{
  "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": 0.013724190848214302,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4087.0,
      "completions/mean_length": 599.6725463867188,
      "completions/mean_terminated_length": 551.0205078125,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 9.333310000058333e-05,
      "grad_norm": 0.1351688802242279,
      "learning_rate": 1e-06,
      "loss": 0.0478,
      "num_tokens": 80197318.0,
      "reward": 0.4954223930835724,
      "reward_std": 0.26438432931900024,
      "rewards/simpleverify_reward/mean": 0.49542236328125,
      "rewards/simpleverify_reward/std": 0.49998122453689575,
      "step": 1
    },
    {
      "clip_ratio/high_max": 0.0023478127041016705,
      "clip_ratio/high_mean": 0.0011073373243561946,
      "clip_ratio/low_mean": 0.000518497255143302,
      "clip_ratio/low_min": 3.340999137435574e-05,
      "clip_ratio/region_mean": 0.0016258345349342562,
      "epoch": 0.00018666620000116666,
      "grad_norm": 0.12884752452373505,
      "learning_rate": 1e-06,
      "loss": -0.0299,
      "step": 2
    },
    {
      "clip_ratio/high_max": 0.0019141813027090393,
      "clip_ratio/high_mean": 0.0008050140222621849,
      "clip_ratio/low_mean": 0.0007772632998239715,
      "clip_ratio/low_min": 0.00011569632079044823,
      "clip_ratio/region_mean": 0.0015822773493709974,
      "epoch": 0.00027999930000175,
      "grad_norm": 0.10905759036540985,
      "learning_rate": 1e-06,
      "loss": 0.0585,
      "step": 3
    },
    {
      "clip_ratio/high_max": 0.0022400690213544294,
      "clip_ratio/high_mean": 0.0009223831257259008,
      "clip_ratio/low_mean": 0.0009029188040585723,
      "clip_ratio/low_min": 0.00013121906431479147,
      "clip_ratio/region_mean": 0.0018253018861287273,
      "epoch": 0.0003733324000023333,
      "grad_norm": 0.13122092187404633,
      "learning_rate": 1e-06,
      "loss": 0.0623,
      "step": 4
    },
    {
      "clip_ratio/high_max": 0.002449180894473102,
      "clip_ratio/high_mean": 0.0011378790113667492,
      "clip_ratio/low_mean": 0.0008680689552420517,
      "clip_ratio/low_min": 0.00010780939919641241,
      "clip_ratio/region_mean": 0.0020059479647898115,
      "epoch": 0.0004666655000029167,
      "grad_norm": 0.1299799531698227,
      "learning_rate": 1e-06,
      "loss": -0.0001,
      "step": 5
    },
    {
      "clip_ratio/high_max": 0.0027988183064735495,
      "clip_ratio/high_mean": 0.0012843796102970373,
      "clip_ratio/low_mean": 0.0013021820304857101,
      "clip_ratio/low_min": 0.00023420465731760487,
      "clip_ratio/region_mean": 0.002586561626230832,
      "epoch": 0.0005599986000035,
      "grad_norm": 0.13312117755413055,
      "learning_rate": 1e-06,
      "loss": -0.0133,
      "step": 6
    },
    {
      "clip_ratio/high_max": 0.002765578028629534,
      "clip_ratio/high_mean": 0.0011841880659630988,
      "clip_ratio/low_mean": 0.0013377274335653055,
      "clip_ratio/low_min": 0.0002463115406499128,
      "clip_ratio/region_mean": 0.002521915434044786,
      "epoch": 0.0006533317000040833,
      "grad_norm": 0.13714255392551422,
      "learning_rate": 1e-06,
      "loss": 0.038,
      "step": 7
    },
    {
      "clip_ratio/high_max": 0.00270877756702248,
      "clip_ratio/high_mean": 0.0012838548318541143,
      "clip_ratio/low_mean": 0.0012081002714694478,
      "clip_ratio/low_min": 0.00016637541557429358,
      "clip_ratio/region_mean": 0.002491955085133668,
      "epoch": 0.0007466648000046666,
      "grad_norm": 0.13007622957229614,
      "learning_rate": 1e-06,
      "loss": -0.0221,
      "step": 8
    },
    {
      "clip_ratio/high_max": 0.0024598598756711,
      "clip_ratio/high_mean": 0.001140238789957948,
      "clip_ratio/low_mean": 0.0014735562181158457,
      "clip_ratio/low_min": 8.273639014078071e-05,
      "clip_ratio/region_mean": 0.0026137950335396454,
      "epoch": 0.00083999790000525,
      "grad_norm": 0.12082390487194061,
      "learning_rate": 1e-06,
      "loss": 0.0555,
      "step": 9
    },
    {
      "clip_ratio/high_max": 0.002673635055543855,
      "clip_ratio/high_mean": 0.001122347173804883,
      "clip_ratio/low_mean": 0.0012391256059345324,
      "clip_ratio/low_min": 9.760110151546542e-05,
      "clip_ratio/region_mean": 0.0023614727542735636,
      "epoch": 0.0009333310000058334,
      "grad_norm": 0.12336327880620956,
      "learning_rate": 1e-06,
      "loss": -0.0016,
      "step": 10
    },
    {
      "clip_ratio/high_max": 0.002751210682617966,
      "clip_ratio/high_mean": 0.0011633767971943598,
      "clip_ratio/low_mean": 0.0012193960355944,
      "clip_ratio/low_min": 0.00019072842951572966,
      "clip_ratio/region_mean": 0.0023827728000469506,
      "epoch": 0.0010266641000064166,
      "grad_norm": 0.1197395846247673,
      "learning_rate": 1e-06,
      "loss": 0.0628,
      "step": 11
    },
    {
      "clip_ratio/high_max": 0.002759794377197977,
      "clip_ratio/high_mean": 0.0012307062424952164,
      "clip_ratio/low_mean": 0.001164543969935039,
      "clip_ratio/low_min": 0.00011344149243086576,
      "clip_ratio/region_mean": 0.002395250165136531,
      "epoch": 0.001119997200007,
      "grad_norm": 0.1405230462551117,
      "learning_rate": 1e-06,
      "loss": 0.0137,
      "step": 12
    },
    {
      "clip_ratio/high_max": 0.0023893758188933134,
      "clip_ratio/high_mean": 0.0011513511381053831,
      "clip_ratio/low_mean": 0.0011078872103098547,
      "clip_ratio/low_min": 0.00021513757565116975,
      "clip_ratio/region_mean": 0.002259238339320291,
      "epoch": 0.0012133303000075833,
      "grad_norm": 0.11387713998556137,
      "learning_rate": 1e-06,
      "loss": -0.0032,
      "step": 13
    },
    {
      "clip_ratio/high_max": 0.0024001618730835617,
      "clip_ratio/high_mean": 0.0010402810585219413,
      "clip_ratio/low_mean": 0.0011266607652942184,
      "clip_ratio/low_min": 0.00023190594765765127,
      "clip_ratio/region_mean": 0.0021669417328666896,
      "epoch": 0.0013066634000081666,
      "grad_norm": 0.11974268406629562,
      "learning_rate": 1e-06,
      "loss": 0.037,
      "step": 14
    },
    {
      "clip_ratio/high_max": 0.0024508071510354057,
      "clip_ratio/high_mean": 0.001112225349061191,
      "clip_ratio/low_mean": 0.0011875995078298729,
      "clip_ratio/low_min": 0.00025513387208775384,
      "clip_ratio/region_mean": 0.0022998248678050004,
      "epoch": 0.00139999650000875,
      "grad_norm": 0.12656979262828827,
      "learning_rate": 1e-06,
      "loss": 0.0348,
      "step": 15
    },
    {
      "clip_ratio/high_max": 0.002322030508366879,
      "clip_ratio/high_mean": 0.0010483957048563752,
      "clip_ratio/low_mean": 0.000957322492467938,
      "clip_ratio/low_min": 0.00015151336992857978,
      "clip_ratio/region_mean": 0.0020057182118762285,
      "epoch": 0.0014933296000093333,
      "grad_norm": 0.11600138247013092,
      "learning_rate": 1e-06,
      "loss": 0.0158,
      "step": 16
    },
    {
      "clip_ratio/high_max": 0.0026436500920681283,
      "clip_ratio/high_mean": 0.001141931970778387,
      "clip_ratio/low_mean": 0.0010170992245548405,
      "clip_ratio/low_min": 0.00010865482090594014,
      "clip_ratio/region_mean": 0.0021590311807813123,
      "epoch": 0.0015866627000099165,
      "grad_norm": 0.1152438074350357,
      "learning_rate": 1e-06,
      "loss": 0.0108,
      "step": 17
    },
    {
      "clip_ratio/high_max": 0.002515043524908833,
      "clip_ratio/high_mean": 0.0011454090708866715,
      "clip_ratio/low_mean": 0.0010353123507229611,
      "clip_ratio/low_min": 0.0001434843188690138,
      "clip_ratio/region_mean": 0.0021807214216096327,
      "epoch": 0.0016799958000105,
      "grad_norm": 0.12648127973079681,
      "learning_rate": 1e-06,
      "loss": -0.0031,
      "step": 18
    },
    {
      "clip_ratio/high_max": 0.002629626455018297,
      "clip_ratio/high_mean": 0.0010910109886026476,
      "clip_ratio/low_mean": 0.0010667181413737126,
      "clip_ratio/low_min": 0.0001797896029529511,
      "clip_ratio/region_mean": 0.0021577291627181694,
      "epoch": 0.0017733289000110833,
      "grad_norm": 0.11609940230846405,
      "learning_rate": 1e-06,
      "loss": -0.0109,
      "step": 19
    },
    {
      "clip_ratio/high_max": 0.0027949537980020978,
      "clip_ratio/high_mean": 0.0011497604682517704,
      "clip_ratio/low_mean": 0.0012121964937250596,
      "clip_ratio/low_min": 0.00023940318169479724,
      "clip_ratio/region_mean": 0.002361956925597042,
      "epoch": 0.0018666620000116667,
      "grad_norm": 0.12692219018936157,
      "learning_rate": 1e-06,
      "loss": 0.0344,
      "step": 20
    },
    {
      "clip_ratio/high_max": 0.002589399264252279,
      "clip_ratio/high_mean": 0.0011234683042857796,
      "clip_ratio/low_mean": 0.0010738386808952782,
      "clip_ratio/low_min": 0.00018489967715140665,
      "clip_ratio/region_mean": 0.002197307017922867,
      "epoch": 0.00195999510001225,
      "grad_norm": 0.13158082962036133,
      "learning_rate": 1e-06,
      "loss": 0.0449,
      "step": 21
    },
    {
      "clip_ratio/high_max": 0.0024172619087039493,
      "clip_ratio/high_mean": 0.0011121215211460367,
      "clip_ratio/low_mean": 0.0012496604249463417,
      "clip_ratio/low_min": 0.0001313423508690903,
      "clip_ratio/region_mean": 0.002361781931540463,
      "epoch": 0.002053328200012833,
      "grad_norm": 0.12087717652320862,
      "learning_rate": 1e-06,
      "loss": 0.0789,
      "step": 22
    },
    {
      "clip_ratio/high_max": 0.002466805191943422,
      "clip_ratio/high_mean": 0.0011839956532639917,
      "clip_ratio/low_mean": 0.001536189029138768,
      "clip_ratio/low_min": 0.00026916667411569506,
      "clip_ratio/region_mean": 0.0027201846896787174,
      "epoch": 0.0021466613000134167,
      "grad_norm": 0.12805938720703125,
      "learning_rate": 1e-06,
      "loss": 0.0351,
      "step": 23
    },
    {
      "clip_ratio/high_max": 0.002562341578595806,
      "clip_ratio/high_mean": 0.0011825717610918218,
      "clip_ratio/low_mean": 0.0013199982458900195,
      "clip_ratio/low_min": 0.00024161395504052052,
      "clip_ratio/region_mean": 0.002502569965145085,
      "epoch": 0.002239994400014,
      "grad_norm": 0.12345980107784271,
      "learning_rate": 1e-06,
      "loss": -0.0054,
      "step": 24
    },
    {
      "clip_ratio/high_max": 0.002660014637513086,
      "clip_ratio/high_mean": 0.001104355113056954,
      "clip_ratio/low_mean": 0.001319493276241701,
      "clip_ratio/low_min": 0.0001816941785364179,
      "clip_ratio/region_mean": 0.002423848389298655,
      "epoch": 0.002333327500014583,
      "grad_norm": 0.1219700425863266,
      "learning_rate": 1e-06,
      "loss": 0.0513,
      "step": 25
    },
    {
      "clip_ratio/high_max": 0.002305815323779825,
      "clip_ratio/high_mean": 0.00100868127810827,
      "clip_ratio/low_mean": 0.0013425168399407994,
      "clip_ratio/low_min": 0.00027819257229566574,
      "clip_ratio/region_mean": 0.002351198061660398,
      "epoch": 0.0024266606000151666,
      "grad_norm": 0.1232110783457756,
      "learning_rate": 1e-06,
      "loss": 0.0757,
      "step": 26
    },
    {
      "clip_ratio/high_max": 0.0026411455910420045,
      "clip_ratio/high_mean": 0.0010462454229127616,
      "clip_ratio/low_mean": 0.0014150662900647148,
      "clip_ratio/low_min": 0.0003456768763498985,
      "clip_ratio/region_mean": 0.0024613117275293916,
      "epoch": 0.00251999370001575,
      "grad_norm": 0.11845528334379196,
      "learning_rate": 1e-06,
      "loss": 0.0542,
      "step": 27
    },
    {
      "clip_ratio/high_max": 0.002325190529518295,
      "clip_ratio/high_mean": 0.0009594632647349499,
      "clip_ratio/low_mean": 0.0014218334035831504,
      "clip_ratio/low_min": 0.0002624542821649811,
      "clip_ratio/region_mean": 0.0023812966464902274,
      "epoch": 0.002613326800016333,
      "grad_norm": 0.11605717986822128,
      "learning_rate": 1e-06,
      "loss": 0.0625,
      "step": 28
    },
    {
      "clip_ratio/high_max": 0.0030251408825279213,
      "clip_ratio/high_mean": 0.0013527981900551822,
      "clip_ratio/low_mean": 0.001140159150963882,
      "clip_ratio/low_min": 0.00011908031501661753,
      "clip_ratio/region_mean": 0.0024929573337431066,
      "epoch": 0.0027066599000169166,
      "grad_norm": 0.12137246131896973,
      "learning_rate": 1e-06,
      "loss": -0.0538,
      "step": 29
    },
    {
      "clip_ratio/high_max": 0.0022979435307206586,
      "clip_ratio/high_mean": 0.0009442981317988597,
      "clip_ratio/low_mean": 0.0014302614436019212,
      "clip_ratio/low_min": 0.0002501899180060718,
      "clip_ratio/region_mean": 0.002374559626332484,
      "epoch": 0.0027999930000175,
      "grad_norm": 0.1159074679017067,
      "learning_rate": 1e-06,
      "loss": 0.0721,
      "step": 30
    },
    {
      "clip_ratio/high_max": 0.0025673703785287216,
      "clip_ratio/high_mean": 0.0012295757660467643,
      "clip_ratio/low_mean": 0.0013573341093433555,
      "clip_ratio/low_min": 0.00016855412104632705,
      "clip_ratio/region_mean": 0.0025869098681141622,
      "epoch": 0.002893326100018083,
      "grad_norm": 0.1223529651761055,
      "learning_rate": 1e-06,
      "loss": 0.0047,
      "step": 31
    },
    {
      "clip_ratio/high_max": 0.0025453735506744124,
      "clip_ratio/high_mean": 0.0011597320954024326,
      "clip_ratio/low_mean": 0.0013843528722645715,
      "clip_ratio/low_min": 0.00021935500444669742,
      "clip_ratio/region_mean": 0.002544085022236686,
      "epoch": 0.0029866592000186666,
      "grad_norm": 0.12275739014148712,
      "learning_rate": 1e-06,
      "loss": 0.0431,
      "step": 32
    },
    {
      "clip_ratio/high_max": 0.002729063700826373,
      "clip_ratio/high_mean": 0.0012258453971298877,
      "clip_ratio/low_mean": 0.001404339254804654,
      "clip_ratio/low_min": 0.0003080388714806759,
      "clip_ratio/region_mean": 0.0026301846155547537,
      "epoch": 0.00307999230001925,
      "grad_norm": 0.13245970010757446,
      "learning_rate": 1e-06,
      "loss": 0.0388,
      "step": 33
    },
    {
      "clip_ratio/high_max": 0.0025372079908265732,
      "clip_ratio/high_mean": 0.001119392465625424,
      "clip_ratio/low_mean": 0.0013647336709254887,
      "clip_ratio/low_min": 0.00018539652683102759,
      "clip_ratio/region_mean": 0.0024841261983965524,
      "epoch": 0.003173325400019833,
      "grad_norm": 0.18169943988323212,
      "learning_rate": 1e-06,
      "loss": 0.0276,
      "step": 34
    },
    {
      "clip_ratio/high_max": 0.002517153181543108,
      "clip_ratio/high_mean": 0.001101550049497746,
      "clip_ratio/low_mean": 0.001335564760665875,
      "clip_ratio/low_min": 0.0001049614775183727,
      "clip_ratio/region_mean": 0.002437114824715536,
      "epoch": 0.0032666585000204165,
      "grad_norm": 0.12524020671844482,
      "learning_rate": 1e-06,
      "loss": -0.0019,
      "step": 35
    },
    {
      "clip_ratio/high_max": 0.0025958751866710372,
      "clip_ratio/high_mean": 0.0011561296778381802,
      "clip_ratio/low_mean": 0.0013680337942787446,
      "clip_ratio/low_min": 0.00021737143106292933,
      "clip_ratio/region_mean": 0.0025241635012207553,
      "epoch": 0.003359991600021,
      "grad_norm": 0.12481582909822464,
      "learning_rate": 1e-06,
      "loss": 0.0143,
      "step": 36
    },
    {
      "clip_ratio/high_max": 0.0025699134785099886,
      "clip_ratio/high_mean": 0.001172711308754515,
      "clip_ratio/low_mean": 0.0012586960001499392,
      "clip_ratio/low_min": 0.0003111901296506403,
      "clip_ratio/region_mean": 0.0024314072798006237,
      "epoch": 0.0034533247000215835,
      "grad_norm": 0.12213467806577682,
      "learning_rate": 1e-06,
      "loss": 0.0051,
      "step": 37
    },
    {
      "clip_ratio/high_max": 0.0026844480526051484,
      "clip_ratio/high_mean": 0.0012004291784251109,
      "clip_ratio/low_mean": 0.0011842669009638485,
      "clip_ratio/low_min": 0.00024278982982650632,
      "clip_ratio/region_mean": 0.0023846960903028958,
      "epoch": 0.0035466578000221665,
      "grad_norm": 0.11984220147132874,
      "learning_rate": 1e-06,
      "loss": -0.0045,
      "step": 38
    },
    {
      "clip_ratio/high_max": 0.0027357147337170318,
      "clip_ratio/high_mean": 0.001222223239892628,
      "clip_ratio/low_mean": 0.0014722723135491833,
      "clip_ratio/low_min": 0.0002249274493806297,
      "clip_ratio/region_mean": 0.0026944955898215994,
      "epoch": 0.00363999090002275,
      "grad_norm": 0.1276833415031433,
      "learning_rate": 1e-06,
      "loss": 0.0606,
      "step": 39
    },
    {
      "clip_ratio/high_max": 0.0024828402092680335,
      "clip_ratio/high_mean": 0.0012137264875491383,
      "clip_ratio/low_mean": 0.001327302736171987,
      "clip_ratio/low_min": 0.000284347188880929,
      "clip_ratio/region_mean": 0.002541029251005966,
      "epoch": 0.0037333240000233334,
      "grad_norm": 0.11976026743650436,
      "learning_rate": 1e-06,
      "loss": 0.011,
      "step": 40
    },
    {
      "clip_ratio/high_max": 0.002808928315062076,
      "clip_ratio/high_mean": 0.0012745399326377083,
      "clip_ratio/low_mean": 0.001354664233076619,
      "clip_ratio/low_min": 0.00014309158814285183,
      "clip_ratio/region_mean": 0.002629204209370073,
      "epoch": 0.0038266571000239165,
      "grad_norm": 0.12221518903970718,
      "learning_rate": 1e-06,
      "loss": 0.0068,
      "step": 41
    },
    {
      "clip_ratio/high_max": 0.0030057493568165228,
      "clip_ratio/high_mean": 0.0014087753152125515,
      "clip_ratio/low_mean": 0.0011849932416225784,
      "clip_ratio/low_min": 0.0001294406010856619,
      "clip_ratio/region_mean": 0.0025937685859389603,
      "epoch": 0.0039199902000245,
      "grad_norm": 0.12715640664100647,
      "learning_rate": 1e-06,
      "loss": -0.0756,
      "step": 42
    },
    {
      "clip_ratio/high_max": 0.0026467816132935695,
      "clip_ratio/high_mean": 0.0011393803033570293,
      "clip_ratio/low_mean": 0.0012746798092848621,
      "clip_ratio/low_min": 0.0002086070753648528,
      "clip_ratio/region_mean": 0.002414060159935616,
      "epoch": 0.004013323300025083,
      "grad_norm": 0.1203455999493599,
      "learning_rate": 1e-06,
      "loss": 0.0226,
      "step": 43
    },
    {
      "clip_ratio/high_max": 0.002541160887631122,
      "clip_ratio/high_mean": 0.0012985061184735969,
      "clip_ratio/low_mean": 0.0012353502861515153,
      "clip_ratio/low_min": 0.00020070204118383117,
      "clip_ratio/region_mean": 0.0025338564228150062,
      "epoch": 0.004106656400025666,
      "grad_norm": 0.12440450489521027,
      "learning_rate": 1e-06,
      "loss": 0.0369,
      "step": 44
    },
    {
      "clip_ratio/high_max": 0.0027139170488226227,
      "clip_ratio/high_mean": 0.0011793430185207399,
      "clip_ratio/low_mean": 0.001420053582478431,
      "clip_ratio/low_min": 0.00012604999665200012,
      "clip_ratio/region_mean": 0.0025993965755333193,
      "epoch": 0.00419998950002625,
      "grad_norm": 0.1202644407749176,
      "learning_rate": 1e-06,
      "loss": 0.0656,
      "step": 45
    },
    {
      "clip_ratio/high_max": 0.002754934292170219,
      "clip_ratio/high_mean": 0.0012010007740173023,
      "clip_ratio/low_mean": 0.0014191860100254416,
      "clip_ratio/low_min": 0.0002793925368678174,
      "clip_ratio/region_mean": 0.0026201868167845532,
      "epoch": 0.004293322600026833,
      "grad_norm": 0.11849617958068848,
      "learning_rate": 1e-06,
      "loss": -0.0504,
      "step": 46
    },
    {
      "clip_ratio/high_max": 0.0024550102098146453,
      "clip_ratio/high_mean": 0.0010567437020654324,
      "clip_ratio/low_mean": 0.0014334456500364468,
      "clip_ratio/low_min": 0.00017170624414575286,
      "clip_ratio/region_mean": 0.0024901893120841123,
      "epoch": 0.004386655700027417,
      "grad_norm": 0.11086788028478622,
      "learning_rate": 1e-06,
      "loss": 0.0513,
      "step": 47
    },
    {
      "clip_ratio/high_max": 0.002958431141451001,
      "clip_ratio/high_mean": 0.0012115780664316844,
      "clip_ratio/low_mean": 0.0012065150658600032,
      "clip_ratio/low_min": 0.0001335978704446461,
      "clip_ratio/region_mean": 0.002418093128653709,
      "epoch": 0.004479988800028,
      "grad_norm": 0.1252577304840088,
      "learning_rate": 1e-06,
      "loss": 0.0062,
      "step": 48
    },
    {
      "clip_ratio/high_max": 0.0022706098461640067,
      "clip_ratio/high_mean": 0.0010665518675523344,
      "clip_ratio/low_mean": 0.0014747400309715886,
      "clip_ratio/low_min": 0.00020870684238616377,
      "clip_ratio/region_mean": 0.0025412919057998806,
      "epoch": 0.004573321900028583,
      "grad_norm": 0.10884135961532593,
      "learning_rate": 1e-06,
      "loss": 0.0236,
      "step": 49
    },
    {
      "clip_ratio/high_max": 0.002185671604820527,
      "clip_ratio/high_mean": 0.001060843529558042,
      "clip_ratio/low_mean": 0.0013342364218260627,
      "clip_ratio/low_min": 0.00022071847206461825,
      "clip_ratio/region_mean": 0.00239507996593602,
      "epoch": 0.004666655000029166,
      "grad_norm": 0.12361767143011093,
      "learning_rate": 1e-06,
      "loss": 0.0313,
      "step": 50
    },
    {
      "clip_ratio/high_max": 0.0027597283042268828,
      "clip_ratio/high_mean": 0.0011761163605115144,
      "clip_ratio/low_mean": 0.001213630408528843,
      "clip_ratio/low_min": 0.0001908261219796259,
      "clip_ratio/region_mean": 0.002389746812696103,
      "epoch": 0.00475998810002975,
      "grad_norm": 0.11355671286582947,
      "learning_rate": 1e-06,
      "loss": 0.0207,
      "step": 51
    },
    {
      "clip_ratio/high_max": 0.0024905576574383304,
      "clip_ratio/high_mean": 0.0011331064633850474,
      "clip_ratio/low_mean": 0.0013893898321839515,
      "clip_ratio/low_min": 0.0003023253630090039,
      "clip_ratio/region_mean": 0.0025224962664651684,
      "epoch": 0.004853321200030333,
      "grad_norm": 0.12120325118303299,
      "learning_rate": 1e-06,
      "loss": 0.0473,
      "step": 52
    },
    {
      "clip_ratio/high_max": 0.002222864786745049,
      "clip_ratio/high_mean": 0.0011238621809752658,
      "clip_ratio/low_mean": 0.0012951597236678936,
      "clip_ratio/low_min": 0.0002244625247840304,
      "clip_ratio/region_mean": 0.002419021948298905,
      "epoch": 0.004946654300030917,
      "grad_norm": 0.11711551249027252,
      "learning_rate": 1e-06,
      "loss": -0.004,
      "step": 53
    },
    {
      "clip_ratio/high_max": 0.002689632492547389,
      "clip_ratio/high_mean": 0.0012400245395838283,
      "clip_ratio/low_mean": 0.0014652921454398893,
      "clip_ratio/low_min": 0.00025164604903693544,
      "clip_ratio/region_mean": 0.002705316714127548,
      "epoch": 0.0050399874000315,
      "grad_norm": 0.12448856979608536,
      "learning_rate": 1e-06,
      "loss": 0.0183,
      "step": 54
    },
    {
      "clip_ratio/high_max": 0.0023022337845759466,
      "clip_ratio/high_mean": 0.0011531529162311926,
      "clip_ratio/low_mean": 0.001143354749729042,
      "clip_ratio/low_min": 0.0002030430341619649,
      "clip_ratio/region_mean": 0.0022965076423133723,
      "epoch": 0.005133320500032083,
      "grad_norm": 0.11327353119850159,
      "learning_rate": 1e-06,
      "loss": 0.0141,
      "step": 55
    },
    {
      "clip_ratio/high_max": 0.0029010622238274664,
      "clip_ratio/high_mean": 0.0012158983372501098,
      "clip_ratio/low_mean": 0.0012990137256565504,
      "clip_ratio/low_min": 0.0001827138557928265,
      "clip_ratio/region_mean": 0.002514912099286448,
      "epoch": 0.005226653600032666,
      "grad_norm": 0.13181783258914948,
      "learning_rate": 1e-06,
      "loss": 0.0205,
      "step": 56
    },
    {
      "clip_ratio/high_max": 0.0027543388096091803,
      "clip_ratio/high_mean": 0.0011148851735924836,
      "clip_ratio/low_mean": 0.0013057968244538642,
      "clip_ratio/low_min": 0.00020840396882704226,
      "clip_ratio/region_mean": 0.002420682030788157,
      "epoch": 0.00531998670003325,
      "grad_norm": 0.12502296268939972,
      "learning_rate": 1e-06,
      "loss": 0.0735,
      "step": 57
    },
    {
      "clip_ratio/high_max": 0.0027627505696727894,
      "clip_ratio/high_mean": 0.0012729899899568409,
      "clip_ratio/low_mean": 0.0013732074221479706,
      "clip_ratio/low_min": 0.00019152652657794533,
      "clip_ratio/region_mean": 0.002646197346621193,
      "epoch": 0.005413319800033833,
      "grad_norm": 0.12117017805576324,
      "learning_rate": 1e-06,
      "loss": 0.038,
      "step": 58
    },
    {
      "clip_ratio/high_max": 0.0026648359271348454,
      "clip_ratio/high_mean": 0.0012008250414510258,
      "clip_ratio/low_mean": 0.0013067040526948404,
      "clip_ratio/low_min": 0.00021925389592070132,
      "clip_ratio/region_mean": 0.002507529075955972,
      "epoch": 0.005506652900034417,
      "grad_norm": 0.13083091378211975,
      "learning_rate": 1e-06,
      "loss": -0.0015,
      "step": 59
    },
    {
      "clip_ratio/high_max": 0.0023332468190346844,
      "clip_ratio/high_mean": 0.0011102884272986557,
      "clip_ratio/low_mean": 0.0014840043040749151,
      "clip_ratio/low_min": 0.0001599972110852832,
      "clip_ratio/region_mean": 0.002594292745925486,
      "epoch": 0.005599986000035,
      "grad_norm": 0.11433768272399902,
      "learning_rate": 1e-06,
      "loss": 0.005,
      "step": 60
    },
    {
      "clip_ratio/high_max": 0.0028035322538926266,
      "clip_ratio/high_mean": 0.0011521758897288237,
      "clip_ratio/low_mean": 0.0013908127111790236,
      "clip_ratio/low_min": 0.0002726918983171345,
      "clip_ratio/region_mean": 0.0025429886154597625,
      "epoch": 0.005693319100035584,
      "grad_norm": 0.11670524626970291,
      "learning_rate": 1e-06,
      "loss": 0.0281,
      "step": 61
    },
    {
      "clip_ratio/high_max": 0.002536535459512379,
      "clip_ratio/high_mean": 0.00121431296429364,
      "clip_ratio/low_mean": 0.0012722949650196824,
      "clip_ratio/low_min": 0.00022249042103794636,
      "clip_ratio/region_mean": 0.0024866079329513013,
      "epoch": 0.005786652200036166,
      "grad_norm": 0.12424971908330917,
      "learning_rate": 1e-06,
      "loss": 0.019,
      "step": 62
    },
    {
      "clip_ratio/high_max": 0.0025815168119152077,
      "clip_ratio/high_mean": 0.0012384331566863693,
      "clip_ratio/low_mean": 0.0012156461416452657,
      "clip_ratio/low_min": 0.00012347833853709744,
      "clip_ratio/region_mean": 0.002454079338349402,
      "epoch": 0.00587998530003675,
      "grad_norm": 0.10702453553676605,
      "learning_rate": 1e-06,
      "loss": -0.0233,
      "step": 63
    },
    {
      "clip_ratio/high_max": 0.0031096722559595946,
      "clip_ratio/high_mean": 0.0011724801315722289,
      "clip_ratio/low_mean": 0.0015286608031601645,
      "clip_ratio/low_min": 0.0003675774805742549,
      "clip_ratio/region_mean": 0.0027011409183614887,
      "epoch": 0.005973318400037333,
      "grad_norm": 0.11808144301176071,
      "learning_rate": 1e-06,
      "loss": 0.0507,
      "step": 64
    },
    {
      "clip_ratio/high_max": 0.002826274634571746,
      "clip_ratio/high_mean": 0.0011323906401230488,
      "clip_ratio/low_mean": 0.0016584002878516912,
      "clip_ratio/low_min": 0.00033293380329268984,
      "clip_ratio/region_mean": 0.002790790909784846,
      "epoch": 0.006066651500037917,
      "grad_norm": 0.11598782241344452,
      "learning_rate": 1e-06,
      "loss": 0.0458,
      "step": 65
    },
    {
      "clip_ratio/high_max": 0.0024665794771863148,
      "clip_ratio/high_mean": 0.001183727457828354,
      "clip_ratio/low_mean": 0.001549983357108431,
      "clip_ratio/low_min": 0.00017830143406172283,
      "clip_ratio/region_mean": 0.0027337107458151877,
      "epoch": 0.0061599846000385,
      "grad_norm": 0.11802730709314346,
      "learning_rate": 1e-06,
      "loss": 0.0703,
      "step": 66
    },
    {
      "clip_ratio/high_max": 0.0034556466853246093,
      "clip_ratio/high_mean": 0.0015078558899404015,
      "clip_ratio/low_mean": 0.0015664736711187288,
      "clip_ratio/low_min": 0.00029567185265477747,
      "clip_ratio/region_mean": 0.003074329550145194,
      "epoch": 0.0062533177000390835,
      "grad_norm": 0.12435410171747208,
      "learning_rate": 1e-06,
      "loss": 0.0157,
      "step": 67
    },
    {
      "clip_ratio/high_max": 0.002682604972505942,
      "clip_ratio/high_mean": 0.0011244208089919994,
      "clip_ratio/low_mean": 0.0014367879375640769,
      "clip_ratio/low_min": 0.00015121962132980116,
      "clip_ratio/region_mean": 0.0025612086901674047,
      "epoch": 0.006346650800039666,
      "grad_norm": 0.1238340437412262,
      "learning_rate": 1e-06,
      "loss": 0.0282,
      "step": 68
    },
    {
      "clip_ratio/high_max": 0.0028364117169985548,
      "clip_ratio/high_mean": 0.0012174231796961976,
      "clip_ratio/low_mean": 0.0014808492487645708,
      "clip_ratio/low_min": 0.0003865883045364171,
      "clip_ratio/region_mean": 0.002698272481211461,
      "epoch": 0.00643998390004025,
      "grad_norm": 0.1309591382741928,
      "learning_rate": 1e-06,
      "loss": -0.0123,
      "step": 69
    },
    {
      "clip_ratio/high_max": 0.0028682243209914304,
      "clip_ratio/high_mean": 0.00127961009820865,
      "clip_ratio/low_mean": 0.0013721636423724703,
      "clip_ratio/low_min": 0.00014195374387782067,
      "clip_ratio/region_mean": 0.0026517737496760674,
      "epoch": 0.006533317000040833,
      "grad_norm": 0.12093537300825119,
      "learning_rate": 1e-06,
      "loss": -0.0167,
      "step": 70
    },
    {
      "clip_ratio/high_max": 0.0026145253286813386,
      "clip_ratio/high_mean": 0.0011623787504504435,
      "clip_ratio/low_mean": 0.0013004832762817387,
      "clip_ratio/low_min": 0.00023329568102781195,
      "clip_ratio/region_mean": 0.002462862044922076,
      "epoch": 0.0066266501000414165,
      "grad_norm": 0.11307942122220993,
      "learning_rate": 1e-06,
      "loss": 0.0217,
      "step": 71
    },
    {
      "clip_ratio/high_max": 0.0029586045056930743,
      "clip_ratio/high_mean": 0.001300655978411669,
      "clip_ratio/low_mean": 0.0012729625268548261,
      "clip_ratio/low_min": 0.00015535668353550136,
      "clip_ratio/region_mean": 0.002573618483438622,
      "epoch": 0.006719983200042,
      "grad_norm": 0.1201862320303917,
      "learning_rate": 1e-06,
      "loss": 0.0153,
      "step": 72
    },
    {
      "clip_ratio/high_max": 0.0025655183562776074,
      "clip_ratio/high_mean": 0.0011379388015484437,
      "clip_ratio/low_mean": 0.0013663674253621139,
      "clip_ratio/low_min": 0.00034249923373863567,
      "clip_ratio/region_mean": 0.002504306197806727,
      "epoch": 0.0068133163000425835,
      "grad_norm": 0.12244287133216858,
      "learning_rate": 1e-06,
      "loss": 0.0368,
      "step": 73
    },
    {
      "clip_ratio/high_max": 0.0027429223846411332,
      "clip_ratio/high_mean": 0.0010778947798826266,
      "clip_ratio/low_mean": 0.0013019870566495229,
      "clip_ratio/low_min": 0.00017331588605884463,
      "clip_ratio/region_mean": 0.00237988186563598,
      "epoch": 0.006906649400043167,
      "grad_norm": 0.11468847841024399,
      "learning_rate": 1e-06,
      "loss": 0.0001,
      "step": 74
    },
    {
      "clip_ratio/high_max": 0.0026020435980171897,
      "clip_ratio/high_mean": 0.0012703805841738358,
      "clip_ratio/low_mean": 0.0014648977921751793,
      "clip_ratio/low_min": 0.0001831877998483833,
      "clip_ratio/region_mean": 0.002735278438194655,
      "epoch": 0.0069999825000437495,
      "grad_norm": 0.11755255609750748,
      "learning_rate": 1e-06,
      "loss": 0.0189,
      "step": 75
    },
    {
      "clip_ratio/high_max": 0.002817681059241295,
      "clip_ratio/high_mean": 0.0013301539620442782,
      "clip_ratio/low_mean": 0.0013364174410526175,
      "clip_ratio/low_min": 0.00011838049067591783,
      "clip_ratio/region_mean": 0.0026665713521651924,
      "epoch": 0.007093315600044333,
      "grad_norm": 0.11992045491933823,
      "learning_rate": 1e-06,
      "loss": -0.0544,
      "step": 76
    },
    {
      "clip_ratio/high_max": 0.002334528460778529,
      "clip_ratio/high_mean": 0.0011476118379505351,
      "clip_ratio/low_mean": 0.0015280926272680517,
      "clip_ratio/low_min": 0.00030930779666960007,
      "clip_ratio/region_mean": 0.0026757044688565657,
      "epoch": 0.0071866487000449165,
      "grad_norm": 0.12068290263414383,
      "learning_rate": 1e-06,
      "loss": 0.0294,
      "step": 77
    },
    {
      "clip_ratio/high_max": 0.0027745606494136155,
      "clip_ratio/high_mean": 0.0012665794092754368,
      "clip_ratio/low_mean": 0.0013899393161409535,
      "clip_ratio/low_min": 0.0002143612400686834,
      "clip_ratio/region_mean": 0.0026565187436062843,
      "epoch": 0.0072799818000455,
      "grad_norm": 0.11019036918878555,
      "learning_rate": 1e-06,
      "loss": 0.0042,
      "step": 78
    },
    {
      "clip_ratio/high_max": 0.002435784030240029,
      "clip_ratio/high_mean": 0.0012236549646331696,
      "clip_ratio/low_mean": 0.0014473684277618304,
      "clip_ratio/low_min": 0.00024480762249368127,
      "clip_ratio/region_mean": 0.0026710233869380318,
      "epoch": 0.007373314900046083,
      "grad_norm": 0.12387555092573166,
      "learning_rate": 1e-06,
      "loss": -0.0001,
      "step": 79
    },
    {
      "clip_ratio/high_max": 0.002483940726961009,
      "clip_ratio/high_mean": 0.0010340837689000182,
      "clip_ratio/low_mean": 0.0013392387554631568,
      "clip_ratio/low_min": 0.00023337047696259106,
      "clip_ratio/region_mean": 0.002373322487983387,
      "epoch": 0.007466648000046667,
      "grad_norm": 0.11911188066005707,
      "learning_rate": 1e-06,
      "loss": -0.0016,
      "step": 80
    },
    {
      "clip_ratio/high_max": 0.002534215891500935,
      "clip_ratio/high_mean": 0.001200334412715165,
      "clip_ratio/low_mean": 0.001505252341303276,
      "clip_ratio/low_min": 0.0003896178604918532,
      "clip_ratio/region_mean": 0.0027055867831222713,
      "epoch": 0.0075599811000472495,
      "grad_norm": 0.12401816993951797,
      "learning_rate": 1e-06,
      "loss": 0.0511,
      "step": 81
    },
    {
      "clip_ratio/high_max": 0.0027460782512207516,
      "clip_ratio/high_mean": 0.001146390273788711,
      "clip_ratio/low_mean": 0.0013218955646152608,
      "clip_ratio/low_min": 0.0001522299744465272,
      "clip_ratio/region_mean": 0.0024682858420419507,
      "epoch": 0.007653314200047833,
      "grad_norm": 0.1271621733903885,
      "learning_rate": 1e-06,
      "loss": -0.0355,
      "step": 82
    },
    {
      "clip_ratio/high_max": 0.0027357460858183913,
      "clip_ratio/high_mean": 0.0012101973879907746,
      "clip_ratio/low_mean": 0.0015687971099396236,
      "clip_ratio/low_min": 0.0002497866480553057,
      "clip_ratio/region_mean": 0.0027789945161202922,
      "epoch": 0.007746647300048416,
      "grad_norm": 0.12573960423469543,
      "learning_rate": 1e-06,
      "loss": 0.0232,
      "step": 83
    },
    {
      "clip_ratio/high_max": 0.0027602964473771863,
      "clip_ratio/high_mean": 0.0014019418449606746,
      "clip_ratio/low_mean": 0.0015700076110078953,
      "clip_ratio/low_min": 0.000192812726709235,
      "clip_ratio/region_mean": 0.0029719493904849514,
      "epoch": 0.007839980400049,
      "grad_norm": 0.12834490835666656,
      "learning_rate": 1e-06,
      "loss": -0.0236,
      "step": 84
    },
    {
      "clip_ratio/high_max": 0.002873798403015826,
      "clip_ratio/high_mean": 0.0012417943034961354,
      "clip_ratio/low_mean": 0.0014508737658616155,
      "clip_ratio/low_min": 0.00036596354493667604,
      "clip_ratio/region_mean": 0.002692668109375518,
      "epoch": 0.007933313500049582,
      "grad_norm": 0.12216285616159439,
      "learning_rate": 1e-06,
      "loss": -0.0186,
      "step": 85
    },
    {
      "clip_ratio/high_max": 0.0031415919147548266,
      "clip_ratio/high_mean": 0.0013476370768330526,
      "clip_ratio/low_mean": 0.001391533442074433,
      "clip_ratio/low_min": 0.0001743201992212562,
      "clip_ratio/region_mean": 0.0027391705225454643,
      "epoch": 0.008026646600050166,
      "grad_norm": 0.12674564123153687,
      "learning_rate": 1e-06,
      "loss": -0.0234,
      "step": 86
    },
    {
      "clip_ratio/high_max": 0.0026021780795417726,
      "clip_ratio/high_mean": 0.0011719479552994017,
      "clip_ratio/low_mean": 0.0015808066455065273,
      "clip_ratio/low_min": 0.00028470718189055333,
      "clip_ratio/region_mean": 0.0027527546044439077,
      "epoch": 0.00811997970005075,
      "grad_norm": 0.12727433443069458,
      "learning_rate": 1e-06,
      "loss": 0.0085,
      "step": 87
    },
    {
      "clip_ratio/high_max": 0.0026504448251216672,
      "clip_ratio/high_mean": 0.0013693557848455384,
      "clip_ratio/low_mean": 0.0014677377839689143,
      "clip_ratio/low_min": 0.00018616943725646706,
      "clip_ratio/region_mean": 0.002837093561538495,
      "epoch": 0.008213312800051333,
      "grad_norm": 0.12803950905799866,
      "learning_rate": 1e-06,
      "loss": -0.0057,
      "step": 88
    },
    {
      "clip_ratio/high_max": 0.0026206430775346234,
      "clip_ratio/high_mean": 0.0012244423414813355,
      "clip_ratio/low_mean": 0.001532272457552608,
      "clip_ratio/low_min": 0.00022172410626808414,
      "clip_ratio/region_mean": 0.0027567148572416045,
      "epoch": 0.008306645900051916,
      "grad_norm": 0.11617273092269897,
      "learning_rate": 1e-06,
      "loss": 0.0314,
      "step": 89
    },
    {
      "clip_ratio/high_max": 0.002430669810564723,
      "clip_ratio/high_mean": 0.0010987007117364556,
      "clip_ratio/low_mean": 0.0014864155782561284,
      "clip_ratio/low_min": 0.00034380300076009007,
      "clip_ratio/region_mean": 0.0025851162936305627,
      "epoch": 0.0083999790000525,
      "grad_norm": 0.11640790104866028,
      "learning_rate": 1e-06,
      "loss": 0.062,
      "step": 90
    },
    {
      "clip_ratio/high_max": 0.0027008131437469274,
      "clip_ratio/high_mean": 0.0012744264058710542,
      "clip_ratio/low_mean": 0.0014847731108602602,
      "clip_ratio/low_min": 0.00027809551465907134,
      "clip_ratio/region_mean": 0.0027591994585236534,
      "epoch": 0.008493312100053083,
      "grad_norm": 0.12253836542367935,
      "learning_rate": 1e-06,
      "loss": 0.0247,
      "step": 91
    },
    {
      "clip_ratio/high_max": 0.0030946138067520224,
      "clip_ratio/high_mean": 0.0012652283439820167,
      "clip_ratio/low_mean": 0.0015399536132463254,
      "clip_ratio/low_min": 0.0002860111262634746,
      "clip_ratio/region_mean": 0.0028051819099346176,
      "epoch": 0.008586645200053667,
      "grad_norm": 0.1208665519952774,
      "learning_rate": 1e-06,
      "loss": -0.0231,
      "step": 92
    },
    {
      "clip_ratio/high_max": 0.0029941294342279434,
      "clip_ratio/high_mean": 0.0013417743321042508,
      "clip_ratio/low_mean": 0.001346117518551182,
      "clip_ratio/low_min": 0.00023732907084195176,
      "clip_ratio/region_mean": 0.0026878918142756447,
      "epoch": 0.00867997830005425,
      "grad_norm": 0.1292804777622223,
      "learning_rate": 1e-06,
      "loss": 0.0164,
      "step": 93
    },
    {
      "clip_ratio/high_max": 0.0029322607879294083,
      "clip_ratio/high_mean": 0.0012803628378605936,
      "clip_ratio/low_mean": 0.0016392632605857216,
      "clip_ratio/low_min": 0.0003152219724142924,
      "clip_ratio/region_mean": 0.0029196261311881244,
      "epoch": 0.008773311400054834,
      "grad_norm": 0.1228199377655983,
      "learning_rate": 1e-06,
      "loss": 0.0645,
      "step": 94
    },
    {
      "clip_ratio/high_max": 0.0025236464352929033,
      "clip_ratio/high_mean": 0.0012460195575840771,
      "clip_ratio/low_mean": 0.001547534189739963,
      "clip_ratio/low_min": 0.0002313568111276254,
      "clip_ratio/region_mean": 0.002793553765513934,
      "epoch": 0.008866644500055417,
      "grad_norm": 0.11896580457687378,
      "learning_rate": 1e-06,
      "loss": 0.023,
      "step": 95
    },
    {
      "clip_ratio/high_max": 0.0024031530047068372,
      "clip_ratio/high_mean": 0.0011397364978620317,
      "clip_ratio/low_mean": 0.001470630151743535,
      "clip_ratio/low_min": 0.0001873053420240467,
      "clip_ratio/region_mean": 0.002610366602311842,
      "epoch": 0.008959977600056,
      "grad_norm": 0.11692328751087189,
      "learning_rate": 1e-06,
      "loss": 0.0027,
      "step": 96
    },
    {
      "clip_ratio/high_max": 0.002619394777866546,
      "clip_ratio/high_mean": 0.001199335394630907,
      "clip_ratio/low_mean": 0.0015835727390367538,
      "clip_ratio/low_min": 0.0002894433882829617,
      "clip_ratio/region_mean": 0.0027829081373056397,
      "epoch": 0.009053310700056582,
      "grad_norm": 0.12827742099761963,
      "learning_rate": 1e-06,
      "loss": 0.0461,
      "step": 97
    },
    {
      "clip_ratio/high_max": 0.0026653434615582228,
      "clip_ratio/high_mean": 0.0012437725854397286,
      "clip_ratio/low_mean": 0.001574280428030761,
      "clip_ratio/low_min": 0.0002538182880016393,
      "clip_ratio/region_mean": 0.002818052984366659,
      "epoch": 0.009146643800057166,
      "grad_norm": 0.1247875839471817,
      "learning_rate": 1e-06,
      "loss": 0.0214,
      "step": 98
    },
    {
      "clip_ratio/high_max": 0.002603532724606339,
      "clip_ratio/high_mean": 0.0012048694479744881,
      "clip_ratio/low_mean": 0.001481337756558787,
      "clip_ratio/low_min": 0.0001852586910899845,
      "clip_ratio/region_mean": 0.002686207204533275,
      "epoch": 0.00923997690005775,
      "grad_norm": 0.11257535964250565,
      "learning_rate": 1e-06,
      "loss": 0.0077,
      "step": 99
    },
    {
      "clip_ratio/high_max": 0.002924049971625209,
      "clip_ratio/high_mean": 0.0012575002801895607,
      "clip_ratio/low_mean": 0.0015386971317639109,
      "clip_ratio/low_min": 0.00033075985629693605,
      "clip_ratio/region_mean": 0.0027961974337813444,
      "epoch": 0.009333310000058333,
      "grad_norm": 0.12220936268568039,
      "learning_rate": 1e-06,
      "loss": 0.0352,
      "step": 100
    },
    {
      "clip_ratio/high_max": 0.0028391593587002717,
      "clip_ratio/high_mean": 0.0012918183238070924,
      "clip_ratio/low_mean": 0.0013782262103632092,
      "clip_ratio/low_min": 0.0001240499914274551,
      "clip_ratio/region_mean": 0.002670044530532323,
      "epoch": 0.009426643100058916,
      "grad_norm": 0.12901794910430908,
      "learning_rate": 1e-06,
      "loss": -0.0133,
      "step": 101
    },
    {
      "clip_ratio/high_max": 0.002537941516493447,
      "clip_ratio/high_mean": 0.0013183612245484255,
      "clip_ratio/low_mean": 0.0013246296730358154,
      "clip_ratio/low_min": 0.00013077422318019671,
      "clip_ratio/region_mean": 0.002642990875756368,
      "epoch": 0.0095199762000595,
      "grad_norm": 0.1298808455467224,
      "learning_rate": 1e-06,
      "loss": -0.0233,
      "step": 102
    },
    {
      "clip_ratio/high_max": 0.0031578919224557467,
      "clip_ratio/high_mean": 0.001373731909552589,
      "clip_ratio/low_mean": 0.0014723148960911203,
      "clip_ratio/low_min": 0.00019456338122836314,
      "clip_ratio/region_mean": 0.0028460468456614763,
      "epoch": 0.009613309300060083,
      "grad_norm": 0.11997205764055252,
      "learning_rate": 1e-06,
      "loss": 0.0065,
      "step": 103
    },
    {
      "clip_ratio/high_max": 0.002865104914235417,
      "clip_ratio/high_mean": 0.0012580548718688078,
      "clip_ratio/low_mean": 0.0014033523948455695,
      "clip_ratio/low_min": 0.0004038890856463695,
      "clip_ratio/region_mean": 0.0026614072121446952,
      "epoch": 0.009706642400060667,
      "grad_norm": 0.12166479229927063,
      "learning_rate": 1e-06,
      "loss": 0.0303,
      "step": 104
    },
    {
      "clip_ratio/high_max": 0.0024868289765436202,
      "clip_ratio/high_mean": 0.001170450708741555,
      "clip_ratio/low_mean": 0.0014502817575703375,
      "clip_ratio/low_min": 0.0002118278325724532,
      "clip_ratio/region_mean": 0.0026207323535345495,
      "epoch": 0.00979997550006125,
      "grad_norm": 0.1195027306675911,
      "learning_rate": 1e-06,
      "loss": 0.0467,
      "step": 105
    },
    {
      "clip_ratio/high_max": 0.003201271560101304,
      "clip_ratio/high_mean": 0.0014800217068113852,
      "clip_ratio/low_mean": 0.0015999262213881593,
      "clip_ratio/low_min": 0.0003387703791304375,
      "clip_ratio/region_mean": 0.0030799479718552902,
      "epoch": 0.009893308600061834,
      "grad_norm": 0.13096079230308533,
      "learning_rate": 1e-06,
      "loss": -0.0112,
      "step": 106
    },
    {
      "clip_ratio/high_max": 0.0030543005632353015,
      "clip_ratio/high_mean": 0.0012968190567335114,
      "clip_ratio/low_mean": 0.0015272485397872515,
      "clip_ratio/low_min": 0.0001728877341520274,
      "clip_ratio/region_mean": 0.002824067632900551,
      "epoch": 0.009986641700062417,
      "grad_norm": 0.1275666058063507,
      "learning_rate": 1e-06,
      "loss": 0.0272,
      "step": 107
    },
    {
      "clip_ratio/high_max": 0.0025191621753037907,
      "clip_ratio/high_mean": 0.0012134683529438917,
      "clip_ratio/low_mean": 0.0014848986320430413,
      "clip_ratio/low_min": 0.00025858148364932276,
      "clip_ratio/region_mean": 0.002698366981348954,
      "epoch": 0.010079974800063,
      "grad_norm": 0.11229578405618668,
      "learning_rate": 1e-06,
      "loss": 0.0519,
      "step": 108
    },
    {
      "clip_ratio/high_max": 0.003106487449258566,
      "clip_ratio/high_mean": 0.0014111388445599005,
      "clip_ratio/low_mean": 0.0014543828710884554,
      "clip_ratio/low_min": 0.00022016003640601411,
      "clip_ratio/region_mean": 0.0028655217320192605,
      "epoch": 0.010173307900063584,
      "grad_norm": 0.13031111657619476,
      "learning_rate": 1e-06,
      "loss": -0.0293,
      "step": 109
    },
    {
      "clip_ratio/high_max": 0.002698599433642812,
      "clip_ratio/high_mean": 0.0012986355268367333,
      "clip_ratio/low_mean": 0.0016266366365016438,
      "clip_ratio/low_min": 0.00011085279948019888,
      "clip_ratio/region_mean": 0.0029252721869852394,
      "epoch": 0.010266641000064166,
      "grad_norm": 0.12719281017780304,
      "learning_rate": 1e-06,
      "loss": 0.0417,
      "step": 110
    },
    {
      "clip_ratio/high_max": 0.0024644344302942045,
      "clip_ratio/high_mean": 0.0012884143980045337,
      "clip_ratio/low_mean": 0.0014313229476101696,
      "clip_ratio/low_min": 0.000225196647534176,
      "clip_ratio/region_mean": 0.0027197373201488517,
      "epoch": 0.010359974100064749,
      "grad_norm": 0.11651661992073059,
      "learning_rate": 1e-06,
      "loss": 0.009,
      "step": 111
    },
    {
      "clip_ratio/high_max": 0.002528496646846179,
      "clip_ratio/high_mean": 0.001220474463480059,
      "clip_ratio/low_mean": 0.0014707193258800544,
      "clip_ratio/low_min": 0.0003620400821091607,
      "clip_ratio/region_mean": 0.002691193869395647,
      "epoch": 0.010453307200065333,
      "grad_norm": 0.10828004777431488,
      "learning_rate": 1e-06,
      "loss": 0.0247,
      "step": 112
    },
    {
      "clip_ratio/high_max": 0.0033653701102593914,
      "clip_ratio/high_mean": 0.001461264935642248,
      "clip_ratio/low_mean": 0.00145121775494772,
      "clip_ratio/low_min": 0.00017661723177297972,
      "clip_ratio/region_mean": 0.002912482712417841,
      "epoch": 0.010546640300065916,
      "grad_norm": 0.12943993508815765,
      "learning_rate": 1e-06,
      "loss": -0.0168,
      "step": 113
    },
    {
      "clip_ratio/high_max": 0.002859338892449159,
      "clip_ratio/high_mean": 0.001295949798077345,
      "clip_ratio/low_mean": 0.0015416161986649968,
      "clip_ratio/low_min": 0.0002221035938418936,
      "clip_ratio/region_mean": 0.0028375659458106384,
      "epoch": 0.0106399734000665,
      "grad_norm": 0.11572157591581345,
      "learning_rate": 1e-06,
      "loss": 0.0296,
      "step": 114
    },
    {
      "clip_ratio/high_max": 0.002783154930511955,
      "clip_ratio/high_mean": 0.0013088373962091282,
      "clip_ratio/low_mean": 0.00147791879135184,
      "clip_ratio/low_min": 0.0002673045901246951,
      "clip_ratio/region_mean": 0.002786756187560968,
      "epoch": 0.010733306500067083,
      "grad_norm": 0.12409446388483047,
      "learning_rate": 1e-06,
      "loss": 0.0011,
      "step": 115
    },
    {
      "clip_ratio/high_max": 0.002771793559077196,
      "clip_ratio/high_mean": 0.0013845524408679921,
      "clip_ratio/low_mean": 0.001649686226301128,
      "clip_ratio/low_min": 0.0003981206173193641,
      "clip_ratio/region_mean": 0.0030342386598931625,
      "epoch": 0.010826639600067666,
      "grad_norm": 0.13282372057437897,
      "learning_rate": 1e-06,
      "loss": 0.0223,
      "step": 116
    },
    {
      "clip_ratio/high_max": 0.0022662589472020045,
      "clip_ratio/high_mean": 0.0012029814461129718,
      "clip_ratio/low_mean": 0.0013570538721978664,
      "clip_ratio/low_min": 0.000257093673099007,
      "clip_ratio/region_mean": 0.0025600353546906263,
      "epoch": 0.01091997270006825,
      "grad_norm": 0.11931352317333221,
      "learning_rate": 1e-06,
      "loss": 0.0028,
      "step": 117
    },
    {
      "clip_ratio/high_max": 0.003215425334929023,
      "clip_ratio/high_mean": 0.0013237579569249647,
      "clip_ratio/low_mean": 0.0016452279669465497,
      "clip_ratio/low_min": 0.0003323610362713225,
      "clip_ratio/region_mean": 0.002968985980260186,
      "epoch": 0.011013305800068833,
      "grad_norm": 0.13158798217773438,
      "learning_rate": 1e-06,
      "loss": 0.0152,
      "step": 118
    },
    {
      "clip_ratio/high_max": 0.002647452463861555,
      "clip_ratio/high_mean": 0.0012800487056665588,
      "clip_ratio/low_mean": 0.001443458786525298,
      "clip_ratio/low_min": 0.00033292964508291334,
      "clip_ratio/region_mean": 0.0027235074812779203,
      "epoch": 0.011106638900069417,
      "grad_norm": 0.11989909410476685,
      "learning_rate": 1e-06,
      "loss": 0.0483,
      "step": 119
    },
    {
      "clip_ratio/high_max": 0.0027026427269447595,
      "clip_ratio/high_mean": 0.0010280060960212722,
      "clip_ratio/low_mean": 0.0014192807830113452,
      "clip_ratio/low_min": 0.00029264237309689634,
      "clip_ratio/region_mean": 0.002447286926326342,
      "epoch": 0.01119997200007,
      "grad_norm": 0.11595442146062851,
      "learning_rate": 1e-06,
      "loss": 0.068,
      "step": 120
    },
    {
      "clip_ratio/high_max": 0.0025730949273565784,
      "clip_ratio/high_mean": 0.0011617753261816688,
      "clip_ratio/low_mean": 0.0015755972526676487,
      "clip_ratio/low_min": 0.00029739353885815945,
      "clip_ratio/region_mean": 0.002737372647970915,
      "epoch": 0.011293305100070584,
      "grad_norm": 0.11768896877765656,
      "learning_rate": 1e-06,
      "loss": 0.0569,
      "step": 121
    },
    {
      "clip_ratio/high_max": 0.0026708618825068697,
      "clip_ratio/high_mean": 0.0012442792249203194,
      "clip_ratio/low_mean": 0.0014611152982979547,
      "clip_ratio/low_min": 0.00034541680088295834,
      "clip_ratio/region_mean": 0.0027053944577346556,
      "epoch": 0.011386638200071167,
      "grad_norm": 0.11789402365684509,
      "learning_rate": 1e-06,
      "loss": 0.0193,
      "step": 122
    },
    {
      "clip_ratio/high_max": 0.0028895758150611073,
      "clip_ratio/high_mean": 0.0014895897838869132,
      "clip_ratio/low_mean": 0.0015124876772460993,
      "clip_ratio/low_min": 0.00019328471171320416,
      "clip_ratio/region_mean": 0.0030020774429431185,
      "epoch": 0.011479971300071749,
      "grad_norm": 0.12825018167495728,
      "learning_rate": 1e-06,
      "loss": -0.0431,
      "step": 123
    },
    {
      "clip_ratio/high_max": 0.0023921758111100644,
      "clip_ratio/high_mean": 0.001148466060840292,
      "clip_ratio/low_mean": 0.0014945909897505771,
      "clip_ratio/low_min": 0.00017136218139057746,
      "clip_ratio/region_mean": 0.002643057086970657,
      "epoch": 0.011573304400072332,
      "grad_norm": 0.12371445447206497,
      "learning_rate": 1e-06,
      "loss": 0.0536,
      "step": 124
    },
    {
      "clip_ratio/high_max": 0.0026537046942394227,
      "clip_ratio/high_mean": 0.001262595902517205,
      "clip_ratio/low_mean": 0.0016034173786465544,
      "clip_ratio/low_min": 0.0002627986832521856,
      "clip_ratio/region_mean": 0.0028660132811637595,
      "epoch": 0.011666637500072916,
      "grad_norm": 0.11962024867534637,
      "learning_rate": 1e-06,
      "loss": 0.0329,
      "step": 125
    },
    {
      "clip_ratio/high_max": 0.0028672960033873096,
      "clip_ratio/high_mean": 0.0012027163611492142,
      "clip_ratio/low_mean": 0.0014232714383979328,
      "clip_ratio/low_min": 0.0004464297744561918,
      "clip_ratio/region_mean": 0.0026259877486154437,
      "epoch": 0.0117599706000735,
      "grad_norm": 0.1233714148402214,
      "learning_rate": 1e-06,
      "loss": 0.0099,
      "step": 126
    },
    {
      "clip_ratio/high_max": 0.0030454081352218054,
      "clip_ratio/high_mean": 0.0013154065491107758,
      "clip_ratio/low_mean": 0.0013777863496216014,
      "clip_ratio/low_min": 0.00026856406748265726,
      "clip_ratio/region_mean": 0.002693192960578017,
      "epoch": 0.011853303700074083,
      "grad_norm": 0.11404651403427124,
      "learning_rate": 1e-06,
      "loss": -0.0047,
      "step": 127
    },
    {
      "clip_ratio/high_max": 0.003028228136827238,
      "clip_ratio/high_mean": 0.001399489050527336,
      "clip_ratio/low_mean": 0.0014854848777758889,
      "clip_ratio/low_min": 0.00018905064644059166,
      "clip_ratio/region_mean": 0.0028849739173892885,
      "epoch": 0.011946636800074666,
      "grad_norm": 0.12079603970050812,
      "learning_rate": 1e-06,
      "loss": 0.0171,
      "step": 128
    },
    {
      "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": 0.013593401227678603,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4095.0,
      "completions/mean_length": 608.6326293945312,
      "completions/mean_terminated_length": 560.5741577148438,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.01203996990007525,
      "grad_norm": 0.13403193652629852,
      "learning_rate": 1e-06,
      "loss": 0.0436,
      "num_tokens": 161463676.0,
      "reward": 0.5264195203781128,
      "reward_std": 0.24368982017040253,
      "rewards/simpleverify_reward/mean": 0.5264195203781128,
      "rewards/simpleverify_reward/std": 0.49930375814437866,
      "step": 129
    },
    {
      "clip_ratio/high_max": 0.0024332596149179153,
      "clip_ratio/high_mean": 0.000988849033092265,
      "clip_ratio/low_mean": 0.0007325897458940744,
      "clip_ratio/low_min": 7.720795656496193e-05,
      "clip_ratio/region_mean": 0.0017214387553394772,
      "epoch": 0.012133303000075833,
      "grad_norm": 0.1320538967847824,
      "learning_rate": 1e-06,
      "loss": 0.0148,
      "step": 130
    },
    {
      "clip_ratio/high_max": 0.0021657638280885294,
      "clip_ratio/high_mean": 0.0008973378025984857,
      "clip_ratio/low_mean": 0.0007111463273759,
      "clip_ratio/low_min": 7.660079336346826e-05,
      "clip_ratio/region_mean": 0.0016084840826806612,
      "epoch": 0.012226636100076417,
      "grad_norm": 0.11757486313581467,
      "learning_rate": 1e-06,
      "loss": 0.0488,
      "step": 131
    },
    {
      "clip_ratio/high_max": 0.0022863169870106503,
      "clip_ratio/high_mean": 0.000983288615316269,
      "clip_ratio/low_mean": 0.0006977904340601526,
      "clip_ratio/low_min": 4.470737712836126e-05,
      "clip_ratio/region_mean": 0.0016810790621093474,
      "epoch": 0.012319969200077,
      "grad_norm": 0.13243581354618073,
      "learning_rate": 1e-06,
      "loss": 0.0306,
      "step": 132
    },
    {
      "clip_ratio/high_max": 0.0021634436197928153,
      "clip_ratio/high_mean": 0.0010413669515401125,
      "clip_ratio/low_mean": 0.0009701348044472979,
      "clip_ratio/low_min": 0.00018172072850575205,
      "clip_ratio/region_mean": 0.0020115017250645906,
      "epoch": 0.012413302300077584,
      "grad_norm": 0.13197748363018036,
      "learning_rate": 1e-06,
      "loss": 0.0428,
      "step": 133
    },
    {
      "clip_ratio/high_max": 0.002508608471543994,
      "clip_ratio/high_mean": 0.0010944333698716946,
      "clip_ratio/low_mean": 0.0010340974677092163,
      "clip_ratio/low_min": 0.00015072810447236407,
      "clip_ratio/region_mean": 0.002128530861227773,
      "epoch": 0.012506635400078167,
      "grad_norm": 0.12780120968818665,
      "learning_rate": 1e-06,
      "loss": -0.0193,
      "step": 134
    },
    {
      "clip_ratio/high_max": 0.0025976869801525027,
      "clip_ratio/high_mean": 0.0011295270887785591,
      "clip_ratio/low_mean": 0.0011326861276756972,
      "clip_ratio/low_min": 0.00012717880417767446,
      "clip_ratio/region_mean": 0.002262213201902341,
      "epoch": 0.01259996850007875,
      "grad_norm": 0.11698048561811447,
      "learning_rate": 1e-06,
      "loss": 0.0413,
      "step": 135
    },
    {
      "clip_ratio/high_max": 0.0025464736609137617,
      "clip_ratio/high_mean": 0.0011202241403225344,
      "clip_ratio/low_mean": 0.0010715174212236889,
      "clip_ratio/low_min": 0.00012168852572358446,
      "clip_ratio/region_mean": 0.002191741543356329,
      "epoch": 0.012693301600079332,
      "grad_norm": 0.12443061918020248,
      "learning_rate": 1e-06,
      "loss": 0.0103,
      "step": 136
    },
    {
      "clip_ratio/high_max": 0.002053405638434924,
      "clip_ratio/high_mean": 0.0009248903033949318,
      "clip_ratio/low_mean": 0.00100735711021116,
      "clip_ratio/low_min": 6.899488653289154e-05,
      "clip_ratio/region_mean": 0.0019322473381180316,
      "epoch": 0.012786634700079916,
      "grad_norm": 0.11504258960485458,
      "learning_rate": 1e-06,
      "loss": 0.0563,
      "step": 137
    },
    {
      "clip_ratio/high_max": 0.0025004914423334412,
      "clip_ratio/high_mean": 0.0011608715503825806,
      "clip_ratio/low_mean": 0.0009811282870941795,
      "clip_ratio/low_min": 0.00014834668490948388,
      "clip_ratio/region_mean": 0.0021419998156488873,
      "epoch": 0.0128799678000805,
      "grad_norm": 0.11799511313438416,
      "learning_rate": 1e-06,
      "loss": -0.0253,
      "step": 138
    },
    {
      "clip_ratio/high_max": 0.002182101146900095,
      "clip_ratio/high_mean": 0.0011294264459138503,
      "clip_ratio/low_mean": 0.0010483198529982474,
      "clip_ratio/low_min": 0.0001590806550666457,
      "clip_ratio/region_mean": 0.0021777462752652355,
      "epoch": 0.012973300900081083,
      "grad_norm": 0.10931219160556793,
      "learning_rate": 1e-06,
      "loss": -0.0026,
      "step": 139
    },
    {
      "clip_ratio/high_max": 0.0023643400927539915,
      "clip_ratio/high_mean": 0.001019347782857949,
      "clip_ratio/low_mean": 0.0010191293695243075,
      "clip_ratio/low_min": 0.00012544995706775808,
      "clip_ratio/region_mean": 0.002038477163296193,
      "epoch": 0.013066634000081666,
      "grad_norm": 0.12056972831487656,
      "learning_rate": 1e-06,
      "loss": 0.0039,
      "step": 140
    },
    {
      "clip_ratio/high_max": 0.002797265253320802,
      "clip_ratio/high_mean": 0.0011310938352835365,
      "clip_ratio/low_mean": 0.0012077284227416385,
      "clip_ratio/low_min": 0.00016638736451568548,
      "clip_ratio/region_mean": 0.002338822239835281,
      "epoch": 0.01315996710008225,
      "grad_norm": 0.12474213540554047,
      "learning_rate": 1e-06,
      "loss": 0.0228,
      "step": 141
    },
    {
      "clip_ratio/high_max": 0.0023029514122754335,
      "clip_ratio/high_mean": 0.0009922978970280383,
      "clip_ratio/low_mean": 0.0010987028290401213,
      "clip_ratio/low_min": 0.00017076500898838276,
      "clip_ratio/region_mean": 0.002091000773361884,
      "epoch": 0.013253300200082833,
      "grad_norm": 0.12109792232513428,
      "learning_rate": 1e-06,
      "loss": 0.0917,
      "step": 142
    },
    {
      "clip_ratio/high_max": 0.0023453186986444052,
      "clip_ratio/high_mean": 0.0010823465017892886,
      "clip_ratio/low_mean": 0.0012704171913355822,
      "clip_ratio/low_min": 0.00016696958391548833,
      "clip_ratio/region_mean": 0.002352763716771733,
      "epoch": 0.013346633300083417,
      "grad_norm": 0.12181831896305084,
      "learning_rate": 1e-06,
      "loss": 0.0506,
      "step": 143
    },
    {
      "clip_ratio/high_max": 0.002538202148571145,
      "clip_ratio/high_mean": 0.001040334809658816,
      "clip_ratio/low_mean": 0.0009443219387321733,
      "clip_ratio/low_min": 5.9650946695910534e-05,
      "clip_ratio/region_mean": 0.0019846567083732225,
      "epoch": 0.013439966400084,
      "grad_norm": 0.12078903615474701,
      "learning_rate": 1e-06,
      "loss": -0.004,
      "step": 144
    },
    {
      "clip_ratio/high_max": 0.002726344384427648,
      "clip_ratio/high_mean": 0.001087585336790653,
      "clip_ratio/low_mean": 0.0011553774274943862,
      "clip_ratio/low_min": 0.00021918675520282704,
      "clip_ratio/region_mean": 0.0022429627060773782,
      "epoch": 0.013533299500084583,
      "grad_norm": 0.1193271055817604,
      "learning_rate": 1e-06,
      "loss": 0.0332,
      "step": 145
    },
    {
      "clip_ratio/high_max": 0.002232237191492459,
      "clip_ratio/high_mean": 0.0010926271625066875,
      "clip_ratio/low_mean": 0.0010220541535090888,
      "clip_ratio/low_min": 0.0001043354222929338,
      "clip_ratio/region_mean": 0.0021146814033272676,
      "epoch": 0.013626632600085167,
      "grad_norm": 0.11858843266963959,
      "learning_rate": 1e-06,
      "loss": 0.0226,
      "step": 146
    },
    {
      "clip_ratio/high_max": 0.0022686543998133857,
      "clip_ratio/high_mean": 0.0010066488266602391,
      "clip_ratio/low_mean": 0.0011608630047703627,
      "clip_ratio/low_min": 0.00013585816213890212,
      "clip_ratio/region_mean": 0.0021675117968698032,
      "epoch": 0.01371996570008575,
      "grad_norm": 0.11356138437986374,
      "learning_rate": 1e-06,
      "loss": 0.0212,
      "step": 147
    },
    {
      "clip_ratio/high_max": 0.0021834527287865058,
      "clip_ratio/high_mean": 0.0011363685262040235,
      "clip_ratio/low_mean": 0.001056505801898311,
      "clip_ratio/low_min": 0.00016823627811390907,
      "clip_ratio/region_mean": 0.0021928743517491966,
      "epoch": 0.013813298800086334,
      "grad_norm": 0.1225375235080719,
      "learning_rate": 1e-06,
      "loss": 0.0023,
      "step": 148
    },
    {
      "clip_ratio/high_max": 0.0024487768532708287,
      "clip_ratio/high_mean": 0.0010493347981537227,
      "clip_ratio/low_mean": 0.00105377857471467,
      "clip_ratio/low_min": 0.00017336217479169136,
      "clip_ratio/region_mean": 0.0021031133801443502,
      "epoch": 0.013906631900086916,
      "grad_norm": 0.11625830084085464,
      "learning_rate": 1e-06,
      "loss": 0.0069,
      "step": 149
    },
    {
      "clip_ratio/high_max": 0.0023190810898086056,
      "clip_ratio/high_mean": 0.0009918206469592405,
      "clip_ratio/low_mean": 0.0012297029243200086,
      "clip_ratio/low_min": 0.00022102572802396026,
      "clip_ratio/region_mean": 0.002221523565822281,
      "epoch": 0.013999965000087499,
      "grad_norm": 0.1541500836610794,
      "learning_rate": 1e-06,
      "loss": 0.0353,
      "step": 150
    },
    {
      "clip_ratio/high_max": 0.002041557072516298,
      "clip_ratio/high_mean": 0.0009195821912726387,
      "clip_ratio/low_mean": 0.0011850562696054112,
      "clip_ratio/low_min": 7.665563680347987e-05,
      "clip_ratio/region_mean": 0.002104638442688156,
      "epoch": 0.014093298100088083,
      "grad_norm": 0.10795846581459045,
      "learning_rate": 1e-06,
      "loss": 0.0586,
      "step": 151
    },
    {
      "clip_ratio/high_max": 0.0023418266500812024,
      "clip_ratio/high_mean": 0.0010353720535931643,
      "clip_ratio/low_mean": 0.0012098116203560494,
      "clip_ratio/low_min": 0.00022125856412458234,
      "clip_ratio/region_mean": 0.0022451836994150653,
      "epoch": 0.014186631200088666,
      "grad_norm": 0.11836786568164825,
      "learning_rate": 1e-06,
      "loss": 0.0316,
      "step": 152
    },
    {
      "clip_ratio/high_max": 0.002334540316951461,
      "clip_ratio/high_mean": 0.001038872684148373,
      "clip_ratio/low_mean": 0.001198381680296734,
      "clip_ratio/low_min": 0.0002770094288280234,
      "clip_ratio/region_mean": 0.0022372543389792554,
      "epoch": 0.01427996430008925,
      "grad_norm": 0.1169411838054657,
      "learning_rate": 1e-06,
      "loss": 0.0653,
      "step": 153
    },
    {
      "clip_ratio/high_max": 0.0026761881235870533,
      "clip_ratio/high_mean": 0.0011457030232122634,
      "clip_ratio/low_mean": 0.0011620547084021382,
      "clip_ratio/low_min": 0.00014709090828546323,
      "clip_ratio/region_mean": 0.002307757742528338,
      "epoch": 0.014373297400089833,
      "grad_norm": 0.12875445187091827,
      "learning_rate": 1e-06,
      "loss": -0.0193,
      "step": 154
    },
    {
      "clip_ratio/high_max": 0.002504294730897527,
      "clip_ratio/high_mean": 0.0010995161756000016,
      "clip_ratio/low_mean": 0.0013625548344862182,
      "clip_ratio/low_min": 0.00011030960831703851,
      "clip_ratio/region_mean": 0.0024620710173621774,
      "epoch": 0.014466630500090416,
      "grad_norm": 0.13295584917068481,
      "learning_rate": 1e-06,
      "loss": 0.0388,
      "step": 155
    },
    {
      "clip_ratio/high_max": 0.002898297374485992,
      "clip_ratio/high_mean": 0.0012882258597528562,
      "clip_ratio/low_mean": 0.0009775020225788467,
      "clip_ratio/low_min": 9.865721949608997e-05,
      "clip_ratio/region_mean": 0.0022657278168480843,
      "epoch": 0.014559963600091,
      "grad_norm": 0.11341188102960587,
      "learning_rate": 1e-06,
      "loss": -0.0161,
      "step": 156
    },
    {
      "clip_ratio/high_max": 0.002397498770733364,
      "clip_ratio/high_mean": 0.0011049304812331684,
      "clip_ratio/low_mean": 0.0013211759433033876,
      "clip_ratio/low_min": 0.0003025866217285511,
      "clip_ratio/region_mean": 0.0024261063590529375,
      "epoch": 0.014653296700091583,
      "grad_norm": 0.12226711213588715,
      "learning_rate": 1e-06,
      "loss": 0.0367,
      "step": 157
    },
    {
      "clip_ratio/high_max": 0.0027256596731604077,
      "clip_ratio/high_mean": 0.0012023343224427663,
      "clip_ratio/low_mean": 0.0012399832849041559,
      "clip_ratio/low_min": 0.00010837760873982916,
      "clip_ratio/region_mean": 0.002442317629174795,
      "epoch": 0.014746629800092167,
      "grad_norm": 0.13183185458183289,
      "learning_rate": 1e-06,
      "loss": -0.0048,
      "step": 158
    },
    {
      "clip_ratio/high_max": 0.0027951238662353717,
      "clip_ratio/high_mean": 0.0013079852215014398,
      "clip_ratio/low_mean": 0.0011484756687423214,
      "clip_ratio/low_min": 7.220344923553057e-05,
      "clip_ratio/region_mean": 0.0024564609047956765,
