.001901442650705576,
      "epoch": 0.12749301460079684,
      "grad_norm": 0.12608879804611206,
      "learning_rate": 5e-07,
      "loss": 0.0555,
      "step": 1366
    },
    {
      "clip_ratio/high_max": 0.002368626133829821,
      "clip_ratio/high_mean": 0.0009416294251423096,
      "clip_ratio/low_mean": 0.0008332045526913134,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0017748339741956443,
      "epoch": 0.1275863477007974,
      "grad_norm": 0.10313794016838074,
      "learning_rate": 5e-07,
      "loss": -0.0112,
      "step": 1367
    },
    {
      "clip_ratio/high_max": 0.0026235070399707183,
      "clip_ratio/high_mean": 0.0011121243223897181,
      "clip_ratio/low_mean": 0.0009418910558451898,
      "clip_ratio/low_min": 0.00013452638995659072,
      "clip_ratio/region_mean": 0.002054015392786823,
      "epoch": 0.127679680800798,
      "grad_norm": 0.1338038444519043,
      "learning_rate": 5e-07,
      "loss": 0.0294,
      "step": 1368
    },
    {
      "clip_ratio/high_max": 0.0024285830222652294,
      "clip_ratio/high_mean": 0.0010072784607473295,
      "clip_ratio/low_mean": 0.0009128288256761152,
      "clip_ratio/low_min": 3.428429045015946e-05,
      "clip_ratio/region_mean": 0.0019201073155272752,
      "epoch": 0.1277730139007986,
      "grad_norm": 0.14824582636356354,
      "learning_rate": 5e-07,
      "loss": 0.0111,
      "step": 1369
    },
    {
      "clip_ratio/high_max": 0.0021476227884704713,
      "clip_ratio/high_mean": 0.0010095391971844947,
      "clip_ratio/low_mean": 0.0010150998532481026,
      "clip_ratio/low_min": 9.06522836885415e-05,
      "clip_ratio/region_mean": 0.0020246390704414807,
      "epoch": 0.12786634700079916,
      "grad_norm": 0.11752218008041382,
      "learning_rate": 5e-07,
      "loss": 0.0348,
      "step": 1370
    },
    {
      "clip_ratio/high_max": 0.0023033009565551765,
      "clip_ratio/high_mean": 0.0010150385060114786,
      "clip_ratio/low_mean": 0.0009604163824405987,
      "clip_ratio/low_min": 8.053998772084014e-05,
      "clip_ratio/region_mean": 0.001975454892090056,
      "epoch": 0.12795968010079975,
      "grad_norm": 1.0908182859420776,
      "learning_rate": 5e-07,
      "loss": -0.0009,
      "step": 1371
    },
    {
      "clip_ratio/high_max": 0.0022144467266116408,
      "clip_ratio/high_mean": 0.0008919643901208474,
      "clip_ratio/low_mean": 0.0009995703767344821,
      "clip_ratio/low_min": 5.820105980092194e-05,
      "clip_ratio/region_mean": 0.0018915347900474444,
      "epoch": 0.12805301320080034,
      "grad_norm": 0.11959429830312729,
      "learning_rate": 5e-07,
      "loss": 0.0561,
      "step": 1372
    },
    {
      "clip_ratio/high_max": 0.0020592662258422934,
      "clip_ratio/high_mean": 0.0009684482847660547,
      "clip_ratio/low_mean": 0.0010527418817218859,
      "clip_ratio/low_min": 5.7605700931162573e-05,
      "clip_ratio/region_mean": 0.0020211901210132055,
      "epoch": 0.1281463463008009,
      "grad_norm": 0.10729443281888962,
      "learning_rate": 5e-07,
      "loss": 0.0066,
      "step": 1373
    },
    {
      "clip_ratio/high_max": 0.002272283469210379,
      "clip_ratio/high_mean": 0.0010210171130893286,
      "clip_ratio/low_mean": 0.0008815374567348044,
      "clip_ratio/low_min": 6.059174938854994e-05,
      "clip_ratio/region_mean": 0.001902554628031794,
      "epoch": 0.1282396794008015,
      "grad_norm": 0.1173202395439148,
      "learning_rate": 5e-07,
      "loss": 0.016,
      "step": 1374
    },
    {
      "clip_ratio/high_max": 0.0018403922331344802,
      "clip_ratio/high_mean": 0.0008144807525241049,
      "clip_ratio/low_mean": 0.0011142565545014804,
      "clip_ratio/low_min": 0.00010456359177624108,
      "clip_ratio/region_mean": 0.0019287373070255853,
      "epoch": 0.1283330125008021,
      "grad_norm": 0.77057284116745,
      "learning_rate": 5e-07,
      "loss": 0.0443,
      "step": 1375
    },
    {
      "clip_ratio/high_max": 0.0022811617091065273,
      "clip_ratio/high_mean": 0.0009799790641409345,
      "clip_ratio/low_mean": 0.0010074745296151377,
      "clip_ratio/low_min": 5.4168205679161474e-05,
      "clip_ratio/region_mean": 0.0019874536228599027,
      "epoch": 0.12842634560080265,
      "grad_norm": 0.16942241787910461,
      "learning_rate": 5e-07,
      "loss": 0.0037,
      "step": 1376
    },
    {
      "clip_ratio/high_max": 0.0023185335376183502,
      "clip_ratio/high_mean": 0.0008814144912321353,
      "clip_ratio/low_mean": 0.001034510702083935,
      "clip_ratio/low_min": 8.328196690854384e-05,
      "clip_ratio/region_mean": 0.0019159251314704306,
      "epoch": 0.12851967870080325,
      "grad_norm": 0.11266382783651352,
      "learning_rate": 5e-07,
      "loss": 0.0434,
      "step": 1377
    },
    {
      "clip_ratio/high_max": 0.0016769564535934478,
      "clip_ratio/high_mean": 0.0007557457993243588,
      "clip_ratio/low_mean": 0.0011166961539856857,
      "clip_ratio/low_min": 7.303760230570333e-05,
      "clip_ratio/region_mean": 0.001872441964223981,
      "epoch": 0.12861301180080384,
      "grad_norm": 0.33707013726234436,
      "learning_rate": 5e-07,
      "loss": 0.0534,
      "step": 1378
    },
    {
      "clip_ratio/high_max": 0.0019896657540812157,
      "clip_ratio/high_mean": 0.0008173505502782064,
      "clip_ratio/low_mean": 0.000944935734878527,
      "clip_ratio/low_min": 0.00015258611165336333,
      "clip_ratio/region_mean": 0.0017622862906137016,
      "epoch": 0.1287063449008044,
      "grad_norm": 0.11083129048347473,
      "learning_rate": 5e-07,
      "loss": 0.0684,
      "step": 1379
    },
    {
      "clip_ratio/high_max": 0.002130959815985989,
      "clip_ratio/high_mean": 0.0008310828543471871,
      "clip_ratio/low_mean": 0.001058404088325915,
      "clip_ratio/low_min": 7.669593651371542e-05,
      "clip_ratio/region_mean": 0.0018894869135692716,
      "epoch": 0.128799678000805,
      "grad_norm": 0.11411848664283752,
      "learning_rate": 5e-07,
      "loss": 0.0259,
      "step": 1380
    },
    {
      "clip_ratio/high_max": 0.0020564449587254785,
      "clip_ratio/high_mean": 0.0008644419467600528,
      "clip_ratio/low_mean": 0.001034989269101061,
      "clip_ratio/low_min": 8.313787293445785e-05,
      "clip_ratio/region_mean": 0.0018994312194990925,
      "epoch": 0.1288930111008056,
      "grad_norm": 0.10537859052419662,
      "learning_rate": 5e-07,
      "loss": 0.0094,
      "step": 1381
    },
    {
      "clip_ratio/high_max": 0.0022223972882784437,
      "clip_ratio/high_mean": 0.0009722475842863787,
      "clip_ratio/low_mean": 0.000910546921659261,
      "clip_ratio/low_min": 5.4568830819334835e-05,
      "clip_ratio/region_mean": 0.0018827944586519152,
      "epoch": 0.12898634420080615,
      "grad_norm": 0.12146515399217606,
      "learning_rate": 5e-07,
      "loss": -0.0067,
      "step": 1382
    },
    {
      "clip_ratio/high_max": 0.0019558602434699424,
      "clip_ratio/high_mean": 0.0008651504849694902,
      "clip_ratio/low_mean": 0.0009688607042335207,
      "clip_ratio/low_min": 7.362370524788275e-05,
      "clip_ratio/region_mean": 0.0018340111782890745,
      "epoch": 0.12907967730080674,
      "grad_norm": 0.10876553505659103,
      "learning_rate": 5e-07,
      "loss": 0.0104,
      "step": 1383
    },
    {
      "clip_ratio/high_max": 0.002282194582221564,
      "clip_ratio/high_mean": 0.0009321165944129461,
      "clip_ratio/low_mean": 0.0010963197237288114,
      "clip_ratio/low_min": 0.0001567733206684352,
      "clip_ratio/region_mean": 0.0020284363054088317,
      "epoch": 0.12917301040080734,
      "grad_norm": 0.10939362645149231,
      "learning_rate": 5e-07,
      "loss": 0.0573,
      "step": 1384
    },
    {
      "clip_ratio/high_max": 0.0025513974396744743,
      "clip_ratio/high_mean": 0.0010356518487242283,
      "clip_ratio/low_mean": 0.0010660778407327598,
      "clip_ratio/low_min": 7.300134893739596e-05,
      "clip_ratio/region_mean": 0.0021017296676291153,
      "epoch": 0.1292663435008079,
      "grad_norm": 0.11003376543521881,
      "learning_rate": 5e-07,
      "loss": 0.0138,
      "step": 1385
    },
    {
      "clip_ratio/high_max": 0.002375795938860392,
      "clip_ratio/high_mean": 0.0008445016846962972,
      "clip_ratio/low_mean": 0.0010699187514546793,
      "clip_ratio/low_min": 8.265719498012913e-05,
      "clip_ratio/region_mean": 0.0019144204416079447,
      "epoch": 0.1293596766008085,
      "grad_norm": 10.86213493347168,
      "learning_rate": 5e-07,
      "loss": 0.0356,
      "step": 1386
    },
    {
      "clip_ratio/high_max": 0.0021917184349149466,
      "clip_ratio/high_mean": 0.0008492803590343101,
      "clip_ratio/low_mean": 0.0010196426392212743,
      "clip_ratio/low_min": 1.3484358532878105e-05,
      "clip_ratio/region_mean": 0.0018689230491872877,
      "epoch": 0.12945300970080909,
      "grad_norm": 1.9071619510650635,
      "learning_rate": 5e-07,
      "loss": 0.0291,
      "step": 1387
    },
    {
      "clip_ratio/high_max": 0.00228698260980309,
      "clip_ratio/high_mean": 0.0008650503004901111,
      "clip_ratio/low_mean": 0.001211097698615049,
      "clip_ratio/low_min": 0.00017369997658533975,
      "clip_ratio/region_mean": 0.0020761479827342555,
      "epoch": 0.12954634280080968,
      "grad_norm": 0.11905862390995026,
      "learning_rate": 5e-07,
      "loss": 0.0441,
      "step": 1388
    },
    {
      "clip_ratio/high_max": 0.002411422352452064,
      "clip_ratio/high_mean": 0.000978070233031758,
      "clip_ratio/low_mean": 0.0008641633612569422,
      "clip_ratio/low_min": 5.183315624890383e-05,
      "clip_ratio/region_mean": 0.0018422335924697109,
      "epoch": 0.12963967590081024,
      "grad_norm": 0.13385848701000214,
      "learning_rate": 5e-07,
      "loss": 0.0304,
      "step": 1389
    },
    {
      "clip_ratio/high_max": 0.0020798163423023652,
      "clip_ratio/high_mean": 0.0008064571538852761,
      "clip_ratio/low_mean": 0.0010104232205776498,
      "clip_ratio/low_min": 7.10068616172066e-05,
      "clip_ratio/region_mean": 0.001816880379919894,
      "epoch": 0.12973300900081083,
      "grad_norm": 0.11186782270669937,
      "learning_rate": 5e-07,
      "loss": 0.0648,
      "step": 1390
    },
    {
      "clip_ratio/high_max": 0.002322492000530474,
      "clip_ratio/high_mean": 0.0009184296795865521,
      "clip_ratio/low_mean": 0.001013213288388215,
      "clip_ratio/low_min": 0.00011296154661977198,
      "clip_ratio/region_mean": 0.0019316430043545552,
      "epoch": 0.12982634210081143,
      "grad_norm": 1.2462831735610962,
      "learning_rate": 5e-07,
      "loss": 0.0349,
      "step": 1391
    },
    {
      "clip_ratio/high_max": 0.002083553386910353,
      "clip_ratio/high_mean": 0.0009065100675798021,
      "clip_ratio/low_mean": 0.0008850965932651889,
      "clip_ratio/low_min": 1.3664189282280859e-05,
      "clip_ratio/region_mean": 0.0017916066717589274,
      "epoch": 0.129919675200812,
      "grad_norm": 0.11262314766645432,
      "learning_rate": 5e-07,
      "loss": 0.0125,
      "step": 1392
    },
    {
      "clip_ratio/high_max": 0.0025202309188898653,
      "clip_ratio/high_mean": 0.0010085978392453399,
      "clip_ratio/low_mean": 0.0009122504525294062,
      "clip_ratio/low_min": 3.346720041008666e-05,
      "clip_ratio/region_mean": 0.0019208482772228308,
      "epoch": 0.13001300830081258,
      "grad_norm": 0.12921041250228882,
      "learning_rate": 5e-07,
      "loss": 0.0292,
      "step": 1393
    },
    {
      "clip_ratio/high_max": 0.0021012343568145297,
      "clip_ratio/high_mean": 0.000961629455559887,
      "clip_ratio/low_mean": 0.001227278549777111,
      "clip_ratio/low_min": 0.00013712476356886327,
      "clip_ratio/region_mean": 0.002188907950767316,
      "epoch": 0.13010634140081317,
      "grad_norm": 0.12570779025554657,
      "learning_rate": 5e-07,
      "loss": -0.0255,
      "step": 1394
    },
    {
      "clip_ratio/high_max": 0.0020283366975490935,
      "clip_ratio/high_mean": 0.0008978894820756977,
      "clip_ratio/low_mean": 0.0013503489244612865,
      "clip_ratio/low_min": 0.00016022320778574795,
      "clip_ratio/region_mean": 0.002248238422907889,
      "epoch": 0.13019967450081374,
      "grad_norm": 0.40569016337394714,
      "learning_rate": 5e-07,
      "loss": 0.0793,
      "step": 1395
    },
    {
      "clip_ratio/high_max": 0.001935236152348807,
      "clip_ratio/high_mean": 0.0006964200592847192,
      "clip_ratio/low_mean": 0.0010288267949363217,
