{
  "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": 0.013706752232142905,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4096.0,
      "completions/mean_length": 601.608154296875,
      "completions/mean_terminated_length": 553.045654296875,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 9.333310000058333e-05,
      "grad_norm": 0.1617286503314972,
      "learning_rate": 1e-06,
      "loss": 0.0659,
      "num_tokens": 80419305.0,
      "reward": 0.4935739040374756,
      "reward_std": 0.26311954855918884,
      "rewards/simpleverify_reward/mean": 0.4935738742351532,
      "rewards/simpleverify_reward/std": 0.49996092915534973,
      "step": 1
    },
    {
      "clip_ratio/high_max": 0.0021018415718572214,
      "clip_ratio/high_mean": 0.0008761105800658697,
      "clip_ratio/low_mean": 0.0006582708429050399,
      "clip_ratio/low_min": 3.986312549386639e-05,
      "clip_ratio/region_mean": 0.0015343814302468672,
      "epoch": 0.00018666620000116666,
      "grad_norm": 0.13120125234127045,
      "learning_rate": 1e-06,
      "loss": 0.0166,
      "step": 2
    },
    {
      "clip_ratio/high_max": 0.0025242570336558856,
      "clip_ratio/high_mean": 0.0010744326500571333,
      "clip_ratio/low_mean": 0.000577790844545234,
      "clip_ratio/low_min": 5.2952727401134325e-05,
      "clip_ratio/region_mean": 0.001652223498240346,
      "epoch": 0.00027999930000175,
      "grad_norm": 0.13642381131649017,
      "learning_rate": 1e-06,
      "loss": -0.0195,
      "step": 3
    },
    {
      "clip_ratio/high_max": 0.0025384860928170383,
      "clip_ratio/high_mean": 0.0010642884444678202,
      "clip_ratio/low_mean": 0.0007844070605642628,
      "clip_ratio/low_min": 6.364297132677166e-05,
      "clip_ratio/region_mean": 0.0018486955013941042,
      "epoch": 0.0003733324000023333,
      "grad_norm": 0.13279423117637634,
      "learning_rate": 1e-06,
      "loss": 0.029,
      "step": 4
    },
    {
      "clip_ratio/high_max": 0.002351232928049285,
      "clip_ratio/high_mean": 0.0009795452569960617,
      "clip_ratio/low_mean": 0.000770336386267445,
      "clip_ratio/low_min": 7.805315362929832e-05,
      "clip_ratio/region_mean": 0.0017498816378065385,
      "epoch": 0.0004666655000029167,
      "grad_norm": 0.1236974447965622,
      "learning_rate": 1e-06,
      "loss": 0.0171,
      "step": 5
    },
    {
      "clip_ratio/high_max": 0.00210517428786261,
      "clip_ratio/high_mean": 0.0010023075574281393,
      "clip_ratio/low_mean": 0.0011638228534138761,
      "clip_ratio/low_min": 0.0002580384380053147,
      "clip_ratio/region_mean": 0.002166130449040793,
      "epoch": 0.0005599986000035,
      "grad_norm": 0.12330015003681183,
      "learning_rate": 1e-06,
      "loss": 0.0276,
      "step": 6
    },
    {
      "clip_ratio/high_max": 0.002245760704681743,
      "clip_ratio/high_mean": 0.0010316514126316179,
      "clip_ratio/low_mean": 0.001184837798064109,
      "clip_ratio/low_min": 0.00031664362677474855,
      "clip_ratio/region_mean": 0.002216489185229875,
      "epoch": 0.0006533317000040833,
      "grad_norm": 0.13061660528182983,
      "learning_rate": 1e-06,
      "loss": 0.0615,
      "step": 7
    },
    {
      "clip_ratio/high_max": 0.002292564146046061,
      "clip_ratio/high_mean": 0.0010635452599672135,
      "clip_ratio/low_mean": 0.0011019938629033277,
      "clip_ratio/low_min": 0.000150440389461437,
      "clip_ratio/region_mean": 0.0021655391246895306,
      "epoch": 0.0007466648000046666,
      "grad_norm": 0.12682916224002838,
      "learning_rate": 1e-06,
      "loss": 0.0411,
      "step": 8
    },
    {
      "clip_ratio/high_max": 0.002415546106931288,
      "clip_ratio/high_mean": 0.0010379563664173475,
      "clip_ratio/low_mean": 0.0010673627039068379,
      "clip_ratio/low_min": 0.0001500330990893417,
      "clip_ratio/region_mean": 0.002105319101247005,
      "epoch": 0.00083999790000525,
      "grad_norm": 0.12642963230609894,
      "learning_rate": 1e-06,
      "loss": 0.0212,
      "step": 9
    },
    {
      "clip_ratio/high_max": 0.0022386027485481463,
      "clip_ratio/high_mean": 0.0010087977134389803,
      "clip_ratio/low_mean": 0.001090410052711377,
      "clip_ratio/low_min": 0.0001997013214349863,
      "clip_ratio/region_mean": 0.0020992077188566327,
      "epoch": 0.0009333310000058334,
      "grad_norm": 0.12079668790102005,
      "learning_rate": 1e-06,
      "loss": 0.0252,
      "step": 10
    },
    {
      "clip_ratio/high_max": 0.0022823772014817223,
      "clip_ratio/high_mean": 0.0010938989689748269,
      "clip_ratio/low_mean": 0.001060018928910722,
      "clip_ratio/low_min": 0.00016260559914371697,
      "clip_ratio/region_mean": 0.002153917906980496,
      "epoch": 0.0010266641000064166,
      "grad_norm": 0.13344547152519226,
      "learning_rate": 1e-06,
      "loss": -0.0337,
      "step": 11
    },
    {
      "clip_ratio/high_max": 0.0023792159336153418,
      "clip_ratio/high_mean": 0.0011063774581998587,
      "clip_ratio/low_mean": 0.001029559462040197,
      "clip_ratio/low_min": 0.0001911046219902346,
      "clip_ratio/region_mean": 0.0021359368911362253,
      "epoch": 0.001119997200007,
      "grad_norm": 0.12550796568393707,
      "learning_rate": 1e-06,
      "loss": 0.0236,
      "step": 12
    },
    {
      "clip_ratio/high_max": 0.0021791565377498046,
      "clip_ratio/high_mean": 0.0010023262584581971,
      "clip_ratio/low_mean": 0.001116699004342081,
      "clip_ratio/low_min": 0.00015036796776257688,
      "clip_ratio/region_mean": 0.0021190252009546384,
      "epoch": 0.0012133303000075833,
      "grad_norm": 0.10936053842306137,
      "learning_rate": 1e-06,
      "loss": 0.0252,
      "step": 13
    },
    {
      "clip_ratio/high_max": 0.002366712418734096,
      "clip_ratio/high_mean": 0.0010922391484200489,
      "clip_ratio/low_mean": 0.0010556360975897405,
      "clip_ratio/low_min": 0.00016136068188643549,
      "clip_ratio/region_mean": 0.0021478752678376622,
      "epoch": 0.0013066634000081666,
      "grad_norm": 0.11846575140953064,
      "learning_rate": 1e-06,
      "loss": -0.0137,
      "step": 14
    },
    {
      "clip_ratio/high_max": 0.002180356503231451,
      "clip_ratio/high_mean": 0.0011556230310816318,
      "clip_ratio/low_mean": 0.0012274282853468321,
      "clip_ratio/low_min": 0.00022236318000068422,
      "clip_ratio/region_mean": 0.0023830512654967606,
      "epoch": 0.00139999650000875,
      "grad_norm": 0.13327762484550476,
      "learning_rate": 1e-06,
      "loss": -0.005,
      "step": 15
    },
    {
      "clip_ratio/high_max": 0.0025269318866776302,
      "clip_ratio/high_mean": 0.0009510802665317897,
      "clip_ratio/low_mean": 0.0011573204064916354,
      "clip_ratio/low_min": 0.0001506609914940782,
      "clip_ratio/region_mean": 0.0021084006220917217,
      "epoch": 0.0014933296000093333,
      "grad_norm": 0.1190929263830185,
      "learning_rate": 1e-06,
      "loss": 0.061,
      "step": 16
    },
    {
      "clip_ratio/high_max": 0.0024306618215632625,
      "clip_ratio/high_mean": 0.0009805159934330732,
      "clip_ratio/low_mean": 0.0010411641524115112,
      "clip_ratio/low_min": 6.725791308781481e-05,
      "clip_ratio/region_mean": 0.0020216801203787327,
      "epoch": 0.0015866627000099165,
      "grad_norm": 0.12228909134864807,
      "learning_rate": 1e-06,
      "loss": 0.0356,
      "step": 17
    },
    {
      "clip_ratio/high_max": 0.002325063502212288,
      "clip_ratio/high_mean": 0.0010392249423603062,
      "clip_ratio/low_mean": 0.0011159386403960525,
      "clip_ratio/low_min": 0.000262607077274879,
      "clip_ratio/region_mean": 0.002155163587303832,
      "epoch": 0.0016799958000105,
      "grad_norm": 0.29469606280326843,
      "learning_rate": 1e-06,
      "loss": 0.0383,
      "step": 18
    },
    {
      "clip_ratio/high_max": 0.0020973205209884327,
      "clip_ratio/high_mean": 0.0009110002392844763,
      "clip_ratio/low_mean": 0.00112293640995631,
      "clip_ratio/low_min": 0.0002131746878148988,
      "clip_ratio/region_mean": 0.0020339366019470617,
      "epoch": 0.0017733289000110833,
      "grad_norm": 0.11302761733531952,
      "learning_rate": 1e-06,
      "loss": 0.0502,
      "step": 19
    },
    {
      "clip_ratio/high_max": 0.002688774446141906,
      "clip_ratio/high_mean": 0.0012194520895718597,
      "clip_ratio/low_mean": 0.0012293192157812882,
      "clip_ratio/low_min": 0.00025207292401319137,
      "clip_ratio/region_mean": 0.002448771381750703,
      "epoch": 0.0018666620000116667,
      "grad_norm": 0.1296168863773346,
      "learning_rate": 1e-06,
      "loss": 0.0095,
      "step": 20
    },
    {
      "clip_ratio/high_max": 0.0024523598622181453,
      "clip_ratio/high_mean": 0.0010830594583239872,
      "clip_ratio/low_mean": 0.0011122717642138014,
      "clip_ratio/low_min": 8.203778361348668e-05,
      "clip_ratio/region_mean": 0.0021953312098048627,
      "epoch": 0.00195999510001225,
      "grad_norm": 0.11740437150001526,
      "learning_rate": 1e-06,
      "loss": 0.037,
      "step": 21
    },
    {
      "clip_ratio/high_max": 0.002164478093618527,
      "clip_ratio/high_mean": 0.0010168895387323573,
      "clip_ratio/low_mean": 0.001135280243033776,
      "clip_ratio/low_min": 0.00018341509257879807,
      "clip_ratio/region_mean": 0.00215216979268007,
      "epoch": 0.002053328200012833,
      "grad_norm": 0.12829430401325226,
      "learning_rate": 1e-06,
      "loss": 0.0506,
      "step": 22
    },
    {
      "clip_ratio/high_max": 0.002617655773065053,
      "clip_ratio/high_mean": 0.0011648389627225697,
      "clip_ratio/low_mean": 0.001181104267743649,
      "clip_ratio/low_min": 0.00019392528702155687,
      "clip_ratio/region_mean": 0.0023459432486561127,
      "epoch": 0.0021466613000134167,
      "grad_norm": 0.13261590898036957,
      "learning_rate": 1e-06,
      "loss": -0.0158,
      "step": 23
    },
    {
      "clip_ratio/high_max": 0.002484638462192379,
      "clip_ratio/high_mean": 0.0011100026458734646,
      "clip_ratio/low_mean": 0.0011723230418283492,
      "clip_ratio/low_min": 0.00020529584980977233,
      "clip_ratio/region_mean": 0.0022823256804258563,
      "epoch": 0.002239994400014,
      "grad_norm": 0.12374509125947952,
      "learning_rate": 1e-06,
      "loss": -0.0211,
      "step": 24
    },
    {
      "clip_ratio/high_max": 0.002413399124634452,
      "clip_ratio/high_mean": 0.0010723094710556325,
      "clip_ratio/low_mean": 0.0010932834193226881,
      "clip_ratio/low_min": 0.0001882707147160545,
      "clip_ratio/region_mean": 0.0021655928358086385,
      "epoch": 0.002333327500014583,
      "grad_norm": 0.12279490381479263,
      "learning_rate": 1e-06,
      "loss": 0.0228,
      "step": 25
    },
    {
      "clip_ratio/high_max": 0.0025048256866284646,
      "clip_ratio/high_mean": 0.0011354289417795371,
      "clip_ratio/low_mean": 0.001106794576116954,
      "clip_ratio/low_min": 0.00020337846490292577,
      "clip_ratio/region_mean": 0.0022422235415433533,
      "epoch": 0.0024266606000151666,
      "grad_norm": 0.11415532231330872,
      "learning_rate": 1e-06,
      "loss": -0.034,
      "step": 26
    },
    {
      "clip_ratio/high_max": 0.0025189682783093303,
      "clip_ratio/high_mean": 0.0010854579959413968,
      "clip_ratio/low_mean": 0.0011868625442730263,
      "clip_ratio/low_min": 0.00022448066738434136,
      "clip_ratio/region_mean": 0.0022723205474903807,
      "epoch": 0.00251999370001575,
      "grad_norm": 0.12822604179382324,
      "learning_rate": 1e-06,
      "loss": -0.0113,
      "step": 27
    },
    {
      "clip_ratio/high_max": 0.0028029351378791034,
      "clip_ratio/high_mean": 0.0012144052852818277,
      "clip_ratio/low_mean": 0.00119122615615197,
      "clip_ratio/low_min": 9.276076889364049e-05,
      "clip_ratio/region_mean": 0.0024056313632172532,
      "epoch": 0.002613326800016333,
      "grad_norm": 0.13119523227214813,
      "learning_rate": 1e-06,
      "loss": -0.0247,
      "step": 28
    },
    {
      "clip_ratio/high_max": 0.0023764651850797236,
      "clip_ratio/high_mean": 0.0010464549268363044,
      "clip_ratio/low_mean": 0.0011260242499702144,
      "clip_ratio/low_min": 0.00011438582987466361,
      "clip_ratio/region_mean": 0.002172479151340667,
      "epoch": 0.0027066599000169166,
      "grad_norm": 0.12753500044345856,
      "learning_rate": 1e-06,
      "loss": 0.0274,
      "step": 29
    },
    {
      "clip_ratio/high_max": 0.002228257624665275,
      "clip_ratio/high_mean": 0.000980409078692901,
      "clip_ratio/low_mean": 0.0010730762915045489,
      "clip_ratio/low_min": 0.00014890969669068,
      "clip_ratio/region_mean": 0.0020534853829303756,
      "epoch": 0.0027999930000175,
      "grad_norm": 0.11440373957157135,
      "learning_rate": 1e-06,
      "loss": 0.0488,
      "step": 30
    },
    {
      "clip_ratio/high_max": 0.0028200717933941633,
      "clip_ratio/high_mean": 0.0012030283360218164,
      "clip_ratio/low_mean": 0.0012063452377333306,
      "clip_ratio/low_min": 0.00022382396673492622,
      "clip_ratio/region_mean": 0.002409373570117168,
      "epoch": 0.002893326100018083,
      "grad_norm": 0.12738914787769318,
      "learning_rate": 1e-06,
      "loss": 0.0389,
      "step": 31
    },
    {
      "clip_ratio/high_max": 0.0023557710701425094,
      "clip_ratio/high_mean": 0.0011099687735622865,
      "clip_ratio/low_mean": 0.0012141624465584755,
      "clip_ratio/low_min": 0.0001383327376061061,
      "clip_ratio/region_mean": 0.0023241312301252037,
      "epoch": 0.0029866592000186666,
      "grad_norm": 0.1252320408821106,
      "learning_rate": 1e-06,
      "loss": 0.0197,
      "step": 32
    },
    {
      "clip_ratio/high_max": 0.002819161250954494,
      "clip_ratio/high_mean": 0.0012134340831835289,
      "clip_ratio/low_mean": 0.001090383291739272,
      "clip_ratio/low_min": 0.00010541199026192771,
      "clip_ratio/region_mean": 0.002303817331267055,
      "epoch": 0.00307999230001925,
      "grad_norm": 0.1348554641008377,
      "learning_rate": 1e-06,
      "loss": -0.0516,
      "step": 33
    },
    {
      "clip_ratio/high_max": 0.002043310392764397,
      "clip_ratio/high_mean": 0.000896439072676003,
      "clip_ratio/low_mean": 0.0010872985585592687,
      "clip_ratio/low_min": 0.00016304017844959162,
      "clip_ratio/region_mean": 0.0019837376166833565,
      "epoch": 0.003173325400019833,
      "grad_norm": 0.1039976105093956,
      "learning_rate": 1e-06,
      "loss": 0.0273,
      "step": 34
    },
    {
      "clip_ratio/high_max": 0.0020466843379836064,
      "clip_ratio/high_mean": 0.0009615424060029909,
      "clip_ratio/low_mean": 0.0010886559557548026,
      "clip_ratio/low_min": 0.0002417429041088326,
      "clip_ratio/region_mean": 0.0020501983308349736,
      "epoch": 0.0032666585000204165,
      "grad_norm": 0.12059943377971649,
      "learning_rate": 1e-06,
      "loss": -0.0128,
      "step": 35
    },
    {
      "clip_ratio/high_max": 0.002565672344644554,
      "clip_ratio/high_mean": 0.001127321447711438,
      "clip_ratio/low_mean": 0.0012912679703731555,
      "clip_ratio/low_min": 0.0002091407413900015,
      "clip_ratio/region_mean": 0.0024185894362744875,
      "epoch": 0.003359991600021,
      "grad_norm": 0.12734465301036835,
      "learning_rate": 1e-06,
      "loss": 0.0197,
      "step": 36
    },
    {
      "clip_ratio/high_max": 0.002476813635439612,
      "clip_ratio/high_mean": 0.0011007639332092367,
      "clip_ratio/low_mean": 0.00113988334487658,
      "clip_ratio/low_min": 0.00017671908517513657,
      "clip_ratio/region_mean": 0.0022406472635339014,
      "epoch": 0.0034533247000215835,
      "grad_norm": 0.12069344520568848,
      "learning_rate": 1e-06,
      "loss": -0.0171,
      "step": 37
    },
    {
      "clip_ratio/high_max": 0.002689410546736326,
      "clip_ratio/high_mean": 0.001120532033382915,
      "clip_ratio/low_mean": 0.0012245463603903772,
      "clip_ratio/low_min": 0.0001022342685246258,
      "clip_ratio/region_mean": 0.002345078391954303,
      "epoch": 0.0035466578000221665,
      "grad_norm": 0.12638184428215027,
      "learning_rate": 1e-06,
      "loss": 0.0294,
      "step": 38
    },
    {
      "clip_ratio/high_max": 0.0025230765459127724,
      "clip_ratio/high_mean": 0.0010956735313811805,
      "clip_ratio/low_mean": 0.0011703356758516748,
      "clip_ratio/low_min": 0.00012289282949495828,
      "clip_ratio/region_mean": 0.002266009214508813,
      "epoch": 0.00363999090002275,
      "grad_norm": 0.1270855963230133,
      "learning_rate": 1e-06,
      "loss": 0.0253,
      "step": 39
    },
    {
      "clip_ratio/high_max": 0.0021315785343176685,
      "clip_ratio/high_mean": 0.0009402183604834136,
      "clip_ratio/low_mean": 0.0013044903535046615,
      "clip_ratio/low_min": 0.0002609282209959929,
      "clip_ratio/region_mean": 0.0022447087758337148,
      "epoch": 0.0037333240000233334,
      "grad_norm": 0.12138303369283676,
      "learning_rate": 1e-06,
      "loss": 0.0693,
      "step": 40
    },
    {
      "clip_ratio/high_max": 0.0025183569159707986,
      "clip_ratio/high_mean": 0.0010974137749144575,
      "clip_ratio/low_mean": 0.0011443735093052965,
      "clip_ratio/low_min": 8.779424115346046e-05,
      "clip_ratio/region_mean": 0.002241787311504595,
      "epoch": 0.0038266571000239165,
      "grad_norm": 0.11889399588108063,
      "learning_rate": 1e-06,
      "loss": 0.0092,
      "step": 41
    },
    {
      "clip_ratio/high_max": 0.002495914122846443,
      "clip_ratio/high_mean": 0.0011805417052528355,
      "clip_ratio/low_mean": 0.0013795145059702918,
      "clip_ratio/low_min": 0.00027673101794789545,
      "clip_ratio/region_mean": 0.002560056178481318,
      "epoch": 0.0039199902000245,
      "grad_norm": 0.12510091066360474,
      "learning_rate": 1e-06,
      "loss": -0.0059,
      "step": 42
    },
    {
      "clip_ratio/high_max": 0.002712288376642391,
      "clip_ratio/high_mean": 0.00125330957598635,
      "clip_ratio/low_mean": 0.0012523688092187513,
      "clip_ratio/low_min": 0.00017083998500311282,
      "clip_ratio/region_mean": 0.002505678407032974,
      "epoch": 0.004013323300025083,
      "grad_norm": 0.12959682941436768,
      "learning_rate": 1e-06,
      "loss": -0.0066,
      "step": 43
    },
    {
      "clip_ratio/high_max": 0.0025484361685812473,
      "clip_ratio/high_mean": 0.0010958715029119048,
      "clip_ratio/low_mean": 0.001375765403281548,
      "clip_ratio/low_min": 0.00032213253143709153,
      "clip_ratio/region_mean": 0.002471636929840315,
      "epoch": 0.004106656400025666,
      "grad_norm": 0.11655577272176743,
      "learning_rate": 1e-06,
      "loss": 0.0254,
      "step": 44
    },
    {
      "clip_ratio/high_max": 0.0023462956669391133,
      "clip_ratio/high_mean": 0.0010477971027285093,
      "clip_ratio/low_mean": 0.0013792256177111994,
      "clip_ratio/low_min": 0.00016807036263344344,
      "clip_ratio/region_mean": 0.002427022722258698,
      "epoch": 0.00419998950002625,
      "grad_norm": 0.12113282829523087,
      "learning_rate": 1e-06,
      "loss": 0.0709,
      "step": 45
    },
    {
      "clip_ratio/high_max": 0.0027967745627393015,
      "clip_ratio/high_mean": 0.0010746633743110579,
      "clip_ratio/low_mean": 0.001387392152537359,
      "clip_ratio/low_min": 0.00026867872020375216,
      "clip_ratio/region_mean": 0.0024620555341243744,
      "epoch": 0.004293322600026833,
      "grad_norm": 0.12973441183567047,
      "learning_rate": 1e-06,
      "loss": 0.0028,
      "step": 46
    },
    {
      "clip_ratio/high_max": 0.00203274275190779,
      "clip_ratio/high_mean": 0.0009612759522497072,
      "clip_ratio/low_mean": 0.0012365398688416462,
      "clip_ratio/low_min": 0.00011934027997995145,
      "clip_ratio/region_mean": 0.0021978158474666998,
      "epoch": 0.004386655700027417,
      "grad_norm": 0.1308363527059555,
      "learning_rate": 1e-06,
      "loss": -0.0234,
      "step": 47
    },
    {
      "clip_ratio/high_max": 0.002577153281890787,
      "clip_ratio/high_mean": 0.0011867203211295418,
      "clip_ratio/low_mean": 0.001367621840472566,
      "clip_ratio/low_min": 0.00017779837753550964,
      "clip_ratio/region_mean": 0.002554342136136256,
      "epoch": 0.004479988800028,
      "grad_norm": 0.11871274560689926,
      "learning_rate": 1e-06,
      "loss": 0.0074,
      "step": 48
    },
    {
      "clip_ratio/high_max": 0.0024006854655453935,
      "clip_ratio/high_mean": 0.001045826658810256,
      "clip_ratio/low_mean": 0.0014536851449520327,
      "clip_ratio/low_min": 0.00029494047703337856,
      "clip_ratio/region_mean": 0.0024995118292281404,
      "epoch": 0.004573321900028583,
      "grad_norm": 0.11289472877979279,
      "learning_rate": 1e-06,
      "loss": 0.0174,
      "step": 49
    },
    {
      "clip_ratio/high_max": 0.0025945085726561956,
      "clip_ratio/high_mean": 0.0012336107247392647,
      "clip_ratio/low_mean": 0.0014252222463255748,
      "clip_ratio/low_min": 0.0002270189115733956,
      "clip_ratio/region_mean": 0.002658832920133136,
      "epoch": 0.004666655000029166,
      "grad_norm": 0.12433332204818726,
      "learning_rate": 1e-06,
      "loss": -0.0122,
      "step": 50
    },
    {
      "clip_ratio/high_max": 0.002196036595705664,
      "clip_ratio/high_mean": 0.0010196405019087251,
      "clip_ratio/low_mean": 0.0014380335196619853,
      "clip_ratio/low_min": 0.00020265601779101416,
      "clip_ratio/region_mean": 0.002457673988828901,
      "epoch": 0.00475998810002975,
      "grad_norm": 0.12437108904123306,
      "learning_rate": 1e-06,
      "loss": 0.0449,
      "step": 51
    },
    {
      "clip_ratio/high_max": 0.0025174221154884435,
      "clip_ratio/high_mean": 0.0010574618390819523,
      "clip_ratio/low_mean": 0.0013778387219645083,
      "clip_ratio/low_min": 0.00031915157933326554,
      "clip_ratio/region_mean": 0.0024353005428565666,
      "epoch": 0.004853321200030333,
      "grad_norm": 0.1645129770040512,
      "learning_rate": 1e-06,
      "loss": 0.0026,
      "step": 52
    },
    {
      "clip_ratio/high_max": 0.0022650664468528703,
      "clip_ratio/high_mean": 0.000943411752814427,
      "clip_ratio/low_mean": 0.0014958809442759957,
      "clip_ratio/low_min": 0.0003346283510836656,
      "clip_ratio/region_mean": 0.002439292708004359,
      "epoch": 0.004946654300030917,
      "grad_norm": 0.1280021220445633,
      "learning_rate": 1e-06,
      "loss": 0.0719,
      "step": 53
    },
    {
      "clip_ratio/high_max": 0.002466234873281792,
      "clip_ratio/high_mean": 0.0010917734871327411,
      "clip_ratio/low_mean": 0.0015650268687750213,
      "clip_ratio/low_min": 0.00026476419770915527,
      "clip_ratio/region_mean": 0.002656800381373614,
      "epoch": 0.0050399874000315,
      "grad_norm": 0.1332934945821762,
      "learning_rate": 1e-06,
      "loss": 0.0661,
      "step": 54
    },
    {
      "clip_ratio/high_max": 0.0022577394629479386,
      "clip_ratio/high_mean": 0.0010745605613919906,
      "clip_ratio/low_mean": 0.001415130405803211,
      "clip_ratio/low_min": 0.000132281943479029,
      "clip_ratio/region_mean": 0.002489690996299032,
      "epoch": 0.005133320500032083,
      "grad_norm": 0.11874745786190033,
      "learning_rate": 1e-06,
      "loss": 0.0106,
      "step": 55
    },
    {
      "clip_ratio/high_max": 0.0022746101822122,
      "clip_ratio/high_mean": 0.0010714436393755022,
      "clip_ratio/low_mean": 0.0016711111493350472,
      "clip_ratio/low_min": 0.00027733490151149454,
      "clip_ratio/region_mean": 0.0027425547523307614,
      "epoch": 0.005226653600032666,
      "grad_norm": 0.12368755787611008,
      "learning_rate": 1e-06,
      "loss": 0.0225,
      "step": 56
    },
    {
      "clip_ratio/high_max": 0.002423052217636723,
      "clip_ratio/high_mean": 0.0010949523020826746,
      "clip_ratio/low_mean": 0.0013366991515795235,
      "clip_ratio/low_min": 0.00018049324626190355,
      "clip_ratio/region_mean": 0.002431651431834325,
      "epoch": 0.00531998670003325,
      "grad_norm": 0.1228901818394661,
      "learning_rate": 1e-06,
      "loss": -0.0322,
      "step": 57
    },
    {
      "clip_ratio/high_max": 0.002108056600263808,
      "clip_ratio/high_mean": 0.0010210948930762243,
      "clip_ratio/low_mean": 0.0015501944471907336,
      "clip_ratio/low_min": 0.00027131374463351676,
      "clip_ratio/region_mean": 0.002571289340266958,
      "epoch": 0.005413319800033833,
      "grad_norm": 2.066697359085083,
      "learning_rate": 1e-06,
      "loss": 0.0542,
      "step": 58
    },
    {
      "clip_ratio/high_max": 0.0020602999720722437,
      "clip_ratio/high_mean": 0.0009926433140208246,
      "clip_ratio/low_mean": 0.0016167068461072631,
      "clip_ratio/low_min": 0.0003623974162110244,
      "clip_ratio/region_mean": 0.0026093501510331407,
      "epoch": 0.005506652900034417,
      "grad_norm": 0.1115637943148613,
      "learning_rate": 1e-06,
      "loss": 0.0361,
      "step": 59
    },
    {
      "clip_ratio/high_max": 0.0023626167603651993,
      "clip_ratio/high_mean": 0.0010147511529794428,
      "clip_ratio/low_mean": 0.0015369821448985022,
      "clip_ratio/low_min": 0.00020909743761876598,
      "clip_ratio/region_mean": 0.002551733297877945,
      "epoch": 0.005599986000035,
      "grad_norm": 0.12371265143156052,
      "learning_rate": 1e-06,
      "loss": 0.027,
      "step": 60
    },
    {
      "clip_ratio/high_max": 0.003005859201948624,
      "clip_ratio/high_mean": 0.001278374755202094,
      "clip_ratio/low_mean": 0.0015204250266833697,
      "clip_ratio/low_min": 0.00013415809280559188,
      "clip_ratio/region_mean": 0.002798799738229718,
      "epoch": 0.005693319100035584,
      "grad_norm": 0.13408105075359344,
      "learning_rate": 1e-06,
      "loss": -0.0094,
      "step": 61
    },
    {
      "clip_ratio/high_max": 0.002455111301969737,
      "clip_ratio/high_mean": 0.0011070089421991725,
      "clip_ratio/low_mean": 0.001333669697487494,
      "clip_ratio/low_min": 0.000334344715156476,
      "clip_ratio/region_mean": 0.002440678632410709,
      "epoch": 0.005786652200036166,
      "grad_norm": 0.12359930574893951,
      "learning_rate": 1e-06,
      "loss": 0.0335,
      "step": 62
    },
    {
      "clip_ratio/high_max": 0.002831522113410756,
      "clip_ratio/high_mean": 0.0011042114783776924,
      "clip_ratio/low_mean": 0.0015467919256479945,
      "clip_ratio/low_min": 0.0003798273955908371,
      "clip_ratio/region_mean": 0.0026510033931117505,
      "epoch": 0.00587998530003675,
      "grad_norm": 0.11751088500022888,
      "learning_rate": 1e-06,
      "loss": 0.0195,
      "step": 63
    },
    {
      "clip_ratio/high_max": 0.0023007421332295053,
      "clip_ratio/high_mean": 0.0011200906992598902,
      "clip_ratio/low_mean": 0.0013016235207032878,
      "clip_ratio/low_min": 0.00026949078437610297,
      "clip_ratio/region_mean": 0.002421714219963178,
      "epoch": 0.005973318400037333,
      "grad_norm": 0.11680912226438522,
      "learning_rate": 1e-06,
      "loss": -0.0031,
      "step": 64
    },
    {
      "clip_ratio/high_max": 0.0023685664709773846,
      "clip_ratio/high_mean": 0.0011035526640625903,
      "clip_ratio/low_mean": 0.0016556819427933078,
      "clip_ratio/low_min": 0.0002963187589557492,
      "clip_ratio/region_mean": 0.002759234579571057,
      "epoch": 0.006066651500037917,
      "grad_norm": 0.12468979507684708,
      "learning_rate": 1e-06,
      "loss": -0.0098,
      "step": 65
    },
    {
      "clip_ratio/high_max": 0.002694370625249576,
      "clip_ratio/high_mean": 0.001144878155173501,
      "clip_ratio/low_mean": 0.0017936700824066065,
      "clip_ratio/low_min": 0.0004304626581870252,
      "clip_ratio/region_mean": 0.0029385482412180863,
      "epoch": 0.0061599846000385,
      "grad_norm": 0.13200826942920685,
      "learning_rate": 1e-06,
      "loss": 0.036,
      "step": 66
    },
    {
      "clip_ratio/high_max": 0.0025700881524244323,
      "clip_ratio/high_mean": 0.0011668774495774414,
      "clip_ratio/low_mean": 0.001772287880157819,
      "clip_ratio/low_min": 0.00022172380340634845,
      "clip_ratio/region_mean": 0.0029391653515631333,
      "epoch": 0.0062533177000390835,
      "grad_norm": 0.12837441265583038,
      "learning_rate": 1e-06,
      "loss": 0.0477,
      "step": 67
    },
    {
      "clip_ratio/high_max": 0.0025398676152690314,
      "clip_ratio/high_mean": 0.0010521953736315481,
      "clip_ratio/low_mean": 0.0014053867671464104,
      "clip_ratio/low_min": 0.00016638472425256623,
      "clip_ratio/region_mean": 0.0024575820862082765,
      "epoch": 0.006346650800039666,
      "grad_norm": 0.12504403293132782,
      "learning_rate": 1e-06,
      "loss": 0.0239,
      "step": 68
    },
    {
      "clip_ratio/high_max": 0.002294306097610388,
      "clip_ratio/high_mean": 0.0010584088922769297,
      "clip_ratio/low_mean": 0.0017622818013478536,
      "clip_ratio/low_min": 0.0003273519287176896,
      "clip_ratio/region_mean": 0.002820690620865207,
      "epoch": 0.00643998390004025,
      "grad_norm": 0.12804903090000153,
      "learning_rate": 1e-06,
      "loss": 0.0151,
      "step": 69
    },
    {
      "clip_ratio/high_max": 0.002505788674170617,
      "clip_ratio/high_mean": 0.0011982092582911719,
      "clip_ratio/low_mean": 0.001765437627909705,
      "clip_ratio/low_min": 0.0004004208240075968,
      "clip_ratio/region_mean": 0.0029636468534590676,
      "epoch": 0.006533317000040833,
      "grad_norm": 0.1482425183057785,
      "learning_rate": 1e-06,
      "loss": -0.0027,
      "step": 70
    },
    {
      "clip_ratio/high_max": 0.002191903164202813,
      "clip_ratio/high_mean": 0.0010576176973700058,
      "clip_ratio/low_mean": 0.0016184864616661798,
      "clip_ratio/low_min": 0.00029498931053240085,
      "clip_ratio/region_mean": 0.0026761041081044823,
      "epoch": 0.0066266501000414165,
      "grad_norm": 0.11269011348485947,
      "learning_rate": 1e-06,
      "loss": 0.0245,
      "step": 71
    },
    {
      "clip_ratio/high_max": 0.0023948498055688106,
      "clip_ratio/high_mean": 0.0011416518391342834,
      "clip_ratio/low_mean": 0.001558263975312002,
      "clip_ratio/low_min": 0.0003109849458269309,
      "clip_ratio/region_mean": 0.002699915821722243,
      "epoch": 0.006719983200042,
      "grad_norm": 0.12281899154186249,
      "learning_rate": 1e-06,
      "loss": -0.0014,
      "step": 72
    },
    {
      "clip_ratio/high_max": 0.0022177253194968216,
      "clip_ratio/high_mean": 0.0010973968346661422,
      "clip_ratio/low_mean": 0.0019604489934863523,
      "clip_ratio/low_min": 0.00027768588824983453,
      "clip_ratio/region_mean": 0.003057845853618346,
      "epoch": 0.0068133163000425835,
      "grad_norm": 0.1317450851202011,
      "learning_rate": 1e-06,
      "loss": 0.034,
      "step": 73
    },
    {
      "clip_ratio/high_max": 0.0022507070752908476,
      "clip_ratio/high_mean": 0.0009198605457640951,
      "clip_ratio/low_mean": 0.0015583668646286242,
      "clip_ratio/low_min": 0.00020644260621338617,
      "clip_ratio/region_mean": 0.002478227390383836,
      "epoch": 0.006906649400043167,
      "grad_norm": 0.12079409509897232,
      "learning_rate": 1e-06,
      "loss": 0.0684,
      "step": 74
    },
    {
      "clip_ratio/high_max": 0.0024843343926477246,
      "clip_ratio/high_mean": 0.0011641666824289132,
      "clip_ratio/low_mean": 0.001618807582417503,
      "clip_ratio/low_min": 0.00015905514101177687,
      "clip_ratio/region_mean": 0.0027829742248286493,
      "epoch": 0.0069999825000437495,
      "grad_norm": 0.1247481182217598,
      "learning_rate": 1e-06,
      "loss": 0.0319,
      "step": 75
    },
    {
      "clip_ratio/high_max": 0.002368537876463961,
      "clip_ratio/high_mean": 0.0010069880518130958,
      "clip_ratio/low_mean": 0.0016674303624313325,
      "clip_ratio/low_min": 0.0003192582225892693,
      "clip_ratio/region_mean": 0.0026744183560367674,
      "epoch": 0.007093315600044333,
      "grad_norm": 0.12213882058858871,
      "learning_rate": 1e-06,
      "loss": 0.0681,
      "step": 76
    },
    {
      "clip_ratio/high_max": 0.002555884471803438,
      "clip_ratio/high_mean": 0.0010987444838974625,
      "clip_ratio/low_mean": 0.001698022650089115,
      "clip_ratio/low_min": 0.00027045703791372944,
      "clip_ratio/region_mean": 0.0027967671267106198,
      "epoch": 0.0071866487000449165,
      "grad_norm": 0.12074452638626099,
      "learning_rate": 1e-06,
      "loss": 0.0465,
      "step": 77
    },
    {
      "clip_ratio/high_max": 0.002588353760074824,
      "clip_ratio/high_mean": 0.001214584946865216,
      "clip_ratio/low_mean": 0.0015450818609679118,
      "clip_ratio/low_min": 0.0002666832497197902,
      "clip_ratio/region_mean": 0.0027596667569014244,
      "epoch": 0.0072799818000455,
      "grad_norm": 0.12084449827671051,
      "learning_rate": 1e-06,
      "loss": -0.0297,
      "step": 78
    },
    {
      "clip_ratio/high_max": 0.002571704411820974,
      "clip_ratio/high_mean": 0.0011780707700381754,
      "clip_ratio/low_mean": 0.0017109721884480678,
      "clip_ratio/low_min": 0.00018040862050838768,
      "clip_ratio/region_mean": 0.002889042931201402,
      "epoch": 0.007373314900046083,
      "grad_norm": 0.12859264016151428,
      "learning_rate": 1e-06,
      "loss": 0.0135,
      "step": 79
    },
    {
      "clip_ratio/high_max": 0.002559574968472589,
      "clip_ratio/high_mean": 0.0010937461302091833,
      "clip_ratio/low_mean": 0.0018106154093402438,
      "clip_ratio/low_min": 0.00022208099017007044,
      "clip_ratio/region_mean": 0.002904361601395067,
      "epoch": 0.007466648000046667,
      "grad_norm": 0.13039356470108032,
      "learning_rate": 1e-06,
      "loss": 0.0142,
      "step": 80
    },
    {
      "clip_ratio/high_max": 0.0024957659406936727,
      "clip_ratio/high_mean": 0.0011449147241364699,
      "clip_ratio/low_mean": 0.0017148948754766025,
      "clip_ratio/low_min": 0.00038437886996689485,
      "clip_ratio/region_mean": 0.0028598095741472207,
      "epoch": 0.0075599811000472495,
      "grad_norm": 0.1267310231924057,
      "learning_rate": 1e-06,
      "loss": -0.0168,
      "step": 81
    },
    {
      "clip_ratio/high_max": 0.0024354822526220232,
      "clip_ratio/high_mean": 0.0010882727219723165,
      "clip_ratio/low_mean": 0.002038623635598924,
      "clip_ratio/low_min": 0.00044295336192590185,
      "clip_ratio/region_mean": 0.0031268963575712405,
      "epoch": 0.007653314200047833,
      "grad_norm": 0.11634138226509094,
      "learning_rate": 1e-06,
      "loss": 0.0617,
      "step": 82
    },
    {
      "clip_ratio/high_max": 0.0024210622650571167,
      "clip_ratio/high_mean": 0.0011834132055810187,
      "clip_ratio/low_mean": 0.0018665518437046558,
      "clip_ratio/low_min": 0.00018165723258789512,
      "clip_ratio/region_mean": 0.00304996500199195,
      "epoch": 0.007746647300048416,
      "grad_norm": 0.11252500861883163,
      "learning_rate": 1e-06,
      "loss": 0.0446,
      "step": 83
    },
    {
      "clip_ratio/high_max": 0.0023836860636947677,
      "clip_ratio/high_mean": 0.0011186951960553415,
      "clip_ratio/low_mean": 0.0017712138396746013,
      "clip_ratio/low_min": 0.00030266990324889775,
      "clip_ratio/region_mean": 0.0028899090248160064,
      "epoch": 0.007839980400049,
      "grad_norm": 0.12852348387241364,
      "learning_rate": 1e-06,
      "loss": 0.0135,
      "step": 84
    },
    {
      "clip_ratio/high_max": 0.0024267022527055815,
      "clip_ratio/high_mean": 0.0011336017669236753,
      "clip_ratio/low_mean": 0.001672986640187446,
      "clip_ratio/low_min": 0.00027634374146146,
      "clip_ratio/region_mean": 0.0028065883816452697,
      "epoch": 0.007933313500049582,
      "grad_norm": 0.12799330055713654,
      "learning_rate": 1e-06,
      "loss": 0.0108,
      "step": 85
    },
    {
      "clip_ratio/high_max": 0.0025601494053262286,
      "clip_ratio/high_mean": 0.0012128133821533993,
      "clip_ratio/low_mean": 0.001678594449913362,
      "clip_ratio/low_min": 1.711391087155789e-05,
      "clip_ratio/region_mean": 0.0028914077120134607,
      "epoch": 0.008026646600050166,
      "grad_norm": 0.13526631891727448,
      "learning_rate": 1e-06,
      "loss": -0.0123,
      "step": 86
    },
    {
      "clip_ratio/high_max": 0.0025152130547212437,
      "clip_ratio/high_mean": 0.00105414194331388,
      "clip_ratio/low_mean": 0.0017104383950936608,
      "clip_ratio/low_min": 0.0002389557321293978,
      "clip_ratio/region_mean": 0.002764580334769562,
      "epoch": 0.00811997970005075,
      "grad_norm": 0.12694324553012848,
      "learning_rate": 1e-06,
      "loss": 0.0426,
      "step": 87
    },
    {
      "clip_ratio/high_max": 0.002423869627818931,
      "clip_ratio/high_mean": 0.0010796450042107608,
      "clip_ratio/low_mean": 0.0016469793336000293,
      "clip_ratio/low_min": 0.0003427411829761695,
      "clip_ratio/region_mean": 0.0027266243123449385,
      "epoch": 0.008213312800051333,
      "grad_norm": 0.11928199976682663,
      "learning_rate": 1e-06,
      "loss": 0.014,
      "step": 88
    },
    {
      "clip_ratio/high_max": 0.0028011376707581803,
      "clip_ratio/high_mean": 0.001124978814914357,
      "clip_ratio/low_mean": 0.0017385409446433187,
      "clip_ratio/low_min": 0.0004417475101945456,
      "clip_ratio/region_mean": 0.0028635197231778875,
      "epoch": 0.008306645900051916,
      "grad_norm": 0.12897472083568573,
      "learning_rate": 1e-06,
      "loss": 0.0174,
      "step": 89
    },
    {
      "clip_ratio/high_max": 0.00299468948651338,
      "clip_ratio/high_mean": 0.0012471801856008824,
      "clip_ratio/low_mean": 0.0015908674686215818,
      "clip_ratio/low_min": 0.00015413759319926612,
      "clip_ratio/region_mean": 0.002838047694240231,
      "epoch": 0.0083999790000525,
      "grad_norm": 0.1397995501756668,
      "learning_rate": 1e-06,
      "loss": 0.0509,
      "step": 90
    },
    {
      "clip_ratio/high_max": 0.0024705522664589807,
      "clip_ratio/high_mean": 0.0011441953447501874,
      "clip_ratio/low_mean": 0.0015895076357992366,
      "clip_ratio/low_min": 0.00030276219695224427,
      "clip_ratio/region_mean": 0.0027337030405760743,
      "epoch": 0.008493312100053083,
      "grad_norm": 0.1318233609199524,
      "learning_rate": 1e-06,
      "loss": 0.0043,
      "step": 91
    },
    {
      "clip_ratio/high_max": 0.002432436573144514,
      "clip_ratio/high_mean": 0.0011215947088203393,
      "clip_ratio/low_mean": 0.0016778742101450916,
      "clip_ratio/low_min": 0.00024281909190904116,
      "clip_ratio/region_mean": 0.002799469046294689,
      "epoch": 0.008586645200053667,
      "grad_norm": 0.12331629544496536,
      "learning_rate": 1e-06,
      "loss": 0.0251,
      "step": 92
    },
    {
      "clip_ratio/high_max": 0.0027539411166799255,
      "clip_ratio/high_mean": 0.0012068548494426068,
      "clip_ratio/low_mean": 0.001572672488691751,
      "clip_ratio/low_min": 0.00018596320569486124,
      "clip_ratio/region_mean": 0.0027795273199444637,
      "epoch": 0.00867997830005425,
      "grad_norm": 0.11946596205234528,
      "learning_rate": 1e-06,
      "loss": 0.0072,
      "step": 93
    },
    {
      "clip_ratio/high_max": 0.002665993459231686,
      "clip_ratio/high_mean": 0.001243518836417934,
      "clip_ratio/low_mean": 0.0016472251300001517,
      "clip_ratio/low_min": 0.00028363862384139793,
      "clip_ratio/region_mean": 0.0028907440428156406,
      "epoch": 0.008773311400054834,
      "grad_norm": 0.12517011165618896,
      "learning_rate": 1e-06,
      "loss": -0.0061,
      "step": 94
    },
    {
      "clip_ratio/high_max": 0.0022710794837621506,
      "clip_ratio/high_mean": 0.001101587688026484,
      "clip_ratio/low_mean": 0.001575810441863723,
      "clip_ratio/low_min": 0.00016782256079750368,
      "clip_ratio/region_mean": 0.002677398137166165,
      "epoch": 0.008866644500055417,
      "grad_norm": 0.12414906919002533,
      "learning_rate": 1e-06,
      "loss": -0.0258,
      "step": 95
    },
    {
      "clip_ratio/high_max": 0.0023688660767220426,
      "clip_ratio/high_mean": 0.0011477822736196686,
      "clip_ratio/low_mean": 0.0015816522791283205,
      "clip_ratio/low_min": 0.00018785280281008454,
      "clip_ratio/region_mean": 0.002729434512730222,
      "epoch": 0.008959977600056,
      "grad_norm": 0.12111297249794006,
      "learning_rate": 1e-06,
      "loss": 0.0102,
      "step": 96
    },
    {
      "clip_ratio/high_max": 0.0024623051212984137,
      "clip_ratio/high_mean": 0.0011101971431344282,
      "clip_ratio/low_mean": 0.001513851406343747,
      "clip_ratio/low_min": 0.00027694273103406886,
      "clip_ratio/region_mean": 0.0026240485749440268,
      "epoch": 0.009053310700056582,
      "grad_norm": 0.11820439994335175,
      "learning_rate": 1e-06,
      "loss": 0.0104,
      "step": 97
    },
    {
      "clip_ratio/high_max": 0.002735242494964041,
      "clip_ratio/high_mean": 0.0011144193340442143,
      "clip_ratio/low_mean": 0.0019397073156142142,
      "clip_ratio/low_min": 0.00027727985798264854,
      "clip_ratio/region_mean": 0.0030541266896761954,
      "epoch": 0.009146643800057166,
      "grad_norm": 0.11758563667535782,
      "learning_rate": 1e-06,
      "loss": -0.0107,
      "step": 98
    },
    {
      "clip_ratio/high_max": 0.0024884922459023073,
      "clip_ratio/high_mean": 0.001027773903842899,
      "clip_ratio/low_mean": 0.0019888922324753366,
      "clip_ratio/low_min": 0.0003608038427955762,
      "clip_ratio/region_mean": 0.0030166661163093522,
      "epoch": 0.00923997690005775,
      "grad_norm": 0.11934468150138855,
      "learning_rate": 1e-06,
      "loss": 0.0577,
      "step": 99
    },
    {
      "clip_ratio/high_max": 0.002381966100074351,
      "clip_ratio/high_mean": 0.0010493788031453732,
      "clip_ratio/low_mean": 0.0019476753514027223,
      "clip_ratio/low_min": 0.00017321978066320298,
      "clip_ratio/region_mean": 0.002997054165462032,
      "epoch": 0.009333310000058333,
      "grad_norm": 0.6169129014015198,
      "learning_rate": 1e-06,
      "loss": 0.0484,
      "step": 100
    },
    {
      "clip_ratio/high_max": 0.0022514205775223672,
      "clip_ratio/high_mean": 0.0009954330635082442,
      "clip_ratio/low_mean": 0.0018879740237025544,
      "clip_ratio/low_min": 0.00021392679627751932,
      "clip_ratio/region_mean": 0.002883407098124735,
      "epoch": 0.009426643100058916,
      "grad_norm": 0.12227354198694229,
      "learning_rate": 1e-06,
      "loss": 0.0531,
      "step": 101
    },
    {
      "clip_ratio/high_max": 0.002587458031484857,
      "clip_ratio/high_mean": 0.0012456623171601677,
      "clip_ratio/low_mean": 0.0021699201897718012,
      "clip_ratio/low_min": 0.00022070783052186016,
      "clip_ratio/region_mean": 0.0034155824832851067,
      "epoch": 0.0095199762000595,
      "grad_norm": 0.13665755093097687,
      "learning_rate": 1e-06,
      "loss": 0.0284,
      "step": 102
    },
    {
      "clip_ratio/high_max": 0.002236638232716359,
      "clip_ratio/high_mean": 0.0010470595807419159,
      "clip_ratio/low_mean": 0.001851815792178968,
      "clip_ratio/low_min": 0.00022481873475044267,
      "clip_ratio/region_mean": 0.0028988753765588626,
      "epoch": 0.009613309300060083,
      "grad_norm": 0.12030473351478577,
      "learning_rate": 1e-06,
      "loss": 0.018,
      "step": 103
    },
    {
      "clip_ratio/high_max": 0.0022463720888481475,
      "clip_ratio/high_mean": 0.000988552266790066,
      "clip_ratio/low_mean": 0.0017420161966583692,
      "clip_ratio/low_min": 0.0004026728001917945,
      "clip_ratio/region_mean": 0.0027305684561724775,
      "epoch": 0.009706642400060667,
      "grad_norm": 0.12268640846014023,
      "learning_rate": 1e-06,
      "loss": 0.0166,
      "step": 104
    },
    {
      "clip_ratio/high_max": 0.002458012240822427,
      "clip_ratio/high_mean": 0.0010333459977118764,
      "clip_ratio/low_mean": 0.0020641325318138115,
      "clip_ratio/low_min": 0.0002868674846467911,
      "clip_ratio/region_mean": 0.003097478547715582,
      "epoch": 0.00979997550006125,
      "grad_norm": 0.12414582818746567,
      "learning_rate": 1e-06,
      "loss": 0.0135,
      "step": 105
    },
    {
      "clip_ratio/high_max": 0.0026661057345336303,
      "clip_ratio/high_mean": 0.0011742309179680888,
      "clip_ratio/low_mean": 0.002047063160716789,
      "clip_ratio/low_min": 0.00025208337501680944,
      "clip_ratio/region_mean": 0.0032212939840974286,
      "epoch": 0.009893308600061834,
      "grad_norm": 0.12151814252138138,
      "learning_rate": 1e-06,
      "loss": 0.0208,
      "step": 106
    },
    {
      "clip_ratio/high_max": 0.002588125367765315,
      "clip_ratio/high_mean": 0.0011614342729444616,
      "clip_ratio/low_mean": 0.001879544579423964,
      "clip_ratio/low_min": 0.00039051946077961475,
      "clip_ratio/region_mean": 0.003040978845092468,
      "epoch": 0.009986641700062417,
      "grad_norm": 0.12045180052518845,
      "learning_rate": 1e-06,
      "loss": 0.0283,
      "step": 107
    },
    {
      "clip_ratio/high_max": 0.002477358590112999,
      "clip_ratio/high_mean": 0.001163388958957512,
      "clip_ratio/low_mean": 0.0019053846772294492,
      "clip_ratio/low_min": 0.00023204635908768978,
      "clip_ratio/region_mean": 0.0030687737016705796,
      "epoch": 0.010079974800063,
      "grad_norm": 0.12709839642047882,
      "learning_rate": 1e-06,
      "loss": 0.0223,
      "step": 108
    },
    {
      "clip_ratio/high_max": 0.0024174013669835404,
      "clip_ratio/high_mean": 0.0011152332481287885,
      "clip_ratio/low_mean": 0.0019080139172729105,
      "clip_ratio/low_min": 0.00030921201778255636,
      "clip_ratio/region_mean": 0.003023247219971381,
      "epoch": 0.010173307900063584,
      "grad_norm": 0.12614239752292633,
      "learning_rate": 1e-06,
      "loss": 0.031,
      "step": 109
    },
    {
      "clip_ratio/high_max": 0.002114980947226286,
      "clip_ratio/high_mean": 0.0011003297768183984,
      "clip_ratio/low_mean": 0.002239013585494831,
      "clip_ratio/low_min": 0.00033608295962039847,
      "clip_ratio/region_mean": 0.003339343369589187,
      "epoch": 0.010266641000064166,
      "grad_norm": 0.13278627395629883,
      "learning_rate": 1e-06,
      "loss": 0.0426,
      "step": 110
    },
    {
      "clip_ratio/high_max": 0.002821992071403656,
      "clip_ratio/high_mean": 0.001197408088046359,
      "clip_ratio/low_mean": 0.0019378728247829713,
      "clip_ratio/low_min": 0.00033207244086952414,
      "clip_ratio/region_mean": 0.003135280894639436,
      "epoch": 0.010359974100064749,
      "grad_norm": 0.12661196291446686,
      "learning_rate": 1e-06,
      "loss": 0.0205,
      "step": 111
    },
    {
      "clip_ratio/high_max": 0.0028136772307334468,
      "clip_ratio/high_mean": 0.0012724134267045883,
      "clip_ratio/low_mean": 0.001824662227591034,
      "clip_ratio/low_min": 0.0002584917856438551,
      "clip_ratio/region_mean": 0.0030970755906309932,
      "epoch": 0.010453307200065333,
      "grad_norm": 0.18222671747207642,
      "learning_rate": 1e-06,
      "loss": -0.0116,
      "step": 112
    },
    {
      "clip_ratio/high_max": 0.0030055799943511374,
      "clip_ratio/high_mean": 0.0013276239224069286,
      "clip_ratio/low_mean": 0.002040242121438496,
      "clip_ratio/low_min": 0.0003637545923993457,
      "clip_ratio/region_mean": 0.0033678660402074456,
      "epoch": 0.010546640300065916,
      "grad_norm": 0.13751061260700226,
      "learning_rate": 1e-06,
      "loss": 0.0025,
      "step": 113
    },
    {
      "clip_ratio/high_max": 0.002621527215524111,
      "clip_ratio/high_mean": 0.0012256510999577586,
      "clip_ratio/low_mean": 0.0019793871069850866,
      "clip_ratio/low_min": 0.0002253668808407383,
      "clip_ratio/region_mean": 0.003205038323358167,
      "epoch": 0.0106399734000665,
      "grad_norm": 0.13413459062576294,
      "learning_rate": 1e-06,
      "loss": -0.0018,
      "step": 114
    },
    {
      "clip_ratio/high_max": 0.0028729236510116607,
      "clip_ratio/high_mean": 0.0012719973692583153,
      "clip_ratio/low_mean": 0.0018577749287942424,
      "clip_ratio/low_min": 0.0001991901717701694,
      "clip_ratio/region_mean": 0.003129772303509526,
      "epoch": 0.010733306500067083,
      "grad_norm": 0.13839739561080933,
      "learning_rate": 1e-06,
      "loss": 0.0186,
      "step": 115
    },
    {
      "clip_ratio/high_max": 0.0026556626762612723,
      "clip_ratio/high_mean": 0.0011971744133916218,
      "clip_ratio/low_mean": 0.001761995896231383,
      "clip_ratio/low_min": 0.00018820153218257474,
      "clip_ratio/region_mean": 0.0029591703350888565,
      "epoch": 0.010826639600067666,
      "grad_norm": 0.12764184176921844,
      "learning_rate": 1e-06,
      "loss": 0.0146,
      "step": 116
    },
    {
      "clip_ratio/high_max": 0.0023235606131493114,
      "clip_ratio/high_mean": 0.001061090937582776,
      "clip_ratio/low_mean": 0.002012656448641792,
      "clip_ratio/low_min": 0.0001853870944614755,
      "clip_ratio/region_mean": 0.0030737474298803136,
      "epoch": 0.01091997270006825,
      "grad_norm": 0.12334010004997253,
      "learning_rate": 1e-06,
      "loss": 0.0619,
      "step": 117
    },
    {
      "clip_ratio/high_max": 0.0030490902572637424,
      "clip_ratio/high_mean": 0.0013991236046422273,
      "clip_ratio/low_mean": 0.0021201470735832117,
      "clip_ratio/low_min": 0.0002730680898821447,
      "clip_ratio/region_mean": 0.003519270714605227,
      "epoch": 0.011013305800068833,
      "grad_norm": 0.404316782951355,
      "learning_rate": 1e-06,
      "loss": -0.0199,
      "step": 118
    },
    {
      "clip_ratio/high_max": 0.002557805804826785,
      "clip_ratio/high_mean": 0.0011218647996429354,
      "clip_ratio/low_mean": 0.0017191165243275464,
      "clip_ratio/low_min": 0.0001289654164793319,
      "clip_ratio/region_mean": 0.002840981338522397,
      "epoch": 0.011106638900069417,
      "grad_norm": 0.12503401935100555,
      "learning_rate": 1e-06,
      "loss": -0.0002,
      "step": 119
    },
    {
      "clip_ratio/high_max": 0.0027102772874059156,
      "clip_ratio/high_mean": 0.0011512573546497151,
      "clip_ratio/low_mean": 0.002133196932845749,
      "clip_ratio/low_min": 0.0004344923236203613,
      "clip_ratio/region_mean": 0.0032844543602550402,
      "epoch": 0.01119997200007,
      "grad_norm": 0.12219876796007156,
      "learning_rate": 1e-06,
      "loss": 0.0122,
      "step": 120
    },
    {
      "clip_ratio/high_max": 0.0025009219170897268,
      "clip_ratio/high_mean": 0.0010768282081698999,
      "clip_ratio/low_mean": 0.0021460636162373703,
      "clip_ratio/low_min": 0.0002805102385536884,
      "clip_ratio/region_mean": 0.003222891842597164,
      "epoch": 0.011293305100070584,
      "grad_norm": 0.12973983585834503,
      "learning_rate": 1e-06,
      "loss": 0.0052,
      "step": 121
    },
    {
      "clip_ratio/high_max": 0.0025484035577392206,
      "clip_ratio/high_mean": 0.0011680889656418003,
      "clip_ratio/low_mean": 0.002039420240180334,
      "clip_ratio/low_min": 0.000354983488250582,
      "clip_ratio/region_mean": 0.0032075092458399013,
      "epoch": 0.011386638200071167,
      "grad_norm": 0.8162333369255066,
      "learning_rate": 1e-06,
      "loss": 0.0448,
      "step": 122
    },
    {
      "clip_ratio/high_max": 0.002766628058452625,
      "clip_ratio/high_mean": 0.0013111048210703302,
      "clip_ratio/low_mean": 0.002181306299462449,
      "clip_ratio/low_min": 0.00037754039840365294,
      "clip_ratio/region_mean": 0.0034924111532745883,
      "epoch": 0.011479971300071749,
      "grad_norm": 0.13874521851539612,
      "learning_rate": 1e-06,
      "loss": -0.0215,
      "step": 123
    },
    {
      "clip_ratio/high_max": 0.0030544891633326188,
      "clip_ratio/high_mean": 0.0013875375298084691,
      "clip_ratio/low_mean": 0.0020280593271309044,
      "clip_ratio/low_min": 0.00028534032389870845,
      "clip_ratio/region_mean": 0.0034155968605773523,
      "epoch": 0.011573304400072332,
      "grad_norm": 0.13649602234363556,
      "learning_rate": 1e-06,
      "loss": -0.0329,
      "step": 124
    },
    {
      "clip_ratio/high_max": 0.0023659215730731376,
      "clip_ratio/high_mean": 0.0011312648875900777,
      "clip_ratio/low_mean": 0.0020022026074002497,
      "clip_ratio/low_min": 0.00019996420724055497,
      "clip_ratio/region_mean": 0.0031334675077232532,
      "epoch": 0.011666637500072916,
      "grad_norm": 0.12368867546319962,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "step": 125
    },
    {
      "clip_ratio/high_max": 0.0024065821125986986,
      "clip_ratio/high_mean": 0.0011076565897383261,
      "clip_ratio/low_mean": 0.0019181899551767856,
      "clip_ratio/low_min": 0.00023527296434622258,
      "clip_ratio/region_mean": 0.003025846541277133,
      "epoch": 0.0117599706000735,
      "grad_norm": 0.13523416221141815,
      "learning_rate": 1e-06,
      "loss": 0.027,
      "step": 126
    },
    {
      "clip_ratio/high_max": 0.0024364546334254555,
      "clip_ratio/high_mean": 0.001143281020631548,
      "clip_ratio/low_mean": 0.0018475305842002854,
      "clip_ratio/low_min": 0.0001368756757074152,
      "clip_ratio/region_mean": 0.002990811612107791,
      "epoch": 0.011853303700074083,
      "grad_norm": 0.12084290385246277,
      "learning_rate": 1e-06,
      "loss": -0.0238,
      "step": 127
    },
    {
      "clip_ratio/high_max": 0.0024855052542989142,
      "clip_ratio/high_mean": 0.0010713422670960426,
      "clip_ratio/low_mean": 0.002105702609696891,
      "clip_ratio/low_min": 0.000371893281226221,
      "clip_ratio/region_mean": 0.0031770448258612305,
      "epoch": 0.011946636800074666,
      "grad_norm": 0.12129528075456619,
      "learning_rate": 1e-06,
      "loss": 0.0562,
      "step": 128
    },
    {
      "clip_ratio/high_max": 0.002161408141546417,
      "clip_ratio/high_mean": 0.0008277388988062739,
      "clip_ratio/low_mean": 0.0008564443451177794,
      "clip_ratio/low_min": 7.493534849345451e-05,
      "clip_ratio/region_mean": 0.0016841832475620322,
      "completions/clipped_ratio": 0.013968331473214302,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4094.0,
      "completions/mean_length": 614.7697143554688,
      "completions/mean_terminated_length": 565.4537963867188,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.01203996990007525,
      "grad_norm": 0.11894074827432632,
      "learning_rate": 1e-06,
      "loss": 0.0127,
      "num_tokens": 162389510.0,
      "reward": 0.5611311197280884,
      "reward_std": 0.20702067017555237,
      "rewards/simpleverify_reward/mean": 0.5611310601234436,
      "rewards/simpleverify_reward/std": 0.49625107645988464,
      "step": 129
    },
    {
      "clip_ratio/high_max": 0.0019244481445639394,
      "clip_ratio/high_mean": 0.0008159040826285491,
      "clip_ratio/low_mean": 0.0009070359938050387,
      "clip_ratio/low_min": 4.257251930539496e-05,
      "clip_ratio/region_mean": 0.0017229400400537997,
      "epoch": 0.012133303000075833,
      "grad_norm": 0.09997950494289398,
      "learning_rate": 1e-06,
      "loss": 0.0186,
      "step": 130
    },
    {
      "clip_ratio/high_max": 0.001922179748362396,
      "clip_ratio/high_mean": 0.0007555869933639769,
      "clip_ratio/low_mean": 0.0009793227145564742,
      "clip_ratio/low_min": 9.517786565993447e-05,
      "clip_ratio/region_mean": 0.0017349096815451048,
      "epoch": 0.012226636100076417,
      "grad_norm": 0.10746411979198456,
      "learning_rate": 1e-06,
      "loss": 0.0676,
      "step": 131
    },
    {
      "clip_ratio/high_max": 0.0025278526372858323,
      "clip_ratio/high_mean": 0.0009213798912242055,
      "clip_ratio/low_mean": 0.0008448825083178235,
      "clip_ratio/low_min": 5.5044874898158014e-05,
      "clip_ratio/region_mean": 0.0017662623649812303,
      "epoch": 0.012319969200077,
      "grad_norm": 0.10569746047258377,
      "learning_rate": 1e-06,
      "loss": -0.01,
      "step": 132
    },
    {
      "clip_ratio/high_max": 0.0027123287218273617,
      "clip_ratio/high_mean": 0.0010814159759320319,
      "clip_ratio/low_mean": 0.0008209372754208744,
      "clip_ratio/low_min": 0.00010357579776609782,
      "clip_ratio/region_mean": 0.0019023532659048215,
      "epoch": 0.012413302300077584,
      "grad_norm": 0.10641106963157654,
      "learning_rate": 1e-06,
      "loss": -0.0059,
      "step": 133
    },
    {
      "clip_ratio/high_max": 0.0023935708159115165,
      "clip_ratio/high_mean": 0.0009718834226077888,
      "clip_ratio/low_mean": 0.000910684108021087,
      "clip_ratio/low_min": 5.389281614043284e-05,
      "clip_ratio/region_mean": 0.0018825675433618017,
      "epoch": 0.012506635400078167,
      "grad_norm": 0.10697611421346664,
      "learning_rate": 1e-06,
      "loss": 0.003,
      "step": 134
    },
    {
      "clip_ratio/high_max": 0.0025179963413393125,
      "clip_ratio/high_mean": 0.0009670342951721977,
      "clip_ratio/low_mean": 0.0008859125573508209,
      "clip_ratio/low_min": 7.011599427642068e-05,
      "clip_ratio/region_mean": 0.0018529468434280716,
      "epoch": 0.01259996850007875,
      "grad_norm": 0.12203706055879593,
      "learning_rate": 1e-06,
      "loss": 0.0459,
      "step": 135
    },
    {
      "clip_ratio/high_max": 0.002006823677220382,
      "clip_ratio/high_mean": 0.0009237128906534053,
      "clip_ratio/low_mean": 0.0009380030278407503,
      "clip_ratio/low_min": 8.04917945060879e-05,
      "clip_ratio/region_mean": 0.001861715929408092,
      "epoch": 0.012693301600079332,
      "grad_norm": 0.11572477221488953,
      "learning_rate": 1e-06,
      "loss": 0.0349,
      "step": 136
    },
    {
      "clip_ratio/high_max": 0.0022455390280811116,
      "clip_ratio/high_mean": 0.0009581133708707057,
      "clip_ratio/low_mean": 0.0008806293171801371,
      "clip_ratio/low_min": 6.871248660900164e-05,
      "clip_ratio/region_mean": 0.001838742675317917,
      "epoch": 0.012786634700079916,
      "grad_norm": 0.1089639663696289,
      "learning_rate": 1e-06,
      "loss": 0.0145,
      "step": 137
    },
    {
      "clip_ratio/high_max": 0.0023253438848769292,
      "clip_ratio/high_mean": 0.0009870462818071246,
      "clip_ratio/low_mean": 0.0008008372496988159,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0017878835933515802,
      "epoch": 0.0128799678000805,
      "grad_norm": 0.11664681881666183,
      "learning_rate": 1e-06,
      "loss": -0.006,
      "step": 138
    },
    {
      "clip_ratio/high_max": 0.002125671318935929,
      "clip_ratio/high_mean": 0.000952323382080067,
      "clip_ratio/low_mean": 0.0010867085657082498,
      "clip_ratio/low_min": 0.00023532289833383402,
      "clip_ratio/region_mean": 0.0020390319114085287,
      "epoch": 0.012973300900081083,
      "grad_norm": 0.11493740975856781,
      "learning_rate": 1e-06,
      "loss": 0.0563,
      "step": 139
    },
    {
      "clip_ratio/high_max": 0.0018843048746930435,
      "clip_ratio/high_mean": 0.0008160637844412122,
      "clip_ratio/low_mean": 0.0009262105268135201,
      "clip_ratio/low_min": 6.60446557958494e-05,
      "clip_ratio/region_mean": 0.0017422743330826052,
      "epoch": 0.013066634000081666,
      "grad_norm": 0.10611748695373535,
      "learning_rate": 1e-06,
      "loss": 0.0235,
      "step": 140
    },
    {
      "clip_ratio/high_max": 0.002287157425598707,
      "clip_ratio/high_mean": 0.0009172473055514274,
      "clip_ratio/low_mean": 0.0010591678183118347,
      "clip_ratio/low_min": 0.00019992587203887524,
      "clip_ratio/region_mean": 0.001976415158424061,
      "epoch": 0.01315996710008225,
      "grad_norm": 0.11522714048624039,
      "learning_rate": 1e-06,
      "loss": 0.0426,
      "step": 141
    },
    {
      "clip_ratio/high_max": 0.001953459155629389,
      "clip_ratio/high_mean": 0.0008758882304391591,
      "clip_ratio/low_mean": 0.001051960689437692,
      "clip_ratio/low_min": 0.00013661285265698098,
      "clip_ratio/region_mean": 0.001927848905324936,
      "epoch": 0.013253300200082833,
      "grad_norm": 0.11635539680719376,
      "learning_rate": 1e-06,
      "loss": 0.0604,
      "step": 142
    },
    {
      "clip_ratio/high_max": 0.0019318033482704777,
      "clip_ratio/high_mean": 0.0007581848458357854,
      "clip_ratio/low_mean": 0.0011441625974839553,
      "clip_ratio/low_min": 0.00018216911485069431,
      "clip_ratio/region_mean": 0.0019023473578272387,
      "epoch": 0.013346633300083417,
      "grad_norm": 0.10934232920408249,
      "learning_rate": 1e-06,
      "loss": 0.0441,
      "step": 143
    },
    {
      "clip_ratio/high_max": 0.002223715218860889,
      "clip_ratio/high_mean": 0.0009109926231758436,
      "clip_ratio/low_mean": 0.0010616847721394151,
      "clip_ratio/low_min": 0.00012821391919715097,
      "clip_ratio/region_mean": 0.0019726774335140362,
      "epoch": 0.013439966400084,
      "grad_norm": 0.11126284301280975,
      "learning_rate": 1e-06,
      "loss": 0.0719,
      "step": 144
    },
    {
      "clip_ratio/high_max": 0.0022930012273718603,
      "clip_ratio/high_mean": 0.0009078173316083848,
      "clip_ratio/low_mean": 0.0010419095087854657,
      "clip_ratio/low_min": 0.0001388745340591413,
      "clip_ratio/region_mean": 0.0019497268222039565,
      "epoch": 0.013533299500084583,
      "grad_norm": 0.11850086599588394,
      "learning_rate": 1e-06,
      "loss": 0.0188,
      "step": 145
    },
    {
      "clip_ratio/high_max": 0.0023042570537654683,
      "clip_ratio/high_mean": 0.0009658703602326568,
      "clip_ratio/low_mean": 0.0009650740394135937,
      "clip_ratio/low_min": 8.241498926508939e-05,
      "clip_ratio/region_mean": 0.001930944352352526,
      "epoch": 0.013626632600085167,
      "grad_norm": 0.10880748927593231,
      "learning_rate": 1e-06,
      "loss": 0.0257,
      "step": 146
    },
    {
      "clip_ratio/high_max": 0.0021564784183283336,
      "clip_ratio/high_mean": 0.0009590455920260865,
      "clip_ratio/low_mean": 0.0009871662841760553,
      "clip_ratio/low_min": 0.00018428189378028037,
      "clip_ratio/region_mean": 0.001946211894392036,
      "epoch": 0.01371996570008575,
      "grad_norm": 0.11974553018808365,
      "learning_rate": 1e-06,
      "loss": -0.0055,
      "step": 147
    },
    {
      "clip_ratio/high_max": 0.0029374732985161245,
      "clip_ratio/high_mean": 0.001042643802065868,
      "clip_ratio/low_mean": 0.001084575844288338,
      "clip_ratio/low_min": 5.8345849538454786e-05,
      "clip_ratio/region_mean": 0.002127219660906121,
      "epoch": 0.013813298800086334,
      "grad_norm": 0.1198730543255806,
      "learning_rate": 1e-06,
      "loss": 0.0137,
      "step": 148
    },
    {
      "clip_ratio/high_max": 0.0023015585938992444,
      "clip_ratio/high_mean": 0.0008549333106202539,
      "clip_ratio/low_mean": 0.001007696868327912,
      "clip_ratio/low_min": 4.690584864874836e-05,
      "clip_ratio/region_mean": 0.0018626301316544414,
      "epoch": 0.013906631900086916,
      "grad_norm": 0.3750462830066681,
      "learning_rate": 1e-06,
      "loss": 0.0223,
      "step": 149
    },
    {
      "clip_ratio/high_max": 0.0021754269546363503,
      "clip_ratio/high_mean": 0.0008916510378185194,
      "clip_ratio/low_mean": 0.0011523259854584467,
      "clip_ratio/low_min": 5.7523982832208276e-05,
      "clip_ratio/region_mean": 0.0020439770742086694,
      "epoch": 0.013999965000087499,
      "grad_norm": 0.1076037660241127,
      "learning_rate": 1e-06,
      "loss": 0.0729,
      "step": 150
    },
    {
      "clip_ratio/high_max": 0.0024364274431718513,
      "clip_ratio/high_mean": 0.0009684265933174174,
      "clip_ratio/low_mean": 0.0011742259666789323,
      "clip_ratio/low_min": 5.952266747044632e-05,
      "clip_ratio/region_mean": 0.002142652556358371,
      "epoch": 0.014093298100088083,
      "grad_norm": 0.11541232466697693,
      "learning_rate": 1e-06,
      "loss": 0.0216,
      "step": 151
    },
    {
      "clip_ratio/high_max": 0.0019661002079374157,
      "clip_ratio/high_mean": 0.0008246558172686491,
      "clip_ratio/low_mean": 0.0011414500077080447,
      "clip_ratio/low_min": 0.0001294427815992094,
      "clip_ratio/region_mean": 0.0019661058468045667,
      "epoch": 0.014186631200088666,
      "grad_norm": 0.11190304160118103,
      "learning_rate": 1e-06,
      "loss": 0.0752,
      "step": 152
    },
    {
      "clip_ratio/high_max": 0.002053126307146158,
      "clip_ratio/high_mean": 0.0008752066005399683,
      "clip_ratio/low_mean": 0.0009766246239450993,
      "clip_ratio/low_min": 0.00013271671195980161,
      "clip_ratio/region_mean": 0.0018518312062951736,
      "epoch": 0.01427996430008925,
      "grad_norm": 0.10394339263439178,
      "learning_rate": 1e-06,
      "loss": 0.0293,
      "step": 153
    },
    {
      "clip_ratio/high_max": 0.001958266308065504,
      "clip_ratio/high_mean": 0.000847771805638331,
      "clip_ratio/low_mean": 0.0010144932093680836,
      "clip_ratio/low_min": 0.00012687309117609402,
      "clip_ratio/region_mean": 0.0018622650459292345,
      "epoch": 0.014373297400089833,
      "grad_norm": 0.10715346038341522,
      "learning_rate": 1e-06,
      "loss": 0.0282,
      "step": 154
    },
    {
      "clip_ratio/high_max": 0.0023149186963564716,
      "clip_ratio/high_mean": 0.0009205482856486924,
      "clip_ratio/low_mean": 0.0009852970979409292,
      "clip_ratio/low_min": 9.318105003330857e-05,
      "clip_ratio/region_mean": 0.0019058454272453673,
      "epoch": 0.014466630500090416,
      "grad_norm": 0.1153310164809227,
      "learning_rate": 1e-06,
      "loss": 0.0515,
      "step": 155
    },
    {
      "clip_ratio/high_max": 0.0022802790699643083,
      "clip_ratio/high_mean": 0.0009375233603350352,
      "clip_ratio/low_mean": 0.001135696209530579,
      "clip_ratio/low_min": 0.00018112708949047374,
      "clip_ratio/region_mean": 0.0020732195480377413,
      "epoch": 0.014559963600091,
      "grad_norm": 0.11021652817726135,
      "learning_rate": 1e-06,
      "loss": 0.0492,
      "step": 156
    },
    {
      "clip_ratio/high_max": 0.002113158334395848,
      "clip_ratio/high_mean": 0.000859156700244057,
      "clip_ratio/low_mean": 0.0009488925807090709,
      "clip_ratio/low_min": 9.812972530198749e-05,
      "clip_ratio/region_mean": 0.0018080492300214246,
      "epoch": 0.014653296700091583,
      "grad_norm": 0.1025896891951561,
      "learning_rate": 1e-06,
      "loss": 0.0144,
      "step": 157
    },
    {
      "clip_ratio/high_max": 0.002496098000847269,
      "clip_ratio/high_mean": 0.0010491368957445957,
      "clip_ratio/low_mean": 0.0008757588693697471,
      "clip_ratio/low_min": 5.840846279170364e-05,
      "clip_ratio/region_mean": 0.0019248957396484911,
      "epoch": 0.014746629800092167,
      "grad_norm": 0.11381614953279495,
      "learning_rate": 1e-06,
      "loss": 0.0099,
      "step": 158
    },
    {
      "clip_ratio/high_max": 0.002546114192227833,
      "clip_ratio/high_mean": 0.0009751469042384997,
      "clip_ratio/low_mean": 0.0010020688314398285,
      "clip_ratio/low_min": 0.00012872707065980649,
      "clip_ratio/region_mean": 0.001977215739316307,
      "epoch": 0.01483996290009275,
      "grad_norm": 0.1121005266904831,
      "learning_rate": 1e-06,
      "loss": 0.061,
      "step": 159
    },
    {
      "clip_ratio/high_max": 0.002150193067791406,
      "clip_ratio/high_mean": 0.0008916723272704985,
      "clip_ratio/low_mean": 0.0010205037033301778,
      "clip_ratio/low_min": 0.00013426712666841922,
      "clip_ratio/region_mean": 0.0019121760051348247,
      "epoch": 0.014933296000093334,
      "grad_norm": 0.12039100378751755,
      "learning_rate": 1e-06,
      "loss": 0.0238,
      "step": 160
    },
    {
      "clip_ratio/high_max": 0.002424445243377704,
      "clip_ratio/high_mean": 0.0010037648717116099,
      "clip_ratio/low_mean": 0.0010338006359233987,
      "clip_ratio/low_min": 7.64307069403003e-05,
      "clip_ratio/region_mean": 0.0020375655221869238,
      "epoch": 0.015026629100093917,
      "grad_norm": 0.11659151315689087,
      "learning_rate": 1e-06,
      "loss": -0.0014,
      "step": 161
    },
    {
      "clip_ratio/high_max": 0.0021807785524288192,
      "clip_ratio/high_mean": 0.0008761026565480279,
      "clip_ratio/low_mean": 0.0010180029348703101,
      "clip_ratio/low_min": 0.00018196645305579295,
      "clip_ratio/region_mean": 0.001894105582323391,
      "epoch": 0.015119962200094499,
      "grad_norm": 0.11176208406686783,
      "learning_rate": 1e-06,
      "loss": 0.0589,
      "step": 162
    },
    {
      "clip_ratio/high_max": 0.001838619944464881,
      "clip_ratio/high_mean": 0.0008191784290829673,
      "clip_ratio/low_mean": 0.0009176180592476157,
      "clip_ratio/low_min": 5.925031837250572e-05,
      "clip_ratio/region_mean": 0.0017367964755976573,
      "epoch": 0.015213295300095082,
      "grad_norm": 0.10197355598211288,
      "learning_rate": 1e-06,
      "loss": 0.0355,
      "step": 163
    },
    {
      "clip_ratio/high_max": 0.002138756404747255,
      "clip_ratio/high_mean": 0.0008771116281423019,
      "clip_ratio/low_mean": 0.001067933022568468,
      "clip_ratio/low_min": 8.830692240735516e-05,
      "clip_ratio/region_mean": 0.0019450446707196534,
      "epoch": 0.015306628400095666,
      "grad_norm": 0.26354193687438965,
      "learning_rate": 1e-06,
      "loss": 0.057,
      "step": 164
    },
    {
      "clip_ratio/high_max": 0.0022207497313502245,
      "clip_ratio/high_mean": 0.000880809702721308,
      "clip_ratio/low_mean": 0.0010350446245865896,
      "clip_ratio/low_min": 0.00012348507243586937,
      "clip_ratio/region_mean": 0.001915854329126887,
      "epoch": 0.01539996150009625,
      "grad_norm": 0.10693710297346115,
      "learning_rate": 1e-06,
      "loss": 0.0462,
      "step": 165
    },
    {
      "clip_ratio/high_max": 0.002169806361052906,
      "clip_ratio/high_mean": 0.0008588912296545459,
      "clip_ratio/low_mean": 0.0009284107727580704,
      "clip_ratio/low_min": 9.478376341576222e-05,
      "clip_ratio/region_mean": 0.0017873020042316057,
      "epoch": 0.015493294600096833,
      "grad_norm": 0.10736197978258133,
      "learning_rate": 1e-06,
      "loss": 0.037,
      "step": 166
    },
    {
      "clip_ratio/high_max": 0.0023127159729483537,
      "clip_ratio/high_mean": 0.0009983401723729912,
      "clip_ratio/low_mean": 0.0009717591565276962,
      "clip_ratio/low_min": 0.00011505640941322781,
      "clip_ratio/region_mean": 0.0019700992852449417,
      "epoch": 0.015586627700097416,
      "grad_norm": 0.1165332943201065,
      "learning_rate": 1e-06,
      "loss": 0.0066,
      "step": 167
    },
    {
      "clip_ratio/high_max": 0.002206595156167168,
      "clip_ratio/high_mean": 0.0009195062084472738,
      "clip_ratio/low_mean": 0.0011236162354180124,
      "clip_ratio/low_min": 0.00011721985902113374,
      "clip_ratio/region_mean": 0.002043122469331138,
      "epoch": 0.015679960800098,
      "grad_norm": 0.11286017298698425,
      "learning_rate": 1e-06,
      "loss": 0.0355,
      "step": 168
    },
    {
      "clip_ratio/high_max": 0.0020838089440076146,
      "clip_ratio/high_mean": 0.0009937254653777927,
      "clip_ratio/low_mean": 0.0010102739634021418,
      "clip_ratio/low_min": 0.00010326492883905303,
      "clip_ratio/region_mean": 0.002003999368753284,
      "epoch": 0.015773293900098583,
      "grad_norm": 0.12594398856163025,
      "learning_rate": 1e-06,
      "loss": 0.0394,
      "step": 169
    },
    {
      "clip_ratio/high_max": 0.002377126300416421,
      "clip_ratio/high_mean": 0.0009301012614741921,
      "clip_ratio/low_mean": 0.0009329656841146061,
      "clip_ratio/low_min": 0.00011017421456926968,
      "clip_ratio/region_mean": 0.0018630669655976817,
      "epoch": 0.015866627000099165,
      "grad_norm": 0.11675780266523361,
      "learning_rate": 1e-06,
      "loss": -0.0,
      "step": 170
    },
    {
      "clip_ratio/high_max": 0.0020867814382654615,
      "clip_ratio/high_mean": 0.0008868259756127372,
      "clip_ratio/low_mean": 0.0010179107489420858,
      "clip_ratio/low_min": 0.0002070386108243838,
      "clip_ratio/region_mean": 0.0019047367459279485,
      "epoch": 0.01595996010009975,
      "grad_norm": 0.12032227963209152,
      "learning_rate": 1e-06,
      "loss": 0.0117,
      "step": 171
    },
    {
      "clip_ratio/high_max": 0.001971932768356055,
      "clip_ratio/high_mean": 0.0009522500204184325,
      "clip_ratio/low_mean": 0.0009487866918789223,
      "clip_ratio/low_min": 4.6684855078638066e-05,
      "clip_ratio/region_mean": 0.0019010366668226197,
      "epoch": 0.016053293200100332,
      "grad_norm": 0.11389598250389099,
      "learning_rate": 1e-06,
      "loss": 0.0139,
      "step": 172
    },
    {
      "clip_ratio/high_max": 0.002201709765358828,
      "clip_ratio/high_mean": 0.0008747073097765679,
      "clip_ratio/low_mean": 0.0011275410688540433,
      "clip_ratio/low_min": 0.0001378677898173919,
      "clip_ratio/region_mean": 0.0020022483586217277,
      "epoch": 0.016146626300100917,
      "grad_norm": 0.11421126872301102,
      "learning_rate": 1e-06,
      "loss": 0.0531,
      "step": 173
    },
    {
      "clip_ratio/high_max": 0.0022835715499240905,
      "clip_ratio/high_mean": 0.0009154123854386853,
      "clip_ratio/low_mean": 0.0008950499250204302,
      "clip_ratio/low_min": 5.714001599699259e-05,
      "clip_ratio/region_mean": 0.0018104623231920414,
      "epoch": 0.0162399594001015,
      "grad_norm": 0.12231060117483139,
      "learning_rate": 1e-06,
      "loss": 0.0477,
      "step": 174
    },
    {
      "clip_ratio/high_max": 0.002472468069754541,
      "clip_ratio/high_mean": 0.0010857721354113892,
      "clip_ratio/low_mean": 0.0010049748325400287,
      "clip_ratio/low_min": 2.7149178094987292e-05,
      "clip_ratio/region_mean": 0.0020907469479425345,
      "epoch": 0.016333292500102084,
      "grad_norm": 0.10905659943819046,
      "learning_rate": 1e-06,
      "loss": -0.0006,
      "step": 175
    },
    {
      "clip_ratio/high_max": 0.0022082540308474563,
      "clip_ratio/high_mean": 0.0008410517675656592,
      "clip_ratio/low_mean": 0.0009752658534125658,
      "clip_ratio/low_min": 0.00016588959351793164,
      "clip_ratio/region_mean": 0.001816317620978225,
      "epoch": 0.016426625600102666,
      "grad_norm": 0.10905282944440842,
      "learning_rate": 1e-06,
      "loss": 0.0108,
      "step": 176
    },
    {
      "clip_ratio/high_max": 0.002118591142789228,
      "clip_ratio/high_mean": 0.0009659828519943403,
      "clip_ratio/low_mean": 0.001117067993618548,
      "clip_ratio/low_min": 0.00015997291211533593,
      "clip_ratio/region_mean": 0.0020830508656217717,
      "epoch": 0.01651995870010325,
      "grad_norm": 0.10279494524002075,
      "learning_rate": 1e-06,
      "loss": 0.0483,
      "step": 177
    },
    {
      "clip_ratio/high_max": 0.0023061638967192266,
      "clip_ratio/high_mean": 0.00094044086017675,
      "clip_ratio/low_mean": 0.0011471924299257807,
      "clip_ratio/low_min": 7.573713992314879e-05,
      "clip_ratio/region_mean": 0.002087633343762718,
      "epoch": 0.016613291800103833,
      "grad_norm": 0.11682261526584625,
      "learning_rate": 1e-06,
      "loss": 0.0526,
      "step": 178
    },
    {
      "clip_ratio/high_max": 0.0019308992159494665,
      "clip_ratio/high_mean": 0.0008092739044514019,
      "clip_ratio/low_mean": 0.0009166926683974452,
      "clip_ratio/low_min": 0.00011727929722837871,
      "clip_ratio/region_mean": 0.0017259665910387412,
      "epoch": 0.016706624900104418,
      "grad_norm": 0.11142003536224365,
      "learning_rate": 1e-06,
      "loss": 0.019,
      "step": 179
    },
    {
      "clip_ratio/high_max": 0.002123392972862348,
      "clip_ratio/high_mean": 0.00096100414157263,
      "clip_ratio/low_mean": 0.0010481630997674074,
      "clip_ratio/low_min": 2.7603220587479882e-05,
      "clip_ratio/region_mean": 0.002009167248615995,
      "epoch": 0.016799958000105,
      "grad_norm": 0.10944481939077377,
      "learning_rate": 1e-06,
      "loss": 0.0443,
      "step": 180
    },
    {
      "clip_ratio/high_max": 0.0022595435148105025,
      "clip_ratio/high_mean": 0.0009288617347920081,
      "clip_ratio/low_mean": 0.0014279976403486216,
      "clip_ratio/low_min": 0.00011325609193590935,
      "clip_ratio/region_mean": 0.0023568593387608416,
      "epoch": 0.016893291100105585,
      "grad_norm": 0.1177840381860733,
      "learning_rate": 1e-06,
      "loss": 0.0605,
      "step": 181
    },
    {
      "clip_ratio/high_max": 0.002379469027800951,
      "clip_ratio/high_mean": 0.0010155923882848583,
      "clip_ratio/low_mean": 0.0010046198694908526,
      "clip_ratio/low_min": 8.140969748637872e-05,
      "clip_ratio/region_mean": 0.0020202122250339016,
      "epoch": 0.016986624200106167,
      "grad_norm": 0.1077289804816246,
      "learning_rate": 1e-06,
      "loss": -0.0078,
      "step": 182
    },
    {
      "clip_ratio/high_max": 0.002302628017787356,
      "clip_ratio/high_mean": 0.0008849685782479355,
      "clip_ratio/low_mean": 0.00109211862218217,
      "clip_ratio/low_min": 0.00016074363338702824,
      "clip_ratio/region_mean": 0.0019770871367654763,
      "epoch": 0.017079957300106748,
      "grad_norm": 0.2381676435470581,
      "learning_rate": 1e-06,
      "loss": 0.0438,
      "step": 183
    },
    {
      "clip_ratio/high_max": 0.0019240915207774378,
      "clip_ratio/high_mean": 0.0008243355241575046,
      "clip_ratio/low_mean": 0.0009939919491444016,
      "clip_ratio/low_min": 3.820173333224375e-05,
      "clip_ratio/region_mean": 0.0018183274114562664,
      "epoch": 0.017173290400107333,
      "grad_norm": 0.12016787379980087,
      "learning_rate": 1e-06,
      "loss": 0.0602,
      "step": 184
    },
    {
      "clip_ratio/high_max": 0.0024942127893154975,
      "clip_ratio/high_mean": 0.0010485043276275974,
      "clip_ratio/low_mean": 0.0009196217333737877,
      "clip_ratio/low_min": 9.459688953938894e-05,
      "clip_ratio/region_mean": 0.0019681260600918904,
      "epoch": 0.017266623500107915,
      "grad_norm": 0.09575652331113815,
      "learning_rate": 1e-06,
      "loss": -0.0141,
      "step": 185
    },
    {
      "clip_ratio/high_max": 0.002212736442743335,
      "clip_ratio/high_mean": 0.0009334607493656222,
      "clip_ratio/low_mean": 0.0010552561016083928,
      "clip_ratio/low_min": 6.551646765728947e-05,
      "clip_ratio/region_mean": 0.0019887168455170467,
      "epoch": 0.0173599566001085,
      "grad_norm": 0.10698789358139038,
      "learning_rate": 1e-06,
      "loss": 0.0436,
      "step": 186
    },
    {
      "clip_ratio/high_max": 0.0022086959615990054,
      "clip_ratio/high_mean": 0.0009477929706918076,
      "clip_ratio/low_mean": 0.0010155749187106267,
      "clip_ratio/low_min": 0.00011371195432730019,
      "clip_ratio/region_mean": 0.0019633678675745614,
      "epoch": 0.017453289700109082,
      "grad_norm": 0.11505325883626938,
      "learning_rate": 1e-06,
      "loss": 0.0456,
      "step": 187
    },
    {
      "clip_ratio/high_max": 0.002223488365416415,
      "clip_ratio/high_mean": 0.0009709603546070866,
      "clip_ratio/low_mean": 0.0009627137533243513,
      "clip_ratio/low_min": 5.509776292456081e-05,
      "clip_ratio/region_mean": 0.001933674058818724,
      "epoch": 0.017546622800109667,
      "grad_norm": 0.1694178283214569,
      "learning_rate": 1e-06,
      "loss": 0.0172,
      "step": 188
    },
    {
      "clip_ratio/high_max": 0.0022287796964519657,
      "clip_ratio/high_mean": 0.0009651735381339677,
      "clip_ratio/low_mean": 0.0009683517419034615,
      "clip_ratio/low_min": 4.17794562963536e-05,
      "clip_ratio/region_mean": 0.0019335253236931749,
      "epoch": 0.01763995590011025,
      "grad_norm": 0.11302310973405838,
      "learning_rate": 1e-06,
      "loss": 0.0375,
      "step": 189
    },
    {
      "clip_ratio/high_max": 0.0021402684069471434,
      "clip_ratio/high_mean": 0.0008638818180770613,
      "clip_ratio/low_mean": 0.0008136473952617962,
      "clip_ratio/low_min": 3.57307362719439e-05,
      "clip_ratio/region_mean": 0.0016775292278907727,
      "epoch": 0.017733289000110834,
      "grad_norm": 0.11362725496292114,
      "learning_rate": 1e-06,
      "loss": 0.0204,
      "step": 190
    },
    {
      "clip_ratio/high_max": 0.0021006721726735123,
      "clip_ratio/high_mean": 0.0009117627378145698,
      "clip_ratio/low_mean": 0.0009677176021796186,
      "clip_ratio/low_min": 4.301445369492285e-05,
      "clip_ratio/region_mean": 0.0018794803945638705,
      "epoch": 0.017826622100111416,
      "grad_norm": 0.11704517155885696,
      "learning_rate": 1e-06,
      "loss": 0.0209,
      "step": 191
    },
    {
      "clip_ratio/high_max": 0.001939426289027324,
      "clip_ratio/high_mean": 0.0009004323474073317,
      "clip_ratio/low_mean": 0.0009891694389807526,
      "clip_ratio/low_min": 0.0001037706706483732,
      "clip_ratio/region_mean": 0.0018896018009399995,
      "epoch": 0.017919955200112,
      "grad_norm": 0.107717365026474,
      "learning_rate": 1e-06,
      "loss": 0.0227,
      "step": 192
    },
    {
      "clip_ratio/high_max": 0.002167451471905224,
      "clip_ratio/high_mean": 0.0007966815464897081,
      "clip_ratio/low_mean": 0.0011213892066734843,
      "clip_ratio/low_min": 5.822916318720672e-05,
      "clip_ratio/region_mean": 0.0019180707895429805,
      "epoch": 0.018013288300112583,
      "grad_norm": 0.11653489619493484,
      "learning_rate": 1e-06,
      "loss": 0.0764,
      "step": 193
    },
    {
      "clip_ratio/high_max": 0.0020121706256759353,
      "clip_ratio/high_mean": 0.0008923529694584431,
      "clip_ratio/low_mean": 0.0011409554972487967,
      "clip_ratio/low_min": 0.00020639755166484974,
      "clip_ratio/region_mean": 0.002033308512181975,
      "epoch": 0.018106621400113165,
      "grad_norm": 0.10933557897806168,
      "learning_rate": 1e-06,
      "loss": 0.03,
      "step": 194
    },
    {
      "clip_ratio/high_max": 0.001967484855413204,
      "clip_ratio/high_mean": 0.0008534214885003166,
      "clip_ratio/low_mean": 0.0010785847280203598,
      "clip_ratio/low_min": 3.398756052774843e-05,
      "clip_ratio/region_mean": 0.0019320062710903585,
      "epoch": 0.01819995450011375,
      "grad_norm": 0.11805937439203262,
      "learning_rate": 1e-06,
      "loss": 0.0371,
      "step": 195
    },
    {
      "clip_ratio/high_max": 0.002049378599622287,
      "clip_ratio/high_mean": 0.0009569281064614188,
      "clip_ratio/low_mean": 0.0009143788884102833,
      "clip_ratio/low_min": 8.688524758326821e-05,
      "clip_ratio/region_mean": 0.0018713069512159564,
      "epoch": 0.01829328760011433,
      "grad_norm": 0.10525800287723541,
      "learning_rate": 1e-06,
      "loss": -0.0058,
      "step": 196
    },
    {
      "clip_ratio/high_max": 0.0021906488509557676,
      "clip_ratio/high_mean": 0.0009428213979845168,
      "clip_ratio/low_mean": 0.0010363991423218977,
      "clip_ratio/low_min": 0.00011028917106159497,
      "clip_ratio/region_mean": 0.0019792204911937006,
      "epoch": 0.018386620700114917,
      "grad_norm": 0.11151842772960663,
      "learning_rate": 1e-06,
      "loss": 0.0296,
      "step": 197
    },
    {
      "clip_ratio/high_max": 0.0018811374466167763,
      "clip_ratio/high_mean": 0.0008195067366614239,
      "clip_ratio/low_mean": 0.0008978890673461137,
      "clip_ratio/low_min": 6.23137839284027e-05,
      "clip_ratio/region_mean": 0.0017173958331113681,
      "epoch": 0.0184799538001155,
      "grad_norm": 0.10290457308292389,
      "learning_rate": 1e-06,
      "loss": 0.0346,
      "step": 198
    },
    {
      "clip_ratio/high_max": 0.00213869426806923,
      "clip_ratio/high_mean": 0.0008587574375269469,
      "clip_ratio/low_mean": 0.0010173071113968035,
      "clip_ratio/low_min": 7.005389124969952e-05,
      "clip_ratio/region_mean": 0.0018760645689326338,
      "epoch": 0.018573286900116084,
      "grad_norm": 0.10898451507091522,
      "learning_rate": 1e-06,
      "loss": 0.0355,
      "step": 199
    },
    {
      "clip_ratio/high_max": 0.0020946437398379203,
      "clip_ratio/high_mean": 0.0008866869247867726,
      "clip_ratio/low_mean": 0.0011017338583769742,
      "clip_ratio/low_min": 0.00014374458260135725,
      "clip_ratio/region_mean": 0.0019884207722498104,
      "epoch": 0.018666620000116665,
      "grad_norm": 0.11538136005401611,
      "learning_rate": 1e-06,
      "loss": -0.0077,