      "epoch": 0.01483996290009275,
      "grad_norm": 0.1265721619129181,
      "learning_rate": 1e-06,
      "loss": -0.0289,
      "step": 159
    },
    {
      "clip_ratio/high_max": 0.002463600321789272,
      "clip_ratio/high_mean": 0.0010970926232403144,
      "clip_ratio/low_mean": 0.0012090505733794998,
      "clip_ratio/low_min": 0.00024864260376489256,
      "clip_ratio/region_mean": 0.0023061432148097083,
      "epoch": 0.014933296000093334,
      "grad_norm": 0.11900194734334946,
      "learning_rate": 1e-06,
      "loss": 0.0294,
      "step": 160
    },
    {
      "clip_ratio/high_max": 0.0030124678887659684,
      "clip_ratio/high_mean": 0.0012069379117747303,
      "clip_ratio/low_mean": 0.001343024010566296,
      "clip_ratio/low_min": 0.0002747145690591424,
      "clip_ratio/region_mean": 0.002549961893237196,
      "epoch": 0.015026629100093917,
      "grad_norm": 0.13085706532001495,
      "learning_rate": 1e-06,
      "loss": -0.0138,
      "step": 161
    },
    {
      "clip_ratio/high_max": 0.0029037394851911813,
      "clip_ratio/high_mean": 0.0012902680682600476,
      "clip_ratio/low_mean": 0.0014299489303084556,
      "clip_ratio/low_min": 0.0002330641882508644,
      "clip_ratio/region_mean": 0.0027202170094824396,
      "epoch": 0.015119962200094499,
      "grad_norm": 0.12124091386795044,
      "learning_rate": 1e-06,
      "loss": 0.0245,
      "step": 162
    },
    {
      "clip_ratio/high_max": 0.002570524586190004,
      "clip_ratio/high_mean": 0.0010408045891381335,
      "clip_ratio/low_mean": 0.0014011953135195654,
      "clip_ratio/low_min": 0.0001897479796753032,
      "clip_ratio/region_mean": 0.0024419998735538684,
      "epoch": 0.015213295300095082,
      "grad_norm": 0.11770489811897278,
      "learning_rate": 1e-06,
      "loss": 0.0537,
      "step": 163
    },
    {
      "clip_ratio/high_max": 0.002462083582940977,
      "clip_ratio/high_mean": 0.0012201415847812314,
      "clip_ratio/low_mean": 0.0013771850954071851,
      "clip_ratio/low_min": 0.0002169743620470399,
      "clip_ratio/region_mean": 0.002597326696559321,
      "epoch": 0.015306628400095666,
      "grad_norm": 0.12022513896226883,
      "learning_rate": 1e-06,
      "loss": 0.0005,
      "step": 164
    },
    {
      "clip_ratio/high_max": 0.0023391723589156754,
      "clip_ratio/high_mean": 0.0010765838596853428,
      "clip_ratio/low_mean": 0.0012353022757451981,
      "clip_ratio/low_min": 0.0002053519001492532,
      "clip_ratio/region_mean": 0.0023118862009141594,
      "epoch": 0.01539996150009625,
      "grad_norm": 0.12212057411670685,
      "learning_rate": 1e-06,
      "loss": 0.0259,
      "step": 165
    },
    {
      "clip_ratio/high_max": 0.002613412339997012,
      "clip_ratio/high_mean": 0.0011951558954024222,
      "clip_ratio/low_mean": 0.0012524801059043966,
      "clip_ratio/low_min": 9.570693509886041e-05,
      "clip_ratio/region_mean": 0.0024476360122207552,
      "epoch": 0.015493294600096833,
      "grad_norm": 0.11848278343677521,
      "learning_rate": 1e-06,
      "loss": -0.0015,
      "step": 166
    },
    {
      "clip_ratio/high_max": 0.0026641819858923554,
      "clip_ratio/high_mean": 0.0011898095290234778,
      "clip_ratio/low_mean": 0.0014335005325847305,
      "clip_ratio/low_min": 0.00018667688163986895,
      "clip_ratio/region_mean": 0.0026233100361423567,
      "epoch": 0.015586627700097416,
      "grad_norm": 0.11074207723140717,
      "learning_rate": 1e-06,
      "loss": 0.0358,
      "step": 167
    },
    {
      "clip_ratio/high_max": 0.002792465042148251,
      "clip_ratio/high_mean": 0.0012589432826644043,
      "clip_ratio/low_mean": 0.001214016450830968,
      "clip_ratio/low_min": 0.0002791898023133399,
      "clip_ratio/region_mean": 0.0024729597353143618,
      "epoch": 0.015679960800098,
      "grad_norm": 0.1204812079668045,
      "learning_rate": 1e-06,
      "loss": 0.0061,
      "step": 168
    },
    {
      "clip_ratio/high_max": 0.002655859261722071,
      "clip_ratio/high_mean": 0.0012477895252231974,
      "clip_ratio/low_mean": 0.0013207292249717284,
      "clip_ratio/low_min": 0.00018592403375805588,
      "clip_ratio/region_mean": 0.0025685187792987563,
      "epoch": 0.015773293900098583,
      "grad_norm": 0.127878338098526,
      "learning_rate": 1e-06,
      "loss": 0.0376,
      "step": 169
    },
    {
      "clip_ratio/high_max": 0.002435986214550212,
      "clip_ratio/high_mean": 0.0011270721333858091,
      "clip_ratio/low_mean": 0.001023003274895018,
      "clip_ratio/low_min": 8.427184548054356e-05,
      "clip_ratio/region_mean": 0.0021500754592125304,
      "epoch": 0.015866627000099165,
      "grad_norm": 0.11675351858139038,
      "learning_rate": 1e-06,
      "loss": -0.0311,
      "step": 170
    },
    {
      "clip_ratio/high_max": 0.0022785776636737864,
      "clip_ratio/high_mean": 0.001066446466211346,
      "clip_ratio/low_mean": 0.001355757503915811,
      "clip_ratio/low_min": 0.00021683182967535686,
      "clip_ratio/region_mean": 0.0024222039646701887,
      "epoch": 0.01595996010009975,
      "grad_norm": 0.12287482619285583,
      "learning_rate": 1e-06,
      "loss": 0.0524,
      "step": 171
    },
    {
      "clip_ratio/high_max": 0.002698982549190987,
      "clip_ratio/high_mean": 0.0011119126538687851,
      "clip_ratio/low_mean": 0.0011199601940461434,
      "clip_ratio/low_min": 6.396692151611205e-05,
      "clip_ratio/region_mean": 0.002231872880656738,
      "epoch": 0.016053293200100332,
      "grad_norm": 0.10930777341127396,
      "learning_rate": 1e-06,
      "loss": 0.0501,
      "step": 172
    },
    {
      "clip_ratio/high_max": 0.0029524349665734917,
      "clip_ratio/high_mean": 0.001257061452633934,
      "clip_ratio/low_mean": 0.0011075040310970508,
      "clip_ratio/low_min": 2.797046363411937e-05,
      "clip_ratio/region_mean": 0.002364565574680455,
      "epoch": 0.016146626300100917,
      "grad_norm": 0.12324044853448868,
      "learning_rate": 1e-06,
      "loss": -0.0223,
      "step": 173
    },
    {
      "clip_ratio/high_max": 0.0030870284972479567,
      "clip_ratio/high_mean": 0.0013111203588778153,
      "clip_ratio/low_mean": 0.0010724750227382174,
      "clip_ratio/low_min": 3.4246347240696196e-05,
      "clip_ratio/region_mean": 0.0023835953616071492,
      "epoch": 0.0162399594001015,
      "grad_norm": 0.11606115102767944,
      "learning_rate": 1e-06,
      "loss": -0.0054,
      "step": 174
    },
    {
      "clip_ratio/high_max": 0.002638303725689184,
      "clip_ratio/high_mean": 0.0011559507074707653,
      "clip_ratio/low_mean": 0.0013022475613979623,
      "clip_ratio/low_min": 0.00029158973120502196,
      "clip_ratio/region_mean": 0.002458198221575003,
      "epoch": 0.016333292500102084,
      "grad_norm": 0.1235213652253151,
      "learning_rate": 1e-06,
      "loss": 0.0264,
      "step": 175
    },
    {
      "clip_ratio/high_max": 0.0027016413878300227,
      "clip_ratio/high_mean": 0.0011622654237726238,
      "clip_ratio/low_mean": 0.0014873583386361133,
      "clip_ratio/low_min": 0.0002066812085104175,
      "clip_ratio/region_mean": 0.0026496236823732033,
      "epoch": 0.016426625600102666,
      "grad_norm": 0.1200484111905098,
      "learning_rate": 1e-06,
      "loss": 0.0522,
      "step": 176
    },
    {
      "clip_ratio/high_max": 0.002672854039701633,
      "clip_ratio/high_mean": 0.0012158513345639221,
      "clip_ratio/low_mean": 0.001363845191008295,
      "clip_ratio/low_min": 0.0003310314705231576,
      "clip_ratio/region_mean": 0.0025796965492190793,
      "epoch": 0.01651995870010325,
      "grad_norm": 0.11586089432239532,
      "learning_rate": 1e-06,
      "loss": 0.0199,
      "step": 177
    },
    {
      "clip_ratio/high_max": 0.0023066884532454424,
      "clip_ratio/high_mean": 0.001152584245573962,
      "clip_ratio/low_mean": 0.0015285496956494171,
      "clip_ratio/low_min": 0.00022844660452392418,
      "clip_ratio/region_mean": 0.002681133948499337,
      "epoch": 0.016613291800103833,
      "grad_norm": 0.11998248845338821,
      "learning_rate": 1e-06,
      "loss": 0.0494,
      "step": 178
    },
    {
      "clip_ratio/high_max": 0.0025488793035037816,
      "clip_ratio/high_mean": 0.001124043934396468,
      "clip_ratio/low_mean": 0.001438444851373788,
      "clip_ratio/low_min": 0.0002278391793879564,
      "clip_ratio/region_mean": 0.002562488843977917,
      "epoch": 0.016706624900104418,
      "grad_norm": 0.1215491071343422,
      "learning_rate": 1e-06,
      "loss": 0.0332,
      "step": 179
    },
    {
      "clip_ratio/high_max": 0.002647778470418416,
      "clip_ratio/high_mean": 0.00114215135545237,
      "clip_ratio/low_mean": 0.0013873987918486819,
      "clip_ratio/low_min": 0.00020759096332767513,
      "clip_ratio/region_mean": 0.0025295501691289246,
      "epoch": 0.016799958000105,
      "grad_norm": 0.13117018342018127,
      "learning_rate": 1e-06,
      "loss": 0.0383,
      "step": 180
    },
    {
      "clip_ratio/high_max": 0.0025569337012711912,
      "clip_ratio/high_mean": 0.0011582444039959228,
      "clip_ratio/low_mean": 0.0013539685933210421,
      "clip_ratio/low_min": 0.0002557817451815936,
      "clip_ratio/region_mean": 0.00251221295184223,
      "epoch": 0.016893291100105585,
      "grad_norm": 0.11314269155263901,
      "learning_rate": 1e-06,
      "loss": 0.0101,
      "step": 181
    },
    {
      "clip_ratio/high_max": 0.0026542178384261206,
      "clip_ratio/high_mean": 0.0011803568595496472,
      "clip_ratio/low_mean": 0.001240528654307127,
      "clip_ratio/low_min": 0.00016900484843063168,
      "clip_ratio/region_mean": 0.0024208855247707106,
      "epoch": 0.016986624200106167,
      "grad_norm": 0.11319568753242493,
      "learning_rate": 1e-06,
      "loss": -0.0093,
      "step": 182
    },
    {
      "clip_ratio/high_max": 0.0025909023970598355,
      "clip_ratio/high_mean": 0.0012374790785543155,
      "clip_ratio/low_mean": 0.001149815034295898,
      "clip_ratio/low_min": 9.820628747547744e-05,
      "clip_ratio/region_mean": 0.0023872940728324465,
      "epoch": 0.017079957300106748,
      "grad_norm": 0.1228477731347084,
      "learning_rate": 1e-06,
      "loss": -0.0159,
      "step": 183
    },
    {
      "clip_ratio/high_max": 0.0026282051803718787,
      "clip_ratio/high_mean": 0.001076097305485746,
      "clip_ratio/low_mean": 0.0013790780431008898,
      "clip_ratio/low_min": 0.00014604539319407195,
      "clip_ratio/region_mean": 0.0024551753886044025,
      "epoch": 0.017173290400107333,
      "grad_norm": 0.11773689836263657,
      "learning_rate": 1e-06,
      "loss": 0.0332,
      "step": 184
    },
    {
      "clip_ratio/high_max": 0.002487379388185218,
      "clip_ratio/high_mean": 0.0011027091277355794,
      "clip_ratio/low_mean": 0.0014333704857563134,
      "clip_ratio/low_min": 0.00023913930817798246,
      "clip_ratio/region_mean": 0.0025360796207678504,
      "epoch": 0.017266623500107915,
      "grad_norm": 0.12084262818098068,
      "learning_rate": 1e-06,
      "loss": 0.0375,
      "step": 185
    },
    {
      "clip_ratio/high_max": 0.0027148363151354715,
      "clip_ratio/high_mean": 0.0012640070017368998,
      "clip_ratio/low_mean": 0.0013348884640436154,
      "clip_ratio/low_min": 0.00010849974933080375,
      "clip_ratio/region_mean": 0.0025988954585045576,
      "epoch": 0.0173599566001085,
      "grad_norm": 0.12811660766601562,
      "learning_rate": 1e-06,
      "loss": 0.0047,
      "step": 186
    },
    {
      "clip_ratio/high_max": 0.0025311945064458996,
      "clip_ratio/high_mean": 0.0011070284162997268,
      "clip_ratio/low_mean": 0.0014850531370029785,
      "clip_ratio/low_min": 0.00022472956516139675,
      "clip_ratio/region_mean": 0.002592081575130578,
      "epoch": 0.017453289700109082,
      "grad_norm": 0.12231775373220444,
      "learning_rate": 1e-06,
      "loss": 0.0497,
      "step": 187
    },
    {
      "clip_ratio/high_max": 0.002489825477823615,
      "clip_ratio/high_mean": 0.001205796728754649,
      "clip_ratio/low_mean": 0.0014040306305105332,
      "clip_ratio/low_min": 0.0001636901706660865,
      "clip_ratio/region_mean": 0.002609827417472843,
      "epoch": 0.017546622800109667,
      "grad_norm": 0.13298480212688446,
      "learning_rate": 1e-06,
      "loss": 0.0322,
      "step": 188
    },
    {
      "clip_ratio/high_max": 0.0027122661122120917,
      "clip_ratio/high_mean": 0.0011768161966756452,
      "clip_ratio/low_mean": 0.001252476402441971,
      "clip_ratio/low_min": 0.000145522688399069,
      "clip_ratio/region_mean": 0.002429292602755595,
      "epoch": 0.01763995590011025,
      "grad_norm": 0.11797142028808594,
      "learning_rate": 1e-06,
      "loss": 0.0056,
      "step": 189
    },
    {
      "clip_ratio/high_max": 0.0025622150496928953,
      "clip_ratio/high_mean": 0.0011796395519922953,
      "clip_ratio/low_mean": 0.0011735809675883502,
      "clip_ratio/low_min": 9.31727090573986e-05,
      "clip_ratio/region_mean": 0.002353220494114794,
      "epoch": 0.017733289000110834,
      "grad_norm": 0.11661848425865173,
      "learning_rate": 1e-06,
      "loss": 0.0263,
      "step": 190
    },
    {
      "clip_ratio/high_max": 0.002745186437095981,
      "clip_ratio/high_mean": 0.0012337444786680862,
      "clip_ratio/low_mean": 0.0012545866557047702,
      "clip_ratio/low_min": 4.716317380371038e-05,
      "clip_ratio/region_mean": 0.0024883311125449836,
      "epoch": 0.017826622100111416,
      "grad_norm": 0.1126817911863327,
      "learning_rate": 1e-06,
      "loss": 0.0351,
      "step": 191
    },
    {
      "clip_ratio/high_max": 0.002563778281910345,
      "clip_ratio/high_mean": 0.0011736436263163341,
      "clip_ratio/low_mean": 0.001236382762726862,
      "clip_ratio/low_min": 0.00013949385265732417,
      "clip_ratio/region_mean": 0.0024100263763102703,
      "epoch": 0.017919955200112,
      "grad_norm": 0.10997709631919861,
      "learning_rate": 1e-06,
      "loss": -0.0091,
      "step": 192
    },
    {
      "clip_ratio/high_max": 0.0025424959167139605,
      "clip_ratio/high_mean": 0.0012055810184392612,
      "clip_ratio/low_mean": 0.0011300416990707163,
      "clip_ratio/low_min": 4.500285558606265e-05,
      "clip_ratio/region_mean": 0.0023356227538897656,
      "epoch": 0.018013288300112583,
      "grad_norm": 0.12096629291772842,
      "learning_rate": 1e-06,
      "loss": 0.0247,
      "step": 193
    },
    {
      "clip_ratio/high_max": 0.0026967603407683782,
      "clip_ratio/high_mean": 0.0012921491615998093,
      "clip_ratio/low_mean": 0.001306394240600639,
      "clip_ratio/low_min": 0.0003159637963108253,
      "clip_ratio/region_mean": 0.0025985434112953953,
      "epoch": 0.018106621400113165,
      "grad_norm": 0.11602344363927841,
      "learning_rate": 1e-06,
      "loss": -0.0158,
      "step": 194
    },
    {
      "clip_ratio/high_max": 0.002505861884856131,
      "clip_ratio/high_mean": 0.0011906351828656625,
      "clip_ratio/low_mean": 0.0013018415120313875,
      "clip_ratio/low_min": 0.00014446664863498881,
      "clip_ratio/region_mean": 0.0024924766912590712,
      "epoch": 0.01819995450011375,
      "grad_norm": 0.10961132496595383,
      "learning_rate": 1e-06,
      "loss": 0.021,
      "step": 195
    },
    {
      "clip_ratio/high_max": 0.0029728039080509916,
      "clip_ratio/high_mean": 0.0013984148354211356,
      "clip_ratio/low_mean": 0.001233438993949676,
      "clip_ratio/low_min": 0.00020975907318643294,
      "clip_ratio/region_mean": 0.0026318538730265573,
      "epoch": 0.01829328760011433,
      "grad_norm": 0.12933892011642456,
      "learning_rate": 1e-06,
      "loss": -0.0077,
      "step": 196
    },
    {
      "clip_ratio/high_max": 0.002315868485311512,
      "clip_ratio/high_mean": 0.0010439206307637505,
      "clip_ratio/low_mean": 0.0012818770665035117,
      "clip_ratio/low_min": 0.00022156216709845467,
      "clip_ratio/region_mean": 0.0023257977445609868,
      "epoch": 0.018386620700114917,
      "grad_norm": 0.11547909677028656,
      "learning_rate": 1e-06,
      "loss": 0.0783,
      "step": 197
    },
    {
      "clip_ratio/high_max": 0.0030729667996638454,
      "clip_ratio/high_mean": 0.0012934623337059747,
      "clip_ratio/low_mean": 0.0010308970995538402,
      "clip_ratio/low_min": 7.482250111934263e-05,
      "clip_ratio/region_mean": 0.002324359411431942,
      "epoch": 0.0184799538001155,
      "grad_norm": 0.10921128839254379,
      "learning_rate": 1e-06,
      "loss": -0.0103,
      "step": 198
    },
    {
      "clip_ratio/high_max": 0.0027546002602321096,
      "clip_ratio/high_mean": 0.0011375779504305683,
      "clip_ratio/low_mean": 0.0013485822637449019,
      "clip_ratio/low_min": 0.00010711663435358787,
      "clip_ratio/region_mean": 0.002486160199623555,
      "epoch": 0.018573286900116084,
      "grad_norm": 0.10429203510284424,
      "learning_rate": 1e-06,
      "loss": 0.039,
      "step": 199
    },
    {
      "clip_ratio/high_max": 0.0029651976146851666,
      "clip_ratio/high_mean": 0.001185284218081506,
      "clip_ratio/low_mean": 0.001405682025506394,
      "clip_ratio/low_min": 0.000203739423341176,
      "clip_ratio/region_mean": 0.0025909661926561967,
      "epoch": 0.018666620000116665,
      "grad_norm": 0.1098906546831131,
      "learning_rate": 1e-06,
      "loss": 0.0095,
      "step": 200
    },
    {
      "clip_ratio/high_max": 0.002753616361587774,
      "clip_ratio/high_mean": 0.0012288225007068831,
      "clip_ratio/low_mean": 0.0014717400299559813,
      "clip_ratio/low_min": 0.0002930818809545599,
      "clip_ratio/region_mean": 0.0027005625452147797,
      "epoch": 0.01875995310011725,
      "grad_norm": 0.11615803837776184,
      "learning_rate": 1e-06,
      "loss": 0.0524,
      "step": 201
    },
    {
      "clip_ratio/high_max": 0.002436910195683595,
      "clip_ratio/high_mean": 0.0012218611664138734,
      "clip_ratio/low_mean": 0.0013838372942700516,
      "clip_ratio/low_min": 0.0001856030121416552,
      "clip_ratio/region_mean": 0.00260569853708148,
      "epoch": 0.018853286200117832,
      "grad_norm": 0.11929242312908173,
      "learning_rate": 1e-06,
      "loss": 0.02,
      "step": 202
    },
    {
      "clip_ratio/high_max": 0.002949557761894539,
      "clip_ratio/high_mean": 0.0013158322180970572,
      "clip_ratio/low_mean": 0.0012549054190458264,
      "clip_ratio/low_min": 0.000141459025144286,
      "clip_ratio/region_mean": 0.0025707376626087353,
      "epoch": 0.018946619300118418,
      "grad_norm": 0.11886332929134369,
      "learning_rate": 1e-06,
      "loss": 0.0007,
      "step": 203
    },
    {
      "clip_ratio/high_max": 0.0025808335703914054,
      "clip_ratio/high_mean": 0.0011586524269660003,
      "clip_ratio/low_mean": 0.0013152622996130958,
      "clip_ratio/low_min": 0.0001259202563232975,
      "clip_ratio/region_mean": 0.0024739147775107995,
      "epoch": 0.019039952400119,
      "grad_norm": 0.1246223896741867,
      "learning_rate": 1e-06,
      "loss": 0.0322,
      "step": 204
    },
    {
      "clip_ratio/high_max": 0.0026471492237760685,
      "clip_ratio/high_mean": 0.0011050266730308067,
      "clip_ratio/low_mean": 0.0010999647311109584,
      "clip_ratio/low_min": 0.00021924682278040564,
      "clip_ratio/region_mean": 0.0022049914332455955,
      "epoch": 0.019133285500119585,
      "grad_norm": 0.10954298079013824,
      "learning_rate": 1e-06,
      "loss": 0.0226,
      "step": 205
    },
    {
      "clip_ratio/high_max": 0.002576317318016663,
      "clip_ratio/high_mean": 0.001156758709839778,
      "clip_ratio/low_mean": 0.0013909499139117543,
      "clip_ratio/low_min": 0.00019147875445924,
      "clip_ratio/region_mean": 0.0025477086019236594,
      "epoch": 0.019226618600120166,
      "grad_norm": 0.1190459206700325,
      "learning_rate": 1e-06,
      "loss": 0.0545,
      "step": 206
    },
    {
      "clip_ratio/high_max": 0.0027874516090378165,
      "clip_ratio/high_mean": 0.0012371846933092456,
      "clip_ratio/low_mean": 0.001243129518115893,
      "clip_ratio/low_min": 0.0002374109571974259,
      "clip_ratio/region_mean": 0.002480314185959287,
      "epoch": 0.019319951700120748,
      "grad_norm": 0.11833468079566956,
      "learning_rate": 1e-06,
      "loss": 0.0456,
      "step": 207
    },
    {
      "clip_ratio/high_max": 0.0027853806896018796,
      "clip_ratio/high_mean": 0.0012385505651764106,
      "clip_ratio/low_mean": 0.001268453099328326,
      "clip_ratio/low_min": 0.00011179314060427714,
      "clip_ratio/region_mean": 0.002507003620848991,
      "epoch": 0.019413284800121333,
      "grad_norm": 0.11821004748344421,
      "learning_rate": 1e-06,
      "loss": 0.0081,
      "step": 208
    },
    {
      "clip_ratio/high_max": 0.0024134113918989897,
      "clip_ratio/high_mean": 0.0010693396070564631,
      "clip_ratio/low_mean": 0.001365362993965391,
      "clip_ratio/low_min": 0.00020577540999511257,
      "clip_ratio/region_mean": 0.002434702590107918,
      "epoch": 0.019506617900121915,
      "grad_norm": 0.10630277544260025,
      "learning_rate": 1e-06,
      "loss": -0.0213,
      "step": 209
    },
    {
      "clip_ratio/high_max": 0.0024340629170183092,
      "clip_ratio/high_mean": 0.0011245457098993938,
      "clip_ratio/low_mean": 0.001490510501753306,
      "clip_ratio/low_min": 0.00010901557652687188,
      "clip_ratio/region_mean": 0.002615056175272912,
      "epoch": 0.0195999510001225,
      "grad_norm": 0.13615168631076813,
      "learning_rate": 1e-06,
      "loss": 0.0385,
      "step": 210
    },
    {
      "clip_ratio/high_max": 0.00241769700369332,
      "clip_ratio/high_mean": 0.0011127788384328596,
      "clip_ratio/low_mean": 0.001352664185105823,
      "clip_ratio/low_min": 0.00019827650248771533,
      "clip_ratio/region_mean": 0.002465442979882937,
      "epoch": 0.019693284100123082,
      "grad_norm": 0.12077221274375916,
      "learning_rate": 1e-06,
      "loss": 0.0024,
      "step": 211
    },
    {
      "clip_ratio/high_max": 0.002666712556674611,
      "clip_ratio/high_mean": 0.001316230835072929,
      "clip_ratio/low_mean": 0.0013837130391038954,
      "clip_ratio/low_min": 0.0001587056594871683,
      "clip_ratio/region_mean": 0.002699943899642676,
      "epoch": 0.019786617200123667,
      "grad_norm": 0.11692502349615097,
      "learning_rate": 1e-06,
      "loss": -0.0286,
      "step": 212
    },
    {
      "clip_ratio/high_max": 0.002690632412850391,
      "clip_ratio/high_mean": 0.0013632758236781228,
      "clip_ratio/low_mean": 0.0015113556801225059,
      "clip_ratio/low_min": 0.00016518930533493403,
      "clip_ratio/region_mean": 0.0028746315656462684,
      "epoch": 0.01987995030012425,
      "grad_norm": 0.11587584018707275,
      "learning_rate": 1e-06,
      "loss": -0.0292,
      "step": 213
    },
    {
      "clip_ratio/high_max": 0.0028760911300196312,
      "clip_ratio/high_mean": 0.0012737659344566055,
      "clip_ratio/low_mean": 0.001509167817857815,
      "clip_ratio/low_min": 0.0002808178414852591,
      "clip_ratio/region_mean": 0.0027829337122966535,
      "epoch": 0.019973283400124834,
      "grad_norm": 0.11286624521017075,
      "learning_rate": 1e-06,
      "loss": -0.0086,
      "step": 214
    },
    {
      "clip_ratio/high_max": 0.002930935617769137,
      "clip_ratio/high_mean": 0.0012926538583997171,
      "clip_ratio/low_mean": 0.0015894604512141086,
      "clip_ratio/low_min": 0.0002447009601382888,
      "clip_ratio/region_mean": 0.002882114305975847,
      "epoch": 0.020066616500125416,
      "grad_norm": 0.11991050839424133,
      "learning_rate": 1e-06,
      "loss": 0.0149,
      "step": 215
    },
    {
      "clip_ratio/high_max": 0.0027271677245153114,
      "clip_ratio/high_mean": 0.0012860386668762658,
      "clip_ratio/low_mean": 0.0014214065304258838,
      "clip_ratio/low_min": 9.606748517398955e-05,
      "clip_ratio/region_mean": 0.0027074452373199165,
      "epoch": 0.020159949600126,
      "grad_norm": 0.1182783767580986,
      "learning_rate": 1e-06,
      "loss": 0.0202,
      "step": 216
    },
    {
      "clip_ratio/high_max": 0.0024879729317035526,
      "clip_ratio/high_mean": 0.0011563311818463262,
      "clip_ratio/low_mean": 0.0013710670536966063,
      "clip_ratio/low_min": 0.0001953144837898435,
      "clip_ratio/region_mean": 0.0025273981591453776,
      "epoch": 0.020253282700126583,
      "grad_norm": 0.11814951151609421,
      "learning_rate": 1e-06,
      "loss": 0.043,
      "step": 217
    },
    {
      "clip_ratio/high_max": 0.002947408640466165,
      "clip_ratio/high_mean": 0.0013484851369867101,
      "clip_ratio/low_mean": 0.0012738424993585795,
      "clip_ratio/low_min": 0.00017427248803869588,
      "clip_ratio/region_mean": 0.0026223276217933744,
      "epoch": 0.020346615800127168,
      "grad_norm": 0.12284554541110992,
      "learning_rate": 1e-06,
      "loss": 0.0069,
      "step": 218
    },
    {
      "clip_ratio/high_max": 0.0027303431561449543,
      "clip_ratio/high_mean": 0.0012052442434651311,
      "clip_ratio/low_mean": 0.001110031284042634,
      "clip_ratio/low_min": 0.00011965695830440382,
      "clip_ratio/region_mean": 0.0023152755384217016,
      "epoch": 0.02043994890012775,
      "grad_norm": 0.1070648580789566,
      "learning_rate": 1e-06,
      "loss": 0.008,
      "step": 219
    },
    {
      "clip_ratio/high_max": 0.003096452579484321,
      "clip_ratio/high_mean": 0.0013992584827065002,
      "clip_ratio/low_mean": 0.0012040935798722785,
      "clip_ratio/low_min": 0.00016171355036931345,
      "clip_ratio/region_mean": 0.0026033521280623972,
      "epoch": 0.02053328200012833,
      "grad_norm": 0.1266152560710907,
      "learning_rate": 1e-06,
      "loss": 0.0043,
      "step": 220
    },
    {
      "clip_ratio/high_max": 0.0025792756059672683,
      "clip_ratio/high_mean": 0.0012948244439030532,
      "clip_ratio/low_mean": 0.0014399615320144221,
      "clip_ratio/low_min": 0.00016513191440026276,
      "clip_ratio/region_mean": 0.0027347859868314117,
      "epoch": 0.020626615100128916,
      "grad_norm": 0.12148232758045197,
      "learning_rate": 1e-06,
      "loss": 0.0083,
      "step": 221
    },
    {
      "clip_ratio/high_max": 0.0025228388549294323,
      "clip_ratio/high_mean": 0.0010800192994793179,
      "clip_ratio/low_mean": 0.001403281421517022,
      "clip_ratio/low_min": 8.814985812932719e-05,
      "clip_ratio/region_mean": 0.002483300704625435,
      "epoch": 0.020719948200129498,
      "grad_norm": 0.11848271638154984,
      "learning_rate": 1e-06,
      "loss": 0.0395,
      "step": 222
    },
    {
      "clip_ratio/high_max": 0.0028991815488552675,
      "clip_ratio/high_mean": 0.0012010799437121022,
      "clip_ratio/low_mean": 0.0013955115791759454,
      "clip_ratio/low_min": 0.00021726133763877442,
      "clip_ratio/region_mean": 0.002596591497422196,
      "epoch": 0.020813281300130083,
      "grad_norm": 0.11115968972444534,
      "learning_rate": 1e-06,
      "loss": 0.0468,
      "step": 223
    },
    {
      "clip_ratio/high_max": 0.0026336591399740428,
      "clip_ratio/high_mean": 0.001224983723659534,
      "clip_ratio/low_mean": 0.0014509059074043762,
      "clip_ratio/low_min": 0.00024209196999436244,
      "clip_ratio/region_mean": 0.0026758896274259314,
      "epoch": 0.020906614400130665,
      "grad_norm": 0.12176219373941422,
      "learning_rate": 1e-06,
      "loss": 0.0215,
      "step": 224
    },
    {
      "clip_ratio/high_max": 0.002578550651378464,
      "clip_ratio/high_mean": 0.0011918759628315456,
      "clip_ratio/low_mean": 0.0014368755764735397,
      "clip_ratio/low_min": 0.0002343893993383972,
      "clip_ratio/region_mean": 0.0026287515574949794,
      "epoch": 0.02099994750013125,
      "grad_norm": 0.11891946196556091,
      "learning_rate": 1e-06,
      "loss": 0.0114,
      "step": 225
    },
    {
      "clip_ratio/high_max": 0.0027156503419973888,
      "clip_ratio/high_mean": 0.0011570048882276751,
      "clip_ratio/low_mean": 0.0015513499492953997,
      "clip_ratio/low_min": 0.0001733959979901556,
      "clip_ratio/region_mean": 0.002708354892092757,
      "epoch": 0.021093280600131832,
      "grad_norm": 0.1076967865228653,
      "learning_rate": 1e-06,
      "loss": 0.0255,
      "step": 226
    },
    {
      "clip_ratio/high_max": 0.0027221765121794306,
      "clip_ratio/high_mean": 0.0012483207101467997,
      "clip_ratio/low_mean": 0.0014540683041559532,
      "clip_ratio/low_min": 0.00020745715028169798,
      "clip_ratio/region_mean": 0.00270238899247488,
      "epoch": 0.021186613700132417,
      "grad_norm": 0.1128716692328453,
      "learning_rate": 1e-06,
      "loss": -0.0167,
      "step": 227
    },
    {
      "clip_ratio/high_max": 0.002753770248091314,
      "clip_ratio/high_mean": 0.001242840640770737,
      "clip_ratio/low_mean": 0.0013551625634136144,
      "clip_ratio/low_min": 0.00023705119474470848,
      "clip_ratio/region_mean": 0.0025980032587540336,
      "epoch": 0.021279946800133,
      "grad_norm": 0.11067776381969452,
      "learning_rate": 1e-06,
      "loss": 0.0408,
      "step": 228
    },
    {
      "clip_ratio/high_max": 0.0028592185844900087,
      "clip_ratio/high_mean": 0.001326610377873294,
      "clip_ratio/low_mean": 0.001492405961471377,
      "clip_ratio/low_min": 0.0001630086717341328,
      "clip_ratio/region_mean": 0.0028190163720864803,
      "epoch": 0.021373279900133584,
      "grad_norm": 0.12158869206905365,
      "learning_rate": 1e-06,
      "loss": 0.0098,
      "step": 229
    },
    {
      "clip_ratio/high_max": 0.002937079145340249,
      "clip_ratio/high_mean": 0.0012737819306494202,
      "clip_ratio/low_mean": 0.0014161024591885507,
      "clip_ratio/low_min": 0.0002785625792967039,
      "clip_ratio/region_mean": 0.0026898844225797802,
      "epoch": 0.021466613000134166,
      "grad_norm": 0.12741751968860626,
      "learning_rate": 1e-06,
      "loss": 0.0316,
      "step": 230
    },
    {
      "clip_ratio/high_max": 0.0031803894307813607,
      "clip_ratio/high_mean": 0.0014429756774916314,
      "clip_ratio/low_mean": 0.0012438033445505425,
      "clip_ratio/low_min": 0.00024903894427552586,
      "clip_ratio/region_mean": 0.002686778978386428,
      "epoch": 0.02155994610013475,
      "grad_norm": 0.1174270361661911,
      "learning_rate": 1e-06,
      "loss": 0.0148,
      "step": 231
    },
    {
      "clip_ratio/high_max": 0.002933542364189634,
      "clip_ratio/high_mean": 0.0012495396276790416,
      "clip_ratio/low_mean": 0.0014253993394959252,
      "clip_ratio/low_min": 0.0002664927314981469,
      "clip_ratio/region_mean": 0.002674939052667469,
      "epoch": 0.021653279200135333,
      "grad_norm": 0.11752340197563171,
      "learning_rate": 1e-06,
      "loss": 0.0594,
      "step": 232
    },
    {
      "clip_ratio/high_max": 0.0029448304485413246,
      "clip_ratio/high_mean": 0.0013079808268230408,
      "clip_ratio/low_mean": 0.0013072635119897313,
      "clip_ratio/low_min": 0.00020943713843735168,
      "clip_ratio/region_mean": 0.002615244382468518,
      "epoch": 0.021746612300135915,
      "grad_norm": 0.11533144861459732,
      "learning_rate": 1e-06,
      "loss": 0.0221,
      "step": 233
    },
    {
      "clip_ratio/high_max": 0.002893707096518483,
      "clip_ratio/high_mean": 0.0012507598985393997,
      "clip_ratio/low_mean": 0.00145119241278735,
      "clip_ratio/low_min": 0.000206605081075395,
      "clip_ratio/region_mean": 0.0027019523113267496,
      "epoch": 0.0218399454001365,
      "grad_norm": 0.1245647668838501,
      "learning_rate": 1e-06,
      "loss": 0.0099,
      "step": 234
    },
    {
      "clip_ratio/high_max": 0.002663630344613921,
      "clip_ratio/high_mean": 0.0012397000027704053,
      "clip_ratio/low_mean": 0.0014314172694867011,
      "clip_ratio/low_min": 0.00011440727666922612,
      "clip_ratio/region_mean": 0.0026711172176874243,
      "epoch": 0.02193327850013708,
      "grad_norm": 0.11414322257041931,
      "learning_rate": 1e-06,
      "loss": 0.0126,
      "step": 235
    },
    {
      "clip_ratio/high_max": 0.0029554450447903946,
      "clip_ratio/high_mean": 0.001208468915137928,
      "clip_ratio/low_mean": 0.0013771112535323482,
      "clip_ratio/low_min": 0.0002789856989693362,
      "clip_ratio/region_mean": 0.002585580099548679,
      "epoch": 0.022026611600137667,
      "grad_norm": 0.11437011510133743,
      "learning_rate": 1e-06,
      "loss": -0.0145,
      "step": 236
    },
    {
      "clip_ratio/high_max": 0.0026809996415977366,
      "clip_ratio/high_mean": 0.0012158017743786331,
      "clip_ratio/low_mean": 0.0015558118466287851,
      "clip_ratio/low_min": 0.00024096857305266894,
      "clip_ratio/region_mean": 0.002771613624645397,
      "epoch": 0.02211994470013825,
      "grad_norm": 0.11856529116630554,
      "learning_rate": 1e-06,
      "loss": 0.0067,
      "step": 237
    },
    {
      "clip_ratio/high_max": 0.0026812001124199014,
      "clip_ratio/high_mean": 0.0010683003083613585,
      "clip_ratio/low_mean": 0.0016891086670511868,
      "clip_ratio/low_min": 0.00021632341304211877,
      "clip_ratio/region_mean": 0.0027574089472182095,
      "epoch": 0.022213277800138834,
      "grad_norm": 0.11973568797111511,
      "learning_rate": 1e-06,
      "loss": 0.0892,
      "step": 238
    },
    {
      "clip_ratio/high_max": 0.0029301593312993646,
      "clip_ratio/high_mean": 0.001317656358878594,
      "clip_ratio/low_mean": 0.0013663338759215549,
      "clip_ratio/low_min": 8.015544881345704e-05,
      "clip_ratio/region_mean": 0.0026839902566280216,
      "epoch": 0.022306610900139415,
      "grad_norm": 0.11149156093597412,
      "learning_rate": 1e-06,
      "loss": -0.0059,
      "step": 239
    },
    {
      "clip_ratio/high_max": 0.002814397055772133,
      "clip_ratio/high_mean": 0.0012506991661211941,
      "clip_ratio/low_mean": 0.001508244858996477,
      "clip_ratio/low_min": 0.00015515810628130566,
      "clip_ratio/region_mean": 0.0027589439632720314,
      "epoch": 0.02239994400014,
      "grad_norm": 0.12311536073684692,
      "learning_rate": 1e-06,
      "loss": 0.0207,
      "step": 240
    },
    {
      "clip_ratio/high_max": 0.003241408929170575,
      "clip_ratio/high_mean": 0.0013674206020368729,
      "clip_ratio/low_mean": 0.0011476982654130552,
      "clip_ratio/low_min": 0.00011804434052464785,
      "clip_ratio/region_mean": 0.002515118867449928,
      "epoch": 0.022493277100140582,
      "grad_norm": 0.12148340046405792,
      "learning_rate": 1e-06,
      "loss": -0.0134,
      "step": 241
    },
    {
      "clip_ratio/high_max": 0.0028867476430605166,
      "clip_ratio/high_mean": 0.0012265812802070286,
      "clip_ratio/low_mean": 0.0014747263558092527,
      "clip_ratio/low_min": 0.00014939865286578424,
      "clip_ratio/region_mean": 0.0027013076469302177,
      "epoch": 0.022586610200141168,
      "grad_norm": 0.11273916065692902,
      "learning_rate": 1e-06,
      "loss": 0.0243,
      "step": 242
    },
    {
      "clip_ratio/high_max": 0.002602900640340522,
      "clip_ratio/high_mean": 0.0012631772260647267,
      "clip_ratio/low_mean": 0.0013574150907516014,
      "clip_ratio/low_min": 0.00017087049309338909,
      "clip_ratio/region_mean": 0.002620592335006222,
      "epoch": 0.02267994330014175,
      "grad_norm": 0.11515071243047714,
      "learning_rate": 1e-06,
      "loss": 0.0078,
      "step": 243
    },
    {
      "clip_ratio/high_max": 0.0030365166894625872,
      "clip_ratio/high_mean": 0.0013074428352410905,
      "clip_ratio/low_mean": 0.0013274852317408659,
      "clip_ratio/low_min": 0.00014806052149651805,
      "clip_ratio/region_mean": 0.002634928052430041,
      "epoch": 0.022773276400142334,
      "grad_norm": 0.11722594499588013,
      "learning_rate": 1e-06,
      "loss": 0.0074,
      "step": 244
    },
    {
      "clip_ratio/high_max": 0.002536213396524545,
      "clip_ratio/high_mean": 0.0011760884008253925,
      "clip_ratio/low_mean": 0.0015724250297353137,
      "clip_ratio/low_min": 0.00025744376307557104,
      "clip_ratio/region_mean": 0.0027485134196467698,
      "epoch": 0.022866609500142916,
      "grad_norm": 0.1268276870250702,
      "learning_rate": 1e-06,
      "loss": 0.083,
      "step": 245
    },
    {
      "clip_ratio/high_max": 0.002958224016765598,
      "clip_ratio/high_mean": 0.001265724618860986,
      "clip_ratio/low_mean": 0.0014083201058383565,
      "clip_ratio/low_min": 0.00018465370885678567,
      "clip_ratio/region_mean": 0.0026740447647171095,
      "epoch": 0.022959942600143498,
      "grad_norm": 0.12519189715385437,
      "learning_rate": 1e-06,
      "loss": 0.0354,
      "step": 246
    },
    {
      "clip_ratio/high_max": 0.002893728429626208,
      "clip_ratio/high_mean": 0.0013277997677505482,
      "clip_ratio/low_mean": 0.0014527560051647015,
      "clip_ratio/low_min": 0.00021506683242478175,
      "clip_ratio/region_mean": 0.0027805557183455676,
      "epoch": 0.023053275700144083,
      "grad_norm": 0.1117105707526207,
      "learning_rate": 1e-06,
      "loss": 0.0108,
      "step": 247
    },
    {
      "clip_ratio/high_max": 0.002741170108492952,
      "clip_ratio/high_mean": 0.0013270340459712315,
      "clip_ratio/low_mean": 0.0013807948562316597,
      "clip_ratio/low_min": 0.00013223127461969852,
      "clip_ratio/region_mean": 0.0027078288912889548,
      "epoch": 0.023146608800144665,
      "grad_norm": 0.1205824613571167,
      "learning_rate": 1e-06,
      "loss": -0.0088,
      "step": 248
    },
    {
      "clip_ratio/high_max": 0.0032962685509119183,
      "clip_ratio/high_mean": 0.0013764514042122755,
      "clip_ratio/low_mean": 0.0015203620096144732,
      "clip_ratio/low_min": 0.00027015406158170663,
      "clip_ratio/region_mean": 0.0028968133847229183,
      "epoch": 0.02323994190014525,
      "grad_norm": 0.12086623162031174,
      "learning_rate": 1e-06,
      "loss": 0.0223,
      "step": 249
    },
    {
      "clip_ratio/high_max": 0.002714697089686524,
      "clip_ratio/high_mean": 0.0011880185520567466,
      "clip_ratio/low_mean": 0.0014526119703077711,
      "clip_ratio/low_min": 0.0002161014035664266,
      "clip_ratio/region_mean": 0.002640630496898666,
      "epoch": 0.023333275000145832,
      "grad_norm": 0.10611660033464432,
      "learning_rate": 1e-06,
      "loss": 0.0299,
      "step": 250
    },
    {
      "clip_ratio/high_max": 0.0026539059908827767,
      "clip_ratio/high_mean": 0.0012327325639489572,
      "clip_ratio/low_mean": 0.0014886019998812117,
      "clip_ratio/low_min": 0.00017664152255747467,
      "clip_ratio/region_mean": 0.0027213345747441053,
      "epoch": 0.023426608100146417,
      "grad_norm": 0.10782354325056076,
      "learning_rate": 1e-06,
      "loss": 0.0537,
      "step": 251
    },
    {
      "clip_ratio/high_max": 0.0031486807274632156,
      "clip_ratio/high_mean": 0.001254881797649432,
      "clip_ratio/low_mean": 0.0014445605629589409,
      "clip_ratio/low_min": 0.00010275974727846915,
      "clip_ratio/region_mean": 0.0026994424042641185,
      "epoch": 0.023519941200147,
      "grad_norm": 0.1270337551832199,
      "learning_rate": 1e-06,
      "loss": -0.0053,
      "step": 252
    },
    {
      "clip_ratio/high_max": 0.002889482297177892,
      "clip_ratio/high_mean": 0.0012911734738736413,
      "clip_ratio/low_mean": 0.0015569323622912634,
      "clip_ratio/low_min": 0.00020511935053946218,
      "clip_ratio/region_mean": 0.0028481058252509683,
      "epoch": 0.023613274300147584,
      "grad_norm": 0.11966459453105927,
      "learning_rate": 1e-06,
      "loss": 0.0178,
      "step": 253
    },
    {
      "clip_ratio/high_max": 0.002719169919146225,
      "clip_ratio/high_mean": 0.0013231332013674546,
      "clip_ratio/low_mean": 0.0017619675782043487,
      "clip_ratio/low_min": 0.00038492104522447335,
      "clip_ratio/region_mean": 0.0030851007904857397,
      "epoch": 0.023706607400148166,
      "grad_norm": 0.13348238170146942,
      "learning_rate": 1e-06,
      "loss": 0.0227,
      "step": 254
    },
    {
      "clip_ratio/high_max": 0.0027464530139695853,
      "clip_ratio/high_mean": 0.0012679077153734397,
      "clip_ratio/low_mean": 0.0014296650879259687,
      "clip_ratio/low_min": 0.00025208152965205954,
      "clip_ratio/region_mean": 0.0026975728251272812,
      "epoch": 0.02379994050014875,
      "grad_norm": 0.11844424158334732,
      "learning_rate": 1e-06,
      "loss": 0.0321,
      "step": 255
    },
    {
      "clip_ratio/high_max": 0.002598723782284651,
      "clip_ratio/high_mean": 0.001076618198567303,
      "clip_ratio/low_mean": 0.0015559640887659043,
      "clip_ratio/low_min": 0.00040255888870888157,
      "clip_ratio/region_mean": 0.0026325823055231012,
      "epoch": 0.023893273600149333,
      "grad_norm": 0.1172008290886879,
      "learning_rate": 1e-06,
      "loss": 0.0971,
      "step": 256
    },
    {
      "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": 0.014020647321428603,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4095.0,
      "completions/mean_length": 606.3728637695312,
      "completions/mean_terminated_length": 556.7503051757812,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.023986606700149918,
      "grad_norm": 0.13878346979618073,
      "learning_rate": 1e-06,
      "loss": 0.0479,
      "num_tokens": 242343459.0,
      "reward": 0.5473458766937256,
      "reward_std": 0.22819411754608154,
      "rewards/simpleverify_reward/mean": 0.5473458170890808,
      "rewards/simpleverify_reward/std": 0.4977554976940155,
      "step": 257
    },
    {
      "clip_ratio/high_max": 0.002318706101505086,
      "clip_ratio/high_mean": 0.0009321549168817,
      "clip_ratio/low_mean": 0.0006447340729209827,
      "clip_ratio/low_min": 5.173052704776637e-05,
      "clip_ratio/region_mean": 0.0015768890079925768,
      "epoch": 0.0240799398001505,
      "grad_norm": 0.13692863285541534,
      "learning_rate": 1e-06,
      "loss": 0.0519,
      "step": 258
    },
    {
      "clip_ratio/high_max": 0.0022346855184878223,
      "clip_ratio/high_mean": 0.001037432604789501,
      "clip_ratio/low_mean": 0.0005807069028378464,
      "clip_ratio/low_min": 3.277349878771929e-05,
      "clip_ratio/region_mean": 0.0016181395476451144,
      "epoch": 0.02417327290015108,
      "grad_norm": 0.1287120282649994,
      "learning_rate": 1e-06,
      "loss": -0.0069,
      "step": 259
    },
    {
      "clip_ratio/high_max": 0.0019780331131187268,
      "clip_ratio/high_mean": 0.0007728182972641662,
      "clip_ratio/low_mean": 0.0006453432533817249,
      "clip_ratio/low_min": 3.711226236191578e-05,
      "clip_ratio/region_mean": 0.001418161547917407,
      "epoch": 0.024266606000151666,
      "grad_norm": 0.1013762354850769,
      "learning_rate": 1e-06,
      "loss": 0.0459,
      "step": 260
    },
    {
      "clip_ratio/high_max": 0.002177521473640809,
      "clip_ratio/high_mean": 0.000954049093706999,
      "clip_ratio/low_mean": 0.0006498518005173537,
      "clip_ratio/low_min": 5.5541762776556425e-05,
      "clip_ratio/region_mean": 0.0016039009096857626,
      "epoch": 0.024359939100152248,
      "grad_norm": 0.11394771188497543,
      "learning_rate": 1e-06,
      "loss": -0.032,
      "step": 261
    },
    {
      "clip_ratio/high_max": 0.002149220817955211,
      "clip_ratio/high_mean": 0.0009187996620312333,
      "clip_ratio/low_mean": 0.0008728065549803432,
      "clip_ratio/low_min": 0.00010882023434533039,
      "clip_ratio/region_mean": 0.001791606227925513,
      "epoch": 0.024453272200152833,
      "grad_norm": 0.12061510980129242,
      "learning_rate": 1e-06,
      "loss": 0.046,
      "step": 262
    },
    {
      "clip_ratio/high_max": 0.00240359095914755,
      "clip_ratio/high_mean": 0.0010290763493685517,
      "clip_ratio/low_mean": 0.0010250703071505995,
      "clip_ratio/low_min": 0.000153132894411101,
      "clip_ratio/region_mean": 0.0020541466001304798,
      "epoch": 0.024546605300153415,
      "grad_norm": 0.11530864983797073,
      "learning_rate": 1e-06,
      "loss": 0.0318,
      "step": 263
    },
    {
      "clip_ratio/high_max": 0.002490508930350188,
      "clip_ratio/high_mean": 0.0011761773894249927,
      "clip_ratio/low_mean": 0.0009135854343185201,
      "clip_ratio/low_min": 0.00011792420264100656,
      "clip_ratio/region_mean": 0.002089762856485322,
      "epoch": 0.024639938400154,
      "grad_norm": 0.12418489903211594,
      "learning_rate": 1e-06,
      "loss": 0.0057,
      "step": 264
    },
    {
      "clip_ratio/high_max": 0.0025673400232335553,
      "clip_ratio/high_mean": 0.001129146739913267,
      "clip_ratio/low_mean": 0.001020339612296084,
      "clip_ratio/low_min": 0.0001122549165302189,
      "clip_ratio/region_mean": 0.0021494863103725947,
      "epoch": 0.024733271500154582,
      "grad_norm": 0.12576733529567719,
      "learning_rate": 1e-06,
      "loss": 0.0559,
      "step": 265
    },
    {
      "clip_ratio/high_max": 0.002444140314764809,
      "clip_ratio/high_mean": 0.0010282442162861116,
      "clip_ratio/low_mean": 0.0010951087588182418,
      "clip_ratio/low_min": 0.00013668149222212378,
      "clip_ratio/region_mean": 0.0021233530205790885,
      "epoch": 0.024826604600155167,
      "grad_norm": 0.12605029344558716,
      "learning_rate": 1e-06,
      "loss": 0.0561,
      "step": 266
    },
    {
      "clip_ratio/high_max": 0.002505919932445977,
      "clip_ratio/high_mean": 0.0010706119082897203,
      "clip_ratio/low_mean": 0.001019883970002411,
      "clip_ratio/low_min": 8.928609531722032e-05,
      "clip_ratio/region_mean": 0.002090495872835163,
      "epoch": 0.02491993770015575,
      "grad_norm": 0.11480946093797684,
      "learning_rate": 1e-06,
      "loss": 0.0429,
      "step": 267
    },
    {
      "clip_ratio/high_max": 0.002146953935152851,
      "clip_ratio/high_mean": 0.0009213567136612255,
      "clip_ratio/low_mean": 0.0008541341776435729,
      "clip_ratio/low_min": 0.00012193677412142279,
      "clip_ratio/region_mean": 0.001775490898580756,
      "epoch": 0.025013270800156334,
      "grad_norm": 0.11736516654491425,
      "learning_rate": 1e-06,
      "loss": 0.0347,
      "step": 268
    },
    {
      "clip_ratio/high_max": 0.002444287318212446,
      "clip_ratio/high_mean": 0.0009080634717975045,
      "clip_ratio/low_mean": 0.0008916878086893121,
      "clip_ratio/low_min": 8.94487575351377e-05,
      "clip_ratio/region_mean": 0.0017997512404690497,
      "epoch": 0.025106603900156916,
      "grad_norm": 0.10688665509223938,
      "learning_rate": 1e-06,
      "loss": 0.05,
      "step": 269
    },
    {
      "clip_ratio/high_max": 0.0022405747331504244,
      "clip_ratio/high_mean": 0.0009181412024190649,
      "clip_ratio/low_mean": 0.0008927080343710259,
      "clip_ratio/low_min": 0.00020293468332965858,
      "clip_ratio/region_mean": 0.0018108492731698789,
      "epoch": 0.0251999370001575,
      "grad_norm": 0.11290182173252106,
      "learning_rate": 1e-06,
      "loss": 0.0481,
      "step": 270
    },
    {
      "clip_ratio/high_max": 0.0024090096485451795,
      "clip_ratio/high_mean": 0.0011666065765894018,
      "clip_ratio/low_mean": 0.0008310027260449715,
      "clip_ratio/low_min": 2.82986902675475e-05,
      "clip_ratio/region_mean": 0.001997609288082458,
      "epoch": 0.025293270100158083,
      "grad_norm": 0.12206444889307022,
      "learning_rate": 1e-06,
      "loss": 0.0006,
      "step": 271
    },
    {
      "clip_ratio/high_max": 0.0019530435238266364,
      "clip_ratio/high_mean": 0.0009773091514944099,
      "clip_ratio/low_mean": 0.000938744269660674,
      "clip_ratio/low_min": 9.81302964646602e-05,
      "clip_ratio/region_mean": 0.001916053399327211,
      "epoch": 0.025386603200158665,
      "grad_norm": 0.12658779323101044,
      "learning_rate": 1e-06,
      "loss": 0.042,
      "step": 272
    },
    {
      "clip_ratio/high_max": 0.0025241987968911417,
      "clip_ratio/high_mean": 0.0010535933797655161,
      "clip_ratio/low_mean": 0.001068296391167678,
      "clip_ratio/low_min": 0.00014435025423154002,
      "clip_ratio/region_mean": 0.0021218897600192577,
      "epoch": 0.02547993630015925,
      "grad_norm": 0.11415829509496689,
      "learning_rate": 1e-06,
      "loss": 0.0148,
      "step": 273
    },
    {
      "clip_ratio/high_max": 0.002588375165942125,
      "clip_ratio/high_mean": 0.0011596155563893262,
      "clip_ratio/low_mean": 0.0008853486688167322,
      "clip_ratio/low_min": 9.122736810240895e-05,
      "clip_ratio/region_mean": 0.0020449642106541432,
      "epoch": 0.02557326940015983,
      "grad_norm": 0.11924593895673752,
      "learning_rate": 1e-06,
      "loss": -0.0118,
      "step": 274
    },
    {
      "clip_ratio/high_max": 0.0022943424264667556,
      "clip_ratio/high_mean": 0.0009754979764693417,
      "clip_ratio/low_mean": 0.0011792521363531705,
      "clip_ratio/low_min": 0.00024328667132067494,
      "clip_ratio/region_mean": 0.0021547501455643214,
      "epoch": 0.025666602500160417,
      "grad_norm": 0.12239724397659302,
      "learning_rate": 1e-06,
      "loss": 0.0906,
      "step": 275
    },
    {
      "clip_ratio/high_max": 0.0024246125904028304,
      "clip_ratio/high_mean": 0.001187376692541875,
      "clip_ratio/low_mean": 0.0010666898979252437,
      "clip_ratio/low_min": 0.00015142666052270215,
      "clip_ratio/region_mean": 0.0022540666541317478,
      "epoch": 0.025759935600161,
      "grad_norm": 0.1227109357714653,
      "learning_rate": 1e-06,
      "loss": -0.0087,
      "step": 276
    },
    {
      "clip_ratio/high_max": 0.0025024011702043936,
      "clip_ratio/high_mean": 0.0011753052822314203,
      "clip_ratio/low_mean": 0.0010576730783213861,
      "clip_ratio/low_min": 9.673169734014664e-05,
      "clip_ratio/region_mean": 0.002232978353276849,
      "epoch": 0.025853268700161584,
      "grad_norm": 0.11423332244157791,
      "learning_rate": 1e-06,
      "loss": 0.0091,
      "step": 277
    },
    {
      "clip_ratio/high_max": 0.002409491644357331,
      "clip_ratio/high_mean": 0.0011441790647950256,
      "clip_ratio/low_mean": 0.001143206340202596,
      "clip_ratio/low_min": 0.00014949106298445258,
      "clip_ratio/region_mean": 0.0022873853231430985,
      "epoch": 0.025946601800162165,
      "grad_norm": 0.11554890125989914,
      "learning_rate": 1e-06,
      "loss": -0.0285,
      "step": 278
    },
    {
      "clip_ratio/high_max": 0.0025720396006363444,
      "clip_ratio/high_mean": 0.0011215429731237236,
      "clip_ratio/low_mean": 0.0011445862292021047,
      "clip_ratio/low_min": 9.396823588758707e-05,
      "clip_ratio/region_mean": 0.0022661291441181675,
      "epoch": 0.02603993490016275,
      "grad_norm": 0.11064556986093521,
      "learning_rate": 1e-06,
      "loss": -0.0037,
      "step": 279
    },
    {
      "clip_ratio/high_max": 0.002317258797120303,
      "clip_ratio/high_mean": 0.0010377992839494254,
      "clip_ratio/low_mean": 0.0011915607374248793,
      "clip_ratio/low_min": 0.00012314695413806476,
      "clip_ratio/region_mean": 0.002229359990451485,
      "epoch": 0.026133268000163332,
      "grad_norm": 0.12614858150482178,
      "learning_rate": 1e-06,
      "loss": 0.0042,
      "step": 280
    },
    {
      "clip_ratio/high_max": 0.0024208695322158746,
      "clip_ratio/high_mean": 0.0009814514733079704,
      "clip_ratio/low_mean": 0.0012528287588793319,
      "clip_ratio/low_min": 0.00010306581862096209,
      "clip_ratio/region_mean": 0.002234280233096797,
      "epoch": 0.026226601100163918,
      "grad_norm": 0.1160554587841034,
      "learning_rate": 1e-06,
      "loss": 0.0203,
      "step": 281
    },
    {
      "clip_ratio/high_max": 0.0023500206334574614,
      "clip_ratio/high_mean": 0.0010458977503731148,
      "clip_ratio/low_mean": 0.0011094500969193177,
      "clip_ratio/low_min": 8.827497367747128e-05,
      "clip_ratio/region_mean": 0.0021553478873101994,
      "epoch": 0.0263199342001645,
      "grad_norm": 0.11173048615455627,
      "learning_rate": 1e-06,
      "loss": 0.0211,
      "step": 282
    },
    {
      "clip_ratio/high_max": 0.0022284902370302007,
      "clip_ratio/high_mean": 0.0010493646113900468,
      "clip_ratio/low_mean": 0.0011318081051285844,
      "clip_ratio/low_min": 0.00012473552123992704,
      "clip_ratio/region_mean": 0.002181172756536398,
      "epoch": 0.026413267300165084,
      "grad_norm": 0.12013093382120132,
      "learning_rate": 1e-06,
      "loss": 0.0261,
      "step": 283
    },
    {
      "clip_ratio/high_max": 0.0027971367380814627,
      "clip_ratio/high_mean": 0.001220919877596316,
      "clip_ratio/low_mean": 0.0011303797909931745,
      "clip_ratio/low_min": 0.00014531417218677234,
      "clip_ratio/region_mean": 0.0023512996558565646,
      "epoch": 0.026506600400165666,
      "grad_norm": 0.12292158603668213,
      "learning_rate": 1e-06,
      "loss": -0.011,
      "step": 284
    },
    {
      "clip_ratio/high_max": 0.0023757604940328747,
      "clip_ratio/high_mean": 0.0009779406964298687,
      "clip_ratio/low_mean": 0.001226168911671266,
      "clip_ratio/low_min": 0.00017896837744046934,
      "clip_ratio/region_mean": 0.0022041096235625446,
      "epoch": 0.026599933500166248,
      "grad_norm": 0.11741437762975693,
      "learning_rate": 1e-06,
      "loss": 0.0373,
      "step": 285
    },
    {
      "clip_ratio/high_max": 0.0026118098103324883,
      "clip_ratio/high_mean": 0.0011304804720566608,
      "clip_ratio/low_mean": 0.0011518621704453835,
      "clip_ratio/low_min": 7.186270431702724e-05,
      "clip_ratio/region_mean": 0.002282342677062843,
      "epoch": 0.026693266600166833,
      "grad_norm": 0.12293212860822678,
      "learning_rate": 1e-06,
      "loss": -0.0149,
      "step": 286
    },
    {
      "clip_ratio/high_max": 0.002940037113148719,
      "clip_ratio/high_mean": 0.0011611158224695828,
      "clip_ratio/low_mean": 0.0012260290022823028,
      "clip_ratio/low_min": 0.00024637759725010255,
      "clip_ratio/region_mean": 0.002387144777458161,
      "epoch": 0.026786599700167415,
      "grad_norm": 0.1197468563914299,
      "learning_rate": 1e-06,
      "loss": 0.021,
      "step": 287
    },
    {
      "clip_ratio/high_max": 0.0025703799474285915,
      "clip_ratio/high_mean": 0.0011514400066516828,
      "clip_ratio/low_mean": 0.0012723642939818092,
      "clip_ratio/low_min": 0.00012272383537492715,
      "clip_ratio/region_mean": 0.0024238042751676403,
      "epoch": 0.026879932800168,
      "grad_norm": 0.1248224601149559,
      "learning_rate": 1e-06,
      "loss": -0.0219,
      "step": 288
    },
    {
      "clip_ratio/high_max": 0.002599159473902546,
      "clip_ratio/high_mean": 0.0011211236342205666,
      "clip_ratio/low_mean": 0.0012730159505736083,
      "clip_ratio/low_min": 9.851210597844329e-05,
      "clip_ratio/region_mean": 0.002394139548414387,
      "epoch": 0.026973265900168582,
      "grad_norm": 0.12003982067108154,
      "learning_rate": 1e-06,
      "loss": 0.0327,
      "step": 289
    },
    {
      "clip_ratio/high_max": 0.002249806304462254,
      "clip_ratio/high_mean": 0.0009766307084646542,
      "clip_ratio/low_mean": 0.0013646035422425484,
      "clip_ratio/low_min": 0.00021926810950390063,
      "clip_ratio/region_mean": 0.002341234234336298,
      "epoch": 0.027066599000169167,
      "grad_norm": 0.11406214535236359,
      "learning_rate": 1e-06,
      "loss": 0.0468,
      "step": 290
    },
    {
      "clip_ratio/high_max": 0.0027012326536350884,
      "clip_ratio/high_mean": 0.0011246063477301504,
      "clip_ratio/low_mean": 0.0013270542185637169,
      "clip_ratio/low_min": 0.00013454911277221981,
      "clip_ratio/region_mean": 0.002451660533552058,
      "epoch": 0.02715993210016975,
      "grad_norm": 0.12362117320299149,
      "learning_rate": 1e-06,
      "loss": 0.0216,
      "step": 291
    },
    {
      "clip_ratio/high_max": 0.0024649514198245015,
      "clip_ratio/high_mean": 0.0010324402755941264,
      "clip_ratio/low_mean": 0.0014683713015983813,
      "clip_ratio/low_min": 0.00016491775295435218,
      "clip_ratio/region_mean": 0.002500811511708889,
      "epoch": 0.027253265200170334,
      "grad_norm": 0.12036436051130295,
      "learning_rate": 1e-06,
      "loss": 0.0537,
      "step": 292
    },
    {
      "clip_ratio/high_max": 0.0023901978456706274,
      "clip_ratio/high_mean": 0.0010643073719620588,
      "clip_ratio/low_mean": 0.001386093190376414,
      "clip_ratio/low_min": 0.00015086051098478492,
      "clip_ratio/region_mean": 0.0024504005268681794,
      "epoch": 0.027346598300170916,
      "grad_norm": 0.12816454470157623,
      "learning_rate": 1e-06,
      "loss": 0.0315,
      "step": 293
    },
    {
      "clip_ratio/high_max": 0.0026513835109653883,
      "clip_ratio/high_mean": 0.0011005796204699436,
      "clip_ratio/low_mean": 0.0012435173666744959,
      "clip_ratio/low_min": 0.00012286496348679066,
      "clip_ratio/region_mean": 0.0023440970107913017,
      "epoch": 0.0274399314001715,
      "grad_norm": 0.11072500050067902,
      "learning_rate": 1e-06,
      "loss": 0.0417,
      "step": 294
    },
    {
      "clip_ratio/high_max": 0.0023924853521748446,
      "clip_ratio/high_mean": 0.0010282583698426606,
      "clip_ratio/low_mean": 0.0012225905193190556,
      "clip_ratio/low_min": 0.00016921822407311993,
      "clip_ratio/region_mean": 0.0022508489273604937,
      "epoch": 0.027533264500172083,
      "grad_norm": 0.12008463591337204,
      "learning_rate": 1e-06,
      "loss": 0.0546,
      "step": 295
    },
    {
      "clip_ratio/high_max": 0.0024777651924523525,
      "clip_ratio/high_mean": 0.0010775557930173818,
      "clip_ratio/low_mean": 0.001231388043379411,
      "clip_ratio/low_min": 0.00018410832126392052,
      "clip_ratio/region_mean": 0.0023089438400347717,
      "epoch": 0.027626597600172668,
      "grad_norm": 0.11875315755605698,
      "learning_rate": 1e-06,
      "loss": 0.0054,
      "step": 296
    },
    {
      "clip_ratio/high_max": 0.0022739601699868217,
      "clip_ratio/high_mean": 0.0010673532051441725,
      "clip_ratio/low_mean": 0.0011142037074023392,
      "clip_ratio/low_min": 0.00020274594407965196,
      "clip_ratio/region_mean": 0.0021815569125465117,
      "epoch": 0.02771993070017325,
      "grad_norm": 0.1161278784275055,
      "learning_rate": 1e-06,
      "loss": 0.0203,
      "step": 297
    },
    {
      "clip_ratio/high_max": 0.002784185518976301,
      "clip_ratio/high_mean": 0.001252472629857948,
      "clip_ratio/low_mean": 0.0013023063074797392,
      "clip_ratio/low_min": 5.17031985509675e-05,
      "clip_ratio/region_mean": 0.0025547789555275813,
      "epoch": 0.02781326380017383,
      "grad_norm": 0.11731606721878052,
      "learning_rate": 1e-06,
      "loss": 0.0207,
      "step": 298
    },
    {
      "clip_ratio/high_max": 0.0021159514326427598,
      "clip_ratio/high_mean": 0.0010194711121584987,
      "clip_ratio/low_mean": 0.001165938207122963,
      "clip_ratio/low_min": 0.0001392071517329896,
      "clip_ratio/region_mean": 0.0021854093720321544,
      "epoch": 0.027906596900174416,
      "grad_norm": 0.42902833223342896,
      "learning_rate": 1e-06,
      "loss": 0.024,
      "step": 299
    },
    {
      "clip_ratio/high_max": 0.0025800122602959163,
      "clip_ratio/high_mean": 0.0010770422741188668,
      "clip_ratio/low_mean": 0.00122316302076797,
      "clip_ratio/low_min": 0.00013648294498125324,
      "clip_ratio/region_mean": 0.0023002052621450275,
      "epoch": 0.027999930000174998,
      "grad_norm": 0.10511124134063721,
      "learning_rate": 1e-06,
      "loss": 0.0001,
      "step": 300
    },
    {
      "clip_ratio/high_max": 0.002678452874533832,
      "clip_ratio/high_mean": 0.0011743729719455587,
      "clip_ratio/low_mean": 0.0009771113655006047,
      "clip_ratio/low_min": 7.334643396461615e-05,
      "clip_ratio/region_mean": 0.0021514844047487713,
      "epoch": 0.028093263100175583,
      "grad_norm": 0.11369849741458893,
      "learning_rate": 1e-06,
      "loss": 0.0011,
      "step": 301
    },
    {
      "clip_ratio/high_max": 0.002597427723230794,
      "clip_ratio/high_mean": 0.001141971641118289,
      "clip_ratio/low_mean": 0.0014551690692314878,
      "clip_ratio/low_min": 0.0002136166876880452,
      "clip_ratio/region_mean": 0.002597140693978872,
      "epoch": 0.028186596200176165,
      "grad_norm": 0.12733303010463715,
      "learning_rate": 1e-06,
      "loss": 0.0685,
      "step": 302
    },
    {
      "clip_ratio/high_max": 0.002422091525659198,
      "clip_ratio/high_mean": 0.0010322401703888318,
      "clip_ratio/low_mean": 0.0014132260002952535,
      "clip_ratio/low_min": 0.0001757511909090681,
      "clip_ratio/region_mean": 0.0024454661397612654,
      "epoch": 0.02827992930017675,
      "grad_norm": 0.11881496012210846,
      "learning_rate": 1e-06,
      "loss": 0.0089,
      "step": 303
    },
    {
      "clip_ratio/high_max": 0.0026955693174386397,
      "clip_ratio/high_mean": 0.0012299519730731845,
      "clip_ratio/low_mean": 0.001312518390477635,
      "clip_ratio/low_min": 8.885224451660179e-05,
      "clip_ratio/region_mean": 0.0025424703999306075,
      "epoch": 0.028373262400177332,
      "grad_norm": 0.11214599758386612,
      "learning_rate": 1e-06,
      "loss": 0.0207,
      "step": 304
    },
    {
      "clip_ratio/high_max": 0.0030520404980052263,
      "clip_ratio/high_mean": 0.0012664409950957634,
      "clip_ratio/low_mean": 0.0012687414782703854,
      "clip_ratio/low_min": 0.00025071760228456696,
      "clip_ratio/region_mean": 0.0025351825315738097,
      "epoch": 0.028466595500177917,
      "grad_norm": 0.12294237315654755,
      "learning_rate": 1e-06,
      "loss": 0.0428,
      "step": 305
    },
    {
      "clip_ratio/high_max": 0.002863376423192676,
      "clip_ratio/high_mean": 0.001243401042302139,
      "clip_ratio/low_mean": 0.0013304653075465467,
      "clip_ratio/low_min": 0.00011821213593066204,
      "clip_ratio/region_mean": 0.002573866324382834,
      "epoch": 0.0285599286001785,
      "grad_norm": 0.1343970000743866,
      "learning_rate": 1e-06,
      "loss": 0.002,
      "step": 306
    },
    {
      "clip_ratio/high_max": 0.0023996468080440536,
      "clip_ratio/high_mean": 0.001076956312317634,
      "clip_ratio/low_mean": 0.0012048578028043266,
      "clip_ratio/low_min": 0.00012952494034834672,
      "clip_ratio/region_mean": 0.0022818141733296216,
      "epoch": 0.028653261700179084,
      "grad_norm": 0.10756761580705643,
      "learning_rate": 1e-06,
      "loss": -0.0002,
      "step": 307
    },
    {
      "clip_ratio/high_max": 0.0022127933443698566,
      "clip_ratio/high_mean": 0.0010018030552600976,
      "clip_ratio/low_mean": 0.001273589994525537,
      "clip_ratio/low_min": 0.0001267386260224157,
      "clip_ratio/region_mean": 0.0022753930679755285,
      "epoch": 0.028746594800179666,
      "grad_norm": 0.11581108719110489,
      "learning_rate": 1e-06,
      "loss": 0.0579,
      "step": 308
    },
    {
      "clip_ratio/high_max": 0.002870077354600653,
      "clip_ratio/high_mean": 0.0011821799562312663,
      "clip_ratio/low_mean": 0.0015533137411694042,
      "clip_ratio/low_min": 0.00018565398204373196,
      "clip_ratio/region_mean": 0.002735493704676628,
      "epoch": 0.02883992790018025,
      "grad_norm": 0.11946620047092438,
      "learning_rate": 1e-06,
      "loss": 0.0303,
      "step": 309
    },
    {
      "clip_ratio/high_max": 0.0028245630965102464,
      "clip_ratio/high_mean": 0.0011898544362338725,
      "clip_ratio/low_mean": 0.001317115682468284,
      "clip_ratio/low_min": 0.00017805923789637745,
      "clip_ratio/region_mean": 0.0025069700641324744,
      "epoch": 0.028933261000180833,
      "grad_norm": 0.11811016499996185,
      "learning_rate": 1e-06,
      "loss": 0.007,
      "step": 310
    },
    {
      "clip_ratio/high_max": 0.002491500199539587,
      "clip_ratio/high_mean": 0.0011784347443608567,
      "clip_ratio/low_mean": 0.0012403953915054444,
      "clip_ratio/low_min": 0.00017528533408039948,
      "clip_ratio/region_mean": 0.0024188301686081104,
      "epoch": 0.029026594100181415,
      "grad_norm": 0.12050150334835052,
      "learning_rate": 1e-06,
      "loss": 0.0164,
      "step": 311
    },
    {
      "clip_ratio/high_max": 0.0028014828567393124,
      "clip_ratio/high_mean": 0.001221913451445289,
      "clip_ratio/low_mean": 0.0012070527009200305,
      "clip_ratio/low_min": 8.27523872430902e-05,
      "clip_ratio/region_mean": 0.002428966145089362,
      "epoch": 0.029119927200182,
      "grad_norm": 0.1260824203491211,
      "learning_rate": 1e-06,
      "loss": 0.0046,
      "step": 312
    },
    {
      "clip_ratio/high_max": 0.0024019197953748517,
      "clip_ratio/high_mean": 0.0010809826126205735,
      "clip_ratio/low_mean": 0.0012612868267751765,
      "clip_ratio/low_min": 0.0003237895361962728,
      "clip_ratio/region_mean": 0.0023422694866894744,
      "epoch": 0.02921326030018258,
      "grad_norm": 0.10993025451898575,
      "learning_rate": 1e-06,
      "loss": 0.0532,
      "step": 313
    },
    {
      "clip_ratio/high_max": 0.0026066493446705863,
      "clip_ratio/high_mean": 0.0011838960181194125,
      "clip_ratio/low_mean": 0.0013028596549702343,
      "clip_ratio/low_min": 0.00019492600586090703,
      "clip_ratio/region_mean": 0.0024867557294783182,
      "epoch": 0.029306593400183167,
      "grad_norm": 0.11327281594276428,
      "learning_rate": 1e-06,
      "loss": 0.0572,
      "step": 314
    },
    {
      "clip_ratio/high_max": 0.0023374292431981303,
      "clip_ratio/high_mean": 0.0010577563261904288,
      "clip_ratio/low_mean": 0.0014068042182771023,
      "clip_ratio/low_min": 0.0001055463344528107,
      "clip_ratio/region_mean": 0.002464560529915616,
      "epoch": 0.02939992650018375,
      "grad_norm": 0.1130322590470314,
      "learning_rate": 1e-06,
      "loss": 0.0323,
      "step": 315
    },
    {
      "clip_ratio/high_max": 0.002613388714962639,
      "clip_ratio/high_mean": 0.0012897571941721253,
      "clip_ratio/low_mean": 0.001050957234838279,
      "clip_ratio/low_min": 5.0486847612774e-05,
      "clip_ratio/region_mean": 0.0023407143817166798,
      "epoch": 0.029493259600184334,
      "grad_norm": 0.11195064336061478,
      "learning_rate": 1e-06,
      "loss": 0.0119,
      "step": 316
    },
    {
      "clip_ratio/high_max": 0.002533223043428734,
      "clip_ratio/high_mean": 0.001145669855759479,
      "clip_ratio/low_mean": 0.001398324515321292,
      "clip_ratio/low_min": 0.00014239074243960204,
      "clip_ratio/region_mean": 0.0025439944001846015,
      "epoch": 0.029586592700184915,
      "grad_norm": 0.12074705958366394,
      "learning_rate": 1e-06,
      "loss": 0.0316,
      "step": 317
    },
    {
      "clip_ratio/high_max": 0.00338101114903111,
      "clip_ratio/high_mean": 0.0012102191358280834,
      "clip_ratio/low_mean": 0.0014048545417608693,
      "clip_ratio/low_min": 0.0002666663258423796,
      "clip_ratio/region_mean": 0.0026150736666750163,
      "epoch": 0.0296799258001855,