      "clip_ratio/low_min": 9.332195804745425e-05,
      "clip_ratio/region_mean": 0.0017252468605875038,
      "epoch": 0.13029300760081433,
      "grad_norm": 0.11520501971244812,
      "learning_rate": 5e-07,
      "loss": 0.0745,
      "step": 1396
    },
    {
      "clip_ratio/high_max": 0.00214580122337793,
      "clip_ratio/high_mean": 0.0008700250127731124,
      "clip_ratio/low_mean": 0.0009845152690104442,
      "clip_ratio/low_min": 0.00011769480806833599,
      "clip_ratio/region_mean": 0.001854540292697493,
      "epoch": 0.13038634070081492,
      "grad_norm": 0.09472132474184036,
      "learning_rate": 5e-07,
      "loss": 0.0144,
      "step": 1397
    },
    {
      "clip_ratio/high_max": 0.0024585033606854267,
      "clip_ratio/high_mean": 0.0010037892025138717,
      "clip_ratio/low_mean": 0.000927291965126642,
      "clip_ratio/low_min": 3.654015381471254e-05,
      "clip_ratio/region_mean": 0.001931081191287376,
      "epoch": 0.1304796738008155,
      "grad_norm": 0.1257484257221222,
      "learning_rate": 5e-07,
      "loss": 0.0145,
      "step": 1398
    },
    {
      "clip_ratio/high_max": 0.0021362416810006835,
      "clip_ratio/high_mean": 0.0009073386127056438,
      "clip_ratio/low_mean": 0.0010323099486413412,
      "clip_ratio/low_min": 6.220089562702924e-05,
      "clip_ratio/region_mean": 0.0019396485586185008,
      "epoch": 0.13057300690081608,
      "grad_norm": 0.1097995936870575,
      "learning_rate": 5e-07,
      "loss": 0.0065,
      "step": 1399
    },
    {
      "clip_ratio/high_max": 0.002054729531664634,
      "clip_ratio/high_mean": 0.0009176798794214847,
      "clip_ratio/low_mean": 0.001128849315136904,
      "clip_ratio/low_min": 0.00010260000453854445,
      "clip_ratio/region_mean": 0.0020465291891014203,
      "epoch": 0.13066634000081667,
      "grad_norm": 0.10772724449634552,
      "learning_rate": 5e-07,
      "loss": 0.0361,
      "step": 1400
    },
    {
      "clip_ratio/high_max": 0.0030651318229502067,
      "clip_ratio/high_mean": 0.0010582625181996264,
      "clip_ratio/low_mean": 0.0008659203067509225,
      "clip_ratio/low_min": 1.4494434253720101e-05,
      "clip_ratio/region_mean": 0.001924182812217623,
      "epoch": 0.13075967310081724,
      "grad_norm": 1.8662290573120117,
      "learning_rate": 5e-07,
      "loss": -0.0002,
      "step": 1401
    },
    {
      "clip_ratio/high_max": 0.002539124401664594,
      "clip_ratio/high_mean": 0.0009384847289766185,
      "clip_ratio/low_mean": 0.001030563249514671,
      "clip_ratio/low_min": 3.280839882791042e-05,
      "clip_ratio/region_mean": 0.0019690479821292683,
      "epoch": 0.13085300620081783,
      "grad_norm": 0.14886876940727234,
      "learning_rate": 5e-07,
      "loss": 0.0258,
      "step": 1402
    },
    {
      "clip_ratio/high_max": 0.0023702648250036873,
      "clip_ratio/high_mean": 0.000951530451857252,
      "clip_ratio/low_mean": 0.0009617937939765397,
      "clip_ratio/low_min": 2.366975968470797e-05,
      "clip_ratio/region_mean": 0.0019133242167299613,
      "epoch": 0.13094633930081842,
      "grad_norm": 0.11545968800783157,
      "learning_rate": 5e-07,
      "loss": -0.0069,
      "step": 1403
    },
    {
      "clip_ratio/high_max": 0.002365935972193256,
      "clip_ratio/high_mean": 0.0009716996391944122,
      "clip_ratio/low_mean": 0.00117170758494467,
      "clip_ratio/low_min": 4.559691933536669e-05,
      "clip_ratio/region_mean": 0.002143407218682114,
      "epoch": 0.13103967240081899,
      "grad_norm": 0.1292003095149994,
      "learning_rate": 5e-07,
      "loss": 0.0275,
      "step": 1404
    },
    {
      "clip_ratio/high_max": 0.0023950017712195404,
      "clip_ratio/high_mean": 0.0010366160349803977,
      "clip_ratio/low_mean": 0.0012097376620658906,
      "clip_ratio/low_min": 0.00017670308807282709,
      "clip_ratio/region_mean": 0.0022463537170551717,
      "epoch": 0.13113300550081958,
      "grad_norm": 0.1131095141172409,
      "learning_rate": 5e-07,
      "loss": -0.0282,
      "step": 1405
    },
    {
      "clip_ratio/high_max": 0.0021649825575877912,
      "clip_ratio/high_mean": 0.0008329630145453848,
      "clip_ratio/low_mean": 0.0012509254011092708,
      "clip_ratio/low_min": 2.7387925911170896e-05,
      "clip_ratio/region_mean": 0.002083888386550825,
      "epoch": 0.13122633860082017,
      "grad_norm": 0.11973380297422409,
      "learning_rate": 5e-07,
      "loss": 0.0811,
      "step": 1406
    },
    {
      "clip_ratio/high_max": 0.0023285197748919018,
      "clip_ratio/high_mean": 0.0009900696259137476,
      "clip_ratio/low_mean": 0.0010864570804187679,
      "clip_ratio/low_min": 4.7838821046752855e-05,
      "clip_ratio/region_mean": 0.0020765267763636075,
      "epoch": 0.13131967170082076,
      "grad_norm": 0.1183408796787262,
      "learning_rate": 5e-07,
      "loss": 0.0247,
      "step": 1407
    },
    {
      "clip_ratio/high_max": 0.0021873875812161714,
      "clip_ratio/high_mean": 0.0009435434658371378,
      "clip_ratio/low_mean": 0.0012307231372687966,
      "clip_ratio/low_min": 5.212396717979573e-05,
      "clip_ratio/region_mean": 0.002174266606743913,
      "epoch": 0.13141300480082133,
      "grad_norm": 0.27477023005485535,
      "learning_rate": 5e-07,
      "loss": 0.0262,
      "step": 1408
    },
    {
      "clip_ratio/high_max": 0.002158569077437278,
      "clip_ratio/high_mean": 0.0008345782352989772,
      "clip_ratio/low_mean": 0.0011266367764619645,
      "clip_ratio/low_min": 9.988948386308039e-05,
      "clip_ratio/region_mean": 0.001961215035407804,
      "epoch": 0.13150633790082192,
      "grad_norm": 0.11923806369304657,
      "learning_rate": 5e-07,
      "loss": 0.0728,
      "step": 1409
    },
    {
      "clip_ratio/high_max": 0.0024001613855944015,
      "clip_ratio/high_mean": 0.000875217921930016,
      "clip_ratio/low_mean": 0.0011389388782845344,
      "clip_ratio/low_min": 0.0001275393542528036,
      "clip_ratio/region_mean": 0.0020141567947575822,
      "epoch": 0.1315996710008225,
      "grad_norm": 0.13309374451637268,
      "learning_rate": 5e-07,
      "loss": 0.0378,
      "step": 1410
    },
    {
      "clip_ratio/high_max": 0.0022486208035843447,
      "clip_ratio/high_mean": 0.0009225801350112306,
      "clip_ratio/low_mean": 0.0011133573370898375,
      "clip_ratio/low_min": 0.00019998504285467789,
      "clip_ratio/region_mean": 0.0020359374611871317,
      "epoch": 0.13169300410082307,
      "grad_norm": 0.11534848064184189,
      "learning_rate": 5e-07,
      "loss": 0.0318,
      "step": 1411
    },
    {
      "clip_ratio/high_max": 0.002512487662897911,
      "clip_ratio/high_mean": 0.001039912152918987,
      "clip_ratio/low_mean": 0.0010317152155039366,
      "clip_ratio/low_min": 4.145423918089364e-05,
      "clip_ratio/region_mean": 0.0020716273502330296,
      "epoch": 0.13178633720082367,
      "grad_norm": 0.12116452306509018,
      "learning_rate": 5e-07,
      "loss": 0.002,
      "step": 1412
    },
    {
      "clip_ratio/high_max": 0.002511247574148001,
      "clip_ratio/high_mean": 0.0010125235785380937,
      "clip_ratio/low_mean": 0.0009211699780280469,
      "clip_ratio/low_min": 3.162008579238318e-05,
      "clip_ratio/region_mean": 0.0019336935656610876,
      "epoch": 0.13187967030082426,
      "grad_norm": 61.45252990722656,
      "learning_rate": 5e-07,
      "loss": 0.0264,
      "step": 1413
    },
    {
      "clip_ratio/high_max": 0.0022986665499047376,
      "clip_ratio/high_mean": 0.0009879372682917165,
      "clip_ratio/low_mean": 0.00104161809940706,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0020295553622418083,
      "epoch": 0.13197300340082482,
      "grad_norm": 1.4994559288024902,
      "learning_rate": 5e-07,
      "loss": 0.0056,
      "step": 1414
    },
    {
      "clip_ratio/high_max": 0.0018708243442233652,
      "clip_ratio/high_mean": 0.00081459067769174,
      "clip_ratio/low_mean": 0.0009309713441325584,
      "clip_ratio/low_min": 7.881659257691354e-05,
      "clip_ratio/region_mean": 0.0017455620036344044,
      "epoch": 0.13206633650082542,
      "grad_norm": 0.1112850159406662,
      "learning_rate": 5e-07,
      "loss": 0.0256,
      "step": 1415
    },
    {
      "clip_ratio/high_max": 0.0020517240845947526,
      "clip_ratio/high_mean": 0.0008229646846302785,
      "clip_ratio/low_mean": 0.0011974395201832522,
      "clip_ratio/low_min": 0.00012580309703480452,
      "clip_ratio/region_mean": 0.002020404201175552,
      "epoch": 0.132159669600826,
      "grad_norm": 0.12007731944322586,
      "learning_rate": 5e-07,
      "loss": 0.0191,
      "step": 1416
    },
    {
      "clip_ratio/high_max": 0.0022204655833775178,
      "clip_ratio/high_mean": 0.0009927962382789701,
      "clip_ratio/low_mean": 0.000996926028165035,
      "clip_ratio/low_min": 6.802358802815434e-05,
      "clip_ratio/region_mean": 0.0019897222809959203,
      "epoch": 0.13225300270082657,
      "grad_norm": 0.14312432706356049,
      "learning_rate": 5e-07,
      "loss": 0.0059,
      "step": 1417
    },
    {
      "clip_ratio/high_max": 0.0021444440571940504,
      "clip_ratio/high_mean": 0.00090322667529108,
      "clip_ratio/low_mean": 0.0011826291320176097,
      "clip_ratio/low_min": 0.00014247405488276854,
      "clip_ratio/region_mean": 0.0020858557982137427,
      "epoch": 0.13234633580082716,
      "grad_norm": 0.23588015139102936,
      "learning_rate": 5e-07,
      "loss": 0.0208,
      "step": 1418
    },
    {
      "clip_ratio/high_max": 0.00222471532470081,
      "clip_ratio/high_mean": 0.0007550680256827036,
      "clip_ratio/low_mean": 0.0011302359253022587,
      "clip_ratio/low_min": 1.0269471204082947e-05,
      "clip_ratio/region_mean": 0.0018853039291570894,
      "epoch": 0.13243966890082776,
      "grad_norm": 0.1047421470284462,
      "learning_rate": 5e-07,
      "loss": 0.0416,
      "step": 1419
    },
    {
      "clip_ratio/high_max": 0.0019991299959656317,
      "clip_ratio/high_mean": 0.0008528583894076291,
      "clip_ratio/low_mean": 0.0010776974522741511,
      "clip_ratio/low_min": 2.6612731744535267e-05,
      "clip_ratio/region_mean": 0.0019305557580082677,
      "epoch": 0.13253300200082832,
      "grad_norm": 0.11503029614686966,
      "learning_rate": 5e-07,
      "loss": 0.0483,
      "step": 1420
    },
    {
      "clip_ratio/high_max": 0.0020831649417232256,
      "clip_ratio/high_mean": 0.000858217834320385,
      "clip_ratio/low_mean": 0.001186785491881892,
      "clip_ratio/low_min": 0.00015270067524397746,
      "clip_ratio/region_mean": 0.0020450033334782347,
      "epoch": 0.1326263351008289,
      "grad_norm": 0.10669190436601639,
      "learning_rate": 5e-07,
      "loss": 1.5671,
      "step": 1421
    },
    {
      "clip_ratio/high_max": 0.002048577880486846,
      "clip_ratio/high_mean": 0.0008253140713350149,
      "clip_ratio/low_mean": 0.0009004645944514778,
      "clip_ratio/low_min": 4.4150016037747264e-05,
      "clip_ratio/region_mean": 0.001725778631225694,
      "epoch": 0.1327196682008295,
      "grad_norm": 0.10778655111789703,
      "learning_rate": 5e-07,
      "loss": 0.0313,
      "step": 1422
    },
    {
      "clip_ratio/high_max": 0.0021477067566593178,
      "clip_ratio/high_mean": 0.0009772336161404382,
      "clip_ratio/low_mean": 0.0011487722422316438,
      "clip_ratio/low_min": 2.8372264750942122e-05,
      "clip_ratio/region_mean": 0.002126005907484796,
      "epoch": 0.13281300130083007,
      "grad_norm": 0.1256420910358429,
      "learning_rate": 5e-07,
      "loss": 0.0105,
      "step": 1423
    },
    {
      "clip_ratio/high_max": 0.002081134414765984,
      "clip_ratio/high_mean": 0.0008126348020596197,
      "clip_ratio/low_mean": 0.0011391939224267844,
      "clip_ratio/low_min": 3.6838521737081464e-05,
      "clip_ratio/region_mean": 0.0019518287517712452,
      "epoch": 0.13290633440083066,
      "grad_norm": 0.1759616881608963,
      "learning_rate": 5e-07,
      "loss": 0.0373,
      "step": 1424
    },
    {
      "clip_ratio/high_max": 0.002112757218128536,
      "clip_ratio/high_mean": 0.0008553508614568273,
      "clip_ratio/low_mean": 0.0011168225901201367,
      "clip_ratio/low_min": 0.00011810856449301355,
      "clip_ratio/region_mean": 0.0019721734352060594,
      "epoch": 0.13299966750083125,
      "grad_norm": 0.11456030607223511,
      "learning_rate": 5e-07,
      "loss": 0.0213,
      "step": 1425
    },
    {