      "step": 200
    },
    {
      "clip_ratio/high_max": 0.0021541278692893684,
      "clip_ratio/high_mean": 0.0009477971761953086,
      "clip_ratio/low_mean": 0.0010456737400090788,
      "clip_ratio/low_min": 7.926578655315097e-05,
      "clip_ratio/region_mean": 0.0019934709125664085,
      "epoch": 0.01875995310011725,
      "grad_norm": 0.1162070706486702,
      "learning_rate": 1e-06,
      "loss": 0.0244,
      "step": 201
    },
    {
      "clip_ratio/high_max": 0.0023056704776536208,
      "clip_ratio/high_mean": 0.0010438414428790566,
      "clip_ratio/low_mean": 0.0011379790121281985,
      "clip_ratio/low_min": 0.00012575384744195617,
      "clip_ratio/region_mean": 0.0021818204695591703,
      "epoch": 0.018853286200117832,
      "grad_norm": 0.11591261625289917,
      "learning_rate": 1e-06,
      "loss": 0.0308,
      "step": 202
    },
    {
      "clip_ratio/high_max": 0.0020941249531460926,
      "clip_ratio/high_mean": 0.0008581130496168043,
      "clip_ratio/low_mean": 0.0009921733508235775,
      "clip_ratio/low_min": 0.00011524317960720509,
      "clip_ratio/region_mean": 0.0018502863749745302,
      "epoch": 0.018946619300118418,
      "grad_norm": 0.10963311046361923,
      "learning_rate": 1e-06,
      "loss": 0.0724,
      "step": 203
    },
    {
      "clip_ratio/high_max": 0.0022479714098153636,
      "clip_ratio/high_mean": 0.0010425368418509606,
      "clip_ratio/low_mean": 0.0009532710992061766,
      "clip_ratio/low_min": 8.883651571522932e-05,
      "clip_ratio/region_mean": 0.001995807957428042,
      "epoch": 0.019039952400119,
      "grad_norm": 0.10802527517080307,
      "learning_rate": 1e-06,
      "loss": 0.0092,
      "step": 204
    },
    {
      "clip_ratio/high_max": 0.002085646046907641,
      "clip_ratio/high_mean": 0.000918427813303424,
      "clip_ratio/low_mean": 0.0010653214121703058,
      "clip_ratio/low_min": 0.00010971641950163757,
      "clip_ratio/region_mean": 0.0019837492363876663,
      "epoch": 0.019133285500119585,
      "grad_norm": 0.11404747515916824,
      "learning_rate": 1e-06,
      "loss": -0.0062,
      "step": 205
    },
    {
      "clip_ratio/high_max": 0.0021899579296587035,
      "clip_ratio/high_mean": 0.0009628759780753171,
      "clip_ratio/low_mean": 0.001122700450650882,
      "clip_ratio/low_min": 6.675414169876603e-05,
      "clip_ratio/region_mean": 0.002085576386889443,
      "epoch": 0.019226618600120166,
      "grad_norm": 0.107424296438694,
      "learning_rate": 1e-06,
      "loss": 0.02,
      "step": 206
    },
    {
      "clip_ratio/high_max": 0.0023592188117618207,
      "clip_ratio/high_mean": 0.0009842861445577,
      "clip_ratio/low_mean": 0.0009870921130641364,
      "clip_ratio/low_min": 0.0001591050222486956,
      "clip_ratio/region_mean": 0.0019713782603503205,
      "epoch": 0.019319951700120748,
      "grad_norm": 0.12021970003843307,
      "learning_rate": 1e-06,
      "loss": -0.017,
      "step": 207
    },
    {
      "clip_ratio/high_max": 0.0020937302251695655,
      "clip_ratio/high_mean": 0.0010327574600523803,
      "clip_ratio/low_mean": 0.000963145883360994,
      "clip_ratio/low_min": 0.00011117216126876883,
      "clip_ratio/region_mean": 0.0019959033306804486,
      "epoch": 0.019413284800121333,
      "grad_norm": 0.12263026833534241,
      "learning_rate": 1e-06,
      "loss": 0.0358,
      "step": 208
    },
    {
      "clip_ratio/high_max": 0.0018762995568977203,
      "clip_ratio/high_mean": 0.0008226645895774709,
      "clip_ratio/low_mean": 0.00111507356268703,
      "clip_ratio/low_min": 6.65598063278594e-05,
      "clip_ratio/region_mean": 0.0019377381104277447,
      "epoch": 0.019506617900121915,
      "grad_norm": 0.10565012693405151,
      "learning_rate": 1e-06,
      "loss": 0.0524,
      "step": 209
    },
    {
      "clip_ratio/high_max": 0.002638690668391064,
      "clip_ratio/high_mean": 0.001115183131332742,
      "clip_ratio/low_mean": 0.000947213296967675,
      "clip_ratio/low_min": 8.75063205967308e-05,
      "clip_ratio/region_mean": 0.0020623964446713217,
      "epoch": 0.0195999510001225,
      "grad_norm": 0.12090546637773514,
      "learning_rate": 1e-06,
      "loss": -0.0036,
      "step": 210
    },
    {
      "clip_ratio/high_max": 0.002234870982647408,
      "clip_ratio/high_mean": 0.000933173583689495,
      "clip_ratio/low_mean": 0.0010040104261861416,
      "clip_ratio/low_min": 0.00018935407115350245,
      "clip_ratio/region_mean": 0.001937184002599679,
      "epoch": 0.019693284100123082,
      "grad_norm": 0.11095651239156723,
      "learning_rate": 1e-06,
      "loss": 0.0193,
      "step": 211
    },
    {
      "clip_ratio/high_max": 0.002367613349633757,
      "clip_ratio/high_mean": 0.0010650542826624587,
      "clip_ratio/low_mean": 0.0009907163857860724,
      "clip_ratio/low_min": 1.414347116224235e-05,
      "clip_ratio/region_mean": 0.0020557706302497536,
      "epoch": 0.019786617200123667,
      "grad_norm": 0.13546325266361237,
      "learning_rate": 1e-06,
      "loss": -0.0164,
      "step": 212
    },
    {
      "clip_ratio/high_max": 0.0019728094557649456,
      "clip_ratio/high_mean": 0.000914378544621286,
      "clip_ratio/low_mean": 0.0009974736640288029,
      "clip_ratio/low_min": 6.0291994486760814e-05,
      "clip_ratio/region_mean": 0.001911852195917163,
      "epoch": 0.01987995030012425,
      "grad_norm": 0.1279425323009491,
      "learning_rate": 1e-06,
      "loss": 0.008,
      "step": 213
    },
    {
      "clip_ratio/high_max": 0.0023448467436537612,
      "clip_ratio/high_mean": 0.0010103245003847405,
      "clip_ratio/low_mean": 0.0010073525190819055,
      "clip_ratio/low_min": 0.000172418247530004,
      "clip_ratio/region_mean": 0.0020176769903628156,
      "epoch": 0.019973283400124834,
      "grad_norm": 0.10428622364997864,
      "learning_rate": 1e-06,
      "loss": 0.0363,
      "step": 214
    },
    {
      "clip_ratio/high_max": 0.001850732911407249,
      "clip_ratio/high_mean": 0.0008369260494873743,
      "clip_ratio/low_mean": 0.001212673098052619,
      "clip_ratio/low_min": 0.00016832503297337098,
      "clip_ratio/region_mean": 0.0020495992284850217,
      "epoch": 0.020066616500125416,
      "grad_norm": 0.11830378323793411,
      "learning_rate": 1e-06,
      "loss": 0.0532,
      "step": 215
    },
    {
      "clip_ratio/high_max": 0.001899744020192884,
      "clip_ratio/high_mean": 0.0008709589128557127,
      "clip_ratio/low_mean": 0.0008804627850622637,
      "clip_ratio/low_min": 4.245876698405482e-05,
      "clip_ratio/region_mean": 0.0017514217033749446,
      "epoch": 0.020159949600126,
      "grad_norm": 0.11459111422300339,
      "learning_rate": 1e-06,
      "loss": 0.0289,
      "step": 216
    },
    {
      "clip_ratio/high_max": 0.0017330941154796164,
      "clip_ratio/high_mean": 0.0007122519618860679,
      "clip_ratio/low_mean": 0.0011193732025276404,
      "clip_ratio/low_min": 0.00011346063456585398,
      "clip_ratio/region_mean": 0.0018316251662326977,
      "epoch": 0.020253282700126583,
      "grad_norm": 0.11213616281747818,
      "learning_rate": 1e-06,
      "loss": 0.0714,
      "step": 217
    },
    {
      "clip_ratio/high_max": 0.002310619624040555,
      "clip_ratio/high_mean": 0.0010488324478501454,
      "clip_ratio/low_mean": 0.0009332481240562629,
      "clip_ratio/low_min": 9.051858432940207e-05,
      "clip_ratio/region_mean": 0.001982080502784811,
      "epoch": 0.020346615800127168,
      "grad_norm": 0.10472150146961212,
      "learning_rate": 1e-06,
      "loss": 0.0103,
      "step": 218
    },
    {
      "clip_ratio/high_max": 0.00214025368768489,
      "clip_ratio/high_mean": 0.0009075563848455204,
      "clip_ratio/low_mean": 0.0010840917584573617,
      "clip_ratio/low_min": 0.0001759737770044012,
      "clip_ratio/region_mean": 0.001991648146940861,
      "epoch": 0.02043994890012775,
      "grad_norm": 0.11451179534196854,
      "learning_rate": 1e-06,
      "loss": 0.0232,
      "step": 219
    },
    {
      "clip_ratio/high_max": 0.0019043495485675521,
      "clip_ratio/high_mean": 0.0008271847873402294,
      "clip_ratio/low_mean": 0.001076140339137055,
      "clip_ratio/low_min": 0.0001006030588541762,
      "clip_ratio/region_mean": 0.0019033251446671784,
      "epoch": 0.02053328200012833,
      "grad_norm": 0.11380618810653687,
      "learning_rate": 1e-06,
      "loss": 0.0546,
      "step": 220
    },
    {
      "clip_ratio/high_max": 0.0021941617524134926,
      "clip_ratio/high_mean": 0.0009049884847627254,
      "clip_ratio/low_mean": 0.0011537418358784635,
      "clip_ratio/low_min": 8.618706942797871e-05,
      "clip_ratio/region_mean": 0.002058730271528475,
      "epoch": 0.020626615100128916,
      "grad_norm": 0.12104861438274384,
      "learning_rate": 1e-06,
      "loss": 0.017,
      "step": 221
    },
    {
      "clip_ratio/high_max": 0.0024534166004741564,
      "clip_ratio/high_mean": 0.0009078702751139645,
      "clip_ratio/low_mean": 0.0009813616561586969,
      "clip_ratio/low_min": 5.7123578699247446e-05,
      "clip_ratio/region_mean": 0.001889231956738513,
      "epoch": 0.020719948200129498,
      "grad_norm": 0.11052046716213226,
      "learning_rate": 1e-06,
      "loss": 0.0108,
      "step": 222
    },
    {
      "clip_ratio/high_max": 0.002098733984894352,
      "clip_ratio/high_mean": 0.000848316016345052,
      "clip_ratio/low_mean": 0.0010787546780193225,
      "clip_ratio/low_min": 0.00012500591947173234,
      "clip_ratio/region_mean": 0.0019270707198302262,
      "epoch": 0.020813281300130083,
      "grad_norm": 0.109070785343647,
      "learning_rate": 1e-06,
      "loss": 0.0478,
      "step": 223
    },
    {
      "clip_ratio/high_max": 0.0022960092064749915,
      "clip_ratio/high_mean": 0.00092519794452528,
      "clip_ratio/low_mean": 0.0009774558420758694,
      "clip_ratio/low_min": 0.00015045182044559624,
      "clip_ratio/region_mean": 0.0019026537629542872,
      "epoch": 0.020906614400130665,
      "grad_norm": 0.11426587402820587,
      "learning_rate": 1e-06,
      "loss": 0.0267,
      "step": 224
    },
    {
      "clip_ratio/high_max": 0.002138144125638064,
      "clip_ratio/high_mean": 0.0008678825925017009,
      "clip_ratio/low_mean": 0.0009975082921300782,
      "clip_ratio/low_min": 5.39730763193802e-05,
      "clip_ratio/region_mean": 0.0018653908555279486,
      "epoch": 0.02099994750013125,
      "grad_norm": 0.10962416231632233,
      "learning_rate": 1e-06,
      "loss": 0.053,
      "step": 225
    },
    {
      "clip_ratio/high_max": 0.002490065286110621,
      "clip_ratio/high_mean": 0.0011171596561325714,
      "clip_ratio/low_mean": 0.0008788071827439126,
      "clip_ratio/low_min": 1.9311972209834494e-05,
      "clip_ratio/region_mean": 0.001995966878894251,
      "epoch": 0.021093280600131832,
      "grad_norm": 0.1325608193874359,
      "learning_rate": 1e-06,
      "loss": -0.0415,
      "step": 226
    },
    {
      "clip_ratio/high_max": 0.0021953234463580884,
      "clip_ratio/high_mean": 0.0009879996432573535,
      "clip_ratio/low_mean": 0.0008496245955029735,
      "clip_ratio/low_min": 7.815466551619465e-05,
      "clip_ratio/region_mean": 0.00183762422966538,
      "epoch": 0.021186613700132417,
      "grad_norm": 0.11213158816099167,
      "learning_rate": 1e-06,
      "loss": 0.0001,
      "step": 227
    },
    {
      "clip_ratio/high_max": 0.0024829938847688027,
      "clip_ratio/high_mean": 0.000908926005649846,
      "clip_ratio/low_mean": 0.0010305980467819609,
      "clip_ratio/low_min": 0.00010798132279887795,
      "clip_ratio/region_mean": 0.0019395240597077645,
      "epoch": 0.021279946800133,
      "grad_norm": 0.11000971496105194,
      "learning_rate": 1e-06,
      "loss": 0.0347,
      "step": 228
    },
    {
      "clip_ratio/high_max": 0.002539554610848427,
      "clip_ratio/high_mean": 0.0010273880143358838,
      "clip_ratio/low_mean": 0.0011381345757399686,
      "clip_ratio/low_min": 0.00015615619122399949,
      "clip_ratio/region_mean": 0.0021655225864378735,
      "epoch": 0.021373279900133584,
      "grad_norm": 0.1189996749162674,
      "learning_rate": 1e-06,
      "loss": 0.0251,
      "step": 229
    },
    {
      "clip_ratio/high_max": 0.0024407244491158053,
      "clip_ratio/high_mean": 0.0010192626468779054,
      "clip_ratio/low_mean": 0.0009032363959704526,
      "clip_ratio/low_min": 4.907828588329721e-05,
      "clip_ratio/region_mean": 0.0019224990901420824,
      "epoch": 0.021466613000134166,
      "grad_norm": 0.11909337341785431,
      "learning_rate": 1e-06,
      "loss": -0.0178,
      "step": 230
    },
    {
      "clip_ratio/high_max": 0.002424677564704325,
      "clip_ratio/high_mean": 0.0010363195215177257,
      "clip_ratio/low_mean": 0.0010111930096172728,
      "clip_ratio/low_min": 5.805942964798305e-05,
      "clip_ratio/region_mean": 0.0020475125347729772,
      "epoch": 0.02155994610013475,
      "grad_norm": 0.11340123414993286,
      "learning_rate": 1e-06,
      "loss": 0.0336,
      "step": 231
    },
    {
      "clip_ratio/high_max": 0.0019159656076226383,
      "clip_ratio/high_mean": 0.0008645427242299775,
      "clip_ratio/low_mean": 0.0010895783270825632,
      "clip_ratio/low_min": 7.422575754389982e-05,
      "clip_ratio/region_mean": 0.0019541210785973817,
      "epoch": 0.021653279200135333,
      "grad_norm": 0.11788474768400192,
      "learning_rate": 1e-06,
      "loss": 0.0679,
      "step": 232
    },
    {
      "clip_ratio/high_max": 0.0019080695492448285,
      "clip_ratio/high_mean": 0.0007964155192894395,
      "clip_ratio/low_mean": 0.0010572892570053227,
      "clip_ratio/low_min": 0.00017893908352561994,
      "clip_ratio/region_mean": 0.0018537047653808258,
      "epoch": 0.021746612300135915,
      "grad_norm": 0.12439021468162537,
      "learning_rate": 1e-06,
      "loss": 0.054,
      "step": 233
    },
    {
      "clip_ratio/high_max": 0.0021464417659444734,
      "clip_ratio/high_mean": 0.0009470107142988127,
      "clip_ratio/low_mean": 0.0010860409747692756,
      "clip_ratio/low_min": 0.00018239432210975792,
      "clip_ratio/region_mean": 0.002033051656326279,
      "epoch": 0.0218399454001365,
      "grad_norm": 0.11479232460260391,
      "learning_rate": 1e-06,
      "loss": -0.0018,
      "step": 234
    },
    {
      "clip_ratio/high_max": 0.00214841213892214,
      "clip_ratio/high_mean": 0.000886670812178636,
      "clip_ratio/low_mean": 0.0011134746582683874,
      "clip_ratio/low_min": 0.00018994514721271116,
      "clip_ratio/region_mean": 0.002000145508645801,
      "epoch": 0.02193327850013708,
      "grad_norm": 0.09970298409461975,
      "learning_rate": 1e-06,
      "loss": 0.023,
      "step": 235
    },
    {
      "clip_ratio/high_max": 0.002168571067159064,
      "clip_ratio/high_mean": 0.0008643800611025654,
      "clip_ratio/low_mean": 0.0010122475841853884,
      "clip_ratio/low_min": 6.922038573975442e-05,
      "clip_ratio/region_mean": 0.0018766276334645227,
      "epoch": 0.022026611600137667,
      "grad_norm": 0.1070210263133049,
      "learning_rate": 1e-06,
      "loss": 0.0178,
      "step": 236
    },
    {
      "clip_ratio/high_max": 0.002073378796922043,
      "clip_ratio/high_mean": 0.0009625376042095013,
      "clip_ratio/low_mean": 0.000940343423280865,
      "clip_ratio/low_min": 2.969238721561851e-05,
      "clip_ratio/region_mean": 0.0019028810274903663,
      "epoch": 0.02211994470013825,
      "grad_norm": 0.13581731915473938,
      "learning_rate": 1e-06,
      "loss": 0.0274,
      "step": 237
    },
    {
      "clip_ratio/high_max": 0.002210548824223224,
      "clip_ratio/high_mean": 0.0008758097883401206,
      "clip_ratio/low_mean": 0.0011279759019089397,
      "clip_ratio/low_min": 8.098124817479402e-05,
      "clip_ratio/region_mean": 0.0020037857102579437,
      "epoch": 0.022213277800138834,
      "grad_norm": 0.12062512338161469,
      "learning_rate": 1e-06,
      "loss": 0.0426,
      "step": 238
    },
    {
      "clip_ratio/high_max": 0.0022998643544269726,
      "clip_ratio/high_mean": 0.0009921831151586957,
      "clip_ratio/low_mean": 0.0010372236283728853,
      "clip_ratio/low_min": 7.738099884591065e-05,
      "clip_ratio/region_mean": 0.002029406801739242,
      "epoch": 0.022306610900139415,
      "grad_norm": 0.1370217353105545,
      "learning_rate": 1e-06,
      "loss": 0.0009,
      "step": 239
    },
    {
      "clip_ratio/high_max": 0.0024262699225801043,
      "clip_ratio/high_mean": 0.000984808248176705,
      "clip_ratio/low_mean": 0.0009955452132999199,
      "clip_ratio/low_min": 9.318272987002274e-05,
      "clip_ratio/region_mean": 0.001980353452381678,
      "epoch": 0.02239994400014,
      "grad_norm": 0.11358516663312912,
      "learning_rate": 1e-06,
      "loss": 0.0077,
      "step": 240
    },
    {
      "clip_ratio/high_max": 0.0025296202147728764,
      "clip_ratio/high_mean": 0.0008934057877922896,
      "clip_ratio/low_mean": 0.0010643806599546224,
      "clip_ratio/low_min": 7.650142106285784e-05,
      "clip_ratio/region_mean": 0.0019577864950406365,
      "epoch": 0.022493277100140582,
      "grad_norm": 0.1107291653752327,
      "learning_rate": 1e-06,
      "loss": 0.0128,
      "step": 241
    },
    {
      "clip_ratio/high_max": 0.0023834252351662144,
      "clip_ratio/high_mean": 0.0009954757606465137,
      "clip_ratio/low_mean": 0.0010605910792946815,
      "clip_ratio/low_min": 0.00011055981985919061,
      "clip_ratio/region_mean": 0.002056066870864015,
      "epoch": 0.022586610200141168,
      "grad_norm": 0.11257448047399521,
      "learning_rate": 1e-06,
      "loss": -0.0146,
      "step": 242
    },
    {
      "clip_ratio/high_max": 0.0021795274733449332,
      "clip_ratio/high_mean": 0.0009250603907275945,
      "clip_ratio/low_mean": 0.0010644061894709012,
      "clip_ratio/low_min": 0.00018681574238144094,
      "clip_ratio/region_mean": 0.0019894666256732307,
      "epoch": 0.02267994330014175,
      "grad_norm": 0.11343173682689667,
      "learning_rate": 1e-06,
      "loss": 0.0204,
      "step": 243
    },
    {
      "clip_ratio/high_max": 0.002128443305991823,
      "clip_ratio/high_mean": 0.0009035770835907897,
      "clip_ratio/low_mean": 0.0010444948529766407,
      "clip_ratio/low_min": 0.0001148682404163992,
      "clip_ratio/region_mean": 0.0019480719056446105,
      "epoch": 0.022773276400142334,
      "grad_norm": 0.1172831729054451,
      "learning_rate": 1e-06,
      "loss": 0.0257,
      "step": 244
    },
    {
      "clip_ratio/high_max": 0.0021832419151905924,
      "clip_ratio/high_mean": 0.0009231668518623337,
      "clip_ratio/low_mean": 0.0011320406265440397,
      "clip_ratio/low_min": 8.43684620122076e-05,
      "clip_ratio/region_mean": 0.002055207463854458,
      "epoch": 0.022866609500142916,
      "grad_norm": 0.11971227824687958,
      "learning_rate": 1e-06,
      "loss": 0.0223,
      "step": 245
    },
    {
      "clip_ratio/high_max": 0.002301872031239327,
      "clip_ratio/high_mean": 0.0009581696031091269,
      "clip_ratio/low_mean": 0.00104950022068806,
      "clip_ratio/low_min": 9.482742461841553e-05,
      "clip_ratio/region_mean": 0.0020076698347111233,
      "epoch": 0.022959942600143498,
      "grad_norm": 0.12075507640838623,
      "learning_rate": 1e-06,
      "loss": 0.0184,
      "step": 246
    },
    {
      "clip_ratio/high_max": 0.0023539223766420037,
      "clip_ratio/high_mean": 0.000887859448994277,
      "clip_ratio/low_mean": 0.0012119601451558992,
      "clip_ratio/low_min": 0.00017464127631683368,
      "clip_ratio/region_mean": 0.0020998196268919855,
      "epoch": 0.023053275700144083,
      "grad_norm": 0.10851837694644928,
      "learning_rate": 1e-06,
      "loss": 0.0383,
      "step": 247
    },
    {
      "clip_ratio/high_max": 0.0021011630233260803,
      "clip_ratio/high_mean": 0.0010566969467618037,
      "clip_ratio/low_mean": 0.0010376392747275531,
      "clip_ratio/low_min": 8.686814544489607e-05,
      "clip_ratio/region_mean": 0.002094336217851378,
      "epoch": 0.023146608800144665,
      "grad_norm": 0.11641940474510193,
      "learning_rate": 1e-06,
      "loss": -0.04,
      "step": 248
    },
    {
      "clip_ratio/high_max": 0.0022874041096656583,
      "clip_ratio/high_mean": 0.001076203345292015,
      "clip_ratio/low_mean": 0.0013142316711309832,
      "clip_ratio/low_min": 0.00020346790370240342,
      "clip_ratio/region_mean": 0.0023904349873191677,
      "epoch": 0.02323994190014525,
      "grad_norm": 0.12583139538764954,
      "learning_rate": 1e-06,
      "loss": 0.0693,
      "step": 249
    },
    {
      "clip_ratio/high_max": 0.002026106718403753,
      "clip_ratio/high_mean": 0.0009205698734149337,
      "clip_ratio/low_mean": 0.001014294037304353,
      "clip_ratio/low_min": 9.524939650873421e-05,
      "clip_ratio/region_mean": 0.0019348639252712019,
      "epoch": 0.023333275000145832,
      "grad_norm": 0.1877448707818985,
      "learning_rate": 1e-06,
      "loss": -0.0274,
      "step": 250
    },
    {
      "clip_ratio/high_max": 0.0019113739399472252,
      "clip_ratio/high_mean": 0.0008814228458504658,
      "clip_ratio/low_mean": 0.0009779076699487632,
      "clip_ratio/low_min": 3.899715557054151e-05,
      "clip_ratio/region_mean": 0.00185933054308407,
      "epoch": 0.023426608100146417,
      "grad_norm": 0.14381368458271027,
      "learning_rate": 1e-06,
      "loss": 0.0178,
      "step": 251
    },
    {
      "clip_ratio/high_max": 0.002252974092698423,
      "clip_ratio/high_mean": 0.0008434499231952941,
      "clip_ratio/low_mean": 0.0013243314788269345,
      "clip_ratio/low_min": 0.00016336069893441163,
      "clip_ratio/region_mean": 0.002167781407479197,
      "epoch": 0.023519941200147,
      "grad_norm": 2.371664524078369,
      "learning_rate": 1e-06,
      "loss": 0.0716,
      "step": 252
    },
    {
      "clip_ratio/high_max": 0.002164042853110004,
      "clip_ratio/high_mean": 0.0009433994600840379,
      "clip_ratio/low_mean": 0.001225969301231089,
      "clip_ratio/low_min": 0.00019286684573671664,
      "clip_ratio/region_mean": 0.0021693687594961375,
      "epoch": 0.023613274300147584,
      "grad_norm": 0.10952296108007431,
      "learning_rate": 1e-06,
      "loss": 0.0349,
      "step": 253
    },
    {
      "clip_ratio/high_max": 0.002279012966027949,
      "clip_ratio/high_mean": 0.0010077389742946252,
      "clip_ratio/low_mean": 0.0011922855592274573,
      "clip_ratio/low_min": 0.00017263070185435936,
      "clip_ratio/region_mean": 0.002200024522608146,
      "epoch": 0.023706607400148166,
      "grad_norm": 0.12145056575536728,
      "learning_rate": 1e-06,
      "loss": 0.0475,
      "step": 254
    },
    {
      "clip_ratio/high_max": 0.002155759902962018,
      "clip_ratio/high_mean": 0.0009342498997284565,
      "clip_ratio/low_mean": 0.0009492247372691054,
      "clip_ratio/low_min": 5.5615576457057614e-05,
      "clip_ratio/region_mean": 0.0018834746442735195,
      "epoch": 0.02379994050014875,
      "grad_norm": 0.10751894861459732,
      "learning_rate": 1e-06,
      "loss": -0.0167,
      "step": 255
    },
    {
      "clip_ratio/high_max": 0.0021634652803186327,
      "clip_ratio/high_mean": 0.0008521262952854158,
      "clip_ratio/low_mean": 0.0012216700488352217,
      "clip_ratio/low_min": 4.012518684248789e-05,
      "clip_ratio/region_mean": 0.002073796364129521,
      "epoch": 0.023893273600149333,
      "grad_norm": 0.11659747362136841,
      "learning_rate": 1e-06,
      "loss": 0.0252,
      "step": 256
    },
    {
      "clip_ratio/high_max": 0.0023720954268355854,
      "clip_ratio/high_mean": 0.0009556506665830966,
      "clip_ratio/low_mean": 0.0009196366409014445,
      "clip_ratio/low_min": 4.506940604187548e-05,
      "clip_ratio/region_mean": 0.0018752872856566682,
      "completions/clipped_ratio": 0.0135498046875,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4095.0,
      "completions/mean_length": 608.2213134765625,
      "completions/mean_terminated_length": 560.3133544921875,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.023986606700149918,
      "grad_norm": 101.60354614257812,
      "learning_rate": 1e-06,
      "loss": 0.2708,
      "num_tokens": 243481278.0,
      "reward": 0.5733642578125,
      "reward_std": 0.19922226667404175,
      "rewards/simpleverify_reward/mean": 0.5733642578125,
      "rewards/simpleverify_reward/std": 0.494590699672699,
      "step": 257
    },
    {
      "clip_ratio/high_max": 0.0021538904729823116,
      "clip_ratio/high_mean": 0.0009296576226915931,
      "clip_ratio/low_mean": 0.001109331686166115,
      "clip_ratio/low_min": 9.17857860258664e-05,
      "clip_ratio/region_mean": 0.0020389893179526553,
      "epoch": 0.0240799398001505,
      "grad_norm": 0.11701799184083939,
      "learning_rate": 1e-06,
      "loss": 0.0371,
      "step": 258
    },
    {
      "clip_ratio/high_max": 0.0023623750785191078,
      "clip_ratio/high_mean": 0.0008973419080575695,
      "clip_ratio/low_mean": 0.000874067680342705,
      "clip_ratio/low_min": 4.655217890103813e-05,
      "clip_ratio/region_mean": 0.0017714095920382533,
      "epoch": 0.02417327290015108,
      "grad_norm": 0.23635396361351013,
      "learning_rate": 1e-06,
      "loss": 0.0207,
      "step": 259
    },
    {
      "clip_ratio/high_max": 0.001980001041374635,
      "clip_ratio/high_mean": 0.0008090350147540448,
      "clip_ratio/low_mean": 0.0009179293028864777,
      "clip_ratio/low_min": 8.68928373165545e-05,
      "clip_ratio/region_mean": 0.001726964306726586,
      "epoch": 0.024266606000151666,
      "grad_norm": 0.09978413581848145,
      "learning_rate": 1e-06,
      "loss": 0.0265,
      "step": 260
    },
    {
      "clip_ratio/high_max": 0.0020471981188165955,
      "clip_ratio/high_mean": 0.0008724212530069053,
      "clip_ratio/low_mean": 0.0009256584289687453,
      "clip_ratio/low_min": 7.888262553024106e-05,
      "clip_ratio/region_mean": 0.00179807968379464,
      "epoch": 0.024359939100152248,
      "grad_norm": 1.4574960470199585,
      "learning_rate": 1e-06,
      "loss": 0.0269,
      "step": 261
    },
    {
      "clip_ratio/high_max": 0.0023386417669826187,
      "clip_ratio/high_mean": 0.0010859356661967468,
      "clip_ratio/low_mean": 0.0008676300567458384,
      "clip_ratio/low_min": 3.0226190574467182e-05,
      "clip_ratio/region_mean": 0.001953565741132479,
      "epoch": 0.024453272200152833,
      "grad_norm": 0.11507795751094818,
      "learning_rate": 1e-06,
      "loss": -0.0231,
      "step": 262
    },
    {
      "clip_ratio/high_max": 0.0021133939881110564,
      "clip_ratio/high_mean": 0.0009408792211615946,
      "clip_ratio/low_mean": 0.0010678440903575392,
      "clip_ratio/low_min": 0.00013820266303810058,
      "clip_ratio/region_mean": 0.002008723356993869,
      "epoch": 0.024546605300153415,
      "grad_norm": 0.12888933718204498,
      "learning_rate": 1e-06,
      "loss": 0.0651,
      "step": 263
    },
    {
      "clip_ratio/high_max": 0.0019742484982998576,
      "clip_ratio/high_mean": 0.0008053209021454677,
      "clip_ratio/low_mean": 0.0009693596948636696,
      "clip_ratio/low_min": 0.0001142224846262252,
      "clip_ratio/region_mean": 0.0017746805606293492,
      "epoch": 0.024639938400154,
      "grad_norm": 211872.734375,
      "learning_rate": 1e-06,
      "loss": 1107.0792,
      "step": 264
    },
    {
      "clip_ratio/high_max": 0.0025999167046393268,
      "clip_ratio/high_mean": 0.0009686993944342248,
      "clip_ratio/low_mean": 0.00107698624196928,
      "clip_ratio/low_min": 0.00020360700364108197,
      "clip_ratio/region_mean": 0.002045685654593399,
      "epoch": 0.024733271500154582,
      "grad_norm": 0.12191295623779297,
      "learning_rate": 1e-06,
      "loss": 0.0458,
      "step": 265
    },
    {
      "clip_ratio/high_max": 0.0022056036577851046,
      "clip_ratio/high_mean": 0.0009684755659691291,
      "clip_ratio/low_mean": 0.0010323439673811663,
      "clip_ratio/low_min": 0.0001548218560856185,
      "clip_ratio/region_mean": 0.0020008195060654543,
      "epoch": 0.024826604600155167,
      "grad_norm": 0.1116814836859703,
      "learning_rate": 1e-06,
      "loss": 0.0458,
      "step": 266
    },
    {
      "clip_ratio/high_max": 0.00264313152001705,
      "clip_ratio/high_mean": 0.0011148343583045062,
      "clip_ratio/low_mean": 0.0009596938398317434,
      "clip_ratio/low_min": 6.548561032104772e-05,
      "clip_ratio/region_mean": 0.002074528230878059,
      "epoch": 0.02491993770015575,
      "grad_norm": 0.1257859766483307,
      "learning_rate": 1e-06,
      "loss": -0.002,
      "step": 267
    },
    {
      "clip_ratio/high_max": 0.0017358685945509933,
      "clip_ratio/high_mean": 0.0007508427897846559,
      "clip_ratio/low_mean": 0.0009057802744791843,
      "clip_ratio/low_min": 8.455717943434138e-05,
      "clip_ratio/region_mean": 0.0016566230624448508,
      "epoch": 0.025013270800156334,
      "grad_norm": 25.43267250061035,
      "learning_rate": 1e-06,
      "loss": 0.048,
      "step": 268
    },
    {
      "clip_ratio/high_max": 0.0020468689435801934,
      "clip_ratio/high_mean": 0.0008374350272788433,
      "clip_ratio/low_mean": 0.0010345795744797215,
      "clip_ratio/low_min": 2.3317839804803953e-05,
      "clip_ratio/region_mean": 0.0018720146035775542,
      "epoch": 0.025106603900156916,
      "grad_norm": 2.809274196624756,
      "learning_rate": 1e-06,
      "loss": 0.0505,
      "step": 269
    },
    {
      "clip_ratio/high_max": 0.00194508030108409,
      "clip_ratio/high_mean": 0.000816213167126989,
      "clip_ratio/low_mean": 0.0011209035765205044,
      "clip_ratio/low_min": 9.659905026637716e-05,
      "clip_ratio/region_mean": 0.001937116787303239,
      "epoch": 0.0251999370001575,
      "grad_norm": 0.10319977253675461,
      "learning_rate": 1e-06,
      "loss": 0.0301,
      "step": 270
    },
    {
      "clip_ratio/high_max": 0.002447914346703328,
      "clip_ratio/high_mean": 0.0009979642291000346,
      "clip_ratio/low_mean": 0.0009408927089680219,
      "clip_ratio/low_min": 9.07915564312134e-05,
      "clip_ratio/region_mean": 0.0019388569926377386,
      "epoch": 0.025293270100158083,
      "grad_norm": 0.1134476289153099,
      "learning_rate": 1e-06,
      "loss": 0.0333,
      "step": 271
    },
    {
      "clip_ratio/high_max": 0.0024025061647989787,
      "clip_ratio/high_mean": 0.0010154991687159054,
      "clip_ratio/low_mean": 0.0010577546345302835,
      "clip_ratio/low_min": 0.00011584590356505942,
      "clip_ratio/region_mean": 0.0020732537595904432,
      "epoch": 0.025386603200158665,
      "grad_norm": 0.10023599117994308,
      "learning_rate": 1e-06,
      "loss": 0.0109,
      "step": 272
    },
    {
      "clip_ratio/high_max": 0.0022039792711439077,
      "clip_ratio/high_mean": 0.0008787852093519177,
      "clip_ratio/low_mean": 0.0013139429429429583,
      "clip_ratio/low_min": 0.000118511903565377,
      "clip_ratio/region_mean": 0.002192728134104982,
      "epoch": 0.02547993630015925,
      "grad_norm": 0.11383773386478424,
      "learning_rate": 1e-06,
      "loss": 0.0634,
      "step": 273
    },
    {
      "clip_ratio/high_max": 0.002123242535162717,
      "clip_ratio/high_mean": 0.0010181207035202533,
      "clip_ratio/low_mean": 0.0008940824391174829,
      "clip_ratio/low_min": 6.807116005802527e-05,
      "clip_ratio/region_mean": 0.0019122031080769375,
      "epoch": 0.02557326940015983,
      "grad_norm": 0.11560788750648499,
      "learning_rate": 1e-06,
      "loss": -0.0254,
      "step": 274
    },
    {
      "clip_ratio/high_max": 0.0022261288759182207,
      "clip_ratio/high_mean": 0.0008659750201331917,
      "clip_ratio/low_mean": 0.0011666952996165492,
      "clip_ratio/low_min": 8.28755564725725e-05,
      "clip_ratio/region_mean": 0.0020326703634054866,
      "epoch": 0.025666602500160417,
      "grad_norm": 0.11708521842956543,
      "learning_rate": 1e-06,
      "loss": 0.0385,
      "step": 275
    },
    {
      "clip_ratio/high_max": 0.002127394240233116,
      "clip_ratio/high_mean": 0.0009219192579621449,
      "clip_ratio/low_mean": 0.0011407461788621731,
      "clip_ratio/low_min": 1.685346069280058e-05,
      "clip_ratio/region_mean": 0.0020626654659281485,
      "epoch": 0.025759935600161,
      "grad_norm": 0.12133800238370895,
      "learning_rate": 1e-06,
      "loss": 0.0277,
      "step": 276
    },
    {
      "clip_ratio/high_max": 0.002553348444052972,
      "clip_ratio/high_mean": 0.0010130150349141331,
      "clip_ratio/low_mean": 0.0009643308694649022,
      "clip_ratio/low_min": 6.193570607138099e-05,
      "clip_ratio/region_mean": 0.0019773459280258976,
      "epoch": 0.025853268700161584,
      "grad_norm": 0.11382672190666199,
      "learning_rate": 1e-06,
      "loss": -0.0166,
      "step": 277
    },
    {
      "clip_ratio/high_max": 0.002261892528622411,
      "clip_ratio/high_mean": 0.0009346344340883661,
      "clip_ratio/low_mean": 0.0011951681663049385,
      "clip_ratio/low_min": 0.00014592427578463685,
      "clip_ratio/region_mean": 0.002129802574927453,
      "epoch": 0.025946601800162165,
      "grad_norm": 0.12542285025119781,
      "learning_rate": 1e-06,
      "loss": 0.026,
      "step": 278
    },
    {
      "clip_ratio/high_max": 0.0022741039319953416,
      "clip_ratio/high_mean": 0.0008146316813508747,
      "clip_ratio/low_mean": 0.0011442370578151895,
      "clip_ratio/low_min": 0.0001342641453447868,
      "clip_ratio/region_mean": 0.00195886872097617,
      "epoch": 0.02603993490016275,
      "grad_norm": 0.12644465267658234,
      "learning_rate": 1e-06,
      "loss": 0.0815,
      "step": 279
    },
    {
      "clip_ratio/high_max": 0.0018161654734285548,
      "clip_ratio/high_mean": 0.0008414362273470033,
      "clip_ratio/low_mean": 0.001065722040948458,
      "clip_ratio/low_min": 2.7908015908906236e-05,
      "clip_ratio/region_mean": 0.0019071582428296097,
      "epoch": 0.026133268000163332,
      "grad_norm": 0.12692326307296753,
      "learning_rate": 1e-06,
      "loss": 0.0635,
      "step": 280
    },
    {
      "clip_ratio/high_max": 0.002485525685187895,
      "clip_ratio/high_mean": 0.0009320987992396113,
      "clip_ratio/low_mean": 0.0010240671635983745,
      "clip_ratio/low_min": 0.0001568649968248792,
      "clip_ratio/region_mean": 0.0019561659210012294,
      "epoch": 0.026226601100163918,
      "grad_norm": 0.1111765205860138,
      "learning_rate": 1e-06,
      "loss": 0.0165,
      "step": 281
    },
    {
      "clip_ratio/high_max": 0.0021119122611708008,
      "clip_ratio/high_mean": 0.0008515945046383422,
      "clip_ratio/low_mean": 0.00109626169250987,
      "clip_ratio/low_min": 7.348210601776373e-05,
      "clip_ratio/region_mean": 0.0019478561880532652,
      "epoch": 0.0263199342001645,
      "grad_norm": 0.11516562849283218,
      "learning_rate": 1e-06,
      "loss": 0.0399,
      "step": 282
    },
    {
      "clip_ratio/high_max": 0.0026272412069374695,
      "clip_ratio/high_mean": 0.0011091487176599912,
      "clip_ratio/low_mean": 0.001020450086798519,
      "clip_ratio/low_min": 0.0001115727391152177,
      "clip_ratio/region_mean": 0.00212959880445851,
      "epoch": 0.026413267300165084,
      "grad_norm": 0.1166430339217186,
      "learning_rate": 1e-06,
      "loss": -0.0052,
      "step": 283
    },
    {
      "clip_ratio/high_max": 0.0023727270308882,
      "clip_ratio/high_mean": 0.0010180645549553446,
      "clip_ratio/low_mean": 0.0011141158065584023,
      "clip_ratio/low_min": 7.28704562789062e-05,
      "clip_ratio/region_mean": 0.002132180343323853,
      "epoch": 0.026506600400165666,
      "grad_norm": 0.14391209185123444,
      "learning_rate": 1e-06,
      "loss": 0.004,
      "step": 284
    },
    {
      "clip_ratio/high_max": 0.0024710543002584018,
      "clip_ratio/high_mean": 0.0010852410086954478,
      "clip_ratio/low_mean": 0.0013846052897861227,
      "clip_ratio/low_min": 0.00015100027667358518,
      "clip_ratio/region_mean": 0.0024698463748791255,
      "epoch": 0.026599933500166248,
      "grad_norm": 0.1591976135969162,
      "learning_rate": 1e-06,
      "loss": 0.0048,
      "step": 285
    },
    {
      "clip_ratio/high_max": 0.0022533032097271644,
      "clip_ratio/high_mean": 0.0009276878372475039,
      "clip_ratio/low_mean": 0.0011239837731409352,
      "clip_ratio/low_min": 0.00010055847451440059,
      "clip_ratio/region_mean": 0.0020516715885605663,
      "epoch": 0.026693266600166833,
      "grad_norm": 0.12282620370388031,
      "learning_rate": 1e-06,
      "loss": 0.0304,
      "step": 286
    },
    {
      "clip_ratio/high_max": 0.0022062804237066302,
      "clip_ratio/high_mean": 0.0009301087266067043,
      "clip_ratio/low_mean": 0.0010107943780894857,
      "clip_ratio/low_min": 7.176871258707251e-05,
      "clip_ratio/region_mean": 0.0019409031447139569,
      "epoch": 0.026786599700167415,
      "grad_norm": 0.1139829158782959,
      "learning_rate": 1e-06,
      "loss": 0.0213,
      "step": 287
    },
    {
      "clip_ratio/high_max": 0.002141230615961831,
      "clip_ratio/high_mean": 0.0009377644128107931,
      "clip_ratio/low_mean": 0.0009456081547796202,
      "clip_ratio/low_min": 8.164348037098534e-05,
      "clip_ratio/region_mean": 0.0018833725189324468,
      "epoch": 0.026879932800168,
      "grad_norm": 0.1083705946803093,
      "learning_rate": 1e-06,
      "loss": -0.027,
      "step": 288
    },
    {
      "clip_ratio/high_max": 0.0021596043225144967,
      "clip_ratio/high_mean": 0.0009366572612634627,
      "clip_ratio/low_mean": 0.001154423393018078,
      "clip_ratio/low_min": 0.00017751159339240985,
      "clip_ratio/region_mean": 0.0020910806706524454,
      "epoch": 0.026973265900168582,
      "grad_norm": 0.11221802234649658,
      "learning_rate": 1e-06,
      "loss": 0.0296,
      "step": 289
    },
    {
      "clip_ratio/high_max": 0.0023212663727463223,
      "clip_ratio/high_mean": 0.0008584045190218603,
      "clip_ratio/low_mean": 0.0012100212079531047,
      "clip_ratio/low_min": 0.00019799784422502853,
      "clip_ratio/region_mean": 0.0020684257251559757,
      "epoch": 0.027066599000169167,
      "grad_norm": 0.11031017452478409,
      "learning_rate": 1e-06,
      "loss": 0.0482,
      "step": 290
    },
    {
      "clip_ratio/high_max": 0.0018162807318731211,
      "clip_ratio/high_mean": 0.0008221095104090637,
      "clip_ratio/low_mean": 0.0011979391438217135,
      "clip_ratio/low_min": 8.421747315878747e-05,
      "clip_ratio/region_mean": 0.002020048661506735,
      "epoch": 0.02715993210016975,
      "grad_norm": 0.10802154242992401,
      "learning_rate": 1e-06,
      "loss": 0.0658,
      "step": 291
    },
    {
      "clip_ratio/high_max": 0.002360517657507444,
      "clip_ratio/high_mean": 0.0010021632942880387,
      "clip_ratio/low_mean": 0.001076934360753512,
      "clip_ratio/low_min": 5.497665006259922e-05,
      "clip_ratio/region_mean": 0.0020790976341231726,
      "epoch": 0.027253265200170334,
      "grad_norm": 0.11743683367967606,
      "learning_rate": 1e-06,
      "loss": -0.0019,
      "step": 292
    },
    {
      "clip_ratio/high_max": 0.002440800904878415,
      "clip_ratio/high_mean": 0.0010539209433773067,
      "clip_ratio/low_mean": 0.0012650684020627523,
      "clip_ratio/low_min": 9.336321272712667e-05,
      "clip_ratio/region_mean": 0.0023189894200186245,
      "epoch": 0.027346598300170916,
      "grad_norm": 0.13771085441112518,
      "learning_rate": 1e-06,
      "loss": -0.0241,
      "step": 293
    },
    {
      "clip_ratio/high_max": 0.0025593096725060605,
      "clip_ratio/high_mean": 0.0009615876770112664,
      "clip_ratio/low_mean": 0.0010978662940033246,
      "clip_ratio/low_min": 0.0001406737937941216,
      "clip_ratio/region_mean": 0.002059453967376612,
      "epoch": 0.0274399314001715,
      "grad_norm": 0.11490236967802048,
      "learning_rate": 1e-06,
      "loss": 0.0049,
      "step": 294
    },
    {
      "clip_ratio/high_max": 0.002203147654654458,
      "clip_ratio/high_mean": 0.0009295364034187514,
      "clip_ratio/low_mean": 0.0009648299746913835,
      "clip_ratio/low_min": 1.770538256096188e-05,
      "clip_ratio/region_mean": 0.0018943663890240714,
      "epoch": 0.027533264500172083,
      "grad_norm": 0.11392612755298615,
      "learning_rate": 1e-06,
      "loss": -0.0008,
      "step": 295
    },
    {
      "clip_ratio/high_max": 0.0019143160498060752,
      "clip_ratio/high_mean": 0.0009036548781296005,
      "clip_ratio/low_mean": 0.0009823409563978203,
      "clip_ratio/low_min": 8.575135234423215e-05,
      "clip_ratio/region_mean": 0.0018859958290704526,
      "epoch": 0.027626597600172668,
      "grad_norm": 0.11274272948503494,
      "learning_rate": 1e-06,
      "loss": 0.0034,
      "step": 296
    },
    {
      "clip_ratio/high_max": 0.0021235786225588527,
      "clip_ratio/high_mean": 0.0009286711947424919,
      "clip_ratio/low_mean": 0.0010827420665009413,
      "clip_ratio/low_min": 9.054255770024611e-05,
      "clip_ratio/region_mean": 0.0020114132785238326,
      "epoch": 0.02771993070017325,
      "grad_norm": 0.11259263008832932,
      "learning_rate": 1e-06,
      "loss": 0.0267,
      "step": 297
    },
    {
      "clip_ratio/high_max": 0.002343071962968679,
      "clip_ratio/high_mean": 0.0010438790541229537,
      "clip_ratio/low_mean": 0.001059468137100339,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0021033471639384516,
      "epoch": 0.02781326380017383,
      "grad_norm": 0.12148614227771759,
      "learning_rate": 1e-06,
      "loss": -0.0121,
      "step": 298
    },
    {
      "clip_ratio/high_max": 0.002493363179382868,
      "clip_ratio/high_mean": 0.0010799922183650779,
      "clip_ratio/low_mean": 0.0009481222350586904,
      "clip_ratio/low_min": 2.8298322831687983e-05,
      "clip_ratio/region_mean": 0.002028114424319938,
      "epoch": 0.027906596900174416,
      "grad_norm": 0.11882860213518143,
      "learning_rate": 1e-06,
      "loss": -0.0315,
      "step": 299
    },
    {
      "clip_ratio/high_max": 0.0022521089704241604,
      "clip_ratio/high_mean": 0.0009415843305760063,
      "clip_ratio/low_mean": 0.0009593866561772302,
      "clip_ratio/low_min": 0.00013306337132235058,
      "clip_ratio/region_mean": 0.0019009710376849398,
      "epoch": 0.027999930000174998,
      "grad_norm": 0.10964560508728027,
      "learning_rate": 1e-06,
      "loss": -0.0162,
      "step": 300
    },
    {
      "clip_ratio/high_max": 0.002038241731497692,
      "clip_ratio/high_mean": 0.0007765646369080059,
      "clip_ratio/low_mean": 0.0010706147386372322,
      "clip_ratio/low_min": 0.00013939641121396562,
      "clip_ratio/region_mean": 0.0018471794028300792,
      "epoch": 0.028093263100175583,
      "grad_norm": 0.10963646322488785,
      "learning_rate": 1e-06,
      "loss": 0.0385,
      "step": 301
    },
    {
      "clip_ratio/high_max": 0.002626213747134898,
      "clip_ratio/high_mean": 0.0009720066900626989,
      "clip_ratio/low_mean": 0.0010703817824833095,
      "clip_ratio/low_min": 0.00010004171963373665,
      "clip_ratio/region_mean": 0.0020423884852789342,
      "epoch": 0.028186596200176165,
      "grad_norm": 0.1182062178850174,
      "learning_rate": 1e-06,
      "loss": -0.0022,
      "step": 302
    },
    {
      "clip_ratio/high_max": 0.0018748773509287275,
      "clip_ratio/high_mean": 0.0009008149536384735,
      "clip_ratio/low_mean": 0.0008921420248952927,
      "clip_ratio/low_min": 0.00013410473820840707,
      "clip_ratio/region_mean": 0.001792956973076798,
      "epoch": 0.02827992930017675,
      "grad_norm": 0.10940016806125641,
      "learning_rate": 1e-06,
      "loss": -0.0035,
      "step": 303
    },
    {
      "clip_ratio/high_max": 0.002016915019339649,
      "clip_ratio/high_mean": 0.0008629738986201119,
      "clip_ratio/low_mean": 0.001146636226621922,
      "clip_ratio/low_min": 0.00010632408884703182,
      "clip_ratio/region_mean": 0.0020096101143280976,
      "epoch": 0.028373262400177332,
      "grad_norm": 0.1155250295996666,
      "learning_rate": 1e-06,
      "loss": 0.047,
      "step": 304
    },
    {
      "clip_ratio/high_max": 0.0019444970785116311,
      "clip_ratio/high_mean": 0.0008174063568731071,
      "clip_ratio/low_mean": 0.0011137496803712565,
      "clip_ratio/low_min": 0.00014554495373886311,
      "clip_ratio/region_mean": 0.001931156039063353,
      "epoch": 0.028466595500177917,
      "grad_norm": 14.725848197937012,
      "learning_rate": 1e-06,
      "loss": 0.0396,
      "step": 305
    },
    {
      "clip_ratio/high_max": 0.0021021909997216426,
      "clip_ratio/high_mean": 0.0009064140031114221,
      "clip_ratio/low_mean": 0.000976428500507609,
      "clip_ratio/low_min": 1.3067112377029844e-05,
      "clip_ratio/region_mean": 0.0018828425018000416,
      "epoch": 0.0285599286001785,
      "grad_norm": 0.11437109112739563,
      "learning_rate": 1e-06,
      "loss": 0.0031,
      "step": 306
    },
    {
      "clip_ratio/high_max": 0.0020876354465144686,
      "clip_ratio/high_mean": 0.0009094852357520722,
      "clip_ratio/low_mean": 0.0011950351581617724,
      "clip_ratio/low_min": 0.00011705498945957515,
      "clip_ratio/region_mean": 0.002104520426655654,
      "epoch": 0.028653261700179084,
      "grad_norm": 0.12165649235248566,
      "learning_rate": 1e-06,
      "loss": -0.0095,
      "step": 307
    },
    {
      "clip_ratio/high_max": 0.0020882127719232813,
      "clip_ratio/high_mean": 0.0009038070656970376,
      "clip_ratio/low_mean": 0.0011496131082822103,
      "clip_ratio/low_min": 0.00011077620729338378,
      "clip_ratio/region_mean": 0.0020534201757982373,
      "epoch": 0.028746594800179666,
      "grad_norm": 0.12291403859853745,
      "learning_rate": 1e-06,
      "loss": 0.0114,
      "step": 308
    },
    {
      "clip_ratio/high_max": 0.0024690960271982476,
      "clip_ratio/high_mean": 0.0009290014877478825,
      "clip_ratio/low_mean": 0.0012561733237816952,
      "clip_ratio/low_min": 8.222426913562231e-05,
      "clip_ratio/region_mean": 0.0021851748242625035,
      "epoch": 0.02883992790018025,
      "grad_norm": 0.11932417005300522,
      "learning_rate": 1e-06,
      "loss": 0.0299,
      "step": 309
    },
    {
      "clip_ratio/high_max": 0.002151043310732348,
      "clip_ratio/high_mean": 0.0008489551582897548,
      "clip_ratio/low_mean": 0.0011632040059339488,
      "clip_ratio/low_min": 2.3563326976727694e-05,
      "clip_ratio/region_mean": 0.0020121591951465234,
      "epoch": 0.028933261000180833,
      "grad_norm": 0.11020629107952118,
      "learning_rate": 1e-06,
      "loss": 0.0336,
      "step": 310
    },
    {
      "clip_ratio/high_max": 0.0020902167016174644,
      "clip_ratio/high_mean": 0.0008407848545175511,
      "clip_ratio/low_mean": 0.0010362534849264193,
      "clip_ratio/low_min": 8.118540063151158e-05,
      "clip_ratio/region_mean": 0.0018770383321680129,
      "epoch": 0.029026594100181415,
      "grad_norm": 0.11123541742563248,
      "learning_rate": 1e-06,
      "loss": 0.0168,
      "step": 311
    },
    {
      "clip_ratio/high_max": 0.002179583036195254,
      "clip_ratio/high_mean": 0.0008577987227909034,
      "clip_ratio/low_mean": 0.0010695968376239762,
      "clip_ratio/low_min": 4.6227102757256944e-05,
      "clip_ratio/region_mean": 0.0019273955695098266,
      "epoch": 0.029119927200182,
      "grad_norm": 0.11267873644828796,
      "learning_rate": 1e-06,
      "loss": 0.0096,
      "step": 312
    },
    {
      "clip_ratio/high_max": 0.002187814459830406,
      "clip_ratio/high_mean": 0.0008259893897957227,
      "clip_ratio/low_mean": 0.0011067908199038357,
      "clip_ratio/low_min": 5.453302583191544e-05,
      "clip_ratio/region_mean": 0.0019327802147017792,
      "epoch": 0.02921326030018258,
      "grad_norm": 0.10996173322200775,
      "learning_rate": 1e-06,
      "loss": 0.0188,
      "step": 313
    },
    {
      "clip_ratio/high_max": 0.002290935481141787,
      "clip_ratio/high_mean": 0.0009460082583245821,
      "clip_ratio/low_mean": 0.0011237544349569362,
      "clip_ratio/low_min": 0.00019898545542673673,
      "clip_ratio/region_mean": 0.0020697627114714123,
      "epoch": 0.029306593400183167,
      "grad_norm": 0.11206992715597153,
      "learning_rate": 1e-06,
      "loss": 0.0099,
      "step": 314
    },
    {
      "clip_ratio/high_max": 0.0018592779779282864,
      "clip_ratio/high_mean": 0.0007766994185658405,
      "clip_ratio/low_mean": 0.00106459978633211,
      "clip_ratio/low_min": 0.0001234176761499839,
      "clip_ratio/region_mean": 0.0018412991994409822,
      "epoch": 0.02939992650018375,
      "grad_norm": 0.10743377357721329,
      "learning_rate": 1e-06,
      "loss": 0.028,
      "step": 315
    },
    {
      "clip_ratio/high_max": 0.00216169571649516,
      "clip_ratio/high_mean": 0.0009073383462236961,
      "clip_ratio/low_mean": 0.0009665958641562611,
      "clip_ratio/low_min": 8.019068354769843e-05,
      "clip_ratio/region_mean": 0.001873934168543201,
      "epoch": 0.029493259600184334,
      "grad_norm": 0.11096478998661041,
      "learning_rate": 1e-06,
      "loss": -0.0066,
      "step": 316
    },
    {
      "clip_ratio/high_max": 0.001815407202229835,
      "clip_ratio/high_mean": 0.0007989068417373346,
      "clip_ratio/low_mean": 0.0013156889435776975,
      "clip_ratio/low_min": 0.0001044754662871128,
      "clip_ratio/region_mean": 0.0021145957653061487,
      "epoch": 0.029586592700184915,
      "grad_norm": 0.1608605533838272,
      "learning_rate": 1e-06,
      "loss": 0.0549,
      "step": 317
    },
    {
      "clip_ratio/high_max": 0.002236041751530138,
      "clip_ratio/high_mean": 0.000868625141265511,
      "clip_ratio/low_mean": 0.0011786719078372698,
      "clip_ratio/low_min": 6.258014946070034e-05,
      "clip_ratio/region_mean": 0.0020472970500122756,
      "epoch": 0.0296799258001855,
      "grad_norm": 0.11986640095710754,
      "learning_rate": 1e-06,
      "loss": 0.0293,
      "step": 318
    },
    {
      "clip_ratio/high_max": 0.0021051574003649876,
      "clip_ratio/high_mean": 0.0008974846241471823,
      "clip_ratio/low_mean": 0.0012301670685701538,
      "clip_ratio/low_min": 8.920971049519721e-05,
      "clip_ratio/region_mean": 0.002127651678165421,
      "epoch": 0.029773258900186082,
      "grad_norm": 0.12771056592464447,
      "learning_rate": 1e-06,
      "loss": 0.0813,
      "step": 319
    },
    {
      "clip_ratio/high_max": 0.0021571613433479797,
      "clip_ratio/high_mean": 0.0008580247031204635,
      "clip_ratio/low_mean": 0.0010435702915856382,
      "clip_ratio/low_min": 0.00013387511171458755,
      "clip_ratio/region_mean": 0.0019015949656022713,
      "epoch": 0.029866592000186667,
      "grad_norm": 0.12085594981908798,
      "learning_rate": 1e-06,
      "loss": -0.0077,
      "step": 320
    },
    {
      "clip_ratio/high_max": 0.002569294931163313,
      "clip_ratio/high_mean": 0.0009803638513403712,
      "clip_ratio/low_mean": 0.001121017903642496,
      "clip_ratio/low_min": 5.670980135619175e-05,
      "clip_ratio/region_mean": 0.002101381804095581,
      "epoch": 0.02995992510018725,
      "grad_norm": 0.10860329121351242,
      "learning_rate": 1e-06,
      "loss": 0.0299,
      "step": 321
    },
    {
      "clip_ratio/high_max": 0.002290455511683831,
      "clip_ratio/high_mean": 0.0010337076855648775,
      "clip_ratio/low_mean": 0.001258689138921909,
      "clip_ratio/low_min": 7.156406809372129e-05,
      "clip_ratio/region_mean": 0.0022923968645045534,
      "epoch": 0.030053258200187834,
      "grad_norm": 0.14300259947776794,
      "learning_rate": 1e-06,
      "loss": 0.0233,
      "step": 322
    },
    {
      "clip_ratio/high_max": 0.002157535061996896,
      "clip_ratio/high_mean": 0.0010063192603411153,
      "clip_ratio/low_mean": 0.0010595787480269792,
      "clip_ratio/low_min": 6.554570427397266e-05,
      "clip_ratio/region_mean": 0.002065898028376978,
      "epoch": 0.030146591300188416,
      "grad_norm": 0.12497463822364807,
      "learning_rate": 1e-06,
      "loss": 0.0025,
      "step": 323
    },
    {
      "clip_ratio/high_max": 0.002143306970538106,
      "clip_ratio/high_mean": 0.0009250070907000918,
      "clip_ratio/low_mean": 0.001001356817141641,
      "clip_ratio/low_min": 0.0001660984598856885,
      "clip_ratio/region_mean": 0.001926363882375881,
      "epoch": 0.030239924400188998,
      "grad_norm": 0.11590266227722168,
      "learning_rate": 1e-06,
      "loss": 0.0046,
      "step": 324
    },
    {
      "clip_ratio/high_max": 0.0023267439974006265,
      "clip_ratio/high_mean": 0.0009486937760811998,
      "clip_ratio/low_mean": 0.0010370833133492852,
      "clip_ratio/low_min": 0.00011028562857973156,
      "clip_ratio/region_mean": 0.001985777067602612,
      "epoch": 0.030333257500189583,
      "grad_norm": 0.11165519058704376,
      "learning_rate": 1e-06,
      "loss": 0.0114,
      "step": 325
    },
    {
      "clip_ratio/high_max": 0.0019282541616121307,
      "clip_ratio/high_mean": 0.0008478929066768615,
      "clip_ratio/low_mean": 0.0011901712969120126,
      "clip_ratio/low_min": 0.00015262997476384044,
      "clip_ratio/region_mean": 0.0020380642235977575,
      "epoch": 0.030426590600190165,
      "grad_norm": 0.1079166904091835,
      "learning_rate": 1e-06,
      "loss": 0.0341,
      "step": 326
    },
    {
      "clip_ratio/high_max": 0.002220818139903713,
      "clip_ratio/high_mean": 0.0009001561902550748,
      "clip_ratio/low_mean": 0.0011336224706610665,
      "clip_ratio/low_min": 0.00010049212050944334,
      "clip_ratio/region_mean": 0.002033778640907258,
      "epoch": 0.03051992370019075,
      "grad_norm": 0.11433017253875732,
      "learning_rate": 1e-06,
      "loss": 0.0484,
      "step": 327
    },
    {
      "clip_ratio/high_max": 0.0021585938629868906,
      "clip_ratio/high_mean": 0.0008333931491506519,
      "clip_ratio/low_mean": 0.0013346746491151862,
      "clip_ratio/low_min": 0.0001245234270754736,
      "clip_ratio/region_mean": 0.0021680677818949334,
      "epoch": 0.030613256800191332,
      "grad_norm": 0.10329735279083252,
      "learning_rate": 1e-06,
      "loss": 0.0646,
      "step": 328
    },
    {
      "clip_ratio/high_max": 0.002627769506943878,
      "clip_ratio/high_mean": 0.0011090613079431932,
      "clip_ratio/low_mean": 0.0013199484637880232,
      "clip_ratio/low_min": 9.724599294713698e-06,
      "clip_ratio/region_mean": 0.0024290097717312165,
      "epoch": 0.030706589900191917,
      "grad_norm": 0.22804972529411316,
      "learning_rate": 1e-06,
      "loss": 0.0118,
      "step": 329
    },
    {
      "clip_ratio/high_max": 0.0021940586593700573,
      "clip_ratio/high_mean": 0.0010116602315974887,
      "clip_ratio/low_mean": 0.0010665427253115922,
      "clip_ratio/low_min": 7.944414210214745e-05,
      "clip_ratio/region_mean": 0.0020782028950634412,
      "epoch": 0.0307999230001925,
      "grad_norm": 0.10244179517030716,
      "learning_rate": 1e-06,
      "loss": 0.0165,
      "step": 330
    },
    {
      "clip_ratio/high_max": 0.002239552872197237,
      "clip_ratio/high_mean": 0.0009741118919919245,
      "clip_ratio/low_mean": 0.001268049460122711,
      "clip_ratio/low_min": 0.00016382148351112846,
      "clip_ratio/region_mean": 0.002242161353933625,
      "epoch": 0.030893256100193084,
      "grad_norm": 0.11611955612897873,
      "learning_rate": 1e-06,
      "loss": 0.0332,
      "step": 331
    },
    {
      "clip_ratio/high_max": 0.002064609434455633,
      "clip_ratio/high_mean": 0.0008662734035169706,
      "clip_ratio/low_mean": 0.0012566667901410256,
      "clip_ratio/low_min": 0.0001835051916714292,
      "clip_ratio/region_mean": 0.002122940124536399,
      "epoch": 0.030986589200193666,
      "grad_norm": 0.13188059628009796,
      "learning_rate": 1e-06,
      "loss": 0.056,
      "step": 332
    },
    {
      "clip_ratio/high_max": 0.0021246587857604027,
      "clip_ratio/high_mean": 0.0009811239651753567,
      "clip_ratio/low_mean": 0.0011925911840080516,
      "clip_ratio/low_min": 0.0001146252870967146,
      "clip_ratio/region_mean": 0.0021737151328125037,
      "epoch": 0.03107992230019425,
      "grad_norm": 0.12084190547466278,
      "learning_rate": 1e-06,
      "loss": 0.0089,
      "step": 333
    },
    {
      "clip_ratio/high_max": 0.0020908947408315726,
      "clip_ratio/high_mean": 0.000870091213073465,
      "clip_ratio/low_mean": 0.0011460989444458392,
      "clip_ratio/low_min": 8.154174929586588e-05,
      "clip_ratio/region_mean": 0.0020161901411483996,
      "epoch": 0.031173255400194833,
      "grad_norm": 0.1228744387626648,
      "learning_rate": 1e-06,
      "loss": 0.0692,
      "step": 334
    },
    {
      "clip_ratio/high_max": 0.0021643416112056,
      "clip_ratio/high_mean": 0.0008296875603264198,
      "clip_ratio/low_mean": 0.0011237840626563411,
      "clip_ratio/low_min": 9.355169504488003e-05,
      "clip_ratio/region_mean": 0.001953471604792867,
      "epoch": 0.03126658850019542,
      "grad_norm": 0.11427238583564758,
      "learning_rate": 1e-06,
      "loss": 0.0253,
      "step": 335
    },
    {
      "clip_ratio/high_max": 0.0019447591839707457,
      "clip_ratio/high_mean": 0.0009052424302353757,
      "clip_ratio/low_mean": 0.0010355626727687195,
      "clip_ratio/low_min": 9.105355456995312e-05,
      "clip_ratio/region_mean": 0.0019408051084610634,
      "epoch": 0.031359921600196,
      "grad_norm": 0.11841615289449692,
      "learning_rate": 1e-06,
      "loss": 0.0131,
      "step": 336
    },
    {
      "clip_ratio/high_max": 0.00232812426838791,
      "clip_ratio/high_mean": 0.0009957498878065962,
      "clip_ratio/low_mean": 0.0010864943724300247,
      "clip_ratio/low_min": 0.00013056925308774225,
      "clip_ratio/region_mean": 0.002082244238408748,
      "epoch": 0.03145325470019658,
      "grad_norm": 0.12674465775489807,
      "learning_rate": 1e-06,
      "loss": 0.0027,
      "step": 337
    },
    {
      "clip_ratio/high_max": 0.0025400919912499376,
      "clip_ratio/high_mean": 0.0010203268793702591,
      "clip_ratio/low_mean": 0.0010479550910531543,
      "clip_ratio/low_min": 7.761822325846879e-05,
      "clip_ratio/region_mean": 0.002068281937681604,
      "epoch": 0.031546587800197166,
      "grad_norm": 0.10925080627202988,
      "learning_rate": 1e-06,
      "loss": 0.007,
      "step": 338
    },
    {
      "clip_ratio/high_max": 0.002594425001007039,
      "clip_ratio/high_mean": 0.0011677702459564898,
      "clip_ratio/low_mean": 0.0009922743774950504,
      "clip_ratio/low_min": 1.7801196008804254e-05,
      "clip_ratio/region_mean": 0.0021600445470539853,
      "epoch": 0.03163992090019775,
      "grad_norm": 0.4444403052330017,
      "learning_rate": 1e-06,
      "loss": -0.0159,
      "step": 339
    },
    {
      "clip_ratio/high_max": 0.0018279580544913188,
      "clip_ratio/high_mean": 0.0007993062654350069,
      "clip_ratio/low_mean": 0.0011365246537025087,
      "clip_ratio/low_min": 5.94459115745849e-05,
      "clip_ratio/region_mean": 0.0019358308854862116,
      "epoch": 0.03173325400019833,
      "grad_norm": 0.10690231621265411,
      "learning_rate": 1e-06,
      "loss": 0.0825,
      "step": 340
    },
    {
      "clip_ratio/high_max": 0.002140695243724622,
      "clip_ratio/high_mean": 0.0009172743375529535,
      "clip_ratio/low_mean": 0.0010918516491074115,
      "clip_ratio/low_min": 9.728156146593392e-05,
      "clip_ratio/region_mean": 0.0020091259430046193,
      "epoch": 0.031826587100198915,
      "grad_norm": 0.11435524374246597,
      "learning_rate": 1e-06,
      "loss": 0.0374,
      "step": 341
    },
    {
      "clip_ratio/high_max": 0.0020586257523973472,
      "clip_ratio/high_mean": 0.000902438179764431,
      "clip_ratio/low_mean": 0.001106838470150251,
      "clip_ratio/low_min": 4.30491054430604e-05,
      "clip_ratio/region_mean": 0.002009276649914682,
      "epoch": 0.0319199202001995,
      "grad_norm": 0.13048726320266724,
      "learning_rate": 1e-06,
      "loss": 0.0465,
      "step": 342
    },
    {
      "clip_ratio/high_max": 0.002136928407708183,
      "clip_ratio/high_mean": 0.000896078025107272,
      "clip_ratio/low_mean": 0.0011898585507879034,
      "clip_ratio/low_min": 0.00011722445742634591,
      "clip_ratio/region_mean": 0.002085936546791345,
      "epoch": 0.032013253300200085,
      "grad_norm": 0.1033177301287651,
      "learning_rate": 1e-06,
      "loss": 0.0701,
      "step": 343
    },
    {
      "clip_ratio/high_max": 0.0022084057782194577,
      "clip_ratio/high_mean": 0.0008568549201299902,
      "clip_ratio/low_mean": 0.0012664664645853918,
      "clip_ratio/low_min": 0.0001900614661280997,
      "clip_ratio/region_mean": 0.002123321406543255,
      "epoch": 0.032106586400200664,
      "grad_norm": 0.10965591669082642,
      "learning_rate": 1e-06,
      "loss": 0.081,
      "step": 344
    },
    {
      "clip_ratio/high_max": 0.0021995499773765914,
      "clip_ratio/high_mean": 0.0009204053349094465,
      "clip_ratio/low_mean": 0.0010610223434923682,
      "clip_ratio/low_min": 8.669406906847144e-05,
      "clip_ratio/region_mean": 0.0019814276456600055,
      "epoch": 0.03219991950020125,
      "grad_norm": 0.13363026082515717,
      "learning_rate": 1e-06,
      "loss": 0.0108,
      "step": 345
    },
    {
      "clip_ratio/high_max": 0.0025101989158429205,
      "clip_ratio/high_mean": 0.0010780927477753721,
      "clip_ratio/low_mean": 0.001075920521543594,
      "clip_ratio/low_min": 6.821509487053845e-05,
      "clip_ratio/region_mean": 0.0021540133166126907,
      "epoch": 0.032293252600201834,
      "grad_norm": 0.11479067802429199,
      "learning_rate": 1e-06,
      "loss": 0.0085,
      "step": 346
    },
    {
      "clip_ratio/high_max": 0.0021954900221317075,
      "clip_ratio/high_mean": 0.0009020977868203772,
      "clip_ratio/low_mean": 0.0013978856331959832,
      "clip_ratio/low_min": 0.00016852553017088212,
      "clip_ratio/region_mean": 0.0022999833890935406,
      "epoch": 0.03238658570020242,
      "grad_norm": 0.14521950483322144,
      "learning_rate": 1e-06,
      "loss": 0.0584,
      "step": 347
    },
    {
      "clip_ratio/high_max": 0.002100695488479687,
      "clip_ratio/high_mean": 0.0008622984587418614,
      "clip_ratio/low_mean": 0.001215741373016499,
      "clip_ratio/low_min": 0.00012669900752371177,
      "clip_ratio/region_mean": 0.0020780398626811802,
      "epoch": 0.032479918800203,
      "grad_norm": 0.10538921505212784,
      "learning_rate": 1e-06,
      "loss": 0.0125,
      "step": 348
    },
    {
      "clip_ratio/high_max": 0.0021563248701568227,
      "clip_ratio/high_mean": 0.0009867449170997133,
      "clip_ratio/low_mean": 0.0011401438314351253,
      "clip_ratio/low_min": 8.875741150404792e-05,
      "clip_ratio/region_mean": 0.0021268887794576585,
      "epoch": 0.03257325190020358,
      "grad_norm": 0.11249448359012604,
      "learning_rate": 1e-06,
      "loss": 0.0135,
      "step": 349
    },
    {
      "clip_ratio/high_max": 0.002390588961134199,
      "clip_ratio/high_mean": 0.0009480214575887658,
      "clip_ratio/low_mean": 0.001145987107520341,
      "clip_ratio/low_min": 6.574898907274473e-05,
      "clip_ratio/region_mean": 0.002094008566928096,
      "epoch": 0.03266658500020417,
      "grad_norm": 0.11310872435569763,
      "learning_rate": 1e-06,
      "loss": 0.0151,
      "step": 350
    },
    {
      "clip_ratio/high_max": 0.001988746036658995,
      "clip_ratio/high_mean": 0.0008116280841932166,
      "clip_ratio/low_mean": 0.001365374027955113,
      "clip_ratio/low_min": 0.00024016555744310608,
      "clip_ratio/region_mean": 0.002177002126700245,
      "epoch": 0.032759918100204746,
      "grad_norm": 0.11652226746082306,
      "learning_rate": 1e-06,
      "loss": 0.087,
      "step": 351
    },
    {
      "clip_ratio/high_max": 0.0020331219893705565,
      "clip_ratio/high_mean": 0.0009234167628164869,
      "clip_ratio/low_mean": 0.0012328605589573272,
      "clip_ratio/low_min": 0.00022346949299389962,
      "clip_ratio/region_mean": 0.0021562772890320048,
      "epoch": 0.03285325120020533,
      "grad_norm": 0.11358150839805603,
      "learning_rate": 1e-06,
      "loss": 0.0143,
      "step": 352
    },
    {
      "clip_ratio/high_max": 0.0021666164975613356,
      "clip_ratio/high_mean": 0.0008399095604545437,
      "clip_ratio/low_mean": 0.0012059905056958087,
      "clip_ratio/low_min": 0.00014595930952054914,
      "clip_ratio/region_mean": 0.002045900087978225,
      "epoch": 0.03294658430020592,
      "grad_norm": 0.10419805347919464,
      "learning_rate": 1e-06,
      "loss": 0.045,
      "step": 353
    },
    {
      "clip_ratio/high_max": 0.0020624875105568208,
      "clip_ratio/high_mean": 0.0008539489972463343,
      "clip_ratio/low_mean": 0.00117095968380454,
      "clip_ratio/low_min": 5.2058303481317125e-05,
      "clip_ratio/region_mean": 0.0020249086810508743,
      "epoch": 0.0330399174002065,
      "grad_norm": 3558.2763671875,
      "learning_rate": 1e-06,
      "loss": 0.3708,
      "step": 354
    },
    {
      "clip_ratio/high_max": 0.002189752980484627,
      "clip_ratio/high_mean": 0.0008734756684134481,
      "clip_ratio/low_mean": 0.0010751479403552366,
      "clip_ratio/low_min": 0.00011319543955323752,
      "clip_ratio/region_mean": 0.0019486236124066636,
      "epoch": 0.03313325050020708,
      "grad_norm": 0.11278904229402542,
      "learning_rate": 1e-06,
      "loss": 0.0342,
      "step": 355
    },
    {
      "clip_ratio/high_max": 0.002278018748256727,
      "clip_ratio/high_mean": 0.0008883386590241571,
      "clip_ratio/low_mean": 0.0010244712721032556,
      "clip_ratio/low_min": 5.442007568490226e-05,
      "clip_ratio/region_mean": 0.001912809930217918,
      "epoch": 0.033226583600207665,
      "grad_norm": 0.1159723773598671,
      "learning_rate": 1e-06,
      "loss": -0.0039,
      "step": 356
    },
    {
      "clip_ratio/high_max": 0.0023154462687671185,
      "clip_ratio/high_mean": 0.0009308602202509064,
      "clip_ratio/low_mean": 0.00125598987142439,
      "clip_ratio/low_min": 9.143451734416885e-05,
      "clip_ratio/region_mean": 0.002186850157158915,
      "epoch": 0.03331991670020825,
      "grad_norm": 0.1177138015627861,
      "learning_rate": 1e-06,
      "loss": 0.0292,
      "step": 357
    },
    {
      "clip_ratio/high_max": 0.00206620594690321,
      "clip_ratio/high_mean": 0.0008164736009348417,
      "clip_ratio/low_mean": 0.0011954403889831156,
      "clip_ratio/low_min": 0.00011787036692112451,
      "clip_ratio/region_mean": 0.0020119140099268407,
      "epoch": 0.033413249800208836,
      "grad_norm": 0.10872387140989304,
      "learning_rate": 1e-06,
      "loss": 0.0838,
      "step": 358
    },
    {
      "clip_ratio/high_max": 0.002361755156016443,
      "clip_ratio/high_mean": 0.0009098943064600462,
      "clip_ratio/low_mean": 0.0011377494683983969,
      "clip_ratio/low_min": 0.00013214747650636127,
      "clip_ratio/region_mean": 0.0020476438076002523,
      "epoch": 0.033506582900209414,
      "grad_norm": 0.11202988028526306,
      "learning_rate": 1e-06,
      "loss": 0.0681,
      "step": 359
    },
    {
      "clip_ratio/high_max": 0.0019100447389064357,
      "clip_ratio/high_mean": 0.0008295353891298873,
      "clip_ratio/low_mean": 0.0010534365555940894,
      "clip_ratio/low_min": 0.0001322676289419178,
      "clip_ratio/region_mean": 0.001882971941085998,
      "epoch": 0.03359991600021,
      "grad_norm": 0.11695244908332825,
      "learning_rate": 1e-06,
      "loss": 0.0462,
      "step": 360
    },
    {
      "clip_ratio/high_max": 0.002434186142636463,
      "clip_ratio/high_mean": 0.0010246202728012577,
      "clip_ratio/low_mean": 0.001124836260714801,
      "clip_ratio/low_min": 8.7745472228562e-05,
      "clip_ratio/region_mean": 0.002149456471670419,
      "epoch": 0.033693249100210584,
      "grad_norm": 0.12341535836458206,
      "learning_rate": 1e-06,
      "loss": 0.0308,
      "step": 361
    },
    {
      "clip_ratio/high_max": 0.002108447100908961,
      "clip_ratio/high_mean": 0.0009159620240097865,
      "clip_ratio/low_mean": 0.0011480096836748999,
      "clip_ratio/low_min": 2.7470548047858756e-05,
      "clip_ratio/region_mean": 0.002063971711322665,
      "epoch": 0.03378658220021117,
      "grad_norm": 77.47904968261719,
      "learning_rate": 1e-06,
      "loss": 0.0425,
      "step": 362
    },
    {
      "clip_ratio/high_max": 0.0019328292546560988,
      "clip_ratio/high_mean": 0.0008381344696317683,
      "clip_ratio/low_mean": 0.0011714386382664088,
      "clip_ratio/low_min": 7.131160236895084e-05,
      "clip_ratio/region_mean": 0.0020095731160836294,
      "epoch": 0.03387991530021175,
      "grad_norm": 0.1070476546883583,
      "learning_rate": 1e-06,
      "loss": 0.0396,
      "step": 363
    },
    {
      "clip_ratio/high_max": 0.0025864454873953946,
      "clip_ratio/high_mean": 0.0010019448891398497,
      "clip_ratio/low_mean": 0.0011095358204329386,
      "clip_ratio/low_min": 0.00011711732349795057,
      "clip_ratio/region_mean": 0.0021114807241247036,
      "epoch": 0.03397324840021233,
      "grad_norm": 0.10823500156402588,
      "learning_rate": 1e-06,
      "loss": 0.0079,
      "step": 364
    },
    {
      "clip_ratio/high_max": 0.0024609017054899596,
      "clip_ratio/high_mean": 0.0009992888808483258,
      "clip_ratio/low_mean": 0.001211238373798551,
      "clip_ratio/low_min": 0.00016066131684056018,
      "clip_ratio/region_mean": 0.002210527192801237,
      "epoch": 0.03406658150021292,
      "grad_norm": 0.10757739096879959,
      "learning_rate": 1e-06,
      "loss": 0.0476,
      "step": 365
    },
    {
      "clip_ratio/high_max": 0.0019327660484123044,
      "clip_ratio/high_mean": 0.0008466597228107275,
      "clip_ratio/low_mean": 0.0012629792581719812,
      "clip_ratio/low_min": 0.00019227057327952934,
      "clip_ratio/region_mean": 0.0021096389536978677,
      "epoch": 0.034159914600213497,
      "grad_norm": 0.10895657539367676,
      "learning_rate": 1e-06,
      "loss": 0.0477,
      "step": 366
    },
    {
      "clip_ratio/high_max": 0.0025174269394483417,
      "clip_ratio/high_mean": 0.0009726378939376445,
      "clip_ratio/low_mean": 0.001160546064056689,
      "clip_ratio/low_min": 7.140652814996429e-05,
      "clip_ratio/region_mean": 0.0021331839452614076,
      "epoch": 0.03425324770021408,
      "grad_norm": 0.11871457099914551,
      "learning_rate": 1e-06,
      "loss": 0.0087,
      "step": 367
    },
    {
      "clip_ratio/high_max": 0.002498274807294365,
      "clip_ratio/high_mean": 0.0009608788041077787,
      "clip_ratio/low_mean": 0.0017753513166098855,
      "clip_ratio/low_min": 7.549638758064248e-05,
      "clip_ratio/region_mean": 0.0027362301480025053,
      "epoch": 0.03434658080021467,
      "grad_norm": 0.14470025897026062,
      "learning_rate": 1e-06,
      "loss": 0.0368,
      "step": 368
    },
    {
      "clip_ratio/high_max": 0.0018706831469899043,
      "clip_ratio/high_mean": 0.0008562452712794766,
      "clip_ratio/low_mean": 0.0011088792816735804,
      "clip_ratio/low_min": 8.010771489352919e-05,
      "clip_ratio/region_mean": 0.0019651246329885907,
      "epoch": 0.03443991390021525,
      "grad_norm": 142.6408233642578,
      "learning_rate": 1e-06,
      "loss": 0.0493,
      "step": 369
    },
    {
      "clip_ratio/high_max": 0.0023074456985341385,
      "clip_ratio/high_mean": 0.001000052234303439,
      "clip_ratio/low_mean": 0.0010730547783168731,
      "clip_ratio/low_min": 7.081450348778162e-05,
      "clip_ratio/region_mean": 0.002073107098112814,
      "epoch": 0.03453324700021583,
      "grad_norm": 0.3243756890296936,
      "learning_rate": 1e-06,
      "loss": -0.0217,
      "step": 370
    },
    {
      "clip_ratio/high_max": 0.0022518236510222778,
      "clip_ratio/high_mean": 0.0009693707743281266,
      "clip_ratio/low_mean": 0.001249856944923522,
      "clip_ratio/low_min": 0.0001641616627239273,
      "clip_ratio/region_mean": 0.002219227739260532,
      "epoch": 0.034626580100216416,
      "grad_norm": 0.1239929273724556,
      "learning_rate": 1e-06,
      "loss": 0.0465,
      "step": 371
    },
    {
      "clip_ratio/high_max": 0.0026092430343851447,
      "clip_ratio/high_mean": 0.001003756478894502,
      "clip_ratio/low_mean": 0.001093214936190634,
      "clip_ratio/low_min": 0.00012626219540834427,
      "clip_ratio/region_mean": 0.00209697140235221,
      "epoch": 0.034719913200217,
      "grad_norm": 0.11750996112823486,
      "learning_rate": 1e-06,
      "loss": -0.0068,
      "step": 372
    },
    {
      "clip_ratio/high_max": 0.002271275734528899,
      "clip_ratio/high_mean": 0.0010254267763230018,
      "clip_ratio/low_mean": 0.0014832128399575595,
      "clip_ratio/low_min": 8.646424794278573e-05,
      "clip_ratio/region_mean": 0.0025086395326070487,
      "epoch": 0.034813246300217586,
      "grad_norm": 0.1160498559474945,
      "learning_rate": 1e-06,
      "loss": 0.031,
      "step": 373
    },
    {
      "clip_ratio/high_max": 0.0022865480605105404,
      "clip_ratio/high_mean": 0.0009589161909389077,
      "clip_ratio/low_mean": 0.001251539524673717,
      "clip_ratio/low_min": 0.00012960705316800158,
      "clip_ratio/region_mean": 0.00221045569924172,
      "epoch": 0.034906579400218164,
      "grad_norm": 0.12079624831676483,
      "learning_rate": 1e-06,
      "loss": 0.0627,
      "step": 374
    },
    {
      "clip_ratio/high_max": 0.0025596896302886307,
      "clip_ratio/high_mean": 0.0009454310347791761,
      "clip_ratio/low_mean": 0.0011658837320283055,
      "clip_ratio/low_min": 0.00013075372226012405,
      "clip_ratio/region_mean": 0.002111314817739185,
      "epoch": 0.03499991250021875,
      "grad_norm": 0.11875633150339127,
      "learning_rate": 1e-06,
      "loss": 0.0272,
      "step": 375
    },
    {
      "clip_ratio/high_max": 0.0025779101488296874,
      "clip_ratio/high_mean": 0.0010267890356772114,
      "clip_ratio/low_mean": 0.0011818734201369807,
      "clip_ratio/low_min": 0.00012896342195745092,
      "clip_ratio/region_mean": 0.002208662474004086,
      "epoch": 0.035093245600219335,
      "grad_norm": 2.0617852210998535,
      "learning_rate": 1e-06,
      "loss": 0.0342,
      "step": 376
    },
    {
      "clip_ratio/high_max": 0.0023847867487347685,
      "clip_ratio/high_mean": 0.0009529884318908444,
      "clip_ratio/low_mean": 0.0012494894035626203,
      "clip_ratio/low_min": 6.29909309282084e-05,
      "clip_ratio/region_mean": 0.002202477800892666,
      "epoch": 0.03518657870021991,
      "grad_norm": 0.11993952095508575,
      "learning_rate": 1e-06,
      "loss": 0.0515,
      "step": 377
    },
    {
      "clip_ratio/high_max": 0.0021552698672167026,
      "clip_ratio/high_mean": 0.000986358878435567,
      "clip_ratio/low_mean": 0.0010060342774522724,
      "clip_ratio/low_min": 3.663903316919459e-05,
      "clip_ratio/region_mean": 0.0019923931831726804,
      "epoch": 0.0352799118002205,
      "grad_norm": 0.11223357170820236,
      "learning_rate": 1e-06,
      "loss": 0.0166,
      "step": 378
    },
    {
      "clip_ratio/high_max": 0.002161166830774164,
      "clip_ratio/high_mean": 0.001033863580232719,
      "clip_ratio/low_mean": 0.0011994639498880133,
      "clip_ratio/low_min": 8.22612000774825e-05,
      "clip_ratio/region_mean": 0.002233327519206796,
      "epoch": 0.03537324490022108,
      "grad_norm": 0.12360091507434845,
      "learning_rate": 1e-06,
      "loss": 0.0106,
      "step": 379
    },
    {
      "clip_ratio/high_max": 0.002008361647312995,
      "clip_ratio/high_mean": 0.0008517967498846701,
      "clip_ratio/low_mean": 0.0011015180789399892,
      "clip_ratio/low_min": 8.637665087007917e-05,
      "clip_ratio/region_mean": 0.001953314807906281,
      "epoch": 0.03546657800022167,
      "grad_norm": 0.11588394641876221,
      "learning_rate": 1e-06,
      "loss": 0.0098,
      "step": 380
    },
    {
      "clip_ratio/high_max": 0.0025197108698193915,
      "clip_ratio/high_mean": 0.0010250580944557441,
      "clip_ratio/low_mean": 0.0011763858419726603,
      "clip_ratio/low_min": 5.473867895489093e-05,
      "clip_ratio/region_mean": 0.0022014439455233514,
      "epoch": 0.03555991110022225,
      "grad_norm": 0.1170274168252945,
      "learning_rate": 1e-06,
      "loss": 0.0051,
      "step": 381
    },
    {
      "clip_ratio/high_max": 0.0024813237905618735,
      "clip_ratio/high_mean": 0.0010466479743627133,
      "clip_ratio/low_mean": 0.0013100554278935306,
      "clip_ratio/low_min": 0.00032503129477845505,
      "clip_ratio/region_mean": 0.0023567034004372545,
      "epoch": 0.03565324420022283,
      "grad_norm": 0.12184745818376541,
      "learning_rate": 1e-06,
      "loss": 0.014,
      "step": 382
    },
    {
      "clip_ratio/high_max": 0.002297039158293046,
      "clip_ratio/high_mean": 0.0010228568207821809,
      "clip_ratio/low_mean": 0.0012469372504710918,
      "clip_ratio/low_min": 0.00012439452621038072,
      "clip_ratio/region_mean": 0.002269794036692474,
      "epoch": 0.03574657730022342,
      "grad_norm": 0.1195698007941246,
      "learning_rate": 1e-06,
      "loss": -0.0077,
      "step": 383
    },
    {
      "clip_ratio/high_max": 0.0020837840129388496,
      "clip_ratio/high_mean": 0.0008683273645146983,
      "clip_ratio/low_mean": 0.0012905644834972918,
      "clip_ratio/low_min": 0.0002028144008363597,
      "clip_ratio/region_mean": 0.0021588918898487464,
      "epoch": 0.035839910400224,
      "grad_norm": 0.1446634829044342,
      "learning_rate": 1e-06,
      "loss": -0.0095,
      "step": 384
    },
    {
      "clip_ratio/high_max": 0.002249407330964459,
      "clip_ratio/high_mean": 0.0009522568707325263,
      "clip_ratio/low_mean": 0.0009188744315906661,
      "clip_ratio/low_min": 8.93153783181333e-05,
      "clip_ratio/region_mean": 0.0018711313896346837,
      "completions/clipped_ratio": 0.013619559151785698,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4087.0,
      "completions/mean_length": 613.9982299804688,
      "completions/mean_terminated_length": 565.9200439453125,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.03593324350022458,
      "grad_norm": 25.646211624145508,
      "learning_rate": 1e-06,
      "loss": 0.1073,
      "num_tokens": 325348833.0,
      "reward": 0.582711398601532,
      "reward_std": 0.19923368096351624,
      "rewards/simpleverify_reward/mean": 0.5827113389968872,
      "rewards/simpleverify_reward/std": 0.49311351776123047,
      "step": 385
    },
    {
      "clip_ratio/high_max": 0.002067670058750082,
      "clip_ratio/high_mean": 0.0008996190608741017,
      "clip_ratio/low_mean": 0.0010475958952156361,
      "clip_ratio/low_min": 4.895178244623821e-05,
      "clip_ratio/region_mean": 0.0019472149760986213,
      "epoch": 0.036026576600225166,
      "grad_norm": 17.868595123291016,
      "learning_rate": 1e-06,
      "loss": 0.2024,
      "step": 386
    },
    {
      "clip_ratio/high_max": 0.0026831048671738245,
      "clip_ratio/high_mean": 0.0010850908856809838,
      "clip_ratio/low_mean": 0.0010147848843189422,
      "clip_ratio/low_min": 0.00010342623772885418,
      "clip_ratio/region_mean": 0.002099875775456894,
      "epoch": 0.03611990970022575,
      "grad_norm": 0.12918300926685333,
      "learning_rate": 1e-06,
      "loss": 0.057,
      "step": 387
    },
    {
      "clip_ratio/high_max": 0.002469547434884589,
      "clip_ratio/high_mean": 0.0009313369773735758,
      "clip_ratio/low_mean": 0.0009581187514413614,
      "clip_ratio/low_min": 8.98518137546489e-05,
      "clip_ratio/region_mean": 0.001889455692435149,
      "epoch": 0.03621324280022633,
      "grad_norm": 111.1423110961914,
      "learning_rate": 1e-06,
      "loss": 0.1181,
      "step": 388
    },
    {
      "clip_ratio/high_max": 0.0020690788951469585,
      "clip_ratio/high_mean": 0.0008665561781526776,
      "clip_ratio/low_mean": 0.0010723034756665584,
      "clip_ratio/low_min": 0.00012222520399518544,
      "clip_ratio/region_mean": 0.0019388596701901406,
      "epoch": 0.036306575900226914,
      "grad_norm": 182.8689422607422,
      "learning_rate": 1e-06,
      "loss": 0.0617,
      "step": 389
    },
    {
      "clip_ratio/high_max": 0.0025762005243450403,
      "clip_ratio/high_mean": 0.0009452105859963922,
      "clip_ratio/low_mean": 0.001112248273784644,
      "clip_ratio/low_min": 0.00011019068097084528,
      "clip_ratio/region_mean": 0.0020574588197632693,
      "epoch": 0.0363999090002275,
      "grad_norm": 260.7861633300781,
      "learning_rate": 1e-06,
      "loss": 0.2447,
      "step": 390
    },
    {
      "clip_ratio/high_max": 0.0028776615363312885,
      "clip_ratio/high_mean": 0.0011305768821330275,
      "clip_ratio/low_mean": 0.0009817893151193857,
      "clip_ratio/low_min": 0.000157995007612044,
      "clip_ratio/region_mean": 0.0021123662445461378,
      "epoch": 0.036493242100228085,
      "grad_norm": 0.15227451920509338,
      "learning_rate": 1e-06,
      "loss": 0.0009,
      "step": 391
    },
    {
      "clip_ratio/high_max": 0.0023742825142107904,
      "clip_ratio/high_mean": 0.001022162312438013,
      "clip_ratio/low_mean": 0.0010293040395481512,
      "clip_ratio/low_min": 2.9523555895138998e-05,
      "clip_ratio/region_mean": 0.0020514663992798887,
      "epoch": 0.03658657520022866,
      "grad_norm": 0.12371998280286789,
      "learning_rate": 1e-06,
      "loss": 0.0188,
      "step": 392
    },
    {
      "clip_ratio/high_max": 0.0024497416816302575,
      "clip_ratio/high_mean": 0.0009842597391980235,
      "clip_ratio/low_mean": 0.001050512641086243,
      "clip_ratio/low_min": 0.00016549810061405879,
      "clip_ratio/region_mean": 0.002034772311162669,
      "epoch": 0.03667990830022925,
      "grad_norm": 6616.79150390625,
      "learning_rate": 1e-06,
      "loss": 1.4815,
      "step": 393
    },
    {
      "clip_ratio/high_max": 0.002531377787818201,
      "clip_ratio/high_mean": 0.0010408186390122864,
      "clip_ratio/low_mean": 0.0009986791792471195,
      "clip_ratio/low_min": 1.6771769878687337e-05,
      "clip_ratio/region_mean": 0.002039497790974565,
      "epoch": 0.036773241400229834,
      "grad_norm": 0.12149332463741302,
      "learning_rate": 1e-06,
      "loss": 0.0209,
      "step": 394
    },
    {
      "clip_ratio/high_max": 0.0023246789205586538,
      "clip_ratio/high_mean": 0.0009743188820721116,
      "clip_ratio/low_mean": 0.001059644178894814,
      "clip_ratio/low_min": 4.478173559618881e-05,
      "clip_ratio/region_mean": 0.0020339630791568197,
      "epoch": 0.03686657450023042,
      "grad_norm": 0.12550579011440277,
      "learning_rate": 1e-06,
      "loss": 0.0595,
      "step": 395
    },
    {
      "clip_ratio/high_max": 0.002719729862292297,
      "clip_ratio/high_mean": 0.0010334120634070132,
      "clip_ratio/low_mean": 0.0010996741038979962,
      "clip_ratio/low_min": 8.656009595142677e-05,
      "clip_ratio/region_mean": 0.002133086192770861,
      "epoch": 0.036959907600231,
      "grad_norm": 0.10799600183963776,
      "learning_rate": 1e-06,
      "loss": -0.0098,
      "step": 396
    },
    {
      "clip_ratio/high_max": 0.0024350728635909036,
      "clip_ratio/high_mean": 0.0010369525007263292,
      "clip_ratio/low_mean": 0.0012364416979835369,
      "clip_ratio/low_min": 0.00014030232341610827,
      "clip_ratio/region_mean": 0.0022733941950718872,
      "epoch": 0.03705324070023158,
      "grad_norm": 0.2517393231391907,
      "learning_rate": 1e-06,
      "loss": 0.0213,
      "step": 397
    },
    {
      "clip_ratio/high_max": 0.0022064178774598986,
      "clip_ratio/high_mean": 0.0009866075888567138,
      "clip_ratio/low_mean": 0.0011152268034493318,
      "clip_ratio/low_min": 0.0001264476595679298,
      "clip_ratio/region_mean": 0.0021018343686591834,
      "epoch": 0.03714657380023217,
      "grad_norm": 0.42689386010169983,
      "learning_rate": 1e-06,
      "loss": 0.0223,
      "step": 398
    },
    {
      "clip_ratio/high_max": 0.0027222053104196675,
      "clip_ratio/high_mean": 0.0010609816854412202,
      "clip_ratio/low_mean": 0.0011185719304194208,
      "clip_ratio/low_min": 0.0001686264713498531,
      "clip_ratio/region_mean": 0.0021795535903947894,
      "epoch": 0.03723990690023275,
      "grad_norm": 12.289047241210938,
      "learning_rate": 1e-06,
      "loss": 0.0404,
      "step": 399
    },
    {
      "clip_ratio/high_max": 0.002141905002645217,
      "clip_ratio/high_mean": 0.0008924581707105972,
      "clip_ratio/low_mean": 0.0010605488569126464,