      "grad_norm": 0.1311887502670288,
      "learning_rate": 1e-06,
      "loss": 0.0339,
      "step": 318
    },
    {
      "clip_ratio/high_max": 0.0028307714019319974,
      "clip_ratio/high_mean": 0.0012912246857013088,
      "clip_ratio/low_mean": 0.0012666746115428396,
      "clip_ratio/low_min": 0.00013638117343361955,
      "clip_ratio/region_mean": 0.0025578993081580848,
      "epoch": 0.029773258900186082,
      "grad_norm": 0.11552929133176804,
      "learning_rate": 1e-06,
      "loss": -0.0098,
      "step": 319
    },
    {
      "clip_ratio/high_max": 0.002431904333207058,
      "clip_ratio/high_mean": 0.0010434661162435077,
      "clip_ratio/low_mean": 0.0013269542941998225,
      "clip_ratio/low_min": 0.0001878975181170972,
      "clip_ratio/region_mean": 0.002370420392253436,
      "epoch": 0.029866592000186667,
      "grad_norm": 0.113045334815979,
      "learning_rate": 1e-06,
      "loss": 0.0229,
      "step": 320
    },
    {
      "clip_ratio/high_max": 0.002727728264289908,
      "clip_ratio/high_mean": 0.001258336560567841,
      "clip_ratio/low_mean": 0.001537319207272958,
      "clip_ratio/low_min": 9.894037793856114e-05,
      "clip_ratio/region_mean": 0.0027956557751167566,
      "epoch": 0.02995992510018725,
      "grad_norm": 0.12713514268398285,
      "learning_rate": 1e-06,
      "loss": 0.0232,
      "step": 321
    },
    {
      "clip_ratio/high_max": 0.0027570805468712933,
      "clip_ratio/high_mean": 0.001182385425636312,
      "clip_ratio/low_mean": 0.0013822237106069224,
      "clip_ratio/low_min": 0.00010947411919914884,
      "clip_ratio/region_mean": 0.002564609138062224,
      "epoch": 0.030053258200187834,
      "grad_norm": 0.11906226724386215,
      "learning_rate": 1e-06,
      "loss": 0.0276,
      "step": 322
    },
    {
      "clip_ratio/high_max": 0.00273782334261341,
      "clip_ratio/high_mean": 0.0012277323185116984,
      "clip_ratio/low_mean": 0.0016281834068649914,
      "clip_ratio/low_min": 0.0002921199702541344,
      "clip_ratio/region_mean": 0.0028559158236021176,
      "epoch": 0.030146591300188416,
      "grad_norm": 0.1219710111618042,
      "learning_rate": 1e-06,
      "loss": 0.0763,
      "step": 323
    },
    {
      "clip_ratio/high_max": 0.0026153652906941716,
      "clip_ratio/high_mean": 0.0011733440314856125,
      "clip_ratio/low_mean": 0.001203061947308015,
      "clip_ratio/low_min": 0.0001541512829135172,
      "clip_ratio/region_mean": 0.0023764060097164474,
      "epoch": 0.030239924400188998,
      "grad_norm": 0.11505386233329773,
      "learning_rate": 1e-06,
      "loss": 0.0098,
      "step": 324
    },
    {
      "clip_ratio/high_max": 0.0029785673395963386,
      "clip_ratio/high_mean": 0.0013684470468433574,
      "clip_ratio/low_mean": 0.0013609007364721037,
      "clip_ratio/low_min": 0.0001766563109413255,
      "clip_ratio/region_mean": 0.0027293477542116307,
      "epoch": 0.030333257500189583,
      "grad_norm": 0.11739931255578995,
      "learning_rate": 1e-06,
      "loss": -0.0273,
      "step": 325
    },
    {
      "clip_ratio/high_max": 0.0028727469325531274,
      "clip_ratio/high_mean": 0.0012607965181814507,
      "clip_ratio/low_mean": 0.0012595268235600088,
      "clip_ratio/low_min": 0.00010610255776555277,
      "clip_ratio/region_mean": 0.00252032330899965,
      "epoch": 0.030426590600190165,
      "grad_norm": 0.12706126272678375,
      "learning_rate": 1e-06,
      "loss": -0.0123,
      "step": 326
    },
    {
      "clip_ratio/high_max": 0.002294195153808687,
      "clip_ratio/high_mean": 0.0010198140535067068,
      "clip_ratio/low_mean": 0.0013177910768717993,
      "clip_ratio/low_min": 6.472573386417935e-05,
      "clip_ratio/region_mean": 0.0023376051103696227,
      "epoch": 0.03051992370019075,
      "grad_norm": 0.1108463779091835,
      "learning_rate": 1e-06,
      "loss": 0.0716,
      "step": 327
    },
    {
      "clip_ratio/high_max": 0.0022406296484405175,
      "clip_ratio/high_mean": 0.0010030687444668729,
      "clip_ratio/low_mean": 0.0012518016919784714,
      "clip_ratio/low_min": 0.0002432438222967903,
      "clip_ratio/region_mean": 0.0022548704109794926,
      "epoch": 0.030613256800191332,
      "grad_norm": 0.11512810736894608,
      "learning_rate": 1e-06,
      "loss": 0.031,
      "step": 328
    },
    {
      "clip_ratio/high_max": 0.002654530129802879,
      "clip_ratio/high_mean": 0.0012471846494008787,
      "clip_ratio/low_mean": 0.001384411683829967,
      "clip_ratio/low_min": 0.00021466767975653056,
      "clip_ratio/region_mean": 0.002631596384162549,
      "epoch": 0.030706589900191917,
      "grad_norm": 0.1292494535446167,
      "learning_rate": 1e-06,
      "loss": -0.0139,
      "step": 329
    },
    {
      "clip_ratio/high_max": 0.002669588844582904,
      "clip_ratio/high_mean": 0.001118953663535649,
      "clip_ratio/low_mean": 0.0012583058160089422,
      "clip_ratio/low_min": 0.00015707740931247827,
      "clip_ratio/region_mean": 0.0023772594722686335,
      "epoch": 0.0307999230001925,
      "grad_norm": 0.11671560257673264,
      "learning_rate": 1e-06,
      "loss": 0.0397,
      "step": 330
    },
    {
      "clip_ratio/high_max": 0.002987729363667313,
      "clip_ratio/high_mean": 0.0013143653159204405,
      "clip_ratio/low_mean": 0.0014170816175465006,
      "clip_ratio/low_min": 0.00032416541489510564,
      "clip_ratio/region_mean": 0.002731446824327577,
      "epoch": 0.030893256100193084,
      "grad_norm": 0.12937036156654358,
      "learning_rate": 1e-06,
      "loss": 0.0041,
      "step": 331
    },
    {
      "clip_ratio/high_max": 0.00297994892753195,
      "clip_ratio/high_mean": 0.0013374622758419719,
      "clip_ratio/low_mean": 0.0013030631016590632,
      "clip_ratio/low_min": 7.35727344363113e-05,
      "clip_ratio/region_mean": 0.002640525322931353,
      "epoch": 0.030986589200193666,
      "grad_norm": 0.12331847846508026,
      "learning_rate": 1e-06,
      "loss": -0.0112,
      "step": 332
    },
    {
      "clip_ratio/high_max": 0.00271753131528385,
      "clip_ratio/high_mean": 0.0012775933973898645,
      "clip_ratio/low_mean": 0.001287443723413162,
      "clip_ratio/low_min": 0.00021289817414071877,
      "clip_ratio/region_mean": 0.0025650370807852596,
      "epoch": 0.03107992230019425,
      "grad_norm": 0.1075827106833458,
      "learning_rate": 1e-06,
      "loss": 0.0109,
      "step": 333
    },
    {
      "clip_ratio/high_max": 0.002579079162387643,
      "clip_ratio/high_mean": 0.0012311333302932326,
      "clip_ratio/low_mean": 0.0015370732035080437,
      "clip_ratio/low_min": 0.00031929068063618615,
      "clip_ratio/region_mean": 0.0027682064755936153,
      "epoch": 0.031173255400194833,
      "grad_norm": 0.11311246454715729,
      "learning_rate": 1e-06,
      "loss": 0.0352,
      "step": 334
    },
    {
      "clip_ratio/high_max": 0.0029205515020294115,
      "clip_ratio/high_mean": 0.0012675274047069252,
      "clip_ratio/low_mean": 0.0012723055770038627,
      "clip_ratio/low_min": 0.00019051301933359355,
      "clip_ratio/region_mean": 0.0025398330035386607,
      "epoch": 0.03126658850019542,
      "grad_norm": 0.11139726638793945,
      "learning_rate": 1e-06,
      "loss": 0.0009,
      "step": 335
    },
    {
      "clip_ratio/high_max": 0.002710441993258428,
      "clip_ratio/high_mean": 0.0011613564893195871,
      "clip_ratio/low_mean": 0.0012366141090751626,
      "clip_ratio/low_min": 7.743687365291407e-05,
      "clip_ratio/region_mean": 0.002397970631136559,
      "epoch": 0.031359921600196,
      "grad_norm": 0.1116127148270607,
      "learning_rate": 1e-06,
      "loss": -0.0108,
      "step": 336
    },
    {
      "clip_ratio/high_max": 0.0024759200096013956,
      "clip_ratio/high_mean": 0.0012100106014258927,
      "clip_ratio/low_mean": 0.0014488231245195493,
      "clip_ratio/low_min": 0.0002433279987599235,
      "clip_ratio/region_mean": 0.002658833698660601,
      "epoch": 0.03145325470019658,
      "grad_norm": 0.125503808259964,
      "learning_rate": 1e-06,
      "loss": 0.021,
      "step": 337
    },
    {
      "clip_ratio/high_max": 0.002818977656716015,
      "clip_ratio/high_mean": 0.001187575497169746,
      "clip_ratio/low_mean": 0.0014269797175074928,
      "clip_ratio/low_min": 0.00014719645605509868,
      "clip_ratio/region_mean": 0.002614555196487345,
      "epoch": 0.031546587800197166,
      "grad_norm": 0.12357683479785919,
      "learning_rate": 1e-06,
      "loss": 0.0522,
      "step": 338
    },
    {
      "clip_ratio/high_max": 0.0024323719771928154,
      "clip_ratio/high_mean": 0.0011744552193704294,
      "clip_ratio/low_mean": 0.0015022774787212256,
      "clip_ratio/low_min": 5.556790347327478e-05,
      "clip_ratio/region_mean": 0.0026767327217385173,
      "epoch": 0.03163992090019775,
      "grad_norm": 0.11504726856946945,
      "learning_rate": 1e-06,
      "loss": 0.0384,
      "step": 339
    },
    {
      "clip_ratio/high_max": 0.0028221156244399026,
      "clip_ratio/high_mean": 0.0013185626157792285,
      "clip_ratio/low_mean": 0.0014383208654180635,
      "clip_ratio/low_min": 0.0001980749329959508,
      "clip_ratio/region_mean": 0.002756883463007398,
      "epoch": 0.03173325400019833,
      "grad_norm": 0.13010273873806,
      "learning_rate": 1e-06,
      "loss": 0.0563,
      "step": 340
    },
    {
      "clip_ratio/high_max": 0.0024896442992030643,
      "clip_ratio/high_mean": 0.001195636734337313,
      "clip_ratio/low_mean": 0.0012817933020414785,
      "clip_ratio/low_min": 0.00014836681566521293,
      "clip_ratio/region_mean": 0.0024774300909484737,
      "epoch": 0.031826587100198915,
      "grad_norm": 0.11577541381120682,
      "learning_rate": 1e-06,
      "loss": -0.0049,
      "step": 341
    },
    {
      "clip_ratio/high_max": 0.0027691277718986385,
      "clip_ratio/high_mean": 0.0012069160329701845,
      "clip_ratio/low_mean": 0.0013301407307153568,
      "clip_ratio/low_min": 9.675918954599183e-05,
      "clip_ratio/region_mean": 0.002537056752771605,
      "epoch": 0.0319199202001995,
      "grad_norm": 0.11978305876255035,
      "learning_rate": 1e-06,
      "loss": 0.0307,
      "step": 342
    },
    {
      "clip_ratio/high_max": 0.002609323670185404,
      "clip_ratio/high_mean": 0.0011365679511072813,
      "clip_ratio/low_mean": 0.0014654387232440058,
      "clip_ratio/low_min": 0.0002511220859560126,
      "clip_ratio/region_mean": 0.002602006701636128,
      "epoch": 0.032013253300200085,
      "grad_norm": 0.13147114217281342,
      "learning_rate": 1e-06,
      "loss": 0.0728,
      "step": 343
    },
    {
      "clip_ratio/high_max": 0.002931735318270512,
      "clip_ratio/high_mean": 0.0012131395778851584,
      "clip_ratio/low_mean": 0.0012386130656523164,
      "clip_ratio/low_min": 0.0002098496979670017,
      "clip_ratio/region_mean": 0.0024517526835552417,
      "epoch": 0.032106586400200664,
      "grad_norm": 0.12044328451156616,
      "learning_rate": 1e-06,
      "loss": 0.0324,
      "step": 344
    },
    {
      "clip_ratio/high_max": 0.002839184606273193,
      "clip_ratio/high_mean": 0.001230621859576786,
      "clip_ratio/low_mean": 0.0013291972973092925,
      "clip_ratio/low_min": 0.00017719788775139023,
      "clip_ratio/region_mean": 0.002559819149610121,
      "epoch": 0.03219991950020125,
      "grad_norm": 0.11433827131986618,
      "learning_rate": 1e-06,
      "loss": 0.0281,
      "step": 345
    },
    {
      "clip_ratio/high_max": 0.0029480933299055323,
      "clip_ratio/high_mean": 0.0012881237562396564,
      "clip_ratio/low_mean": 0.0014575713721569628,
      "clip_ratio/low_min": 0.00031186802607408026,
      "clip_ratio/region_mean": 0.002745695164776407,
      "epoch": 0.032293252600201834,
      "grad_norm": 0.12129674851894379,
      "learning_rate": 1e-06,
      "loss": 0.0456,
      "step": 346
    },
    {
      "clip_ratio/high_max": 0.0027298552959109657,
      "clip_ratio/high_mean": 0.001182255509775132,
      "clip_ratio/low_mean": 0.0014558730908902362,
      "clip_ratio/low_min": 0.00019792932380369166,
      "clip_ratio/region_mean": 0.002638128622493241,
      "epoch": 0.03238658570020242,
      "grad_norm": 0.11985555291175842,
      "learning_rate": 1e-06,
      "loss": 0.0352,
      "step": 347
    },
    {
      "clip_ratio/high_max": 0.0026596702955430374,
      "clip_ratio/high_mean": 0.001141934440965997,
      "clip_ratio/low_mean": 0.0012547573078336427,
      "clip_ratio/low_min": 0.00014345739509735722,
      "clip_ratio/region_mean": 0.0023966917287907563,
      "epoch": 0.032479918800203,
      "grad_norm": 0.11207590997219086,
      "learning_rate": 1e-06,
      "loss": -0.0092,
      "step": 348
    },
    {
      "clip_ratio/high_max": 0.002559121923695784,
      "clip_ratio/high_mean": 0.0012003442679997534,
      "clip_ratio/low_mean": 0.0014691905016661622,
      "clip_ratio/low_min": 9.125880569627043e-05,
      "clip_ratio/region_mean": 0.002669534776941873,
      "epoch": 0.03257325190020358,
      "grad_norm": 3.4749622344970703,
      "learning_rate": 1e-06,
      "loss": 0.0241,
      "step": 349
    },
    {
      "clip_ratio/high_max": 0.002477469613950234,
      "clip_ratio/high_mean": 0.0011365012142050546,
      "clip_ratio/low_mean": 0.0013982561358716339,
      "clip_ratio/low_min": 0.00016291175415972248,
      "clip_ratio/region_mean": 0.002534757317334879,
      "epoch": 0.03266658500020417,
      "grad_norm": 0.10832560807466507,
      "learning_rate": 1e-06,
      "loss": 0.0101,
      "step": 350
    },
    {
      "clip_ratio/high_max": 0.0024960657028714195,
      "clip_ratio/high_mean": 0.001266965857212199,
      "clip_ratio/low_mean": 0.0016646083749947138,
      "clip_ratio/low_min": 0.00031376024253404466,
      "clip_ratio/region_mean": 0.0029315741994651034,
      "epoch": 0.032759918100204746,
      "grad_norm": 0.12081333994865417,
      "learning_rate": 1e-06,
      "loss": 0.0491,
      "step": 351
    },
    {
      "clip_ratio/high_max": 0.002582907116448041,
      "clip_ratio/high_mean": 0.001202720268338453,
      "clip_ratio/low_mean": 0.0014803973208472598,
      "clip_ratio/low_min": 0.00019903177508240333,
      "clip_ratio/region_mean": 0.0026831175928236917,
      "epoch": 0.03285325120020533,
      "grad_norm": 0.11948749423027039,
      "learning_rate": 1e-06,
      "loss": 0.0409,
      "step": 352
    },
    {
      "clip_ratio/high_max": 0.0030550208903150633,
      "clip_ratio/high_mean": 0.0012226207763887942,
      "clip_ratio/low_mean": 0.0015107838371477555,
      "clip_ratio/low_min": 0.00012934763435623609,
      "clip_ratio/region_mean": 0.0027334046171745285,
      "epoch": 0.03294658430020592,
      "grad_norm": 0.1121947318315506,
      "learning_rate": 1e-06,
      "loss": 0.0079,
      "step": 353
    },
    {
      "clip_ratio/high_max": 0.0023161769968282897,
      "clip_ratio/high_mean": 0.001042079231410753,
      "clip_ratio/low_mean": 0.0014469076922978275,
      "clip_ratio/low_min": 0.00015345194333349355,
      "clip_ratio/region_mean": 0.002488986909156665,
      "epoch": 0.0330399174002065,
      "grad_norm": 0.11080152541399002,
      "learning_rate": 1e-06,
      "loss": 0.0186,
      "step": 354
    },
    {
      "clip_ratio/high_max": 0.002782282972475514,
      "clip_ratio/high_mean": 0.0011958974719163962,
      "clip_ratio/low_mean": 0.001502432132838294,
      "clip_ratio/low_min": 0.0002410057913948549,
      "clip_ratio/region_mean": 0.0026983295974787325,
      "epoch": 0.03313325050020708,
      "grad_norm": 0.10277802497148514,
      "learning_rate": 1e-06,
      "loss": 0.0455,
      "step": 355
    },
    {
      "clip_ratio/high_max": 0.003092012084380258,
      "clip_ratio/high_mean": 0.0013035802330705337,
      "clip_ratio/low_mean": 0.001442345317627769,
      "clip_ratio/low_min": 9.913241046888288e-05,
      "clip_ratio/region_mean": 0.0027459256525617093,
      "epoch": 0.033226583600207665,
      "grad_norm": 0.2214948683977127,
      "learning_rate": 1e-06,
      "loss": 0.0189,
      "step": 356
    },
    {
      "clip_ratio/high_max": 0.0026209849966107868,
      "clip_ratio/high_mean": 0.0011954216133744922,
      "clip_ratio/low_mean": 0.001534127106424421,
      "clip_ratio/low_min": 0.00040555588111601537,
      "clip_ratio/region_mean": 0.002729548723436892,
      "epoch": 0.03331991670020825,
      "grad_norm": 0.11518749594688416,
      "learning_rate": 1e-06,
      "loss": 0.0176,
      "step": 357
    },
    {
      "clip_ratio/high_max": 0.0024458394764224067,
      "clip_ratio/high_mean": 0.0011301611411909107,
      "clip_ratio/low_mean": 0.0013621316575154196,
      "clip_ratio/low_min": 0.00017250300606974633,
      "clip_ratio/region_mean": 0.0024922927550505847,
      "epoch": 0.033413249800208836,
      "grad_norm": 0.11775501817464828,
      "learning_rate": 1e-06,
      "loss": 0.0644,
      "step": 358
    },
    {
      "clip_ratio/high_max": 0.0024289016146212816,
      "clip_ratio/high_mean": 0.0011500306172820274,
      "clip_ratio/low_mean": 0.0012023261660942808,
      "clip_ratio/low_min": 0.00015564248133159708,
      "clip_ratio/region_mean": 0.002352356787014287,
      "epoch": 0.033506582900209414,
      "grad_norm": 0.11520274728536606,
      "learning_rate": 1e-06,
      "loss": 0.0143,
      "step": 359
    },
    {
      "clip_ratio/high_max": 0.002975747687742114,
      "clip_ratio/high_mean": 0.0013569052534876391,
      "clip_ratio/low_mean": 0.0012018972192890942,
      "clip_ratio/low_min": 0.0001467452475480968,
      "clip_ratio/region_mean": 0.0025588025091565214,
      "epoch": 0.03359991600021,
      "grad_norm": 0.11080080270767212,
      "learning_rate": 1e-06,
      "loss": -0.0184,
      "step": 360
    },
    {
      "clip_ratio/high_max": 0.0031076144878170453,
      "clip_ratio/high_mean": 0.0014688008268421981,
      "clip_ratio/low_mean": 0.001412544552295003,
      "clip_ratio/low_min": 0.00015802310281287646,
      "clip_ratio/region_mean": 0.002881345404603053,
      "epoch": 0.033693249100210584,
      "grad_norm": 0.12494487315416336,
      "learning_rate": 1e-06,
      "loss": -0.0005,
      "step": 361
    },
    {
      "clip_ratio/high_max": 0.003029650433745701,
      "clip_ratio/high_mean": 0.0013258152503112797,
      "clip_ratio/low_mean": 0.0013449108737404458,
      "clip_ratio/low_min": 6.173439942358527e-05,
      "clip_ratio/region_mean": 0.0026707261567935348,
      "epoch": 0.03378658220021117,
      "grad_norm": 0.1218714639544487,
      "learning_rate": 1e-06,
      "loss": 0.0138,
      "step": 362
    },
    {
      "clip_ratio/high_max": 0.003296908544143662,
      "clip_ratio/high_mean": 0.0014315507396531757,
      "clip_ratio/low_mean": 0.0014824158424744383,
      "clip_ratio/low_min": 0.00027321754532749765,
      "clip_ratio/region_mean": 0.0029139665493858047,
      "epoch": 0.03387991530021175,
      "grad_norm": 0.11771242320537567,
      "learning_rate": 1e-06,
      "loss": 0.0399,
      "step": 363
    },
    {
      "clip_ratio/high_max": 0.002922888335888274,
      "clip_ratio/high_mean": 0.0013917280466557713,
      "clip_ratio/low_mean": 0.0014605308060708921,
      "clip_ratio/low_min": 0.0001180035833385773,
      "clip_ratio/region_mean": 0.002852258854545653,
      "epoch": 0.03397324840021233,
      "grad_norm": 0.11393259465694427,
      "learning_rate": 1e-06,
      "loss": 0.0135,
      "step": 364
    },
    {
      "clip_ratio/high_max": 0.0030631140180048533,
      "clip_ratio/high_mean": 0.0012989162241865415,
      "clip_ratio/low_mean": 0.0015420503877976444,
      "clip_ratio/low_min": 0.0002679603967408184,
      "clip_ratio/region_mean": 0.002840966553776525,
      "epoch": 0.03406658150021292,
      "grad_norm": 0.12158150225877762,
      "learning_rate": 1e-06,
      "loss": 0.0673,
      "step": 365
    },
    {
      "clip_ratio/high_max": 0.002992504494613968,
      "clip_ratio/high_mean": 0.001317954454862047,
      "clip_ratio/low_mean": 0.0016970324140856974,
      "clip_ratio/low_min": 0.0003657548495539231,
      "clip_ratio/region_mean": 0.0030149868689477444,
      "epoch": 0.034159914600213497,
      "grad_norm": 0.12091277539730072,
      "learning_rate": 1e-06,
      "loss": 0.0342,
      "step": 366
    },
    {
      "clip_ratio/high_max": 0.0026127718956558965,
      "clip_ratio/high_mean": 0.0012259299801371526,
      "clip_ratio/low_mean": 0.001328467573330272,
      "clip_ratio/low_min": 0.00014471973736362997,
      "clip_ratio/region_mean": 0.002554397564381361,
      "epoch": 0.03425324770021408,
      "grad_norm": 0.12249797582626343,
      "learning_rate": 1e-06,
      "loss": 0.0239,
      "step": 367
    },
    {
      "clip_ratio/high_max": 0.003144436050206423,
      "clip_ratio/high_mean": 0.001477711739426013,
      "clip_ratio/low_mean": 0.001165086836408591,
      "clip_ratio/low_min": 9.815675184654538e-05,
      "clip_ratio/region_mean": 0.0026427985285408795,
      "epoch": 0.03434658080021467,
      "grad_norm": 0.11737898737192154,
      "learning_rate": 1e-06,
      "loss": -0.0186,
      "step": 368
    },
    {
      "clip_ratio/high_max": 0.003237921053369064,
      "clip_ratio/high_mean": 0.0013613178925879765,
      "clip_ratio/low_mean": 0.0014945425282348879,
      "clip_ratio/low_min": 0.0002728998360908008,
      "clip_ratio/region_mean": 0.002855860446288716,
      "epoch": 0.03443991390021525,
      "grad_norm": 0.12224118411540985,
      "learning_rate": 1e-06,
      "loss": 0.0012,
      "step": 369
    },
    {
      "clip_ratio/high_max": 0.002930335816927254,
      "clip_ratio/high_mean": 0.0011756890198739711,
      "clip_ratio/low_mean": 0.0013318125384103041,
      "clip_ratio/low_min": 0.0002064401523966808,
      "clip_ratio/region_mean": 0.0025075016237678938,
      "epoch": 0.03453324700021583,
      "grad_norm": 0.11294194310903549,
      "learning_rate": 1e-06,
      "loss": 0.0223,
      "step": 370
    },
    {
      "clip_ratio/high_max": 0.0030744605683139525,
      "clip_ratio/high_mean": 0.0013768448843620718,
      "clip_ratio/low_mean": 0.0013118575898261042,
      "clip_ratio/low_min": 0.0001530354256829014,
      "clip_ratio/region_mean": 0.0026887024578172714,
      "epoch": 0.034626580100216416,
      "grad_norm": 0.1312245875597,
      "learning_rate": 1e-06,
      "loss": -0.0347,
      "step": 371
    },
    {
      "clip_ratio/high_max": 0.002997469222464133,
      "clip_ratio/high_mean": 0.0013667259299836587,
      "clip_ratio/low_mean": 0.0013200467146816663,
      "clip_ratio/low_min": 0.00016788743232609704,
      "clip_ratio/region_mean": 0.002686772611923516,
      "epoch": 0.034719913200217,
      "grad_norm": 0.11536245793104172,
      "learning_rate": 1e-06,
      "loss": -0.0226,
      "step": 372
    },
    {
      "clip_ratio/high_max": 0.0030330172085086815,
      "clip_ratio/high_mean": 0.0012987891968805343,
      "clip_ratio/low_mean": 0.0016039513066061772,
      "clip_ratio/low_min": 0.00014207320418790914,
      "clip_ratio/region_mean": 0.0029027405616943724,
      "epoch": 0.034813246300217586,
      "grad_norm": 0.11989035457372665,
      "learning_rate": 1e-06,
      "loss": 0.0253,
      "step": 373
    },
    {
      "clip_ratio/high_max": 0.003129093471216038,
      "clip_ratio/high_mean": 0.0013848109992977697,
      "clip_ratio/low_mean": 0.001588617444213014,
      "clip_ratio/low_min": 0.00021316480160749052,
      "clip_ratio/region_mean": 0.002973428403493017,
      "epoch": 0.034906579400218164,
      "grad_norm": 0.11638612300157547,
      "learning_rate": 1e-06,
      "loss": 0.0296,
      "step": 374
    },
    {
      "clip_ratio/high_max": 0.0028542610234580934,
      "clip_ratio/high_mean": 0.0012471241752791684,
      "clip_ratio/low_mean": 0.0014790143723075744,
      "clip_ratio/low_min": 0.00019667933338496368,
      "clip_ratio/region_mean": 0.002726138540310785,
      "epoch": 0.03499991250021875,
      "grad_norm": 0.1196187362074852,
      "learning_rate": 1e-06,
      "loss": 0.0031,
      "step": 375
    },
    {
      "clip_ratio/high_max": 0.002658857723872643,
      "clip_ratio/high_mean": 0.0011874367119162343,
      "clip_ratio/low_mean": 0.0015645574349036906,
      "clip_ratio/low_min": 0.00030970828993304167,
      "clip_ratio/region_mean": 0.0027519941213540733,
      "epoch": 0.035093245600219335,
      "grad_norm": 0.11873576045036316,
      "learning_rate": 1e-06,
      "loss": 0.0442,
      "step": 376
    },
    {
      "clip_ratio/high_max": 0.002949292211269494,
      "clip_ratio/high_mean": 0.0013498104235623032,
      "clip_ratio/low_mean": 0.0014495048362732632,
      "clip_ratio/low_min": 0.00013135279459675075,
      "clip_ratio/region_mean": 0.00279931521799881,
      "epoch": 0.03518657870021991,
      "grad_norm": 0.11756071448326111,
      "learning_rate": 1e-06,
      "loss": 0.0334,
      "step": 377
    },
    {
      "clip_ratio/high_max": 0.0032875392425921746,
      "clip_ratio/high_mean": 0.0013379990232351702,
      "clip_ratio/low_mean": 0.001447006499802228,
      "clip_ratio/low_min": 0.00026105966935574543,
      "clip_ratio/region_mean": 0.002785005490295589,
      "epoch": 0.0352799118002205,
      "grad_norm": 0.11876508593559265,
      "learning_rate": 1e-06,
      "loss": -0.0003,
      "step": 378
    },
    {
      "clip_ratio/high_max": 0.0033529016509419307,
      "clip_ratio/high_mean": 0.0015341117104981095,
      "clip_ratio/low_mean": 0.001427228286047466,
      "clip_ratio/low_min": 0.0002483739290255471,
      "clip_ratio/region_mean": 0.002961340025649406,
      "epoch": 0.03537324490022108,
      "grad_norm": 0.11736912280321121,
      "learning_rate": 1e-06,
      "loss": -0.0237,
      "step": 379
    },
    {
      "clip_ratio/high_max": 0.0025889503958751447,
      "clip_ratio/high_mean": 0.0009806359439608059,
      "clip_ratio/low_mean": 0.0014777261894778349,
      "clip_ratio/low_min": 0.00016089421842480078,
      "clip_ratio/region_mean": 0.0024583620761404745,
      "epoch": 0.03546657800022167,
      "grad_norm": 0.12600675225257874,
      "learning_rate": 1e-06,
      "loss": 0.0366,
      "step": 380
    },
    {
      "clip_ratio/high_max": 0.002983310798299499,
      "clip_ratio/high_mean": 0.0012190710367576685,
      "clip_ratio/low_mean": 0.0013812572688038927,
      "clip_ratio/low_min": 0.00022087665092840325,
      "clip_ratio/region_mean": 0.002600328291009646,
      "epoch": 0.03555991110022225,
      "grad_norm": 0.12188021093606949,
      "learning_rate": 1e-06,
      "loss": 0.0033,
      "step": 381
    },
    {
      "clip_ratio/high_max": 0.0027397128578741103,
      "clip_ratio/high_mean": 0.0011885113854077645,
      "clip_ratio/low_mean": 0.0017685258280835114,
      "clip_ratio/low_min": 0.00022877414630784187,
      "clip_ratio/region_mean": 0.0029570372353191487,
      "epoch": 0.03565324420022283,
      "grad_norm": 0.11412032693624496,
      "learning_rate": 1e-06,
      "loss": 0.0555,
      "step": 382
    },
    {
      "clip_ratio/high_max": 0.003093159233685583,
      "clip_ratio/high_mean": 0.0013495236344169825,
      "clip_ratio/low_mean": 0.0014810246939305216,
      "clip_ratio/low_min": 0.00021714700960728806,
      "clip_ratio/region_mean": 0.0028305482992436737,
      "epoch": 0.03574657730022342,
      "grad_norm": 0.12263639271259308,
      "learning_rate": 1e-06,
      "loss": 0.0372,
      "step": 383
    },
    {
      "clip_ratio/high_max": 0.002536262647481635,
      "clip_ratio/high_mean": 0.0011663670593407005,
      "clip_ratio/low_mean": 0.001471982501243474,
      "clip_ratio/low_min": 0.00014538026334776077,
      "clip_ratio/region_mean": 0.0026383495569461957,
      "epoch": 0.035839910400224,
      "grad_norm": 0.11592624336481094,
      "learning_rate": 1e-06,
      "loss": 0.0076,
      "step": 384
    },
    {
      "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": 0.012956891741071397,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4096.0,
      "completions/mean_length": 605.6300659179688,
      "completions/mean_terminated_length": 559.81201171875,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 0.03593324350022458,
      "grad_norm": 0.12711025774478912,
      "learning_rate": 1e-06,
      "loss": 0.0677,
      "num_tokens": 323251285.0,
      "reward": 0.567391574382782,
      "reward_std": 0.2123998999595642,
      "rewards/simpleverify_reward/mean": 0.5673915147781372,
      "rewards/simpleverify_reward/std": 0.4954396188259125,
      "step": 385
    },
    {
      "clip_ratio/high_max": 0.0021397297496150713,
      "clip_ratio/high_mean": 0.0008496433792970493,
      "clip_ratio/low_mean": 0.0006479338917415589,
      "clip_ratio/low_min": 3.825265412160661e-05,
      "clip_ratio/region_mean": 0.0014975772573961876,
      "epoch": 0.036026576600225166,
      "grad_norm": 0.12022633105516434,
      "learning_rate": 1e-06,
      "loss": 0.0407,
      "step": 386
    },
    {
      "clip_ratio/high_max": 0.00232318328198744,
      "clip_ratio/high_mean": 0.0009690656061138725,
      "clip_ratio/low_mean": 0.000670978288326296,
      "clip_ratio/low_min": 6.840613878011936e-05,
      "clip_ratio/region_mean": 0.0016400438980781473,
      "epoch": 0.03611990970022575,
      "grad_norm": 0.11227843910455704,
      "learning_rate": 1e-06,
      "loss": 0.0522,
      "step": 387
    },
    {
      "clip_ratio/high_max": 0.0020417370687937364,
      "clip_ratio/high_mean": 0.0008666624235047493,
      "clip_ratio/low_mean": 0.000664237180899363,
      "clip_ratio/low_min": 2.379434499744093e-05,
      "clip_ratio/region_mean": 0.001530899571662303,
      "epoch": 0.03621324280022633,
      "grad_norm": 0.11939997225999832,
      "learning_rate": 1e-06,
      "loss": 0.0485,
      "step": 388
    },
    {
      "clip_ratio/high_max": 0.0027182477424503304,
      "clip_ratio/high_mean": 0.0010685947145248065,
      "clip_ratio/low_mean": 0.0006693238592561102,
      "clip_ratio/low_min": 6.567220771103166e-05,
      "clip_ratio/region_mean": 0.0017379185737809166,
      "epoch": 0.036306575900226914,
      "grad_norm": 0.11462533473968506,
      "learning_rate": 1e-06,
      "loss": -0.0355,
      "step": 389
    },
    {
      "clip_ratio/high_max": 0.002425007405690849,
      "clip_ratio/high_mean": 0.0010334346188756172,
      "clip_ratio/low_mean": 0.0007138050896173809,
      "clip_ratio/low_min": 8.032506775634829e-05,
      "clip_ratio/region_mean": 0.0017472397157689556,
      "epoch": 0.0363999090002275,
      "grad_norm": 0.12447582930326462,
      "learning_rate": 1e-06,
      "loss": -0.0093,
      "step": 390
    },
    {
      "clip_ratio/high_max": 0.0025341107611893676,
      "clip_ratio/high_mean": 0.0011683505472319666,
      "clip_ratio/low_mean": 0.0007385787139355671,
      "clip_ratio/low_min": 3.290339736850001e-05,
      "clip_ratio/region_mean": 0.0019069292611675337,
      "epoch": 0.036493242100228085,
      "grad_norm": 0.11291956901550293,
      "learning_rate": 1e-06,
      "loss": -0.046,
      "step": 391
    },
    {
      "clip_ratio/high_max": 0.0020968693861505017,
      "clip_ratio/high_mean": 0.0009629784399294294,
      "clip_ratio/low_mean": 0.0009910686094372068,
      "clip_ratio/low_min": 6.0827079323644284e-05,
      "clip_ratio/region_mean": 0.0019540470675565302,
      "epoch": 0.03658657520022866,
      "grad_norm": 0.11530353873968124,
      "learning_rate": 1e-06,
      "loss": 0.0613,
      "step": 392
    },
    {
      "clip_ratio/high_max": 0.002384906867519021,
      "clip_ratio/high_mean": 0.0010603293012536597,
      "clip_ratio/low_mean": 0.0009049226209754124,
      "clip_ratio/low_min": 0.00011611211812123656,
      "clip_ratio/region_mean": 0.001965251882211305,
      "epoch": 0.03667990830022925,
      "grad_norm": 0.1233193576335907,
      "learning_rate": 1e-06,
      "loss": -0.003,
      "step": 393
    },
    {
      "clip_ratio/high_max": 0.002504220545233693,
      "clip_ratio/high_mean": 0.0010534356842981651,
      "clip_ratio/low_mean": 0.0008702893701411085,
      "clip_ratio/low_min": 9.4570267265226e-05,
      "clip_ratio/region_mean": 0.0019237250162404962,
      "epoch": 0.036773241400229834,
      "grad_norm": 0.11533639580011368,
      "learning_rate": 1e-06,
      "loss": 0.0375,
      "step": 394
    },
    {
      "clip_ratio/high_max": 0.002351952418393921,
      "clip_ratio/high_mean": 0.0009425225825907546,
      "clip_ratio/low_mean": 0.0011128354526590556,
      "clip_ratio/low_min": 0.0001173481878140592,
      "clip_ratio/region_mean": 0.002055358068901114,
      "epoch": 0.03686657450023042,
      "grad_norm": 0.1315789818763733,
      "learning_rate": 1e-06,
      "loss": 0.0916,
      "step": 395
    },
    {
      "clip_ratio/high_max": 0.002362157429161016,
      "clip_ratio/high_mean": 0.000931930241677037,
      "clip_ratio/low_mean": 0.0009760237371665426,
      "clip_ratio/low_min": 8.948628601501696e-05,
      "clip_ratio/region_mean": 0.0019079539415542968,
      "epoch": 0.036959907600231,
      "grad_norm": 0.1327863186597824,
      "learning_rate": 1e-06,
      "loss": 0.0321,
      "step": 396
    },
    {
      "clip_ratio/high_max": 0.002023422217462212,
      "clip_ratio/high_mean": 0.0009445934592804406,
      "clip_ratio/low_mean": 0.0009359381001559086,
      "clip_ratio/low_min": 9.366624090034747e-05,
      "clip_ratio/region_mean": 0.0018805315485224128,
      "epoch": 0.03705324070023158,
      "grad_norm": 0.12058063596487045,
      "learning_rate": 1e-06,
      "loss": 0.0116,
      "step": 397
    },
    {
      "clip_ratio/high_max": 0.002045342462224653,
      "clip_ratio/high_mean": 0.0009971644794859458,
      "clip_ratio/low_mean": 0.0008318648015119834,
      "clip_ratio/low_min": 6.286709049163619e-05,
      "clip_ratio/region_mean": 0.001829029293730855,
      "epoch": 0.03714657380023217,
      "grad_norm": 0.12755998969078064,
      "learning_rate": 1e-06,
      "loss": 0.0006,
      "step": 398
    },
    {
      "clip_ratio/high_max": 0.0024093371248454787,
      "clip_ratio/high_mean": 0.0010071235046780203,
      "clip_ratio/low_mean": 0.0009501873009867268,
      "clip_ratio/low_min": 0.00013041961392445955,
      "clip_ratio/region_mean": 0.0019573108220356517,
      "epoch": 0.03723990690023275,
      "grad_norm": 0.13397479057312012,
      "learning_rate": 1e-06,
      "loss": 0.0351,
      "step": 399
    },
    {
      "clip_ratio/high_max": 0.0019218649940739851,
      "clip_ratio/high_mean": 0.0008739265640542726,
      "clip_ratio/low_mean": 0.00089426988051855,
      "clip_ratio/low_min": 6.989745543251047e-05,
      "clip_ratio/region_mean": 0.0017681964382063597,
      "epoch": 0.03733324000023333,
      "grad_norm": 0.1116487979888916,
      "learning_rate": 1e-06,
      "loss": -0.0038,
      "step": 400
    },
    {
      "clip_ratio/high_max": 0.0022813589894212782,
      "clip_ratio/high_mean": 0.0009934133413480595,
      "clip_ratio/low_mean": 0.0011305456682748627,
      "clip_ratio/low_min": 8.463089579890948e-05,
      "clip_ratio/region_mean": 0.0021239590641926043,
      "epoch": 0.037426573100233916,
      "grad_norm": 0.12167389690876007,
      "learning_rate": 1e-06,
      "loss": 0.0134,
      "step": 401
    },
    {
      "clip_ratio/high_max": 0.0027896390602109022,
      "clip_ratio/high_mean": 0.0011046835752495099,
      "clip_ratio/low_mean": 0.0009482977329753339,
      "clip_ratio/low_min": 8.5561519881594e-05,
      "clip_ratio/region_mean": 0.002052981326414738,
      "epoch": 0.0375199062002345,
      "grad_norm": 0.11247431486845016,
      "learning_rate": 1e-06,
      "loss": 0.0117,
      "step": 402
    },
    {
      "clip_ratio/high_max": 0.0024053056913544424,
      "clip_ratio/high_mean": 0.0010184167076658923,
      "clip_ratio/low_mean": 0.0011096590424131136,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002128075764630921,
      "epoch": 0.03761323930023508,
      "grad_norm": 0.1222907081246376,
      "learning_rate": 1e-06,
      "loss": 0.0198,
      "step": 403
    },
    {
      "clip_ratio/high_max": 0.002224021009169519,
      "clip_ratio/high_mean": 0.0010099315622937866,
      "clip_ratio/low_mean": 0.0010289443853253033,
      "clip_ratio/low_min": 0.00012426178545865696,
      "clip_ratio/region_mean": 0.0020388758966873866,
      "epoch": 0.037706572400235665,
      "grad_norm": 0.11835585534572601,
      "learning_rate": 1e-06,
      "loss": 0.0092,
      "step": 404
    },
    {
      "clip_ratio/high_max": 0.002185758152336348,
      "clip_ratio/high_mean": 0.0010172069050895516,
      "clip_ratio/low_mean": 0.0010902521971729584,
      "clip_ratio/low_min": 0.00017644204490352422,
      "clip_ratio/region_mean": 0.002107459142280277,
      "epoch": 0.03779990550023625,
      "grad_norm": 0.11552343517541885,
      "learning_rate": 1e-06,
      "loss": -0.002,
      "step": 405
    },
    {
      "clip_ratio/high_max": 0.0030390612155315466,
      "clip_ratio/high_mean": 0.001208569279697258,
      "clip_ratio/low_mean": 0.001038592014083406,
      "clip_ratio/low_min": 0.00013717379442823585,
      "clip_ratio/region_mean": 0.0022471613265224732,
      "epoch": 0.037893238600236835,
      "grad_norm": 0.11450153589248657,
      "learning_rate": 1e-06,
      "loss": -0.0371,
      "step": 406
    },
    {
      "clip_ratio/high_max": 0.002155105015845038,
      "clip_ratio/high_mean": 0.0008182993442460429,
      "clip_ratio/low_mean": 0.0009600231023796368,
      "clip_ratio/low_min": 0.00011936077498830855,
      "clip_ratio/region_mean": 0.0017783224466256797,
      "epoch": 0.03798657170023741,
      "grad_norm": 0.11137264221906662,
      "learning_rate": 1e-06,
      "loss": 0.0752,
      "step": 407
    },
    {
      "clip_ratio/high_max": 0.0023896176207927056,
      "clip_ratio/high_mean": 0.0010247544669255149,
      "clip_ratio/low_mean": 0.0011780979148170445,
      "clip_ratio/low_min": 0.00013312280771060614,
      "clip_ratio/region_mean": 0.00220285241084639,
      "epoch": 0.038079904800238,
      "grad_norm": 0.12629003822803497,
      "learning_rate": 1e-06,
      "loss": 0.0307,
      "step": 408
    },
    {
      "clip_ratio/high_max": 0.0023310889191634487,
      "clip_ratio/high_mean": 0.0010472496487636818,
      "clip_ratio/low_mean": 0.0010237017859253683,
      "clip_ratio/low_min": 0.00010384480447100941,
      "clip_ratio/region_mean": 0.002070951486530248,
      "epoch": 0.038173237900238584,
      "grad_norm": 0.12324889749288559,
      "learning_rate": 1e-06,
      "loss": -0.0035,
      "step": 409
    },
    {
      "clip_ratio/high_max": 0.0021046855981694534,
      "clip_ratio/high_mean": 0.0009924437017616583,
      "clip_ratio/low_mean": 0.0011546058158273809,
      "clip_ratio/low_min": 4.921210347674787e-05,
      "clip_ratio/region_mean": 0.002147049570339732,
      "epoch": 0.03826657100023917,
      "grad_norm": 0.1212676614522934,
      "learning_rate": 1e-06,
      "loss": 0.0439,
      "step": 410
    },
    {
      "clip_ratio/high_max": 0.0025673795462353155,
      "clip_ratio/high_mean": 0.0011265973189438228,
      "clip_ratio/low_mean": 0.0011353701302141417,
      "clip_ratio/low_min": 0.00013318741730472539,
      "clip_ratio/region_mean": 0.0022619674491579644,
      "epoch": 0.03835990410023975,
      "grad_norm": 0.11497417092323303,
      "learning_rate": 1e-06,
      "loss": 0.0238,
      "step": 411
    },
    {
      "clip_ratio/high_max": 0.0024536750788684003,
      "clip_ratio/high_mean": 0.0009998320310842246,
      "clip_ratio/low_mean": 0.0010761069715954363,
      "clip_ratio/low_min": 0.00011594409988902044,
      "clip_ratio/region_mean": 0.0020759389517479576,
      "epoch": 0.03845323720024033,
      "grad_norm": 0.11113645881414413,
      "learning_rate": 1e-06,
      "loss": -0.0057,
      "step": 412
    },
    {
      "clip_ratio/high_max": 0.002352974857785739,
      "clip_ratio/high_mean": 0.00101596657805203,
      "clip_ratio/low_mean": 0.001127457398979459,
      "clip_ratio/low_min": 9.757455154613126e-05,
      "clip_ratio/region_mean": 0.002143423967936542,
      "epoch": 0.03854657030024092,
      "grad_norm": 0.10741639137268066,
      "learning_rate": 1e-06,
      "loss": 0.0181,
      "step": 413
    },
    {
      "clip_ratio/high_max": 0.0025393421019543894,
      "clip_ratio/high_mean": 0.001066478731445386,
      "clip_ratio/low_mean": 0.0011650801043288084,
      "clip_ratio/low_min": 0.00013418069829640444,
      "clip_ratio/region_mean": 0.002231558828498237,
      "epoch": 0.038639903400241496,
      "grad_norm": 0.10366897284984589,
      "learning_rate": 1e-06,
      "loss": 0.0226,
      "step": 414
    },
    {
      "clip_ratio/high_max": 0.0022344187964336015,
      "clip_ratio/high_mean": 0.0010451171328895725,
      "clip_ratio/low_mean": 0.0010399218008387834,
      "clip_ratio/low_min": 0.0001321624231422902,
      "clip_ratio/region_mean": 0.0020850389410043135,
      "epoch": 0.03873323650024208,
      "grad_norm": 0.10847318172454834,
      "learning_rate": 1e-06,
      "loss": 0.0023,
      "step": 415
    },
    {
      "clip_ratio/high_max": 0.0025231009421986528,
      "clip_ratio/high_mean": 0.0010436738848511595,
      "clip_ratio/low_mean": 0.0012916867381136399,
      "clip_ratio/low_min": 0.00019523526589182438,
      "clip_ratio/region_mean": 0.002335360593860969,
      "epoch": 0.038826569600242666,
      "grad_norm": 0.11652623862028122,
      "learning_rate": 1e-06,
      "loss": -0.0004,
      "step": 416
    },
    {
      "clip_ratio/high_max": 0.0022899263276485726,
      "clip_ratio/high_mean": 0.0009768082582013449,
      "clip_ratio/low_mean": 0.001154935500380816,
      "clip_ratio/low_min": 0.00017526986448501702,
      "clip_ratio/region_mean": 0.0021317437203833833,
      "epoch": 0.03891990270024325,
      "grad_norm": 0.10895755887031555,
      "learning_rate": 1e-06,
      "loss": 0.0089,
      "step": 417
    },
    {
      "clip_ratio/high_max": 0.0021623237153107766,
      "clip_ratio/high_mean": 0.0009271793951484142,
      "clip_ratio/low_mean": 0.001203729523695074,
      "clip_ratio/low_min": 0.00014051249672775157,
      "clip_ratio/region_mean": 0.0021309089424903505,
      "epoch": 0.03901323580024383,
      "grad_norm": 0.11828435212373734,
      "learning_rate": 1e-06,
      "loss": 0.0487,
      "step": 418
    },
    {
      "clip_ratio/high_max": 0.0020629802565963473,
      "clip_ratio/high_mean": 0.0009097443526115967,
      "clip_ratio/low_mean": 0.0011997543842880987,
      "clip_ratio/low_min": 0.00012134482312831096,
      "clip_ratio/region_mean": 0.0021094987823744304,
      "epoch": 0.039106568900244415,
      "grad_norm": 0.1027655303478241,
      "learning_rate": 1e-06,
      "loss": 0.0329,
      "step": 419
    },
    {
      "clip_ratio/high_max": 0.002252902719192207,
      "clip_ratio/high_mean": 0.0009738856806507101,
      "clip_ratio/low_mean": 0.0013321080987225287,
      "clip_ratio/low_min": 7.121721318981145e-05,
      "clip_ratio/region_mean": 0.0023059937229845673,
      "epoch": 0.039199902000245,
      "grad_norm": 0.17782095074653625,
      "learning_rate": 1e-06,
      "loss": 0.0268,
      "step": 420
    },
    {
      "clip_ratio/high_max": 0.002589685194834601,
      "clip_ratio/high_mean": 0.0010109698450833093,
      "clip_ratio/low_mean": 0.0013040199009992648,
      "clip_ratio/low_min": 0.00014795976494497154,
      "clip_ratio/region_mean": 0.002314989746082574,
      "epoch": 0.039293235100245585,
      "grad_norm": 0.11937125027179718,
      "learning_rate": 1e-06,
      "loss": 0.0198,
      "step": 421
    },
    {
      "clip_ratio/high_max": 0.0022994001556071453,
      "clip_ratio/high_mean": 0.000989869935438037,
      "clip_ratio/low_mean": 0.0011434461157477926,
      "clip_ratio/low_min": 6.799359834985808e-05,
      "clip_ratio/region_mean": 0.0021333160184440203,
      "epoch": 0.039386568200246164,
      "grad_norm": 0.12590163946151733,
      "learning_rate": 1e-06,
      "loss": 0.0252,
      "step": 422
    },
    {
      "clip_ratio/high_max": 0.0020929700403939933,
      "clip_ratio/high_mean": 0.0009600345874787308,
      "clip_ratio/low_mean": 0.001167414080555318,
      "clip_ratio/low_min": 0.00016555865931877634,
      "clip_ratio/region_mean": 0.002127448591636494,
      "epoch": 0.03947990130024675,
      "grad_norm": 0.11396259814500809,
      "learning_rate": 1e-06,
      "loss": 0.0471,
      "step": 423
    },
    {
      "clip_ratio/high_max": 0.0025033290512510575,
      "clip_ratio/high_mean": 0.001124679885833757,
      "clip_ratio/low_mean": 0.0011718738132913131,
      "clip_ratio/low_min": 0.00011433269628469134,
      "clip_ratio/region_mean": 0.00229655369912507,
      "epoch": 0.039573234400247334,
      "grad_norm": 0.11035384982824326,
      "learning_rate": 1e-06,
      "loss": 0.0391,
      "step": 424
    },
    {
      "clip_ratio/high_max": 0.002575597885879688,
      "clip_ratio/high_mean": 0.0010167077452933881,
      "clip_ratio/low_mean": 0.001029267248668475,
      "clip_ratio/low_min": 6.282557842496317e-05,
      "clip_ratio/region_mean": 0.002045974979409948,
      "epoch": 0.03966656750024792,
      "grad_norm": 0.11969095468521118,
      "learning_rate": 1e-06,
      "loss": 0.036,
      "step": 425
    },
    {
      "clip_ratio/high_max": 0.0028100311537855305,
      "clip_ratio/high_mean": 0.0012184547013021074,
      "clip_ratio/low_mean": 0.0012659263993555214,
      "clip_ratio/low_min": 0.00010975159420922864,
      "clip_ratio/region_mean": 0.002484381118847523,
      "epoch": 0.0397599006002485,
      "grad_norm": 0.12384101748466492,
      "learning_rate": 1e-06,
      "loss": 0.0016,
      "step": 426
    },
    {
      "clip_ratio/high_max": 0.0027885406598215923,
      "clip_ratio/high_mean": 0.001222028222400695,
      "clip_ratio/low_mean": 0.0012854080523538869,
      "clip_ratio/low_min": 0.00016744929416745435,
      "clip_ratio/region_mean": 0.0025074362638406456,
      "epoch": 0.03985323370024908,
      "grad_norm": 0.1150302067399025,
      "learning_rate": 1e-06,
      "loss": 0.0071,
      "step": 427
    },
    {
      "clip_ratio/high_max": 0.0021578748419415206,
      "clip_ratio/high_mean": 0.0009818261132750195,
      "clip_ratio/low_mean": 0.001476924298913218,
      "clip_ratio/low_min": 0.00017322531493846327,
      "clip_ratio/region_mean": 0.0024587504303781316,
      "epoch": 0.03994656680024967,
      "grad_norm": 0.12892085313796997,
      "learning_rate": 1e-06,
      "loss": 0.0623,
      "step": 428
    },
    {
      "clip_ratio/high_max": 0.0024276287913380656,
      "clip_ratio/high_mean": 0.0010696872996049933,
      "clip_ratio/low_mean": 0.0011784744920078083,
      "clip_ratio/low_min": 0.0001868274212029064,
      "clip_ratio/region_mean": 0.002248161836178042,
      "epoch": 0.040039899900250246,
      "grad_norm": 0.11940957605838776,
      "learning_rate": 1e-06,
      "loss": 0.0254,
      "step": 429
    },
    {
      "clip_ratio/high_max": 0.002712379500735551,
      "clip_ratio/high_mean": 0.0011103753167844843,
      "clip_ratio/low_mean": 0.001316132471401943,
      "clip_ratio/low_min": 0.00014854518576612463,
      "clip_ratio/region_mean": 0.002426507846394088,
      "epoch": 0.04013323300025083,
      "grad_norm": 0.12025794386863708,
      "learning_rate": 1e-06,
      "loss": 0.0167,
      "step": 430
    },
    {
      "clip_ratio/high_max": 0.0021951302915113047,
      "clip_ratio/high_mean": 0.0009840695493039675,
      "clip_ratio/low_mean": 0.001477239806263242,
      "clip_ratio/low_min": 0.0002702295041672187,
      "clip_ratio/region_mean": 0.002461309341015294,
      "epoch": 0.04022656610025142,
      "grad_norm": 0.12111403793096542,
      "learning_rate": 1e-06,
      "loss": 0.0418,
      "step": 431
    },
    {
      "clip_ratio/high_max": 0.002914804055762943,
      "clip_ratio/high_mean": 0.0011710129620041698,
      "clip_ratio/low_mean": 0.0011693419237417402,
      "clip_ratio/low_min": 9.946343197952956e-05,
      "clip_ratio/region_mean": 0.002340354876650963,
      "epoch": 0.040319899200252,
      "grad_norm": 0.11317253857851028,
      "learning_rate": 1e-06,
      "loss": 0.0413,
      "step": 432
    },
    {
      "clip_ratio/high_max": 0.002791720755340066,
      "clip_ratio/high_mean": 0.001191430053950171,
      "clip_ratio/low_mean": 0.001183473963465076,
      "clip_ratio/low_min": 7.877407733758446e-05,
      "clip_ratio/region_mean": 0.0023749039246467873,
      "epoch": 0.04041323230025258,
      "grad_norm": 0.1236572116613388,
      "learning_rate": 1e-06,
      "loss": 0.0306,
      "step": 433
    },
    {
      "clip_ratio/high_max": 0.0026482223329367116,
      "clip_ratio/high_mean": 0.0011231598327867687,
      "clip_ratio/low_mean": 0.0010935265490843449,
      "clip_ratio/low_min": 9.633883337301086e-05,
      "clip_ratio/region_mean": 0.0022166864218888804,
      "epoch": 0.040506565400253165,
      "grad_norm": 0.11718609929084778,
      "learning_rate": 1e-06,
      "loss": -0.0033,
      "step": 434
    },
    {
      "clip_ratio/high_max": 0.002645078388013644,
      "clip_ratio/high_mean": 0.0011033074151782785,
      "clip_ratio/low_mean": 0.0012399249826557934,
      "clip_ratio/low_min": 0.0001457012076571118,
      "clip_ratio/region_mean": 0.0023432324451277964,
      "epoch": 0.04059989850025375,
      "grad_norm": 0.10465870797634125,
      "learning_rate": 1e-06,
      "loss": 0.0092,
      "step": 435
    },
    {
      "clip_ratio/high_max": 0.0031988687624107115,
      "clip_ratio/high_mean": 0.0013430521830741782,
      "clip_ratio/low_mean": 0.0010818801056302618,
      "clip_ratio/low_min": 6.306897284957813e-05,
      "clip_ratio/region_mean": 0.002424932266876567,
      "epoch": 0.040693231600254336,
      "grad_norm": 0.11486940830945969,
      "learning_rate": 1e-06,
      "loss": -0.0005,
      "step": 436
    },
    {
      "clip_ratio/high_max": 0.0026578874239930883,
      "clip_ratio/high_mean": 0.0010474859482201282,
      "clip_ratio/low_mean": 0.0014028800214873627,
      "clip_ratio/low_min": 9.14539323275676e-05,
      "clip_ratio/region_mean": 0.0024503660315531306,
      "epoch": 0.040786564700254914,
      "grad_norm": 0.11749535799026489,
      "learning_rate": 1e-06,
      "loss": 0.0493,
      "step": 437
    },
    {
      "clip_ratio/high_max": 0.002215251537563745,
      "clip_ratio/high_mean": 0.00098038495889341,
      "clip_ratio/low_mean": 0.001221110018377658,
      "clip_ratio/low_min": 0.00015379883734567557,
      "clip_ratio/region_mean": 0.0022014950081938878,
      "epoch": 0.0408798978002555,
      "grad_norm": 0.11227718740701675,
      "learning_rate": 1e-06,
      "loss": 0.0411,
      "step": 438
    },
    {
      "clip_ratio/high_max": 0.002576027167378925,
      "clip_ratio/high_mean": 0.001060488611983601,
      "clip_ratio/low_mean": 0.0012537051807157695,
      "clip_ratio/low_min": 6.072116866562283e-05,
      "clip_ratio/region_mean": 0.0023141937563195825,
      "epoch": 0.040973230900256084,
      "grad_norm": 0.10874490439891815,
      "learning_rate": 1e-06,
      "loss": 0.0374,
      "step": 439
    },
    {
      "clip_ratio/high_max": 0.0026765053044073284,
      "clip_ratio/high_mean": 0.0011153004743391648,
      "clip_ratio/low_mean": 0.0012127916088502388,
      "clip_ratio/low_min": 0.00022910187544766814,
      "clip_ratio/region_mean": 0.002328092115931213,
      "epoch": 0.04106656400025666,
      "grad_norm": 0.12040571868419647,
      "learning_rate": 1e-06,
      "loss": 0.0214,
      "step": 440
    },
    {
      "clip_ratio/high_max": 0.0024024201338761486,
      "clip_ratio/high_mean": 0.0011041076795663685,
      "clip_ratio/low_mean": 0.0014185359432303812,
      "clip_ratio/low_min": 0.0002264940703753382,
      "clip_ratio/region_mean": 0.0025226436409866437,
      "epoch": 0.04115989710025725,
      "grad_norm": 0.12071618437767029,
      "learning_rate": 1e-06,
      "loss": 0.0663,
      "step": 441
    },
    {
      "clip_ratio/high_max": 0.0032360234326915815,
      "clip_ratio/high_mean": 0.0013241096385172568,
      "clip_ratio/low_mean": 0.0010865663571166806,
      "clip_ratio/low_min": 5.424283881438896e-05,
      "clip_ratio/region_mean": 0.0024106759155984037,
      "epoch": 0.04125323020025783,
      "grad_norm": 0.1231648400425911,
      "learning_rate": 1e-06,
      "loss": -0.0089,
      "step": 442
    },
    {
      "clip_ratio/high_max": 0.002679995115613565,
      "clip_ratio/high_mean": 0.001158734665295924,
      "clip_ratio/low_mean": 0.0014259270774346078,
      "clip_ratio/low_min": 0.0002741580392466858,
      "clip_ratio/region_mean": 0.0025846617863862775,
      "epoch": 0.04134656330025842,
      "grad_norm": 0.1178274005651474,
      "learning_rate": 1e-06,
      "loss": 0.0266,
      "step": 443
    },
    {
      "clip_ratio/high_max": 0.0025484498910373077,
      "clip_ratio/high_mean": 0.0010472833000676474,
      "clip_ratio/low_mean": 0.0013999972943565808,
      "clip_ratio/low_min": 6.0549829868250526e-05,
      "clip_ratio/region_mean": 0.002447280625347048,
      "epoch": 0.041439896400258996,
      "grad_norm": 0.12369096279144287,
      "learning_rate": 1e-06,
      "loss": 0.0736,
      "step": 444
    },
    {
      "clip_ratio/high_max": 0.0026862284175876994,
      "clip_ratio/high_mean": 0.0011537462596606929,
      "clip_ratio/low_mean": 0.0011293766892777057,
      "clip_ratio/low_min": 0.00019748830254684435,
      "clip_ratio/region_mean": 0.0022831229434814304,
      "epoch": 0.04153322950025958,
      "grad_norm": 0.10899684578180313,
      "learning_rate": 1e-06,
      "loss": 0.0253,
      "step": 445
    },
    {
      "clip_ratio/high_max": 0.0029682034291909076,
      "clip_ratio/high_mean": 0.001209483458296745,
      "clip_ratio/low_mean": 0.0011931194967473857,
      "clip_ratio/low_min": 0.0002559849999670405,
      "clip_ratio/region_mean": 0.0024026029277592897,
      "epoch": 0.04162656260026017,
      "grad_norm": 0.1255938857793808,
      "learning_rate": 1e-06,
      "loss": 0.0461,
      "step": 446
    },
    {
      "clip_ratio/high_max": 0.003150494012515992,
      "clip_ratio/high_mean": 0.001252271787961945,
      "clip_ratio/low_mean": 0.0011317522330500651,
      "clip_ratio/low_min": 9.059268904820783e-05,
      "clip_ratio/region_mean": 0.0023840240100980736,
      "epoch": 0.04171989570026075,
      "grad_norm": 0.1184663474559784,
      "learning_rate": 1e-06,
      "loss": 0.0214,
      "step": 447
    },
    {
      "clip_ratio/high_max": 0.002483110685716383,
      "clip_ratio/high_mean": 0.001090563844627468,
      "clip_ratio/low_mean": 0.0013386291830101982,
      "clip_ratio/low_min": 0.00026584475199342705,
      "clip_ratio/region_mean": 0.0024291930385516025,
      "epoch": 0.04181322880026133,
      "grad_norm": 0.12208592146635056,
      "learning_rate": 1e-06,
      "loss": 0.0493,
      "step": 448
    },
    {
      "clip_ratio/high_max": 0.0027344242625986226,
      "clip_ratio/high_mean": 0.0011705778779287357,
      "clip_ratio/low_mean": 0.0013157717730791774,
      "clip_ratio/low_min": 0.0002751404063019436,
      "clip_ratio/region_mean": 0.0024863496655598283,
      "epoch": 0.041906561900261916,
      "grad_norm": 0.1273927390575409,
      "learning_rate": 1e-06,
      "loss": 0.0414,
      "step": 449
    },
    {
      "clip_ratio/high_max": 0.0028503137145889923,
      "clip_ratio/high_mean": 0.0010730548146966612,
      "clip_ratio/low_mean": 0.0013499146625690628,
      "clip_ratio/low_min": 0.00015746967983432114,
      "clip_ratio/region_mean": 0.0024229694245150313,
      "epoch": 0.0419998950002625,
      "grad_norm": 0.12964798510074615,
      "learning_rate": 1e-06,
      "loss": 0.0579,
      "step": 450
    },
    {
      "clip_ratio/high_max": 0.002570183205534704,
      "clip_ratio/high_mean": 0.0010310067773389164,
      "clip_ratio/low_mean": 0.0013300511127454229,
      "clip_ratio/low_min": 0.00015957068808347685,
      "clip_ratio/region_mean": 0.0023610578864463605,
      "epoch": 0.042093228100263086,
      "grad_norm": 0.11883798986673355,
      "learning_rate": 1e-06,
      "loss": 0.0696,
      "step": 451
    },
    {
      "clip_ratio/high_max": 0.0028321592617430724,
      "clip_ratio/high_mean": 0.001186878052976681,
      "clip_ratio/low_mean": 0.001336474819254363,
      "clip_ratio/low_min": 0.00016158549351530382,
      "clip_ratio/region_mean": 0.002523352872231044,
      "epoch": 0.042186561200263664,
      "grad_norm": 0.12103655934333801,
      "learning_rate": 1e-06,
      "loss": 0.0339,
      "step": 452
    },
    {
      "clip_ratio/high_max": 0.002958241391752381,
      "clip_ratio/high_mean": 0.0012343205307843164,
      "clip_ratio/low_mean": 0.0010745342697191518,
      "clip_ratio/low_min": 8.26233699626755e-05,
      "clip_ratio/region_mean": 0.002308854767761659,
      "epoch": 0.04227989430026425,
      "grad_norm": 0.10631893575191498,
      "learning_rate": 1e-06,
      "loss": 0.022,
      "step": 453
    },
    {
      "clip_ratio/high_max": 0.002495729553629644,
      "clip_ratio/high_mean": 0.0010520065770833753,
      "clip_ratio/low_mean": 0.001160851421445841,
      "clip_ratio/low_min": 0.00011522226213855902,
      "clip_ratio/region_mean": 0.0022128580530988984,
      "epoch": 0.042373227400264835,
      "grad_norm": 0.1074850857257843,
      "learning_rate": 1e-06,
      "loss": 0.0212,
      "step": 454
    },
    {
      "clip_ratio/high_max": 0.0023758730676490813,
      "clip_ratio/high_mean": 0.0010872426682908554,
      "clip_ratio/low_mean": 0.0012397541395330336,
      "clip_ratio/low_min": 0.0001317692640441237,
      "clip_ratio/region_mean": 0.002326996785996016,
      "epoch": 0.04246656050026541,
      "grad_norm": 0.11900975555181503,
      "learning_rate": 1e-06,
      "loss": 0.0555,
      "step": 455
    },
    {
      "clip_ratio/high_max": 0.002852059551514685,
      "clip_ratio/high_mean": 0.0013110979489283636,
      "clip_ratio/low_mean": 0.001148153722169809,
      "clip_ratio/low_min": 8.584175884607248e-05,
      "clip_ratio/region_mean": 0.002459251663822215,
      "epoch": 0.042559893600266,
      "grad_norm": 0.12325873970985413,
      "learning_rate": 1e-06,
      "loss": 0.0415,
      "step": 456
    },
    {
      "clip_ratio/high_max": 0.0028292798888287507,
      "clip_ratio/high_mean": 0.0013528350209526252,
      "clip_ratio/low_mean": 0.0012471344380173832,
      "clip_ratio/low_min": 0.0001571071770740673,
      "clip_ratio/region_mean": 0.0025999694626079872,
      "epoch": 0.04265322670026658,
      "grad_norm": 0.12609592080116272,
      "learning_rate": 1e-06,
      "loss": 0.049,
      "step": 457
    },
    {
      "clip_ratio/high_max": 0.002836095947714057,
      "clip_ratio/high_mean": 0.001192644518596353,
      "clip_ratio/low_mean": 0.001219635803863639,
      "clip_ratio/low_min": 0.00014255207497626543,
      "clip_ratio/region_mean": 0.002412280264252331,
      "epoch": 0.04274655980026717,
      "grad_norm": 0.11276479810476303,
      "learning_rate": 1e-06,
      "loss": 0.0211,
      "step": 458
    },
    {
      "clip_ratio/high_max": 0.002672570895811077,
      "clip_ratio/high_mean": 0.0013578443249571137,
      "clip_ratio/low_mean": 0.0011806834845629055,
      "clip_ratio/low_min": 0.00014179004028846975,
      "clip_ratio/region_mean": 0.002538527754950337,
      "epoch": 0.04283989290026775,
      "grad_norm": 0.11869664490222931,
      "learning_rate": 1e-06,
      "loss": -0.0114,
      "step": 459
    },
    {
      "clip_ratio/high_max": 0.002805124473525211,
      "clip_ratio/high_mean": 0.001244487488293089,
      "clip_ratio/low_mean": 0.0012005355893052183,
      "clip_ratio/low_min": 0.00010051603203464765,
      "clip_ratio/region_mean": 0.0024450231285300106,
      "epoch": 0.04293322600026833,
      "grad_norm": 0.11884006857872009,
      "learning_rate": 1e-06,
      "loss": 0.0041,
      "step": 460
    },
    {
      "clip_ratio/high_max": 0.0032767006050562486,
      "clip_ratio/high_mean": 0.0013355009250517469,
      "clip_ratio/low_mean": 0.001249744036613265,
      "clip_ratio/low_min": 9.217625211022096e-05,
      "clip_ratio/region_mean": 0.002585245019872673,
      "epoch": 0.04302655910026892,
      "grad_norm": 0.1172538697719574,
      "learning_rate": 1e-06,
      "loss": -0.0025,
      "step": 461
    },
    {
      "clip_ratio/high_max": 0.002603926412120927,
      "clip_ratio/high_mean": 0.0011304153340461198,
      "clip_ratio/low_mean": 0.0012496151612140238,
      "clip_ratio/low_min": 0.00015021450053609442,
      "clip_ratio/region_mean": 0.0023800305207259953,
      "epoch": 0.0431198922002695,
      "grad_norm": 0.11923906952142715,
      "learning_rate": 1e-06,
      "loss": 0.0108,
      "step": 462
    },
    {
      "clip_ratio/high_max": 0.0026303007907699794,
      "clip_ratio/high_mean": 0.0011468100146885263,
      "clip_ratio/low_mean": 0.0013169388294045348,
      "clip_ratio/low_min": 0.0002506978089513723,
      "clip_ratio/region_mean": 0.002463748838636093,
      "epoch": 0.04321322530027008,
      "grad_norm": 0.12104181200265884,
      "learning_rate": 1e-06,
      "loss": 0.0573,
      "step": 463
    },
    {
      "clip_ratio/high_max": 0.002296301092428621,
      "clip_ratio/high_mean": 0.0010385345449321903,
      "clip_ratio/low_mean": 0.0012297647608647821,
      "clip_ratio/low_min": 0.00018888493832491804,
      "clip_ratio/region_mean": 0.0022682993512717076,
      "epoch": 0.043306558400270666,
      "grad_norm": 0.10575677454471588,
      "learning_rate": 1e-06,
      "loss": 0.0516,
      "step": 464
    },
    {
      "clip_ratio/high_max": 0.0030926807958167046,
      "clip_ratio/high_mean": 0.001284816815314116,
      "clip_ratio/low_mean": 0.001207638833875535,
      "clip_ratio/low_min": 4.7732088205520995e-05,
      "clip_ratio/region_mean": 0.002492455685569439,
      "epoch": 0.04339989150027125,
      "grad_norm": 0.11239206045866013,
      "learning_rate": 1e-06,
      "loss": 0.0179,
      "step": 465
    },
    {
      "clip_ratio/high_max": 0.002655661228345707,
      "clip_ratio/high_mean": 0.001172369175037602,
      "clip_ratio/low_mean": 0.0011677321235765703,
      "clip_ratio/low_min": 2.9391017960733734e-05,
      "clip_ratio/region_mean": 0.0023401012949761935,
      "epoch": 0.04349322460027183,
      "grad_norm": 0.12310929596424103,
      "learning_rate": 1e-06,
      "loss": 0.01,
      "step": 466
    },
    {
      "clip_ratio/high_max": 0.0029448211134877056,
      "clip_ratio/high_mean": 0.0013379647753026802,
      "clip_ratio/low_mean": 0.0014643511385656893,
      "clip_ratio/low_min": 0.00027341156874172157,
      "clip_ratio/region_mean": 0.0028023159684380516,
      "epoch": 0.043586557700272414,
      "grad_norm": 0.11911243200302124,
      "learning_rate": 1e-06,
      "loss": 0.0192,
      "step": 467
    },
    {
      "clip_ratio/high_max": 0.002272747464303393,
      "clip_ratio/high_mean": 0.0010893298967857845,
      "clip_ratio/low_mean": 0.001343431376881199,
      "clip_ratio/low_min": 0.0002126211711583892,
      "clip_ratio/region_mean": 0.0024327613136847503,
      "epoch": 0.043679890800273,
      "grad_norm": 0.107632115483284,
      "learning_rate": 1e-06,
      "loss": 0.0168,
      "step": 468
    },
    {
      "clip_ratio/high_max": 0.0028668950690189376,
      "clip_ratio/high_mean": 0.0013185363059164956,
      "clip_ratio/low_mean": 0.001355787411739584,
      "clip_ratio/low_min": 0.0002422854468022706,
      "clip_ratio/region_mean": 0.002674323732207995,
      "epoch": 0.043773223900273585,
      "grad_norm": 0.12274787575006485,
      "learning_rate": 1e-06,
      "loss": 0.0124,
      "step": 469
    },
    {
      "clip_ratio/high_max": 0.0028060728145646863,
      "clip_ratio/high_mean": 0.0012101395332138054,
      "clip_ratio/low_mean": 0.0013300097270985134,
      "clip_ratio/low_min": 0.00014283526434155647,
      "clip_ratio/region_mean": 0.0025401492894161493,
      "epoch": 0.04386655700027416,
      "grad_norm": 0.11154117435216904,
      "learning_rate": 1e-06,
      "loss": 0.0448,
      "step": 470
    },
    {
      "clip_ratio/high_max": 0.0027159384699189104,
      "clip_ratio/high_mean": 0.0012539946110337041,
      "clip_ratio/low_mean": 0.0011513183235365432,
      "clip_ratio/low_min": 9.54349397943588e-05,
      "clip_ratio/region_mean": 0.0024053129163803533,
      "epoch": 0.04395989010027475,
      "grad_norm": 0.11300830543041229,
      "learning_rate": 1e-06,
      "loss": 0.0026,
      "step": 471
    },
    {
      "clip_ratio/high_max": 0.002835048217093572,
      "clip_ratio/high_mean": 0.0011275003635091707,
      "clip_ratio/low_mean": 0.0011441112801549025,
      "clip_ratio/low_min": 0.00011486600669741165,
      "clip_ratio/region_mean": 0.002271611650940031,
      "epoch": 0.044053223200275334,
      "grad_norm": 0.1108628660440445,
      "learning_rate": 1e-06,
      "loss": -0.0016,
      "step": 472
    },
    {
      "clip_ratio/high_max": 0.0023499372400692664,
      "clip_ratio/high_mean": 0.001188060636195587,
      "clip_ratio/low_mean": 0.0013718581467401236,
      "clip_ratio/low_min": 0.00015301451276172884,
      "clip_ratio/region_mean": 0.0025599187865736894,
      "epoch": 0.04414655630027592,
      "grad_norm": 0.1288527101278305,
      "learning_rate": 1e-06,
      "loss": 0.0093,
      "step": 473
    },
    {
      "clip_ratio/high_max": 0.002598185070382897,
      "clip_ratio/high_mean": 0.0011076146201958181,
      "clip_ratio/low_mean": 0.001352495892206207,
      "clip_ratio/low_min": 0.00014286307487054728,
      "clip_ratio/region_mean": 0.002460110503307078,
      "epoch": 0.0442398894002765,
      "grad_norm": 0.11513441056013107,
      "learning_rate": 1e-06,
      "loss": 0.0276,
      "step": 474
    },
    {
      "clip_ratio/high_max": 0.0031010133025120012,
      "clip_ratio/high_mean": 0.0013350563858693931,
      "clip_ratio/low_mean": 0.0012915327497466933,
      "clip_ratio/low_min": 0.00011129882477689534,
      "clip_ratio/region_mean": 0.002626589142892044,
      "epoch": 0.04433322250027708,
      "grad_norm": 0.11405772715806961,
      "learning_rate": 1e-06,
      "loss": 0.0131,
      "step": 475
    },
    {
      "clip_ratio/high_max": 0.002686013547645416,
      "clip_ratio/high_mean": 0.001177495127194561,
      "clip_ratio/low_mean": 0.0014041948670637794,
      "clip_ratio/low_min": 0.00011557006655493751,
      "clip_ratio/region_mean": 0.002581689986982383,
      "epoch": 0.04442655560027767,
      "grad_norm": 0.11358251422643661,
      "learning_rate": 1e-06,
      "loss": 0.028,
      "step": 476
    },
    {
      "clip_ratio/high_max": 0.0026814865123014897,
      "clip_ratio/high_mean": 0.0012361757762846537,
      "clip_ratio/low_mean": 0.0012965224614163162,
      "clip_ratio/low_min": 0.00013232356832304504,
      "clip_ratio/region_mean": 0.0025326982213300653,
      "epoch": 0.04451988870027825,
      "grad_norm": 0.11191324889659882,
      "learning_rate": 1e-06,
      "loss": -0.0258,
      "step": 477
    },
    {
      "clip_ratio/high_max": 0.0023534242245659698,