      "clip_ratio/high_max": 0.0025265287767979316,
      "clip_ratio/high_mean": 0.0010015440075221704,
      "clip_ratio/low_mean": 0.0012365912643872434,
      "clip_ratio/low_min": 6.821351598773617e-05,
      "clip_ratio/region_mean": 0.002238135304651223,
      "epoch": 0.13309300060083182,
      "grad_norm": 0.12444651871919632,
      "learning_rate": 5e-07,
      "loss": 0.0664,
      "step": 1426
    },
    {
      "clip_ratio/high_max": 0.0020730632459162734,
      "clip_ratio/high_mean": 0.0008837502264213981,
      "clip_ratio/low_mean": 0.0009303583738073939,
      "clip_ratio/low_min": 5.503540432982845e-05,
      "clip_ratio/region_mean": 0.0018141086147807073,
      "epoch": 0.1331863337008324,
      "grad_norm": 0.1206178218126297,
      "learning_rate": 5e-07,
      "loss": 0.0106,
      "step": 1427
    },
    {
      "clip_ratio/high_max": 0.0026617418479872867,
      "clip_ratio/high_mean": 0.0009668182792665903,
      "clip_ratio/low_mean": 0.000991489481748431,
      "clip_ratio/low_min": 0.00012010522186756134,
      "clip_ratio/region_mean": 0.001958307759196032,
      "epoch": 0.133279666800833,
      "grad_norm": 0.13916778564453125,
      "learning_rate": 5e-07,
      "loss": 0.0034,
      "step": 1428
    },
    {
      "clip_ratio/high_max": 0.002532109931053128,
      "clip_ratio/high_mean": 0.0009781476164789638,
      "clip_ratio/low_mean": 0.0009967037512979005,
      "clip_ratio/low_min": 5.229018097452354e-05,
      "clip_ratio/region_mean": 0.0019748513295780867,
      "epoch": 0.1333729999008336,
      "grad_norm": 0.11430589854717255,
      "learning_rate": 5e-07,
      "loss": -0.0257,
      "step": 1429
    },
    {
      "clip_ratio/high_max": 0.0018858508410630748,
      "clip_ratio/high_mean": 0.0008476688781229313,
      "clip_ratio/low_mean": 0.0011245676723774523,
      "clip_ratio/low_min": 8.478486415697262e-05,
      "clip_ratio/region_mean": 0.001972236546862405,
      "epoch": 0.13346633300083416,
      "grad_norm": 0.12527084350585938,
      "learning_rate": 5e-07,
      "loss": 0.0641,
      "step": 1430
    },
    {
      "clip_ratio/high_max": 0.00198872534383554,
      "clip_ratio/high_mean": 0.0009284666230087169,
      "clip_ratio/low_mean": 0.0010247908376186388,
      "clip_ratio/low_min": 5.692951162927784e-05,
      "clip_ratio/region_mean": 0.0019532574151526205,
      "epoch": 0.13355966610083475,
      "grad_norm": 0.1101548820734024,
      "learning_rate": 5e-07,
      "loss": -0.0062,
      "step": 1431
    },
    {
      "clip_ratio/high_max": 0.0021889942763664294,
      "clip_ratio/high_mean": 0.0008651839398226002,
      "clip_ratio/low_mean": 0.0011667265516734915,
      "clip_ratio/low_min": 6.728942207701039e-05,
      "clip_ratio/region_mean": 0.0020319104805821553,
      "epoch": 0.13365299920083534,
      "grad_norm": 29.82280731201172,
      "learning_rate": 5e-07,
      "loss": 0.0039,
      "step": 1432
    },
    {
      "clip_ratio/high_max": 0.002021750384301413,
      "clip_ratio/high_mean": 0.0007711616071901517,
      "clip_ratio/low_mean": 0.0012405939778545871,
      "clip_ratio/low_min": 0.0002912554309659754,
      "clip_ratio/region_mean": 0.0020117555832257494,
      "epoch": 0.1337463323008359,
      "grad_norm": 0.1127149760723114,
      "learning_rate": 5e-07,
      "loss": 0.0573,
      "step": 1433
    },
    {
      "clip_ratio/high_max": 0.002074947886285372,
      "clip_ratio/high_mean": 0.0009006194595713168,
      "clip_ratio/low_mean": 0.000948922772295191,
      "clip_ratio/low_min": 4.541644466371508e-05,
      "clip_ratio/region_mean": 0.0018495422336854972,
      "epoch": 0.1338396654008365,
      "grad_norm": 0.11611531674861908,
      "learning_rate": 5e-07,
      "loss": -0.0071,
      "step": 1434
    },
    {
      "clip_ratio/high_max": 0.0020874256806564517,
      "clip_ratio/high_mean": 0.0008125382319121854,
      "clip_ratio/low_mean": 0.0010421221813885495,
      "clip_ratio/low_min": 2.915554796345532e-05,
      "clip_ratio/region_mean": 0.0018546604187577032,
      "epoch": 0.1339329985008371,
      "grad_norm": 0.11406747251749039,
      "learning_rate": 5e-07,
      "loss": 0.0434,
      "step": 1435
    },
    {
      "clip_ratio/high_max": 0.0024995768326334655,
      "clip_ratio/high_mean": 0.0009082194137590704,
      "clip_ratio/low_mean": 0.0010322848793293815,
      "clip_ratio/low_min": 8.7399926087528e-05,
      "clip_ratio/region_mean": 0.0019405042767175473,
      "epoch": 0.13402633160083766,
      "grad_norm": 0.1100410521030426,
      "learning_rate": 5e-07,
      "loss": 0.024,
      "step": 1436
    },
    {
      "clip_ratio/high_max": 0.0017246520037588198,
      "clip_ratio/high_mean": 0.0009087142225325806,
      "clip_ratio/low_mean": 0.0011148688408866292,
      "clip_ratio/low_min": 6.092376679589506e-05,
      "clip_ratio/region_mean": 0.002023583117988892,
      "epoch": 0.13411966470083825,
      "grad_norm": 0.108804851770401,
      "learning_rate": 5e-07,
      "loss": 0.0364,
      "step": 1437
    },
    {
      "clip_ratio/high_max": 0.002179984272515867,
      "clip_ratio/high_mean": 0.0010337239391446928,
      "clip_ratio/low_mean": 0.0009882066733553074,
      "clip_ratio/low_min": 0.00013805060916638467,
      "clip_ratio/region_mean": 0.0020219306024955586,
      "epoch": 0.13421299780083884,
      "grad_norm": 0.12953844666481018,
      "learning_rate": 5e-07,
      "loss": 0.0406,
      "step": 1438
    },
    {
      "clip_ratio/high_max": 0.0024102376046357676,
      "clip_ratio/high_mean": 0.0009043648115039105,
      "clip_ratio/low_mean": 0.0007903226469352376,
      "clip_ratio/low_min": 8.827683814160991e-06,
      "clip_ratio/region_mean": 0.0016946874602581374,
      "epoch": 0.1343063309008394,
      "grad_norm": 0.11760765314102173,
      "learning_rate": 5e-07,
      "loss": 0.0084,
      "step": 1439
    },
    {
      "clip_ratio/high_max": 0.002296177721291315,
      "clip_ratio/high_mean": 0.0009525791956548346,
      "clip_ratio/low_mean": 0.0009326822946604807,
      "clip_ratio/low_min": 1.1743705726985354e-05,
      "clip_ratio/region_mean": 0.0018852614448405802,
      "epoch": 0.13439966400084,
      "grad_norm": 0.12315467745065689,
      "learning_rate": 5e-07,
      "loss": 0.0089,
      "step": 1440
    },
    {
      "clip_ratio/high_max": 0.002511603190214373,
      "clip_ratio/high_mean": 0.0009906553041219013,
      "clip_ratio/low_mean": 0.0010153336406801827,
      "clip_ratio/low_min": 2.438173851260217e-05,
      "clip_ratio/region_mean": 0.002005988899327349,
      "completions/clipped_ratio": 0.013619559151785698,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4092.0,
      "completions/mean_length": 609.5773315429688,
      "completions/mean_terminated_length": 561.4381713867188,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.1344929971008406,
      "grad_norm": 437707.78125,
      "learning_rate": 5e-07,
      "loss": 324.9169,
      "num_tokens": 1058993358.0,
      "reward": 0.5993565320968628,
      "reward_std": 0.18551112711429596,
      "rewards/simpleverify_reward/mean": 0.5993565320968628,
      "rewards/simpleverify_reward/std": 0.4900308847427368,
      "step": 1441
    },
    {
      "clip_ratio/high_max": 0.00248801722045755,
      "clip_ratio/high_mean": 0.0010129809270438273,
      "clip_ratio/low_mean": 0.000847530631290283,
      "clip_ratio/low_min": 6.566211231984198e-05,
      "clip_ratio/region_mean": 0.0018605115401442163,
      "epoch": 0.13458633020084115,
      "grad_norm": 0.11292179673910141,
      "learning_rate": 5e-07,
      "loss": 0.0195,
      "step": 1442
    },
    {
      "clip_ratio/high_max": 0.002293530691531487,
      "clip_ratio/high_mean": 0.0009314707058365457,
      "clip_ratio/low_mean": 0.0009478838364884723,
      "clip_ratio/low_min": 5.821260128868744e-05,
      "clip_ratio/region_mean": 0.0018793545314110816,
      "epoch": 0.13467966330084175,
      "grad_norm": 0.12158806622028351,
      "learning_rate": 5e-07,
      "loss": 0.0173,
      "step": 1443
    },
    {
      "clip_ratio/high_max": 0.002187023696023971,
      "clip_ratio/high_mean": 0.0008681630333740031,
      "clip_ratio/low_mean": 0.0008876630727172596,
      "clip_ratio/low_min": 4.5922643039375544e-05,
      "clip_ratio/region_mean": 0.001755826102453284,
      "epoch": 0.13477299640084234,
      "grad_norm": 107.51051330566406,
      "learning_rate": 5e-07,
      "loss": 0.0664,
      "step": 1444
    },
    {
      "clip_ratio/high_max": 0.002374813719143276,
      "clip_ratio/high_mean": 0.000986493420896295,
      "clip_ratio/low_mean": 0.0010217917770205531,
      "clip_ratio/low_min": 9.88116989901755e-05,
      "clip_ratio/region_mean": 0.002008285213378258,
      "epoch": 0.1348663295008429,
      "grad_norm": 0.4405878186225891,
      "learning_rate": 5e-07,
      "loss": 0.0388,
      "step": 1445
    },
    {
      "clip_ratio/high_max": 0.0020470031740842387,
      "clip_ratio/high_mean": 0.0009245398596249288,
      "clip_ratio/low_mean": 0.0009418277786608087,
      "clip_ratio/low_min": 0.00010053541336674243,
      "clip_ratio/region_mean": 0.0018663676892174408,
      "epoch": 0.1349596626008435,
      "grad_norm": 0.16266392171382904,
      "learning_rate": 5e-07,
      "loss": -0.0099,
      "step": 1446
    },
    {
      "clip_ratio/high_max": 0.002443654870148748,
      "clip_ratio/high_mean": 0.0009841053579293657,
      "clip_ratio/low_mean": 0.0007681511888222303,
      "clip_ratio/low_min": 3.7737450838903897e-05,
      "clip_ratio/region_mean": 0.0017522565321996808,
      "epoch": 0.1350529957008441,
      "grad_norm": 0.20414386689662933,
      "learning_rate": 5e-07,
      "loss": 0.2525,
      "step": 1447
    },
    {
      "clip_ratio/high_max": 0.0022526923203258775,
      "clip_ratio/high_mean": 0.0009175022423733026,
      "clip_ratio/low_mean": 0.0008866798889357597,
      "clip_ratio/low_min": 6.623957960982807e-05,
      "clip_ratio/region_mean": 0.0018041821240331046,
      "epoch": 0.13514632880084468,
      "grad_norm": 203.52993774414062,
      "learning_rate": 5e-07,
      "loss": 6.4678,
      "step": 1448
    },
    {
      "clip_ratio/high_max": 0.0024677308974787593,
      "clip_ratio/high_mean": 0.0008496535847370978,
      "clip_ratio/low_mean": 0.00098540005274117,
      "clip_ratio/low_min": 0.00015055838321131887,
      "clip_ratio/region_mean": 0.0018350536120124161,
      "epoch": 0.13523966190084524,
      "grad_norm": 36.137447357177734,
      "learning_rate": 5e-07,
      "loss": 0.0861,
      "step": 1449
    },
    {
      "clip_ratio/high_max": 0.0019916202800231986,
      "clip_ratio/high_mean": 0.0008045921404118417,
      "clip_ratio/low_mean": 0.0009037373656610725,
      "clip_ratio/low_min": 2.3079763195710257e-05,
      "clip_ratio/region_mean": 0.0017083295169868506,
      "epoch": 0.13533299500084583,
      "grad_norm": 0.19549039006233215,
      "learning_rate": 5e-07,
      "loss": 0.018,
      "step": 1450
    },
    {
      "clip_ratio/high_max": 0.0017665166851656977,
      "clip_ratio/high_mean": 0.0007834467760403641,
      "clip_ratio/low_mean": 0.000935706131713232,
      "clip_ratio/low_min": 7.998885484994389e-05,
      "clip_ratio/region_mean": 0.0017191529041156173,
      "epoch": 0.13542632810084643,
      "grad_norm": 0.41234833002090454,
      "learning_rate": 5e-07,
      "loss": 0.0162,
      "step": 1451
    },
    {
      "clip_ratio/high_max": 0.0019984659847978037,
      "clip_ratio/high_mean": 0.0008453595710307127,
      "clip_ratio/low_mean": 0.0010610654680931475,
      "clip_ratio/low_min": 9.61370733421063e-05,
      "clip_ratio/region_mean": 0.0019064250300289132,
      "epoch": 0.135519661200847,
      "grad_norm": 0.19430319964885712,
      "learning_rate": 5e-07,
      "loss": 0.0351,
      "step": 1452
    },
    {
      "clip_ratio/high_max": 0.0026020309815066867,
      "clip_ratio/high_mean": 0.0011752484151656972,
      "clip_ratio/low_mean": 0.0009381370637129294,
      "clip_ratio/low_min": 9.388860780745745e-05,
      "clip_ratio/region_mean": 0.002113385453412775,
      "epoch": 0.13561299430084758,
      "grad_norm": 0.15998338162899017,
      "learning_rate": 5e-07,
      "loss": -0.0322,
      "step": 1453
    },
    {
      "clip_ratio/high_max": 0.002251458732644096,
      "clip_ratio/high_mean": 0.0008785721911408473,
      "clip_ratio/low_mean": 0.00090833838294202,
      "clip_ratio/low_min": 7.637024827999994e-05,
      "clip_ratio/region_mean": 0.0017869105431600474,