      "clip_ratio/low_min": 0.00016607354882580694,
      "clip_ratio/region_mean": 0.001953007078554947,
      "epoch": 0.03733324000023333,
      "grad_norm": 0.12708602845668793,
      "learning_rate": 1e-06,
      "loss": 0.0151,
      "step": 400
    },
    {
      "clip_ratio/high_max": 0.0026312369518564083,
      "clip_ratio/high_mean": 0.0009713691142678726,
      "clip_ratio/low_mean": 0.001152117320089019,
      "clip_ratio/low_min": 3.873166861012578e-05,
      "clip_ratio/region_mean": 0.0021234863670542836,
      "epoch": 0.037426573100233916,
      "grad_norm": 0.1036255732178688,
      "learning_rate": 1e-06,
      "loss": 0.0391,
      "step": 401
    },
    {
      "clip_ratio/high_max": 0.002453912478813436,
      "clip_ratio/high_mean": 0.001055428172549,
      "clip_ratio/low_mean": 0.001001802596874768,
      "clip_ratio/low_min": 4.2193163608317263e-05,
      "clip_ratio/region_mean": 0.0020572307621478103,
      "epoch": 0.0375199062002345,
      "grad_norm": 0.1153542622923851,
      "learning_rate": 1e-06,
      "loss": 0.0146,
      "step": 402
    },
    {
      "clip_ratio/high_max": 0.002451273521728581,
      "clip_ratio/high_mean": 0.0010216802638751687,
      "clip_ratio/low_mean": 0.0010770295539259678,
      "clip_ratio/low_min": 0.00012786481875082245,
      "clip_ratio/region_mean": 0.002098709846904967,
      "epoch": 0.03761323930023508,
      "grad_norm": 79.2166976928711,
      "learning_rate": 1e-06,
      "loss": 0.022,
      "step": 403
    },
    {
      "clip_ratio/high_max": 0.002031783093116246,
      "clip_ratio/high_mean": 0.0008570750114813563,
      "clip_ratio/low_mean": 0.0010908130097959656,
      "clip_ratio/low_min": 3.844057209789753e-05,
      "clip_ratio/region_mean": 0.0019478880349197425,
      "epoch": 0.037706572400235665,
      "grad_norm": 0.11656417697668076,
      "learning_rate": 1e-06,
      "loss": 0.0292,
      "step": 404
    },
    {
      "clip_ratio/high_max": 0.002362692335736938,
      "clip_ratio/high_mean": 0.0009676938370830612,
      "clip_ratio/low_mean": 0.001088626577256946,
      "clip_ratio/low_min": 0.00012091054259144585,
      "clip_ratio/region_mean": 0.0020563204670907,
      "epoch": 0.03779990550023625,
      "grad_norm": 0.11351550370454788,
      "learning_rate": 1e-06,
      "loss": 0.0703,
      "step": 405
    },
    {
      "clip_ratio/high_max": 0.0021893087177886628,
      "clip_ratio/high_mean": 0.0010168567332584644,
      "clip_ratio/low_mean": 0.0011922485864488408,
      "clip_ratio/low_min": 0.00015677638839406427,
      "clip_ratio/region_mean": 0.002209105332440231,
      "epoch": 0.037893238600236835,
      "grad_norm": 0.2789289653301239,
      "learning_rate": 1e-06,
      "loss": 0.0212,
      "step": 406
    },
    {
      "clip_ratio/high_max": 0.002066814085992519,
      "clip_ratio/high_mean": 0.0008650986110296799,
      "clip_ratio/low_mean": 0.0011928926141990814,
      "clip_ratio/low_min": 0.00016279277224384714,
      "clip_ratio/region_mean": 0.002057991237961687,
      "epoch": 0.03798657170023741,
      "grad_norm": 0.12234649807214737,
      "learning_rate": 1e-06,
      "loss": 0.0685,
      "step": 407
    },
    {
      "clip_ratio/high_max": 0.0023458638970623724,
      "clip_ratio/high_mean": 0.0009759523345564958,
      "clip_ratio/low_mean": 0.0010563223568169633,
      "clip_ratio/low_min": 0.00013646559455082752,
      "clip_ratio/region_mean": 0.002032274664088618,
      "epoch": 0.038079904800238,
      "grad_norm": 0.11095178872346878,
      "learning_rate": 1e-06,
      "loss": 0.0635,
      "step": 408
    },
    {
      "clip_ratio/high_max": 0.0021028829578426667,
      "clip_ratio/high_mean": 0.000901340401469497,
      "clip_ratio/low_mean": 0.0010760918958112597,
      "clip_ratio/low_min": 9.700328337203246e-05,
      "clip_ratio/region_mean": 0.001977432330022566,
      "epoch": 0.038173237900238584,
      "grad_norm": 0.11165999621152878,
      "learning_rate": 1e-06,
      "loss": 0.0247,
      "step": 409
    },
    {
      "clip_ratio/high_max": 0.002505515411030501,
      "clip_ratio/high_mean": 0.0009516960417386144,
      "clip_ratio/low_mean": 0.0010113672615261748,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0019630632814369164,
      "epoch": 0.03826657100023917,
      "grad_norm": 0.11181530356407166,
      "learning_rate": 1e-06,
      "loss": 0.0363,
      "step": 410
    },
    {
      "clip_ratio/high_max": 0.0025688495879876427,
      "clip_ratio/high_mean": 0.0011073986534029245,
      "clip_ratio/low_mean": 0.0011780047789216042,
      "clip_ratio/low_min": 0.0001348697187495418,
      "clip_ratio/region_mean": 0.002285403446876444,
      "epoch": 0.03835990410023975,
      "grad_norm": 0.7511307001113892,
      "learning_rate": 1e-06,
      "loss": 0.0363,
      "step": 411
    },
    {
      "clip_ratio/high_max": 0.002582698012702167,
      "clip_ratio/high_mean": 0.001013639663142385,
      "clip_ratio/low_mean": 0.0011140792230435181,
      "clip_ratio/low_min": 0.00013854836925020209,
      "clip_ratio/region_mean": 0.0021277188934618607,
      "epoch": 0.03845323720024033,
      "grad_norm": 1.0676027536392212,
      "learning_rate": 1e-06,
      "loss": 0.0184,
      "step": 412
    },
    {
      "clip_ratio/high_max": 0.0022497668833239004,
      "clip_ratio/high_mean": 0.0009708232973935083,
      "clip_ratio/low_mean": 0.001193323107145261,
      "clip_ratio/low_min": 6.63809241814306e-05,
      "clip_ratio/region_mean": 0.0021641464190906845,
      "epoch": 0.03854657030024092,
      "grad_norm": 0.48996543884277344,
      "learning_rate": 1e-06,
      "loss": 0.0171,
      "step": 413
    },
    {
      "clip_ratio/high_max": 0.0024030716813285835,
      "clip_ratio/high_mean": 0.0009532924068480497,
      "clip_ratio/low_mean": 0.001171562365925638,
      "clip_ratio/low_min": 0.00012433270967449062,
      "clip_ratio/region_mean": 0.0021248547855066136,
      "epoch": 0.038639903400241496,
      "grad_norm": 0.11026362329721451,
      "learning_rate": 1e-06,
      "loss": 0.0345,
      "step": 414
    },
    {
      "clip_ratio/high_max": 0.002473651125910692,
      "clip_ratio/high_mean": 0.0008779411837167572,
      "clip_ratio/low_mean": 0.0010945960038952762,
      "clip_ratio/low_min": 4.567735413729679e-05,
      "clip_ratio/region_mean": 0.0019725371967069805,
      "epoch": 0.03873323650024208,
      "grad_norm": 0.11202587187290192,
      "learning_rate": 1e-06,
      "loss": -0.0133,
      "step": 415
    },
    {
      "clip_ratio/high_max": 0.0022820236190455034,
      "clip_ratio/high_mean": 0.0009653055367380148,
      "clip_ratio/low_mean": 0.0010611517136567272,
      "clip_ratio/low_min": 8.180870827345643e-05,
      "clip_ratio/region_mean": 0.002026457237661816,
      "epoch": 0.038826569600242666,
      "grad_norm": 0.11086110770702362,
      "learning_rate": 1e-06,
      "loss": -0.017,
      "step": 416
    },
    {
      "clip_ratio/high_max": 0.0026077920156239998,
      "clip_ratio/high_mean": 0.0010575046890153317,
      "clip_ratio/low_mean": 0.0013064665217825677,
      "clip_ratio/low_min": 0.0001920913127833046,
      "clip_ratio/region_mean": 0.0023639711944269948,
      "epoch": 0.03891990270024325,
      "grad_norm": 0.11942239850759506,
      "learning_rate": 1e-06,
      "loss": 0.0507,
      "step": 417
    },
    {
      "clip_ratio/high_max": 0.0022294865048024803,
      "clip_ratio/high_mean": 0.0009274838212149916,
      "clip_ratio/low_mean": 0.001136209859396331,
      "clip_ratio/low_min": 0.00010910385390161537,
      "clip_ratio/region_mean": 0.0020636937333620153,
      "epoch": 0.03901323580024383,
      "grad_norm": 0.11716679483652115,
      "learning_rate": 1e-06,
      "loss": 0.051,
      "step": 418
    },
    {
      "clip_ratio/high_max": 0.002278532829222968,
      "clip_ratio/high_mean": 0.0009009390378196258,
      "clip_ratio/low_mean": 0.0013087997722323053,
      "clip_ratio/low_min": 0.0001721689832265838,
      "clip_ratio/region_mean": 0.0022097387409303337,
      "epoch": 0.039106568900244415,
      "grad_norm": 0.1899026483297348,
      "learning_rate": 1e-06,
      "loss": 0.016,
      "step": 419
    },
    {
      "clip_ratio/high_max": 0.0022739600535715,
      "clip_ratio/high_mean": 0.0009323005233454751,
      "clip_ratio/low_mean": 0.001358584140689345,
      "clip_ratio/low_min": 0.00012051994599460158,
      "clip_ratio/region_mean": 0.0022908847604412585,
      "epoch": 0.039199902000245,
      "grad_norm": 0.12367464601993561,
      "learning_rate": 1e-06,
      "loss": 0.0295,
      "step": 420
    },
    {
      "clip_ratio/high_max": 0.002480124225257896,
      "clip_ratio/high_mean": 0.0010232046297460329,
      "clip_ratio/low_mean": 0.0012769949244102463,
      "clip_ratio/low_min": 6.096029483160237e-05,
      "clip_ratio/region_mean": 0.0023001995505183004,
      "epoch": 0.039293235100245585,
      "grad_norm": 0.11549799144268036,
      "learning_rate": 1e-06,
      "loss": 0.0125,
      "step": 421
    },
    {
      "clip_ratio/high_max": 0.002469808707246557,
      "clip_ratio/high_mean": 0.0010399159400549252,
      "clip_ratio/low_mean": 0.0012084107147529721,
      "clip_ratio/low_min": 0.00010879743695113575,
      "clip_ratio/region_mean": 0.0022483267021016218,
      "epoch": 0.039386568200246164,
      "grad_norm": 0.11152950674295425,
      "learning_rate": 1e-06,
      "loss": -0.0009,
      "step": 422
    },
    {
      "clip_ratio/high_max": 0.0026854256211663596,
      "clip_ratio/high_mean": 0.0010510823885852005,
      "clip_ratio/low_mean": 0.0013436911594908452,
      "clip_ratio/low_min": 0.0001464334436604986,
      "clip_ratio/region_mean": 0.002394773531705141,
      "epoch": 0.03947990130024675,
      "grad_norm": 0.10431065410375595,
      "learning_rate": 1e-06,
      "loss": 0.0355,
      "step": 423
    },
    {
      "clip_ratio/high_max": 0.002534257189836353,
      "clip_ratio/high_mean": 0.00112330846968689,
      "clip_ratio/low_mean": 0.0013213567399361636,
      "clip_ratio/low_min": 0.00011886351967405062,
      "clip_ratio/region_mean": 0.0024446651514153928,
      "epoch": 0.039573234400247334,
      "grad_norm": 0.13028563559055328,
      "learning_rate": 1e-06,
      "loss": 0.0442,
      "step": 424
    },
    {
      "clip_ratio/high_max": 0.0019954144554503728,
      "clip_ratio/high_mean": 0.000917303295864258,
      "clip_ratio/low_mean": 0.0014813743509876076,
      "clip_ratio/low_min": 0.0001240512710865005,
      "clip_ratio/region_mean": 0.0023986775559023954,
      "epoch": 0.03966656750024792,
      "grad_norm": 0.12728068232536316,
      "learning_rate": 1e-06,
      "loss": 0.0585,
      "step": 425
    },
    {
      "clip_ratio/high_max": 0.0020989308832213283,
      "clip_ratio/high_mean": 0.0009160503723251168,
      "clip_ratio/low_mean": 0.0014201571757439524,
      "clip_ratio/low_min": 0.0002168270275433315,
      "clip_ratio/region_mean": 0.0023362075953627937,
      "epoch": 0.0397599006002485,
      "grad_norm": 0.16264601051807404,
      "learning_rate": 1e-06,
      "loss": 0.0624,
      "step": 426
    },
    {
      "clip_ratio/high_max": 0.0021426433195301797,
      "clip_ratio/high_mean": 0.000896576768354862,
      "clip_ratio/low_mean": 0.001322147747487179,
      "clip_ratio/low_min": 9.162742026092019e-05,
      "clip_ratio/region_mean": 0.0022187244831002317,
      "epoch": 0.03985323370024908,
      "grad_norm": 0.10477511584758759,
      "learning_rate": 1e-06,
      "loss": 0.0099,
      "step": 427
    },
    {
      "clip_ratio/high_max": 0.0024193348581320606,
      "clip_ratio/high_mean": 0.0009610278211766854,
      "clip_ratio/low_mean": 0.0012633223341254052,
      "clip_ratio/low_min": 0.0001198755899167736,
      "clip_ratio/region_mean": 0.0022243501516641118,
      "epoch": 0.03994656680024967,
      "grad_norm": 0.12390594184398651,
      "learning_rate": 1e-06,
      "loss": 0.0232,
      "step": 428
    },
    {
      "clip_ratio/high_max": 0.0020847667692578398,
      "clip_ratio/high_mean": 0.0009542134248476941,
      "clip_ratio/low_mean": 0.0011549616538104601,
      "clip_ratio/low_min": 0.0001373622963001253,
      "clip_ratio/region_mean": 0.0021091750968480483,
      "epoch": 0.040039899900250246,
      "grad_norm": 2.778806447982788,
      "learning_rate": 1e-06,
      "loss": 0.0003,
      "step": 429
    },
    {
      "clip_ratio/high_max": 0.0025836441564024426,
      "clip_ratio/high_mean": 0.0011250056813878473,
      "clip_ratio/low_mean": 0.0012500049233494792,
      "clip_ratio/low_min": 0.0001842158399085747,
      "clip_ratio/region_mean": 0.002375010633841157,
      "epoch": 0.04013323300025083,
      "grad_norm": 54.640708923339844,
      "learning_rate": 1e-06,
      "loss": 9.0728,
      "step": 430
    },
    {
      "clip_ratio/high_max": 0.001933260733494535,
      "clip_ratio/high_mean": 0.0008873352708178572,
      "clip_ratio/low_mean": 0.001147896888141986,
      "clip_ratio/low_min": 0.0001697036059340462,
      "clip_ratio/region_mean": 0.002035232144407928,
      "epoch": 0.04022656610025142,
      "grad_norm": 0.1280539333820343,
      "learning_rate": 1e-06,
      "loss": 0.0412,
      "step": 431
    },
    {
      "clip_ratio/high_max": 0.0023835966203478165,
      "clip_ratio/high_mean": 0.001047114794346271,
      "clip_ratio/low_mean": 0.0011902262558578514,
      "clip_ratio/low_min": 4.6797200411674567e-05,
      "clip_ratio/region_mean": 0.0022373410320142284,
      "epoch": 0.040319899200252,
      "grad_norm": 12.68848991394043,
      "learning_rate": 1e-06,
      "loss": 0.0265,
      "step": 432
    },
    {
      "clip_ratio/high_max": 0.002404195533017628,
      "clip_ratio/high_mean": 0.001040061721141683,
      "clip_ratio/low_mean": 0.0012366080882202368,
      "clip_ratio/low_min": 8.876696938386885e-05,
      "clip_ratio/region_mean": 0.0022766698530176654,
      "epoch": 0.04041323230025258,
      "grad_norm": 0.11501103639602661,
      "learning_rate": 1e-06,
      "loss": 0.0577,
      "step": 433
    },
    {
      "clip_ratio/high_max": 0.002308251685462892,
      "clip_ratio/high_mean": 0.0009945334040821763,
      "clip_ratio/low_mean": 0.0012643223672057502,
      "clip_ratio/low_min": 9.360061358165694e-05,
      "clip_ratio/region_mean": 0.0022588557621929795,
      "epoch": 0.040506565400253165,
      "grad_norm": 0.11349420994520187,
      "learning_rate": 1e-06,
      "loss": 0.0275,
      "step": 434
    },
    {
      "clip_ratio/high_max": 0.002837083717167843,
      "clip_ratio/high_mean": 0.001185728506243322,
      "clip_ratio/low_mean": 0.0011361503638909198,
      "clip_ratio/low_min": 8.328311105287867e-05,
      "clip_ratio/region_mean": 0.00232187890651403,
      "epoch": 0.04059989850025375,
      "grad_norm": 0.1295388787984848,
      "learning_rate": 1e-06,
      "loss": -0.0434,
      "step": 435
    },
    {
      "clip_ratio/high_max": 0.002334456396056339,
      "clip_ratio/high_mean": 0.0009760251523402985,
      "clip_ratio/low_mean": 0.001292510401981417,
      "clip_ratio/low_min": 0.00011655015623546205,
      "clip_ratio/region_mean": 0.0022685355215799063,
      "epoch": 0.040693231600254336,
      "grad_norm": 0.12310700118541718,
      "learning_rate": 1e-06,
      "loss": 0.0508,
      "step": 436
    },
    {
      "clip_ratio/high_max": 0.0022471420052170288,
      "clip_ratio/high_mean": 0.0009750290591910016,
      "clip_ratio/low_mean": 0.0013760944257228402,
      "clip_ratio/low_min": 9.890980982163455e-05,
      "clip_ratio/region_mean": 0.0023511234976467676,
      "epoch": 0.040786564700254914,
      "grad_norm": 0.12615050375461578,
      "learning_rate": 1e-06,
      "loss": 0.0437,
      "step": 437
    },
    {
      "clip_ratio/high_max": 0.0026431280675751623,
      "clip_ratio/high_mean": 0.0010137643012058106,
      "clip_ratio/low_mean": 0.0011139116850245045,
      "clip_ratio/low_min": 7.798544083925663e-05,
      "clip_ratio/region_mean": 0.0021276760307955556,
      "epoch": 0.0408798978002555,
      "grad_norm": 0.11678317934274673,
      "learning_rate": 1e-06,
      "loss": -0.0252,
      "step": 438
    },
    {
      "clip_ratio/high_max": 0.0023802153300493956,
      "clip_ratio/high_mean": 0.0009454761584493099,
      "clip_ratio/low_mean": 0.00115106920566177,
      "clip_ratio/low_min": 0.00011781001921917778,
      "clip_ratio/region_mean": 0.0020965453441021964,
      "epoch": 0.040973230900256084,
      "grad_norm": 0.1235341802239418,
      "learning_rate": 1e-06,
      "loss": -0.0053,
      "step": 439
    },
    {
      "clip_ratio/high_max": 0.0020673832041211426,
      "clip_ratio/high_mean": 0.0009385839366586879,
      "clip_ratio/low_mean": 0.0011467592667031568,
      "clip_ratio/low_min": 8.075160440057516e-05,
      "clip_ratio/region_mean": 0.0020853432433796115,
      "epoch": 0.04106656400025666,
      "grad_norm": 0.10878008604049683,
      "learning_rate": 1e-06,
      "loss": 0.0487,
      "step": 440
    },
    {
      "clip_ratio/high_max": 0.0021675955067621544,
      "clip_ratio/high_mean": 0.0009030082328536082,
      "clip_ratio/low_mean": 0.001254392587725306,
      "clip_ratio/low_min": 0.0001369479005006724,
      "clip_ratio/region_mean": 0.0021574007623712532,
      "epoch": 0.04115989710025725,
      "grad_norm": 0.10853538662195206,
      "learning_rate": 1e-06,
      "loss": 0.0433,
      "step": 441
    },
    {
      "clip_ratio/high_max": 0.0025476321825408377,
      "clip_ratio/high_mean": 0.0010242823518638033,
      "clip_ratio/low_mean": 0.0014408091028599301,
      "clip_ratio/low_min": 0.0001836762257880764,
      "clip_ratio/region_mean": 0.0024650913910591044,
      "epoch": 0.04125323020025783,
      "grad_norm": 0.12676697969436646,
      "learning_rate": 1e-06,
      "loss": 0.043,
      "step": 442
    },
    {
      "clip_ratio/high_max": 0.002140582466381602,
      "clip_ratio/high_mean": 0.0008623576413810952,
      "clip_ratio/low_mean": 0.0011736539308913052,
      "clip_ratio/low_min": 7.872206879255828e-05,
      "clip_ratio/region_mean": 0.002036011530435644,
      "epoch": 0.04134656330025842,
      "grad_norm": 0.11287907510995865,
      "learning_rate": 1e-06,
      "loss": 0.0266,
      "step": 443
    },
    {
      "clip_ratio/high_max": 0.002424163936666446,
      "clip_ratio/high_mean": 0.0010643073601386277,
      "clip_ratio/low_mean": 0.0010743604125309503,
      "clip_ratio/low_min": 4.598328723659506e-05,
      "clip_ratio/region_mean": 0.002138667790859472,
      "epoch": 0.041439896400258996,
      "grad_norm": 0.13857538998126984,
      "learning_rate": 1e-06,
      "loss": 0.001,
      "step": 444
    },
    {
      "clip_ratio/high_max": 0.002274577105708886,
      "clip_ratio/high_mean": 0.0009725368345243623,
      "clip_ratio/low_mean": 0.0010961568277707556,
      "clip_ratio/low_min": 0.000193777819731622,
      "clip_ratio/region_mean": 0.002068693662295118,
      "epoch": 0.04153322950025958,
      "grad_norm": 0.10923687368631363,
      "learning_rate": 1e-06,
      "loss": -0.002,
      "step": 445
    },
    {
      "clip_ratio/high_max": 0.002088048840960255,
      "clip_ratio/high_mean": 0.0009893544010992628,
      "clip_ratio/low_mean": 0.0010823304044151882,
      "clip_ratio/low_min": 6.492273860203568e-05,
      "clip_ratio/region_mean": 0.0020716848084703088,
      "epoch": 0.04162656260026017,
      "grad_norm": 0.13394789397716522,
      "learning_rate": 1e-06,
      "loss": -0.0257,
      "step": 446
    },
    {
      "clip_ratio/high_max": 0.002701765079109464,
      "clip_ratio/high_mean": 0.0010838742018677294,
      "clip_ratio/low_mean": 0.0011468359552964102,
      "clip_ratio/low_min": 0.0001046391635100008,
      "clip_ratio/region_mean": 0.0022307101025944576,
      "epoch": 0.04171989570026075,
      "grad_norm": 0.12949150800704956,
      "learning_rate": 1e-06,
      "loss": -0.0451,
      "step": 447
    },
    {
      "clip_ratio/high_max": 0.0021030796342529356,
      "clip_ratio/high_mean": 0.0008702351115061902,
      "clip_ratio/low_mean": 0.001184272587124724,
      "clip_ratio/low_min": 0.00022214568161871284,
      "clip_ratio/region_mean": 0.0020545077277347445,
      "epoch": 0.04181322880026133,
      "grad_norm": 0.11956897377967834,
      "learning_rate": 1e-06,
      "loss": 0.0506,
      "step": 448
    },
    {
      "clip_ratio/high_max": 0.0025427526052226312,
      "clip_ratio/high_mean": 0.0010415463693789206,
      "clip_ratio/low_mean": 0.001196772966068238,
      "clip_ratio/low_min": 8.376908954232931e-05,
      "clip_ratio/region_mean": 0.0022383193572750315,
      "epoch": 0.041906561900261916,
      "grad_norm": 0.11449374258518219,
      "learning_rate": 1e-06,
      "loss": 0.0032,
      "step": 449
    },
    {
      "clip_ratio/high_max": 0.0022070157356210984,
      "clip_ratio/high_mean": 0.0008446124647889519,
      "clip_ratio/low_mean": 0.0012799747637473047,
      "clip_ratio/low_min": 6.412282345991116e-05,
      "clip_ratio/region_mean": 0.0021245872412691824,
      "epoch": 0.0419998950002625,
      "grad_norm": 0.12278907746076584,
      "learning_rate": 1e-06,
      "loss": 0.0502,
      "step": 450
    },
    {
      "clip_ratio/high_max": 0.002613900818687398,
      "clip_ratio/high_mean": 0.0011630403314484283,
      "clip_ratio/low_mean": 0.0012179805653431686,
      "clip_ratio/low_min": 0.0001019046194414841,
      "clip_ratio/region_mean": 0.0023810209168004803,
      "epoch": 0.042093228100263086,
      "grad_norm": 0.2274618148803711,
      "learning_rate": 1e-06,
      "loss": 0.0062,
      "step": 451
    },
    {
      "clip_ratio/high_max": 0.0020158883817202877,
      "clip_ratio/high_mean": 0.0008125750391627662,
      "clip_ratio/low_mean": 0.0015901314181974158,
      "clip_ratio/low_min": 0.0001677200671110768,
      "clip_ratio/region_mean": 0.002402706471912097,
      "epoch": 0.042186561200263664,
      "grad_norm": 0.11661520600318909,
      "learning_rate": 1e-06,
      "loss": 0.0571,
      "step": 452
    },
    {
      "clip_ratio/high_max": 0.0018951612437376752,
      "clip_ratio/high_mean": 0.0008031379347812617,
      "clip_ratio/low_mean": 0.00128961973132391,
      "clip_ratio/low_min": 0.00017866119196696673,
      "clip_ratio/region_mean": 0.002092757618811447,
      "epoch": 0.04227989430026425,
      "grad_norm": 0.11419399082660675,
      "learning_rate": 1e-06,
      "loss": 0.0527,
      "step": 453
    },
    {
      "clip_ratio/high_max": 0.0019802157912636176,
      "clip_ratio/high_mean": 0.0007942871070554247,
      "clip_ratio/low_mean": 0.0010927617076958995,
      "clip_ratio/low_min": 6.191489092088887e-05,
      "clip_ratio/region_mean": 0.0018870487765525468,
      "epoch": 0.042373227400264835,
      "grad_norm": 0.11077532172203064,
      "learning_rate": 1e-06,
      "loss": 0.0433,
      "step": 454
    },
    {
      "clip_ratio/high_max": 0.002080933227261994,
      "clip_ratio/high_mean": 0.0008692070241522742,
      "clip_ratio/low_mean": 0.0013762066446361132,
      "clip_ratio/low_min": 0.0002110941550199641,
      "clip_ratio/region_mean": 0.0022454136924352497,
      "epoch": 0.04246656050026541,
      "grad_norm": 0.11451329290866852,
      "learning_rate": 1e-06,
      "loss": 0.0698,
      "step": 455
    },
    {
      "clip_ratio/high_max": 0.0028301770871621557,
      "clip_ratio/high_mean": 0.0011058487980335485,
      "clip_ratio/low_mean": 0.001249912013008725,
      "clip_ratio/low_min": 0.00019412276742514223,
      "clip_ratio/region_mean": 0.002355760763748549,
      "epoch": 0.042559893600266,
      "grad_norm": 0.12839896976947784,
      "learning_rate": 1e-06,
      "loss": -0.0184,
      "step": 456
    },
    {
      "clip_ratio/high_max": 0.0021596031438093632,
      "clip_ratio/high_mean": 0.0009629893083911156,
      "clip_ratio/low_mean": 0.0011259939365118043,
      "clip_ratio/low_min": 9.444024453841848e-05,
      "clip_ratio/region_mean": 0.0020889832885586657,
      "epoch": 0.04265322670026658,
      "grad_norm": 0.2612585127353668,
      "learning_rate": 1e-06,
      "loss": 0.0138,
      "step": 457
    },
    {
      "clip_ratio/high_max": 0.002343076281249523,
      "clip_ratio/high_mean": 0.001028607028274564,
      "clip_ratio/low_mean": 0.0012364083959255368,
      "clip_ratio/low_min": 0.00013410425890469924,
      "clip_ratio/region_mean": 0.002265015384182334,
      "epoch": 0.04274655980026717,
      "grad_norm": 0.12061664462089539,
      "learning_rate": 1e-06,
      "loss": 0.0146,
      "step": 458
    },
    {
      "clip_ratio/high_max": 0.002508892248442862,
      "clip_ratio/high_mean": 0.001076467382517876,
      "clip_ratio/low_mean": 0.0012913583013869356,
      "clip_ratio/low_min": 7.221037594717927e-05,
      "clip_ratio/region_mean": 0.002367825662076939,
      "epoch": 0.04283989290026775,
      "grad_norm": 0.1079101711511612,
      "learning_rate": 1e-06,
      "loss": 0.0137,
      "step": 459
    },
    {
      "clip_ratio/high_max": 0.0024721603622310795,
      "clip_ratio/high_mean": 0.000982174722594209,
      "clip_ratio/low_mean": 0.0012021498550893739,
      "clip_ratio/low_min": 4.907491256744834e-05,
      "clip_ratio/region_mean": 0.002184324592235498,
      "epoch": 0.04293322600026833,
      "grad_norm": 0.11388076841831207,
      "learning_rate": 1e-06,
      "loss": 0.0248,
      "step": 460
    },
    {
      "clip_ratio/high_max": 0.0021407990498119034,
      "clip_ratio/high_mean": 0.0008957698009908199,
      "clip_ratio/low_mean": 0.0012666996371990535,
      "clip_ratio/low_min": 0.00021342346644814825,
      "clip_ratio/region_mean": 0.002162469369068276,
      "epoch": 0.04302655910026892,
      "grad_norm": 0.10794167965650558,
      "learning_rate": 1e-06,
      "loss": 0.0517,
      "step": 461
    },
    {
      "clip_ratio/high_max": 0.0022121062866062857,
      "clip_ratio/high_mean": 0.00101082428227528,
      "clip_ratio/low_mean": 0.0013233691024652217,
      "clip_ratio/low_min": 0.00013778938136965735,
      "clip_ratio/region_mean": 0.0023341934065683745,
      "epoch": 0.0431198922002695,
      "grad_norm": 0.12797607481479645,
      "learning_rate": 1e-06,
      "loss": 0.0713,
      "step": 462
    },
    {
      "clip_ratio/high_max": 0.002486055782355834,
      "clip_ratio/high_mean": 0.0010715318439906696,
      "clip_ratio/low_mean": 0.0009811017098400043,
      "clip_ratio/low_min": 8.93899659786257e-05,
      "clip_ratio/region_mean": 0.002052633608400356,
      "epoch": 0.04321322530027008,
      "grad_norm": 0.11894649267196655,
      "learning_rate": 1e-06,
      "loss": 0.0126,
      "step": 463
    },
    {
      "clip_ratio/high_max": 0.0019702802383108065,
      "clip_ratio/high_mean": 0.0009924004334607162,
      "clip_ratio/low_mean": 0.001027456475640065,
      "clip_ratio/low_min": 9.611607947590528e-05,
      "clip_ratio/region_mean": 0.0020198568963678554,
      "epoch": 0.043306558400270666,
      "grad_norm": 0.12023472040891647,
      "learning_rate": 1e-06,
      "loss": -0.0043,
      "step": 464
    },
    {
      "clip_ratio/high_max": 0.002276383886055555,
      "clip_ratio/high_mean": 0.0009723977236717474,
      "clip_ratio/low_mean": 0.0012431670438672882,
      "clip_ratio/low_min": 0.00010941943310172064,
      "clip_ratio/region_mean": 0.002215564774814993,
      "epoch": 0.04339989150027125,
      "grad_norm": 0.11027390509843826,
      "learning_rate": 1e-06,
      "loss": 0.0166,
      "step": 465
    },
    {
      "clip_ratio/high_max": 0.00218901781772729,
      "clip_ratio/high_mean": 0.0009813891720114043,
      "clip_ratio/low_mean": 0.0011943020799662918,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0021756912537966855,
      "epoch": 0.04349322460027183,
      "grad_norm": 0.12403442710638046,
      "learning_rate": 1e-06,
      "loss": -0.0306,
      "step": 466
    },
    {
      "clip_ratio/high_max": 0.0026907776336884126,
      "clip_ratio/high_mean": 0.001170337083749473,
      "clip_ratio/low_mean": 0.0011795625832746737,
      "clip_ratio/low_min": 7.412663671857445e-05,
      "clip_ratio/region_mean": 0.0023498997106798925,
      "epoch": 0.043586557700272414,
      "grad_norm": 0.23572413623332977,
      "learning_rate": 1e-06,
      "loss": -0.0222,
      "step": 467
    },
    {
      "clip_ratio/high_max": 0.0020260073797544464,
      "clip_ratio/high_mean": 0.000941921076446306,
      "clip_ratio/low_mean": 0.0010628185209498042,
      "clip_ratio/low_min": 0.00017466972349211574,
      "clip_ratio/region_mean": 0.0020047395591973327,
      "epoch": 0.043679890800273,
      "grad_norm": 0.11597782373428345,
      "learning_rate": 1e-06,
      "loss": 0.075,
      "step": 468
    },
    {
      "clip_ratio/high_max": 0.0023676328928559087,
      "clip_ratio/high_mean": 0.0010208651328866836,
      "clip_ratio/low_mean": 0.0011701043204084272,
      "clip_ratio/low_min": 0.00025888476557156537,
      "clip_ratio/region_mean": 0.0021909694551141,
      "epoch": 0.043773223900273585,
      "grad_norm": 0.12010545283555984,
      "learning_rate": 1e-06,
      "loss": 0.0392,
      "step": 469
    },
    {
      "clip_ratio/high_max": 0.0024410178084508516,
      "clip_ratio/high_mean": 0.0010038916698249523,
      "clip_ratio/low_mean": 0.001297725255426485,
      "clip_ratio/low_min": 8.251314466178883e-05,
      "clip_ratio/region_mean": 0.0023016169216134585,
      "epoch": 0.04386655700027416,
      "grad_norm": 0.11060360819101334,
      "learning_rate": 1e-06,
      "loss": 0.056,
      "step": 470
    },
    {
      "clip_ratio/high_max": 0.0023246165656019002,
      "clip_ratio/high_mean": 0.0010427327506477013,
      "clip_ratio/low_mean": 0.0011812723314506002,
      "clip_ratio/low_min": 0.00010678233047656249,
      "clip_ratio/region_mean": 0.0022240050457185134,
      "epoch": 0.04395989010027475,
      "grad_norm": 0.13037686049938202,
      "learning_rate": 1e-06,
      "loss": 0.0097,
      "step": 471
    },
    {
      "clip_ratio/high_max": 0.0019807315911748447,
      "clip_ratio/high_mean": 0.000886119763890747,
      "clip_ratio/low_mean": 0.0011592583723540884,
      "clip_ratio/low_min": 0.000134061661810847,
      "clip_ratio/region_mean": 0.0020453781107789837,
      "epoch": 0.044053223200275334,
      "grad_norm": 0.11048023402690887,
      "learning_rate": 1e-06,
      "loss": 0.0296,
      "step": 472
    },
    {
      "clip_ratio/high_max": 0.0021982141843182035,
      "clip_ratio/high_mean": 0.0008661290266900323,
      "clip_ratio/low_mean": 0.0012787375053449068,
      "clip_ratio/low_min": 8.145925312419422e-05,
      "clip_ratio/region_mean": 0.0021448665211210027,
      "epoch": 0.04414655630027592,
      "grad_norm": 0.12781262397766113,
      "learning_rate": 1e-06,
      "loss": 0.0295,
      "step": 473
    },
    {
      "clip_ratio/high_max": 0.0025377973179274704,
      "clip_ratio/high_mean": 0.0010488300358701963,
      "clip_ratio/low_mean": 0.0012911906815133989,
      "clip_ratio/low_min": 0.00013619333185488358,
      "clip_ratio/region_mean": 0.0023400206773658283,
      "epoch": 0.0442398894002765,
      "grad_norm": 0.11543948948383331,
      "learning_rate": 1e-06,
      "loss": 0.0471,
      "step": 474
    },
    {
      "clip_ratio/high_max": 0.002485527344106231,
      "clip_ratio/high_mean": 0.000976199104115949,
      "clip_ratio/low_mean": 0.0011549007213034201,
      "clip_ratio/low_min": 7.295667455764487e-05,
      "clip_ratio/region_mean": 0.0021310998490662314,
      "epoch": 0.04433322250027708,
      "grad_norm": 0.10828111320734024,
      "learning_rate": 1e-06,
      "loss": 0.0199,
      "step": 475
    },
    {
      "clip_ratio/high_max": 0.0022357157067744993,
      "clip_ratio/high_mean": 0.0009449659264646471,
      "clip_ratio/low_mean": 0.0012177722055639606,
      "clip_ratio/low_min": 7.049992518659565e-05,
      "clip_ratio/region_mean": 0.002162738106562756,
      "epoch": 0.04442655560027767,
      "grad_norm": 0.1449502855539322,
      "learning_rate": 1e-06,
      "loss": 0.0198,
      "step": 476
    },
    {
      "clip_ratio/high_max": 0.0023715003990218975,
      "clip_ratio/high_mean": 0.0009669085684436141,
      "clip_ratio/low_mean": 0.0009724647843540879,
      "clip_ratio/low_min": 8.651555435790215e-05,
      "clip_ratio/region_mean": 0.0019393733091419563,
      "epoch": 0.04451988870027825,
      "grad_norm": 0.10657148063182831,
      "learning_rate": 1e-06,
      "loss": 0.0291,
      "step": 477
    },
    {
      "clip_ratio/high_max": 0.002561667024565395,
      "clip_ratio/high_mean": 0.0010363210276409518,
      "clip_ratio/low_mean": 0.0009192878987960285,
      "clip_ratio/low_min": 7.535339773312444e-05,
      "clip_ratio/region_mean": 0.001955608939169906,
      "epoch": 0.04461322180027883,
      "grad_norm": 0.11485034227371216,
      "learning_rate": 1e-06,
      "loss": -0.0229,
      "step": 478
    },
    {
      "clip_ratio/high_max": 0.0024154626407835167,
      "clip_ratio/high_mean": 0.001086388569092378,
      "clip_ratio/low_mean": 0.0012085107864550082,
      "clip_ratio/low_min": 0.00012855926979682408,
      "clip_ratio/region_mean": 0.00229489931371063,
      "epoch": 0.044706554900279416,
      "grad_norm": 0.13590556383132935,
      "learning_rate": 1e-06,
      "loss": 0.0149,
      "step": 479
    },
    {
      "clip_ratio/high_max": 0.0021419750337372534,
      "clip_ratio/high_mean": 0.0009179272092296742,
      "clip_ratio/low_mean": 0.001058829093381064,
      "clip_ratio/low_min": 0.0002057566998701077,
      "clip_ratio/region_mean": 0.001976756306248717,
      "epoch": 0.04479988800028,
      "grad_norm": 0.11014196276664734,
      "learning_rate": 1e-06,
      "loss": 0.0458,
      "step": 480
    },
    {
      "clip_ratio/high_max": 0.0068283693108242005,
      "clip_ratio/high_mean": 0.003388633020222187,
      "clip_ratio/low_mean": 0.0025814563559833914,
      "clip_ratio/low_min": 0.00017360274796374142,
      "clip_ratio/region_mean": 0.005970089347101748,
      "completions/clipped_ratio": 0.013846261160714302,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4092.0,
      "completions/mean_length": 612.9391479492188,
      "completions/mean_terminated_length": 564.0345458984375,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.04489322110028058,
      "grad_norm": 0.4843619465827942,
      "learning_rate": 1e-06,
      "loss": 0.001,
      "num_tokens": 407094918.0,
      "reward": 0.5883702039718628,
      "reward_std": 0.19560304284095764,
      "rewards/simpleverify_reward/mean": 0.5883702039718628,
      "rewards/simpleverify_reward/std": 0.4921310544013977,
      "step": 481
    },
    {
      "clip_ratio/high_max": 0.0033458515972597525,
      "clip_ratio/high_mean": 0.0013139616130501963,
      "clip_ratio/low_mean": 0.0015563023334834725,
      "clip_ratio/low_min": 5.296991093928227e-05,
      "clip_ratio/region_mean": 0.0028702639101538807,
      "epoch": 0.044986554200281165,
      "grad_norm": 2527.047607421875,
      "learning_rate": 1e-06,
      "loss": 1.4222,
      "step": 482
    },
    {
      "clip_ratio/high_max": 0.0027680123457685113,
      "clip_ratio/high_mean": 0.0011017267388524488,
      "clip_ratio/low_mean": 0.0016614682244835421,
      "clip_ratio/low_min": 0.00014853656830382533,
      "clip_ratio/region_mean": 0.0027631948614725843,
      "epoch": 0.04507988730028175,
      "grad_norm": 510.69989013671875,
      "learning_rate": 1e-06,
      "loss": 0.6028,
      "step": 483
    },
    {
      "clip_ratio/high_max": 0.0031768308181199245,
      "clip_ratio/high_mean": 0.0011142092862428399,
      "clip_ratio/low_mean": 0.0014178931924107019,
      "clip_ratio/low_min": 0.00019267274910816923,
      "clip_ratio/region_mean": 0.002532102502300404,
      "epoch": 0.045173220400282335,
      "grad_norm": 0.23238655924797058,
      "learning_rate": 1e-06,
      "loss": 0.0192,
      "step": 484
    },
    {
      "clip_ratio/high_max": 0.002577004437625874,
      "clip_ratio/high_mean": 0.0011110767445643432,
      "clip_ratio/low_mean": 0.0013797566316497978,
      "clip_ratio/low_min": 0.00021669562556780875,
      "clip_ratio/region_mean": 0.0024908332779887132,
      "epoch": 0.04526655350028291,
      "grad_norm": 0.10628186166286469,
      "learning_rate": 1e-06,
      "loss": 0.0635,
      "step": 485
    },
    {
      "clip_ratio/high_max": 0.0025845861964626238,
      "clip_ratio/high_mean": 0.0010997064418916125,
      "clip_ratio/low_mean": 0.0016606345343461726,
      "clip_ratio/low_min": 0.00026107554003829136,
      "clip_ratio/region_mean": 0.002760341048997361,
      "epoch": 0.0453598866002835,
      "grad_norm": 0.8131551146507263,
      "learning_rate": 1e-06,
      "loss": 0.0532,
      "step": 486
    },
    {
      "clip_ratio/high_max": 0.0024196689555537887,
      "clip_ratio/high_mean": 0.0010397553087386768,
      "clip_ratio/low_mean": 0.0012581970731844194,
      "clip_ratio/low_min": 0.00016405338919867063,
      "clip_ratio/region_mean": 0.0022979523564572446,
      "epoch": 0.045453219700284084,
      "grad_norm": 0.23600368201732635,
      "learning_rate": 1e-06,
      "loss": 0.0385,
      "step": 487
    },
    {
      "clip_ratio/high_max": 0.002515620188205503,
      "clip_ratio/high_mean": 0.000991558645182522,
      "clip_ratio/low_mean": 0.0012843496406276245,
      "clip_ratio/low_min": 6.644496625085594e-05,
      "clip_ratio/region_mean": 0.0022759083367418498,
      "epoch": 0.04554655280028467,
      "grad_norm": 0.1144188642501831,
      "learning_rate": 1e-06,
      "loss": 0.0411,
      "step": 488
    },
    {
      "clip_ratio/high_max": 0.0024526447887183167,
      "clip_ratio/high_mean": 0.0010472735157236457,
      "clip_ratio/low_mean": 0.0012560411632875912,
      "clip_ratio/low_min": 4.429894033819437e-05,
      "clip_ratio/region_mean": 0.002303314679011237,
      "epoch": 0.04563988590028525,
      "grad_norm": 0.11381571739912033,
      "learning_rate": 1e-06,
      "loss": 0.0248,
      "step": 489
    },
    {
      "clip_ratio/high_max": 0.0026885835322900675,
      "clip_ratio/high_mean": 0.0009901262747007422,
      "clip_ratio/low_mean": 0.0013964284589746967,
      "clip_ratio/low_min": 0.00018861614807974547,
      "clip_ratio/region_mean": 0.0023865547045716085,
      "epoch": 0.04573321900028583,
      "grad_norm": 0.11780530214309692,
      "learning_rate": 1e-06,
      "loss": 0.0414,
      "step": 490
    },
    {
      "clip_ratio/high_max": 0.002672574919415638,
      "clip_ratio/high_mean": 0.0010306015974492766,
      "clip_ratio/low_mean": 0.0012131199691793881,
      "clip_ratio/low_min": 0.00020800485071958974,
      "clip_ratio/region_mean": 0.002243721595732495,
      "epoch": 0.04582655210028642,
      "grad_norm": 0.11309982091188431,
      "learning_rate": 1e-06,
      "loss": 0.0027,
      "step": 491
    },
    {
      "clip_ratio/high_max": 0.0028789570496883243,
      "clip_ratio/high_mean": 0.001139427004090976,
      "clip_ratio/low_mean": 0.0011789236341428477,
      "clip_ratio/low_min": 0.00014193737115419935,
      "clip_ratio/region_mean": 0.002318350634595845,
      "epoch": 0.045919885200286996,
      "grad_norm": 0.114866241812706,
      "learning_rate": 1e-06,
      "loss": 0.0027,
      "step": 492
    },
    {
      "clip_ratio/high_max": 0.0023531435454060556,
      "clip_ratio/high_mean": 0.0010862128874578048,
      "clip_ratio/low_mean": 0.0010686217556212796,
      "clip_ratio/low_min": 5.942418283666484e-05,
      "clip_ratio/region_mean": 0.002154834663087968,
      "epoch": 0.04601321830028758,
      "grad_norm": 0.10684971511363983,
      "learning_rate": 1e-06,
      "loss": 0.0099,
      "step": 493
    },
    {
      "clip_ratio/high_max": 0.002385315779974917,
      "clip_ratio/high_mean": 0.0010112362306244904,
      "clip_ratio/low_mean": 0.0012513366837083595,
      "clip_ratio/low_min": 0.00010183455015067011,
      "clip_ratio/region_mean": 0.002262572896142956,
      "epoch": 0.046106551400288166,
      "grad_norm": 118.60794830322266,
      "learning_rate": 1e-06,
      "loss": 0.0764,
      "step": 494
    },
    {
      "clip_ratio/high_max": 0.002378626901190728,
      "clip_ratio/high_mean": 0.0010235946356260683,
      "clip_ratio/low_mean": 0.0013515273640223313,
      "clip_ratio/low_min": 0.00021047444624855416,
      "clip_ratio/region_mean": 0.002375121955992654,
      "epoch": 0.04619988450028875,
      "grad_norm": 0.1452789604663849,
      "learning_rate": 1e-06,
      "loss": 0.0794,
      "step": 495
    },
    {
      "clip_ratio/high_max": 0.0028749601187882945,
      "clip_ratio/high_mean": 0.0012039989815093577,
      "clip_ratio/low_mean": 0.0013720227125304518,
      "clip_ratio/low_min": 8.736413110455032e-05,
      "clip_ratio/region_mean": 0.0025760217758943327,
      "epoch": 0.04629321760028933,
      "grad_norm": 0.17568452656269073,
      "learning_rate": 1e-06,
      "loss": -0.0116,
      "step": 496
    },
    {
      "clip_ratio/high_max": 0.0026140173504245467,
      "clip_ratio/high_mean": 0.0010809658142534317,
      "clip_ratio/low_mean": 0.0011473041122371797,
      "clip_ratio/low_min": 4.950197217112873e-05,
      "clip_ratio/region_mean": 0.0022282698628259823,
      "epoch": 0.046386550700289915,
      "grad_norm": 0.11483661830425262,
      "learning_rate": 1e-06,
      "loss": -0.0022,
      "step": 497
    },
    {
      "clip_ratio/high_max": 0.0028459546956582926,
      "clip_ratio/high_mean": 0.0012019352398056071,
      "clip_ratio/low_mean": 0.0010250484356220113,
      "clip_ratio/low_min": 8.880574750946835e-05,
      "clip_ratio/region_mean": 0.0022269836408668198,
      "epoch": 0.0464798838002905,
      "grad_norm": 0.11611884087324142,
      "learning_rate": 1e-06,
      "loss": -0.0317,
      "step": 498
    },
    {
      "clip_ratio/high_max": 0.002179981798690278,
      "clip_ratio/high_mean": 0.0009535617282381281,
      "clip_ratio/low_mean": 0.0010598306198517093,
      "clip_ratio/low_min": 7.751261091470951e-05,
      "clip_ratio/region_mean": 0.0020133923389948905,
      "epoch": 0.046573216900291085,
      "grad_norm": 0.11167261004447937,
      "learning_rate": 1e-06,
      "loss": 0.0363,
      "step": 499
    },
    {
      "clip_ratio/high_max": 0.002407583175227046,
      "clip_ratio/high_mean": 0.0010839545211638324,
      "clip_ratio/low_mean": 0.0012218191659485456,
      "clip_ratio/low_min": 8.460964272671845e-05,
      "clip_ratio/region_mean": 0.0023057736252667382,
      "epoch": 0.046666550000291664,
      "grad_norm": 0.11501043289899826,
      "learning_rate": 1e-06,
      "loss": 0.0172,
      "step": 500
    },
    {
      "clip_ratio/high_max": 0.0020014568872284144,
      "clip_ratio/high_mean": 0.0009790081167011522,
      "clip_ratio/low_mean": 0.0011973440450674389,
      "clip_ratio/low_min": 0.0001430540214641951,
      "clip_ratio/region_mean": 0.0021763521581306122,
      "epoch": 0.04675988310029225,
      "grad_norm": 0.12052631378173828,
      "learning_rate": 1e-06,
      "loss": 0.0284,
      "step": 501
    },
    {
      "clip_ratio/high_max": 0.0025867209405987523,
      "clip_ratio/high_mean": 0.0011445445288700284,
      "clip_ratio/low_mean": 0.0013901802085456438,
      "clip_ratio/low_min": 8.16054980532499e-05,
      "clip_ratio/region_mean": 0.0025347247283207253,
      "epoch": 0.046853216200292834,
      "grad_norm": 4.328678131103516,
      "learning_rate": 1e-06,
      "loss": 0.0247,
      "step": 502
    },
    {
      "clip_ratio/high_max": 0.0025174898582918104,
      "clip_ratio/high_mean": 0.001032432317515486,
      "clip_ratio/low_mean": 0.0008984917385532754,
      "clip_ratio/low_min": 5.683271956513636e-05,
      "clip_ratio/region_mean": 0.0019309240306029096,
      "epoch": 0.04694654930029342,
      "grad_norm": 0.10489113628864288,
      "learning_rate": 1e-06,
      "loss": -0.0039,
      "step": 503
    },
    {
      "clip_ratio/high_max": 0.002338741433050018,
      "clip_ratio/high_mean": 0.0008725345323910005,
      "clip_ratio/low_mean": 0.0011274783901171759,
      "clip_ratio/low_min": 0.00018113549776899163,
      "clip_ratio/region_mean": 0.002000012915232219,
      "epoch": 0.047039882400294,
      "grad_norm": 0.13507111370563507,
      "learning_rate": 1e-06,
      "loss": 0.03,
      "step": 504
    },
    {
      "clip_ratio/high_max": 0.0021831087942700833,
      "clip_ratio/high_mean": 0.0008164533282979392,
      "clip_ratio/low_mean": 0.0011655713606160134,
      "clip_ratio/low_min": 8.811126099317335e-05,
      "clip_ratio/region_mean": 0.0019820246525341645,
      "epoch": 0.04713321550029458,
      "grad_norm": 0.10306805372238159,
      "learning_rate": 1e-06,
      "loss": 0.0535,
      "step": 505
    },
    {
      "clip_ratio/high_max": 0.002360138860240113,
      "clip_ratio/high_mean": 0.000960228875555913,
      "clip_ratio/low_mean": 0.0010687160483939806,
      "clip_ratio/low_min": 5.986460109852487e-05,
      "clip_ratio/region_mean": 0.002028944953053724,
      "epoch": 0.04722654860029517,
      "grad_norm": 0.10228810459375381,
      "learning_rate": 1e-06,
      "loss": -0.0224,
      "step": 506
    },
    {
      "clip_ratio/high_max": 0.002650081616593525,
      "clip_ratio/high_mean": 0.0011420666924095713,
      "clip_ratio/low_mean": 0.0011115521429019282,
      "clip_ratio/low_min": 7.888176514825318e-05,
      "clip_ratio/region_mean": 0.0022536188407684676,
      "epoch": 0.047319881700295746,
      "grad_norm": 0.12124821543693542,
      "learning_rate": 1e-06,
      "loss": 0.0159,
      "step": 507
    },
    {
      "clip_ratio/high_max": 0.0019330538270878606,
      "clip_ratio/high_mean": 0.0008142490733007435,
      "clip_ratio/low_mean": 0.0013981367701489944,
      "clip_ratio/low_min": 5.3297328122425824e-05,
      "clip_ratio/region_mean": 0.002212385821621865,
      "epoch": 0.04741321480029633,
      "grad_norm": 1.066062569618225,
      "learning_rate": 1e-06,
      "loss": 0.0949,
      "step": 508
    },
    {
      "clip_ratio/high_max": 0.002206900480814511,
      "clip_ratio/high_mean": 0.0009112868629017612,
      "clip_ratio/low_mean": 0.0013230906952230725,
      "clip_ratio/low_min": 0.00019779235844907816,
      "clip_ratio/region_mean": 0.002234377578133717,
      "epoch": 0.04750654790029692,
      "grad_norm": 0.130077064037323,
      "learning_rate": 1e-06,
      "loss": 0.0827,
      "step": 509
    },
    {
      "clip_ratio/high_max": 0.002234059527836507,
      "clip_ratio/high_mean": 0.0009583986720826942,
      "clip_ratio/low_mean": 0.0011260432984272484,
      "clip_ratio/low_min": 3.3414446079405025e-05,
      "clip_ratio/region_mean": 0.002084441963233985,
      "epoch": 0.0475998810002975,
      "grad_norm": 0.10715559870004654,
      "learning_rate": 1e-06,
      "loss": 0.033,
      "step": 510
    },
    {
      "clip_ratio/high_max": 0.002303210807440337,
      "clip_ratio/high_mean": 0.000927604574826546,
      "clip_ratio/low_mean": 0.0012452247865439858,
      "clip_ratio/low_min": 0.00013492452580976533,
      "clip_ratio/region_mean": 0.002172829343180638,
      "epoch": 0.04769321410029808,
      "grad_norm": 0.11483106017112732,
      "learning_rate": 1e-06,
      "loss": 0.0212,
      "step": 511
    },
    {
      "clip_ratio/high_max": 0.0025578508502803743,
      "clip_ratio/high_mean": 0.0010219466203125194,
      "clip_ratio/low_mean": 0.0012588810750457924,
      "clip_ratio/low_min": 8.451135454379255e-05,
      "clip_ratio/region_mean": 0.0022808276626165025,
      "epoch": 0.047786547200298665,
      "grad_norm": 0.1137489378452301,
      "learning_rate": 1e-06,
      "loss": 0.0596,
      "step": 512
    },
    {
      "clip_ratio/high_max": 0.002436665912682656,
      "clip_ratio/high_mean": 0.0010937957777059637,
      "clip_ratio/low_mean": 0.0014357199070218485,
      "clip_ratio/low_min": 0.0001584622377777123,
      "clip_ratio/region_mean": 0.0025295156956417486,
      "epoch": 0.04787988030029925,
      "grad_norm": 0.12277857214212418,
      "learning_rate": 1e-06,
      "loss": 0.0135,
      "step": 513
    },
    {
      "clip_ratio/high_max": 0.0025481016127741896,
      "clip_ratio/high_mean": 0.0010744818464445416,
      "clip_ratio/low_mean": 0.001207023422466591,
      "clip_ratio/low_min": 1.9942564904340543e-05,
      "clip_ratio/region_mean": 0.0022815053089288995,
      "epoch": 0.047973213400299836,
      "grad_norm": 0.11549944430589676,
      "learning_rate": 1e-06,
      "loss": -0.0156,
      "step": 514
    },
    {
      "clip_ratio/high_max": 0.0024392907944275066,
      "clip_ratio/high_mean": 0.0010153075454581995,
      "clip_ratio/low_mean": 0.0011312407295918092,
      "clip_ratio/low_min": 0.00010762080364656867,
      "clip_ratio/region_mean": 0.0021465483514475636,
      "epoch": 0.048066546500300414,
      "grad_norm": 0.11370525509119034,
      "learning_rate": 1e-06,
      "loss": 0.0134,
      "step": 515
    },
    {
      "clip_ratio/high_max": 0.0022776698897359893,
      "clip_ratio/high_mean": 0.0009391976673214231,
      "clip_ratio/low_mean": 0.0009749795717652887,
      "clip_ratio/low_min": 8.09999655757565e-05,
      "clip_ratio/region_mean": 0.0019141772427246906,
      "epoch": 0.048159879600301,
      "grad_norm": 0.11053760349750519,
      "learning_rate": 1e-06,
      "loss": 0.0399,
      "step": 516
    },
    {
      "clip_ratio/high_max": 0.0022873763227835298,
      "clip_ratio/high_mean": 0.0008552894523745636,
      "clip_ratio/low_mean": 0.0012872849547420628,
      "clip_ratio/low_min": 0.00017003757238853723,
      "clip_ratio/region_mean": 0.00214257442712551,
      "epoch": 0.048253212700301584,
      "grad_norm": 0.11593953520059586,
      "learning_rate": 1e-06,
      "loss": 0.0414,
      "step": 517
    },
    {
      "clip_ratio/high_max": 0.0022689488650939893,
      "clip_ratio/high_mean": 0.0008752079093028442,
      "clip_ratio/low_mean": 0.0010455894152983092,
      "clip_ratio/low_min": 7.386402103293221e-05,
      "clip_ratio/region_mean": 0.0019207973018637858,
      "epoch": 0.04834654580030216,
      "grad_norm": 0.10284002870321274,
      "learning_rate": 1e-06,
      "loss": 0.0483,
      "step": 518
    },
    {
      "clip_ratio/high_max": 0.0022463795576186385,
      "clip_ratio/high_mean": 0.000922795285077882,
      "clip_ratio/low_mean": 0.0012132966548961122,
      "clip_ratio/low_min": 0.00017335863049083855,
      "clip_ratio/region_mean": 0.002136091956344899,
      "epoch": 0.04843987890030275,
      "grad_norm": 0.15327061712741852,
      "learning_rate": 1e-06,
      "loss": 0.0369,
      "step": 519
    },
    {
      "clip_ratio/high_max": 0.002545334617025219,
      "clip_ratio/high_mean": 0.001126107537857024,
      "clip_ratio/low_mean": 0.0012021581442240858,
      "clip_ratio/low_min": 6.505160035885638e-05,
      "clip_ratio/region_mean": 0.0023282656766241416,
      "epoch": 0.04853321200030333,
      "grad_norm": 0.133977010846138,
      "learning_rate": 1e-06,
      "loss": 0.0609,
      "step": 520
    },
    {
      "clip_ratio/high_max": 0.002465743396896869,
      "clip_ratio/high_mean": 0.0009910798908094876,
      "clip_ratio/low_mean": 0.0011964750337938312,
      "clip_ratio/low_min": 0.00012408259044605074,
      "clip_ratio/region_mean": 0.002187554935517255,
      "epoch": 0.04862654510030392,
      "grad_norm": 0.14651188254356384,
      "learning_rate": 1e-06,
      "loss": 0.0347,
      "step": 521
    },
    {
      "clip_ratio/high_max": 0.0022333893866743892,
      "clip_ratio/high_mean": 0.0009058175401150947,
      "clip_ratio/low_mean": 0.0012181241108919494,
      "clip_ratio/low_min": 6.566829506482463e-05,
      "clip_ratio/region_mean": 0.0021239416673779488,
      "epoch": 0.048719878200304496,
      "grad_norm": 0.11617682129144669,
      "learning_rate": 1e-06,
      "loss": 0.0752,
      "step": 522
    },
    {
      "clip_ratio/high_max": 0.0025374851829838008,
      "clip_ratio/high_mean": 0.001010436229989864,
      "clip_ratio/low_mean": 0.0013953620236861752,
      "clip_ratio/low_min": 8.938389146351255e-05,
      "clip_ratio/region_mean": 0.0024057982009253465,
      "epoch": 0.04881321130030508,
      "grad_norm": 0.14823086559772491,
      "learning_rate": 1e-06,
      "loss": 0.0201,
      "step": 523
    },
    {
      "clip_ratio/high_max": 0.0025780609212233685,
      "clip_ratio/high_mean": 0.0010427060842630453,
      "clip_ratio/low_mean": 0.0010623884554661345,
      "clip_ratio/low_min": 1.6473379218950868e-05,
      "clip_ratio/region_mean": 0.0021050945433671586,
      "epoch": 0.04890654440030567,
      "grad_norm": 0.11438409239053726,
      "learning_rate": 1e-06,
      "loss": 0.021,
      "step": 524
    },
    {
      "clip_ratio/high_max": 0.0020961795817129314,
      "clip_ratio/high_mean": 0.0008928020452003693,
      "clip_ratio/low_mean": 0.0010564436197455507,
      "clip_ratio/low_min": 1.8606728190206923e-05,
      "clip_ratio/region_mean": 0.0019492456849548034,
      "epoch": 0.04899987750030625,
      "grad_norm": 1.1766196489334106,
      "learning_rate": 1e-06,
      "loss": 0.0741,
      "step": 525
    },
    {
      "clip_ratio/high_max": 0.002311453288712073,
      "clip_ratio/high_mean": 0.00102697366673965,
      "clip_ratio/low_mean": 0.00102821009568288,
      "clip_ratio/low_min": 0.00010042948633781634,
      "clip_ratio/region_mean": 0.0020551837733364664,
      "epoch": 0.04909321060030683,
      "grad_norm": 0.12878233194351196,
      "learning_rate": 1e-06,
      "loss": 0.0103,
      "step": 526
    },
    {
      "clip_ratio/high_max": 0.002335183755349135,
      "clip_ratio/high_mean": 0.0009238782386091771,
      "clip_ratio/low_mean": 0.0010043288602901157,
      "clip_ratio/low_min": 0.00013413556189334486,
      "clip_ratio/region_mean": 0.0019282071370980702,
      "epoch": 0.049186543700307415,
      "grad_norm": 0.10969037562608719,
      "learning_rate": 1e-06,
      "loss": 0.034,
      "step": 527
    },
    {
      "clip_ratio/high_max": 0.0019988704880233854,
      "clip_ratio/high_mean": 0.0008094976255961228,
      "clip_ratio/low_mean": 0.0010959244318655692,
      "clip_ratio/low_min": 0.00018863374862121418,
      "clip_ratio/region_mean": 0.0019054220610996708,
      "epoch": 0.049279876800308,
      "grad_norm": 0.11354716867208481,
      "learning_rate": 1e-06,
      "loss": 0.074,
      "step": 528
    },
    {
      "clip_ratio/high_max": 0.002741457319643814,
      "clip_ratio/high_mean": 0.0010872539205593057,
      "clip_ratio/low_mean": 0.0010173525843129028,
      "clip_ratio/low_min": 2.862017117877258e-05,
      "clip_ratio/region_mean": 0.002104606493958272,
      "epoch": 0.049373209900308586,
      "grad_norm": 0.11658629029989243,
      "learning_rate": 1e-06,
      "loss": 0.0483,
      "step": 529
    },
    {
      "clip_ratio/high_max": 0.0021164071513339877,
      "clip_ratio/high_mean": 0.0009590825029590633,
      "clip_ratio/low_mean": 0.0013941892648290377,
      "clip_ratio/low_min": 0.00010167742766498122,
      "clip_ratio/region_mean": 0.002353271731408313,
      "epoch": 0.049466543000309164,
      "grad_norm": 0.1637180894613266,
      "learning_rate": 1e-06,
      "loss": 0.0355,
      "step": 530
    },
    {
      "clip_ratio/high_max": 0.0027464583254186437,
      "clip_ratio/high_mean": 0.0011867928405990824,
      "clip_ratio/low_mean": 0.0008808790043985937,
      "clip_ratio/low_min": 6.548280634888215e-05,
      "clip_ratio/region_mean": 0.002067671804979909,
      "epoch": 0.04955987610030975,
      "grad_norm": 0.11159728467464447,
      "learning_rate": 1e-06,
      "loss": -0.0175,
      "step": 531
    },
    {
      "clip_ratio/high_max": 0.002653493869729573,
      "clip_ratio/high_mean": 0.0011114626468042843,
      "clip_ratio/low_mean": 0.0010718940557126189,
      "clip_ratio/low_min": 9.245149885828141e-05,
      "clip_ratio/region_mean": 0.0021833567661815323,
      "epoch": 0.049653209200310335,
      "grad_norm": 0.12469938397407532,
      "learning_rate": 1e-06,
      "loss": 0.0376,
      "step": 532
    },
    {
      "clip_ratio/high_max": 0.0023215410656121094,
      "clip_ratio/high_mean": 0.0010041421992355026,
      "clip_ratio/low_mean": 0.0011800426000263542,
      "clip_ratio/low_min": 0.00010731277052400401,
      "clip_ratio/region_mean": 0.002184184799261857,
      "epoch": 0.04974654230031091,
      "grad_norm": 0.12142664194107056,
      "learning_rate": 1e-06,
      "loss": 0.0277,
      "step": 533
    },
    {
      "clip_ratio/high_max": 0.00217046843317803,
      "clip_ratio/high_mean": 0.0009255408476747107,
      "clip_ratio/low_mean": 0.001085233847334166,
      "clip_ratio/low_min": 9.088732167583657e-05,
      "clip_ratio/region_mean": 0.0020107746859139297,
      "epoch": 0.0498398754003115,
      "grad_norm": 0.11844430863857269,
      "learning_rate": 1e-06,
      "loss": 0.0502,
      "step": 534
    },
    {
      "clip_ratio/high_max": 0.002323992252058815,
      "clip_ratio/high_mean": 0.0009733416554809082,
      "clip_ratio/low_mean": 0.0011069518513977528,
      "clip_ratio/low_min": 0.00010025935262092389,
      "clip_ratio/region_mean": 0.0020802935177925974,
      "epoch": 0.04993320850031208,
      "grad_norm": 0.10840032994747162,
      "learning_rate": 1e-06,
      "loss": 0.0216,
      "step": 535
    },
    {
      "clip_ratio/high_max": 0.0024229628907050937,
      "clip_ratio/high_mean": 0.001014901803500834,
      "clip_ratio/low_mean": 0.001073445975634968,
      "clip_ratio/low_min": 5.582950143434573e-05,
      "clip_ratio/region_mean": 0.002088347806420643,
      "epoch": 0.05002654160031267,
      "grad_norm": 0.14263685047626495,
      "learning_rate": 1e-06,
      "loss": 0.0268,
      "step": 536
    },
    {
      "clip_ratio/high_max": 0.0021586509901680984,
      "clip_ratio/high_mean": 0.0009574469113431405,
      "clip_ratio/low_mean": 0.0010398111735412385,
      "clip_ratio/low_min": 0.00016133830831677187,
      "clip_ratio/region_mean": 0.0019972581139882095,
      "epoch": 0.05011987470031325,
      "grad_norm": 0.12401726841926575,
      "learning_rate": 1e-06,
      "loss": 0.0508,
      "step": 537
    },
    {
      "clip_ratio/high_max": 0.0022127531774458475,
      "clip_ratio/high_mean": 0.0008974480588221923,
      "clip_ratio/low_mean": 0.0009581594604242127,
      "clip_ratio/low_min": 8.482113571517402e-05,
      "clip_ratio/region_mean": 0.0018556075301603414,
      "epoch": 0.05021320780031383,
      "grad_norm": 0.3128924071788788,
      "learning_rate": 1e-06,
      "loss": 0.0327,
      "step": 538
    },
    {
      "clip_ratio/high_max": 0.0024360563547816128,
      "clip_ratio/high_mean": 0.0009754931506904541,
      "clip_ratio/low_mean": 0.0009930350197464577,
      "clip_ratio/low_min": 0.00011733457722584717,
      "clip_ratio/region_mean": 0.0019685281804413535,
      "epoch": 0.05030654090031442,
      "grad_norm": 0.10646910220384598,
      "learning_rate": 1e-06,
      "loss": 0.0257,
      "step": 539
    },
    {
      "clip_ratio/high_max": 0.0024534834374208003,
      "clip_ratio/high_mean": 0.0009934416721080197,
      "clip_ratio/low_mean": 0.0009415506701770937,
      "clip_ratio/low_min": 5.170057738723699e-05,
      "clip_ratio/region_mean": 0.0019349923240952194,
      "epoch": 0.050399874000315,
      "grad_norm": 0.10769926756620407,
      "learning_rate": 1e-06,
      "loss": 0.0162,
      "step": 540
    },
    {
      "clip_ratio/high_max": 0.002602410997496918,
      "clip_ratio/high_mean": 0.0010775359332910739,
      "clip_ratio/low_mean": 0.0010410390732431551,
      "clip_ratio/low_min": 2.5515987545077223e-05,
      "clip_ratio/region_mean": 0.0021185750229051337,
      "epoch": 0.05049320710031558,
      "grad_norm": 0.10725007951259613,
      "learning_rate": 1e-06,
      "loss": -0.0192,
      "step": 541
    },
    {
      "clip_ratio/high_max": 0.002776624110992998,
      "clip_ratio/high_mean": 0.0010355851754866308,
      "clip_ratio/low_mean": 0.0008953355554695008,
      "clip_ratio/low_min": 4.3283366721880157e-05,
      "clip_ratio/region_mean": 0.0019309207709738985,
      "epoch": 0.050586540200316166,
      "grad_norm": 0.10528475046157837,
      "learning_rate": 1e-06,
      "loss": 0.0094,
      "step": 542
    },
    {
      "clip_ratio/high_max": 0.0020246337408025283,
      "clip_ratio/high_mean": 0.0009088136594073148,
      "clip_ratio/low_mean": 0.0010445900516060647,
      "clip_ratio/low_min": 7.107205146894557e-05,
      "clip_ratio/region_mean": 0.001953403712832369,
      "epoch": 0.05067987330031675,
      "grad_norm": 0.10592474788427353,
      "learning_rate": 1e-06,
      "loss": 0.0339,
      "step": 543
    },
    {
      "clip_ratio/high_max": 0.003016086768184323,
      "clip_ratio/high_mean": 0.0011549005066626705,
      "clip_ratio/low_mean": 0.0009634954649300198,
      "clip_ratio/low_min": 5.9315631006029435e-05,
      "clip_ratio/region_mean": 0.0021183959834161215,
      "epoch": 0.05077320640031733,
      "grad_norm": 0.155888170003891,
      "learning_rate": 1e-06,
      "loss": 0.0132,
      "step": 544
    },
    {
      "clip_ratio/high_max": 0.0025852081816992722,
      "clip_ratio/high_mean": 0.0010890886405832134,
      "clip_ratio/low_mean": 0.001064599349774653,
      "clip_ratio/low_min": 0.0001754275444909581,
      "clip_ratio/region_mean": 0.002153688015823718,
      "epoch": 0.050866539500317914,
      "grad_norm": 0.18943233788013458,
      "learning_rate": 1e-06,
      "loss": -0.0119,
      "step": 545
    },
    {
      "clip_ratio/high_max": 0.0027793663684860803,
      "clip_ratio/high_mean": 0.0010125482913281303,
      "clip_ratio/low_mean": 0.0009451341775275068,
      "clip_ratio/low_min": 5.034581045038067e-05,
      "clip_ratio/region_mean": 0.001957682477950584,
      "epoch": 0.0509598726003185,
      "grad_norm": 0.1030670553445816,
      "learning_rate": 1e-06,
      "loss": -0.0069,
      "step": 546
    },
    {
      "clip_ratio/high_max": 0.002209324185969308,
      "clip_ratio/high_mean": 0.0008844848616718082,
      "clip_ratio/low_mean": 0.0009243311214959249,
      "clip_ratio/low_min": 0.00013581581879407167,
      "clip_ratio/region_mean": 0.0018088159995386377,
      "epoch": 0.051053205700319085,
      "grad_norm": 0.11897844821214676,
      "learning_rate": 1e-06,
      "loss": 0.0555,
      "step": 547
    },
    {
      "clip_ratio/high_max": 0.0026205383910564706,
      "clip_ratio/high_mean": 0.001054772234056145,
      "clip_ratio/low_mean": 0.0009358568895549979,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.00199062919273274,
      "epoch": 0.05114653880031966,
      "grad_norm": 0.10565313696861267,
      "learning_rate": 1e-06,
      "loss": 0.0193,
      "step": 548
    },
    {
      "clip_ratio/high_max": 0.0026611354187480174,
      "clip_ratio/high_mean": 0.0010324603535991628,
      "clip_ratio/low_mean": 0.0011964449749939376,
      "clip_ratio/low_min": 1.6225338185904548e-05,
      "clip_ratio/region_mean": 0.002228905344964005,
      "epoch": 0.05123987190032025,
      "grad_norm": 0.15604837238788605,
      "learning_rate": 1e-06,
      "loss": 0.0236,
      "step": 549
    },
    {
      "clip_ratio/high_max": 0.0024267802509712055,
      "clip_ratio/high_mean": 0.0009575654075888451,
      "clip_ratio/low_mean": 0.001118169617257081,
      "clip_ratio/low_min": 9.856144424702507e-05,
      "clip_ratio/region_mean": 0.0020757350139319897,
      "epoch": 0.05133320500032083,
      "grad_norm": 0.11913684010505676,
      "learning_rate": 1e-06,
      "loss": 0.0519,
      "step": 550
    },
    {
      "clip_ratio/high_max": 0.002002275021368405,
      "clip_ratio/high_mean": 0.0009510376985417679,
      "clip_ratio/low_mean": 0.0011226929418626241,
      "clip_ratio/low_min": 0.00013906175900046946,
      "clip_ratio/region_mean": 0.0020737306476803496,
      "epoch": 0.05142653810032142,
      "grad_norm": 0.10895012319087982,
      "learning_rate": 1e-06,
      "loss": 0.0018,
      "step": 551
    },
    {
      "clip_ratio/high_max": 0.002054436034086393,
      "clip_ratio/high_mean": 0.0009376745620102156,
      "clip_ratio/low_mean": 0.0008807534522929927,
      "clip_ratio/low_min": 5.2354688705236185e-05,
      "clip_ratio/region_mean": 0.0018184279761044309,
      "epoch": 0.051519871200322,
      "grad_norm": 0.09573733061552048,
      "learning_rate": 1e-06,
      "loss": 0.0026,
      "step": 552
    },
    {
      "clip_ratio/high_max": 0.002352635572606232,
      "clip_ratio/high_mean": 0.0009439997666049749,
      "clip_ratio/low_mean": 0.0012090514628653182,
      "clip_ratio/low_min": 9.540954215481179e-05,
      "clip_ratio/region_mean": 0.0021530512094614096,
      "epoch": 0.05161320430032258,
      "grad_norm": 0.10818588733673096,
      "learning_rate": 1e-06,
      "loss": 0.0319,
      "step": 553
    },
    {
      "clip_ratio/high_max": 0.0024579532255302183,
      "clip_ratio/high_mean": 0.0009594352577551035,
      "clip_ratio/low_mean": 0.001280119740840746,
      "clip_ratio/low_min": 0.00018664671642909525,
      "clip_ratio/region_mean": 0.0022395550622604787,
      "epoch": 0.05170653740032317,
      "grad_norm": 0.10303737968206406,
      "learning_rate": 1e-06,
      "loss": 0.0301,
      "step": 554
    },
    {
      "clip_ratio/high_max": 0.002039117993263062,
      "clip_ratio/high_mean": 0.0009296319258282892,
      "clip_ratio/low_mean": 0.0011010477355739567,
      "clip_ratio/low_min": 3.5991939512314275e-05,
      "clip_ratio/region_mean": 0.0020306796723161824,
      "epoch": 0.05179987050032375,
      "grad_norm": 0.11468939483165741,
      "learning_rate": 1e-06,
      "loss": 0.0401,
      "step": 555
    },
    {
      "clip_ratio/high_max": 0.0022879065145389177,
      "clip_ratio/high_mean": 0.0011766945845010923,
      "clip_ratio/low_mean": 0.0010166709653276484,
      "clip_ratio/low_min": 1.5038498531794176e-05,
      "clip_ratio/region_mean": 0.002193365537095815,
      "epoch": 0.05189320360032433,
      "grad_norm": 0.11673793941736221,
      "learning_rate": 1e-06,
      "loss": -0.0213,
      "step": 556
    },
    {
      "clip_ratio/high_max": 0.0020410397555679083,
      "clip_ratio/high_mean": 0.0009163688300759532,
      "clip_ratio/low_mean": 0.0012360066211840604,
      "clip_ratio/low_min": 0.0001504603392277204,
      "clip_ratio/region_mean": 0.002152375498553738,
      "epoch": 0.051986536700324916,
      "grad_norm": 0.12710396945476532,
      "learning_rate": 1e-06,
      "loss": 0.0465,
      "step": 557
    },
    {
      "clip_ratio/high_max": 0.0019881465050275438,
      "clip_ratio/high_mean": 0.0009186605966533534,
      "clip_ratio/low_mean": 0.0011601347614487167,
      "clip_ratio/low_min": 7.704248127993196e-05,
      "clip_ratio/region_mean": 0.0020787953180843033,
      "epoch": 0.0520798698003255,
      "grad_norm": 0.11551938205957413,
      "learning_rate": 1e-06,
      "loss": 0.0158,
      "step": 558
    },
    {
      "clip_ratio/high_max": 0.0026306369472877122,
      "clip_ratio/high_mean": 0.0010184266757278237,
      "clip_ratio/low_mean": 0.0011486162911751308,
      "clip_ratio/low_min": 0.00010442700386192882,
      "clip_ratio/region_mean": 0.002167042955989018,
      "epoch": 0.05217320290032608,
      "grad_norm": 0.11591550707817078,
      "learning_rate": 1e-06,
      "loss": -0.0262,
      "step": 559
    },
    {
      "clip_ratio/high_max": 0.0017481404975114856,
      "clip_ratio/high_mean": 0.0007484360558009939,
      "clip_ratio/low_mean": 0.001068901543476386,
      "clip_ratio/low_min": 6.654752178292256e-05,
      "clip_ratio/region_mean": 0.0018173376010963693,
      "epoch": 0.052266536000326665,
      "grad_norm": 0.10007625818252563,
      "learning_rate": 1e-06,
      "loss": 0.0402,
      "step": 560
    },
    {
      "clip_ratio/high_max": 0.002342764440982137,
      "clip_ratio/high_mean": 0.0009339088519482175,
      "clip_ratio/low_mean": 0.0011359662930772174,
      "clip_ratio/low_min": 8.061372591328109e-05,
      "clip_ratio/region_mean": 0.002069875132292509,
      "epoch": 0.05235986910032725,
      "grad_norm": 0.1115155890583992,
      "learning_rate": 1e-06,
      "loss": 0.0258,
      "step": 561
    },
    {
      "clip_ratio/high_max": 0.0020411468722159043,
      "clip_ratio/high_mean": 0.0008373003420274472,
      "clip_ratio/low_mean": 0.0010375615347584244,
      "clip_ratio/low_min": 7.315738275792683e-05,
      "clip_ratio/region_mean": 0.0018748619040707126,
      "epoch": 0.052453202200327835,
      "grad_norm": 0.10713379085063934,
      "learning_rate": 1e-06,
      "loss": 0.0213,
      "step": 562
    },
    {
      "clip_ratio/high_max": 0.00212736550020054,
      "clip_ratio/high_mean": 0.00101913820617483,
      "clip_ratio/low_mean": 0.0012943415604240727,
      "clip_ratio/low_min": 0.0002359375503147021,
      "clip_ratio/region_mean": 0.0023134798102546483,
      "epoch": 0.05254653530032841,
      "grad_norm": 0.12580713629722595,
      "learning_rate": 1e-06,
      "loss": 0.0124,
      "step": 563
    },
    {
      "clip_ratio/high_max": 0.0020882370918116067,
      "clip_ratio/high_mean": 0.0008644727167848032,
      "clip_ratio/low_mean": 0.001227024280524347,
      "clip_ratio/low_min": 0.00023539673202321865,
      "clip_ratio/region_mean": 0.0020914969936711714,
      "epoch": 0.052639868400329,
      "grad_norm": 0.10341587662696838,
      "learning_rate": 1e-06,
      "loss": 0.0437,
      "step": 564
    },
    {
      "clip_ratio/high_max": 0.002121015335433185,
      "clip_ratio/high_mean": 0.0008249619422713295,
      "clip_ratio/low_mean": 0.0011256293910264503,
      "clip_ratio/low_min": 0.00013979219147586264,
      "clip_ratio/region_mean": 0.0019505913078319281,
      "epoch": 0.052733201500329584,
      "grad_norm": 0.11013689637184143,
      "learning_rate": 1e-06,
      "loss": 0.0295,
      "step": 565
    },
    {
      "clip_ratio/high_max": 0.0020267815634724684,
      "clip_ratio/high_mean": 0.0007923935818325845,
      "clip_ratio/low_mean": 0.0012331218567851465,
      "clip_ratio/low_min": 0.00010452612241351744,
      "clip_ratio/region_mean": 0.002025515503191855,
      "epoch": 0.05282653460033017,
      "grad_norm": 0.11691796034574509,
      "learning_rate": 1e-06,
      "loss": 0.0838,
      "step": 566
    },
    {
      "clip_ratio/high_max": 0.0020507840235950425,
      "clip_ratio/high_mean": 0.0008618296560598537,
      "clip_ratio/low_mean": 0.001163931574410526,
      "clip_ratio/low_min": 8.01679425421753e-05,
      "clip_ratio/region_mean": 0.002025761190452613,
      "epoch": 0.05291986770033075,
      "grad_norm": 0.122233085334301,
      "learning_rate": 1e-06,
      "loss": 0.0378,
      "step": 567
    },
    {
      "clip_ratio/high_max": 0.002239193483546842,
      "clip_ratio/high_mean": 0.0010256996247335337,
      "clip_ratio/low_mean": 0.000930793705265387,
      "clip_ratio/low_min": 3.524883049976779e-05,
      "clip_ratio/region_mean": 0.001956493390025571,
      "epoch": 0.05301320080033133,
      "grad_norm": 0.20606251060962677,
      "learning_rate": 1e-06,
      "loss": -0.0168,
      "step": 568
    },
    {
      "clip_ratio/high_max": 0.002508563680748921,
      "clip_ratio/high_mean": 0.001143041499744868,
      "clip_ratio/low_mean": 0.001249512877620873,
      "clip_ratio/low_min": 0.0001102345504477853,
      "clip_ratio/region_mean": 0.002392554364632815,
      "epoch": 0.05310653390033192,
      "grad_norm": 0.178523451089859,
      "learning_rate": 1e-06,
      "loss": 0.0048,
      "step": 569
    },
    {
      "clip_ratio/high_max": 0.002086374668579083,
      "clip_ratio/high_mean": 0.0008527624759153696,
      "clip_ratio/low_mean": 0.0010658229275577469,
      "clip_ratio/low_min": 4.572267789626494e-05,
      "clip_ratio/region_mean": 0.0019185853816452436,
      "epoch": 0.053199867000332496,
      "grad_norm": 0.11680780351161957,
      "learning_rate": 1e-06,
      "loss": 0.0422,
      "step": 570
    },
    {
      "clip_ratio/high_max": 0.0019599174775066786,
      "clip_ratio/high_mean": 0.0008517913120158482,
      "clip_ratio/low_mean": 0.001141517590440344,
      "clip_ratio/low_min": 0.0001032355175993871,
      "clip_ratio/region_mean": 0.0019933089133701287,
      "epoch": 0.05329320010033308,
      "grad_norm": 0.11743775010108948,
      "learning_rate": 1e-06,
      "loss": 0.0336,
      "step": 571
    },
    {
      "clip_ratio/high_max": 0.002138647156243678,
      "clip_ratio/high_mean": 0.0009568691821186803,
      "clip_ratio/low_mean": 0.0009216963899234543,
      "clip_ratio/low_min": 9.939492974808672e-05,
      "clip_ratio/region_mean": 0.0018785655774991028,
      "epoch": 0.053386533200333666,
      "grad_norm": 0.11797573417425156,
      "learning_rate": 1e-06,
      "loss": 0.0052,
      "step": 572
    },
    {
      "clip_ratio/high_max": 0.002300238855241332,
      "clip_ratio/high_mean": 0.0009358835504826857,
      "clip_ratio/low_mean": 0.001090615618522861,
      "clip_ratio/low_min": 8.214059016609099e-05,
      "clip_ratio/region_mean": 0.0020264991908334196,
      "epoch": 0.05347986630033425,
      "grad_norm": 0.11401925981044769,
      "learning_rate": 1e-06,
      "loss": 0.052,
      "step": 573
    },
    {
      "clip_ratio/high_max": 0.00239048810544773,
      "clip_ratio/high_mean": 0.0009859963784037973,
      "clip_ratio/low_mean": 0.0009539177826809464,
      "clip_ratio/low_min": 0.0001569271735206712,
      "clip_ratio/region_mean": 0.0019399141383473761,
      "epoch": 0.05357319940033483,
      "grad_norm": 0.10502737015485764,
      "learning_rate": 1e-06,
      "loss": 0.0416,
      "step": 574
    },
    {
      "clip_ratio/high_max": 0.002273719474032987,
      "clip_ratio/high_mean": 0.0009481723755015992,
      "clip_ratio/low_mean": 0.0010330390650779009,
      "clip_ratio/low_min": 5.5017604609020054e-05,
      "clip_ratio/region_mean": 0.0019812115060631186,
      "epoch": 0.053666532500335415,
      "grad_norm": 0.10575493425130844,
      "learning_rate": 1e-06,
      "loss": -0.0016,
      "step": 575
    },
    {
      "clip_ratio/high_max": 0.0022129845892777666,
      "clip_ratio/high_mean": 0.0008744621991354506,
      "clip_ratio/low_mean": 0.0009994291212933604,
      "clip_ratio/low_min": 0.0001251541543751955,
      "clip_ratio/region_mean": 0.0018738912986009382,
      "epoch": 0.053759865600336,
      "grad_norm": 0.11958342790603638,
      "learning_rate": 1e-06,
      "loss": 0.0547,
      "step": 576
    },
    {
      "clip_ratio/high_max": 0.0022965703246882185,
      "clip_ratio/high_mean": 0.0009411160499439575,
      "clip_ratio/low_mean": 0.0010088508806802565,
      "clip_ratio/low_min": 7.881337842263747e-05,
      "clip_ratio/region_mean": 0.0019499669870128855,
      "epoch": 0.053853198700336585,
      "grad_norm": 0.09806469082832336,
      "learning_rate": 1e-06,
      "loss": 0.0414,
      "step": 577
    },
    {
      "clip_ratio/high_max": 0.0024612118941149674,
      "clip_ratio/high_mean": 0.0009899283722916152,
      "clip_ratio/low_mean": 0.0008869870707712835,
      "clip_ratio/low_min": 4.3028127947764006e-05,
      "clip_ratio/region_mean": 0.0018769154012261424,
      "epoch": 0.053946531800337164,
      "grad_norm": 0.17731398344039917,
      "learning_rate": 1e-06,
      "loss": -0.0012,
      "step": 578
    },
    {
      "clip_ratio/high_max": 0.002557455918577034,
      "clip_ratio/high_mean": 0.0010909680931945331,
      "clip_ratio/low_mean": 0.0019788719655480236,
      "clip_ratio/low_min": 7.460481720045209e-05,
      "clip_ratio/region_mean": 0.0030698400296387263,
      "epoch": 0.05403986490033775,
      "grad_norm": 0.12621797621250153,
      "learning_rate": 1e-06,
      "loss": -0.0047,
      "step": 579
    },
    {
      "clip_ratio/high_max": 0.002250625784654403,
      "clip_ratio/high_mean": 0.0009864630592346657,
      "clip_ratio/low_mean": 0.0008735170958971139,
      "clip_ratio/low_min": 7.316630035347771e-05,
      "clip_ratio/region_mean": 0.0018599801769596525,
      "epoch": 0.054133198000338334,
      "grad_norm": 0.10964135825634003,
      "learning_rate": 1e-06,
      "loss": -0.0006,
      "step": 580
    },
    {
      "clip_ratio/high_max": 0.0025588975331629626,
      "clip_ratio/high_mean": 0.0010408836969872937,
      "clip_ratio/low_mean": 0.000953475282585714,
      "clip_ratio/low_min": 0.00012291524853935698,
      "clip_ratio/region_mean": 0.0019943590014008805,
      "epoch": 0.05422653110033892,
      "grad_norm": 0.10963660478591919,
      "learning_rate": 1e-06,
      "loss": -0.0003,
      "step": 581
    },
    {
      "clip_ratio/high_max": 0.0020415589242475107,
      "clip_ratio/high_mean": 0.0009287152479373617,
      "clip_ratio/low_mean": 0.001003074358777667,
      "clip_ratio/low_min": 8.005333256733138e-05,
      "clip_ratio/region_mean": 0.0019317895894346293,
      "epoch": 0.0543198642003395,
      "grad_norm": 0.11718995869159698,
      "learning_rate": 1e-06,
      "loss": -0.0077,
      "step": 582
    },
    {
      "clip_ratio/high_max": 0.002175417546823155,
      "clip_ratio/high_mean": 0.0008287317687063478,
      "clip_ratio/low_mean": 0.001077540175174363,
      "clip_ratio/low_min": 8.137037821143167e-05,
      "clip_ratio/region_mean": 0.0019062719511566684,
      "epoch": 0.05441319730034008,
      "grad_norm": 0.129413440823555,
      "learning_rate": 1e-06,
      "loss": 0.0643,
      "step": 583
    },
    {
      "clip_ratio/high_max": 0.0024820500548230484,
      "clip_ratio/high_mean": 0.001035144417983247,
      "clip_ratio/low_mean": 0.0010529138853598852,
      "clip_ratio/low_min": 0.0001305453188251704,
      "clip_ratio/region_mean": 0.0020880583324469626,
      "epoch": 0.05450653040034067,
      "grad_norm": 31.309160232543945,
      "learning_rate": 1e-06,
      "loss": 0.0015,
      "step": 584
    },
    {
      "clip_ratio/high_max": 0.002341946015803842,
      "clip_ratio/high_mean": 0.0010095967209053924,
      "clip_ratio/low_mean": 0.0011283074018137995,
      "clip_ratio/low_min": 6.25489883532282e-05,
      "clip_ratio/region_mean": 0.0021379041063482873,
      "epoch": 0.054599863500341246,
      "grad_norm": 0.12081718444824219,
      "learning_rate": 1e-06,
      "loss": 0.0597,
      "step": 585
    },
    {
      "clip_ratio/high_max": 0.0021600510081043467,
      "clip_ratio/high_mean": 0.0008407682380493497,
      "clip_ratio/low_mean": 0.001240364301338559,
      "clip_ratio/low_min": 7.582831312902272e-05,
      "clip_ratio/region_mean": 0.0020811325157410465,
      "epoch": 0.05469319660034183,
      "grad_norm": 0.11999684572219849,
      "learning_rate": 1e-06,
      "loss": 0.0354,
      "step": 586
    },
    {
      "clip_ratio/high_max": 0.0020459194674913306,
      "clip_ratio/high_mean": 0.0007620115393365268,
      "clip_ratio/low_mean": 0.001060848338966025,
      "clip_ratio/low_min": 5.7424944316153415e-05,
      "clip_ratio/region_mean": 0.0018228598855785094,
      "epoch": 0.054786529700342416,
      "grad_norm": 0.11038127541542053,
      "learning_rate": 1e-06,
      "loss": 0.0467,
      "step": 587
    },
    {
      "clip_ratio/high_max": 0.0022186188616615254,
      "clip_ratio/high_mean": 0.0009010556677822024,
      "clip_ratio/low_mean": 0.0011774348458857276,
      "clip_ratio/low_min": 6.137622676760657e-05,
      "clip_ratio/region_mean": 0.0020784905209438875,
      "epoch": 0.054879862800343,
      "grad_norm": 0.10276598483324051,
      "learning_rate": 1e-06,
      "loss": 0.0256,
      "step": 588
    },
    {
      "clip_ratio/high_max": 0.0023173702938947827,
      "clip_ratio/high_mean": 0.0010650505046214676,
      "clip_ratio/low_mean": 0.0009969648326659808,
      "clip_ratio/low_min": 0.00018824595281330403,
      "clip_ratio/region_mean": 0.0020620153518393636,
      "epoch": 0.05497319590034358,
      "grad_norm": 0.10746926069259644,
      "learning_rate": 1e-06,
      "loss": -0.0238,
      "step": 589
    },
    {
      "clip_ratio/high_max": 0.0024066834012046456,
      "clip_ratio/high_mean": 0.0010481681747478433,
      "clip_ratio/low_mean": 0.0009437980788788991,
      "clip_ratio/low_min": 0.00013782995938527165,
      "clip_ratio/region_mean": 0.0019919662809115835,
      "epoch": 0.055066529000344165,
      "grad_norm": 0.10680969059467316,
      "learning_rate": 1e-06,
      "loss": -0.0009,
      "step": 590
    },
    {
      "clip_ratio/high_max": 0.002390223104157485,
      "clip_ratio/high_mean": 0.0009545165357849328,
      "clip_ratio/low_mean": 0.0011933237256016582,
      "clip_ratio/low_min": 0.00015012832500360673,
      "clip_ratio/region_mean": 0.0021478402995853685,
      "epoch": 0.05515986210034475,
      "grad_norm": 0.11171848326921463,
      "learning_rate": 1e-06,
      "loss": 0.0268,
      "step": 591
    },
    {
      "clip_ratio/high_max": 0.0018758612241072115,
      "clip_ratio/high_mean": 0.0008407090481341584,
      "clip_ratio/low_mean": 0.0010596802785585169,
      "clip_ratio/low_min": 6.277364354900783e-05,
      "clip_ratio/region_mean": 0.0019003893830813468,
      "epoch": 0.055253195200345336,
      "grad_norm": 0.11056873947381973,
      "learning_rate": 1e-06,
      "loss": 0.0344,
      "step": 592
    },
    {
      "clip_ratio/high_max": 0.0024359398375963792,
      "clip_ratio/high_mean": 0.0009761374622030417,
      "clip_ratio/low_mean": 0.0009749716155056376,
      "clip_ratio/low_min": 0.00014220718639990082,
      "clip_ratio/region_mean": 0.0019511091231834143,
      "epoch": 0.055346528300345914,
      "grad_norm": 0.10610097646713257,
      "learning_rate": 1e-06,
      "loss": 0.0155,
      "step": 593
    },
    {
      "clip_ratio/high_max": 0.002388142966083251,
      "clip_ratio/high_mean": 0.0010742774702521274,
      "clip_ratio/low_mean": 0.0009646805610827869,
      "clip_ratio/low_min": 9.010510439111385e-05,
      "clip_ratio/region_mean": 0.002038958038610872,
      "epoch": 0.0554398614003465,
      "grad_norm": 0.10572066158056259,
      "learning_rate": 1e-06,
      "loss": 0.0122,
      "step": 594
    },
    {
      "clip_ratio/high_max": 0.0021172760461922735,
      "clip_ratio/high_mean": 0.0010117343263118528,
      "clip_ratio/low_mean": 0.0010011274061980657,
      "clip_ratio/low_min": 0.00012805586356989807,
      "clip_ratio/region_mean": 0.0020128617106820457,
      "epoch": 0.055533194500347084,
      "grad_norm": 0.11294758319854736,
      "learning_rate": 1e-06,
      "loss": 0.0337,
      "step": 595
    },
    {
      "clip_ratio/high_max": 0.0022302978395600803,
      "clip_ratio/high_mean": 0.0010535142428125255,
      "clip_ratio/low_mean": 0.0010577405337244272,
      "clip_ratio/low_min": 4.503955278778449e-05,
      "clip_ratio/region_mean": 0.00211125475470908,
      "epoch": 0.05562652760034766,
      "grad_norm": 0.12416896224021912,
      "learning_rate": 1e-06,
      "loss": 0.0122,
      "step": 596
    },
    {
      "clip_ratio/high_max": 0.0021628181129926816,
      "clip_ratio/high_mean": 0.0010035060440714005,
      "clip_ratio/low_mean": 0.0011121814659418305,
      "clip_ratio/low_min": 0.0002266084684379166,
      "clip_ratio/region_mean": 0.002115687522746157,
      "epoch": 0.05571986070034825,
      "grad_norm": 0.12608219683170319,
      "learning_rate": 1e-06,
      "loss": 0.0215,
      "step": 597
    },
    {
      "clip_ratio/high_max": 0.0023476473143091425,
      "clip_ratio/high_mean": 0.0009626134633435868,
      "clip_ratio/low_mean": 0.0008621300139566301,
      "clip_ratio/low_min": 8.547347533749416e-05,
      "clip_ratio/region_mean": 0.0018247434200020507,
      "epoch": 0.05581319380034883,
      "grad_norm": 0.10490106046199799,
      "learning_rate": 1e-06,
      "loss": 0.0613,
      "step": 598
    },
    {
      "clip_ratio/high_max": 0.002324442299141083,
      "clip_ratio/high_mean": 0.0009290950983995572,
      "clip_ratio/low_mean": 0.0010374554749432718,
      "clip_ratio/low_min": 0.00010561935414443724,
      "clip_ratio/region_mean": 0.001966550560609903,
      "epoch": 0.05590652690034942,
      "grad_norm": 0.11225977540016174,
      "learning_rate": 1e-06,
      "loss": 0.0384,
      "step": 599
    },
    {
      "clip_ratio/high_max": 0.002352143004827667,
      "clip_ratio/high_mean": 0.0009724052797537297,
      "clip_ratio/low_mean": 0.0010755634866654873,
      "clip_ratio/low_min": 9.959659655578434e-05,
      "clip_ratio/region_mean": 0.0020479687736951746,
      "epoch": 0.055999860000349996,
      "grad_norm": 0.11923374235630035,
      "learning_rate": 1e-06,
      "loss": 0.0169,
      "step": 600
    },
    {
      "clip_ratio/high_max": 0.0023188820923678577,