      "clip_ratio/high_mean": 0.0010918897951341933,
      "clip_ratio/low_mean": 0.0013543551649490837,
      "clip_ratio/low_min": 0.000266472206931212,
      "clip_ratio/region_mean": 0.002446244929160457,
      "epoch": 0.04461322180027883,
      "grad_norm": 0.11773058772087097,
      "learning_rate": 1e-06,
      "loss": 0.0327,
      "step": 478
    },
    {
      "clip_ratio/high_max": 0.0031445046988665126,
      "clip_ratio/high_mean": 0.001196626322780503,
      "clip_ratio/low_mean": 0.0013966872211312875,
      "clip_ratio/low_min": 3.272273443144513e-05,
      "clip_ratio/region_mean": 0.002593313518445939,
      "epoch": 0.044706554900279416,
      "grad_norm": 0.10964041948318481,
      "learning_rate": 1e-06,
      "loss": 0.0529,
      "step": 479
    },
    {
      "clip_ratio/high_max": 0.0025364956745761447,
      "clip_ratio/high_mean": 0.0011413568099669646,
      "clip_ratio/low_mean": 0.00119198762877204,
      "clip_ratio/low_min": 0.00012087325376342051,
      "clip_ratio/region_mean": 0.0023333444114541635,
      "epoch": 0.04479988800028,
      "grad_norm": 0.10653676837682724,
      "learning_rate": 1e-06,
      "loss": 0.0191,
      "step": 480
    },
    {
      "clip_ratio/high_max": 0.002942748680652585,
      "clip_ratio/high_mean": 0.0011751176934922114,
      "clip_ratio/low_mean": 0.001280921722354833,
      "clip_ratio/low_min": 0.00013952586596133187,
      "clip_ratio/region_mean": 0.0024560394522268325,
      "epoch": 0.04489322110028058,
      "grad_norm": 0.11577119678258896,
      "learning_rate": 1e-06,
      "loss": 0.0199,
      "step": 481
    },
    {
      "clip_ratio/high_max": 0.0029228743296698667,
      "clip_ratio/high_mean": 0.0013020505066378973,
      "clip_ratio/low_mean": 0.0012381026572256815,
      "clip_ratio/low_min": 0.00011427838308009086,
      "clip_ratio/region_mean": 0.0025401531893294305,
      "epoch": 0.044986554200281165,
      "grad_norm": 0.11827868968248367,
      "learning_rate": 1e-06,
      "loss": 0.0241,
      "step": 482
    },
    {
      "clip_ratio/high_max": 0.002798367386276368,
      "clip_ratio/high_mean": 0.0012768863125529606,
      "clip_ratio/low_mean": 0.0013054129412921611,
      "clip_ratio/low_min": 0.0001997903764276998,
      "clip_ratio/region_mean": 0.002582299232017249,
      "epoch": 0.04507988730028175,
      "grad_norm": 0.11663104593753815,
      "learning_rate": 1e-06,
      "loss": 0.0609,
      "step": 483
    },
    {
      "clip_ratio/high_max": 0.0031021843024063855,
      "clip_ratio/high_mean": 0.0011812180855486076,
      "clip_ratio/low_mean": 0.00136826848029159,
      "clip_ratio/low_min": 0.00015387914936582092,
      "clip_ratio/region_mean": 0.0025494865840300918,
      "epoch": 0.045173220400282335,
      "grad_norm": 0.12728598713874817,
      "learning_rate": 1e-06,
      "loss": 0.0032,
      "step": 484
    },
    {
      "clip_ratio/high_max": 0.0026322743942728266,
      "clip_ratio/high_mean": 0.0012486109917517751,
      "clip_ratio/low_mean": 0.0014192188828019425,
      "clip_ratio/low_min": 0.00014572951022273628,
      "clip_ratio/region_mean": 0.002667829830897972,
      "epoch": 0.04526655350028291,
      "grad_norm": 0.11983053386211395,
      "learning_rate": 1e-06,
      "loss": 0.0689,
      "step": 485
    },
    {
      "clip_ratio/high_max": 0.0026598095428198576,
      "clip_ratio/high_mean": 0.001260376116988482,
      "clip_ratio/low_mean": 0.0012419340982887661,
      "clip_ratio/low_min": 0.0001565280108479783,
      "clip_ratio/region_mean": 0.002502310228010174,
      "epoch": 0.0453598866002835,
      "grad_norm": 0.11784526705741882,
      "learning_rate": 1e-06,
      "loss": 0.0216,
      "step": 486
    },
    {
      "clip_ratio/high_max": 0.003105874486209359,
      "clip_ratio/high_mean": 0.0012500214343162952,
      "clip_ratio/low_mean": 0.0012417898742569378,
      "clip_ratio/low_min": 0.0002304073650520877,
      "clip_ratio/region_mean": 0.002491811290383339,
      "epoch": 0.045453219700284084,
      "grad_norm": 0.09820187836885452,
      "learning_rate": 1e-06,
      "loss": 0.0148,
      "step": 487
    },
    {
      "clip_ratio/high_max": 0.0026437555425218306,
      "clip_ratio/high_mean": 0.001253314498171676,
      "clip_ratio/low_mean": 0.0012455648575269151,
      "clip_ratio/low_min": 0.00010951254898827756,
      "clip_ratio/region_mean": 0.0024988793302327394,
      "epoch": 0.04554655280028467,
      "grad_norm": 0.11951355636119843,
      "learning_rate": 1e-06,
      "loss": -0.0125,
      "step": 488
    },
    {
      "clip_ratio/high_max": 0.002886282483814284,
      "clip_ratio/high_mean": 0.0012024885836581234,
      "clip_ratio/low_mean": 0.0015162914132815786,
      "clip_ratio/low_min": 0.00014764429579372518,
      "clip_ratio/region_mean": 0.002718779993301723,
      "epoch": 0.04563988590028525,
      "grad_norm": 0.10836157947778702,
      "learning_rate": 1e-06,
      "loss": 0.0558,
      "step": 489
    },
    {
      "clip_ratio/high_max": 0.0027689805065165274,
      "clip_ratio/high_mean": 0.0011672068903862964,
      "clip_ratio/low_mean": 0.0014792614420002792,
      "clip_ratio/low_min": 0.0001762853216860094,
      "clip_ratio/region_mean": 0.002646468310558703,
      "epoch": 0.04573321900028583,
      "grad_norm": 0.1177634596824646,
      "learning_rate": 1e-06,
      "loss": 0.0344,
      "step": 490
    },
    {
      "clip_ratio/high_max": 0.002386733300227206,
      "clip_ratio/high_mean": 0.0011448130971984938,
      "clip_ratio/low_mean": 0.0013705583623959683,
      "clip_ratio/low_min": 7.598549564136192e-05,
      "clip_ratio/region_mean": 0.0025153713795589283,
      "epoch": 0.04582655210028642,
      "grad_norm": 0.1204015240073204,
      "learning_rate": 1e-06,
      "loss": -0.0049,
      "step": 491
    },
    {
      "clip_ratio/high_max": 0.002715635906497482,
      "clip_ratio/high_mean": 0.001149334741057828,
      "clip_ratio/low_mean": 0.0013135757508280221,
      "clip_ratio/low_min": 0.00010997715617122594,
      "clip_ratio/region_mean": 0.0024629104154882953,
      "epoch": 0.045919885200286996,
      "grad_norm": 0.11512818932533264,
      "learning_rate": 1e-06,
      "loss": 0.0142,
      "step": 492
    },
    {
      "clip_ratio/high_max": 0.002689068001927808,
      "clip_ratio/high_mean": 0.0012231886175868567,
      "clip_ratio/low_mean": 0.0014610709076805506,
      "clip_ratio/low_min": 0.0002445696973154554,
      "clip_ratio/region_mean": 0.002684259496163577,
      "epoch": 0.04601321830028758,
      "grad_norm": 0.11573384702205658,
      "learning_rate": 1e-06,
      "loss": 0.0572,
      "step": 493
    },
    {
      "clip_ratio/high_max": 0.0024459760170429945,
      "clip_ratio/high_mean": 0.0010156796051887795,
      "clip_ratio/low_mean": 0.001382606500555994,
      "clip_ratio/low_min": 0.00022269248074735515,
      "clip_ratio/region_mean": 0.0023982860293472186,
      "epoch": 0.046106551400288166,
      "grad_norm": 0.10767379403114319,
      "learning_rate": 1e-06,
      "loss": 0.0276,
      "step": 494
    },
    {
      "clip_ratio/high_max": 0.0024828405294101685,
      "clip_ratio/high_mean": 0.0010891584879573202,
      "clip_ratio/low_mean": 0.001420930308086099,
      "clip_ratio/low_min": 0.00016016650988603942,
      "clip_ratio/region_mean": 0.0025100888015003875,
      "epoch": 0.04619988450028875,
      "grad_norm": 0.10432136803865433,
      "learning_rate": 1e-06,
      "loss": -0.0055,
      "step": 495
    },
    {
      "clip_ratio/high_max": 0.0029428731504594907,
      "clip_ratio/high_mean": 0.001489866404881468,
      "clip_ratio/low_mean": 0.0011714839674823452,
      "clip_ratio/low_min": 6.932638461876195e-05,
      "clip_ratio/region_mean": 0.0026613504014676437,
      "epoch": 0.04629321760028933,
      "grad_norm": 0.12726308405399323,
      "learning_rate": 1e-06,
      "loss": -0.0296,
      "step": 496
    },
    {
      "clip_ratio/high_max": 0.0022470306648756377,
      "clip_ratio/high_mean": 0.0010053157275251579,
      "clip_ratio/low_mean": 0.001660815134528093,
      "clip_ratio/low_min": 0.00039368517445836915,
      "clip_ratio/region_mean": 0.0026661308656912297,
      "epoch": 0.046386550700289915,
      "grad_norm": 0.12325713038444519,
      "learning_rate": 1e-06,
      "loss": 0.089,
      "step": 497
    },
    {
      "clip_ratio/high_max": 0.00275458848773269,
      "clip_ratio/high_mean": 0.0011616728334047366,
      "clip_ratio/low_mean": 0.0012593953797477297,
      "clip_ratio/low_min": 0.00014403153181774542,
      "clip_ratio/region_mean": 0.0024210681585827842,
      "epoch": 0.0464798838002905,
      "grad_norm": 0.11283209919929504,
      "learning_rate": 1e-06,
      "loss": 0.0357,
      "step": 498
    },
    {
      "clip_ratio/high_max": 0.0027246444442425855,
      "clip_ratio/high_mean": 0.001272648663871223,
      "clip_ratio/low_mean": 0.0014084099711908493,
      "clip_ratio/low_min": 0.0001263133617612766,
      "clip_ratio/region_mean": 0.0026810586714418605,
      "epoch": 0.046573216900291085,
      "grad_norm": 0.1395314782857895,
      "learning_rate": 1e-06,
      "loss": 0.0022,
      "step": 499
    },
    {
      "clip_ratio/high_max": 0.002887615963118151,
      "clip_ratio/high_mean": 0.0012879715504823253,
      "clip_ratio/low_mean": 0.001091747566988488,
      "clip_ratio/low_min": 7.684786487516249e-05,
      "clip_ratio/region_mean": 0.0023797191388439387,
      "epoch": 0.046666550000291664,
      "grad_norm": 0.10928663611412048,
      "learning_rate": 1e-06,
      "loss": -0.0092,
      "step": 500
    },
    {
      "clip_ratio/high_max": 0.003059794929868076,
      "clip_ratio/high_mean": 0.0013452258026518393,
      "clip_ratio/low_mean": 0.0012817439892387483,
      "clip_ratio/low_min": 0.00017086114530684426,
      "clip_ratio/region_mean": 0.0026269697918905877,
      "epoch": 0.04675988310029225,
      "grad_norm": 0.11967866867780685,
      "learning_rate": 1e-06,
      "loss": 0.0136,
      "step": 501
    },
    {
      "clip_ratio/high_max": 0.003019440388015937,
      "clip_ratio/high_mean": 0.0013740912872890476,
      "clip_ratio/low_mean": 0.001185422788694268,
      "clip_ratio/low_min": 0.000181762774445815,
      "clip_ratio/region_mean": 0.0025595141123631038,
      "epoch": 0.046853216200292834,
      "grad_norm": 0.11514464765787125,
      "learning_rate": 1e-06,
      "loss": -0.0493,
      "step": 502
    },
    {
      "clip_ratio/high_max": 0.0028277754827286117,
      "clip_ratio/high_mean": 0.001221134061779594,
      "clip_ratio/low_mean": 0.0012805835831386503,
      "clip_ratio/low_min": 0.00010841424591490068,
      "clip_ratio/region_mean": 0.0025017176594701596,
      "epoch": 0.04694654930029342,
      "grad_norm": 0.11402399837970734,
      "learning_rate": 1e-06,
      "loss": -0.0117,
      "step": 503
    },
    {
      "clip_ratio/high_max": 0.002857549501641188,
      "clip_ratio/high_mean": 0.0012763088379870169,
      "clip_ratio/low_mean": 0.0014413449353014585,
      "clip_ratio/low_min": 0.00015726114997960394,
      "clip_ratio/region_mean": 0.0027176537550985813,
      "epoch": 0.047039882400294,
      "grad_norm": 0.1121758371591568,
      "learning_rate": 1e-06,
      "loss": 0.0039,
      "step": 504
    },
    {
      "clip_ratio/high_max": 0.002667604901944287,
      "clip_ratio/high_mean": 0.0011350900822435506,
      "clip_ratio/low_mean": 0.0012854438318754546,
      "clip_ratio/low_min": 0.00011270669983787229,
      "clip_ratio/region_mean": 0.002420533914119005,
      "epoch": 0.04713321550029458,
      "grad_norm": 0.12903131544589996,
      "learning_rate": 1e-06,
      "loss": 0.0411,
      "step": 505
    },
    {
      "clip_ratio/high_max": 0.002416642746538855,
      "clip_ratio/high_mean": 0.0009763216694409493,
      "clip_ratio/low_mean": 0.0014641867419413757,
      "clip_ratio/low_min": 0.0002386602445767494,
      "clip_ratio/region_mean": 0.0024405084041063674,
      "epoch": 0.04722654860029517,
      "grad_norm": 0.10790254175662994,
      "learning_rate": 1e-06,
      "loss": 0.0784,
      "step": 506
    },
    {
      "clip_ratio/high_max": 0.002613978707813658,
      "clip_ratio/high_mean": 0.0011900486970262136,
      "clip_ratio/low_mean": 0.0014505546205327846,
      "clip_ratio/low_min": 0.00029041344441793626,
      "clip_ratio/region_mean": 0.002640603284817189,
      "epoch": 0.047319881700295746,
      "grad_norm": 0.11755881458520889,
      "learning_rate": 1e-06,
      "loss": 0.0575,
      "step": 507
    },
    {
      "clip_ratio/high_max": 0.002734697329287883,
      "clip_ratio/high_mean": 0.0012349998651188798,
      "clip_ratio/low_mean": 0.0015100925265869591,
      "clip_ratio/low_min": 8.998259727377445e-05,
      "clip_ratio/region_mean": 0.002745092337136157,
      "epoch": 0.04741321480029633,
      "grad_norm": 0.12109041213989258,
      "learning_rate": 1e-06,
      "loss": -0.0047,
      "step": 508
    },
    {
      "clip_ratio/high_max": 0.002644393032824155,
      "clip_ratio/high_mean": 0.0011360921525920276,
      "clip_ratio/low_mean": 0.0013230078657215927,
      "clip_ratio/low_min": 0.00015327829714806285,
      "clip_ratio/region_mean": 0.0024590999892097898,
      "epoch": 0.04750654790029692,
      "grad_norm": 0.11833036690950394,
      "learning_rate": 1e-06,
      "loss": 0.0366,
      "step": 509
    },
    {
      "clip_ratio/high_max": 0.0030175659630913287,
      "clip_ratio/high_mean": 0.0012385812806314789,
      "clip_ratio/low_mean": 0.0016291326901409775,
      "clip_ratio/low_min": 0.00031713534554000944,
      "clip_ratio/region_mean": 0.0028677139634964988,
      "epoch": 0.0475998810002975,
      "grad_norm": 0.11917825788259506,
      "learning_rate": 1e-06,
      "loss": 0.0518,
      "step": 510
    },
    {
      "clip_ratio/high_max": 0.0027569230005610734,
      "clip_ratio/high_mean": 0.0013071624598524068,
      "clip_ratio/low_mean": 0.0011490862343634944,
      "clip_ratio/low_min": 4.2066338664881187e-05,
      "clip_ratio/region_mean": 0.0024562487305956893,
      "epoch": 0.04769321410029808,
      "grad_norm": 0.11022017896175385,
      "learning_rate": 1e-06,
      "loss": 0.0022,
      "step": 511
    },
    {
      "clip_ratio/high_max": 0.0029090827665640973,
      "clip_ratio/high_mean": 0.001352490875433432,
      "clip_ratio/low_mean": 0.0011505107941047754,
      "clip_ratio/low_min": 7.641605043318123e-05,
      "clip_ratio/region_mean": 0.002503001618606504,
      "epoch": 0.047786547200298665,
      "grad_norm": 0.11806478351354599,
      "learning_rate": 1e-06,
      "loss": -0.0453,
      "step": 512
    },
    {
      "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": 0.013253348214285698,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4090.0,
      "completions/mean_length": 608.1181640625,
      "completions/mean_terminated_length": 561.2711791992188,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.04787988030029925,
      "grad_norm": 0.11305620521306992,
      "learning_rate": 1e-06,
      "loss": 0.0619,
      "num_tokens": 404459321.0,
      "reward": 0.5736868977546692,
      "reward_std": 0.20325154066085815,
      "rewards/simpleverify_reward/mean": 0.5736868977546692,
      "rewards/simpleverify_reward/std": 0.49454256892204285,
      "step": 513
    },
    {
      "clip_ratio/high_max": 0.0022938845941098407,
      "clip_ratio/high_mean": 0.0009037431773322169,
      "clip_ratio/low_mean": 0.000596653086176957,
      "clip_ratio/low_min": 1.528864959254861e-05,
      "clip_ratio/region_mean": 0.001500396290794015,
      "epoch": 0.047973213400299836,
      "grad_norm": 0.117484450340271,
      "learning_rate": 1e-06,
      "loss": 0.0128,
      "step": 514
    },
    {
      "clip_ratio/high_max": 0.0020708463780465536,
      "clip_ratio/high_mean": 0.0008220297531806864,
      "clip_ratio/low_mean": 0.000598522736254381,
      "clip_ratio/low_min": 3.841953457595082e-05,
      "clip_ratio/region_mean": 0.001420552478521131,
      "epoch": 0.048066546500300414,
      "grad_norm": 0.12512654066085815,
      "learning_rate": 1e-06,
      "loss": 0.0168,
      "step": 515
    },
    {
      "clip_ratio/high_max": 0.002422670215310063,
      "clip_ratio/high_mean": 0.0009986731438402785,
      "clip_ratio/low_mean": 0.0006161394485388882,
      "clip_ratio/low_min": 3.759869741770672e-05,
      "clip_ratio/region_mean": 0.001614812616026029,
      "epoch": 0.048159879600301,
      "grad_norm": 0.10640700906515121,
      "learning_rate": 1e-06,
      "loss": -0.0164,
      "step": 516
    },
    {
      "clip_ratio/high_max": 0.002371778835367877,
      "clip_ratio/high_mean": 0.0008489138144796016,
      "clip_ratio/low_mean": 0.0006929068076715339,
      "clip_ratio/low_min": 3.274192840763135e-05,
      "clip_ratio/region_mean": 0.0015418206094182096,
      "epoch": 0.048253212700301584,
      "grad_norm": 0.10331600159406662,
      "learning_rate": 1e-06,
      "loss": 0.0139,
      "step": 517
    },
    {
      "clip_ratio/high_max": 0.0020433677127584815,
      "clip_ratio/high_mean": 0.0010223066528851632,
      "clip_ratio/low_mean": 0.0009520077510387637,
      "clip_ratio/low_min": 0.00017556018701725407,
      "clip_ratio/region_mean": 0.0019743144293897785,
      "epoch": 0.04834654580030216,
      "grad_norm": 0.11191713809967041,
      "learning_rate": 1e-06,
      "loss": -0.0051,
      "step": 518
    },
    {
      "clip_ratio/high_max": 0.0022547683838638477,
      "clip_ratio/high_mean": 0.0009289155841543106,
      "clip_ratio/low_mean": 0.0009570534821250476,
      "clip_ratio/low_min": 6.77951884426875e-05,
      "clip_ratio/region_mean": 0.0018859690317185596,
      "epoch": 0.04843987890030275,
      "grad_norm": 0.11609487235546112,
      "learning_rate": 1e-06,
      "loss": 0.0236,
      "step": 519
    },
    {
      "clip_ratio/high_max": 0.001952126454852987,
      "clip_ratio/high_mean": 0.0008737843090784736,
      "clip_ratio/low_mean": 0.001069299403752666,
      "clip_ratio/low_min": 0.00014024691699887626,
      "clip_ratio/region_mean": 0.0019430837637628429,
      "epoch": 0.04853321200030333,
      "grad_norm": 0.10823985934257507,
      "learning_rate": 1e-06,
      "loss": 0.028,
      "step": 520
    },
    {
      "clip_ratio/high_max": 0.0022938304900890216,
      "clip_ratio/high_mean": 0.0008503883036610205,
      "clip_ratio/low_mean": 0.0011525513145898003,
      "clip_ratio/low_min": 0.00014091896809986793,
      "clip_ratio/region_mean": 0.0020029396837344393,
      "epoch": 0.04862654510030392,
      "grad_norm": 0.12348370254039764,
      "learning_rate": 1e-06,
      "loss": 0.0454,
      "step": 521
    },
    {
      "clip_ratio/high_max": 0.0020629136488423683,
      "clip_ratio/high_mean": 0.0008307058742502704,
      "clip_ratio/low_mean": 0.001059784619428683,
      "clip_ratio/low_min": 7.583248407172505e-05,
      "clip_ratio/region_mean": 0.0018904904572991654,
      "epoch": 0.048719878200304496,
      "grad_norm": 0.13124702870845795,
      "learning_rate": 1e-06,
      "loss": 0.0609,
      "step": 522
    },
    {
      "clip_ratio/high_max": 0.0024305735423695296,
      "clip_ratio/high_mean": 0.0009842896834015846,
      "clip_ratio/low_mean": 0.0009428224584553391,
      "clip_ratio/low_min": 0.00010360168289480498,
      "clip_ratio/region_mean": 0.0019271121127530932,
      "epoch": 0.04881321130030508,
      "grad_norm": 0.1202758252620697,
      "learning_rate": 1e-06,
      "loss": 0.0036,
      "step": 523
    },
    {
      "clip_ratio/high_max": 0.0021617880047415383,
      "clip_ratio/high_mean": 0.0010954533336189343,
      "clip_ratio/low_mean": 0.0007716032396274386,
      "clip_ratio/low_min": 4.3243162508588284e-05,
      "clip_ratio/region_mean": 0.001867056533228606,
      "epoch": 0.04890654440030567,
      "grad_norm": 0.11454305052757263,
      "learning_rate": 1e-06,
      "loss": -0.0066,
      "step": 524
    },
    {
      "clip_ratio/high_max": 0.002247830852866173,
      "clip_ratio/high_mean": 0.0009238106358679943,
      "clip_ratio/low_mean": 0.0008934875786508201,
      "clip_ratio/low_min": 5.8065073972102255e-05,
      "clip_ratio/region_mean": 0.0018172982090618461,
      "epoch": 0.04899987750030625,
      "grad_norm": 0.12081579864025116,
      "learning_rate": 1e-06,
      "loss": 0.0445,
      "step": 525
    },
    {
      "clip_ratio/high_max": 0.0026712418257375248,
      "clip_ratio/high_mean": 0.0010170068799197907,
      "clip_ratio/low_mean": 0.0007595505321660312,
      "clip_ratio/low_min": 5.329184659785824e-05,
      "clip_ratio/region_mean": 0.0017765574011718854,
      "epoch": 0.04909321060030683,
      "grad_norm": 0.12667986750602722,
      "learning_rate": 1e-06,
      "loss": 0.0074,
      "step": 526
    },
    {
      "clip_ratio/high_max": 0.0023257058855961077,
      "clip_ratio/high_mean": 0.000968858123087557,
      "clip_ratio/low_mean": 0.0008188400042854482,
      "clip_ratio/low_min": 4.377752520667855e-05,
      "clip_ratio/region_mean": 0.0017876981510198675,
      "epoch": 0.049186543700307415,
      "grad_norm": 0.12136593461036682,
      "learning_rate": 1e-06,
      "loss": 0.0112,
      "step": 527
    },
    {
      "clip_ratio/high_max": 0.002502967559848912,
      "clip_ratio/high_mean": 0.0009909093132591806,
      "clip_ratio/low_mean": 0.0008073075241554761,
      "clip_ratio/low_min": 4.310705526222591e-05,
      "clip_ratio/region_mean": 0.0017982168646994978,
      "epoch": 0.049279876800308,
      "grad_norm": 0.1273898333311081,
      "learning_rate": 1e-06,
      "loss": 0.0444,
      "step": 528
    },
    {
      "clip_ratio/high_max": 0.002444306570396293,
      "clip_ratio/high_mean": 0.0010627529554767534,
      "clip_ratio/low_mean": 0.0009356704722449649,
      "clip_ratio/low_min": 0.00012519238589447923,
      "clip_ratio/region_mean": 0.0019984234604635276,
      "epoch": 0.049373209900308586,
      "grad_norm": 0.11384916305541992,
      "learning_rate": 1e-06,
      "loss": 0.0214,
      "step": 529
    },
    {
      "clip_ratio/high_max": 0.0019527282674971502,
      "clip_ratio/high_mean": 0.0007767343377054203,
      "clip_ratio/low_mean": 0.0009547128865960985,
      "clip_ratio/low_min": 6.039664094714681e-05,
      "clip_ratio/region_mean": 0.0017314472279394977,
      "epoch": 0.049466543000309164,
      "grad_norm": 0.10346849262714386,
      "learning_rate": 1e-06,
      "loss": 0.035,
      "step": 530
    },
    {
      "clip_ratio/high_max": 0.002386239582847338,
      "clip_ratio/high_mean": 0.0009497268874838483,
      "clip_ratio/low_mean": 0.0010229159706796054,
      "clip_ratio/low_min": 3.5132095945300534e-05,
      "clip_ratio/region_mean": 0.001972642829059623,
      "epoch": 0.04955987610030975,
      "grad_norm": 0.11370111256837845,
      "learning_rate": 1e-06,
      "loss": 0.0139,
      "step": 531
    },
    {
      "clip_ratio/high_max": 0.0025752184228622355,
      "clip_ratio/high_mean": 0.0010965920228045434,
      "clip_ratio/low_mean": 0.0011692429725371767,
      "clip_ratio/low_min": 6.39326790405903e-05,
      "clip_ratio/region_mean": 0.0022658350571873598,
      "epoch": 0.049653209200310335,
      "grad_norm": 0.12252366542816162,
      "learning_rate": 1e-06,
      "loss": -0.0088,
      "step": 532
    },
    {
      "clip_ratio/high_max": 0.0025580211367923766,
      "clip_ratio/high_mean": 0.0010781207129184622,
      "clip_ratio/low_mean": 0.0011872038230649196,
      "clip_ratio/low_min": 4.8454917305207346e-05,
      "clip_ratio/region_mean": 0.0022653245760011487,
      "epoch": 0.04974654230031091,
      "grad_norm": 0.12165111303329468,
      "learning_rate": 1e-06,
      "loss": 0.001,
      "step": 533
    },
    {
      "clip_ratio/high_max": 0.002439030482491944,
      "clip_ratio/high_mean": 0.0009942480191966752,
      "clip_ratio/low_mean": 0.001273912737815408,
      "clip_ratio/low_min": 0.00016214824245253112,
      "clip_ratio/region_mean": 0.00226816076610703,
      "epoch": 0.0498398754003115,
      "grad_norm": 0.11765293776988983,
      "learning_rate": 1e-06,
      "loss": 0.0168,
      "step": 534
    },
    {
      "clip_ratio/high_max": 0.002474566863384098,
      "clip_ratio/high_mean": 0.0009806419529923005,
      "clip_ratio/low_mean": 0.0011716983208316378,
      "clip_ratio/low_min": 0.0001299355735682184,
      "clip_ratio/region_mean": 0.0021523402829188854,
      "epoch": 0.04993320850031208,
      "grad_norm": 0.12225670367479324,
      "learning_rate": 1e-06,
      "loss": 0.0325,
      "step": 535
    },
    {
      "clip_ratio/high_max": 0.0024211660274886526,
      "clip_ratio/high_mean": 0.0009722914601297816,
      "clip_ratio/low_mean": 0.001114476483053295,
      "clip_ratio/low_min": 5.219522245170083e-05,
      "clip_ratio/region_mean": 0.0020867679340881296,
      "epoch": 0.05002654160031267,
      "grad_norm": 0.1208510547876358,
      "learning_rate": 1e-06,
      "loss": 0.0303,
      "step": 536
    },
    {
      "clip_ratio/high_max": 0.002375648356974125,
      "clip_ratio/high_mean": 0.0009706059518066468,
      "clip_ratio/low_mean": 0.000983849327894859,
      "clip_ratio/low_min": 3.261325400671922e-05,
      "clip_ratio/region_mean": 0.0019544552997103892,
      "epoch": 0.05011987470031325,
      "grad_norm": 0.10823806375265121,
      "learning_rate": 1e-06,
      "loss": -0.0116,
      "step": 537
    },
    {
      "clip_ratio/high_max": 0.002742798660619883,
      "clip_ratio/high_mean": 0.0010465313534950837,
      "clip_ratio/low_mean": 0.0011149627734994283,
      "clip_ratio/low_min": 9.473226782574784e-05,
      "clip_ratio/region_mean": 0.002161494121537544,
      "epoch": 0.05021320780031383,
      "grad_norm": 0.10242088884115219,
      "learning_rate": 1e-06,
      "loss": 0.0558,
      "step": 538
    },
    {
      "clip_ratio/high_max": 0.0026951371401082724,
      "clip_ratio/high_mean": 0.0010893955768551677,
      "clip_ratio/low_mean": 0.001053309541021008,
      "clip_ratio/low_min": 9.017143202072475e-05,
      "clip_ratio/region_mean": 0.0021427051469800062,
      "epoch": 0.05030654090031442,
      "grad_norm": 0.11764271557331085,
      "learning_rate": 1e-06,
      "loss": 0.0271,
      "step": 539
    },
    {
      "clip_ratio/high_max": 0.0023856143525335938,
      "clip_ratio/high_mean": 0.0009541919480398064,
      "clip_ratio/low_mean": 0.0012469342036638409,
      "clip_ratio/low_min": 0.00019069206791755278,
      "clip_ratio/region_mean": 0.0022011262335581705,
      "epoch": 0.050399874000315,
      "grad_norm": 0.5091419816017151,
      "learning_rate": 1e-06,
      "loss": 0.0784,
      "step": 540
    },
    {
      "clip_ratio/high_max": 0.002293923324032221,
      "clip_ratio/high_mean": 0.001104503415263025,
      "clip_ratio/low_mean": 0.0010798866460390855,
      "clip_ratio/low_min": 6.423753711715108e-05,
      "clip_ratio/region_mean": 0.002184390090405941,
      "epoch": 0.05049320710031558,
      "grad_norm": 0.11446491628885269,
      "learning_rate": 1e-06,
      "loss": 0.0026,
      "step": 541
    },
    {
      "clip_ratio/high_max": 0.002394167640886735,
      "clip_ratio/high_mean": 0.00119633993745083,
      "clip_ratio/low_mean": 0.0010826653706317302,
      "clip_ratio/low_min": 0.00015781784532009624,
      "clip_ratio/region_mean": 0.0022790052971686237,
      "epoch": 0.050586540200316166,
      "grad_norm": 0.12535390257835388,
      "learning_rate": 1e-06,
      "loss": 0.0051,
      "step": 542
    },
    {
      "clip_ratio/high_max": 0.002593322533357423,
      "clip_ratio/high_mean": 0.0010485982857062481,
      "clip_ratio/low_mean": 0.0011854558179038577,
      "clip_ratio/low_min": 9.415505519427825e-05,
      "clip_ratio/region_mean": 0.0022340541254379787,
      "epoch": 0.05067987330031675,
      "grad_norm": 0.11848200112581253,
      "learning_rate": 1e-06,
      "loss": 0.0445,
      "step": 543
    },
    {
      "clip_ratio/high_max": 0.002403954124019947,
      "clip_ratio/high_mean": 0.001005131289275596,
      "clip_ratio/low_mean": 0.0010457935495651327,
      "clip_ratio/low_min": 0.00012072416757291649,
      "clip_ratio/region_mean": 0.002050924827926792,
      "epoch": 0.05077320640031733,
      "grad_norm": 0.11786353588104248,
      "learning_rate": 1e-06,
      "loss": -0.0262,
      "step": 544
    },
    {
      "clip_ratio/high_max": 0.0026527815680310596,
      "clip_ratio/high_mean": 0.0010455009960423922,
      "clip_ratio/low_mean": 0.0011517081475176383,
      "clip_ratio/low_min": 0.00015454444564966252,
      "clip_ratio/region_mean": 0.002197209141741041,
      "epoch": 0.050866539500317914,
      "grad_norm": 0.11207284033298492,
      "learning_rate": 1e-06,
      "loss": 0.0043,
      "step": 545
    },
    {
      "clip_ratio/high_max": 0.00240755571576301,
      "clip_ratio/high_mean": 0.001150607396994019,
      "clip_ratio/low_mean": 0.0013976555856061168,
      "clip_ratio/low_min": 0.00018781676044454798,
      "clip_ratio/region_mean": 0.0025482630589976907,
      "epoch": 0.0509598726003185,
      "grad_norm": 0.11939078569412231,
      "learning_rate": 1e-06,
      "loss": 0.0234,
      "step": 546
    },
    {
      "clip_ratio/high_max": 0.0026024213366326876,
      "clip_ratio/high_mean": 0.00108860780892428,
      "clip_ratio/low_mean": 0.0013370455544645665,
      "clip_ratio/low_min": 0.0001822290250856895,
      "clip_ratio/region_mean": 0.0024256533215520903,
      "epoch": 0.051053205700319085,
      "grad_norm": 0.11460070312023163,
      "learning_rate": 1e-06,
      "loss": 0.0282,
      "step": 547
    },
    {
      "clip_ratio/high_max": 0.0025708858338475693,
      "clip_ratio/high_mean": 0.0010650688191162772,
      "clip_ratio/low_mean": 0.0013487387805071194,
      "clip_ratio/low_min": 0.00010173968257731758,
      "clip_ratio/region_mean": 0.0024138076114468277,
      "epoch": 0.05114653880031966,
      "grad_norm": 0.11298304051160812,
      "learning_rate": 1e-06,
      "loss": 0.0066,
      "step": 548
    },
    {
      "clip_ratio/high_max": 0.0026097415284311865,
      "clip_ratio/high_mean": 0.0012252685492057935,
      "clip_ratio/low_mean": 0.0012879170790256467,
      "clip_ratio/low_min": 0.00017008917893690523,
      "clip_ratio/region_mean": 0.002513185601856094,
      "epoch": 0.05123987190032025,
      "grad_norm": 0.13417081534862518,
      "learning_rate": 1e-06,
      "loss": -0.0199,
      "step": 549
    },
    {
      "clip_ratio/high_max": 0.0027926547700189985,
      "clip_ratio/high_mean": 0.0012437009827408474,
      "clip_ratio/low_mean": 0.001228071336299763,
      "clip_ratio/low_min": 4.769744191435166e-05,
      "clip_ratio/region_mean": 0.0024717723281355575,
      "epoch": 0.05133320500032083,
      "grad_norm": 0.12110395729541779,
      "learning_rate": 1e-06,
      "loss": 0.0161,
      "step": 550
    },
    {
      "clip_ratio/high_max": 0.002581809188995976,
      "clip_ratio/high_mean": 0.0011146844881295692,
      "clip_ratio/low_mean": 0.001317385849688435,
      "clip_ratio/low_min": 0.00015514890856138663,
      "clip_ratio/region_mean": 0.0024320702941622585,
      "epoch": 0.05142653810032142,
      "grad_norm": 0.12100648134946823,
      "learning_rate": 1e-06,
      "loss": 0.0404,
      "step": 551
    },
    {
      "clip_ratio/high_max": 0.0024883095029508695,
      "clip_ratio/high_mean": 0.001081148293451406,
      "clip_ratio/low_mean": 0.0011426204418967245,
      "clip_ratio/low_min": 0.00013123269854986575,
      "clip_ratio/region_mean": 0.0022237687444430776,
      "epoch": 0.051519871200322,
      "grad_norm": 0.1108996719121933,
      "learning_rate": 1e-06,
      "loss": -0.0131,
      "step": 552
    },
    {
      "clip_ratio/high_max": 0.0025357191989314742,
      "clip_ratio/high_mean": 0.0010701419378165156,
      "clip_ratio/low_mean": 0.001349059271888109,
      "clip_ratio/low_min": 0.0001485577886342071,
      "clip_ratio/region_mean": 0.0024192011696868576,
      "epoch": 0.05161320430032258,
      "grad_norm": 0.11375448852777481,
      "learning_rate": 1e-06,
      "loss": 0.0044,
      "step": 553
    },
    {
      "clip_ratio/high_max": 0.0027622483248705976,
      "clip_ratio/high_mean": 0.0012032637969241478,
      "clip_ratio/low_mean": 0.001359804708044976,
      "clip_ratio/low_min": 0.0001637648656469537,
      "clip_ratio/region_mean": 0.002563068541348912,
      "epoch": 0.05170653740032317,
      "grad_norm": 0.5694599151611328,
      "learning_rate": 1e-06,
      "loss": 0.0026,
      "step": 554
    },
    {
      "clip_ratio/high_max": 0.0025685182481538504,
      "clip_ratio/high_mean": 0.0010880275949602947,
      "clip_ratio/low_mean": 0.0012558269481814932,
      "clip_ratio/low_min": 2.3918866645544767e-05,
      "clip_ratio/region_mean": 0.0023438544958480634,
      "epoch": 0.05179987050032375,
      "grad_norm": 0.11959235370159149,
      "learning_rate": 1e-06,
      "loss": 0.0456,
      "step": 555
    },
    {
      "clip_ratio/high_max": 0.0023812199142412283,
      "clip_ratio/high_mean": 0.0009857916102191666,
      "clip_ratio/low_mean": 0.0014461428127106046,
      "clip_ratio/low_min": 0.00014719656837769435,
      "clip_ratio/region_mean": 0.002431934430205729,
      "epoch": 0.05189320360032433,
      "grad_norm": 0.11535393446683884,
      "learning_rate": 1e-06,
      "loss": 0.0509,
      "step": 556
    },
    {
      "clip_ratio/high_max": 0.0023443118916475214,
      "clip_ratio/high_mean": 0.0010782462813949678,
      "clip_ratio/low_mean": 0.0012639374454010976,
      "clip_ratio/low_min": 9.613549627829343e-05,
      "clip_ratio/region_mean": 0.002342183761356864,
      "epoch": 0.051986536700324916,
      "grad_norm": 0.10409792512655258,
      "learning_rate": 1e-06,
      "loss": 0.0026,
      "step": 557
    },
    {
      "clip_ratio/high_max": 0.0026739557142718695,
      "clip_ratio/high_mean": 0.0011256642337684752,
      "clip_ratio/low_mean": 0.001414404370734701,
      "clip_ratio/low_min": 0.00015633211114618462,
      "clip_ratio/region_mean": 0.002540068577218335,
      "epoch": 0.0520798698003255,
      "grad_norm": 0.11572989076375961,
      "learning_rate": 1e-06,
      "loss": 0.0418,
      "step": 558
    },
    {
      "clip_ratio/high_max": 0.002377290184085723,
      "clip_ratio/high_mean": 0.00114520425995579,
      "clip_ratio/low_mean": 0.0012214684902573936,
      "clip_ratio/low_min": 0.00016913914623728488,
      "clip_ratio/region_mean": 0.0023666727356612682,
      "epoch": 0.05217320290032608,
      "grad_norm": 0.11622529476881027,
      "learning_rate": 1e-06,
      "loss": -0.016,
      "step": 559
    },
    {
      "clip_ratio/high_max": 0.0027728189670597203,
      "clip_ratio/high_mean": 0.0011612942726060282,
      "clip_ratio/low_mean": 0.0013770258738077246,
      "clip_ratio/low_min": 0.00013348496577236801,
      "clip_ratio/region_mean": 0.0025383201718796045,
      "epoch": 0.052266536000326665,
      "grad_norm": 0.12185611575841904,
      "learning_rate": 1e-06,
      "loss": 0.0078,
      "step": 560
    },
    {
      "clip_ratio/high_max": 0.0027572427861741744,
      "clip_ratio/high_mean": 0.0011848831272800453,
      "clip_ratio/low_mean": 0.0014325601878226735,
      "clip_ratio/low_min": 0.0001359142806904856,
      "clip_ratio/region_mean": 0.0026174432859988883,
      "epoch": 0.05235986910032725,
      "grad_norm": 0.11497235298156738,
      "learning_rate": 1e-06,
      "loss": 0.0216,
      "step": 561
    },
    {
      "clip_ratio/high_max": 0.0026100702743860893,
      "clip_ratio/high_mean": 0.0011189342512807343,
      "clip_ratio/low_mean": 0.0012487166241044179,
      "clip_ratio/low_min": 0.0002088825299324526,
      "clip_ratio/region_mean": 0.0023676509226788767,
      "epoch": 0.052453202200327835,
      "grad_norm": 0.11312676966190338,
      "learning_rate": 1e-06,
      "loss": 0.0163,
      "step": 562
    },
    {
      "clip_ratio/high_max": 0.0027594675339059904,
      "clip_ratio/high_mean": 0.0011417407695262227,
      "clip_ratio/low_mean": 0.0013484936607710551,
      "clip_ratio/low_min": 7.538398403994506e-05,
      "clip_ratio/region_mean": 0.0024902344230213203,
      "epoch": 0.05254653530032841,
      "grad_norm": 0.12057051807641983,
      "learning_rate": 1e-06,
      "loss": 0.0549,
      "step": 563
    },
    {
      "clip_ratio/high_max": 0.0025116864489973523,
      "clip_ratio/high_mean": 0.0011374509158486035,
      "clip_ratio/low_mean": 0.0011922353878617287,
      "clip_ratio/low_min": 5.325620077201165e-05,
      "clip_ratio/region_mean": 0.0023296863146242686,
      "epoch": 0.052639868400329,
      "grad_norm": 0.11815297603607178,
      "learning_rate": 1e-06,
      "loss": -0.0028,
      "step": 564
    },
    {
      "clip_ratio/high_max": 0.0022530104979523458,
      "clip_ratio/high_mean": 0.0009999750145652797,
      "clip_ratio/low_mean": 0.001297568465815857,
      "clip_ratio/low_min": 5.7107778957288247e-05,
      "clip_ratio/region_mean": 0.0022975434621912427,
      "epoch": 0.052733201500329584,
      "grad_norm": 0.11339268833398819,
      "learning_rate": 1e-06,
      "loss": 0.0452,
      "step": 565
    },
    {
      "clip_ratio/high_max": 0.00248011741132359,
      "clip_ratio/high_mean": 0.0011184336144651752,
      "clip_ratio/low_mean": 0.001197814883198589,
      "clip_ratio/low_min": 9.738258540892275e-05,
      "clip_ratio/region_mean": 0.002316248464921955,
      "epoch": 0.05282653460033017,
      "grad_norm": 0.1128305122256279,
      "learning_rate": 1e-06,
      "loss": 0.0291,
      "step": 566
    },
    {
      "clip_ratio/high_max": 0.0026540504331933334,
      "clip_ratio/high_mean": 0.001125739247072488,
      "clip_ratio/low_mean": 0.0010907519463216886,
      "clip_ratio/low_min": 6.852324986539315e-05,
      "clip_ratio/region_mean": 0.0022164912370499223,
      "epoch": 0.05291986770033075,
      "grad_norm": 0.10074286162853241,
      "learning_rate": 1e-06,
      "loss": 0.023,
      "step": 567
    },
    {
      "clip_ratio/high_max": 0.002943443407275481,
      "clip_ratio/high_mean": 0.0012677842987613985,
      "clip_ratio/low_mean": 0.0012342028094280977,
      "clip_ratio/low_min": 9.10896087589208e-05,
      "clip_ratio/region_mean": 0.0025019871100084856,
      "epoch": 0.05301320080033133,
      "grad_norm": 0.11268115043640137,
      "learning_rate": 1e-06,
      "loss": -0.0035,
      "step": 568
    },
    {
      "clip_ratio/high_max": 0.0030965563346398994,
      "clip_ratio/high_mean": 0.0012327997974352911,
      "clip_ratio/low_mean": 0.0013548318529501557,
      "clip_ratio/low_min": 7.121752241801005e-05,
      "clip_ratio/region_mean": 0.00258763170131715,
      "epoch": 0.05310653390033192,
      "grad_norm": 0.11782576143741608,
      "learning_rate": 1e-06,
      "loss": 0.0143,
      "step": 569
    },
    {
      "clip_ratio/high_max": 0.0024675445092725568,
      "clip_ratio/high_mean": 0.001130588338128291,
      "clip_ratio/low_mean": 0.0013564268774644006,
      "clip_ratio/low_min": 8.581010752095608e-05,
      "clip_ratio/region_mean": 0.00248701519012684,
      "epoch": 0.053199867000332496,
      "grad_norm": 0.10595322400331497,
      "learning_rate": 1e-06,
      "loss": 0.0081,
      "step": 570
    },
    {
      "clip_ratio/high_max": 0.0028545003006001934,
      "clip_ratio/high_mean": 0.0012170638947281986,
      "clip_ratio/low_mean": 0.0011107133177574724,
      "clip_ratio/low_min": 6.0930760810151696e-05,
      "clip_ratio/region_mean": 0.0023277771688299254,
      "epoch": 0.05329320010033308,
      "grad_norm": 0.11617729067802429,
      "learning_rate": 1e-06,
      "loss": 0.0054,
      "step": 571
    },
    {
      "clip_ratio/high_max": 0.0027577823784668,
      "clip_ratio/high_mean": 0.001325263536273269,
      "clip_ratio/low_mean": 0.0010861684058909304,
      "clip_ratio/low_min": 9.476870582147967e-05,
      "clip_ratio/region_mean": 0.0024114319603540935,
      "epoch": 0.053386533200333666,
      "grad_norm": 0.1142783835530281,
      "learning_rate": 1e-06,
      "loss": 0.0058,
      "step": 572
    },
    {
      "clip_ratio/high_max": 0.00254910382500384,
      "clip_ratio/high_mean": 0.0010939086096186657,
      "clip_ratio/low_mean": 0.0012719541082333308,
      "clip_ratio/low_min": 4.8896016778599005e-05,
      "clip_ratio/region_mean": 0.002365862703300081,
      "epoch": 0.05347986630033425,
      "grad_norm": 4.01998233795166,
      "learning_rate": 1e-06,
      "loss": 0.0517,
      "step": 573
    },
    {
      "clip_ratio/high_max": 0.0024419658875558525,
      "clip_ratio/high_mean": 0.0011289127105555963,
      "clip_ratio/low_mean": 0.0013267945359984878,
      "clip_ratio/low_min": 0.00014345609451993369,
      "clip_ratio/region_mean": 0.0024557072974857874,
      "epoch": 0.05357319940033483,
      "grad_norm": 0.12506824731826782,
      "learning_rate": 1e-06,
      "loss": 0.0342,
      "step": 574
    },
    {
      "clip_ratio/high_max": 0.0032088188527268358,
      "clip_ratio/high_mean": 0.0014075598355702823,
      "clip_ratio/low_mean": 0.0013373718538787216,
      "clip_ratio/low_min": 0.0002551303150539752,
      "clip_ratio/region_mean": 0.0027449316839920357,
      "epoch": 0.053666532500335415,
      "grad_norm": 0.14207856357097626,
      "learning_rate": 1e-06,
      "loss": 0.0253,
      "step": 575
    },
    {
      "clip_ratio/high_max": 0.002352807998249773,
      "clip_ratio/high_mean": 0.000967294190559187,
      "clip_ratio/low_mean": 0.0013993982320243958,
      "clip_ratio/low_min": 0.0002421751614747336,
      "clip_ratio/region_mean": 0.0023666924389544874,
      "epoch": 0.053759865600336,
      "grad_norm": 0.17422142624855042,
      "learning_rate": 1e-06,
      "loss": 0.0424,
      "step": 576
    },
    {
      "clip_ratio/high_max": 0.002820875815814361,
      "clip_ratio/high_mean": 0.00132078929891577,
      "clip_ratio/low_mean": 0.0012677728991548065,
      "clip_ratio/low_min": 3.611976899264846e-05,
      "clip_ratio/region_mean": 0.0025885622017085552,
      "epoch": 0.053853198700336585,
      "grad_norm": 0.1095849797129631,
      "learning_rate": 1e-06,
      "loss": 0.0011,
      "step": 577
    },
    {
      "clip_ratio/high_max": 0.002381853155384306,
      "clip_ratio/high_mean": 0.0009803358170756837,
      "clip_ratio/low_mean": 0.001393428690789733,
      "clip_ratio/low_min": 0.000167344353030785,
      "clip_ratio/region_mean": 0.0023737644514767453,
      "epoch": 0.053946531800337164,
      "grad_norm": 0.10863973945379257,
      "learning_rate": 1e-06,
      "loss": 0.0661,
      "step": 578
    },
    {
      "clip_ratio/high_max": 0.0026694867701735348,
      "clip_ratio/high_mean": 0.0011427963618189096,
      "clip_ratio/low_mean": 0.0014050775534997229,
      "clip_ratio/low_min": 0.00018719708896242082,
      "clip_ratio/region_mean": 0.002547873795265332,
      "epoch": 0.05403986490033775,
      "grad_norm": 0.11603222787380219,
      "learning_rate": 1e-06,
      "loss": 0.043,
      "step": 579
    },
    {
      "clip_ratio/high_max": 0.003046132915187627,
      "clip_ratio/high_mean": 0.001369683272059774,
      "clip_ratio/low_mean": 0.001360263649985427,
      "clip_ratio/low_min": 0.00024008280888665468,
      "clip_ratio/region_mean": 0.0027299469657009467,
      "epoch": 0.054133198000338334,
      "grad_norm": 0.12285274267196655,
      "learning_rate": 1e-06,
      "loss": 0.0466,
      "step": 580
    },
    {
      "clip_ratio/high_max": 0.003033043903997168,
      "clip_ratio/high_mean": 0.0012858603586209938,
      "clip_ratio/low_mean": 0.0012211418252263684,
      "clip_ratio/low_min": 0.00012805784808733733,
      "clip_ratio/region_mean": 0.002507002187485341,
      "epoch": 0.05422653110033892,
      "grad_norm": 0.13200485706329346,
      "learning_rate": 1e-06,
      "loss": -0.0044,
      "step": 581
    },
    {
      "clip_ratio/high_max": 0.002537907668738626,
      "clip_ratio/high_mean": 0.0011251911018916871,
      "clip_ratio/low_mean": 0.001203045088914223,
      "clip_ratio/low_min": 9.355846486869268e-05,
      "clip_ratio/region_mean": 0.0023282361653400585,
      "epoch": 0.0543198642003395,
      "grad_norm": 0.11725179851055145,
      "learning_rate": 1e-06,
      "loss": 0.0117,
      "step": 582
    },
    {
      "clip_ratio/high_max": 0.0027843005445902236,
      "clip_ratio/high_mean": 0.0011539477782207541,
      "clip_ratio/low_mean": 0.0011952742042922182,
      "clip_ratio/low_min": 9.549087644700194e-05,
      "clip_ratio/region_mean": 0.002349221962504089,
      "epoch": 0.05441319730034008,
      "grad_norm": 0.1376514434814453,
      "learning_rate": 1e-06,
      "loss": 0.0452,
      "step": 583
    },
    {
      "clip_ratio/high_max": 0.0031040568646858446,
      "clip_ratio/high_mean": 0.0012525530037237331,
      "clip_ratio/low_mean": 0.001269270591365057,
      "clip_ratio/low_min": 0.0001405190305376891,
      "clip_ratio/region_mean": 0.0025218236332875676,
      "epoch": 0.05450653040034067,
      "grad_norm": 0.10900263488292694,
      "learning_rate": 1e-06,
      "loss": 0.0408,
      "step": 584
    },
    {
      "clip_ratio/high_max": 0.002753465436398983,
      "clip_ratio/high_mean": 0.0011064121936215088,
      "clip_ratio/low_mean": 0.0013788378055323847,
      "clip_ratio/low_min": 0.0002352017154407804,
      "clip_ratio/region_mean": 0.0024852499409462325,
      "epoch": 0.054599863500341246,
      "grad_norm": 0.16603875160217285,
      "learning_rate": 1e-06,
      "loss": 0.0496,
      "step": 585
    },
    {
      "clip_ratio/high_max": 0.0023427415944752283,
      "clip_ratio/high_mean": 0.0011698730486386921,
      "clip_ratio/low_mean": 0.0011950733241974376,
      "clip_ratio/low_min": 0.00013395195492194034,
      "clip_ratio/region_mean": 0.0023649463619221933,
      "epoch": 0.05469319660034183,
      "grad_norm": 0.11876308917999268,
      "learning_rate": 1e-06,
      "loss": 0.0114,
      "step": 586
    },
    {
      "clip_ratio/high_max": 0.0025814474720391445,
      "clip_ratio/high_mean": 0.0010721033577283379,
      "clip_ratio/low_mean": 0.0015546890717814676,
      "clip_ratio/low_min": 0.00011013074436050374,
      "clip_ratio/region_mean": 0.0026267923967679963,
      "epoch": 0.054786529700342416,
      "grad_norm": 0.1272927224636078,
      "learning_rate": 1e-06,
      "loss": 0.0536,
      "step": 587
    },
    {
      "clip_ratio/high_max": 0.0025365491092088632,
      "clip_ratio/high_mean": 0.0012100449202989694,
      "clip_ratio/low_mean": 0.0013668191568285692,
      "clip_ratio/low_min": 0.0001328071994066704,
      "clip_ratio/region_mean": 0.0025768641789909452,
      "epoch": 0.054879862800343,
      "grad_norm": 0.1082814484834671,
      "learning_rate": 1e-06,
      "loss": 0.0392,
      "step": 588
    },
    {
      "clip_ratio/high_max": 0.0032100252574309707,
      "clip_ratio/high_mean": 0.001355565051198937,
      "clip_ratio/low_mean": 0.0014500094184768386,
      "clip_ratio/low_min": 8.803711807559012e-05,
      "clip_ratio/region_mean": 0.002805574498779606,
      "epoch": 0.05497319590034358,
      "grad_norm": 0.11585516482591629,
      "learning_rate": 1e-06,
      "loss": -0.032,
      "step": 589
    },
    {
      "clip_ratio/high_max": 0.002697335039556492,
      "clip_ratio/high_mean": 0.001279321004403755,
      "clip_ratio/low_mean": 0.0014537881543219555,
      "clip_ratio/low_min": 0.00021021044358349172,
      "clip_ratio/region_mean": 0.0027331091550877318,
      "epoch": 0.055066529000344165,
      "grad_norm": 0.12308011949062347,
      "learning_rate": 1e-06,
      "loss": 0.0241,
      "step": 590
    },
    {
      "clip_ratio/high_max": 0.0030548342838301323,
      "clip_ratio/high_mean": 0.001186602905363543,
      "clip_ratio/low_mean": 0.0012894511673948728,
      "clip_ratio/low_min": 9.116056571656372e-05,
      "clip_ratio/region_mean": 0.0024760540254646912,
      "epoch": 0.05515986210034475,
      "grad_norm": 0.12500542402267456,
      "learning_rate": 1e-06,
      "loss": 0.0453,
      "step": 591
    },
    {
      "clip_ratio/high_max": 0.002761060077318689,
      "clip_ratio/high_mean": 0.001086662981833797,
      "clip_ratio/low_mean": 0.0012974886922165751,
      "clip_ratio/low_min": 4.474154229683336e-05,
      "clip_ratio/region_mean": 0.002384151695878245,
      "epoch": 0.055253195200345336,
      "grad_norm": 0.1094045415520668,
      "learning_rate": 1e-06,
      "loss": 0.0615,
      "step": 592
    },
    {
      "clip_ratio/high_max": 0.002913882060965989,
      "clip_ratio/high_mean": 0.0014260840471251868,
      "clip_ratio/low_mean": 0.0013511558681784663,
      "clip_ratio/low_min": 0.00013532372940971982,
      "clip_ratio/region_mean": 0.00277723995532142,
      "epoch": 0.055346528300345914,
      "grad_norm": 0.12525342404842377,
      "learning_rate": 1e-06,
      "loss": 0.0005,
      "step": 593
    },
    {
      "clip_ratio/high_max": 0.0024594295682618394,
      "clip_ratio/high_mean": 0.0010692717914935201,
      "clip_ratio/low_mean": 0.0016086845644167624,
      "clip_ratio/low_min": 0.00039245718835445587,
      "clip_ratio/region_mean": 0.002677956370462198,
      "epoch": 0.0554398614003465,
      "grad_norm": 56.352691650390625,
      "learning_rate": 1e-06,
      "loss": 0.0616,
      "step": 594
    },
    {
      "clip_ratio/high_max": 0.0029018530767643824,
      "clip_ratio/high_mean": 0.0012118536251364276,
      "clip_ratio/low_mean": 0.00147406952601159,
      "clip_ratio/low_min": 8.366415204363875e-05,
      "clip_ratio/region_mean": 0.0026859231656999327,
      "epoch": 0.055533194500347084,
      "grad_norm": 0.12930914759635925,
      "learning_rate": 1e-06,
      "loss": 0.0326,
      "step": 595
    },
    {
      "clip_ratio/high_max": 0.002946642227470875,
      "clip_ratio/high_mean": 0.001237690965353977,
      "clip_ratio/low_mean": 0.001491498351242626,
      "clip_ratio/low_min": 0.00020836423846049001,
      "clip_ratio/region_mean": 0.0027291893420624547,
      "epoch": 0.05562652760034766,
      "grad_norm": 0.1227770671248436,
      "learning_rate": 1e-06,
      "loss": 0.0001,
      "step": 596
    },
    {
      "clip_ratio/high_max": 0.002995901209942531,
      "clip_ratio/high_mean": 0.0012675451253016945,
      "clip_ratio/low_mean": 0.0013838087652402464,
      "clip_ratio/low_min": 0.000258805377598037,
      "clip_ratio/region_mean": 0.0026513538978178985,
      "epoch": 0.05571986070034825,
      "grad_norm": 0.10995718091726303,
      "learning_rate": 1e-06,
      "loss": 0.0032,
      "step": 597
    },
    {
      "clip_ratio/high_max": 0.002594681085611228,
      "clip_ratio/high_mean": 0.0011624784929153975,
      "clip_ratio/low_mean": 0.0014592079423891846,
      "clip_ratio/low_min": 0.0002578041221568128,
      "clip_ratio/region_mean": 0.0026216864498564973,
      "epoch": 0.05581319380034883,
      "grad_norm": 0.11237485706806183,
      "learning_rate": 1e-06,
      "loss": 0.0488,
      "step": 598
    },
    {
      "clip_ratio/high_max": 0.002932543524366338,
      "clip_ratio/high_mean": 0.001473056930990424,
      "clip_ratio/low_mean": 0.0014338534601847641,
      "clip_ratio/low_min": 0.0002242224545625504,
      "clip_ratio/region_mean": 0.0029069104202790186,
      "epoch": 0.05590652690034942,
      "grad_norm": 0.1207275539636612,
      "learning_rate": 1e-06,
      "loss": -0.0014,
      "step": 599
    },
    {
      "clip_ratio/high_max": 0.003175174104399048,
      "clip_ratio/high_mean": 0.0012610718913492747,
      "clip_ratio/low_mean": 0.0012987626614631154,
      "clip_ratio/low_min": 0.0001589283410794451,
      "clip_ratio/region_mean": 0.0025598346401238814,
      "epoch": 0.055999860000349996,
      "grad_norm": 0.11774420738220215,
      "learning_rate": 1e-06,
      "loss": -0.0118,
      "step": 600
    },
    {
      "clip_ratio/high_max": 0.003017504022864159,
      "clip_ratio/high_mean": 0.0012930801167385653,
      "clip_ratio/low_mean": 0.0013243357425380964,
      "clip_ratio/low_min": 0.0001299791383644333,
      "clip_ratio/region_mean": 0.002617415797431022,
      "epoch": 0.05609319310035058,
      "grad_norm": 0.10962067544460297,
      "learning_rate": 1e-06,
      "loss": -0.0033,
      "step": 601
    },
    {
      "clip_ratio/high_max": 0.002408566484518815,
      "clip_ratio/high_mean": 0.0011331773057463579,
      "clip_ratio/low_mean": 0.001511076607130235,
      "clip_ratio/low_min": 0.00019113015514449216,
      "clip_ratio/region_mean": 0.002644253909238614,
      "epoch": 0.05618652620035117,
      "grad_norm": 0.11985189467668533,
      "learning_rate": 1e-06,
      "loss": 0.0242,
      "step": 602
    },
    {
      "clip_ratio/high_max": 0.0029132041236152872,
      "clip_ratio/high_mean": 0.001350120499409968,
      "clip_ratio/low_mean": 0.0014923360940883867,
      "clip_ratio/low_min": 0.00021058001129858894,
      "clip_ratio/region_mean": 0.002842456553480588,
      "epoch": 0.05627985930035175,
      "grad_norm": 0.11751165986061096,
      "learning_rate": 1e-06,
      "loss": 0.0063,
      "step": 603
    },
    {
      "clip_ratio/high_max": 0.0033193147683050483,
      "clip_ratio/high_mean": 0.0012864779091614764,
      "clip_ratio/low_mean": 0.0014792458059673663,
      "clip_ratio/low_min": 0.00015850120144023094,
      "clip_ratio/region_mean": 0.0027657236860250123,
      "epoch": 0.05637319240035233,
      "grad_norm": 0.1329202950000763,
      "learning_rate": 1e-06,
      "loss": 0.0033,
      "step": 604
    },
    {
      "clip_ratio/high_max": 0.0031351850266219117,
      "clip_ratio/high_mean": 0.0013310584363352973,
      "clip_ratio/low_mean": 0.0017237356369150802,
      "clip_ratio/low_min": 0.00024564145769545576,
      "clip_ratio/region_mean": 0.0030547940696123987,
      "epoch": 0.056466525500352915,
      "grad_norm": 0.11847762018442154,
      "learning_rate": 1e-06,
      "loss": 0.0426,
      "step": 605
    },
    {
      "clip_ratio/high_max": 0.002764619726804085,
      "clip_ratio/high_mean": 0.0011567974725039676,
      "clip_ratio/low_mean": 0.00151305268809665,
      "clip_ratio/low_min": 0.00012714555305137765,
      "clip_ratio/region_mean": 0.0026698501751525328,
      "epoch": 0.0565598586003535,
      "grad_norm": 0.11249374598264694,
      "learning_rate": 1e-06,
      "loss": 0.0405,
      "step": 606
    },
    {
      "clip_ratio/high_max": 0.0031606808697688393,
      "clip_ratio/high_mean": 0.0012830835257773288,
      "clip_ratio/low_mean": 0.0014400148429558612,
      "clip_ratio/low_min": 0.00024713687707844656,
      "clip_ratio/region_mean": 0.002723098346905317,
      "epoch": 0.056653191700354086,
      "grad_norm": 0.11802874505519867,
      "learning_rate": 1e-06,
      "loss": 0.0183,
      "step": 607
    },
    {
      "clip_ratio/high_max": 0.003382972688996233,
      "clip_ratio/high_mean": 0.0013577564604929648,
      "clip_ratio/low_mean": 0.0014644498041889165,
      "clip_ratio/low_min": 0.00012427875026332913,
      "clip_ratio/region_mean": 0.002822206217388157,
      "epoch": 0.056746524800354664,
      "grad_norm": 0.11685334146022797,
      "learning_rate": 1e-06,
      "loss": 0.0238,
      "step": 608
    },
    {
      "clip_ratio/high_max": 0.002916577403084375,
      "clip_ratio/high_mean": 0.0012009530437353533,
      "clip_ratio/low_mean": 0.0015385350925498642,
      "clip_ratio/low_min": 0.00014482042115560034,
      "clip_ratio/region_mean": 0.002739488161751069,
      "epoch": 0.05683985790035525,
      "grad_norm": 0.13132593035697937,
      "learning_rate": 1e-06,
      "loss": 0.0021,
      "step": 609
    },
    {
      "clip_ratio/high_max": 0.002846942596079316,
      "clip_ratio/high_mean": 0.0012231544424139429,
      "clip_ratio/low_mean": 0.0018343539195484482,
      "clip_ratio/low_min": 0.00025931542040780187,
      "clip_ratio/region_mean": 0.0030575084092561156,
      "epoch": 0.056933191000355834,
      "grad_norm": 0.12039321660995483,
      "learning_rate": 1e-06,
      "loss": 0.058,
      "step": 610
    },
    {
      "clip_ratio/high_max": 0.0024926215992309153,
      "clip_ratio/high_mean": 0.0011125080909550888,
      "clip_ratio/low_mean": 0.0014655374761787243,
      "clip_ratio/low_min": 5.463968773256056e-05,
      "clip_ratio/region_mean": 0.00257804557622876,
      "epoch": 0.05702652410035641,
      "grad_norm": 0.10390654951334,
      "learning_rate": 1e-06,
      "loss": 0.0349,
      "step": 611
    },
    {
      "clip_ratio/high_max": 0.0028619467266253196,
      "clip_ratio/high_mean": 0.0012707455280178692,
      "clip_ratio/low_mean": 0.001434564601368038,
      "clip_ratio/low_min": 0.00012798572970496025,
      "clip_ratio/region_mean": 0.002705310173041653,
      "epoch": 0.057119857200357,
      "grad_norm": 0.11988730728626251,
      "learning_rate": 1e-06,
      "loss": 0.0246,
      "step": 612
    },
    {
      "clip_ratio/high_max": 0.0029487076026271097,
      "clip_ratio/high_mean": 0.0013413972046691924,
      "clip_ratio/low_mean": 0.0015923161372484174,
      "clip_ratio/low_min": 7.876181825849926e-05,
      "clip_ratio/region_mean": 0.0029337133528315462,
      "epoch": 0.05721319030035758,
      "grad_norm": 0.12389518320560455,
      "learning_rate": 1e-06,
      "loss": 0.0066,
      "step": 613
    },
    {
      "clip_ratio/high_max": 0.0031791578949196264,
      "clip_ratio/high_mean": 0.0013678569448529743,
      "clip_ratio/low_mean": 0.0015660199242120143,
      "clip_ratio/low_min": 0.0003195867648173589,
      "clip_ratio/region_mean": 0.002933876901806798,
      "epoch": 0.05730652340035817,
      "grad_norm": 0.18571637570858002,
      "learning_rate": 1e-06,
      "loss": 0.0513,
      "step": 614
    },
    {
      "clip_ratio/high_max": 0.003133909725875128,
      "clip_ratio/high_mean": 0.0012686830505117541,
      "clip_ratio/low_mean": 0.001598485014255857,
      "clip_ratio/low_min": 0.00016843396952026524,
      "clip_ratio/region_mean": 0.002867168055672664,
      "epoch": 0.05739985650035875,
      "grad_norm": 0.10513711720705032,
      "learning_rate": 1e-06,
      "loss": -0.0017,
      "step": 615
    },
    {
      "clip_ratio/high_max": 0.0030570370799978264,
      "clip_ratio/high_mean": 0.0013293832744238898,
      "clip_ratio/low_mean": 0.0013120000185153913,
      "clip_ratio/low_min": 9.725565905682743e-05,
      "clip_ratio/region_mean": 0.0026413833402330056,
      "epoch": 0.05749318960035933,
      "grad_norm": 0.12293823063373566,
      "learning_rate": 1e-06,
      "loss": -0.0123,
      "step": 616
    },
    {
      "clip_ratio/high_max": 0.003299827942100819,
      "clip_ratio/high_mean": 0.0014612694867537357,
      "clip_ratio/low_mean": 0.0013754075043834746,
      "clip_ratio/low_min": 0.00019858918312820606,
      "clip_ratio/region_mean": 0.0028366769838612527,
      "epoch": 0.05758652270035992,
      "grad_norm": 0.11497383564710617,
      "learning_rate": 1e-06,
      "loss": 0.0078,
      "step": 617
    },
    {
      "clip_ratio/high_max": 0.0031383688692585565,
      "clip_ratio/high_mean": 0.0013155838314560242,
      "clip_ratio/low_mean": 0.0015653529044357128,
      "clip_ratio/low_min": 0.0001314942483077175,
      "clip_ratio/region_mean": 0.0028809367067879066,
      "epoch": 0.0576798558003605,
      "grad_norm": 0.10731995105743408,
      "learning_rate": 1e-06,
      "loss": 0.0328,
      "step": 618
    },
    {
      "clip_ratio/high_max": 0.0026809280388988554,
      "clip_ratio/high_mean": 0.0012080861488357186,
      "clip_ratio/low_mean": 0.0019553159745555604,
      "clip_ratio/low_min": 0.00034075777512043715,
      "clip_ratio/region_mean": 0.0031634021288482472,
      "epoch": 0.05777318890036108,
      "grad_norm": 0.11680079251527786,
      "learning_rate": 1e-06,
      "loss": 0.018,
      "step": 619
    },
    {
      "clip_ratio/high_max": 0.0026415278334752657,
      "clip_ratio/high_mean": 0.001101141799153993,
      "clip_ratio/low_mean": 0.0017012868120218627,
      "clip_ratio/low_min": 0.00011531197924341541,
      "clip_ratio/region_mean": 0.0028024285420542583,
      "epoch": 0.057866522000361666,
      "grad_norm": 0.10773280262947083,
      "learning_rate": 1e-06,
      "loss": 0.0477,
      "step": 620
    },
    {
      "clip_ratio/high_max": 0.002566681148891803,
      "clip_ratio/high_mean": 0.0011477045100036776,
      "clip_ratio/low_mean": 0.0018021069336100481,
      "clip_ratio/low_min": 0.0002992164900206262,
      "clip_ratio/region_mean": 0.002949811481812503,
      "epoch": 0.05795985510036225,
      "grad_norm": 0.10499243438243866,
      "learning_rate": 1e-06,
      "loss": 0.0322,
      "step": 621
    },
    {
      "clip_ratio/high_max": 0.003188927636074368,
      "clip_ratio/high_mean": 0.001448851136956364,
      "clip_ratio/low_mean": 0.0015544437646894949,
      "clip_ratio/low_min": 0.0001414512289557024,
      "clip_ratio/region_mean": 0.003003294885274954,
      "epoch": 0.05805318820036283,
      "grad_norm": 0.12040673941373825,
      "learning_rate": 1e-06,
      "loss": -0.0306,
      "step": 622
    },
    {
      "clip_ratio/high_max": 0.0033192904229508713,
      "clip_ratio/high_mean": 0.0013392424698395189,
      "clip_ratio/low_mean": 0.0015561041727778502,
      "clip_ratio/low_min": 0.00020276426039345097,
      "clip_ratio/region_mean": 0.0028953466389793903,
      "epoch": 0.058146521300363414,
      "grad_norm": 0.13179415464401245,
      "learning_rate": 1e-06,
      "loss": 0.0449,
      "step": 623
    },
    {
      "clip_ratio/high_max": 0.003174079567543231,
      "clip_ratio/high_mean": 0.0012380525295156986,
      "clip_ratio/low_mean": 0.0016126817208714783,
      "clip_ratio/low_min": 0.00027876444983121473,
      "clip_ratio/region_mean": 0.0028507342212833464,
      "epoch": 0.058239854400364,
      "grad_norm": 0.11259009689092636,
      "learning_rate": 1e-06,
      "loss": 0.0643,
      "step": 624
    },
    {
      "clip_ratio/high_max": 0.0030925749597372487,
      "clip_ratio/high_mean": 0.0011946113481826615,
      "clip_ratio/low_mean": 0.001656367712712381,
      "clip_ratio/low_min": 8.057512241066433e-05,
      "clip_ratio/region_mean": 0.002850979071808979,
      "epoch": 0.058333187500364585,
      "grad_norm": 0.11597687751054764,
      "learning_rate": 1e-06,
      "loss": 0.0747,
      "step": 625
    },
    {
      "clip_ratio/high_max": 0.0028178526554256678,
      "clip_ratio/high_mean": 0.0012578428359120153,
      "clip_ratio/low_mean": 0.0013812756678817095,
      "clip_ratio/low_min": 0.00013082805708108936,
      "clip_ratio/region_mean": 0.0026391184655949473,
      "epoch": 0.05842652060036516,
      "grad_norm": 0.1210600957274437,
      "learning_rate": 1e-06,
      "loss": 0.0121,
      "step": 626
    },
    {
      "clip_ratio/high_max": 0.003386612137546763,
      "clip_ratio/high_mean": 0.0014514080285152886,
      "clip_ratio/low_mean": 0.001366763244732283,
      "clip_ratio/low_min": 0.00011221376189496368,
      "clip_ratio/region_mean": 0.0028181711677461863,
      "epoch": 0.05851985370036575,
      "grad_norm": 0.11617657542228699,
      "learning_rate": 1e-06,
      "loss": -0.0077,
      "step": 627
    },
    {
      "clip_ratio/high_max": 0.0034576827310957015,
      "clip_ratio/high_mean": 0.001391749014146626,
      "clip_ratio/low_mean": 0.0015356980948126875,
      "clip_ratio/low_min": 0.00013342677448235918,
      "clip_ratio/region_mean": 0.002927447007095907,
      "epoch": 0.05861318680036633,
      "grad_norm": 0.11794304847717285,
      "learning_rate": 1e-06,
      "loss": 0.0147,
      "step": 628
    },
    {
      "clip_ratio/high_max": 0.0028020602476317436,
      "clip_ratio/high_mean": 0.0012487415315263206,
      "clip_ratio/low_mean": 0.0014458097030001227,
      "clip_ratio/low_min": 0.00011995400018349756,
      "clip_ratio/region_mean": 0.0026945512436213903,
      "epoch": 0.05870651990036692,
      "grad_norm": 0.10536064207553864,
      "learning_rate": 1e-06,
      "loss": 0.0432,
      "step": 629
    },
    {
      "clip_ratio/high_max": 0.00295761782763293,
      "clip_ratio/high_mean": 0.0012614783117896877,
      "clip_ratio/low_mean": 0.0015288841859728564,
      "clip_ratio/low_min": 9.996736662287731e-05,
      "clip_ratio/region_mean": 0.0027903624868486077,
      "epoch": 0.0587998530003675,
      "grad_norm": 0.1187087669968605,
      "learning_rate": 1e-06,
      "loss": 0.0319,
      "step": 630
    },
    {
      "clip_ratio/high_max": 0.0033629569443291984,
      "clip_ratio/high_mean": 0.0014393862220458686,
      "clip_ratio/low_mean": 0.001504298510553781,
      "clip_ratio/low_min": 9.758964733919129e-05,
      "clip_ratio/region_mean": 0.002943684739875607,
      "epoch": 0.05889318610036808,
      "grad_norm": 0.11731305718421936,
      "learning_rate": 1e-06,
      "loss": 0.0368,
      "step": 631
    },
    {
      "clip_ratio/high_max": 0.0025362236992805265,
      "clip_ratio/high_mean": 0.0011733405772247352,
      "clip_ratio/low_mean": 0.0014804913189436775,
      "clip_ratio/low_min": 6.86692173985648e-05,
      "clip_ratio/region_mean": 0.002653831907082349,
      "epoch": 0.05898651920036867,
      "grad_norm": 0.11169592291116714,
      "learning_rate": 1e-06,
      "loss": 0.039,
      "step": 632
    },
    {
      "clip_ratio/high_max": 0.002341818224522285,
      "clip_ratio/high_mean": 0.001009324987535365,
      "clip_ratio/low_mean": 0.0016309768834616989,
      "clip_ratio/low_min": 0.00016387016694352496,
      "clip_ratio/region_mean": 0.0026403017691336572,
      "epoch": 0.05907985230036925,
      "grad_norm": 0.10973479598760605,
      "learning_rate": 1e-06,
      "loss": 0.0802,
      "step": 633
    },
    {
      "clip_ratio/high_max": 0.003161839136737399,
      "clip_ratio/high_mean": 0.001390608878864441,
      "clip_ratio/low_mean": 0.001491869319579564,
      "clip_ratio/low_min": 0.00013183088321966352,
      "clip_ratio/region_mean": 0.0028824782057199627,
      "epoch": 0.05917318540036983,
      "grad_norm": 0.10946914553642273,
      "learning_rate": 1e-06,
      "loss": 0.0234,
      "step": 634
    },
    {
      "clip_ratio/high_max": 0.002981438963615801,
      "clip_ratio/high_mean": 0.0012554377171909437,
      "clip_ratio/low_mean": 0.001528946559119504,
      "clip_ratio/low_min": 0.00020870682055829093,
      "clip_ratio/region_mean": 0.0027843843126902357,
      "epoch": 0.059266518500370416,
      "grad_norm": 0.11729389429092407,
      "learning_rate": 1e-06,
      "loss": 0.0103,
      "step": 635
    },
    {
      "clip_ratio/high_max": 0.0028081943601137027,
      "clip_ratio/high_mean": 0.0012507840474427212,
      "clip_ratio/low_mean": 0.0015382885794679169,
      "clip_ratio/low_min": 0.0002337202031412744,
      "clip_ratio/region_mean": 0.0027890726341865957,
      "epoch": 0.059359851600371,
      "grad_norm": 0.12659451365470886,
      "learning_rate": 1e-06,
      "loss": 0.0091,
      "step": 636
    },
    {
      "clip_ratio/high_max": 0.0027931696458836086,
      "clip_ratio/high_mean": 0.00120272222920903,
      "clip_ratio/low_mean": 0.0017151880128949415,