      "epoch": 0.13570632740084818,
      "grad_norm": 5056.32568359375,
      "learning_rate": 5e-07,
      "loss": 0.4147,
      "step": 1454
    },
    {
      "clip_ratio/high_max": 0.002072065348329488,
      "clip_ratio/high_mean": 0.0007955561068229144,
      "clip_ratio/low_mean": 0.0011984035591012798,
      "clip_ratio/low_min": 0.00011582180377445184,
      "clip_ratio/region_mean": 0.0019939596313633956,
      "epoch": 0.13579966050084874,
      "grad_norm": 1.0539230108261108,
      "learning_rate": 5e-07,
      "loss": 0.0959,
      "step": 1455
    },
    {
      "clip_ratio/high_max": 0.0023933939010021277,
      "clip_ratio/high_mean": 0.0009918602190737147,
      "clip_ratio/low_mean": 0.0009956625908671413,
      "clip_ratio/low_min": 0.0001007830687740352,
      "clip_ratio/region_mean": 0.001987522824492771,
      "epoch": 0.13589299360084933,
      "grad_norm": 4051.26171875,
      "learning_rate": 5e-07,
      "loss": 1.0588,
      "step": 1456
    },
    {
      "clip_ratio/high_max": 0.0024190873773477506,
      "clip_ratio/high_mean": 0.0009789173200260848,
      "clip_ratio/low_mean": 0.0010954057033814024,
      "clip_ratio/low_min": 9.606649837223813e-05,
      "clip_ratio/region_mean": 0.002074323005217593,
      "epoch": 0.13598632670084992,
      "grad_norm": 0.3165597915649414,
      "learning_rate": 5e-07,
      "loss": 0.032,
      "step": 1457
    },
    {
      "clip_ratio/high_max": 0.0021102602004248183,
      "clip_ratio/high_mean": 0.0008404040436289506,
      "clip_ratio/low_mean": 0.0010065073729492724,
      "clip_ratio/low_min": 0.0001500426415077527,
      "clip_ratio/region_mean": 0.0018469114365871064,
      "epoch": 0.1360796598008505,
      "grad_norm": 0.14677642285823822,
      "learning_rate": 5e-07,
      "loss": 0.0215,
      "step": 1458
    },
    {
      "clip_ratio/high_max": 0.0020240262310835533,
      "clip_ratio/high_mean": 0.0007690447946515633,
      "clip_ratio/low_mean": 0.001017241578665562,
      "clip_ratio/low_min": 8.223286749853287e-05,
      "clip_ratio/region_mean": 0.0017862863969639875,
      "epoch": 0.13617299290085108,
      "grad_norm": 0.14875495433807373,
      "learning_rate": 5e-07,
      "loss": 0.0717,
      "step": 1459
    },
    {
      "clip_ratio/high_max": 0.002028931528911926,
      "clip_ratio/high_mean": 0.0009082734850380803,
      "clip_ratio/low_mean": 0.0009972001771529904,
      "clip_ratio/low_min": 6.44641904727905e-05,
      "clip_ratio/region_mean": 0.0019054736621910706,
      "epoch": 0.13626632600085167,
      "grad_norm": 0.12217123806476593,
      "learning_rate": 5e-07,
      "loss": 0.0087,
      "step": 1460
    },
    {
      "clip_ratio/high_max": 0.0018423894907755312,
      "clip_ratio/high_mean": 0.000798477141870535,
      "clip_ratio/low_mean": 0.0010828055455931462,
      "clip_ratio/low_min": 2.4823774765536655e-05,
      "clip_ratio/region_mean": 0.0018812826965586282,
      "epoch": 0.13635965910085224,
      "grad_norm": 0.7075853943824768,
      "learning_rate": 5e-07,
      "loss": 0.0461,
      "step": 1461
    },
    {
      "clip_ratio/high_max": 0.002303819826920517,
      "clip_ratio/high_mean": 0.0008908412855817005,
      "clip_ratio/low_mean": 0.0009416690518264659,
      "clip_ratio/low_min": 5.5192934269143734e-05,
      "clip_ratio/region_mean": 0.0018325103519600816,
      "epoch": 0.13645299220085283,
      "grad_norm": 0.11304020136594772,
      "learning_rate": 5e-07,
      "loss": -0.0064,
      "step": 1462
    },
    {
      "clip_ratio/high_max": 0.0018144624700653367,
      "clip_ratio/high_mean": 0.0008039159420150099,
      "clip_ratio/low_mean": 0.001166640991868917,
      "clip_ratio/low_min": 0.00014433653814194258,
      "clip_ratio/region_mean": 0.0019705569138750434,
      "epoch": 0.13654632530085342,
      "grad_norm": 0.12767888605594635,
      "learning_rate": 5e-07,
      "loss": 0.0715,
      "step": 1463
    },
    {
      "clip_ratio/high_max": 0.002218931789684575,
      "clip_ratio/high_mean": 0.0009110344799410086,
      "clip_ratio/low_mean": 0.0009571417813276639,
      "clip_ratio/low_min": 7.755612750770524e-05,
      "clip_ratio/region_mean": 0.0018681763031054288,
      "epoch": 0.13663965840085399,
      "grad_norm": 0.1053435280919075,
      "learning_rate": 5e-07,
      "loss": -0.0079,
      "step": 1464
    },
    {
      "clip_ratio/high_max": 0.002051836851023836,
      "clip_ratio/high_mean": 0.000877264428709168,
      "clip_ratio/low_mean": 0.0010776113122119568,
      "clip_ratio/low_min": 9.656666406954173e-05,
      "clip_ratio/region_mean": 0.001954875733645167,
      "epoch": 0.13673299150085458,
      "grad_norm": 7.635754585266113,
      "learning_rate": 5e-07,
      "loss": 1.1279,
      "step": 1465
    },
    {
      "clip_ratio/high_max": 0.002392874623183161,
      "clip_ratio/high_mean": 0.0009749313503562007,
      "clip_ratio/low_mean": 0.0010472562989889411,
      "clip_ratio/low_min": 3.517172353895148e-05,
      "clip_ratio/region_mean": 0.0020221876839059405,
      "epoch": 0.13682632460085517,
      "grad_norm": 0.12732411921024323,
      "learning_rate": 5e-07,
      "loss": -0.0037,
      "step": 1466
    },
    {
      "clip_ratio/high_max": 0.002211287384852767,
      "clip_ratio/high_mean": 0.0009516812715446576,
      "clip_ratio/low_mean": 0.0009538964313833276,
      "clip_ratio/low_min": 5.066307949164184e-05,
      "clip_ratio/region_mean": 0.0019055776283494197,
      "epoch": 0.13691965770085573,
      "grad_norm": 0.11474256217479706,
      "learning_rate": 5e-07,
      "loss": -0.0331,
      "step": 1467
    },
    {
      "clip_ratio/high_max": 0.002280897897435352,
      "clip_ratio/high_mean": 0.001037278154399246,
      "clip_ratio/low_mean": 0.0009866541240626248,
      "clip_ratio/low_min": 0.00011928515596082434,
      "clip_ratio/region_mean": 0.0020239322548150085,
      "epoch": 0.13701299080085633,
      "grad_norm": 0.10826075822114944,
      "learning_rate": 5e-07,
      "loss": -0.0029,
      "step": 1468
    },
    {
      "clip_ratio/high_max": 0.0019546952753444202,
      "clip_ratio/high_mean": 0.0007975439384608762,
      "clip_ratio/low_mean": 0.0010050732926174533,
      "clip_ratio/low_min": 9.044292801263509e-05,
      "clip_ratio/region_mean": 0.0018026172183454037,
      "epoch": 0.13710632390085692,
      "grad_norm": 0.12354385107755661,
      "learning_rate": 5e-07,
      "loss": -0.0022,
      "step": 1469
    },
    {
      "clip_ratio/high_max": 0.0022133023012429476,
      "clip_ratio/high_mean": 0.0008747626179683721,
      "clip_ratio/low_mean": 0.0011943849858653266,
      "clip_ratio/low_min": 5.3174846470938064e-05,
      "clip_ratio/region_mean": 0.0020691475074272603,
      "epoch": 0.1371996570008575,
      "grad_norm": 0.1513563096523285,
      "learning_rate": 5e-07,
      "loss": 0.0895,
      "step": 1470
    },
    {
      "clip_ratio/high_max": 0.002317627273441758,
      "clip_ratio/high_mean": 0.0009965084063878749,
      "clip_ratio/low_mean": 0.0009619571028451901,
      "clip_ratio/low_min": 8.529460865247529e-05,
      "clip_ratio/region_mean": 0.001958465531060938,
      "epoch": 0.13729299010085808,
      "grad_norm": 0.8805445432662964,
      "learning_rate": 5e-07,
      "loss": -0.0225,
      "step": 1471
    },
    {
      "clip_ratio/high_max": 0.002133441168552963,
      "clip_ratio/high_mean": 0.0008752857720537577,
      "clip_ratio/low_mean": 0.000966243096627295,
      "clip_ratio/low_min": 0.00011120848921564175,
      "clip_ratio/region_mean": 0.0018415288941469043,
      "epoch": 0.13738632320085867,
      "grad_norm": 0.11865788698196411,
      "learning_rate": 5e-07,
      "loss": 0.0188,
      "step": 1472
    },
    {
      "clip_ratio/high_max": 0.002013197517953813,
      "clip_ratio/high_mean": 0.0007957791640365031,
      "clip_ratio/low_mean": 0.0009630956701585092,
      "clip_ratio/low_min": 3.289706364739686e-05,
      "clip_ratio/region_mean": 0.001758874765073415,
      "epoch": 0.13747965630085926,
      "grad_norm": 0.13261142373085022,
      "learning_rate": 5e-07,
      "loss": 0.4261,
      "step": 1473
    },
    {
      "clip_ratio/high_max": 0.002225493542937329,
      "clip_ratio/high_mean": 0.0009489051008131355,
      "clip_ratio/low_mean": 0.001099431927286787,
      "clip_ratio/low_min": 8.094275108305737e-05,
      "clip_ratio/region_mean": 0.002048337053565774,
      "epoch": 0.13757298940085982,
      "grad_norm": 0.11820437014102936,
      "learning_rate": 5e-07,
      "loss": 0.0297,
      "step": 1474
    },
    {
      "clip_ratio/high_max": 0.002353871474042535,
      "clip_ratio/high_mean": 0.0008490031832479872,
      "clip_ratio/low_mean": 0.0013064675877103582,
      "clip_ratio/low_min": 6.105004649725743e-05,
      "clip_ratio/region_mean": 0.0021554708291660063,
      "epoch": 0.13766632250086042,
      "grad_norm": 0.14490850269794464,
      "learning_rate": 5e-07,
      "loss": 0.0668,
      "step": 1475
    },
    {
      "clip_ratio/high_max": 0.0025120490245171823,
      "clip_ratio/high_mean": 0.0010650203039404005,
      "clip_ratio/low_mean": 0.001161056130513316,
      "clip_ratio/low_min": 0.0001243235128640663,
      "clip_ratio/region_mean": 0.0022260764308157377,
      "epoch": 0.137759655600861,
      "grad_norm": 0.14134487509727478,
      "learning_rate": 5e-07,
      "loss": 0.037,
      "step": 1476
    },
    {
      "clip_ratio/high_max": 0.002633313983096741,
      "clip_ratio/high_mean": 0.0008831077211652882,
      "clip_ratio/low_mean": 0.001050310329446802,
      "clip_ratio/low_min": 4.0089647882268764e-05,
      "clip_ratio/region_mean": 0.0019334180105943233,
      "epoch": 0.13785298870086157,
      "grad_norm": 0.11947498470544815,
      "learning_rate": 5e-07,
      "loss": 0.0322,
      "step": 1477
    },
    {
      "clip_ratio/high_max": 0.0021315399681043345,
      "clip_ratio/high_mean": 0.0009660884097684175,
      "clip_ratio/low_mean": 0.0010984029231622117,
      "clip_ratio/low_min": 0.00013369045336730778,
      "clip_ratio/region_mean": 0.0020644912947318517,
      "epoch": 0.13794632180086216,
      "grad_norm": 0.13932152092456818,
      "learning_rate": 5e-07,
      "loss": 0.024,
      "step": 1478
    },
    {
      "clip_ratio/high_max": 0.0020765635927091353,
      "clip_ratio/high_mean": 0.0008783464727457613,
      "clip_ratio/low_mean": 0.0010730692411016207,
      "clip_ratio/low_min": 7.974910386110423e-05,
      "clip_ratio/region_mean": 0.0019514157174853608,
      "epoch": 0.13803965490086276,
      "grad_norm": 0.12095864862203598,
      "learning_rate": 5e-07,
      "loss": 0.0238,
      "step": 1479
    },
    {
      "clip_ratio/high_max": 0.0021065120745333843,
      "clip_ratio/high_mean": 0.0009448620148759801,
      "clip_ratio/low_mean": 0.0010463172911840957,
      "clip_ratio/low_min": 0.00011089603140135296,
      "clip_ratio/region_mean": 0.0019911793278879486,
      "epoch": 0.13813298800086332,
      "grad_norm": 0.11993414163589478,
      "learning_rate": 5e-07,
      "loss": -0.0079,
      "step": 1480
    },
    {
      "clip_ratio/high_max": 0.0024449457378068473,
      "clip_ratio/high_mean": 0.0010024800585597404,
      "clip_ratio/low_mean": 0.0012033623534080107,
      "clip_ratio/low_min": 0.00011332775829941966,
      "clip_ratio/region_mean": 0.00220584240014432,
      "epoch": 0.1382263211008639,
      "grad_norm": 0.14739081263542175,
      "learning_rate": 5e-07,
      "loss": 0.0019,
      "step": 1481
    },
    {
      "clip_ratio/high_max": 0.0021256162726785988,
      "clip_ratio/high_mean": 0.0008887241874617757,
      "clip_ratio/low_mean": 0.0012003564243059373,
      "clip_ratio/low_min": 8.385144792555366e-05,
      "clip_ratio/region_mean": 0.00208908058993984,
      "epoch": 0.1383196542008645,
      "grad_norm": 0.11691886931657791,
      "learning_rate": 5e-07,
      "loss": 0.0406,
      "step": 1482
    },
    {
      "clip_ratio/high_max": 0.0020361111201054882,
      "clip_ratio/high_mean": 0.0008511786891176598,
      "clip_ratio/low_mean": 0.0009433588966203388,
      "clip_ratio/low_min": 6.939749982848298e-05,
      "clip_ratio/region_mean": 0.0017945376021089032,
      "epoch": 0.13841298730086507,
      "grad_norm": 1.8656814098358154,
      "learning_rate": 5e-07,
      "loss": 0.0253,
      "step": 1483
    },
    {
      "clip_ratio/high_max": 0.002168887382140383,
      "clip_ratio/high_mean": 0.000830627901450498,