      "clip_ratio/high_mean": 0.0009774119080248056,
      "clip_ratio/low_mean": 0.0008481391596433241,
      "clip_ratio/low_min": 5.699911525880452e-05,
      "clip_ratio/region_mean": 0.0018255510658491403,
      "epoch": 0.05609319310035058,
      "grad_norm": 0.10098270326852798,
      "learning_rate": 1e-06,
      "loss": 0.0019,
      "step": 601
    },
    {
      "clip_ratio/high_max": 0.002604272187454626,
      "clip_ratio/high_mean": 0.0009815658449952025,
      "clip_ratio/low_mean": 0.001053436581059941,
      "clip_ratio/low_min": 5.977434830128914e-05,
      "clip_ratio/region_mean": 0.0020350023842183873,
      "epoch": 0.05618652620035117,
      "grad_norm": 0.11951037496328354,
      "learning_rate": 1e-06,
      "loss": 0.0077,
      "step": 602
    },
    {
      "clip_ratio/high_max": 0.002145596910850145,
      "clip_ratio/high_mean": 0.0009673955046309857,
      "clip_ratio/low_mean": 0.001266419636522187,
      "clip_ratio/low_min": 8.729849287192337e-05,
      "clip_ratio/region_mean": 0.002233815161162056,
      "epoch": 0.05627985930035175,
      "grad_norm": 0.11715636402368546,
      "learning_rate": 1e-06,
      "loss": 0.0457,
      "step": 603
    },
    {
      "clip_ratio/high_max": 0.0022288630607363302,
      "clip_ratio/high_mean": 0.0008411181770497933,
      "clip_ratio/low_mean": 0.0012082733919669408,
      "clip_ratio/low_min": 1.3177314031054266e-05,
      "clip_ratio/region_mean": 0.0020493915799306706,
      "epoch": 0.05637319240035233,
      "grad_norm": 0.30399492383003235,
      "learning_rate": 1e-06,
      "loss": 0.0631,
      "step": 604
    },
    {
      "clip_ratio/high_max": 0.0025918883038684726,
      "clip_ratio/high_mean": 0.001042553278239211,
      "clip_ratio/low_mean": 0.0012045267303619767,
      "clip_ratio/low_min": 0.00013828648116032127,
      "clip_ratio/region_mean": 0.002247080068627838,
      "epoch": 0.056466525500352915,
      "grad_norm": 0.11313539743423462,
      "learning_rate": 1e-06,
      "loss": 0.032,
      "step": 605
    },
    {
      "clip_ratio/high_max": 0.002171586485928856,
      "clip_ratio/high_mean": 0.000912574239919195,
      "clip_ratio/low_mean": 0.0012378535466268659,
      "clip_ratio/low_min": 0.00014586246834369376,
      "clip_ratio/region_mean": 0.0021504278120119125,
      "epoch": 0.0565598586003535,
      "grad_norm": 0.1191086545586586,
      "learning_rate": 1e-06,
      "loss": 0.0186,
      "step": 606
    },
    {
      "clip_ratio/high_max": 0.0028559632191900164,
      "clip_ratio/high_mean": 0.0011514084944792558,
      "clip_ratio/low_mean": 0.0013359503755054902,
      "clip_ratio/low_min": 9.57002084760461e-05,
      "clip_ratio/region_mean": 0.0024873588990885764,
      "epoch": 0.056653191700354086,
      "grad_norm": 0.13263286650180817,
      "learning_rate": 1e-06,
      "loss": 0.0372,
      "step": 607
    },
    {
      "clip_ratio/high_max": 0.002273844998853747,
      "clip_ratio/high_mean": 0.0010449366964166984,
      "clip_ratio/low_mean": 0.0011178272470715456,
      "clip_ratio/low_min": 0.00014016128807270434,
      "clip_ratio/region_mean": 0.002162763979868032,
      "epoch": 0.056746524800354664,
      "grad_norm": 0.10531739890575409,
      "learning_rate": 1e-06,
      "loss": 0.0329,
      "step": 608
    },
    {
      "clip_ratio/high_max": 0.002481375660863705,
      "clip_ratio/high_mean": 0.0010798064031405374,
      "clip_ratio/low_mean": 0.0009624852191336686,
      "clip_ratio/low_min": 5.298283213051036e-05,
      "clip_ratio/region_mean": 0.0020422916059033014,
      "completions/clipped_ratio": 0.014107840401785698,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4079.0,
      "completions/mean_length": 614.7670288085938,
      "completions/mean_terminated_length": 564.9515991210938,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.05683985790035525,
      "grad_norm": 0.13478153944015503,
      "learning_rate": 1e-06,
      "loss": 0.003,
      "num_tokens": 489065502.0,
      "reward": 0.5779855251312256,
      "reward_std": 0.19758881628513336,
      "rewards/simpleverify_reward/mean": 0.5779854655265808,
      "rewards/simpleverify_reward/std": 0.4938828945159912,
      "step": 609
    },
    {
      "clip_ratio/high_max": 0.0018826923187589273,
      "clip_ratio/high_mean": 0.000883283328221296,
      "clip_ratio/low_mean": 0.0009435781030333601,
      "clip_ratio/low_min": 8.98214466360514e-05,
      "clip_ratio/region_mean": 0.001826861458539497,
      "epoch": 0.056933191000355834,
      "grad_norm": 1.8454992771148682,
      "learning_rate": 1e-06,
      "loss": 0.0656,
      "step": 610
    },
    {
      "clip_ratio/high_max": 0.002433124180242885,
      "clip_ratio/high_mean": 0.0011184483428223757,
      "clip_ratio/low_mean": 0.0010766275809146464,
      "clip_ratio/low_min": 7.665696466574445e-05,
      "clip_ratio/region_mean": 0.0021950759037281387,
      "epoch": 0.05702652410035641,
      "grad_norm": 0.1422373205423355,
      "learning_rate": 1e-06,
      "loss": 0.0329,
      "step": 611
    },
    {
      "clip_ratio/high_max": 0.0026827713300008327,
      "clip_ratio/high_mean": 0.0011337460673530586,
      "clip_ratio/low_mean": 0.001051625289619551,
      "clip_ratio/low_min": 0.0001889002614916535,
      "clip_ratio/region_mean": 0.0021853713478776626,
      "epoch": 0.057119857200357,
      "grad_norm": 0.13265828788280487,
      "learning_rate": 1e-06,
      "loss": 0.007,
      "step": 612
    },
    {
      "clip_ratio/high_max": 0.002417869749478996,
      "clip_ratio/high_mean": 0.0009905324168357765,
      "clip_ratio/low_mean": 0.0011561478459043428,
      "clip_ratio/low_min": 0.00017516242223791778,
      "clip_ratio/region_mean": 0.002146680242731236,
      "epoch": 0.05721319030035758,
      "grad_norm": 0.12621721625328064,
      "learning_rate": 1e-06,
      "loss": 0.0461,
      "step": 613
    },
    {
      "clip_ratio/high_max": 0.0021351930918172,
      "clip_ratio/high_mean": 0.0009299481207563076,
      "clip_ratio/low_mean": 0.0011066958632000023,
      "clip_ratio/low_min": 9.874462193693034e-05,
      "clip_ratio/region_mean": 0.0020366439493955113,
      "epoch": 0.05730652340035817,
      "grad_norm": 14072937472.0,
      "learning_rate": 1e-06,
      "loss": 6914351.0,
      "step": 614
    },
    {
      "clip_ratio/high_max": 0.0024725770417717285,
      "clip_ratio/high_mean": 0.001070097780029755,
      "clip_ratio/low_mean": 0.0009615337785362499,
      "clip_ratio/low_min": 6.97443974786438e-05,
      "clip_ratio/region_mean": 0.002031631549471058,
      "epoch": 0.05739985650035875,
      "grad_norm": 1.0688698291778564,
      "learning_rate": 1e-06,
      "loss": 0.0509,
      "step": 615
    },
    {
      "clip_ratio/high_max": 0.0027717277116607875,
      "clip_ratio/high_mean": 0.0010635005201038439,
      "clip_ratio/low_mean": 0.001033225857099751,
      "clip_ratio/low_min": 8.539021473552566e-05,
      "clip_ratio/region_mean": 0.0020967263699276373,
      "epoch": 0.05749318960035933,
      "grad_norm": 0.10949176549911499,
      "learning_rate": 1e-06,
      "loss": 0.0277,
      "step": 616
    },
    {
      "clip_ratio/high_max": 0.002559550375735853,
      "clip_ratio/high_mean": 0.001045377061018371,
      "clip_ratio/low_mean": 0.001116386421927018,
      "clip_ratio/low_min": 0.00013004834636376472,
      "clip_ratio/region_mean": 0.0021617634847643785,
      "epoch": 0.05758652270035992,
      "grad_norm": 0.3339146077632904,
      "learning_rate": 1e-06,
      "loss": 0.021,
      "step": 617
    },
    {
      "clip_ratio/high_max": 0.0023403273662552238,
      "clip_ratio/high_mean": 0.0009199930627801223,
      "clip_ratio/low_mean": 0.001144464811659418,
      "clip_ratio/low_min": 0.00016603298718109727,
      "clip_ratio/region_mean": 0.002064457890810445,
      "epoch": 0.0576798558003605,
      "grad_norm": 249700.59375,
      "learning_rate": 1e-06,
      "loss": 62.5008,
      "step": 618
    },
    {
      "clip_ratio/high_max": 0.0024026289393077604,
      "clip_ratio/high_mean": 0.001161467815109063,
      "clip_ratio/low_mean": 0.001040013969031861,
      "clip_ratio/low_min": 7.728922901151236e-05,
      "clip_ratio/region_mean": 0.0022014817586750723,
      "epoch": 0.05777318890036108,
      "grad_norm": 0.12954115867614746,
      "learning_rate": 1e-06,
      "loss": 0.0157,
      "step": 619
    },
    {
      "clip_ratio/high_max": 0.0024663466901984066,
      "clip_ratio/high_mean": 0.0010262158739351435,
      "clip_ratio/low_mean": 0.0011104269688075874,
      "clip_ratio/low_min": 2.800179208861664e-05,
      "clip_ratio/region_mean": 0.002136642920959275,
      "epoch": 0.057866522000361666,
      "grad_norm": 0.1635865569114685,
      "learning_rate": 1e-06,
      "loss": 0.0413,
      "step": 620
    },
    {
      "clip_ratio/high_max": 0.0023338408282143064,
      "clip_ratio/high_mean": 0.0009335654831374995,
      "clip_ratio/low_mean": 0.0011179965804331005,
      "clip_ratio/low_min": 0.00015746902499813586,
      "clip_ratio/region_mean": 0.0020515621145023033,
      "epoch": 0.05795985510036225,
      "grad_norm": 0.11043478548526764,
      "learning_rate": 1e-06,
      "loss": 0.0522,
      "step": 621
    },
    {
      "clip_ratio/high_max": 0.002195848341216333,
      "clip_ratio/high_mean": 0.0008944363162299851,
      "clip_ratio/low_mean": 0.0011744457733584568,
      "clip_ratio/low_min": 6.835143176431302e-05,
      "clip_ratio/region_mean": 0.002068882131425198,
      "epoch": 0.05805318820036283,
      "grad_norm": 0.1274164766073227,
      "learning_rate": 1e-06,
      "loss": 0.04,
      "step": 622
    },
    {
      "clip_ratio/high_max": 0.002555703977122903,
      "clip_ratio/high_mean": 0.0009996252265409566,
      "clip_ratio/low_mean": 0.0011054466704081278,
      "clip_ratio/low_min": 7.226069556054426e-05,
      "clip_ratio/region_mean": 0.0021050718569313176,
      "epoch": 0.058146521300363414,
      "grad_norm": 0.12116770446300507,
      "learning_rate": 1e-06,
      "loss": 0.0344,
      "step": 623
    },
    {
      "clip_ratio/high_max": 0.0023710469213256147,
      "clip_ratio/high_mean": 0.0009325961764261592,
      "clip_ratio/low_mean": 0.0009719665431475732,
      "clip_ratio/low_min": 2.7580582354858052e-05,
      "clip_ratio/region_mean": 0.0019045626831939444,
      "epoch": 0.058239854400364,
      "grad_norm": 965.5730590820312,
      "learning_rate": 1e-06,
      "loss": 0.4894,
      "step": 624
    },
    {
      "clip_ratio/high_max": 0.0024476631078869104,
      "clip_ratio/high_mean": 0.0009908318879752187,
      "clip_ratio/low_mean": 0.0012181521378806792,
      "clip_ratio/low_min": 2.84762872979627e-05,
      "clip_ratio/region_mean": 0.002208983998571057,
      "epoch": 0.058333187500364585,
      "grad_norm": 0.1634451001882553,
      "learning_rate": 1e-06,
      "loss": 0.0331,
      "step": 625
    },
    {
      "clip_ratio/high_max": 0.002235976582596777,
      "clip_ratio/high_mean": 0.0009083714066946413,
      "clip_ratio/low_mean": 0.0011043392005376518,
      "clip_ratio/low_min": 7.413418097712565e-05,
      "clip_ratio/region_mean": 0.0020127105963183567,
      "epoch": 0.05842652060036516,
      "grad_norm": 0.12290123850107193,
      "learning_rate": 1e-06,
      "loss": 0.0217,
      "step": 626
    },
    {
      "clip_ratio/high_max": 0.0025451778201386333,
      "clip_ratio/high_mean": 0.001139744788815733,
      "clip_ratio/low_mean": 0.0013215845538070425,
      "clip_ratio/low_min": 6.971872699068626e-05,
      "clip_ratio/region_mean": 0.002461329349898733,
      "epoch": 0.05851985370036575,
      "grad_norm": 0.12009480595588684,
      "learning_rate": 1e-06,
      "loss": 0.0309,
      "step": 627
    },
    {
      "clip_ratio/high_max": 0.002643365107360296,
      "clip_ratio/high_mean": 0.0011768949079851154,
      "clip_ratio/low_mean": 0.0011976478272117674,
      "clip_ratio/low_min": 0.0001431542623322457,
      "clip_ratio/region_mean": 0.0023745427970425226,
      "epoch": 0.05861318680036633,
      "grad_norm": 0.11753562092781067,
      "learning_rate": 1e-06,
      "loss": 0.0276,
      "step": 628
    },
    {
      "clip_ratio/high_max": 0.002438943429297069,
      "clip_ratio/high_mean": 0.001046201165081584,
      "clip_ratio/low_mean": 0.0013472400642058346,
      "clip_ratio/low_min": 0.00020198828860884532,
      "clip_ratio/region_mean": 0.002393441172898747,
      "epoch": 0.05870651990036692,
      "grad_norm": 0.11168830096721649,
      "learning_rate": 1e-06,
      "loss": 0.0703,
      "step": 629
    },
    {
      "clip_ratio/high_max": 0.002333088868908817,
      "clip_ratio/high_mean": 0.0009067199443961727,
      "clip_ratio/low_mean": 0.0017064188577933237,
      "clip_ratio/low_min": 0.00022318211449601222,
      "clip_ratio/region_mean": 0.0026131387567147613,
      "epoch": 0.0587998530003675,
      "grad_norm": 0.11786709725856781,
      "learning_rate": 1e-06,
      "loss": 0.0916,
      "step": 630
    },
    {
      "clip_ratio/high_max": 0.0027130329035571776,
      "clip_ratio/high_mean": 0.0010847731264220783,
      "clip_ratio/low_mean": 0.0014855799272481818,
      "clip_ratio/low_min": 0.00016107022383948788,
      "clip_ratio/region_mean": 0.002570353026385419,
      "epoch": 0.05889318610036808,
      "grad_norm": 10.57763385772705,
      "learning_rate": 1e-06,
      "loss": 0.0595,
      "step": 631
    },
    {
      "clip_ratio/high_max": 0.002469524544721935,
      "clip_ratio/high_mean": 0.000999443742330186,
      "clip_ratio/low_mean": 0.001408760135745979,
      "clip_ratio/low_min": 0.0001192190138681326,
      "clip_ratio/region_mean": 0.002408203828963451,
      "epoch": 0.05898651920036867,
      "grad_norm": 0.355061799287796,
      "learning_rate": 1e-06,
      "loss": 0.0343,
      "step": 632
    },
    {
      "clip_ratio/high_max": 0.002734995221544523,
      "clip_ratio/high_mean": 0.0011616006140684476,
      "clip_ratio/low_mean": 0.0014469487032329198,
      "clip_ratio/low_min": 5.343414613889763e-05,
      "clip_ratio/region_mean": 0.00260854927910259,
      "epoch": 0.05907985230036925,
      "grad_norm": 0.10703109949827194,
      "learning_rate": 1e-06,
      "loss": 0.0147,
      "step": 633
    },
    {
      "clip_ratio/high_max": 0.002768713493424002,
      "clip_ratio/high_mean": 0.0010938397063000593,
      "clip_ratio/low_mean": 0.0011693555825331714,
      "clip_ratio/low_min": 2.7276426408207044e-05,
      "clip_ratio/region_mean": 0.0022631952888332307,
      "epoch": 0.05917318540036983,
      "grad_norm": 0.0950351357460022,
      "learning_rate": 1e-06,
      "loss": -0.0122,
      "step": 634
    },
    {
      "clip_ratio/high_max": 0.002465018398652319,
      "clip_ratio/high_mean": 0.0009798237042559776,
      "clip_ratio/low_mean": 0.0016322332103300141,
      "clip_ratio/low_min": 0.00019665213130792836,
      "clip_ratio/region_mean": 0.002612056880025193,
      "epoch": 0.059266518500370416,
      "grad_norm": 0.11052601039409637,
      "learning_rate": 1e-06,
      "loss": 0.0763,
      "step": 635
    },
    {
      "clip_ratio/high_max": 0.002533671118726488,
      "clip_ratio/high_mean": 0.0009781113803910557,
      "clip_ratio/low_mean": 0.0014456789394898806,
      "clip_ratio/low_min": 0.00011923054444196168,
      "clip_ratio/region_mean": 0.002423790378088597,
      "epoch": 0.059359851600371,
      "grad_norm": 0.10943303257226944,
      "learning_rate": 1e-06,
      "loss": 0.0262,
      "step": 636
    },
    {
      "clip_ratio/high_max": 0.0023464998630515765,
      "clip_ratio/high_mean": 0.001087652106434689,
      "clip_ratio/low_mean": 0.0014745159605809022,
      "clip_ratio/low_min": 0.00018325439941691002,
      "clip_ratio/region_mean": 0.002562168097938411,
      "epoch": 0.05945318470037158,
      "grad_norm": 0.12654410302639008,
      "learning_rate": 1e-06,
      "loss": -0.0059,
      "step": 637
    },
    {
      "clip_ratio/high_max": 0.0025381618324900046,
      "clip_ratio/high_mean": 0.0011521074775373563,
      "clip_ratio/low_mean": 0.0013021217382629402,
      "clip_ratio/low_min": 0.00011212957633688347,
      "clip_ratio/region_mean": 0.0024542291939724237,
      "epoch": 0.059546517800372165,
      "grad_norm": 0.11000388860702515,
      "learning_rate": 1e-06,
      "loss": 0.0312,
      "step": 638
    },
    {
      "clip_ratio/high_max": 0.002776867288048379,
      "clip_ratio/high_mean": 0.0011716094959410839,
      "clip_ratio/low_mean": 0.0011528494014783064,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0023244589538080618,
      "epoch": 0.05963985090037275,
      "grad_norm": 0.10943210124969482,
      "learning_rate": 1e-06,
      "loss": -0.005,
      "step": 639
    },
    {
      "clip_ratio/high_max": 0.002140525441063801,
      "clip_ratio/high_mean": 0.0008681018589413725,
      "clip_ratio/low_mean": 0.0016497030919708777,
      "clip_ratio/low_min": 0.00013927290819992777,
      "clip_ratio/region_mean": 0.0025178049836540595,
      "epoch": 0.059733184000373335,
      "grad_norm": 1.599152684211731,
      "learning_rate": 1e-06,
      "loss": 0.0822,
      "step": 640
    },
    {
      "clip_ratio/high_max": 0.002320529361895751,
      "clip_ratio/high_mean": 0.0009316174982814118,
      "clip_ratio/low_mean": 0.0014806601939199027,
      "clip_ratio/low_min": 0.0001431610789950355,
      "clip_ratio/region_mean": 0.0024122776594595052,
      "epoch": 0.05982651710037391,
      "grad_norm": 0.36795562505722046,
      "learning_rate": 1e-06,
      "loss": 0.0498,
      "step": 641
    },
    {
      "clip_ratio/high_max": 0.002545662267948501,
      "clip_ratio/high_mean": 0.001078245128155686,
      "clip_ratio/low_mean": 0.0014442984793276992,
      "clip_ratio/low_min": 5.239991514827125e-05,
      "clip_ratio/region_mean": 0.002522543611121364,
      "epoch": 0.0599198502003745,
      "grad_norm": 0.11597011983394623,
      "learning_rate": 1e-06,
      "loss": 0.0277,
      "step": 642
    },
    {
      "clip_ratio/high_max": 0.002377368466113694,
      "clip_ratio/high_mean": 0.0010435167168907356,
      "clip_ratio/low_mean": 0.0015064447361510247,
      "clip_ratio/low_min": 9.258969839720521e-05,
      "clip_ratio/region_mean": 0.0025499614712316543,
      "epoch": 0.060013183300375084,
      "grad_norm": 0.12030437588691711,
      "learning_rate": 1e-06,
      "loss": 0.0271,
      "step": 643
    },
    {
      "clip_ratio/high_max": 0.0022764059831388295,
      "clip_ratio/high_mean": 0.0009969972343242262,
      "clip_ratio/low_mean": 0.0014344241571961902,
      "clip_ratio/low_min": 0.00012481987869250588,
      "clip_ratio/region_mean": 0.002431421358778607,
      "epoch": 0.06010651640037567,
      "grad_norm": 0.11691172420978546,
      "learning_rate": 1e-06,
      "loss": 0.0108,
      "step": 644
    },
    {
      "clip_ratio/high_max": 0.002200591094151605,
      "clip_ratio/high_mean": 0.001027626805807813,
      "clip_ratio/low_mean": 0.0014785796774958726,
      "clip_ratio/low_min": 0.0001361388131044805,
      "clip_ratio/region_mean": 0.0025062064742087387,
      "epoch": 0.06019984950037625,
      "grad_norm": 0.6515962481498718,
      "learning_rate": 1e-06,
      "loss": 0.1354,
      "step": 645
    },
    {
      "clip_ratio/high_max": 0.002287144372530747,
      "clip_ratio/high_mean": 0.001025917266815668,
      "clip_ratio/low_mean": 0.0013302338411449455,
      "clip_ratio/low_min": 0.00010401302370155463,
      "clip_ratio/region_mean": 0.002356151097046677,
      "epoch": 0.06029318260037683,
      "grad_norm": 19.04352378845215,
      "learning_rate": 1e-06,
      "loss": 0.0194,
      "step": 646
    },
    {
      "clip_ratio/high_max": 0.0025620360247557983,
      "clip_ratio/high_mean": 0.000973580787103856,
      "clip_ratio/low_mean": 0.0013649256143253297,
      "clip_ratio/low_min": 0.00015349126442743,
      "clip_ratio/region_mean": 0.0023385063905152492,
      "epoch": 0.06038651570037742,
      "grad_norm": 0.11697337031364441,
      "learning_rate": 1e-06,
      "loss": -0.0043,
      "step": 647
    },
    {
      "clip_ratio/high_max": 0.002432079843856627,
      "clip_ratio/high_mean": 0.0009917522274918156,
      "clip_ratio/low_mean": 0.001269569795113057,
      "clip_ratio/low_min": 0.00010833987926162081,
      "clip_ratio/region_mean": 0.0022613220353377983,
      "epoch": 0.060479848800377996,
      "grad_norm": 0.10863753408193588,
      "learning_rate": 1e-06,
      "loss": 0.0093,
      "step": 648
    },
    {
      "clip_ratio/high_max": 0.0022621683310717344,
      "clip_ratio/high_mean": 0.0009445001178391976,
      "clip_ratio/low_mean": 0.0013273297627165448,
      "clip_ratio/low_min": 7.740234832454007e-05,
      "clip_ratio/region_mean": 0.0022718298860127106,
      "epoch": 0.06057318190037858,
      "grad_norm": 0.10702554881572723,
      "learning_rate": 1e-06,
      "loss": 0.0217,
      "step": 649
    },
    {
      "clip_ratio/high_max": 0.0024523667743778788,
      "clip_ratio/high_mean": 0.00097852002363652,
      "clip_ratio/low_mean": 0.001233047998539405,
      "clip_ratio/low_min": 0.00010808253045979654,
      "clip_ratio/region_mean": 0.0022115680621936917,
      "epoch": 0.060666515000379166,
      "grad_norm": 0.12258566915988922,
      "learning_rate": 1e-06,
      "loss": -0.0035,
      "step": 650
    },
    {
      "clip_ratio/high_max": 0.0020648834470193833,
      "clip_ratio/high_mean": 0.0008412961196881952,
      "clip_ratio/low_mean": 0.0012769153181579895,
      "clip_ratio/low_min": 6.171621680550743e-05,
      "clip_ratio/region_mean": 0.002118211457855068,
      "epoch": 0.06075984810037975,
      "grad_norm": 0.10569457709789276,
      "learning_rate": 1e-06,
      "loss": 0.0262,
      "step": 651
    },
    {
      "clip_ratio/high_max": 0.0027495974500197917,
      "clip_ratio/high_mean": 0.0011145794778713025,
      "clip_ratio/low_mean": 0.0011676070498651825,
      "clip_ratio/low_min": 0.00014539828634951846,
      "clip_ratio/region_mean": 0.002282186505908612,
      "epoch": 0.06085318120038033,
      "grad_norm": 0.1090521365404129,
      "learning_rate": 1e-06,
      "loss": 0.0134,
      "step": 652
    },
    {
      "clip_ratio/high_max": 0.0025869550445349887,
      "clip_ratio/high_mean": 0.0010744609462562948,
      "clip_ratio/low_mean": 0.0011594561765377875,
      "clip_ratio/low_min": 2.653700630617095e-05,
      "clip_ratio/region_mean": 0.0022339171409839764,
      "epoch": 0.060946514300380915,
      "grad_norm": 0.13510650396347046,
      "learning_rate": 1e-06,
      "loss": 0.0044,
      "step": 653
    },
    {
      "clip_ratio/high_max": 0.0027787536528194323,
      "clip_ratio/high_mean": 0.001104193739593029,
      "clip_ratio/low_mean": 0.0014708929556945805,
      "clip_ratio/low_min": 0.00015398228970298078,
      "clip_ratio/region_mean": 0.002575086684373673,
      "epoch": 0.0610398474003815,
      "grad_norm": 0.11401999741792679,
      "learning_rate": 1e-06,
      "loss": 0.0126,
      "step": 654
    },
    {
      "clip_ratio/high_max": 0.0026963075579260476,
      "clip_ratio/high_mean": 0.0010910008750215638,
      "clip_ratio/low_mean": 0.0015076146701176185,
      "clip_ratio/low_min": 8.807423819234828e-05,
      "clip_ratio/region_mean": 0.0025986155596910976,
      "epoch": 0.061133180500382085,
      "grad_norm": 0.15589646995067596,
      "learning_rate": 1e-06,
      "loss": 0.039,
      "step": 655
    },
    {
      "clip_ratio/high_max": 0.0026853707313421182,
      "clip_ratio/high_mean": 0.001006870956189232,
      "clip_ratio/low_mean": 0.0015459465284948237,
      "clip_ratio/low_min": 0.00025763245503185317,
      "clip_ratio/region_mean": 0.0025528174737701192,
      "epoch": 0.061226513600382663,
      "grad_norm": 0.12471504509449005,
      "learning_rate": 1e-06,
      "loss": 0.0374,
      "step": 656
    },
    {
      "clip_ratio/high_max": 0.0024121908318193164,
      "clip_ratio/high_mean": 0.001032410938933026,
      "clip_ratio/low_mean": 0.0013212125522841234,
      "clip_ratio/low_min": 0.00010638949515850982,
      "clip_ratio/region_mean": 0.0023536234948551282,
      "epoch": 0.06131984670038325,
      "grad_norm": 0.11951066553592682,
      "learning_rate": 1e-06,
      "loss": 0.0248,
      "step": 657
    },
    {
      "clip_ratio/high_max": 0.002063850646663923,
      "clip_ratio/high_mean": 0.0009129626741923857,
      "clip_ratio/low_mean": 0.0012775774303008802,
      "clip_ratio/low_min": 4.5842156396247447e-05,
      "clip_ratio/region_mean": 0.002190540100855287,
      "epoch": 0.061413179800383834,
      "grad_norm": 0.11594922095537186,
      "learning_rate": 1e-06,
      "loss": 0.0586,
      "step": 658
    },
    {
      "clip_ratio/high_max": 0.002625801251269877,
      "clip_ratio/high_mean": 0.0011583187624637503,
      "clip_ratio/low_mean": 0.0013048889086348936,
      "clip_ratio/low_min": 8.299439923575846e-05,
      "clip_ratio/region_mean": 0.002463207631080877,
      "epoch": 0.06150651290038442,
      "grad_norm": 0.11306975781917572,
      "learning_rate": 1e-06,
      "loss": -0.0371,
      "step": 659
    },
    {
      "clip_ratio/high_max": 0.0023783933866070583,
      "clip_ratio/high_mean": 0.0011153668237966485,
      "clip_ratio/low_mean": 0.0009566960943629965,
      "clip_ratio/low_min": 2.5938990802387707e-05,
      "clip_ratio/region_mean": 0.002072062918159645,
      "epoch": 0.061599846000385,
      "grad_norm": 0.11043727397918701,
      "learning_rate": 1e-06,
      "loss": -0.0405,
      "step": 660
    },
    {
      "clip_ratio/high_max": 0.0024551346941734664,
      "clip_ratio/high_mean": 0.0010959892078972189,
      "clip_ratio/low_mean": 0.001192376970720943,
      "clip_ratio/low_min": 3.619626249928842e-05,
      "clip_ratio/region_mean": 0.002288366187713109,
      "epoch": 0.06169317910038558,
      "grad_norm": 0.1374572366476059,
      "learning_rate": 1e-06,
      "loss": 0.039,
      "step": 661
    },
    {
      "clip_ratio/high_max": 0.0023530258840764873,
      "clip_ratio/high_mean": 0.0010477811010787264,
      "clip_ratio/low_mean": 0.0013215098697401118,
      "clip_ratio/low_min": 9.351839253213257e-05,
      "clip_ratio/region_mean": 0.002369290858041495,
      "epoch": 0.06178651220038617,
      "grad_norm": 0.13867244124412537,
      "learning_rate": 1e-06,
      "loss": -0.0017,
      "step": 662
    },
    {
      "clip_ratio/high_max": 0.002232126076705754,
      "clip_ratio/high_mean": 0.0008987615583464503,
      "clip_ratio/low_mean": 0.0011110207069577882,
      "clip_ratio/low_min": 4.9956074690271635e-05,
      "clip_ratio/region_mean": 0.002009782263485249,
      "epoch": 0.061879845300386746,
      "grad_norm": 0.10422000288963318,
      "learning_rate": 1e-06,
      "loss": -0.0049,
      "step": 663
    },
    {
      "clip_ratio/high_max": 0.002710353903239593,
      "clip_ratio/high_mean": 0.0012015982829325367,
      "clip_ratio/low_mean": 0.0012092820616089739,
      "clip_ratio/low_min": 0.00010489207670616452,
      "clip_ratio/region_mean": 0.002410880333627574,
      "epoch": 0.06197317840038733,
      "grad_norm": 4148.28466796875,
      "learning_rate": 1e-06,
      "loss": 6.3788,
      "step": 664
    },
    {
      "clip_ratio/high_max": 0.002445989379339153,
      "clip_ratio/high_mean": 0.0009419266734767007,
      "clip_ratio/low_mean": 0.0010934119709418155,
      "clip_ratio/low_min": 4.1172873352479655e-05,
      "clip_ratio/region_mean": 0.0020353386498754844,
      "epoch": 0.062066511500387916,
      "grad_norm": 0.17105872929096222,
      "learning_rate": 1e-06,
      "loss": 0.0138,
      "step": 665
    },
    {
      "clip_ratio/high_max": 0.0019694851071108133,
      "clip_ratio/high_mean": 0.0008912036519177491,
      "clip_ratio/low_mean": 0.001200806837005075,
      "clip_ratio/low_min": 0.0002483644893800374,
      "clip_ratio/region_mean": 0.002092010479827877,
      "epoch": 0.0621598446003885,
      "grad_norm": 0.10640674829483032,
      "learning_rate": 1e-06,
      "loss": 0.0192,
      "step": 666
    },
    {
      "clip_ratio/high_max": 0.002233234976301901,
      "clip_ratio/high_mean": 0.0009870616231637541,
      "clip_ratio/low_mean": 0.0012969460985914338,
      "clip_ratio/low_min": 0.00015328968584071845,
      "clip_ratio/region_mean": 0.002284007736307103,
      "epoch": 0.06225317770038908,
      "grad_norm": 0.10902467370033264,
      "learning_rate": 1e-06,
      "loss": 0.0233,
      "step": 667
    },
    {
      "clip_ratio/high_max": 0.002011421100178268,
      "clip_ratio/high_mean": 0.0009281812126573641,
      "clip_ratio/low_mean": 0.001393393617036054,
      "clip_ratio/low_min": 0.00019431123837421183,
      "clip_ratio/region_mean": 0.0023215748005895875,
      "epoch": 0.062346510800389665,
      "grad_norm": 0.17937719821929932,
      "learning_rate": 1e-06,
      "loss": 0.0588,
      "step": 668
    },
    {
      "clip_ratio/high_max": 0.0020904075463477056,
      "clip_ratio/high_mean": 0.0008997024615382543,
      "clip_ratio/low_mean": 0.0013801790446450468,
      "clip_ratio/low_min": 0.0001435560807294678,
      "clip_ratio/region_mean": 0.0022798815261921845,
      "epoch": 0.06243984390039025,
      "grad_norm": 0.10588958114385605,
      "learning_rate": 1e-06,
      "loss": -0.0151,
      "step": 669
    },
    {
      "clip_ratio/high_max": 0.002417557443550322,
      "clip_ratio/high_mean": 0.0010329084743716521,
      "clip_ratio/low_mean": 0.001336307374003809,
      "clip_ratio/low_min": 6.038274568709312e-05,
      "clip_ratio/region_mean": 0.002369215857470408,
      "epoch": 0.06253317700039084,
      "grad_norm": 0.1187441274523735,
      "learning_rate": 1e-06,
      "loss": 0.0352,
      "step": 670
    },
    {
      "clip_ratio/high_max": 0.002480857896443922,
      "clip_ratio/high_mean": 0.0010278425834258087,
      "clip_ratio/low_mean": 0.0013508358097169548,
      "clip_ratio/low_min": 0.00010568636116659036,
      "clip_ratio/region_mean": 0.002378678422246594,
      "epoch": 0.06262651010039141,
      "grad_norm": 0.11163929104804993,
      "learning_rate": 1e-06,
      "loss": -0.0164,
      "step": 671
    },
    {
      "clip_ratio/high_max": 0.0022365770164469723,
      "clip_ratio/high_mean": 0.0009602849804650759,
      "clip_ratio/low_mean": 0.001330734790826682,
      "clip_ratio/low_min": 0.00015553867615381023,
      "clip_ratio/region_mean": 0.0022910197731107473,
      "epoch": 0.062719843200392,
      "grad_norm": 0.2668677568435669,
      "learning_rate": 1e-06,
      "loss": 0.0067,
      "step": 672
    },
    {
      "clip_ratio/high_max": 0.0023627673945156857,
      "clip_ratio/high_mean": 0.0009864389485301217,
      "clip_ratio/low_mean": 0.001440965237634373,
      "clip_ratio/low_min": 0.00013962466800876427,
      "clip_ratio/region_mean": 0.0024274041716125794,
      "epoch": 0.06281317630039258,
      "grad_norm": 0.1117556095123291,
      "learning_rate": 1e-06,
      "loss": 0.0018,
      "step": 673
    },
    {
      "clip_ratio/high_max": 0.0019086802494712174,
      "clip_ratio/high_mean": 0.0008545816053810995,
      "clip_ratio/low_mean": 0.0013530310534406453,
      "clip_ratio/low_min": 9.74384220171487e-05,
      "clip_ratio/region_mean": 0.0022076127061154693,
      "epoch": 0.06290650940039316,
      "grad_norm": 0.11400160193443298,
      "learning_rate": 1e-06,
      "loss": 0.0296,
      "step": 674
    },
    {
      "clip_ratio/high_max": 0.0018440688945702277,
      "clip_ratio/high_mean": 0.0007894118371041259,
      "clip_ratio/low_mean": 0.0013532640623452608,
      "clip_ratio/low_min": 0.00010083082270284649,
      "clip_ratio/region_mean": 0.002142675861250609,
      "epoch": 0.06299984250039375,
      "grad_norm": 0.11896184831857681,
      "learning_rate": 1e-06,
      "loss": 0.0582,
      "step": 675
    },
    {
      "clip_ratio/high_max": 0.0025069195035030134,
      "clip_ratio/high_mean": 0.0011351410903444048,
      "clip_ratio/low_mean": 0.0013034091534791514,
      "clip_ratio/low_min": 5.0169653150078375e-05,
      "clip_ratio/region_mean": 0.0024385501965298317,
      "epoch": 0.06309317560039433,
      "grad_norm": 0.11076658219099045,
      "learning_rate": 1e-06,
      "loss": 0.0071,
      "step": 676
    },
    {
      "clip_ratio/high_max": 0.0021391708869487047,
      "clip_ratio/high_mean": 0.0009580245223332895,
      "clip_ratio/low_mean": 0.001430384028935805,
      "clip_ratio/low_min": 0.00010103542626893613,
      "clip_ratio/region_mean": 0.0023884086185717024,
      "epoch": 0.06318650870039491,
      "grad_norm": 0.10459767282009125,
      "learning_rate": 1e-06,
      "loss": 0.0624,
      "step": 677
    },
    {
      "clip_ratio/high_max": 0.002137682429747656,
      "clip_ratio/high_mean": 0.00099198569660075,
      "clip_ratio/low_mean": 0.0013740914582740515,
      "clip_ratio/low_min": 0.0002392204860370839,
      "clip_ratio/region_mean": 0.002366077133046929,
      "epoch": 0.0632798418003955,
      "grad_norm": 0.1039733737707138,
      "learning_rate": 1e-06,
      "loss": 0.0197,
      "step": 678
    },
    {
      "clip_ratio/high_max": 0.002055105462204665,
      "clip_ratio/high_mean": 0.0009679204322310397,
      "clip_ratio/low_mean": 0.001264243363038986,
      "clip_ratio/low_min": 0.00016018713631638093,
      "clip_ratio/region_mean": 0.0022321637807181105,
      "epoch": 0.06337317490039608,
      "grad_norm": 0.10956466197967529,
      "learning_rate": 1e-06,
      "loss": 0.0123,
      "step": 679
    },
    {
      "clip_ratio/high_max": 0.002592860924778506,
      "clip_ratio/high_mean": 0.0011743278046196792,
      "clip_ratio/low_mean": 0.0011391170937713468,
      "clip_ratio/low_min": 0.0001533035674583516,
      "clip_ratio/region_mean": 0.0023134449002100155,
      "epoch": 0.06346650800039666,
      "grad_norm": 0.10671522468328476,
      "learning_rate": 1e-06,
      "loss": -0.0452,
      "step": 680
    },
    {
      "clip_ratio/high_max": 0.0022551204820047133,
      "clip_ratio/high_mean": 0.0010086747442983324,
      "clip_ratio/low_mean": 0.0013218061249062885,
      "clip_ratio/low_min": 1.367315690004034e-05,
      "clip_ratio/region_mean": 0.0023304809074033983,
      "epoch": 0.06355984110039725,
      "grad_norm": 0.11453437060117722,
      "learning_rate": 1e-06,
      "loss": -0.0076,
      "step": 681
    },
    {
      "clip_ratio/high_max": 0.0022475221412605606,
      "clip_ratio/high_mean": 0.0009552631890983321,
      "clip_ratio/low_mean": 0.0015905241853033658,
      "clip_ratio/low_min": 0.00023384841188089922,
      "clip_ratio/region_mean": 0.0025457874580752105,
      "epoch": 0.06365317420039783,
      "grad_norm": 0.13428255915641785,
      "learning_rate": 1e-06,
      "loss": 0.0406,
      "step": 682
    },
    {
      "clip_ratio/high_max": 0.0021352813455450814,
      "clip_ratio/high_mean": 0.0009092930313272518,
      "clip_ratio/low_mean": 0.0012580564216477796,
      "clip_ratio/low_min": 4.360519415058661e-05,
      "clip_ratio/region_mean": 0.002167349426599685,
      "epoch": 0.06374650730039842,
      "grad_norm": 2.868584632873535,
      "learning_rate": 1e-06,
      "loss": 0.0301,
      "step": 683
    },
    {
      "clip_ratio/high_max": 0.002089362908009207,
      "clip_ratio/high_mean": 0.0009201261000271188,
      "clip_ratio/low_mean": 0.0013270883246150333,
      "clip_ratio/low_min": 0.00030350187989824917,
      "clip_ratio/region_mean": 0.002247214477392845,
      "epoch": 0.063839840400399,
      "grad_norm": 0.11900093406438828,
      "learning_rate": 1e-06,
      "loss": 0.0252,
      "step": 684
    },
    {
      "clip_ratio/high_max": 0.002147254053852521,
      "clip_ratio/high_mean": 0.0009190749860863434,
      "clip_ratio/low_mean": 0.0013434622051136103,
      "clip_ratio/low_min": 6.048674049452529e-05,
      "clip_ratio/region_mean": 0.002262537193018943,
      "epoch": 0.06393317350039958,
      "grad_norm": 0.1181182786822319,
      "learning_rate": 1e-06,
      "loss": 0.0459,
      "step": 685
    },
    {
      "clip_ratio/high_max": 0.002067133267701138,
      "clip_ratio/high_mean": 0.0008905928480089642,
      "clip_ratio/low_mean": 0.0011316949103274965,
      "clip_ratio/low_min": 0.00010732088048825972,
      "clip_ratio/region_mean": 0.0020222877428750508,
      "epoch": 0.06402650660040017,
      "grad_norm": 0.10931537300348282,
      "learning_rate": 1e-06,
      "loss": 0.0269,
      "step": 686
    },
    {
      "clip_ratio/high_max": 0.0027406108856666833,
      "clip_ratio/high_mean": 0.0011706712411978515,
      "clip_ratio/low_mean": 0.0011570697497518267,
      "clip_ratio/low_min": 0.00016425488502136432,
      "clip_ratio/region_mean": 0.0023277410145965405,
      "epoch": 0.06411983970040075,
      "grad_norm": 0.12323232740163803,
      "learning_rate": 1e-06,
      "loss": 0.008,
      "step": 687
    },
    {
      "clip_ratio/high_max": 0.0027424366053310223,
      "clip_ratio/high_mean": 0.001030556961268303,
      "clip_ratio/low_mean": 0.00158773594921513,
      "clip_ratio/low_min": 0.00019340653125254903,
      "clip_ratio/region_mean": 0.002618292892293539,
      "epoch": 0.06421317280040133,
      "grad_norm": 0.5412478446960449,
      "learning_rate": 1e-06,
      "loss": 0.0399,
      "step": 688
    },
    {
      "clip_ratio/high_max": 0.0023235082771861926,
      "clip_ratio/high_mean": 0.0008790420288278256,
      "clip_ratio/low_mean": 0.0013361312667257152,
      "clip_ratio/low_min": 0.00013549268351198407,
      "clip_ratio/region_mean": 0.0022151732773636468,
      "epoch": 0.06430650590040192,
      "grad_norm": 0.10890794545412064,
      "learning_rate": 1e-06,
      "loss": 0.0363,
      "step": 689
    },
    {
      "clip_ratio/high_max": 0.0023400458667310886,
      "clip_ratio/high_mean": 0.0009628291845729109,
      "clip_ratio/low_mean": 0.0014204945291567128,
      "clip_ratio/low_min": 0.0002308327939317678,
      "clip_ratio/region_mean": 0.0023833237501094118,
      "epoch": 0.0643998390004025,
      "grad_norm": 0.12933948636054993,
      "learning_rate": 1e-06,
      "loss": 0.0632,
      "step": 690
    },
    {
      "clip_ratio/high_max": 0.002740357434959151,
      "clip_ratio/high_mean": 0.001158433486125432,
      "clip_ratio/low_mean": 0.0011139394482597709,
      "clip_ratio/low_min": 2.5783829187275842e-05,
      "clip_ratio/region_mean": 0.0022723729634890333,
      "epoch": 0.06449317210040308,
      "grad_norm": 0.1131989061832428,
      "learning_rate": 1e-06,
      "loss": -0.0069,
      "step": 691
    },
    {
      "clip_ratio/high_max": 0.002331867472094018,
      "clip_ratio/high_mean": 0.0009702574625407578,
      "clip_ratio/low_mean": 0.0011739674919226673,
      "clip_ratio/low_min": 7.384502441709628e-05,
      "clip_ratio/region_mean": 0.0021442248762468807,
      "epoch": 0.06458650520040367,
      "grad_norm": 0.1338718831539154,
      "learning_rate": 1e-06,
      "loss": 0.0563,
      "step": 692
    },
    {
      "clip_ratio/high_max": 0.0023515865177614614,
      "clip_ratio/high_mean": 0.0009812846983550116,
      "clip_ratio/low_mean": 0.0010844938769878354,
      "clip_ratio/low_min": 8.952659572969424e-05,
      "clip_ratio/region_mean": 0.002065778578980826,
      "epoch": 0.06467983830040425,
      "grad_norm": 0.11498841643333435,
      "learning_rate": 1e-06,
      "loss": 0.0272,
      "step": 693
    },
    {
      "clip_ratio/high_max": 0.002324499888345599,
      "clip_ratio/high_mean": 0.000953960415245092,
      "clip_ratio/low_mean": 0.001281638706132071,
      "clip_ratio/low_min": 0.00023566906929772813,
      "clip_ratio/region_mean": 0.002235599131381605,
      "epoch": 0.06477317140040484,
      "grad_norm": 0.11788497865200043,
      "learning_rate": 1e-06,
      "loss": 0.0648,
      "step": 694
    },
    {
      "clip_ratio/high_max": 0.0026258151920046657,
      "clip_ratio/high_mean": 0.001108573282181169,
      "clip_ratio/low_mean": 0.0009595559749868698,
      "clip_ratio/low_min": 3.55531410605181e-05,
      "clip_ratio/region_mean": 0.002068129244435113,
      "epoch": 0.06486650450040542,
      "grad_norm": 0.11140355467796326,
      "learning_rate": 1e-06,
      "loss": 0.0112,
      "step": 695
    },
    {
      "clip_ratio/high_max": 0.002771210318314843,
      "clip_ratio/high_mean": 0.001031831772706937,
      "clip_ratio/low_mean": 0.0012863392475992441,
      "clip_ratio/low_min": 0.00016965200666163582,
      "clip_ratio/region_mean": 0.0023181710566859692,
      "epoch": 0.064959837600406,
      "grad_norm": 0.10203178226947784,
      "learning_rate": 1e-06,
      "loss": 0.0257,
      "step": 696
    },
    {
      "clip_ratio/high_max": 0.0021398632088676095,
      "clip_ratio/high_mean": 0.000935660777031444,
      "clip_ratio/low_mean": 0.0011616647734626895,
      "clip_ratio/low_min": 6.220911200216506e-05,
      "clip_ratio/region_mean": 0.00209732553048525,
      "epoch": 0.06505317070040659,
      "grad_norm": 0.10208957642316818,
      "learning_rate": 1e-06,
      "loss": 0.0257,
      "step": 697
    },
    {
      "clip_ratio/high_max": 0.002198674472310813,
      "clip_ratio/high_mean": 0.0009424757809028961,
      "clip_ratio/low_mean": 0.001290460455493303,
      "clip_ratio/low_min": 6.455591483245371e-05,
      "clip_ratio/region_mean": 0.002232936218206305,
      "epoch": 0.06514650380040717,
      "grad_norm": 0.11768817156553268,
      "learning_rate": 1e-06,
      "loss": 0.0358,
      "step": 698
    },
    {
      "clip_ratio/high_max": 0.0024097610876196995,
      "clip_ratio/high_mean": 0.0010552777366683586,
      "clip_ratio/low_mean": 0.001397711894242093,
      "clip_ratio/low_min": 0.00017318117534159683,
      "clip_ratio/region_mean": 0.0024529896400053985,
      "epoch": 0.06523983690040774,
      "grad_norm": 0.13768014311790466,
      "learning_rate": 1e-06,
      "loss": 0.0468,
      "step": 699
    },
    {
      "clip_ratio/high_max": 0.002438643597997725,
      "clip_ratio/high_mean": 0.0011547299109224696,
      "clip_ratio/low_mean": 0.0011869404897879576,
      "clip_ratio/low_min": 0.0001390645466017304,
      "clip_ratio/region_mean": 0.002341670318855904,
      "epoch": 0.06533317000040834,
      "grad_norm": 0.11751200258731842,
      "learning_rate": 1e-06,
      "loss": -0.0038,
      "step": 700
    },
    {
      "clip_ratio/high_max": 0.0028118964364693966,
      "clip_ratio/high_mean": 0.0011020062356692506,
      "clip_ratio/low_mean": 0.001395051409417647,
      "clip_ratio/low_min": 7.224008004413918e-05,
      "clip_ratio/region_mean": 0.002497057597793173,
      "epoch": 0.06542650310040891,
      "grad_norm": 0.12057358771562576,
      "learning_rate": 1e-06,
      "loss": 0.011,
      "step": 701
    },
    {
      "clip_ratio/high_max": 0.0026519623934291303,
      "clip_ratio/high_mean": 0.0009300831898144679,
      "clip_ratio/low_mean": 0.0012893246057501528,
      "clip_ratio/low_min": 0.00011676877511490602,
      "clip_ratio/region_mean": 0.002219407819211483,
      "epoch": 0.06551983620040949,
      "grad_norm": 0.11774525791406631,
      "learning_rate": 1e-06,
      "loss": 0.0497,
      "step": 702
    },
    {
      "clip_ratio/high_max": 0.0021846843264938798,
      "clip_ratio/high_mean": 0.0010203428064414766,
      "clip_ratio/low_mean": 0.0010067184284707764,
      "clip_ratio/low_min": 8.176434130291454e-05,
      "clip_ratio/region_mean": 0.0020270612367312424,
      "epoch": 0.06561316930041008,
      "grad_norm": 0.11034981906414032,
      "learning_rate": 1e-06,
      "loss": 0.0131,
      "step": 703
    },
    {
      "clip_ratio/high_max": 0.0022549977802555077,
      "clip_ratio/high_mean": 0.0009660979085310828,
      "clip_ratio/low_mean": 0.0011627740113908658,
      "clip_ratio/low_min": 6.548420788021758e-05,
      "clip_ratio/region_mean": 0.0021288719508447684,
      "epoch": 0.06570650240041066,
      "grad_norm": 0.10844568908214569,
      "learning_rate": 1e-06,
      "loss": -0.0068,
      "step": 704
    },
    {
      "clip_ratio/high_max": 0.002234734653029591,
      "clip_ratio/high_mean": 0.0009234660992660793,
      "clip_ratio/low_mean": 0.001220959147758549,
      "clip_ratio/low_min": 7.287728294613771e-05,
      "clip_ratio/region_mean": 0.0021444251615321264,
      "epoch": 0.06579983550041126,
      "grad_norm": 0.11419650912284851,
      "learning_rate": 1e-06,
      "loss": 0.018,
      "step": 705
    },
    {
      "clip_ratio/high_max": 0.0027125859996885993,
      "clip_ratio/high_mean": 0.0012363481691863853,
      "clip_ratio/low_mean": 0.0011968626245106861,
      "clip_ratio/low_min": 4.00187709601596e-05,
      "clip_ratio/region_mean": 0.002433210793242324,
      "epoch": 0.06589316860041183,
      "grad_norm": 0.12124373763799667,
      "learning_rate": 1e-06,
      "loss": -0.0231,
      "step": 706
    },
    {
      "clip_ratio/high_max": 0.0021565806127910037,
      "clip_ratio/high_mean": 0.0008688764110047487,
      "clip_ratio/low_mean": 0.001272557052288903,
      "clip_ratio/low_min": 0.00012981864165340085,
      "clip_ratio/region_mean": 0.0021414334478322417,
      "epoch": 0.06598650170041241,
      "grad_norm": 0.11262965947389603,
      "learning_rate": 1e-06,
      "loss": 0.0402,
      "step": 707
    },
    {
      "clip_ratio/high_max": 0.002467541169608012,
      "clip_ratio/high_mean": 0.0010572205173957627,
      "clip_ratio/low_mean": 0.0014089090182096697,
      "clip_ratio/low_min": 0.00035368261524126865,
      "clip_ratio/region_mean": 0.002466129466483835,
      "epoch": 0.066079834800413,
      "grad_norm": 0.12729088962078094,
      "learning_rate": 1e-06,
      "loss": 0.0054,
      "step": 708
    },
    {
      "clip_ratio/high_max": 0.002418801268504467,
      "clip_ratio/high_mean": 0.0009145463500317419,
      "clip_ratio/low_mean": 0.0013171310783945955,
      "clip_ratio/low_min": 7.043410187179688e-05,
      "clip_ratio/region_mean": 0.0022316774193313904,
      "epoch": 0.06617316790041358,
      "grad_norm": 0.09995414316654205,
      "learning_rate": 1e-06,
      "loss": 0.0095,
      "step": 709
    },
    {
      "clip_ratio/high_max": 0.0025145779582089745,
      "clip_ratio/high_mean": 0.0010026472591562197,
      "clip_ratio/low_mean": 0.001356084663711954,
      "clip_ratio/low_min": 0.0002667441121957381,
      "clip_ratio/region_mean": 0.0023587318501085974,
      "epoch": 0.06626650100041416,
      "grad_norm": 0.11940798908472061,
      "learning_rate": 1e-06,
      "loss": 0.0368,
      "step": 710
    },
    {
      "clip_ratio/high_max": 0.0022791301998950075,
      "clip_ratio/high_mean": 0.0009585223961039446,
      "clip_ratio/low_mean": 0.0011777116706070956,
      "clip_ratio/low_min": 0.00013839095026924042,
      "clip_ratio/region_mean": 0.0021362340266932733,
      "epoch": 0.06635983410041475,
      "grad_norm": 151.8549041748047,
      "learning_rate": 1e-06,
      "loss": 0.0416,
      "step": 711
    },
    {
      "clip_ratio/high_max": 0.0021692305235774256,
      "clip_ratio/high_mean": 0.0009993428357120138,
      "clip_ratio/low_mean": 0.0011989409795205574,
      "clip_ratio/low_min": 9.363579101773212e-05,
      "clip_ratio/region_mean": 0.0021982838079566136,
      "epoch": 0.06645316720041533,
      "grad_norm": 0.11236035078763962,
      "learning_rate": 1e-06,
      "loss": 0.0267,
      "step": 712
    },
    {
      "clip_ratio/high_max": 0.002412203684798442,
      "clip_ratio/high_mean": 0.0009201784123433754,
      "clip_ratio/low_mean": 0.0011337073246977525,
      "clip_ratio/low_min": 6.704450788674876e-05,
      "clip_ratio/region_mean": 0.002053885742498096,
      "epoch": 0.06654650030041591,
      "grad_norm": 0.1132621169090271,
      "learning_rate": 1e-06,
      "loss": 0.0213,
      "step": 713
    },
    {
      "clip_ratio/high_max": 0.002183757947932463,
      "clip_ratio/high_mean": 0.0009011215606733458,
      "clip_ratio/low_mean": 0.0012254153625690378,
      "clip_ratio/low_min": 0.0001408164571330417,
      "clip_ratio/region_mean": 0.002126536906871479,
      "epoch": 0.0666398334004165,
      "grad_norm": 0.10990343987941742,
      "learning_rate": 1e-06,
      "loss": 0.0238,
      "step": 714
    },
    {
      "clip_ratio/high_max": 0.002301058608281892,
      "clip_ratio/high_mean": 0.0009983988893509377,
      "clip_ratio/low_mean": 0.0011379522002243903,
      "clip_ratio/low_min": 8.526602869096678e-06,
      "clip_ratio/region_mean": 0.002136351089575328,
      "epoch": 0.06673316650041708,
      "grad_norm": 0.13453735411167145,
      "learning_rate": 1e-06,
      "loss": 0.0026,
      "step": 715
    },
    {
      "clip_ratio/high_max": 0.0021830594560015015,
      "clip_ratio/high_mean": 0.0010218853203696199,
      "clip_ratio/low_mean": 0.0011447137821960496,
      "clip_ratio/low_min": 6.446682800742565e-05,
      "clip_ratio/region_mean": 0.0021665990498149768,
      "epoch": 0.06682649960041767,
      "grad_norm": 0.11695725470781326,
      "learning_rate": 1e-06,
      "loss": -0.0051,
      "step": 716
    },
    {
      "clip_ratio/high_max": 0.002474335560691543,
      "clip_ratio/high_mean": 0.00103653740734444,
      "clip_ratio/low_mean": 0.0010922658548224717,
      "clip_ratio/low_min": 0.0001107346124626929,
      "clip_ratio/region_mean": 0.0021288032439770177,
      "epoch": 0.06691983270041825,
      "grad_norm": 0.11490193009376526,
      "learning_rate": 1e-06,
      "loss": -0.0066,
      "step": 717
    },
    {
      "clip_ratio/high_max": 0.002176738973503234,
      "clip_ratio/high_mean": 0.0009673962731540087,
      "clip_ratio/low_mean": 0.00108000465479563,
      "clip_ratio/low_min": 4.1708126445882954e-05,
      "clip_ratio/region_mean": 0.002047400936135091,
      "epoch": 0.06701316580041883,
      "grad_norm": 0.10898280888795853,
      "learning_rate": 1e-06,
      "loss": 0.0141,
      "step": 718
    },
    {
      "clip_ratio/high_max": 0.0019998301613668445,
      "clip_ratio/high_mean": 0.0009073895762412576,
      "clip_ratio/low_mean": 0.0011026247884728946,
      "clip_ratio/low_min": 0.00014411894608201692,
      "clip_ratio/region_mean": 0.002010014337429311,
      "epoch": 0.06710649890041942,
      "grad_norm": 0.09870455414056778,
      "learning_rate": 1e-06,
      "loss": 0.0148,
      "step": 719
    },
    {
      "clip_ratio/high_max": 0.002582363107649144,
      "clip_ratio/high_mean": 0.0010400756054878002,
      "clip_ratio/low_mean": 0.0010733928829722572,
      "clip_ratio/low_min": 6.478199429693632e-05,
      "clip_ratio/region_mean": 0.002113468464813195,
      "epoch": 0.06719983200042,
      "grad_norm": 0.2356414645910263,
      "learning_rate": 1e-06,
      "loss": 0.005,
      "step": 720
    },
    {
      "clip_ratio/high_max": 0.0019777264751610346,
      "clip_ratio/high_mean": 0.0008256175078713568,
      "clip_ratio/low_mean": 0.0013880869464628631,
      "clip_ratio/low_min": 0.00017353309522150084,
      "clip_ratio/region_mean": 0.002213704472524114,
      "epoch": 0.06729316510042058,
      "grad_norm": 0.18862295150756836,
      "learning_rate": 1e-06,
      "loss": 0.0628,
      "step": 721
    },
    {
      "clip_ratio/high_max": 0.0029793506109854206,
      "clip_ratio/high_mean": 0.0012327299737080466,
      "clip_ratio/low_mean": 0.001211147457070183,
      "clip_ratio/low_min": 9.931488511938369e-05,
      "clip_ratio/region_mean": 0.002443877463520039,
      "epoch": 0.06738649820042117,
      "grad_norm": 0.16819368302822113,
      "learning_rate": 1e-06,
      "loss": -0.0074,
      "step": 722
    },
    {
      "clip_ratio/high_max": 0.0021481366857187822,
      "clip_ratio/high_mean": 0.0009157162985502509,
      "clip_ratio/low_mean": 0.001276731598409242,
      "clip_ratio/low_min": 0.0001271406608793768,
      "clip_ratio/region_mean": 0.002192447878769599,
      "epoch": 0.06747983130042175,
      "grad_norm": 0.12451296299695969,
      "learning_rate": 1e-06,
      "loss": 0.0426,
      "step": 723
    },
    {
      "clip_ratio/high_max": 0.0026987026431015693,
      "clip_ratio/high_mean": 0.0010706787634262582,
      "clip_ratio/low_mean": 0.0014110391457506921,
      "clip_ratio/low_min": 0.00010851296519831521,
      "clip_ratio/region_mean": 0.0024817179510137066,
      "epoch": 0.06757316440042234,
      "grad_norm": 0.1136854961514473,
      "learning_rate": 1e-06,
      "loss": 0.041,
      "step": 724
    },
    {
      "clip_ratio/high_max": 0.0028791422737413086,
      "clip_ratio/high_mean": 0.0011597061711654533,
      "clip_ratio/low_mean": 0.0008778686897130683,
      "clip_ratio/low_min": 3.154972364427522e-05,
      "clip_ratio/region_mean": 0.0020375748863443732,
      "epoch": 0.06766649750042292,
      "grad_norm": 0.11603917181491852,
      "learning_rate": 1e-06,
      "loss": -0.0398,
      "step": 725
    },
    {
      "clip_ratio/high_max": 0.002593861492641736,
      "clip_ratio/high_mean": 0.001096424508432392,
      "clip_ratio/low_mean": 0.0013482749855029397,
      "clip_ratio/low_min": 0.000178154088644078,
      "clip_ratio/region_mean": 0.0024446995157632045,
      "epoch": 0.0677598306004235,
      "grad_norm": 0.09812898188829422,
      "learning_rate": 1e-06,
      "loss": -0.0021,
      "step": 726
    },
    {
      "clip_ratio/high_max": 0.0021078989921079483,
      "clip_ratio/high_mean": 0.0008909482312446926,
      "clip_ratio/low_mean": 0.001310424635448726,
      "clip_ratio/low_min": 0.00012902215712529141,
      "clip_ratio/region_mean": 0.0022013729176251218,
      "epoch": 0.06785316370042409,
      "grad_norm": 0.10486070066690445,
      "learning_rate": 1e-06,
      "loss": 0.0471,
      "step": 727
    },
    {
      "clip_ratio/high_max": 0.002501400376786478,
      "clip_ratio/high_mean": 0.0010108197602676228,
      "clip_ratio/low_mean": 0.0011508404641062953,
      "clip_ratio/low_min": 4.1113013139693066e-05,
      "clip_ratio/region_mean": 0.0021616602316498756,
      "epoch": 0.06794649680042467,
      "grad_norm": 0.11481024324893951,
      "learning_rate": 1e-06,
      "loss": 0.0269,
      "step": 728
    },
    {
      "clip_ratio/high_max": 0.0022550193170900457,
      "clip_ratio/high_mean": 0.0008807580161374062,
      "clip_ratio/low_mean": 0.001298228780797217,
      "clip_ratio/low_min": 0.00019226646054448793,
      "clip_ratio/region_mean": 0.002178986818762496,
      "epoch": 0.06803982990042524,
      "grad_norm": 0.23314028978347778,
      "learning_rate": 1e-06,
      "loss": 0.0884,
      "step": 729
    },
    {
      "clip_ratio/high_max": 0.002380192425334826,
      "clip_ratio/high_mean": 0.0009700238533696393,
      "clip_ratio/low_mean": 0.0015136128349695355,
      "clip_ratio/low_min": 0.00022444814658229006,
      "clip_ratio/region_mean": 0.002483636708348058,
      "epoch": 0.06813316300042584,
      "grad_norm": 61.04166793823242,
      "learning_rate": 1e-06,
      "loss": 0.0982,
      "step": 730
    },
    {
      "clip_ratio/high_max": 0.002765322686173022,
      "clip_ratio/high_mean": 0.00109710556716891,
      "clip_ratio/low_mean": 0.0010807329636008944,
      "clip_ratio/low_min": 4.8075104132294655e-05,
      "clip_ratio/region_mean": 0.002177838556235656,
      "epoch": 0.06822649610042641,
      "grad_norm": 0.15944159030914307,
      "learning_rate": 1e-06,
      "loss": -0.0055,
      "step": 731
    },
    {
      "clip_ratio/high_max": 0.0023373873336822726,
      "clip_ratio/high_mean": 0.0009826585719565628,
      "clip_ratio/low_mean": 0.0012317266664467752,
      "clip_ratio/low_min": 0.0001022003070829669,
      "clip_ratio/region_mean": 0.00221438523294637,
      "epoch": 0.06831982920042699,
      "grad_norm": 0.11558610945940018,
      "learning_rate": 1e-06,
      "loss": -0.0066,
      "step": 732
    },
    {
      "clip_ratio/high_max": 0.002130705863237381,
      "clip_ratio/high_mean": 0.0008369657953153364,
      "clip_ratio/low_mean": 0.0014816935399721842,
      "clip_ratio/low_min": 0.0003079702391914907,
      "clip_ratio/region_mean": 0.0023186594116850756,
      "epoch": 0.06841316230042759,
      "grad_norm": 0.11695141345262527,
      "learning_rate": 1e-06,
      "loss": 0.0627,
      "step": 733
    },
    {
      "clip_ratio/high_max": 0.002312582942977315,
      "clip_ratio/high_mean": 0.000989941087027546,
      "clip_ratio/low_mean": 0.0011645044050965225,
      "clip_ratio/low_min": 6.361932901199907e-05,
      "clip_ratio/region_mean": 0.0021544454430113547,
      "epoch": 0.06850649540042816,
      "grad_norm": 0.11236712336540222,
      "learning_rate": 1e-06,
      "loss": 0.0022,
      "step": 734
    },
    {
      "clip_ratio/high_max": 0.0022859539167257026,
      "clip_ratio/high_mean": 0.0009047948169609299,
      "clip_ratio/low_mean": 0.001427615710781538,
      "clip_ratio/low_min": 0.00017723374730849173,
      "clip_ratio/region_mean": 0.002332410542294383,
      "epoch": 0.06859982850042876,
      "grad_norm": 0.12946714460849762,
      "learning_rate": 1e-06,
      "loss": 0.0572,
      "step": 735
    },
    {
      "clip_ratio/high_max": 0.002316066420462448,
      "clip_ratio/high_mean": 0.0009481475117354421,
      "clip_ratio/low_mean": 0.001361851931505953,
      "clip_ratio/low_min": 0.00014957154417061247,
      "clip_ratio/region_mean": 0.0023099995305528864,
      "epoch": 0.06869316160042933,
      "grad_norm": 0.16663967072963715,
      "learning_rate": 1e-06,
      "loss": 0.0439,
      "step": 736
    },
    {
      "clip_ratio/high_max": 0.0024259949277620763,
      "clip_ratio/high_mean": 0.0012105186106055044,
      "clip_ratio/low_mean": 0.000957082309469115,
      "clip_ratio/low_min": 2.9418596568575595e-05,
      "clip_ratio/region_mean": 0.002167600927350577,
      "completions/clipped_ratio": 0.013392857142857095,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4092.0,
      "completions/mean_length": 610.1763916015625,
      "completions/mean_terminated_length": 562.8575439453125,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.06878649470042991,
      "grad_norm": 1901.3165283203125,
      "learning_rate": 1e-06,
      "loss": 55.3028,
      "num_tokens": 570521796.0,
      "reward": 0.5895037055015564,
      "reward_std": 0.19454404711723328,
      "rewards/simpleverify_reward/mean": 0.5895037055015564,
      "rewards/simpleverify_reward/std": 0.49192607402801514,
      "step": 737
    },
    {
      "clip_ratio/high_max": 0.0025185917620547116,
      "clip_ratio/high_mean": 0.001024678191242856,
      "clip_ratio/low_mean": 0.001020813384457142,
      "clip_ratio/low_min": 0.00011270969935139874,
      "clip_ratio/region_mean": 0.002045491579337977,
      "epoch": 0.0688798278004305,
      "grad_norm": 11995.03515625,
      "learning_rate": 1e-06,
      "loss": 13.7257,
      "step": 738
    },
    {
      "clip_ratio/high_max": 0.0022589843574678525,
      "clip_ratio/high_mean": 0.00094279388031282,
      "clip_ratio/low_mean": 0.0010056657629320398,
      "clip_ratio/low_min": 0.00011417547466407996,
      "clip_ratio/region_mean": 0.001948459648701828,
      "epoch": 0.06897316090043108,
      "grad_norm": 458178656.0,
      "learning_rate": 1e-06,
      "loss": 291329.625,
      "step": 739
    },
    {
      "clip_ratio/high_max": 0.002194894078456855,
      "clip_ratio/high_mean": 0.0010231018181912077,
      "clip_ratio/low_mean": 0.0010900486522587016,
      "clip_ratio/low_min": 0.00015250716933223885,
      "clip_ratio/region_mean": 0.0021131505200173706,
      "epoch": 0.06906649400043166,
      "grad_norm": 1.656571388244629,
      "learning_rate": 1e-06,
      "loss": 0.0397,
      "step": 740
    },
    {
      "clip_ratio/high_max": 0.002340232997084968,
      "clip_ratio/high_mean": 0.0010958867460431065,
      "clip_ratio/low_mean": 0.0010355805643484928,
      "clip_ratio/low_min": 8.592584435973549e-05,
      "clip_ratio/region_mean": 0.0021314672922017053,
      "epoch": 0.06915982710043225,
      "grad_norm": 187562.546875,
      "learning_rate": 1e-06,
      "loss": 12.5408,
      "step": 741
    },
    {
      "clip_ratio/high_max": 0.0023647777488804422,
      "clip_ratio/high_mean": 0.0010473912479938008,
      "clip_ratio/low_mean": 0.0010617330631248478,
      "clip_ratio/low_min": 7.926825765025569e-05,
      "clip_ratio/region_mean": 0.0021091242888360284,
      "epoch": 0.06925316020043283,
      "grad_norm": 1575.906005859375,
      "learning_rate": 1e-06,
      "loss": 0.2248,
      "step": 742
    },
    {
      "clip_ratio/high_max": 0.002860847242118325,
      "clip_ratio/high_mean": 0.0010350693119107746,
      "clip_ratio/low_mean": 0.0012349658136372454,
      "clip_ratio/low_min": 0.0001598538774487679,
      "clip_ratio/region_mean": 0.002270035147375893,
      "epoch": 0.06934649330043341,
      "grad_norm": 7.796701431274414,
      "learning_rate": 1e-06,
      "loss": 0.1096,
      "step": 743
    },
    {
      "clip_ratio/high_max": 0.0026164639020862523,
      "clip_ratio/high_mean": 0.001119265049965179,
      "clip_ratio/low_mean": 0.0010607179283397272,
      "clip_ratio/low_min": 0.00013157120520190801,
      "clip_ratio/region_mean": 0.0021799830137751997,
      "epoch": 0.069439826400434,
      "grad_norm": 0.12173054367303848,
      "learning_rate": 1e-06,
      "loss": 0.0333,
      "step": 744
    },
    {
      "clip_ratio/high_max": 0.003021635231561959,
      "clip_ratio/high_mean": 0.0013215109902375843,
      "clip_ratio/low_mean": 0.0010101567841047654,
      "clip_ratio/low_min": 4.712853296950925e-05,
      "clip_ratio/region_mean": 0.0023316678052651696,
      "epoch": 0.06953315950043458,
      "grad_norm": 0.6599025130271912,
      "learning_rate": 1e-06,
      "loss": -0.0099,
      "step": 745
    },
    {
      "clip_ratio/high_max": 0.002587840805063024,
      "clip_ratio/high_mean": 0.0011933927598875016,
      "clip_ratio/low_mean": 0.001061537159330328,
      "clip_ratio/low_min": 0.00014597251538361888,
      "clip_ratio/region_mean": 0.00225492991739884,
      "epoch": 0.06962649260043517,
      "grad_norm": 0.12067849189043045,
      "learning_rate": 1e-06,
      "loss": -0.0214,
      "step": 746
    },
    {
      "clip_ratio/high_max": 0.0024288952190545388,
      "clip_ratio/high_mean": 0.0010250623054162133,
      "clip_ratio/low_mean": 0.0010926186459983,
      "clip_ratio/low_min": 0.0001026450154313352,
      "clip_ratio/region_mean": 0.0021176809823373333,
      "epoch": 0.06971982570043575,
      "grad_norm": 0.37357601523399353,
      "learning_rate": 1e-06,
      "loss": 0.0175,
      "step": 747
    },
    {
      "clip_ratio/high_max": 0.0031707603920949623,
      "clip_ratio/high_mean": 0.0013268662405607756,
      "clip_ratio/low_mean": 0.001109620649003773,
      "clip_ratio/low_min": 9.896720257529523e-05,
      "clip_ratio/region_mean": 0.002436486887745559,
      "epoch": 0.06981315880043633,
      "grad_norm": 0.12083915621042252,
      "learning_rate": 1e-06,
      "loss": 0.0015,
      "step": 748
    },
    {
      "clip_ratio/high_max": 0.002716463914111955,
      "clip_ratio/high_mean": 0.000957385678702849,
      "clip_ratio/low_mean": 0.001219520898303017,
      "clip_ratio/low_min": 8.752021221880568e-05,
      "clip_ratio/region_mean": 0.0021769066152046435,
      "epoch": 0.06990649190043692,
      "grad_norm": 0.1293472945690155,
      "learning_rate": 1e-06,
      "loss": 0.0929,
      "step": 749
    },
    {
      "clip_ratio/high_max": 0.002743180164543446,
      "clip_ratio/high_mean": 0.0010686141868063714,
      "clip_ratio/low_mean": 0.0013260503255878575,
      "clip_ratio/low_min": 5.803081785415998e-05,
      "clip_ratio/region_mean": 0.0023946644432726316,
      "epoch": 0.0699998250004375,
      "grad_norm": 0.10545019805431366,
      "learning_rate": 1e-06,
      "loss": 0.0645,
      "step": 750
    },
    {
      "clip_ratio/high_max": 0.0025358893690281548,
      "clip_ratio/high_mean": 0.0010852183077076916,
      "clip_ratio/low_mean": 0.0012669122552324552,
      "clip_ratio/low_min": 8.182271085388493e-05,
      "clip_ratio/region_mean": 0.0023521305120084435,
      "epoch": 0.07009315810043808,
      "grad_norm": 0.1239662915468216,
      "learning_rate": 1e-06,
      "loss": 0.0092,
      "step": 751
    },
    {
      "clip_ratio/high_max": 0.002627882560773287,
      "clip_ratio/high_mean": 0.001024362791213207,
      "clip_ratio/low_mean": 0.0012412054584274301,
      "clip_ratio/low_min": 9.672793930803891e-05,
      "clip_ratio/region_mean": 0.0022655682187178172,
      "epoch": 0.07018649120043867,
      "grad_norm": 0.13950856029987335,
      "learning_rate": 1e-06,
      "loss": 0.0126,
      "step": 752
    },
    {
      "clip_ratio/high_max": 0.0029165967243898194,
      "clip_ratio/high_mean": 0.00111639602255309,
      "clip_ratio/low_mean": 0.001319195311225485,
      "clip_ratio/low_min": 0.00010080587981065037,
      "clip_ratio/region_mean": 0.002435591391986236,
      "epoch": 0.07027982430043925,
      "grad_norm": 0.22012284398078918,
      "learning_rate": 1e-06,
      "loss": 0.0188,
      "step": 753
    },
    {
      "clip_ratio/high_max": 0.0027905923343496397,
      "clip_ratio/high_mean": 0.001184568762255367,
      "clip_ratio/low_mean": 0.0013675775480805896,
      "clip_ratio/low_min": 9.46670738812827e-05,
      "clip_ratio/region_mean": 0.0025521463321638294,
      "epoch": 0.07037315740043983,
      "grad_norm": 0.2553885281085968,
      "learning_rate": 1e-06,
      "loss": 0.0369,
      "step": 754
    },
    {
      "clip_ratio/high_max": 0.002629054506542161,
      "clip_ratio/high_mean": 0.0011348401567374822,
      "clip_ratio/low_mean": 0.0014029588528501336,
      "clip_ratio/low_min": 4.317703132983297e-05,
      "clip_ratio/region_mean": 0.0025377991260029376,
      "epoch": 0.07046649050044042,
      "grad_norm": 0.11253459751605988,
      "learning_rate": 1e-06,
      "loss": 0.0297,
      "step": 755
    },
    {
      "clip_ratio/high_max": 0.0026100531249539927,
      "clip_ratio/high_mean": 0.0010582643808447756,
      "clip_ratio/low_mean": 0.0013642092417285312,
      "clip_ratio/low_min": 0.00015064558101585135,
      "clip_ratio/region_mean": 0.0024224735680036247,
      "epoch": 0.070559823600441,
      "grad_norm": 0.20744431018829346,
      "learning_rate": 1e-06,
      "loss": 0.0393,
      "step": 756
    },
    {
      "clip_ratio/high_max": 0.0028485467410064302,
      "clip_ratio/high_mean": 0.0012469643152144272,
      "clip_ratio/low_mean": 0.0015671485452912748,
      "clip_ratio/low_min": 0.00010396844572824193,
      "clip_ratio/region_mean": 0.002814112900523469,
      "epoch": 0.07065315670044159,
      "grad_norm": 0.2889653742313385,
      "learning_rate": 1e-06,
      "loss": 0.0215,
      "step": 757
    },
    {
      "clip_ratio/high_max": 0.0028358777635730803,
      "clip_ratio/high_mean": 0.0012443721734598512,
      "clip_ratio/low_mean": 0.0012220137596159475,
      "clip_ratio/low_min": 0.00017459284572396427,
      "clip_ratio/region_mean": 0.0024663859730935656,
      "epoch": 0.07074648980044217,
      "grad_norm": 0.12828651070594788,
      "learning_rate": 1e-06,
      "loss": -0.0126,
      "step": 758
    },
    {
      "clip_ratio/high_max": 0.0025452781628700905,
      "clip_ratio/high_mean": 0.0011796855469583534,
      "clip_ratio/low_mean": 0.0013494804843503516,
      "clip_ratio/low_min": 1.7399777789250948e-05,
      "clip_ratio/region_mean": 0.002529166034946684,
      "epoch": 0.07083982290044274,
      "grad_norm": 0.2257552295923233,
      "learning_rate": 1e-06,
      "loss": -0.0108,
      "step": 759
    },
    {
      "clip_ratio/high_max": 0.002919017497333698,
      "clip_ratio/high_mean": 0.0012375586229609326,
      "clip_ratio/low_mean": 0.0011128117503176327,
      "clip_ratio/low_min": 4.926426299789455e-05,
      "clip_ratio/region_mean": 0.002350370370550081,
      "epoch": 0.07093315600044334,
      "grad_norm": 0.12018465995788574,
      "learning_rate": 1e-06,
      "loss": -0.024,
      "step": 760
    },
    {
      "clip_ratio/high_max": 0.0029345636794460006,
      "clip_ratio/high_mean": 0.001132534132921137,
      "clip_ratio/low_mean": 0.001423005018295953,
      "clip_ratio/low_min": 6.205457702890271e-05,
      "clip_ratio/region_mean": 0.0025555391621310264,
      "epoch": 0.07102648910044392,
      "grad_norm": 0.13740438222885132,
      "learning_rate": 1e-06,
      "loss": 0.0328,
      "step": 761
    },
    {
      "clip_ratio/high_max": 0.002372321981965797,
      "clip_ratio/high_mean": 0.0010106234876730014,
      "clip_ratio/low_mean": 0.0014293776803242508,
      "clip_ratio/low_min": 0.00011450143574620597,
      "clip_ratio/region_mean": 0.0024400011243415065,
      "epoch": 0.0711198222004445,
      "grad_norm": 0.13104663789272308,
      "learning_rate": 1e-06,
      "loss": 0.0532,
      "step": 762
    },
    {
      "clip_ratio/high_max": 0.002375677169766277,
      "clip_ratio/high_mean": 0.0009800430125324056,
      "clip_ratio/low_mean": 0.0015799014654476196,
      "clip_ratio/low_min": 4.874952355748974e-05,
      "clip_ratio/region_mean": 0.0025599445070838556,
      "epoch": 0.07121315530044509,
      "grad_norm": 0.7211567163467407,
      "learning_rate": 1e-06,
      "loss": 0.0282,
      "step": 763
    },
    {
      "clip_ratio/high_max": 0.002381478676397819,
      "clip_ratio/high_mean": 0.0008929906034609303,
      "clip_ratio/low_mean": 0.0019658247110783122,
      "clip_ratio/low_min": 0.00013837007372785592,
      "clip_ratio/region_mean": 0.0028588152999873273,
      "epoch": 0.07130648840044566,
      "grad_norm": 96.26534271240234,
      "learning_rate": 1e-06,
      "loss": 0.0913,
      "step": 764
    },
    {
      "clip_ratio/high_max": 0.0024116245622280985,
      "clip_ratio/high_mean": 0.0009714016705402173,
      "clip_ratio/low_mean": 0.0014594723106711172,
      "clip_ratio/low_min": 0.00010956234382319963,
      "clip_ratio/region_mean": 0.0024308740903506987,
      "epoch": 0.07139982150044624,
      "grad_norm": 0.12967278063297272,
      "learning_rate": 1e-06,
      "loss": 0.0719,
      "step": 765
    },
    {
      "clip_ratio/high_max": 0.0028174537801533006,
      "clip_ratio/high_mean": 0.0010660446296242299,
      "clip_ratio/low_mean": 0.0017296833102591336,
      "clip_ratio/low_min": 0.0003092023334829719,
      "clip_ratio/region_mean": 0.002795727923512459,
      "epoch": 0.07149315460044683,
      "grad_norm": 497.11798095703125,
      "learning_rate": 1e-06,
      "loss": 0.1236,
      "step": 766
    },
    {
      "clip_ratio/high_max": 0.002451124135404825,
      "clip_ratio/high_mean": 0.0010397819241916295,
      "clip_ratio/low_mean": 0.0014246764876588713,
      "clip_ratio/low_min": 0.0001576373515490559,
      "clip_ratio/region_mean": 0.0024644585282658227,
      "epoch": 0.07158648770044741,
      "grad_norm": 0.10416387766599655,
      "learning_rate": 1e-06,
      "loss": 0.0125,
      "step": 767
    },
    {
      "clip_ratio/high_max": 0.0029229553474579006,
      "clip_ratio/high_mean": 0.0010960493018501438,
      "clip_ratio/low_mean": 0.0013133260436006822,
      "clip_ratio/low_min": 0.00013450737151288195,
      "clip_ratio/region_mean": 0.0024093753963825293,
      "epoch": 0.071679820800448,
      "grad_norm": 0.11774514615535736,
      "learning_rate": 1e-06,
      "loss": -0.0233,
      "step": 768
    },
    {
      "clip_ratio/high_max": 0.0026815063756657764,
      "clip_ratio/high_mean": 0.0012512667854025494,
      "clip_ratio/low_mean": 0.0013472000537149142,
      "clip_ratio/low_min": 2.5557144908816554e-05,
      "clip_ratio/region_mean": 0.002598466795461718,
      "epoch": 0.07177315390044858,
      "grad_norm": 0.13921667635440826,
      "learning_rate": 1e-06,
      "loss": -0.0075,
      "step": 769
    },
    {
      "clip_ratio/high_max": 0.004260317735315766,
      "clip_ratio/high_mean": 0.0013174217856430914,
      "clip_ratio/low_mean": 0.0015055412623041775,
      "clip_ratio/low_min": 0.00014331521379062906,
      "clip_ratio/region_mean": 0.0028229629970155656,
      "epoch": 0.07186648700044916,
      "grad_norm": 0.15411517024040222,
      "learning_rate": 1e-06,
      "loss": 0.0181,
      "step": 770
    },
    {
      "clip_ratio/high_max": 0.002614982266095467,
      "clip_ratio/high_mean": 0.0010318012627976714,
      "clip_ratio/low_mean": 0.0013159202098904643,
      "clip_ratio/low_min": 0.00010681984804250533,
      "clip_ratio/region_mean": 0.0023477214708691463,
      "epoch": 0.07195982010044975,
      "grad_norm": 1.2771843671798706,
      "learning_rate": 1e-06,
      "loss": 0.0063,
      "step": 771
    },
    {
      "clip_ratio/high_max": 0.002211797567724716,
      "clip_ratio/high_mean": 0.001017159789626021,
      "clip_ratio/low_mean": 0.0014056354193598963,
      "clip_ratio/low_min": 0.0001349385165667627,
      "clip_ratio/region_mean": 0.002422795172606129,
      "epoch": 0.07205315320045033,
      "grad_norm": 0.11526695638895035,
      "learning_rate": 1e-06,
      "loss": 0.0144,
      "step": 772
    },
    {
      "clip_ratio/high_max": 0.0025003318587550893,
      "clip_ratio/high_mean": 0.0009228111994161736,
      "clip_ratio/low_mean": 0.0013565575682150666,
      "clip_ratio/low_min": 7.00051487001474e-05,
      "clip_ratio/region_mean": 0.002279368774907198,
      "epoch": 0.07214648630045091,
      "grad_norm": 0.3818627893924713,
      "learning_rate": 1e-06,
      "loss": 0.0552,
      "step": 773
    },
    {
      "clip_ratio/high_max": 0.0024978064247989096,
      "clip_ratio/high_mean": 0.0011297078963252716,
      "clip_ratio/low_mean": 0.0014146217872621492,
      "clip_ratio/low_min": 0.0001026806694426341,
      "clip_ratio/region_mean": 0.002544329712691251,
      "epoch": 0.0722398194004515,
      "grad_norm": 0.3097515106201172,
      "learning_rate": 1e-06,
      "loss": -0.0067,
      "step": 774
    },
    {
      "clip_ratio/high_max": 0.0025603243775549345,
      "clip_ratio/high_mean": 0.0010167901345994323,
      "clip_ratio/low_mean": 0.0016238366915786173,
      "clip_ratio/low_min": 0.0001610846957191825,
      "clip_ratio/region_mean": 0.002640626873471774,
      "epoch": 0.07233315250045208,
      "grad_norm": 0.21705465018749237,
      "learning_rate": 1e-06,
      "loss": 0.0081,
      "step": 775
    },
    {
      "clip_ratio/high_max": 0.0023104565625544637,
      "clip_ratio/high_mean": 0.0010679982751753414,
      "clip_ratio/low_mean": 0.0016751723960624076,
      "clip_ratio/low_min": 6.190402200445533e-05,
      "clip_ratio/region_mean": 0.0027431706548668444,
      "epoch": 0.07242648560045266,
      "grad_norm": 0.12319537997245789,
      "learning_rate": 1e-06,
      "loss": 0.0338,
      "step": 776
    },
    {
      "clip_ratio/high_max": 0.002255221043014899,
      "clip_ratio/high_mean": 0.0009452218710066518,
      "clip_ratio/low_mean": 0.0014244780504668597,
      "clip_ratio/low_min": 0.00010671240033843787,
      "clip_ratio/region_mean": 0.002369699941482395,
      "epoch": 0.07251981870045325,
      "grad_norm": 1.0070823431015015,
      "learning_rate": 1e-06,
      "loss": -0.0003,
      "step": 777
    },
    {
      "clip_ratio/high_max": 0.002453761058859527,
      "clip_ratio/high_mean": 0.000986099930742057,
      "clip_ratio/low_mean": 0.0012249174433236476,
      "clip_ratio/low_min": 0.0001155388217739528,
      "clip_ratio/region_mean": 0.0022110174104454927,
      "epoch": 0.07261315180045383,
      "grad_norm": 0.12033914774656296,
      "learning_rate": 1e-06,
      "loss": 0.0436,
      "step": 778
    },
    {
      "clip_ratio/high_max": 0.0027256453977315687,
      "clip_ratio/high_mean": 0.0010520487849134952,
      "clip_ratio/low_mean": 0.001619505444978131,
      "clip_ratio/low_min": 0.00022553786675416632,
      "clip_ratio/region_mean": 0.0026715542189776897,
      "epoch": 0.07270648490045442,
      "grad_norm": 0.12250439077615738,
      "learning_rate": 1e-06,
      "loss": 0.0564,
      "step": 779
    },
    {
      "clip_ratio/high_max": 0.002887733295210637,
      "clip_ratio/high_mean": 0.0011350037711963523,
      "clip_ratio/low_mean": 0.0013143059986759908,
      "clip_ratio/low_min": 0.00012444751882867422,
      "clip_ratio/region_mean": 0.0024493097662343644,
      "epoch": 0.072799818000455,
      "grad_norm": 0.5759520530700684,
      "learning_rate": 1e-06,
      "loss": 0.0125,
      "step": 780
    },
    {
      "clip_ratio/high_max": 0.0029090345196891576,
      "clip_ratio/high_mean": 0.0011424010845075827,
      "clip_ratio/low_mean": 0.0016882859526958782,
      "clip_ratio/low_min": 0.00017925473457580665,
      "clip_ratio/region_mean": 0.002830687000823673,
      "epoch": 0.07289315110045558,
      "grad_norm": 83.99930572509766,
      "learning_rate": 1e-06,
      "loss": 0.8566,
      "step": 781
    },
    {
      "clip_ratio/high_max": 0.0022162762797961477,
      "clip_ratio/high_mean": 0.001064435762600624,
      "clip_ratio/low_mean": 0.0015534348785877228,
      "clip_ratio/low_min": 0.0001091413214453496,
      "clip_ratio/region_mean": 0.002617870683025103,
      "epoch": 0.07298648420045617,
      "grad_norm": 24.931503295898438,
      "learning_rate": 1e-06,
      "loss": 0.0041,
      "step": 782
    },
    {
      "clip_ratio/high_max": 0.0022471648298960645,
      "clip_ratio/high_mean": 0.0008939484578149859,
      "clip_ratio/low_mean": 0.001784996555215912,
      "clip_ratio/low_min": 0.0001075128311640583,
      "clip_ratio/region_mean": 0.0026789450348587707,
      "epoch": 0.07307981730045675,
      "grad_norm": 4.502617835998535,
      "learning_rate": 1e-06,
      "loss": 0.0676,
      "step": 783
    },
    {
      "clip_ratio/high_max": 0.002785466807836201,
      "clip_ratio/high_mean": 0.0010771551606012508,
      "clip_ratio/low_mean": 0.0012221929100633133,
      "clip_ratio/low_min": 0.00016796332602098119,
      "clip_ratio/region_mean": 0.0022993480597506277,
      "epoch": 0.07317315040045733,
      "grad_norm": 0.12705950438976288,
      "learning_rate": 1e-06,
      "loss": 0.0474,
      "step": 784
    },
    {
      "clip_ratio/high_max": 0.0023336016020039096,
      "clip_ratio/high_mean": 0.0010187950792897027,
      "clip_ratio/low_mean": 0.0013977449234516826,
      "clip_ratio/low_min": 0.00021942931198282167,
      "clip_ratio/region_mean": 0.0024165400172933005,
      "epoch": 0.07326648350045792,
      "grad_norm": 3.4466166496276855,
      "learning_rate": 1e-06,
      "loss": 0.0021,
      "step": 785
    },
    {
      "clip_ratio/high_max": 0.0023920931489556096,
      "clip_ratio/high_mean": 0.0009995540422096383,
      "clip_ratio/low_mean": 0.0014322755196189974,
      "clip_ratio/low_min": 0.0001961415673576994,
      "clip_ratio/region_mean": 0.0024318295982084237,
      "epoch": 0.0733598166004585,
      "grad_norm": 8375429.0,
      "learning_rate": 1e-06,
      "loss": 1643.3694,
      "step": 786
    },
    {
      "clip_ratio/high_max": 0.0022965621028561145,
      "clip_ratio/high_mean": 0.0010004942741943523,
      "clip_ratio/low_mean": 0.0015754296036902815,
      "clip_ratio/low_min": 0.0003203391970600933,
      "clip_ratio/region_mean": 0.00257592395064421,
      "epoch": 0.07345314970045909,
      "grad_norm": 0.21115601062774658,
      "learning_rate": 1e-06,
      "loss": 0.044,
      "step": 787
    },
    {
      "clip_ratio/high_max": 0.0022607045466429554,
      "clip_ratio/high_mean": 0.000918513280339539,
      "clip_ratio/low_mean": 0.0014542408353008796,
      "clip_ratio/low_min": 1.2921232155349571e-05,
      "clip_ratio/region_mean": 0.0023727541556581855,
      "epoch": 0.07354648280045967,
      "grad_norm": 47.85354232788086,
      "learning_rate": 1e-06,
      "loss": 0.0244,
      "step": 788
    },
    {
      "clip_ratio/high_max": 0.0024737106941756792,
      "clip_ratio/high_mean": 0.0010195445211138576,
      "clip_ratio/low_mean": 0.0013340751465875655,
      "clip_ratio/low_min": 0.00010331808425689815,
      "clip_ratio/region_mean": 0.0023536196604254656,
      "epoch": 0.07363981590046025,
      "grad_norm": 215.67294311523438,
      "learning_rate": 1e-06,
      "loss": 0.2172,
      "step": 789
    },
    {
      "clip_ratio/high_max": 0.0023018523133941926,
      "clip_ratio/high_mean": 0.001017206803226145,
      "clip_ratio/low_mean": 0.0013939339041826315,
      "clip_ratio/low_min": 0.00019272493318567285,
      "clip_ratio/region_mean": 0.0024111407255986705,
      "epoch": 0.07373314900046084,
      "grad_norm": 0.12516115605831146,
      "learning_rate": 1e-06,
      "loss": 0.0358,
      "step": 790
    },
    {
      "clip_ratio/high_max": 0.002252256228530314,
      "clip_ratio/high_mean": 0.0009084639605134726,
      "clip_ratio/low_mean": 0.0011517660204845015,
      "clip_ratio/low_min": 7.832294795662165e-05,
      "clip_ratio/region_mean": 0.002060229948256165,
      "epoch": 0.07382648210046142,
      "grad_norm": 0.1127663180232048,
      "learning_rate": 1e-06,
      "loss": 0.0354,
      "step": 791
    },
    {
      "clip_ratio/high_max": 0.002542590729717631,
      "clip_ratio/high_mean": 0.0010722878650994971,
      "clip_ratio/low_mean": 0.0013257544924272224,
      "clip_ratio/low_min": 4.888391231361311e-05,
      "clip_ratio/region_mean": 0.0023980423211469315,
      "epoch": 0.073919815200462,
      "grad_norm": 0.0983455628156662,
      "learning_rate": 1e-06,
      "loss": -0.0185,
      "step": 792
    },
    {
      "clip_ratio/high_max": 0.0027854084328282624,
      "clip_ratio/high_mean": 0.001093721828510752,
      "clip_ratio/low_mean": 0.001555481219838839,
      "clip_ratio/low_min": 0.0002449233388688299,
      "clip_ratio/region_mean": 0.0026492030228837393,
      "epoch": 0.07401314830046259,
      "grad_norm": 0.12017360329627991,
      "learning_rate": 1e-06,
      "loss": 0.0532,
      "step": 793
    },
    {
      "clip_ratio/high_max": 0.0026098071502929088,
      "clip_ratio/high_mean": 0.0009595419160177698,
      "clip_ratio/low_mean": 0.0013041621168667916,
      "clip_ratio/low_min": 4.399183399073081e-05,
      "clip_ratio/region_mean": 0.0022637040383415297,
      "epoch": 0.07410648140046316,
      "grad_norm": 0.10721056908369064,
      "learning_rate": 1e-06,
      "loss": 0.0017,
      "step": 794
    },
    {
      "clip_ratio/high_max": 0.0022860275639686733,
      "clip_ratio/high_mean": 0.001027212001645239,
      "clip_ratio/low_mean": 0.0014301472438091878,
      "clip_ratio/low_min": 0.00010816502617672086,
      "clip_ratio/region_mean": 0.002457359281834215,
      "epoch": 0.07419981450046374,
      "grad_norm": 0.111719511449337,
      "learning_rate": 1e-06,
      "loss": 0.0026,
      "step": 795
    },
    {
      "clip_ratio/high_max": 0.002570167423982639,
      "clip_ratio/high_mean": 0.0010109798404300818,
      "clip_ratio/low_mean": 0.0015996165020624176,
      "clip_ratio/low_min": 0.00018007378275797237,
      "clip_ratio/region_mean": 0.0026105962897418067,
      "epoch": 0.07429314760046433,
      "grad_norm": 0.12304951250553131,
      "learning_rate": 1e-06,
      "loss": 0.0082,
      "step": 796
    },
    {
      "clip_ratio/high_max": 0.0025197822105837986,
      "clip_ratio/high_mean": 0.0011801023247244302,
      "clip_ratio/low_mean": 0.0011522752756718546,
      "clip_ratio/low_min": 9.680084076535422e-05,
      "clip_ratio/region_mean": 0.0023323775531025603,
      "epoch": 0.07438648070046491,
      "grad_norm": 0.11943760514259338,
      "learning_rate": 1e-06,
      "loss": -0.0319,
      "step": 797
    },
    {
      "clip_ratio/high_max": 0.0021831479825777933,
      "clip_ratio/high_mean": 0.0010424584634165512,
      "clip_ratio/low_mean": 0.0015146094701776747,
      "clip_ratio/low_min": 0.0001680079658399336,
      "clip_ratio/region_mean": 0.0025570679135853425,
      "epoch": 0.0744798138004655,
      "grad_norm": 0.12011537700891495,
      "learning_rate": 1e-06,
      "loss": 0.0519,
      "step": 798
    },
    {
      "clip_ratio/high_max": 0.002574672755145002,
      "clip_ratio/high_mean": 0.000999525287625147,
      "clip_ratio/low_mean": 0.0013867078923794907,
      "clip_ratio/low_min": 9.164701805275399e-05,
      "clip_ratio/region_mean": 0.002386233158176765,
      "epoch": 0.07457314690046608,
      "grad_norm": 0.1203724592924118,
      "learning_rate": 1e-06,
      "loss": 0.0265,
      "step": 799
    },
    {
      "clip_ratio/high_max": 0.002303191984537989,
      "clip_ratio/high_mean": 0.0009787777307792567,
      "clip_ratio/low_mean": 0.0013409042840066832,
      "clip_ratio/low_min": 8.923406130634248e-05,
      "clip_ratio/region_mean": 0.0023196820038720034,
      "epoch": 0.07466648000046666,
      "grad_norm": 0.1313478797674179,