      "clip_ratio/low_min": 4.1624176446930505e-05,
      "clip_ratio/region_mean": 0.0029179101838963106,
      "epoch": 0.05945318470037158,
      "grad_norm": 0.11294504255056381,
      "learning_rate": 1e-06,
      "loss": 0.0289,
      "step": 637
    },
    {
      "clip_ratio/high_max": 0.002893213117204141,
      "clip_ratio/high_mean": 0.0010985886874550488,
      "clip_ratio/low_mean": 0.001700567481748294,
      "clip_ratio/low_min": 0.0001591967975400621,
      "clip_ratio/region_mean": 0.002799156151013449,
      "epoch": 0.059546517800372165,
      "grad_norm": 0.1137283593416214,
      "learning_rate": 1e-06,
      "loss": 0.0446,
      "step": 638
    },
    {
      "clip_ratio/high_max": 0.003044217679416761,
      "clip_ratio/high_mean": 0.0012996570476389024,
      "clip_ratio/low_mean": 0.0014075102044444066,
      "clip_ratio/low_min": 9.399888313055271e-05,
      "clip_ratio/region_mean": 0.002707167252083309,
      "epoch": 0.05963985090037275,
      "grad_norm": 0.11308509111404419,
      "learning_rate": 1e-06,
      "loss": -0.0169,
      "step": 639
    },
    {
      "clip_ratio/high_max": 0.002678591539734043,
      "clip_ratio/high_mean": 0.0012060598564858083,
      "clip_ratio/low_mean": 0.0017007987589749973,
      "clip_ratio/low_min": 0.00013706863319384865,
      "clip_ratio/region_mean": 0.0029068586736684665,
      "epoch": 0.059733184000373335,
      "grad_norm": 0.11297818273305893,
      "learning_rate": 1e-06,
      "loss": 0.041,
      "step": 640
    },
    {
      "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": 0.012058803013392905,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4093.0,
      "completions/mean_length": 609.9797973632812,
      "completions/mean_terminated_length": 567.429443359375,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.05982651710037391,
      "grad_norm": 0.1292581856250763,
      "learning_rate": 1e-06,
      "loss": 0.0193,
      "num_tokens": 485893065.0,
      "reward": 0.5891374945640564,
      "reward_std": 0.19757407903671265,
      "rewards/simpleverify_reward/mean": 0.5891374945640564,
      "rewards/simpleverify_reward/std": 0.4919925034046173,
      "step": 641
    },
    {
      "clip_ratio/high_max": 0.0021748554172518197,
      "clip_ratio/high_mean": 0.0009954512443073327,
      "clip_ratio/low_mean": 0.0005990892204863485,
      "clip_ratio/low_min": 1.7090511391870677e-05,
      "clip_ratio/region_mean": 0.0015945403974910732,
      "epoch": 0.0599198502003745,
      "grad_norm": 0.1223272904753685,
      "learning_rate": 1e-06,
      "loss": 0.017,
      "step": 642
    },
    {
      "clip_ratio/high_max": 0.0018065920812659897,
      "clip_ratio/high_mean": 0.0008048314630286768,
      "clip_ratio/low_mean": 0.0005610977905234904,
      "clip_ratio/low_min": 4.243129205860896e-05,
      "clip_ratio/region_mean": 0.0013659292217198526,
      "epoch": 0.060013183300375084,
      "grad_norm": 0.12602369487285614,
      "learning_rate": 1e-06,
      "loss": 0.0023,
      "step": 643
    },
    {
      "clip_ratio/high_max": 0.0020949177342117764,
      "clip_ratio/high_mean": 0.0009120941485889489,
      "clip_ratio/low_mean": 0.0006879099582874915,
      "clip_ratio/low_min": 6.950073020561831e-05,
      "clip_ratio/region_mean": 0.0016000041214283556,
      "epoch": 0.06010651640037567,
      "grad_norm": 0.11360519379377365,
      "learning_rate": 1e-06,
      "loss": 0.0057,
      "step": 644
    },
    {
      "clip_ratio/high_max": 0.0018249375534651335,
      "clip_ratio/high_mean": 0.0008150199009833159,
      "clip_ratio/low_mean": 0.0006981166598052368,
      "clip_ratio/low_min": 3.552807447704254e-05,
      "clip_ratio/region_mean": 0.001513136532594217,
      "epoch": 0.06019984950037625,
      "grad_norm": 0.1097647026181221,
      "learning_rate": 1e-06,
      "loss": 0.0,
      "step": 645
    },
    {
      "clip_ratio/high_max": 0.0020257036412658636,
      "clip_ratio/high_mean": 0.0008049288662732579,
      "clip_ratio/low_mean": 0.0008355631180165801,
      "clip_ratio/low_min": 5.522824176296126e-05,
      "clip_ratio/region_mean": 0.0016404919952037744,
      "epoch": 0.06029318260037683,
      "grad_norm": 0.12153657525777817,
      "learning_rate": 1e-06,
      "loss": 0.0226,
      "step": 646
    },
    {
      "clip_ratio/high_max": 0.002552907095378032,
      "clip_ratio/high_mean": 0.0009890525543596596,
      "clip_ratio/low_mean": 0.000778659514253377,
      "clip_ratio/low_min": 2.18493278225651e-05,
      "clip_ratio/region_mean": 0.0017677120013104286,
      "epoch": 0.06038651570037742,
      "grad_norm": 0.47265344858169556,
      "learning_rate": 1e-06,
      "loss": 0.0194,
      "step": 647
    },
    {
      "clip_ratio/high_max": 0.002179434915888123,
      "clip_ratio/high_mean": 0.0009403069689142285,
      "clip_ratio/low_mean": 0.0008266525037470274,
      "clip_ratio/low_min": 3.832214861176908e-05,
      "clip_ratio/region_mean": 0.0017669594817562029,
      "epoch": 0.060479848800377996,
      "grad_norm": 0.1060282364487648,
      "learning_rate": 1e-06,
      "loss": -0.0001,
      "step": 648
    },
    {
      "clip_ratio/high_max": 0.0019388398286537267,
      "clip_ratio/high_mean": 0.0008207587234210223,
      "clip_ratio/low_mean": 0.0008359317253052723,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0016566904741921462,
      "epoch": 0.06057318190037858,
      "grad_norm": 0.11346718668937683,
      "learning_rate": 1e-06,
      "loss": 0.0049,
      "step": 649
    },
    {
      "clip_ratio/high_max": 0.0021642236315528862,
      "clip_ratio/high_mean": 0.0008643663350085262,
      "clip_ratio/low_mean": 0.0009825911620282568,
      "clip_ratio/low_min": 0.00012871516446466558,
      "clip_ratio/region_mean": 0.0018469574642949738,
      "epoch": 0.060666515000379166,
      "grad_norm": 0.10506804287433624,
      "learning_rate": 1e-06,
      "loss": 0.0366,
      "step": 650
    },
    {
      "clip_ratio/high_max": 0.0018231422181997914,
      "clip_ratio/high_mean": 0.0008435171821474796,
      "clip_ratio/low_mean": 0.001088205670384923,
      "clip_ratio/low_min": 0.00010629372263792902,
      "clip_ratio/region_mean": 0.0019317228143336251,
      "epoch": 0.06075984810037975,
      "grad_norm": 0.1282629817724228,
      "learning_rate": 1e-06,
      "loss": 0.0514,
      "step": 651
    },
    {
      "clip_ratio/high_max": 0.0021607658491120674,
      "clip_ratio/high_mean": 0.0008906453622330446,
      "clip_ratio/low_mean": 0.0011829749691969482,
      "clip_ratio/low_min": 0.00023498674363509053,
      "clip_ratio/region_mean": 0.002073620315059088,
      "epoch": 0.06085318120038033,
      "grad_norm": 0.10715054720640182,
      "learning_rate": 1e-06,
      "loss": 0.0603,
      "step": 652
    },
    {
      "clip_ratio/high_max": 0.002410183828033041,
      "clip_ratio/high_mean": 0.0009837968354986515,
      "clip_ratio/low_mean": 0.0009434997627977282,
      "clip_ratio/low_min": 6.215477696969174e-05,
      "clip_ratio/region_mean": 0.0019272965437266976,
      "epoch": 0.060946514300380915,
      "grad_norm": 0.11937594413757324,
      "learning_rate": 1e-06,
      "loss": 0.0328,
      "step": 653
    },
    {
      "clip_ratio/high_max": 0.0024948293867055327,
      "clip_ratio/high_mean": 0.0010107441357831703,
      "clip_ratio/low_mean": 0.0009076120550162159,
      "clip_ratio/low_min": 1.8241353245684877e-05,
      "clip_ratio/region_mean": 0.0019183562108082697,
      "epoch": 0.0610398474003815,
      "grad_norm": 0.12305525690317154,
      "learning_rate": 1e-06,
      "loss": 0.0097,
      "step": 654
    },
    {
      "clip_ratio/high_max": 0.002373426097619813,
      "clip_ratio/high_mean": 0.0010299016303179087,
      "clip_ratio/low_mean": 0.0009326153976871865,
      "clip_ratio/low_min": 6.017443956807256e-05,
      "clip_ratio/region_mean": 0.0019625170461949892,
      "epoch": 0.061133180500382085,
      "grad_norm": 0.11715622991323471,
      "learning_rate": 1e-06,
      "loss": 0.0078,
      "step": 655
    },
    {
      "clip_ratio/high_max": 0.001954997111170087,
      "clip_ratio/high_mean": 0.0009834772390604485,
      "clip_ratio/low_mean": 0.0009611216191842686,
      "clip_ratio/low_min": 9.363302615383873e-05,
      "clip_ratio/region_mean": 0.0019445988873485476,
      "epoch": 0.061226513600382663,
      "grad_norm": 0.11515656858682632,
      "learning_rate": 1e-06,
      "loss": 0.0282,
      "step": 656
    },
    {
      "clip_ratio/high_max": 0.002431402994261589,
      "clip_ratio/high_mean": 0.0010576932418189244,
      "clip_ratio/low_mean": 0.0010466949352121446,
      "clip_ratio/low_min": 0.00013691628373635467,
      "clip_ratio/region_mean": 0.0021043881788500585,
      "epoch": 0.06131984670038325,
      "grad_norm": 0.12049777060747147,
      "learning_rate": 1e-06,
      "loss": 0.0106,
      "step": 657
    },
    {
      "clip_ratio/high_max": 0.002144788690202404,
      "clip_ratio/high_mean": 0.001019918498059269,
      "clip_ratio/low_mean": 0.0009519484938209644,
      "clip_ratio/low_min": 0.00016175894779735245,
      "clip_ratio/region_mean": 0.001971866993699223,
      "epoch": 0.061413179800383834,
      "grad_norm": 0.11356595158576965,
      "learning_rate": 1e-06,
      "loss": 0.007,
      "step": 658
    },
    {
      "clip_ratio/high_max": 0.0021800879621878266,
      "clip_ratio/high_mean": 0.0009550613358442206,
      "clip_ratio/low_mean": 0.0010843024974747095,
      "clip_ratio/low_min": 9.379323364555603e-05,
      "clip_ratio/region_mean": 0.002039363869698718,
      "epoch": 0.06150651290038442,
      "grad_norm": 0.12183915823698044,
      "learning_rate": 1e-06,
      "loss": 0.029,
      "step": 659
    },
    {
      "clip_ratio/high_max": 0.0025504031509626657,
      "clip_ratio/high_mean": 0.00108420853575808,
      "clip_ratio/low_mean": 0.0011944966045120964,
      "clip_ratio/low_min": 0.00013418217895377893,
      "clip_ratio/region_mean": 0.0022787051493651234,
      "epoch": 0.061599846000385,
      "grad_norm": 0.1095348596572876,
      "learning_rate": 1e-06,
      "loss": 0.0127,
      "step": 660
    },
    {
      "clip_ratio/high_max": 0.002132608959072968,
      "clip_ratio/high_mean": 0.0008687532008480048,
      "clip_ratio/low_mean": 0.0011514902544149663,
      "clip_ratio/low_min": 0.00012971089927305002,
      "clip_ratio/region_mean": 0.0020202434752718545,
      "epoch": 0.06169317910038558,
      "grad_norm": 0.12734737992286682,
      "learning_rate": 1e-06,
      "loss": 0.0849,
      "step": 661
    },
    {
      "clip_ratio/high_max": 0.0027423021601862274,
      "clip_ratio/high_mean": 0.0011134156411571894,
      "clip_ratio/low_mean": 0.0010306433559890138,
      "clip_ratio/low_min": 3.0472036087303422e-05,
      "clip_ratio/region_mean": 0.002144059028069023,
      "epoch": 0.06178651220038617,
      "grad_norm": 0.11798778921365738,
      "learning_rate": 1e-06,
      "loss": 0.0016,
      "step": 662
    },
    {
      "clip_ratio/high_max": 0.002260082990687806,
      "clip_ratio/high_mean": 0.0010156289717997424,
      "clip_ratio/low_mean": 0.0011134239121020073,
      "clip_ratio/low_min": 0.00022802861167292576,
      "clip_ratio/region_mean": 0.0021290528820827603,
      "epoch": 0.061879845300386746,
      "grad_norm": 0.1136472076177597,
      "learning_rate": 1e-06,
      "loss": 0.0168,
      "step": 663
    },
    {
      "clip_ratio/high_max": 0.002391207504842896,
      "clip_ratio/high_mean": 0.0009677176240074914,
      "clip_ratio/low_mean": 0.0009122883857344277,
      "clip_ratio/low_min": 6.210313949850388e-05,
      "clip_ratio/region_mean": 0.0018800059879140463,
      "epoch": 0.06197317840038733,
      "grad_norm": 0.11377140879631042,
      "learning_rate": 1e-06,
      "loss": 0.0243,
      "step": 664
    },
    {
      "clip_ratio/high_max": 0.0024142058900906704,
      "clip_ratio/high_mean": 0.0009860117061180063,
      "clip_ratio/low_mean": 0.0010925081669483916,
      "clip_ratio/low_min": 0.00016608188343525399,
      "clip_ratio/region_mean": 0.0020785199085366912,
      "epoch": 0.062066511500387916,
      "grad_norm": 0.1222008764743805,
      "learning_rate": 1e-06,
      "loss": 0.0258,
      "step": 665
    },
    {
      "clip_ratio/high_max": 0.00221043895726325,
      "clip_ratio/high_mean": 0.0009247103316738503,
      "clip_ratio/low_mean": 0.0010705184067774098,
      "clip_ratio/low_min": 0.00015207652086246526,
      "clip_ratio/region_mean": 0.0019952287548221648,
      "epoch": 0.0621598446003885,
      "grad_norm": 0.11470475047826767,
      "learning_rate": 1e-06,
      "loss": 0.0706,
      "step": 666
    },
    {
      "clip_ratio/high_max": 0.002046182482445147,
      "clip_ratio/high_mean": 0.0010548308746365365,
      "clip_ratio/low_mean": 0.0011983355962001951,
      "clip_ratio/low_min": 0.00011185111543454695,
      "clip_ratio/region_mean": 0.0022531664217240177,
      "epoch": 0.06225317770038908,
      "grad_norm": 0.11831323802471161,
      "learning_rate": 1e-06,
      "loss": 0.0183,
      "step": 667
    },
    {
      "clip_ratio/high_max": 0.0023645868386665825,
      "clip_ratio/high_mean": 0.0009916117160173599,
      "clip_ratio/low_mean": 0.0012133550735597964,
      "clip_ratio/low_min": 0.00011389496103220154,
      "clip_ratio/region_mean": 0.0022049667895771563,
      "epoch": 0.062346510800389665,
      "grad_norm": 0.12757113575935364,
      "learning_rate": 1e-06,
      "loss": 0.0364,
      "step": 668
    },
    {
      "clip_ratio/high_max": 0.0024345343408640474,
      "clip_ratio/high_mean": 0.0011065738308388973,
      "clip_ratio/low_mean": 0.0011969369097641902,
      "clip_ratio/low_min": 4.826254735235125e-05,
      "clip_ratio/region_mean": 0.002303510751517024,
      "epoch": 0.06243984390039025,
      "grad_norm": 0.12438348680734634,
      "learning_rate": 1e-06,
      "loss": 0.0029,
      "step": 669
    },
    {
      "clip_ratio/high_max": 0.0019871227705152705,
      "clip_ratio/high_mean": 0.0008757966425037012,
      "clip_ratio/low_mean": 0.00103066617884906,
      "clip_ratio/low_min": 5.639658684231108e-05,
      "clip_ratio/region_mean": 0.0019064628504565917,
      "epoch": 0.06253317700039084,
      "grad_norm": 0.11792006343603134,
      "learning_rate": 1e-06,
      "loss": -0.0008,
      "step": 670
    },
    {
      "clip_ratio/high_max": 0.0023602003675478045,
      "clip_ratio/high_mean": 0.001051755029038759,
      "clip_ratio/low_mean": 0.0012430751412466634,
      "clip_ratio/low_min": 0.00018060886031889822,
      "clip_ratio/region_mean": 0.0022948301339056343,
      "epoch": 0.06262651010039141,
      "grad_norm": 0.11470434069633484,
      "learning_rate": 1e-06,
      "loss": -0.0023,
      "step": 671
    },
    {
      "clip_ratio/high_max": 0.00284223556809593,
      "clip_ratio/high_mean": 0.0012327261283644475,
      "clip_ratio/low_mean": 0.0010937725273834076,
      "clip_ratio/low_min": 0.00011392452324798796,
      "clip_ratio/region_mean": 0.0023264986521098763,
      "epoch": 0.062719843200392,
      "grad_norm": 0.12206578999757767,
      "learning_rate": 1e-06,
      "loss": -0.0226,
      "step": 672
    },
    {
      "clip_ratio/high_max": 0.002285585542267654,
      "clip_ratio/high_mean": 0.0010097148151544388,
      "clip_ratio/low_mean": 0.0011519285435497295,
      "clip_ratio/low_min": 0.00012479134875320597,
      "clip_ratio/region_mean": 0.0021616434169118293,
      "epoch": 0.06281317630039258,
      "grad_norm": 0.11518562585115433,
      "learning_rate": 1e-06,
      "loss": 0.0236,
      "step": 673
    },
    {
      "clip_ratio/high_max": 0.0021758834627689794,
      "clip_ratio/high_mean": 0.0009735883795656264,
      "clip_ratio/low_mean": 0.0011830461517092772,
      "clip_ratio/low_min": 6.17078912910074e-05,
      "clip_ratio/region_mean": 0.0021566345749306493,
      "epoch": 0.06290650940039316,
      "grad_norm": 0.1052321121096611,
      "learning_rate": 1e-06,
      "loss": 0.0373,
      "step": 674
    },
    {
      "clip_ratio/high_max": 0.002513353480026126,
      "clip_ratio/high_mean": 0.0010438256676934543,
      "clip_ratio/low_mean": 0.0013691830754396506,
      "clip_ratio/low_min": 0.00015871398773015244,
      "clip_ratio/region_mean": 0.0024130087695084512,
      "epoch": 0.06299984250039375,
      "grad_norm": 0.12379326671361923,
      "learning_rate": 1e-06,
      "loss": 0.0563,
      "step": 675
    },
    {
      "clip_ratio/high_max": 0.002718938012549188,
      "clip_ratio/high_mean": 0.001030139610520564,
      "clip_ratio/low_mean": 0.0012635992534342222,
      "clip_ratio/low_min": 0.0001264313450519694,
      "clip_ratio/region_mean": 0.002293738885782659,
      "epoch": 0.06309317560039433,
      "grad_norm": 0.12343112379312515,
      "learning_rate": 1e-06,
      "loss": 0.0314,
      "step": 676
    },
    {
      "clip_ratio/high_max": 0.0025925431109499186,
      "clip_ratio/high_mean": 0.001092134727514349,
      "clip_ratio/low_mean": 0.0010619158092595171,
      "clip_ratio/low_min": 3.811750502791256e-05,
      "clip_ratio/region_mean": 0.0021540505331358872,
      "epoch": 0.06318650870039491,
      "grad_norm": 0.11260983347892761,
      "learning_rate": 1e-06,
      "loss": 0.009,
      "step": 677
    },
    {
      "clip_ratio/high_max": 0.003240023215766996,
      "clip_ratio/high_mean": 0.0012721459461317863,
      "clip_ratio/low_mean": 0.0010284298605256481,
      "clip_ratio/low_min": 5.104638239572523e-05,
      "clip_ratio/region_mean": 0.0023005758557701483,
      "epoch": 0.0632798418003955,
      "grad_norm": 0.12015233933925629,
      "learning_rate": 1e-06,
      "loss": -0.012,
      "step": 678
    },
    {
      "clip_ratio/high_max": 0.0026589845947455615,
      "clip_ratio/high_mean": 0.0011535403646121267,
      "clip_ratio/low_mean": 0.0010735983196354937,
      "clip_ratio/low_min": 0.00011731040285667405,
      "clip_ratio/region_mean": 0.0022271386624197476,
      "epoch": 0.06337317490039608,
      "grad_norm": 0.12267571687698364,
      "learning_rate": 1e-06,
      "loss": 0.0142,
      "step": 679
    },
    {
      "clip_ratio/high_max": 0.0025322256187791936,
      "clip_ratio/high_mean": 0.0010675332887331024,
      "clip_ratio/low_mean": 0.0011451830541773234,
      "clip_ratio/low_min": 0.00015298763446480734,
      "clip_ratio/region_mean": 0.0022127163465484045,
      "epoch": 0.06346650800039666,
      "grad_norm": 0.3585658073425293,
      "learning_rate": 1e-06,
      "loss": 0.0511,
      "step": 680
    },
    {
      "clip_ratio/high_max": 0.0023519998358096927,
      "clip_ratio/high_mean": 0.0009954732122423593,
      "clip_ratio/low_mean": 0.0012203052538097836,
      "clip_ratio/low_min": 0.00014456269491347484,
      "clip_ratio/region_mean": 0.002215778462414164,
      "epoch": 0.06355984110039725,
      "grad_norm": 0.20242321491241455,
      "learning_rate": 1e-06,
      "loss": 0.0491,
      "step": 681
    },
    {
      "clip_ratio/high_max": 0.002439431962557137,
      "clip_ratio/high_mean": 0.0009475969072809676,
      "clip_ratio/low_mean": 0.0013035246010986157,
      "clip_ratio/low_min": 0.00019228864766773768,
      "clip_ratio/region_mean": 0.0022511215356644243,
      "epoch": 0.06365317420039783,
      "grad_norm": 0.10807636380195618,
      "learning_rate": 1e-06,
      "loss": 0.0789,
      "step": 682
    },
    {
      "clip_ratio/high_max": 0.002316114077984821,
      "clip_ratio/high_mean": 0.0009486514791205991,
      "clip_ratio/low_mean": 0.0012019726309517864,
      "clip_ratio/low_min": 0.0001298677152590244,
      "clip_ratio/region_mean": 0.0021506240955204703,
      "epoch": 0.06374650730039842,
      "grad_norm": 0.1070273295044899,
      "learning_rate": 1e-06,
      "loss": 0.0298,
      "step": 683
    },
    {
      "clip_ratio/high_max": 0.002226147538749501,
      "clip_ratio/high_mean": 0.0010514173700357787,
      "clip_ratio/low_mean": 0.0012112994663766585,
      "clip_ratio/low_min": 9.296199641539715e-05,
      "clip_ratio/region_mean": 0.0022627168364124373,
      "epoch": 0.063839840400399,
      "grad_norm": 0.11416471749544144,
      "learning_rate": 1e-06,
      "loss": 0.0339,
      "step": 684
    },
    {
      "clip_ratio/high_max": 0.0025248121601180173,
      "clip_ratio/high_mean": 0.0010145499363716226,
      "clip_ratio/low_mean": 0.0012123338365199743,
      "clip_ratio/low_min": 7.565199302916881e-05,
      "clip_ratio/region_mean": 0.0022268837565206923,
      "epoch": 0.06393317350039958,
      "grad_norm": 0.11256154626607895,
      "learning_rate": 1e-06,
      "loss": 0.0129,
      "step": 685
    },
    {
      "clip_ratio/high_max": 0.002097346165101044,
      "clip_ratio/high_mean": 0.0009084048760996666,
      "clip_ratio/low_mean": 0.0011575487078516744,
      "clip_ratio/low_min": 1.950686601048801e-05,
      "clip_ratio/region_mean": 0.002065953565761447,
      "epoch": 0.06402650660040017,
      "grad_norm": 0.11213254183530807,
      "learning_rate": 1e-06,
      "loss": 0.0465,
      "step": 686
    },
    {
      "clip_ratio/high_max": 0.002256944280816242,
      "clip_ratio/high_mean": 0.0010432040271552978,
      "clip_ratio/low_mean": 0.0012024112547805998,
      "clip_ratio/low_min": 0.0002010854204854695,
      "clip_ratio/region_mean": 0.002245615287392866,
      "epoch": 0.06411983970040075,
      "grad_norm": 0.11101026833057404,
      "learning_rate": 1e-06,
      "loss": 0.0416,
      "step": 687
    },
    {
      "clip_ratio/high_max": 0.002001195040065795,
      "clip_ratio/high_mean": 0.0009077958966372535,
      "clip_ratio/low_mean": 0.0011917410647583893,
      "clip_ratio/low_min": 0.0001307397496930207,
      "clip_ratio/region_mean": 0.0020995369923184626,
      "epoch": 0.06421317280040133,
      "grad_norm": 0.10993636399507523,
      "learning_rate": 1e-06,
      "loss": 0.0459,
      "step": 688
    },
    {
      "clip_ratio/high_max": 0.0030557825666619465,
      "clip_ratio/high_mean": 0.0010894620136241429,
      "clip_ratio/low_mean": 0.0010890003431995865,
      "clip_ratio/low_min": 7.668862235732377e-05,
      "clip_ratio/region_mean": 0.0021784623531857505,
      "epoch": 0.06430650590040192,
      "grad_norm": 0.11251064389944077,
      "learning_rate": 1e-06,
      "loss": 0.0068,
      "step": 689
    },
    {
      "clip_ratio/high_max": 0.0025424556006328203,
      "clip_ratio/high_mean": 0.0010000574275181862,
      "clip_ratio/low_mean": 0.0013550070289056748,
      "clip_ratio/low_min": 0.00015537701074208599,
      "clip_ratio/region_mean": 0.0023550644400529563,
      "epoch": 0.0643998390004025,
      "grad_norm": 0.11436987668275833,
      "learning_rate": 1e-06,
      "loss": 0.046,
      "step": 690
    },
    {
      "clip_ratio/high_max": 0.0024922296215663664,
      "clip_ratio/high_mean": 0.0011286482476862147,
      "clip_ratio/low_mean": 0.0011835709301522002,
      "clip_ratio/low_min": 0.00011363453631929588,
      "clip_ratio/region_mean": 0.002312219097802881,
      "epoch": 0.06449317210040308,
      "grad_norm": 0.1161859780550003,
      "learning_rate": 1e-06,
      "loss": 0.0096,
      "step": 691
    },
    {
      "clip_ratio/high_max": 0.00299485755385831,
      "clip_ratio/high_mean": 0.0012416012050380232,
      "clip_ratio/low_mean": 0.001249080705747474,
      "clip_ratio/low_min": 0.00010149267836823128,
      "clip_ratio/region_mean": 0.0024906818798626773,
      "epoch": 0.06458650520040367,
      "grad_norm": 0.12285619229078293,
      "learning_rate": 1e-06,
      "loss": 0.0326,
      "step": 692
    },
    {
      "clip_ratio/high_max": 0.0027557476132642478,
      "clip_ratio/high_mean": 0.0010278811569151003,
      "clip_ratio/low_mean": 0.0012661598811973818,
      "clip_ratio/low_min": 3.7130223063286394e-05,
      "clip_ratio/region_mean": 0.0022940410635783337,
      "epoch": 0.06467983830040425,
      "grad_norm": 0.11306583136320114,
      "learning_rate": 1e-06,
      "loss": 0.0664,
      "step": 693
    },
    {
      "clip_ratio/high_max": 0.0024865824343578424,
      "clip_ratio/high_mean": 0.0010564833082753466,
      "clip_ratio/low_mean": 0.0011395050332794199,
      "clip_ratio/low_min": 8.61471016833093e-05,
      "clip_ratio/region_mean": 0.0021959883597446606,
      "epoch": 0.06477317140040484,
      "grad_norm": 0.10932648926973343,
      "learning_rate": 1e-06,
      "loss": 0.0481,
      "step": 694
    },
    {
      "clip_ratio/high_max": 0.0026135559819522314,
      "clip_ratio/high_mean": 0.0011820854015240911,
      "clip_ratio/low_mean": 0.0012931187702633906,
      "clip_ratio/low_min": 0.00024147951353370445,
      "clip_ratio/region_mean": 0.0024752041717874818,
      "epoch": 0.06486650450040542,
      "grad_norm": 0.12203668802976608,
      "learning_rate": 1e-06,
      "loss": 0.0139,
      "step": 695
    },
    {
      "clip_ratio/high_max": 0.0029835702225682326,
      "clip_ratio/high_mean": 0.0012344263232080266,
      "clip_ratio/low_mean": 0.0009928158397087827,
      "clip_ratio/low_min": 1.1378117960703094e-05,
      "clip_ratio/region_mean": 0.0022272421265370212,
      "epoch": 0.064959837600406,
      "grad_norm": 0.10823118686676025,
      "learning_rate": 1e-06,
      "loss": -0.0247,
      "step": 696
    },
    {
      "clip_ratio/high_max": 0.002486766898073256,
      "clip_ratio/high_mean": 0.001023224062009831,
      "clip_ratio/low_mean": 0.0012401856038195547,
      "clip_ratio/low_min": 0.00011983016520389356,
      "clip_ratio/region_mean": 0.0022634096385445446,
      "epoch": 0.06505317070040659,
      "grad_norm": 0.11041391640901566,
      "learning_rate": 1e-06,
      "loss": -0.0081,
      "step": 697
    },
    {
      "clip_ratio/high_max": 0.003181499705533497,
      "clip_ratio/high_mean": 0.001253966176591348,
      "clip_ratio/low_mean": 0.0012152980743849184,
      "clip_ratio/low_min": 0.0001974070673895767,
      "clip_ratio/region_mean": 0.002469264349201694,
      "epoch": 0.06514650380040717,
      "grad_norm": 0.12527211010456085,
      "learning_rate": 1e-06,
      "loss": 0.0065,
      "step": 698
    },
    {
      "clip_ratio/high_max": 0.0025787828853935935,
      "clip_ratio/high_mean": 0.0011685543322528247,
      "clip_ratio/low_mean": 0.0011808987892436562,
      "clip_ratio/low_min": 5.9521842558751814e-05,
      "clip_ratio/region_mean": 0.002349453112401534,
      "epoch": 0.06523983690040774,
      "grad_norm": 0.1265258938074112,
      "learning_rate": 1e-06,
      "loss": -0.005,
      "step": 699
    },
    {
      "clip_ratio/high_max": 0.0027186387960682623,
      "clip_ratio/high_mean": 0.0011066180850320961,
      "clip_ratio/low_mean": 0.0011967343016294762,
      "clip_ratio/low_min": 0.00011390815052436665,
      "clip_ratio/region_mean": 0.002303352397575509,
      "epoch": 0.06533317000040834,
      "grad_norm": 0.11757099628448486,
      "learning_rate": 1e-06,
      "loss": 0.0237,
      "step": 700
    },
    {
      "clip_ratio/high_max": 0.0026916003262158483,
      "clip_ratio/high_mean": 0.0011009733643732034,
      "clip_ratio/low_mean": 0.0010691498573578428,
      "clip_ratio/low_min": 4.0817776607582346e-05,
      "clip_ratio/region_mean": 0.0021701232544728555,
      "epoch": 0.06542650310040891,
      "grad_norm": 0.17064279317855835,
      "learning_rate": 1e-06,
      "loss": -0.0163,
      "step": 701
    },
    {
      "clip_ratio/high_max": 0.0029597807661048137,
      "clip_ratio/high_mean": 0.001204866810439853,
      "clip_ratio/low_mean": 0.0011565085005713627,
      "clip_ratio/low_min": 0.00011697697118506767,
      "clip_ratio/region_mean": 0.0023613753364770673,
      "epoch": 0.06551983620040949,
      "grad_norm": 0.11354461312294006,
      "learning_rate": 1e-06,
      "loss": 0.0107,
      "step": 702
    },
    {
      "clip_ratio/high_max": 0.002540388082707068,
      "clip_ratio/high_mean": 0.0011217966948606772,
      "clip_ratio/low_mean": 0.0011787978692154866,
      "clip_ratio/low_min": 0.00022767904556530993,
      "clip_ratio/region_mean": 0.002300594547705259,
      "epoch": 0.06561316930041008,
      "grad_norm": 0.10583575069904327,
      "learning_rate": 1e-06,
      "loss": 0.025,
      "step": 703
    },
    {
      "clip_ratio/high_max": 0.0025225327408406883,
      "clip_ratio/high_mean": 0.0012109802883060183,
      "clip_ratio/low_mean": 0.0012246007536305115,
      "clip_ratio/low_min": 0.00024415691314061405,
      "clip_ratio/region_mean": 0.0024355810237466358,
      "epoch": 0.06570650240041066,
      "grad_norm": 0.11225082725286484,
      "learning_rate": 1e-06,
      "loss": 0.0502,
      "step": 704
    },
    {
      "clip_ratio/high_max": 0.0025045224465429783,
      "clip_ratio/high_mean": 0.0011060026445193216,
      "clip_ratio/low_mean": 0.001219853980728658,
      "clip_ratio/low_min": 0.00011860257745865965,
      "clip_ratio/region_mean": 0.0023258565852302127,
      "epoch": 0.06579983550041126,
      "grad_norm": 0.12580445408821106,
      "learning_rate": 1e-06,
      "loss": 0.0599,
      "step": 705
    },
    {
      "clip_ratio/high_max": 0.0028461952388170175,
      "clip_ratio/high_mean": 0.0012014506664854707,
      "clip_ratio/low_mean": 0.001123272806580644,
      "clip_ratio/low_min": 9.10626758923172e-05,
      "clip_ratio/region_mean": 0.0023247234857990406,
      "epoch": 0.06589316860041183,
      "grad_norm": 0.11595622450113297,
      "learning_rate": 1e-06,
      "loss": 0.0131,
      "step": 706
    },
    {
      "clip_ratio/high_max": 0.0028481978151830845,
      "clip_ratio/high_mean": 0.0013104877689329442,
      "clip_ratio/low_mean": 0.0011574751588341314,
      "clip_ratio/low_min": 9.656323345552664e-05,
      "clip_ratio/region_mean": 0.002467962920491118,
      "epoch": 0.06598650170041241,
      "grad_norm": 0.1162097305059433,
      "learning_rate": 1e-06,
      "loss": 0.0064,
      "step": 707
    },
    {
      "clip_ratio/high_max": 0.0028246581423445605,
      "clip_ratio/high_mean": 0.0011492847515910398,
      "clip_ratio/low_mean": 0.0010771316101454431,
      "clip_ratio/low_min": 6.393207877408713e-05,
      "clip_ratio/region_mean": 0.002226416349003557,
      "epoch": 0.066079834800413,
      "grad_norm": 0.11277379095554352,
      "learning_rate": 1e-06,
      "loss": -0.0009,
      "step": 708
    },
    {
      "clip_ratio/high_max": 0.0027570801830734126,
      "clip_ratio/high_mean": 0.0011877820343215717,
      "clip_ratio/low_mean": 0.001361203430860769,
      "clip_ratio/low_min": 8.253211581177311e-05,
      "clip_ratio/region_mean": 0.0025489854597253725,
      "epoch": 0.06617316790041358,
      "grad_norm": 0.11838237196207047,
      "learning_rate": 1e-06,
      "loss": 0.0378,
      "step": 709
    },
    {
      "clip_ratio/high_max": 0.002480254028341733,
      "clip_ratio/high_mean": 0.0010067512557725422,
      "clip_ratio/low_mean": 0.0012594378385983873,
      "clip_ratio/low_min": 0.00012312238141021226,
      "clip_ratio/region_mean": 0.002266189141664654,
      "epoch": 0.06626650100041416,
      "grad_norm": 0.11159567534923553,
      "learning_rate": 1e-06,
      "loss": 0.0409,
      "step": 710
    },
    {
      "clip_ratio/high_max": 0.0028501835113274865,
      "clip_ratio/high_mean": 0.0011509106188896112,
      "clip_ratio/low_mean": 0.0011076549635617994,
      "clip_ratio/low_min": 7.029519838397391e-05,
      "clip_ratio/region_mean": 0.00225856555334758,
      "epoch": 0.06635983410041475,
      "grad_norm": 0.1090884730219841,
      "learning_rate": 1e-06,
      "loss": -0.019,
      "step": 711
    },
    {
      "clip_ratio/high_max": 0.0025015131250256673,
      "clip_ratio/high_mean": 0.0011309608998999465,
      "clip_ratio/low_mean": 0.0013818166880810168,
      "clip_ratio/low_min": 0.0001644355534153874,
      "clip_ratio/region_mean": 0.002512777646188624,
      "epoch": 0.06645316720041533,
      "grad_norm": 0.1104603111743927,
      "learning_rate": 1e-06,
      "loss": 0.0116,
      "step": 712
    },
    {
      "clip_ratio/high_max": 0.002846267518179957,
      "clip_ratio/high_mean": 0.001182878570034518,
      "clip_ratio/low_mean": 0.0012490217668528203,
      "clip_ratio/low_min": 0.0001320163682976272,
      "clip_ratio/region_mean": 0.002431900327792391,
      "epoch": 0.06654650030041591,
      "grad_norm": 0.11057287454605103,
      "learning_rate": 1e-06,
      "loss": 0.0394,
      "step": 713
    },
    {
      "clip_ratio/high_max": 0.0026766815717564896,
      "clip_ratio/high_mean": 0.0011324906154186465,
      "clip_ratio/low_mean": 0.001155380730779143,
      "clip_ratio/low_min": 0.00015753878324176185,
      "clip_ratio/region_mean": 0.0022878713498357683,
      "epoch": 0.0666398334004165,
      "grad_norm": 0.11118446290493011,
      "learning_rate": 1e-06,
      "loss": 0.0163,
      "step": 714
    },
    {
      "clip_ratio/high_max": 0.0028064691941835918,
      "clip_ratio/high_mean": 0.0011794291567639448,
      "clip_ratio/low_mean": 0.0013450968253891915,
      "clip_ratio/low_min": 7.189430152720888e-05,
      "clip_ratio/region_mean": 0.0025245259748771787,
      "epoch": 0.06673316650041708,
      "grad_norm": 0.10817889869213104,
      "learning_rate": 1e-06,
      "loss": 0.0139,
      "step": 715
    },
    {
      "clip_ratio/high_max": 0.002478754802723415,
      "clip_ratio/high_mean": 0.0010416226614324842,
      "clip_ratio/low_mean": 0.0014740600272489246,
      "clip_ratio/low_min": 0.00015510835419263458,
      "clip_ratio/region_mean": 0.0025156826595775783,
      "epoch": 0.06682649960041767,
      "grad_norm": 0.12320508062839508,
      "learning_rate": 1e-06,
      "loss": 0.0807,
      "step": 716
    },
    {
      "clip_ratio/high_max": 0.002839442102413159,
      "clip_ratio/high_mean": 0.0012444161147868726,
      "clip_ratio/low_mean": 0.0014227368628780823,
      "clip_ratio/low_min": 0.00010660336010914762,
      "clip_ratio/region_mean": 0.0026671530213207006,
      "epoch": 0.06691983270041825,
      "grad_norm": 0.10894238203763962,
      "learning_rate": 1e-06,
      "loss": 0.0101,
      "step": 717
    },
    {
      "clip_ratio/high_max": 0.0027487784682307392,
      "clip_ratio/high_mean": 0.0011286169828963466,
      "clip_ratio/low_mean": 0.001303982895478839,
      "clip_ratio/low_min": 0.00011971952881140169,
      "clip_ratio/region_mean": 0.002432599852909334,
      "epoch": 0.06701316580041883,
      "grad_norm": 0.11518412083387375,
      "learning_rate": 1e-06,
      "loss": 0.0245,
      "step": 718
    },
    {
      "clip_ratio/high_max": 0.002953848939796444,
      "clip_ratio/high_mean": 0.0012476090596464928,
      "clip_ratio/low_mean": 0.001168877261079615,
      "clip_ratio/low_min": 0.00022012464160070522,
      "clip_ratio/region_mean": 0.0024164863061741926,
      "epoch": 0.06710649890041942,
      "grad_norm": 0.10688501596450806,
      "learning_rate": 1e-06,
      "loss": 0.0023,
      "step": 719
    },
    {
      "clip_ratio/high_max": 0.002876053396903444,
      "clip_ratio/high_mean": 0.0012736888820654713,
      "clip_ratio/low_mean": 0.0011923532256332692,
      "clip_ratio/low_min": 1.4282450138125569e-05,
      "clip_ratio/region_mean": 0.002466042038577143,
      "epoch": 0.06719983200042,
      "grad_norm": 0.11770960688591003,
      "learning_rate": 1e-06,
      "loss": -0.001,
      "step": 720
    },
    {
      "clip_ratio/high_max": 0.00280849384580506,
      "clip_ratio/high_mean": 0.0012143038838985376,
      "clip_ratio/low_mean": 0.0013375899943639524,
      "clip_ratio/low_min": 0.0001574281122884713,
      "clip_ratio/region_mean": 0.0025518938491586596,
      "epoch": 0.06729316510042058,
      "grad_norm": 0.10870195180177689,
      "learning_rate": 1e-06,
      "loss": -0.0131,
      "step": 721
    },
    {
      "clip_ratio/high_max": 0.002300151107192505,
      "clip_ratio/high_mean": 0.0010804168778122403,
      "clip_ratio/low_mean": 0.0013466928285197355,
      "clip_ratio/low_min": 0.0001748389968270203,
      "clip_ratio/region_mean": 0.002427109742711764,
      "epoch": 0.06738649820042117,
      "grad_norm": 0.11212006211280823,
      "learning_rate": 1e-06,
      "loss": 0.0141,
      "step": 722
    },
    {
      "clip_ratio/high_max": 0.002081649723550072,
      "clip_ratio/high_mean": 0.0009708205252536573,
      "clip_ratio/low_mean": 0.0013232474211690715,
      "clip_ratio/low_min": 0.00024585640676377807,
      "clip_ratio/region_mean": 0.0022940679627936333,
      "epoch": 0.06747983130042175,
      "grad_norm": 0.10556382685899734,
      "learning_rate": 1e-06,
      "loss": 0.0628,
      "step": 723
    },
    {
      "clip_ratio/high_max": 0.002365284766710829,
      "clip_ratio/high_mean": 0.001005058957161964,
      "clip_ratio/low_mean": 0.0014573321132047568,
      "clip_ratio/low_min": 0.0002775772572931601,
      "clip_ratio/region_mean": 0.002462391057633795,
      "epoch": 0.06757316440042234,
      "grad_norm": 0.11068706959486008,
      "learning_rate": 1e-06,
      "loss": 0.0409,
      "step": 724
    },
    {
      "clip_ratio/high_max": 0.0025041052504093386,
      "clip_ratio/high_mean": 0.0011567464152903995,
      "clip_ratio/low_mean": 0.00125418507559516,
      "clip_ratio/low_min": 0.00010440914866194362,
      "clip_ratio/region_mean": 0.00241093151998939,
      "epoch": 0.06766649750042292,
      "grad_norm": 0.1133076548576355,
      "learning_rate": 1e-06,
      "loss": 0.0088,
      "step": 725
    },
    {
      "clip_ratio/high_max": 0.00271190805506194,
      "clip_ratio/high_mean": 0.0011754864372051088,
      "clip_ratio/low_mean": 0.0014167626213748008,
      "clip_ratio/low_min": 0.0001713991878204979,
      "clip_ratio/region_mean": 0.002592249002191238,
      "epoch": 0.0677598306004235,
      "grad_norm": 0.11904425173997879,
      "learning_rate": 1e-06,
      "loss": 0.0058,
      "step": 726
    },
    {
      "clip_ratio/high_max": 0.0030013936921022832,
      "clip_ratio/high_mean": 0.00122209042092436,
      "clip_ratio/low_mean": 0.0013235732239991194,
      "clip_ratio/low_min": 0.00020283639059925918,
      "clip_ratio/region_mean": 0.0025456636358285323,
      "epoch": 0.06785316370042409,
      "grad_norm": 0.12318696826696396,
      "learning_rate": 1e-06,
      "loss": 0.0225,
      "step": 727
    },
    {
      "clip_ratio/high_max": 0.0024411594931734726,
      "clip_ratio/high_mean": 0.001115340750402538,
      "clip_ratio/low_mean": 0.001319159367994871,
      "clip_ratio/low_min": 0.00010093897981278133,
      "clip_ratio/region_mean": 0.0024345001074834727,
      "epoch": 0.06794649680042467,
      "grad_norm": 0.12597160041332245,
      "learning_rate": 1e-06,
      "loss": 0.0019,
      "step": 728
    },
    {
      "clip_ratio/high_max": 0.0026826402463484555,
      "clip_ratio/high_mean": 0.0011313702489132993,
      "clip_ratio/low_mean": 0.0013665519873029552,
      "clip_ratio/low_min": 0.00012475447510951199,
      "clip_ratio/region_mean": 0.0024979221852845512,
      "epoch": 0.06803982990042524,
      "grad_norm": 0.10503245145082474,
      "learning_rate": 1e-06,
      "loss": 0.0321,
      "step": 729
    },
    {
      "clip_ratio/high_max": 0.002960867976071313,
      "clip_ratio/high_mean": 0.0012720336235361174,
      "clip_ratio/low_mean": 0.0013114199246047065,
      "clip_ratio/low_min": 0.00011685091521940194,
      "clip_ratio/region_mean": 0.002583453526312951,
      "epoch": 0.06813316300042584,
      "grad_norm": 0.2732866704463959,
      "learning_rate": 1e-06,
      "loss": -0.0046,
      "step": 730
    },
    {
      "clip_ratio/high_max": 0.002719235031690914,
      "clip_ratio/high_mean": 0.001160748168331338,
      "clip_ratio/low_mean": 0.0014644000912085176,
      "clip_ratio/low_min": 0.0001880654162960127,
      "clip_ratio/region_mean": 0.0026251482486259192,
      "epoch": 0.06822649610042641,
      "grad_norm": 0.11016158014535904,
      "learning_rate": 1e-06,
      "loss": 0.0422,
      "step": 731
    },
    {
      "clip_ratio/high_max": 0.0023739947100693826,
      "clip_ratio/high_mean": 0.0010047666419268353,
      "clip_ratio/low_mean": 0.0014650142729806248,
      "clip_ratio/low_min": 0.00016231764584517805,
      "clip_ratio/region_mean": 0.0024697809349163435,
      "epoch": 0.06831982920042699,
      "grad_norm": 0.11983786523342133,
      "learning_rate": 1e-06,
      "loss": 0.0787,
      "step": 732
    },
    {
      "clip_ratio/high_max": 0.00272560837038327,
      "clip_ratio/high_mean": 0.0012138942620367743,
      "clip_ratio/low_mean": 0.0012309012290643295,
      "clip_ratio/low_min": 0.00011816013829957228,
      "clip_ratio/region_mean": 0.0024447954856441356,
      "epoch": 0.06841316230042759,
      "grad_norm": 0.10642242431640625,
      "learning_rate": 1e-06,
      "loss": 0.0253,
      "step": 733
    },
    {
      "clip_ratio/high_max": 0.002649971909704618,
      "clip_ratio/high_mean": 0.001168540577054955,
      "clip_ratio/low_mean": 0.001448224727937486,
      "clip_ratio/low_min": 0.00021643979016516823,
      "clip_ratio/region_mean": 0.002616765268612653,
      "epoch": 0.06850649540042816,
      "grad_norm": 0.11385363340377808,
      "learning_rate": 1e-06,
      "loss": 0.0491,
      "step": 734
    },
    {
      "clip_ratio/high_max": 0.0028327024629106745,
      "clip_ratio/high_mean": 0.0012554569984786212,
      "clip_ratio/low_mean": 0.0013119755385559984,
      "clip_ratio/low_min": 2.8936887247255072e-05,
      "clip_ratio/region_mean": 0.002567432551586535,
      "epoch": 0.06859982850042876,
      "grad_norm": 0.11786264926195145,
      "learning_rate": 1e-06,
      "loss": 0.0242,
      "step": 735
    },
    {
      "clip_ratio/high_max": 0.002444076741085155,
      "clip_ratio/high_mean": 0.0010475339877302758,
      "clip_ratio/low_mean": 0.0013390347667154856,
      "clip_ratio/low_min": 0.00016115663493110333,
      "clip_ratio/region_mean": 0.0023865687689976767,
      "epoch": 0.06869316160042933,
      "grad_norm": 0.11437604576349258,
      "learning_rate": 1e-06,
      "loss": 0.0067,
      "step": 736
    },
    {
      "clip_ratio/high_max": 0.0025760113931028172,
      "clip_ratio/high_mean": 0.0010824208584381267,
      "clip_ratio/low_mean": 0.001232916072694934,
      "clip_ratio/low_min": 4.539676956483163e-05,
      "clip_ratio/region_mean": 0.00231533693295205,
      "epoch": 0.06878649470042991,
      "grad_norm": 0.10543030500411987,
      "learning_rate": 1e-06,
      "loss": 0.0358,
      "step": 737
    },
    {
      "clip_ratio/high_max": 0.002850871860573534,
      "clip_ratio/high_mean": 0.0010817082293215208,
      "clip_ratio/low_mean": 0.0012590585465659387,
      "clip_ratio/low_min": 0.00010499057316337712,
      "clip_ratio/region_mean": 0.0023407667904393747,
      "epoch": 0.0688798278004305,
      "grad_norm": 0.11870167404413223,
      "learning_rate": 1e-06,
      "loss": 0.0418,
      "step": 738
    },
    {
      "clip_ratio/high_max": 0.00297409145423444,
      "clip_ratio/high_mean": 0.0013074675953248516,
      "clip_ratio/low_mean": 0.0012806278282369021,
      "clip_ratio/low_min": 0.0002119890214089537,
      "clip_ratio/region_mean": 0.0025880953908199444,
      "epoch": 0.06897316090043108,
      "grad_norm": 0.13427087664604187,
      "learning_rate": 1e-06,
      "loss": -0.0024,
      "step": 739
    },
    {
      "clip_ratio/high_max": 0.0025721776619320735,
      "clip_ratio/high_mean": 0.0012095088732166914,
      "clip_ratio/low_mean": 0.0012556532874441473,
      "clip_ratio/low_min": 0.000200507942281547,
      "clip_ratio/region_mean": 0.002465162193402648,
      "epoch": 0.06906649400043166,
      "grad_norm": 0.11577577143907547,
      "learning_rate": 1e-06,
      "loss": -0.0034,
      "step": 740
    },
    {
      "clip_ratio/high_max": 0.002934826072305441,
      "clip_ratio/high_mean": 0.0012419092599884607,
      "clip_ratio/low_mean": 0.0012650964144995669,
      "clip_ratio/low_min": 0.0001582368367962772,
      "clip_ratio/region_mean": 0.0025070056872209534,
      "epoch": 0.06915982710043225,
      "grad_norm": 0.1072765663266182,
      "learning_rate": 1e-06,
      "loss": 0.0219,
      "step": 741
    },
    {
      "clip_ratio/high_max": 0.0024932229352998547,
      "clip_ratio/high_mean": 0.0009867256394500146,
      "clip_ratio/low_mean": 0.0011244362340221414,
      "clip_ratio/low_min": 0.00014509032644127728,
      "clip_ratio/region_mean": 0.0021111618989380077,
      "epoch": 0.06925316020043283,
      "grad_norm": 0.09720559418201447,
      "learning_rate": 1e-06,
      "loss": 0.0583,
      "step": 742
    },
    {
      "clip_ratio/high_max": 0.0031298769026761875,
      "clip_ratio/high_mean": 0.001249256940354826,
      "clip_ratio/low_mean": 0.0013765303701802623,
      "clip_ratio/low_min": 8.651172993268119e-05,
      "clip_ratio/region_mean": 0.0026257873250870034,
      "epoch": 0.06934649330043341,
      "grad_norm": 0.12963922321796417,
      "learning_rate": 1e-06,
      "loss": 0.019,
      "step": 743
    },
    {
      "clip_ratio/high_max": 0.0030056244577281177,
      "clip_ratio/high_mean": 0.0012920232547912747,
      "clip_ratio/low_mean": 0.0013579841397586279,
      "clip_ratio/low_min": 0.00018727317637967644,
      "clip_ratio/region_mean": 0.002650007460033521,
      "epoch": 0.069439826400434,
      "grad_norm": 0.1084214374423027,
      "learning_rate": 1e-06,
      "loss": 0.0018,
      "step": 744
    },
    {
      "clip_ratio/high_max": 0.0022582934543606825,
      "clip_ratio/high_mean": 0.0010689882383303484,
      "clip_ratio/low_mean": 0.0014702399348607287,
      "clip_ratio/low_min": 0.00028344635938992724,
      "clip_ratio/region_mean": 0.002539228131354321,
      "epoch": 0.06953315950043458,
      "grad_norm": 0.11832050234079361,
      "learning_rate": 1e-06,
      "loss": 0.0976,
      "step": 745
    },
    {
      "clip_ratio/high_max": 0.002255209503346123,
      "clip_ratio/high_mean": 0.0010784399892145302,
      "clip_ratio/low_mean": 0.0010898211221501697,
      "clip_ratio/low_min": 3.723439294844866e-05,
      "clip_ratio/region_mean": 0.002168261067708954,
      "epoch": 0.06962649260043517,
      "grad_norm": 0.1100601777434349,
      "learning_rate": 1e-06,
      "loss": 0.0595,
      "step": 746
    },
    {
      "clip_ratio/high_max": 0.0026475909544387832,
      "clip_ratio/high_mean": 0.0011875226664415095,
      "clip_ratio/low_mean": 0.0014723654276167508,
      "clip_ratio/low_min": 0.0002479485392541392,
      "clip_ratio/region_mean": 0.0026598880504025146,
      "epoch": 0.06971982570043575,
      "grad_norm": 0.10789845883846283,
      "learning_rate": 1e-06,
      "loss": 0.0307,
      "step": 747
    },
    {
      "clip_ratio/high_max": 0.003017264862137381,
      "clip_ratio/high_mean": 0.0013137899659341201,
      "clip_ratio/low_mean": 0.0014057157313800417,
      "clip_ratio/low_min": 0.00024162018235074356,
      "clip_ratio/region_mean": 0.00271950573369395,
      "epoch": 0.06981315880043633,
      "grad_norm": 0.11357614398002625,
      "learning_rate": 1e-06,
      "loss": -0.0033,
      "step": 748
    },
    {
      "clip_ratio/high_max": 0.0025546381875756197,
      "clip_ratio/high_mean": 0.0011461432222859003,
      "clip_ratio/low_mean": 0.0015304677654057741,
      "clip_ratio/low_min": 0.0003436168626649305,
      "clip_ratio/region_mean": 0.0026766110095195472,
      "epoch": 0.06990649190043692,
      "grad_norm": 0.10405183583498001,
      "learning_rate": 1e-06,
      "loss": 0.0235,
      "step": 749
    },
    {
      "clip_ratio/high_max": 0.003007886822160799,
      "clip_ratio/high_mean": 0.0012398003673297353,
      "clip_ratio/low_mean": 0.0011930224791285582,
      "clip_ratio/low_min": 0.00013628236047225073,
      "clip_ratio/region_mean": 0.002432822839182336,
      "epoch": 0.0699998250004375,
      "grad_norm": 0.10911568999290466,
      "learning_rate": 1e-06,
      "loss": 0.0061,
      "step": 750
    },
    {
      "clip_ratio/high_max": 0.0030501093424391,
      "clip_ratio/high_mean": 0.0013584345470007975,
      "clip_ratio/low_mean": 0.0012423960179148708,
      "clip_ratio/low_min": 4.5048564970784355e-05,
      "clip_ratio/region_mean": 0.0026008305358118378,
      "epoch": 0.07009315810043808,
      "grad_norm": 0.1271698772907257,
      "learning_rate": 1e-06,
      "loss": 0.0146,
      "step": 751
    },
    {
      "clip_ratio/high_max": 0.003073713342018891,
      "clip_ratio/high_mean": 0.0012448882771423087,
      "clip_ratio/low_mean": 0.0012325837269600015,
      "clip_ratio/low_min": 7.209786963358056e-05,
      "clip_ratio/region_mean": 0.0024774719204287976,
      "epoch": 0.07018649120043867,
      "grad_norm": 0.11275521665811539,
      "learning_rate": 1e-06,
      "loss": -0.0127,
      "step": 752
    },
    {
      "clip_ratio/high_max": 0.002723751800658647,
      "clip_ratio/high_mean": 0.0011510503572935704,
      "clip_ratio/low_mean": 0.0012933056059409864,
      "clip_ratio/low_min": 0.00015398129653476644,
      "clip_ratio/region_mean": 0.002444355937768705,
      "epoch": 0.07027982430043925,
      "grad_norm": 0.11377551406621933,
      "learning_rate": 1e-06,
      "loss": 0.0368,
      "step": 753
    },
    {
      "clip_ratio/high_max": 0.002962904422020074,
      "clip_ratio/high_mean": 0.0013752389058936387,
      "clip_ratio/low_mean": 0.0012707047862932086,
      "clip_ratio/low_min": 5.269622943160357e-05,
      "clip_ratio/region_mean": 0.0026459436703589745,
      "epoch": 0.07037315740043983,
      "grad_norm": 0.1154618039727211,
      "learning_rate": 1e-06,
      "loss": 0.0017,
      "step": 754
    },
    {
      "clip_ratio/high_max": 0.0028729629411827773,
      "clip_ratio/high_mean": 0.0010724228050094098,
      "clip_ratio/low_mean": 0.0013544600406021345,
      "clip_ratio/low_min": 0.00017528566422697622,
      "clip_ratio/region_mean": 0.0024268827692139894,
      "epoch": 0.07046649050044042,
      "grad_norm": 0.13094009459018707,
      "learning_rate": 1e-06,
      "loss": 0.0437,
      "step": 755
    },
    {
      "clip_ratio/high_max": 0.00311863864044426,
      "clip_ratio/high_mean": 0.0012684028824878624,
      "clip_ratio/low_mean": 0.0012262765280866006,
      "clip_ratio/low_min": 0.0001873908331617713,
      "clip_ratio/region_mean": 0.0024946794073912315,
      "epoch": 0.070559823600441,
      "grad_norm": 0.1197633147239685,
      "learning_rate": 1e-06,
      "loss": 0.0287,
      "step": 756
    },
    {
      "clip_ratio/high_max": 0.002939700265415013,
      "clip_ratio/high_mean": 0.0012404045919538476,
      "clip_ratio/low_mean": 0.0013211458826845046,
      "clip_ratio/low_min": 1.6464699001517147e-05,
      "clip_ratio/region_mean": 0.0025615505219320767,
      "epoch": 0.07065315670044159,
      "grad_norm": 0.11195140331983566,
      "learning_rate": 1e-06,
      "loss": -0.0134,
      "step": 757
    },
    {
      "clip_ratio/high_max": 0.002776704881398473,
      "clip_ratio/high_mean": 0.0011888511617144104,
      "clip_ratio/low_mean": 0.0014347892101795878,
      "clip_ratio/low_min": 0.00023000847249932121,
      "clip_ratio/region_mean": 0.002623640415549744,
      "epoch": 0.07074648980044217,
      "grad_norm": 0.11405761539936066,
      "learning_rate": 1e-06,
      "loss": 0.0614,
      "step": 758
    },
    {
      "clip_ratio/high_max": 0.002627781381306704,
      "clip_ratio/high_mean": 0.0012184412153146695,
      "clip_ratio/low_mean": 0.0012199986958876252,
      "clip_ratio/low_min": 0.00015227431140374392,
      "clip_ratio/region_mean": 0.002438439922116231,
      "epoch": 0.07083982290044274,
      "grad_norm": 0.11139947175979614,
      "learning_rate": 1e-06,
      "loss": 0.0033,
      "step": 759
    },
    {
      "clip_ratio/high_max": 0.002774520566163119,
      "clip_ratio/high_mean": 0.001122625675634481,
      "clip_ratio/low_mean": 0.0014449931913986802,
      "clip_ratio/low_min": 0.00021774545439257054,
      "clip_ratio/region_mean": 0.0025676188088255003,
      "epoch": 0.07093315600044334,
      "grad_norm": 0.1145111620426178,
      "learning_rate": 1e-06,
      "loss": 0.0457,
      "step": 760
    },
    {
      "clip_ratio/high_max": 0.0027189368920517154,
      "clip_ratio/high_mean": 0.0011743571376428008,
      "clip_ratio/low_mean": 0.0014953151876397897,
      "clip_ratio/low_min": 0.00026165100007347064,
      "clip_ratio/region_mean": 0.0026696724526118487,
      "epoch": 0.07102648910044392,
      "grad_norm": 0.10632248222827911,
      "learning_rate": 1e-06,
      "loss": 0.0162,
      "step": 761
    },
    {
      "clip_ratio/high_max": 0.002787663324852474,
      "clip_ratio/high_mean": 0.0011830617731902748,
      "clip_ratio/low_mean": 0.0015124076016945764,
      "clip_ratio/low_min": 5.873068676010007e-05,
      "clip_ratio/region_mean": 0.0026954693530569784,
      "epoch": 0.0711198222004445,
      "grad_norm": 0.1719726324081421,
      "learning_rate": 1e-06,
      "loss": 0.0374,
      "step": 762
    },
    {
      "clip_ratio/high_max": 0.003003754078235943,
      "clip_ratio/high_mean": 0.0012541587675514165,
      "clip_ratio/low_mean": 0.0013991387786518317,
      "clip_ratio/low_min": 7.044962512736674e-05,
      "clip_ratio/region_mean": 0.0026532975170994177,
      "epoch": 0.07121315530044509,
      "grad_norm": 0.11904733628034592,
      "learning_rate": 1e-06,
      "loss": 0.0186,
      "step": 763
    },
    {
      "clip_ratio/high_max": 0.0033765009065973572,
      "clip_ratio/high_mean": 0.001281166980334092,
      "clip_ratio/low_mean": 0.0015819539039512165,
      "clip_ratio/low_min": 0.00016568659793847473,
      "clip_ratio/region_mean": 0.0028631208988372236,
      "epoch": 0.07130648840044566,
      "grad_norm": 0.11197473853826523,
      "learning_rate": 1e-06,
      "loss": 0.0364,
      "step": 764
    },
    {
      "clip_ratio/high_max": 0.002852642923244275,
      "clip_ratio/high_mean": 0.0011721480223059189,
      "clip_ratio/low_mean": 0.0013013201169087552,
      "clip_ratio/low_min": 6.967284753045533e-05,
      "clip_ratio/region_mean": 0.002473468099196907,
      "epoch": 0.07139982150044624,
      "grad_norm": 0.11385203897953033,
      "learning_rate": 1e-06,
      "loss": -0.0272,
      "step": 765
    },
    {
      "clip_ratio/high_max": 0.002533957340347115,
      "clip_ratio/high_mean": 0.0011181412955920678,
      "clip_ratio/low_mean": 0.0014496797302854247,
      "clip_ratio/low_min": 0.00020601628239091951,
      "clip_ratio/region_mean": 0.0025678210076875985,
      "epoch": 0.07149315460044683,
      "grad_norm": 0.10289259999990463,
      "learning_rate": 1e-06,
      "loss": 0.0521,
      "step": 766
    },
    {
      "clip_ratio/high_max": 0.0025922762506525032,
      "clip_ratio/high_mean": 0.0010080376850964967,
      "clip_ratio/low_mean": 0.001377177017275244,
      "clip_ratio/low_min": 0.00015607318982802099,
      "clip_ratio/region_mean": 0.002385214676905889,
      "epoch": 0.07158648770044741,
      "grad_norm": 0.11131215840578079,
      "learning_rate": 1e-06,
      "loss": 0.0201,
      "step": 767
    },
    {
      "clip_ratio/high_max": 0.002780564631393645,
      "clip_ratio/high_mean": 0.001201951326947892,
      "clip_ratio/low_mean": 0.0011877912329509854,
      "clip_ratio/low_min": 5.9996538766426966e-05,
      "clip_ratio/region_mean": 0.0023897426362964325,
      "epoch": 0.071679820800448,
      "grad_norm": 0.10477583855390549,
      "learning_rate": 1e-06,
      "loss": 0.0101,
      "step": 768
    },
    {
      "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": 0.011204310825892905,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4094.0,
      "completions/mean_length": 603.15576171875,
      "completions/mean_terminated_length": 563.577392578125,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.07177315390044858,
      "grad_norm": 0.12820403277873993,
      "learning_rate": 1e-06,
      "loss": 0.0217,
      "num_tokens": 566593954.0,
      "reward": 0.597115695476532,
      "reward_std": 0.18933433294296265,
      "rewards/simpleverify_reward/mean": 0.5971156358718872,
      "rewards/simpleverify_reward/std": 0.4904799163341522,
      "step": 769
    },
    {
      "clip_ratio/high_max": 0.002051092989859171,
      "clip_ratio/high_mean": 0.0009391540825163247,
      "clip_ratio/low_mean": 0.0005050464451414882,
      "clip_ratio/low_min": 1.314405926677864e-05,
      "clip_ratio/region_mean": 0.0014442005449382123,
      "epoch": 0.07186648700044916,
      "grad_norm": 0.12566576898097992,
      "learning_rate": 1e-06,
      "loss": -0.0002,
      "step": 770
    },
    {
      "clip_ratio/high_max": 0.0017706296130199917,
      "clip_ratio/high_mean": 0.00081976316505461,
      "clip_ratio/low_mean": 0.0007088625784490432,
      "clip_ratio/low_min": 5.78703666178626e-05,
      "clip_ratio/region_mean": 0.0015286257330444641,
      "epoch": 0.07195982010044975,
      "grad_norm": 0.11572977900505066,
      "learning_rate": 1e-06,
      "loss": 0.0479,
      "step": 771
    },
    {
      "clip_ratio/high_max": 0.002138843272405211,
      "clip_ratio/high_mean": 0.0008725789120944683,
      "clip_ratio/low_mean": 0.0007034297286736546,
      "clip_ratio/low_min": 1.4172335795592517e-05,
      "clip_ratio/region_mean": 0.0015760086243972182,
      "epoch": 0.07205315320045033,
      "grad_norm": 0.11675462871789932,
      "learning_rate": 1e-06,
      "loss": 0.0509,
      "step": 772
    },
    {
      "clip_ratio/high_max": 0.0020723529378301464,
      "clip_ratio/high_mean": 0.0008848889883665834,
      "clip_ratio/low_mean": 0.0007510084979003295,
      "clip_ratio/low_min": 3.8654676245641895e-05,
      "clip_ratio/region_mean": 0.001635897482628934,
      "epoch": 0.07214648630045091,
      "grad_norm": 0.11294642090797424,
      "learning_rate": 1e-06,
      "loss": 0.0277,
      "step": 773
    },
    {
      "clip_ratio/high_max": 0.002080842066789046,
      "clip_ratio/high_mean": 0.000885394414581242,
      "clip_ratio/low_mean": 0.0006023007954354398,
      "clip_ratio/low_min": 2.299259267601883e-05,
      "clip_ratio/region_mean": 0.0014876952482154593,
      "epoch": 0.0722398194004515,
      "grad_norm": 0.09766869992017746,
      "learning_rate": 1e-06,
      "loss": -0.0242,
      "step": 774
    },
    {
      "clip_ratio/high_max": 0.0022430263343267143,
      "clip_ratio/high_mean": 0.0008442738326266408,
      "clip_ratio/low_mean": 0.0007915704281913349,
      "clip_ratio/low_min": 4.910353345621843e-05,
      "clip_ratio/region_mean": 0.0016358441862394102,
      "epoch": 0.07233315250045208,
      "grad_norm": 0.12099959701299667,
      "learning_rate": 1e-06,
      "loss": 0.0325,
      "step": 775
    },
    {
      "clip_ratio/high_max": 0.0021076721350254957,
      "clip_ratio/high_mean": 0.0008769266496528871,
      "clip_ratio/low_mean": 0.0008853892832121346,
      "clip_ratio/low_min": 7.717847256571986e-05,
      "clip_ratio/region_mean": 0.0017623159365030006,
      "epoch": 0.07242648560045266,
      "grad_norm": 0.11272159218788147,
      "learning_rate": 1e-06,
      "loss": 0.016,
      "step": 776
    },
    {
      "clip_ratio/high_max": 0.0020168940354778897,
      "clip_ratio/high_mean": 0.0008096988167380914,
      "clip_ratio/low_mean": 0.0007753350128041347,
      "clip_ratio/low_min": 5.0387608098390047e-05,
      "clip_ratio/region_mean": 0.0015850338349991944,
      "epoch": 0.07251981870045325,
      "grad_norm": 0.1247406154870987,
      "learning_rate": 1e-06,
      "loss": 0.0627,
      "step": 777
    },
    {
      "clip_ratio/high_max": 0.002209799386037048,
      "clip_ratio/high_mean": 0.0009233534183294978,
      "clip_ratio/low_mean": 0.0009001679973152932,
      "clip_ratio/low_min": 4.590253774949815e-05,
      "clip_ratio/region_mean": 0.0018235213719890453,
      "epoch": 0.07261315180045383,
      "grad_norm": 0.11831159144639969,
      "learning_rate": 1e-06,
      "loss": 0.0242,
      "step": 778
    },
    {
      "clip_ratio/high_max": 0.0025225516292266548,
      "clip_ratio/high_mean": 0.0011233956065552775,
      "clip_ratio/low_mean": 0.0006616796999878716,
      "clip_ratio/low_min": 1.2649261407204904e-05,
      "clip_ratio/region_mean": 0.0017850752919912338,
      "epoch": 0.07270648490045442,
      "grad_norm": 0.11290524899959564,
      "learning_rate": 1e-06,
      "loss": -0.0551,
      "step": 779
    },
    {
      "clip_ratio/high_max": 0.0025450853863731027,
      "clip_ratio/high_mean": 0.0009829581504163798,
      "clip_ratio/low_mean": 0.0008543614640075248,
      "clip_ratio/low_min": 3.2444766475236975e-05,
      "clip_ratio/region_mean": 0.0018373196216998622,
      "epoch": 0.072799818000455,
      "grad_norm": 0.10938029736280441,
      "learning_rate": 1e-06,
      "loss": 0.0388,
      "step": 780
    },
    {
      "clip_ratio/high_max": 0.002183779033657629,
      "clip_ratio/high_mean": 0.0008654488938191207,
      "clip_ratio/low_mean": 0.000757923505261715,
      "clip_ratio/low_min": 5.14010462211445e-05,
      "clip_ratio/region_mean": 0.0016233724090852775,
      "epoch": 0.07289315110045558,
      "grad_norm": 0.12256066501140594,
      "learning_rate": 1e-06,
      "loss": 0.0489,
      "step": 781
    },
    {
      "clip_ratio/high_max": 0.002266704206704162,
      "clip_ratio/high_mean": 0.0010063832487503532,
      "clip_ratio/low_mean": 0.0008115047530736774,
      "clip_ratio/low_min": 2.5297049432992935e-05,
      "clip_ratio/region_mean": 0.001817888012737967,
      "epoch": 0.07298648420045617,
      "grad_norm": 0.11712535470724106,
      "learning_rate": 1e-06,
      "loss": -0.0269,
      "step": 782
    },
    {
      "clip_ratio/high_max": 0.0021909744609729387,
      "clip_ratio/high_mean": 0.0009347949526272714,
      "clip_ratio/low_mean": 0.0008700080306880409,
      "clip_ratio/low_min": 9.440225949219894e-05,
      "clip_ratio/region_mean": 0.001804803017876111,
      "epoch": 0.07307981730045675,
      "grad_norm": 0.11367373168468475,
      "learning_rate": 1e-06,
      "loss": -0.0085,
      "step": 783
    },
    {
      "clip_ratio/high_max": 0.0021500897128134966,
      "clip_ratio/high_mean": 0.0010276847569912206,
      "clip_ratio/low_mean": 0.0010036926905740984,
      "clip_ratio/low_min": 2.5253820240322966e-05,
      "clip_ratio/region_mean": 0.002031377429375425,
      "epoch": 0.07317315040045733,
      "grad_norm": 0.13200776278972626,
      "learning_rate": 1e-06,
      "loss": 0.0439,
      "step": 784
    },
    {
      "clip_ratio/high_max": 0.0023409711284330115,
      "clip_ratio/high_mean": 0.0008731545967748389,
      "clip_ratio/low_mean": 0.0009059252279257635,
      "clip_ratio/low_min": 8.034350230445853e-05,
      "clip_ratio/region_mean": 0.0017790797865018249,
      "epoch": 0.07326648350045792,
      "grad_norm": 0.11846556514501572,
      "learning_rate": 1e-06,
      "loss": 0.0278,
      "step": 785
    },
    {
      "clip_ratio/high_max": 0.0026085656136274338,
      "clip_ratio/high_mean": 0.0010803904078784399,
      "clip_ratio/low_mean": 0.0010722352089942433,
      "clip_ratio/low_min": 0.00010050079072243534,
      "clip_ratio/region_mean": 0.0021526256314245984,
      "epoch": 0.0733598166004585,
      "grad_norm": 0.12004795670509338,
      "learning_rate": 1e-06,
      "loss": -0.0085,
      "step": 786
    },
    {
      "clip_ratio/high_max": 0.002253969170851633,
      "clip_ratio/high_mean": 0.0009531120922474656,
      "clip_ratio/low_mean": 0.0011178096883668331,
      "clip_ratio/low_min": 0.00016803065591375344,
      "clip_ratio/region_mean": 0.002070921786071267,
      "epoch": 0.07345314970045909,
      "grad_norm": 0.12405817210674286,
      "learning_rate": 1e-06,
      "loss": 0.0162,
      "step": 787
    },
    {
      "clip_ratio/high_max": 0.0019295849560876377,
      "clip_ratio/high_mean": 0.00087690779400873,
      "clip_ratio/low_mean": 0.0011875842574227136,
      "clip_ratio/low_min": 8.876276933733607e-05,
      "clip_ratio/region_mean": 0.0020644920659833588,
      "epoch": 0.07354648280045967,
      "grad_norm": 0.12075860053300858,
      "learning_rate": 1e-06,
      "loss": 0.03,
      "step": 788
    },
    {
      "clip_ratio/high_max": 0.0025981288636103272,
      "clip_ratio/high_mean": 0.0009626758183003403,
      "clip_ratio/low_mean": 0.0009141045484284405,
      "clip_ratio/low_min": 4.4804218305216637e-05,
      "clip_ratio/region_mean": 0.0018767803339869715,
      "epoch": 0.07363981590046025,
      "grad_norm": 0.11440103501081467,
      "learning_rate": 1e-06,
      "loss": 0.0225,
      "step": 789
    },
    {
      "clip_ratio/high_max": 0.002327212929230882,
      "clip_ratio/high_mean": 0.000994183979855734,
      "clip_ratio/low_mean": 0.000941378173592966,
      "clip_ratio/low_min": 7.623283181601437e-05,
      "clip_ratio/region_mean": 0.0019355622061993927,
      "epoch": 0.07373314900046084,
      "grad_norm": 0.09917795658111572,
      "learning_rate": 1e-06,
      "loss": 0.0201,
      "step": 790
    },
    {
      "clip_ratio/high_max": 0.0023168384868768044,
      "clip_ratio/high_mean": 0.0008904602800612338,
      "clip_ratio/low_mean": 0.0010573219024081482,
      "clip_ratio/low_min": 0.00013963030414743116,
      "clip_ratio/region_mean": 0.0019477821624604985,
      "epoch": 0.07382648210046142,
      "grad_norm": 0.10493776202201843,
      "learning_rate": 1e-06,
      "loss": 0.0476,
      "step": 791
    },
    {
      "clip_ratio/high_max": 0.0022290104898274876,
      "clip_ratio/high_mean": 0.0009588014254404698,
      "clip_ratio/low_mean": 0.001075389522156911,
      "clip_ratio/low_min": 7.14579364284873e-05,
      "clip_ratio/region_mean": 0.0020341909112175927,
      "epoch": 0.073919815200462,
      "grad_norm": 0.12100069224834442,
      "learning_rate": 1e-06,
      "loss": 0.026,
      "step": 792
    },
    {
      "clip_ratio/high_max": 0.002559536565968301,
      "clip_ratio/high_mean": 0.001010480151308002,
      "clip_ratio/low_mean": 0.0011545784673216986,
      "clip_ratio/low_min": 0.00010771318920888007,
      "clip_ratio/region_mean": 0.002165058584068902,
      "epoch": 0.07401314830046259,
      "grad_norm": 0.12782274186611176,
      "learning_rate": 1e-06,
      "loss": 0.0221,
      "step": 793
    },
    {
      "clip_ratio/high_max": 0.0025937915925169364,
      "clip_ratio/high_mean": 0.001009241557767382,
      "clip_ratio/low_mean": 0.001053117917763302,
      "clip_ratio/low_min": 4.2666571971494704e-05,
      "clip_ratio/region_mean": 0.0020623594100470655,
      "epoch": 0.07410648140046316,
      "grad_norm": 0.11918506771326065,
      "learning_rate": 1e-06,
      "loss": 0.0338,
      "step": 794
    },
    {
      "clip_ratio/high_max": 0.0023571307319798507,
      "clip_ratio/high_mean": 0.0009932012726494577,
      "clip_ratio/low_mean": 0.0010559585298324237,
      "clip_ratio/low_min": 0.00020315511392254848,
      "clip_ratio/region_mean": 0.0020491597679210827,
      "epoch": 0.07419981450046374,
      "grad_norm": 0.11347195506095886,
      "learning_rate": 1e-06,
      "loss": -0.0092,
      "step": 795
    },
    {
      "clip_ratio/high_max": 0.0025715811243571807,