      "clip_ratio/low_mean": 0.0012032496197207365,
      "clip_ratio/low_min": 0.00013305073298397474,
      "clip_ratio/region_mean": 0.0020338774993433617,
      "epoch": 0.13850632040086566,
      "grad_norm": 0.1162618026137352,
      "learning_rate": 5e-07,
      "loss": 0.0575,
      "step": 1484
    },
    {
      "clip_ratio/high_max": 0.002094409537676256,
      "clip_ratio/high_mean": 0.0009200308086292353,
      "clip_ratio/low_mean": 0.0011300481128273532,
      "clip_ratio/low_min": 2.7658316867018584e-05,
      "clip_ratio/region_mean": 0.0020500788596109487,
      "epoch": 0.13859965350086625,
      "grad_norm": 0.11767467856407166,
      "learning_rate": 5e-07,
      "loss": 0.0716,
      "step": 1485
    },
    {
      "clip_ratio/high_max": 0.0018534699665906373,
      "clip_ratio/high_mean": 0.0007279967412614496,
      "clip_ratio/low_mean": 0.0011818598250101786,
      "clip_ratio/low_min": 0.00010821794148796471,
      "clip_ratio/region_mean": 0.00190985656081466,
      "epoch": 0.13869298660086682,
      "grad_norm": 0.12091667205095291,
      "learning_rate": 5e-07,
      "loss": 0.1121,
      "step": 1486
    },
    {
      "clip_ratio/high_max": 0.002143157384125516,
      "clip_ratio/high_mean": 0.0008534560020052595,
      "clip_ratio/low_mean": 0.0011055197846872034,
      "clip_ratio/low_min": 8.441014688287396e-05,
      "clip_ratio/region_mean": 0.001958975837624166,
      "epoch": 0.1387863197008674,
      "grad_norm": 69.50796508789062,
      "learning_rate": 5e-07,
      "loss": 0.0603,
      "step": 1487
    },
    {
      "clip_ratio/high_max": 0.0021697996999137104,
      "clip_ratio/high_mean": 0.0009475333536101971,
      "clip_ratio/low_mean": 0.0010955966754409019,
      "clip_ratio/low_min": 8.922867164073978e-05,
      "clip_ratio/region_mean": 0.00204313008725876,
      "epoch": 0.138879652800868,
      "grad_norm": 0.11784769594669342,
      "learning_rate": 5e-07,
      "loss": 0.041,
      "step": 1488
    },
    {
      "clip_ratio/high_max": 0.0020961320587957744,
      "clip_ratio/high_mean": 0.0008749490480113309,
      "clip_ratio/low_mean": 0.0009316259656770853,
      "clip_ratio/low_min": 8.982285453384975e-05,
      "clip_ratio/region_mean": 0.0018065750336972997,
      "epoch": 0.13897298590086857,
      "grad_norm": 0.4952276945114136,
      "learning_rate": 5e-07,
      "loss": -0.0093,
      "step": 1489
    },
    {
      "clip_ratio/high_max": 0.00208389212275506,
      "clip_ratio/high_mean": 0.0007907765921117971,
      "clip_ratio/low_mean": 0.0010616809977364028,
      "clip_ratio/low_min": 5.032206172472797e-05,
      "clip_ratio/region_mean": 0.001852457608038094,
      "epoch": 0.13906631900086916,
      "grad_norm": 0.10841172188520432,
      "learning_rate": 5e-07,
      "loss": 0.0516,
      "step": 1490
    },
    {
      "clip_ratio/high_max": 0.0025638092738518026,
      "clip_ratio/high_mean": 0.001012801747492631,
      "clip_ratio/low_mean": 0.00098778822029999,
      "clip_ratio/low_min": 0.0001461718738937634,
      "clip_ratio/region_mean": 0.002000589964154642,
      "epoch": 0.13915965210086975,
      "grad_norm": 0.10945624113082886,
      "learning_rate": 5e-07,
      "loss": -0.012,
      "step": 1491
    },
    {
      "clip_ratio/high_max": 0.0022285889499471523,
      "clip_ratio/high_mean": 0.0007945596171339275,
      "clip_ratio/low_mean": 0.0010017802596848924,
      "clip_ratio/low_min": 8.131178219628055e-05,
      "clip_ratio/region_mean": 0.0017963399077416398,
      "epoch": 0.13925298520087034,
      "grad_norm": 0.11661396920681,
      "learning_rate": 5e-07,
      "loss": 0.0172,
      "step": 1492
    },
    {
      "clip_ratio/high_max": 0.0024962666066130623,
      "clip_ratio/high_mean": 0.0009610107390471967,
      "clip_ratio/low_mean": 0.0009267249388358323,
      "clip_ratio/low_min": 3.4261546716152225e-05,
      "clip_ratio/region_mean": 0.0018877357069868594,
      "epoch": 0.1393463183008709,
      "grad_norm": 0.1281287968158722,
      "learning_rate": 5e-07,
      "loss": -0.0185,
      "step": 1493
    },
    {
      "clip_ratio/high_max": 0.0016659849316056352,
      "clip_ratio/high_mean": 0.0006720276815030957,
      "clip_ratio/low_mean": 0.0010794810496008722,
      "clip_ratio/low_min": 0.00020075108113815077,
      "clip_ratio/region_mean": 0.0017515087783976924,
      "epoch": 0.1394396514008715,
      "grad_norm": 0.11983296275138855,
      "learning_rate": 5e-07,
      "loss": 0.054,
      "step": 1494
    },
    {
      "clip_ratio/high_max": 0.002102938527968945,
      "clip_ratio/high_mean": 0.0009448071341466857,
      "clip_ratio/low_mean": 0.0010866647608054336,
      "clip_ratio/low_min": 6.146474879642483e-05,
      "clip_ratio/region_mean": 0.002031471907685045,
      "epoch": 0.1395329845008721,
      "grad_norm": 1.95286226272583,
      "learning_rate": 5e-07,
      "loss": 0.0312,
      "step": 1495
    },
    {
      "clip_ratio/high_max": 0.0024897013281588443,
      "clip_ratio/high_mean": 0.0009863704162853537,
      "clip_ratio/low_mean": 0.0010292120477970457,
      "clip_ratio/low_min": 0.00010407501395093277,
      "clip_ratio/region_mean": 0.002015582474996336,
      "epoch": 0.13962631760087266,
      "grad_norm": 0.109664686024189,
      "learning_rate": 5e-07,
      "loss": -0.0244,
      "step": 1496
    },
    {
      "clip_ratio/high_max": 0.002051809504337143,
      "clip_ratio/high_mean": 0.000919434683964937,
      "clip_ratio/low_mean": 0.0010701582541514654,
      "clip_ratio/low_min": 9.725681411509868e-05,
      "clip_ratio/region_mean": 0.0019895929071935825,
      "epoch": 0.13971965070087325,
      "grad_norm": 0.1121363565325737,
      "learning_rate": 5e-07,
      "loss": -0.0192,
      "step": 1497
    },
    {
      "clip_ratio/high_max": 0.0021641410494339652,
      "clip_ratio/high_mean": 0.0009328565192845417,
      "clip_ratio/low_mean": 0.0009899840224534273,
      "clip_ratio/low_min": 5.8163917856290936e-05,
      "clip_ratio/region_mean": 0.0019228405362810008,
      "epoch": 0.13981298380087384,
      "grad_norm": 0.21202358603477478,
      "learning_rate": 5e-07,
      "loss": 0.0022,
      "step": 1498
    },
    {
      "clip_ratio/high_max": 0.002239337431092281,
      "clip_ratio/high_mean": 0.0009112978714256315,
      "clip_ratio/low_mean": 0.0010484723570698407,
      "clip_ratio/low_min": 0.00011488628479128238,
      "clip_ratio/region_mean": 0.0019597701975726523,
      "epoch": 0.1399063169008744,
      "grad_norm": 0.11675988882780075,
      "learning_rate": 5e-07,
      "loss": 0.0232,
      "step": 1499
    },
    {
      "clip_ratio/high_max": 0.0021216947279754095,
      "clip_ratio/high_mean": 0.0007903262649051612,
      "clip_ratio/low_mean": 0.0009525862860755296,
      "clip_ratio/low_min": 0.00010731506154115777,
      "clip_ratio/region_mean": 0.0017429125946364366,
      "epoch": 0.139999650000875,
      "grad_norm": 0.1066182404756546,
      "learning_rate": 5e-07,
      "loss": 0.0368,
      "step": 1500
    },
    {
      "clip_ratio/high_max": 0.0022547917906194925,
      "clip_ratio/high_mean": 0.0008801265466900077,
      "clip_ratio/low_mean": 0.0010372792476118775,
      "clip_ratio/low_min": 0.00010542249492573319,
      "clip_ratio/region_mean": 0.0019174057670170441,
      "epoch": 0.1400929831008756,
      "grad_norm": 0.12336811423301697,
      "learning_rate": 5e-07,
      "loss": 0.0466,
      "step": 1501
    },
    {
      "clip_ratio/high_max": 0.0021275230901665054,
      "clip_ratio/high_mean": 0.0008537862013326958,
      "clip_ratio/low_mean": 0.0010277315341227222,
      "clip_ratio/low_min": 0.00011016419830411905,
      "clip_ratio/region_mean": 0.0018815177027136087,
      "epoch": 0.14018631620087615,
      "grad_norm": 136.8732147216797,
      "learning_rate": 5e-07,
      "loss": 0.0844,
      "step": 1502
    },
    {
      "clip_ratio/high_max": 0.0025450468456256203,
      "clip_ratio/high_mean": 0.0009880010056804167,
      "clip_ratio/low_mean": 0.0009294592437072424,
      "clip_ratio/low_min": 0.00013284097440191545,
      "clip_ratio/region_mean": 0.0019174602202838287,
      "epoch": 0.14027964930087675,
      "grad_norm": 0.1282316893339157,
      "learning_rate": 5e-07,
      "loss": -0.0271,
      "step": 1503
    },
    {
      "clip_ratio/high_max": 0.0023321386324823834,
      "clip_ratio/high_mean": 0.0009419859979971079,
      "clip_ratio/low_mean": 0.0010737546317614033,
      "clip_ratio/low_min": 4.5403543481370434e-05,
      "clip_ratio/region_mean": 0.002015740654314868,
      "epoch": 0.14037298240087734,
      "grad_norm": 0.15739886462688446,
      "learning_rate": 5e-07,
      "loss": 0.0276,
      "step": 1504
    },
    {
      "clip_ratio/high_max": 0.002342017483897507,
      "clip_ratio/high_mean": 0.0009086139089049539,
      "clip_ratio/low_mean": 0.0009933575602190103,
      "clip_ratio/low_min": 7.4613545621105e-05,
      "clip_ratio/region_mean": 0.0019019715036847629,
      "epoch": 0.1404663155008779,
      "grad_norm": 0.11573600769042969,
      "learning_rate": 5e-07,
      "loss": 0.0062,
      "step": 1505
    },
    {
      "clip_ratio/high_max": 0.0023413925082422793,
      "clip_ratio/high_mean": 0.0009847523688222282,
      "clip_ratio/low_mean": 0.0011021769223589217,
      "clip_ratio/low_min": 0.0001287985833187122,
      "clip_ratio/region_mean": 0.002086929263896309,
      "epoch": 0.1405596486008785,
      "grad_norm": 0.1641882359981537,
      "learning_rate": 5e-07,
      "loss": 0.0304,
      "step": 1506
    },
    {
      "clip_ratio/high_max": 0.0023229334910865873,
      "clip_ratio/high_mean": 0.0008962647734733764,
      "clip_ratio/low_mean": 0.0010921452067123028,
      "clip_ratio/low_min": 9.752021287567914e-05,
      "clip_ratio/region_mean": 0.001988409996556584,
      "epoch": 0.1406529817008791,
      "grad_norm": 0.11175739020109177,
      "learning_rate": 5e-07,
      "loss": 0.0425,
      "step": 1507
    },
    {
      "clip_ratio/high_max": 0.002278301319165621,
      "clip_ratio/high_mean": 0.0009192815487040207,
      "clip_ratio/low_mean": 0.0007915876176411984,
      "clip_ratio/low_min": 2.7460457204142585e-05,
      "clip_ratio/region_mean": 0.0017108691463363357,
      "epoch": 0.14074631480087965,
      "grad_norm": 0.11750739812850952,
      "learning_rate": 5e-07,
      "loss": -0.0158,
      "step": 1508
    },
    {
      "clip_ratio/high_max": 0.002168156839616131,
      "clip_ratio/high_mean": 0.0009078129114641342,
      "clip_ratio/low_mean": 0.0010882920105359517,
      "clip_ratio/low_min": 8.130043079290772e-05,
      "clip_ratio/region_mean": 0.001996104998397641,
      "epoch": 0.14083964790088024,
      "grad_norm": 0.11539280414581299,
      "learning_rate": 5e-07,
      "loss": 0.0175,
      "step": 1509
    },
    {
      "clip_ratio/high_max": 0.001965772404219024,
      "clip_ratio/high_mean": 0.0008141691250784788,
      "clip_ratio/low_mean": 0.0010223379395029042,
      "clip_ratio/low_min": 4.73541972496605e-05,
      "clip_ratio/region_mean": 0.0018365070718573406,
      "epoch": 0.14093298100088084,
      "grad_norm": 1.48096764087677,
      "learning_rate": 5e-07,
      "loss": 0.056,
      "step": 1510
    },
    {
      "clip_ratio/high_max": 0.0018849515981855802,
      "clip_ratio/high_mean": 0.0007840941143513191,
      "clip_ratio/low_mean": 0.0011361557808413636,
      "clip_ratio/low_min": 0.0001746272337186383,
      "clip_ratio/region_mean": 0.0019202498879167251,
      "epoch": 0.14102631410088143,
      "grad_norm": 0.12801167368888855,
      "learning_rate": 5e-07,
      "loss": 0.0548,
      "step": 1511
    },
    {
      "clip_ratio/high_max": 0.0022350424369506072,
      "clip_ratio/high_mean": 0.0009101026316784555,
      "clip_ratio/low_mean": 0.001028128626785474,
      "clip_ratio/low_min": 8.880440691427793e-05,
      "clip_ratio/region_mean": 0.001938231238455046,
      "epoch": 0.141119647200882,
      "grad_norm": 117.49984741210938,
      "learning_rate": 5e-07,
      "loss": 0.0654,
      "step": 1512
    },
    {
      "clip_ratio/high_max": 0.00230165342145483,
      "clip_ratio/high_mean": 0.0009693082611192949,
      "clip_ratio/low_mean": 0.0009307078707934124,
      "clip_ratio/low_min": 2.0018469058413757e-05,
      "clip_ratio/region_mean": 0.0019000161337316968,
      "epoch": 0.14121298030088258,
      "grad_norm": 0.11783675849437714,
      "learning_rate": 5e-07,
      "loss": 0.0277,