      "learning_rate": 1e-06,
      "loss": 0.0211,
      "step": 800
    },
    {
      "clip_ratio/high_max": 0.008327030911459588,
      "clip_ratio/high_mean": 0.0036666516316472553,
      "clip_ratio/low_mean": 0.002788988291285932,
      "clip_ratio/low_min": 0.0002465945744916098,
      "clip_ratio/region_mean": 0.006455639857449569,
      "completions/clipped_ratio": 0.013139997209821397,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4064.0,
      "completions/mean_length": 605.9010009765625,
      "completions/mean_terminated_length": 559.430419921875,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.07475981310046725,
      "grad_norm": 101064.3125,
      "learning_rate": 1e-06,
      "loss": 1733865.5,
      "num_tokens": 651537526.0,
      "reward": 0.5855277180671692,
      "reward_std": 0.19071511924266815,
      "rewards/simpleverify_reward/mean": 0.5855277180671692,
      "rewards/simpleverify_reward/std": 0.4926328957080841,
      "step": 801
    },
    {
      "clip_ratio/high_max": 0.0035391675191931427,
      "clip_ratio/high_mean": 0.0014897661749273539,
      "clip_ratio/low_mean": 0.00189780623986735,
      "clip_ratio/low_min": 0.00025063848806894384,
      "clip_ratio/region_mean": 0.003387572374776937,
      "epoch": 0.07485314620046783,
      "grad_norm": 19597.63671875,
      "learning_rate": 1e-06,
      "loss": 7289.4453,
      "step": 802
    },
    {
      "clip_ratio/high_max": 0.002509581536287442,
      "clip_ratio/high_mean": 0.0011021544814866502,
      "clip_ratio/low_mean": 0.001305746194702806,
      "clip_ratio/low_min": 6.73087697578012e-05,
      "clip_ratio/region_mean": 0.0024079006907413714,
      "epoch": 0.07494647930046841,
      "grad_norm": 23015.837890625,
      "learning_rate": 1e-06,
      "loss": 5.4413,
      "step": 803
    },
    {
      "clip_ratio/high_max": 0.002721167569688987,
      "clip_ratio/high_mean": 0.0011376955735613592,
      "clip_ratio/low_mean": 0.0014100532171141822,
      "clip_ratio/low_min": 0.00012447980952856597,
      "clip_ratio/region_mean": 0.0025477488597971387,
      "epoch": 0.075039812400469,
      "grad_norm": 0.4986385107040405,
      "learning_rate": 1e-06,
      "loss": 0.0291,
      "step": 804
    },
    {
      "clip_ratio/high_max": 0.0027081956941401586,
      "clip_ratio/high_mean": 0.0010714517775340937,
      "clip_ratio/low_mean": 0.0011555775909073418,
      "clip_ratio/low_min": 8.060287655098364e-05,
      "clip_ratio/region_mean": 0.0022270293193287216,
      "epoch": 0.07513314550046958,
      "grad_norm": 0.12783238291740417,
      "learning_rate": 1e-06,
      "loss": 0.038,
      "step": 805
    },
    {
      "clip_ratio/high_max": 0.002583015761047136,
      "clip_ratio/high_mean": 0.0010607417025312316,
      "clip_ratio/low_mean": 0.0012262309246580116,
      "clip_ratio/low_min": 0.0001517219661764102,
      "clip_ratio/region_mean": 0.0022869726381031796,
      "epoch": 0.07522647860047016,
      "grad_norm": 33.71275329589844,
      "learning_rate": 1e-06,
      "loss": 0.1202,
      "step": 806
    },
    {
      "clip_ratio/high_max": 0.002716500141104916,
      "clip_ratio/high_mean": 0.0010896660460275598,
      "clip_ratio/low_mean": 0.0012519440861069597,
      "clip_ratio/low_min": 0.00012644107846426778,
      "clip_ratio/region_mean": 0.0023416101685143076,
      "epoch": 0.07531981170047075,
      "grad_norm": 69.53738403320312,
      "learning_rate": 1e-06,
      "loss": 0.0335,
      "step": 807
    },
    {
      "clip_ratio/high_max": 0.0027018263426725753,
      "clip_ratio/high_mean": 0.001221783459186554,
      "clip_ratio/low_mean": 0.0010398273025202798,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002261610767163802,
      "epoch": 0.07541314480047133,
      "grad_norm": 0.14749875664710999,
      "learning_rate": 1e-06,
      "loss": -0.0101,
      "step": 808
    },
    {
      "clip_ratio/high_max": 0.00294557467350387,
      "clip_ratio/high_mean": 0.0012184558254375588,
      "clip_ratio/low_mean": 0.0014991872558312025,
      "clip_ratio/low_min": 5.789188253402244e-05,
      "clip_ratio/region_mean": 0.002717643088544719,
      "epoch": 0.07550647790047192,
      "grad_norm": 1811309.125,
      "learning_rate": 1e-06,
      "loss": 249.5219,
      "step": 809
    },
    {
      "clip_ratio/high_max": 0.002644067702931352,
      "clip_ratio/high_mean": 0.0011352808687661309,
      "clip_ratio/low_mean": 0.0013471494676196016,
      "clip_ratio/low_min": 0.00022321876895148307,
      "clip_ratio/region_mean": 0.0024824303327477537,
      "epoch": 0.0755998110004725,
      "grad_norm": 55.80194091796875,
      "learning_rate": 1e-06,
      "loss": 0.0318,
      "step": 810
    },
    {
      "clip_ratio/high_max": 0.0026288292938261293,
      "clip_ratio/high_mean": 0.0010290294430888025,
      "clip_ratio/low_mean": 0.0014469246525550261,
      "clip_ratio/low_min": 7.32876205802313e-05,
      "clip_ratio/region_mean": 0.002475954075634945,
      "epoch": 0.07569314410047308,
      "grad_norm": 1.3655775785446167,
      "learning_rate": 1e-06,
      "loss": 0.0674,
      "step": 811
    },
    {
      "clip_ratio/high_max": 0.002630128357850481,
      "clip_ratio/high_mean": 0.001060525046341354,
      "clip_ratio/low_mean": 0.001312859483732609,
      "clip_ratio/low_min": 0.0001577770426592906,
      "clip_ratio/region_mean": 0.002373384493694175,
      "epoch": 0.07578647720047367,
      "grad_norm": 1.169458031654358,
      "learning_rate": 1e-06,
      "loss": 0.0438,
      "step": 812
    },
    {
      "clip_ratio/high_max": 0.002709727705223486,
      "clip_ratio/high_mean": 0.0011132797808386385,
      "clip_ratio/low_mean": 0.0013109297105984297,
      "clip_ratio/low_min": 0.00010995767479471397,
      "clip_ratio/region_mean": 0.0024242095387307927,
      "epoch": 0.07587981030047425,
      "grad_norm": 0.12129896134138107,
      "learning_rate": 1e-06,
      "loss": 0.0113,
      "step": 813
    },
    {
      "clip_ratio/high_max": 0.0026854495008592494,
      "clip_ratio/high_mean": 0.0011012501836376032,
      "clip_ratio/low_mean": 0.001404240909323562,
      "clip_ratio/low_min": 0.00014764164734515361,
      "clip_ratio/region_mean": 0.0025054911166080274,
      "epoch": 0.07597314340047483,
      "grad_norm": 0.2171059250831604,
      "learning_rate": 1e-06,
      "loss": 0.0551,
      "step": 814
    },
    {
      "clip_ratio/high_max": 0.002810167999996338,
      "clip_ratio/high_mean": 0.0011666692116705235,
      "clip_ratio/low_mean": 0.0014704880968565703,
      "clip_ratio/low_min": 0.00014680441290693125,
      "clip_ratio/region_mean": 0.0026371573185315356,
      "epoch": 0.07606647650047542,
      "grad_norm": 0.165121927857399,
      "learning_rate": 1e-06,
      "loss": 0.0491,
      "step": 815
    },
    {
      "clip_ratio/high_max": 0.0034815813341992907,
      "clip_ratio/high_mean": 0.0013558651589846704,
      "clip_ratio/low_mean": 0.001244781360583147,
      "clip_ratio/low_min": 8.153441740432754e-05,
      "clip_ratio/region_mean": 0.0026006465195678174,
      "epoch": 0.076159809600476,
      "grad_norm": 0.1426796317100525,
      "learning_rate": 1e-06,
      "loss": -0.047,
      "step": 816
    },
    {
      "clip_ratio/high_max": 0.0026250017108395696,
      "clip_ratio/high_mean": 0.0011445680211181752,
      "clip_ratio/low_mean": 0.0012474640061554965,
      "clip_ratio/low_min": 0.00010768878382805269,
      "clip_ratio/region_mean": 0.002392031987255905,
      "epoch": 0.07625314270047658,
      "grad_norm": 0.14920775592327118,
      "learning_rate": 1e-06,
      "loss": 0.0132,
      "step": 817
    },
    {
      "clip_ratio/high_max": 0.002687466454517562,
      "clip_ratio/high_mean": 0.0011310209883959033,
      "clip_ratio/low_mean": 0.001391334462823579,
      "clip_ratio/low_min": 0.00012124189561291132,
      "clip_ratio/region_mean": 0.0025223554475815035,
      "epoch": 0.07634647580047717,
      "grad_norm": 0.10995069146156311,
      "learning_rate": 1e-06,
      "loss": 0.0018,
      "step": 818
    },
    {
      "clip_ratio/high_max": 0.002700510769500397,
      "clip_ratio/high_mean": 0.0009833559070102638,
      "clip_ratio/low_mean": 0.001493043004302308,
      "clip_ratio/low_min": 5.635131128656212e-05,
      "clip_ratio/region_mean": 0.0024763989058556035,
      "epoch": 0.07643980890047775,
      "grad_norm": 0.1840856671333313,
      "learning_rate": 1e-06,
      "loss": 0.0847,
      "step": 819
    },
    {
      "clip_ratio/high_max": 0.0029620448403875344,
      "clip_ratio/high_mean": 0.001259825916349655,
      "clip_ratio/low_mean": 0.0013704102639167104,
      "clip_ratio/low_min": 3.171020762238186e-05,
      "clip_ratio/region_mean": 0.0026302362311980687,
      "epoch": 0.07653314200047834,
      "grad_norm": 0.14069418609142303,
      "learning_rate": 1e-06,
      "loss": -0.0035,
      "step": 820
    },
    {
      "clip_ratio/high_max": 0.0025293509315815754,
      "clip_ratio/high_mean": 0.001065507911334862,
      "clip_ratio/low_mean": 0.0012286804376344662,
      "clip_ratio/low_min": 6.277704142121365e-05,
      "clip_ratio/region_mean": 0.0022941883289604448,
      "epoch": 0.07662647510047892,
      "grad_norm": 0.11177564412355423,
      "learning_rate": 1e-06,
      "loss": 0.0459,
      "step": 821
    },
    {
      "clip_ratio/high_max": 0.0022356047338689677,
      "clip_ratio/high_mean": 0.0010488571224414045,
      "clip_ratio/low_mean": 0.0014486389045487158,
      "clip_ratio/low_min": 0.00027421891172707547,
      "clip_ratio/region_mean": 0.0024974959524115548,
      "epoch": 0.0767198082004795,
      "grad_norm": 0.7017294764518738,
      "learning_rate": 1e-06,
      "loss": 0.0433,
      "step": 822
    },
    {
      "clip_ratio/high_max": 0.0027817498448712286,
      "clip_ratio/high_mean": 0.0011642079134617234,
      "clip_ratio/low_mean": 0.001469093287596479,
      "clip_ratio/low_min": 9.905035858537303e-05,
      "clip_ratio/region_mean": 0.002633301235619001,
      "epoch": 0.07681314130048009,
      "grad_norm": 32.07141876220703,
      "learning_rate": 1e-06,
      "loss": 0.0499,
      "step": 823
    },
    {
      "clip_ratio/high_max": 0.0024185820075217634,
      "clip_ratio/high_mean": 0.0010990880546160042,
      "clip_ratio/low_mean": 0.0013953841153124813,
      "clip_ratio/low_min": 0.0001409956985298777,
      "clip_ratio/region_mean": 0.002494472180842422,
      "epoch": 0.07690647440048066,
      "grad_norm": 0.13829414546489716,
      "learning_rate": 1e-06,
      "loss": 0.0312,
      "step": 824
    },
    {
      "clip_ratio/high_max": 0.00220758964860579,
      "clip_ratio/high_mean": 0.0010455196133989375,
      "clip_ratio/low_mean": 0.0016037230016081594,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002649242691404652,
      "epoch": 0.07699980750048124,
      "grad_norm": 0.35364866256713867,
      "learning_rate": 1e-06,
      "loss": 0.0271,
      "step": 825
    },
    {
      "clip_ratio/high_max": 0.002517393382731825,
      "clip_ratio/high_mean": 0.0010453175491420552,
      "clip_ratio/low_mean": 0.0015536792861894355,
      "clip_ratio/low_min": 0.00026197274837613804,
      "clip_ratio/region_mean": 0.002598996870801784,
      "epoch": 0.07709314060048184,
      "grad_norm": 1.539804220199585,
      "learning_rate": 1e-06,
      "loss": 0.0404,
      "step": 826
    },
    {
      "clip_ratio/high_max": 0.002512122860935051,
      "clip_ratio/high_mean": 0.0009638931824156316,
      "clip_ratio/low_mean": 0.0013821202337567229,
      "clip_ratio/low_min": 0.0001671765585342655,
      "clip_ratio/region_mean": 0.002346013432543259,
      "epoch": 0.07718647370048241,
      "grad_norm": 0.10920978337526321,
      "learning_rate": 1e-06,
      "loss": 0.0172,
      "step": 827
    },
    {
      "clip_ratio/high_max": 0.0025429152592550963,
      "clip_ratio/high_mean": 0.0011168379787704907,
      "clip_ratio/low_mean": 0.0011847098503494635,
      "clip_ratio/low_min": 1.5111218999663834e-05,
      "clip_ratio/region_mean": 0.002301547836395912,
      "epoch": 0.07727980680048299,
      "grad_norm": 6.9402337074279785,
      "learning_rate": 1e-06,
      "loss": 0.014,
      "step": 828
    },
    {
      "clip_ratio/high_max": 0.002954852840048261,
      "clip_ratio/high_mean": 0.0012403167311276775,
      "clip_ratio/low_mean": 0.001396391066009528,
      "clip_ratio/low_min": 0.000214487326957169,
      "clip_ratio/region_mean": 0.0026367077734903432,
      "epoch": 0.07737313990048358,
      "grad_norm": 0.11157985031604767,
      "learning_rate": 1e-06,
      "loss": -0.0154,
      "step": 829
    },
    {
      "clip_ratio/high_max": 0.002259429445985006,
      "clip_ratio/high_mean": 0.0009761795172380516,
      "clip_ratio/low_mean": 0.0015210828241833951,
      "clip_ratio/low_min": 1.156122834800044e-05,
      "clip_ratio/region_mean": 0.002497262386896182,
      "epoch": 0.07746647300048416,
      "grad_norm": 0.12391701340675354,
      "learning_rate": 1e-06,
      "loss": -0.0,
      "step": 830
    },
    {
      "clip_ratio/high_max": 0.0029618892367579974,
      "clip_ratio/high_mean": 0.001162765456683701,
      "clip_ratio/low_mean": 0.0018380040055490099,
      "clip_ratio/low_min": 4.736358823720366e-05,
      "clip_ratio/region_mean": 0.003000769480422605,
      "epoch": 0.07755980610048475,
      "grad_norm": 0.6005366444587708,
      "learning_rate": 1e-06,
      "loss": 0.0438,
      "step": 831
    },
    {
      "clip_ratio/high_max": 0.002424318459816277,
      "clip_ratio/high_mean": 0.0009576944721629843,
      "clip_ratio/low_mean": 0.0013155195047147572,
      "clip_ratio/low_min": 0.00012579851136251818,
      "clip_ratio/region_mean": 0.002273214020533487,
      "epoch": 0.07765313920048533,
      "grad_norm": 0.09429342299699783,
      "learning_rate": 1e-06,
      "loss": 0.0149,
      "step": 832
    },
    {
      "clip_ratio/high_max": 0.0026715394415077753,
      "clip_ratio/high_mean": 0.0010084235873364378,
      "clip_ratio/low_mean": 0.001314596220254316,
      "clip_ratio/low_min": 0.00011282059494988061,
      "clip_ratio/region_mean": 0.002323019791219849,
      "epoch": 0.07774647230048591,
      "grad_norm": 0.10347605496644974,
      "learning_rate": 1e-06,
      "loss": 0.0141,
      "step": 833
    },
    {
      "clip_ratio/high_max": 0.0024801087674859446,
      "clip_ratio/high_mean": 0.0009608512318663998,
      "clip_ratio/low_mean": 0.0013840262654412072,
      "clip_ratio/low_min": 9.610293000150705e-05,
      "clip_ratio/region_mean": 0.002344877430004999,
      "epoch": 0.0778398054004865,
      "grad_norm": 0.0953790545463562,
      "learning_rate": 1e-06,
      "loss": 0.0427,
      "step": 834
    },
    {
      "clip_ratio/high_max": 0.0029015839827479795,
      "clip_ratio/high_mean": 0.0010931900651485194,
      "clip_ratio/low_mean": 0.001293820434511872,
      "clip_ratio/low_min": 8.856584463501349e-05,
      "clip_ratio/region_mean": 0.002387010506936349,
      "epoch": 0.07793313850048708,
      "grad_norm": 0.11080574244260788,
      "learning_rate": 1e-06,
      "loss": -0.0247,
      "step": 835
    },
    {
      "clip_ratio/high_max": 0.0023929066155687906,
      "clip_ratio/high_mean": 0.001115258888603421,
      "clip_ratio/low_mean": 0.0014133512413536664,
      "clip_ratio/low_min": 6.461722387030022e-05,
      "clip_ratio/region_mean": 0.002528610159060918,
      "epoch": 0.07802647160048766,
      "grad_norm": 0.1153893694281578,
      "learning_rate": 1e-06,
      "loss": -0.0209,
      "step": 836
    },
    {
      "clip_ratio/high_max": 0.0022937074827495962,
      "clip_ratio/high_mean": 0.0010396977222626447,
      "clip_ratio/low_mean": 0.0012711027175100753,
      "clip_ratio/low_min": 3.580635893740691e-05,
      "clip_ratio/region_mean": 0.002310800460691098,
      "epoch": 0.07811980470048825,
      "grad_norm": 41.6697998046875,
      "learning_rate": 1e-06,
      "loss": 0.0717,
      "step": 837
    },
    {
      "clip_ratio/high_max": 0.002025997415330494,
      "clip_ratio/high_mean": 0.0008962771662481828,
      "clip_ratio/low_mean": 0.0011883129209309118,
      "clip_ratio/low_min": 1.5747040379210375e-05,
      "clip_ratio/region_mean": 0.002084590116282925,
      "epoch": 0.07821313780048883,
      "grad_norm": 0.1756000518798828,
      "learning_rate": 1e-06,
      "loss": 1.6431,
      "step": 838
    },
    {
      "clip_ratio/high_max": 0.0022138013337098528,
      "clip_ratio/high_mean": 0.0010341593697376084,
      "clip_ratio/low_mean": 0.0013606284592242446,
      "clip_ratio/low_min": 9.632536603021435e-05,
      "clip_ratio/region_mean": 0.002394787887169514,
      "epoch": 0.07830647090048942,
      "grad_norm": 0.247129425406456,
      "learning_rate": 1e-06,
      "loss": 0.0188,
      "step": 839
    },
    {
      "clip_ratio/high_max": 0.00232323283853475,
      "clip_ratio/high_mean": 0.0009981944422179367,
      "clip_ratio/low_mean": 0.0011628296851995401,
      "clip_ratio/low_min": 2.7746948035201058e-05,
      "clip_ratio/region_mean": 0.002161024145607371,
      "epoch": 0.07839980400049,
      "grad_norm": 0.10771391540765762,
      "learning_rate": 1e-06,
      "loss": 0.0204,
      "step": 840
    },
    {
      "clip_ratio/high_max": 0.0023740843244013377,
      "clip_ratio/high_mean": 0.0009991943079512566,
      "clip_ratio/low_mean": 0.0015144946592045017,
      "clip_ratio/low_min": 0.00012666471229749732,
      "clip_ratio/region_mean": 0.002513689032639377,
      "epoch": 0.07849313710049058,
      "grad_norm": 0.14446231722831726,
      "learning_rate": 1e-06,
      "loss": 0.0265,
      "step": 841
    },
    {
      "clip_ratio/high_max": 0.0024020333694352303,
      "clip_ratio/high_mean": 0.0009544108434056398,
      "clip_ratio/low_mean": 0.0013701232019229792,
      "clip_ratio/low_min": 5.891822092962684e-05,
      "clip_ratio/region_mean": 0.002324534085346386,
      "epoch": 0.07858647020049117,
      "grad_norm": 0.12900720536708832,
      "learning_rate": 1e-06,
      "loss": 0.0359,
      "step": 842
    },
    {
      "clip_ratio/high_max": 0.002759324728685897,
      "clip_ratio/high_mean": 0.001045010121742962,
      "clip_ratio/low_mean": 0.00148967353743501,
      "clip_ratio/low_min": 0.0001977697011170676,
      "clip_ratio/region_mean": 0.002534683677367866,
      "epoch": 0.07867980330049175,
      "grad_norm": 0.11388585716485977,
      "learning_rate": 1e-06,
      "loss": 0.0138,
      "step": 843
    },
    {
      "clip_ratio/high_max": 0.0022038313472876325,
      "clip_ratio/high_mean": 0.001007417988148518,
      "clip_ratio/low_mean": 0.001209892718179617,
      "clip_ratio/low_min": 9.760590819496429e-05,
      "clip_ratio/region_mean": 0.0022173106990521774,
      "epoch": 0.07877313640049233,
      "grad_norm": 0.13638710975646973,
      "learning_rate": 1e-06,
      "loss": -0.0179,
      "step": 844
    },
    {
      "clip_ratio/high_max": 0.0021493658314284403,
      "clip_ratio/high_mean": 0.0009132369596045464,
      "clip_ratio/low_mean": 0.0011534922778082546,
      "clip_ratio/low_min": 8.425274245382752e-05,
      "clip_ratio/region_mean": 0.0020667292701546103,
      "epoch": 0.07886646950049292,
      "grad_norm": 0.10076100379228592,
      "learning_rate": 1e-06,
      "loss": 0.0396,
      "step": 845
    },
    {
      "clip_ratio/high_max": 0.0025229732418665662,
      "clip_ratio/high_mean": 0.0010883177965297364,
      "clip_ratio/low_mean": 0.001250967357918853,
      "clip_ratio/low_min": 0.00013781040979665704,
      "clip_ratio/region_mean": 0.0023392851362586953,
      "epoch": 0.0789598026004935,
      "grad_norm": 0.11551445722579956,
      "learning_rate": 1e-06,
      "loss": 0.0064,
      "step": 846
    },
    {
      "clip_ratio/high_max": 0.0023669461043027695,
      "clip_ratio/high_mean": 0.0009316054456576239,
      "clip_ratio/low_mean": 0.0012426102512108628,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002174215725972317,
      "epoch": 0.07905313570049408,
      "grad_norm": 0.11276073008775711,
      "learning_rate": 1e-06,
      "loss": 0.0209,
      "step": 847
    },
    {
      "clip_ratio/high_max": 0.002016357317188522,
      "clip_ratio/high_mean": 0.0008894437523849774,
      "clip_ratio/low_mean": 0.0014651426463387907,
      "clip_ratio/low_min": 4.2508221667958423e-05,
      "clip_ratio/region_mean": 0.002354586438741535,
      "epoch": 0.07914646880049467,
      "grad_norm": 0.1048005074262619,
      "learning_rate": 1e-06,
      "loss": 0.052,
      "step": 848
    },
    {
      "clip_ratio/high_max": 0.0025408468427485786,
      "clip_ratio/high_mean": 0.001019345876557054,
      "clip_ratio/low_mean": 0.0014447482353716623,
      "clip_ratio/low_min": 7.6112450187793e-05,
      "clip_ratio/region_mean": 0.002464094097376801,
      "epoch": 0.07923980190049525,
      "grad_norm": 0.1779157817363739,
      "learning_rate": 1e-06,
      "loss": 0.017,
      "step": 849
    },
    {
      "clip_ratio/high_max": 0.0025285063311457634,
      "clip_ratio/high_mean": 0.0010080963365908246,
      "clip_ratio/low_mean": 0.0011521328415255994,
      "clip_ratio/low_min": 5.75060412302264e-05,
      "clip_ratio/region_mean": 0.0021602292472380213,
      "epoch": 0.07933313500049584,
      "grad_norm": 0.1164686307311058,
      "learning_rate": 1e-06,
      "loss": 0.0365,
      "step": 850
    },
    {
      "clip_ratio/high_max": 0.002545826879213564,
      "clip_ratio/high_mean": 0.0011510423755680677,
      "clip_ratio/low_mean": 0.00121481356836739,
      "clip_ratio/low_min": 0.00014498043037747266,
      "clip_ratio/region_mean": 0.0023658558930037543,
      "epoch": 0.07942646810049642,
      "grad_norm": 0.10660649091005325,
      "learning_rate": 1e-06,
      "loss": -0.0008,
      "step": 851
    },
    {
      "clip_ratio/high_max": 0.002732219531026203,
      "clip_ratio/high_mean": 0.0011672659693431342,
      "clip_ratio/low_mean": 0.0013485058007063344,
      "clip_ratio/low_min": 0.00011175960844411748,
      "clip_ratio/region_mean": 0.002515771753678564,
      "epoch": 0.079519801200497,
      "grad_norm": 0.14384303987026215,
      "learning_rate": 1e-06,
      "loss": -0.0027,
      "step": 852
    },
    {
      "clip_ratio/high_max": 0.002412931527942419,
      "clip_ratio/high_mean": 0.000984912263447768,
      "clip_ratio/low_mean": 0.001190990034956485,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0021759023074992,
      "epoch": 0.07961313430049759,
      "grad_norm": 0.2093774378299713,
      "learning_rate": 1e-06,
      "loss": 0.0394,
      "step": 853
    },
    {
      "clip_ratio/high_max": 0.0021997795774950646,
      "clip_ratio/high_mean": 0.0008447825930488762,
      "clip_ratio/low_mean": 0.0010668647373677231,
      "clip_ratio/low_min": 5.8082654504687525e-05,
      "clip_ratio/region_mean": 0.0019116473049507476,
      "epoch": 0.07970646740049817,
      "grad_norm": 0.10855469107627869,
      "learning_rate": 1e-06,
      "loss": 0.0238,
      "step": 854
    },
    {
      "clip_ratio/high_max": 0.0021874937920074444,
      "clip_ratio/high_mean": 0.0008731650068511954,
      "clip_ratio/low_mean": 0.0013044651514064753,
      "clip_ratio/low_min": 0.0001932637478603283,
      "clip_ratio/region_mean": 0.0021776301946374588,
      "epoch": 0.07979980050049874,
      "grad_norm": 0.12426037341356277,
      "learning_rate": 1e-06,
      "loss": 0.0225,
      "step": 855
    },
    {
      "clip_ratio/high_max": 0.0026216671540169045,
      "clip_ratio/high_mean": 0.0009840668353717774,
      "clip_ratio/low_mean": 0.001274728088901611,
      "clip_ratio/low_min": 0.00019591110958572244,
      "clip_ratio/region_mean": 0.0022587949206354097,
      "epoch": 0.07989313360049934,
      "grad_norm": 0.12642495334148407,
      "learning_rate": 1e-06,
      "loss": 0.0216,
      "step": 856
    },
    {
      "clip_ratio/high_max": 0.002338920116017107,
      "clip_ratio/high_mean": 0.0009410486327396939,
      "clip_ratio/low_mean": 0.0012541345859062858,
      "clip_ratio/low_min": 6.535313696076628e-05,
      "clip_ratio/region_mean": 0.00219518318772316,
      "epoch": 0.07998646670049991,
      "grad_norm": 0.11876281350851059,
      "learning_rate": 1e-06,
      "loss": 0.0316,
      "step": 857
    },
    {
      "clip_ratio/high_max": 0.0022746940376237035,
      "clip_ratio/high_mean": 0.0010265095697832294,
      "clip_ratio/low_mean": 0.0011364503880031407,
      "clip_ratio/low_min": 6.768035109416815e-05,
      "clip_ratio/region_mean": 0.002162959979614243,
      "epoch": 0.08007979980050049,
      "grad_norm": 0.30983495712280273,
      "learning_rate": 1e-06,
      "loss": -0.0163,
      "step": 858
    },
    {
      "clip_ratio/high_max": 0.0020234958465152886,
      "clip_ratio/high_mean": 0.0009981917828554288,
      "clip_ratio/low_mean": 0.0012964901616214775,
      "clip_ratio/low_min": 0.00011418876238167286,
      "clip_ratio/region_mean": 0.0022946819008211605,
      "epoch": 0.08017313290050108,
      "grad_norm": 0.16812914609909058,
      "learning_rate": 1e-06,
      "loss": 0.0122,
      "step": 859
    },
    {
      "clip_ratio/high_max": 0.0021906105321249925,
      "clip_ratio/high_mean": 0.00092416816187324,
      "clip_ratio/low_mean": 0.0013499877786671277,
      "clip_ratio/low_min": 0.00013236531958682463,
      "clip_ratio/region_mean": 0.0022741559296264313,
      "epoch": 0.08026646600050166,
      "grad_norm": 0.10505940020084381,
      "learning_rate": 1e-06,
      "loss": 0.0525,
      "step": 860
    },
    {
      "clip_ratio/high_max": 0.0021604920984827913,
      "clip_ratio/high_mean": 0.0008747429728828138,
      "clip_ratio/low_mean": 0.001236018375493586,
      "clip_ratio/low_min": 6.750577631464694e-05,
      "clip_ratio/region_mean": 0.0021107612919877283,
      "epoch": 0.08035979910050225,
      "grad_norm": 0.11796213686466217,
      "learning_rate": 1e-06,
      "loss": 0.0107,
      "step": 861
    },
    {
      "clip_ratio/high_max": 0.0022350820872816257,
      "clip_ratio/high_mean": 0.0009030160654219799,
      "clip_ratio/low_mean": 0.001405017279466847,
      "clip_ratio/low_min": 0.0001911307881528046,
      "clip_ratio/region_mean": 0.002308033363078721,
      "epoch": 0.08045313220050283,
      "grad_norm": 0.12946298718452454,
      "learning_rate": 1e-06,
      "loss": 0.06,
      "step": 862
    },
    {
      "clip_ratio/high_max": 0.0022636927678831853,
      "clip_ratio/high_mean": 0.0009499923035036772,
      "clip_ratio/low_mean": 0.001223393981490517,
      "clip_ratio/low_min": 4.709288350568386e-05,
      "clip_ratio/region_mean": 0.0021733862449764274,
      "epoch": 0.08054646530050341,
      "grad_norm": 0.11522744596004486,
      "learning_rate": 1e-06,
      "loss": -0.0019,
      "step": 863
    },
    {
      "clip_ratio/high_max": 0.002344078846363118,
      "clip_ratio/high_mean": 0.0010036355979536893,
      "clip_ratio/low_mean": 0.0011440496382419951,
      "clip_ratio/low_min": 0.00010483691221452318,
      "clip_ratio/region_mean": 0.002147685234376695,
      "epoch": 0.080639798400504,
      "grad_norm": 0.10673494637012482,
      "learning_rate": 1e-06,
      "loss": -0.0162,
      "step": 864
    },
    {
      "clip_ratio/high_max": 0.001942062302987324,
      "clip_ratio/high_mean": 0.0008828175168673624,
      "clip_ratio/low_mean": 0.001247084503120277,
      "clip_ratio/low_min": 9.555863107379992e-05,
      "clip_ratio/region_mean": 0.0021299020008882508,
      "epoch": 0.08073313150050458,
      "grad_norm": 0.11050200462341309,
      "learning_rate": 1e-06,
      "loss": 0.0402,
      "step": 865
    },
    {
      "clip_ratio/high_max": 0.0023977595774340443,
      "clip_ratio/high_mean": 0.0009578078825143166,
      "clip_ratio/low_mean": 0.0013287999026942998,
      "clip_ratio/low_min": 6.0110775848443154e-05,
      "clip_ratio/region_mean": 0.002286607770656701,
      "epoch": 0.08082646460050516,
      "grad_norm": 0.11569397896528244,
      "learning_rate": 1e-06,
      "loss": 0.0594,
      "step": 866
    },
    {
      "clip_ratio/high_max": 0.002359185309614986,
      "clip_ratio/high_mean": 0.00098547071320354,
      "clip_ratio/low_mean": 0.0012392127791827079,
      "clip_ratio/low_min": 6.680681690340862e-05,
      "clip_ratio/region_mean": 0.00222468345600646,
      "epoch": 0.08091979770050575,
      "grad_norm": 0.13643470406532288,
      "learning_rate": 1e-06,
      "loss": 0.0266,
      "step": 867
    },
    {
      "clip_ratio/high_max": 0.002664159081177786,
      "clip_ratio/high_mean": 0.0011410006263758987,
      "clip_ratio/low_mean": 0.0013658201496582478,
      "clip_ratio/low_min": 0.00010390758052380988,
      "clip_ratio/region_mean": 0.002506820783310104,
      "epoch": 0.08101313080050633,
      "grad_norm": 0.11330758035182953,
      "learning_rate": 1e-06,
      "loss": 0.0466,
      "step": 868
    },
    {
      "clip_ratio/high_max": 0.0024894229354686104,
      "clip_ratio/high_mean": 0.0009335126342193689,
      "clip_ratio/low_mean": 0.0011458650660642888,
      "clip_ratio/low_min": 9.861582293524407e-05,
      "clip_ratio/region_mean": 0.0020793776930077,
      "epoch": 0.08110646390050691,
      "grad_norm": 0.10997138172388077,
      "learning_rate": 1e-06,
      "loss": 0.0371,
      "step": 869
    },
    {
      "clip_ratio/high_max": 0.00247035260690609,
      "clip_ratio/high_mean": 0.0009542091356706806,
      "clip_ratio/low_mean": 0.001411927652952727,
      "clip_ratio/low_min": 0.00012325794887146913,
      "clip_ratio/region_mean": 0.0023661367886234075,
      "epoch": 0.0811997970005075,
      "grad_norm": 0.6086474061012268,
      "learning_rate": 1e-06,
      "loss": 0.0503,
      "step": 870
    },
    {
      "clip_ratio/high_max": 0.002391709218500182,
      "clip_ratio/high_mean": 0.0010303383496648166,
      "clip_ratio/low_mean": 0.0012374086254567374,
      "clip_ratio/low_min": 0.00011426570927142166,
      "clip_ratio/region_mean": 0.002267746989673469,
      "epoch": 0.08129313010050808,
      "grad_norm": 0.20141176879405975,
      "learning_rate": 1e-06,
      "loss": 0.0318,
      "step": 871
    },
    {
      "clip_ratio/high_max": 0.002784316850011237,
      "clip_ratio/high_mean": 0.001004057063255459,
      "clip_ratio/low_mean": 0.0012415803412295645,
      "clip_ratio/low_min": 0.00020129359381826362,
      "clip_ratio/region_mean": 0.002245637442683801,
      "epoch": 0.08138646320050867,
      "grad_norm": 0.11298583447933197,
      "learning_rate": 1e-06,
      "loss": 0.0521,
      "step": 872
    },
    {
      "clip_ratio/high_max": 0.002325666748220101,
      "clip_ratio/high_mean": 0.0009547723821015097,
      "clip_ratio/low_mean": 0.0010779980766528752,
      "clip_ratio/low_min": 7.225132048915839e-05,
      "clip_ratio/region_mean": 0.002032770476944279,
      "epoch": 0.08147979630050925,
      "grad_norm": 0.10313452035188675,
      "learning_rate": 1e-06,
      "loss": 0.0098,
      "step": 873
    },
    {
      "clip_ratio/high_max": 0.0022977184162300546,
      "clip_ratio/high_mean": 0.0009579784327797825,
      "clip_ratio/low_mean": 0.0014666750066680834,
      "clip_ratio/low_min": 0.00013325582403922454,
      "clip_ratio/region_mean": 0.0024246534158010036,
      "epoch": 0.08157312940050983,
      "grad_norm": 0.11318870633840561,
      "learning_rate": 1e-06,
      "loss": 0.0191,
      "step": 874
    },
    {
      "clip_ratio/high_max": 0.0020165925234323367,
      "clip_ratio/high_mean": 0.0008996675678645261,
      "clip_ratio/low_mean": 0.0010485840903129429,
      "clip_ratio/low_min": 0.0001311471551161958,
      "clip_ratio/region_mean": 0.0019482515854178928,
      "epoch": 0.08166646250051042,
      "grad_norm": 0.24277649819850922,
      "learning_rate": 1e-06,
      "loss": 0.0427,
      "step": 875
    },
    {
      "clip_ratio/high_max": 0.002348750742385164,
      "clip_ratio/high_mean": 0.0010094275949086295,
      "clip_ratio/low_mean": 0.0011026529255104833,
      "clip_ratio/low_min": 0.00020930047594447387,
      "clip_ratio/region_mean": 0.0021120804667589255,
      "epoch": 0.081759795600511,
      "grad_norm": 0.18388061225414276,
      "learning_rate": 1e-06,
      "loss": 0.0057,
      "step": 876
    },
    {
      "clip_ratio/high_max": 0.002254111175716389,
      "clip_ratio/high_mean": 0.0009372075182909612,
      "clip_ratio/low_mean": 0.0012236012735229451,
      "clip_ratio/low_min": 2.2698384782415815e-05,
      "clip_ratio/region_mean": 0.002160808799089864,
      "epoch": 0.08185312870051158,
      "grad_norm": 0.44638508558273315,
      "learning_rate": 1e-06,
      "loss": 0.052,
      "step": 877
    },
    {
      "clip_ratio/high_max": 0.0022413329061237164,
      "clip_ratio/high_mean": 0.0008774938178248703,
      "clip_ratio/low_mean": 0.001086651798686944,
      "clip_ratio/low_min": 4.1848927139653824e-05,
      "clip_ratio/region_mean": 0.0019641455946839415,
      "epoch": 0.08194646180051217,
      "grad_norm": 0.10878467559814453,
      "learning_rate": 1e-06,
      "loss": 0.0729,
      "step": 878
    },
    {
      "clip_ratio/high_max": 0.0020848131462116726,
      "clip_ratio/high_mean": 0.0009510009604127845,
      "clip_ratio/low_mean": 0.0010740179859567434,
      "clip_ratio/low_min": 8.13105789347901e-05,
      "clip_ratio/region_mean": 0.002025018933636602,
      "epoch": 0.08203979490051275,
      "grad_norm": 0.10448770225048065,
      "learning_rate": 1e-06,
      "loss": 0.041,
      "step": 879
    },
    {
      "clip_ratio/high_max": 0.0026984763753716834,
      "clip_ratio/high_mean": 0.0009850375881796936,
      "clip_ratio/low_mean": 0.00127541557958466,
      "clip_ratio/low_min": 0.0001279512762266677,
      "clip_ratio/region_mean": 0.0022604531186516397,
      "epoch": 0.08213312800051333,
      "grad_norm": 0.1236085444688797,
      "learning_rate": 1e-06,
      "loss": 0.0666,
      "step": 880
    },
    {
      "clip_ratio/high_max": 0.002340782779356232,
      "clip_ratio/high_mean": 0.000971670230228483,
      "clip_ratio/low_mean": 0.001378974488034146,
      "clip_ratio/low_min": 9.547714034852106e-05,
      "clip_ratio/region_mean": 0.002350644746911712,
      "epoch": 0.08222646110051392,
      "grad_norm": 0.15762795507907867,
      "learning_rate": 1e-06,
      "loss": 0.0475,
      "step": 881
    },
    {
      "clip_ratio/high_max": 0.002312309210537933,
      "clip_ratio/high_mean": 0.0008442941016255645,
      "clip_ratio/low_mean": 0.0012366292176011484,
      "clip_ratio/low_min": 8.033882477320731e-05,
      "clip_ratio/region_mean": 0.0020809233174077235,
      "epoch": 0.0823197942005145,
      "grad_norm": 0.37249353528022766,
      "learning_rate": 1e-06,
      "loss": 0.0508,
      "step": 882
    },
    {
      "clip_ratio/high_max": 0.002722452103625983,
      "clip_ratio/high_mean": 0.0010439098841743544,
      "clip_ratio/low_mean": 0.0012929949116369244,
      "clip_ratio/low_min": 0.00016100466564239468,
      "clip_ratio/region_mean": 0.0023369047848973423,
      "epoch": 0.08241312730051509,
      "grad_norm": 0.11022623628377914,
      "learning_rate": 1e-06,
      "loss": 0.0354,
      "step": 883
    },
    {
      "clip_ratio/high_max": 0.0022517828037962317,
      "clip_ratio/high_mean": 0.0009518332735751756,
      "clip_ratio/low_mean": 0.0014104233232501429,
      "clip_ratio/low_min": 0.00014663810725323856,
      "clip_ratio/region_mean": 0.0023622565786354244,
      "epoch": 0.08250646040051567,
      "grad_norm": 0.1112028956413269,
      "learning_rate": 1e-06,
      "loss": 0.0155,
      "step": 884
    },
    {
      "clip_ratio/high_max": 0.0021193179054534994,
      "clip_ratio/high_mean": 0.0009566934895701706,
      "clip_ratio/low_mean": 0.0011692178995872382,
      "clip_ratio/low_min": 1.4643861504737288e-05,
      "clip_ratio/region_mean": 0.002125911407347303,
      "epoch": 0.08259979350051624,
      "grad_norm": 2.0604805946350098,
      "learning_rate": 1e-06,
      "loss": 0.0236,
      "step": 885
    },
    {
      "clip_ratio/high_max": 0.0026521035033511,
      "clip_ratio/high_mean": 0.0011164571224071551,
      "clip_ratio/low_mean": 0.0011642363642749842,
      "clip_ratio/low_min": 6.635881891270401e-05,
      "clip_ratio/region_mean": 0.002280693472130224,
      "epoch": 0.08269312660051684,
      "grad_norm": 0.1110633835196495,
      "learning_rate": 1e-06,
      "loss": 0.0288,
      "step": 886
    },
    {
      "clip_ratio/high_max": 0.0023651731098652817,
      "clip_ratio/high_mean": 0.0010694454467738979,
      "clip_ratio/low_mean": 0.0010925703354587313,
      "clip_ratio/low_min": 0.00010994618696713587,
      "clip_ratio/region_mean": 0.002162015822250396,
      "epoch": 0.08278645970051741,
      "grad_norm": 0.11572252959012985,
      "learning_rate": 1e-06,
      "loss": -0.0124,
      "step": 887
    },
    {
      "clip_ratio/high_max": 0.0020946152944816276,
      "clip_ratio/high_mean": 0.0008596991428930778,
      "clip_ratio/low_mean": 0.0014544814221153501,
      "clip_ratio/low_min": 0.00018069351790472865,
      "clip_ratio/region_mean": 0.002314180543180555,
      "epoch": 0.08287979280051799,
      "grad_norm": 0.10051079094409943,
      "learning_rate": 1e-06,
      "loss": 0.0728,
      "step": 888
    },
    {
      "clip_ratio/high_max": 0.0026639462521416135,
      "clip_ratio/high_mean": 0.0009583651408320293,
      "clip_ratio/low_mean": 0.0010621514811646193,
      "clip_ratio/low_min": 3.611003194237128e-05,
      "clip_ratio/region_mean": 0.0020205165637889877,
      "epoch": 0.08297312590051859,
      "grad_norm": 0.48735469579696655,
      "learning_rate": 1e-06,
      "loss": 0.0049,
      "step": 889
    },
    {
      "clip_ratio/high_max": 0.0024260861464426853,
      "clip_ratio/high_mean": 0.0010849874379346147,
      "clip_ratio/low_mean": 0.0011253281318204245,
      "clip_ratio/low_min": 9.578489925843314e-05,
      "clip_ratio/region_mean": 0.002210315542470198,
      "epoch": 0.08306645900051916,
      "grad_norm": 0.10304472595453262,
      "learning_rate": 1e-06,
      "loss": -0.0107,
      "step": 890
    },
    {
      "clip_ratio/high_max": 0.002215232787420973,
      "clip_ratio/high_mean": 0.0008943595203163568,
      "clip_ratio/low_mean": 0.0013783484700979898,
      "clip_ratio/low_min": 0.00017142461001640186,
      "clip_ratio/region_mean": 0.002272708032251103,
      "epoch": 0.08315979210051976,
      "grad_norm": 0.14530344307422638,
      "learning_rate": 1e-06,
      "loss": 0.0759,
      "step": 891
    },
    {
      "clip_ratio/high_max": 0.002144011094060261,
      "clip_ratio/high_mean": 0.0009147500486506033,
      "clip_ratio/low_mean": 0.001410330027283635,
      "clip_ratio/low_min": 0.00013872673389414558,
      "clip_ratio/region_mean": 0.0023250801168615,
      "epoch": 0.08325312520052033,
      "grad_norm": 0.1049463078379631,
      "learning_rate": 1e-06,
      "loss": 0.017,
      "step": 892
    },
    {
      "clip_ratio/high_max": 0.002171644187910715,
      "clip_ratio/high_mean": 0.0008838319972710451,
      "clip_ratio/low_mean": 0.0011495420785649912,
      "clip_ratio/low_min": 7.570941579615464e-05,
      "clip_ratio/region_mean": 0.002033374104939867,
      "epoch": 0.08334645830052091,
      "grad_norm": 0.11366205662488937,
      "learning_rate": 1e-06,
      "loss": 0.0225,
      "step": 893
    },
    {
      "clip_ratio/high_max": 0.0022619613155256957,
      "clip_ratio/high_mean": 0.0009261451195925474,
      "clip_ratio/low_mean": 0.0011723415009328164,
      "clip_ratio/low_min": 0.00023839016830606852,
      "clip_ratio/region_mean": 0.0020984866496291943,
      "epoch": 0.0834397914005215,
      "grad_norm": 0.1208035871386528,
      "learning_rate": 1e-06,
      "loss": 0.0788,
      "step": 894
    },
    {
      "clip_ratio/high_max": 0.0024429210934613366,
      "clip_ratio/high_mean": 0.001026021394864074,
      "clip_ratio/low_mean": 0.0012642092697205953,
      "clip_ratio/low_min": 0.00015144837198022287,
      "clip_ratio/region_mean": 0.0022902306882315315,
      "epoch": 0.08353312450052208,
      "grad_norm": 379.2685241699219,
      "learning_rate": 1e-06,
      "loss": 0.1067,
      "step": 895
    },
    {
      "clip_ratio/high_max": 0.0023735536306048743,
      "clip_ratio/high_mean": 0.0009185903909383342,
      "clip_ratio/low_mean": 0.0011832196032628417,
      "clip_ratio/low_min": 0.00012658051218750188,
      "clip_ratio/region_mean": 0.0021018100014771335,
      "epoch": 0.08362645760052266,
      "grad_norm": 0.12086167186498642,
      "learning_rate": 1e-06,
      "loss": 0.0477,
      "step": 896
    },
    {
      "clip_ratio/high_max": 0.0024008142354432493,
      "clip_ratio/high_mean": 0.0010434840241941856,
      "clip_ratio/low_mean": 0.0011500921591505175,
      "clip_ratio/low_min": 3.950086284021381e-05,
      "clip_ratio/region_mean": 0.0021935761396889575,
      "epoch": 0.08371979070052325,
      "grad_norm": 1498173.625,
      "learning_rate": 1e-06,
      "loss": 63.8014,
      "step": 897
    },
    {
      "clip_ratio/high_max": 0.0023613000084878877,
      "clip_ratio/high_mean": 0.0010318738313799258,
      "clip_ratio/low_mean": 0.0011949530489800964,
      "clip_ratio/low_min": 7.660968276468338e-05,
      "clip_ratio/region_mean": 0.0022268268730840646,
      "epoch": 0.08381312380052383,
      "grad_norm": 0.11082210391759872,
      "learning_rate": 1e-06,
      "loss": 0.0482,
      "step": 898
    },
    {
      "clip_ratio/high_max": 0.0024838549143169075,
      "clip_ratio/high_mean": 0.0010703700281737838,
      "clip_ratio/low_mean": 0.0010024417460954282,
      "clip_ratio/low_min": 9.429518922843272e-05,
      "clip_ratio/region_mean": 0.002072811759717297,
      "epoch": 0.08390645690052441,
      "grad_norm": 0.09950433671474457,
      "learning_rate": 1e-06,
      "loss": 0.0036,
      "step": 899
    },
    {
      "clip_ratio/high_max": 0.002268324842589209,
      "clip_ratio/high_mean": 0.0008833024767227471,
      "clip_ratio/low_mean": 0.0014224285587260965,
      "clip_ratio/low_min": 5.858836902916664e-05,
      "clip_ratio/region_mean": 0.0023057309954310767,
      "epoch": 0.083999790000525,
      "grad_norm": 33.7497673034668,
      "learning_rate": 1e-06,
      "loss": 0.0399,
      "step": 900
    },
    {
      "clip_ratio/high_max": 0.0023017935891402885,
      "clip_ratio/high_mean": 0.0009715641572256573,
      "clip_ratio/low_mean": 0.0010959513783745933,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002067515510134399,
      "epoch": 0.08409312310052558,
      "grad_norm": 0.11014106124639511,
      "learning_rate": 1e-06,
      "loss": -0.0124,
      "step": 901
    },
    {
      "clip_ratio/high_max": 0.0023868624994065613,
      "clip_ratio/high_mean": 0.0010377027647336945,
      "clip_ratio/low_mean": 0.0012187745851406362,
      "clip_ratio/low_min": 9.586280702933436e-05,
      "clip_ratio/region_mean": 0.0022564773389603943,
      "epoch": 0.08418645620052617,
      "grad_norm": 14.505834579467773,
      "learning_rate": 1e-06,
      "loss": 0.0214,
      "step": 902
    },
    {
      "clip_ratio/high_max": 0.002561476501796278,
      "clip_ratio/high_mean": 0.0009719652730382222,
      "clip_ratio/low_mean": 0.0014163736377668101,
      "clip_ratio/low_min": 0.00020562474037433276,
      "clip_ratio/region_mean": 0.0023883389294496737,
      "epoch": 0.08427978930052675,
      "grad_norm": 0.2170296460390091,
      "learning_rate": 1e-06,
      "loss": 0.0711,
      "step": 903
    },
    {
      "clip_ratio/high_max": 0.0026172805883106776,
      "clip_ratio/high_mean": 0.0010360503692936618,
      "clip_ratio/low_mean": 0.0015687572195020039,
      "clip_ratio/low_min": 0.00010546327393967658,
      "clip_ratio/region_mean": 0.0026048076106235385,
      "epoch": 0.08437312240052733,
      "grad_norm": 0.1139143705368042,
      "learning_rate": 1e-06,
      "loss": 0.0434,
      "step": 904
    },
    {
      "clip_ratio/high_max": 0.002303227629454341,
      "clip_ratio/high_mean": 0.0008711810296517797,
      "clip_ratio/low_mean": 0.0012094752910343232,
      "clip_ratio/low_min": 0.00011234086014155764,
      "clip_ratio/region_mean": 0.002080656311591156,
      "epoch": 0.08446645550052792,
      "grad_norm": 0.11276731640100479,
      "learning_rate": 1e-06,
      "loss": 0.0464,
      "step": 905
    },
    {
      "clip_ratio/high_max": 0.0022801099403295666,
      "clip_ratio/high_mean": 0.000999399217107566,
      "clip_ratio/low_mean": 0.001317723417741945,
      "clip_ratio/low_min": 0.00016726861576898955,
      "clip_ratio/region_mean": 0.0023171226785052568,
      "epoch": 0.0845597886005285,
      "grad_norm": 0.11814355850219727,
      "learning_rate": 1e-06,
      "loss": 0.0196,
      "step": 906
    },
    {
      "clip_ratio/high_max": 0.0023774189176037908,
      "clip_ratio/high_mean": 0.0010647673479979858,
      "clip_ratio/low_mean": 0.0011631750385276973,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0022279423428699374,
      "epoch": 0.08465312170052908,
      "grad_norm": 0.11206215620040894,
      "learning_rate": 1e-06,
      "loss": -0.0277,
      "step": 907
    },
    {
      "clip_ratio/high_max": 0.0019795977241301443,
      "clip_ratio/high_mean": 0.0008602875859651249,
      "clip_ratio/low_mean": 0.0011299404268356739,
      "clip_ratio/low_min": 9.358750321553089e-05,
      "clip_ratio/region_mean": 0.00199022804008564,
      "epoch": 0.08474645480052967,
      "grad_norm": 0.10877736657857895,
      "learning_rate": 1e-06,
      "loss": 0.0172,
      "step": 908
    },
    {
      "clip_ratio/high_max": 0.002549438962887507,
      "clip_ratio/high_mean": 0.0010372703109169379,
      "clip_ratio/low_mean": 0.0015779779023432638,
      "clip_ratio/low_min": 3.47672903444618e-05,
      "clip_ratio/region_mean": 0.0026152482532779686,
      "epoch": 0.08483978790053025,
      "grad_norm": 0.16966469585895538,
      "learning_rate": 1e-06,
      "loss": 0.0128,
      "step": 909
    },
    {
      "clip_ratio/high_max": 0.002389495442912448,
      "clip_ratio/high_mean": 0.0009297276428696932,
      "clip_ratio/low_mean": 0.0012547899823402986,
      "clip_ratio/low_min": 0.0001997924155148212,
      "clip_ratio/region_mean": 0.0021845176015631296,
      "epoch": 0.08493312100053083,
      "grad_norm": 0.10381964594125748,
      "learning_rate": 1e-06,
      "loss": 0.0097,
      "step": 910
    },
    {
      "clip_ratio/high_max": 0.0023043394103297032,
      "clip_ratio/high_mean": 0.0010334826147300191,
      "clip_ratio/low_mean": 0.0011366517528585973,
      "clip_ratio/low_min": 0.00013663454137713416,
      "clip_ratio/region_mean": 0.002170134444895666,
      "epoch": 0.08502645410053142,
      "grad_norm": 0.11094743013381958,
      "learning_rate": 1e-06,
      "loss": -0.0152,
      "step": 911
    },
    {
      "clip_ratio/high_max": 0.002263615173433209,
      "clip_ratio/high_mean": 0.0009786826885829214,
      "clip_ratio/low_mean": 0.001256348070455715,
      "clip_ratio/low_min": 6.04115666646976e-05,
      "clip_ratio/region_mean": 0.002235030733572785,
      "epoch": 0.085119787200532,
      "grad_norm": 0.3648679554462433,
      "learning_rate": 1e-06,
      "loss": 0.0285,
      "step": 912
    },
    {
      "clip_ratio/high_max": 0.002099015509884339,
      "clip_ratio/high_mean": 0.0008645005109428894,
      "clip_ratio/low_mean": 0.0014571586689271498,
      "clip_ratio/low_min": 6.089243834139779e-05,
      "clip_ratio/region_mean": 0.002321659201697912,
      "epoch": 0.08521312030053259,
      "grad_norm": 0.17229481041431427,
      "learning_rate": 1e-06,
      "loss": 0.0345,
      "step": 913
    },
    {
      "clip_ratio/high_max": 0.0026263648542226292,
      "clip_ratio/high_mean": 0.0010387585789430887,
      "clip_ratio/low_mean": 0.0014933757956896443,
      "clip_ratio/low_min": 0.00016493399198225234,
      "clip_ratio/region_mean": 0.0025321344364783727,
      "epoch": 0.08530645340053317,
      "grad_norm": 0.16887377202510834,
      "learning_rate": 1e-06,
      "loss": 0.0099,
      "step": 914
    },
    {
      "clip_ratio/high_max": 0.002455261277646059,
      "clip_ratio/high_mean": 0.0009095840850932291,
      "clip_ratio/low_mean": 0.0013396572103374638,
      "clip_ratio/low_min": 0.00018635055130289402,
      "clip_ratio/region_mean": 0.0022492413118015975,
      "epoch": 0.08539978650053374,
      "grad_norm": 0.21369841694831848,
      "learning_rate": 1e-06,
      "loss": 0.0314,
      "step": 915
    },
    {
      "clip_ratio/high_max": 0.002347531550185522,
      "clip_ratio/high_mean": 0.000951391493799747,
      "clip_ratio/low_mean": 0.0013145883413017145,
      "clip_ratio/low_min": 0.00027512239284988027,
      "clip_ratio/region_mean": 0.0022659798560198396,
      "epoch": 0.08549311960053434,
      "grad_norm": 0.12547805905342102,
      "learning_rate": 1e-06,
      "loss": 0.0364,
      "step": 916
    },
    {
      "clip_ratio/high_max": 0.0024531892631785013,
      "clip_ratio/high_mean": 0.0010786664515762823,
      "clip_ratio/low_mean": 0.001318588243520935,
      "clip_ratio/low_min": 7.283358354470693e-05,
      "clip_ratio/region_mean": 0.002397254698735196,
      "epoch": 0.08558645270053492,
      "grad_norm": 0.31122174859046936,
      "learning_rate": 1e-06,
      "loss": 0.022,
      "step": 917
    },
    {
      "clip_ratio/high_max": 0.0021741417513112538,
      "clip_ratio/high_mean": 0.0008625397240393795,
      "clip_ratio/low_mean": 0.0013882866951462347,
      "clip_ratio/low_min": 0.00020721524924738333,
      "clip_ratio/region_mean": 0.0022508264155476354,
      "epoch": 0.0856797858005355,
      "grad_norm": 14.696321487426758,
      "learning_rate": 1e-06,
      "loss": 0.067,
      "step": 918
    },
    {
      "clip_ratio/high_max": 0.0029387307731667534,
      "clip_ratio/high_mean": 0.0011057026604248676,
      "clip_ratio/low_mean": 0.0010671899253793526,
      "clip_ratio/low_min": 8.397746842092602e-05,
      "clip_ratio/region_mean": 0.002172892571252305,
      "epoch": 0.08577311890053609,
      "grad_norm": 0.11167183518409729,
      "learning_rate": 1e-06,
      "loss": 0.0048,
      "step": 919
    },
    {
      "clip_ratio/high_max": 0.0026019670185633004,
      "clip_ratio/high_mean": 0.0009697596506157424,
      "clip_ratio/low_mean": 0.0013117019971105037,
      "clip_ratio/low_min": 9.068149483937304e-05,
      "clip_ratio/region_mean": 0.002281461660459172,
      "epoch": 0.08586645200053666,
      "grad_norm": 0.10400262475013733,
      "learning_rate": 1e-06,
      "loss": 0.0267,
      "step": 920
    },
    {
      "clip_ratio/high_max": 0.002282887253386434,
      "clip_ratio/high_mean": 0.0010124723266926594,
      "clip_ratio/low_mean": 0.0010988165413436946,
      "clip_ratio/low_min": 8.7904143583728e-05,
      "clip_ratio/region_mean": 0.002111288864398375,
      "epoch": 0.08595978510053724,
      "grad_norm": 0.12238967418670654,
      "learning_rate": 1e-06,
      "loss": 0.0104,
      "step": 921
    },
    {
      "clip_ratio/high_max": 0.0025052935670828447,
      "clip_ratio/high_mean": 0.0009398449365107808,
      "clip_ratio/low_mean": 0.0011888236840604804,
      "clip_ratio/low_min": 7.10683179931948e-05,
      "clip_ratio/region_mean": 0.002128668587829452,
      "epoch": 0.08605311820053783,
      "grad_norm": 0.2997726500034332,
      "learning_rate": 1e-06,
      "loss": 0.0306,
      "step": 922
    },
    {
      "clip_ratio/high_max": 0.0023128594511945266,
      "clip_ratio/high_mean": 0.0009728028544486733,
      "clip_ratio/low_mean": 0.0013744936695729848,
      "clip_ratio/low_min": 0.00013301632316142786,
      "clip_ratio/region_mean": 0.0023472965112887323,
      "epoch": 0.08614645130053841,
      "grad_norm": 0.11684460937976837,
      "learning_rate": 1e-06,
      "loss": 0.0267,
      "step": 923
    },
    {
      "clip_ratio/high_max": 0.002228422265034169,
      "clip_ratio/high_mean": 0.0007883524613134796,
      "clip_ratio/low_mean": 0.0013270641284179874,
      "clip_ratio/low_min": 0.00013172165472497,
      "clip_ratio/region_mean": 0.0021154166097403504,
      "epoch": 0.086239784400539,
      "grad_norm": 0.1094125509262085,
      "learning_rate": 1e-06,
      "loss": 0.0322,
      "step": 924
    },
    {
      "clip_ratio/high_max": 0.0022775792931497563,
      "clip_ratio/high_mean": 0.0008262887890850834,
      "clip_ratio/low_mean": 0.0013585323904408142,
      "clip_ratio/low_min": 0.0001292492997890804,
      "clip_ratio/region_mean": 0.0021848212054464966,
      "epoch": 0.08633311750053958,
      "grad_norm": 0.21094855666160583,
      "learning_rate": 1e-06,
      "loss": 0.0853,
      "step": 925
    },
    {
      "clip_ratio/high_max": 0.0025841073838819284,
      "clip_ratio/high_mean": 0.0010466866369824857,
      "clip_ratio/low_mean": 0.0009866291911748704,
      "clip_ratio/low_min": 5.644580778607633e-05,
      "clip_ratio/region_mean": 0.002033315809967462,
      "epoch": 0.08642645060054016,
      "grad_norm": 0.11110901832580566,
      "learning_rate": 1e-06,
      "loss": -0.0147,
      "step": 926
    },
    {
      "clip_ratio/high_max": 0.002120171455317177,
      "clip_ratio/high_mean": 0.000920732965823845,
      "clip_ratio/low_mean": 0.0011272655938228127,
      "clip_ratio/low_min": 7.595165152451955e-05,
      "clip_ratio/region_mean": 0.0020479985105339438,
      "epoch": 0.08651978370054075,
      "grad_norm": 0.3409970998764038,
      "learning_rate": 1e-06,
      "loss": 0.0258,
      "step": 927
    },
    {
      "clip_ratio/high_max": 0.002264707873109728,
      "clip_ratio/high_mean": 0.0009114696367760189,
      "clip_ratio/low_mean": 0.0011135901513625868,
      "clip_ratio/low_min": 8.535096822015475e-05,
      "clip_ratio/region_mean": 0.0020250597735866904,
      "epoch": 0.08661311680054133,
      "grad_norm": 0.11092744022607803,
      "learning_rate": 1e-06,
      "loss": 0.0072,
      "step": 928
    },
    {
      "clip_ratio/high_max": 0.0029259155489853583,
      "clip_ratio/high_mean": 0.0011901314464921597,
      "clip_ratio/low_mean": 0.0010359873558627442,
      "clip_ratio/low_min": 5.0713119435386034e-05,
      "clip_ratio/region_mean": 0.002226118740509264,
      "completions/clipped_ratio": 0.012433733258928603,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4092.0,
      "completions/mean_length": 606.3265991210938,
      "completions/mean_terminated_length": 562.3905639648438,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.08670644990054191,
      "grad_norm": 658.1107788085938,
      "learning_rate": 1e-06,
      "loss": 920.7662,
      "num_tokens": 732468601.0,
      "reward": 0.581856906414032,
      "reward_std": 0.19840924441814423,
      "rewards/simpleverify_reward/mean": 0.5818568468093872,
      "rewards/simpleverify_reward/std": 0.4932560920715332,
      "step": 929
    },
    {
      "clip_ratio/high_max": 0.0034058319142786786,
      "clip_ratio/high_mean": 0.0011287498200545087,
      "clip_ratio/low_mean": 0.0011267033260082826,
      "clip_ratio/low_min": 0.00014275316425482742,
      "clip_ratio/region_mean": 0.002255453153338749,
      "epoch": 0.0867997830005425,
      "grad_norm": 80630872.0,
      "learning_rate": 1e-06,
      "loss": 15628.332,
      "step": 930
    },
    {
      "clip_ratio/high_max": 0.002698423617403023,
      "clip_ratio/high_mean": 0.0011878734112542588,
      "clip_ratio/low_mean": 0.0009699943511805031,
      "clip_ratio/low_min": 5.638257516693557e-05,
      "clip_ratio/region_mean": 0.0021578677478828467,
      "epoch": 0.08689311610054308,
      "grad_norm": 1000.2466430664062,
      "learning_rate": 1e-06,
      "loss": 3.1991,
      "step": 931
    },
    {
      "clip_ratio/high_max": 0.0027802466865978204,
      "clip_ratio/high_mean": 0.0012451053080440033,
      "clip_ratio/low_mean": 0.000949066143220989,
      "clip_ratio/low_min": 7.313903097383445e-05,
      "clip_ratio/region_mean": 0.0021941714658169076,
      "epoch": 0.08698644920054366,
      "grad_norm": 3595.9853515625,
      "learning_rate": 1e-06,
      "loss": 12.6799,
      "step": 932
    },
    {
      "clip_ratio/high_max": 0.0028793093442800455,
      "clip_ratio/high_mean": 0.001297881508435239,
      "clip_ratio/low_mean": 0.0010068388110084925,
      "clip_ratio/low_min": 0.00019474184227874503,
      "clip_ratio/region_mean": 0.002304720335814636,
      "epoch": 0.08707978230054425,
      "grad_norm": 39064.96875,
      "learning_rate": 1e-06,
      "loss": 6.4856,
      "step": 933
    },
    {
      "clip_ratio/high_max": 0.002898460501455702,
      "clip_ratio/high_mean": 0.0012248599632584956,
      "clip_ratio/low_mean": 0.0010910550081462134,
      "clip_ratio/low_min": 0.0001481485724070808,
      "clip_ratio/region_mean": 0.0023159149641287513,
      "epoch": 0.08717311540054483,
      "grad_norm": 144.14561462402344,
      "learning_rate": 1e-06,
      "loss": 0.0765,
      "step": 934
    },
    {
      "clip_ratio/high_max": 0.002663971608853899,
      "clip_ratio/high_mean": 0.001215269701788202,
      "clip_ratio/low_mean": 0.001067837296432117,
      "clip_ratio/low_min": 0.00011083995923399925,
      "clip_ratio/region_mean": 0.002283106980030425,
      "epoch": 0.08726644850054542,
      "grad_norm": 1607.0867919921875,
      "learning_rate": 1e-06,
      "loss": 16.6825,
      "step": 935
    },
    {
      "clip_ratio/high_max": 0.0027065208123531193,
      "clip_ratio/high_mean": 0.001296229129366111,
      "clip_ratio/low_mean": 0.0010284048130415613,
      "clip_ratio/low_min": 0.00011034236740670167,
      "clip_ratio/region_mean": 0.0023246338751050644,
      "epoch": 0.087359781600546,
      "grad_norm": 10.217474937438965,
      "learning_rate": 1e-06,
      "loss": -0.0226,
      "step": 936
    },
    {
      "clip_ratio/high_max": 0.002616501340526156,
      "clip_ratio/high_mean": 0.001097550337362918,
      "clip_ratio/low_mean": 0.0013795242011838127,
      "clip_ratio/low_min": 0.00017977006882574642,
      "clip_ratio/region_mean": 0.002477074544003699,
      "epoch": 0.08745311470054658,
      "grad_norm": 25.305007934570312,
      "learning_rate": 1e-06,
      "loss": 0.0776,
      "step": 937
    },
    {
      "clip_ratio/high_max": 0.002169427643821109,
      "clip_ratio/high_mean": 0.0009409247904841322,
      "clip_ratio/low_mean": 0.0011030634632334113,
      "clip_ratio/low_min": 5.6443348512402736e-05,
      "clip_ratio/region_mean": 0.002043988242803607,
      "epoch": 0.08754644780054717,
      "grad_norm": 3.802832841873169,
      "learning_rate": 1e-06,
      "loss": 0.061,
      "step": 938
    },
    {
      "clip_ratio/high_max": 0.0026284974301233888,
      "clip_ratio/high_mean": 0.0010768719366751611,
      "clip_ratio/low_mean": 0.0011288458008493762,
      "clip_ratio/low_min": 6.795461376896128e-05,
      "clip_ratio/region_mean": 0.002205717726610601,
      "epoch": 0.08763978090054775,
      "grad_norm": 0.12048052251338959,
      "learning_rate": 1e-06,
      "loss": 0.0127,
      "step": 939
    },
    {
      "clip_ratio/high_max": 0.0027050889329984784,
      "clip_ratio/high_mean": 0.0011865939704875927,
      "clip_ratio/low_mean": 0.0011583276555029443,
      "clip_ratio/low_min": 0.00012447621702449396,
      "clip_ratio/region_mean": 0.00234492161689559,
      "epoch": 0.08773311400054833,
      "grad_norm": 0.7302131652832031,
      "learning_rate": 1e-06,
      "loss": -0.0277,
      "step": 940
    },
    {
      "clip_ratio/high_max": 0.002358895471843425,
      "clip_ratio/high_mean": 0.0009820188606681768,
      "clip_ratio/low_mean": 0.0014514831309497822,
      "clip_ratio/low_min": 1.2700670595222618e-05,
      "clip_ratio/region_mean": 0.0024335019843420014,
      "epoch": 0.08782644710054892,
      "grad_norm": 0.5652409791946411,
      "learning_rate": 1e-06,
      "loss": 0.0729,
      "step": 941
    },
    {
      "clip_ratio/high_max": 0.0026311205874662846,
      "clip_ratio/high_mean": 0.0011160112917423248,
      "clip_ratio/low_mean": 0.0015240918219205923,
      "clip_ratio/low_min": 0.0001546228668303229,
      "clip_ratio/region_mean": 0.002640103062731214,
      "epoch": 0.0879197802005495,
      "grad_norm": 1.129449725151062,
      "learning_rate": 1e-06,
      "loss": 0.0362,
      "step": 942
    },
    {
      "clip_ratio/high_max": 0.0025298894397565164,
      "clip_ratio/high_mean": 0.0011450928814156214,
      "clip_ratio/low_mean": 0.0016939030574576464,
      "clip_ratio/low_min": 0.00011486561743367929,
      "clip_ratio/region_mean": 0.0028389959115884267,
      "epoch": 0.08801311330055009,
      "grad_norm": 58.09937286376953,
      "learning_rate": 1e-06,
      "loss": 0.0677,
      "step": 943
    },
    {
      "clip_ratio/high_max": 0.002646366374392528,
      "clip_ratio/high_mean": 0.0011582256483961828,
      "clip_ratio/low_mean": 0.0017861177475424483,
      "clip_ratio/low_min": 0.000292622606139048,
      "clip_ratio/region_mean": 0.002944343454146292,
      "epoch": 0.08810644640055067,
      "grad_norm": 1.307054042816162,
      "learning_rate": 1e-06,
      "loss": 0.0508,
      "step": 944
    },
    {
      "clip_ratio/high_max": 0.0027794577763415873,
      "clip_ratio/high_mean": 0.0011400759758544154,
      "clip_ratio/low_mean": 0.0017639938741922379,
      "clip_ratio/low_min": 1.544735459901858e-05,
      "clip_ratio/region_mean": 0.0029040698427706957,
      "epoch": 0.08819977950055125,
      "grad_norm": 0.4146556854248047,
      "learning_rate": 1e-06,
      "loss": 0.021,
      "step": 945
    },
    {
      "clip_ratio/high_max": 0.002447194310661871,
      "clip_ratio/high_mean": 0.0011346678329573479,
      "clip_ratio/low_mean": 0.0019092099682893604,
      "clip_ratio/low_min": 0.0003389314042578917,
      "clip_ratio/region_mean": 0.0030438778194366023,
      "epoch": 0.08829311260055184,
      "grad_norm": 0.1193733960390091,
      "learning_rate": 1e-06,
      "loss": 0.0492,
      "step": 946
    },
    {
      "clip_ratio/high_max": 0.0026018462594947778,
      "clip_ratio/high_mean": 0.0010851564475160558,
      "clip_ratio/low_mean": 0.0016620873211650178,
      "clip_ratio/low_min": 7.24562141840579e-05,
      "clip_ratio/region_mean": 0.0027472437723190524,
      "epoch": 0.08838644570055242,
      "grad_norm": 0.15501439571380615,
      "learning_rate": 1e-06,
      "loss": 0.0134,
      "step": 947
    },
    {
      "clip_ratio/high_max": 0.002631387527799234,
      "clip_ratio/high_mean": 0.0012107435322832316,
      "clip_ratio/low_mean": 0.0014972333374316804,
      "clip_ratio/low_min": 0.00011391548332539969,
      "clip_ratio/region_mean": 0.002707976855162997,
      "epoch": 0.088479778800553,
      "grad_norm": 0.13161900639533997,
      "learning_rate": 1e-06,
      "loss": 0.0132,
      "step": 948
    },
    {
      "clip_ratio/high_max": 0.0028324291270109825,
      "clip_ratio/high_mean": 0.0010979366124956869,
      "clip_ratio/low_mean": 0.002003681380301714,
      "clip_ratio/low_min": 0.00025417295364604797,
      "clip_ratio/region_mean": 0.003101617985521443,
      "epoch": 0.08857311190055359,
      "grad_norm": 18580.810546875,
      "learning_rate": 1e-06,
      "loss": 2.7264,
      "step": 949
    },
    {
      "clip_ratio/high_max": 0.0023946603178046644,
      "clip_ratio/high_mean": 0.0010583803159534,
      "clip_ratio/low_mean": 0.0015508402575505897,
      "clip_ratio/low_min": 8.250276187027339e-05,
      "clip_ratio/region_mean": 0.002609220566228032,
      "epoch": 0.08866644500055416,
      "grad_norm": 0.15283074975013733,
      "learning_rate": 1e-06,
      "loss": 0.0191,
      "step": 950
    },
    {
      "clip_ratio/high_max": 0.0025217513102688827,
      "clip_ratio/high_mean": 0.0009943358272721525,
      "clip_ratio/low_mean": 0.0014997832622611895,
      "clip_ratio/low_min": 0.00019928392430301756,
      "clip_ratio/region_mean": 0.002494119071343448,
      "epoch": 0.08875977810055474,
      "grad_norm": 0.10834085941314697,
      "learning_rate": 1e-06,
      "loss": 0.0395,
      "step": 951
    },
    {
      "clip_ratio/high_max": 0.002701760757190641,
      "clip_ratio/high_mean": 0.0011713325293385424,
      "clip_ratio/low_mean": 0.002080030579236336,
      "clip_ratio/low_min": 0.00021892567792747286,
      "clip_ratio/region_mean": 0.003251363188610412,
      "epoch": 0.08885311120055533,
      "grad_norm": 0.4292258322238922,
      "learning_rate": 1e-06,
      "loss": 0.0409,
      "step": 952
    },
    {
      "clip_ratio/high_max": 0.003101715679804329,
      "clip_ratio/high_mean": 0.0012029106983391102,
      "clip_ratio/low_mean": 0.0015936565723677631,
      "clip_ratio/low_min": 0.00010612279402266722,
      "clip_ratio/region_mean": 0.0027965671979472972,
      "epoch": 0.08894644430055591,
      "grad_norm": 0.1338549107313156,
      "learning_rate": 1e-06,
      "loss": 0.0263,
      "step": 953
    },
    {
      "clip_ratio/high_max": 0.0030695839086547494,
      "clip_ratio/high_mean": 0.0011215854592592223,
      "clip_ratio/low_mean": 0.0015305491069739219,
      "clip_ratio/low_min": 6.853561990283197e-05,
      "clip_ratio/region_mean": 0.00265213457896607,
      "epoch": 0.0890397774005565,
      "grad_norm": 0.12780126929283142,
      "learning_rate": 1e-06,
      "loss": 0.0094,
      "step": 954
    },
    {
      "clip_ratio/high_max": 0.00236971069170977,
      "clip_ratio/high_mean": 0.0010469768167240545,
      "clip_ratio/low_mean": 0.0014215620467439294,
      "clip_ratio/low_min": 0.00011546862333489116,
      "clip_ratio/region_mean": 0.0024685388925718144,
      "epoch": 0.08913311050055708,
      "grad_norm": 0.1021844893693924,
      "learning_rate": 1e-06,
      "loss": 0.0311,
      "step": 955
    },
    {
      "clip_ratio/high_max": 0.0025919151084963232,
      "clip_ratio/high_mean": 0.001123786694734008,
      "clip_ratio/low_mean": 0.001994975758861983,
      "clip_ratio/low_min": 0.00014724188258696813,
      "clip_ratio/region_mean": 0.0031187623972073197,
      "epoch": 0.08922644360055766,
      "grad_norm": 1233.413330078125,
      "learning_rate": 1e-06,
      "loss": 0.1991,
      "step": 956
    },
    {
      "clip_ratio/high_max": 0.002833966318576131,
      "clip_ratio/high_mean": 0.00111185597597796,
      "clip_ratio/low_mean": 0.0018087287826347165,
      "clip_ratio/low_min": 0.00017405671223968966,
      "clip_ratio/region_mean": 0.0029205848113633692,
      "epoch": 0.08931977670055825,
      "grad_norm": 0.10991702228784561,
      "learning_rate": 1e-06,
      "loss": 0.0416,
      "step": 957
    },
    {
      "clip_ratio/high_max": 0.0027754683178500272,
      "clip_ratio/high_mean": 0.0012341040346655063,
      "clip_ratio/low_mean": 0.001622908308490878,
      "clip_ratio/low_min": 7.870357512729242e-05,
      "clip_ratio/region_mean": 0.002857012426829897,
      "epoch": 0.08941310980055883,
      "grad_norm": 48.008544921875,
      "learning_rate": 1e-06,
      "loss": 0.0172,
      "step": 958
    },
    {
      "clip_ratio/high_max": 0.0023099228856153786,
      "clip_ratio/high_mean": 0.0010256685272906907,
      "clip_ratio/low_mean": 0.001928425299411174,
      "clip_ratio/low_min": 0.00013614695126307197,
      "clip_ratio/region_mean": 0.0029540938994614407,
      "epoch": 0.08950644290055941,
      "grad_norm": 0.15738925337791443,
      "learning_rate": 1e-06,
      "loss": 0.0717,
      "step": 959
    },
    {
      "clip_ratio/high_max": 0.002546827479818603,
      "clip_ratio/high_mean": 0.0012053147747792536,
      "clip_ratio/low_mean": 0.001494118641858222,
      "clip_ratio/low_min": 0.00012901766058348585,
      "clip_ratio/region_mean": 0.002699433476664126,
      "epoch": 0.08959977600056,
      "grad_norm": 0.12766140699386597,
      "learning_rate": 1e-06,
      "loss": -0.0442,
      "step": 960
    },
    {
      "clip_ratio/high_max": 0.002865133195882663,
      "clip_ratio/high_mean": 0.0012718562138616107,
      "clip_ratio/low_mean": 0.001514236930233892,
      "clip_ratio/low_min": 3.713743444677675e-05,
      "clip_ratio/region_mean": 0.0027860930567840114,
      "epoch": 0.08969310910056058,
      "grad_norm": 0.1301388293504715,
      "learning_rate": 1e-06,
      "loss": -0.0345,
      "step": 961
    },
    {
      "clip_ratio/high_max": 0.0029480006778612733,
      "clip_ratio/high_mean": 0.0012709887923847418,
      "clip_ratio/low_mean": 0.0014145162604108918,
      "clip_ratio/low_min": 5.115070234751329e-05,
      "clip_ratio/region_mean": 0.00268550512555521,
      "epoch": 0.08978644220056116,
      "grad_norm": 0.11750379204750061,
      "learning_rate": 1e-06,
      "loss": -0.0044,
      "step": 962
    },
    {
      "clip_ratio/high_max": 0.0025278916145907715,
      "clip_ratio/high_mean": 0.0009999431968026329,
      "clip_ratio/low_mean": 0.0017290908508584835,
      "clip_ratio/low_min": 0.000227160857320996,
      "clip_ratio/region_mean": 0.002729034094954841,
      "epoch": 0.08987977530056175,
      "grad_norm": 0.11249005794525146,
      "learning_rate": 1e-06,
      "loss": 0.0437,
      "step": 963
    },
    {
      "clip_ratio/high_max": 0.002835528561263345,
      "clip_ratio/high_mean": 0.0011164538191223983,
      "clip_ratio/low_mean": 0.0017168393824249506,
      "clip_ratio/low_min": 7.206099780887598e-05,
      "clip_ratio/region_mean": 0.0028332932051853277,
      "epoch": 0.08997310840056233,
      "grad_norm": 0.11565061658620834,
      "learning_rate": 1e-06,
      "loss": 0.0065,
      "step": 964
    },
    {
      "clip_ratio/high_max": 0.0025258780078729615,
      "clip_ratio/high_mean": 0.001039100403431803,
      "clip_ratio/low_mean": 0.001595698318851646,
      "clip_ratio/low_min": 4.252992403053213e-05,
      "clip_ratio/region_mean": 0.00263479878049111,
      "epoch": 0.09006644150056292,
      "grad_norm": 0.6675903797149658,
      "learning_rate": 1e-06,
      "loss": 0.0344,
      "step": 965
    },
    {
      "clip_ratio/high_max": 0.0024378097114095,
      "clip_ratio/high_mean": 0.0010198693780694157,
      "clip_ratio/low_mean": 0.0014414132929232437,
      "clip_ratio/low_min": 7.952272335387534e-05,
      "clip_ratio/region_mean": 0.0024612826455268078,
      "epoch": 0.0901597746005635,
      "grad_norm": 0.10590285062789917,
      "learning_rate": 1e-06,
      "loss": -0.0029,
      "step": 966
    },
    {
      "clip_ratio/high_max": 0.002850593977200333,
      "clip_ratio/high_mean": 0.0011228631774429232,
      "clip_ratio/low_mean": 0.0016011863881431054,
      "clip_ratio/low_min": 6.342563392536249e-05,
      "clip_ratio/region_mean": 0.0027240496638114564,
      "epoch": 0.09025310770056408,
      "grad_norm": 176.32424926757812,
      "learning_rate": 1e-06,
      "loss": 0.0384,
      "step": 967
    },
    {
      "clip_ratio/high_max": 0.0026763011555885896,
      "clip_ratio/high_mean": 0.0010797035210998729,
      "clip_ratio/low_mean": 0.0016338121786247939,
      "clip_ratio/low_min": 0.00021653350222550216,
      "clip_ratio/region_mean": 0.0027135156487929635,
      "epoch": 0.09034644080056467,
      "grad_norm": 0.12173662334680557,
      "learning_rate": 1e-06,
      "loss": 0.0706,
      "step": 968
    },
    {
      "clip_ratio/high_max": 0.0023993426584638655,
      "clip_ratio/high_mean": 0.0011845326589536853,
      "clip_ratio/low_mean": 0.0016304294622386806,
      "clip_ratio/low_min": 0.00020578582552843727,
      "clip_ratio/region_mean": 0.002814962157572154,
      "epoch": 0.09043977390056525,
      "grad_norm": 0.11350627988576889,
      "learning_rate": 1e-06,
      "loss": 0.0065,
      "step": 969
    },
    {
      "clip_ratio/high_max": 0.0029194879898568615,
      "clip_ratio/high_mean": 0.0011662225224426948,
      "clip_ratio/low_mean": 0.0016439703431387898,
      "clip_ratio/low_min": 0.00023466075435862876,
      "clip_ratio/region_mean": 0.002810192854667548,
      "epoch": 0.09053310700056583,
      "grad_norm": 0.12750056385993958,
      "learning_rate": 1e-06,
      "loss": 0.0071,
      "step": 970
    },
    {
      "clip_ratio/high_max": 0.0023622112057637423,
      "clip_ratio/high_mean": 0.0010675961821107194,
      "clip_ratio/low_mean": 0.001563400134727999,
      "clip_ratio/low_min": 0.00018963728234666632,
      "clip_ratio/region_mean": 0.002630996285006404,
      "epoch": 0.09062644010056642,
      "grad_norm": 0.12649251520633698,
      "learning_rate": 1e-06,
      "loss": 0.0365,
      "step": 971
    },
    {
      "clip_ratio/high_max": 0.002768394253507722,
      "clip_ratio/high_mean": 0.0010969074101012666,
      "clip_ratio/low_mean": 0.0018255294125992805,
      "clip_ratio/low_min": 0.0001825466893023986,
      "clip_ratio/region_mean": 0.002922436877270229,
      "epoch": 0.090719773200567,
      "grad_norm": 1.3245729207992554,
      "learning_rate": 1e-06,
      "loss": 0.0403,
      "step": 972
    },
    {
      "clip_ratio/high_max": 0.0027267038167337887,
      "clip_ratio/high_mean": 0.0011833486423711292,
      "clip_ratio/low_mean": 0.00142173962740344,
      "clip_ratio/low_min": 6.574588041985407e-05,
      "clip_ratio/region_mean": 0.0026050882806885056,
      "epoch": 0.09081310630056758,
      "grad_norm": 0.3616175055503845,
      "learning_rate": 1e-06,
      "loss": -0.0108,
      "step": 973
    },
    {
      "clip_ratio/high_max": 0.0025984255189541727,
      "clip_ratio/high_mean": 0.0011566717439563945,
      "clip_ratio/low_mean": 0.0014222343779692892,
      "clip_ratio/low_min": 8.970064664026722e-05,
      "clip_ratio/region_mean": 0.002578906118287705,
      "epoch": 0.09090643940056817,
      "grad_norm": 0.11126550287008286,
      "learning_rate": 1e-06,
      "loss": 0.0367,
      "step": 974
    },
    {
      "clip_ratio/high_max": 0.0024302278252434917,
      "clip_ratio/high_mean": 0.0010615752034937032,
      "clip_ratio/low_mean": 0.001568183972267434,
      "clip_ratio/low_min": 0.00013949740286989254,
      "clip_ratio/region_mean": 0.0026297592266928405,
      "epoch": 0.09099977250056875,
      "grad_norm": 0.3150697946548462,
      "learning_rate": 1e-06,
      "loss": -0.0113,
      "step": 975
    },
    {
      "clip_ratio/high_max": 0.0028099539122194983,
      "clip_ratio/high_mean": 0.0011007877983502112,
      "clip_ratio/low_mean": 0.0017331377748632804,
      "clip_ratio/low_min": 0.00019785277436312754,
      "clip_ratio/region_mean": 0.0028339256459730677,
      "epoch": 0.09109310560056934,
      "grad_norm": 0.5172707438468933,
      "learning_rate": 1e-06,
      "loss": 0.0533,
      "step": 976
    },
    {
      "clip_ratio/high_max": 0.0024785328350844793,
      "clip_ratio/high_mean": 0.000984700021945173,
      "clip_ratio/low_mean": 0.0014817291230428964,
      "clip_ratio/low_min": 5.411065740190679e-05,
      "clip_ratio/region_mean": 0.0024664291049703024,
      "epoch": 0.09118643870056992,
      "grad_norm": 0.817656934261322,
      "learning_rate": 1e-06,
      "loss": 0.0412,
      "step": 977
    },
    {
      "clip_ratio/high_max": 0.002422324123472208,
      "clip_ratio/high_mean": 0.0009541405452182516,
      "clip_ratio/low_mean": 0.0015630449270247482,
      "clip_ratio/low_min": 0.000106721445263247,
      "clip_ratio/region_mean": 0.0025171855013468303,
      "epoch": 0.0912797718005705,
      "grad_norm": 41.40570831298828,
      "learning_rate": 1e-06,
      "loss": 0.0888,
      "step": 978
    },
    {
      "clip_ratio/high_max": 0.0018276834380230866,
      "clip_ratio/high_mean": 0.0008153427370416466,
      "clip_ratio/low_mean": 0.0015795414037711453,
      "clip_ratio/low_min": 0.00015140006962610641,
      "clip_ratio/region_mean": 0.0023948841626406647,
      "epoch": 0.09137310490057109,
      "grad_norm": 0.1352696567773819,
      "learning_rate": 1e-06,
      "loss": 0.1003,
      "step": 979
    },
    {
      "clip_ratio/high_max": 0.00261139221402118,
      "clip_ratio/high_mean": 0.0010639927131705917,
      "clip_ratio/low_mean": 0.0012667731461988296,
      "clip_ratio/low_min": 6.958876019780291e-05,
      "clip_ratio/region_mean": 0.002330765884835273,
      "epoch": 0.09146643800057166,
      "grad_norm": 0.22210972011089325,
      "learning_rate": 1e-06,
      "loss": 0.0286,
      "step": 980
    },
    {
      "clip_ratio/high_max": 0.002344028114748653,
      "clip_ratio/high_mean": 0.0011078451334469719,
      "clip_ratio/low_mean": 0.0013005328000872396,
      "clip_ratio/low_min": 0.0002134958303940948,
      "clip_ratio/region_mean": 0.0024083779571810737,
      "epoch": 0.09155977110057224,
      "grad_norm": 0.290182888507843,
      "learning_rate": 1e-06,
      "loss": 0.024,
      "step": 981
    },
    {
      "clip_ratio/high_max": 0.002362330043979455,
      "clip_ratio/high_mean": 0.0010354335499869194,
      "clip_ratio/low_mean": 0.0015081310884852428,
      "clip_ratio/low_min": 3.981289410148747e-05,
      "clip_ratio/region_mean": 0.0025435646675759926,
      "epoch": 0.09165310420057284,
      "grad_norm": 0.11489500850439072,
      "learning_rate": 1e-06,
      "loss": 0.0073,
      "step": 982
    },
    {
      "clip_ratio/high_max": 0.0024011111963773146,
      "clip_ratio/high_mean": 0.0010692693904275075,
      "clip_ratio/low_mean": 0.0012818294126191176,
      "clip_ratio/low_min": 8.829537273413735e-05,
      "clip_ratio/region_mean": 0.0023510988685302436,
      "epoch": 0.09174643730057341,
      "grad_norm": 0.8046979904174805,
      "learning_rate": 1e-06,
      "loss": -0.0101,
      "step": 983
    },
    {
      "clip_ratio/high_max": 0.0024106841083266772,
      "clip_ratio/high_mean": 0.0011014197516487911,
      "clip_ratio/low_mean": 0.0015164341930358205,
      "clip_ratio/low_min": 0.00013213888951213448,
      "clip_ratio/region_mean": 0.0026178538682870567,
      "epoch": 0.09183977040057399,
      "grad_norm": 0.998933732509613,
      "learning_rate": 1e-06,
      "loss": 0.0584,
      "step": 984
    },
    {
      "clip_ratio/high_max": 0.002503044313925784,
      "clip_ratio/high_mean": 0.0009758497963048285,
      "clip_ratio/low_mean": 0.0015415022608067375,
      "clip_ratio/low_min": 0.00011525819900271017,
      "clip_ratio/region_mean": 0.002517351989808958,
      "epoch": 0.09193310350057458,
      "grad_norm": 0.12569668889045715,
      "learning_rate": 1e-06,
      "loss": 0.0756,
      "step": 985
    },
    {
      "clip_ratio/high_max": 0.002325701185327489,
      "clip_ratio/high_mean": 0.0010083155830216128,
      "clip_ratio/low_mean": 0.0014818382514931727,
      "clip_ratio/low_min": 0.00012115579193050507,
      "clip_ratio/region_mean": 0.0024901538345147856,
      "epoch": 0.09202643660057516,
      "grad_norm": 0.1126972883939743,
      "learning_rate": 1e-06,
      "loss": 0.0079,
      "step": 986
    },
    {
      "clip_ratio/high_max": 0.002616191588458605,
      "clip_ratio/high_mean": 0.0010832682146428851,
      "clip_ratio/low_mean": 0.001513116068963427,
      "clip_ratio/low_min": 0.00022573885507881641,
      "clip_ratio/region_mean": 0.00259638435090892,
      "epoch": 0.09211976970057575,
      "grad_norm": 0.6002849340438843,
      "learning_rate": 1e-06,
      "loss": 0.0282,
      "step": 987
    },
    {
      "clip_ratio/high_max": 0.002155070767912548,
      "clip_ratio/high_mean": 0.0009797469447221374,
      "clip_ratio/low_mean": 0.00128266272804467,
      "clip_ratio/low_min": 3.6421747608983424e-05,
      "clip_ratio/region_mean": 0.002262409638206009,
      "epoch": 0.09221310280057633,
      "grad_norm": 0.31428274512290955,
      "learning_rate": 1e-06,
      "loss": 0.016,
      "step": 988
    },
    {
      "clip_ratio/high_max": 0.0022386796335922554,
      "clip_ratio/high_mean": 0.0009786887821974233,
      "clip_ratio/low_mean": 0.0012545868448796682,
      "clip_ratio/low_min": 7.038202784315217e-05,
      "clip_ratio/region_mean": 0.002233275656180922,
      "epoch": 0.09230643590057691,
      "grad_norm": 0.20584438741207123,
      "learning_rate": 1e-06,
      "loss": 0.0209,
      "step": 989
    },
    {
      "clip_ratio/high_max": 0.0023859011635067873,
      "clip_ratio/high_mean": 0.0010055982675112318,
      "clip_ratio/low_mean": 0.0012287222143640975,
      "clip_ratio/low_min": 5.5242478993022814e-05,
      "clip_ratio/region_mean": 0.0022343204545904882,
      "epoch": 0.0923997690005775,
      "grad_norm": 0.11135967075824738,
      "learning_rate": 1e-06,
      "loss": 0.039,
      "step": 990
    },
    {
      "clip_ratio/high_max": 0.0025239391688955948,
      "clip_ratio/high_mean": 0.0011136974571854807,
      "clip_ratio/low_mean": 0.0014366712784976698,
      "clip_ratio/low_min": 6.92541307216743e-05,
      "clip_ratio/region_mean": 0.0025503687793388963,
      "epoch": 0.09249310210057808,
      "grad_norm": 0.103728286921978,
      "learning_rate": 1e-06,
      "loss": 0.0186,
      "step": 991
    },
    {
      "clip_ratio/high_max": 0.002382981878326973,
      "clip_ratio/high_mean": 0.001031460136800888,
      "clip_ratio/low_mean": 0.0014163679115881678,
      "clip_ratio/low_min": 0.00012731249626085628,
      "clip_ratio/region_mean": 0.0024478280611219816,
      "epoch": 0.09258643520057866,
      "grad_norm": 0.24044102430343628,
      "learning_rate": 1e-06,
      "loss": 0.0198,
      "step": 992
    },
    {
      "clip_ratio/high_max": 0.0026172061407123692,
      "clip_ratio/high_mean": 0.0009421429385838564,
      "clip_ratio/low_mean": 0.001335981534793973,
      "clip_ratio/low_min": 0.00010563249452388845,
      "clip_ratio/region_mean": 0.002278124484291766,
      "epoch": 0.09267976830057925,
      "grad_norm": 0.10154741257429123,
      "learning_rate": 1e-06,
      "loss": 0.007,
      "step": 993
    },
    {
      "clip_ratio/high_max": 0.0028142588707851246,
      "clip_ratio/high_mean": 0.00115209560317453,
      "clip_ratio/low_mean": 0.0011584869298530975,
      "clip_ratio/low_min": 9.399178816238418e-05,
      "clip_ratio/region_mean": 0.0023105825457605533,
      "epoch": 0.09277310140057983,
      "grad_norm": 0.1097271591424942,
      "learning_rate": 1e-06,
      "loss": -0.0076,
      "step": 994
    },
    {
      "clip_ratio/high_max": 0.00263357119547436,
      "clip_ratio/high_mean": 0.0010795430353027768,
      "clip_ratio/low_mean": 0.0012707334881270071,
      "clip_ratio/low_min": 0.00012705187509709504,
      "clip_ratio/region_mean": 0.002350276510696858,
      "epoch": 0.09286643450058042,
      "grad_norm": 0.12392475455999374,
      "learning_rate": 1e-06,
      "loss": 0.0032,
      "step": 995
    },
    {
      "clip_ratio/high_max": 0.0021766968857264146,
      "clip_ratio/high_mean": 0.0010299709501850884,
      "clip_ratio/low_mean": 0.0013107002450851724,
      "clip_ratio/low_min": 7.586887659272179e-05,
      "clip_ratio/region_mean": 0.0023406712061841972,
      "epoch": 0.092959767600581,
      "grad_norm": 0.1134057343006134,
      "learning_rate": 1e-06,
      "loss": 0.0385,
      "step": 996
    },
    {
      "clip_ratio/high_max": 0.002529985169530846,
      "clip_ratio/high_mean": 0.001061465440216125,
      "clip_ratio/low_mean": 0.0014184961328282952,
      "clip_ratio/low_min": 2.5298522814409807e-05,
      "clip_ratio/region_mean": 0.0024799615057418123,
      "epoch": 0.09305310070058158,
      "grad_norm": 1.5392310619354248,
      "learning_rate": 1e-06,
      "loss": 0.016,
      "step": 997
    },
    {
      "clip_ratio/high_max": 0.0022402687682188116,
      "clip_ratio/high_mean": 0.0009063351972145028,
      "clip_ratio/low_mean": 0.0013951569526398089,
      "clip_ratio/low_min": 0.00018309052393306047,
      "clip_ratio/region_mean": 0.0023014921171125025,
      "epoch": 0.09314643380058217,
      "grad_norm": 0.2566203474998474,
      "learning_rate": 1e-06,
      "loss": 0.0497,
      "step": 998
    },
    {
      "clip_ratio/high_max": 0.0029917960782768205,
      "clip_ratio/high_mean": 0.0011093155371781904,
      "clip_ratio/low_mean": 0.0015334379640989937,
      "clip_ratio/low_min": 0.0001135174334194744,
      "clip_ratio/region_mean": 0.002642753519467078,
      "epoch": 0.09323976690058275,
      "grad_norm": 0.4379431903362274,
      "learning_rate": 1e-06,
      "loss": 0.0308,
      "step": 999
    },
    {
      "clip_ratio/high_max": 0.002529861143557355,
      "clip_ratio/high_mean": 0.0010291887756466167,
      "clip_ratio/low_mean": 0.0011212038825760828,
      "clip_ratio/low_min": 7.376048597507179e-05,
      "clip_ratio/region_mean": 0.0021503927127923816,
      "epoch": 0.09333310000058333,
      "grad_norm": 0.10886456072330475,
      "learning_rate": 1e-06,
      "loss": 0.0256,
      "step": 1000
    },
    {
      "clip_ratio/high_max": 0.00273510672559496,