      "clip_ratio/high_mean": 0.0009562175309838494,
      "clip_ratio/low_mean": 0.001068593968739151,
      "clip_ratio/low_min": 0.00011595513751672115,
      "clip_ratio/region_mean": 0.0020248114597052336,
      "epoch": 0.07429314760046433,
      "grad_norm": 0.10754869878292084,
      "learning_rate": 1e-06,
      "loss": 0.0308,
      "step": 796
    },
    {
      "clip_ratio/high_max": 0.0024075661385722924,
      "clip_ratio/high_mean": 0.0010922811015916523,
      "clip_ratio/low_mean": 0.0011443973144196207,
      "clip_ratio/low_min": 0.00011810382693511201,
      "clip_ratio/region_mean": 0.0022366784323821776,
      "epoch": 0.07438648070046491,
      "grad_norm": 0.11134686321020126,
      "learning_rate": 1e-06,
      "loss": -0.0014,
      "step": 797
    },
    {
      "clip_ratio/high_max": 0.0018771039358398411,
      "clip_ratio/high_mean": 0.0008169102638930781,
      "clip_ratio/low_mean": 0.0009692325202195207,
      "clip_ratio/low_min": 2.715423579502385e-05,
      "clip_ratio/region_mean": 0.0017861428023024928,
      "epoch": 0.0744798138004655,
      "grad_norm": 0.1033652126789093,
      "learning_rate": 1e-06,
      "loss": 0.0151,
      "step": 798
    },
    {
      "clip_ratio/high_max": 0.002284582624270115,
      "clip_ratio/high_mean": 0.0009443743456358789,
      "clip_ratio/low_mean": 0.0011741655907826498,
      "clip_ratio/low_min": 0.00012079526277375408,
      "clip_ratio/region_mean": 0.0021185399091336876,
      "epoch": 0.07457314690046608,
      "grad_norm": 0.11647457629442215,
      "learning_rate": 1e-06,
      "loss": 0.0343,
      "step": 799
    },
    {
      "clip_ratio/high_max": 0.002678997792827431,
      "clip_ratio/high_mean": 0.0010899615590460598,
      "clip_ratio/low_mean": 0.0011122225332655944,
      "clip_ratio/low_min": 0.00017038251644407865,
      "clip_ratio/region_mean": 0.002202184099587612,
      "epoch": 0.07466648000046666,
      "grad_norm": 0.12350889295339584,
      "learning_rate": 1e-06,
      "loss": 0.0484,
      "step": 800
    },
    {
      "clip_ratio/high_max": 0.002412290203210432,
      "clip_ratio/high_mean": 0.0010598797707643826,
      "clip_ratio/low_mean": 0.0009714974657981656,
      "clip_ratio/low_min": 5.190667070564814e-05,
      "clip_ratio/region_mean": 0.0020313772329245694,
      "epoch": 0.07475981310046725,
      "grad_norm": 0.11538942158222198,
      "learning_rate": 1e-06,
      "loss": 0.0348,
      "step": 801
    },
    {
      "clip_ratio/high_max": 0.002418118150671944,
      "clip_ratio/high_mean": 0.0010661182641342748,
      "clip_ratio/low_mean": 0.0009209596519212937,
      "clip_ratio/low_min": 8.859075023792684e-05,
      "clip_ratio/region_mean": 0.001987077877856791,
      "epoch": 0.07485314620046783,
      "grad_norm": 0.10948257148265839,
      "learning_rate": 1e-06,
      "loss": 0.0077,
      "step": 802
    },
    {
      "clip_ratio/high_max": 0.0023883522299001925,
      "clip_ratio/high_mean": 0.0010372653468948556,
      "clip_ratio/low_mean": 0.0009967588193831034,
      "clip_ratio/low_min": 4.212394560454413e-05,
      "clip_ratio/region_mean": 0.002034024197200779,
      "epoch": 0.07494647930046841,
      "grad_norm": 0.10789617151021957,
      "learning_rate": 1e-06,
      "loss": 0.0096,
      "step": 803
    },
    {
      "clip_ratio/high_max": 0.002301316511875484,
      "clip_ratio/high_mean": 0.0009994779984481283,
      "clip_ratio/low_mean": 0.0010736448102761642,
      "clip_ratio/low_min": 0.00016360287372663151,
      "clip_ratio/region_mean": 0.0020731228087242926,
      "epoch": 0.075039812400469,
      "grad_norm": 0.11090195178985596,
      "learning_rate": 1e-06,
      "loss": 0.016,
      "step": 804
    },
    {
      "clip_ratio/high_max": 0.002645769083756022,
      "clip_ratio/high_mean": 0.001123054989875527,
      "clip_ratio/low_mean": 0.0011681924370350316,
      "clip_ratio/low_min": 7.465640555892605e-05,
      "clip_ratio/region_mean": 0.0022912474451004528,
      "epoch": 0.07513314550046958,
      "grad_norm": 0.25976425409317017,
      "learning_rate": 1e-06,
      "loss": 0.0248,
      "step": 805
    },
    {
      "clip_ratio/high_max": 0.002684735634829849,
      "clip_ratio/high_mean": 0.0010951919430226553,
      "clip_ratio/low_mean": 0.0009336313232779503,
      "clip_ratio/low_min": 0.00011956647813349264,
      "clip_ratio/region_mean": 0.00202882331359433,
      "epoch": 0.07522647860047016,
      "grad_norm": 0.11199431121349335,
      "learning_rate": 1e-06,
      "loss": 0.0388,
      "step": 806
    },
    {
      "clip_ratio/high_max": 0.002553266785980668,
      "clip_ratio/high_mean": 0.001117124586016871,
      "clip_ratio/low_mean": 0.001148157760326285,
      "clip_ratio/low_min": 0.00015109952801140025,
      "clip_ratio/region_mean": 0.0022652823172393255,
      "epoch": 0.07531981170047075,
      "grad_norm": 0.1271596997976303,
      "learning_rate": 1e-06,
      "loss": 0.0078,
      "step": 807
    },
    {
      "clip_ratio/high_max": 0.002470468491083011,
      "clip_ratio/high_mean": 0.0009934043700923212,
      "clip_ratio/low_mean": 0.001109728324081516,
      "clip_ratio/low_min": 3.391439986444311e-05,
      "clip_ratio/region_mean": 0.0021031326832599007,
      "epoch": 0.07541314480047133,
      "grad_norm": 0.12198836356401443,
      "learning_rate": 1e-06,
      "loss": 0.0278,
      "step": 808
    },
    {
      "clip_ratio/high_max": 0.002124332979292376,
      "clip_ratio/high_mean": 0.0009733429669722682,
      "clip_ratio/low_mean": 0.0012702129133685958,
      "clip_ratio/low_min": 9.579544712323695e-05,
      "clip_ratio/region_mean": 0.0022435559003497474,
      "epoch": 0.07550647790047192,
      "grad_norm": 0.11199678480625153,
      "learning_rate": 1e-06,
      "loss": 0.0639,
      "step": 809
    },
    {
      "clip_ratio/high_max": 0.0021873594014323317,
      "clip_ratio/high_mean": 0.000937352799155633,
      "clip_ratio/low_mean": 0.0012296169243199984,
      "clip_ratio/low_min": 0.00017922391816682648,
      "clip_ratio/region_mean": 0.0021669697380275466,
      "epoch": 0.0755998110004725,
      "grad_norm": 0.11988547444343567,
      "learning_rate": 1e-06,
      "loss": 0.0347,
      "step": 810
    },
    {
      "clip_ratio/high_max": 0.0026810174676938914,
      "clip_ratio/high_mean": 0.0012048442476952914,
      "clip_ratio/low_mean": 0.001280928925552871,
      "clip_ratio/low_min": 0.0001074354713637149,
      "clip_ratio/region_mean": 0.0024857731550582685,
      "epoch": 0.07569314410047308,
      "grad_norm": 0.1250828206539154,
      "learning_rate": 1e-06,
      "loss": 0.0015,
      "step": 811
    },
    {
      "clip_ratio/high_max": 0.002780757102300413,
      "clip_ratio/high_mean": 0.0011945388760068454,
      "clip_ratio/low_mean": 0.0011200920780538581,
      "clip_ratio/low_min": 6.386037784977816e-05,
      "clip_ratio/region_mean": 0.002314631004992407,
      "epoch": 0.07578647720047367,
      "grad_norm": 0.12443851679563522,
      "learning_rate": 1e-06,
      "loss": 0.0209,
      "step": 812
    },
    {
      "clip_ratio/high_max": 0.002125648872606689,
      "clip_ratio/high_mean": 0.0008933621629694244,
      "clip_ratio/low_mean": 0.0010431468108436093,
      "clip_ratio/low_min": 9.345857870357577e-05,
      "clip_ratio/region_mean": 0.0019365089538041502,
      "epoch": 0.07587981030047425,
      "grad_norm": 0.09821508079767227,
      "learning_rate": 1e-06,
      "loss": 0.0161,
      "step": 813
    },
    {
      "clip_ratio/high_max": 0.0027740029072447214,
      "clip_ratio/high_mean": 0.0010859190260816831,
      "clip_ratio/low_mean": 0.0010761445282696513,
      "clip_ratio/low_min": 9.192534071189584e-05,
      "clip_ratio/region_mean": 0.0021620636034640484,
      "epoch": 0.07597314340047483,
      "grad_norm": 0.11543142795562744,
      "learning_rate": 1e-06,
      "loss": -0.0134,
      "step": 814
    },
    {
      "clip_ratio/high_max": 0.002336179051781073,
      "clip_ratio/high_mean": 0.001012662069115322,
      "clip_ratio/low_mean": 0.0011903145041287644,
      "clip_ratio/low_min": 8.642133798275609e-05,
      "clip_ratio/region_mean": 0.00220297653140733,
      "epoch": 0.07606647650047542,
      "grad_norm": 0.11538077145814896,
      "learning_rate": 1e-06,
      "loss": 0.0063,
      "step": 815
    },
    {
      "clip_ratio/high_max": 0.0026883843675022945,
      "clip_ratio/high_mean": 0.0012067052703059744,
      "clip_ratio/low_mean": 0.0011605535364651587,
      "clip_ratio/low_min": 4.938949132338166e-05,
      "clip_ratio/region_mean": 0.002367258806771133,
      "epoch": 0.076159809600476,
      "grad_norm": 0.11419616639614105,
      "learning_rate": 1e-06,
      "loss": 0.0138,
      "step": 816
    },
    {
      "clip_ratio/high_max": 0.002302663488080725,
      "clip_ratio/high_mean": 0.0009473786285525421,
      "clip_ratio/low_mean": 0.0014439004808082245,
      "clip_ratio/low_min": 0.00021686234958906425,
      "clip_ratio/region_mean": 0.0023912791366456077,
      "epoch": 0.07625314270047658,
      "grad_norm": 0.12642024457454681,
      "learning_rate": 1e-06,
      "loss": 0.0611,
      "step": 817
    },
    {
      "clip_ratio/high_max": 0.0024478775449097157,
      "clip_ratio/high_mean": 0.001012768603686709,
      "clip_ratio/low_mean": 0.001272786124900449,
      "clip_ratio/low_min": 0.00011893514238181524,
      "clip_ratio/region_mean": 0.00228555469220737,
      "epoch": 0.07634647580047717,
      "grad_norm": 0.10971798002719879,
      "learning_rate": 1e-06,
      "loss": 0.0118,
      "step": 818
    },
    {
      "clip_ratio/high_max": 0.0027245371893513948,
      "clip_ratio/high_mean": 0.0011951471715292428,
      "clip_ratio/low_mean": 0.001217750472278567,
      "clip_ratio/low_min": 2.928316462202929e-05,
      "clip_ratio/region_mean": 0.0024128976292558946,
      "epoch": 0.07643980890047775,
      "grad_norm": 0.1201469674706459,
      "learning_rate": 1e-06,
      "loss": 0.0199,
      "step": 819
    },
    {
      "clip_ratio/high_max": 0.0026759453758131713,
      "clip_ratio/high_mean": 0.0010629039206833113,
      "clip_ratio/low_mean": 0.001152547964011319,
      "clip_ratio/low_min": 5.900878204556648e-05,
      "clip_ratio/region_mean": 0.0022154518810566515,
      "epoch": 0.07653314200047834,
      "grad_norm": 0.11807885766029358,
      "learning_rate": 1e-06,
      "loss": 0.0153,
      "step": 820
    },
    {
      "clip_ratio/high_max": 0.0023412224036292173,
      "clip_ratio/high_mean": 0.0010300843787263148,
      "clip_ratio/low_mean": 0.0012751088288496248,
      "clip_ratio/low_min": 0.00012151322516729124,
      "clip_ratio/region_mean": 0.002305193214851897,
      "epoch": 0.07662647510047892,
      "grad_norm": 0.11873375624418259,
      "learning_rate": 1e-06,
      "loss": 0.0401,
      "step": 821
    },
    {
      "clip_ratio/high_max": 0.0021195502267801203,
      "clip_ratio/high_mean": 0.0009045373262779322,
      "clip_ratio/low_mean": 0.0012838650363846682,
      "clip_ratio/low_min": 7.722931695752777e-05,
      "clip_ratio/region_mean": 0.002188402315368876,
      "epoch": 0.0767198082004795,
      "grad_norm": 0.10836665332317352,
      "learning_rate": 1e-06,
      "loss": 0.0599,
      "step": 822
    },
    {
      "clip_ratio/high_max": 0.0021443845907924697,
      "clip_ratio/high_mean": 0.001007751152428682,
      "clip_ratio/low_mean": 0.00144003579771379,
      "clip_ratio/low_min": 0.0002094564324579551,
      "clip_ratio/region_mean": 0.002447786901029758,
      "epoch": 0.07681314130048009,
      "grad_norm": 0.1180749461054802,
      "learning_rate": 1e-06,
      "loss": 0.0289,
      "step": 823
    },
    {
      "clip_ratio/high_max": 0.0025228763770428486,
      "clip_ratio/high_mean": 0.0009985250908357557,
      "clip_ratio/low_mean": 0.0014108365176070947,
      "clip_ratio/low_min": 8.019329834496602e-05,
      "clip_ratio/region_mean": 0.0024093616812024266,
      "epoch": 0.07690647440048066,
      "grad_norm": 0.12274163961410522,
      "learning_rate": 1e-06,
      "loss": 0.0381,
      "step": 824
    },
    {
      "clip_ratio/high_max": 0.002513311876100488,
      "clip_ratio/high_mean": 0.0010567716144578299,
      "clip_ratio/low_mean": 0.001161065109045012,
      "clip_ratio/low_min": 3.436139286350226e-05,
      "clip_ratio/region_mean": 0.0022178367580636404,
      "epoch": 0.07699980750048124,
      "grad_norm": 0.11557767540216446,
      "learning_rate": 1e-06,
      "loss": -0.0128,
      "step": 825
    },
    {
      "clip_ratio/high_max": 0.002527158176235389,
      "clip_ratio/high_mean": 0.0009697247296571732,
      "clip_ratio/low_mean": 0.0013765989970124792,
      "clip_ratio/low_min": 0.00023680822232563514,
      "clip_ratio/region_mean": 0.0023463237084797584,
      "epoch": 0.07709314060048184,
      "grad_norm": 0.11587980389595032,
      "learning_rate": 1e-06,
      "loss": 0.0476,
      "step": 826
    },
    {
      "clip_ratio/high_max": 0.002271386307256762,
      "clip_ratio/high_mean": 0.0009781260323507013,
      "clip_ratio/low_mean": 0.0012646821451198775,
      "clip_ratio/low_min": 0.0001422819250365137,
      "clip_ratio/region_mean": 0.002242808164737653,
      "epoch": 0.07718647370048241,
      "grad_norm": 0.10734894871711731,
      "learning_rate": 1e-06,
      "loss": 0.0598,
      "step": 827
    },
    {
      "clip_ratio/high_max": 0.002675210627785418,
      "clip_ratio/high_mean": 0.0011202763416804373,
      "clip_ratio/low_mean": 0.0011107365862699226,
      "clip_ratio/low_min": 3.319171446491964e-05,
      "clip_ratio/region_mean": 0.0022310129133984447,
      "epoch": 0.07727980680048299,
      "grad_norm": 0.110447458922863,
      "learning_rate": 1e-06,
      "loss": 0.0168,
      "step": 828
    },
    {
      "clip_ratio/high_max": 0.002626883033371996,
      "clip_ratio/high_mean": 0.0011036710275220685,
      "clip_ratio/low_mean": 0.0012790057226084173,
      "clip_ratio/low_min": 0.00019176518617314287,
      "clip_ratio/region_mean": 0.002382676779234316,
      "epoch": 0.07737313990048358,
      "grad_norm": 0.12311238795518875,
      "learning_rate": 1e-06,
      "loss": 0.0767,
      "step": 829
    },
    {
      "clip_ratio/high_max": 0.002495641056157183,
      "clip_ratio/high_mean": 0.0010171380708925426,
      "clip_ratio/low_mean": 0.0010762759739009198,
      "clip_ratio/low_min": 0.00010596569427434588,
      "clip_ratio/region_mean": 0.0020934140411554836,
      "epoch": 0.07746647300048416,
      "grad_norm": 0.1093924343585968,
      "learning_rate": 1e-06,
      "loss": 0.0101,
      "step": 830
    },
    {
      "clip_ratio/high_max": 0.002840391098288819,
      "clip_ratio/high_mean": 0.0012321114936639788,
      "clip_ratio/low_mean": 0.0010165530256927013,
      "clip_ratio/low_min": 0.00014056388135941233,
      "clip_ratio/region_mean": 0.0022486645830213092,
      "epoch": 0.07755980610048475,
      "grad_norm": 0.11260376870632172,
      "learning_rate": 1e-06,
      "loss": -0.0124,
      "step": 831
    },
    {
      "clip_ratio/high_max": 0.0025712110800668597,
      "clip_ratio/high_mean": 0.0010986134875565767,
      "clip_ratio/low_mean": 0.0012721074563160073,
      "clip_ratio/low_min": 0.00018343739793635905,
      "clip_ratio/region_mean": 0.0023707208965788595,
      "epoch": 0.07765313920048533,
      "grad_norm": 0.11848191916942596,
      "learning_rate": 1e-06,
      "loss": 0.0329,
      "step": 832
    },
    {
      "clip_ratio/high_max": 0.002364235304412432,
      "clip_ratio/high_mean": 0.0009977382414945168,
      "clip_ratio/low_mean": 0.0012987564186914824,
      "clip_ratio/low_min": 0.00017530275545141194,
      "clip_ratio/region_mean": 0.002296494654729031,
      "epoch": 0.07774647230048591,
      "grad_norm": 0.12366092950105667,
      "learning_rate": 1e-06,
      "loss": 0.0599,
      "step": 833
    },
    {
      "clip_ratio/high_max": 0.00294971872062888,
      "clip_ratio/high_mean": 0.001173786982690217,
      "clip_ratio/low_mean": 0.0012067906282027252,
      "clip_ratio/low_min": 0.0001133947771450039,
      "clip_ratio/region_mean": 0.0023805776072549634,
      "epoch": 0.0778398054004865,
      "grad_norm": 0.11560620367527008,
      "learning_rate": 1e-06,
      "loss": 0.0053,
      "step": 834
    },
    {
      "clip_ratio/high_max": 0.0028235580102773383,
      "clip_ratio/high_mean": 0.0011722293529601302,
      "clip_ratio/low_mean": 0.0012163692772446666,
      "clip_ratio/low_min": 0.00011307509976177244,
      "clip_ratio/region_mean": 0.0023885986811365,
      "epoch": 0.07793313850048708,
      "grad_norm": 0.1150728091597557,
      "learning_rate": 1e-06,
      "loss": 0.027,
      "step": 835
    },
    {
      "clip_ratio/high_max": 0.002796860979287885,
      "clip_ratio/high_mean": 0.001230579313414637,
      "clip_ratio/low_mean": 0.0011900466452061664,
      "clip_ratio/low_min": 0.00010438288518344052,
      "clip_ratio/region_mean": 0.0024206259913626127,
      "epoch": 0.07802647160048766,
      "grad_norm": 0.12293171137571335,
      "learning_rate": 1e-06,
      "loss": 0.0091,
      "step": 836
    },
    {
      "clip_ratio/high_max": 0.0025184596815961413,
      "clip_ratio/high_mean": 0.0010847919293155428,
      "clip_ratio/low_mean": 0.0010645002948876936,
      "clip_ratio/low_min": 3.018687311850954e-05,
      "clip_ratio/region_mean": 0.002149292267858982,
      "epoch": 0.07811980470048825,
      "grad_norm": 0.10963098704814911,
      "learning_rate": 1e-06,
      "loss": 0.0009,
      "step": 837
    },
    {
      "clip_ratio/high_max": 0.0029446048793033697,
      "clip_ratio/high_mean": 0.0012566983023134526,
      "clip_ratio/low_mean": 0.0011154347703268286,
      "clip_ratio/low_min": 0.00018814946815837175,
      "clip_ratio/region_mean": 0.0023721331017441116,
      "epoch": 0.07821313780048883,
      "grad_norm": 0.10519551485776901,
      "learning_rate": 1e-06,
      "loss": -0.0229,
      "step": 838
    },
    {
      "clip_ratio/high_max": 0.002930307964561507,
      "clip_ratio/high_mean": 0.0012489281725720502,
      "clip_ratio/low_mean": 0.001091754149456392,
      "clip_ratio/low_min": 9.750380831974326e-05,
      "clip_ratio/region_mean": 0.002340682352951262,
      "epoch": 0.07830647090048942,
      "grad_norm": 0.1064944714307785,
      "learning_rate": 1e-06,
      "loss": -0.0335,
      "step": 839
    },
    {
      "clip_ratio/high_max": 0.0028890523899463005,
      "clip_ratio/high_mean": 0.0012158993595221546,
      "clip_ratio/low_mean": 0.0011043915510526858,
      "clip_ratio/low_min": 5.079952461528592e-05,
      "clip_ratio/region_mean": 0.0023202909287647344,
      "epoch": 0.07839980400049,
      "grad_norm": 0.1067441925406456,
      "learning_rate": 1e-06,
      "loss": -0.0023,
      "step": 840
    },
    {
      "clip_ratio/high_max": 0.002793265895888908,
      "clip_ratio/high_mean": 0.0011566314387891907,
      "clip_ratio/low_mean": 0.0013418986018223222,
      "clip_ratio/low_min": 5.787646114185918e-05,
      "clip_ratio/region_mean": 0.0024985300260595977,
      "epoch": 0.07849313710049058,
      "grad_norm": 0.1163916364312172,
      "learning_rate": 1e-06,
      "loss": 0.02,
      "step": 841
    },
    {
      "clip_ratio/high_max": 0.0023071855248417705,
      "clip_ratio/high_mean": 0.0010460580670041963,
      "clip_ratio/low_mean": 0.0011510213262226898,
      "clip_ratio/low_min": 0.00017384290185873397,
      "clip_ratio/region_mean": 0.0021970793895889074,
      "epoch": 0.07858647020049117,
      "grad_norm": 0.11197704821825027,
      "learning_rate": 1e-06,
      "loss": 0.0124,
      "step": 842
    },
    {
      "clip_ratio/high_max": 0.0026716525098890997,
      "clip_ratio/high_mean": 0.0011010273428837536,
      "clip_ratio/low_mean": 0.0012139241334807593,
      "clip_ratio/low_min": 5.7995189308712725e-05,
      "clip_ratio/region_mean": 0.002314951503649354,
      "epoch": 0.07867980330049175,
      "grad_norm": 0.117385134100914,
      "learning_rate": 1e-06,
      "loss": 0.0185,
      "step": 843
    },
    {
      "clip_ratio/high_max": 0.0029825856909155846,
      "clip_ratio/high_mean": 0.0012078943036613055,
      "clip_ratio/low_mean": 0.001284895039134426,
      "clip_ratio/low_min": 7.221832129289396e-05,
      "clip_ratio/region_mean": 0.002492789259122219,
      "epoch": 0.07877313640049233,
      "grad_norm": 0.10704333335161209,
      "learning_rate": 1e-06,
      "loss": -0.0033,
      "step": 844
    },
    {
      "clip_ratio/high_max": 0.0028190696612000465,
      "clip_ratio/high_mean": 0.0011748472570616286,
      "clip_ratio/low_mean": 0.0011886053762282245,
      "clip_ratio/low_min": 0.00013773003411188256,
      "clip_ratio/region_mean": 0.002363452615099959,
      "epoch": 0.07886646950049292,
      "grad_norm": 0.11524241417646408,
      "learning_rate": 1e-06,
      "loss": 0.0061,
      "step": 845
    },
    {
      "clip_ratio/high_max": 0.0026027618878288195,
      "clip_ratio/high_mean": 0.0011713986968970858,
      "clip_ratio/low_mean": 0.0013452168423100375,
      "clip_ratio/low_min": 0.00020449037401704118,
      "clip_ratio/region_mean": 0.0025166155173792504,
      "epoch": 0.0789598026004935,
      "grad_norm": 0.1149684265255928,
      "learning_rate": 1e-06,
      "loss": 0.0434,
      "step": 846
    },
    {
      "clip_ratio/high_max": 0.0027084273388027214,
      "clip_ratio/high_mean": 0.0012229471067257691,
      "clip_ratio/low_mean": 0.0012291662824281957,
      "clip_ratio/low_min": 0.00013775792467640713,
      "clip_ratio/region_mean": 0.002452113381878007,
      "epoch": 0.07905313570049408,
      "grad_norm": 0.11223486810922623,
      "learning_rate": 1e-06,
      "loss": 0.0415,
      "step": 847
    },
    {
      "clip_ratio/high_max": 0.0023342169188254047,
      "clip_ratio/high_mean": 0.00104853719494713,
      "clip_ratio/low_mean": 0.001133318828578922,
      "clip_ratio/low_min": 7.183461275417358e-05,
      "clip_ratio/region_mean": 0.0021818560126121156,
      "epoch": 0.07914646880049467,
      "grad_norm": 0.11231688410043716,
      "learning_rate": 1e-06,
      "loss": 0.0376,
      "step": 848
    },
    {
      "clip_ratio/high_max": 0.002410042034171056,
      "clip_ratio/high_mean": 0.0010396162579127122,
      "clip_ratio/low_mean": 0.0012280759401619434,
      "clip_ratio/low_min": 2.5278059183619916e-05,
      "clip_ratio/region_mean": 0.002267692194436677,
      "epoch": 0.07923980190049525,
      "grad_norm": 0.10515587776899338,
      "learning_rate": 1e-06,
      "loss": 0.0175,
      "step": 849
    },
    {
      "clip_ratio/high_max": 0.0026403689917060547,
      "clip_ratio/high_mean": 0.00108723109588027,
      "clip_ratio/low_mean": 0.0011319163877487881,
      "clip_ratio/low_min": 7.417487086058827e-05,
      "clip_ratio/region_mean": 0.002219147529103793,
      "epoch": 0.07933313500049584,
      "grad_norm": 0.11551614105701447,
      "learning_rate": 1e-06,
      "loss": 0.0021,
      "step": 850
    },
    {
      "clip_ratio/high_max": 0.002728172690694919,
      "clip_ratio/high_mean": 0.0011947342190978816,
      "clip_ratio/low_mean": 0.0012031684673274867,
      "clip_ratio/low_min": 7.300599918380613e-05,
      "clip_ratio/region_mean": 0.0023979027319001034,
      "epoch": 0.07942646810049642,
      "grad_norm": 0.11337242275476456,
      "learning_rate": 1e-06,
      "loss": 0.0193,
      "step": 851
    },
    {
      "clip_ratio/high_max": 0.0028930796834174544,
      "clip_ratio/high_mean": 0.0011206011458853027,
      "clip_ratio/low_mean": 0.0013113266868458595,
      "clip_ratio/low_min": 0.00011218701638426865,
      "clip_ratio/region_mean": 0.0024319278090843,
      "epoch": 0.079519801200497,
      "grad_norm": 0.1045721247792244,
      "learning_rate": 1e-06,
      "loss": 0.0228,
      "step": 852
    },
    {
      "clip_ratio/high_max": 0.0021872713186894543,
      "clip_ratio/high_mean": 0.000961685353104258,
      "clip_ratio/low_mean": 0.0012616278145287652,
      "clip_ratio/low_min": 0.00014936704792489763,
      "clip_ratio/region_mean": 0.0022233130803215317,
      "epoch": 0.07961313430049759,
      "grad_norm": 0.1051497608423233,
      "learning_rate": 1e-06,
      "loss": 0.0498,
      "step": 853
    },
    {
      "clip_ratio/high_max": 0.002884042500227224,
      "clip_ratio/high_mean": 0.0012240650030435063,
      "clip_ratio/low_mean": 0.001252728863619268,
      "clip_ratio/low_min": 0.00020089035842829617,
      "clip_ratio/region_mean": 0.0024767938666627742,
      "epoch": 0.07970646740049817,
      "grad_norm": 0.1235123798251152,
      "learning_rate": 1e-06,
      "loss": 0.0036,
      "step": 854
    },
    {
      "clip_ratio/high_max": 0.00263397454546066,
      "clip_ratio/high_mean": 0.0010142055889446056,
      "clip_ratio/low_mean": 0.0015909727226244286,
      "clip_ratio/low_min": 0.00019899124799849233,
      "clip_ratio/region_mean": 0.002605178357043769,
      "epoch": 0.07979980050049874,
      "grad_norm": 0.1250627636909485,
      "learning_rate": 1e-06,
      "loss": 0.07,
      "step": 855
    },
    {
      "clip_ratio/high_max": 0.002509389945771545,
      "clip_ratio/high_mean": 0.001222724633407779,
      "clip_ratio/low_mean": 0.00121611468057381,
      "clip_ratio/low_min": 5.433012483990751e-05,
      "clip_ratio/region_mean": 0.002438839292153716,
      "epoch": 0.07989313360049934,
      "grad_norm": 0.11074072867631912,
      "learning_rate": 1e-06,
      "loss": 0.0144,
      "step": 856
    },
    {
      "clip_ratio/high_max": 0.002395431110926438,
      "clip_ratio/high_mean": 0.0011117208487121388,
      "clip_ratio/low_mean": 0.001253226993867429,
      "clip_ratio/low_min": 0.0001308160190092167,
      "clip_ratio/region_mean": 0.002364947860769462,
      "epoch": 0.07998646670049991,
      "grad_norm": 0.11242078989744186,
      "learning_rate": 1e-06,
      "loss": 0.0323,
      "step": 857
    },
    {
      "clip_ratio/high_max": 0.002333924509002827,
      "clip_ratio/high_mean": 0.0010449303554196376,
      "clip_ratio/low_mean": 0.0013359494896576507,
      "clip_ratio/low_min": 0.00010576903787296033,
      "clip_ratio/region_mean": 0.0023808798359823413,
      "epoch": 0.08007979980050049,
      "grad_norm": 0.1026012971997261,
      "learning_rate": 1e-06,
      "loss": 0.0254,
      "step": 858
    },
    {
      "clip_ratio/high_max": 0.0029559947943198495,
      "clip_ratio/high_mean": 0.0011964665682171471,
      "clip_ratio/low_mean": 0.0013974406283523422,
      "clip_ratio/low_min": 0.00021447910694405437,
      "clip_ratio/region_mean": 0.002593907149275765,
      "epoch": 0.08017313290050108,
      "grad_norm": 0.11363668739795685,
      "learning_rate": 1e-06,
      "loss": 0.0268,
      "step": 859
    },
    {
      "clip_ratio/high_max": 0.0025750106360646896,
      "clip_ratio/high_mean": 0.0011252224030613434,
      "clip_ratio/low_mean": 0.0011689675484376494,
      "clip_ratio/low_min": 8.529292972525582e-05,
      "clip_ratio/region_mean": 0.0022941899951547384,
      "epoch": 0.08026646600050166,
      "grad_norm": 0.11206766963005066,
      "learning_rate": 1e-06,
      "loss": 0.0089,
      "step": 860
    },
    {
      "clip_ratio/high_max": 0.0026344709185650572,
      "clip_ratio/high_mean": 0.0011701535950123798,
      "clip_ratio/low_mean": 0.001301527696341509,
      "clip_ratio/low_min": 0.00013713348016608506,
      "clip_ratio/region_mean": 0.002471681291353889,
      "epoch": 0.08035979910050225,
      "grad_norm": 0.6191704273223877,
      "learning_rate": 1e-06,
      "loss": 0.0287,
      "step": 861
    },
    {
      "clip_ratio/high_max": 0.002676965232240036,
      "clip_ratio/high_mean": 0.001188356374768773,
      "clip_ratio/low_mean": 0.001243033017090056,
      "clip_ratio/low_min": 8.402799539908301e-05,
      "clip_ratio/region_mean": 0.0024313893882208504,
      "epoch": 0.08045313220050283,
      "grad_norm": 0.11981311440467834,
      "learning_rate": 1e-06,
      "loss": 0.0133,
      "step": 862
    },
    {
      "clip_ratio/high_max": 0.0029913152975495905,
      "clip_ratio/high_mean": 0.001332960480795009,
      "clip_ratio/low_mean": 0.0013263007094792556,
      "clip_ratio/low_min": 9.373093053000048e-05,
      "clip_ratio/region_mean": 0.0026592612848617136,
      "epoch": 0.08054646530050341,
      "grad_norm": 0.10774748772382736,
      "learning_rate": 1e-06,
      "loss": 0.0051,
      "step": 863
    },
    {
      "clip_ratio/high_max": 0.0022657581212115474,
      "clip_ratio/high_mean": 0.001019522193018929,
      "clip_ratio/low_mean": 0.0012398361341183772,
      "clip_ratio/low_min": 0.00012176808741060086,
      "clip_ratio/region_mean": 0.0022593583198613487,
      "epoch": 0.080639798400504,
      "grad_norm": 0.10538513213396072,
      "learning_rate": 1e-06,
      "loss": 0.034,
      "step": 864
    },
    {
      "clip_ratio/high_max": 0.0032340588804800063,
      "clip_ratio/high_mean": 0.0013334745563042816,
      "clip_ratio/low_mean": 0.0011402142336010002,
      "clip_ratio/low_min": 7.988152538018767e-05,
      "clip_ratio/region_mean": 0.002473688822647091,
      "epoch": 0.08073313150050458,
      "grad_norm": 0.12368640303611755,
      "learning_rate": 1e-06,
      "loss": -0.0055,
      "step": 865
    },
    {
      "clip_ratio/high_max": 0.0027304650720907375,
      "clip_ratio/high_mean": 0.0011897902186319698,
      "clip_ratio/low_mean": 0.001282854387682164,
      "clip_ratio/low_min": 0.00012809545660275035,
      "clip_ratio/region_mean": 0.002472644584486261,
      "epoch": 0.08082646460050516,
      "grad_norm": 0.11296059191226959,
      "learning_rate": 1e-06,
      "loss": 0.0263,
      "step": 866
    },
    {
      "clip_ratio/high_max": 0.0026717867731349543,
      "clip_ratio/high_mean": 0.001015289382849005,
      "clip_ratio/low_mean": 0.001372029826598009,
      "clip_ratio/low_min": 4.58370550404652e-05,
      "clip_ratio/region_mean": 0.0023873192112660035,
      "epoch": 0.08091979770050575,
      "grad_norm": 0.11703436076641083,
      "learning_rate": 1e-06,
      "loss": 0.0705,
      "step": 867
    },
    {
      "clip_ratio/high_max": 0.00266984743939247,
      "clip_ratio/high_mean": 0.001182723219244508,
      "clip_ratio/low_mean": 0.0013851462026650552,
      "clip_ratio/low_min": 5.295644950820133e-05,
      "clip_ratio/region_mean": 0.002567869334598072,
      "epoch": 0.08101313080050633,
      "grad_norm": 0.120257169008255,
      "learning_rate": 1e-06,
      "loss": 0.0198,
      "step": 868
    },
    {
      "clip_ratio/high_max": 0.0026716306529124267,
      "clip_ratio/high_mean": 0.0012233324996486772,
      "clip_ratio/low_mean": 0.0012099921932531288,
      "clip_ratio/low_min": 9.078643597604241e-05,
      "clip_ratio/region_mean": 0.002433324720186647,
      "epoch": 0.08110646390050691,
      "grad_norm": 0.11764660477638245,
      "learning_rate": 1e-06,
      "loss": -0.017,
      "step": 869
    },
    {
      "clip_ratio/high_max": 0.0030705239478265867,
      "clip_ratio/high_mean": 0.0012332064143265598,
      "clip_ratio/low_mean": 0.0014900982932886109,
      "clip_ratio/low_min": 0.00011409409489715472,
      "clip_ratio/region_mean": 0.0027233046930632554,
      "epoch": 0.0811997970005075,
      "grad_norm": 0.11546960473060608,
      "learning_rate": 1e-06,
      "loss": 0.0333,
      "step": 870
    },
    {
      "clip_ratio/high_max": 0.003083862153289374,
      "clip_ratio/high_mean": 0.0012245197758602444,
      "clip_ratio/low_mean": 0.0012763446320604999,
      "clip_ratio/low_min": 0.00011840130991913611,
      "clip_ratio/region_mean": 0.002500864415196702,
      "epoch": 0.08129313010050808,
      "grad_norm": 0.12118712067604065,
      "learning_rate": 1e-06,
      "loss": -0.0064,
      "step": 871
    },
    {
      "clip_ratio/high_max": 0.0029794194852001965,
      "clip_ratio/high_mean": 0.0013708833139389753,
      "clip_ratio/low_mean": 0.0014867627505736891,
      "clip_ratio/low_min": 0.0001623352109163534,
      "clip_ratio/region_mean": 0.002857646053598728,
      "epoch": 0.08138646320050867,
      "grad_norm": 0.1265120506286621,
      "learning_rate": 1e-06,
      "loss": -0.0439,
      "step": 872
    },
    {
      "clip_ratio/high_max": 0.002703121557715349,
      "clip_ratio/high_mean": 0.0011338754047756083,
      "clip_ratio/low_mean": 0.0016530198154214304,
      "clip_ratio/low_min": 0.00010148712135560345,
      "clip_ratio/region_mean": 0.0027868952238350175,
      "epoch": 0.08147979630050925,
      "grad_norm": 0.10864236950874329,
      "learning_rate": 1e-06,
      "loss": 0.0292,
      "step": 873
    },
    {
      "clip_ratio/high_max": 0.0025929372532118578,
      "clip_ratio/high_mean": 0.0010713470146583859,
      "clip_ratio/low_mean": 0.00130601479759207,
      "clip_ratio/low_min": 4.2274246879969724e-05,
      "clip_ratio/region_mean": 0.0023773618013365194,
      "epoch": 0.08157312940050983,
      "grad_norm": 0.10903564840555191,
      "learning_rate": 1e-06,
      "loss": 0.0344,
      "step": 874
    },
    {
      "clip_ratio/high_max": 0.00267447571241064,
      "clip_ratio/high_mean": 0.0011267735535511747,
      "clip_ratio/low_mean": 0.001447578670195071,
      "clip_ratio/low_min": 0.000233820806897711,
      "clip_ratio/region_mean": 0.002574352256488055,
      "epoch": 0.08166646250051042,
      "grad_norm": 0.10689591616392136,
      "learning_rate": 1e-06,
      "loss": 0.0339,
      "step": 875
    },
    {
      "clip_ratio/high_max": 0.002816759282723069,
      "clip_ratio/high_mean": 0.0013318099736352451,
      "clip_ratio/low_mean": 0.0014332242935779504,
      "clip_ratio/low_min": 0.00016015996880014427,
      "clip_ratio/region_mean": 0.002765034296317026,
      "epoch": 0.081759795600511,
      "grad_norm": 0.15753105282783508,
      "learning_rate": 1e-06,
      "loss": 0.0182,
      "step": 876
    },
    {
      "clip_ratio/high_max": 0.0028222528599144425,
      "clip_ratio/high_mean": 0.0011794420606747735,
      "clip_ratio/low_mean": 0.0014150172319205012,
      "clip_ratio/low_min": 7.90039212006377e-06,
      "clip_ratio/region_mean": 0.0025944592998712324,
      "epoch": 0.08185312870051158,
      "grad_norm": 0.12091733515262604,
      "learning_rate": 1e-06,
      "loss": 0.0294,
      "step": 877
    },
    {
      "clip_ratio/high_max": 0.0026184621565334965,
      "clip_ratio/high_mean": 0.0012445320462575182,
      "clip_ratio/low_mean": 0.001264230773813324,
      "clip_ratio/low_min": 5.083018641016679e-05,
      "clip_ratio/region_mean": 0.002508762845536694,
      "epoch": 0.08194646180051217,
      "grad_norm": 0.10422682017087936,
      "learning_rate": 1e-06,
      "loss": 0.0231,
      "step": 878
    },
    {
      "clip_ratio/high_max": 0.002115822055202443,
      "clip_ratio/high_mean": 0.0009537266942061251,
      "clip_ratio/low_mean": 0.0016013810054573696,
      "clip_ratio/low_min": 0.00017287244736508,
      "clip_ratio/region_mean": 0.0025551076614647172,
      "epoch": 0.08203979490051275,
      "grad_norm": 0.10884254425764084,
      "learning_rate": 1e-06,
      "loss": 0.0533,
      "step": 879
    },
    {
      "clip_ratio/high_max": 0.0025673884301795624,
      "clip_ratio/high_mean": 0.0010874926865653833,
      "clip_ratio/low_mean": 0.0013618801931443159,
      "clip_ratio/low_min": 0.00015549774252576753,
      "clip_ratio/region_mean": 0.002449372928822413,
      "epoch": 0.08213312800051333,
      "grad_norm": 0.11862734705209732,
      "learning_rate": 1e-06,
      "loss": 0.0801,
      "step": 880
    },
    {
      "clip_ratio/high_max": 0.0028271170594962314,
      "clip_ratio/high_mean": 0.0011623361006058985,
      "clip_ratio/low_mean": 0.0014281211742854794,
      "clip_ratio/low_min": 0.00022740460372006055,
      "clip_ratio/region_mean": 0.002590457246697042,
      "epoch": 0.08222646110051392,
      "grad_norm": 0.11558318138122559,
      "learning_rate": 1e-06,
      "loss": 0.0596,
      "step": 881
    },
    {
      "clip_ratio/high_max": 0.00272104359100922,
      "clip_ratio/high_mean": 0.001244183591552428,
      "clip_ratio/low_mean": 0.0013736167566094082,
      "clip_ratio/low_min": 0.00022559764056495624,
      "clip_ratio/region_mean": 0.0026178003463428468,
      "epoch": 0.0823197942005145,
      "grad_norm": 0.11596973985433578,
      "learning_rate": 1e-06,
      "loss": 0.0514,
      "step": 882
    },
    {
      "clip_ratio/high_max": 0.0030806600334472023,
      "clip_ratio/high_mean": 0.0011541204803506844,
      "clip_ratio/low_mean": 0.0013255390513222665,
      "clip_ratio/low_min": 0.00014947133058740292,
      "clip_ratio/region_mean": 0.0024796595607767813,
      "epoch": 0.08241312730051509,
      "grad_norm": 0.1079336479306221,
      "learning_rate": 1e-06,
      "loss": 0.041,
      "step": 883
    },
    {
      "clip_ratio/high_max": 0.002756727328232955,
      "clip_ratio/high_mean": 0.0012181342699477682,
      "clip_ratio/low_mean": 0.0014362711772264447,
      "clip_ratio/low_min": 0.00019357741985004395,
      "clip_ratio/region_mean": 0.0026544054780970328,
      "epoch": 0.08250646040051567,
      "grad_norm": 0.10953733325004578,
      "learning_rate": 1e-06,
      "loss": 0.0351,
      "step": 884
    },
    {
      "clip_ratio/high_max": 0.002775097222183831,
      "clip_ratio/high_mean": 0.001262925346964039,
      "clip_ratio/low_mean": 0.00116158917080611,
      "clip_ratio/low_min": 7.620512496941956e-05,
      "clip_ratio/region_mean": 0.0024245145032182336,
      "epoch": 0.08259979350051624,
      "grad_norm": 0.11950094997882843,
      "learning_rate": 1e-06,
      "loss": 0.0049,
      "step": 885
    },
    {
      "clip_ratio/high_max": 0.002757563030172605,
      "clip_ratio/high_mean": 0.0011204800066479947,
      "clip_ratio/low_mean": 0.0012934416954522021,
      "clip_ratio/low_min": 0.00011284019365120912,
      "clip_ratio/region_mean": 0.002413921771221794,
      "epoch": 0.08269312660051684,
      "grad_norm": 0.10900633037090302,
      "learning_rate": 1e-06,
      "loss": -0.0058,
      "step": 886
    },
    {
      "clip_ratio/high_max": 0.0028210538839630317,
      "clip_ratio/high_mean": 0.001050157366989879,
      "clip_ratio/low_mean": 0.0016014536304282956,
      "clip_ratio/low_min": 0.0002004827492783079,
      "clip_ratio/region_mean": 0.0026516110519878566,
      "epoch": 0.08278645970051741,
      "grad_norm": 0.11915874481201172,
      "learning_rate": 1e-06,
      "loss": 0.0302,
      "step": 887
    },
    {
      "clip_ratio/high_max": 0.002610648218251299,
      "clip_ratio/high_mean": 0.0011100116025772877,
      "clip_ratio/low_mean": 0.001413670281181112,
      "clip_ratio/low_min": 0.00024200794359785505,
      "clip_ratio/region_mean": 0.0025236818837583996,
      "epoch": 0.08287979280051799,
      "grad_norm": 0.11571001261472702,
      "learning_rate": 1e-06,
      "loss": 0.0461,
      "step": 888
    },
    {
      "clip_ratio/high_max": 0.0025575663821655326,
      "clip_ratio/high_mean": 0.0011261267063673586,
      "clip_ratio/low_mean": 0.0012038480526825879,
      "clip_ratio/low_min": 0.00016985584079520777,
      "clip_ratio/region_mean": 0.002329974711756222,
      "epoch": 0.08297312590051859,
      "grad_norm": 0.1134910061955452,
      "learning_rate": 1e-06,
      "loss": 0.0107,
      "step": 889
    },
    {
      "clip_ratio/high_max": 0.002807971635775175,
      "clip_ratio/high_mean": 0.0011861139719258063,
      "clip_ratio/low_mean": 0.0013165185700927395,
      "clip_ratio/low_min": 0.00015775557494634995,
      "clip_ratio/region_mean": 0.0025026325820363127,
      "epoch": 0.08306645900051916,
      "grad_norm": 0.10823081433773041,
      "learning_rate": 1e-06,
      "loss": 0.0217,
      "step": 890
    },
    {
      "clip_ratio/high_max": 0.0026585467348922975,
      "clip_ratio/high_mean": 0.0011474129896669183,
      "clip_ratio/low_mean": 0.0014322423594421707,
      "clip_ratio/low_min": 0.00011148946487082867,
      "clip_ratio/region_mean": 0.0025796553745749407,
      "epoch": 0.08315979210051976,
      "grad_norm": 0.11732596904039383,
      "learning_rate": 1e-06,
      "loss": 0.0376,
      "step": 891
    },
    {
      "clip_ratio/high_max": 0.002762632444500923,
      "clip_ratio/high_mean": 0.0012664586683968082,
      "clip_ratio/low_mean": 0.0013926984611316584,
      "clip_ratio/low_min": 7.680372254981194e-05,
      "clip_ratio/region_mean": 0.002659157144080382,
      "epoch": 0.08325312520052033,
      "grad_norm": 0.10904115438461304,
      "learning_rate": 1e-06,
      "loss": 0.0139,
      "step": 892
    },
    {
      "clip_ratio/high_max": 0.0030935159302316606,
      "clip_ratio/high_mean": 0.0012770246357831638,
      "clip_ratio/low_mean": 0.001306820984609658,
      "clip_ratio/low_min": 5.368848542275373e-05,
      "clip_ratio/region_mean": 0.0025838457222562283,
      "epoch": 0.08334645830052091,
      "grad_norm": 0.1260535717010498,
      "learning_rate": 1e-06,
      "loss": 0.0389,
      "step": 893
    },
    {
      "clip_ratio/high_max": 0.0028869533707620576,
      "clip_ratio/high_mean": 0.0012445216380001511,
      "clip_ratio/low_mean": 0.001347474528301973,
      "clip_ratio/low_min": 0.00010394027776783332,
      "clip_ratio/region_mean": 0.002591996220871806,
      "epoch": 0.0834397914005215,
      "grad_norm": 0.11635053157806396,
      "learning_rate": 1e-06,
      "loss": 0.0175,
      "step": 894
    },
    {
      "clip_ratio/high_max": 0.0027193515707040206,
      "clip_ratio/high_mean": 0.0012923296562803444,
      "clip_ratio/low_mean": 0.0013158954025129788,
      "clip_ratio/low_min": 0.00013268914153741207,
      "clip_ratio/region_mean": 0.002608225062431302,
      "epoch": 0.08353312450052208,
      "grad_norm": 0.12040353566408157,
      "learning_rate": 1e-06,
      "loss": -0.0061,
      "step": 895
    },
    {
      "clip_ratio/high_max": 0.0025315207603853196,
      "clip_ratio/high_mean": 0.001118036514526466,
      "clip_ratio/low_mean": 0.0014116798229224514,
      "clip_ratio/low_min": 8.406334018218331e-05,
      "clip_ratio/region_mean": 0.0025297163956565782,
      "epoch": 0.08362645760052266,
      "grad_norm": 0.4274236559867859,
      "learning_rate": 1e-06,
      "loss": 0.0508,
      "step": 896
    },
    {
      "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": 0.010332380022321397,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4076.0,
      "completions/mean_length": 604.8611450195312,
      "completions/mean_terminated_length": 568.4127197265625,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.08371979070052325,
      "grad_norm": 0.13180045783519745,
      "learning_rate": 1e-06,
      "loss": 0.0251,
      "num_tokens": 647356960.0,
      "reward": 0.6045271158218384,
      "reward_std": 0.19037386775016785,
      "rewards/simpleverify_reward/mean": 0.6045270562171936,
      "rewards/simpleverify_reward/std": 0.4889540672302246,
      "step": 897
    },
    {
      "clip_ratio/high_max": 0.0020903320437355433,
      "clip_ratio/high_mean": 0.000811422971310094,
      "clip_ratio/low_mean": 0.0004955820868417504,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013070050299575087,
      "epoch": 0.08381312380052383,
      "grad_norm": 0.12040230631828308,
      "learning_rate": 1e-06,
      "loss": 0.0368,
      "step": 898
    },
    {
      "clip_ratio/high_max": 0.0019020930922124535,
      "clip_ratio/high_mean": 0.0008108365400403272,
      "clip_ratio/low_mean": 0.0005846929034305504,
      "clip_ratio/low_min": 2.8351099899737164e-05,
      "clip_ratio/region_mean": 0.0013955294416518882,
      "epoch": 0.08390645690052441,
      "grad_norm": 0.11102444678544998,
      "learning_rate": 1e-06,
      "loss": 0.0132,
      "step": 899
    },
    {
      "clip_ratio/high_max": 0.0021109771987539716,
      "clip_ratio/high_mean": 0.0009411347873538034,
      "clip_ratio/low_mean": 0.0005980320720482268,
      "clip_ratio/low_min": 3.838850534521043e-05,
      "clip_ratio/region_mean": 0.0015391668493975885,
      "epoch": 0.083999790000525,
      "grad_norm": 0.13241131603717804,
      "learning_rate": 1e-06,
      "loss": -0.0254,
      "step": 900
    },
    {
      "clip_ratio/high_max": 0.001951029320480302,
      "clip_ratio/high_mean": 0.0008549535177735379,
      "clip_ratio/low_mean": 0.0006839488560217433,
      "clip_ratio/low_min": 8.409043948631734e-05,
      "clip_ratio/region_mean": 0.0015389024010801222,
      "epoch": 0.08409312310052558,
      "grad_norm": 0.10430038720369339,
      "learning_rate": 1e-06,
      "loss": 0.0262,
      "step": 901
    },
    {
      "clip_ratio/high_max": 0.0017992737630265765,
      "clip_ratio/high_mean": 0.000774283518694574,
      "clip_ratio/low_mean": 0.0007132975924832863,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014875811466481537,
      "epoch": 0.08418645620052617,
      "grad_norm": 0.5818588137626648,
      "learning_rate": 1e-06,
      "loss": 0.0309,
      "step": 902
    },
    {
      "clip_ratio/high_max": 0.0021047825066489168,
      "clip_ratio/high_mean": 0.0008510122970619705,
      "clip_ratio/low_mean": 0.0008836374217935372,
      "clip_ratio/low_min": 1.541307028674055e-05,
      "clip_ratio/region_mean": 0.0017346497188555077,
      "epoch": 0.08427978930052675,
      "grad_norm": 0.1185864806175232,
      "learning_rate": 1e-06,
      "loss": 0.053,
      "step": 903
    },
    {
      "clip_ratio/high_max": 0.0022040233852749225,
      "clip_ratio/high_mean": 0.0008466147646686295,
      "clip_ratio/low_mean": 0.0008286899992526742,
      "clip_ratio/low_min": 5.653566404362209e-05,
      "clip_ratio/region_mean": 0.0016753047239035368,
      "epoch": 0.08437312240052733,
      "grad_norm": 0.12117908149957657,
      "learning_rate": 1e-06,
      "loss": 0.0533,
      "step": 904
    },
    {
      "clip_ratio/high_max": 0.0018884313103626482,
      "clip_ratio/high_mean": 0.000758550286263926,
      "clip_ratio/low_mean": 0.0008438970198767493,
      "clip_ratio/low_min": 0.0001521305075584678,
      "clip_ratio/region_mean": 0.0016024473079596646,
      "epoch": 0.08446645550052792,
      "grad_norm": 0.10082881152629852,
      "learning_rate": 1e-06,
      "loss": 0.0428,
      "step": 905
    },
    {
      "clip_ratio/high_max": 0.002562358098657569,
      "clip_ratio/high_mean": 0.0010030534522229573,
      "clip_ratio/low_mean": 0.0009143080096691847,
      "clip_ratio/low_min": 6.863703765702667e-05,
      "clip_ratio/region_mean": 0.0019173614491592161,
      "epoch": 0.0845597886005285,
      "grad_norm": 0.12264148890972137,
      "learning_rate": 1e-06,
      "loss": 0.0363,
      "step": 906
    },
    {
      "clip_ratio/high_max": 0.002145728485629661,
      "clip_ratio/high_mean": 0.0009420317655894905,
      "clip_ratio/low_mean": 0.0008138321354635991,
      "clip_ratio/low_min": 1.2980270184925757e-05,
      "clip_ratio/region_mean": 0.0017558639010530896,
      "epoch": 0.08465312170052908,
      "grad_norm": 0.11554498225450516,
      "learning_rate": 1e-06,
      "loss": 0.0079,
      "step": 907
    },
    {
      "clip_ratio/high_max": 0.0022196019417606294,
      "clip_ratio/high_mean": 0.0010051094632217428,
      "clip_ratio/low_mean": 0.0009380039646202931,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0019431133841862902,
      "epoch": 0.08474645480052967,
      "grad_norm": 0.12976033985614777,
      "learning_rate": 1e-06,
      "loss": 0.0387,
      "step": 908
    },
    {
      "clip_ratio/high_max": 0.0023158696276368573,
      "clip_ratio/high_mean": 0.0010266714125464205,
      "clip_ratio/low_mean": 0.0009847607452684315,
      "clip_ratio/low_min": 8.343649278685916e-05,
      "clip_ratio/region_mean": 0.0020114321014261805,
      "epoch": 0.08483978790053025,
      "grad_norm": 0.11366299539804459,
      "learning_rate": 1e-06,
      "loss": 0.0467,
      "step": 909
    },
    {
      "clip_ratio/high_max": 0.0024726804476813413,
      "clip_ratio/high_mean": 0.001053126548868022,
      "clip_ratio/low_mean": 0.0009124658427026588,
      "clip_ratio/low_min": 0.00011002197788911872,
      "clip_ratio/region_mean": 0.0019655923533719033,
      "epoch": 0.08493312100053083,
      "grad_norm": 0.1178712546825409,
      "learning_rate": 1e-06,
      "loss": 0.0373,
      "step": 910
    },
    {
      "clip_ratio/high_max": 0.002646814682520926,
      "clip_ratio/high_mean": 0.0010974636225000722,
      "clip_ratio/low_mean": 0.0009178663640341256,
      "clip_ratio/low_min": 7.914322213764535e-05,
      "clip_ratio/region_mean": 0.0020153299628873356,
      "epoch": 0.08502645410053142,
      "grad_norm": 0.13061457872390747,
      "learning_rate": 1e-06,
      "loss": -0.0102,
      "step": 911
    },
    {
      "clip_ratio/high_max": 0.0020276003779144958,
      "clip_ratio/high_mean": 0.0009705177908472251,
      "clip_ratio/low_mean": 0.0008762455418036552,
      "clip_ratio/low_min": 6.748240321030607e-05,
      "clip_ratio/region_mean": 0.0018467633708496578,
      "epoch": 0.085119787200532,
      "grad_norm": 0.3669838011264801,
      "learning_rate": 1e-06,
      "loss": 0.0128,
      "step": 912
    },
    {
      "clip_ratio/high_max": 0.0026896395211224444,
      "clip_ratio/high_mean": 0.0011159031182614854,
      "clip_ratio/low_mean": 0.0010102335581905209,
      "clip_ratio/low_min": 9.22293202165747e-05,
      "clip_ratio/region_mean": 0.0021261366200633347,
      "epoch": 0.08521312030053259,
      "grad_norm": 0.11618983000516891,
      "learning_rate": 1e-06,
      "loss": 0.0238,
      "step": 913
    },
    {
      "clip_ratio/high_max": 0.002566167931945529,
      "clip_ratio/high_mean": 0.0010500563876121305,
      "clip_ratio/low_mean": 0.0010380182466178667,
      "clip_ratio/low_min": 0.0001485766224504914,
      "clip_ratio/region_mean": 0.0020880746305920184,
      "epoch": 0.08530645340053317,
      "grad_norm": 0.12886705994606018,
      "learning_rate": 1e-06,
      "loss": -0.0104,
      "step": 914
    },
    {
      "clip_ratio/high_max": 0.002359906822675839,
      "clip_ratio/high_mean": 0.000975397793808952,
      "clip_ratio/low_mean": 0.0010993423056788743,
      "clip_ratio/low_min": 0.0001564110552862985,
      "clip_ratio/region_mean": 0.0020747400922118686,
      "epoch": 0.08539978650053374,
      "grad_norm": 0.11995469033718109,
      "learning_rate": 1e-06,
      "loss": 0.0523,
      "step": 915
    },
    {
      "clip_ratio/high_max": 0.0026835996759473346,
      "clip_ratio/high_mean": 0.0011424657695897622,
      "clip_ratio/low_mean": 0.0011959493770064,
      "clip_ratio/low_min": 0.00016448516544187441,
      "clip_ratio/region_mean": 0.0023384150917991064,
      "epoch": 0.08549311960053434,
      "grad_norm": 0.11073128879070282,
      "learning_rate": 1e-06,
      "loss": 0.0087,
      "step": 916
    },
    {
      "clip_ratio/high_max": 0.0022553076269105077,
      "clip_ratio/high_mean": 0.0009291547939938027,
      "clip_ratio/low_mean": 0.0012759980709233787,
      "clip_ratio/low_min": 0.00013660632794199046,
      "clip_ratio/region_mean": 0.002205152908572927,
      "epoch": 0.08558645270053492,
      "grad_norm": 0.1244710385799408,
      "learning_rate": 1e-06,
      "loss": 0.0431,
      "step": 917
    },
    {
      "clip_ratio/high_max": 0.0025015782011905685,
      "clip_ratio/high_mean": 0.0010640408781910082,
      "clip_ratio/low_mean": 0.001145112793892622,
      "clip_ratio/low_min": 1.7250897144549526e-05,
      "clip_ratio/region_mean": 0.00220915370300645,
      "epoch": 0.0856797858005355,
      "grad_norm": 0.12307003885507584,
      "learning_rate": 1e-06,
      "loss": 0.0071,
      "step": 918
    },
    {
      "clip_ratio/high_max": 0.0024824382344377227,
      "clip_ratio/high_mean": 0.0010619299973768648,
      "clip_ratio/low_mean": 0.001083579430996906,
      "clip_ratio/low_min": 3.900230694853235e-05,
      "clip_ratio/region_mean": 0.00214550946111558,
      "epoch": 0.08577311890053609,
      "grad_norm": 0.1148950457572937,
      "learning_rate": 1e-06,
      "loss": 0.0205,
      "step": 919
    },
    {
      "clip_ratio/high_max": 0.0025234888889826834,
      "clip_ratio/high_mean": 0.0010395415738457814,
      "clip_ratio/low_mean": 0.0011789917807618622,
      "clip_ratio/low_min": 4.821899619855685e-05,
      "clip_ratio/region_mean": 0.0022185333364177495,
      "epoch": 0.08586645200053666,
      "grad_norm": 0.1140666976571083,
      "learning_rate": 1e-06,
      "loss": 0.0252,
      "step": 920
    },
    {
      "clip_ratio/high_max": 0.002604686866106931,
      "clip_ratio/high_mean": 0.0012305085583648179,
      "clip_ratio/low_mean": 0.0011976935456914362,
      "clip_ratio/low_min": 7.791272673784988e-05,
      "clip_ratio/region_mean": 0.002428202162263915,
      "epoch": 0.08595978510053724,
      "grad_norm": 0.2378448247909546,
      "learning_rate": 1e-06,
      "loss": 0.0076,
      "step": 921
    },
    {
      "clip_ratio/high_max": 0.0022589188847632613,
      "clip_ratio/high_mean": 0.0009832003379415255,
      "clip_ratio/low_mean": 0.0010548079371801578,
      "clip_ratio/low_min": 7.642799937457312e-05,
      "clip_ratio/region_mean": 0.002038008278759662,
      "epoch": 0.08605311820053783,
      "grad_norm": 0.11038652807474136,
      "learning_rate": 1e-06,
      "loss": 0.0033,
      "step": 922
    },
    {
      "clip_ratio/high_max": 0.0029273399195517413,
      "clip_ratio/high_mean": 0.0012167400163889397,
      "clip_ratio/low_mean": 0.0011397859634598717,
      "clip_ratio/low_min": 6.687169388897019e-05,
      "clip_ratio/region_mean": 0.0023565260125906207,
      "epoch": 0.08614645130053841,
      "grad_norm": 0.10846617072820663,
      "learning_rate": 1e-06,
      "loss": 0.0068,
      "step": 923
    },
    {
      "clip_ratio/high_max": 0.0026016525152954273,
      "clip_ratio/high_mean": 0.0010866862867260352,
      "clip_ratio/low_mean": 0.0010949773532047402,
      "clip_ratio/low_min": 8.901059482013807e-05,
      "clip_ratio/region_mean": 0.002181663665396627,
      "epoch": 0.086239784400539,
      "grad_norm": 0.1089077815413475,
      "learning_rate": 1e-06,
      "loss": 0.0263,
      "step": 924
    },
    {
      "clip_ratio/high_max": 0.0021645506858476438,
      "clip_ratio/high_mean": 0.0010588792829366866,
      "clip_ratio/low_mean": 0.0011073275891249068,
      "clip_ratio/low_min": 5.3161484174779616e-05,
      "clip_ratio/region_mean": 0.0021662068756995723,
      "epoch": 0.08633311750053958,
      "grad_norm": 0.11644066870212555,
      "learning_rate": 1e-06,
      "loss": 0.0053,
      "step": 925
    },
    {
      "clip_ratio/high_max": 0.0024562943799537607,
      "clip_ratio/high_mean": 0.0011145613152621081,
      "clip_ratio/low_mean": 0.001179668674012646,
      "clip_ratio/low_min": 7.074141831253655e-05,
      "clip_ratio/region_mean": 0.002294229998369701,
      "epoch": 0.08642645060054016,
      "grad_norm": 0.12333524972200394,
      "learning_rate": 1e-06,
      "loss": -0.0313,
      "step": 926
    },
    {
      "clip_ratio/high_max": 0.002317774858966004,
      "clip_ratio/high_mean": 0.0011376612710591871,
      "clip_ratio/low_mean": 0.001218876896018628,
      "clip_ratio/low_min": 0.00014656296480097808,
      "clip_ratio/region_mean": 0.0023565382143715397,
      "epoch": 0.08651978370054075,
      "grad_norm": 0.11655978113412857,
      "learning_rate": 1e-06,
      "loss": -0.0032,
      "step": 927
    },
    {
      "clip_ratio/high_max": 0.0026441082591190934,
      "clip_ratio/high_mean": 0.001151671924162656,
      "clip_ratio/low_mean": 0.0013011670707783196,
      "clip_ratio/low_min": 8.304755101562478e-05,
      "clip_ratio/region_mean": 0.0024528390204068273,
      "epoch": 0.08661311680054133,
      "grad_norm": 0.12562242150306702,
      "learning_rate": 1e-06,
      "loss": 0.0219,
      "step": 928
    },
    {
      "clip_ratio/high_max": 0.00245697409263812,
      "clip_ratio/high_mean": 0.0010541370629653102,
      "clip_ratio/low_mean": 0.0013386718419496901,
      "clip_ratio/low_min": 0.00012002697440038901,
      "clip_ratio/region_mean": 0.0023928089140099473,
      "epoch": 0.08670644990054191,
      "grad_norm": 0.11794578284025192,
      "learning_rate": 1e-06,
      "loss": 0.0223,
      "step": 929
    },
    {
      "clip_ratio/high_max": 0.0023919832274259534,
      "clip_ratio/high_mean": 0.0010860691600100836,
      "clip_ratio/low_mean": 0.0013822069777233992,
      "clip_ratio/low_min": 9.76255096247769e-05,
      "clip_ratio/region_mean": 0.002468276121362578,
      "epoch": 0.0867997830005425,
      "grad_norm": 0.12333954870700836,
      "learning_rate": 1e-06,
      "loss": 0.0072,
      "step": 930
    },
    {
      "clip_ratio/high_max": 0.0025176404451485723,
      "clip_ratio/high_mean": 0.0010153427028853912,
      "clip_ratio/low_mean": 0.0013434517677524127,
      "clip_ratio/low_min": 8.390972107008565e-05,
      "clip_ratio/region_mean": 0.002358794503379613,
      "epoch": 0.08689311610054308,
      "grad_norm": 0.11604081094264984,
      "learning_rate": 1e-06,
      "loss": 0.0075,
      "step": 931
    },
    {
      "clip_ratio/high_max": 0.0021745060694229323,
      "clip_ratio/high_mean": 0.0009546953333483543,
      "clip_ratio/low_mean": 0.0015578732745780144,
      "clip_ratio/low_min": 0.0002290548136443249,
      "clip_ratio/region_mean": 0.0025125685933744535,
      "epoch": 0.08698644920054366,
      "grad_norm": 0.10966379195451736,
      "learning_rate": 1e-06,
      "loss": 0.0601,
      "step": 932
    },
    {
      "clip_ratio/high_max": 0.002769292696029879,
      "clip_ratio/high_mean": 0.001277127204957651,
      "clip_ratio/low_mean": 0.001254626158697647,
      "clip_ratio/low_min": 4.278972846805118e-05,
      "clip_ratio/region_mean": 0.0025317533873021603,
      "epoch": 0.08707978230054425,
      "grad_norm": 0.12039266526699066,
      "learning_rate": 1e-06,
      "loss": -0.0555,
      "step": 933
    },
    {
      "clip_ratio/high_max": 0.0028365253820084035,
      "clip_ratio/high_mean": 0.001245771494723158,
      "clip_ratio/low_mean": 0.0014007402023707982,
      "clip_ratio/low_min": 0.0001116386611101916,
      "clip_ratio/region_mean": 0.0026465117989573628,
      "epoch": 0.08717311540054483,
      "grad_norm": 0.12246831506490707,
      "learning_rate": 1e-06,
      "loss": 0.0121,
      "step": 934
    },
    {
      "clip_ratio/high_max": 0.002520124297006987,
      "clip_ratio/high_mean": 0.001015829599054996,
      "clip_ratio/low_mean": 0.0011046435474781902,
      "clip_ratio/low_min": 2.8745544113917276e-05,
      "clip_ratio/region_mean": 0.002120473094691988,
      "epoch": 0.08726644850054542,
      "grad_norm": 0.11671555042266846,
      "learning_rate": 1e-06,
      "loss": 0.0106,
      "step": 935
    },
    {
      "clip_ratio/high_max": 0.0024313078829436563,
      "clip_ratio/high_mean": 0.0010604682775010588,
      "clip_ratio/low_mean": 0.0012984707136638463,
      "clip_ratio/low_min": 0.00015652061847504228,
      "clip_ratio/region_mean": 0.0023589390111737885,
      "epoch": 0.087359781600546,
      "grad_norm": 0.11363453418016434,
      "learning_rate": 1e-06,
      "loss": 0.0391,
      "step": 936
    },
    {
      "clip_ratio/high_max": 0.0022487197420559824,
      "clip_ratio/high_mean": 0.0009560376274748705,
      "clip_ratio/low_mean": 0.0013037988319410942,
      "clip_ratio/low_min": 0.00011548104339453857,
      "clip_ratio/region_mean": 0.0022598364885197952,
      "epoch": 0.08745311470054658,
      "grad_norm": 0.11499801278114319,
      "learning_rate": 1e-06,
      "loss": 0.043,
      "step": 937
    },
    {
      "clip_ratio/high_max": 0.0026057502400362864,
      "clip_ratio/high_mean": 0.0011198134689038852,
      "clip_ratio/low_mean": 0.0012438147350621875,
      "clip_ratio/low_min": 0.0001233796137967147,
      "clip_ratio/region_mean": 0.002363628249440808,
      "epoch": 0.08754644780054717,
      "grad_norm": 0.1672276109457016,
      "learning_rate": 1e-06,
      "loss": 0.0293,
      "step": 938
    },
    {
      "clip_ratio/high_max": 0.00285910876118578,
      "clip_ratio/high_mean": 0.0010590961210255045,
      "clip_ratio/low_mean": 0.0013069356718915515,
      "clip_ratio/low_min": 0.0002795633099594852,
      "clip_ratio/region_mean": 0.0023660318038309924,
      "epoch": 0.08763978090054775,
      "grad_norm": 0.11041127890348434,
      "learning_rate": 1e-06,
      "loss": 0.0173,
      "step": 939
    },
    {
      "clip_ratio/high_max": 0.0026718849330791272,
      "clip_ratio/high_mean": 0.001027100719511509,
      "clip_ratio/low_mean": 0.0012909763208881486,
      "clip_ratio/low_min": 9.275022330257343e-05,
      "clip_ratio/region_mean": 0.002318077051313594,
      "epoch": 0.08773311400054833,
      "grad_norm": 0.11999907344579697,
      "learning_rate": 1e-06,
      "loss": 0.0269,
      "step": 940
    },
    {
      "clip_ratio/high_max": 0.002634908159961924,
      "clip_ratio/high_mean": 0.0011355004207871389,
      "clip_ratio/low_mean": 0.0012214113703521434,
      "clip_ratio/low_min": 0.00018193683627032442,
      "clip_ratio/region_mean": 0.0023569117693114094,
      "epoch": 0.08782644710054892,
      "grad_norm": 0.2274075597524643,
      "learning_rate": 1e-06,
      "loss": 0.0457,
      "step": 941
    },
    {
      "clip_ratio/high_max": 0.002534883147745859,
      "clip_ratio/high_mean": 0.0012450102694856469,
      "clip_ratio/low_mean": 0.0011261576237302506,
      "clip_ratio/low_min": 5.616821727016941e-05,
      "clip_ratio/region_mean": 0.002371167851379141,
      "epoch": 0.0879197802005495,
      "grad_norm": 0.1208011582493782,
      "learning_rate": 1e-06,
      "loss": -0.0252,
      "step": 942
    },
    {
      "clip_ratio/high_max": 0.002788424084428698,
      "clip_ratio/high_mean": 0.0011727850323950406,
      "clip_ratio/low_mean": 0.001143006174970651,
      "clip_ratio/low_min": 4.4686891669698525e-05,
      "clip_ratio/region_mean": 0.0023157911928137764,
      "epoch": 0.08801311330055009,
      "grad_norm": 0.117280974984169,
      "learning_rate": 1e-06,
      "loss": -0.0059,
      "step": 943
    },
    {
      "clip_ratio/high_max": 0.0025379768921993673,
      "clip_ratio/high_mean": 0.001176511068479158,
      "clip_ratio/low_mean": 0.0014114357654761989,
      "clip_ratio/low_min": 0.0001698935620879638,
      "clip_ratio/region_mean": 0.0025879468230414204,
      "epoch": 0.08810644640055067,
      "grad_norm": 0.11293445527553558,
      "learning_rate": 1e-06,
      "loss": 0.0408,
      "step": 944
    },
    {
      "clip_ratio/high_max": 0.002642636922246311,
      "clip_ratio/high_mean": 0.0011102025346190203,
      "clip_ratio/low_mean": 0.0013499246779247187,
      "clip_ratio/low_min": 4.9862807827594224e-05,
      "clip_ratio/region_mean": 0.002460127157974057,
      "epoch": 0.08819977950055125,
      "grad_norm": 0.111526720225811,
      "learning_rate": 1e-06,
      "loss": -0.0146,
      "step": 945
    },
    {
      "clip_ratio/high_max": 0.0025249352293030825,
      "clip_ratio/high_mean": 0.0011404987053538207,
      "clip_ratio/low_mean": 0.0013171319587854668,
      "clip_ratio/low_min": 0.00013225787915871479,
      "clip_ratio/region_mean": 0.0024576306823291816,
      "epoch": 0.08829311260055184,
      "grad_norm": 0.12684796750545502,
      "learning_rate": 1e-06,
      "loss": 0.0618,
      "step": 946
    },
    {
      "clip_ratio/high_max": 0.0027552930696401745,
      "clip_ratio/high_mean": 0.0011042953919968568,
      "clip_ratio/low_mean": 0.0013201149085944053,
      "clip_ratio/low_min": 7.282524893525988e-05,
      "clip_ratio/region_mean": 0.0024244102896773256,
      "epoch": 0.08838644570055242,
      "grad_norm": 0.16028104722499847,
      "learning_rate": 1e-06,
      "loss": 0.0161,
      "step": 947
    },
    {
      "clip_ratio/high_max": 0.0028171928133815527,
      "clip_ratio/high_mean": 0.0011875251211677096,
      "clip_ratio/low_mean": 0.0014720461149408948,
      "clip_ratio/low_min": 0.0001122882540585124,
      "clip_ratio/region_mean": 0.0026595712333801202,
      "epoch": 0.088479778800553,
      "grad_norm": 0.10995173454284668,
      "learning_rate": 1e-06,
      "loss": 0.0237,
      "step": 948
    },
    {
      "clip_ratio/high_max": 0.0026523575506871566,
      "clip_ratio/high_mean": 0.0011990972016064916,
      "clip_ratio/low_mean": 0.001458189912227681,
      "clip_ratio/low_min": 0.0001184472203021869,
      "clip_ratio/region_mean": 0.002657287062902469,
      "epoch": 0.08857311190055359,
      "grad_norm": 0.12484999001026154,
      "learning_rate": 1e-06,
      "loss": 0.0599,
      "step": 949
    },
    {
      "clip_ratio/high_max": 0.001983057001780253,
      "clip_ratio/high_mean": 0.0009208516785292886,
      "clip_ratio/low_mean": 0.001373267423332436,
      "clip_ratio/low_min": 0.00018387226828053826,
      "clip_ratio/region_mean": 0.002294119054568,
      "epoch": 0.08866644500055416,
      "grad_norm": 0.1285124272108078,
      "learning_rate": 1e-06,
      "loss": 0.0732,
      "step": 950
    },
    {
      "clip_ratio/high_max": 0.003028925355465617,
      "clip_ratio/high_mean": 0.001133382087573409,
      "clip_ratio/low_mean": 0.0012056826199113857,
      "clip_ratio/low_min": 0.00014831778753432445,
      "clip_ratio/region_mean": 0.0023390646747429855,
      "epoch": 0.08875977810055474,
      "grad_norm": 0.12723256647586823,
      "learning_rate": 1e-06,
      "loss": 0.012,
      "step": 951
    },
    {
      "clip_ratio/high_max": 0.002673895469342824,
      "clip_ratio/high_mean": 0.0011443130606494378,
      "clip_ratio/low_mean": 0.0013673353532794863,
      "clip_ratio/low_min": 0.00014478527464234503,
      "clip_ratio/region_mean": 0.0025116483884630725,
      "epoch": 0.08885311120055533,
      "grad_norm": 0.11702253669500351,
      "learning_rate": 1e-06,
      "loss": 0.0214,
      "step": 952
    },
    {
      "clip_ratio/high_max": 0.0028391328232828528,
      "clip_ratio/high_mean": 0.0012477754789870232,
      "clip_ratio/low_mean": 0.0014510735854855739,
      "clip_ratio/low_min": 8.068501119851135e-05,
      "clip_ratio/region_mean": 0.002698849064472597,
      "epoch": 0.08894644430055591,
      "grad_norm": 0.1425998955965042,
      "learning_rate": 1e-06,
      "loss": 0.0343,
      "step": 953
    },
    {
      "clip_ratio/high_max": 0.002632967552926857,
      "clip_ratio/high_mean": 0.0012115016870666295,
      "clip_ratio/low_mean": 0.0010972554591717198,
      "clip_ratio/low_min": 8.112301929941168e-05,
      "clip_ratio/region_mean": 0.00230875717534218,
      "epoch": 0.0890397774005565,
      "grad_norm": 0.10918445140123367,
      "learning_rate": 1e-06,
      "loss": -0.0242,
      "step": 954
    },
    {
      "clip_ratio/high_max": 0.002498929898138158,
      "clip_ratio/high_mean": 0.0011500391774461605,
      "clip_ratio/low_mean": 0.001282649376662448,
      "clip_ratio/low_min": 3.1408855647896416e-05,
      "clip_ratio/region_mean": 0.002432688510452863,
      "epoch": 0.08913311050055708,
      "grad_norm": 0.12890565395355225,
      "learning_rate": 1e-06,