      "step": 1513
    },
    {
      "clip_ratio/high_max": 0.002350371600186918,
      "clip_ratio/high_mean": 0.001033935826853849,
      "clip_ratio/low_mean": 0.0008183254030882381,
      "clip_ratio/low_min": 5.635597790387692e-05,
      "clip_ratio/region_mean": 0.0018522612008382566,
      "epoch": 0.14130631340088318,
      "grad_norm": 0.10767554491758347,
      "learning_rate": 5e-07,
      "loss": -0.0155,
      "step": 1514
    },
    {
      "clip_ratio/high_max": 0.002030469047895167,
      "clip_ratio/high_mean": 0.0008384005795960547,
      "clip_ratio/low_mean": 0.0009334941569250077,
      "clip_ratio/low_min": 8.063463974394836e-05,
      "clip_ratio/region_mean": 0.0017718947201501578,
      "epoch": 0.14139964650088374,
      "grad_norm": 2.1288254261016846,
      "learning_rate": 5e-07,
      "loss": -0.0073,
      "step": 1515
    },
    {
      "clip_ratio/high_max": 0.002335599892830942,
      "clip_ratio/high_mean": 0.0009103227857849561,
      "clip_ratio/low_mean": 0.0009925249250954948,
      "clip_ratio/low_min": 8.201510172511917e-05,
      "clip_ratio/region_mean": 0.001902847747260239,
      "epoch": 0.14149297960088433,
      "grad_norm": 0.12281722575426102,
      "learning_rate": 5e-07,
      "loss": 0.0295,
      "step": 1516
    },
    {
      "clip_ratio/high_max": 0.002309647185029462,
      "clip_ratio/high_mean": 0.0008996253673103638,
      "clip_ratio/low_mean": 0.0009689533708296949,
      "clip_ratio/low_min": 4.4208584768057335e-05,
      "clip_ratio/region_mean": 0.001868578721769154,
      "epoch": 0.14158631270088493,
      "grad_norm": 0.10539444535970688,
      "learning_rate": 5e-07,
      "loss": 0.0498,
      "step": 1517
    },
    {
      "clip_ratio/high_max": 0.002397207761532627,
      "clip_ratio/high_mean": 0.0010753772148746066,
      "clip_ratio/low_mean": 0.0010037935371656204,
      "clip_ratio/low_min": 2.4174833015422337e-05,
      "clip_ratio/region_mean": 0.002079170757497195,
      "epoch": 0.1416796458008855,
      "grad_norm": 1.4348334074020386,
      "learning_rate": 5e-07,
      "loss": 0.0055,
      "step": 1518
    },
    {
      "clip_ratio/high_max": 0.0021834959552506916,
      "clip_ratio/high_mean": 0.000904203900063294,
      "clip_ratio/low_mean": 0.0012631913377845194,
      "clip_ratio/low_min": 5.147816409589723e-05,
      "clip_ratio/region_mean": 0.002167395272408612,
      "epoch": 0.14177297890088608,
      "grad_norm": 0.12535347044467926,
      "learning_rate": 5e-07,
      "loss": 0.04,
      "step": 1519
    },
    {
      "clip_ratio/high_max": 0.0019509717130858917,
      "clip_ratio/high_mean": 0.0008055231701291632,
      "clip_ratio/low_mean": 0.0009181688164972002,
      "clip_ratio/low_min": 2.5429128072573803e-05,
      "clip_ratio/region_mean": 0.001723692002997268,
      "epoch": 0.14186631200088667,
      "grad_norm": 0.10418714582920074,
      "learning_rate": 5e-07,
      "loss": 0.0058,
      "step": 1520
    },
    {
      "clip_ratio/high_max": 0.0026116590743185952,
      "clip_ratio/high_mean": 0.0009860728532657959,
      "clip_ratio/low_mean": 0.0010554486925684614,
      "clip_ratio/low_min": 2.7108770154882222e-05,
      "clip_ratio/region_mean": 0.0020415215549292043,
      "epoch": 0.14195964510088724,
      "grad_norm": 0.12761647999286652,
      "learning_rate": 5e-07,
      "loss": -0.0049,
      "step": 1521
    },
    {
      "clip_ratio/high_max": 0.002060891638393514,
      "clip_ratio/high_mean": 0.0007819753791409312,
      "clip_ratio/low_mean": 0.0009923369470925536,
      "clip_ratio/low_min": 0.0001222893542944803,
      "clip_ratio/region_mean": 0.0017743123607942834,
      "epoch": 0.14205297820088783,
      "grad_norm": 0.13103511929512024,
      "learning_rate": 5e-07,
      "loss": 0.0703,
      "step": 1522
    },
    {
      "clip_ratio/high_max": 0.0022593937483179616,
      "clip_ratio/high_mean": 0.0008817224338599772,
      "clip_ratio/low_mean": 0.0011992889685643604,
      "clip_ratio/low_min": 0.00012270818569959374,
      "clip_ratio/region_mean": 0.0020810113855986856,
      "epoch": 0.14214631130088842,
      "grad_norm": 0.124531589448452,
      "learning_rate": 5e-07,
      "loss": 0.067,
      "step": 1523
    },
    {
      "clip_ratio/high_max": 0.0019818065120489337,
      "clip_ratio/high_mean": 0.0007759069376334082,
      "clip_ratio/low_mean": 0.0011191657540621236,
      "clip_ratio/low_min": 0.00010524189929128624,
      "clip_ratio/region_mean": 0.0018950726735056378,
      "epoch": 0.142239644400889,
      "grad_norm": 0.12772896885871887,
      "learning_rate": 5e-07,
      "loss": 0.0393,
      "step": 1524
    },
    {
      "clip_ratio/high_max": 0.002163084802305093,
      "clip_ratio/high_mean": 0.0009063878496817779,
      "clip_ratio/low_mean": 0.001004887351882644,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001911275161546655,
      "epoch": 0.14233297750088958,
      "grad_norm": 0.10713318735361099,
      "learning_rate": 5e-07,
      "loss": 0.0302,
      "step": 1525
    },
    {
      "clip_ratio/high_max": 0.0017380001845594961,
      "clip_ratio/high_mean": 0.0007472217166650807,
      "clip_ratio/low_mean": 0.0010502526893105824,
      "clip_ratio/low_min": 0.00010589295106910868,
      "clip_ratio/region_mean": 0.0017974744041566737,
      "epoch": 0.14242631060089017,
      "grad_norm": 0.18302907049655914,
      "learning_rate": 5e-07,
      "loss": 0.0607,
      "step": 1526
    },
    {
      "clip_ratio/high_max": 0.002291129028890282,
      "clip_ratio/high_mean": 0.0009755135542945936,
      "clip_ratio/low_mean": 0.0011055434733862057,
      "clip_ratio/low_min": 6.888963980600238e-05,
      "clip_ratio/region_mean": 0.002081056998576969,
      "epoch": 0.14251964370089074,
      "grad_norm": 0.11340068280696869,
      "learning_rate": 5e-07,
      "loss": -0.0064,
      "step": 1527
    },
    {
      "clip_ratio/high_max": 0.002125005456036888,
      "clip_ratio/high_mean": 0.000874074328748975,
      "clip_ratio/low_mean": 0.0011329945755278459,
      "clip_ratio/low_min": 8.781911674304865e-05,
      "clip_ratio/region_mean": 0.002007068873354001,
      "epoch": 0.14261297680089133,
      "grad_norm": 0.11688084155321121,
      "learning_rate": 5e-07,
      "loss": 0.0296,
      "step": 1528
    },
    {
      "clip_ratio/high_max": 0.00218953873263672,
      "clip_ratio/high_mean": 0.0009144378927885555,
      "clip_ratio/low_mean": 0.0009784485555428546,
      "clip_ratio/low_min": 0.00014087730869505322,
      "clip_ratio/region_mean": 0.0018928864155896008,
      "epoch": 0.14270630990089192,
      "grad_norm": 0.10730821639299393,
      "learning_rate": 5e-07,
      "loss": 0.032,
      "step": 1529
    },
    {
      "clip_ratio/high_max": 0.0019691433699335903,
      "clip_ratio/high_mean": 0.000795549920439953,
      "clip_ratio/low_mean": 0.0012830931300413795,
      "clip_ratio/low_min": 0.00016395038346672663,
      "clip_ratio/region_mean": 0.0020786430686712265,
      "epoch": 0.14279964300089248,
      "grad_norm": 0.8442116379737854,
      "learning_rate": 5e-07,
      "loss": 0.0828,
      "step": 1530
    },
    {
      "clip_ratio/high_max": 0.0021902928056078963,
      "clip_ratio/high_mean": 0.0009244846023648279,
      "clip_ratio/low_mean": 0.0009543613141431706,
      "clip_ratio/low_min": 3.341995670780307e-05,
      "clip_ratio/region_mean": 0.0018788459419738501,
      "epoch": 0.14289297610089308,
      "grad_norm": 0.10820360481739044,
      "learning_rate": 5e-07,
      "loss": -0.0061,
      "step": 1531
    },
    {
      "clip_ratio/high_max": 0.0023696925345575437,
      "clip_ratio/high_mean": 0.0009072027987713227,
      "clip_ratio/low_mean": 0.0010991566559823696,
      "clip_ratio/low_min": 9.656856491346844e-05,
      "clip_ratio/region_mean": 0.0020063594638486393,
      "epoch": 0.14298630920089367,
      "grad_norm": 0.10890711843967438,
      "learning_rate": 5e-07,
      "loss": 0.0547,
      "step": 1532
    },
    {
      "clip_ratio/high_max": 0.0019543067064660136,
      "clip_ratio/high_mean": 0.0008316786579598556,
      "clip_ratio/low_mean": 0.0011444572737673298,
      "clip_ratio/low_min": 7.787761569488794e-05,
      "clip_ratio/region_mean": 0.001976135892618913,
      "epoch": 0.14307964230089426,
      "grad_norm": 0.1412850022315979,
      "learning_rate": 5e-07,
      "loss": 0.0061,
      "step": 1533
    },
    {
      "clip_ratio/high_max": 0.002079761547065573,
      "clip_ratio/high_mean": 0.0008392063064093236,
      "clip_ratio/low_mean": 0.0011748597098630853,
      "clip_ratio/low_min": 8.045303002290893e-05,
      "clip_ratio/region_mean": 0.0020140660199103877,
      "epoch": 0.14317297540089483,
      "grad_norm": 0.10942728817462921,
      "learning_rate": 5e-07,
      "loss": 0.0617,
      "step": 1534
    },
    {
      "clip_ratio/high_max": 0.0018139632702514064,
      "clip_ratio/high_mean": 0.0007512362280976959,
      "clip_ratio/low_mean": 0.0008304119037347846,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001581648139108438,
      "epoch": 0.14326630850089542,
      "grad_norm": 0.09509874135255814,
      "learning_rate": 5e-07,
      "loss": 0.02,
      "step": 1535
    },
    {
      "clip_ratio/high_max": 0.00224372954107821,
      "clip_ratio/high_mean": 0.0009275160555262119,
      "clip_ratio/low_mean": 0.001003328377919388,
      "clip_ratio/low_min": 0.00010035008381237276,
      "clip_ratio/region_mean": 0.0019308444352645893,
      "epoch": 0.143359641600896,
      "grad_norm": 0.1463407576084137,
      "learning_rate": 5e-07,
      "loss": -0.003,
      "step": 1536
    },
    {
      "clip_ratio/high_max": 0.0019525040879670996,
      "clip_ratio/high_mean": 0.0008070391631918028,
      "clip_ratio/low_mean": 0.001157094402515213,
      "clip_ratio/low_min": 0.0001223288832079561,
      "clip_ratio/region_mean": 0.0019641336039057933,
      "epoch": 0.14345297470089657,
      "grad_norm": 0.11255869269371033,
      "learning_rate": 5e-07,
      "loss": 0.0082,
      "step": 1537
    },
    {
      "clip_ratio/high_max": 0.002140965916623827,
      "clip_ratio/high_mean": 0.0008542881587345619,
      "clip_ratio/low_mean": 0.0010515540670894552,
      "clip_ratio/low_min": 1.4817449482507072e-05,
      "clip_ratio/region_mean": 0.0019058422330999747,
      "epoch": 0.14354630780089717,
      "grad_norm": 0.11107280850410461,
      "learning_rate": 5e-07,
      "loss": 0.0268,
      "step": 1538
    },
    {
      "clip_ratio/high_max": 0.0021202394091233145,
      "clip_ratio/high_mean": 0.000893575772352051,
      "clip_ratio/low_mean": 0.0009414369851583615,
      "clip_ratio/low_min": 5.7490729886922054e-05,
      "clip_ratio/region_mean": 0.0018350127429584973,
      "epoch": 0.14363964090089776,
      "grad_norm": 0.10781792551279068,
      "learning_rate": 5e-07,
      "loss": -0.0036,
      "step": 1539
    },
    {
      "clip_ratio/high_max": 0.00221089823753573,
      "clip_ratio/high_mean": 0.0008854350726323901,
      "clip_ratio/low_mean": 0.0012209873675601557,
      "clip_ratio/low_min": 7.477324106730521e-05,
      "clip_ratio/region_mean": 0.0021064224492874928,
      "epoch": 0.14373297400089832,
      "grad_norm": 1.6525875329971313,
      "learning_rate": 5e-07,
      "loss": 0.0485,
      "step": 1540
    },
    {
      "clip_ratio/high_max": 0.0020323668541095685,
      "clip_ratio/high_mean": 0.0008081061314442195,
      "clip_ratio/low_mean": 0.0011345924940542318,
      "clip_ratio/low_min": 0.00011982508658547886,
      "clip_ratio/region_mean": 0.001942698610946536,
      "epoch": 0.14382630710089891,
      "grad_norm": 0.3063213527202606,
      "learning_rate": 5e-07,
      "loss": 0.0549,
      "step": 1541
    },
    {
      "clip_ratio/high_max": 0.0022972993028815836,
      "clip_ratio/high_mean": 0.0008842751813062932,
      "clip_ratio/low_mean": 0.0011266967121628113,
      "clip_ratio/low_min": 6.48172790533863e-05,
      "clip_ratio/region_mean": 0.002010971882555168,
      "epoch": 0.1439196402008995,
      "grad_norm": 0.1363879144191742,
      "learning_rate": 5e-07,
      "loss": 0.0187,
      "step": 1542
    },
    {
      "clip_ratio/high_max": 0.002167943093809299,
      "clip_ratio/high_mean": 0.0008894404254533583,
      "clip_ratio/low_mean": 0.0011113604832644342,
      "clip_ratio/low_min": 0.00022948966216063127,
      "clip_ratio/region_mean": 0.0020008009596494958,
      "epoch": 0.14401297330090007,