      "clip_ratio/high_mean": 0.0010997926201525843,
      "clip_ratio/low_mean": 0.0014155381613818463,
      "clip_ratio/low_min": 0.00010484305948921246,
      "clip_ratio/region_mean": 0.0025153306996799074,
      "epoch": 0.09342643310058392,
      "grad_norm": 43.277496337890625,
      "learning_rate": 1e-06,
      "loss": 0.0458,
      "step": 1001
    },
    {
      "clip_ratio/high_max": 0.0024636176676722243,
      "clip_ratio/high_mean": 0.00110682215745328,
      "clip_ratio/low_mean": 0.001600837513251463,
      "clip_ratio/low_min": 0.00012456223976187175,
      "clip_ratio/region_mean": 0.002707659667066764,
      "epoch": 0.0935197662005845,
      "grad_norm": 0.9413765072822571,
      "learning_rate": 1e-06,
      "loss": 0.0069,
      "step": 1002
    },
    {
      "clip_ratio/high_max": 0.002407715051958803,
      "clip_ratio/high_mean": 0.0010900501874857582,
      "clip_ratio/low_mean": 0.0015839362204133067,
      "clip_ratio/low_min": 0.00021959385594527703,
      "clip_ratio/region_mean": 0.002673986404261086,
      "epoch": 0.09361309930058508,
      "grad_norm": 0.10675783455371857,
      "learning_rate": 1e-06,
      "loss": 0.0268,
      "step": 1003
    },
    {
      "clip_ratio/high_max": 0.002793648098304402,
      "clip_ratio/high_mean": 0.0010685122288123239,
      "clip_ratio/low_mean": 0.0017600591927475762,
      "clip_ratio/low_min": 0.00014434717922995333,
      "clip_ratio/region_mean": 0.0028285713924560696,
      "epoch": 0.09370643240058567,
      "grad_norm": 0.10406289994716644,
      "learning_rate": 1e-06,
      "loss": 0.0586,
      "step": 1004
    },
    {
      "clip_ratio/high_max": 0.0024772695105639286,
      "clip_ratio/high_mean": 0.001065781765646534,
      "clip_ratio/low_mean": 0.0014227735082386062,
      "clip_ratio/low_min": 0.00032432557964057196,
      "clip_ratio/region_mean": 0.0024885552484192885,
      "epoch": 0.09379976550058625,
      "grad_norm": 0.11525371670722961,
      "learning_rate": 1e-06,
      "loss": 0.0469,
      "step": 1005
    },
    {
      "clip_ratio/high_max": 0.0025516322639305145,
      "clip_ratio/high_mean": 0.0011065759535995312,
      "clip_ratio/low_mean": 0.001271146484214114,
      "clip_ratio/low_min": 0.00014019234367879108,
      "clip_ratio/region_mean": 0.002377722419623751,
      "epoch": 0.09389309860058684,
      "grad_norm": 0.11251242458820343,
      "learning_rate": 1e-06,
      "loss": -0.0035,
      "step": 1006
    },
    {
      "clip_ratio/high_max": 0.002637171965034213,
      "clip_ratio/high_mean": 0.0011244721918046707,
      "clip_ratio/low_mean": 0.0015851949101488572,
      "clip_ratio/low_min": 0.0001297859453188721,
      "clip_ratio/region_mean": 0.0027096670819446445,
      "epoch": 0.09398643170058742,
      "grad_norm": 0.15932558476924896,
      "learning_rate": 1e-06,
      "loss": 0.0122,
      "step": 1007
    },
    {
      "clip_ratio/high_max": 0.0025412279428564943,
      "clip_ratio/high_mean": 0.001115857761760708,
      "clip_ratio/low_mean": 0.001457088717870647,
      "clip_ratio/low_min": 5.219623926677741e-05,
      "clip_ratio/region_mean": 0.0025729465050972067,
      "epoch": 0.094079764800588,
      "grad_norm": 0.1427977830171585,
      "learning_rate": 1e-06,
      "loss": 0.0375,
      "step": 1008
    },
    {
      "clip_ratio/high_max": 0.0024408898389083333,
      "clip_ratio/high_mean": 0.0010944160057988483,
      "clip_ratio/low_mean": 0.0013344156905077398,
      "clip_ratio/low_min": 8.224411249102559e-05,
      "clip_ratio/region_mean": 0.0024288316490128636,
      "epoch": 0.09417309790058859,
      "grad_norm": 0.12036091089248657,
      "learning_rate": 1e-06,
      "loss": -0.0247,
      "step": 1009
    },
    {
      "clip_ratio/high_max": 0.0027292422091704793,
      "clip_ratio/high_mean": 0.0012204352824483067,
      "clip_ratio/low_mean": 0.001409094922564691,
      "clip_ratio/low_min": 0.00027870587655343115,
      "clip_ratio/region_mean": 0.0026295301868231036,
      "epoch": 0.09426643100058917,
      "grad_norm": 1.0272916555404663,
      "learning_rate": 1e-06,
      "loss": -0.0266,
      "step": 1010
    },
    {
      "clip_ratio/high_max": 0.0021359871607273817,
      "clip_ratio/high_mean": 0.0009000364843814168,
      "clip_ratio/low_mean": 0.0014012872234161478,
      "clip_ratio/low_min": 7.746000665065367e-05,
      "clip_ratio/region_mean": 0.002301323736901395,
      "epoch": 0.09435976410058974,
      "grad_norm": 0.10471700131893158,
      "learning_rate": 1e-06,
      "loss": 0.0078,
      "step": 1011
    },
    {
      "clip_ratio/high_max": 0.002750959429249633,
      "clip_ratio/high_mean": 0.0010999839396390598,
      "clip_ratio/low_mean": 0.0016230285182246007,
      "clip_ratio/low_min": 4.658384932554327e-05,
      "clip_ratio/region_mean": 0.002723012526985258,
      "epoch": 0.09445309720059034,
      "grad_norm": 0.15478749573230743,
      "learning_rate": 1e-06,
      "loss": 0.0206,
      "step": 1012
    },
    {
      "clip_ratio/high_max": 0.0022105910247773863,
      "clip_ratio/high_mean": 0.0009340969882032368,
      "clip_ratio/low_mean": 0.0017193727508129086,
      "clip_ratio/low_min": 0.00027211768792767543,
      "clip_ratio/region_mean": 0.0026534697244642302,
      "epoch": 0.09454643030059091,
      "grad_norm": 0.21624431014060974,
      "learning_rate": 1e-06,
      "loss": 0.0804,
      "step": 1013
    },
    {
      "clip_ratio/high_max": 0.002289614134497242,
      "clip_ratio/high_mean": 0.00099690524439211,
      "clip_ratio/low_mean": 0.0016533989928575465,
      "clip_ratio/low_min": 0.0002077474164252635,
      "clip_ratio/region_mean": 0.0026503042681724764,
      "epoch": 0.09463976340059149,
      "grad_norm": 0.15156012773513794,
      "learning_rate": 1e-06,
      "loss": 0.0416,
      "step": 1014
    },
    {
      "clip_ratio/high_max": 0.00254740835953271,
      "clip_ratio/high_mean": 0.001091957510652719,
      "clip_ratio/low_mean": 0.0013925210241723107,
      "clip_ratio/low_min": 7.374403958237963e-05,
      "clip_ratio/region_mean": 0.002484478522092104,
      "epoch": 0.09473309650059208,
      "grad_norm": 0.36712679266929626,
      "learning_rate": 1e-06,
      "loss": 0.0462,
      "step": 1015
    },
    {
      "clip_ratio/high_max": 0.002153635083232075,
      "clip_ratio/high_mean": 0.000936221453230246,
      "clip_ratio/low_mean": 0.001566298284160439,
      "clip_ratio/low_min": 0.0002341756844543852,
      "clip_ratio/region_mean": 0.0025025196955539286,
      "epoch": 0.09482642960059266,
      "grad_norm": 0.19550590217113495,
      "learning_rate": 1e-06,
      "loss": 0.0636,
      "step": 1016
    },
    {
      "clip_ratio/high_max": 0.0023482123142457567,
      "clip_ratio/high_mean": 0.0009431124162802007,
      "clip_ratio/low_mean": 0.0014192474154697265,
      "clip_ratio/low_min": 0.00010341357301513199,
      "clip_ratio/region_mean": 0.002362359802646097,
      "epoch": 0.09491976270059325,
      "grad_norm": 0.23598073422908783,
      "learning_rate": 1e-06,
      "loss": 0.0211,
      "step": 1017
    },
    {
      "clip_ratio/high_max": 0.0027490474603837356,
      "clip_ratio/high_mean": 0.0010602396905596834,
      "clip_ratio/low_mean": 0.001699717657174915,
      "clip_ratio/low_min": 0.00023243802570505068,
      "clip_ratio/region_mean": 0.002759957358648535,
      "epoch": 0.09501309580059383,
      "grad_norm": 0.7179739475250244,
      "learning_rate": 1e-06,
      "loss": 0.0415,
      "step": 1018
    },
    {
      "clip_ratio/high_max": 0.002744025732681621,
      "clip_ratio/high_mean": 0.001063942392647732,
      "clip_ratio/low_mean": 0.0014018245601619128,
      "clip_ratio/low_min": 0.00014277450191002572,
      "clip_ratio/region_mean": 0.0024657669055159204,
      "epoch": 0.09510642890059441,
      "grad_norm": 0.1302684247493744,
      "learning_rate": 1e-06,
      "loss": 0.0016,
      "step": 1019
    },
    {
      "clip_ratio/high_max": 0.0024234028824139386,
      "clip_ratio/high_mean": 0.0010589727171463892,
      "clip_ratio/low_mean": 0.0016759285281295888,
      "clip_ratio/low_min": 5.259621684672311e-05,
      "clip_ratio/region_mean": 0.0027349011943442747,
      "epoch": 0.095199762000595,
      "grad_norm": 0.20395095646381378,
      "learning_rate": 1e-06,
      "loss": 0.0386,
      "step": 1020
    },
    {
      "clip_ratio/high_max": 0.0026095060384250246,
      "clip_ratio/high_mean": 0.0009672060405137017,
      "clip_ratio/low_mean": 0.0015556010039290413,
      "clip_ratio/low_min": 3.430506694712676e-05,
      "clip_ratio/region_mean": 0.0025228070953744464,
      "epoch": 0.09529309510059558,
      "grad_norm": 0.1260862648487091,
      "learning_rate": 1e-06,
      "loss": 0.0377,
      "step": 1021
    },
    {
      "clip_ratio/high_max": 0.0027780027958215214,
      "clip_ratio/high_mean": 0.0011060325232392643,
      "clip_ratio/low_mean": 0.0015691542794229463,
      "clip_ratio/low_min": 0.00020678279452113202,
      "clip_ratio/region_mean": 0.002675186849955935,
      "epoch": 0.09538642820059616,
      "grad_norm": 0.1276027113199234,
      "learning_rate": 1e-06,
      "loss": 0.0177,
      "step": 1022
    },
    {
      "clip_ratio/high_max": 0.0025821499148150906,
      "clip_ratio/high_mean": 0.0011101393720309716,
      "clip_ratio/low_mean": 0.0013182413022150286,
      "clip_ratio/low_min": 0.0001094849712899304,
      "clip_ratio/region_mean": 0.0024283806851599365,
      "epoch": 0.09547976130059675,
      "grad_norm": 1.5559098720550537,
      "learning_rate": 1e-06,
      "loss": 0.0159,
      "step": 1023
    },
    {
      "clip_ratio/high_max": 0.0022457818704424426,
      "clip_ratio/high_mean": 0.0010378893275628798,
      "clip_ratio/low_mean": 0.0014103770954534411,
      "clip_ratio/low_min": 8.981925384432543e-05,
      "clip_ratio/region_mean": 0.0024482663720846176,
      "epoch": 0.09557309440059733,
      "grad_norm": 0.10609094053506851,
      "learning_rate": 1e-06,
      "loss": 0.0027,
      "step": 1024
    },
    {
      "clip_ratio/high_max": 0.0028740140041918494,
      "clip_ratio/high_mean": 0.0011669460982375313,
      "clip_ratio/low_mean": 0.0016561232987442054,
      "clip_ratio/low_min": 0.0002337534406251507,
      "clip_ratio/region_mean": 0.002823069429723546,
      "epoch": 0.09566642750059791,
      "grad_norm": 0.17098350822925568,
      "learning_rate": 1e-06,
      "loss": 0.0291,
      "step": 1025
    },
    {
      "clip_ratio/high_max": 0.0022569885732082184,
      "clip_ratio/high_mean": 0.0009531265550322132,
      "clip_ratio/low_mean": 0.001427520764991641,
      "clip_ratio/low_min": 0.0001411345147062093,
      "clip_ratio/region_mean": 0.00238064733275678,
      "epoch": 0.0957597606005985,
      "grad_norm": 0.11011157184839249,
      "learning_rate": 1e-06,
      "loss": 0.0316,
      "step": 1026
    },
    {
      "clip_ratio/high_max": 0.0026150273261009715,
      "clip_ratio/high_mean": 0.0010006312004406936,
      "clip_ratio/low_mean": 0.0014856450470688287,
      "clip_ratio/low_min": 0.0001168062153737992,
      "clip_ratio/region_mean": 0.0024862762875272892,
      "epoch": 0.09585309370059908,
      "grad_norm": 0.7985674142837524,
      "learning_rate": 1e-06,
      "loss": 0.0138,
      "step": 1027
    },
    {
      "clip_ratio/high_max": 0.0026076947142428253,
      "clip_ratio/high_mean": 0.0010348516934755025,
      "clip_ratio/low_mean": 0.001373599618091248,
      "clip_ratio/low_min": 5.559255259868223e-05,
      "clip_ratio/region_mean": 0.0024084513643174432,
      "epoch": 0.09594642680059967,
      "grad_norm": 0.12488450109958649,
      "learning_rate": 1e-06,
      "loss": -0.0003,
      "step": 1028
    },
    {
      "clip_ratio/high_max": 0.0024484193927492015,
      "clip_ratio/high_mean": 0.0010525511352170724,
      "clip_ratio/low_mean": 0.0017963830769076594,
      "clip_ratio/low_min": 0.0001597672871866962,
      "clip_ratio/region_mean": 0.002848934345820453,
      "epoch": 0.09603975990060025,
      "grad_norm": 0.16543079912662506,
      "learning_rate": 1e-06,
      "loss": 0.0302,
      "step": 1029
    },
    {
      "clip_ratio/high_max": 0.002799492249323521,
      "clip_ratio/high_mean": 0.0011888555345649365,
      "clip_ratio/low_mean": 0.0010550299421083764,
      "clip_ratio/low_min": 2.1349958842620254e-05,
      "clip_ratio/region_mean": 0.002243885443022009,
      "epoch": 0.09613309300060083,
      "grad_norm": 0.11115060746669769,
      "learning_rate": 1e-06,
      "loss": -0.0416,
      "step": 1030
    },
    {
      "clip_ratio/high_max": 0.002123236368788639,
      "clip_ratio/high_mean": 0.0009793448716663988,
      "clip_ratio/low_mean": 0.0012815610425604973,
      "clip_ratio/low_min": 8.41796818349394e-05,
      "clip_ratio/region_mean": 0.002260905850562267,
      "epoch": 0.09622642610060142,
      "grad_norm": 0.11418361961841583,
      "learning_rate": 1e-06,
      "loss": -0.0207,
      "step": 1031
    },
    {
      "clip_ratio/high_max": 0.0026167353498749435,
      "clip_ratio/high_mean": 0.0011643699035630561,
      "clip_ratio/low_mean": 0.0014643017857451923,
      "clip_ratio/low_min": 8.175284892786294e-05,
      "clip_ratio/region_mean": 0.0026286716529284604,
      "epoch": 0.096319759200602,
      "grad_norm": 6.70403528213501,
      "learning_rate": 1e-06,
      "loss": 0.0167,
      "step": 1032
    },
    {
      "clip_ratio/high_max": 0.0023788318503648043,
      "clip_ratio/high_mean": 0.001081062542652944,
      "clip_ratio/low_mean": 0.001619060025404906,
      "clip_ratio/low_min": 9.49936656979844e-05,
      "clip_ratio/region_mean": 0.002700122509850189,
      "epoch": 0.09641309230060258,
      "grad_norm": 0.11737395823001862,
      "learning_rate": 1e-06,
      "loss": 0.0376,
      "step": 1033
    },
    {
      "clip_ratio/high_max": 0.0024865820232662372,
      "clip_ratio/high_mean": 0.0010667846618162002,
      "clip_ratio/low_mean": 0.0015340850986831356,
      "clip_ratio/low_min": 0.00015708232058386784,
      "clip_ratio/region_mean": 0.0026008698259829544,
      "epoch": 0.09650642540060317,
      "grad_norm": 0.11282369494438171,
      "learning_rate": 1e-06,
      "loss": 0.011,
      "step": 1034
    },
    {
      "clip_ratio/high_max": 0.0024976714412332512,
      "clip_ratio/high_mean": 0.0011453477200120687,
      "clip_ratio/low_mean": 0.001466803752919077,
      "clip_ratio/low_min": 9.28330046008341e-05,
      "clip_ratio/region_mean": 0.0026121515038539656,
      "epoch": 0.09659975850060375,
      "grad_norm": 2.127736806869507,
      "learning_rate": 1e-06,
      "loss": 0.0361,
      "step": 1035
    },
    {
      "clip_ratio/high_max": 0.002254596503917128,
      "clip_ratio/high_mean": 0.0010046278730442282,
      "clip_ratio/low_mean": 0.001678002932749223,
      "clip_ratio/low_min": 0.0002276703821735282,
      "clip_ratio/region_mean": 0.0026826307584997267,
      "epoch": 0.09669309160060433,
      "grad_norm": 0.1636512130498886,
      "learning_rate": 1e-06,
      "loss": 0.0349,
      "step": 1036
    },
    {
      "clip_ratio/high_max": 0.0026917438226519153,
      "clip_ratio/high_mean": 0.0010972836971632205,
      "clip_ratio/low_mean": 0.0012886290951428236,
      "clip_ratio/low_min": 8.287899800052401e-05,
      "clip_ratio/region_mean": 0.002385912826866843,
      "epoch": 0.09678642470060492,
      "grad_norm": 0.10557028651237488,
      "learning_rate": 1e-06,
      "loss": 0.016,
      "step": 1037
    },
    {
      "clip_ratio/high_max": 0.0021997827006998705,
      "clip_ratio/high_mean": 0.0009391536532348255,
      "clip_ratio/low_mean": 0.0017274617857765406,
      "clip_ratio/low_min": 0.00034551463068055455,
      "clip_ratio/region_mean": 0.0026666154371923767,
      "epoch": 0.0968797578006055,
      "grad_norm": 0.12786470353603363,
      "learning_rate": 1e-06,
      "loss": 0.0214,
      "step": 1038
    },
    {
      "clip_ratio/high_max": 0.0024857334574335255,
      "clip_ratio/high_mean": 0.0009328208161605289,
      "clip_ratio/low_mean": 0.0014514240938297007,
      "clip_ratio/low_min": 3.765109431697056e-05,
      "clip_ratio/region_mean": 0.0023842448863433674,
      "epoch": 0.09697309090060609,
      "grad_norm": 0.1199268326163292,
      "learning_rate": 1e-06,
      "loss": 0.0579,
      "step": 1039
    },
    {
      "clip_ratio/high_max": 0.0027313846221659333,
      "clip_ratio/high_mean": 0.001156201626145048,
      "clip_ratio/low_mean": 0.001556612209242303,
      "clip_ratio/low_min": 6.832637154730037e-05,
      "clip_ratio/region_mean": 0.0027128137517138384,
      "epoch": 0.09706642400060667,
      "grad_norm": 0.13708259165287018,
      "learning_rate": 1e-06,
      "loss": -0.006,
      "step": 1040
    },
    {
      "clip_ratio/high_max": 0.0024884929007384926,
      "clip_ratio/high_mean": 0.0010645560869306792,
      "clip_ratio/low_mean": 0.0014780164892727043,
      "clip_ratio/low_min": 0.00013456806209433125,
      "clip_ratio/region_mean": 0.002542572532547638,
      "epoch": 0.09715975710060724,
      "grad_norm": 0.12088126689195633,
      "learning_rate": 1e-06,
      "loss": -0.0005,
      "step": 1041
    },
    {
      "clip_ratio/high_max": 0.002451437816489488,
      "clip_ratio/high_mean": 0.0010310456145816715,
      "clip_ratio/low_mean": 0.0017180982686113566,
      "clip_ratio/low_min": 0.00020637681336665992,
      "clip_ratio/region_mean": 0.002749143859546166,
      "epoch": 0.09725309020060784,
      "grad_norm": 0.12734945118427277,
      "learning_rate": 1e-06,
      "loss": 0.0598,
      "step": 1042
    },
    {
      "clip_ratio/high_max": 0.0024859129698597826,
      "clip_ratio/high_mean": 0.0009966537127183983,
      "clip_ratio/low_mean": 0.0019490449649310904,
      "clip_ratio/low_min": 0.00012581245209730696,
      "clip_ratio/region_mean": 0.002945698710391298,
      "epoch": 0.09734642330060841,
      "grad_norm": 3.4777934551239014,
      "learning_rate": 1e-06,
      "loss": 0.042,
      "step": 1043
    },
    {
      "clip_ratio/high_max": 0.0023609272102476098,
      "clip_ratio/high_mean": 0.0010063399295177078,
      "clip_ratio/low_mean": 0.0016369394943467341,
      "clip_ratio/low_min": 0.00016572749882470816,
      "clip_ratio/region_mean": 0.0026432793820276856,
      "epoch": 0.09743975640060899,
      "grad_norm": 0.19785448908805847,
      "learning_rate": 1e-06,
      "loss": 0.0825,
      "step": 1044
    },
    {
      "clip_ratio/high_max": 0.0019945313106290996,
      "clip_ratio/high_mean": 0.0008731581419851864,
      "clip_ratio/low_mean": 0.0016990704716590699,
      "clip_ratio/low_min": 0.0002243034559796797,
      "clip_ratio/region_mean": 0.002572228586359415,
      "epoch": 0.09753308950060958,
      "grad_norm": 0.13721875846385956,
      "learning_rate": 1e-06,
      "loss": 0.052,
      "step": 1045
    },
    {
      "clip_ratio/high_max": 0.0022703743015881628,
      "clip_ratio/high_mean": 0.0009585947482264601,
      "clip_ratio/low_mean": 0.0017468062724219635,
      "clip_ratio/low_min": 0.00012227893603267148,
      "clip_ratio/region_mean": 0.002705401049752254,
      "epoch": 0.09762642260061016,
      "grad_norm": 0.1105123832821846,
      "learning_rate": 1e-06,
      "loss": 0.0589,
      "step": 1046
    },
    {
      "clip_ratio/high_max": 0.002762889016594272,
      "clip_ratio/high_mean": 0.0010930320095212664,
      "clip_ratio/low_mean": 0.0017191348488267977,
      "clip_ratio/low_min": 0.0002919521739386255,
      "clip_ratio/region_mean": 0.002812166785588488,
      "epoch": 0.09771975570061076,
      "grad_norm": 3.411590337753296,
      "learning_rate": 1e-06,
      "loss": 0.0427,
      "step": 1047
    },
    {
      "clip_ratio/high_max": 0.002408101012406405,
      "clip_ratio/high_mean": 0.0011082909841206856,
      "clip_ratio/low_mean": 0.0014730837247043382,
      "clip_ratio/low_min": 6.010919787513558e-05,
      "clip_ratio/region_mean": 0.0025813747488427907,
      "epoch": 0.09781308880061133,
      "grad_norm": 0.1541268527507782,
      "learning_rate": 1e-06,
      "loss": -0.0011,
      "step": 1048
    },
    {
      "clip_ratio/high_max": 0.0025276943488279358,
      "clip_ratio/high_mean": 0.0010492534638615325,
      "clip_ratio/low_mean": 0.0015621190177625977,
      "clip_ratio/low_min": 0.0002017591305047972,
      "clip_ratio/region_mean": 0.0026113725107279606,
      "epoch": 0.09790642190061191,
      "grad_norm": 0.7781962156295776,
      "learning_rate": 1e-06,
      "loss": 0.0434,
      "step": 1049
    },
    {
      "clip_ratio/high_max": 0.0020950286561856046,
      "clip_ratio/high_mean": 0.0010302228583896067,
      "clip_ratio/low_mean": 0.001510117119323695,
      "clip_ratio/low_min": 0.0001770286335158744,
      "clip_ratio/region_mean": 0.0025403399995411746,
      "epoch": 0.0979997550006125,
      "grad_norm": 1.9998055696487427,
      "learning_rate": 1e-06,
      "loss": 0.029,
      "step": 1050
    },
    {
      "clip_ratio/high_max": 0.0023859030116000213,
      "clip_ratio/high_mean": 0.0011139920188725227,
      "clip_ratio/low_mean": 0.001309117658820469,
      "clip_ratio/low_min": 7.262455801537726e-05,
      "clip_ratio/region_mean": 0.002423109697701875,
      "epoch": 0.09809308810061308,
      "grad_norm": 0.10248728841543198,
      "learning_rate": 1e-06,
      "loss": -0.0248,
      "step": 1051
    },
    {
      "clip_ratio/high_max": 0.002476397618011106,
      "clip_ratio/high_mean": 0.0010308366472600028,
      "clip_ratio/low_mean": 0.0016942097463470418,
      "clip_ratio/low_min": 0.00016970499382296111,
      "clip_ratio/region_mean": 0.0027250464117969386,
      "epoch": 0.09818642120061366,
      "grad_norm": 0.8370645642280579,
      "learning_rate": 1e-06,
      "loss": 0.0219,
      "step": 1052
    },
    {
      "clip_ratio/high_max": 0.002790626353089465,
      "clip_ratio/high_mean": 0.0010914618642345886,
      "clip_ratio/low_mean": 0.0014964292495278642,
      "clip_ratio/low_min": 0.00016038402463891543,
      "clip_ratio/region_mean": 0.0025878911474137567,
      "epoch": 0.09827975430061425,
      "grad_norm": 0.12005890160799026,
      "learning_rate": 1e-06,
      "loss": 0.0197,
      "step": 1053
    },
    {
      "clip_ratio/high_max": 0.002567402145359665,
      "clip_ratio/high_mean": 0.0010272291983710602,
      "clip_ratio/low_mean": 0.0017165825884148944,
      "clip_ratio/low_min": 0.00010195728646067437,
      "clip_ratio/region_mean": 0.0027438118268037215,
      "epoch": 0.09837308740061483,
      "grad_norm": 0.3239002823829651,
      "learning_rate": 1e-06,
      "loss": 0.0266,
      "step": 1054
    },
    {
      "clip_ratio/high_max": 0.002806235548632685,
      "clip_ratio/high_mean": 0.0011477070383989485,
      "clip_ratio/low_mean": 0.0015595470067637507,
      "clip_ratio/low_min": 0.00023611872438777937,
      "clip_ratio/region_mean": 0.002707254076085519,
      "epoch": 0.09846642050061541,
      "grad_norm": 0.11918503791093826,
      "learning_rate": 1e-06,
      "loss": 0.0322,
      "step": 1055
    },
    {
      "clip_ratio/high_max": 0.0020969543620594777,
      "clip_ratio/high_mean": 0.0009565349537297152,
      "clip_ratio/low_mean": 0.0016179051890503615,
      "clip_ratio/low_min": 0.000247909571044147,
      "clip_ratio/region_mean": 0.002574440120952204,
      "epoch": 0.098559753600616,
      "grad_norm": 0.34376922249794006,
      "learning_rate": 1e-06,
      "loss": 0.0296,
      "step": 1056
    },
    {
      "clip_ratio/high_max": 0.0026545548280410003,
      "clip_ratio/high_mean": 0.001156085809270735,
      "clip_ratio/low_mean": 0.0009134982683463022,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002069584108539857,
      "completions/clipped_ratio": 0.011631556919642905,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4095.0,
      "completions/mean_length": 600.4644775390625,
      "completions/mean_terminated_length": 559.3274536132812,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.09865308670061658,
      "grad_norm": 19376.447265625,
      "learning_rate": 1e-06,
      "loss": 543.0246,
      "num_tokens": 812901776.0,
      "reward": 0.581551730632782,
      "reward_std": 0.1905154287815094,
      "rewards/simpleverify_reward/mean": 0.5815516710281372,
      "rewards/simpleverify_reward/std": 0.4933067262172699,
      "step": 1057
    },
    {
      "clip_ratio/high_max": 0.0027160520912730135,
      "clip_ratio/high_mean": 0.001073583527613664,
      "clip_ratio/low_mean": 0.0010691176757973153,
      "clip_ratio/low_min": 7.919052404758986e-05,
      "clip_ratio/region_mean": 0.002142701174307149,
      "epoch": 0.09874641980061717,
      "grad_norm": 66346643456.0,
      "learning_rate": 1e-06,
      "loss": 10626219.0,
      "step": 1058
    },
    {
      "clip_ratio/high_max": 0.0030447074823314324,
      "clip_ratio/high_mean": 0.0011915833711100277,
      "clip_ratio/low_mean": 0.0009738258686411427,
      "clip_ratio/low_min": 4.312604050937807e-05,
      "clip_ratio/region_mean": 0.0021654092997778207,
      "epoch": 0.09883975290061775,
      "grad_norm": 89.51912689208984,
      "learning_rate": 1e-06,
      "loss": 0.1202,
      "step": 1059
    },
    {
      "clip_ratio/high_max": 0.0026044099940918386,
      "clip_ratio/high_mean": 0.0011421316157793626,
      "clip_ratio/low_mean": 0.0010248394537484273,
      "clip_ratio/low_min": 0.00012890936523035634,
      "clip_ratio/region_mean": 0.0021669710549758747,
      "epoch": 0.09893308600061833,
      "grad_norm": 70.45943450927734,
      "learning_rate": 1e-06,
      "loss": 0.0545,
      "step": 1060
    },
    {
      "clip_ratio/high_max": 0.0026771254342747852,
      "clip_ratio/high_mean": 0.0011095823210780509,
      "clip_ratio/low_mean": 0.001226841739480733,
      "clip_ratio/low_min": 0.00021057507183286361,
      "clip_ratio/region_mean": 0.0023364240551018156,
      "epoch": 0.09902641910061892,
      "grad_norm": 158818.5,
      "learning_rate": 1e-06,
      "loss": 18.1625,
      "step": 1061
    },
    {
      "clip_ratio/high_max": 0.0028003475308651105,
      "clip_ratio/high_mean": 0.0011146185552206589,
      "clip_ratio/low_mean": 0.0010491998546058312,
      "clip_ratio/low_min": 0.00010102821215696167,
      "clip_ratio/region_mean": 0.0021638184334733523,
      "epoch": 0.0991197522006195,
      "grad_norm": 254.01470947265625,
      "learning_rate": 1e-06,
      "loss": 0.7729,
      "step": 1062
    },
    {
      "clip_ratio/high_max": 0.0029343472051550634,
      "clip_ratio/high_mean": 0.001039605114783626,
      "clip_ratio/low_mean": 0.0010474810605956009,
      "clip_ratio/low_min": 2.8839199330832344e-05,
      "clip_ratio/region_mean": 0.0020870862063020468,
      "epoch": 0.09921308530062008,
      "grad_norm": 91345.3515625,
      "learning_rate": 1e-06,
      "loss": 39.5631,
      "step": 1063
    },
    {
      "clip_ratio/high_max": 0.0027216048329137266,
      "clip_ratio/high_mean": 0.0011726452285074629,
      "clip_ratio/low_mean": 0.0010962007545458619,
      "clip_ratio/low_min": 8.783598241279833e-05,
      "clip_ratio/region_mean": 0.002268845957587473,
      "epoch": 0.09930641840062067,
      "grad_norm": 0.4986717402935028,
      "learning_rate": 1e-06,
      "loss": 0.0023,
      "step": 1064
    },
    {
      "clip_ratio/high_max": 0.0031283964417525567,
      "clip_ratio/high_mean": 0.001216457396367332,
      "clip_ratio/low_mean": 0.0012029144691041438,
      "clip_ratio/low_min": 9.832020987232681e-05,
      "clip_ratio/region_mean": 0.0024193718636524864,
      "epoch": 0.09939975150062125,
      "grad_norm": 11.444372177124023,
      "learning_rate": 1e-06,
      "loss": 0.0429,
      "step": 1065
    },
    {
      "clip_ratio/high_max": 0.0027087220732937567,
      "clip_ratio/high_mean": 0.0011457652872195467,
      "clip_ratio/low_mean": 0.001239418390468927,
      "clip_ratio/low_min": 0.00011277338217041688,
      "clip_ratio/region_mean": 0.0023851836886024103,
      "epoch": 0.09949308460062183,
      "grad_norm": 0.13417837023735046,
      "learning_rate": 1e-06,
      "loss": 0.0297,
      "step": 1066
    },
    {
      "clip_ratio/high_max": 0.0024075435285340063,
      "clip_ratio/high_mean": 0.0010678663129510824,
      "clip_ratio/low_mean": 0.0011138090485474095,
      "clip_ratio/low_min": 7.473115692846477e-05,
      "clip_ratio/region_mean": 0.0021816753142047673,
      "epoch": 0.09958641770062242,
      "grad_norm": 0.11461979895830154,
      "learning_rate": 1e-06,
      "loss": 0.0398,
      "step": 1067
    },
    {
      "clip_ratio/high_max": 0.0030587448563892394,
      "clip_ratio/high_mean": 0.001280219843465602,
      "clip_ratio/low_mean": 0.00138875340053346,
      "clip_ratio/low_min": 0.00014916058535163756,
      "clip_ratio/region_mean": 0.0026689731821534224,
      "epoch": 0.099679750800623,
      "grad_norm": 82.8593978881836,
      "learning_rate": 1e-06,
      "loss": 0.0404,
      "step": 1068
    },
    {
      "clip_ratio/high_max": 0.0026132461498491466,
      "clip_ratio/high_mean": 0.0010389417220721953,
      "clip_ratio/low_mean": 0.0012845349720009835,
      "clip_ratio/low_min": 9.349343963549472e-05,
      "clip_ratio/region_mean": 0.0023234767286339775,
      "epoch": 0.09977308390062359,
      "grad_norm": 63.38811111450195,
      "learning_rate": 1e-06,
      "loss": 0.0582,
      "step": 1069
    },
    {
      "clip_ratio/high_max": 0.0028535951023513917,
      "clip_ratio/high_mean": 0.001180681476398604,
      "clip_ratio/low_mean": 0.0015972310829965863,
      "clip_ratio/low_min": 0.00032978928356897086,
      "clip_ratio/region_mean": 0.0027779125375673175,
      "epoch": 0.09986641700062417,
      "grad_norm": 0.11527776718139648,
      "learning_rate": 1e-06,
      "loss": 0.0521,
      "step": 1070
    },
    {
      "clip_ratio/high_max": 0.0027820640680147335,
      "clip_ratio/high_mean": 0.0011365437912900234,
      "clip_ratio/low_mean": 0.001479933565860847,
      "clip_ratio/low_min": 0.00015167714263952803,
      "clip_ratio/region_mean": 0.0026164773662458174,
      "epoch": 0.09995975010062474,
      "grad_norm": 4.616727352142334,
      "learning_rate": 1e-06,
      "loss": 0.0673,
      "step": 1071
    },
    {
      "clip_ratio/high_max": 0.002767252881312743,
      "clip_ratio/high_mean": 0.0011979056762356777,
      "clip_ratio/low_mean": 0.0013403817683865782,
      "clip_ratio/low_min": 3.452340661169728e-05,
      "clip_ratio/region_mean": 0.002538287459174171,
      "epoch": 0.10005308320062534,
      "grad_norm": 0.4958588182926178,
      "learning_rate": 1e-06,
      "loss": 0.0332,
      "step": 1072
    },
    {
      "clip_ratio/high_max": 0.0024288301792694256,
      "clip_ratio/high_mean": 0.0010714032978285104,
      "clip_ratio/low_mean": 0.0016034773434512317,
      "clip_ratio/low_min": 0.00019295911351946415,
      "clip_ratio/region_mean": 0.00267488067765953,
      "epoch": 0.10014641630062592,
      "grad_norm": 0.11871877312660217,
      "learning_rate": 1e-06,
      "loss": 0.026,
      "step": 1073
    },
    {
      "clip_ratio/high_max": 0.0027953477183473296,
      "clip_ratio/high_mean": 0.0011518957808220875,
      "clip_ratio/low_mean": 0.0014157051155052613,
      "clip_ratio/low_min": 0.00021085304251755588,
      "clip_ratio/region_mean": 0.0025676008881418966,
      "epoch": 0.1002397494006265,
      "grad_norm": 0.1406594067811966,
      "learning_rate": 1e-06,
      "loss": 0.0442,
      "step": 1074
    },
    {
      "clip_ratio/high_max": 0.0030373085974133573,
      "clip_ratio/high_mean": 0.001308071288804058,
      "clip_ratio/low_mean": 0.0016581290401518345,
      "clip_ratio/low_min": 0.0002750885123532498,
      "clip_ratio/region_mean": 0.0029662003071280196,
      "epoch": 0.10033308250062709,
      "grad_norm": 0.12567895650863647,
      "learning_rate": 1e-06,
      "loss": 0.0292,
      "step": 1075
    },
    {
      "clip_ratio/high_max": 0.003033902816241607,
      "clip_ratio/high_mean": 0.0010880818226723932,
      "clip_ratio/low_mean": 0.0017523367241665255,
      "clip_ratio/low_min": 0.00022834419814898865,
      "clip_ratio/region_mean": 0.0028404185868566856,
      "epoch": 0.10042641560062766,
      "grad_norm": 8.243338584899902,
      "learning_rate": 1e-06,
      "loss": 0.0674,
      "step": 1076
    },
    {
      "clip_ratio/high_max": 0.003005389546160586,
      "clip_ratio/high_mean": 0.0012947889335919172,
      "clip_ratio/low_mean": 0.0017762050847522914,
      "clip_ratio/low_min": 8.96064484550152e-05,
      "clip_ratio/region_mean": 0.0030709940619999543,
      "epoch": 0.10051974870062824,
      "grad_norm": 0.4808621406555176,
      "learning_rate": 1e-06,
      "loss": 0.0332,
      "step": 1077
    },
    {
      "clip_ratio/high_max": 0.003207053247024305,
      "clip_ratio/high_mean": 0.001290653926844243,
      "clip_ratio/low_mean": 0.0013424466233118437,
      "clip_ratio/low_min": 0.00015511627316300292,
      "clip_ratio/region_mean": 0.002633100564708002,
      "epoch": 0.10061308180062883,
      "grad_norm": 0.43675824999809265,
      "learning_rate": 1e-06,
      "loss": -0.0176,
      "step": 1078
    },
    {
      "clip_ratio/high_max": 0.002586764945590403,
      "clip_ratio/high_mean": 0.0011011242331733229,
      "clip_ratio/low_mean": 0.0015010885035735555,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002602212734927889,
      "epoch": 0.10070641490062941,
      "grad_norm": 15.26230525970459,
      "learning_rate": 1e-06,
      "loss": 0.0389,
      "step": 1079
    },
    {
      "clip_ratio/high_max": 0.0032891732480493374,
      "clip_ratio/high_mean": 0.0012608786255441373,
      "clip_ratio/low_mean": 0.0017761425551725551,
      "clip_ratio/low_min": 0.00014223435573512688,
      "clip_ratio/region_mean": 0.003037021138879936,
      "epoch": 0.10079974800063,
      "grad_norm": 9.487072944641113,
      "learning_rate": 1e-06,
      "loss": 0.0118,
      "step": 1080
    },
    {
      "clip_ratio/high_max": 0.002668848777830135,
      "clip_ratio/high_mean": 0.001214121362863807,
      "clip_ratio/low_mean": 0.0013416658512142021,
      "clip_ratio/low_min": 3.760221261472907e-05,
      "clip_ratio/region_mean": 0.002555787214078009,
      "epoch": 0.10089308110063058,
      "grad_norm": 0.14420552551746368,
      "learning_rate": 1e-06,
      "loss": -0.0286,
      "step": 1081
    },
    {
      "clip_ratio/high_max": 0.0030078307099756785,
      "clip_ratio/high_mean": 0.001245437262696214,
      "clip_ratio/low_mean": 0.0016068250370153692,
      "clip_ratio/low_min": 0.0001333706150035141,
      "clip_ratio/region_mean": 0.002852262361557223,
      "epoch": 0.10098641420063116,
      "grad_norm": 384.564208984375,
      "learning_rate": 1e-06,
      "loss": 0.067,
      "step": 1082
    },
    {
      "clip_ratio/high_max": 0.0027996929820801597,
      "clip_ratio/high_mean": 0.001112127891246928,
      "clip_ratio/low_mean": 0.0017498916749900673,
      "clip_ratio/low_min": 0.0001482537891206448,
      "clip_ratio/region_mean": 0.0028620195807889104,
      "epoch": 0.10107974730063175,
      "grad_norm": 0.15250636637210846,
      "learning_rate": 1e-06,
      "loss": 0.0326,
      "step": 1083
    },
    {
      "clip_ratio/high_max": 0.002414898910501506,
      "clip_ratio/high_mean": 0.00102338167198468,
      "clip_ratio/low_mean": 0.0014487097869277932,
      "clip_ratio/low_min": 5.268881068332121e-05,
      "clip_ratio/region_mean": 0.002472091458912473,
      "epoch": 0.10117308040063233,
      "grad_norm": 0.10656650364398956,
      "learning_rate": 1e-06,
      "loss": 0.0528,
      "step": 1084
    },
    {
      "clip_ratio/high_max": 0.002807499789923895,
      "clip_ratio/high_mean": 0.001080316462321207,
      "clip_ratio/low_mean": 0.0015384740800072905,
      "clip_ratio/low_min": 0.00013388932711677626,
      "clip_ratio/region_mean": 0.0026187905386905186,
      "epoch": 0.10126641350063291,
      "grad_norm": 0.11980854719877243,
      "learning_rate": 1e-06,
      "loss": 0.0461,
      "step": 1085
    },
    {
      "clip_ratio/high_max": 0.0025518119509797543,
      "clip_ratio/high_mean": 0.0010949425886792596,
      "clip_ratio/low_mean": 0.001347809306025738,
      "clip_ratio/low_min": 8.174173126462847e-05,
      "clip_ratio/region_mean": 0.002442751923808828,
      "epoch": 0.1013597466006335,
      "grad_norm": 0.10463058203458786,
      "learning_rate": 1e-06,
      "loss": 0.0182,
      "step": 1086
    },
    {
      "clip_ratio/high_max": 0.002697751857340336,
      "clip_ratio/high_mean": 0.0010930513381026685,
      "clip_ratio/low_mean": 0.001615939756447915,
      "clip_ratio/low_min": 0.00015889149381109746,
      "clip_ratio/region_mean": 0.002708991101826541,
      "epoch": 0.10145307970063408,
      "grad_norm": 3.475515604019165,
      "learning_rate": 1e-06,
      "loss": 0.0354,
      "step": 1087
    },
    {
      "clip_ratio/high_max": 0.002832560167007614,
      "clip_ratio/high_mean": 0.0012938145173393423,
      "clip_ratio/low_mean": 0.0016758460442360956,
      "clip_ratio/low_min": 0.0003195853187207831,
      "clip_ratio/region_mean": 0.0029696605852223,
      "epoch": 0.10154641280063466,
      "grad_norm": 8.802103042602539,
      "learning_rate": 1e-06,
      "loss": 0.718,
      "step": 1088
    },
    {
      "clip_ratio/high_max": 0.0029150086775189266,
      "clip_ratio/high_mean": 0.0012245245488884393,
      "clip_ratio/low_mean": 0.0015771983307786286,
      "clip_ratio/low_min": 0.00011248974260524847,
      "clip_ratio/region_mean": 0.002801722817821428,
      "epoch": 0.10163974590063525,
      "grad_norm": 24.858625411987305,
      "learning_rate": 1e-06,
      "loss": 0.0467,
      "step": 1089
    },
    {
      "clip_ratio/high_max": 0.0029586773162009194,
      "clip_ratio/high_mean": 0.0012060261287842877,
      "clip_ratio/low_mean": 0.0014964021011110162,
      "clip_ratio/low_min": 0.00019901075575035065,
      "clip_ratio/region_mean": 0.002702428311749827,
      "epoch": 0.10173307900063583,
      "grad_norm": 0.24916265904903412,
      "learning_rate": 1e-06,
      "loss": 0.0032,
      "step": 1090
    },
    {
      "clip_ratio/high_max": 0.002863522953703068,
      "clip_ratio/high_mean": 0.0011764052433136385,
      "clip_ratio/low_mean": 0.0016461819650430698,
      "clip_ratio/low_min": 6.304127418843564e-05,
      "clip_ratio/region_mean": 0.0028225872592884116,
      "epoch": 0.10182641210063642,
      "grad_norm": 0.31088370084762573,
      "learning_rate": 1e-06,
      "loss": 0.0063,
      "step": 1091
    },
    {
      "clip_ratio/high_max": 0.002600468993477989,
      "clip_ratio/high_mean": 0.0010884742841881234,
      "clip_ratio/low_mean": 0.0014470604583038948,
      "clip_ratio/low_min": 0.00013499182750820182,
      "clip_ratio/region_mean": 0.0025355347534059547,
      "epoch": 0.101919745200637,
      "grad_norm": 0.3091491460800171,
      "learning_rate": 1e-06,
      "loss": 0.0225,
      "step": 1092
    },
    {
      "clip_ratio/high_max": 0.0025902636552928016,
      "clip_ratio/high_mean": 0.0011193327482033055,
      "clip_ratio/low_mean": 0.0015518261843681103,
      "clip_ratio/low_min": 9.310906716564205e-05,
      "clip_ratio/region_mean": 0.002671158901648596,
      "epoch": 0.10201307830063758,
      "grad_norm": 0.11468497663736343,
      "learning_rate": 1e-06,
      "loss": 0.0218,
      "step": 1093
    },
    {
      "clip_ratio/high_max": 0.0028588921268237755,
      "clip_ratio/high_mean": 0.0010601534995657858,
      "clip_ratio/low_mean": 0.001494357522460632,
      "clip_ratio/low_min": 0.0001017522627080325,
      "clip_ratio/region_mean": 0.0025545109892846085,
      "epoch": 0.10210641140063817,
      "grad_norm": 0.10773865133523941,
      "learning_rate": 1e-06,
      "loss": 0.0226,
      "step": 1094
    },
    {
      "clip_ratio/high_max": 0.0023960199396242388,
      "clip_ratio/high_mean": 0.0010427312627143692,
      "clip_ratio/low_mean": 0.0017747869387676474,
      "clip_ratio/low_min": 0.0001251918583875522,
      "clip_ratio/region_mean": 0.002817518194206059,
      "epoch": 0.10219974450063875,
      "grad_norm": 4.2700042724609375,
      "learning_rate": 1e-06,
      "loss": 0.066,
      "step": 1095
    },
    {
      "clip_ratio/high_max": 0.0024806067522149533,
      "clip_ratio/high_mean": 0.0011294237865513423,
      "clip_ratio/low_mean": 0.0014996684694779105,
      "clip_ratio/low_min": 0.00018065202675643377,
      "clip_ratio/region_mean": 0.0026290922760381363,
      "epoch": 0.10229307760063933,
      "grad_norm": 17.473588943481445,
      "learning_rate": 1e-06,
      "loss": 0.024,
      "step": 1096
    },
    {
      "clip_ratio/high_max": 0.00234174382785568,
      "clip_ratio/high_mean": 0.0010099523788085207,
      "clip_ratio/low_mean": 0.0015370887176686665,
      "clip_ratio/low_min": 0.00012869787133240607,
      "clip_ratio/region_mean": 0.0025470411419519223,
      "epoch": 0.10238641070063992,
      "grad_norm": 2654.74755859375,
      "learning_rate": 1e-06,
      "loss": 0.6887,
      "step": 1097
    },
    {
      "clip_ratio/high_max": 0.00292250463826349,
      "clip_ratio/high_mean": 0.0012656719081860501,
      "clip_ratio/low_mean": 0.0014556308160535991,
      "clip_ratio/low_min": 0.0001274228488910012,
      "clip_ratio/region_mean": 0.0027213027569814585,
      "epoch": 0.1024797438006405,
      "grad_norm": 0.1260678917169571,
      "learning_rate": 1e-06,
      "loss": -0.0008,
      "step": 1098
    },
    {
      "clip_ratio/high_max": 0.002370185095060151,
      "clip_ratio/high_mean": 0.0010993133673764532,
      "clip_ratio/low_mean": 0.0017103398276958615,
      "clip_ratio/low_min": 0.00018475731303624343,
      "clip_ratio/region_mean": 0.002809653196891304,
      "epoch": 0.10257307690064109,
      "grad_norm": 0.15316139161586761,
      "learning_rate": 1e-06,
      "loss": 0.006,
      "step": 1099
    },
    {
      "clip_ratio/high_max": 0.002844724753231276,
      "clip_ratio/high_mean": 0.0011724418509402312,
      "clip_ratio/low_mean": 0.0017135146263171919,
      "clip_ratio/low_min": 9.519406557956245e-05,
      "clip_ratio/region_mean": 0.002885956477257423,
      "epoch": 0.10266641000064167,
      "grad_norm": 0.5944458842277527,
      "learning_rate": 1e-06,
      "loss": 0.0064,
      "step": 1100
    },
    {
      "clip_ratio/high_max": 0.002321340980415698,
      "clip_ratio/high_mean": 0.0010224503366771387,
      "clip_ratio/low_mean": 0.0015442519179487135,
      "clip_ratio/low_min": 4.808463199879043e-05,
      "clip_ratio/region_mean": 0.002566702227341011,
      "epoch": 0.10275974310064225,
      "grad_norm": 0.32268863916397095,
      "learning_rate": 1e-06,
      "loss": 0.0417,
      "step": 1101
    },
    {
      "clip_ratio/high_max": 0.0024788510345388204,
      "clip_ratio/high_mean": 0.0010483164223842323,
      "clip_ratio/low_mean": 0.0014292606501840055,
      "clip_ratio/low_min": 0.00012038344266329659,
      "clip_ratio/region_mean": 0.0024775770434644073,
      "epoch": 0.10285307620064284,
      "grad_norm": 0.13296392560005188,
      "learning_rate": 1e-06,
      "loss": 0.0215,
      "step": 1102
    },
    {
      "clip_ratio/high_max": 0.0025340823813166935,
      "clip_ratio/high_mean": 0.000980192637143773,
      "clip_ratio/low_mean": 0.0014907277763995808,
      "clip_ratio/low_min": 0.00026823886946658604,
      "clip_ratio/region_mean": 0.0024709203935344703,
      "epoch": 0.10294640930064342,
      "grad_norm": 0.11375102400779724,
      "learning_rate": 1e-06,
      "loss": 0.0589,
      "step": 1103
    },
    {
      "clip_ratio/high_max": 0.003034240158740431,
      "clip_ratio/high_mean": 0.001298970168136293,
      "clip_ratio/low_mean": 0.001752458370901877,
      "clip_ratio/low_min": 0.0002350144823139999,
      "clip_ratio/region_mean": 0.0030514284590026364,
      "epoch": 0.103039742400644,
      "grad_norm": 156.73641967773438,
      "learning_rate": 1e-06,
      "loss": -0.0042,
      "step": 1104
    },
    {
      "clip_ratio/high_max": 0.0029413750671665184,
      "clip_ratio/high_mean": 0.0011398695169191342,
      "clip_ratio/low_mean": 0.001502103445091052,
      "clip_ratio/low_min": 0.00013782737732981332,
      "clip_ratio/region_mean": 0.0026419729547342286,
      "epoch": 0.10313307550064459,
      "grad_norm": 0.37896502017974854,
      "learning_rate": 1e-06,
      "loss": 0.0192,
      "step": 1105
    },
    {
      "clip_ratio/high_max": 0.0026544243446551263,
      "clip_ratio/high_mean": 0.001177929876575945,
      "clip_ratio/low_mean": 0.0014402927045011893,
      "clip_ratio/low_min": 0.00012283551404834725,
      "clip_ratio/region_mean": 0.0026182225919910707,
      "epoch": 0.10322640860064516,
      "grad_norm": 1.1917195320129395,
      "learning_rate": 1e-06,
      "loss": 0.0251,
      "step": 1106
    },
    {
      "clip_ratio/high_max": 0.002472171137924306,
      "clip_ratio/high_mean": 0.0010606614087009802,
      "clip_ratio/low_mean": 0.0015006561370682903,
      "clip_ratio/low_min": 4.6068795199971646e-05,
      "clip_ratio/region_mean": 0.0025613175239413977,
      "epoch": 0.10331974170064574,
      "grad_norm": 0.8193889856338501,
      "learning_rate": 1e-06,
      "loss": -0.0188,
      "step": 1107
    },
    {
      "clip_ratio/high_max": 0.002694274371606298,
      "clip_ratio/high_mean": 0.0012016507316729985,
      "clip_ratio/low_mean": 0.0014590852879337035,
      "clip_ratio/low_min": 7.493342491216026e-05,
      "clip_ratio/region_mean": 0.0026607360268826596,
      "epoch": 0.10341307480064633,
      "grad_norm": 0.11526229232549667,
      "learning_rate": 1e-06,
      "loss": 0.0302,
      "step": 1108
    },
    {
      "clip_ratio/high_max": 0.0029282200121087953,
      "clip_ratio/high_mean": 0.0011730564910976682,
      "clip_ratio/low_mean": 0.0015058741664688569,
      "clip_ratio/low_min": 0.0002026395704888273,
      "clip_ratio/region_mean": 0.0026789306502905674,
      "epoch": 0.10350640790064691,
      "grad_norm": 1.113185167312622,
      "learning_rate": 1e-06,
      "loss": 0.0095,
      "step": 1109
    },
    {
      "clip_ratio/high_max": 0.0026138090615859255,
      "clip_ratio/high_mean": 0.001089922470782767,
      "clip_ratio/low_mean": 0.001945942571182968,
      "clip_ratio/low_min": 0.00017403253968950594,
      "clip_ratio/region_mean": 0.0030358650838024914,
      "epoch": 0.1035997410006475,
      "grad_norm": 0.13811784982681274,
      "learning_rate": 1e-06,
      "loss": 0.032,
      "step": 1110
    },
    {
      "clip_ratio/high_max": 0.002650943184562493,
      "clip_ratio/high_mean": 0.0010927115199592663,
      "clip_ratio/low_mean": 0.0015771086000313517,
      "clip_ratio/low_min": 3.997352905571461e-05,
      "clip_ratio/region_mean": 0.0026698200963437557,
      "epoch": 0.10369307410064808,
      "grad_norm": 0.2351246327161789,
      "learning_rate": 1e-06,
      "loss": 0.0447,
      "step": 1111
    },
    {
      "clip_ratio/high_max": 0.002422716272121761,
      "clip_ratio/high_mean": 0.0011060118122259155,
      "clip_ratio/low_mean": 0.0014811184373684227,
      "clip_ratio/low_min": 0.00022183147939358605,
      "clip_ratio/region_mean": 0.0025871302641462535,
      "epoch": 0.10378640720064866,
      "grad_norm": 0.12535996735095978,
      "learning_rate": 1e-06,
      "loss": 0.0197,
      "step": 1112
    },
    {
      "clip_ratio/high_max": 0.0023927312504383735,
      "clip_ratio/high_mean": 0.0010091246222145855,
      "clip_ratio/low_mean": 0.0014695629761263262,
      "clip_ratio/low_min": 0.0001592255212017335,
      "clip_ratio/region_mean": 0.0024786875874269754,
      "epoch": 0.10387974030064925,
      "grad_norm": 0.12993058562278748,
      "learning_rate": 1e-06,
      "loss": 0.0345,
      "step": 1113
    },
    {
      "clip_ratio/high_max": 0.0025049443138414063,
      "clip_ratio/high_mean": 0.0010873453593376325,
      "clip_ratio/low_mean": 0.0014161132276058197,
      "clip_ratio/low_min": 0.00022265576717472868,
      "clip_ratio/region_mean": 0.0025034585560206324,
      "epoch": 0.10397307340064983,
      "grad_norm": 198.1874542236328,
      "learning_rate": 1e-06,
      "loss": 0.1569,
      "step": 1114
    },
    {
      "clip_ratio/high_max": 0.0025274532235926017,
      "clip_ratio/high_mean": 0.0010891232195717748,
      "clip_ratio/low_mean": 0.001649478330364218,
      "clip_ratio/low_min": 8.891508332453668e-05,
      "clip_ratio/region_mean": 0.0027386015790398233,
      "epoch": 0.10406640650065041,
      "grad_norm": 2.943773031234741,
      "learning_rate": 1e-06,
      "loss": 0.0281,
      "step": 1115
    },
    {
      "clip_ratio/high_max": 0.0029280090529937297,
      "clip_ratio/high_mean": 0.0011059882654080866,
      "clip_ratio/low_mean": 0.0012266908634046558,
      "clip_ratio/low_min": 4.638930386136053e-05,
      "clip_ratio/region_mean": 0.002332679068786092,
      "epoch": 0.104159739600651,
      "grad_norm": 0.1100318655371666,
      "learning_rate": 1e-06,
      "loss": -0.0026,
      "step": 1116
    },
    {
      "clip_ratio/high_max": 0.0023475680936826393,
      "clip_ratio/high_mean": 0.0009771306649781764,
      "clip_ratio/low_mean": 0.0017699179370538332,
      "clip_ratio/low_min": 0.0002464298340782989,
      "clip_ratio/region_mean": 0.002747048609307967,
      "epoch": 0.10425307270065158,
      "grad_norm": 0.38106921315193176,
      "learning_rate": 1e-06,
      "loss": 0.0599,
      "step": 1117
    },
    {
      "clip_ratio/high_max": 0.002319193896255456,
      "clip_ratio/high_mean": 0.000981407620201935,
      "clip_ratio/low_mean": 0.0013981730035084183,
      "clip_ratio/low_min": 5.6276252507814206e-05,
      "clip_ratio/region_mean": 0.002379580633714795,
      "epoch": 0.10434640580065216,
      "grad_norm": 0.1079186275601387,
      "learning_rate": 1e-06,
      "loss": 0.0076,
      "step": 1118
    },
    {
      "clip_ratio/high_max": 0.0022938608599361032,
      "clip_ratio/high_mean": 0.0010277015317115001,
      "clip_ratio/low_mean": 0.0014022658688190859,
      "clip_ratio/low_min": 0.00016592146130278707,
      "clip_ratio/region_mean": 0.002429967345960904,
      "epoch": 0.10443973890065275,
      "grad_norm": 0.1319061815738678,
      "learning_rate": 1e-06,
      "loss": -0.0142,
      "step": 1119
    },
    {
      "clip_ratio/high_max": 0.00252931920113042,
      "clip_ratio/high_mean": 0.001000481710434542,
      "clip_ratio/low_mean": 0.0015538172083324753,
      "clip_ratio/low_min": 7.660049413971137e-05,
      "clip_ratio/region_mean": 0.0025542989606037736,
      "epoch": 0.10453307200065333,
      "grad_norm": 0.19144785404205322,
      "learning_rate": 1e-06,
      "loss": 0.034,
      "step": 1120
    },
    {
      "clip_ratio/high_max": 0.0025256265507778153,
      "clip_ratio/high_mean": 0.0011509384930832312,
      "clip_ratio/low_mean": 0.0012117600381316151,
      "clip_ratio/low_min": 0.00010051626668428071,
      "clip_ratio/region_mean": 0.0023626985857845284,
      "epoch": 0.10462640510065392,
      "grad_norm": 0.10469915717840195,
      "learning_rate": 1e-06,
      "loss": -0.0294,
      "step": 1121
    },
    {
      "clip_ratio/high_max": 0.0025710243280627765,
      "clip_ratio/high_mean": 0.0011006846179952845,
      "clip_ratio/low_mean": 0.001546981613500975,
      "clip_ratio/low_min": 0.00013654349822900258,
      "clip_ratio/region_mean": 0.002647666187840514,
      "epoch": 0.1047197382006545,
      "grad_norm": 20701.240234375,
      "learning_rate": 1e-06,
      "loss": 8.8434,
      "step": 1122
    },
    {
      "clip_ratio/high_max": 0.0025527682519168593,
      "clip_ratio/high_mean": 0.0011990619896096177,
      "clip_ratio/low_mean": 0.0012008287139906315,
      "clip_ratio/low_min": 5.96671643506852e-05,
      "clip_ratio/region_mean": 0.0023998907054192387,
      "epoch": 0.10481307130065508,
      "grad_norm": 0.1038522720336914,
      "learning_rate": 1e-06,
      "loss": -0.0236,
      "step": 1123
    },
    {
      "clip_ratio/high_max": 0.002656278600625228,
      "clip_ratio/high_mean": 0.0011056520343117882,
      "clip_ratio/low_mean": 0.0015240982902469113,
      "clip_ratio/low_min": 0.00014422373169509228,
      "clip_ratio/region_mean": 0.002629750299092848,
      "epoch": 0.10490640440065567,
      "grad_norm": 0.19483205676078796,
      "learning_rate": 1e-06,
      "loss": 0.049,
      "step": 1124
    },
    {
      "clip_ratio/high_max": 0.0022810882874182425,
      "clip_ratio/high_mean": 0.000966720861470094,
      "clip_ratio/low_mean": 0.001735957139317179,
      "clip_ratio/low_min": 4.5520849198510405e-05,
      "clip_ratio/region_mean": 0.0027026780444430187,
      "epoch": 0.10499973750065625,
      "grad_norm": 0.32446226477622986,
      "learning_rate": 1e-06,
      "loss": 0.0434,
      "step": 1125
    },
    {
      "clip_ratio/high_max": 0.0030878846446285024,
      "clip_ratio/high_mean": 0.001148663121057325,
      "clip_ratio/low_mean": 0.001595439069205895,
      "clip_ratio/low_min": 1.989378324651625e-05,
      "clip_ratio/region_mean": 0.0027441021884442307,
      "epoch": 0.10509307060065683,
      "grad_norm": 5.806354999542236,
      "learning_rate": 1e-06,
      "loss": 0.0267,
      "step": 1126
    },
    {
      "clip_ratio/high_max": 0.0023994951916392893,
      "clip_ratio/high_mean": 0.0010409827846160624,
      "clip_ratio/low_mean": 0.0014425911049329443,
      "clip_ratio/low_min": 0.00021041771924501518,
      "clip_ratio/region_mean": 0.002483573873178102,
      "epoch": 0.10518640370065742,
      "grad_norm": 0.12018430233001709,
      "learning_rate": 1e-06,
      "loss": 0.0338,
      "step": 1127
    },
    {
      "clip_ratio/high_max": 0.002376298616582062,
      "clip_ratio/high_mean": 0.001055398657626938,
      "clip_ratio/low_mean": 0.0015098216863407288,
      "clip_ratio/low_min": 7.986284163052915e-05,
      "clip_ratio/region_mean": 0.0025652203112258576,
      "epoch": 0.105279736800658,
      "grad_norm": 0.21106520295143127,
      "learning_rate": 1e-06,
      "loss": 0.0281,
      "step": 1128
    },
    {
      "clip_ratio/high_max": 0.0025821992894634604,
      "clip_ratio/high_mean": 0.0010473803413333371,
      "clip_ratio/low_mean": 0.00155523468129104,
      "clip_ratio/low_min": 0.00015527075447607785,
      "clip_ratio/region_mean": 0.002602615022624377,
      "epoch": 0.10537306990065858,
      "grad_norm": 27.19087028503418,
      "learning_rate": 1e-06,
      "loss": 0.0173,
      "step": 1129
    },
    {
      "clip_ratio/high_max": 0.002762049283774104,
      "clip_ratio/high_mean": 0.0010838034431799315,
      "clip_ratio/low_mean": 0.0013598512650787598,
      "clip_ratio/low_min": 0.00014690825628349558,
      "clip_ratio/region_mean": 0.002443654702801723,
      "epoch": 0.10546640300065917,
      "grad_norm": 1.0987893342971802,
      "learning_rate": 1e-06,
      "loss": 0.0023,
      "step": 1130
    },
    {
      "clip_ratio/high_max": 0.002577096442109905,
      "clip_ratio/high_mean": 0.0010172219954256434,
      "clip_ratio/low_mean": 0.001542750764201628,
      "clip_ratio/low_min": 4.602594708558172e-05,
      "clip_ratio/region_mean": 0.0025599726795917377,
      "epoch": 0.10555973610065975,
      "grad_norm": 0.1445363610982895,
      "learning_rate": 1e-06,
      "loss": 0.057,
      "step": 1131
    },
    {
      "clip_ratio/high_max": 0.002608786140626762,
      "clip_ratio/high_mean": 0.0011486086150398478,
      "clip_ratio/low_mean": 0.0013332708876987454,
      "clip_ratio/low_min": 7.936724432511255e-05,
      "clip_ratio/region_mean": 0.0024818794991006143,
      "epoch": 0.10565306920066034,
      "grad_norm": 0.12205726653337479,
      "learning_rate": 1e-06,
      "loss": 0.0062,
      "step": 1132
    },
    {
      "clip_ratio/high_max": 0.0024981431488413364,
      "clip_ratio/high_mean": 0.0011118799484393094,
      "clip_ratio/low_mean": 0.0017443321048631333,
      "clip_ratio/low_min": 0.00023727012739982456,
      "clip_ratio/region_mean": 0.0028562120787682943,
      "epoch": 0.10574640230066092,
      "grad_norm": 0.11857272684574127,
      "learning_rate": 1e-06,
      "loss": 0.0321,
      "step": 1133
    },
    {
      "clip_ratio/high_max": 0.00250393919122871,
      "clip_ratio/high_mean": 0.0011594168172450736,
      "clip_ratio/low_mean": 0.0015158178721321747,
      "clip_ratio/low_min": 0.00015182946481218096,
      "clip_ratio/region_mean": 0.002675234754860867,
      "epoch": 0.1058397354006615,
      "grad_norm": 0.10825088620185852,
      "learning_rate": 1e-06,
      "loss": 0.0004,
      "step": 1134
    },
    {
      "clip_ratio/high_max": 0.0023394157979055308,
      "clip_ratio/high_mean": 0.0010343670437578112,
      "clip_ratio/low_mean": 0.0016300256866088603,
      "clip_ratio/low_min": 0.00015745593918836676,
      "clip_ratio/region_mean": 0.002664392741280608,
      "epoch": 0.10593306850066209,
      "grad_norm": 0.12784479558467865,
      "learning_rate": 1e-06,
      "loss": 0.0381,
      "step": 1135
    },
    {
      "clip_ratio/high_max": 0.0024102604875224642,
      "clip_ratio/high_mean": 0.0010591411883069668,
      "clip_ratio/low_mean": 0.0014244805825001094,
      "clip_ratio/low_min": 6.143748396425508e-05,
      "clip_ratio/region_mean": 0.002483621734427288,
      "epoch": 0.10602640160066266,
      "grad_norm": 22.513933181762695,
      "learning_rate": 1e-06,
      "loss": 784.9518,
      "step": 1136
    },
    {
      "clip_ratio/high_max": 0.0025080766790779307,
      "clip_ratio/high_mean": 0.001036096400639508,
      "clip_ratio/low_mean": 0.0016372616446460597,
      "clip_ratio/low_min": 0.00010924560046987608,
      "clip_ratio/region_mean": 0.0026733580671134405,
      "epoch": 0.10611973470066324,
      "grad_norm": 0.20479612052440643,
      "learning_rate": 1e-06,
      "loss": 0.0356,
      "step": 1137
    },
    {
      "clip_ratio/high_max": 0.002433931964333169,
      "clip_ratio/high_mean": 0.001040183586155763,
      "clip_ratio/low_mean": 0.001634392701816978,
      "clip_ratio/low_min": 0.00013433927233563736,
      "clip_ratio/region_mean": 0.0026745763098006137,
      "epoch": 0.10621306780066384,
      "grad_norm": 0.6353483200073242,
      "learning_rate": 1e-06,
      "loss": 0.0113,
      "step": 1138
    },
    {
      "clip_ratio/high_max": 0.002414541973848827,
      "clip_ratio/high_mean": 0.0010201572677033255,
      "clip_ratio/low_mean": 0.0016940726636676118,
      "clip_ratio/low_min": 0.00011109549177490408,
      "clip_ratio/region_mean": 0.002714229980483651,
      "epoch": 0.10630640090066441,
      "grad_norm": 0.12792839109897614,
      "learning_rate": 1e-06,
      "loss": 0.026,
      "step": 1139
    },
    {
      "clip_ratio/high_max": 0.0025791230946197174,
      "clip_ratio/high_mean": 0.0011314996918372344,
      "clip_ratio/low_mean": 0.0016081087960628793,
      "clip_ratio/low_min": 0.0001330619943473721,
      "clip_ratio/region_mean": 0.0027396084915380925,
      "epoch": 0.10639973400066499,
      "grad_norm": 0.12060131132602692,
      "learning_rate": 1e-06,
      "loss": 0.0106,
      "step": 1140
    },
    {
      "clip_ratio/high_max": 0.00268881548254285,
      "clip_ratio/high_mean": 0.0010181948255194584,
      "clip_ratio/low_mean": 0.0015097438590601087,
      "clip_ratio/low_min": 0.00018763658954412676,
      "clip_ratio/region_mean": 0.0025279386900365353,
      "epoch": 0.10649306710066558,
      "grad_norm": 0.12730512022972107,
      "learning_rate": 1e-06,
      "loss": 0.0413,
      "step": 1141
    },
    {
      "clip_ratio/high_max": 0.002521760769013781,
      "clip_ratio/high_mean": 0.0009629589967516949,
      "clip_ratio/low_mean": 0.00130176794664294,
      "clip_ratio/low_min": 0.00010137976823898498,
      "clip_ratio/region_mean": 0.0022647269724984653,
      "epoch": 0.10658640020066616,
      "grad_norm": 0.11136295646429062,
      "learning_rate": 1e-06,
      "loss": 0.0203,
      "step": 1142
    },
    {
      "clip_ratio/high_max": 0.0024047069709922653,
      "clip_ratio/high_mean": 0.0010565934135229327,
      "clip_ratio/low_mean": 0.0015082901481946465,
      "clip_ratio/low_min": 0.0001308686623815447,
      "clip_ratio/region_mean": 0.0025648835508036427,
      "epoch": 0.10667973330066675,
      "grad_norm": 0.8497651219367981,
      "learning_rate": 1e-06,
      "loss": 0.0421,
      "step": 1143
    },
    {
      "clip_ratio/high_max": 0.0023329517789534293,
      "clip_ratio/high_mean": 0.001110437424358679,
      "clip_ratio/low_mean": 0.0014975852136558387,
      "clip_ratio/low_min": 0.0001335406723228516,
      "clip_ratio/region_mean": 0.0026080226962221786,
      "epoch": 0.10677306640066733,
      "grad_norm": 1.4519132375717163,
      "learning_rate": 1e-06,
      "loss": 0.0187,
      "step": 1144
    },
    {
      "clip_ratio/high_max": 0.0023515520224464126,
      "clip_ratio/high_mean": 0.0010293052000633907,
      "clip_ratio/low_mean": 0.0014958283209125511,
      "clip_ratio/low_min": 9.770324322744273e-05,
      "clip_ratio/region_mean": 0.0025251335100620054,
      "epoch": 0.10686639950066791,
      "grad_norm": 0.8970760703086853,
      "learning_rate": 1e-06,
      "loss": 0.0071,
      "step": 1145
    },
    {
      "clip_ratio/high_max": 0.002454465240589343,
      "clip_ratio/high_mean": 0.0010758003845694475,
      "clip_ratio/low_mean": 0.0013590464859589702,
      "clip_ratio/low_min": 0.00013524835230782628,
      "clip_ratio/region_mean": 0.0024348468868993223,
      "epoch": 0.1069597326006685,
      "grad_norm": 0.12648969888687134,
      "learning_rate": 1e-06,
      "loss": 0.0148,
      "step": 1146
    },
    {
      "clip_ratio/high_max": 0.0028738573819282465,
      "clip_ratio/high_mean": 0.0012112499316572212,
      "clip_ratio/low_mean": 0.0015169698745012283,
      "clip_ratio/low_min": 0.00018402168188913492,
      "clip_ratio/region_mean": 0.002728219798882492,
      "epoch": 0.10705306570066908,
      "grad_norm": 0.1184571161866188,
      "learning_rate": 1e-06,
      "loss": -0.0386,
      "step": 1147
    },
    {
      "clip_ratio/high_max": 0.0023294651982723735,
      "clip_ratio/high_mean": 0.0010594530995149398,
      "clip_ratio/low_mean": 0.0014024254342075437,
      "clip_ratio/low_min": 9.011303518491331e-05,
      "clip_ratio/region_mean": 0.0024618785027996637,
      "epoch": 0.10714639880066966,
      "grad_norm": 0.12048061192035675,
      "learning_rate": 1e-06,
      "loss": 0.0131,
      "step": 1148
    },
    {
      "clip_ratio/high_max": 0.0027656443417072296,
      "clip_ratio/high_mean": 0.0011772946272685658,
      "clip_ratio/low_mean": 0.0014784574959776364,
      "clip_ratio/low_min": 0.00010673908491298789,
      "clip_ratio/region_mean": 0.002655752112332266,
      "epoch": 0.10723973190067025,
      "grad_norm": 0.830747127532959,
      "learning_rate": 1e-06,
      "loss": 0.0089,
      "step": 1149
    },
    {
      "clip_ratio/high_max": 0.0026511835676501505,
      "clip_ratio/high_mean": 0.0011788259653258137,
      "clip_ratio/low_mean": 0.0014782018515688833,
      "clip_ratio/low_min": 0.00012411908028298058,
      "clip_ratio/region_mean": 0.0026570278423605487,
      "epoch": 0.10733306500067083,
      "grad_norm": 0.1409129649400711,
      "learning_rate": 1e-06,
      "loss": 0.0074,
      "step": 1150
    },
    {
      "clip_ratio/high_max": 0.002441094140522182,
      "clip_ratio/high_mean": 0.000984349702775944,
      "clip_ratio/low_mean": 0.0016933773549681064,
      "clip_ratio/low_min": 0.00011370659649401205,
      "clip_ratio/region_mean": 0.002677727010450326,
      "epoch": 0.10742639810067142,
      "grad_norm": 0.2805463373661041,
      "learning_rate": 1e-06,
      "loss": 0.0283,
      "step": 1151
    },
    {
      "clip_ratio/high_max": 0.0022611791573581286,
      "clip_ratio/high_mean": 0.0009394842272740789,
      "clip_ratio/low_mean": 0.0015625487103534397,
      "clip_ratio/low_min": 0.00027780121035902994,
      "clip_ratio/region_mean": 0.0025020329558174126,
      "epoch": 0.107519731200672,
      "grad_norm": 0.14808697998523712,
      "learning_rate": 1e-06,
      "loss": 0.0403,
      "step": 1152
    },
    {
      "clip_ratio/high_max": 0.0021056226978544146,
      "clip_ratio/high_mean": 0.0009584882609487977,
      "clip_ratio/low_mean": 0.0013512465993699152,
      "clip_ratio/low_min": 0.00017055282023648033,
      "clip_ratio/region_mean": 0.002309734816662967,
      "epoch": 0.10761306430067258,
      "grad_norm": 5.437313079833984,
      "learning_rate": 1e-06,
      "loss": 0.0179,
      "step": 1153
    },
    {
      "clip_ratio/high_max": 0.0022523833831655793,
      "clip_ratio/high_mean": 0.0009239434857590823,
      "clip_ratio/low_mean": 0.001556642342620762,
      "clip_ratio/low_min": 9.151407357421704e-05,
      "clip_ratio/region_mean": 0.002480585826560855,
      "epoch": 0.10770639740067317,
      "grad_norm": 14.293571472167969,
      "learning_rate": 1e-06,
      "loss": 0.0196,
      "step": 1154
    },
    {
      "clip_ratio/high_max": 0.002250166449812241,
      "clip_ratio/high_mean": 0.0009183474248857237,
      "clip_ratio/low_mean": 0.0015268499701051041,
      "clip_ratio/low_min": 0.00010505731370358262,
      "clip_ratio/region_mean": 0.0024451974168187007,
      "epoch": 0.10779973050067375,
      "grad_norm": 0.14646099507808685,
      "learning_rate": 1e-06,
      "loss": 0.0621,
      "step": 1155
    },
    {
      "clip_ratio/high_max": 0.002269261323817773,
      "clip_ratio/high_mean": 0.0009304488157795276,
      "clip_ratio/low_mean": 0.0015893066047283355,
      "clip_ratio/low_min": 8.157099182426464e-05,
      "clip_ratio/region_mean": 0.0025197554277838208,
      "epoch": 0.10789306360067433,
      "grad_norm": 0.13117019832134247,
      "learning_rate": 1e-06,
      "loss": 0.0334,
      "step": 1156
    },
    {
      "clip_ratio/high_max": 0.0029169384433771484,
      "clip_ratio/high_mean": 0.001134302481659688,
      "clip_ratio/low_mean": 0.0015523278343607672,
      "clip_ratio/low_min": 4.92832205054583e-05,
      "clip_ratio/region_mean": 0.002686630265088752,
      "epoch": 0.10798639670067492,
      "grad_norm": 0.12029363214969635,
      "learning_rate": 1e-06,
      "loss": 0.0229,
      "step": 1157
    },
    {
      "clip_ratio/high_max": 0.0027234578265051823,
      "clip_ratio/high_mean": 0.0011646097063930938,
      "clip_ratio/low_mean": 0.001637611749174539,
      "clip_ratio/low_min": 0.00013192225014790893,
      "clip_ratio/region_mean": 0.002802221497404389,
      "epoch": 0.1080797298006755,
      "grad_norm": 0.11221719533205032,
      "learning_rate": 1e-06,
      "loss": 0.0139,
      "step": 1158
    },
    {
      "clip_ratio/high_max": 0.002248412412882317,
      "clip_ratio/high_mean": 0.0009550651757308515,
      "clip_ratio/low_mean": 0.001644369007408386,
      "clip_ratio/low_min": 0.00015320246711780783,
      "clip_ratio/region_mean": 0.002599434163130354,
      "epoch": 0.10817306290067608,
      "grad_norm": 0.14077673852443695,
      "learning_rate": 1e-06,
      "loss": 0.0219,
      "step": 1159
    },
    {
      "clip_ratio/high_max": 0.0023488279548473656,
      "clip_ratio/high_mean": 0.0010281364166075946,
      "clip_ratio/low_mean": 0.001378965473122662,
      "clip_ratio/low_min": 0.00018107322830474004,
      "clip_ratio/region_mean": 0.0024071018997346982,
      "epoch": 0.10826639600067667,
      "grad_norm": 0.1234094649553299,
      "learning_rate": 1e-06,
      "loss": 0.0215,
      "step": 1160
    },
    {
      "clip_ratio/high_max": 0.0029186873071012087,
      "clip_ratio/high_mean": 0.0013197747648518998,
      "clip_ratio/low_mean": 0.001438031855286681,
      "clip_ratio/low_min": 4.919927232549526e-05,
      "clip_ratio/region_mean": 0.002757806665613316,
      "epoch": 0.10835972910067725,
      "grad_norm": 8.374993324279785,
      "learning_rate": 1e-06,
      "loss": 0.0106,
      "step": 1161
    },
    {
      "clip_ratio/high_max": 0.0026132753409910947,
      "clip_ratio/high_mean": 0.0011815812140412163,
      "clip_ratio/low_mean": 0.0014921426809451077,
      "clip_ratio/low_min": 8.586989042669302e-05,
      "clip_ratio/region_mean": 0.002673723880434409,
      "epoch": 0.10845306220067784,
      "grad_norm": 0.22813093662261963,
      "learning_rate": 1e-06,
      "loss": -0.0217,
      "step": 1162
    },
    {
      "clip_ratio/high_max": 0.0024783123517408967,
      "clip_ratio/high_mean": 0.0010287514778610785,
      "clip_ratio/low_mean": 0.0017533973550598603,
      "clip_ratio/low_min": 0.00018909599839389557,
      "clip_ratio/region_mean": 0.002782148789265193,
      "epoch": 0.10854639530067842,
      "grad_norm": 0.1336006224155426,
      "learning_rate": 1e-06,
      "loss": 0.0153,
      "step": 1163
    },
    {
      "clip_ratio/high_max": 0.002699063756153919,
      "clip_ratio/high_mean": 0.0011499940046633128,
      "clip_ratio/low_mean": 0.001743998502206523,
      "clip_ratio/low_min": 0.00022184449335327372,
      "clip_ratio/region_mean": 0.0028939924886799417,
      "epoch": 0.108639728400679,
      "grad_norm": 0.674048125743866,
      "learning_rate": 1e-06,
      "loss": 0.0541,
      "step": 1164
    },
    {
      "clip_ratio/high_max": 0.002533651153498795,
      "clip_ratio/high_mean": 0.0010122582461917773,
      "clip_ratio/low_mean": 0.0017590508541616146,
      "clip_ratio/low_min": 6.615089478145819e-05,
      "clip_ratio/region_mean": 0.0027713090894394554,
      "epoch": 0.10873306150067959,
      "grad_norm": 0.12195254862308502,
      "learning_rate": 1e-06,
      "loss": 0.0283,
      "step": 1165
    },
    {
      "clip_ratio/high_max": 0.0024692603037692606,
      "clip_ratio/high_mean": 0.0010916392639046535,
      "clip_ratio/low_mean": 0.0018298918912478257,
      "clip_ratio/low_min": 9.400539602211211e-05,
      "clip_ratio/region_mean": 0.002921531136962585,
      "epoch": 0.10882639460068017,
      "grad_norm": 2.757406234741211,
      "learning_rate": 1e-06,
      "loss": 0.0236,
      "step": 1166
    },
    {
      "clip_ratio/high_max": 0.0023226002595038153,
      "clip_ratio/high_mean": 0.0009791282209334895,
      "clip_ratio/low_mean": 0.0015479675093956757,
      "clip_ratio/low_min": 0.00011426099536038237,
      "clip_ratio/region_mean": 0.0025270956903113984,
      "epoch": 0.10891972770068074,
      "grad_norm": 0.11199580132961273,
      "learning_rate": 1e-06,
      "loss": 0.0307,
      "step": 1167
    },
    {
      "clip_ratio/high_max": 0.002611228861496784,
      "clip_ratio/high_mean": 0.0011405101722630206,
      "clip_ratio/low_mean": 0.0015856686950428411,
      "clip_ratio/low_min": 0.00012575715663842857,
      "clip_ratio/region_mean": 0.0027261788709438406,
      "epoch": 0.10901306080068134,
      "grad_norm": 0.11596285551786423,
      "learning_rate": 1e-06,
      "loss": 0.0287,
      "step": 1168
    },
    {
      "clip_ratio/high_max": 0.0023346685338765383,
      "clip_ratio/high_mean": 0.0009945332367351511,
      "clip_ratio/low_mean": 0.001598068334715208,
      "clip_ratio/low_min": 0.00036743910823133774,
      "clip_ratio/region_mean": 0.002592601544165518,
      "epoch": 0.10910639390068191,
      "grad_norm": 0.12039542943239212,
      "learning_rate": 1e-06,
      "loss": 0.0317,
      "step": 1169
    },
    {
      "clip_ratio/high_max": 0.0026123062198166735,
      "clip_ratio/high_mean": 0.0010124552572960965,
      "clip_ratio/low_mean": 0.0018334796695853584,
      "clip_ratio/low_min": 0.00023767389211570844,
      "clip_ratio/region_mean": 0.0028459349341574125,
      "epoch": 0.10919972700068249,
      "grad_norm": 0.19903850555419922,
      "learning_rate": 1e-06,
      "loss": 0.0603,
      "step": 1170
    },
    {
      "clip_ratio/high_max": 0.0026690758240874857,
      "clip_ratio/high_mean": 0.0011615412622631993,
      "clip_ratio/low_mean": 0.0014739277758053504,
      "clip_ratio/low_min": 4.657471799873747e-05,
      "clip_ratio/region_mean": 0.0026354690635344014,
      "epoch": 0.10929306010068308,
      "grad_norm": 0.11112910509109497,
      "learning_rate": 1e-06,
      "loss": 0.02,
      "step": 1171
    },
    {
      "clip_ratio/high_max": 0.002784635333227925,
      "clip_ratio/high_mean": 0.0011873923722305335,
      "clip_ratio/low_mean": 0.001487686295149615,
      "clip_ratio/low_min": 0.00019459550912870327,
      "clip_ratio/region_mean": 0.0026750786710181274,
      "epoch": 0.10938639320068366,
      "grad_norm": 3.0499300956726074,
      "learning_rate": 1e-06,
      "loss": -0.0218,
      "step": 1172
    },
    {
      "clip_ratio/high_max": 0.002443659381242469,
      "clip_ratio/high_mean": 0.0010049440934380982,
      "clip_ratio/low_mean": 0.0019322255539009348,
      "clip_ratio/low_min": 9.919327567331493e-05,
      "clip_ratio/region_mean": 0.002937169629149139,
      "epoch": 0.10947972630068425,
      "grad_norm": 0.2186526507139206,
      "learning_rate": 1e-06,
      "loss": 0.0215,
      "step": 1173
    },
    {
      "clip_ratio/high_max": 0.0025458042582613416,
      "clip_ratio/high_mean": 0.0010951334043056704,
      "clip_ratio/low_mean": 0.0019436176262388472,
      "clip_ratio/low_min": 0.00015485615585930645,
      "clip_ratio/region_mean": 0.003038751005078666,
      "epoch": 0.10957305940068483,
      "grad_norm": 0.2321746051311493,
      "learning_rate": 1e-06,
      "loss": -0.0063,
      "step": 1174
    },
    {
      "clip_ratio/high_max": 0.0024702243426872883,
      "clip_ratio/high_mean": 0.0009409493031853344,
      "clip_ratio/low_mean": 0.0015604922155034728,
      "clip_ratio/low_min": 0.00010564335389062762,
      "clip_ratio/region_mean": 0.0025014415368787013,
      "epoch": 0.10966639250068541,
      "grad_norm": 0.11201521754264832,
      "learning_rate": 1e-06,
      "loss": 0.0323,
      "step": 1175
    },
    {
      "clip_ratio/high_max": 0.002274602258694358,
      "clip_ratio/high_mean": 0.0009656934380473103,
      "clip_ratio/low_mean": 0.001773669122485444,
      "clip_ratio/low_min": 0.0003532913806338911,
      "clip_ratio/region_mean": 0.0027393625205149874,
      "epoch": 0.109759725600686,
      "grad_norm": 0.1147800087928772,
      "learning_rate": 1e-06,
      "loss": 0.0193,
      "step": 1176
    },
    {
      "clip_ratio/high_max": 0.002356181350478437,
      "clip_ratio/high_mean": 0.000986929069767939,
      "clip_ratio/low_mean": 0.0016318887574016117,
      "clip_ratio/low_min": 4.377805362310028e-05,
      "clip_ratio/region_mean": 0.002618817801703699,
      "epoch": 0.10985305870068658,
      "grad_norm": 0.17265908420085907,
      "learning_rate": 1e-06,
      "loss": 0.0561,
      "step": 1177
    },
    {
      "clip_ratio/high_max": 0.002528626428102143,
      "clip_ratio/high_mean": 0.0010560396876826417,
      "clip_ratio/low_mean": 0.0014436405144806486,
      "clip_ratio/low_min": 9.18391360755777e-05,
      "clip_ratio/region_mean": 0.002499680223991163,
      "epoch": 0.10994639180068716,
      "grad_norm": 247.41246032714844,
      "learning_rate": 1e-06,
      "loss": 243.5589,
      "step": 1178
    },
    {
      "clip_ratio/high_max": 0.0023474520749005023,
      "clip_ratio/high_mean": 0.0010316269836039282,
      "clip_ratio/low_mean": 0.0014443036252487218,
      "clip_ratio/low_min": 7.071547952364199e-05,
      "clip_ratio/region_mean": 0.002475930603395682,
      "epoch": 0.11003972490068775,
      "grad_norm": 0.11761941760778427,
      "learning_rate": 1e-06,
      "loss": 0.0109,
      "step": 1179
    },
    {
      "clip_ratio/high_max": 0.002321440464584157,
      "clip_ratio/high_mean": 0.0010045192957477411,
      "clip_ratio/low_mean": 0.0017134848749265075,
      "clip_ratio/low_min": 0.00018554481721366756,
      "clip_ratio/region_mean": 0.002718004208873026,
      "epoch": 0.11013305800068833,
      "grad_norm": 0.9480327367782593,
      "learning_rate": 1e-06,
      "loss": 0.0164,
      "step": 1180
    },
    {
      "clip_ratio/high_max": 0.0025491319320281036,
      "clip_ratio/high_mean": 0.0009353582972835284,
      "clip_ratio/low_mean": 0.001538360560516594,
      "clip_ratio/low_min": 0.00011004501175193582,
      "clip_ratio/region_mean": 0.0024737188578001224,
      "epoch": 0.11022639110068891,
      "grad_norm": 0.11550415307283401,
      "learning_rate": 1e-06,
      "loss": -0.0058,
      "step": 1181
    },
    {
      "clip_ratio/high_max": 0.0025997889970312826,
      "clip_ratio/high_mean": 0.0010012016045948258,
      "clip_ratio/low_mean": 0.00173277840258379,
      "clip_ratio/low_min": 0.000186779353498423,
      "clip_ratio/region_mean": 0.0027339800290064886,
      "epoch": 0.1103197242006895,
      "grad_norm": 55.790584564208984,
      "learning_rate": 1e-06,
      "loss": 0.0362,
      "step": 1182
    },
    {
      "clip_ratio/high_max": 0.002636319322846248,
      "clip_ratio/high_mean": 0.0010693519607229973,
      "clip_ratio/low_mean": 0.0015868947812123224,
      "clip_ratio/low_min": 0.00014547255068464437,
      "clip_ratio/region_mean": 0.002656246710103005,
      "epoch": 0.11041305730069008,
      "grad_norm": 0.11102475225925446,
      "learning_rate": 1e-06,
      "loss": 0.0404,
      "step": 1183
    },
    {
      "clip_ratio/high_max": 0.00252573199395556,
      "clip_ratio/high_mean": 0.0010742717095126864,
      "clip_ratio/low_mean": 0.001395404771756148,
      "clip_ratio/low_min": 5.633953605865827e-05,
      "clip_ratio/region_mean": 0.0024696764958207496,
      "epoch": 0.11050639040069067,
      "grad_norm": 0.10893546789884567,
      "learning_rate": 1e-06,
      "loss": 0.012,
      "step": 1184
    },
    {
      "clip_ratio/high_max": 0.003032694097782951,
      "clip_ratio/high_mean": 0.0013811760873068124,
      "clip_ratio/low_mean": 0.001046356399456272,
      "clip_ratio/low_min": 4.110179088456789e-05,
      "clip_ratio/region_mean": 0.002427532417641487,
      "completions/clipped_ratio": 0.013044084821428603,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4091.0,
      "completions/mean_length": 604.4788818359375,
      "completions/mean_terminated_length": 558.3333129882812,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.11059972350069125,
      "grad_norm": 794392068096.0,
      "learning_rate": 1e-06,
      "loss": 1065595568128.0,
      "num_tokens": 893554330.0,
      "reward": 0.5915091633796692,
      "reward_std": 0.19118820130825043,
      "rewards/simpleverify_reward/mean": 0.5915091633796692,
      "rewards/simpleverify_reward/std": 0.491556853055954,
      "step": 1185
    },
    {
      "clip_ratio/high_max": 0.0032812982390169054,
      "clip_ratio/high_mean": 0.0013259194674901664,
      "clip_ratio/low_mean": 0.0010756525280157803,
      "clip_ratio/low_min": 6.813856543885777e-05,
      "clip_ratio/region_mean": 0.002401571946393233,
      "epoch": 0.11069305660069183,
      "grad_norm": 2032945.0,
      "learning_rate": 1e-06,
      "loss": 303.6327,
      "step": 1186
    },
    {
      "clip_ratio/high_max": 0.002685646490135696,
      "clip_ratio/high_mean": 0.0011909100794582628,
      "clip_ratio/low_mean": 0.0012029447498207446,
      "clip_ratio/low_min": 8.945473655330716e-05,
      "clip_ratio/region_mean": 0.0023938547674333677,
      "epoch": 0.11078638970069242,
      "grad_norm": 77396104.0,
      "learning_rate": 1e-06,
      "loss": 40551.8242,
      "step": 1187
    },
    {
      "clip_ratio/high_max": 0.0024277561824419536,
      "clip_ratio/high_mean": 0.0011242178916290868,
      "clip_ratio/low_mean": 0.0010116304983966984,
      "clip_ratio/low_min": 5.449965647130739e-05,
      "clip_ratio/region_mean": 0.0021358483427320607,
      "epoch": 0.110879722800693,
      "grad_norm": 6430587.0,
      "learning_rate": 1e-06,
      "loss": 8795.7891,
      "step": 1188
    },
    {
      "clip_ratio/high_max": 0.0028360644246276934,
      "clip_ratio/high_mean": 0.001222999006131431,
      "clip_ratio/low_mean": 0.0010287557015544735,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0022517547040479258,
      "epoch": 0.11097305590069358,
      "grad_norm": 3894154.0,
      "learning_rate": 1e-06,
      "loss": 432.3489,
      "step": 1189
    },
    {
      "clip_ratio/high_max": 0.003117634456430096,
      "clip_ratio/high_mean": 0.0013883083629480097,
      "clip_ratio/low_mean": 0.0010426388907944784,
      "clip_ratio/low_min": 4.074778553331271e-05,
      "clip_ratio/region_mean": 0.0024309473737957887,
      "epoch": 0.11106638900069417,
      "grad_norm": 4270651.5,
      "learning_rate": 1e-06,
      "loss": 5669.4448,
      "step": 1190
    },
    {
      "clip_ratio/high_max": 0.0026514838682487607,
      "clip_ratio/high_mean": 0.0010602464626572328,
      "clip_ratio/low_mean": 0.001156151502073044,
      "clip_ratio/low_min": 9.802377280720975e-05,
      "clip_ratio/region_mean": 0.0022163979811011814,
      "epoch": 0.11115972210069475,
      "grad_norm": 2222.460205078125,
      "learning_rate": 1e-06,
      "loss": 236.2243,
      "step": 1191
    },
    {
      "clip_ratio/high_max": 0.0029485541163012385,
      "clip_ratio/high_mean": 0.0012724938824248966,
      "clip_ratio/low_mean": 0.0013198232336435467,
      "clip_ratio/low_min": 4.522431117948145e-05,
      "clip_ratio/region_mean": 0.0025923170760506764,
      "epoch": 0.11125305520069532,
      "grad_norm": 327.8789978027344,
      "learning_rate": 1e-06,
      "loss": 1.0671,
      "step": 1192
    },
    {
      "clip_ratio/high_max": 0.002309681902261218,
      "clip_ratio/high_mean": 0.0009305920048063854,
      "clip_ratio/low_mean": 0.0011323188082315028,
      "clip_ratio/low_min": 0.00024599146127002314,
      "clip_ratio/region_mean": 0.002062910840322729,
      "epoch": 0.11134638830069592,
      "grad_norm": 217.44329833984375,
      "learning_rate": 1e-06,
      "loss": 0.0963,
      "step": 1193
    },
    {
      "clip_ratio/high_max": 0.0024939299255493097,
      "clip_ratio/high_mean": 0.0011097246351710055,
      "clip_ratio/low_mean": 0.0010291857288393658,
      "clip_ratio/low_min": 4.5923356083221734e-05,
      "clip_ratio/region_mean": 0.002138910313078668,
      "epoch": 0.1114397214006965,
      "grad_norm": 800.3222045898438,
      "learning_rate": 1e-06,
      "loss": 0.2334,
      "step": 1194
    },
    {
      "clip_ratio/high_max": 0.0032204855378950015,
      "clip_ratio/high_mean": 0.0013059646298643202,
      "clip_ratio/low_mean": 0.001289039839321049,
      "clip_ratio/low_min": 5.4787949920864776e-05,
      "clip_ratio/region_mean": 0.002595004450995475,
      "epoch": 0.11153305450069709,
      "grad_norm": 2.8990097045898438,
      "learning_rate": 1e-06,
      "loss": 0.0561,
      "step": 1195
    },
    {
      "clip_ratio/high_max": 0.0029867501434637234,
      "clip_ratio/high_mean": 0.0013275199889903888,
      "clip_ratio/low_mean": 0.0010883847389777657,
      "clip_ratio/low_min": 6.401405698852614e-05,
      "clip_ratio/region_mean": 0.0024159047607099637,
      "epoch": 0.11162638760069767,
      "grad_norm": 1731.1109619140625,
      "learning_rate": 1e-06,
      "loss": 1063.0155,
      "step": 1196
    },
    {
      "clip_ratio/high_max": 0.0028330145578365773,
      "clip_ratio/high_mean": 0.001162853674031794,
      "clip_ratio/low_mean": 0.0012446948276192416,
      "clip_ratio/low_min": 7.604400161653757e-05,
      "clip_ratio/region_mean": 0.0024075484689092264,
      "epoch": 0.11171972070069824,
      "grad_norm": 601.0494995117188,
      "learning_rate": 1e-06,
      "loss": 0.0909,
      "step": 1197
    },
    {
      "clip_ratio/high_max": 0.002584543191915145,
      "clip_ratio/high_mean": 0.0011109060142189264,
      "clip_ratio/low_mean": 0.001239766108483309,
      "clip_ratio/low_min": 8.229774539358914e-05,
      "clip_ratio/region_mean": 0.002350672111788299,
      "epoch": 0.11181305380069884,
      "grad_norm": 89585.140625,
      "learning_rate": 1e-06,
      "loss": 69.6457,
      "step": 1198
    },
    {
      "clip_ratio/high_max": 0.002952156399260275,
      "clip_ratio/high_mean": 0.0012270632905710954,
      "clip_ratio/low_mean": 0.0013625667270389386,
      "clip_ratio/low_min": 0.00014371296310855541,
      "clip_ratio/region_mean": 0.0025896300285239704,
      "epoch": 0.11190638690069941,
      "grad_norm": 2.4704442024230957,
      "learning_rate": 1e-06,
      "loss": 0.0441,
      "step": 1199
    },
    {
      "clip_ratio/high_max": 0.0029167511602281593,
      "clip_ratio/high_mean": 0.0012493978829297703,
      "clip_ratio/low_mean": 0.001405919494573027,
      "clip_ratio/low_min": 7.225741501315497e-05,
      "clip_ratio/region_mean": 0.002655317359312903,
      "epoch": 0.11199972000069999,