      "loss": -0.0057,
      "step": 955
    },
    {
      "clip_ratio/high_max": 0.002750506053416757,
      "clip_ratio/high_mean": 0.0011363541871105554,
      "clip_ratio/low_mean": 0.0013804125374008436,
      "clip_ratio/low_min": 5.9311465520295314e-05,
      "clip_ratio/region_mean": 0.0025167667408823036,
      "epoch": 0.08922644360055766,
      "grad_norm": 0.12218194454908371,
      "learning_rate": 1e-06,
      "loss": 0.051,
      "step": 956
    },
    {
      "clip_ratio/high_max": 0.0027811216059490107,
      "clip_ratio/high_mean": 0.0012290315025893506,
      "clip_ratio/low_mean": 0.001322785497904988,
      "clip_ratio/low_min": 0.0001337063604296418,
      "clip_ratio/region_mean": 0.0025518170004943386,
      "epoch": 0.08931977670055825,
      "grad_norm": 0.12276507169008255,
      "learning_rate": 1e-06,
      "loss": -0.0153,
      "step": 957
    },
    {
      "clip_ratio/high_max": 0.0029567002347903326,
      "clip_ratio/high_mean": 0.0011472656005935278,
      "clip_ratio/low_mean": 0.0013763130918960087,
      "clip_ratio/low_min": 0.00018796045060298638,
      "clip_ratio/region_mean": 0.0025235787106794305,
      "epoch": 0.08941310980055883,
      "grad_norm": 0.1302059441804886,
      "learning_rate": 1e-06,
      "loss": 0.0607,
      "step": 958
    },
    {
      "clip_ratio/high_max": 0.0024740926673985086,
      "clip_ratio/high_mean": 0.0010495662318135146,
      "clip_ratio/low_mean": 0.001175986317321076,
      "clip_ratio/low_min": 2.317389771633316e-05,
      "clip_ratio/region_mean": 0.002225552514573792,
      "epoch": 0.08950644290055941,
      "grad_norm": 0.10669755190610886,
      "learning_rate": 1e-06,
      "loss": 0.0302,
      "step": 959
    },
    {
      "clip_ratio/high_max": 0.00262820185162127,
      "clip_ratio/high_mean": 0.0011092682179878466,
      "clip_ratio/low_mean": 0.0014082114503253251,
      "clip_ratio/low_min": 1.8058364730677567e-05,
      "clip_ratio/region_mean": 0.0025174795810016803,
      "epoch": 0.08959977600056,
      "grad_norm": 0.10697541385889053,
      "learning_rate": 1e-06,
      "loss": 0.0138,
      "step": 960
    },
    {
      "clip_ratio/high_max": 0.0027912798468605615,
      "clip_ratio/high_mean": 0.0012065249211445916,
      "clip_ratio/low_mean": 0.001237166488863295,
      "clip_ratio/low_min": 6.789954750274774e-05,
      "clip_ratio/region_mean": 0.0024436914318357594,
      "epoch": 0.08969310910056058,
      "grad_norm": 0.11158915609121323,
      "learning_rate": 1e-06,
      "loss": 0.0033,
      "step": 961
    },
    {
      "clip_ratio/high_max": 0.0029689383736695163,
      "clip_ratio/high_mean": 0.0013222349189163651,
      "clip_ratio/low_mean": 0.0012593958817888051,
      "clip_ratio/low_min": 5.276702177070547e-05,
      "clip_ratio/region_mean": 0.0025816308334469795,
      "epoch": 0.08978644220056116,
      "grad_norm": 0.12170516699552536,
      "learning_rate": 1e-06,
      "loss": -0.0051,
      "step": 962
    },
    {
      "clip_ratio/high_max": 0.002842773770680651,
      "clip_ratio/high_mean": 0.001290344156586798,
      "clip_ratio/low_mean": 0.0012439305537554901,
      "clip_ratio/low_min": 8.368101862288313e-05,
      "clip_ratio/region_mean": 0.002534274732170161,
      "epoch": 0.08987977530056175,
      "grad_norm": 0.11743982881307602,
      "learning_rate": 1e-06,
      "loss": -0.0007,
      "step": 963
    },
    {
      "clip_ratio/high_max": 0.002831010155205149,
      "clip_ratio/high_mean": 0.0012584279393195175,
      "clip_ratio/low_mean": 0.0013923864098615013,
      "clip_ratio/low_min": 0.00012306672942941077,
      "clip_ratio/region_mean": 0.002650814363732934,
      "epoch": 0.08997310840056233,
      "grad_norm": 0.11645185202360153,
      "learning_rate": 1e-06,
      "loss": 0.0485,
      "step": 964
    },
    {
      "clip_ratio/high_max": 0.002493349886208307,
      "clip_ratio/high_mean": 0.0011607019587245304,
      "clip_ratio/low_mean": 0.0013702734213438816,
      "clip_ratio/low_min": 0.00011183765309397131,
      "clip_ratio/region_mean": 0.002530975347326603,
      "epoch": 0.09006644150056292,
      "grad_norm": 0.12098593264818192,
      "learning_rate": 1e-06,
      "loss": 0.0289,
      "step": 965
    },
    {
      "clip_ratio/high_max": 0.0025933179349522106,
      "clip_ratio/high_mean": 0.0011341691497364081,
      "clip_ratio/low_mean": 0.001301575106481323,
      "clip_ratio/low_min": 0.00018550738059275318,
      "clip_ratio/region_mean": 0.002435744318063371,
      "epoch": 0.0901597746005635,
      "grad_norm": 0.11580844223499298,
      "learning_rate": 1e-06,
      "loss": 0.0213,
      "step": 966
    },
    {
      "clip_ratio/high_max": 0.0025339243074995466,
      "clip_ratio/high_mean": 0.0010514588302612538,
      "clip_ratio/low_mean": 0.0013844799650541972,
      "clip_ratio/low_min": 0.00012641030025406508,
      "clip_ratio/region_mean": 0.002435938782582525,
      "epoch": 0.09025310770056408,
      "grad_norm": 0.11469963937997818,
      "learning_rate": 1e-06,
      "loss": 0.0287,
      "step": 967
    },
    {
      "clip_ratio/high_max": 0.0026930405510938726,
      "clip_ratio/high_mean": 0.001141781423939392,
      "clip_ratio/low_mean": 0.0014822542798356153,
      "clip_ratio/low_min": 0.00023987569147720933,
      "clip_ratio/region_mean": 0.002624035674671177,
      "epoch": 0.09034644080056467,
      "grad_norm": 0.12461795657873154,
      "learning_rate": 1e-06,
      "loss": 0.0139,
      "step": 968
    },
    {
      "clip_ratio/high_max": 0.0023683330746280262,
      "clip_ratio/high_mean": 0.0011057031997552258,
      "clip_ratio/low_mean": 0.0014790066234127153,
      "clip_ratio/low_min": 0.00011092543354607187,
      "clip_ratio/region_mean": 0.0025847098586382344,
      "epoch": 0.09043977390056525,
      "grad_norm": 0.16061313450336456,
      "learning_rate": 1e-06,
      "loss": 0.0515,
      "step": 969
    },
    {
      "clip_ratio/high_max": 0.0028513290744740516,
      "clip_ratio/high_mean": 0.001155625957835582,
      "clip_ratio/low_mean": 0.001233182741998462,
      "clip_ratio/low_min": 2.111361300194403e-05,
      "clip_ratio/region_mean": 0.0023888087598606944,
      "epoch": 0.09053310700056583,
      "grad_norm": 0.12160170823335648,
      "learning_rate": 1e-06,
      "loss": 0.0288,
      "step": 970
    },
    {
      "clip_ratio/high_max": 0.0026947276091959793,
      "clip_ratio/high_mean": 0.0012257949838385684,
      "clip_ratio/low_mean": 0.0014641191810369492,
      "clip_ratio/low_min": 0.00023094736206985544,
      "clip_ratio/region_mean": 0.0026899141812464222,
      "epoch": 0.09062644010056642,
      "grad_norm": 0.11060559749603271,
      "learning_rate": 1e-06,
      "loss": 0.0276,
      "step": 971
    },
    {
      "clip_ratio/high_max": 0.0031339486376964487,
      "clip_ratio/high_mean": 0.0012617829997907393,
      "clip_ratio/low_mean": 0.0012479627057473408,
      "clip_ratio/low_min": 0.0001483262240071781,
      "clip_ratio/region_mean": 0.0025097457400988787,
      "epoch": 0.090719773200567,
      "grad_norm": 0.12609367072582245,
      "learning_rate": 1e-06,
      "loss": -0.0391,
      "step": 972
    },
    {
      "clip_ratio/high_max": 0.0024247981345979497,
      "clip_ratio/high_mean": 0.0010785798913275357,
      "clip_ratio/low_mean": 0.001235927891684696,
      "clip_ratio/low_min": 1.2700670595222618e-05,
      "clip_ratio/region_mean": 0.0023145077866502106,
      "epoch": 0.09081310630056758,
      "grad_norm": 0.11527407914400101,
      "learning_rate": 1e-06,
      "loss": 0.0556,
      "step": 973
    },
    {
      "clip_ratio/high_max": 0.0026806148161995225,
      "clip_ratio/high_mean": 0.001233730454259785,
      "clip_ratio/low_mean": 0.001235786310644471,
      "clip_ratio/low_min": 0.00014530838598147966,
      "clip_ratio/region_mean": 0.002469516795827076,
      "epoch": 0.09090643940056817,
      "grad_norm": 0.12235342711210251,
      "learning_rate": 1e-06,
      "loss": 0.0086,
      "step": 974
    },
    {
      "clip_ratio/high_max": 0.0026093997003044933,
      "clip_ratio/high_mean": 0.0012172102760814596,
      "clip_ratio/low_mean": 0.0013219025240687188,
      "clip_ratio/low_min": 0.0001458983479096787,
      "clip_ratio/region_mean": 0.0025391128583578393,
      "epoch": 0.09099977250056875,
      "grad_norm": 0.1196315586566925,
      "learning_rate": 1e-06,
      "loss": 0.0337,
      "step": 975
    },
    {
      "clip_ratio/high_max": 0.002150374373741215,
      "clip_ratio/high_mean": 0.0010012361999542918,
      "clip_ratio/low_mean": 0.0015102154829946812,
      "clip_ratio/low_min": 0.00013764554660156136,
      "clip_ratio/region_mean": 0.0025114516756730154,
      "epoch": 0.09109310560056934,
      "grad_norm": 0.10887237638235092,
      "learning_rate": 1e-06,
      "loss": 0.0559,
      "step": 976
    },
    {
      "clip_ratio/high_max": 0.0022300366836134344,
      "clip_ratio/high_mean": 0.0009779280953807756,
      "clip_ratio/low_mean": 0.0013395770729403012,
      "clip_ratio/low_min": 0.00014393094170372933,
      "clip_ratio/region_mean": 0.0023175052338046953,
      "epoch": 0.09118643870056992,
      "grad_norm": 0.10701128095388412,
      "learning_rate": 1e-06,
      "loss": 0.0258,
      "step": 977
    },
    {
      "clip_ratio/high_max": 0.003646559787739534,
      "clip_ratio/high_mean": 0.0014837396593065932,
      "clip_ratio/low_mean": 0.0012861792092735413,
      "clip_ratio/low_min": 0.00010775718510558363,
      "clip_ratio/region_mean": 0.0027699188285623677,
      "epoch": 0.0912797718005705,
      "grad_norm": 0.11658689379692078,
      "learning_rate": 1e-06,
      "loss": 0.0034,
      "step": 978
    },
    {
      "clip_ratio/high_max": 0.0028070593762095086,
      "clip_ratio/high_mean": 0.0011891994799952954,
      "clip_ratio/low_mean": 0.0014283322416304145,
      "clip_ratio/low_min": 6.652608317381237e-05,
      "clip_ratio/region_mean": 0.0026175316888839006,
      "epoch": 0.09137310490057109,
      "grad_norm": 6.494184494018555,
      "learning_rate": 1e-06,
      "loss": 0.033,
      "step": 979
    },
    {
      "clip_ratio/high_max": 0.00276714709616499,
      "clip_ratio/high_mean": 0.0011871292226715013,
      "clip_ratio/low_mean": 0.0013687313330592588,
      "clip_ratio/low_min": 0.0002524561386962887,
      "clip_ratio/region_mean": 0.0025558605848345906,
      "epoch": 0.09146643800057166,
      "grad_norm": 0.11277235299348831,
      "learning_rate": 1e-06,
      "loss": 0.0335,
      "step": 980
    },
    {
      "clip_ratio/high_max": 0.002775694170850329,
      "clip_ratio/high_mean": 0.0012744389459840022,
      "clip_ratio/low_mean": 0.0012568929014378227,
      "clip_ratio/low_min": 3.302860750409309e-05,
      "clip_ratio/region_mean": 0.0025313318910775706,
      "epoch": 0.09155977110057224,
      "grad_norm": 0.10077925026416779,
      "learning_rate": 1e-06,
      "loss": 0.0004,
      "step": 981
    },
    {
      "clip_ratio/high_max": 0.0030001112245372497,
      "clip_ratio/high_mean": 0.0012147217676101718,
      "clip_ratio/low_mean": 0.0017618795081943972,
      "clip_ratio/low_min": 0.00010447325803397689,
      "clip_ratio/region_mean": 0.002976601383124944,
      "epoch": 0.09165310420057284,
      "grad_norm": 0.16938641667366028,
      "learning_rate": 1e-06,
      "loss": 0.0616,
      "step": 982
    },
    {
      "clip_ratio/high_max": 0.0026180426066275686,
      "clip_ratio/high_mean": 0.0011985322344116867,
      "clip_ratio/low_mean": 0.0014680899221275467,
      "clip_ratio/low_min": 6.433726957766339e-05,
      "clip_ratio/region_mean": 0.002666622218384873,
      "epoch": 0.09174643730057341,
      "grad_norm": 0.11450305581092834,
      "learning_rate": 1e-06,
      "loss": 0.0217,
      "step": 983
    },
    {
      "clip_ratio/high_max": 0.0023163015284808353,
      "clip_ratio/high_mean": 0.001109094126150012,
      "clip_ratio/low_mean": 0.0014027495199115947,
      "clip_ratio/low_min": 0.00015151396837609354,
      "clip_ratio/region_mean": 0.0025118436315096915,
      "epoch": 0.09183977040057399,
      "grad_norm": 0.12174700200557709,
      "learning_rate": 1e-06,
      "loss": 0.0199,
      "step": 984
    },
    {
      "clip_ratio/high_max": 0.002674655268492643,
      "clip_ratio/high_mean": 0.0010775317787192762,
      "clip_ratio/low_mean": 0.0015676867806178052,
      "clip_ratio/low_min": 0.00015655748848075746,
      "clip_ratio/region_mean": 0.0026452185556991026,
      "epoch": 0.09193310350057458,
      "grad_norm": 0.1115269809961319,
      "learning_rate": 1e-06,
      "loss": 0.0485,
      "step": 985
    },
    {
      "clip_ratio/high_max": 0.002467248596076388,
      "clip_ratio/high_mean": 0.001117363128287252,
      "clip_ratio/low_mean": 0.0011798180385085288,
      "clip_ratio/low_min": 5.335040623322129e-05,
      "clip_ratio/region_mean": 0.0022971812068135478,
      "epoch": 0.09202643660057516,
      "grad_norm": 0.10868289321660995,
      "learning_rate": 1e-06,
      "loss": 0.0017,
      "step": 986
    },
    {
      "clip_ratio/high_max": 0.002487644786015153,
      "clip_ratio/high_mean": 0.001049490732839331,
      "clip_ratio/low_mean": 0.0015151495681493543,
      "clip_ratio/low_min": 5.959920508757932e-05,
      "clip_ratio/region_mean": 0.0025646403009886853,
      "epoch": 0.09211976970057575,
      "grad_norm": 0.11784178763628006,
      "learning_rate": 1e-06,
      "loss": 0.0459,
      "step": 987
    },
    {
      "clip_ratio/high_max": 0.0027295782456349116,
      "clip_ratio/high_mean": 0.0011878538298333297,
      "clip_ratio/low_mean": 0.0014676620448881295,
      "clip_ratio/low_min": 5.278142816678155e-05,
      "clip_ratio/region_mean": 0.002655515883816406,
      "epoch": 0.09221310280057633,
      "grad_norm": 0.1076555848121643,
      "learning_rate": 1e-06,
      "loss": 0.0424,
      "step": 988
    },
    {
      "clip_ratio/high_max": 0.002901508785726037,
      "clip_ratio/high_mean": 0.0013105931066093035,
      "clip_ratio/low_mean": 0.0015459497699339408,
      "clip_ratio/low_min": 7.488697792723542e-05,
      "clip_ratio/region_mean": 0.0028565428874571808,
      "epoch": 0.09230643590057691,
      "grad_norm": 0.1147349551320076,
      "learning_rate": 1e-06,
      "loss": 0.0205,
      "step": 989
    },
    {
      "clip_ratio/high_max": 0.0025767290571820922,
      "clip_ratio/high_mean": 0.0010862722829187987,
      "clip_ratio/low_mean": 0.0013963995079393499,
      "clip_ratio/low_min": 0.0001059698329299863,
      "clip_ratio/region_mean": 0.00248267175629735,
      "epoch": 0.0923997690005775,
      "grad_norm": 0.11017246544361115,
      "learning_rate": 1e-06,
      "loss": 0.0361,
      "step": 990
    },
    {
      "clip_ratio/high_max": 0.0026134031286346726,
      "clip_ratio/high_mean": 0.00136757614382077,
      "clip_ratio/low_mean": 0.001320318890066119,
      "clip_ratio/low_min": 0.0001321766339970054,
      "clip_ratio/region_mean": 0.0026878950448008254,
      "epoch": 0.09249310210057808,
      "grad_norm": 0.12110080569982529,
      "learning_rate": 1e-06,
      "loss": 0.0236,
      "step": 991
    },
    {
      "clip_ratio/high_max": 0.0029008361852902453,
      "clip_ratio/high_mean": 0.0012395746580295963,
      "clip_ratio/low_mean": 0.001359284982754616,
      "clip_ratio/low_min": 0.00010582365393929649,
      "clip_ratio/region_mean": 0.002598859660793096,
      "epoch": 0.09258643520057866,
      "grad_norm": 0.12579837441444397,
      "learning_rate": 1e-06,
      "loss": 0.0363,
      "step": 992
    },
    {
      "clip_ratio/high_max": 0.003535606461809948,
      "clip_ratio/high_mean": 0.0014662159810541198,
      "clip_ratio/low_mean": 0.0014731299452250823,
      "clip_ratio/low_min": 0.00014710106916027144,
      "clip_ratio/region_mean": 0.002939345868071541,
      "epoch": 0.09267976830057925,
      "grad_norm": 0.14476199448108673,
      "learning_rate": 1e-06,
      "loss": -0.0148,
      "step": 993
    },
    {
      "clip_ratio/high_max": 0.002774726308416575,
      "clip_ratio/high_mean": 0.0012344773749646265,
      "clip_ratio/low_mean": 0.001647737153689377,
      "clip_ratio/low_min": 0.00011739384763131966,
      "clip_ratio/region_mean": 0.0028822145686717704,
      "epoch": 0.09277310140057983,
      "grad_norm": 0.11765889823436737,
      "learning_rate": 1e-06,
      "loss": 0.0779,
      "step": 994
    },
    {
      "clip_ratio/high_max": 0.003133786449325271,
      "clip_ratio/high_mean": 0.001201414084789576,
      "clip_ratio/low_mean": 0.0014623204842791893,
      "clip_ratio/low_min": 7.799505237926496e-05,
      "clip_ratio/region_mean": 0.002663734558154829,
      "epoch": 0.09286643450058042,
      "grad_norm": 0.12022411078214645,
      "learning_rate": 1e-06,
      "loss": 0.0138,
      "step": 995
    },
    {
      "clip_ratio/high_max": 0.0030907098116585985,
      "clip_ratio/high_mean": 0.0012947207214892842,
      "clip_ratio/low_mean": 0.0014917460557626327,
      "clip_ratio/low_min": 0.00011814427671197336,
      "clip_ratio/region_mean": 0.0027864666990353726,
      "epoch": 0.092959767600581,
      "grad_norm": 0.1165364682674408,
      "learning_rate": 1e-06,
      "loss": -0.0012,
      "step": 996
    },
    {
      "clip_ratio/high_max": 0.003275159055192489,
      "clip_ratio/high_mean": 0.0012671573895204347,
      "clip_ratio/low_mean": 0.0017015972880471963,
      "clip_ratio/low_min": 0.0001549023982079234,
      "clip_ratio/region_mean": 0.002968754735775292,
      "epoch": 0.09305310070058158,
      "grad_norm": 0.10712571442127228,
      "learning_rate": 1e-06,
      "loss": 0.0455,
      "step": 997
    },
    {
      "clip_ratio/high_max": 0.0024871829300536774,
      "clip_ratio/high_mean": 0.001137826408012188,
      "clip_ratio/low_mean": 0.0016198411758523434,
      "clip_ratio/low_min": 0.0001743524244375294,
      "clip_ratio/region_mean": 0.002757667549303733,
      "epoch": 0.09314643380058217,
      "grad_norm": 0.11063006520271301,
      "learning_rate": 1e-06,
      "loss": 0.0325,
      "step": 998
    },
    {
      "clip_ratio/high_max": 0.0027525357509148307,
      "clip_ratio/high_mean": 0.0011536253332451452,
      "clip_ratio/low_mean": 0.0017016248202708084,
      "clip_ratio/low_min": 0.0002547297553974204,
      "clip_ratio/region_mean": 0.00285525007348042,
      "epoch": 0.09323976690058275,
      "grad_norm": 0.1114213764667511,
      "learning_rate": 1e-06,
      "loss": 0.0564,
      "step": 999
    },
    {
      "clip_ratio/high_max": 0.002417416326352395,
      "clip_ratio/high_mean": 0.001042430028974195,
      "clip_ratio/low_mean": 0.0017356326097797137,
      "clip_ratio/low_min": 0.00018953188828163547,
      "clip_ratio/region_mean": 0.002778062662400771,
      "epoch": 0.09333310000058333,
      "grad_norm": 0.14488564431667328,
      "learning_rate": 1e-06,
      "loss": 0.0964,
      "step": 1000
    },
    {
      "clip_ratio/high_max": 0.0028707007149932906,
      "clip_ratio/high_mean": 0.001260689619812183,
      "clip_ratio/low_mean": 0.0014072748344915453,
      "clip_ratio/low_min": 8.791204891167581e-05,
      "clip_ratio/region_mean": 0.0026679644361138344,
      "epoch": 0.09342643310058392,
      "grad_norm": 0.12729983031749725,
      "learning_rate": 1e-06,
      "loss": -0.0002,
      "step": 1001
    },
    {
      "clip_ratio/high_max": 0.0029966982765472494,
      "clip_ratio/high_mean": 0.001215299365867395,
      "clip_ratio/low_mean": 0.001570864817040274,
      "clip_ratio/low_min": 0.00011974100380029995,
      "clip_ratio/region_mean": 0.0027861642302013934,
      "epoch": 0.0935197662005845,
      "grad_norm": 0.11563847959041595,
      "learning_rate": 1e-06,
      "loss": 0.0143,
      "step": 1002
    },
    {
      "clip_ratio/high_max": 0.002537423377361847,
      "clip_ratio/high_mean": 0.0010740548132162075,
      "clip_ratio/low_mean": 0.0016666319497744553,
      "clip_ratio/low_min": 0.00011701982657541521,
      "clip_ratio/region_mean": 0.0027406867520767264,
      "epoch": 0.09361309930058508,
      "grad_norm": 0.11845163255929947,
      "learning_rate": 1e-06,
      "loss": 0.0849,
      "step": 1003
    },
    {
      "clip_ratio/high_max": 0.002433712601487059,
      "clip_ratio/high_mean": 0.0010959279261442134,
      "clip_ratio/low_mean": 0.0014119522929831874,
      "clip_ratio/low_min": 6.466150807682425e-05,
      "clip_ratio/region_mean": 0.0025078802354983054,
      "epoch": 0.09370643240058567,
      "grad_norm": 0.14227983355522156,
      "learning_rate": 1e-06,
      "loss": 0.0768,
      "step": 1004
    },
    {
      "clip_ratio/high_max": 0.003072989289648831,
      "clip_ratio/high_mean": 0.0014026462522451766,
      "clip_ratio/low_mean": 0.0017797433320083655,
      "clip_ratio/low_min": 0.00019703758243849734,
      "clip_ratio/region_mean": 0.0031823895551497117,
      "epoch": 0.09379976550058625,
      "grad_norm": 0.1346999555826187,
      "learning_rate": 1e-06,
      "loss": 0.011,
      "step": 1005
    },
    {
      "clip_ratio/high_max": 0.0030411221814574674,
      "clip_ratio/high_mean": 0.001289644238568144,
      "clip_ratio/low_mean": 0.001281272227060981,
      "clip_ratio/low_min": 0.00013580263657786418,
      "clip_ratio/region_mean": 0.002570916447439231,
      "epoch": 0.09389309860058684,
      "grad_norm": 0.10416793078184128,
      "learning_rate": 1e-06,
      "loss": 0.0025,
      "step": 1006
    },
    {
      "clip_ratio/high_max": 0.002908468020905275,
      "clip_ratio/high_mean": 0.0012044460036122473,
      "clip_ratio/low_mean": 0.0013638799682667013,
      "clip_ratio/low_min": 0.00014062000991543755,
      "clip_ratio/region_mean": 0.0025683260246296413,
      "epoch": 0.09398643170058742,
      "grad_norm": 0.10859540849924088,
      "learning_rate": 1e-06,
      "loss": 0.046,
      "step": 1007
    },
    {
      "clip_ratio/high_max": 0.0029799915937473997,
      "clip_ratio/high_mean": 0.0012231259788677562,
      "clip_ratio/low_mean": 0.0013812620854878332,
      "clip_ratio/low_min": 1.975035593204666e-05,
      "clip_ratio/region_mean": 0.0026043879915960133,
      "epoch": 0.094079764800588,
      "grad_norm": 0.11374291032552719,
      "learning_rate": 1e-06,
      "loss": 0.0328,
      "step": 1008
    },
    {
      "clip_ratio/high_max": 0.002981277779326774,
      "clip_ratio/high_mean": 0.0012567323392431717,
      "clip_ratio/low_mean": 0.0013621409343613777,
      "clip_ratio/low_min": 9.466828487347811e-05,
      "clip_ratio/region_mean": 0.002618873208120931,
      "epoch": 0.09417309790058859,
      "grad_norm": 0.11963991075754166,
      "learning_rate": 1e-06,
      "loss": 0.037,
      "step": 1009
    },
    {
      "clip_ratio/high_max": 0.002924138847447466,
      "clip_ratio/high_mean": 0.0011684025303111412,
      "clip_ratio/low_mean": 0.0012690034182014642,
      "clip_ratio/low_min": 9.931239037541673e-05,
      "clip_ratio/region_mean": 0.002437405928503722,
      "epoch": 0.09426643100058917,
      "grad_norm": 0.1102556437253952,
      "learning_rate": 1e-06,
      "loss": 0.0162,
      "step": 1010
    },
    {
      "clip_ratio/high_max": 0.003490545117529109,
      "clip_ratio/high_mean": 0.001336478475423064,
      "clip_ratio/low_mean": 0.0014367848270921968,
      "clip_ratio/low_min": 3.6649937101174146e-05,
      "clip_ratio/region_mean": 0.002773263258859515,
      "epoch": 0.09435976410058974,
      "grad_norm": 0.10565842688083649,
      "learning_rate": 1e-06,
      "loss": 0.0118,
      "step": 1011
    },
    {
      "clip_ratio/high_max": 0.0024250521819340065,
      "clip_ratio/high_mean": 0.0011224260142626008,
      "clip_ratio/low_mean": 0.0015114995840121992,
      "clip_ratio/low_min": 0.0002255729923490435,
      "clip_ratio/region_mean": 0.002633925607369747,
      "epoch": 0.09445309720059034,
      "grad_norm": 0.11838560551404953,
      "learning_rate": 1e-06,
      "loss": 0.0583,
      "step": 1012
    },
    {
      "clip_ratio/high_max": 0.0032207021431531757,
      "clip_ratio/high_mean": 0.0014960345069994219,
      "clip_ratio/low_mean": 0.0013963352430437226,
      "clip_ratio/low_min": 0.00011786611321440432,
      "clip_ratio/region_mean": 0.002892369797336869,
      "epoch": 0.09454643030059091,
      "grad_norm": 0.1224701777100563,
      "learning_rate": 1e-06,
      "loss": -0.0047,
      "step": 1013
    },
    {
      "clip_ratio/high_max": 0.003352995991008356,
      "clip_ratio/high_mean": 0.001287487013541977,
      "clip_ratio/low_mean": 0.0016660987821524031,
      "clip_ratio/low_min": 8.061644257395528e-05,
      "clip_ratio/region_mean": 0.0029535857611335814,
      "epoch": 0.09463976340059149,
      "grad_norm": 0.35519301891326904,
      "learning_rate": 1e-06,
      "loss": 0.0438,
      "step": 1014
    },
    {
      "clip_ratio/high_max": 0.0029679783692699857,
      "clip_ratio/high_mean": 0.0012489094842749182,
      "clip_ratio/low_mean": 0.0015583560780214611,
      "clip_ratio/low_min": 9.543924352328759e-05,
      "clip_ratio/region_mean": 0.0028072655622963794,
      "epoch": 0.09473309650059208,
      "grad_norm": 0.11893009394407272,
      "learning_rate": 1e-06,
      "loss": 0.0285,
      "step": 1015
    },
    {
      "clip_ratio/high_max": 0.002471135536325164,
      "clip_ratio/high_mean": 0.0011829351933556609,
      "clip_ratio/low_mean": 0.001563579364301404,
      "clip_ratio/low_min": 0.00017570037471159594,
      "clip_ratio/region_mean": 0.002746514554019086,
      "epoch": 0.09482642960059266,
      "grad_norm": 0.11624384671449661,
      "learning_rate": 1e-06,
      "loss": 0.0412,
      "step": 1016
    },
    {
      "clip_ratio/high_max": 0.0030758403736399487,
      "clip_ratio/high_mean": 0.0012291601997276302,
      "clip_ratio/low_mean": 0.0015185346273938194,
      "clip_ratio/low_min": 0.00016362998030672316,
      "clip_ratio/region_mean": 0.002747694874415174,
      "epoch": 0.09491976270059325,
      "grad_norm": 0.11920436471700668,
      "learning_rate": 1e-06,
      "loss": 0.0543,
      "step": 1017
    },
    {
      "clip_ratio/high_max": 0.0025371479569002986,
      "clip_ratio/high_mean": 0.001281979424675228,
      "clip_ratio/low_mean": 0.0014869609440211207,
      "clip_ratio/low_min": 0.00013216199113230687,
      "clip_ratio/region_mean": 0.0027689404087141156,
      "epoch": 0.09501309580059383,
      "grad_norm": 0.11914224177598953,
      "learning_rate": 1e-06,
      "loss": 0.0087,
      "step": 1018
    },
    {
      "clip_ratio/high_max": 0.0031767375403433107,
      "clip_ratio/high_mean": 0.0014190832698659506,
      "clip_ratio/low_mean": 0.001348505960777402,
      "clip_ratio/low_min": 7.851443388062762e-05,
      "clip_ratio/region_mean": 0.0027675891542457975,
      "epoch": 0.09510642890059441,
      "grad_norm": 0.10922086983919144,
      "learning_rate": 1e-06,
      "loss": -0.0615,
      "step": 1019
    },
    {
      "clip_ratio/high_max": 0.0029020875299465843,
      "clip_ratio/high_mean": 0.0014033407896931749,
      "clip_ratio/low_mean": 0.0012925723640364595,
      "clip_ratio/low_min": 0.00011625457773334347,
      "clip_ratio/region_mean": 0.0026959132592310198,
      "epoch": 0.095199762000595,
      "grad_norm": 0.11653022468090057,
      "learning_rate": 1e-06,
      "loss": -0.0014,
      "step": 1020
    },
    {
      "clip_ratio/high_max": 0.0028071497690689284,
      "clip_ratio/high_mean": 0.0012579893627844285,
      "clip_ratio/low_mean": 0.0013232964010967407,
      "clip_ratio/low_min": 0.0001721415319480002,
      "clip_ratio/region_mean": 0.0025812857638811693,
      "epoch": 0.09529309510059558,
      "grad_norm": 0.11123798787593842,
      "learning_rate": 1e-06,
      "loss": 0.0155,
      "step": 1021
    },
    {
      "clip_ratio/high_max": 0.0029149906258680858,
      "clip_ratio/high_mean": 0.0011823010245279875,
      "clip_ratio/low_mean": 0.0017846755290520377,
      "clip_ratio/low_min": 0.00018575931153463898,
      "clip_ratio/region_mean": 0.0029669764699065126,
      "epoch": 0.09538642820059616,
      "grad_norm": 0.11519214510917664,
      "learning_rate": 1e-06,
      "loss": 0.0355,
      "step": 1022
    },
    {
      "clip_ratio/high_max": 0.0028542855216073804,
      "clip_ratio/high_mean": 0.0011931294939131476,
      "clip_ratio/low_mean": 0.0014672696561319754,
      "clip_ratio/low_min": 0.00017124263922596583,
      "clip_ratio/region_mean": 0.0026603991937008686,
      "epoch": 0.09547976130059675,
      "grad_norm": 0.12846031785011292,
      "learning_rate": 1e-06,
      "loss": 0.0436,
      "step": 1023
    },
    {
      "clip_ratio/high_max": 0.002703148595173843,
      "clip_ratio/high_mean": 0.0012149533249612432,
      "clip_ratio/low_mean": 0.001366138178127585,
      "clip_ratio/low_min": 0.00016187837354664225,
      "clip_ratio/region_mean": 0.0025810914958128706,
      "epoch": 0.09557309440059733,
      "grad_norm": 0.10476890206336975,
      "learning_rate": 1e-06,
      "loss": 0.0124,
      "step": 1024
    },
    {
      "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": 0.010105678013392905,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4085.0,
      "completions/mean_length": 607.3308715820312,
      "completions/mean_terminated_length": 571.7156372070312,
      "completions/min_length": 5.0,
      "completions/min_terminated_length": 5.0,
      "epoch": 0.09566642750059791,
      "grad_norm": 0.11734706908464432,
      "learning_rate": 1e-06,
      "loss": 0.0358,
      "num_tokens": 728577627.0,
      "reward": 0.6058088541030884,
      "reward_std": 0.18527096509933472,
      "rewards/simpleverify_reward/mean": 0.6058087944984436,
      "rewards/simpleverify_reward/std": 0.488678514957428,
      "step": 1025
    },
    {
      "clip_ratio/high_max": 0.002203545438533183,
      "clip_ratio/high_mean": 0.0008861995393090183,
      "clip_ratio/low_mean": 0.0004953558945999248,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001381555455736816,
      "epoch": 0.0957597606005985,
      "grad_norm": 0.11628786474466324,
      "learning_rate": 1e-06,
      "loss": 0.0061,
      "step": 1026
    },
    {
      "clip_ratio/high_max": 0.0019790424448729027,
      "clip_ratio/high_mean": 0.0008057031436692341,
      "clip_ratio/low_mean": 0.000578062220938591,
      "clip_ratio/low_min": 2.3079763195710257e-05,
      "clip_ratio/region_mean": 0.0013837653641530778,
      "epoch": 0.09585309370059908,
      "grad_norm": 0.11739090830087662,
      "learning_rate": 1e-06,
      "loss": 0.0209,
      "step": 1027
    },
    {
      "clip_ratio/high_max": 0.002154977591999341,
      "clip_ratio/high_mean": 0.000874872150234296,
      "clip_ratio/low_mean": 0.0006546993681695312,
      "clip_ratio/low_min": 2.7606633011600934e-05,
      "clip_ratio/region_mean": 0.0015295714983949438,
      "epoch": 0.09594642680059967,
      "grad_norm": 0.11764016002416611,
      "learning_rate": 1e-06,
      "loss": 0.0304,
      "step": 1028
    },
    {
      "clip_ratio/high_max": 0.0021571518445853144,
      "clip_ratio/high_mean": 0.0009240433573722839,
      "clip_ratio/low_mean": 0.0005817247983941343,
      "clip_ratio/low_min": 4.2850915633607656e-05,
      "clip_ratio/region_mean": 0.0015057681739563122,
      "epoch": 0.09603975990060025,
      "grad_norm": 0.12174678593873978,
      "learning_rate": 1e-06,
      "loss": -0.007,
      "step": 1029
    },
    {
      "clip_ratio/high_max": 0.0024027827821555547,
      "clip_ratio/high_mean": 0.000912268107640557,
      "clip_ratio/low_mean": 0.0007820751652616309,
      "clip_ratio/low_min": 9.473861882725032e-05,
      "clip_ratio/region_mean": 0.0016943432347034104,
      "epoch": 0.09613309300060083,
      "grad_norm": 0.11720043420791626,
      "learning_rate": 1e-06,
      "loss": 0.0351,
      "step": 1030
    },
    {
      "clip_ratio/high_max": 0.00186784199468093,
      "clip_ratio/high_mean": 0.0008012004655029159,
      "clip_ratio/low_mean": 0.0007481279699277366,
      "clip_ratio/low_min": 3.0222437999327667e-05,
      "clip_ratio/region_mean": 0.0015493284117837902,
      "epoch": 0.09622642610060142,
      "grad_norm": 0.18158195912837982,
      "learning_rate": 1e-06,
      "loss": 0.0453,
      "step": 1031
    },
    {
      "clip_ratio/high_max": 0.002229470032034442,
      "clip_ratio/high_mean": 0.0008827615674817935,
      "clip_ratio/low_mean": 0.0009120985141635174,
      "clip_ratio/low_min": 8.200300544558559e-05,
      "clip_ratio/region_mean": 0.0017948600579984486,
      "epoch": 0.096319759200602,
      "grad_norm": 0.11961593478918076,
      "learning_rate": 1e-06,
      "loss": 0.0428,
      "step": 1032
    },
    {
      "clip_ratio/high_max": 0.001949259705725126,
      "clip_ratio/high_mean": 0.0009293647708545905,
      "clip_ratio/low_mean": 0.0006682530784019036,
      "clip_ratio/low_min": 8.57691793498816e-06,
      "clip_ratio/region_mean": 0.0015976178765413351,
      "epoch": 0.09641309230060258,
      "grad_norm": 0.11553668975830078,
      "learning_rate": 1e-06,
      "loss": -0.0225,
      "step": 1033
    },
    {
      "clip_ratio/high_max": 0.0020059601301909424,
      "clip_ratio/high_mean": 0.000866851016326109,
      "clip_ratio/low_mean": 0.0007999814642971614,
      "clip_ratio/low_min": 6.335255329759093e-05,
      "clip_ratio/region_mean": 0.0016668324824422598,
      "epoch": 0.09650642540060317,
      "grad_norm": 0.11509881168603897,
      "learning_rate": 1e-06,
      "loss": 0.0288,
      "step": 1034
    },
    {
      "clip_ratio/high_max": 0.002290750271640718,
      "clip_ratio/high_mean": 0.0010511786113056587,
      "clip_ratio/low_mean": 0.0007876292620494496,
      "clip_ratio/low_min": 4.162153345532715e-05,
      "clip_ratio/region_mean": 0.0018388078351563308,
      "epoch": 0.09659975850060375,
      "grad_norm": 0.11182078719139099,
      "learning_rate": 1e-06,
      "loss": -0.0183,
      "step": 1035
    },
    {
      "clip_ratio/high_max": 0.0023164551821537316,
      "clip_ratio/high_mean": 0.0009914912152453326,
      "clip_ratio/low_mean": 0.000819183254861855,
      "clip_ratio/low_min": 3.7730063013441395e-05,
      "clip_ratio/region_mean": 0.0018106744610122405,
      "epoch": 0.09669309160060433,
      "grad_norm": 0.12165460735559464,
      "learning_rate": 1e-06,
      "loss": 0.0096,
      "step": 1036
    },
    {
      "clip_ratio/high_max": 0.0024439232729491778,
      "clip_ratio/high_mean": 0.0009857240274868673,
      "clip_ratio/low_mean": 0.0007959898302942747,
      "clip_ratio/low_min": 3.829734396276763e-05,
      "clip_ratio/region_mean": 0.0017817138141253963,
      "epoch": 0.09678642470060492,
      "grad_norm": 0.11259244382381439,
      "learning_rate": 1e-06,
      "loss": -0.0017,
      "step": 1037
    },
    {
      "clip_ratio/high_max": 0.0019664743886096403,
      "clip_ratio/high_mean": 0.0007329306408792036,
      "clip_ratio/low_mean": 0.0008232615400629584,
      "clip_ratio/low_min": 5.787256031908328e-05,
      "clip_ratio/region_mean": 0.0015561921827611513,
      "epoch": 0.0968797578006055,
      "grad_norm": 0.1141917034983635,
      "learning_rate": 1e-06,
      "loss": 0.0429,
      "step": 1038
    },
    {
      "clip_ratio/high_max": 0.0023949110400280915,
      "clip_ratio/high_mean": 0.0009441434631298762,
      "clip_ratio/low_mean": 0.0008892881432984723,
      "clip_ratio/low_min": 6.639495586568955e-05,
      "clip_ratio/region_mean": 0.0018334316191612743,
      "epoch": 0.09697309090060609,
      "grad_norm": 0.10631438344717026,
      "learning_rate": 1e-06,
      "loss": -0.0005,
      "step": 1039
    },
    {
      "clip_ratio/high_max": 0.0028446987307688687,
      "clip_ratio/high_mean": 0.0011105857956863474,
      "clip_ratio/low_mean": 0.001017337981465971,
      "clip_ratio/low_min": 0.00010017254317062907,
      "clip_ratio/region_mean": 0.0021279238135321066,
      "epoch": 0.09706642400060667,
      "grad_norm": 0.11398673057556152,
      "learning_rate": 1e-06,
      "loss": -0.0016,
      "step": 1040
    },
    {
      "clip_ratio/high_max": 0.0024882530415197834,
      "clip_ratio/high_mean": 0.0009914970560203074,
      "clip_ratio/low_mean": 0.0008791560558165656,
      "clip_ratio/low_min": 4.821873881155625e-05,
      "clip_ratio/region_mean": 0.0018706530900090002,
      "epoch": 0.09715975710060724,
      "grad_norm": 0.10839464515447617,
      "learning_rate": 1e-06,
      "loss": 0.0197,
      "step": 1041
    },
    {
      "clip_ratio/high_max": 0.002378000812313985,
      "clip_ratio/high_mean": 0.0010027813077613246,
      "clip_ratio/low_mean": 0.0009191029876092216,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001921884271723684,
      "epoch": 0.09725309020060784,
      "grad_norm": 0.11780335754156113,
      "learning_rate": 1e-06,
      "loss": -0.013,
      "step": 1042
    },
    {
      "clip_ratio/high_max": 0.002430081120110117,
      "clip_ratio/high_mean": 0.0009942003889591433,
      "clip_ratio/low_mean": 0.0009172251120617148,
      "clip_ratio/low_min": 6.252175626286771e-05,
      "clip_ratio/region_mean": 0.0019114254755550064,
      "epoch": 0.09734642330060841,
      "grad_norm": 0.11445480585098267,
      "learning_rate": 1e-06,
      "loss": 0.0146,
      "step": 1043
    },
    {
      "clip_ratio/high_max": 0.001884766861621756,
      "clip_ratio/high_mean": 0.0008490565087413415,
      "clip_ratio/low_mean": 0.0010101776260853512,
      "clip_ratio/low_min": 0.0001224055959028192,
      "clip_ratio/region_mean": 0.001859234158473555,
      "epoch": 0.09743975640060899,
      "grad_norm": 0.12587323784828186,
      "learning_rate": 1e-06,
      "loss": 0.0129,
      "step": 1044
    },
    {
      "clip_ratio/high_max": 0.002351960061787395,
      "clip_ratio/high_mean": 0.0009211548076564213,
      "clip_ratio/low_mean": 0.0011607014275796246,
      "clip_ratio/low_min": 0.000128675425912661,
      "clip_ratio/region_mean": 0.0020818562334170565,
      "epoch": 0.09753308950060958,
      "grad_norm": 0.11390280723571777,
      "learning_rate": 1e-06,
      "loss": 0.0178,
      "step": 1045
    },
    {
      "clip_ratio/high_max": 0.0020965763214917388,
      "clip_ratio/high_mean": 0.0008331206827278947,
      "clip_ratio/low_mean": 0.0010927095499937423,
      "clip_ratio/low_min": 4.396080930746393e-05,
      "clip_ratio/region_mean": 0.0019258302127127536,
      "epoch": 0.09762642260061016,
      "grad_norm": 0.12111048400402069,
      "learning_rate": 1e-06,
      "loss": 0.0533,
      "step": 1046
    },
    {
      "clip_ratio/high_max": 0.0024366968573303893,
      "clip_ratio/high_mean": 0.001031734680509544,
      "clip_ratio/low_mean": 0.0011139175039716065,
      "clip_ratio/low_min": 4.6712941184523515e-05,
      "clip_ratio/region_mean": 0.0021456522517837584,
      "epoch": 0.09771975570061076,
      "grad_norm": 0.12409225106239319,
      "learning_rate": 1e-06,
      "loss": -0.0302,
      "step": 1047
    },
    {
      "clip_ratio/high_max": 0.002305422880453989,
      "clip_ratio/high_mean": 0.0009752197820489528,
      "clip_ratio/low_mean": 0.0011876127846335294,
      "clip_ratio/low_min": 0.0001382908067171229,
      "clip_ratio/region_mean": 0.0021628325121128,
      "epoch": 0.09781308880061133,
      "grad_norm": 0.12369311600923538,
      "learning_rate": 1e-06,
      "loss": 0.0322,
      "step": 1048
    },
    {
      "clip_ratio/high_max": 0.0024026472310652025,
      "clip_ratio/high_mean": 0.0009585549669282045,
      "clip_ratio/low_mean": 0.0011513419631228317,
      "clip_ratio/low_min": 5.141630845173495e-05,
      "clip_ratio/region_mean": 0.0021098969082231633,
      "epoch": 0.09790642190061191,
      "grad_norm": 0.1379605531692505,
      "learning_rate": 1e-06,
      "loss": 0.0039,
      "step": 1049
    },
    {
      "clip_ratio/high_max": 0.0024780290223134216,
      "clip_ratio/high_mean": 0.0009574517334840493,
      "clip_ratio/low_mean": 0.0009234890603693202,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0018809408429660834,
      "epoch": 0.0979997550006125,
      "grad_norm": 0.10189446061849594,
      "learning_rate": 1e-06,
      "loss": -0.0099,
      "step": 1050
    },
    {
      "clip_ratio/high_max": 0.0024892426663427614,
      "clip_ratio/high_mean": 0.0010142828468815424,
      "clip_ratio/low_mean": 0.0011273604941379745,
      "clip_ratio/low_min": 9.914198017213494e-05,
      "clip_ratio/region_mean": 0.002141643373761326,
      "epoch": 0.09809308810061308,
      "grad_norm": 0.1702851802110672,
      "learning_rate": 1e-06,
      "loss": 0.0582,
      "step": 1051
    },
    {
      "clip_ratio/high_max": 0.0021126051506143995,
      "clip_ratio/high_mean": 0.0009414844571438152,
      "clip_ratio/low_mean": 0.001179920824142755,
      "clip_ratio/low_min": 5.6766763009363785e-05,
      "clip_ratio/region_mean": 0.0021214052831055596,
      "epoch": 0.09818642120061366,
      "grad_norm": 0.13180114328861237,
      "learning_rate": 1e-06,
      "loss": 0.0283,
      "step": 1052
    },
    {
      "clip_ratio/high_max": 0.0025132970768027008,
      "clip_ratio/high_mean": 0.0011431561506469734,
      "clip_ratio/low_mean": 0.0012076263828930678,
      "clip_ratio/low_min": 5.9605768910842016e-05,
      "clip_ratio/region_mean": 0.0023507824807893485,
      "epoch": 0.09827975430061425,
      "grad_norm": 0.13643735647201538,
      "learning_rate": 1e-06,
      "loss": 0.0461,
      "step": 1053
    },
    {
      "clip_ratio/high_max": 0.002515937536372803,
      "clip_ratio/high_mean": 0.0011588189663598314,
      "clip_ratio/low_mean": 0.001067479237462976,
      "clip_ratio/low_min": 8.296840314869769e-05,
      "clip_ratio/region_mean": 0.002226298143796157,
      "epoch": 0.09837308740061483,
      "grad_norm": 0.11702553182840347,
      "learning_rate": 1e-06,
      "loss": -0.0292,
      "step": 1054
    },
    {
      "clip_ratio/high_max": 0.0023767808961565606,
      "clip_ratio/high_mean": 0.0010425375839986373,
      "clip_ratio/low_mean": 0.0010662447875802172,
      "clip_ratio/low_min": 7.189812276919838e-05,
      "clip_ratio/region_mean": 0.002108782373397844,
      "epoch": 0.09846642050061541,
      "grad_norm": 0.11354535818099976,
      "learning_rate": 1e-06,
      "loss": -0.0198,
      "step": 1055
    },
    {
      "clip_ratio/high_max": 0.002434593850921374,
      "clip_ratio/high_mean": 0.0009861520084086806,
      "clip_ratio/low_mean": 0.001331477120402269,
      "clip_ratio/low_min": 0.000134748039272381,
      "clip_ratio/region_mean": 0.0023176291069830768,
      "epoch": 0.098559753600616,
      "grad_norm": 0.11405406892299652,
      "learning_rate": 1e-06,
      "loss": 0.0327,
      "step": 1056
    },
    {
      "clip_ratio/high_max": 0.0022987370612099767,
      "clip_ratio/high_mean": 0.0009943765180651098,
      "clip_ratio/low_mean": 0.0013056318202870898,
      "clip_ratio/low_min": 0.00010054455833596876,
      "clip_ratio/region_mean": 0.0023000083238002844,
      "epoch": 0.09865308670061658,
      "grad_norm": 0.11773454397916794,
      "learning_rate": 1e-06,
      "loss": 0.0211,
      "step": 1057
    },
    {
      "clip_ratio/high_max": 0.0024161640540114604,
      "clip_ratio/high_mean": 0.0009474781018070644,
      "clip_ratio/low_mean": 0.001187206349641201,
      "clip_ratio/low_min": 5.713464997825213e-05,
      "clip_ratio/region_mean": 0.002134684422344435,
      "epoch": 0.09874641980061717,
      "grad_norm": 0.10381419956684113,
      "learning_rate": 1e-06,
      "loss": 0.0322,
      "step": 1058
    },
    {
      "clip_ratio/high_max": 0.002561836015956942,
      "clip_ratio/high_mean": 0.001045305689331144,
      "clip_ratio/low_mean": 0.0010182710029766895,
      "clip_ratio/low_min": 6.0208321883692406e-05,
      "clip_ratio/region_mean": 0.002063576685031876,
      "epoch": 0.09883975290061775,
      "grad_norm": 0.13515760004520416,
      "learning_rate": 1e-06,
      "loss": 0.0179,
      "step": 1059
    },
    {
      "clip_ratio/high_max": 0.002278441490489058,
      "clip_ratio/high_mean": 0.0010177104068134213,
      "clip_ratio/low_mean": 0.001230415622558212,
      "clip_ratio/low_min": 0.00015775989413668867,
      "clip_ratio/region_mean": 0.0022481260166387074,
      "epoch": 0.09893308600061833,
      "grad_norm": 0.1366504579782486,
      "learning_rate": 1e-06,
      "loss": 0.0433,
      "step": 1060
    },
    {
      "clip_ratio/high_max": 0.0024114710176945664,
      "clip_ratio/high_mean": 0.0009586821852280991,
      "clip_ratio/low_mean": 0.0013040469275438227,
      "clip_ratio/low_min": 6.107902754592942e-05,
      "clip_ratio/region_mean": 0.002262729154608678,
      "epoch": 0.09902641910061892,
      "grad_norm": 0.09972595423460007,
      "learning_rate": 1e-06,
      "loss": 0.0395,
      "step": 1061
    },
    {
      "clip_ratio/high_max": 0.0021520118170883507,
      "clip_ratio/high_mean": 0.0009067023474926827,
      "clip_ratio/low_mean": 0.0011340478595229797,
      "clip_ratio/low_min": 5.071438044979004e-05,
      "clip_ratio/region_mean": 0.002040750208834652,
      "epoch": 0.0991197522006195,
      "grad_norm": 0.10718478262424469,
      "learning_rate": 1e-06,
      "loss": 0.0345,
      "step": 1062
    },
    {
      "clip_ratio/high_max": 0.002620814244437497,
      "clip_ratio/high_mean": 0.0012037802516715601,
      "clip_ratio/low_mean": 0.0010417981029604562,
      "clip_ratio/low_min": 4.45548339484958e-05,
      "clip_ratio/region_mean": 0.0022455783109762706,
      "epoch": 0.09921308530062008,
      "grad_norm": 0.11672727018594742,
      "learning_rate": 1e-06,
      "loss": -0.0433,
      "step": 1063
    },
    {
      "clip_ratio/high_max": 0.0027213723442400806,
      "clip_ratio/high_mean": 0.001120669265219476,
      "clip_ratio/low_mean": 0.0011299401230644435,
      "clip_ratio/low_min": 0.0001174892604467459,
      "clip_ratio/region_mean": 0.002250609381007962,
      "epoch": 0.09930641840062067,
      "grad_norm": 0.1069716140627861,
      "learning_rate": 1e-06,
      "loss": 0.0297,
      "step": 1064
    },
    {
      "clip_ratio/high_max": 0.002789350524835754,
      "clip_ratio/high_mean": 0.001190496723211254,
      "clip_ratio/low_mean": 0.0012492367568484042,
      "clip_ratio/low_min": 8.338424322573701e-05,
      "clip_ratio/region_mean": 0.0024397334491368383,
      "epoch": 0.09939975150062125,
      "grad_norm": 0.11621293425559998,
      "learning_rate": 1e-06,
      "loss": 0.002,
      "step": 1065
    },
    {
      "clip_ratio/high_max": 0.0023896116981632076,
      "clip_ratio/high_mean": 0.0010325006915081758,
      "clip_ratio/low_mean": 0.0010244978693663143,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0020569985717884265,
      "epoch": 0.09949308460062183,
      "grad_norm": 0.11649531871080399,
      "learning_rate": 1e-06,
      "loss": 0.0025,
      "step": 1066
    },
    {
      "clip_ratio/high_max": 0.002675373980309814,
      "clip_ratio/high_mean": 0.001119227999879513,
      "clip_ratio/low_mean": 0.0010504302099434426,
      "clip_ratio/low_min": 0.00012363130736048333,
      "clip_ratio/region_mean": 0.002169658189814072,
      "epoch": 0.09958641770062242,
      "grad_norm": 0.11689122021198273,
      "learning_rate": 1e-06,
      "loss": 0.0476,
      "step": 1067
    },
    {
      "clip_ratio/high_max": 0.003016795228177216,
      "clip_ratio/high_mean": 0.001307435319176875,
      "clip_ratio/low_mean": 0.0010618365740810987,
      "clip_ratio/low_min": 9.151411177299451e-05,
      "clip_ratio/region_mean": 0.0023692718968959525,
      "epoch": 0.099679750800623,
      "grad_norm": 0.12360195815563202,
      "learning_rate": 1e-06,
      "loss": -0.0513,
      "step": 1068
    },
    {
      "clip_ratio/high_max": 0.0024809023343550507,
      "clip_ratio/high_mean": 0.0008891513189155376,
      "clip_ratio/low_mean": 0.0011078695497417357,
      "clip_ratio/low_min": 4.79866876048618e-05,
      "clip_ratio/region_mean": 0.001997020903218072,
      "epoch": 0.09977308390062359,
      "grad_norm": 0.09974703192710876,
      "learning_rate": 1e-06,
      "loss": 0.0155,
      "step": 1069
    },
    {
      "clip_ratio/high_max": 0.00273111074056942,
      "clip_ratio/high_mean": 0.001131101857026806,
      "clip_ratio/low_mean": 0.0012078444178769132,
      "clip_ratio/low_min": 0.00013443205170915462,
      "clip_ratio/region_mean": 0.002338946251256857,
      "epoch": 0.09986641700062417,
      "grad_norm": 0.11888189613819122,
      "learning_rate": 1e-06,
      "loss": 0.0427,
      "step": 1070
    },
    {
      "clip_ratio/high_max": 0.002887275615648832,
      "clip_ratio/high_mean": 0.0012772666341334116,
      "clip_ratio/low_mean": 0.0012335664723650552,
      "clip_ratio/low_min": 8.425303394687944e-05,
      "clip_ratio/region_mean": 0.002510833124688361,
      "epoch": 0.09995975010062474,
      "grad_norm": 0.12239677459001541,
      "learning_rate": 1e-06,
      "loss": 0.0015,
      "step": 1071
    },
    {
      "clip_ratio/high_max": 0.002579187144874595,
      "clip_ratio/high_mean": 0.0011054616479668766,
      "clip_ratio/low_mean": 0.0013819660089211538,
      "clip_ratio/low_min": 0.00012948144467372913,
      "clip_ratio/region_mean": 0.0024874277296476066,
      "epoch": 0.10005308320062534,
      "grad_norm": 0.12685957551002502,
      "learning_rate": 1e-06,
      "loss": 0.0405,
      "step": 1072
    },
    {
      "clip_ratio/high_max": 0.0025072550561162643,
      "clip_ratio/high_mean": 0.0011194720736966701,
      "clip_ratio/low_mean": 0.0010372953802288976,
      "clip_ratio/low_min": 5.5406057072104886e-05,
      "clip_ratio/region_mean": 0.0021567675212281756,
      "epoch": 0.10014641630062592,
      "grad_norm": 0.11538335680961609,
      "learning_rate": 1e-06,
      "loss": -0.0202,
      "step": 1073
    },
    {
      "clip_ratio/high_max": 0.0019684297330968548,
      "clip_ratio/high_mean": 0.0010255548240820644,
      "clip_ratio/low_mean": 0.0012416544414008968,
      "clip_ratio/low_min": 5.227260589890648e-05,
      "clip_ratio/region_mean": 0.002267209281853866,
      "epoch": 0.1002397494006265,
      "grad_norm": 0.11673750728368759,
      "learning_rate": 1e-06,
      "loss": 0.0124,
      "step": 1074
    },
    {
      "clip_ratio/high_max": 0.0024463470035698265,
      "clip_ratio/high_mean": 0.0010314030059817014,
      "clip_ratio/low_mean": 0.001159633702627616,
      "clip_ratio/low_min": 4.8209774831775576e-05,
      "clip_ratio/region_mean": 0.002191036743170116,
      "epoch": 0.10033308250062709,
      "grad_norm": 0.10937150567770004,
      "learning_rate": 1e-06,
      "loss": 0.0241,
      "step": 1075
    },
    {
      "clip_ratio/high_max": 0.002496567711204989,
      "clip_ratio/high_mean": 0.0011542028332769405,
      "clip_ratio/low_mean": 0.0010634353930072393,
      "clip_ratio/low_min": 3.797896351898089e-05,
      "clip_ratio/region_mean": 0.0022176381971803494,
      "epoch": 0.10042641560062766,
      "grad_norm": 0.10290578752756119,
      "learning_rate": 1e-06,
      "loss": -0.0173,
      "step": 1076
    },
    {
      "clip_ratio/high_max": 0.002785484801279381,
      "clip_ratio/high_mean": 0.0012426740868249908,
      "clip_ratio/low_mean": 0.0010342115492676385,
      "clip_ratio/low_min": 0.00011341815206833417,
      "clip_ratio/region_mean": 0.002276885621540714,
      "epoch": 0.10051974870062824,
      "grad_norm": 0.10617270320653915,
      "learning_rate": 1e-06,
      "loss": -0.01,
      "step": 1077
    },
    {
      "clip_ratio/high_max": 0.0029206702020019293,
      "clip_ratio/high_mean": 0.0012211155080876779,
      "clip_ratio/low_mean": 0.0010975272380164824,
      "clip_ratio/low_min": 3.594410009100102e-05,
      "clip_ratio/region_mean": 0.002318642713362351,
      "epoch": 0.10061308180062883,
      "grad_norm": 0.11008171737194061,
      "learning_rate": 1e-06,
      "loss": 0.0201,
      "step": 1078
    },
    {
      "clip_ratio/high_max": 0.002840934605046641,
      "clip_ratio/high_mean": 0.0010943061442958424,
      "clip_ratio/low_mean": 0.001305307261645794,
      "clip_ratio/low_min": 0.00020026239599246765,
      "clip_ratio/region_mean": 0.002399613324087113,
      "epoch": 0.10070641490062941,
      "grad_norm": 0.11556420475244522,
      "learning_rate": 1e-06,
      "loss": 0.089,
      "step": 1079
    },
    {
      "clip_ratio/high_max": 0.00236867959756637,
      "clip_ratio/high_mean": 0.0009672880096331937,
      "clip_ratio/low_mean": 0.0011380839096091222,
      "clip_ratio/low_min": 8.657145554025192e-05,
      "clip_ratio/region_mean": 0.0021053719538031146,
      "epoch": 0.10079974800063,
      "grad_norm": 0.10728225857019424,
      "learning_rate": 1e-06,
      "loss": 0.0295,
      "step": 1080
    },
    {
      "clip_ratio/high_max": 0.0025966270914068446,
      "clip_ratio/high_mean": 0.0010549810976954177,
      "clip_ratio/low_mean": 0.0011490706601762213,
      "clip_ratio/low_min": 0.0001105655105675396,
      "clip_ratio/region_mean": 0.0022040517869754694,
      "epoch": 0.10089308110063058,
      "grad_norm": 0.1247933879494667,
      "learning_rate": 1e-06,
      "loss": 0.0363,
      "step": 1081
    },
    {
      "clip_ratio/high_max": 0.0025589694996597245,
      "clip_ratio/high_mean": 0.0010329538617952494,
      "clip_ratio/low_mean": 0.0013034118928771932,
      "clip_ratio/low_min": 0.00015880875798757188,
      "clip_ratio/region_mean": 0.0023363656873698346,
      "epoch": 0.10098641420063116,
      "grad_norm": 0.11883296817541122,
      "learning_rate": 1e-06,
      "loss": 0.0471,
      "step": 1082
    },
    {
      "clip_ratio/high_max": 0.0024430182384094223,
      "clip_ratio/high_mean": 0.0009682027248345548,
      "clip_ratio/low_mean": 0.0013421356670733076,
      "clip_ratio/low_min": 0.00017714464684104314,
      "clip_ratio/region_mean": 0.0023103384155547246,
      "epoch": 0.10107974730063175,
      "grad_norm": 0.11756071448326111,
      "learning_rate": 1e-06,
      "loss": 0.0522,
      "step": 1083
    },
    {
      "clip_ratio/high_max": 0.0029525988284149207,
      "clip_ratio/high_mean": 0.0012053053505951539,
      "clip_ratio/low_mean": 0.0011951777023568866,
      "clip_ratio/low_min": 0.0001447406866645906,
      "clip_ratio/region_mean": 0.002400483026576694,
      "epoch": 0.10117308040063233,
      "grad_norm": 0.11909200996160507,
      "learning_rate": 1e-06,
      "loss": -0.0141,
      "step": 1084
    },
    {
      "clip_ratio/high_max": 0.0023794097505742684,
      "clip_ratio/high_mean": 0.0011081549528171308,
      "clip_ratio/low_mean": 0.001021991116431309,
      "clip_ratio/low_min": 6.935955752851442e-05,
      "clip_ratio/region_mean": 0.0021301460874383338,
      "epoch": 0.10126641350063291,
      "grad_norm": 0.11934073269367218,
      "learning_rate": 1e-06,
      "loss": 0.009,
      "step": 1085
    },
    {
      "clip_ratio/high_max": 0.0024595874128863215,
      "clip_ratio/high_mean": 0.0009960763054550625,
      "clip_ratio/low_mean": 0.0011105345147370826,
      "clip_ratio/low_min": 0.00012179011264379369,
      "clip_ratio/region_mean": 0.002106610882037785,
      "epoch": 0.1013597466006335,
      "grad_norm": 0.11388830095529556,
      "learning_rate": 1e-06,
      "loss": 0.0356,
      "step": 1086
    },
    {
      "clip_ratio/high_max": 0.0027253152074990794,
      "clip_ratio/high_mean": 0.0011164219868078362,
      "clip_ratio/low_mean": 0.0013074361777398735,
      "clip_ratio/low_min": 0.0001853404182838858,
      "clip_ratio/region_mean": 0.0024238581900135614,
      "epoch": 0.10145307970063408,
      "grad_norm": 0.11670181155204773,
      "learning_rate": 1e-06,
      "loss": 0.0754,
      "step": 1087
    },
    {
      "clip_ratio/high_max": 0.002694049384444952,
      "clip_ratio/high_mean": 0.0011580070895433892,
      "clip_ratio/low_mean": 0.001186084860819392,
      "clip_ratio/low_min": 5.331829197530169e-05,
      "clip_ratio/region_mean": 0.0023440919758286327,
      "epoch": 0.10154641280063466,
      "grad_norm": 0.12323874235153198,
      "learning_rate": 1e-06,
      "loss": 0.0213,
      "step": 1088
    },
    {
      "clip_ratio/high_max": 0.002950062364106998,
      "clip_ratio/high_mean": 0.001152325676230248,
      "clip_ratio/low_mean": 0.001114763621444581,
      "clip_ratio/low_min": 0.00010728094275691546,
      "clip_ratio/region_mean": 0.0022670893085887656,
      "epoch": 0.10163974590063525,
      "grad_norm": 0.11454440653324127,
      "learning_rate": 1e-06,
      "loss": 0.001,
      "step": 1089
    },
    {
      "clip_ratio/high_max": 0.002618478763906751,
      "clip_ratio/high_mean": 0.00103928150201682,
      "clip_ratio/low_mean": 0.0011396243608032819,
      "clip_ratio/low_min": 5.77608952880837e-05,
      "clip_ratio/region_mean": 0.0021789058664580807,
      "epoch": 0.10173307900063583,
      "grad_norm": 0.10497259348630905,
      "learning_rate": 1e-06,
      "loss": 0.0408,
      "step": 1090
    },
    {
      "clip_ratio/high_max": 0.003017491202626843,
      "clip_ratio/high_mean": 0.0011521638098201947,
      "clip_ratio/low_mean": 0.0011818067432614043,
      "clip_ratio/low_min": 0.00013988734826853033,
      "clip_ratio/region_mean": 0.0023339705148828216,
      "epoch": 0.10182641210063642,
      "grad_norm": 0.10692637413740158,
      "learning_rate": 1e-06,
      "loss": 0.0047,
      "step": 1091
    },
    {
      "clip_ratio/high_max": 0.002412800578895258,
      "clip_ratio/high_mean": 0.0009487999195698649,
      "clip_ratio/low_mean": 0.001282595903830952,
      "clip_ratio/low_min": 5.246302407613257e-05,
      "clip_ratio/region_mean": 0.002231395774288103,
      "epoch": 0.101919745200637,
      "grad_norm": 0.10796523094177246,
      "learning_rate": 1e-06,
      "loss": 0.05,
      "step": 1092
    },
    {
      "clip_ratio/high_max": 0.002751141888438724,
      "clip_ratio/high_mean": 0.0011391532025299966,
      "clip_ratio/low_mean": 0.0012838768197980244,
      "clip_ratio/low_min": 1.3586956811195705e-05,
      "clip_ratio/region_mean": 0.0024230299895862117,
      "epoch": 0.10201307830063758,
      "grad_norm": 0.11812913417816162,
      "learning_rate": 1e-06,
      "loss": 0.0268,
      "step": 1093
    },
    {
      "clip_ratio/high_max": 0.002707813720917329,
      "clip_ratio/high_mean": 0.0011065188191423658,
      "clip_ratio/low_mean": 0.00135228780345642,
      "clip_ratio/low_min": 3.724730049725622e-05,
      "clip_ratio/region_mean": 0.002458806637150701,
      "epoch": 0.10210641140063817,
      "grad_norm": 0.1216379702091217,
      "learning_rate": 1e-06,
      "loss": 0.0518,
      "step": 1094
    },
    {
      "clip_ratio/high_max": 0.003174927936925087,
      "clip_ratio/high_mean": 0.0013223898931755684,
      "clip_ratio/low_mean": 0.0013807560899294913,
      "clip_ratio/low_min": 3.065340933972038e-05,
      "clip_ratio/region_mean": 0.00270314601220889,
      "epoch": 0.10219974450063875,
      "grad_norm": 0.13937297463417053,
      "learning_rate": 1e-06,
      "loss": 0.0086,
      "step": 1095
    },
    {
      "clip_ratio/high_max": 0.002800120688334573,
      "clip_ratio/high_mean": 0.0012272596941329539,
      "clip_ratio/low_mean": 0.0013185914540372323,
      "clip_ratio/low_min": 0.00012680955660471227,
      "clip_ratio/region_mean": 0.0025458511227043346,
      "epoch": 0.10229307760063933,
      "grad_norm": 0.11575004458427429,
      "learning_rate": 1e-06,
      "loss": 0.0083,
      "step": 1096
    },
    {
      "clip_ratio/high_max": 0.0032278427679557353,
      "clip_ratio/high_mean": 0.001216051994560985,
      "clip_ratio/low_mean": 0.0015723384931334294,
      "clip_ratio/low_min": 0.0001675063685979694,
      "clip_ratio/region_mean": 0.0027883905422640964,
      "epoch": 0.10238641070063992,
      "grad_norm": 0.12887288630008698,
      "learning_rate": 1e-06,
      "loss": 0.021,
      "step": 1097
    },
    {
      "clip_ratio/high_max": 0.0025176868948619813,
      "clip_ratio/high_mean": 0.0010847801859199535,
      "clip_ratio/low_mean": 0.001257452695426764,
      "clip_ratio/low_min": 0.00013740182657784317,
      "clip_ratio/region_mean": 0.0023422329395543784,
      "epoch": 0.1024797438006405,
      "grad_norm": 0.10793988406658173,
      "learning_rate": 1e-06,
      "loss": 0.0067,
      "step": 1098
    },
    {
      "clip_ratio/high_max": 0.0028035539071424864,
      "clip_ratio/high_mean": 0.001135479749791557,
      "clip_ratio/low_mean": 0.0011583281884668395,
      "clip_ratio/low_min": 0.00013805752678308636,
      "clip_ratio/region_mean": 0.002293807905516587,
      "epoch": 0.10257307690064109,
      "grad_norm": 0.12659579515457153,
      "learning_rate": 1e-06,
      "loss": 0.0069,
      "step": 1099
    },
    {
      "clip_ratio/high_max": 0.0026034199618152343,
      "clip_ratio/high_mean": 0.0009543860342091648,
      "clip_ratio/low_mean": 0.0011771291501645464,
      "clip_ratio/low_min": 7.552693477919092e-05,
      "clip_ratio/region_mean": 0.0021315151898306794,
      "epoch": 0.10266641000064167,
      "grad_norm": 0.09649745374917984,
      "learning_rate": 1e-06,
      "loss": 0.0303,
      "step": 1100
    },
    {
      "clip_ratio/high_max": 0.0031048729506437667,
      "clip_ratio/high_mean": 0.0012960248004674213,
      "clip_ratio/low_mean": 0.0013950432803540025,
      "clip_ratio/low_min": 0.00017725034558679909,
      "clip_ratio/region_mean": 0.002691068089916371,
      "epoch": 0.10275974310064225,
      "grad_norm": 0.12436746060848236,
      "learning_rate": 1e-06,
      "loss": -0.0176,
      "step": 1101
    },
    {
      "clip_ratio/high_max": 0.0025201681528415065,
      "clip_ratio/high_mean": 0.0011660555574053433,
      "clip_ratio/low_mean": 0.001305936457356438,
      "clip_ratio/low_min": 0.00014024285155755933,
      "clip_ratio/region_mean": 0.00247199201839976,
      "epoch": 0.10285307620064284,
      "grad_norm": 0.13194289803504944,
      "learning_rate": 1e-06,
      "loss": 0.0371,
      "step": 1102
    },
    {
      "clip_ratio/high_max": 0.002811998245306313,
      "clip_ratio/high_mean": 0.001105553057641373,
      "clip_ratio/low_mean": 0.0012419717295415467,
      "clip_ratio/low_min": 8.691742641531164e-05,
      "clip_ratio/region_mean": 0.0023475248235627078,
      "epoch": 0.10294640930064342,
      "grad_norm": 0.11174826323986053,
      "learning_rate": 1e-06,
      "loss": 0.0444,
      "step": 1103
    },
    {
      "clip_ratio/high_max": 0.0029067390169075225,
      "clip_ratio/high_mean": 0.0010887072148761945,
      "clip_ratio/low_mean": 0.0013747961238550488,
      "clip_ratio/low_min": 0.00014209014534571907,
      "clip_ratio/region_mean": 0.0024635033769300207,
      "epoch": 0.103039742400644,
      "grad_norm": 0.11580396443605423,
      "learning_rate": 1e-06,
      "loss": 0.0685,
      "step": 1104
    },
    {
      "clip_ratio/high_max": 0.0025924588553607464,
      "clip_ratio/high_mean": 0.0011545375673449598,
      "clip_ratio/low_mean": 0.0010833912219823105,
      "clip_ratio/low_min": 5.3648069297196344e-05,
      "clip_ratio/region_mean": 0.002237928711110726,
      "epoch": 0.10313307550064459,
      "grad_norm": 0.12212143838405609,
      "learning_rate": 1e-06,
      "loss": 0.0017,
      "step": 1105
    },
    {
      "clip_ratio/high_max": 0.0029773897913401015,
      "clip_ratio/high_mean": 0.001277524384931894,
      "clip_ratio/low_mean": 0.0012416719255270436,
      "clip_ratio/low_min": 0.00013018519166507758,
      "clip_ratio/region_mean": 0.0025191962704411708,
      "epoch": 0.10322640860064516,
      "grad_norm": 0.11835592985153198,
      "learning_rate": 1e-06,
      "loss": 0.0512,
      "step": 1106
    },
    {
      "clip_ratio/high_max": 0.002519008434319403,
      "clip_ratio/high_mean": 0.0010240841293125413,
      "clip_ratio/low_mean": 0.0011124684879177948,
      "clip_ratio/low_min": 1.1299945981591009e-05,
      "clip_ratio/region_mean": 0.002136552648153156,
      "epoch": 0.10331974170064574,
      "grad_norm": 0.1100822240114212,
      "learning_rate": 1e-06,
      "loss": 0.0211,
      "step": 1107
    },
    {
      "clip_ratio/high_max": 0.003239823978219647,
      "clip_ratio/high_mean": 0.0012647863622987643,
      "clip_ratio/low_mean": 0.0011455011917860247,
      "clip_ratio/low_min": 3.245824973419076e-05,
      "clip_ratio/region_mean": 0.0024102876050164923,
      "epoch": 0.10341307480064633,
      "grad_norm": 0.12142063677310944,
      "learning_rate": 1e-06,
      "loss": 0.0479,
      "step": 1108
    },
    {
      "clip_ratio/high_max": 0.0024605692160548642,
      "clip_ratio/high_mean": 0.0011022895414498635,
      "clip_ratio/low_mean": 0.0011044156453863252,
      "clip_ratio/low_min": 0.00010550630213401746,
      "clip_ratio/region_mean": 0.002206705161370337,
      "epoch": 0.10350640790064691,
      "grad_norm": 0.11533405631780624,
      "learning_rate": 1e-06,
      "loss": 0.0537,
      "step": 1109
    },
    {
      "clip_ratio/high_max": 0.002634015130752232,
      "clip_ratio/high_mean": 0.0010467530919413548,
      "clip_ratio/low_mean": 0.0012135065953771118,
      "clip_ratio/low_min": 0.00010743216807895806,
      "clip_ratio/region_mean": 0.002260259680042509,
      "epoch": 0.1035997410006475,
      "grad_norm": 0.11456581950187683,
      "learning_rate": 1e-06,
      "loss": 0.0332,
      "step": 1110
    },
    {
      "clip_ratio/high_max": 0.003077726694755256,
      "clip_ratio/high_mean": 0.0013154583939467557,
      "clip_ratio/low_mean": 0.0010996196888299892,
      "clip_ratio/low_min": 1.982553476409521e-05,
      "clip_ratio/region_mean": 0.0024150780591298826,
      "epoch": 0.10369307410064808,
      "grad_norm": 0.11310114711523056,
      "learning_rate": 1e-06,
      "loss": -0.0016,
      "step": 1111
    },
    {
      "clip_ratio/high_max": 0.0026963762429659255,
      "clip_ratio/high_mean": 0.0011136175235151313,
      "clip_ratio/low_mean": 0.0012948331313964445,
      "clip_ratio/low_min": 0.00014351652498589829,
      "clip_ratio/region_mean": 0.0024084506221697666,
      "epoch": 0.10378640720064866,
      "grad_norm": 0.11605637520551682,
      "learning_rate": 1e-06,
      "loss": 0.0304,
      "step": 1112
    },
    {
      "clip_ratio/high_max": 0.0028868283989140764,
      "clip_ratio/high_mean": 0.0011918912623514188,
      "clip_ratio/low_mean": 0.0012752842994814273,
      "clip_ratio/low_min": 0.00010052474772237474,
      "clip_ratio/region_mean": 0.0024671755454619415,
      "epoch": 0.10387974030064925,
      "grad_norm": 0.12642115354537964,
      "learning_rate": 1e-06,
      "loss": 0.0358,
      "step": 1113
    },
    {
      "clip_ratio/high_max": 0.00247761289938353,
      "clip_ratio/high_mean": 0.0010557337609498063,
      "clip_ratio/low_mean": 0.001374893054162385,
      "clip_ratio/low_min": 0.0001848703104769811,
      "clip_ratio/region_mean": 0.0024306268023792654,
      "epoch": 0.10397307340064983,
      "grad_norm": 0.11440667510032654,
      "learning_rate": 1e-06,
      "loss": 0.0286,
      "step": 1114
    },
    {
      "clip_ratio/high_max": 0.003179244667990133,