      "grad_norm": 0.12232199311256409,
      "learning_rate": 5e-07,
      "loss": 0.0237,
      "step": 1543
    },
    {
      "clip_ratio/high_max": 0.0018289401050424203,
      "clip_ratio/high_mean": 0.0007621798977197614,
      "clip_ratio/low_mean": 0.0010057208328362321,
      "clip_ratio/low_min": 4.878207437286619e-05,
      "clip_ratio/region_mean": 0.001767900750564877,
      "epoch": 0.14410630640090066,
      "grad_norm": 0.10553750395774841,
      "learning_rate": 5e-07,
      "loss": 0.0209,
      "step": 1544
    },
    {
      "clip_ratio/high_max": 0.0019519671041052788,
      "clip_ratio/high_mean": 0.0007773141624056734,
      "clip_ratio/low_mean": 0.0010368613438913599,
      "clip_ratio/low_min": 0.00010180211393162608,
      "clip_ratio/region_mean": 0.0018141754771932028,
      "epoch": 0.14419963950090126,
      "grad_norm": 0.11537747085094452,
      "learning_rate": 5e-07,
      "loss": 0.0502,
      "step": 1545
    },
    {
      "clip_ratio/high_max": 0.0024058057788352016,
      "clip_ratio/high_mean": 0.0009476646628172603,
      "clip_ratio/low_mean": 0.0010509993517189287,
      "clip_ratio/low_min": 8.704501124157105e-05,
      "clip_ratio/region_mean": 0.0019986640618299134,
      "epoch": 0.14429297260090182,
      "grad_norm": 0.11773722618818283,
      "learning_rate": 5e-07,
      "loss": 0.0093,
      "step": 1546
    },
    {
      "clip_ratio/high_max": 0.0019591799427871592,
      "clip_ratio/high_mean": 0.0007964147989696357,
      "clip_ratio/low_mean": 0.0010308759701729286,
      "clip_ratio/low_min": 7.773204833938507e-05,
      "clip_ratio/region_mean": 0.001827290776418522,
      "epoch": 0.1443863057009024,
      "grad_norm": 0.11130248010158539,
      "learning_rate": 5e-07,
      "loss": 0.0313,
      "step": 1547
    },
    {
      "clip_ratio/high_max": 0.0020970800760551356,
      "clip_ratio/high_mean": 0.0008679198617755901,
      "clip_ratio/low_mean": 0.0011034694325644523,
      "clip_ratio/low_min": 5.3312636737246066e-05,
      "clip_ratio/region_mean": 0.0019713893270818517,
      "epoch": 0.144479638800903,
      "grad_norm": 0.12196942418813705,
      "learning_rate": 5e-07,
      "loss": 0.0325,
      "step": 1548
    },
    {
      "clip_ratio/high_max": 0.0018473451018508058,
      "clip_ratio/high_mean": 0.0008520721958120703,
      "clip_ratio/low_mean": 0.000958059232289088,
      "clip_ratio/low_min": 8.596985117037548e-05,
      "clip_ratio/region_mean": 0.001810131419915706,
      "epoch": 0.14457297190090357,
      "grad_norm": 0.11178313940763474,
      "learning_rate": 5e-07,
      "loss": 0.0006,
      "step": 1549
    },
    {
      "clip_ratio/high_max": 0.0025395772499905434,
      "clip_ratio/high_mean": 0.0010723753366619349,
      "clip_ratio/low_mean": 0.0011434107273089467,
      "clip_ratio/low_min": 1.0820636816788465e-05,
      "clip_ratio/region_mean": 0.0022157860585139133,
      "epoch": 0.14466630500090416,
      "grad_norm": 0.11512450128793716,
      "learning_rate": 5e-07,
      "loss": -0.0023,
      "step": 1550
    },
    {
      "clip_ratio/high_max": 0.0027772134853876196,
      "clip_ratio/high_mean": 0.0011189391007064842,
      "clip_ratio/low_mean": 0.0009564021947880974,
      "clip_ratio/low_min": 6.110904905654024e-05,
      "clip_ratio/region_mean": 0.002075341297313571,
      "epoch": 0.14475963810090475,
      "grad_norm": 0.11799740046262741,
      "learning_rate": 5e-07,
      "loss": -0.0133,
      "step": 1551
    },
    {
      "clip_ratio/high_max": 0.0019888440328941215,
      "clip_ratio/high_mean": 0.0008557152914363542,
      "clip_ratio/low_mean": 0.001047921319695888,
      "clip_ratio/low_min": 0.00010821880368894199,
      "clip_ratio/region_mean": 0.0019036366174987052,
      "epoch": 0.14485297120090532,
      "grad_norm": 0.11274348199367523,
      "learning_rate": 5e-07,
      "loss": 0.0342,
      "step": 1552
    },
    {
      "clip_ratio/high_max": 0.0015809362339496147,
      "clip_ratio/high_mean": 0.000689672688167775,
      "clip_ratio/low_mean": 0.0009651065593061503,
      "clip_ratio/low_min": 5.765708010585513e-05,
      "clip_ratio/region_mean": 0.0016547792256460525,
      "epoch": 0.1449463043009059,
      "grad_norm": 0.15304572880268097,
      "learning_rate": 5e-07,
      "loss": 0.04,
      "step": 1553
    },
    {
      "clip_ratio/high_max": 0.0020405288523761556,
      "clip_ratio/high_mean": 0.0008189849068003241,
      "clip_ratio/low_mean": 0.001138227549745352,
      "clip_ratio/low_min": 0.00012789233096555108,
      "clip_ratio/region_mean": 0.001957212451088708,
      "epoch": 0.1450396374009065,
      "grad_norm": 0.10923785716295242,
      "learning_rate": 5e-07,
      "loss": 0.0524,
      "step": 1554
    },
    {
      "clip_ratio/high_max": 0.0023029644289636053,
      "clip_ratio/high_mean": 0.0009411621358594857,
      "clip_ratio/low_mean": 0.001129970502006472,
      "clip_ratio/low_min": 9.833773310674587e-05,
      "clip_ratio/region_mean": 0.0020711326142190956,
      "epoch": 0.1451329705009071,
      "grad_norm": 0.10467445105314255,
      "learning_rate": 5e-07,
      "loss": 0.014,
      "step": 1555
    },
    {
      "clip_ratio/high_max": 0.0023427587366313674,
      "clip_ratio/high_mean": 0.0009113574124057777,
      "clip_ratio/low_mean": 0.0009048566134879366,
      "clip_ratio/low_min": 4.8360792789026164e-05,
      "clip_ratio/region_mean": 0.0018162140222557355,
      "epoch": 0.14522630360090766,
      "grad_norm": 0.10763195157051086,
      "learning_rate": 5e-07,
      "loss": -0.0241,
      "step": 1556
    },
    {
      "clip_ratio/high_max": 0.002445312071358785,
      "clip_ratio/high_mean": 0.0009239369719580282,
      "clip_ratio/low_mean": 0.0008634666482976172,
      "clip_ratio/low_min": 3.7934242755000014e-05,
      "clip_ratio/region_mean": 0.0017874036129796878,
      "epoch": 0.14531963670090825,
      "grad_norm": 0.10820097476243973,
      "learning_rate": 5e-07,
      "loss": 0.002,
      "step": 1557
    },
    {
      "clip_ratio/high_max": 0.0019355660151632037,
      "clip_ratio/high_mean": 0.0008233819753513671,
      "clip_ratio/low_mean": 0.0010273466796206776,
      "clip_ratio/low_min": 7.097889647411648e-05,
      "clip_ratio/region_mean": 0.0018507286586100236,
      "epoch": 0.14541296980090884,
      "grad_norm": 0.11883153021335602,
      "learning_rate": 5e-07,
      "loss": 0.0052,
      "step": 1558
    },
    {
      "clip_ratio/high_max": 0.0022845338462502696,
      "clip_ratio/high_mean": 0.0008866464322636602,
      "clip_ratio/low_mean": 0.0011263287815381773,
      "clip_ratio/low_min": 3.801105231104884e-05,
      "clip_ratio/region_mean": 0.0020129752228967845,
      "epoch": 0.1455063029009094,
      "grad_norm": 0.11932133883237839,
      "learning_rate": 5e-07,
      "loss": 0.0495,
      "step": 1559
    },
    {
      "clip_ratio/high_max": 0.002456021757097915,
      "clip_ratio/high_mean": 0.0009696063589217374,
      "clip_ratio/low_mean": 0.0012303569164942019,
      "clip_ratio/low_min": 7.068003014865099e-05,
      "clip_ratio/region_mean": 0.002199963237217162,
      "epoch": 0.14559963600091,
      "grad_norm": 0.12180691212415695,
      "learning_rate": 5e-07,
      "loss": 0.0012,
      "step": 1560
    },
    {
      "clip_ratio/high_max": 0.0019265731607447378,
      "clip_ratio/high_mean": 0.000850885944601032,
      "clip_ratio/low_mean": 0.0010893719481828157,
      "clip_ratio/low_min": 6.455057882703841e-05,
      "clip_ratio/region_mean": 0.001940257876412943,
      "epoch": 0.1456929691009106,
      "grad_norm": 0.12028566747903824,
      "learning_rate": 5e-07,
      "loss": 0.0315,
      "step": 1561
    },
    {
      "clip_ratio/high_max": 0.0019269200929556973,
      "clip_ratio/high_mean": 0.0008384443008253584,
      "clip_ratio/low_mean": 0.0009947981452569366,
      "clip_ratio/low_min": 0.00013205836967244977,
      "clip_ratio/region_mean": 0.001833242436987348,
      "epoch": 0.14578630220091116,
      "grad_norm": 0.11781500279903412,
      "learning_rate": 5e-07,
      "loss": 0.0497,
      "step": 1562
    },
    {
      "clip_ratio/high_max": 0.0020010215339425486,
      "clip_ratio/high_mean": 0.0007975434400577797,
      "clip_ratio/low_mean": 0.0010255976721964544,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0018231411086162552,
      "epoch": 0.14587963530091175,
      "grad_norm": 0.09720709919929504,
      "learning_rate": 5e-07,
      "loss": 0.0036,
      "step": 1563
    },
    {
      "clip_ratio/high_max": 0.002193326268752571,
      "clip_ratio/high_mean": 0.0008151596866809996,
      "clip_ratio/low_mean": 0.0011544080680323532,
      "clip_ratio/low_min": 0.00014912755887053208,
      "clip_ratio/region_mean": 0.001969567747437395,
      "epoch": 0.14597296840091234,
      "grad_norm": 0.11153962463140488,
      "learning_rate": 5e-07,
      "loss": 0.0168,
      "step": 1564
    },
    {
      "clip_ratio/high_max": 0.0021144711936358362,
      "clip_ratio/high_mean": 0.0008571105245209765,
      "clip_ratio/low_mean": 0.0010237514488835586,
      "clip_ratio/low_min": 9.40040063142078e-05,
      "clip_ratio/region_mean": 0.0018808620079653338,
      "epoch": 0.1460663015009129,
      "grad_norm": 0.12389111518859863,
      "learning_rate": 5e-07,
      "loss": 0.0046,
      "step": 1565
    },
    {
      "clip_ratio/high_max": 0.0020804832711291965,
      "clip_ratio/high_mean": 0.0009302972757723182,
      "clip_ratio/low_mean": 0.0010667543574527372,
      "clip_ratio/low_min": 6.348876377160195e-05,
      "clip_ratio/region_mean": 0.001997051622311119,
      "epoch": 0.1461596346009135,
      "grad_norm": 0.12115680426359177,
      "learning_rate": 5e-07,
      "loss": 0.019,
      "step": 1566
    },
    {
      "clip_ratio/high_max": 0.0020933100386173464,
      "clip_ratio/high_mean": 0.0008651475072838366,
      "clip_ratio/low_mean": 0.0010898868349613622,
      "clip_ratio/low_min": 3.90130535379285e-05,
      "clip_ratio/region_mean": 0.0019550343131413683,
      "epoch": 0.1462529677009141,
      "grad_norm": 0.22908516228199005,
      "learning_rate": 5e-07,
      "loss": 0.031,
      "step": 1567
    },
    {
      "clip_ratio/high_max": 0.0020358859983389266,
      "clip_ratio/high_mean": 0.0008946135221776785,
      "clip_ratio/low_mean": 0.0011990652310487349,
      "clip_ratio/low_min": 0.00019230944508308312,
      "clip_ratio/region_mean": 0.0020936787623213604,
      "epoch": 0.14634630080091465,
      "grad_norm": 0.11620750278234482,
      "learning_rate": 5e-07,
      "loss": 0.0324,
      "step": 1568
    },
    {
      "clip_ratio/high_max": 0.0017732167543726973,
      "clip_ratio/high_mean": 0.0007737759124211152,
      "clip_ratio/low_mean": 0.0010052521338366205,
      "clip_ratio/low_min": 0.00015595924924127758,
      "clip_ratio/region_mean": 0.0017790280689951032,
      "completions/clipped_ratio": 0.013096400669642905,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4089.0,
      "completions/mean_length": 607.4140014648438,
      "completions/mean_terminated_length": 561.1198120117188,
      "completions/min_length": 5.0,
      "completions/min_terminated_length": 5.0,
      "epoch": 0.14643963390091524,
      "grad_norm": 11.481955528259277,
      "learning_rate": 5e-07,
      "loss": 0.0372,
      "num_tokens": 1140012876.0,
      "reward": 0.6108311414718628,
      "reward_std": 0.186237171292305,
      "rewards/simpleverify_reward/mean": 0.6108311414718628,
      "rewards/simpleverify_reward/std": 0.48756375908851624,
      "step": 1569
    },
    {
      "clip_ratio/high_max": 0.0022004945130902342,
      "clip_ratio/high_mean": 0.0008182924084394472,
      "clip_ratio/low_mean": 0.0008632640456198715,
      "clip_ratio/low_min": 3.1713580938230734e-05,
      "clip_ratio/region_mean": 0.0016815564595162868,
      "epoch": 0.14653296700091584,
      "grad_norm": 291.79632568359375,
      "learning_rate": 5e-07,
      "loss": 0.6219,
      "step": 1570
    },
    {
      "clip_ratio/high_max": 0.002549530367105035,
      "clip_ratio/high_mean": 0.001003577066512662,
      "clip_ratio/low_mean": 0.0010257657904730877,
      "clip_ratio/low_min": 5.636765490635298e-05,
      "clip_ratio/region_mean": 0.0020293428751756437,
      "epoch": 0.1466263001009164,
      "grad_norm": 4526.4951171875,
      "learning_rate": 5e-07,
      "loss": 24.7551,
      "step": 1571
    },
    {
      "clip_ratio/high_max": 0.002274598395160865,