      "grad_norm": 580.558349609375,
      "learning_rate": 1e-06,
      "loss": 0.1047,
      "step": 1200
    },
    {
      "clip_ratio/high_max": 0.0026779835316119716,
      "clip_ratio/high_mean": 0.001147859096818138,
      "clip_ratio/low_mean": 0.001546420418890193,
      "clip_ratio/low_min": 0.00015940708726702724,
      "clip_ratio/region_mean": 0.0026942794647766277,
      "epoch": 0.11209305310070058,
      "grad_norm": 9.425857543945312,
      "learning_rate": 1e-06,
      "loss": 0.1292,
      "step": 1201
    },
    {
      "clip_ratio/high_max": 0.003031703694432508,
      "clip_ratio/high_mean": 0.0013717358815483749,
      "clip_ratio/low_mean": 0.001517954693554202,
      "clip_ratio/low_min": 0.00013567385030910373,
      "clip_ratio/region_mean": 0.0028896905860165134,
      "epoch": 0.11218638620070116,
      "grad_norm": 104.549072265625,
      "learning_rate": 1e-06,
      "loss": 0.0702,
      "step": 1202
    },
    {
      "clip_ratio/high_max": 0.003224461841455195,
      "clip_ratio/high_mean": 0.0012773208945873193,
      "clip_ratio/low_mean": 0.0015749740377941635,
      "clip_ratio/low_min": 0.00017195318105223123,
      "clip_ratio/region_mean": 0.0028522949141915888,
      "epoch": 0.11227971930070174,
      "grad_norm": 1.1381465196609497,
      "learning_rate": 1e-06,
      "loss": 0.0165,
      "step": 1203
    },
    {
      "clip_ratio/high_max": 0.0031134786622715183,
      "clip_ratio/high_mean": 0.0012439658348739613,
      "clip_ratio/low_mean": 0.0015783280177856795,
      "clip_ratio/low_min": 6.882951220177347e-05,
      "clip_ratio/region_mean": 0.0028222939508850686,
      "epoch": 0.11237305240070233,
      "grad_norm": 7.47293758392334,
      "learning_rate": 1e-06,
      "loss": 0.0573,
      "step": 1204
    },
    {
      "clip_ratio/high_max": 0.0028630380911636166,
      "clip_ratio/high_mean": 0.0011970900704909582,
      "clip_ratio/low_mean": 0.0016848786908667535,
      "clip_ratio/low_min": 5.800292728963541e-05,
      "clip_ratio/region_mean": 0.0028819687795476057,
      "epoch": 0.11246638550070291,
      "grad_norm": 0.29964470863342285,
      "learning_rate": 1e-06,
      "loss": 0.0151,
      "step": 1205
    },
    {
      "clip_ratio/high_max": 0.003358416368428152,
      "clip_ratio/high_mean": 0.0014295887103799032,
      "clip_ratio/low_mean": 0.0014843653607385932,
      "clip_ratio/low_min": 0.00015880863793427125,
      "clip_ratio/region_mean": 0.0029139541293261573,
      "epoch": 0.1125597186007035,
      "grad_norm": 0.6256915330886841,
      "learning_rate": 1e-06,
      "loss": -0.0033,
      "step": 1206
    },
    {
      "clip_ratio/high_max": 0.002788866746413987,
      "clip_ratio/high_mean": 0.001101296664273832,
      "clip_ratio/low_mean": 0.0016295774366881233,
      "clip_ratio/low_min": 9.108985341299558e-05,
      "clip_ratio/region_mean": 0.0027308740536682308,
      "epoch": 0.11265305170070408,
      "grad_norm": 1.931517243385315,
      "learning_rate": 1e-06,
      "loss": 0.0763,
      "step": 1207
    },
    {
      "clip_ratio/high_max": 0.002541311907407362,
      "clip_ratio/high_mean": 0.0011258821505180094,
      "clip_ratio/low_mean": 0.0019550233337213285,
      "clip_ratio/low_min": 0.00018722818276728503,
      "clip_ratio/region_mean": 0.0030809054005658254,
      "epoch": 0.11274638480070466,
      "grad_norm": 2452.421142578125,
      "learning_rate": 1e-06,
      "loss": 0.5394,
      "step": 1208
    },
    {
      "clip_ratio/high_max": 0.002967640779388603,
      "clip_ratio/high_mean": 0.0012073879479430616,
      "clip_ratio/low_mean": 0.001830215347581543,
      "clip_ratio/low_min": 0.0001834741042330279,
      "clip_ratio/region_mean": 0.0030376032955246046,
      "epoch": 0.11283971790070525,
      "grad_norm": 6.742492198944092,
      "learning_rate": 1e-06,
      "loss": 0.2086,
      "step": 1209
    },
    {
      "clip_ratio/high_max": 0.0027895457387785427,
      "clip_ratio/high_mean": 0.0011781330922531197,
      "clip_ratio/low_mean": 0.0018373019047430716,
      "clip_ratio/low_min": 0.00020010494881717023,
      "clip_ratio/region_mean": 0.003015434922417626,
      "epoch": 0.11293305100070583,
      "grad_norm": 0.23429690301418304,
      "learning_rate": 1e-06,
      "loss": 0.0299,
      "step": 1210
    },
    {
      "clip_ratio/high_max": 0.002603128130431287,
      "clip_ratio/high_mean": 0.0011555631463124882,
      "clip_ratio/low_mean": 0.0019232652994105592,
      "clip_ratio/low_min": 0.00020352118372102268,
      "clip_ratio/region_mean": 0.003078828420257196,
      "epoch": 0.11302638410070641,
      "grad_norm": 0.1572112739086151,
      "learning_rate": 1e-06,
      "loss": 0.0199,
      "step": 1211
    },
    {
      "clip_ratio/high_max": 0.003294277295935899,
      "clip_ratio/high_mean": 0.0013924883678555489,
      "clip_ratio/low_mean": 0.0015115123060240876,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0029040006920695305,
      "epoch": 0.113119717200707,
      "grad_norm": 4.687248229980469,
      "learning_rate": 1e-06,
      "loss": 0.0358,
      "step": 1212
    },
    {
      "clip_ratio/high_max": 0.0028070095140719786,
      "clip_ratio/high_mean": 0.0012718518046312965,
      "clip_ratio/low_mean": 0.0018819677607098129,
      "clip_ratio/low_min": 0.00026105763572559226,
      "clip_ratio/region_mean": 0.003153819649014622,
      "epoch": 0.11321305030070758,
      "grad_norm": 1.0149513483047485,
      "learning_rate": 1e-06,
      "loss": 0.0415,
      "step": 1213
    },
    {
      "clip_ratio/high_max": 0.0034492992417654023,
      "clip_ratio/high_mean": 0.0013732083716604393,
      "clip_ratio/low_mean": 0.0018147242990380619,
      "clip_ratio/low_min": 0.00027785704151028767,
      "clip_ratio/region_mean": 0.003187932656146586,
      "epoch": 0.11330638340070817,
      "grad_norm": 8.762857437133789,
      "learning_rate": 1e-06,
      "loss": -0.0046,
      "step": 1214
    },
    {
      "clip_ratio/high_max": 0.002777370056719519,
      "clip_ratio/high_mean": 0.0012619030858331826,
      "clip_ratio/low_mean": 0.0018029679922619835,
      "clip_ratio/low_min": 8.60692316564382e-05,
      "clip_ratio/region_mean": 0.003064871081733145,
      "epoch": 0.11339971650070875,
      "grad_norm": 0.15594303607940674,
      "learning_rate": 1e-06,
      "loss": -0.0286,
      "step": 1215
    },
    {
      "clip_ratio/high_max": 0.0024864997976692393,
      "clip_ratio/high_mean": 0.0009758406158653088,
      "clip_ratio/low_mean": 0.0018266438783030026,
      "clip_ratio/low_min": 8.593178699811688e-05,
      "clip_ratio/region_mean": 0.0028024846033076756,
      "epoch": 0.11349304960070933,
      "grad_norm": 4.194972991943359,
      "learning_rate": 1e-06,
      "loss": 0.0588,
      "step": 1216
    },
    {
      "clip_ratio/high_max": 0.0029669780415133573,
      "clip_ratio/high_mean": 0.0012851457213400863,
      "clip_ratio/low_mean": 0.001996494484046707,
      "clip_ratio/low_min": 0.00012038096610922366,
      "clip_ratio/region_mean": 0.003281640281784348,
      "epoch": 0.11358638270070992,
      "grad_norm": 0.7980758547782898,
      "learning_rate": 1e-06,
      "loss": 0.0069,
      "step": 1217
    },
    {
      "clip_ratio/high_max": 0.0027649380899674725,
      "clip_ratio/high_mean": 0.0011233926106797298,
      "clip_ratio/low_mean": 0.0016570268744544592,
      "clip_ratio/low_min": 0.00018395105144008994,
      "clip_ratio/region_mean": 0.002780419592454564,
      "epoch": 0.1136797158007105,
      "grad_norm": 0.1547294557094574,
      "learning_rate": 1e-06,
      "loss": 0.0276,
      "step": 1218
    },
    {
      "clip_ratio/high_max": 0.002502340270439163,
      "clip_ratio/high_mean": 0.0011344733393343631,
      "clip_ratio/low_mean": 0.0019340486323926598,
      "clip_ratio/low_min": 0.00020018002032884397,
      "clip_ratio/region_mean": 0.003068522048124578,
      "epoch": 0.11377304890071108,
      "grad_norm": 266490.875,
      "learning_rate": 1e-06,
      "loss": 31.2843,
      "step": 1219
    },
    {
      "clip_ratio/high_max": 0.0029546780351665802,
      "clip_ratio/high_mean": 0.0012561836520035286,
      "clip_ratio/low_mean": 0.0016470184818899725,
      "clip_ratio/low_min": 0.000241303585426067,
      "clip_ratio/region_mean": 0.002903202206653077,
      "epoch": 0.11386638200071167,
      "grad_norm": 0.195596843957901,
      "learning_rate": 1e-06,
      "loss": -0.0216,
      "step": 1220
    },
    {
      "clip_ratio/high_max": 0.0028919655014760792,
      "clip_ratio/high_mean": 0.0012267936526768608,
      "clip_ratio/low_mean": 0.0018526626517996192,
      "clip_ratio/low_min": 5.674742396877264e-05,
      "clip_ratio/region_mean": 0.0030794562844675966,
      "epoch": 0.11395971510071225,
      "grad_norm": 0.1119137704372406,
      "learning_rate": 1e-06,
      "loss": 0.0675,
      "step": 1221
    },
    {
      "clip_ratio/high_max": 0.002733828870987054,
      "clip_ratio/high_mean": 0.0010845898495972506,
      "clip_ratio/low_mean": 0.0019417991970840376,
      "clip_ratio/low_min": 0.00024353000480914488,
      "clip_ratio/region_mean": 0.0030263890730566345,
      "epoch": 0.11405304820071283,
      "grad_norm": 0.6785203218460083,
      "learning_rate": 1e-06,
      "loss": 0.0422,
      "step": 1222
    },
    {
      "clip_ratio/high_max": 0.002741071773925796,
      "clip_ratio/high_mean": 0.0011416804954933468,
      "clip_ratio/low_mean": 0.001983925401873421,
      "clip_ratio/low_min": 0.0002812875245581381,
      "clip_ratio/region_mean": 0.003125605915556662,
      "epoch": 0.11414638130071342,
      "grad_norm": 0.32578977942466736,
      "learning_rate": 1e-06,
      "loss": 0.0526,
      "step": 1223
    },
    {
      "clip_ratio/high_max": 0.0035384619040996768,
      "clip_ratio/high_mean": 0.0013636497569677886,
      "clip_ratio/low_mean": 0.0017791824466257822,
      "clip_ratio/low_min": 0.0002631363458931446,
      "clip_ratio/region_mean": 0.003142832181765698,
      "epoch": 0.114239714400714,
      "grad_norm": 0.14653603732585907,
      "learning_rate": 1e-06,
      "loss": 0.0326,
      "step": 1224
    },
    {
      "clip_ratio/high_max": 0.002709354965190869,
      "clip_ratio/high_mean": 0.0011962852968281368,
      "clip_ratio/low_mean": 0.0018557922485342715,
      "clip_ratio/low_min": 0.00024172243047360098,
      "clip_ratio/region_mean": 0.003052077525353525,
      "epoch": 0.11433304750071459,
      "grad_norm": 1.0941698551177979,
      "learning_rate": 1e-06,
      "loss": 5.5556,
      "step": 1225
    },
    {
      "clip_ratio/high_max": 0.0028288704343140125,
      "clip_ratio/high_mean": 0.0011237307444389444,
      "clip_ratio/low_mean": 0.002013173470913898,
      "clip_ratio/low_min": 0.0002691760892048478,
      "clip_ratio/region_mean": 0.003136904226266779,
      "epoch": 0.11442638060071517,
      "grad_norm": 1520.499267578125,
      "learning_rate": 1e-06,
      "loss": 1.6141,
      "step": 1226
    },
    {
      "clip_ratio/high_max": 0.002226488009910099,
      "clip_ratio/high_mean": 0.00095945191969804,
      "clip_ratio/low_mean": 0.002001902314077597,
      "clip_ratio/low_min": 0.00026526784131419845,
      "clip_ratio/region_mean": 0.0029613541773869656,
      "epoch": 0.11451971370071574,
      "grad_norm": 3.255891799926758,
      "learning_rate": 1e-06,
      "loss": 0.0482,
      "step": 1227
    },
    {
      "clip_ratio/high_max": 0.0031671427495894022,
      "clip_ratio/high_mean": 0.0014287199155660346,
      "clip_ratio/low_mean": 0.0016771097471064422,
      "clip_ratio/low_min": 0.00014281956828199327,
      "clip_ratio/region_mean": 0.003105829659034498,
      "epoch": 0.11461304680071634,
      "grad_norm": 0.11460442841053009,
      "learning_rate": 1e-06,
      "loss": -0.0035,
      "step": 1228
    },
    {
      "clip_ratio/high_max": 0.002764810502412729,
      "clip_ratio/high_mean": 0.0011847493951790966,
      "clip_ratio/low_mean": 0.0020044864068040624,
      "clip_ratio/low_min": 0.00020119971668464132,
      "clip_ratio/region_mean": 0.003189235765603371,
      "epoch": 0.11470637990071691,
      "grad_norm": 0.15332002937793732,
      "learning_rate": 1e-06,
      "loss": 0.0714,
      "step": 1229
    },
    {
      "clip_ratio/high_max": 0.00315444352600025,
      "clip_ratio/high_mean": 0.0013098239651299082,
      "clip_ratio/low_mean": 0.0016207654771278612,
      "clip_ratio/low_min": 0.00010815789119078545,
      "clip_ratio/region_mean": 0.002930589391326066,
      "epoch": 0.1147997130007175,
      "grad_norm": 0.11037442833185196,
      "learning_rate": 1e-06,
      "loss": -0.0023,
      "step": 1230
    },
    {
      "clip_ratio/high_max": 0.003091499711445067,
      "clip_ratio/high_mean": 0.0013358835076360265,
      "clip_ratio/low_mean": 0.0020024567857035436,
      "clip_ratio/low_min": 0.00018932899001811165,
      "clip_ratio/region_mean": 0.0033383403351763263,
      "epoch": 0.11489304610071809,
      "grad_norm": 1.1134250164031982,
      "learning_rate": 1e-06,
      "loss": 0.004,
      "step": 1231
    },
    {
      "clip_ratio/high_max": 0.0023337664242717437,
      "clip_ratio/high_mean": 0.0009820510331337573,
      "clip_ratio/low_mean": 0.0021878711122553796,
      "clip_ratio/low_min": 0.0002635634618854965,
      "clip_ratio/region_mean": 0.0031699221290182322,
      "epoch": 0.11498637920071866,
      "grad_norm": 626.478759765625,
      "learning_rate": 1e-06,
      "loss": 0.5195,
      "step": 1232
    },
    {
      "clip_ratio/high_max": 0.0027651966956909746,
      "clip_ratio/high_mean": 0.0011395619476388674,
      "clip_ratio/low_mean": 0.0018406770886940649,
      "clip_ratio/low_min": 0.00014595335323974723,
      "clip_ratio/region_mean": 0.002980238990858197,
      "epoch": 0.11507971230071924,
      "grad_norm": 0.1234096959233284,
      "learning_rate": 1e-06,
      "loss": 0.0543,
      "step": 1233
    },
    {
      "clip_ratio/high_max": 0.002956455748062581,
      "clip_ratio/high_mean": 0.0011226865062781144,
      "clip_ratio/low_mean": 0.0018596818190417252,
      "clip_ratio/low_min": 0.00014584953714802396,
      "clip_ratio/region_mean": 0.002982368408993352,
      "epoch": 0.11517304540071983,
      "grad_norm": 0.13140106201171875,
      "learning_rate": 1e-06,
      "loss": 0.0405,
      "step": 1234
    },
    {
      "clip_ratio/high_max": 0.002669380854058545,
      "clip_ratio/high_mean": 0.0010818442369782133,
      "clip_ratio/low_mean": 0.0020418209533090703,
      "clip_ratio/low_min": 0.0001974732422240777,
      "clip_ratio/region_mean": 0.003123665228486061,
      "epoch": 0.11526637850072041,
      "grad_norm": 0.12612858414649963,
      "learning_rate": 1e-06,
      "loss": 0.0645,
      "step": 1235
    },
    {
      "clip_ratio/high_max": 0.003160827051033266,
      "clip_ratio/high_mean": 0.001297491959121544,
      "clip_ratio/low_mean": 0.0016278140356007498,
      "clip_ratio/low_min": 8.797007103567012e-05,
      "clip_ratio/region_mean": 0.0029253060347400606,
      "epoch": 0.115359711600721,
      "grad_norm": 0.17970788478851318,
      "learning_rate": 1e-06,
      "loss": -0.0061,
      "step": 1236
    },
    {
      "clip_ratio/high_max": 0.0022971027792664245,
      "clip_ratio/high_mean": 0.0009947096477844752,
      "clip_ratio/low_mean": 0.0016389978118240833,
      "clip_ratio/low_min": 0.00014986932364990935,
      "clip_ratio/region_mean": 0.002633707510540262,
      "epoch": 0.11545304470072158,
      "grad_norm": 0.1073864996433258,
      "learning_rate": 1e-06,
      "loss": 0.0153,
      "step": 1237
    },
    {
      "clip_ratio/high_max": 0.002956458651169669,
      "clip_ratio/high_mean": 0.001118570304242894,
      "clip_ratio/low_mean": 0.0018358497618464753,
      "clip_ratio/low_min": 0.00013398986084212083,
      "clip_ratio/region_mean": 0.0029544200078817084,
      "epoch": 0.11554637780072216,
      "grad_norm": 76.84618377685547,
      "learning_rate": 1e-06,
      "loss": 0.0255,
      "step": 1238
    },
    {
      "clip_ratio/high_max": 0.0028000598831567913,
      "clip_ratio/high_mean": 0.001073163228284102,
      "clip_ratio/low_mean": 0.0020497106452239677,
      "clip_ratio/low_min": 0.00020179963303235127,
      "clip_ratio/region_mean": 0.0031228738589561544,
      "epoch": 0.11563971090072275,
      "grad_norm": 0.4443994462490082,
      "learning_rate": 1e-06,
      "loss": 0.0433,
      "step": 1239
    },
    {
      "clip_ratio/high_max": 0.0021829877223353833,
      "clip_ratio/high_mean": 0.0009795482510526199,
      "clip_ratio/low_mean": 0.0017536543673486449,
      "clip_ratio/low_min": 0.000196994006728346,
      "clip_ratio/region_mean": 0.002733202614763286,
      "epoch": 0.11573304400072333,
      "grad_norm": 0.11739692091941833,
      "learning_rate": 1e-06,
      "loss": 0.0385,
      "step": 1240
    },
    {
      "clip_ratio/high_max": 0.0029265650882734917,
      "clip_ratio/high_mean": 0.0011322862810629886,
      "clip_ratio/low_mean": 0.001775075688783545,
      "clip_ratio/low_min": 0.00013829570707457606,
      "clip_ratio/region_mean": 0.002907361908000894,
      "epoch": 0.11582637710072391,
      "grad_norm": 43.0748176574707,
      "learning_rate": 1e-06,
      "loss": 0.0339,
      "step": 1241
    },
    {
      "clip_ratio/high_max": 0.0024362038748222403,
      "clip_ratio/high_mean": 0.0009572764047334203,
      "clip_ratio/low_mean": 0.0017483118353993632,
      "clip_ratio/low_min": 8.527196223440114e-05,
      "clip_ratio/region_mean": 0.0027055882674176246,
      "epoch": 0.1159197102007245,
      "grad_norm": 0.29234376549720764,
      "learning_rate": 1e-06,
      "loss": 0.1213,
      "step": 1242
    },
    {
      "clip_ratio/high_max": 0.0024204413894040044,
      "clip_ratio/high_mean": 0.0010568282395979622,
      "clip_ratio/low_mean": 0.001684581788140349,
      "clip_ratio/low_min": 0.0003453019216976827,
      "clip_ratio/region_mean": 0.0027414099968154915,
      "epoch": 0.11601304330072508,
      "grad_norm": 92.03839111328125,
      "learning_rate": 1e-06,
      "loss": 0.0752,
      "step": 1243
    },
    {
      "clip_ratio/high_max": 0.002403621554549318,
      "clip_ratio/high_mean": 0.0011329416338412557,
      "clip_ratio/low_mean": 0.0017711455147946253,
      "clip_ratio/low_min": 0.00014479933633992914,
      "clip_ratio/region_mean": 0.0029040871013421565,
      "epoch": 0.11610637640072566,
      "grad_norm": 1.886216640472412,
      "learning_rate": 1e-06,
      "loss": 0.0626,
      "step": 1244
    },
    {
      "clip_ratio/high_max": 0.002889584626245778,
      "clip_ratio/high_mean": 0.0011757361171476077,
      "clip_ratio/low_mean": 0.001774308351741638,
      "clip_ratio/low_min": 0.00012336359213804826,
      "clip_ratio/region_mean": 0.002950044443423394,
      "epoch": 0.11619970950072625,
      "grad_norm": 0.6351476907730103,
      "learning_rate": 1e-06,
      "loss": 0.0153,
      "step": 1245
    },
    {
      "clip_ratio/high_max": 0.002820053523464594,
      "clip_ratio/high_mean": 0.0011566770117497072,
      "clip_ratio/low_mean": 0.0019905082444893196,
      "clip_ratio/low_min": 0.00028400716291798744,
      "clip_ratio/region_mean": 0.0031471852853428572,
      "epoch": 0.11629304260072683,
      "grad_norm": 0.5719003081321716,
      "learning_rate": 1e-06,
      "loss": 0.0116,
      "step": 1246
    },
    {
      "clip_ratio/high_max": 0.002817532527842559,
      "clip_ratio/high_mean": 0.0011545338165888097,
      "clip_ratio/low_mean": 0.0019023437853320502,
      "clip_ratio/low_min": 0.00014981811273173662,
      "clip_ratio/region_mean": 0.0030568776855943725,
      "epoch": 0.11638637570072742,
      "grad_norm": 0.11359849572181702,
      "learning_rate": 1e-06,
      "loss": 0.0165,
      "step": 1247
    },
    {
      "clip_ratio/high_max": 0.0026225447363685817,
      "clip_ratio/high_mean": 0.001107781334212632,
      "clip_ratio/low_mean": 0.001633396495890338,
      "clip_ratio/low_min": 0.00021244072922854684,
      "clip_ratio/region_mean": 0.0027411778428358957,
      "epoch": 0.116479708800728,
      "grad_norm": 0.11829929053783417,
      "learning_rate": 1e-06,
      "loss": 0.0028,
      "step": 1248
    },
    {
      "clip_ratio/high_max": 0.0027807414953713305,
      "clip_ratio/high_mean": 0.0011598324490478262,
      "clip_ratio/low_mean": 0.001705436130578164,
      "clip_ratio/low_min": 0.0001993938221858116,
      "clip_ratio/region_mean": 0.0028652685723500326,
      "epoch": 0.11657304190072858,
      "grad_norm": 0.3348468244075775,
      "learning_rate": 1e-06,
      "loss": 0.0175,
      "step": 1249
    },
    {
      "clip_ratio/high_max": 0.002594205812783912,
      "clip_ratio/high_mean": 0.001149193682067562,
      "clip_ratio/low_mean": 0.0017035869095707312,
      "clip_ratio/low_min": 8.415698175667785e-05,
      "clip_ratio/region_mean": 0.00285278054070659,
      "epoch": 0.11666637500072917,
      "grad_norm": 15.92387580871582,
      "learning_rate": 1e-06,
      "loss": 0.0123,
      "step": 1250
    },
    {
      "clip_ratio/high_max": 0.0024011996501940303,
      "clip_ratio/high_mean": 0.0010468473738001194,
      "clip_ratio/low_mean": 0.0015372876805486158,
      "clip_ratio/low_min": 0.0001214348712892388,
      "clip_ratio/region_mean": 0.002584135094366502,
      "epoch": 0.11675970810072975,
      "grad_norm": 25.111967086791992,
      "learning_rate": 1e-06,
      "loss": 0.0358,
      "step": 1251
    },
    {
      "clip_ratio/high_max": 0.0033022605639416724,
      "clip_ratio/high_mean": 0.001250336856173817,
      "clip_ratio/low_mean": 0.0015794538339832798,
      "clip_ratio/low_min": 5.6344608310610056e-05,
      "clip_ratio/region_mean": 0.0028297906828811392,
      "epoch": 0.11685304120073033,
      "grad_norm": 0.4591279625892639,
      "learning_rate": 1e-06,
      "loss": -0.0271,
      "step": 1252
    },
    {
      "clip_ratio/high_max": 0.0020914003944199067,
      "clip_ratio/high_mean": 0.0009098018454096746,
      "clip_ratio/low_mean": 0.0019995495676994324,
      "clip_ratio/low_min": 0.00031711560859548626,
      "clip_ratio/region_mean": 0.0029093513876432553,
      "epoch": 0.11694637430073092,
      "grad_norm": 5.456788539886475,
      "learning_rate": 1e-06,
      "loss": 0.0775,
      "step": 1253
    },
    {
      "clip_ratio/high_max": 0.002621678475406952,
      "clip_ratio/high_mean": 0.0011481400797492824,
      "clip_ratio/low_mean": 0.0016896303386602085,
      "clip_ratio/low_min": 0.00021568697684415383,
      "clip_ratio/region_mean": 0.002837770342011936,
      "epoch": 0.1170397074007315,
      "grad_norm": 7443535.5,
      "learning_rate": 1e-06,
      "loss": 1525166.375,
      "step": 1254
    },
    {
      "clip_ratio/high_max": 0.002634889773617033,
      "clip_ratio/high_mean": 0.0011017769793397747,
      "clip_ratio/low_mean": 0.0015114700549929694,
      "clip_ratio/low_min": 0.00014962339810153935,
      "clip_ratio/region_mean": 0.0026132470375159755,
      "epoch": 0.11713304050073207,
      "grad_norm": 0.16583870351314545,
      "learning_rate": 1e-06,
      "loss": 0.0421,
      "step": 1255
    },
    {
      "clip_ratio/high_max": 0.0026016592673840933,
      "clip_ratio/high_mean": 0.0011186912852281239,
      "clip_ratio/low_mean": 0.0014728064015798736,
      "clip_ratio/low_min": 0.0001130934469983913,
      "clip_ratio/region_mean": 0.0025914976722560823,
      "epoch": 0.11722637360073267,
      "grad_norm": 1.7303484678268433,
      "learning_rate": 1e-06,
      "loss": -0.0225,
      "step": 1256
    },
    {
      "clip_ratio/high_max": 0.0025716617528814822,
      "clip_ratio/high_mean": 0.001122258461691672,
      "clip_ratio/low_mean": 0.001627819801797159,
      "clip_ratio/low_min": 0.00011881568843818968,
      "clip_ratio/region_mean": 0.0027500782744027674,
      "epoch": 0.11731970670073325,
      "grad_norm": 0.573452353477478,
      "learning_rate": 1e-06,
      "loss": 0.0103,
      "step": 1257
    },
    {
      "clip_ratio/high_max": 0.0029006407348788343,
      "clip_ratio/high_mean": 0.0011830037237814395,
      "clip_ratio/low_mean": 0.0017434575129300356,
      "clip_ratio/low_min": 0.00024209160437749233,
      "clip_ratio/region_mean": 0.002926461245806422,
      "epoch": 0.11741303980073384,
      "grad_norm": 18.35322380065918,
      "learning_rate": 1e-06,
      "loss": 11.4306,
      "step": 1258
    },
    {
      "clip_ratio/high_max": 0.0023429351203958504,
      "clip_ratio/high_mean": 0.00099605746618181,
      "clip_ratio/low_mean": 0.001709912387013901,
      "clip_ratio/low_min": 0.0001604028616384312,
      "clip_ratio/region_mean": 0.0027059698186349124,
      "epoch": 0.11750637290073442,
      "grad_norm": 0.39945757389068604,
      "learning_rate": 1e-06,
      "loss": 0.0445,
      "step": 1259
    },
    {
      "clip_ratio/high_max": 0.0025692359886306804,
      "clip_ratio/high_mean": 0.001092638362024445,
      "clip_ratio/low_mean": 0.0017810750105127227,
      "clip_ratio/low_min": 0.0001803276845748769,
      "clip_ratio/region_mean": 0.002873713332519401,
      "epoch": 0.117599706000735,
      "grad_norm": 21.694705963134766,
      "learning_rate": 1e-06,
      "loss": 0.0239,
      "step": 1260
    },
    {
      "clip_ratio/high_max": 0.0027784700359916314,
      "clip_ratio/high_mean": 0.0011262063544563716,
      "clip_ratio/low_mean": 0.0016389257361879572,
      "clip_ratio/low_min": 0.00010603273585729767,
      "clip_ratio/region_mean": 0.002765132063359488,
      "epoch": 0.11769303910073559,
      "grad_norm": 1.8864012956619263,
      "learning_rate": 1e-06,
      "loss": 0.0254,
      "step": 1261
    },
    {
      "clip_ratio/high_max": 0.0031021242612041533,
      "clip_ratio/high_mean": 0.0012276673442102037,
      "clip_ratio/low_mean": 0.0018145157046092208,
      "clip_ratio/low_min": 0.0003790237396970042,
      "clip_ratio/region_mean": 0.0030421830160776153,
      "epoch": 0.11778637220073616,
      "grad_norm": 0.18558058142662048,
      "learning_rate": 1e-06,
      "loss": 0.0076,
      "step": 1262
    },
    {
      "clip_ratio/high_max": 0.0024200998377637006,
      "clip_ratio/high_mean": 0.0010604286871966906,
      "clip_ratio/low_mean": 0.002044226937869098,
      "clip_ratio/low_min": 0.00015289765360648744,
      "clip_ratio/region_mean": 0.0031046556250657886,
      "epoch": 0.11787970530073674,
      "grad_norm": 1.6986167430877686,
      "learning_rate": 1e-06,
      "loss": 0.0399,
      "step": 1263
    },
    {
      "clip_ratio/high_max": 0.002635616561747156,
      "clip_ratio/high_mean": 0.001049485228577396,
      "clip_ratio/low_mean": 0.0017352894938085228,
      "clip_ratio/low_min": 7.518211896240246e-05,
      "clip_ratio/region_mean": 0.0027847747114719823,
      "epoch": 0.11797303840073733,
      "grad_norm": 1077.0032958984375,
      "learning_rate": 1e-06,
      "loss": 0.3703,
      "step": 1264
    },
    {
      "clip_ratio/high_max": 0.002858298466890119,
      "clip_ratio/high_mean": 0.0011186864867340773,
      "clip_ratio/low_mean": 0.001685362462012563,
      "clip_ratio/low_min": 6.833515453763539e-05,
      "clip_ratio/region_mean": 0.0028040489996783435,
      "epoch": 0.11806637150073791,
      "grad_norm": 0.440521776676178,
      "learning_rate": 1e-06,
      "loss": 0.0339,
      "step": 1265
    },
    {
      "clip_ratio/high_max": 0.0024358613081858493,
      "clip_ratio/high_mean": 0.0010616764047881588,
      "clip_ratio/low_mean": 0.0016246877639787272,
      "clip_ratio/low_min": 0.00015998480739654042,
      "clip_ratio/region_mean": 0.0026863640887313522,
      "epoch": 0.1181597046007385,
      "grad_norm": 8.292718887329102,
      "learning_rate": 1e-06,
      "loss": 651214.75,
      "step": 1266
    },
    {
      "clip_ratio/high_max": 0.0028760029235854745,
      "clip_ratio/high_mean": 0.0012014865751552861,
      "clip_ratio/low_mean": 0.001623543674213579,
      "clip_ratio/low_min": 0.00014958317842683755,
      "clip_ratio/region_mean": 0.002825030154781416,
      "epoch": 0.11825303770073908,
      "grad_norm": 141.85693359375,
      "learning_rate": 1e-06,
      "loss": 0.0649,
      "step": 1267
    },
    {
      "clip_ratio/high_max": 0.0028612568203243427,
      "clip_ratio/high_mean": 0.001172155865788227,
      "clip_ratio/low_mean": 0.0019057675744988956,
      "clip_ratio/low_min": 1.1968594662903342e-05,
      "clip_ratio/region_mean": 0.0030779234948568046,
      "epoch": 0.11834637080073966,
      "grad_norm": 11331551.0,
      "learning_rate": 1e-06,
      "loss": 4685.4932,
      "step": 1268
    },
    {
      "clip_ratio/high_max": 0.002327132177015301,
      "clip_ratio/high_mean": 0.0009849578018474858,
      "clip_ratio/low_mean": 0.0016447174239146989,
      "clip_ratio/low_min": 5.3297328122425824e-05,
      "clip_ratio/region_mean": 0.0026296751893823966,
      "epoch": 0.11843970390074025,
      "grad_norm": 2.2576262950897217,
      "learning_rate": 1e-06,
      "loss": 0.0551,
      "step": 1269
    },
    {
      "clip_ratio/high_max": 0.0025863627743092366,
      "clip_ratio/high_mean": 0.0010621324290696066,
      "clip_ratio/low_mean": 0.0013763710121565964,
      "clip_ratio/low_min": 0.00017661631864029914,
      "clip_ratio/region_mean": 0.0024385033975704573,
      "epoch": 0.11853303700074083,
      "grad_norm": 64226.171875,
      "learning_rate": 1e-06,
      "loss": 112.0592,
      "step": 1270
    },
    {
      "clip_ratio/high_max": 0.002343168311199406,
      "clip_ratio/high_mean": 0.0010886430536629632,
      "clip_ratio/low_mean": 0.0014820904871157836,
      "clip_ratio/low_min": 0.00011277654084551614,
      "clip_ratio/region_mean": 0.0025707335662445985,
      "epoch": 0.11862637010074141,
      "grad_norm": 1.34003484249115,
      "learning_rate": 1e-06,
      "loss": 0.0434,
      "step": 1271
    },
    {
      "clip_ratio/high_max": 0.00225474782200763,
      "clip_ratio/high_mean": 0.0009727455253596418,
      "clip_ratio/low_mean": 0.0013826721915393136,
      "clip_ratio/low_min": 0.00010036127059720457,
      "clip_ratio/region_mean": 0.0023554176223115064,
      "epoch": 0.118719703200742,
      "grad_norm": 178811.484375,
      "learning_rate": 1e-06,
      "loss": 5.4301,
      "step": 1272
    },
    {
      "clip_ratio/high_max": 0.002521527374483412,
      "clip_ratio/high_mean": 0.0010823165612237062,
      "clip_ratio/low_mean": 0.0014219719378161244,
      "clip_ratio/low_min": 2.7352298275218345e-05,
      "clip_ratio/region_mean": 0.0025042884662980214,
      "epoch": 0.11881303630074258,
      "grad_norm": 128.9577178955078,
      "learning_rate": 1e-06,
      "loss": 0.0298,
      "step": 1273
    },
    {
      "clip_ratio/high_max": 0.0029279654045240022,
      "clip_ratio/high_mean": 0.0010948126782750478,
      "clip_ratio/low_mean": 0.001756403136823792,
      "clip_ratio/low_min": 0.00011030779751308728,
      "clip_ratio/region_mean": 0.002851215780538041,
      "epoch": 0.11890636940074316,
      "grad_norm": 1.7387869358062744,
      "learning_rate": 1e-06,
      "loss": 0.0222,
      "step": 1274
    },
    {
      "clip_ratio/high_max": 0.0022350958242896013,
      "clip_ratio/high_mean": 0.0009996668995881919,
      "clip_ratio/low_mean": 0.0016625109456072096,
      "clip_ratio/low_min": 0.00015270732183125801,
      "clip_ratio/region_mean": 0.0026621778670232743,
      "epoch": 0.11899970250074375,
      "grad_norm": 2761.40869140625,
      "learning_rate": 1e-06,
      "loss": 0.3884,
      "step": 1275
    },
    {
      "clip_ratio/high_max": 0.002866925540729426,
      "clip_ratio/high_mean": 0.0011721632508852053,
      "clip_ratio/low_mean": 0.0016402996188844554,
      "clip_ratio/low_min": 0.00029226318747532787,
      "clip_ratio/region_mean": 0.0028124628734076396,
      "epoch": 0.11909303560074433,
      "grad_norm": 3.6268842220306396,
      "learning_rate": 1e-06,
      "loss": 0.0278,
      "step": 1276
    },
    {
      "clip_ratio/high_max": 0.0023356233214144595,
      "clip_ratio/high_mean": 0.0009571378050168278,
      "clip_ratio/low_mean": 0.001458370434193057,
      "clip_ratio/low_min": 0.0002807661167025799,
      "clip_ratio/region_mean": 0.0024155082282959484,
      "epoch": 0.11918636870074492,
      "grad_norm": 0.37500566244125366,
      "learning_rate": 1e-06,
      "loss": 0.0842,
      "step": 1277
    },
    {
      "clip_ratio/high_max": 0.002454078981827479,
      "clip_ratio/high_mean": 0.0010560654700384475,
      "clip_ratio/low_mean": 0.0014935763902030885,
      "clip_ratio/low_min": 1.5221627108985558e-05,
      "clip_ratio/region_mean": 0.002549641882069409,
      "epoch": 0.1192797018007455,
      "grad_norm": 304439.25,
      "learning_rate": 1e-06,
      "loss": 56.9431,
      "step": 1278
    },
    {
      "clip_ratio/high_max": 0.002539203007472679,
      "clip_ratio/high_mean": 0.0010198548407061026,
      "clip_ratio/low_mean": 0.0017058754183381097,
      "clip_ratio/low_min": 0.000172702903910249,
      "clip_ratio/region_mean": 0.002725730257225223,
      "epoch": 0.11937303490074608,
      "grad_norm": 107.1011734008789,
      "learning_rate": 1e-06,
      "loss": 0.0706,
      "step": 1279
    },
    {
      "clip_ratio/high_max": 0.0025215589703293517,
      "clip_ratio/high_mean": 0.0010095993002323667,
      "clip_ratio/low_mean": 0.0015824723523110151,
      "clip_ratio/low_min": 0.00017615348770050332,
      "clip_ratio/region_mean": 0.0025920716434484348,
      "epoch": 0.11946636800074667,
      "grad_norm": 0.12581756711006165,
      "learning_rate": 1e-06,
      "loss": 0.0425,
      "step": 1280
    },
    {
      "clip_ratio/high_max": 0.002762900992820505,
      "clip_ratio/high_mean": 0.0010711492595874006,
      "clip_ratio/low_mean": 0.0016012663145374972,
      "clip_ratio/low_min": 0.0001288427511099144,
      "clip_ratio/region_mean": 0.0026724155468400568,
      "epoch": 0.11955970110074725,
      "grad_norm": 18.771554946899414,
      "learning_rate": 1e-06,
      "loss": -0.0004,
      "step": 1281
    },
    {
      "clip_ratio/high_max": 0.002937273013230879,
      "clip_ratio/high_mean": 0.0011763448819692712,
      "clip_ratio/low_mean": 0.0018052066516247578,
      "clip_ratio/low_min": 0.0002281651341036195,
      "clip_ratio/region_mean": 0.0029815515445079654,
      "epoch": 0.11965303420074783,
      "grad_norm": 128.1190643310547,
      "learning_rate": 1e-06,
      "loss": 0.0787,
      "step": 1282
    },
    {
      "clip_ratio/high_max": 0.002379294433922041,
      "clip_ratio/high_mean": 0.0009520577841612976,
      "clip_ratio/low_mean": 0.001575715337821748,
      "clip_ratio/low_min": 0.00022441083547164453,
      "clip_ratio/region_mean": 0.0025277731401729397,
      "epoch": 0.11974636730074842,
      "grad_norm": 0.10903871804475784,
      "learning_rate": 1e-06,
      "loss": 0.0041,
      "step": 1283
    },
    {
      "clip_ratio/high_max": 0.0026697091016103514,
      "clip_ratio/high_mean": 0.0010851600127352867,
      "clip_ratio/low_mean": 0.0018996425860677846,
      "clip_ratio/low_min": 0.00024376705459872028,
      "clip_ratio/region_mean": 0.0029848026169929653,
      "epoch": 0.119839700400749,
      "grad_norm": 2.140317678451538,
      "learning_rate": 1e-06,
      "loss": 0.0407,
      "step": 1284
    },
    {
      "clip_ratio/high_max": 0.002785126052913256,
      "clip_ratio/high_mean": 0.0010643614987202454,
      "clip_ratio/low_mean": 0.001758630864060251,
      "clip_ratio/low_min": 0.00014472265411313856,
      "clip_ratio/region_mean": 0.0028229924137121998,
      "epoch": 0.11993303350074958,
      "grad_norm": 5.583578109741211,
      "learning_rate": 1e-06,
      "loss": 0.0383,
      "step": 1285
    },
    {
      "clip_ratio/high_max": 0.0026204491587122902,
      "clip_ratio/high_mean": 0.0010562085881247185,
      "clip_ratio/low_mean": 0.0019424147867539432,
      "clip_ratio/low_min": 0.00012514213085523807,
      "clip_ratio/region_mean": 0.0029986234148964286,
      "epoch": 0.12002636660075017,
      "grad_norm": 1.4959341287612915,
      "learning_rate": 1e-06,
      "loss": 0.0041,
      "step": 1286
    },
    {
      "clip_ratio/high_max": 0.002324942543054931,
      "clip_ratio/high_mean": 0.0010305876148777315,
      "clip_ratio/low_mean": 0.0017553214056533761,
      "clip_ratio/low_min": 0.00016375875475205248,
      "clip_ratio/region_mean": 0.0027859090478159487,
      "epoch": 0.12011969970075075,
      "grad_norm": 0.22705040872097015,
      "learning_rate": 1e-06,
      "loss": 0.0171,
      "step": 1287
    },
    {
      "clip_ratio/high_max": 0.002367006483837031,
      "clip_ratio/high_mean": 0.001063610314304242,
      "clip_ratio/low_mean": 0.0018711815173446666,
      "clip_ratio/low_min": 0.0002173015463995398,
      "clip_ratio/region_mean": 0.0029347918680286966,
      "epoch": 0.12021303280075134,
      "grad_norm": 0.9103193879127502,
      "learning_rate": 1e-06,
      "loss": 0.0434,
      "step": 1288
    },
    {
      "clip_ratio/high_max": 0.00246326452906942,
      "clip_ratio/high_mean": 0.0010631302138790488,
      "clip_ratio/low_mean": 0.001633400246646488,
      "clip_ratio/low_min": 0.00020178403610771056,
      "clip_ratio/region_mean": 0.002696530405955855,
      "epoch": 0.12030636590075192,
      "grad_norm": 0.8848915696144104,
      "learning_rate": 1e-06,
      "loss": -0.0293,
      "step": 1289
    },
    {
      "clip_ratio/high_max": 0.0026815372621058486,
      "clip_ratio/high_mean": 0.001094168681447627,
      "clip_ratio/low_mean": 0.0018804785649990663,
      "clip_ratio/low_min": 0.00010425290201965254,
      "clip_ratio/region_mean": 0.0029746472573606297,
      "epoch": 0.1203996990007525,
      "grad_norm": 0.15472941100597382,
      "learning_rate": 1e-06,
      "loss": 0.0715,
      "step": 1290
    },
    {
      "clip_ratio/high_max": 0.0026537783196545206,
      "clip_ratio/high_mean": 0.0011002218852809165,
      "clip_ratio/low_mean": 0.0024940771181718446,
      "clip_ratio/low_min": 0.00010717975965235382,
      "clip_ratio/region_mean": 0.0035942989343311638,
      "epoch": 0.12049303210075309,
      "grad_norm": 415.4970703125,
      "learning_rate": 1e-06,
      "loss": 0.1435,
      "step": 1291
    },
    {
      "clip_ratio/high_max": 0.0026602099351293873,
      "clip_ratio/high_mean": 0.0012724521111522336,
      "clip_ratio/low_mean": 0.0017916627184604295,
      "clip_ratio/low_min": 8.241842442657799e-05,
      "clip_ratio/region_mean": 0.003064114833250642,
      "epoch": 0.12058636520075366,
      "grad_norm": 95.32950592041016,
      "learning_rate": 1e-06,
      "loss": -0.0074,
      "step": 1292
    },
    {
      "clip_ratio/high_max": 0.002446442384098191,
      "clip_ratio/high_mean": 0.0009719012559799012,
      "clip_ratio/low_mean": 0.0016809420412755571,
      "clip_ratio/low_min": 0.00013997410769661656,
      "clip_ratio/region_mean": 0.002652843242685776,
      "epoch": 0.12067969830075424,
      "grad_norm": 7.08378791809082,
      "learning_rate": 1e-06,
      "loss": 0.0214,
      "step": 1293
    },
    {
      "clip_ratio/high_max": 0.002776145665848162,
      "clip_ratio/high_mean": 0.0010755179882835364,
      "clip_ratio/low_mean": 0.0017547391180414706,
      "clip_ratio/low_min": 0.0003150701813865453,
      "clip_ratio/region_mean": 0.0028302570717642084,
      "epoch": 0.12077303140075484,
      "grad_norm": 0.1413639783859253,
      "learning_rate": 1e-06,
      "loss": 0.0467,
      "step": 1294
    },
    {
      "clip_ratio/high_max": 0.002853964499081485,
      "clip_ratio/high_mean": 0.0011674125089484733,
      "clip_ratio/low_mean": 0.001764378586813109,
      "clip_ratio/low_min": 8.37441530165961e-05,
      "clip_ratio/region_mean": 0.002931790964794345,
      "epoch": 0.12086636450075541,
      "grad_norm": 0.28277555108070374,
      "learning_rate": 1e-06,
      "loss": -0.0018,
      "step": 1295
    },
    {
      "clip_ratio/high_max": 0.002345942164538428,
      "clip_ratio/high_mean": 0.0010516047950659413,
      "clip_ratio/low_mean": 0.0021422000136226416,
      "clip_ratio/low_min": 0.0002182956177421147,
      "clip_ratio/region_mean": 0.003193804863258265,
      "epoch": 0.12095969760075599,
      "grad_norm": 16.739648818969727,
      "learning_rate": 1e-06,
      "loss": 0.0218,
      "step": 1296
    },
    {
      "clip_ratio/high_max": 0.0024812604096950963,
      "clip_ratio/high_mean": 0.0009686353223514743,
      "clip_ratio/low_mean": 0.0019338587480888236,
      "clip_ratio/low_min": 0.00020287244660721626,
      "clip_ratio/region_mean": 0.0029024940376984887,
      "epoch": 0.12105303070075658,
      "grad_norm": 0.2815110683441162,
      "learning_rate": 1e-06,
      "loss": 0.0297,
      "step": 1297
    },
    {
      "clip_ratio/high_max": 0.0027093083954241592,
      "clip_ratio/high_mean": 0.0010830601149791619,
      "clip_ratio/low_mean": 0.002142704419384245,
      "clip_ratio/low_min": 0.00027408121968619525,
      "clip_ratio/region_mean": 0.003225764521630481,
      "epoch": 0.12114636380075716,
      "grad_norm": 0.13505704700946808,
      "learning_rate": 1e-06,
      "loss": 0.0815,
      "step": 1298
    },
    {
      "clip_ratio/high_max": 0.0026842443767236546,
      "clip_ratio/high_mean": 0.0011088426454080036,
      "clip_ratio/low_mean": 0.0017748572608979885,
      "clip_ratio/low_min": 0.00022856307896290673,
      "clip_ratio/region_mean": 0.0028836998535552993,
      "epoch": 0.12123969690075775,
      "grad_norm": 4.790085315704346,
      "learning_rate": 1e-06,
      "loss": 0.0451,
      "step": 1299
    },
    {
      "clip_ratio/high_max": 0.002646590342919808,
      "clip_ratio/high_mean": 0.0011177973210578784,
      "clip_ratio/low_mean": 0.0017304298853559885,
      "clip_ratio/low_min": 0.00023532180148322368,
      "clip_ratio/region_mean": 0.0028482271591201425,
      "epoch": 0.12133303000075833,
      "grad_norm": 0.6362149119377136,
      "learning_rate": 1e-06,
      "loss": -0.0152,
      "step": 1300
    },
    {
      "clip_ratio/high_max": 0.0023714734343229793,
      "clip_ratio/high_mean": 0.0009635728165449109,
      "clip_ratio/low_mean": 0.001666305663093226,
      "clip_ratio/low_min": 0.00010683457367122173,
      "clip_ratio/region_mean": 0.002629878494190052,
      "epoch": 0.12142636310075891,
      "grad_norm": 0.12182816863059998,
      "learning_rate": 1e-06,
      "loss": 0.0452,
      "step": 1301
    },
    {
      "clip_ratio/high_max": 0.002856718514522072,
      "clip_ratio/high_mean": 0.0011808672061306424,
      "clip_ratio/low_mean": 0.0017053154806490056,
      "clip_ratio/low_min": 6.371911149471998e-05,
      "clip_ratio/region_mean": 0.002886182708607521,
      "epoch": 0.1215196962007595,
      "grad_norm": 0.33548665046691895,
      "learning_rate": 1e-06,
      "loss": -0.0372,
      "step": 1302
    },
    {
      "clip_ratio/high_max": 0.0026209691641270183,
      "clip_ratio/high_mean": 0.0010677490136004053,
      "clip_ratio/low_mean": 0.0015185351694526616,
      "clip_ratio/low_min": 0.0001495559681643499,
      "clip_ratio/region_mean": 0.002586284179415088,
      "epoch": 0.12161302930076008,
      "grad_norm": 0.1582452356815338,
      "learning_rate": 1e-06,
      "loss": -0.01,
      "step": 1303
    },
    {
      "clip_ratio/high_max": 0.0024981526839837898,
      "clip_ratio/high_mean": 0.0009750441913638497,
      "clip_ratio/low_mean": 0.0020848522035521455,
      "clip_ratio/low_min": 0.00011993395946774399,
      "clip_ratio/region_mean": 0.0030598964003729634,
      "epoch": 0.12170636240076066,
      "grad_norm": 1.7965190410614014,
      "learning_rate": 1e-06,
      "loss": 0.0594,
      "step": 1304
    },
    {
      "clip_ratio/high_max": 0.0027816733418148942,
      "clip_ratio/high_mean": 0.0011246330959693296,
      "clip_ratio/low_mean": 0.0017055830903700553,
      "clip_ratio/low_min": 3.423761427256977e-05,
      "clip_ratio/region_mean": 0.0028302161299507134,
      "epoch": 0.12179969550076125,
      "grad_norm": 0.5362770557403564,
      "learning_rate": 1e-06,
      "loss": -0.0031,
      "step": 1305
    },
    {
      "clip_ratio/high_max": 0.002099929864925798,
      "clip_ratio/high_mean": 0.0009149324614554644,
      "clip_ratio/low_mean": 0.001991286058910191,
      "clip_ratio/low_min": 0.00020884660898445873,
      "clip_ratio/region_mean": 0.0029062184621579945,
      "epoch": 0.12189302860076183,
      "grad_norm": 28.99228286743164,
      "learning_rate": 1e-06,
      "loss": 0.0744,
      "step": 1306
    },
    {
      "clip_ratio/high_max": 0.002539543049351778,
      "clip_ratio/high_mean": 0.0012048418466292787,
      "clip_ratio/low_mean": 0.0018764610176731367,
      "clip_ratio/low_min": 7.491630458389409e-05,
      "clip_ratio/region_mean": 0.0030813028206466697,
      "epoch": 0.12198636170076241,
      "grad_norm": 777.0072631835938,
      "learning_rate": 1e-06,
      "loss": 0.2584,
      "step": 1307
    },
    {
      "clip_ratio/high_max": 0.0025953483855118975,
      "clip_ratio/high_mean": 0.0011640389275271446,
      "clip_ratio/low_mean": 0.0018990503376699053,
      "clip_ratio/low_min": 0.00024639467210363364,
      "clip_ratio/region_mean": 0.003063089257921092,
      "epoch": 0.122079694800763,
      "grad_norm": 128.30288696289062,
      "learning_rate": 1e-06,
      "loss": 0.039,
      "step": 1308
    },
    {
      "clip_ratio/high_max": 0.0026090781029779464,
      "clip_ratio/high_mean": 0.0011438887704571243,
      "clip_ratio/low_mean": 0.0017591812647879124,
      "clip_ratio/low_min": 0.00018622421339387074,
      "clip_ratio/region_mean": 0.002903070067986846,
      "epoch": 0.12217302790076358,
      "grad_norm": 0.7800815105438232,
      "learning_rate": 1e-06,
      "loss": 0.0146,
      "step": 1309
    },
    {
      "clip_ratio/high_max": 0.0022846799402032048,
      "clip_ratio/high_mean": 0.0009694874515844276,
      "clip_ratio/low_mean": 0.001755118450091686,
      "clip_ratio/low_min": 0.00014912714323145337,
      "clip_ratio/region_mean": 0.002724605830735527,
      "epoch": 0.12226636100076417,
      "grad_norm": 938.2282104492188,
      "learning_rate": 1e-06,
      "loss": 1.3953,
      "step": 1310
    },
    {
      "clip_ratio/high_max": 0.0026915706548606977,
      "clip_ratio/high_mean": 0.001045897719450295,
      "clip_ratio/low_mean": 0.0016949632590694819,
      "clip_ratio/low_min": 0.00020850138571404386,
      "clip_ratio/region_mean": 0.002740861033089459,
      "epoch": 0.12235969410076475,
      "grad_norm": 2.192115306854248,
      "learning_rate": 1e-06,
      "loss": 280.855,
      "step": 1311
    },
    {
      "clip_ratio/high_max": 0.0027553722902666777,
      "clip_ratio/high_mean": 0.0010573356157692615,
      "clip_ratio/low_mean": 0.0019869756215484813,
      "clip_ratio/low_min": 0.00013522309109248454,
      "clip_ratio/region_mean": 0.0030443112191278487,
      "epoch": 0.12245302720076533,
      "grad_norm": 417156.46875,
      "learning_rate": 1e-06,
      "loss": 25.836,
      "step": 1312
    },
    {
      "clip_ratio/high_max": 0.0028961833304492757,
      "clip_ratio/high_mean": 0.0012140483468101593,
      "clip_ratio/low_mean": 0.0013652213019668125,
      "clip_ratio/low_min": 8.400347451242851e-05,
      "clip_ratio/region_mean": 0.0025792696396820247,
      "completions/clipped_ratio": 0.01202392578125,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4074.0,
      "completions/mean_length": 603.0662231445312,
      "completions/mean_terminated_length": 560.5563354492188,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.12254636030076592,
      "grad_norm": 10544022.0,
      "learning_rate": 1e-06,
      "loss": 125965.2969,
      "num_tokens": 974084786.0,
      "reward": 0.5883091688156128,
      "reward_std": 0.1882302314043045,
      "rewards/simpleverify_reward/mean": 0.5883091688156128,
      "rewards/simpleverify_reward/std": 0.4921416938304901,
      "step": 1313
    },
    {
      "clip_ratio/high_max": 0.003347525271237828,
      "clip_ratio/high_mean": 0.0013542946180677973,
      "clip_ratio/low_mean": 0.001061790657331585,
      "clip_ratio/low_min": 0.00010008516028392478,
      "clip_ratio/region_mean": 0.0024160852408385836,
      "epoch": 0.1226396934007665,
      "grad_norm": 25046222.0,
      "learning_rate": 1e-06,
      "loss": 9189.9004,
      "step": 1314
    },
    {
      "clip_ratio/high_max": 0.0028960613562958315,
      "clip_ratio/high_mean": 0.0011054927999794018,
      "clip_ratio/low_mean": 0.0010594565028441139,
      "clip_ratio/low_min": 0.00013437664892990142,
      "clip_ratio/region_mean": 0.0021649492846336216,
      "epoch": 0.12273302650076708,
      "grad_norm": 6170739.5,
      "learning_rate": 1e-06,
      "loss": 10719.4023,
      "step": 1315
    },
    {
      "clip_ratio/high_max": 0.0029601669011753984,
      "clip_ratio/high_mean": 0.0011510662370710634,
      "clip_ratio/low_mean": 0.001264434053155128,
      "clip_ratio/low_min": 0.0001222938244609395,
      "clip_ratio/region_mean": 0.0024155002683983184,
      "epoch": 0.12282635960076767,
      "grad_norm": 14649090048.0,
      "learning_rate": 1e-06,
      "loss": 9281067008.0,
      "step": 1316
    },
    {
      "clip_ratio/high_max": 0.002600384053948801,
      "clip_ratio/high_mean": 0.001070719947165344,
      "clip_ratio/low_mean": 0.0009981944394894526,
      "clip_ratio/low_min": 4.0017260289459955e-05,
      "clip_ratio/region_mean": 0.0020689143748313654,
      "epoch": 0.12291969270076825,
      "grad_norm": 63825.01953125,
      "learning_rate": 1e-06,
      "loss": 734.1898,
      "step": 1317
    },
    {
      "clip_ratio/high_max": 0.0034723718563327566,
      "clip_ratio/high_mean": 0.0014510143337247428,
      "clip_ratio/low_mean": 0.0011123814965685597,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002563395813922398,
      "epoch": 0.12301302580076884,
      "grad_norm": 497526.0625,
      "learning_rate": 1e-06,
      "loss": 413.6533,
      "step": 1318
    },
    {
      "clip_ratio/high_max": 0.0027586057476582937,
      "clip_ratio/high_mean": 0.0011281032893748488,
      "clip_ratio/low_mean": 0.0011721740957000293,
      "clip_ratio/low_min": 0.00010625063077895902,
      "clip_ratio/region_mean": 0.002300277403264772,
      "epoch": 0.12310635890076942,
      "grad_norm": 3490.934326171875,
      "learning_rate": 1e-06,
      "loss": 45.634,
      "step": 1319
    },
    {
      "clip_ratio/high_max": 0.0025460552678850945,
      "clip_ratio/high_mean": 0.0011641192322713323,
      "clip_ratio/low_mean": 0.0011363854828232434,
      "clip_ratio/low_min": 0.00018440070653014118,
      "clip_ratio/region_mean": 0.0023005047551123425,
      "epoch": 0.12319969200077,
      "grad_norm": 1035214.75,
      "learning_rate": 1e-06,
      "loss": 817.832,
      "step": 1320
    },
    {
      "clip_ratio/high_max": 0.0028774368402082473,
      "clip_ratio/high_mean": 0.001188034524602699,
      "clip_ratio/low_mean": 0.000981177970970748,
      "clip_ratio/low_min": 7.708375051151961e-05,
      "clip_ratio/region_mean": 0.002169212471926585,
      "epoch": 0.12329302510077059,
      "grad_norm": 193839.96875,
      "learning_rate": 1e-06,
      "loss": 22.8366,
      "step": 1321
    },
    {
      "clip_ratio/high_max": 0.0027686473258654587,
      "clip_ratio/high_mean": 0.0012172394017397892,
      "clip_ratio/low_mean": 0.0011842159510706551,
      "clip_ratio/low_min": 0.0001557590376251028,
      "clip_ratio/region_mean": 0.002401455400104169,
      "epoch": 0.12338635820077117,
      "grad_norm": 8212786.5,
      "learning_rate": 1e-06,
      "loss": 1091.8442,
      "step": 1322
    },
    {
      "clip_ratio/high_max": 0.003094690735451877,
      "clip_ratio/high_mean": 0.0012448113811842632,
      "clip_ratio/low_mean": 0.0011990642506134463,
      "clip_ratio/low_min": 8.930230251280591e-05,
      "clip_ratio/region_mean": 0.0024438756081508473,
      "epoch": 0.12347969130077174,
      "grad_norm": 1.9770727157592773,
      "learning_rate": 1e-06,
      "loss": -0.0075,
      "step": 1323
    },
    {
      "clip_ratio/high_max": 0.0028810346266254783,
      "clip_ratio/high_mean": 0.00122314972395543,
      "clip_ratio/low_mean": 0.0010687179819797166,
      "clip_ratio/low_min": 4.253152383171255e-05,
      "clip_ratio/region_mean": 0.0022918677641428076,
      "epoch": 0.12357302440077234,
      "grad_norm": 1905365.875,
      "learning_rate": 1e-06,
      "loss": 6765263.0,
      "step": 1324
    },
    {
      "clip_ratio/high_max": 0.003121137386187911,
      "clip_ratio/high_mean": 0.0012522940851340536,
      "clip_ratio/low_mean": 0.0012267583169887075,
      "clip_ratio/low_min": 5.816938391944859e-05,
      "clip_ratio/region_mean": 0.002479052411217708,
      "epoch": 0.12366635750077291,
      "grad_norm": 3167.805419921875,
      "learning_rate": 1e-06,
      "loss": 1.5535,
      "step": 1325
    },
    {
      "clip_ratio/high_max": 0.0027913033991353586,
      "clip_ratio/high_mean": 0.0012098609731765464,
      "clip_ratio/low_mean": 0.0011652859393507242,
      "clip_ratio/low_min": 8.597171927249292e-05,
      "clip_ratio/region_mean": 0.0023751469125272706,
      "epoch": 0.12375969060077349,
      "grad_norm": 34311772.0,
      "learning_rate": 1e-06,
      "loss": 24000.7148,
      "step": 1326
    },
    {
      "clip_ratio/high_max": 0.0027516176196513698,
      "clip_ratio/high_mean": 0.0011580460231925827,
      "clip_ratio/low_mean": 0.0014469725465460215,
      "clip_ratio/low_min": 4.25977777922526e-05,
      "clip_ratio/region_mean": 0.0026050185988424346,
      "epoch": 0.12385302370077408,
      "grad_norm": 243.29627990722656,
      "learning_rate": 1e-06,
      "loss": 4.6453,
      "step": 1327
    },
    {
      "clip_ratio/high_max": 0.0029805044614477083,
      "clip_ratio/high_mean": 0.0012430451224645367,
      "clip_ratio/low_mean": 0.001253142243513139,
      "clip_ratio/low_min": 0.00011267840636719484,
      "clip_ratio/region_mean": 0.002496187349606771,
      "epoch": 0.12394635680077466,
      "grad_norm": 8.301875114440918,
      "learning_rate": 1e-06,
      "loss": 0.0421,
      "step": 1328
    },
    {
      "clip_ratio/high_max": 0.0026758160929603036,
      "clip_ratio/high_mean": 0.001268159056053264,
      "clip_ratio/low_mean": 0.0014937930136511568,
      "clip_ratio/low_min": 0.00016062554823292885,
      "clip_ratio/region_mean": 0.00276195201149676,
      "epoch": 0.12403968990077525,
      "grad_norm": 3.611328363418579,
      "learning_rate": 1e-06,
      "loss": 11.8485,
      "step": 1329
    },
    {
      "clip_ratio/high_max": 0.0033672382924123667,
      "clip_ratio/high_mean": 0.0013653243677254068,
      "clip_ratio/low_mean": 0.0014212747082638089,
      "clip_ratio/low_min": 0.00017754750115273055,
      "clip_ratio/region_mean": 0.0027865991069120355,
      "epoch": 0.12413302300077583,
      "grad_norm": 4.12019681930542,
      "learning_rate": 1e-06,
      "loss": 0.0248,
      "step": 1330
    },
    {
      "clip_ratio/high_max": 0.002949690526293125,
      "clip_ratio/high_mean": 0.0012496342078520684,
      "clip_ratio/low_mean": 0.0014978455474192742,
      "clip_ratio/low_min": 0.00018984960479428992,
      "clip_ratio/region_mean": 0.002747479775280226,
      "epoch": 0.12422635610077641,
      "grad_norm": 0.23491708934307098,
      "learning_rate": 1e-06,
      "loss": 0.0635,
      "step": 1331
    },
    {
      "clip_ratio/high_max": 0.0023644631219212897,
      "clip_ratio/high_mean": 0.0009763116413523676,
      "clip_ratio/low_mean": 0.0016999932850012556,
      "clip_ratio/low_min": 0.00022220371283765417,
      "clip_ratio/region_mean": 0.002676304917258676,
      "epoch": 0.124319689200777,
      "grad_norm": 0.35941219329833984,
      "learning_rate": 1e-06,
      "loss": 0.0689,
      "step": 1332
    },
    {
      "clip_ratio/high_max": 0.002707583269511815,
      "clip_ratio/high_mean": 0.0011329956032568589,
      "clip_ratio/low_mean": 0.0013309834721439984,
      "clip_ratio/low_min": 0.0001467885376769118,
      "clip_ratio/region_mean": 0.0024639790353830904,
      "epoch": 0.12441302230077758,
      "grad_norm": 103.4138412475586,
      "learning_rate": 1e-06,
      "loss": 29.9006,
      "step": 1333
    },
    {
      "clip_ratio/high_max": 0.0023598151601618156,
      "clip_ratio/high_mean": 0.000986379265668802,
      "clip_ratio/low_mean": 0.001635982273000991,
      "clip_ratio/low_min": 0.00016116808092192514,
      "clip_ratio/region_mean": 0.002622361498652026,
      "epoch": 0.12450635540077816,
      "grad_norm": 3.2083046436309814,
      "learning_rate": 1e-06,
      "loss": 0.0677,
      "step": 1334
    },
    {
      "clip_ratio/high_max": 0.0029471293091773987,
      "clip_ratio/high_mean": 0.0012238292110851035,
      "clip_ratio/low_mean": 0.0014725156834174413,
      "clip_ratio/low_min": 6.115491578384535e-05,
      "clip_ratio/region_mean": 0.0026963449345203117,
      "epoch": 0.12459968850077875,
      "grad_norm": 0.14162856340408325,
      "learning_rate": 1e-06,
      "loss": 0.0158,
      "step": 1335
    },
    {
      "clip_ratio/high_max": 0.0031741782659082673,
      "clip_ratio/high_mean": 0.0013061026511422824,
      "clip_ratio/low_mean": 0.0013866653407603735,
      "clip_ratio/low_min": 6.309938271442661e-05,
      "clip_ratio/region_mean": 0.0026927679864456877,
      "epoch": 0.12469302160077933,
      "grad_norm": 844.8184204101562,
      "learning_rate": 1e-06,
      "loss": 0.1569,
      "step": 1336
    },
    {
      "clip_ratio/high_max": 0.0032562197629886214,
      "clip_ratio/high_mean": 0.001402841616254591,
      "clip_ratio/low_mean": 0.0015069984474394005,
      "clip_ratio/low_min": 0.0001333006966888206,
      "clip_ratio/region_mean": 0.0029098399900249206,
      "epoch": 0.12478635470077991,
      "grad_norm": 22.62038230895996,
      "learning_rate": 1e-06,
      "loss": -0.0065,
      "step": 1337
    },
    {
      "clip_ratio/high_max": 0.0030180084140738472,
      "clip_ratio/high_mean": 0.0012904098330182023,
      "clip_ratio/low_mean": 0.0016129396208270919,
      "clip_ratio/low_min": 0.00016985756701615173,
      "clip_ratio/region_mean": 0.002903349348343909,
      "epoch": 0.1248796878007805,
      "grad_norm": 5185.359375,
      "learning_rate": 1e-06,
      "loss": 1675588992.0,
      "step": 1338
    },
    {
      "clip_ratio/high_max": 0.0028880392128485255,
      "clip_ratio/high_mean": 0.0011796596663771197,
      "clip_ratio/low_mean": 0.0014709192364534829,
      "clip_ratio/low_min": 5.447237526823301e-05,
      "clip_ratio/region_mean": 0.0026505789428483695,
      "epoch": 0.12497302090078108,
      "grad_norm": 65.60166931152344,
      "learning_rate": 1e-06,
      "loss": 5.7471,
      "step": 1339
    },
    {
      "clip_ratio/high_max": 0.0026705306008807383,
      "clip_ratio/high_mean": 0.0011774634149332996,
      "clip_ratio/low_mean": 0.0017858708088169806,
      "clip_ratio/low_min": 0.0002605140298328479,
      "clip_ratio/region_mean": 0.002963334249216132,
      "epoch": 0.12506635400078167,
      "grad_norm": 3.326878786087036,
      "learning_rate": 1e-06,
      "loss": 0.054,
      "step": 1340
    },
    {
      "clip_ratio/high_max": 0.0029294352425495163,
      "clip_ratio/high_mean": 0.0012471622430894058,
      "clip_ratio/low_mean": 0.0015624780280631967,
      "clip_ratio/low_min": 6.610868786083302e-05,
      "clip_ratio/region_mean": 0.0028096401947550476,
      "epoch": 0.12515968710078224,
      "grad_norm": 13365.33203125,
      "learning_rate": 1e-06,
      "loss": 6.1477,
      "step": 1341
    },
    {
      "clip_ratio/high_max": 0.003351216197188478,
      "clip_ratio/high_mean": 0.0012298054643906653,
      "clip_ratio/low_mean": 0.0014938700951461215,
      "clip_ratio/low_min": 0.00016687980860297102,
      "clip_ratio/region_mean": 0.0027236755413468927,
      "epoch": 0.12525302020078283,
      "grad_norm": 0.2032417356967926,
      "learning_rate": 1e-06,
      "loss": -0.0129,
      "step": 1342
    },
    {
      "clip_ratio/high_max": 0.0027873489198100287,
      "clip_ratio/high_mean": 0.0011186481187905883,
      "clip_ratio/low_mean": 0.0015980834050424164,
      "clip_ratio/low_min": 0.00018384671420790255,
      "clip_ratio/region_mean": 0.0027167315274709836,
      "epoch": 0.12534635330078342,
      "grad_norm": 380.8132629394531,
      "learning_rate": 1e-06,
      "loss": 0.2398,
      "step": 1343
    },
    {
      "clip_ratio/high_max": 0.0030305194668471813,
      "clip_ratio/high_mean": 0.0011946755548706278,
      "clip_ratio/low_mean": 0.0016799342556623742,
      "clip_ratio/low_min": 0.00010082079825224355,
      "clip_ratio/region_mean": 0.002874609868740663,
      "epoch": 0.125439686400784,
      "grad_norm": 0.1865394413471222,
      "learning_rate": 1e-06,
      "loss": 0.0097,
      "step": 1344
    },
    {
      "clip_ratio/high_max": 0.0026593375005177222,
      "clip_ratio/high_mean": 0.0010928886295005213,
      "clip_ratio/low_mean": 0.001904479571749107,
      "clip_ratio/low_min": 0.00016771562513895333,
      "clip_ratio/region_mean": 0.0029973682467243634,
      "epoch": 0.12553301950078458,
      "grad_norm": 34960152.0,
      "learning_rate": 1e-06,
      "loss": 30046.6738,
      "step": 1345
    },
    {
      "clip_ratio/high_max": 0.002593464269011747,
      "clip_ratio/high_mean": 0.0010865710210055113,
      "clip_ratio/low_mean": 0.0015823002831893973,
      "clip_ratio/low_min": 0.00013098886483930983,
      "clip_ratio/region_mean": 0.002668871311470866,
      "epoch": 0.12562635260078517,
      "grad_norm": 3.67510724067688,
      "learning_rate": 1e-06,
      "loss": 0.0012,
      "step": 1346
    },
    {
      "clip_ratio/high_max": 0.0031570967730658595,
      "clip_ratio/high_mean": 0.0013122608652338386,
      "clip_ratio/low_mean": 0.0015063734263094375,
      "clip_ratio/low_min": 0.00018411947712593246,
      "clip_ratio/region_mean": 0.0028186341951368377,
      "epoch": 0.12571968570078576,
      "grad_norm": 0.46530383825302124,
      "learning_rate": 1e-06,
      "loss": 0.2359,
      "step": 1347
    },
    {
      "clip_ratio/high_max": 0.0029708821093663573,
      "clip_ratio/high_mean": 0.0012352302328508813,
      "clip_ratio/low_mean": 0.0018282363816979341,
      "clip_ratio/low_min": 0.00019331154726387467,
      "clip_ratio/region_mean": 0.0030634665890829638,
      "epoch": 0.12581301880078632,
      "grad_norm": 0.15034519135951996,
      "learning_rate": 1e-06,
      "loss": 0.0045,
      "step": 1348
    },
    {
      "clip_ratio/high_max": 0.002672720187547384,
      "clip_ratio/high_mean": 0.0011451203645265196,
      "clip_ratio/low_mean": 0.0016769073372415733,
      "clip_ratio/low_min": 0.00014200955592968967,
      "clip_ratio/region_mean": 0.002822027738147881,
      "epoch": 0.12590635190078692,
      "grad_norm": 103.00567626953125,
      "learning_rate": 1e-06,
      "loss": 0.0801,
      "step": 1349
    },
    {
      "clip_ratio/high_max": 0.0025779462011996657,
      "clip_ratio/high_mean": 0.0010173477839998668,
      "clip_ratio/low_mean": 0.001681696350715356,
      "clip_ratio/low_min": 4.938759229844436e-05,
      "clip_ratio/region_mean": 0.0026990441474481486,
      "epoch": 0.1259996850007875,
      "grad_norm": 0.6358668208122253,
      "learning_rate": 1e-06,
      "loss": 0.0498,
      "step": 1350
    },
    {
      "clip_ratio/high_max": 0.0024100137961795554,
      "clip_ratio/high_mean": 0.0010299052664777264,
      "clip_ratio/low_mean": 0.0017007108872348908,
      "clip_ratio/low_min": 0.00010452467540744692,
      "clip_ratio/region_mean": 0.002730616135522723,
      "epoch": 0.12609301810078807,
      "grad_norm": 22.69719696044922,
      "learning_rate": 1e-06,
      "loss": 0.0529,
      "step": 1351
    },
    {
      "clip_ratio/high_max": 0.002751274143520277,
      "clip_ratio/high_mean": 0.0011349360465828795,
      "clip_ratio/low_mean": 0.0014919730347173754,
      "clip_ratio/low_min": 0.00028489053784142016,
      "clip_ratio/region_mean": 0.0026269091249560006,
      "epoch": 0.12618635120078867,
      "grad_norm": 0.8071578145027161,
      "learning_rate": 1e-06,
      "loss": 4.4608,
      "step": 1352
    },
    {
      "clip_ratio/high_max": 0.0025065393492695875,
      "clip_ratio/high_mean": 0.0010474944592715474,
      "clip_ratio/low_mean": 0.0017422355776943732,
      "clip_ratio/low_min": 0.00019379730474611279,
      "clip_ratio/region_mean": 0.0027897300897166133,
      "epoch": 0.12627968430078926,
      "grad_norm": 446.40484619140625,
      "learning_rate": 1e-06,
      "loss": 0.1581,
      "step": 1353
    },
    {
      "clip_ratio/high_max": 0.0023192357512016315,
      "clip_ratio/high_mean": 0.0009305693420174066,
      "clip_ratio/low_mean": 0.0020006406120955944,
      "clip_ratio/low_min": 5.584729342444916e-05,
      "clip_ratio/region_mean": 0.0029312099868548103,
      "epoch": 0.12637301740078982,
      "grad_norm": 12441.0625,
      "learning_rate": 1e-06,
      "loss": 97554.3516,
      "step": 1354
    },
    {
      "clip_ratio/high_max": 0.0025742259531398304,
      "clip_ratio/high_mean": 0.0010223299905192107,
      "clip_ratio/low_mean": 0.0019067253306275234,
      "clip_ratio/low_min": 0.00015493260434595868,
      "clip_ratio/region_mean": 0.0029290552920429036,
      "epoch": 0.12646635050079041,
      "grad_norm": 16.43515968322754,
      "learning_rate": 1e-06,
      "loss": 0.0481,
      "step": 1355
    },
    {
      "clip_ratio/high_max": 0.0022704468137817457,
      "clip_ratio/high_mean": 0.0010347225743316812,
      "clip_ratio/low_mean": 0.0017949999382835813,
      "clip_ratio/low_min": 0.00015929684832372004,
      "clip_ratio/region_mean": 0.0028297225580899976,
      "epoch": 0.126559683600791,
      "grad_norm": 346832.75,
      "learning_rate": 1e-06,
      "loss": 59.9786,
      "step": 1356
    },
    {
      "clip_ratio/high_max": 0.002804802410537377,
      "clip_ratio/high_mean": 0.0012214952948852442,
      "clip_ratio/low_mean": 0.0017772459468687885,
      "clip_ratio/low_min": 0.00017800223031372298,
      "clip_ratio/region_mean": 0.0029987412490299903,
      "epoch": 0.12665301670079157,
      "grad_norm": 1.6749107837677002,
      "learning_rate": 1e-06,
      "loss": 0.0448,
      "step": 1357
    },
    {
      "clip_ratio/high_max": 0.003012486908119172,
      "clip_ratio/high_mean": 0.0012679977480729576,
      "clip_ratio/low_mean": 0.0014326255150081124,
      "clip_ratio/low_min": 4.9747318371373694e-05,
      "clip_ratio/region_mean": 0.0027006232921849005,
      "epoch": 0.12674634980079216,
      "grad_norm": 72151.25,
      "learning_rate": 1e-06,
      "loss": 11.6192,
      "step": 1358
    },
    {
      "clip_ratio/high_max": 0.0030121333329589106,
      "clip_ratio/high_mean": 0.0011580454811337404,
      "clip_ratio/low_mean": 0.0014632416095992085,
      "clip_ratio/low_min": 0.00010403153919469332,
      "clip_ratio/region_mean": 0.0026212870943709277,
      "epoch": 0.12683968290079276,
      "grad_norm": 1.1690666675567627,
      "learning_rate": 1e-06,
      "loss": 0.0251,
      "step": 1359
    },
    {
      "clip_ratio/high_max": 0.002762368691037409,
      "clip_ratio/high_mean": 0.0010374671510362532,
      "clip_ratio/low_mean": 0.0015640249112038873,
      "clip_ratio/low_min": 4.444766091182828e-05,
      "clip_ratio/region_mean": 0.0026014920804300345,
      "epoch": 0.12693301600079332,
      "grad_norm": 20.569284439086914,
      "learning_rate": 1e-06,
      "loss": 0.0465,
      "step": 1360
    },
    {
      "clip_ratio/high_max": 0.0029249489889480174,
      "clip_ratio/high_mean": 0.0012907175259897485,
      "clip_ratio/low_mean": 0.0015227844851324335,
      "clip_ratio/low_min": 0.00017174917775264475,
      "clip_ratio/region_mean": 0.002813502011122182,
      "epoch": 0.1270263491007939,
      "grad_norm": 94.8472671508789,
      "learning_rate": 1e-06,
      "loss": 0.003,
      "step": 1361
    },
    {
      "clip_ratio/high_max": 0.0026098782764165662,
      "clip_ratio/high_mean": 0.0010239554903819226,
      "clip_ratio/low_mean": 0.0017414901049050968,
      "clip_ratio/low_min": 8.76168196555227e-05,
      "clip_ratio/region_mean": 0.0027654455770971254,
      "epoch": 0.1271196822007945,
      "grad_norm": 2.6673460006713867,
      "learning_rate": 1e-06,
      "loss": 0.0349,
      "step": 1362
    },
    {
      "clip_ratio/high_max": 0.0024488610579282977,
      "clip_ratio/high_mean": 0.0010470156848896295,
      "clip_ratio/low_mean": 0.001575091591803357,
      "clip_ratio/low_min": 0.00016256840990536148,
      "clip_ratio/region_mean": 0.0026221072403131984,
      "epoch": 0.12721301530079507,
      "grad_norm": 0.13707396388053894,
      "learning_rate": 1e-06,
      "loss": 0.0218,
      "step": 1363
    },
    {
      "clip_ratio/high_max": 0.003056119261600543,
      "clip_ratio/high_mean": 0.0012559415445139166,
      "clip_ratio/low_mean": 0.0018413906182104256,
      "clip_ratio/low_min": 0.00017275308528041933,
      "clip_ratio/region_mean": 0.003097332126344554,
      "epoch": 0.12730634840079566,
      "grad_norm": 943148.9375,
      "learning_rate": 1e-06,
      "loss": 139.0204,
      "step": 1364
    },
    {
      "clip_ratio/high_max": 0.0023716850228083786,
      "clip_ratio/high_mean": 0.0010917439049080713,
      "clip_ratio/low_mean": 0.0017096003102778923,
      "clip_ratio/low_min": 0.0002219008101747022,
      "clip_ratio/region_mean": 0.0028013442424708046,
      "epoch": 0.12739968150079625,
      "grad_norm": 0.1299154907464981,
      "learning_rate": 1e-06,
      "loss": 0.0756,
      "step": 1365
    },
    {
      "clip_ratio/high_max": 0.002816854823322501,
      "clip_ratio/high_mean": 0.0011024784198525595,
      "clip_ratio/low_mean": 0.0016180742713913787,
      "clip_ratio/low_min": 0.00010820514580700547,
      "clip_ratio/region_mean": 0.0027205527294427156,
      "epoch": 0.12749301460079684,
      "grad_norm": 0.43317341804504395,
      "learning_rate": 1e-06,
      "loss": 0.0493,
      "step": 1366
    },
    {
      "clip_ratio/high_max": 0.0028227652510395274,
      "clip_ratio/high_mean": 0.001115926970669534,
      "clip_ratio/low_mean": 0.001455483681638725,
      "clip_ratio/low_min": 0.00017691719222057145,
      "clip_ratio/region_mean": 0.0025714106304803863,
      "epoch": 0.1275863477007974,
      "grad_norm": 87.6314697265625,
      "learning_rate": 1e-06,
      "loss": 0.0156,
      "step": 1367
    },
    {
      "clip_ratio/high_max": 0.002606844100228045,
      "clip_ratio/high_mean": 0.0011581685084820492,
      "clip_ratio/low_mean": 0.0013427623871393735,
      "clip_ratio/low_min": 2.098417462548241e-05,
      "clip_ratio/region_mean": 0.002500930888345465,
      "epoch": 0.127679680800798,
      "grad_norm": 1070412.625,
      "learning_rate": 1e-06,
      "loss": 152.3054,
      "step": 1368
    },
    {
      "clip_ratio/high_max": 0.00316045150248101,
      "clip_ratio/high_mean": 0.0012049879032929312,
      "clip_ratio/low_mean": 0.0017226222225872334,
      "clip_ratio/low_min": 9.289862737205112e-05,
      "clip_ratio/region_mean": 0.002927610090409871,
      "epoch": 0.1277730139007986,
      "grad_norm": 0.2591453492641449,
      "learning_rate": 1e-06,
      "loss": -0.0184,
      "step": 1369
    },
    {
      "clip_ratio/high_max": 0.002523561670386698,
      "clip_ratio/high_mean": 0.0010778622345242184,
      "clip_ratio/low_mean": 0.001299512183322804,
      "clip_ratio/low_min": 0.00013137760470272042,
      "clip_ratio/region_mean": 0.0023773744542268105,
      "epoch": 0.12786634700079916,
      "grad_norm": 0.27729931473731995,
      "learning_rate": 1e-06,
      "loss": 0.0119,
      "step": 1370
    },
    {
      "clip_ratio/high_max": 0.0026265912674716674,
      "clip_ratio/high_mean": 0.0012920482076879125,
      "clip_ratio/low_mean": 0.001608399448741693,
      "clip_ratio/low_min": 0.00014944261329219444,
      "clip_ratio/region_mean": 0.00290044770372333,
      "epoch": 0.12795968010079975,
      "grad_norm": 1.5196881294250488,
      "learning_rate": 1e-06,
      "loss": 0.0059,
      "step": 1371
    },
    {
      "clip_ratio/high_max": 0.0029461203594109975,
      "clip_ratio/high_mean": 0.0011058318050345406,
      "clip_ratio/low_mean": 0.0012287265199120156,
      "clip_ratio/low_min": 3.429375647101551e-05,
      "clip_ratio/region_mean": 0.0023345582667388953,
      "epoch": 0.12805301320080034,
      "grad_norm": 0.14407366514205933,
      "learning_rate": 1e-06,
      "loss": -0.0008,
      "step": 1372
    },
    {
      "clip_ratio/high_max": 0.0024220183040597476,
      "clip_ratio/high_mean": 0.0010868157805816736,
      "clip_ratio/low_mean": 0.001566384562465828,
      "clip_ratio/low_min": 0.0001373180148220854,
      "clip_ratio/region_mean": 0.002653200368513353,
      "epoch": 0.1281463463008009,
      "grad_norm": 139069632.0,
      "learning_rate": 1e-06,
      "loss": 95620.7578,
      "step": 1373
    },
    {
      "clip_ratio/high_max": 0.0026553634816082194,
      "clip_ratio/high_mean": 0.0009497580504103098,
      "clip_ratio/low_mean": 0.0014684297348139808,
      "clip_ratio/low_min": 2.9056252969894558e-05,
      "clip_ratio/region_mean": 0.002418187810690142,
      "epoch": 0.1282396794008015,
      "grad_norm": 70330.828125,
      "learning_rate": 1e-06,
      "loss": 36.8409,
      "step": 1374
    },
    {
      "clip_ratio/high_max": 0.0026666441044653766,
      "clip_ratio/high_mean": 0.001082396433048416,
      "clip_ratio/low_mean": 0.0014729111499036662,
      "clip_ratio/low_min": 8.50972137413919e-05,
      "clip_ratio/region_mean": 0.0025553076120559126,
      "epoch": 0.1283330125008021,
      "grad_norm": 3025.2099609375,
      "learning_rate": 1e-06,
      "loss": 2.3512,
      "step": 1375
    },
    {
      "clip_ratio/high_max": 0.0024378779708058573,
      "clip_ratio/high_mean": 0.0009895453240460483,
      "clip_ratio/low_mean": 0.0015612897150276694,
      "clip_ratio/low_min": 0.000215641972317826,
      "clip_ratio/region_mean": 0.002550835022702813,
      "epoch": 0.12842634560080265,
      "grad_norm": 22.265060424804688,
      "learning_rate": 1e-06,
      "loss": 0.0333,
      "step": 1376
    },
    {
      "clip_ratio/high_max": 0.002777752553811297,
      "clip_ratio/high_mean": 0.0011693892483890522,
      "clip_ratio/low_mean": 0.0014943634250812465,
      "clip_ratio/low_min": 0.00020059328380739316,
      "clip_ratio/region_mean": 0.002663752718945034,
      "epoch": 0.12851967870080325,
      "grad_norm": 11.997663497924805,
      "learning_rate": 1e-06,
      "loss": 0.0517,
      "step": 1377
    },
    {
      "clip_ratio/high_max": 0.0027311431476846337,
      "clip_ratio/high_mean": 0.0010842281244549667,
      "clip_ratio/low_mean": 0.0015534753147221636,
      "clip_ratio/low_min": 0.0002039544087892864,
      "clip_ratio/region_mean": 0.002637703437358141,
      "epoch": 0.12861301180080384,
      "grad_norm": 187.4585723876953,
      "learning_rate": 1e-06,
      "loss": 0.0918,
      "step": 1378
    },
    {
      "clip_ratio/high_max": 0.002413547452306375,
      "clip_ratio/high_mean": 0.001022085982185672,
      "clip_ratio/low_mean": 0.0014121076092123985,
      "clip_ratio/low_min": 0.00010598198969091754,
      "clip_ratio/region_mean": 0.0024341936223208904,
      "epoch": 0.1287063449008044,
      "grad_norm": 8386586112.0,
      "learning_rate": 1e-06,
      "loss": 1437457.5,
      "step": 1379
    },
    {
      "clip_ratio/high_max": 0.002541276342526544,
      "clip_ratio/high_mean": 0.0009673101103544468,
      "clip_ratio/low_mean": 0.00158500838369946,
      "clip_ratio/low_min": 0.00016196291835512966,
      "clip_ratio/region_mean": 0.002552318495872896,
      "epoch": 0.128799678000805,
      "grad_norm": 606.2467041015625,
      "learning_rate": 1e-06,
      "loss": 2.1694,
      "step": 1380
    },
    {
      "clip_ratio/high_max": 0.0026504655979806557,
      "clip_ratio/high_mean": 0.0011263451779086608,
      "clip_ratio/low_mean": 0.001498097237345064,
      "clip_ratio/low_min": 5.3306962399801705e-05,
      "clip_ratio/region_mean": 0.0026244423715979792,
      "epoch": 0.1288930111008056,
      "grad_norm": 0.2823176980018616,
      "learning_rate": 1e-06,
      "loss": 0.0404,
      "step": 1381
    },
    {
      "clip_ratio/high_max": 0.0026424962052260526,
      "clip_ratio/high_mean": 0.0010761064331745729,
      "clip_ratio/low_mean": 0.0016086902796814684,
      "clip_ratio/low_min": 0.0001325031516898889,
      "clip_ratio/region_mean": 0.00268479671649402,
      "epoch": 0.12898634420080615,
      "grad_norm": 1.0655531883239746,
      "learning_rate": 1e-06,
      "loss": 0.0143,
      "step": 1382
    },
    {
      "clip_ratio/high_max": 0.0031903236158541404,
      "clip_ratio/high_mean": 0.0012527883736765943,
      "clip_ratio/low_mean": 0.0016746588298701681,
      "clip_ratio/low_min": 0.00013047294760326622,
      "clip_ratio/region_mean": 0.002927447247202508,
      "epoch": 0.12907967730080674,
      "grad_norm": 63.9605598449707,
      "learning_rate": 1e-06,
      "loss": -0.0016,
      "step": 1383
    },
    {
      "clip_ratio/high_max": 0.0027157221556990407,
      "clip_ratio/high_mean": 0.0010691424686228856,
      "clip_ratio/low_mean": 0.0014518251446133945,
      "clip_ratio/low_min": 3.35815666403505e-05,
      "clip_ratio/region_mean": 0.002520967638702132,
      "epoch": 0.12917301040080734,
      "grad_norm": 0.1845264732837677,
      "learning_rate": 1e-06,
      "loss": 0.0011,
      "step": 1384
    },
    {
      "clip_ratio/high_max": 0.0026524175045778975,
      "clip_ratio/high_mean": 0.001186581972433487,
      "clip_ratio/low_mean": 0.0014880025264574215,
      "clip_ratio/low_min": 0.00012023159797536209,
      "clip_ratio/region_mean": 0.0026745844807010144,
      "epoch": 0.1292663435008079,
      "grad_norm": 31.096954345703125,
      "learning_rate": 1e-06,
      "loss": 0.0244,
      "step": 1385
    },
    {
      "clip_ratio/high_max": 0.0027504787212819792,
      "clip_ratio/high_mean": 0.0010514798777876422,
      "clip_ratio/low_mean": 0.0018460640567354858,
      "clip_ratio/low_min": 0.0001360344631393673,
      "clip_ratio/region_mean": 0.002897543956351001,
      "epoch": 0.1293596766008085,
      "grad_norm": 1.6837533712387085,
      "learning_rate": 1e-06,
      "loss": 0.0118,
      "step": 1386
    },
    {
      "clip_ratio/high_max": 0.002441510689095594,
      "clip_ratio/high_mean": 0.0011561646861082409,
      "clip_ratio/low_mean": 0.0017586114117875695,
      "clip_ratio/low_min": 9.969240636564791e-05,
      "clip_ratio/region_mean": 0.002914776101533789,
      "epoch": 0.12945300970080909,
      "grad_norm": 3.9044623374938965,
      "learning_rate": 1e-06,
      "loss": 0.0182,
      "step": 1387
    },
    {
      "clip_ratio/high_max": 0.0031801716177142225,
      "clip_ratio/high_mean": 0.0012834373774239793,
      "clip_ratio/low_mean": 0.0015878853773756418,
      "clip_ratio/low_min": 0.00019396785864955746,
      "clip_ratio/region_mean": 0.002871322722057812,
      "epoch": 0.12954634280080968,
      "grad_norm": 0.21645905077457428,
      "learning_rate": 1e-06,
      "loss": 0.0061,
      "step": 1388
    },
    {
      "clip_ratio/high_max": 0.0024777334183454514,
      "clip_ratio/high_mean": 0.0009807090937101748,
      "clip_ratio/low_mean": 0.0016138226201292127,
      "clip_ratio/low_min": 0.0001415236147295218,
      "clip_ratio/region_mean": 0.0025945317174773663,
      "epoch": 0.12963967590081024,
      "grad_norm": 0.13816550374031067,
      "learning_rate": 1e-06,
      "loss": 0.0012,
      "step": 1389
    },
    {
      "clip_ratio/high_max": 0.002441591554088518,
      "clip_ratio/high_mean": 0.0009266625202144496,
      "clip_ratio/low_mean": 0.001571533088281285,
      "clip_ratio/low_min": 0.00013892288006900344,
      "clip_ratio/region_mean": 0.00249819562304765,
      "epoch": 0.12973300900081083,
      "grad_norm": 1.4158962965011597,
      "learning_rate": 1e-06,
      "loss": 0.0545,
      "step": 1390
    },
    {
      "clip_ratio/high_max": 0.002397955147898756,
      "clip_ratio/high_mean": 0.0011183817532582907,
      "clip_ratio/low_mean": 0.001571245211380301,
      "clip_ratio/low_min": 8.463525773549918e-05,
      "clip_ratio/region_mean": 0.0026896269628196023,
      "epoch": 0.12982634210081143,
      "grad_norm": 91517.6328125,
      "learning_rate": 1e-06,
      "loss": 15.2876,
      "step": 1391
    },
    {
      "clip_ratio/high_max": 0.002460081028402783,
      "clip_ratio/high_mean": 0.0010267010075040162,
      "clip_ratio/low_mean": 0.001574430429172935,
      "clip_ratio/low_min": 8.699306454218458e-05,
      "clip_ratio/region_mean": 0.002601131403935142,
      "epoch": 0.129919675200812,
      "grad_norm": 21.62727165222168,
      "learning_rate": 1e-06,
      "loss": 0.1577,
      "step": 1392
    },
    {
      "clip_ratio/high_max": 0.003137223502562847,
      "clip_ratio/high_mean": 0.0013424749340629205,
      "clip_ratio/low_mean": 0.0013437964735203423,
      "clip_ratio/low_min": 8.148366759996861e-05,
      "clip_ratio/region_mean": 0.0026862713712034747,
      "epoch": 0.13001300830081258,
      "grad_norm": 0.16642116010189056,
      "learning_rate": 1e-06,
      "loss": -0.0672,
      "step": 1393
    },
    {
      "clip_ratio/high_max": 0.002282716552144848,
      "clip_ratio/high_mean": 0.000946288801060291,
      "clip_ratio/low_mean": 0.0015198332057480002,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002466122015903238,
      "epoch": 0.13010634140081317,
      "grad_norm": 196.65061950683594,
      "learning_rate": 1e-06,
      "loss": 0.1428,
      "step": 1394
    },
    {
      "clip_ratio/high_max": 0.002296278595167678,
      "clip_ratio/high_mean": 0.0010135039028682513,
      "clip_ratio/low_mean": 0.0017669905537331942,
      "clip_ratio/low_min": 0.00018960191118821967,
      "clip_ratio/region_mean": 0.0027804944620584138,
      "epoch": 0.13019967450081374,
      "grad_norm": 194.7013397216797,
      "learning_rate": 1e-06,
      "loss": 5.4421,
      "step": 1395
    },
    {
      "clip_ratio/high_max": 0.002409439483017195,
      "clip_ratio/high_mean": 0.0009610891229385743,
      "clip_ratio/low_mean": 0.0016240528420894407,
      "clip_ratio/low_min": 7.231796007545199e-05,
      "clip_ratio/region_mean": 0.002585142028692644,
      "epoch": 0.13029300760081433,
      "grad_norm": 2.2608273029327393,
      "learning_rate": 1e-06,
      "loss": 0.041,
      "step": 1396
    },
    {
      "clip_ratio/high_max": 0.0026952748667099513,
      "clip_ratio/high_mean": 0.0011247053880651947,
      "clip_ratio/low_mean": 0.001473238691687584,
      "clip_ratio/low_min": 0.00015692210581619292,
      "clip_ratio/region_mean": 0.0025979440397350118,
      "epoch": 0.13038634070081492,
      "grad_norm": 0.16640086472034454,
      "learning_rate": 1e-06,
      "loss": 0.0156,
      "step": 1397
    },
    {
      "clip_ratio/high_max": 0.003061710885958746,
      "clip_ratio/high_mean": 0.0012513508154370356,
      "clip_ratio/low_mean": 0.0013228721436462365,
      "clip_ratio/low_min": 7.185409594967496e-05,
      "clip_ratio/region_mean": 0.002574222940893378,
      "epoch": 0.1304796738008155,
      "grad_norm": 0.11927152425050735,
      "learning_rate": 1e-06,
      "loss": -0.0245,
      "step": 1398
    },
    {
      "clip_ratio/high_max": 0.0026412271326989867,
      "clip_ratio/high_mean": 0.001060487840732094,
      "clip_ratio/low_mean": 0.001678478638496017,
      "clip_ratio/low_min": 0.00016108862564578885,
      "clip_ratio/region_mean": 0.0027389664537622593,
      "epoch": 0.13057300690081608,
      "grad_norm": 0.13923116028308868,
      "learning_rate": 1e-06,
      "loss": 0.013,
      "step": 1399
    },
    {
      "clip_ratio/high_max": 0.002258217915368732,
      "clip_ratio/high_mean": 0.0009664555927884066,
      "clip_ratio/low_mean": 0.0017232697264262242,
      "clip_ratio/low_min": 0.00017557459250383545,
      "clip_ratio/region_mean": 0.002689725282834843,
      "epoch": 0.13066634000081667,
      "grad_norm": 0.13826005160808563,
      "learning_rate": 1e-06,
      "loss": 0.0461,
      "step": 1400
    },
    {
      "clip_ratio/high_max": 0.002481078823620919,
      "clip_ratio/high_mean": 0.0010340552380512236,
      "clip_ratio/low_mean": 0.0016081076209957246,
      "clip_ratio/low_min": 0.00019811754646070767,
      "clip_ratio/region_mean": 0.002642162929987535,
      "epoch": 0.13075967310081724,
      "grad_norm": 241.93060302734375,
      "learning_rate": 1e-06,