      "clip_ratio/high_mean": 0.0009864213952823775,
      "clip_ratio/low_mean": 0.0011367302031430881,
      "clip_ratio/low_min": 6.89318731019739e-05,
      "clip_ratio/region_mean": 0.002123151622072328,
      "epoch": 0.146719633200917,
      "grad_norm": 31.206111907958984,
      "learning_rate": 5e-07,
      "loss": 0.0218,
      "step": 1572
    },
    {
      "clip_ratio/high_max": 0.002391522764810361,
      "clip_ratio/high_mean": 0.0009931474942277418,
      "clip_ratio/low_mean": 0.0007223213051474886,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001715468788461294,
      "epoch": 0.14681296630091759,
      "grad_norm": 93.17610931396484,
      "learning_rate": 5e-07,
      "loss": 1.8064,
      "step": 1573
    },
    {
      "clip_ratio/high_max": 0.0024441906025458593,
      "clip_ratio/high_mean": 0.0009498649064880738,
      "clip_ratio/low_mean": 0.0008315985160152195,
      "clip_ratio/low_min": 6.4523486798862e-05,
      "clip_ratio/region_mean": 0.001781463473889744,
      "epoch": 0.14690629940091818,
      "grad_norm": 0.22232964634895325,
      "learning_rate": 5e-07,
      "loss": 0.0431,
      "step": 1574
    },
    {
      "clip_ratio/high_max": 0.001912409865326481,
      "clip_ratio/high_mean": 0.0008501543106831377,
      "clip_ratio/low_mean": 0.0008976941662695026,
      "clip_ratio/low_min": 8.767002145759761e-05,
      "clip_ratio/region_mean": 0.0017478484624007251,
      "epoch": 0.14699963250091874,
      "grad_norm": 0.6772211790084839,
      "learning_rate": 5e-07,
      "loss": 0.4473,
      "step": 1575
    },
    {
      "clip_ratio/high_max": 0.00246582366162329,
      "clip_ratio/high_mean": 0.0009148233930318383,
      "clip_ratio/low_mean": 0.0009497581886535045,
      "clip_ratio/low_min": 9.680692164693028e-05,
      "clip_ratio/region_mean": 0.0018645816016942263,
      "epoch": 0.14709296560091933,
      "grad_norm": 0.6396831274032593,
      "learning_rate": 5e-07,
      "loss": 0.0453,
      "step": 1576
    },
    {
      "clip_ratio/high_max": 0.0026185179558524396,
      "clip_ratio/high_mean": 0.0009517264152236748,
      "clip_ratio/low_mean": 0.0008469359590890235,
      "clip_ratio/low_min": 3.141791057714727e-05,
      "clip_ratio/region_mean": 0.0017986624297918752,
      "epoch": 0.14718629870091993,
      "grad_norm": 616.4594116210938,
      "learning_rate": 5e-07,
      "loss": 0.7283,
      "step": 1577
    },
    {
      "clip_ratio/high_max": 0.002865005357307382,
      "clip_ratio/high_mean": 0.001006916621918208,
      "clip_ratio/low_mean": 0.001033078984619351,
      "clip_ratio/low_min": 9.18213881959673e-05,
      "clip_ratio/region_mean": 0.002039995597442612,
      "epoch": 0.1472796318009205,
      "grad_norm": 0.4053150713443756,
      "learning_rate": 5e-07,
      "loss": 0.0449,
      "step": 1578
    },
    {
      "clip_ratio/high_max": 0.0021963505969324615,
      "clip_ratio/high_mean": 0.0008334204958373448,
      "clip_ratio/low_mean": 0.0008814305347186746,
      "clip_ratio/low_min": 8.343981426151004e-05,
      "clip_ratio/region_mean": 0.0017148509869002737,
      "epoch": 0.14737296490092108,
      "grad_norm": 25221748.0,
      "learning_rate": 5e-07,
      "loss": 29876.7461,
      "step": 1579
    },
    {
      "clip_ratio/high_max": 0.002353323856368661,
      "clip_ratio/high_mean": 0.0009732201833685394,
      "clip_ratio/low_mean": 0.0009216564794769511,
      "clip_ratio/low_min": 2.4641695745231118e-05,
      "clip_ratio/region_mean": 0.001894876673759427,
      "epoch": 0.14746629800092168,
      "grad_norm": 0.12115001678466797,
      "learning_rate": 5e-07,
      "loss": 0.0102,
      "step": 1580
    },
    {
      "clip_ratio/high_max": 0.0022070765880926047,
      "clip_ratio/high_mean": 0.0008372922620765166,
      "clip_ratio/low_mean": 0.0008736131312616635,
      "clip_ratio/low_min": 8.864259780239081e-05,
      "clip_ratio/region_mean": 0.001710905387881212,
      "epoch": 0.14755963110092224,
      "grad_norm": 6394.85693359375,
      "learning_rate": 5e-07,
      "loss": 1.7856,
      "step": 1581
    },
    {
      "clip_ratio/high_max": 0.002095962583553046,
      "clip_ratio/high_mean": 0.0008189893760572886,
      "clip_ratio/low_mean": 0.0009026830994116608,
      "clip_ratio/low_min": 4.7725577132951e-05,
      "clip_ratio/region_mean": 0.001721672510029748,
      "epoch": 0.14765296420092283,
      "grad_norm": 0.111531563103199,
      "learning_rate": 5e-07,
      "loss": 0.0383,
      "step": 1582
    },
    {
      "clip_ratio/high_max": 0.0021685095416614786,
      "clip_ratio/high_mean": 0.000886269999682554,
      "clip_ratio/low_mean": 0.0008478013623971492,
      "clip_ratio/low_min": 9.926272468874231e-05,
      "clip_ratio/region_mean": 0.0017340713820885867,
      "epoch": 0.14774629730092342,
      "grad_norm": 1.9485554695129395,
      "learning_rate": 5e-07,
      "loss": -0.0059,
      "step": 1583
    },
    {
      "clip_ratio/high_max": 0.002006289862038102,
      "clip_ratio/high_mean": 0.0007617952323926147,
      "clip_ratio/low_mean": 0.0009023102575156372,
      "clip_ratio/low_min": 7.543917763541685e-05,
      "clip_ratio/region_mean": 0.001664105468080379,
      "epoch": 0.147839630400924,
      "grad_norm": 0.11411027610301971,
      "learning_rate": 5e-07,
      "loss": 0.0685,
      "step": 1584
    },
    {
      "clip_ratio/high_max": 0.002110985129547771,
      "clip_ratio/high_mean": 0.0009225277681252919,
      "clip_ratio/low_mean": 0.00097034876307589,
      "clip_ratio/low_min": 4.0138444092008285e-05,
      "clip_ratio/region_mean": 0.0018928765348391607,
      "epoch": 0.14793296350092458,
      "grad_norm": 0.12071401625871658,
      "learning_rate": 5e-07,
      "loss": 0.0412,
      "step": 1585
    },
    {
      "clip_ratio/high_max": 0.002337812511541415,
      "clip_ratio/high_mean": 0.000922401017305674,
      "clip_ratio/low_mean": 0.0008942735439632088,
      "clip_ratio/low_min": 7.829265359760029e-05,
      "clip_ratio/region_mean": 0.0018166745612688828,
      "epoch": 0.14802629660092517,
      "grad_norm": 608.1509399414062,
      "learning_rate": 5e-07,
      "loss": 0.2714,
      "step": 1586
    },
    {
      "clip_ratio/high_max": 0.002437383089272771,
      "clip_ratio/high_mean": 0.001067565159246442,
      "clip_ratio/low_mean": 0.0008479281241307035,
      "clip_ratio/low_min": 6.693133855151245e-05,
      "clip_ratio/region_mean": 0.0019154932961100712,
      "epoch": 0.14811962970092574,
      "grad_norm": 1.6018788814544678,
      "learning_rate": 5e-07,
      "loss": 0.0438,
      "step": 1587
    },
    {
      "clip_ratio/high_max": 0.00248846518661594,
      "clip_ratio/high_mean": 0.0009797609491215553,
      "clip_ratio/low_mean": 0.0008829779690131545,
      "clip_ratio/low_min": 3.453779027040582e-05,
      "clip_ratio/region_mean": 0.0018627388999448158,
      "epoch": 0.14821296280092633,
      "grad_norm": 0.10569558292627335,
      "learning_rate": 5e-07,
      "loss": 0.0141,
      "step": 1588
    },
    {
      "clip_ratio/high_max": 0.0025841786700766534,
      "clip_ratio/high_mean": 0.0009908577194437385,
      "clip_ratio/low_mean": 0.000838070851386874,
      "clip_ratio/low_min": 5.060918556409888e-05,
      "clip_ratio/region_mean": 0.0018289285580976866,
      "epoch": 0.14830629590092692,
      "grad_norm": 0.11682053655385971,
      "learning_rate": 5e-07,
      "loss": 0.0384,
      "step": 1589
    },
    {
      "clip_ratio/high_max": 0.0022716911989846267,
      "clip_ratio/high_mean": 0.00093676760661765,
      "clip_ratio/low_mean": 0.0009834636584855616,
      "clip_ratio/low_min": 0.00014254090729082236,
      "clip_ratio/region_mean": 0.0019202312469133176,
      "epoch": 0.14839962900092749,
      "grad_norm": 0.1362512707710266,
      "learning_rate": 5e-07,
      "loss": 0.0504,
      "step": 1590
    },
    {
      "clip_ratio/high_max": 0.002175605233787792,
      "clip_ratio/high_mean": 0.0010124201453436399,
      "clip_ratio/low_mean": 0.000932477084461425,
      "clip_ratio/low_min": 5.4629481383017264e-05,
      "clip_ratio/region_mean": 0.0019448972634563688,
      "epoch": 0.14849296210092808,
      "grad_norm": 0.12337587028741837,
      "learning_rate": 5e-07,
      "loss": 0.0054,
      "step": 1591
    },
    {
      "clip_ratio/high_max": 0.0026230055154883303,
      "clip_ratio/high_mean": 0.0011341470235493034,
      "clip_ratio/low_mean": 0.0009866062318906188,
      "clip_ratio/low_min": 9.219030562235275e-05,
      "clip_ratio/region_mean": 0.002120753277267795,
      "epoch": 0.14858629520092867,
      "grad_norm": 0.11643054336309433,
      "learning_rate": 5e-07,
      "loss": 0.0141,
      "step": 1592
    },
    {
      "clip_ratio/high_max": 0.002427253104542615,
      "clip_ratio/high_mean": 0.0010035279447038192,
      "clip_ratio/low_mean": 0.0008309748773172032,
      "clip_ratio/low_min": 1.4966474736866076e-05,
      "clip_ratio/region_mean": 0.001834502792917192,
      "epoch": 0.14867962830092923,
      "grad_norm": 0.11871056258678436,
      "learning_rate": 5e-07,
      "loss": -0.0323,
      "step": 1593
    },
    {
      "clip_ratio/high_max": 0.002607703259855043,
      "clip_ratio/high_mean": 0.0009722934373712633,
      "clip_ratio/low_mean": 0.001036464498611167,
      "clip_ratio/low_min": 9.582613347447477e-05,
      "clip_ratio/region_mean": 0.002008757939620409,
      "epoch": 0.14877296140092983,
      "grad_norm": 0.12232375144958496,
      "learning_rate": 5e-07,
      "loss": 0.025,
      "step": 1594
    },
    {
      "clip_ratio/high_max": 0.0022452728226198815,
      "clip_ratio/high_mean": 0.0008736919680814026,
      "clip_ratio/low_mean": 0.0009342181492684176,
      "clip_ratio/low_min": 4.494527638598811e-05,
      "clip_ratio/region_mean": 0.001807910120987799,
      "epoch": 0.14886629450093042,
      "grad_norm": 0.12030697613954544,
      "learning_rate": 5e-07,
      "loss": 0.0298,
      "step": 1595
    },
    {
      "clip_ratio/high_max": 0.0022726812821929343,
      "clip_ratio/high_mean": 0.0009076148489839397,
      "clip_ratio/low_mean": 0.00098904361766472,
      "clip_ratio/low_min": 7.835019914637087e-05,
      "clip_ratio/region_mean": 0.0018966584757436067,
      "epoch": 0.148959627600931,
      "grad_norm": 0.14236004650592804,
      "learning_rate": 5e-07,
      "loss": 0.037,
      "step": 1596
    },
    {
      "clip_ratio/high_max": 0.0019770802682614885,
      "clip_ratio/high_mean": 0.0008069185496424325,
      "clip_ratio/low_mean": 0.0010896792773564812,
      "clip_ratio/low_min": 9.680805669631809e-05,
      "clip_ratio/region_mean": 0.0018965978815685958,
      "epoch": 0.14905296070093157,
      "grad_norm": 0.16019587218761444,
      "learning_rate": 5e-07,
      "loss": 0.0374,
      "step": 1597
    },
    {
      "clip_ratio/high_max": 0.0024652097272337414,
      "clip_ratio/high_mean": 0.0009674514167272719,
      "clip_ratio/low_mean": 0.0008628276782474131,
      "clip_ratio/low_min": 9.591980960976798e-05,
      "clip_ratio/region_mean": 0.0018302790922462009,
      "epoch": 0.14914629380093217,
      "grad_norm": 0.15268127620220184,
      "learning_rate": 5e-07,
      "loss": -0.0,
      "step": 1598
    },
    {
      "clip_ratio/high_max": 0.0021789906968479045,
      "clip_ratio/high_mean": 0.0008608336975157727,
      "clip_ratio/low_mean": 0.0010289430883858586,
      "clip_ratio/low_min": 3.4350868190813344e-05,
      "clip_ratio/region_mean": 0.001889776838652324,
      "epoch": 0.14923962690093276,
      "grad_norm": 0.719838559627533,
      "learning_rate": 5e-07,
      "loss": 0.059,
      "step": 1599
    },
    {
      "clip_ratio/high_max": 0.0022841406971565448,
      "clip_ratio/high_mean": 0.001033291617204668,
      "clip_ratio/low_mean": 0.001024525506181817,
      "clip_ratio/low_min": 0.0001207420300488593,
      "clip_ratio/region_mean": 0.0020578171315719374,
      "epoch": 0.14933296000093332,
      "grad_norm": 0.1993272751569748,
      "learning_rate": 5e-07,
      "loss": 0.0431,
      "step": 1600
    },
    {
      "epoch": 0.14933296000093332,
      "step": 1600,
      "total_flos": 0.0,
      "train_loss": 19.090027208828705,
      "train_runtime": 110532.8464,
      "train_samples_per_second": 12.97,
      "train_steps_per_second": 0.014
    }
  ],
  "logging_steps": 1,
  "max_steps": 1600,
  "num_input_tokens_seen": 1140012876,
  "num_train_epochs": 1,
  "save_steps": 160,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}