      "loss": 0.1939,
      "step": 1401
    },
    {
      "clip_ratio/high_max": 0.0024730574514251202,
      "clip_ratio/high_mean": 0.0010984615983034018,
      "clip_ratio/low_mean": 0.0016005689685698599,
      "clip_ratio/low_min": 0.00011741509752027923,
      "clip_ratio/region_mean": 0.0026990305559593253,
      "epoch": 0.13085300620081783,
      "grad_norm": 135.19520568847656,
      "learning_rate": 1e-06,
      "loss": 0.0128,
      "step": 1402
    },
    {
      "clip_ratio/high_max": 0.002391772115515778,
      "clip_ratio/high_mean": 0.0010481422850716626,
      "clip_ratio/low_mean": 0.0015887210793152917,
      "clip_ratio/low_min": 0.00016959891945589334,
      "clip_ratio/region_mean": 0.002636863384395838,
      "epoch": 0.13094633930081842,
      "grad_norm": 9.176450729370117,
      "learning_rate": 1e-06,
      "loss": 0.0053,
      "step": 1403
    },
    {
      "clip_ratio/high_max": 0.0026769865544338245,
      "clip_ratio/high_mean": 0.0011089461295341607,
      "clip_ratio/low_mean": 0.0015980123007466318,
      "clip_ratio/low_min": 0.00013346876494324533,
      "clip_ratio/region_mean": 0.0027069584393757395,
      "epoch": 0.13103967240081899,
      "grad_norm": 41.052024841308594,
      "learning_rate": 1e-06,
      "loss": 0.0138,
      "step": 1404
    },
    {
      "clip_ratio/high_max": 0.002473982262017671,
      "clip_ratio/high_mean": 0.0010532237156439805,
      "clip_ratio/low_mean": 0.0015532347970292903,
      "clip_ratio/low_min": 0.00014090799231780693,
      "clip_ratio/region_mean": 0.0026064585326821543,
      "epoch": 0.13113300550081958,
      "grad_norm": 0.1330929696559906,
      "learning_rate": 1e-06,
      "loss": 0.018,
      "step": 1405
    },
    {
      "clip_ratio/high_max": 0.0027944278554059565,
      "clip_ratio/high_mean": 0.001026321348035708,
      "clip_ratio/low_mean": 0.0016032019921112806,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002629523391078692,
      "epoch": 0.13122633860082017,
      "grad_norm": 2934.9677734375,
      "learning_rate": 1e-06,
      "loss": 0.1599,
      "step": 1406
    },
    {
      "clip_ratio/high_max": 0.002365184911468532,
      "clip_ratio/high_mean": 0.0010893745293287793,
      "clip_ratio/low_mean": 0.0017818395463109482,
      "clip_ratio/low_min": 0.00015969385640346445,
      "clip_ratio/region_mean": 0.002871214077458717,
      "epoch": 0.13131967170082076,
      "grad_norm": 0.5821436047554016,
      "learning_rate": 1e-06,
      "loss": 0.0597,
      "step": 1407
    },
    {
      "clip_ratio/high_max": 0.0026922695251414552,
      "clip_ratio/high_mean": 0.001224003248353256,
      "clip_ratio/low_mean": 0.0013902223563491134,
      "clip_ratio/low_min": 1.6684463844285347e-05,
      "clip_ratio/region_mean": 0.0026142256247112527,
      "epoch": 0.13141300480082133,
      "grad_norm": 0.3245605528354645,
      "learning_rate": 1e-06,
      "loss": 0.0018,
      "step": 1408
    },
    {
      "clip_ratio/high_max": 0.0026298124212189578,
      "clip_ratio/high_mean": 0.001025515051878756,
      "clip_ratio/low_mean": 0.001735656609525904,
      "clip_ratio/low_min": 0.00013841494001098908,
      "clip_ratio/region_mean": 0.002761171585007105,
      "epoch": 0.13150633790082192,
      "grad_norm": 273.7525634765625,
      "learning_rate": 1e-06,
      "loss": 0.0941,
      "step": 1409
    },
    {
      "clip_ratio/high_max": 0.0024033721529121976,
      "clip_ratio/high_mean": 0.0009953529170161346,
      "clip_ratio/low_mean": 0.0017387284606229514,
      "clip_ratio/low_min": 0.00028151608785265125,
      "clip_ratio/region_mean": 0.0027340813976479694,
      "epoch": 0.1315996710008225,
      "grad_norm": 0.130961075425148,
      "learning_rate": 1e-06,
      "loss": 0.0631,
      "step": 1410
    },
    {
      "clip_ratio/high_max": 0.00272478587430669,
      "clip_ratio/high_mean": 0.0011675254609144758,
      "clip_ratio/low_mean": 0.0015568342460028362,
      "clip_ratio/low_min": 7.283431114046834e-05,
      "clip_ratio/region_mean": 0.0027243596559856087,
      "epoch": 0.13169300410082307,
      "grad_norm": 0.40550360083580017,
      "learning_rate": 1e-06,
      "loss": 0.0042,
      "step": 1411
    },
    {
      "clip_ratio/high_max": 0.002548497348470846,
      "clip_ratio/high_mean": 0.0011468323955341475,
      "clip_ratio/low_mean": 0.001566671908221906,
      "clip_ratio/low_min": 5.344206510926597e-05,
      "clip_ratio/region_mean": 0.0027135042619192973,
      "epoch": 0.13178633720082367,
      "grad_norm": 0.12724648416042328,
      "learning_rate": 1e-06,
      "loss": -0.0104,
      "step": 1412
    },
    {
      "clip_ratio/high_max": 0.002627470181323588,
      "clip_ratio/high_mean": 0.0011432980918471003,
      "clip_ratio/low_mean": 0.0016754151874920353,
      "clip_ratio/low_min": 0.0001339665086561581,
      "clip_ratio/region_mean": 0.002818713299348019,
      "epoch": 0.13187967030082426,
      "grad_norm": 0.7243697643280029,
      "learning_rate": 1e-06,
      "loss": -0.0088,
      "step": 1413
    },
    {
      "clip_ratio/high_max": 0.002435280752251856,
      "clip_ratio/high_mean": 0.0009853520496108104,
      "clip_ratio/low_mean": 0.0017027171343215741,
      "clip_ratio/low_min": 5.3409672545967624e-05,
      "clip_ratio/region_mean": 0.002688069245778024,
      "epoch": 0.13197300340082482,
      "grad_norm": 188.37423706054688,
      "learning_rate": 1e-06,
      "loss": 0.0672,
      "step": 1414
    },
    {
      "clip_ratio/high_max": 0.002681160916836234,
      "clip_ratio/high_mean": 0.0009766693292476702,
      "clip_ratio/low_mean": 0.0016269573861791287,
      "clip_ratio/low_min": 9.762062836671248e-05,
      "clip_ratio/region_mean": 0.002603626729978714,
      "epoch": 0.13206633650082542,
      "grad_norm": 0.12333964556455612,
      "learning_rate": 1e-06,
      "loss": 0.0334,
      "step": 1415
    },
    {
      "clip_ratio/high_max": 0.0024466469330945984,
      "clip_ratio/high_mean": 0.0010013362916652113,
      "clip_ratio/low_mean": 0.0017507261072751135,
      "clip_ratio/low_min": 0.00011843363972730003,
      "clip_ratio/region_mean": 0.0027520624425960705,
      "epoch": 0.132159669600826,
      "grad_norm": 0.20634008944034576,
      "learning_rate": 1e-06,
      "loss": 0.0051,
      "step": 1416
    },
    {
      "clip_ratio/high_max": 0.0029374447258305736,
      "clip_ratio/high_mean": 0.0011167653356096707,
      "clip_ratio/low_mean": 0.0018540215751272626,
      "clip_ratio/low_min": 0.0002036642617895268,
      "clip_ratio/region_mean": 0.00297078685980523,
      "epoch": 0.13225300270082657,
      "grad_norm": 13.281930923461914,
      "learning_rate": 1e-06,
      "loss": 0.0289,
      "step": 1417
    },
    {
      "clip_ratio/high_max": 0.0028347576735541224,
      "clip_ratio/high_mean": 0.0012266089506738354,
      "clip_ratio/low_mean": 0.0016293151456920896,
      "clip_ratio/low_min": 7.572861431981437e-05,
      "clip_ratio/region_mean": 0.0028559242127812468,
      "epoch": 0.13234633580082716,
      "grad_norm": 258.9142150878906,
      "learning_rate": 1e-06,
      "loss": 30.6861,
      "step": 1418
    },
    {
      "clip_ratio/high_max": 0.002383655904850457,
      "clip_ratio/high_mean": 0.0008805097913864302,
      "clip_ratio/low_mean": 0.001709411561023444,
      "clip_ratio/low_min": 0.00018154647023038706,
      "clip_ratio/region_mean": 0.0025899213724187575,
      "epoch": 0.13243966890082776,
      "grad_norm": 430.251708984375,
      "learning_rate": 1e-06,
      "loss": 1241.2106,
      "step": 1419
    },
    {
      "clip_ratio/high_max": 0.002969776847749017,
      "clip_ratio/high_mean": 0.001251856370799942,
      "clip_ratio/low_mean": 0.001433284724043915,
      "clip_ratio/low_min": 9.145713556790724e-05,
      "clip_ratio/region_mean": 0.002685141036636196,
      "epoch": 0.13253300200082832,
      "grad_norm": 8.915518760681152,
      "learning_rate": 1e-06,
      "loss": -0.0118,
      "step": 1420
    },
    {
      "clip_ratio/high_max": 0.0028583743842318654,
      "clip_ratio/high_mean": 0.0011785467941081151,
      "clip_ratio/low_mean": 0.0017261717221117578,
      "clip_ratio/low_min": 0.00017226733416464413,
      "clip_ratio/region_mean": 0.002904718538047746,
      "epoch": 0.1326263351008289,
      "grad_norm": 0.11725408583879471,
      "learning_rate": 1e-06,
      "loss": 0.0372,
      "step": 1421
    },
    {
      "clip_ratio/high_max": 0.002540175693866331,
      "clip_ratio/high_mean": 0.001076865206414368,
      "clip_ratio/low_mean": 0.0015768845187267289,
      "clip_ratio/low_min": 0.00019682511810970027,
      "clip_ratio/region_mean": 0.002653749739693012,
      "epoch": 0.1327196682008295,
      "grad_norm": 0.12659770250320435,
      "learning_rate": 1e-06,
      "loss": -0.0007,
      "step": 1422
    },
    {
      "clip_ratio/high_max": 0.002712263914872892,
      "clip_ratio/high_mean": 0.0010842850024346262,
      "clip_ratio/low_mean": 0.0018126404065696988,
      "clip_ratio/low_min": 0.00020109376782784238,
      "clip_ratio/region_mean": 0.002896925463574007,
      "epoch": 0.13281300130083007,
      "grad_norm": 1034.2421875,
      "learning_rate": 1e-06,
      "loss": 1.2496,
      "step": 1423
    },
    {
      "clip_ratio/high_max": 0.0024864735460141674,
      "clip_ratio/high_mean": 0.0010395293647889048,
      "clip_ratio/low_mean": 0.0016647437805659138,
      "clip_ratio/low_min": 0.0002000084441533545,
      "clip_ratio/region_mean": 0.002704273138078861,
      "epoch": 0.13290633440083066,
      "grad_norm": 0.10571229457855225,
      "learning_rate": 1e-06,
      "loss": 0.0154,
      "step": 1424
    },
    {
      "clip_ratio/high_max": 0.0022296260176517535,
      "clip_ratio/high_mean": 0.00095350923766091,
      "clip_ratio/low_mean": 0.001687831652816385,
      "clip_ratio/low_min": 0.00012180322664789855,
      "clip_ratio/region_mean": 0.002641340885020327,
      "epoch": 0.13299966750083125,
      "grad_norm": 187.03111267089844,
      "learning_rate": 1e-06,
      "loss": 0.0672,
      "step": 1425
    },
    {
      "clip_ratio/high_max": 0.0029540174291469157,
      "clip_ratio/high_mean": 0.0011986405188508797,
      "clip_ratio/low_mean": 0.0019007343289558776,
      "clip_ratio/low_min": 0.00029376470592978876,
      "clip_ratio/region_mean": 0.0030993748805485666,
      "epoch": 0.13309300060083182,
      "grad_norm": 172669.859375,
      "learning_rate": 1e-06,
      "loss": 62.844,
      "step": 1426
    },
    {
      "clip_ratio/high_max": 0.0025557678382028826,
      "clip_ratio/high_mean": 0.0011500860382511746,
      "clip_ratio/low_mean": 0.0017583253975317348,
      "clip_ratio/low_min": 0.00010957470021821791,
      "clip_ratio/region_mean": 0.00290841146488674,
      "epoch": 0.1331863337008324,
      "grad_norm": 0.1349499225616455,
      "learning_rate": 1e-06,
      "loss": 0.0208,
      "step": 1427
    },
    {
      "clip_ratio/high_max": 0.002436662296531722,
      "clip_ratio/high_mean": 0.0010106390072905924,
      "clip_ratio/low_mean": 0.0019087325272266753,
      "clip_ratio/low_min": 0.00024005529121495783,
      "clip_ratio/region_mean": 0.002919371450843755,
      "epoch": 0.133279666800833,
      "grad_norm": 5.4312357902526855,
      "learning_rate": 1e-06,
      "loss": 0.0135,
      "step": 1428
    },
    {
      "clip_ratio/high_max": 0.0026954376662615687,
      "clip_ratio/high_mean": 0.0010204571335634682,
      "clip_ratio/low_mean": 0.0016871898478711955,
      "clip_ratio/low_min": 0.0001616558647583588,
      "clip_ratio/region_mean": 0.002707646941416897,
      "epoch": 0.1333729999008336,
      "grad_norm": 0.21249426901340485,
      "learning_rate": 1e-06,
      "loss": 0.0177,
      "step": 1429
    },
    {
      "clip_ratio/high_max": 0.0027993397307000123,
      "clip_ratio/high_mean": 0.0010981743853335502,
      "clip_ratio/low_mean": 0.0018174365832237527,
      "clip_ratio/low_min": 0.00013034590028837556,
      "clip_ratio/region_mean": 0.0029156109812902287,
      "epoch": 0.13346633300083416,
      "grad_norm": 0.8861382603645325,
      "learning_rate": 1e-06,
      "loss": 0.0418,
      "step": 1430
    },
    {
      "clip_ratio/high_max": 0.0024428457763860933,
      "clip_ratio/high_mean": 0.0009711748080007965,
      "clip_ratio/low_mean": 0.001741700998536544,
      "clip_ratio/low_min": 9.761672117747366e-05,
      "clip_ratio/region_mean": 0.0027128758156322874,
      "epoch": 0.13355966610083475,
      "grad_norm": 1.3219248056411743,
      "learning_rate": 1e-06,
      "loss": 0.0244,
      "step": 1431
    },
    {
      "clip_ratio/high_max": 0.0019408474472584203,
      "clip_ratio/high_mean": 0.0008184157995856367,
      "clip_ratio/low_mean": 0.0018007251710514538,
      "clip_ratio/low_min": 0.00020190087616356323,
      "clip_ratio/region_mean": 0.002619140919705387,
      "epoch": 0.13365299920083534,
      "grad_norm": 0.1533147692680359,
      "learning_rate": 1e-06,
      "loss": 0.0706,
      "step": 1432
    },
    {
      "clip_ratio/high_max": 0.002205795761256013,
      "clip_ratio/high_mean": 0.0010021921298175585,
      "clip_ratio/low_mean": 0.0017404344835085794,
      "clip_ratio/low_min": 0.00016646071890136227,
      "clip_ratio/region_mean": 0.00274262666789582,
      "epoch": 0.1337463323008359,
      "grad_norm": 39.03219223022461,
      "learning_rate": 1e-06,
      "loss": 0.306,
      "step": 1433
    },
    {
      "clip_ratio/high_max": 0.0025487060920568183,
      "clip_ratio/high_mean": 0.0009893514761643019,
      "clip_ratio/low_mean": 0.0020536193151201587,
      "clip_ratio/low_min": 0.00024965910233731847,
      "clip_ratio/region_mean": 0.003042970798560418,
      "epoch": 0.1338396654008365,
      "grad_norm": 1.1089484691619873,
      "learning_rate": 1e-06,
      "loss": 0.0681,
      "step": 1434
    },
    {
      "clip_ratio/high_max": 0.0021889104828005657,
      "clip_ratio/high_mean": 0.0008505442274326924,
      "clip_ratio/low_mean": 0.001904676879348699,
      "clip_ratio/low_min": 0.00010199920689046849,
      "clip_ratio/region_mean": 0.0027552211395232007,
      "epoch": 0.1339329985008371,
      "grad_norm": 1933.003173828125,
      "learning_rate": 1e-06,
      "loss": 0.6202,
      "step": 1435
    },
    {
      "clip_ratio/high_max": 0.002621724648633972,
      "clip_ratio/high_mean": 0.0011468651209725067,
      "clip_ratio/low_mean": 0.0014508028034470044,
      "clip_ratio/low_min": 5.736778439313639e-05,
      "clip_ratio/region_mean": 0.002597667851659935,
      "epoch": 0.13402633160083766,
      "grad_norm": 6259031040.0,
      "learning_rate": 1e-06,
      "loss": 2310289.0,
      "step": 1436
    },
    {
      "clip_ratio/high_max": 0.002287137584062293,
      "clip_ratio/high_mean": 0.0010277461678924737,
      "clip_ratio/low_mean": 0.0021229051126283593,
      "clip_ratio/low_min": 0.0002761772830126574,
      "clip_ratio/region_mean": 0.0031506513405474834,
      "epoch": 0.13411966470083825,
      "grad_norm": 0.13045425713062286,
      "learning_rate": 1e-06,
      "loss": 0.0571,
      "step": 1437
    },
    {
      "clip_ratio/high_max": 0.002381912992859725,
      "clip_ratio/high_mean": 0.000982425701295142,
      "clip_ratio/low_mean": 0.0017085306899389252,
      "clip_ratio/low_min": 0.00011801501659647329,
      "clip_ratio/region_mean": 0.002690956367587205,
      "epoch": 0.13421299780083884,
      "grad_norm": 0.2502935230731964,
      "learning_rate": 1e-06,
      "loss": 0.0496,
      "step": 1438
    },
    {
      "clip_ratio/high_max": 0.002949854140751995,
      "clip_ratio/high_mean": 0.0011462210241006687,
      "clip_ratio/low_mean": 0.001587361217389116,
      "clip_ratio/low_min": 7.671535968256649e-06,
      "clip_ratio/region_mean": 0.0027335822232998908,
      "epoch": 0.1343063309008394,
      "grad_norm": 0.7111345529556274,
      "learning_rate": 1e-06,
      "loss": -0.0266,
      "step": 1439
    },
    {
      "clip_ratio/high_max": 0.002485919336322695,
      "clip_ratio/high_mean": 0.00097697609635361,
      "clip_ratio/low_mean": 0.0017890233757498208,
      "clip_ratio/low_min": 0.00010785142330860253,
      "clip_ratio/region_mean": 0.0027659994520945475,
      "epoch": 0.13439966400084,
      "grad_norm": 6.836536884307861,
      "learning_rate": 1e-06,
      "loss": 0.0736,
      "step": 1440
    },
    {
      "clip_ratio/high_max": 0.0023693528601143043,
      "clip_ratio/high_mean": 0.0011060235829063458,
      "clip_ratio/low_mean": 0.0012804510733985808,
      "clip_ratio/low_min": 0.00015452839943463914,
      "clip_ratio/region_mean": 0.002386474618106149,
      "completions/clipped_ratio": 0.012965611049107095,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4095.0,
      "completions/mean_length": 607.1629028320312,
      "completions/mean_terminated_length": 561.3338012695312,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.1344929971008406,
      "grad_norm": 541003743232.0,
      "learning_rate": 1e-06,
      "loss": 1099726443249664.0,
      "num_tokens": 1055091901.0,
      "reward": 0.57861328125,
      "reward_std": 0.18524903059005737,
      "rewards/simpleverify_reward/mean": 0.57861328125,
      "rewards/simpleverify_reward/std": 0.49378326535224915,
      "step": 1441
    },
    {
      "clip_ratio/high_max": 0.002696283219847828,
      "clip_ratio/high_mean": 0.0011504272733873222,
      "clip_ratio/low_mean": 0.0012075958911736961,
      "clip_ratio/low_min": 0.00012501117134888773,
      "clip_ratio/region_mean": 0.002358023150009103,
      "epoch": 0.13458633020084115,
      "grad_norm": 6609274667008.0,
      "learning_rate": 1e-06,
      "loss": 6838346240.0,
      "step": 1442
    },
    {
      "clip_ratio/high_max": 0.003130032360786572,
      "clip_ratio/high_mean": 0.0013046305994066643,
      "clip_ratio/low_mean": 0.000954624874793808,
      "clip_ratio/low_min": 6.335805119306315e-05,
      "clip_ratio/region_mean": 0.002259255496028345,
      "epoch": 0.13467966330084175,
      "grad_norm": 12655656.0,
      "learning_rate": 1e-06,
      "loss": 12854152396800.0,
      "step": 1443
    },
    {
      "clip_ratio/high_max": 0.0033774690455175005,
      "clip_ratio/high_mean": 0.0013816131759085692,
      "clip_ratio/low_mean": 0.001182761898235185,
      "clip_ratio/low_min": 7.217589336505625e-05,
      "clip_ratio/region_mean": 0.0025643750486779027,
      "epoch": 0.13477299640084234,
      "grad_norm": 200055415898112.0,
      "learning_rate": 1e-06,
      "loss": 12370237440.0,
      "step": 1444
    },
    {
      "clip_ratio/high_max": 0.00291202831431292,
      "clip_ratio/high_mean": 0.0011468935408629477,
      "clip_ratio/low_mean": 0.0011852568186441204,
      "clip_ratio/low_min": 6.471354026871268e-05,
      "clip_ratio/region_mean": 0.0023321503758779727,
      "epoch": 0.1348663295008429,
      "grad_norm": 23144734720.0,
      "learning_rate": 1e-06,
      "loss": 376667893661696.0,
      "step": 1445
    },
    {
      "clip_ratio/high_max": 0.003294552559964359,
      "clip_ratio/high_mean": 0.0013599780722870491,
      "clip_ratio/low_mean": 0.0011681275645969436,
      "clip_ratio/low_min": 0.00012788169988198206,
      "clip_ratio/region_mean": 0.00252810561505612,
      "epoch": 0.1349596626008435,
      "grad_norm": 3792513024.0,
      "learning_rate": 1e-06,
      "loss": 31824876.0,
      "step": 1446
    },
    {
      "clip_ratio/high_max": 0.002593165307189338,
      "clip_ratio/high_mean": 0.0011639173353614751,
      "clip_ratio/low_mean": 0.0013022872735746205,
      "clip_ratio/low_min": 2.303722794749774e-05,
      "clip_ratio/region_mean": 0.002466204605298117,
      "epoch": 0.1350529957008441,
      "grad_norm": 79509692874752.0,
      "learning_rate": 1e-06,
      "loss": 1581861044224.0,
      "step": 1447
    },
    {
      "clip_ratio/high_max": 0.0027249893319094554,
      "clip_ratio/high_mean": 0.0011779220258176792,
      "clip_ratio/low_mean": 0.0012073728757968638,
      "clip_ratio/low_min": 0.00012239763236721046,
      "clip_ratio/region_mean": 0.002385294937994331,
      "epoch": 0.13514632880084468,
      "grad_norm": 1784650268672.0,
      "learning_rate": 1e-06,
      "loss": 198344304.0,
      "step": 1448
    },
    {
      "clip_ratio/high_max": 0.0027382071421016008,
      "clip_ratio/high_mean": 0.0011431629318394698,
      "clip_ratio/low_mean": 0.0012400315317790955,
      "clip_ratio/low_min": 0.000131476705064415,
      "clip_ratio/region_mean": 0.002383194470894523,
      "epoch": 0.13523966190084524,
      "grad_norm": 1246192599040.0,
      "learning_rate": 1e-06,
      "loss": 530943756468224.0,
      "step": 1449
    },
    {
      "clip_ratio/high_max": 0.002934131698566489,
      "clip_ratio/high_mean": 0.0010814723063958809,
      "clip_ratio/low_mean": 0.001010956906611682,
      "clip_ratio/low_min": 4.7995610657380894e-05,
      "clip_ratio/region_mean": 0.0020924291893607005,
      "epoch": 0.13533299500084583,
      "grad_norm": 1249203453952.0,
      "learning_rate": 1e-06,
      "loss": 163251232.0,
      "step": 1450
    },
    {
      "clip_ratio/high_max": 0.002858911029761657,
      "clip_ratio/high_mean": 0.001094266652216902,
      "clip_ratio/low_mean": 0.0010532965115999104,
      "clip_ratio/low_min": 0.00013665326332557015,
      "clip_ratio/region_mean": 0.0021475632238434628,
      "epoch": 0.13542632810084643,
      "grad_norm": 515118.46875,
      "learning_rate": 1e-06,
      "loss": 16807.9004,
      "step": 1451
    },
    {
      "clip_ratio/high_max": 0.0030716607507201843,
      "clip_ratio/high_mean": 0.0011527667884365655,
      "clip_ratio/low_mean": 0.0012555806224554544,
      "clip_ratio/low_min": 0.00015277917191269808,
      "clip_ratio/region_mean": 0.0024083474272629246,
      "epoch": 0.135519661200847,
      "grad_norm": 38709356.0,
      "learning_rate": 1e-06,
      "loss": 330850048.0,
      "step": 1452
    },
    {
      "clip_ratio/high_max": 0.003258261211158242,
      "clip_ratio/high_mean": 0.0013011778755753767,
      "clip_ratio/low_mean": 0.00134764647737029,
      "clip_ratio/low_min": 8.870191777532455e-05,
      "clip_ratio/region_mean": 0.0026488243529456668,
      "epoch": 0.13561299430084758,
      "grad_norm": 761610560.0,
      "learning_rate": 1e-06,
      "loss": 777385.25,
      "step": 1453
    },
    {
      "clip_ratio/high_max": 0.0023756955488352105,
      "clip_ratio/high_mean": 0.000998451028863201,
      "clip_ratio/low_mean": 0.001275668077141745,
      "clip_ratio/low_min": 0.0001602807387826033,
      "clip_ratio/region_mean": 0.0022741190914530307,
      "epoch": 0.13570632740084818,
      "grad_norm": 294116736.0,
      "learning_rate": 1e-06,
      "loss": 286564.4375,
      "step": 1454
    },
    {
      "clip_ratio/high_max": 0.0037044620257802308,
      "clip_ratio/high_mean": 0.0013623190388898365,
      "clip_ratio/low_mean": 0.0010984848049702123,
      "clip_ratio/low_min": 8.363441338588018e-06,
      "clip_ratio/region_mean": 0.0024608039093436673,
      "epoch": 0.13579966050084874,
      "grad_norm": 112560.53125,
      "learning_rate": 1e-06,
      "loss": 69654.8594,
      "step": 1455
    },
    {
      "clip_ratio/high_max": 0.0029073726691422053,
      "clip_ratio/high_mean": 0.0011535467201611027,
      "clip_ratio/low_mean": 0.0012407429385348223,
      "clip_ratio/low_min": 0.000180566531525983,
      "clip_ratio/region_mean": 0.002394289636868052,
      "epoch": 0.13589299360084933,
      "grad_norm": 163265.15625,
      "learning_rate": 1e-06,
      "loss": 1490.7811,
      "step": 1456
    },
    {
      "clip_ratio/high_max": 0.0030246080714277923,
      "clip_ratio/high_mean": 0.001346336655842606,
      "clip_ratio/low_mean": 0.0012095758429495618,
      "clip_ratio/low_min": 2.9620852728839964e-05,
      "clip_ratio/region_mean": 0.0025559125206200406,
      "epoch": 0.13598632670084992,
      "grad_norm": 3139.61376953125,
      "learning_rate": 1e-06,
      "loss": 31.5692,
      "step": 1457
    },
    {
      "clip_ratio/high_max": 0.003034998670045752,
      "clip_ratio/high_mean": 0.0012340804132691119,
      "clip_ratio/low_mean": 0.0012775945724570192,
      "clip_ratio/low_min": 9.924536789185368e-05,
      "clip_ratio/region_mean": 0.0025116749602602795,
      "epoch": 0.1360796598008505,
      "grad_norm": 22173950.0,
      "learning_rate": 1e-06,
      "loss": 42564.3398,
      "step": 1458
    },
    {
      "clip_ratio/high_max": 0.0027653024590108544,
      "clip_ratio/high_mean": 0.0010914822978520533,
      "clip_ratio/low_mean": 0.001364976640616078,
      "clip_ratio/low_min": 5.9280187997501343e-05,
      "clip_ratio/region_mean": 0.002456458969390951,
      "epoch": 0.13617299290085108,
      "grad_norm": 9155649.0,
      "learning_rate": 1e-06,
      "loss": 1366.3774,
      "step": 1459
    },
    {
      "clip_ratio/high_max": 0.0026723660485004075,
      "clip_ratio/high_mean": 0.0010863188090297626,
      "clip_ratio/low_mean": 0.0013358630749280564,
      "clip_ratio/low_min": 7.267360342666507e-05,
      "clip_ratio/region_mean": 0.0024221818457590416,
      "epoch": 0.13626632600085167,
      "grad_norm": 16312503.0,
      "learning_rate": 1e-06,
      "loss": 61015.5625,
      "step": 1460
    },
    {
      "clip_ratio/high_max": 0.003069936268730089,
      "clip_ratio/high_mean": 0.0011654438494588248,
      "clip_ratio/low_mean": 0.0012870612281403737,
      "clip_ratio/low_min": 6.497378308267798e-05,
      "clip_ratio/region_mean": 0.002452505061228294,
      "epoch": 0.13635965910085224,
      "grad_norm": 3661.021484375,
      "learning_rate": 1e-06,
      "loss": 1.5682,
      "step": 1461
    },
    {
      "clip_ratio/high_max": 0.002802778282784857,
      "clip_ratio/high_mean": 0.0011618156459007878,
      "clip_ratio/low_mean": 0.0016058762121247128,
      "clip_ratio/low_min": 8.116667777358089e-05,
      "clip_ratio/region_mean": 0.002767691810731776,
      "epoch": 0.13645299220085283,
      "grad_norm": 0.17752307653427124,
      "learning_rate": 1e-06,
      "loss": 0.0489,
      "step": 1462
    },
    {
      "clip_ratio/high_max": 0.0033654941435088404,
      "clip_ratio/high_mean": 0.0013382411416387185,
      "clip_ratio/low_mean": 0.001714239999273559,
      "clip_ratio/low_min": 0.00022977018943493022,
      "clip_ratio/region_mean": 0.003052481151826214,
      "epoch": 0.13654632530085342,
      "grad_norm": 132407704.0,
      "learning_rate": 1e-06,
      "loss": 19732.2305,
      "step": 1463
    },
    {
      "clip_ratio/high_max": 0.0028428116638679057,
      "clip_ratio/high_mean": 0.0010520606592763215,
      "clip_ratio/low_mean": 0.0013326241896720603,
      "clip_ratio/low_min": 9.816868623602204e-05,
      "clip_ratio/region_mean": 0.002384684943535831,
      "epoch": 0.13663965840085399,
      "grad_norm": 6.5344109535217285,
      "learning_rate": 1e-06,
      "loss": 0.0431,
      "step": 1464
    },
    {
      "clip_ratio/high_max": 0.003020563948666677,
      "clip_ratio/high_mean": 0.0011408307655074168,
      "clip_ratio/low_mean": 0.001660366848227568,
      "clip_ratio/low_min": 0.00013768580720352475,
      "clip_ratio/region_mean": 0.002801197631924879,
      "epoch": 0.13673299150085458,
      "grad_norm": 87.53910064697266,
      "learning_rate": 1e-06,
      "loss": 0.1598,
      "step": 1465
    },
    {
      "clip_ratio/high_max": 0.0027107544883619994,
      "clip_ratio/high_mean": 0.0010623608413879992,
      "clip_ratio/low_mean": 0.0014829712235950865,
      "clip_ratio/low_min": 0.00011926272145501571,
      "clip_ratio/region_mean": 0.00254533214319963,
      "epoch": 0.13682632460085517,
      "grad_norm": 176.5533905029297,
      "learning_rate": 1e-06,
      "loss": 0.1242,
      "step": 1466
    },
    {
      "clip_ratio/high_max": 0.0026013092865468934,
      "clip_ratio/high_mean": 0.0011091056949226186,
      "clip_ratio/low_mean": 0.0014492754016828258,
      "clip_ratio/low_min": 0.00018529252338339575,
      "clip_ratio/region_mean": 0.00255838104931172,
      "epoch": 0.13691965770085573,
      "grad_norm": 21.03973388671875,
      "learning_rate": 1e-06,
      "loss": 0.5121,
      "step": 1467
    },
    {
      "clip_ratio/high_max": 0.0030666312304674648,
      "clip_ratio/high_mean": 0.0011620019522524672,
      "clip_ratio/low_mean": 0.0017692050387267955,
      "clip_ratio/low_min": 9.229573697666638e-05,
      "clip_ratio/region_mean": 0.0029312069818843156,
      "epoch": 0.13701299080085633,
      "grad_norm": 0.4532798230648041,
      "learning_rate": 1e-06,
      "loss": 0.0502,
      "step": 1468
    },
    {
      "clip_ratio/high_max": 0.0023283137707039714,
      "clip_ratio/high_mean": 0.0009691105151432566,
      "clip_ratio/low_mean": 0.0016064558149082586,
      "clip_ratio/low_min": 1.5052986782393418e-05,
      "clip_ratio/region_mean": 0.0025755663809832186,
      "epoch": 0.13710632390085692,
      "grad_norm": 77.69818115234375,
      "learning_rate": 1e-06,
      "loss": 5.7352,
      "step": 1469
    },
    {
      "clip_ratio/high_max": 0.003395376101252623,
      "clip_ratio/high_mean": 0.0013902069622417912,
      "clip_ratio/low_mean": 0.0014539737949235132,
      "clip_ratio/low_min": 8.237928341259249e-05,
      "clip_ratio/region_mean": 0.002844180751708336,
      "epoch": 0.1371996570008575,
      "grad_norm": 299.71783447265625,
      "learning_rate": 1e-06,
      "loss": 0.0082,
      "step": 1470
    },
    {
      "clip_ratio/high_max": 0.002120830729836598,
      "clip_ratio/high_mean": 0.0009156599826383172,
      "clip_ratio/low_mean": 0.00175433985714335,
      "clip_ratio/low_min": 0.00030856522789690644,
      "clip_ratio/region_mean": 0.002669999870704487,
      "epoch": 0.13729299010085808,
      "grad_norm": 2576.32421875,
      "learning_rate": 1e-06,
      "loss": 0.688,
      "step": 1471
    },
    {
      "clip_ratio/high_max": 0.0025532959698466584,
      "clip_ratio/high_mean": 0.0010217638737231027,
      "clip_ratio/low_mean": 0.0018515736519475468,
      "clip_ratio/low_min": 0.0002334883301955415,
      "clip_ratio/region_mean": 0.0028733375074807554,
      "epoch": 0.13738632320085867,
      "grad_norm": 1146906.625,
      "learning_rate": 1e-06,
      "loss": 126.0968,
      "step": 1472
    },
    {
      "clip_ratio/high_max": 0.0023415247414959595,
      "clip_ratio/high_mean": 0.0008965679935499793,
      "clip_ratio/low_mean": 0.0016249498949036933,
      "clip_ratio/low_min": 0.00011522577642608667,
      "clip_ratio/region_mean": 0.0025215178829967044,
      "epoch": 0.13747965630085926,
      "grad_norm": 56.68210983276367,
      "learning_rate": 1e-06,
      "loss": 0.1344,
      "step": 1473
    },
    {
      "clip_ratio/high_max": 0.0026426260446896777,
      "clip_ratio/high_mean": 0.0011075572583649773,
      "clip_ratio/low_mean": 0.001867687824415043,
      "clip_ratio/low_min": 0.0001511025329818949,
      "clip_ratio/region_mean": 0.0029752450936939567,
      "epoch": 0.13757298940085982,
      "grad_norm": 45.35641860961914,
      "learning_rate": 1e-06,
      "loss": 0.0716,
      "step": 1474
    },
    {
      "clip_ratio/high_max": 0.0026933189656119794,
      "clip_ratio/high_mean": 0.0011102631578978617,
      "clip_ratio/low_mean": 0.0017461525458202232,
      "clip_ratio/low_min": 0.00020138562740612542,
      "clip_ratio/region_mean": 0.0028564157328219153,
      "epoch": 0.13766632250086042,
      "grad_norm": 75.17736053466797,
      "learning_rate": 1e-06,
      "loss": 204.6845,
      "step": 1475
    },
    {
      "clip_ratio/high_max": 0.0025441070101805963,
      "clip_ratio/high_mean": 0.0011320877383695915,
      "clip_ratio/low_mean": 0.0020320771291153505,
      "clip_ratio/low_min": 0.0002113869677486946,
      "clip_ratio/region_mean": 0.0031641648165532388,
      "epoch": 0.137759655600861,
      "grad_norm": 0.15559247136116028,
      "learning_rate": 1e-06,
      "loss": 0.0551,
      "step": 1476
    },
    {
      "clip_ratio/high_max": 0.002552034806285519,
      "clip_ratio/high_mean": 0.0010478249614607194,
      "clip_ratio/low_mean": 0.0015189962578006089,
      "clip_ratio/low_min": 5.760727253800724e-05,
      "clip_ratio/region_mean": 0.002566821247455664,
      "epoch": 0.13785298870086157,
      "grad_norm": 48.580528259277344,
      "learning_rate": 1e-06,
      "loss": 0.3133,
      "step": 1477
    },
    {
      "clip_ratio/high_max": 0.003021911354153417,
      "clip_ratio/high_mean": 0.0012097829840058694,
      "clip_ratio/low_mean": 0.0018334678279643413,
      "clip_ratio/low_min": 5.069810322311241e-05,
      "clip_ratio/region_mean": 0.003043250799237285,
      "epoch": 0.13794632180086216,
      "grad_norm": 1.014416217803955,
      "learning_rate": 1e-06,
      "loss": -0.0159,
      "step": 1478
    },
    {
      "clip_ratio/high_max": 0.0027577435175771825,
      "clip_ratio/high_mean": 0.00114695446609403,
      "clip_ratio/low_mean": 0.002126230210706126,
      "clip_ratio/low_min": 0.0003649435839179205,
      "clip_ratio/region_mean": 0.003273184600402601,
      "epoch": 0.13803965490086276,
      "grad_norm": 0.6722376346588135,
      "learning_rate": 1e-06,
      "loss": 0.0475,
      "step": 1479
    },
    {
      "clip_ratio/high_max": 0.0025276836386183277,
      "clip_ratio/high_mean": 0.0010270712446072139,
      "clip_ratio/low_mean": 0.0018856107708415948,
      "clip_ratio/low_min": 0.00016682858768035658,
      "clip_ratio/region_mean": 0.002912681971793063,
      "epoch": 0.13813298800086332,
      "grad_norm": 138.02804565429688,
      "learning_rate": 1e-06,
      "loss": 0.0701,
      "step": 1480
    },
    {
      "clip_ratio/high_max": 0.0025165362094412558,
      "clip_ratio/high_mean": 0.0010436761367600411,
      "clip_ratio/low_mean": 0.0019109858185402118,
      "clip_ratio/low_min": 0.0002596727417767397,
      "clip_ratio/region_mean": 0.002954661918920465,
      "epoch": 0.1382263211008639,
      "grad_norm": 41.58405685424805,
      "learning_rate": 1e-06,
      "loss": 0.0258,
      "step": 1481
    },
    {
      "clip_ratio/high_max": 0.0025035100552486256,
      "clip_ratio/high_mean": 0.00100844184817106,
      "clip_ratio/low_mean": 0.0016781365739007015,
      "clip_ratio/low_min": 0.00018274706417287234,
      "clip_ratio/region_mean": 0.002686578423890751,
      "epoch": 0.1383196542008645,
      "grad_norm": 94748942336.0,
      "learning_rate": 1e-06,
      "loss": 16039725.0,
      "step": 1482
    },
    {
      "clip_ratio/high_max": 0.0025282146452809684,
      "clip_ratio/high_mean": 0.001100837082049111,
      "clip_ratio/low_mean": 0.001622892279556254,
      "clip_ratio/low_min": 0.00010250700415781466,
      "clip_ratio/region_mean": 0.002723729397985153,
      "epoch": 0.13841298730086507,
      "grad_norm": 47.18560791015625,
      "learning_rate": 1e-06,
      "loss": -0.0018,
      "step": 1483
    },
    {
      "clip_ratio/high_max": 0.0025120902428170666,
      "clip_ratio/high_mean": 0.0011071353046645527,
      "clip_ratio/low_mean": 0.001842096826294437,
      "clip_ratio/low_min": 0.0001426637318218127,
      "clip_ratio/region_mean": 0.0029492320827557705,
      "epoch": 0.13850632040086566,
      "grad_norm": 36.2614631652832,
      "learning_rate": 1e-06,
      "loss": 0.008,
      "step": 1484
    },
    {
      "clip_ratio/high_max": 0.0028797902341466397,
      "clip_ratio/high_mean": 0.0012152022718510125,
      "clip_ratio/low_mean": 0.0018695794133236632,
      "clip_ratio/low_min": 0.00014046985052118544,
      "clip_ratio/region_mean": 0.003084781754296273,
      "epoch": 0.13859965350086625,
      "grad_norm": 0.2104385793209076,
      "learning_rate": 1e-06,
      "loss": -0.0032,
      "step": 1485
    },
    {
      "clip_ratio/high_max": 0.003036441503354581,
      "clip_ratio/high_mean": 0.001093587703508092,
      "clip_ratio/low_mean": 0.0018492365852580406,
      "clip_ratio/low_min": 7.315428683796199e-05,
      "clip_ratio/region_mean": 0.0029428243069560267,
      "epoch": 0.13869298660086682,
      "grad_norm": 2864.622314453125,
      "learning_rate": 1e-06,
      "loss": 0.6687,
      "step": 1486
    },
    {
      "clip_ratio/high_max": 0.0025476403898210265,
      "clip_ratio/high_mean": 0.0010516468064452056,
      "clip_ratio/low_mean": 0.0019159467410645448,
      "clip_ratio/low_min": 0.0001725349520711461,
      "clip_ratio/region_mean": 0.0029675935802515596,
      "epoch": 0.1387863197008674,
      "grad_norm": 0.9033017158508301,
      "learning_rate": 1e-06,
      "loss": 0.0295,
      "step": 1487
    },
    {
      "clip_ratio/high_max": 0.0027203057179576717,
      "clip_ratio/high_mean": 0.0010762014280771837,
      "clip_ratio/low_mean": 0.0019635607895907015,
      "clip_ratio/low_min": 0.00012617603897524532,
      "clip_ratio/region_mean": 0.0030397622322198004,
      "epoch": 0.138879652800868,
      "grad_norm": 0.12829628586769104,
      "learning_rate": 1e-06,
      "loss": 0.036,
      "step": 1488
    },
    {
      "clip_ratio/high_max": 0.002672911221452523,
      "clip_ratio/high_mean": 0.0010790321848617168,
      "clip_ratio/low_mean": 0.0020393501108628698,
      "clip_ratio/low_min": 0.000298680504783988,
      "clip_ratio/region_mean": 0.0031183823448373005,
      "epoch": 0.13897298590086857,
      "grad_norm": 82108.6640625,
      "learning_rate": 1e-06,
      "loss": 98470.9062,
      "step": 1489
    },
    {
      "clip_ratio/high_max": 0.00289368380617816,
      "clip_ratio/high_mean": 0.00111874097638065,
      "clip_ratio/low_mean": 0.0020657636923715472,
      "clip_ratio/low_min": 0.00021526488671952393,
      "clip_ratio/region_mean": 0.0031845046614762396,
      "epoch": 0.13906631900086916,
      "grad_norm": 11798.328125,
      "learning_rate": 1e-06,
      "loss": 3.9193,
      "step": 1490
    },
    {
      "clip_ratio/high_max": 0.002735727437539026,
      "clip_ratio/high_mean": 0.0010649611458575237,
      "clip_ratio/low_mean": 0.0020351482853584457,
      "clip_ratio/low_min": 0.00011033204100385774,
      "clip_ratio/region_mean": 0.003100109417573549,
      "epoch": 0.13915965210086975,
      "grad_norm": 0.2727256715297699,
      "learning_rate": 1e-06,
      "loss": 0.0455,
      "step": 1491
    },
    {
      "clip_ratio/high_max": 0.0028316142052062787,
      "clip_ratio/high_mean": 0.0010857903507712763,
      "clip_ratio/low_mean": 0.0018259168064105324,
      "clip_ratio/low_min": 8.079096005531028e-05,
      "clip_ratio/region_mean": 0.0029117071826476604,
      "epoch": 0.13925298520087034,
      "grad_norm": 361965.40625,
      "learning_rate": 1e-06,
      "loss": 41.9279,
      "step": 1492
    },
    {
      "clip_ratio/high_max": 0.0035483056853991,
      "clip_ratio/high_mean": 0.0012848416808992624,
      "clip_ratio/low_mean": 0.0017576928712514928,
      "clip_ratio/low_min": 9.259940816264134e-05,
      "clip_ratio/region_mean": 0.0030425345394178294,
      "epoch": 0.1393463183008709,
      "grad_norm": 1.8188329935073853,
      "learning_rate": 1e-06,
      "loss": -0.0186,
      "step": 1493
    },
    {
      "clip_ratio/high_max": 0.002997007148223929,
      "clip_ratio/high_mean": 0.0011136674347653752,
      "clip_ratio/low_mean": 0.0021935204713372514,
      "clip_ratio/low_min": 0.0002424653039270197,
      "clip_ratio/region_mean": 0.003307187871541828,
      "epoch": 0.1394396514008715,
      "grad_norm": 1499.675537109375,
      "learning_rate": 1e-06,
      "loss": 0.8552,
      "step": 1494
    },
    {
      "clip_ratio/high_max": 0.0028543345688376576,
      "clip_ratio/high_mean": 0.0011214733185624937,
      "clip_ratio/low_mean": 0.0018787241206155159,
      "clip_ratio/low_min": 5.1910259571741335e-05,
      "clip_ratio/region_mean": 0.003000197422807105,
      "epoch": 0.1395329845008721,
      "grad_norm": 0.1897302269935608,
      "learning_rate": 1e-06,
      "loss": 0.0225,
      "step": 1495
    },
    {
      "clip_ratio/high_max": 0.002491327468305826,
      "clip_ratio/high_mean": 0.0010863590923690936,
      "clip_ratio/low_mean": 0.0018487736961105838,
      "clip_ratio/low_min": 0.00012748785957228392,
      "clip_ratio/region_mean": 0.0029351327975746244,
      "epoch": 0.13962631760087266,
      "grad_norm": 0.5874179601669312,
      "learning_rate": 1e-06,
      "loss": 0.0421,
      "step": 1496
    },
    {
      "clip_ratio/high_max": 0.002512344333808869,
      "clip_ratio/high_mean": 0.001070617987352307,
      "clip_ratio/low_mean": 0.0016460278820886742,
      "clip_ratio/low_min": 0.00010348728847020539,
      "clip_ratio/region_mean": 0.0027166458748979494,
      "epoch": 0.13971965070087325,
      "grad_norm": 0.13642385601997375,
      "learning_rate": 1e-06,
      "loss": 0.0295,
      "step": 1497
    },
    {
      "clip_ratio/high_max": 0.002776670349703636,
      "clip_ratio/high_mean": 0.0010997803365171421,
      "clip_ratio/low_mean": 0.001967505093489308,
      "clip_ratio/low_min": 0.00012074071128154173,
      "clip_ratio/region_mean": 0.0030672854190925136,
      "epoch": 0.13981298380087384,
      "grad_norm": 17646.11328125,
      "learning_rate": 1e-06,
      "loss": 1.2225,
      "step": 1498
    },
    {
      "clip_ratio/high_max": 0.002684170969587285,
      "clip_ratio/high_mean": 0.0010857417455554241,
      "clip_ratio/low_mean": 0.002158684321329929,
      "clip_ratio/low_min": 0.000279772822977975,
      "clip_ratio/region_mean": 0.003244426115998067,
      "epoch": 0.1399063169008744,
      "grad_norm": 32.705810546875,
      "learning_rate": 1e-06,
      "loss": 0.3635,
      "step": 1499
    },
    {
      "clip_ratio/high_max": 0.002476988476701081,
      "clip_ratio/high_mean": 0.0011053278230974684,
      "clip_ratio/low_mean": 0.0018188966823800001,
      "clip_ratio/low_min": 0.00012389728362904862,
      "clip_ratio/region_mean": 0.00292422465281561,
      "epoch": 0.139999650000875,
      "grad_norm": 634.0368041992188,
      "learning_rate": 1e-06,
      "loss": 0.3528,
      "step": 1500
    },
    {
      "clip_ratio/high_max": 0.002559054169978481,
      "clip_ratio/high_mean": 0.000955936819082126,
      "clip_ratio/low_mean": 0.0019511119462549686,
      "clip_ratio/low_min": 0.0002279407526657451,
      "clip_ratio/region_mean": 0.0029070487144053914,
      "epoch": 0.1400929831008756,
      "grad_norm": 1.091138482093811,
      "learning_rate": 1e-06,
      "loss": 0.0722,
      "step": 1501
    },
    {
      "clip_ratio/high_max": 0.002729569867369719,
      "clip_ratio/high_mean": 0.0010826243797055213,
      "clip_ratio/low_mean": 0.0019234130013501272,
      "clip_ratio/low_min": 0.00015380119293695316,
      "clip_ratio/region_mean": 0.0030060373683227226,
      "epoch": 0.14018631620087615,
      "grad_norm": 118.66854858398438,
      "learning_rate": 1e-06,
      "loss": 0.0953,
      "step": 1502
    },
    {
      "clip_ratio/high_max": 0.002382494873018004,
      "clip_ratio/high_mean": 0.0010244989389320835,
      "clip_ratio/low_mean": 0.002014790392422583,
      "clip_ratio/low_min": 0.00014803543854213785,
      "clip_ratio/region_mean": 0.0030392894113902003,
      "epoch": 0.14027964930087675,
      "grad_norm": 622016.375,
      "learning_rate": 1e-06,
      "loss": 2683385.0,
      "step": 1503
    },
    {
      "clip_ratio/high_max": 0.0025807753554545343,
      "clip_ratio/high_mean": 0.0011015739110007416,
      "clip_ratio/low_mean": 0.0019533998492988758,
      "clip_ratio/low_min": 0.00017696638678899035,
      "clip_ratio/region_mean": 0.0030549737784895115,
      "epoch": 0.14037298240087734,
      "grad_norm": 119163952.0,
      "learning_rate": 1e-06,
      "loss": 18249.5703,
      "step": 1504
    },
    {
      "clip_ratio/high_max": 0.002656534365087282,
      "clip_ratio/high_mean": 0.00112109645124292,
      "clip_ratio/low_mean": 0.0019305386922496837,
      "clip_ratio/low_min": 0.00020837357715208782,
      "clip_ratio/region_mean": 0.003051635176234413,
      "epoch": 0.1404663155008779,
      "grad_norm": 0.18996372818946838,
      "learning_rate": 1e-06,
      "loss": 0.033,
      "step": 1505
    },
    {
      "clip_ratio/high_max": 0.002911505704105366,
      "clip_ratio/high_mean": 0.0011872584436787292,
      "clip_ratio/low_mean": 0.0018686972071009222,
      "clip_ratio/low_min": 8.32857949717436e-05,
      "clip_ratio/region_mean": 0.003055955676245503,
      "epoch": 0.1405596486008785,
      "grad_norm": 0.2725635766983032,
      "learning_rate": 1e-06,
      "loss": 0.0157,
      "step": 1506
    },
    {
      "clip_ratio/high_max": 0.002351409784751013,
      "clip_ratio/high_mean": 0.0009633962326915935,
      "clip_ratio/low_mean": 0.0015226272043946665,
      "clip_ratio/low_min": 0.0001658974142628722,
      "clip_ratio/region_mean": 0.002486023433448281,
      "epoch": 0.1406529817008791,
      "grad_norm": 385662.90625,
      "learning_rate": 1e-06,
      "loss": 16.4364,
      "step": 1507
    },
    {
      "clip_ratio/high_max": 0.0024626222366350703,
      "clip_ratio/high_mean": 0.0009602317968528951,
      "clip_ratio/low_mean": 0.002021338754275348,
      "clip_ratio/low_min": 0.00019941251503041713,
      "clip_ratio/region_mean": 0.002981570578413084,
      "epoch": 0.14074631480087965,
      "grad_norm": 127.84528350830078,
      "learning_rate": 1e-06,
      "loss": 1.1158,
      "step": 1508
    },
    {
      "clip_ratio/high_max": 0.0022737359977327287,
      "clip_ratio/high_mean": 0.0009457884279981954,
      "clip_ratio/low_mean": 0.0019727403596334625,
      "clip_ratio/low_min": 0.00023420342313329456,
      "clip_ratio/region_mean": 0.0029185287639847957,
      "epoch": 0.14083964790088024,
      "grad_norm": 190.7408905029297,
      "learning_rate": 1e-06,
      "loss": 0.1127,
      "step": 1509
    },
    {
      "clip_ratio/high_max": 0.00239675917691784,
      "clip_ratio/high_mean": 0.0010256225468765479,
      "clip_ratio/low_mean": 0.001787137702194741,
      "clip_ratio/low_min": 0.00027842019881063607,
      "clip_ratio/region_mean": 0.002812760285451077,
      "epoch": 0.14093298100088084,
      "grad_norm": 60.61906051635742,
      "learning_rate": 1e-06,
      "loss": 0.098,
      "step": 1510
    },
    {
      "clip_ratio/high_max": 0.0025427394939470105,
      "clip_ratio/high_mean": 0.001114632726967102,
      "clip_ratio/low_mean": 0.0020051450774190016,
      "clip_ratio/low_min": 0.00018451150208420586,
      "clip_ratio/region_mean": 0.003119777829851955,
      "epoch": 0.14102631410088143,
      "grad_norm": 3.8603458404541016,
      "learning_rate": 1e-06,
      "loss": 0.0114,
      "step": 1511
    },
    {
      "clip_ratio/high_max": 0.0025595306578907184,
      "clip_ratio/high_mean": 0.0011419912334531546,
      "clip_ratio/low_mean": 0.0016593784603173845,
      "clip_ratio/low_min": 6.422706610464957e-05,
      "clip_ratio/region_mean": 0.0028013697592541575,
      "epoch": 0.141119647200882,
      "grad_norm": 15.372194290161133,
      "learning_rate": 1e-06,
      "loss": 0.011,
      "step": 1512
    },
    {
      "clip_ratio/high_max": 0.0028597326490853447,
      "clip_ratio/high_mean": 0.0010098287148139207,
      "clip_ratio/low_mean": 0.0016525302489753813,
      "clip_ratio/low_min": 0.00010009286415879615,
      "clip_ratio/region_mean": 0.0026623589801602066,
      "epoch": 0.14121298030088258,
      "grad_norm": 0.18187662959098816,
      "learning_rate": 1e-06,
      "loss": 0.034,
      "step": 1513
    },
    {
      "clip_ratio/high_max": 0.002360991478781216,
      "clip_ratio/high_mean": 0.0009326376821263693,
      "clip_ratio/low_mean": 0.0017642461025388911,
      "clip_ratio/low_min": 0.00016139954641403165,
      "clip_ratio/region_mean": 0.00269688375556143,
      "epoch": 0.14130631340088318,
      "grad_norm": 5957963.0,
      "learning_rate": 1e-06,
      "loss": 6755.7212,
      "step": 1514
    },
    {
      "clip_ratio/high_max": 0.002386312113230815,
      "clip_ratio/high_mean": 0.0010744222236098722,
      "clip_ratio/low_mean": 0.001646172608161578,
      "clip_ratio/low_min": 0.00011660064774332568,
      "clip_ratio/region_mean": 0.002720594875427196,
      "epoch": 0.14139964650088374,
      "grad_norm": 22499.126953125,
      "learning_rate": 1e-06,
      "loss": 5727.5049,
      "step": 1515
    },
    {
      "clip_ratio/high_max": 0.002802005074045155,
      "clip_ratio/high_mean": 0.001139350097218994,
      "clip_ratio/low_mean": 0.0015593713969792589,
      "clip_ratio/low_min": 5.4314161388901994e-05,
      "clip_ratio/region_mean": 0.002698721524211578,
      "epoch": 0.14149297960088433,
      "grad_norm": 0.6947351098060608,
      "learning_rate": 1e-06,
      "loss": -0.0062,
      "step": 1516
    },
    {
      "clip_ratio/high_max": 0.0026291890317224897,
      "clip_ratio/high_mean": 0.0010123235115315765,
      "clip_ratio/low_mean": 0.00137959133280674,
      "clip_ratio/low_min": 6.238477726583369e-05,
      "clip_ratio/region_mean": 0.002391914909821935,
      "epoch": 0.14158631270088493,
      "grad_norm": 0.360291987657547,
      "learning_rate": 1e-06,
      "loss": 0.0027,
      "step": 1517
    },
    {
      "clip_ratio/high_max": 0.003240668673242908,
      "clip_ratio/high_mean": 0.001235901945619844,
      "clip_ratio/low_mean": 0.001896585825306829,
      "clip_ratio/low_min": 0.0001170319264929276,
      "clip_ratio/region_mean": 0.0031324878218583763,
      "epoch": 0.1416796458008855,
      "grad_norm": 0.44307708740234375,
      "learning_rate": 1e-06,
      "loss": 0.0287,
      "step": 1518
    },
    {
      "clip_ratio/high_max": 0.002857858209608821,
      "clip_ratio/high_mean": 0.0011926780844078166,
      "clip_ratio/low_mean": 0.0016738115955376998,
      "clip_ratio/low_min": 0.00017300990748481127,
      "clip_ratio/region_mean": 0.002866489565349184,
      "epoch": 0.14177297890088608,
      "grad_norm": 2.150840997695923,
      "learning_rate": 1e-06,
      "loss": -0.0212,
      "step": 1519
    },
    {
      "clip_ratio/high_max": 0.0025947736285161227,
      "clip_ratio/high_mean": 0.0009376536290801596,
      "clip_ratio/low_mean": 0.001650780024647247,
      "clip_ratio/low_min": 0.00016852348380780313,
      "clip_ratio/region_mean": 0.0025884337082970887,
      "epoch": 0.14186631200088667,
      "grad_norm": 0.7292062640190125,
      "learning_rate": 1e-06,
      "loss": 0.0414,
      "step": 1520
    },
    {
      "clip_ratio/high_max": 0.003037308946659323,
      "clip_ratio/high_mean": 0.0012134050302847754,
      "clip_ratio/low_mean": 0.0016742802454245975,
      "clip_ratio/low_min": 6.721875979565084e-05,
      "clip_ratio/region_mean": 0.0028876853175461292,
      "epoch": 0.14195964510088724,
      "grad_norm": 35.17675018310547,
      "learning_rate": 1e-06,
      "loss": -0.0114,
      "step": 1521
    },
    {
      "clip_ratio/high_max": 0.0026719561356003396,
      "clip_ratio/high_mean": 0.00107242417652742,
      "clip_ratio/low_mean": 0.0015977268740243744,
      "clip_ratio/low_min": 5.0152462790720165e-05,
      "clip_ratio/region_mean": 0.002670151057827752,
      "epoch": 0.14205297820088783,
      "grad_norm": 202.90602111816406,
      "learning_rate": 1e-06,
      "loss": 1689.6633,
      "step": 1522
    },
    {
      "clip_ratio/high_max": 0.0027935032994719222,
      "clip_ratio/high_mean": 0.0012418804108165205,
      "clip_ratio/low_mean": 0.0015954648952174466,
      "clip_ratio/low_min": 0.00016618280642433092,
      "clip_ratio/region_mean": 0.002837345273292158,
      "epoch": 0.14214631130088842,
      "grad_norm": 0.17362655699253082,
      "learning_rate": 1e-06,
      "loss": -0.007,
      "step": 1523
    },
    {
      "clip_ratio/high_max": 0.002675141477084253,
      "clip_ratio/high_mean": 0.0011253019565629074,
      "clip_ratio/low_mean": 0.0018174434335378464,
      "clip_ratio/low_min": 0.00012321599206188694,
      "clip_ratio/region_mean": 0.0029427453846437857,
      "epoch": 0.142239644400889,
      "grad_norm": 1808.189208984375,
      "learning_rate": 1e-06,
      "loss": 0.1595,
      "step": 1524
    },
    {
      "clip_ratio/high_max": 0.002512169914552942,
      "clip_ratio/high_mean": 0.001044392971380148,
      "clip_ratio/low_mean": 0.0019251096091466025,
      "clip_ratio/low_min": 0.00017428356295567937,
      "clip_ratio/region_mean": 0.0029695025586988777,
      "epoch": 0.14233297750088958,
      "grad_norm": 10983.962890625,
      "learning_rate": 1e-06,
      "loss": 17.4482,
      "step": 1525
    },
    {
      "clip_ratio/high_max": 0.0029271678649820387,
      "clip_ratio/high_mean": 0.0011840961597044952,
      "clip_ratio/low_mean": 0.0016681844608683605,
      "clip_ratio/low_min": 8.891924426279729e-05,
      "clip_ratio/region_mean": 0.00285228066786658,
      "epoch": 0.14242631060089017,
      "grad_norm": 0.16691197454929352,
      "learning_rate": 1e-06,
      "loss": 0.1573,
      "step": 1526
    },
    {
      "clip_ratio/high_max": 0.002384984720265493,
      "clip_ratio/high_mean": 0.0010091786716657225,
      "clip_ratio/low_mean": 0.00175820903677959,
      "clip_ratio/low_min": 0.00011475205610622652,
      "clip_ratio/region_mean": 0.002767387675703503,
      "epoch": 0.14251964370089074,
      "grad_norm": 0.3756590187549591,
      "learning_rate": 1e-06,
      "loss": 0.0163,
      "step": 1527
    },
    {
      "clip_ratio/high_max": 0.002629722010169644,
      "clip_ratio/high_mean": 0.00115497025399236,
      "clip_ratio/low_mean": 0.001925291548104724,
      "clip_ratio/low_min": 0.00017708532504912,
      "clip_ratio/region_mean": 0.0030802617911831476,
      "epoch": 0.14261297680089133,
      "grad_norm": 20940692.0,
      "learning_rate": 1e-06,
      "loss": 3077.0569,
      "step": 1528
    },
    {
      "clip_ratio/high_max": 0.002441800148517359,
      "clip_ratio/high_mean": 0.0010241254713037051,
      "clip_ratio/low_mean": 0.002081389229715569,
      "clip_ratio/low_min": 8.49371608637739e-05,
      "clip_ratio/region_mean": 0.0031055146901053376,
      "epoch": 0.14270630990089192,
      "grad_norm": 1656.2562255859375,
      "learning_rate": 1e-06,
      "loss": 0.2107,
      "step": 1529
    },
    {
      "clip_ratio/high_max": 0.002847775351256132,
      "clip_ratio/high_mean": 0.0011108239523309749,
      "clip_ratio/low_mean": 0.0019398850126890466,
      "clip_ratio/low_min": 0.00010571417442406528,
      "clip_ratio/region_mean": 0.0030507089395541698,
      "epoch": 0.14279964300089248,
      "grad_norm": 0.16886836290359497,
      "learning_rate": 1e-06,
      "loss": 0.013,
      "step": 1530
    },
    {
      "clip_ratio/high_max": 0.0023026893504720647,
      "clip_ratio/high_mean": 0.0009090209950954886,
      "clip_ratio/low_mean": 0.002193897104007192,
      "clip_ratio/low_min": 0.00018469767746864818,
      "clip_ratio/region_mean": 0.0031029181118356064,
      "epoch": 0.14289297610089308,
      "grad_norm": 3523.4658203125,
      "learning_rate": 1e-06,
      "loss": 3.8969,
      "step": 1531
    },
    {
      "clip_ratio/high_max": 0.002778836900688475,
      "clip_ratio/high_mean": 0.0011307587246847106,
      "clip_ratio/low_mean": 0.0020236671189195476,
      "clip_ratio/low_min": 0.00013172544458939228,
      "clip_ratio/region_mean": 0.0031544257581117563,
      "epoch": 0.14298630920089367,
      "grad_norm": 1.3277515172958374,
      "learning_rate": 1e-06,
      "loss": 0.0124,
      "step": 1532
    },
    {
      "clip_ratio/high_max": 0.002336524943530094,
      "clip_ratio/high_mean": 0.0009155230145552196,
      "clip_ratio/low_mean": 0.0018058124478557147,
      "clip_ratio/low_min": 0.00012848975165979937,
      "clip_ratio/region_mean": 0.002721335527894553,
      "epoch": 0.14307964230089426,
      "grad_norm": 9.080251693725586,
      "learning_rate": 1e-06,
      "loss": 0.0334,
      "step": 1533
    },
    {
      "clip_ratio/high_max": 0.0027948216084041633,
      "clip_ratio/high_mean": 0.001224981027917238,
      "clip_ratio/low_mean": 0.001545853381685447,
      "clip_ratio/low_min": 0.00011692508815031033,
      "clip_ratio/region_mean": 0.0027708344205166213,
      "epoch": 0.14317297540089483,
      "grad_norm": 95.20043182373047,
      "learning_rate": 1e-06,
      "loss": 0.016,
      "step": 1534
    },
    {
      "clip_ratio/high_max": 0.0028045622020727023,
      "clip_ratio/high_mean": 0.0011645861159195192,
      "clip_ratio/low_mean": 0.0016224990540649742,
      "clip_ratio/low_min": 3.11798467009794e-05,
      "clip_ratio/region_mean": 0.0027870852063642815,
      "epoch": 0.14326630850089542,
      "grad_norm": 4437693.5,
      "learning_rate": 1e-06,
      "loss": 1205.972,
      "step": 1535
    },
    {
      "clip_ratio/high_max": 0.0028038497621309943,
      "clip_ratio/high_mean": 0.001094444582122378,
      "clip_ratio/low_mean": 0.00190238327922998,
      "clip_ratio/low_min": 0.00015456132859981153,
      "clip_ratio/region_mean": 0.002996827766764909,
      "epoch": 0.143359641600896,
      "grad_norm": 1.7393862009048462,
      "learning_rate": 1e-06,
      "loss": 0.027,
      "step": 1536
    },
    {
      "clip_ratio/high_max": 0.0029447367196553387,
      "clip_ratio/high_mean": 0.001133869565819623,
      "clip_ratio/low_mean": 0.0019141227639920544,
      "clip_ratio/low_min": 0.00013457245950121433,
      "clip_ratio/region_mean": 0.003047992278879974,
      "epoch": 0.14345297470089657,
      "grad_norm": 0.1973133385181427,
      "learning_rate": 1e-06,
      "loss": 0.0009,
      "step": 1537
    },
    {
      "clip_ratio/high_max": 0.0026746113144326955,
      "clip_ratio/high_mean": 0.0012373189092613757,
      "clip_ratio/low_mean": 0.0015054828218126204,
      "clip_ratio/low_min": 4.110761983611155e-05,
      "clip_ratio/region_mean": 0.0027428017565398477,
      "epoch": 0.14354630780089717,
      "grad_norm": 0.4735668897628784,
      "learning_rate": 1e-06,
      "loss": -0.0611,
      "step": 1538
    },
    {
      "clip_ratio/high_max": 0.0025380641891388223,
      "clip_ratio/high_mean": 0.0009869569439615589,
      "clip_ratio/low_mean": 0.002009772309975233,
      "clip_ratio/low_min": 0.00041927020265575266,
      "clip_ratio/region_mean": 0.0029967292939545587,
      "epoch": 0.14363964090089776,
      "grad_norm": 562.114501953125,
      "learning_rate": 1e-06,
      "loss": 0.2454,
      "step": 1539
    },
    {
      "clip_ratio/high_max": 0.002552912905230187,
      "clip_ratio/high_mean": 0.0009877963966573589,
      "clip_ratio/low_mean": 0.0017049977977876551,
      "clip_ratio/low_min": 0.00011808660019596573,
      "clip_ratio/region_mean": 0.0026927941435133107,
      "epoch": 0.14373297400089832,
      "grad_norm": 0.10326199233531952,
      "learning_rate": 1e-06,
      "loss": 0.0194,
      "step": 1540
    },
    {
      "clip_ratio/high_max": 0.0024103790856315754,
      "clip_ratio/high_mean": 0.0009840424736466957,
      "clip_ratio/low_mean": 0.0019094600938842632,
      "clip_ratio/low_min": 0.00011936086229979992,
      "clip_ratio/region_mean": 0.0028935025620739907,
      "epoch": 0.14382630710089891,
      "grad_norm": 6.811111927032471,
      "learning_rate": 1e-06,
      "loss": 0.0263,
      "step": 1541
    },
    {
      "clip_ratio/high_max": 0.0026147133539780043,
      "clip_ratio/high_mean": 0.0011004669686371926,
      "clip_ratio/low_mean": 0.0017559021871420555,
      "clip_ratio/low_min": 9.48631604842376e-05,
      "clip_ratio/region_mean": 0.0028563691157614812,
      "epoch": 0.1439196402008995,
      "grad_norm": 0.1275119185447693,
      "learning_rate": 1e-06,
      "loss": 0.0121,
      "step": 1542
    },
    {
      "clip_ratio/high_max": 0.00252138889482012,
      "clip_ratio/high_mean": 0.001115317621952272,
      "clip_ratio/low_mean": 0.001678161552263191,
      "clip_ratio/low_min": 0.00012585634158313042,
      "clip_ratio/region_mean": 0.002793479179672431,
      "epoch": 0.14401297330090007,
      "grad_norm": 0.13024497032165527,
      "learning_rate": 1e-06,
      "loss": 0.0143,
      "step": 1543
    },
    {
      "clip_ratio/high_max": 0.0024465847964165732,
      "clip_ratio/high_mean": 0.0011198112115380354,
      "clip_ratio/low_mean": 0.001520789510323084,
      "clip_ratio/low_min": 9.366517133457819e-05,
      "clip_ratio/region_mean": 0.0026406007673358545,
      "epoch": 0.14410630640090066,
      "grad_norm": 0.19698739051818848,
      "learning_rate": 1e-06,
      "loss": 0.0314,
      "step": 1544
    },
    {
      "clip_ratio/high_max": 0.0023658588906982914,
      "clip_ratio/high_mean": 0.00094227220324683,
      "clip_ratio/low_mean": 0.001641942286369158,
      "clip_ratio/low_min": 1.524762137705693e-05,
      "clip_ratio/region_mean": 0.0025842145332717337,
      "epoch": 0.14419963950090126,
      "grad_norm": 16.53726577758789,
      "learning_rate": 1e-06,
      "loss": 0.0208,
      "step": 1545
    },
    {
      "clip_ratio/high_max": 0.0026494650592212565,
      "clip_ratio/high_mean": 0.0009865426800388377,
      "clip_ratio/low_mean": 0.001996525468712207,
      "clip_ratio/low_min": 0.00016797171701909974,
      "clip_ratio/region_mean": 0.00298306810145732,
      "epoch": 0.14429297260090182,
      "grad_norm": 14.814027786254883,
      "learning_rate": 1e-06,
      "loss": 0.3019,
      "step": 1546
    },
    {
      "clip_ratio/high_max": 0.002630096932989545,
      "clip_ratio/high_mean": 0.0010100509134645108,
      "clip_ratio/low_mean": 0.001864409859990701,
      "clip_ratio/low_min": 0.00015251380318659358,
      "clip_ratio/region_mean": 0.0028744607770931907,
      "epoch": 0.1443863057009024,
      "grad_norm": 0.19725888967514038,
      "learning_rate": 1e-06,
      "loss": 0.0513,
      "step": 1547
    },
    {
      "clip_ratio/high_max": 0.0026789793046191335,
      "clip_ratio/high_mean": 0.001211010410770541,
      "clip_ratio/low_mean": 0.001779705849912716,
      "clip_ratio/low_min": 9.62578806138481e-05,
      "clip_ratio/region_mean": 0.002990716340718791,
      "epoch": 0.144479638800903,
      "grad_norm": 665696.0,
      "learning_rate": 1e-06,
      "loss": 102.9458,
      "step": 1548
    },
    {
      "clip_ratio/high_max": 0.002337312005693093,
      "clip_ratio/high_mean": 0.0010466457315487787,
      "clip_ratio/low_mean": 0.0017432257009204477,
      "clip_ratio/low_min": 0.0001165657713499968,
      "clip_ratio/region_mean": 0.002789871381537523,
      "epoch": 0.14457297190090357,
      "grad_norm": 727194.5625,
      "learning_rate": 1e-06,
      "loss": 162.4721,
      "step": 1549
    },
    {
      "clip_ratio/high_max": 0.0026424499665154144,
      "clip_ratio/high_mean": 0.0011280195467406884,
      "clip_ratio/low_mean": 0.002104257651808439,
      "clip_ratio/low_min": 0.00015156389599724207,
      "clip_ratio/region_mean": 0.0032322772894985974,
      "epoch": 0.14466630500090416,
      "grad_norm": 8.772529602050781,
      "learning_rate": 1e-06,
      "loss": 0.0055,
      "step": 1550
    },
    {
      "clip_ratio/high_max": 0.002590702279121615,
      "clip_ratio/high_mean": 0.00112200504008797,
      "clip_ratio/low_mean": 0.0020673071921919473,
      "clip_ratio/low_min": 9.938728908309713e-05,
      "clip_ratio/region_mean": 0.0031893123232293874,
      "epoch": 0.14475963810090475,
      "grad_norm": 8387987.5,
      "learning_rate": 1e-06,
      "loss": 3175947.25,
      "step": 1551
    },
    {
      "clip_ratio/high_max": 0.002854348967957776,
      "clip_ratio/high_mean": 0.001110080807848135,
      "clip_ratio/low_mean": 0.001879286934126867,
      "clip_ratio/low_min": 0.00013872201361664338,
      "clip_ratio/region_mean": 0.002989367741975002,
      "epoch": 0.14485297120090532,
      "grad_norm": 55558.0703125,
      "learning_rate": 1e-06,
      "loss": 1.366,
      "step": 1552
    },
    {
      "clip_ratio/high_max": 0.0023278400549315847,
      "clip_ratio/high_mean": 0.0009991454462578986,
      "clip_ratio/low_mean": 0.00191927971172845,
      "clip_ratio/low_min": 0.00010911193930951413,
      "clip_ratio/region_mean": 0.0029184251834522,
      "epoch": 0.1449463043009059,
      "grad_norm": 0.3620549440383911,
      "learning_rate": 1e-06,
      "loss": 0.0417,
      "step": 1553
    },
    {
      "clip_ratio/high_max": 0.0026657240669010207,
      "clip_ratio/high_mean": 0.0010828655922523467,
      "clip_ratio/low_mean": 0.001869636766059557,
      "clip_ratio/low_min": 0.00010762582860479597,
      "clip_ratio/region_mean": 0.0029525023492169566,
      "epoch": 0.1450396374009065,
      "grad_norm": 3.3240063190460205,
      "learning_rate": 1e-06,
      "loss": 0.0444,
      "step": 1554
    },
    {
      "clip_ratio/high_max": 0.0026116896988241933,
      "clip_ratio/high_mean": 0.0010168802600674098,
      "clip_ratio/low_mean": 0.0019212280385545455,
      "clip_ratio/low_min": 0.00014460312013397925,
      "clip_ratio/region_mean": 0.00293810831499286,
      "epoch": 0.1451329705009071,
      "grad_norm": 5.375405788421631,
      "learning_rate": 1e-06,
      "loss": 677.525,
      "step": 1555
    },
    {
      "clip_ratio/high_max": 0.002663207778823562,
      "clip_ratio/high_mean": 0.0011043696831620764,
      "clip_ratio/low_mean": 0.0018181700033892412,
      "clip_ratio/low_min": 0.00010887289499805775,
      "clip_ratio/region_mean": 0.002922539701103233,
      "epoch": 0.14522630360090766,
      "grad_norm": 0.30215802788734436,
      "learning_rate": 1e-06,
      "loss": 0.0102,
      "step": 1556
    },
    {
      "clip_ratio/high_max": 0.0022382863789971452,
      "clip_ratio/high_mean": 0.0009825547003856627,
      "clip_ratio/low_mean": 0.0019114146889478434,
      "clip_ratio/low_min": 4.953003008267842e-05,
      "clip_ratio/region_mean": 0.0028939694093423896,
      "epoch": 0.14531963670090825,
      "grad_norm": 1.254478931427002,
      "learning_rate": 1e-06,
      "loss": 0.0217,
      "step": 1557
    },
    {
      "clip_ratio/high_max": 0.002280154152686009,
      "clip_ratio/high_mean": 0.0009389863353135297,
      "clip_ratio/low_mean": 0.002273672856972553,
      "clip_ratio/low_min": 0.0002548917200329015,
      "clip_ratio/region_mean": 0.00321265913953539,
      "epoch": 0.14541296980090884,
      "grad_norm": 25.644412994384766,
      "learning_rate": 1e-06,
      "loss": 13.2576,
      "step": 1558
    },
    {
      "clip_ratio/high_max": 0.002329032482521143,
      "clip_ratio/high_mean": 0.0010551533741818275,
      "clip_ratio/low_mean": 0.001995294249354629,
      "clip_ratio/low_min": 0.00010950394334940938,
      "clip_ratio/region_mean": 0.0030504476235364564,
      "epoch": 0.1455063029009094,
      "grad_norm": 0.382550448179245,
      "learning_rate": 1e-06,
      "loss": 0.0568,
      "step": 1559
    },
    {
      "clip_ratio/high_max": 0.0023041013155307155,
      "clip_ratio/high_mean": 0.0009252987283616676,
      "clip_ratio/low_mean": 0.002036337220488349,
      "clip_ratio/low_min": 0.000311169456836069,
      "clip_ratio/region_mean": 0.00296163595339749,
      "epoch": 0.14559963600091,
      "grad_norm": 0.2616417407989502,
      "learning_rate": 1e-06,
      "loss": 0.0692,
      "step": 1560
    },
    {
      "clip_ratio/high_max": 0.0027700834252755158,
      "clip_ratio/high_mean": 0.0010676859947125195,
      "clip_ratio/low_mean": 0.001991885743336752,
      "clip_ratio/low_min": 0.0001697625375527423,
      "clip_ratio/region_mean": 0.0030595717835240066,
      "epoch": 0.1456929691009106,
      "grad_norm": 1.573317050933838,
      "learning_rate": 1e-06,
      "loss": 0.0444,
      "step": 1561
    },
    {
      "clip_ratio/high_max": 0.00326845495874295,
      "clip_ratio/high_mean": 0.001287224036786938,
      "clip_ratio/low_mean": 0.0016744497552281246,
      "clip_ratio/low_min": 0.00016795816918602213,
      "clip_ratio/region_mean": 0.0029616738174809143,
      "epoch": 0.14578630220091116,
      "grad_norm": 0.9270631074905396,
      "learning_rate": 1e-06,
      "loss": -0.0215,
      "step": 1562
    },
    {
      "clip_ratio/high_max": 0.0028114469969295897,
      "clip_ratio/high_mean": 0.0011550192175491247,
      "clip_ratio/low_mean": 0.0016833135814522393,
      "clip_ratio/low_min": 4.99443103763042e-05,
      "clip_ratio/region_mean": 0.0028383327298797667,
      "epoch": 0.14587963530091175,
      "grad_norm": 0.14496400952339172,
      "learning_rate": 1e-06,
      "loss": -0.0249,
      "step": 1563
    },
    {
      "clip_ratio/high_max": 0.0029258170325192623,
      "clip_ratio/high_mean": 0.0011192556594323833,
      "clip_ratio/low_mean": 0.002335351939109387,
      "clip_ratio/low_min": 0.00013288938498590142,
      "clip_ratio/region_mean": 0.003454607620369643,
      "epoch": 0.14597296840091234,
      "grad_norm": 1450.6258544921875,
      "learning_rate": 1e-06,
      "loss": 1.2704,
      "step": 1564
    },
    {
      "clip_ratio/high_max": 0.002235146333987359,
      "clip_ratio/high_mean": 0.0009744386115926318,
      "clip_ratio/low_mean": 0.0020400446992425714,
      "clip_ratio/low_min": 0.00023177365073934197,
      "clip_ratio/region_mean": 0.003014483314473182,
      "epoch": 0.1460663015009129,
      "grad_norm": 0.13401196897029877,
      "learning_rate": 1e-06,
      "loss": 0.0257,
      "step": 1565
    },
    {
      "clip_ratio/high_max": 0.0022301519311440643,
      "clip_ratio/high_mean": 0.0009865138054010458,
      "clip_ratio/low_mean": 0.0022935192537261173,
      "clip_ratio/low_min": 0.0002055229906545719,
      "clip_ratio/region_mean": 0.0032800331246107817,
      "epoch": 0.1461596346009135,
      "grad_norm": 9797.1435546875,
      "learning_rate": 1e-06,
      "loss": 1.0058,
      "step": 1566
    },
    {
      "clip_ratio/high_max": 0.0029357981038629077,
      "clip_ratio/high_mean": 0.0011617877571552526,
      "clip_ratio/low_mean": 0.0020853328351222444,
      "clip_ratio/low_min": 0.00023827277800592128,
      "clip_ratio/region_mean": 0.0032471206941409037,
      "epoch": 0.1462529677009141,
      "grad_norm": 0.22918985784053802,
      "learning_rate": 1e-06,
      "loss": 0.0299,
      "step": 1567
    },
    {
      "clip_ratio/high_max": 0.0028895750947413035,
      "clip_ratio/high_mean": 0.001170220049971249,
      "clip_ratio/low_mean": 0.002253498139907606,
      "clip_ratio/low_min": 0.0003207621157343965,
      "clip_ratio/region_mean": 0.003423718226258643,
      "epoch": 0.14634630080091465,
      "grad_norm": 0.5339184403419495,
      "learning_rate": 1e-06,
      "loss": 0.0363,
      "step": 1568
    },
    {
      "clip_ratio/high_max": 0.0029230715590529144,
      "clip_ratio/high_mean": 0.001218335317389574,
      "clip_ratio/low_mean": 0.0010923545087280218,
      "clip_ratio/low_min": 8.421917482337449e-05,
      "clip_ratio/region_mean": 0.0023106898515834473,
      "completions/clipped_ratio": 0.012032645089285698,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4093.0,
      "completions/mean_length": 603.3818359375,
      "completions/mean_terminated_length": 560.8445434570312,
      "completions/min_length": 5.0,
      "completions/min_terminated_length": 5.0,
      "epoch": 0.14643963390091524,
      "grad_norm": 28565546.0,
      "learning_rate": 1e-06,
      "loss": 2520624.5,
      "num_tokens": 1135648982.0,
      "reward": 0.586922824382782,
      "reward_std": 0.18817292153835297,
      "rewards/simpleverify_reward/mean": 0.5869227647781372,
      "rewards/simpleverify_reward/std": 0.4923885464668274,
      "step": 1569
    },
    {
      "clip_ratio/high_max": 0.0030137619651213754,
      "clip_ratio/high_mean": 0.0012447561293811304,
      "clip_ratio/low_mean": 0.0010305654795956798,
      "clip_ratio/low_min": 6.751879845978692e-05,
      "clip_ratio/region_mean": 0.0022753216107957996,
      "epoch": 0.14653296700091584,
      "grad_norm": 21864908800.0,
      "learning_rate": 1e-06,
      "loss": 20389784.0,
      "step": 1570
    },
    {
      "clip_ratio/high_max": 0.0028389483777573332,
      "clip_ratio/high_mean": 0.0012866233519162051,
      "clip_ratio/low_mean": 0.001145498714322457,
      "clip_ratio/low_min": 0.00013981657684780657,
      "clip_ratio/region_mean": 0.002432122055324726,
      "epoch": 0.1466263001009164,
      "grad_norm": 3831295232.0,
      "learning_rate": 1e-06,
      "loss": 19580633088.0,
      "step": 1571
    },
    {
      "clip_ratio/high_max": 0.0030210322947823443,
      "clip_ratio/high_mean": 0.0012224624297232367,
      "clip_ratio/low_mean": 0.001150653581134975,
      "clip_ratio/low_min": 5.977197906759102e-05,
      "clip_ratio/region_mean": 0.0023731159963062964,
      "epoch": 0.146719633200917,
      "grad_norm": 4588065783808.0,
      "learning_rate": 1e-06,
      "loss": 374512222208.0,
      "step": 1572
    },
    {
      "clip_ratio/high_max": 0.0031125456152949482,
      "clip_ratio/high_mean": 0.0013337968448468018,
      "clip_ratio/low_mean": 0.0012805607766495086,
      "clip_ratio/low_min": 0.0001424820329702925,
      "clip_ratio/region_mean": 0.0026143576542381197,
      "epoch": 0.14681296630091759,
      "grad_norm": 416710240.0,
      "learning_rate": 1e-06,
      "loss": 2405130.5,
      "step": 1573
    },
    {
      "clip_ratio/high_max": 0.002857889332517516,
      "clip_ratio/high_mean": 0.001126748313254211,
      "clip_ratio/low_mean": 0.0012352399389783386,
      "clip_ratio/low_min": 7.148998702177778e-05,
      "clip_ratio/region_mean": 0.002361988299526274,
      "epoch": 0.14690629940091818,
      "grad_norm": 18308866048.0,
      "learning_rate": 1e-06,
      "loss": 3460791808.0,
      "step": 1574
    },
    {
      "clip_ratio/high_max": 0.003078666632063687,
      "clip_ratio/high_mean": 0.0012404187327774707,
      "clip_ratio/low_mean": 0.0011807699302153196,
      "clip_ratio/low_min": 7.42705578886671e-05,
      "clip_ratio/region_mean": 0.002421188648440875,
      "epoch": 0.14699963250091874,
      "grad_norm": 3874119.5,
      "learning_rate": 1e-06,
      "loss": 4755.4546,
      "step": 1575
    },
    {
      "clip_ratio/high_max": 0.0034402690434944816,
      "clip_ratio/high_mean": 0.0013720394690608373,
      "clip_ratio/low_mean": 0.0011528497743711341,
      "clip_ratio/low_min": 0.00010688407928682864,
      "clip_ratio/region_mean": 0.002524889183405321,
      "epoch": 0.14709296560091933,
      "grad_norm": 1089571584.0,
      "learning_rate": 1e-06,
      "loss": 330477.0625,
      "step": 1576
    },
    {
      "clip_ratio/high_max": 0.0033594313863432035,
      "clip_ratio/high_mean": 0.0014116493039182387,
      "clip_ratio/low_mean": 0.0010817144575412385,
      "clip_ratio/low_min": 8.8118315943575e-05,
      "clip_ratio/region_mean": 0.0024933637178037316,
      "epoch": 0.14718629870091993,
      "grad_norm": 1540312.25,
      "learning_rate": 1e-06,
      "loss": 1468.3246,
      "step": 1577
    },
    {
      "clip_ratio/high_max": 0.0029704681073781103,
      "clip_ratio/high_mean": 0.0011912590744032059,
      "clip_ratio/low_mean": 0.001314467936026631,
      "clip_ratio/low_min": 0.00018844029546016827,
      "clip_ratio/region_mean": 0.0025057270395336673,
      "epoch": 0.1472796318009205,
      "grad_norm": 779905.0625,
      "learning_rate": 1e-06,
      "loss": 459.175,
      "step": 1578
    },
    {
      "clip_ratio/high_max": 0.003109902267169673,
      "clip_ratio/high_mean": 0.0013284446140460204,
      "clip_ratio/low_mean": 0.001349199825199321,
      "clip_ratio/low_min": 0.00015743750918773003,
      "clip_ratio/region_mean": 0.002677644391951617,
      "epoch": 0.14737296490092108,
      "grad_norm": 9454.1728515625,
      "learning_rate": 1e-06,
      "loss": 4.7731,
      "step": 1579
    },
    {
      "clip_ratio/high_max": 0.0032486036943737417,
      "clip_ratio/high_mean": 0.0012373789340927033,
      "clip_ratio/low_mean": 0.0013306890250532888,
      "clip_ratio/low_min": 9.487463466939516e-05,
      "clip_ratio/region_mean": 0.002568067931861151,
      "epoch": 0.14746629800092168,
      "grad_norm": 7601012.0,
      "learning_rate": 1e-06,
      "loss": 16110.3232,
      "step": 1580
    },
    {
      "clip_ratio/high_max": 0.0031644735572626814,
      "clip_ratio/high_mean": 0.0013020262849749997,
      "clip_ratio/low_mean": 0.0012839754235756118,
      "clip_ratio/low_min": 9.50353714870289e-05,
      "clip_ratio/region_mean": 0.0025860017485683784,
      "epoch": 0.14755963110092224,
      "grad_norm": 3932926.0,
      "learning_rate": 1e-06,
      "loss": 5218361344.0,
      "step": 1581
    },
    {
      "clip_ratio/high_max": 0.002600990643259138,
      "clip_ratio/high_mean": 0.0011930091750400607,
      "clip_ratio/low_mean": 0.0011814659137598937,
      "clip_ratio/low_min": 3.4019445593003184e-05,
      "clip_ratio/region_mean": 0.002374475145188626,
      "epoch": 0.14765296420092283,
      "grad_norm": 34405941248.0,
      "learning_rate": 1e-06,
      "loss": 5108135.0,
      "step": 1582
    },
    {
      "clip_ratio/high_max": 0.002748634811723605,
      "clip_ratio/high_mean": 0.0011759144654206466,
      "clip_ratio/low_mean": 0.0012018321212963201,
      "clip_ratio/low_min": 8.07980986792245e-05,
      "clip_ratio/region_mean": 0.0023777466485626064,
      "epoch": 0.14774629730092342,
      "grad_norm": 300797.15625,
      "learning_rate": 1e-06,
      "loss": 88.9562,
      "step": 1583
    },
    {
      "clip_ratio/high_max": 0.0027803430348285474,
      "clip_ratio/high_mean": 0.0012593587089213543,
      "clip_ratio/low_mean": 0.001418678668414941,
      "clip_ratio/low_min": 8.06786247267155e-05,
      "clip_ratio/region_mean": 0.0026780373154906556,
      "epoch": 0.147839630400924,
      "grad_norm": 781058.125,
      "learning_rate": 1e-06,
      "loss": 150.4753,
      "step": 1584
    },
    {
      "clip_ratio/high_max": 0.0034344434170634486,
      "clip_ratio/high_mean": 0.0014339090721477987,
      "clip_ratio/low_mean": 0.001440911215468077,
      "clip_ratio/low_min": 9.853634946921375e-05,
      "clip_ratio/region_mean": 0.0028748203185386956,
      "epoch": 0.14793296350092458,
      "grad_norm": 511.2007141113281,
      "learning_rate": 1e-06,
      "loss": 22437.3926,
      "step": 1585
    },
    {
      "clip_ratio/high_max": 0.0035069282530457713,
      "clip_ratio/high_mean": 0.0013038595097896177,
      "clip_ratio/low_mean": 0.001471184914407786,
      "clip_ratio/low_min": 8.048731160670286e-05,
      "clip_ratio/region_mean": 0.0027750444060075097,
      "epoch": 0.14802629660092517,
      "grad_norm": 13778335.0,
      "learning_rate": 1e-06,
      "loss": 3458.4351,
      "step": 1586
    },
    {
      "clip_ratio/high_max": 0.002965187974041328,
      "clip_ratio/high_mean": 0.0012370891054160893,
      "clip_ratio/low_mean": 0.0016227386149694212,
      "clip_ratio/low_min": 0.00019646307919174433,
      "clip_ratio/region_mean": 0.002859827669453807,
      "epoch": 0.14811962970092574,
      "grad_norm": 202.98048400878906,
      "learning_rate": 1e-06,
      "loss": 0.1618,
      "step": 1587
    },
    {
      "clip_ratio/high_max": 0.0033403335692128167,
      "clip_ratio/high_mean": 0.0014088917996559758,
      "clip_ratio/low_mean": 0.00150203059456544,
      "clip_ratio/low_min": 0.00012860166680184193,
      "clip_ratio/region_mean": 0.0029109224342391826,
      "epoch": 0.14821296280092633,
      "grad_norm": 19.36944007873535,
      "learning_rate": 1e-06,
      "loss": 0.0067,
      "step": 1588
    },
    {
      "clip_ratio/high_max": 0.003234310250263661,
      "clip_ratio/high_mean": 0.0013366493585635908,
      "clip_ratio/low_mean": 0.0015972804740158608,
      "clip_ratio/low_min": 5.11289053974906e-05,
      "clip_ratio/region_mean": 0.0029339298271224834,
      "epoch": 0.14830629590092692,
      "grad_norm": 1305844096.0,
      "learning_rate": 1e-06,
      "loss": 269629.9062,
      "step": 1589
    },
    {
      "clip_ratio/high_max": 0.003312863947940059,
      "clip_ratio/high_mean": 0.001299374347581761,
      "clip_ratio/low_mean": 0.00151879384793574,
      "clip_ratio/low_min": 0.00012856240073233494,
      "clip_ratio/region_mean": 0.002818168250087183,
      "epoch": 0.14839962900092749,
      "grad_norm": 185.1660919189453,
      "learning_rate": 1e-06,
      "loss": 7960.3071,
      "step": 1590
    },
    {
      "clip_ratio/high_max": 0.003106338561337907,
      "clip_ratio/high_mean": 0.0012937858373334166,
      "clip_ratio/low_mean": 0.0016290267922158819,
      "clip_ratio/low_min": 0.0002096015587085276,
      "clip_ratio/region_mean": 0.0029228125931695104,
      "epoch": 0.14849296210092808,
      "grad_norm": 137292.40625,
      "learning_rate": 1e-06,
      "loss": 33.3874,
      "step": 1591
    },
    {
      "clip_ratio/high_max": 0.0033875743101816624,
      "clip_ratio/high_mean": 0.0015467292578250635,
      "clip_ratio/low_mean": 0.001573028010170674,
      "clip_ratio/low_min": 6.822130490036216e-05,
      "clip_ratio/region_mean": 0.0031197572316159494,
      "epoch": 0.14858629520092867,
      "grad_norm": 5721.7216796875,
      "learning_rate": 1e-06,
      "loss": 1.5251,
      "step": 1592
    },
    {
      "clip_ratio/high_max": 0.0026431048318045214,
      "clip_ratio/high_mean": 0.0011660960626613814,
      "clip_ratio/low_mean": 0.001824152310291538,
      "clip_ratio/low_min": 0.00036151911535853287,
      "clip_ratio/region_mean": 0.0029902483511250466,
      "epoch": 0.14867962830092923,
      "grad_norm": 988.8856201171875,
      "learning_rate": 1e-06,
      "loss": 0.2976,
      "step": 1593
    },
    {
      "clip_ratio/high_max": 0.0030779329972574487,
      "clip_ratio/high_mean": 0.0012305582458793651,
      "clip_ratio/low_mean": 0.0016532464760530274,
      "clip_ratio/low_min": 0.0001464408769606962,
      "clip_ratio/region_mean": 0.0028838047437602654,
      "epoch": 0.14877296140092983,
      "grad_norm": 2.7741458415985107,
      "learning_rate": 1e-06,
      "loss": 0.0345,
      "step": 1594
    },
    {
      "clip_ratio/high_max": 0.0035970796379842795,
      "clip_ratio/high_mean": 0.001583169479999924,
      "clip_ratio/low_mean": 0.0017590854586160276,
      "clip_ratio/low_min": 9.158254943031352e-05,
      "clip_ratio/region_mean": 0.0033422549022361636,
      "epoch": 0.14886629450093042,
      "grad_norm": 1480150.5,
      "learning_rate": 1e-06,
      "loss": 18602.1855,
      "step": 1595
    },
    {
      "clip_ratio/high_max": 0.0035218798657297157,
      "clip_ratio/high_mean": 0.0014541324380843434,
      "clip_ratio/low_mean": 0.0017742020700097783,
      "clip_ratio/low_min": 0.00017495865540695377,
      "clip_ratio/region_mean": 0.0032283345353789628,
      "epoch": 0.148959627600931,
      "grad_norm": 13392.486328125,
      "learning_rate": 1e-06,
      "loss": 16875.0391,
      "step": 1596
    },
    {
      "clip_ratio/high_max": 0.003159449937811587,
      "clip_ratio/high_mean": 0.0013697167596546933,
      "clip_ratio/low_mean": 0.0019263198628323153,
      "clip_ratio/low_min": 5.722316200262867e-05,
      "clip_ratio/region_mean": 0.0032960366588667966,
      "epoch": 0.14905296070093157,
      "grad_norm": 40718.03515625,
      "learning_rate": 1e-06,
      "loss": 4.4022,
      "step": 1597
    },
    {
      "clip_ratio/high_max": 0.003392810744117014,
      "clip_ratio/high_mean": 0.0014693576777062844,
      "clip_ratio/low_mean": 0.0017080184916267172,
      "clip_ratio/low_min": 0.00012124370186938904,
      "clip_ratio/region_mean": 0.0031773761875228956,
      "epoch": 0.14914629380093217,
      "grad_norm": 62737612.0,
      "learning_rate": 1e-06,
      "loss": 10002.1816,
      "step": 1598
    },
    {
      "clip_ratio/high_max": 0.003099215573456604,
      "clip_ratio/high_mean": 0.0014748414287168998,
      "clip_ratio/low_mean": 0.0016316440851369407,
      "clip_ratio/low_min": 0.00010184631355514284,
      "clip_ratio/region_mean": 0.00310648548475001,
      "epoch": 0.14923962690093276,
      "grad_norm": 2324671.25,
      "learning_rate": 1e-06,
      "loss": 2327.3533,
      "step": 1599
    },
    {
      "clip_ratio/high_max": 0.0034614399846759625,
      "clip_ratio/high_mean": 0.001446096292056609,
      "clip_ratio/low_mean": 0.0017500548710813746,
      "clip_ratio/low_min": 8.624988731753547e-05,
      "clip_ratio/region_mean": 0.003196151214069687,
      "epoch": 0.14933296000093332,
      "grad_norm": 15523.39453125,
      "learning_rate": 1e-06,
      "loss": 7.2142,
      "step": 1600
    },
    {
      "epoch": 0.14933296000093332,
      "step": 1600,
      "total_flos": 0.0,
      "train_loss": 1264545902427.3843,
      "train_runtime": 60559.9674,
      "train_samples_per_second": 23.672,
      "train_steps_per_second": 0.026
    }
  ],
  "logging_steps": 1,
  "max_steps": 1600,
  "num_input_tokens_seen": 1135648982,
  "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
}