      "clip_ratio/high_mean": 0.0012934274636791088,
      "clip_ratio/low_mean": 0.0013286632456583902,
      "clip_ratio/low_min": 0.00010015191583079286,
      "clip_ratio/region_mean": 0.0026220906947855838,
      "epoch": 0.10406640650065041,
      "grad_norm": 0.11868170648813248,
      "learning_rate": 1e-06,
      "loss": 0.0189,
      "step": 1115
    },
    {
      "clip_ratio/high_max": 0.0024273158123833127,
      "clip_ratio/high_mean": 0.0010362270386394812,
      "clip_ratio/low_mean": 0.0013252519311208744,
      "clip_ratio/low_min": 0.00016632347433187533,
      "clip_ratio/region_mean": 0.0023614789388375357,
      "epoch": 0.104159739600651,
      "grad_norm": 0.09607911854982376,
      "learning_rate": 1e-06,
      "loss": 0.0317,
      "step": 1116
    },
    {
      "clip_ratio/high_max": 0.003292489651357755,
      "clip_ratio/high_mean": 0.001346397039014846,
      "clip_ratio/low_mean": 0.0013972801534691826,
      "clip_ratio/low_min": 0.00013283076623338275,
      "clip_ratio/region_mean": 0.00274367712700041,
      "epoch": 0.10425307270065158,
      "grad_norm": 0.12791144847869873,
      "learning_rate": 1e-06,
      "loss": 0.0292,
      "step": 1117
    },
    {
      "clip_ratio/high_max": 0.002678358861885499,
      "clip_ratio/high_mean": 0.0011418829817557707,
      "clip_ratio/low_mean": 0.001304392222664319,
      "clip_ratio/low_min": 0.00011797684510383988,
      "clip_ratio/region_mean": 0.0024462751534883864,
      "epoch": 0.10434640580065216,
      "grad_norm": 0.12478093057870865,
      "learning_rate": 1e-06,
      "loss": 0.0169,
      "step": 1118
    },
    {
      "clip_ratio/high_max": 0.0028471623809309676,
      "clip_ratio/high_mean": 0.0012985945941181853,
      "clip_ratio/low_mean": 0.0014803677913732827,
      "clip_ratio/low_min": 0.00014858556005492574,
      "clip_ratio/region_mean": 0.00277896234911168,
      "epoch": 0.10443973890065275,
      "grad_norm": 0.11772139370441437,
      "learning_rate": 1e-06,
      "loss": 0.0053,
      "step": 1119
    },
    {
      "clip_ratio/high_max": 0.0024437717511318624,
      "clip_ratio/high_mean": 0.0011579339370655362,
      "clip_ratio/low_mean": 0.0014704883178637829,
      "clip_ratio/low_min": 0.00026892401911027264,
      "clip_ratio/region_mean": 0.002628422196721658,
      "epoch": 0.10453307200065333,
      "grad_norm": 0.12378618121147156,
      "learning_rate": 1e-06,
      "loss": 0.0506,
      "step": 1120
    },
    {
      "clip_ratio/high_max": 0.003035665096831508,
      "clip_ratio/high_mean": 0.0011799336498370394,
      "clip_ratio/low_mean": 0.0013901290294597857,
      "clip_ratio/low_min": 0.00011342339439579519,
      "clip_ratio/region_mean": 0.0025700626938487403,
      "epoch": 0.10462640510065392,
      "grad_norm": 0.10745785385370255,
      "learning_rate": 1e-06,
      "loss": 0.0094,
      "step": 1121
    },
    {
      "clip_ratio/high_max": 0.002812719343637582,
      "clip_ratio/high_mean": 0.0011656712122203317,
      "clip_ratio/low_mean": 0.0011819880601251498,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0023476592541555874,
      "epoch": 0.1047197382006545,
      "grad_norm": 0.09620406478643417,
      "learning_rate": 1e-06,
      "loss": 0.0269,
      "step": 1122
    },
    {
      "clip_ratio/high_max": 0.0030243383735069074,
      "clip_ratio/high_mean": 0.001192717549201916,
      "clip_ratio/low_mean": 0.0011905831925105304,
      "clip_ratio/low_min": 3.1554272027278785e-05,
      "clip_ratio/region_mean": 0.0023833007071516477,
      "epoch": 0.10481307130065508,
      "grad_norm": 0.12845869362354279,
      "learning_rate": 1e-06,
      "loss": 0.0218,
      "step": 1123
    },
    {
      "clip_ratio/high_max": 0.002959868113975972,
      "clip_ratio/high_mean": 0.0013269581268104957,
      "clip_ratio/low_mean": 0.0013991171654197387,
      "clip_ratio/low_min": 0.00014159019065118628,
      "clip_ratio/region_mean": 0.002726075290411245,
      "epoch": 0.10490640440065567,
      "grad_norm": 0.11898820102214813,
      "learning_rate": 1e-06,
      "loss": 0.0118,
      "step": 1124
    },
    {
      "clip_ratio/high_max": 0.002799288362439256,
      "clip_ratio/high_mean": 0.0011499168358568568,
      "clip_ratio/low_mean": 0.0013406696889433078,
      "clip_ratio/low_min": 0.00011278265174041735,
      "clip_ratio/region_mean": 0.0024905865429900587,
      "epoch": 0.10499973750065625,
      "grad_norm": 0.11534126102924347,
      "learning_rate": 1e-06,
      "loss": 0.0323,
      "step": 1125
    },
    {
      "clip_ratio/high_max": 0.0026708424265962094,
      "clip_ratio/high_mean": 0.0011207122952328064,
      "clip_ratio/low_mean": 0.001268258009076817,
      "clip_ratio/low_min": 4.435517075762618e-05,
      "clip_ratio/region_mean": 0.0023889703152235597,
      "epoch": 0.10509307060065683,
      "grad_norm": 0.11435788869857788,
      "learning_rate": 1e-06,
      "loss": 0.0388,
      "step": 1126
    },
    {
      "clip_ratio/high_max": 0.002856292532669613,
      "clip_ratio/high_mean": 0.0011401038645999506,
      "clip_ratio/low_mean": 0.0013795285594824236,
      "clip_ratio/low_min": 0.00020529696848825552,
      "clip_ratio/region_mean": 0.002519632500479929,
      "epoch": 0.10518640370065742,
      "grad_norm": 0.1270683854818344,
      "learning_rate": 1e-06,
      "loss": 0.052,
      "step": 1127
    },
    {
      "clip_ratio/high_max": 0.002971828267618548,
      "clip_ratio/high_mean": 0.0012049351826135535,
      "clip_ratio/low_mean": 0.0011503495697979815,
      "clip_ratio/low_min": 1.3799955922877416e-05,
      "clip_ratio/region_mean": 0.002355284770601429,
      "epoch": 0.105279736800658,
      "grad_norm": 0.10787615925073624,
      "learning_rate": 1e-06,
      "loss": 0.0037,
      "step": 1128
    },
    {
      "clip_ratio/high_max": 0.002530510682845488,
      "clip_ratio/high_mean": 0.0009791489810595522,
      "clip_ratio/low_mean": 0.0014299782378657255,
      "clip_ratio/low_min": 0.00022141271983855404,
      "clip_ratio/region_mean": 0.0024091272134683095,
      "epoch": 0.10537306990065858,
      "grad_norm": 0.12056026607751846,
      "learning_rate": 1e-06,
      "loss": 0.0883,
      "step": 1129
    },
    {
      "clip_ratio/high_max": 0.0027782598335761577,
      "clip_ratio/high_mean": 0.001321903331700014,
      "clip_ratio/low_mean": 0.0011844348191516474,
      "clip_ratio/low_min": 8.406902088609058e-05,
      "clip_ratio/region_mean": 0.0025063381326617673,
      "epoch": 0.10546640300065917,
      "grad_norm": 0.11933311820030212,
      "learning_rate": 1e-06,
      "loss": 0.006,
      "step": 1130
    },
    {
      "clip_ratio/high_max": 0.002532692094973754,
      "clip_ratio/high_mean": 0.001146624073953717,
      "clip_ratio/low_mean": 0.0014163031555654015,
      "clip_ratio/low_min": 0.00013558315549744293,
      "clip_ratio/region_mean": 0.0025629272422520444,
      "epoch": 0.10555973610065975,
      "grad_norm": 0.11837572604417801,
      "learning_rate": 1e-06,
      "loss": 0.0297,
      "step": 1131
    },
    {
      "clip_ratio/high_max": 0.003131964367639739,
      "clip_ratio/high_mean": 0.0011996909161098301,
      "clip_ratio/low_mean": 0.0013013777788728476,
      "clip_ratio/low_min": 4.4867192627862096e-05,
      "clip_ratio/region_mean": 0.0025010687022586353,
      "epoch": 0.10565306920066034,
      "grad_norm": 0.11814764142036438,
      "learning_rate": 1e-06,
      "loss": 0.0083,
      "step": 1132
    },
    {
      "clip_ratio/high_max": 0.002500061586033553,
      "clip_ratio/high_mean": 0.0010158518598473165,
      "clip_ratio/low_mean": 0.001411313784046797,
      "clip_ratio/low_min": 0.0001168877279269509,
      "clip_ratio/region_mean": 0.0024271656657219864,
      "epoch": 0.10574640230066092,
      "grad_norm": 0.24052585661411285,
      "learning_rate": 1e-06,
      "loss": 0.0347,
      "step": 1133
    },
    {
      "clip_ratio/high_max": 0.003017571732925717,
      "clip_ratio/high_mean": 0.0013358462165342644,
      "clip_ratio/low_mean": 0.0016696455313649494,
      "clip_ratio/low_min": 0.00012916761716041947,
      "clip_ratio/region_mean": 0.0030054917297093198,
      "epoch": 0.1058397354006615,
      "grad_norm": 0.13456502556800842,
      "learning_rate": 1e-06,
      "loss": 0.0073,
      "step": 1134
    },
    {
      "clip_ratio/high_max": 0.002609604620374739,
      "clip_ratio/high_mean": 0.0010941214168269653,
      "clip_ratio/low_mean": 0.0012300178677833173,
      "clip_ratio/low_min": 9.737022537592566e-05,
      "clip_ratio/region_mean": 0.0023241393209900707,
      "epoch": 0.10593306850066209,
      "grad_norm": 0.11512071639299393,
      "learning_rate": 1e-06,
      "loss": 0.011,
      "step": 1135
    },
    {
      "clip_ratio/high_max": 0.0027544667827896774,
      "clip_ratio/high_mean": 0.0011002486317011062,
      "clip_ratio/low_mean": 0.0011712760096997954,
      "clip_ratio/low_min": 8.004349729162641e-05,
      "clip_ratio/region_mean": 0.0022715246013831347,
      "epoch": 0.10602640160066266,
      "grad_norm": 0.10703384131193161,
      "learning_rate": 1e-06,
      "loss": 0.0482,
      "step": 1136
    },
    {
      "clip_ratio/high_max": 0.0026286660868208855,
      "clip_ratio/high_mean": 0.001149256895587314,
      "clip_ratio/low_mean": 0.0013963623641757295,
      "clip_ratio/low_min": 0.00022232529045140836,
      "clip_ratio/region_mean": 0.002545619245211128,
      "epoch": 0.10611973470066324,
      "grad_norm": 0.11007598787546158,
      "learning_rate": 1e-06,
      "loss": 0.0356,
      "step": 1137
    },
    {
      "clip_ratio/high_max": 0.002739051531534642,
      "clip_ratio/high_mean": 0.0010739501085481606,
      "clip_ratio/low_mean": 0.0013600182355730794,
      "clip_ratio/low_min": 3.835406005237019e-05,
      "clip_ratio/region_mean": 0.0024339684532606043,
      "epoch": 0.10621306780066384,
      "grad_norm": 0.12848563492298126,
      "learning_rate": 1e-06,
      "loss": 0.0722,
      "step": 1138
    },
    {
      "clip_ratio/high_max": 0.002559735548857134,
      "clip_ratio/high_mean": 0.0010289772699252353,
      "clip_ratio/low_mean": 0.0014918754186510341,
      "clip_ratio/low_min": 0.00017435932386433706,
      "clip_ratio/region_mean": 0.0025208526640199125,
      "epoch": 0.10630640090066441,
      "grad_norm": 0.11483762413263321,
      "learning_rate": 1e-06,
      "loss": 0.0353,
      "step": 1139
    },
    {
      "clip_ratio/high_max": 0.0029175181116443127,
      "clip_ratio/high_mean": 0.001080374262528494,
      "clip_ratio/low_mean": 0.0013497868967533577,
      "clip_ratio/low_min": 0.0001887104444904253,
      "clip_ratio/region_mean": 0.0024301611047121696,
      "epoch": 0.10639973400066499,
      "grad_norm": 0.10692422091960907,
      "learning_rate": 1e-06,
      "loss": 0.0379,
      "step": 1140
    },
    {
      "clip_ratio/high_max": 0.002700121905945707,
      "clip_ratio/high_mean": 0.0011649370680970605,
      "clip_ratio/low_mean": 0.0012081735185347497,
      "clip_ratio/low_min": 4.405792060424574e-05,
      "clip_ratio/region_mean": 0.002373110633925535,
      "epoch": 0.10649306710066558,
      "grad_norm": 0.11575724184513092,
      "learning_rate": 1e-06,
      "loss": 0.0079,
      "step": 1141
    },
    {
      "clip_ratio/high_max": 0.00306388007447822,
      "clip_ratio/high_mean": 0.0012905216790386476,
      "clip_ratio/low_mean": 0.001202979481604416,
      "clip_ratio/low_min": 0.00012522148972493596,
      "clip_ratio/region_mean": 0.002493501131539233,
      "epoch": 0.10658640020066616,
      "grad_norm": 0.11531451344490051,
      "learning_rate": 1e-06,
      "loss": 0.0019,
      "step": 1142
    },
    {
      "clip_ratio/high_max": 0.0030013798459549434,
      "clip_ratio/high_mean": 0.001199832830025116,
      "clip_ratio/low_mean": 0.0012669624702539295,
      "clip_ratio/low_min": 6.315956125035882e-05,
      "clip_ratio/region_mean": 0.0024667953330208547,
      "epoch": 0.10667973330066675,
      "grad_norm": 0.12019931524991989,
      "learning_rate": 1e-06,
      "loss": 0.0192,
      "step": 1143
    },
    {
      "clip_ratio/high_max": 0.0023712478287052363,
      "clip_ratio/high_mean": 0.0009431351518287556,
      "clip_ratio/low_mean": 0.0013089040967315668,
      "clip_ratio/low_min": 4.538583652902162e-05,
      "clip_ratio/region_mean": 0.002252039223094471,
      "epoch": 0.10677306640066733,
      "grad_norm": 0.14286024868488312,
      "learning_rate": 1e-06,
      "loss": 0.0554,
      "step": 1144
    },
    {
      "clip_ratio/high_max": 0.0029089252711855806,
      "clip_ratio/high_mean": 0.0012521858698164579,
      "clip_ratio/low_mean": 0.0011544116096047219,
      "clip_ratio/low_min": 4.719277058029547e-05,
      "clip_ratio/region_mean": 0.0024065975376288407,
      "epoch": 0.10686639950066791,
      "grad_norm": 0.14004789292812347,
      "learning_rate": 1e-06,
      "loss": 0.0062,
      "step": 1145
    },
    {
      "clip_ratio/high_max": 0.0030094570392975584,
      "clip_ratio/high_mean": 0.001335574190306943,
      "clip_ratio/low_mean": 0.0015135196408664342,
      "clip_ratio/low_min": 0.00018862119850382442,
      "clip_ratio/region_mean": 0.002849093834811356,
      "epoch": 0.1069597326006685,
      "grad_norm": 0.10762453824281693,
      "learning_rate": 1e-06,
      "loss": 0.0174,
      "step": 1146
    },
    {
      "clip_ratio/high_max": 0.0025431940230191685,
      "clip_ratio/high_mean": 0.001127167975937482,
      "clip_ratio/low_mean": 0.001422966699465178,
      "clip_ratio/low_min": 0.0001494800417276565,
      "clip_ratio/region_mean": 0.002550134580815211,
      "epoch": 0.10705306570066908,
      "grad_norm": 0.11267776787281036,
      "learning_rate": 1e-06,
      "loss": 0.0436,
      "step": 1147
    },
    {
      "clip_ratio/high_max": 0.0023202954907901585,
      "clip_ratio/high_mean": 0.0010011605481849983,
      "clip_ratio/low_mean": 0.0012671764779952355,
      "clip_ratio/low_min": 0.00012124216209485894,
      "clip_ratio/region_mean": 0.002268337018904276,
      "epoch": 0.10714639880066966,
      "grad_norm": 0.11383038014173508,
      "learning_rate": 1e-06,
      "loss": 0.054,
      "step": 1148
    },
    {
      "clip_ratio/high_max": 0.002680772333405912,
      "clip_ratio/high_mean": 0.0011563459120225161,
      "clip_ratio/low_mean": 0.0013334371869859751,
      "clip_ratio/low_min": 0.00015424608773173532,
      "clip_ratio/region_mean": 0.0024897830517147668,
      "epoch": 0.10723973190067025,
      "grad_norm": 0.11772894114255905,
      "learning_rate": 1e-06,
      "loss": 0.0464,
      "step": 1149
    },
    {
      "clip_ratio/high_max": 0.0027182163175893947,
      "clip_ratio/high_mean": 0.001158545182988746,
      "clip_ratio/low_mean": 0.0012444767053239048,
      "clip_ratio/low_min": 3.792418738157721e-05,
      "clip_ratio/region_mean": 0.002403021884674672,
      "epoch": 0.10733306500067083,
      "grad_norm": 0.11122532933950424,
      "learning_rate": 1e-06,
      "loss": 0.041,
      "step": 1150
    },
    {
      "clip_ratio/high_max": 0.003199928018148057,
      "clip_ratio/high_mean": 0.0012628374388441443,
      "clip_ratio/low_mean": 0.0014054879393370356,
      "clip_ratio/low_min": 0.00015092244575498626,
      "clip_ratio/region_mean": 0.0026683254036470316,
      "epoch": 0.10742639810067142,
      "grad_norm": 0.1107155978679657,
      "learning_rate": 1e-06,
      "loss": 0.0533,
      "step": 1151
    },
    {
      "clip_ratio/high_max": 0.0025988160050474107,
      "clip_ratio/high_mean": 0.001165936706456705,
      "clip_ratio/low_mean": 0.0012795019210898317,
      "clip_ratio/low_min": 0.0001081228319890215,
      "clip_ratio/region_mean": 0.0024454386366414838,
      "epoch": 0.107519731200672,
      "grad_norm": 0.12099910527467728,
      "learning_rate": 1e-06,
      "loss": 0.0114,
      "step": 1152
    },
    {
      "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": 0.009722028459821397,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4081.0,
      "completions/mean_length": 605.1776123046875,
      "completions/mean_terminated_length": 570.906494140625,
      "completions/min_length": 3.0,
      "completions/min_terminated_length": 3.0,
      "epoch": 0.10761306430067258,
      "grad_norm": 0.11977685987949371,
      "learning_rate": 1e-06,
      "loss": 0.0285,
      "num_tokens": 809310308.0,
      "reward": 0.6238664984703064,
      "reward_std": 0.17871810495853424,
      "rewards/simpleverify_reward/mean": 0.6238664984703064,
      "rewards/simpleverify_reward/std": 0.4844163954257965,
      "step": 1153
    },
    {
      "clip_ratio/high_max": 0.0022051456398912705,
      "clip_ratio/high_mean": 0.0008482579705741955,
      "clip_ratio/low_mean": 0.0005361665589589393,
      "clip_ratio/low_min": 4.130187153350562e-05,
      "clip_ratio/region_mean": 0.0013844245549989864,
      "epoch": 0.10770639740067317,
      "grad_norm": 0.11634834110736847,
      "learning_rate": 1e-06,
      "loss": 0.0269,
      "step": 1154
    },
    {
      "clip_ratio/high_max": 0.0020037503163621295,
      "clip_ratio/high_mean": 0.0007370135535893496,
      "clip_ratio/low_mean": 0.0005831434064020868,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001320156985457288,
      "epoch": 0.10779973050067375,
      "grad_norm": 0.12227138131856918,
      "learning_rate": 1e-06,
      "loss": 0.0196,
      "step": 1155
    },
    {
      "clip_ratio/high_max": 0.0017835945836850442,
      "clip_ratio/high_mean": 0.0007434545259457082,
      "clip_ratio/low_mean": 0.0005530421085495618,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012964966299477965,
      "epoch": 0.10789306360067433,
      "grad_norm": 0.11062200367450714,
      "learning_rate": 1e-06,
      "loss": 0.007,
      "step": 1156
    },
    {
      "clip_ratio/high_max": 0.002101159185258439,
      "clip_ratio/high_mean": 0.000812598049378721,
      "clip_ratio/low_mean": 0.0007404301886708708,
      "clip_ratio/low_min": 5.102363502373919e-05,
      "clip_ratio/region_mean": 0.0015530282180407085,
      "epoch": 0.10798639670067492,
      "grad_norm": 0.1311548352241516,
      "learning_rate": 1e-06,
      "loss": 0.0564,
      "step": 1157
    },
    {
      "clip_ratio/high_max": 0.0020240997400833294,
      "clip_ratio/high_mean": 0.0007514389690186363,
      "clip_ratio/low_mean": 0.0007478377483494114,
      "clip_ratio/low_min": 8.254503836724325e-05,
      "clip_ratio/region_mean": 0.0014992767028161325,
      "epoch": 0.1080797298006755,
      "grad_norm": 0.11050847917795181,
      "learning_rate": 1e-06,
      "loss": 0.0306,
      "step": 1158
    },
    {
      "clip_ratio/high_max": 0.0021855211671208963,
      "clip_ratio/high_mean": 0.0009592939786671195,
      "clip_ratio/low_mean": 0.0007354513527388917,
      "clip_ratio/low_min": 1.4010312042955775e-05,
      "clip_ratio/region_mean": 0.0016947453477769159,
      "epoch": 0.10817306290067608,
      "grad_norm": 0.11717856675386429,
      "learning_rate": 1e-06,
      "loss": -0.0243,
      "step": 1159
    },
    {
      "clip_ratio/high_max": 0.002265210474433843,
      "clip_ratio/high_mean": 0.0010114832512044813,
      "clip_ratio/low_mean": 0.000883542104929802,
      "clip_ratio/low_min": 0.00010992027819156647,
      "clip_ratio/region_mean": 0.0018950253070215695,
      "epoch": 0.10826639600067667,
      "grad_norm": 0.11830315738916397,
      "learning_rate": 1e-06,
      "loss": 0.0253,
      "step": 1160
    },
    {
      "clip_ratio/high_max": 0.0019347222842043266,
      "clip_ratio/high_mean": 0.0008118970181385521,
      "clip_ratio/low_mean": 0.0010327022901037708,
      "clip_ratio/low_min": 8.361271375179058e-05,
      "clip_ratio/region_mean": 0.0018445992755005136,
      "epoch": 0.10835972910067725,
      "grad_norm": 0.12328173965215683,
      "learning_rate": 1e-06,
      "loss": 0.0506,
      "step": 1161
    },
    {
      "clip_ratio/high_max": 0.002106198477122234,
      "clip_ratio/high_mean": 0.0009211926753778243,
      "clip_ratio/low_mean": 0.0008750574124860577,
      "clip_ratio/low_min": 0.00012926964427606435,
      "clip_ratio/region_mean": 0.0017962500642170198,
      "epoch": 0.10845306220067784,
      "grad_norm": 0.11745533347129822,
      "learning_rate": 1e-06,
      "loss": 0.0135,
      "step": 1162
    },
    {
      "clip_ratio/high_max": 0.0024538260731787886,
      "clip_ratio/high_mean": 0.0009322658333985601,
      "clip_ratio/low_mean": 0.0009371481701236917,
      "clip_ratio/low_min": 7.019098757155007e-05,
      "clip_ratio/region_mean": 0.001869413990789326,
      "epoch": 0.10854639530067842,
      "grad_norm": 0.12173112481832504,
      "learning_rate": 1e-06,
      "loss": 0.008,
      "step": 1163
    },
    {
      "clip_ratio/high_max": 0.0017985076483455487,
      "clip_ratio/high_mean": 0.0008000890466064448,
      "clip_ratio/low_mean": 0.001189785387396114,
      "clip_ratio/low_min": 0.0001357658202323364,
      "clip_ratio/region_mean": 0.001989874435821548,
      "epoch": 0.108639728400679,
      "grad_norm": 0.19829334318637848,
      "learning_rate": 1e-06,
      "loss": 0.049,
      "step": 1164
    },
    {
      "clip_ratio/high_max": 0.002381717160460539,
      "clip_ratio/high_mean": 0.0008635516369395191,
      "clip_ratio/low_mean": 0.0009943249970092438,
      "clip_ratio/low_min": 7.623442797921598e-05,
      "clip_ratio/region_mean": 0.0018578766248538159,
      "epoch": 0.10873306150067959,
      "grad_norm": 0.12362787872552872,
      "learning_rate": 1e-06,
      "loss": 0.0424,
      "step": 1165
    },
    {
      "clip_ratio/high_max": 0.0021821201153215952,
      "clip_ratio/high_mean": 0.0008784778801782522,
      "clip_ratio/low_mean": 0.0009237140584446024,
      "clip_ratio/low_min": 3.912757256330224e-05,
      "clip_ratio/region_mean": 0.0018021919458988123,
      "epoch": 0.10882639460068017,
      "grad_norm": 0.122602678835392,
      "learning_rate": 1e-06,
      "loss": 0.0383,
      "step": 1166
    },
    {
      "clip_ratio/high_max": 0.001917199326271657,
      "clip_ratio/high_mean": 0.0008443322867606184,
      "clip_ratio/low_mean": 0.0008314452061313204,
      "clip_ratio/low_min": 2.09067593459622e-05,
      "clip_ratio/region_mean": 0.001675777428317815,
      "epoch": 0.10891972770068074,
      "grad_norm": 0.11294093728065491,
      "learning_rate": 1e-06,
      "loss": 0.0112,
      "step": 1167
    },
    {
      "clip_ratio/high_max": 0.0022509836562676355,
      "clip_ratio/high_mean": 0.0009490211305092089,
      "clip_ratio/low_mean": 0.0009287308639613912,
      "clip_ratio/low_min": 3.8909884096938185e-05,
      "clip_ratio/region_mean": 0.0018777520162984729,
      "epoch": 0.10901306080068134,
      "grad_norm": 0.11199970543384552,
      "learning_rate": 1e-06,
      "loss": 0.0256,
      "step": 1168
    },
    {
      "clip_ratio/high_max": 0.0022230954527913127,
      "clip_ratio/high_mean": 0.0009541055169393076,
      "clip_ratio/low_mean": 0.0008088467002380639,
      "clip_ratio/low_min": 2.954328738269396e-05,
      "clip_ratio/region_mean": 0.0017629522117204033,
      "epoch": 0.10910639390068191,
      "grad_norm": 0.11580251902341843,
      "learning_rate": 1e-06,
      "loss": 0.0255,
      "step": 1169
    },
    {
      "clip_ratio/high_max": 0.002369122223171871,
      "clip_ratio/high_mean": 0.0008771092525421409,
      "clip_ratio/low_mean": 0.0010278150539306807,
      "clip_ratio/low_min": 9.947158287104685e-05,
      "clip_ratio/region_mean": 0.001904924305563327,
      "epoch": 0.10919972700068249,
      "grad_norm": 0.1623285710811615,
      "learning_rate": 1e-06,
      "loss": 0.0332,
      "step": 1170
    },
    {
      "clip_ratio/high_max": 0.0021901287545915693,
      "clip_ratio/high_mean": 0.0008944836845330428,
      "clip_ratio/low_mean": 0.0010959301725961268,
      "clip_ratio/low_min": 0.00015705118130426854,
      "clip_ratio/region_mean": 0.001990413846215233,
      "epoch": 0.10929306010068308,
      "grad_norm": 0.11249013245105743,
      "learning_rate": 1e-06,
      "loss": 0.0681,
      "step": 1171
    },
    {
      "clip_ratio/high_max": 0.0022758879204047844,
      "clip_ratio/high_mean": 0.0009372177155455574,
      "clip_ratio/low_mean": 0.0011285629698249977,
      "clip_ratio/low_min": 7.89888863437227e-05,
      "clip_ratio/region_mean": 0.002065780685370555,
      "epoch": 0.10938639320068366,
      "grad_norm": 0.11011063307523727,
      "learning_rate": 1e-06,
      "loss": 0.035,
      "step": 1172
    },
    {
      "clip_ratio/high_max": 0.002339449478313327,
      "clip_ratio/high_mean": 0.001067694782250328,
      "clip_ratio/low_mean": 0.000992456285530352,
      "clip_ratio/low_min": 0.00017182131250592647,
      "clip_ratio/region_mean": 0.002060151062323712,
      "epoch": 0.10947972630068425,
      "grad_norm": 0.12196346372365952,
      "learning_rate": 1e-06,
      "loss": -0.0016,
      "step": 1173
    },
    {
      "clip_ratio/high_max": 0.0024089510916383006,
      "clip_ratio/high_mean": 0.0010303717499482445,
      "clip_ratio/low_mean": 0.0008754592508921633,
      "clip_ratio/low_min": 7.280913996510208e-05,
      "clip_ratio/region_mean": 0.0019058309990214184,
      "epoch": 0.10957305940068483,
      "grad_norm": 0.12614992260932922,
      "learning_rate": 1e-06,
      "loss": 0.0249,
      "step": 1174
    },
    {
      "clip_ratio/high_max": 0.002716060036618728,
      "clip_ratio/high_mean": 0.0010410269733256428,
      "clip_ratio/low_mean": 0.0009715198139019776,
      "clip_ratio/low_min": 8.22897745820228e-05,
      "clip_ratio/region_mean": 0.002012546799960546,
      "epoch": 0.10966639250068541,
      "grad_norm": 0.11459046602249146,
      "learning_rate": 1e-06,
      "loss": 0.0375,
      "step": 1175
    },
    {
      "clip_ratio/high_max": 0.0025704871004563756,
      "clip_ratio/high_mean": 0.000968531661783345,
      "clip_ratio/low_mean": 0.0010568624966253992,
      "clip_ratio/low_min": 0.00010840465347428108,
      "clip_ratio/region_mean": 0.002025394198426511,
      "epoch": 0.109759725600686,
      "grad_norm": 0.13366645574569702,
      "learning_rate": 1e-06,
      "loss": 0.035,
      "step": 1176
    },
    {
      "clip_ratio/high_max": 0.0026539053724263795,
      "clip_ratio/high_mean": 0.0010798767252708785,
      "clip_ratio/low_mean": 0.0009525927907816367,
      "clip_ratio/low_min": 9.907875755743589e-05,
      "clip_ratio/region_mean": 0.0020324695433373563,
      "epoch": 0.10985305870068658,
      "grad_norm": 0.11082327365875244,
      "learning_rate": 1e-06,
      "loss": -0.0195,
      "step": 1177
    },
    {
      "clip_ratio/high_max": 0.002270565673825331,
      "clip_ratio/high_mean": 0.0009582634193066042,
      "clip_ratio/low_mean": 0.0009140212441707263,
      "clip_ratio/low_min": 0.00010293228569935309,
      "clip_ratio/region_mean": 0.0018722846507444046,
      "epoch": 0.10994639180068716,
      "grad_norm": 0.11979391425848007,
      "learning_rate": 1e-06,
      "loss": 0.0221,
      "step": 1178
    },
    {
      "clip_ratio/high_max": 0.0026901003657258116,
      "clip_ratio/high_mean": 0.0010208458297711331,
      "clip_ratio/low_mean": 0.0011379824045434361,
      "clip_ratio/low_min": 5.9258822147967294e-05,
      "clip_ratio/region_mean": 0.0021588282907032408,
      "epoch": 0.11003972490068775,
      "grad_norm": 0.11636406928300858,
      "learning_rate": 1e-06,
      "loss": 0.064,
      "step": 1179
    },
    {
      "clip_ratio/high_max": 0.002761453826678917,
      "clip_ratio/high_mean": 0.0010801016542245634,
      "clip_ratio/low_mean": 0.0011200225344509818,
      "clip_ratio/low_min": 0.0002103312972394633,
      "clip_ratio/region_mean": 0.0022001242541591637,
      "epoch": 0.11013305800068833,
      "grad_norm": 0.11787573248147964,
      "learning_rate": 1e-06,
      "loss": 0.0462,
      "step": 1180
    },
    {
      "clip_ratio/high_max": 0.002421198856609408,
      "clip_ratio/high_mean": 0.0008848877150740009,
      "clip_ratio/low_mean": 0.001016052139675594,
      "clip_ratio/low_min": 3.873339119309094e-05,
      "clip_ratio/region_mean": 0.0019009398311027326,
      "epoch": 0.11022639110068891,
      "grad_norm": 0.10136258602142334,
      "learning_rate": 1e-06,
      "loss": 0.0275,
      "step": 1181
    },
    {
      "clip_ratio/high_max": 0.002572277211584151,
      "clip_ratio/high_mean": 0.0011720775219146162,
      "clip_ratio/low_mean": 0.0008886789528332883,
      "clip_ratio/low_min": 6.724361264787149e-05,
      "clip_ratio/region_mean": 0.002060756491118809,
      "epoch": 0.1103197242006895,
      "grad_norm": 0.12229104340076447,
      "learning_rate": 1e-06,
      "loss": 0.0244,
      "step": 1182
    },
    {
      "clip_ratio/high_max": 0.0020963844071957283,
      "clip_ratio/high_mean": 0.0008298370248667197,
      "clip_ratio/low_mean": 0.0011408174177631736,
      "clip_ratio/low_min": 0.00014471824943029787,
      "clip_ratio/region_mean": 0.0019706544626387767,
      "epoch": 0.11041305730069008,
      "grad_norm": 0.13758879899978638,
      "learning_rate": 1e-06,
      "loss": 0.0794,
      "step": 1183
    },
    {
      "clip_ratio/high_max": 0.0026509791568969376,
      "clip_ratio/high_mean": 0.0011043364720535465,
      "clip_ratio/low_mean": 0.0008642825578135671,
      "clip_ratio/low_min": 8.106119821604807e-05,
      "clip_ratio/region_mean": 0.001968619086255785,
      "epoch": 0.11050639040069067,
      "grad_norm": 0.10574328899383545,
      "learning_rate": 1e-06,
      "loss": -0.0136,
      "step": 1184
    },
    {
      "clip_ratio/high_max": 0.0027124802581965923,
      "clip_ratio/high_mean": 0.0010716210999817122,
      "clip_ratio/low_mean": 0.0011267261397733819,
      "clip_ratio/low_min": 4.273506056051701e-05,
      "clip_ratio/region_mean": 0.002198347225203179,
      "epoch": 0.11059972350069125,
      "grad_norm": 0.12926967442035675,
      "learning_rate": 1e-06,
      "loss": 0.0123,
      "step": 1185
    },
    {
      "clip_ratio/high_max": 0.003039923161850311,
      "clip_ratio/high_mean": 0.0012348273485258687,
      "clip_ratio/low_mean": 0.0010891843958233949,
      "clip_ratio/low_min": 0.0001114938404498389,
      "clip_ratio/region_mean": 0.0023240117443492636,
      "epoch": 0.11069305660069183,
      "grad_norm": 0.12365727871656418,
      "learning_rate": 1e-06,
      "loss": 0.0058,
      "step": 1186
    },
    {
      "clip_ratio/high_max": 0.003038015987840481,
      "clip_ratio/high_mean": 0.0012616448439075612,
      "clip_ratio/low_mean": 0.0010106407644343562,
      "clip_ratio/low_min": 3.537572411005385e-05,
      "clip_ratio/region_mean": 0.0022722855646861717,
      "epoch": 0.11078638970069242,
      "grad_norm": 0.12358976900577545,
      "learning_rate": 1e-06,
      "loss": -0.0162,
      "step": 1187
    },
    {
      "clip_ratio/high_max": 0.0023848461678426247,
      "clip_ratio/high_mean": 0.000884216262420523,
      "clip_ratio/low_mean": 0.0011999135531368665,
      "clip_ratio/low_min": 0.00010298970664734952,
      "clip_ratio/region_mean": 0.0020841298101004213,
      "epoch": 0.110879722800693,
      "grad_norm": 0.11596240103244781,
      "learning_rate": 1e-06,
      "loss": 0.0658,
      "step": 1188
    },
    {
      "clip_ratio/high_max": 0.0022402134018193465,
      "clip_ratio/high_mean": 0.0009440933226869674,
      "clip_ratio/low_mean": 0.001158672104793368,
      "clip_ratio/low_min": 0.00011200694098079111,
      "clip_ratio/region_mean": 0.0021027653929195367,
      "epoch": 0.11097305590069358,
      "grad_norm": 0.12584152817726135,
      "learning_rate": 1e-06,
      "loss": 0.0446,
      "step": 1189
    },
    {
      "clip_ratio/high_max": 0.0025912981291185133,
      "clip_ratio/high_mean": 0.0010761734238258214,
      "clip_ratio/low_mean": 0.0011078929419454653,
      "clip_ratio/low_min": 0.0001212302940984955,
      "clip_ratio/region_mean": 0.002184066404879559,
      "epoch": 0.11106638900069417,
      "grad_norm": 0.10775712877511978,
      "learning_rate": 1e-06,
      "loss": 0.0154,
      "step": 1190
    },
    {
      "clip_ratio/high_max": 0.002431743203487713,
      "clip_ratio/high_mean": 0.0010769440195872448,
      "clip_ratio/low_mean": 0.00115745762741426,
      "clip_ratio/low_min": 0.00011558580354176229,
      "clip_ratio/region_mean": 0.0022344017270370387,
      "epoch": 0.11115972210069475,
      "grad_norm": 0.1186540350317955,
      "learning_rate": 1e-06,
      "loss": 0.0433,
      "step": 1191
    },
    {
      "clip_ratio/high_max": 0.0027180488250451162,
      "clip_ratio/high_mean": 0.0011467203294159845,
      "clip_ratio/low_mean": 0.0011393007735023275,
      "clip_ratio/low_min": 5.3872015996603295e-05,
      "clip_ratio/region_mean": 0.0022860210519866087,
      "epoch": 0.11125305520069532,
      "grad_norm": 0.12269347161054611,
      "learning_rate": 1e-06,
      "loss": 0.0189,
      "step": 1192
    },
    {
      "clip_ratio/high_max": 0.00250194763430045,
      "clip_ratio/high_mean": 0.0010861757618840784,
      "clip_ratio/low_mean": 0.0011375939429854043,
      "clip_ratio/low_min": 0.00011869199624925386,
      "clip_ratio/region_mean": 0.0022237696321099065,
      "epoch": 0.11134638830069592,
      "grad_norm": 0.10908220708370209,
      "learning_rate": 1e-06,
      "loss": 0.0148,
      "step": 1193
    },
    {
      "clip_ratio/high_max": 0.0028957383692613803,
      "clip_ratio/high_mean": 0.0011445467389421538,
      "clip_ratio/low_mean": 0.0011427075478422921,
      "clip_ratio/low_min": 4.933065974910278e-05,
      "clip_ratio/region_mean": 0.002287254268594552,
      "epoch": 0.1114397214006965,
      "grad_norm": 0.12823274731636047,
      "learning_rate": 1e-06,
      "loss": -0.0085,
      "step": 1194
    },
    {
      "clip_ratio/high_max": 0.002681483281776309,
      "clip_ratio/high_mean": 0.0011821445768873673,
      "clip_ratio/low_mean": 0.0011066065490012988,
      "clip_ratio/low_min": 5.7073930292972364e-05,
      "clip_ratio/region_mean": 0.0022887511222506873,
      "epoch": 0.11153305450069709,
      "grad_norm": 0.11433789134025574,
      "learning_rate": 1e-06,
      "loss": 0.035,
      "step": 1195
    },
    {
      "clip_ratio/high_max": 0.0023891531163826585,
      "clip_ratio/high_mean": 0.0010262292780680582,
      "clip_ratio/low_mean": 0.0010906782663369086,
      "clip_ratio/low_min": 7.337635179283097e-05,
      "clip_ratio/region_mean": 0.0021169075698708184,
      "epoch": 0.11162638760069767,
      "grad_norm": 0.11177698522806168,
      "learning_rate": 1e-06,
      "loss": 0.0186,
      "step": 1196
    },
    {
      "clip_ratio/high_max": 0.002394787035882473,
      "clip_ratio/high_mean": 0.0009900727891363204,
      "clip_ratio/low_mean": 0.0009499857387709199,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0019400585370021872,
      "epoch": 0.11171972070069824,
      "grad_norm": 0.10699784755706787,
      "learning_rate": 1e-06,
      "loss": 0.0081,
      "step": 1197
    },
    {
      "clip_ratio/high_max": 0.002460182695358526,
      "clip_ratio/high_mean": 0.0010587245360511588,
      "clip_ratio/low_mean": 0.0011826245608972386,
      "clip_ratio/low_min": 0.0001090927926270524,
      "clip_ratio/region_mean": 0.0022413490805774927,
      "epoch": 0.11181305380069884,
      "grad_norm": 0.1167849525809288,
      "learning_rate": 1e-06,
      "loss": 0.066,
      "step": 1198
    },
    {
      "clip_ratio/high_max": 0.002818029279296752,
      "clip_ratio/high_mean": 0.001097101248888066,
      "clip_ratio/low_mean": 0.0010746394636953482,
      "clip_ratio/low_min": 8.465612881991547e-05,
      "clip_ratio/region_mean": 0.0021717406416428275,
      "epoch": 0.11190638690069941,
      "grad_norm": 0.11420687288045883,
      "learning_rate": 1e-06,
      "loss": 0.0098,
      "step": 1199
    },
    {
      "clip_ratio/high_max": 0.002425856677291449,
      "clip_ratio/high_mean": 0.0009930106371029979,
      "clip_ratio/low_mean": 0.00104721345451253,
      "clip_ratio/low_min": 7.833142899471568e-05,
      "clip_ratio/region_mean": 0.002040224091615528,
      "epoch": 0.11199972000069999,
      "grad_norm": 0.112687848508358,
      "learning_rate": 1e-06,
      "loss": -0.004,
      "step": 1200
    },
    {
      "clip_ratio/high_max": 0.0026552399067441,
      "clip_ratio/high_mean": 0.001172763244539965,
      "clip_ratio/low_mean": 0.0009646833277656697,
      "clip_ratio/low_min": 6.048934119462501e-05,
      "clip_ratio/region_mean": 0.00213744658685755,
      "epoch": 0.11209305310070058,
      "grad_norm": 0.10748311877250671,
      "learning_rate": 1e-06,
      "loss": -0.0325,
      "step": 1201
    },
    {
      "clip_ratio/high_max": 0.0028617993521038443,
      "clip_ratio/high_mean": 0.0011784493435698096,
      "clip_ratio/low_mean": 0.0010744831679403433,
      "clip_ratio/low_min": 4.813675332115963e-05,
      "clip_ratio/region_mean": 0.002252932477858849,
      "epoch": 0.11218638620070116,
      "grad_norm": 0.11108695715665817,
      "learning_rate": 1e-06,
      "loss": 0.0023,
      "step": 1202
    },
    {
      "clip_ratio/high_max": 0.0023855465260567144,
      "clip_ratio/high_mean": 0.0010530286399443867,
      "clip_ratio/low_mean": 0.001124067030104925,
      "clip_ratio/low_min": 9.296734515373828e-05,
      "clip_ratio/region_mean": 0.002177095666411333,
      "epoch": 0.11227971930070174,
      "grad_norm": 0.12072212994098663,
      "learning_rate": 1e-06,
      "loss": 0.0305,
      "step": 1203
    },
    {
      "clip_ratio/high_max": 0.002847674175427528,
      "clip_ratio/high_mean": 0.0011625915067270398,
      "clip_ratio/low_mean": 0.0011322244063194375,
      "clip_ratio/low_min": 5.276225601846818e-05,
      "clip_ratio/region_mean": 0.002294815865752753,
      "epoch": 0.11237305240070233,
      "grad_norm": 0.13078653812408447,
      "learning_rate": 1e-06,
      "loss": 0.025,
      "step": 1204
    },
    {
      "clip_ratio/high_max": 0.0024592020781710744,
      "clip_ratio/high_mean": 0.0009955171444744337,
      "clip_ratio/low_mean": 0.001339192567684222,
      "clip_ratio/low_min": 0.00012011306171189062,
      "clip_ratio/region_mean": 0.002334709723072592,
      "epoch": 0.11246638550070291,
      "grad_norm": 0.1268586814403534,
      "learning_rate": 1e-06,
      "loss": 0.0436,
      "step": 1205
    },
    {
      "clip_ratio/high_max": 0.002364511958148796,
      "clip_ratio/high_mean": 0.00107653147460951,
      "clip_ratio/low_mean": 0.0011547120611794526,
      "clip_ratio/low_min": 0.0001686973173491424,
      "clip_ratio/region_mean": 0.0022312435394269414,
      "epoch": 0.1125597186007035,
      "grad_norm": 0.12013255059719086,
      "learning_rate": 1e-06,
      "loss": 0.0272,
      "step": 1206
    },
    {
      "clip_ratio/high_max": 0.002810508587572258,
      "clip_ratio/high_mean": 0.0011008361052518012,
      "clip_ratio/low_mean": 0.0012866086490248563,
      "clip_ratio/low_min": 4.414697286847513e-05,
      "clip_ratio/region_mean": 0.002387444765190594,
      "epoch": 0.11265305170070408,
      "grad_norm": 0.1061701849102974,
      "learning_rate": 1e-06,
      "loss": 0.0126,
      "step": 1207
    },
    {
      "clip_ratio/high_max": 0.002492391831765417,
      "clip_ratio/high_mean": 0.001137933533755131,
      "clip_ratio/low_mean": 0.0010346618673793273,
      "clip_ratio/low_min": 0.00016255233185802354,
      "clip_ratio/region_mean": 0.0021725954284192994,
      "epoch": 0.11274638480070466,
      "grad_norm": 0.1131354421377182,
      "learning_rate": 1e-06,
      "loss": -0.0271,
      "step": 1208
    },
    {
      "clip_ratio/high_max": 0.0026482728535484057,
      "clip_ratio/high_mean": 0.0011294639216430369,
      "clip_ratio/low_mean": 0.0011897526728716912,
      "clip_ratio/low_min": 7.585861749248579e-05,
      "clip_ratio/region_mean": 0.0023192165317595936,
      "epoch": 0.11283971790070525,
      "grad_norm": 0.12359905987977982,
      "learning_rate": 1e-06,
      "loss": 0.0121,
      "step": 1209
    },
    {
      "clip_ratio/high_max": 0.0024440104971290566,
      "clip_ratio/high_mean": 0.0011161999900650699,
      "clip_ratio/low_mean": 0.0012108633454772644,
      "clip_ratio/low_min": 0.00013863556250726106,
      "clip_ratio/region_mean": 0.002327063339180313,
      "epoch": 0.11293305100070583,
      "grad_norm": 0.11111761629581451,
      "learning_rate": 1e-06,
      "loss": 0.0163,
      "step": 1210
    },
    {
      "clip_ratio/high_max": 0.0029320836038095877,
      "clip_ratio/high_mean": 0.001194272601424018,
      "clip_ratio/low_mean": 0.0012606735308509087,
      "clip_ratio/low_min": 6.907318675075658e-05,
      "clip_ratio/region_mean": 0.0024549460722482763,
      "epoch": 0.11302638410070641,
      "grad_norm": 0.11577598750591278,
      "learning_rate": 1e-06,
      "loss": 0.0136,
      "step": 1211
    },
    {
      "clip_ratio/high_max": 0.002413258989690803,
      "clip_ratio/high_mean": 0.0011087110833614133,
      "clip_ratio/low_mean": 0.0012625925155589357,
      "clip_ratio/low_min": 0.000203817498004355,
      "clip_ratio/region_mean": 0.002371303620748222,
      "epoch": 0.113119717200707,
      "grad_norm": 0.11881434172391891,
      "learning_rate": 1e-06,
      "loss": 0.0209,
      "step": 1212
    },
    {
      "clip_ratio/high_max": 0.002713003232202027,
      "clip_ratio/high_mean": 0.001119829361414304,
      "clip_ratio/low_mean": 0.0011212391655135434,
      "clip_ratio/low_min": 2.8261732950340956e-05,
      "clip_ratio/region_mean": 0.0022410686215152964,
      "epoch": 0.11321305030070758,
      "grad_norm": 0.10956117510795593,
      "learning_rate": 1e-06,
      "loss": 0.0131,
      "step": 1213
    },
    {
      "clip_ratio/high_max": 0.002357284181925934,
      "clip_ratio/high_mean": 0.0010268216719850898,
      "clip_ratio/low_mean": 0.0013034044604864903,
      "clip_ratio/low_min": 0.00017426836348022334,
      "clip_ratio/region_mean": 0.0023302261470234953,
      "epoch": 0.11330638340070817,
      "grad_norm": 0.1119605153799057,
      "learning_rate": 1e-06,
      "loss": 0.0272,
      "step": 1214
    },
    {
      "clip_ratio/high_max": 0.0025026722796610557,
      "clip_ratio/high_mean": 0.001099099430575734,
      "clip_ratio/low_mean": 0.0009610571796656586,
      "clip_ratio/low_min": 2.4329051484528463e-05,
      "clip_ratio/region_mean": 0.0020601566357072443,
      "epoch": 0.11339971650070875,
      "grad_norm": 0.11132616549730301,
      "learning_rate": 1e-06,
      "loss": 0.0187,
      "step": 1215
    },
    {
      "clip_ratio/high_max": 0.002510435779186082,
      "clip_ratio/high_mean": 0.0010765408451334224,
      "clip_ratio/low_mean": 0.0011286608241789509,
      "clip_ratio/low_min": 6.877381201775279e-05,
      "clip_ratio/region_mean": 0.0022052016720408574,
      "epoch": 0.11349304960070933,
      "grad_norm": 0.11213754117488861,
      "learning_rate": 1e-06,
      "loss": 0.0254,
      "step": 1216
    },
    {
      "clip_ratio/high_max": 0.002374637821048964,
      "clip_ratio/high_mean": 0.0011195650931767887,
      "clip_ratio/low_mean": 0.0010895597406488378,
      "clip_ratio/low_min": 0.00017216658852703404,
      "clip_ratio/region_mean": 0.0022091248756623827,
      "epoch": 0.11358638270070992,
      "grad_norm": 0.11881782114505768,
      "learning_rate": 1e-06,
      "loss": -0.0014,
      "step": 1217
    },
    {
      "clip_ratio/high_max": 0.002377979391894769,
      "clip_ratio/high_mean": 0.0010857104280148633,
      "clip_ratio/low_mean": 0.0012226139442645945,
      "clip_ratio/low_min": 0.00013999407201481517,
      "clip_ratio/region_mean": 0.0023083243722794577,
      "epoch": 0.1136797158007105,
      "grad_norm": 0.11346249282360077,
      "learning_rate": 1e-06,
      "loss": 0.0499,
      "step": 1218
    },
    {
      "clip_ratio/high_max": 0.0024042427467065863,
      "clip_ratio/high_mean": 0.0010952568009088282,
      "clip_ratio/low_mean": 0.0013081053402856924,
      "clip_ratio/low_min": 0.00011137879482703283,
      "clip_ratio/region_mean": 0.002403362130280584,
      "epoch": 0.11377304890071108,
      "grad_norm": 0.11177940666675568,
      "learning_rate": 1e-06,
      "loss": 0.0116,
      "step": 1219
    },
    {
      "clip_ratio/high_max": 0.0025204455014318228,
      "clip_ratio/high_mean": 0.0010780549309856724,
      "clip_ratio/low_mean": 0.001270218737772666,
      "clip_ratio/low_min": 0.00018541646204539575,
      "clip_ratio/region_mean": 0.0023482737378799357,
      "epoch": 0.11386638200071167,
      "grad_norm": 0.11209125071763992,
      "learning_rate": 1e-06,
      "loss": 0.0026,
      "step": 1220
    },
    {
      "clip_ratio/high_max": 0.002907198140746914,
      "clip_ratio/high_mean": 0.001148980756624951,
      "clip_ratio/low_mean": 0.0009508351067779586,
      "clip_ratio/low_min": 0.00011329497647238895,
      "clip_ratio/region_mean": 0.0020998158724978566,
      "epoch": 0.11395971510071225,
      "grad_norm": 0.12342007458209991,
      "learning_rate": 1e-06,
      "loss": 0.009,
      "step": 1221
    },
    {
      "clip_ratio/high_max": 0.0024654370427015238,
      "clip_ratio/high_mean": 0.0010780396587506402,
      "clip_ratio/low_mean": 0.001451374962925911,
      "clip_ratio/low_min": 7.036116858216701e-05,
      "clip_ratio/region_mean": 0.0025294147053500637,
      "epoch": 0.11405304820071283,
      "grad_norm": 0.10980355739593506,
      "learning_rate": 1e-06,
      "loss": 0.0583,
      "step": 1222
    },
    {
      "clip_ratio/high_max": 0.0027817566369776614,
      "clip_ratio/high_mean": 0.001279632906516781,
      "clip_ratio/low_mean": 0.0011250143852521433,
      "clip_ratio/low_min": 5.3364360610430595e-05,
      "clip_ratio/region_mean": 0.0024046473554335535,
      "epoch": 0.11414638130071342,
      "grad_norm": 0.11107853055000305,
      "learning_rate": 1e-06,
      "loss": 0.0267,
      "step": 1223
    },
    {
      "clip_ratio/high_max": 0.002143105535651557,
      "clip_ratio/high_mean": 0.0009024186274473323,
      "clip_ratio/low_mean": 0.0011317859098198824,
      "clip_ratio/low_min": 0.00016458829577459255,
      "clip_ratio/region_mean": 0.0020342045318102464,
      "epoch": 0.114239714400714,
      "grad_norm": 0.11549653857946396,
      "learning_rate": 1e-06,
      "loss": 0.0252,
      "step": 1224
    },
    {
      "clip_ratio/high_max": 0.002626558351039421,
      "clip_ratio/high_mean": 0.001059851785612409,
      "clip_ratio/low_mean": 0.0010941274922515731,
      "clip_ratio/low_min": 5.223984953772742e-05,
      "clip_ratio/region_mean": 0.002153979272407014,
      "epoch": 0.11433304750071459,
      "grad_norm": 0.12288986146450043,
      "learning_rate": 1e-06,
      "loss": 0.0386,
      "step": 1225
    },
    {
      "clip_ratio/high_max": 0.003055918372410815,
      "clip_ratio/high_mean": 0.001187608351756353,
      "clip_ratio/low_mean": 0.0013058970871497877,
      "clip_ratio/low_min": 0.00016501074242114555,
      "clip_ratio/region_mean": 0.0024935054389061406,
      "epoch": 0.11442638060071517,
      "grad_norm": 0.12508055567741394,
      "learning_rate": 1e-06,
      "loss": 0.0487,
      "step": 1226
    },
    {
      "clip_ratio/high_max": 0.002487231518898625,
      "clip_ratio/high_mean": 0.0010719842903199606,
      "clip_ratio/low_mean": 0.0010408343578092172,
      "clip_ratio/low_min": 1.759572114679031e-05,
      "clip_ratio/region_mean": 0.002112818619934842,
      "epoch": 0.11451971370071574,
      "grad_norm": 0.09493252635002136,
      "learning_rate": 1e-06,
      "loss": 0.0066,
      "step": 1227
    },
    {
      "clip_ratio/high_max": 0.002374014860833995,
      "clip_ratio/high_mean": 0.0010484732974873623,
      "clip_ratio/low_mean": 0.0012189659973955713,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002267439318529796,
      "epoch": 0.11461304680071634,
      "grad_norm": 0.10654571652412415,
      "learning_rate": 1e-06,
      "loss": 0.0278,
      "step": 1228
    },
    {
      "clip_ratio/high_max": 0.002509802689019125,
      "clip_ratio/high_mean": 0.001009592013360816,
      "clip_ratio/low_mean": 0.0011653611109068152,
      "clip_ratio/low_min": 6.169331390992738e-05,
      "clip_ratio/region_mean": 0.002174953064240981,
      "epoch": 0.11470637990071691,
      "grad_norm": 0.10817123204469681,
      "learning_rate": 1e-06,
      "loss": 0.087,
      "step": 1229
    },
    {
      "clip_ratio/high_max": 0.0023047270078677684,
      "clip_ratio/high_mean": 0.0010717355617089197,
      "clip_ratio/low_mean": 0.0012827192185795866,
      "clip_ratio/low_min": 8.209105726564303e-05,
      "clip_ratio/region_mean": 0.0023544548166682944,
      "epoch": 0.1147997130007175,
      "grad_norm": 0.13143272697925568,
      "learning_rate": 1e-06,
      "loss": 0.0102,
      "step": 1230
    },
    {
      "clip_ratio/high_max": 0.002837826672475785,
      "clip_ratio/high_mean": 0.0011027122345694806,
      "clip_ratio/low_mean": 0.0010226727808912983,
      "clip_ratio/low_min": 0.00017012880198308267,
      "clip_ratio/region_mean": 0.0021253850136417896,
      "epoch": 0.11489304610071809,
      "grad_norm": 0.1140839084982872,
      "learning_rate": 1e-06,
      "loss": 0.0186,
      "step": 1231
    },
    {
      "clip_ratio/high_max": 0.0028421363240340725,
      "clip_ratio/high_mean": 0.0013222473535279278,
      "clip_ratio/low_mean": 0.0011667769504128955,
      "clip_ratio/low_min": 6.35658389001037e-05,
      "clip_ratio/region_mean": 0.0024890242639230564,
      "epoch": 0.11498637920071866,
      "grad_norm": 0.12433359026908875,
      "learning_rate": 1e-06,
      "loss": -0.0019,
      "step": 1232
    },
    {
      "clip_ratio/high_max": 0.002858025320165325,
      "clip_ratio/high_mean": 0.0011508914467412978,
      "clip_ratio/low_mean": 0.001295942667638883,
      "clip_ratio/low_min": 0.0001240560495716636,
      "clip_ratio/region_mean": 0.002446834070724435,
      "epoch": 0.11507971230071924,
      "grad_norm": 0.11896398663520813,
      "learning_rate": 1e-06,
      "loss": 0.0288,
      "step": 1233
    },
    {
      "clip_ratio/high_max": 0.0029834737651981413,
      "clip_ratio/high_mean": 0.0013063383048574906,
      "clip_ratio/low_mean": 0.0011824090233858442,
      "clip_ratio/low_min": 7.498757895518793e-05,
      "clip_ratio/region_mean": 0.002488747355528176,
      "epoch": 0.11517304540071983,
      "grad_norm": 0.1223648339509964,
      "learning_rate": 1e-06,
      "loss": -0.0056,
      "step": 1234
    },
    {
      "clip_ratio/high_max": 0.0026859227582463063,
      "clip_ratio/high_mean": 0.0012197845499031246,
      "clip_ratio/low_mean": 0.0012004819072899409,
      "clip_ratio/low_min": 2.5783829187275842e-05,
      "clip_ratio/region_mean": 0.0024202664571930654,
      "epoch": 0.11526637850072041,
      "grad_norm": 0.11144250631332397,
      "learning_rate": 1e-06,
      "loss": -0.001,
      "step": 1235
    },
    {
      "clip_ratio/high_max": 0.0024210904448409565,
      "clip_ratio/high_mean": 0.0009808355289351312,
      "clip_ratio/low_mean": 0.0012403303444443736,
      "clip_ratio/low_min": 0.00012106583926652092,
      "clip_ratio/region_mean": 0.002221165836090222,
      "epoch": 0.115359711600721,
      "grad_norm": 0.11551078408956528,
      "learning_rate": 1e-06,
      "loss": 0.0356,
      "step": 1236
    },
    {
      "clip_ratio/high_max": 0.002920305007137358,
      "clip_ratio/high_mean": 0.001245065202965634,
      "clip_ratio/low_mean": 0.0011656327660602983,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0024106979253701866,
      "epoch": 0.11545304470072158,
      "grad_norm": 0.1116659939289093,
      "learning_rate": 1e-06,
      "loss": -0.0062,
      "step": 1237
    },
    {
      "clip_ratio/high_max": 0.002577817314886488,
      "clip_ratio/high_mean": 0.0010785205613501603,
      "clip_ratio/low_mean": 0.0011799832682299893,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002258503831399139,
      "epoch": 0.11554637780072216,
      "grad_norm": 0.11359122395515442,
      "learning_rate": 1e-06,
      "loss": 0.0212,
      "step": 1238
    },
    {
      "clip_ratio/high_max": 0.0031608296631020494,
      "clip_ratio/high_mean": 0.0011929350766877178,
      "clip_ratio/low_mean": 0.001161477073765127,
      "clip_ratio/low_min": 0.00010525904872338288,
      "clip_ratio/region_mean": 0.0023544121795566753,
      "epoch": 0.11563971090072275,
      "grad_norm": 0.1082422137260437,
      "learning_rate": 1e-06,
      "loss": 0.0178,
      "step": 1239
    },
    {
      "clip_ratio/high_max": 0.00226152062532492,
      "clip_ratio/high_mean": 0.001028628483254579,
      "clip_ratio/low_mean": 0.0012177384523965884,
      "clip_ratio/low_min": 0.00010344469046685845,
      "clip_ratio/region_mean": 0.0022463669192802627,
      "epoch": 0.11573304400072333,
      "grad_norm": 0.1235145777463913,
      "learning_rate": 1e-06,
      "loss": 0.0399,
      "step": 1240
    },
    {
      "clip_ratio/high_max": 0.0025888833552016877,
      "clip_ratio/high_mean": 0.0011082125311077107,
      "clip_ratio/low_mean": 0.0013110085601510946,
      "clip_ratio/low_min": 0.00019853362937283237,
      "clip_ratio/region_mean": 0.0024192210330511443,
      "epoch": 0.11582637710072391,
      "grad_norm": 0.1176135390996933,
      "learning_rate": 1e-06,
      "loss": 0.0554,
      "step": 1241
    },
    {
      "clip_ratio/high_max": 0.0025159292927128263,
      "clip_ratio/high_mean": 0.0011307577733532526,
      "clip_ratio/low_mean": 0.0011334201954014134,
      "clip_ratio/low_min": 5.870101995242294e-05,
      "clip_ratio/region_mean": 0.002264177950564772,
      "epoch": 0.1159197102007245,
      "grad_norm": 0.21855543553829193,
      "learning_rate": 1e-06,
      "loss": 0.0366,
      "step": 1242
    },
    {
      "clip_ratio/high_max": 0.0027163535414729267,
      "clip_ratio/high_mean": 0.0011778916195908096,
      "clip_ratio/low_mean": 0.0011235247147851624,
      "clip_ratio/low_min": 5.8103820265387185e-05,
      "clip_ratio/region_mean": 0.002301416352565866,
      "epoch": 0.11601304330072508,
      "grad_norm": 0.11948242783546448,
      "learning_rate": 1e-06,
      "loss": 0.0043,
      "step": 1243
    },
    {
      "clip_ratio/high_max": 0.0030192918711691163,
      "clip_ratio/high_mean": 0.0012100219064450357,
      "clip_ratio/low_mean": 0.0012370348813419696,
      "clip_ratio/low_min": 0.00017882119936984964,
      "clip_ratio/region_mean": 0.0024470567805110477,
      "epoch": 0.11610637640072566,
      "grad_norm": 0.11817143857479095,
      "learning_rate": 1e-06,
      "loss": 0.0076,
      "step": 1244
    },
    {
      "clip_ratio/high_max": 0.002700486373214517,
      "clip_ratio/high_mean": 0.0010983870961354114,
      "clip_ratio/low_mean": 0.0012288219295442104,
      "clip_ratio/low_min": 8.856002023094334e-05,
      "clip_ratio/region_mean": 0.0023272090547834523,
      "epoch": 0.11619970950072625,
      "grad_norm": 0.13108079135417938,
      "learning_rate": 1e-06,
      "loss": -0.0057,
      "step": 1245
    },
    {
      "clip_ratio/high_max": 0.002508375415345654,
      "clip_ratio/high_mean": 0.001042072781274328,
      "clip_ratio/low_mean": 0.001193254574900493,
      "clip_ratio/low_min": 0.00010190653847530484,
      "clip_ratio/region_mean": 0.002235327374364715,
      "epoch": 0.11629304260072683,
      "grad_norm": 0.1131974533200264,
      "learning_rate": 1e-06,
      "loss": 0.0278,
      "step": 1246
    },
    {
      "clip_ratio/high_max": 0.002657712480868213,
      "clip_ratio/high_mean": 0.0012290649574424606,
      "clip_ratio/low_mean": 0.0013168034820409957,
      "clip_ratio/low_min": 0.0001341599036095431,
      "clip_ratio/region_mean": 0.002545868410379626,
      "epoch": 0.11638637570072742,
      "grad_norm": 0.10812344402074814,
      "learning_rate": 1e-06,
      "loss": 0.0095,
      "step": 1247
    },
    {
      "clip_ratio/high_max": 0.002726197002630215,
      "clip_ratio/high_mean": 0.0011453978841018397,
      "clip_ratio/low_mean": 0.0014631268313678447,
      "clip_ratio/low_min": 4.452624125406146e-05,
      "clip_ratio/region_mean": 0.0026085248246090487,
      "epoch": 0.116479708800728,
      "grad_norm": 0.1212625801563263,
      "learning_rate": 1e-06,
      "loss": 0.04,
      "step": 1248
    },
    {
      "clip_ratio/high_max": 0.003043636112124659,
      "clip_ratio/high_mean": 0.0011938805328099988,
      "clip_ratio/low_mean": 0.0014511906229017768,
      "clip_ratio/low_min": 0.00010345144255552441,
      "clip_ratio/region_mean": 0.0026450710865901783,
      "epoch": 0.11657304190072858,
      "grad_norm": 0.11640874296426773,
      "learning_rate": 1e-06,
      "loss": 0.0203,
      "step": 1249
    },
    {
      "clip_ratio/high_max": 0.002968999164295383,
      "clip_ratio/high_mean": 0.0013741601069341414,
      "clip_ratio/low_mean": 0.0013523021807486657,
      "clip_ratio/low_min": 0.0001274940004805103,
      "clip_ratio/region_mean": 0.0027264622185612097,
      "epoch": 0.11666637500072917,
      "grad_norm": 0.11351455748081207,
      "learning_rate": 1e-06,
      "loss": 0.0063,
      "step": 1250
    },
    {
      "clip_ratio/high_max": 0.0026110495819011703,
      "clip_ratio/high_mean": 0.0010721962080424419,
      "clip_ratio/low_mean": 0.0011775215289162588,
      "clip_ratio/low_min": 8.510787483828608e-05,
      "clip_ratio/region_mean": 0.0022497176832985133,
      "epoch": 0.11675970810072975,
      "grad_norm": 0.1033560186624527,
      "learning_rate": 1e-06,
      "loss": 0.0082,
      "step": 1251
    },
    {
      "clip_ratio/high_max": 0.0027876603744516615,
      "clip_ratio/high_mean": 0.0011413539505156223,
      "clip_ratio/low_mean": 0.0013970071740914136,
      "clip_ratio/low_min": 9.984825373976491e-05,
      "clip_ratio/region_mean": 0.002538361106417142,
      "epoch": 0.11685304120073033,
      "grad_norm": 0.1232597753405571,
      "learning_rate": 1e-06,
      "loss": 0.0044,
      "step": 1252
    },
    {
      "clip_ratio/high_max": 0.0024598976015113294,
      "clip_ratio/high_mean": 0.0010205740181845613,
      "clip_ratio/low_mean": 0.001317896956607001,
      "clip_ratio/low_min": 0.00016895811677386519,
      "clip_ratio/region_mean": 0.0023384709857054986,
      "epoch": 0.11694637430073092,
      "grad_norm": 0.1106187179684639,
      "learning_rate": 1e-06,
      "loss": 0.0595,
      "step": 1253
    },
    {
      "clip_ratio/high_max": 0.0024557662254665047,
      "clip_ratio/high_mean": 0.0011004724274243927,
      "clip_ratio/low_mean": 0.0012089501205991837,
      "clip_ratio/low_min": 0.00011404952419979963,
      "clip_ratio/region_mean": 0.0023094226053217426,
      "epoch": 0.1170397074007315,
      "grad_norm": 0.11428594589233398,
      "learning_rate": 1e-06,
      "loss": 0.0346,
      "step": 1254
    },
    {
      "clip_ratio/high_max": 0.0028476766528910957,
      "clip_ratio/high_mean": 0.0011265062785241753,
      "clip_ratio/low_mean": 0.0014320096834126161,
      "clip_ratio/low_min": 0.00011900360959771206,
      "clip_ratio/region_mean": 0.0025585159310139716,
      "epoch": 0.11713304050073207,
      "grad_norm": 0.11334823817014694,
      "learning_rate": 1e-06,
      "loss": 0.0491,
      "step": 1255
    },
    {
      "clip_ratio/high_max": 0.002735421781835612,
      "clip_ratio/high_mean": 0.0011139361240566359,
      "clip_ratio/low_mean": 0.0012695090517809149,
      "clip_ratio/low_min": 0.00012365471775410697,
      "clip_ratio/region_mean": 0.002383445178566035,
      "epoch": 0.11722637360073267,
      "grad_norm": 0.10950180143117905,
      "learning_rate": 1e-06,
      "loss": 0.0195,
      "step": 1256
    },
    {
      "clip_ratio/high_max": 0.0029859409405617043,
      "clip_ratio/high_mean": 0.0012715082957583945,
      "clip_ratio/low_mean": 0.0011775784496421693,
      "clip_ratio/low_min": 2.7861287890118547e-05,
      "clip_ratio/region_mean": 0.0024490867217537016,
      "epoch": 0.11731970670073325,
      "grad_norm": 0.13847064971923828,
      "learning_rate": 1e-06,
      "loss": -0.0137,
      "step": 1257
    },
    {
      "clip_ratio/high_max": 0.002971746445837198,
      "clip_ratio/high_mean": 0.0012477363616199,
      "clip_ratio/low_mean": 0.0012153943607700057,
      "clip_ratio/low_min": 0.00013913389011577237,
      "clip_ratio/region_mean": 0.002463130746036768,
      "epoch": 0.11741303980073384,
      "grad_norm": 0.25400254130363464,
      "learning_rate": 1e-06,
      "loss": 0.0225,
      "step": 1258
    },
    {
      "clip_ratio/high_max": 0.0024867820902727544,
      "clip_ratio/high_mean": 0.0011244415218243375,
      "clip_ratio/low_mean": 0.0012977943297300953,
      "clip_ratio/low_min": 5.330502062861342e-05,
      "clip_ratio/region_mean": 0.0024222358551924117,
      "epoch": 0.11750637290073442,
      "grad_norm": 0.10334615409374237,
      "learning_rate": 1e-06,
      "loss": 0.0368,
      "step": 1259
    },
    {
      "clip_ratio/high_max": 0.002701937635720242,
      "clip_ratio/high_mean": 0.0011171300920977956,
      "clip_ratio/low_mean": 0.0014942523157515097,
      "clip_ratio/low_min": 0.00023630415125808213,
      "clip_ratio/region_mean": 0.0026113824278581887,
      "epoch": 0.117599706000735,
      "grad_norm": 0.11032275855541229,
      "learning_rate": 1e-06,
      "loss": 0.0342,
      "step": 1260
    },
    {
      "clip_ratio/high_max": 0.0025608039650251158,
      "clip_ratio/high_mean": 0.0011437597167969216,
      "clip_ratio/low_mean": 0.0013113924251229037,
      "clip_ratio/low_min": 0.00012246981896169018,
      "clip_ratio/region_mean": 0.0024551521419198252,
      "epoch": 0.11769303910073559,
      "grad_norm": 0.11309037357568741,
      "learning_rate": 1e-06,
      "loss": 0.0111,
      "step": 1261
    },
    {
      "clip_ratio/high_max": 0.002589380521385465,
      "clip_ratio/high_mean": 0.0011820303407148458,
      "clip_ratio/low_mean": 0.0013472383361659013,
      "clip_ratio/low_min": 6.480483898485545e-05,
      "clip_ratio/region_mean": 0.0025292686113971286,
      "epoch": 0.11778637220073616,
      "grad_norm": 0.12196750193834305,
      "learning_rate": 1e-06,
      "loss": 0.043,
      "step": 1262
    },
    {
      "clip_ratio/high_max": 0.0033571323147043586,
      "clip_ratio/high_mean": 0.001306992964600795,
      "clip_ratio/low_mean": 0.0012608893266587984,
      "clip_ratio/low_min": 1.7443482647649944e-05,
      "clip_ratio/region_mean": 0.0025678823367343284,
      "epoch": 0.11787970530073674,
      "grad_norm": 0.11040571331977844,
      "learning_rate": 1e-06,
      "loss": 0.0159,
      "step": 1263
    },
    {
      "clip_ratio/high_max": 0.002608313436212484,
      "clip_ratio/high_mean": 0.0010171768517466262,
      "clip_ratio/low_mean": 0.0012925037626700941,
      "clip_ratio/low_min": 5.325947859091684e-05,
      "clip_ratio/region_mean": 0.0023096806326066144,
      "epoch": 0.11797303840073733,
      "grad_norm": 0.11099119484424591,
      "learning_rate": 1e-06,
      "loss": 0.0894,
      "step": 1264
    },
    {
      "clip_ratio/high_max": 0.003116911648248788,
      "clip_ratio/high_mean": 0.0011670192616293207,
      "clip_ratio/low_mean": 0.0012749529087159317,
      "clip_ratio/low_min": 6.943041626072954e-05,
      "clip_ratio/region_mean": 0.0024419721885351464,
      "epoch": 0.11806637150073791,
      "grad_norm": 0.11448632925748825,
      "learning_rate": 1e-06,
      "loss": 0.0446,
      "step": 1265
    },
    {
      "clip_ratio/high_max": 0.002724581594520714,
      "clip_ratio/high_mean": 0.0011624906546785496,
      "clip_ratio/low_mean": 0.001213326169818174,
      "clip_ratio/low_min": 1.5217920918075833e-05,
      "clip_ratio/region_mean": 0.0023758168463245966,
      "epoch": 0.1181597046007385,
      "grad_norm": 0.11675304919481277,
      "learning_rate": 1e-06,
      "loss": 0.0414,
      "step": 1266
    },
    {
      "clip_ratio/high_max": 0.0031477264710702,
      "clip_ratio/high_mean": 0.001277949808354606,
      "clip_ratio/low_mean": 0.0013949320564279333,
      "clip_ratio/low_min": 5.5809789955674205e-05,
      "clip_ratio/region_mean": 0.0026728818338597193,
      "epoch": 0.11825303770073908,
      "grad_norm": 0.11598726361989975,
      "learning_rate": 1e-06,
      "loss": 0.005,
      "step": 1267
    },
    {
      "clip_ratio/high_max": 0.0032902609746088274,
      "clip_ratio/high_mean": 0.0013908240071032196,
      "clip_ratio/low_mean": 0.0012551409927255008,
      "clip_ratio/low_min": 4.173062370682601e-05,
      "clip_ratio/region_mean": 0.0026459649816388264,
      "epoch": 0.11834637080073966,
      "grad_norm": 0.1187095046043396,
      "learning_rate": 1e-06,
      "loss": -0.01,
      "step": 1268
    },
    {
      "clip_ratio/high_max": 0.0027369569215807132,
      "clip_ratio/high_mean": 0.0011593812832870753,
      "clip_ratio/low_mean": 0.0013337703494471498,
      "clip_ratio/low_min": 0.00010947536611638498,
      "clip_ratio/region_mean": 0.0024931516309152357,
      "epoch": 0.11843970390074025,
      "grad_norm": 0.1019117459654808,
      "learning_rate": 1e-06,
      "loss": 0.025,
      "step": 1269
    },
    {
      "clip_ratio/high_max": 0.003011727865668945,
      "clip_ratio/high_mean": 0.001362494640488876,
      "clip_ratio/low_mean": 0.0012878921734227333,
      "clip_ratio/low_min": 7.200618165370543e-05,
      "clip_ratio/region_mean": 0.0026503868066356517,
      "epoch": 0.11853303700074083,
      "grad_norm": 0.11724326759576797,
      "learning_rate": 1e-06,
      "loss": 0.0091,
      "step": 1270
    },
    {
      "clip_ratio/high_max": 0.0026873566457652487,
      "clip_ratio/high_mean": 0.0011771650388254784,
      "clip_ratio/low_mean": 0.0012928696905873949,
      "clip_ratio/low_min": 9.021845107781701e-05,
      "clip_ratio/region_mean": 0.0024700347130419686,
      "epoch": 0.11862637010074141,
      "grad_norm": 0.1181105300784111,
      "learning_rate": 1e-06,
      "loss": 0.0419,
      "step": 1271
    },
    {
      "clip_ratio/high_max": 0.002751998181338422,
      "clip_ratio/high_mean": 0.001230129593750462,
      "clip_ratio/low_mean": 0.0011646008606476244,
      "clip_ratio/low_min": 6.25976244919002e-05,
      "clip_ratio/region_mean": 0.0023947304653120227,
      "epoch": 0.118719703200742,
      "grad_norm": 0.15212400257587433,
      "learning_rate": 1e-06,
      "loss": 0.0116,
      "step": 1272
    },
    {
      "clip_ratio/high_max": 0.00277440019272035,
      "clip_ratio/high_mean": 0.001213189087138744,
      "clip_ratio/low_mean": 0.0013494054073817097,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0025625945199863054,
      "epoch": 0.11881303630074258,
      "grad_norm": 0.12205009162425995,
      "learning_rate": 1e-06,
      "loss": 0.0167,
      "step": 1273
    },
    {
      "clip_ratio/high_max": 0.0026543722706264816,
      "clip_ratio/high_mean": 0.0010807045255205594,
      "clip_ratio/low_mean": 0.0011866507338709198,
      "clip_ratio/low_min": 5.900519681745209e-05,
      "clip_ratio/region_mean": 0.002267355281219352,
      "epoch": 0.11890636940074316,
      "grad_norm": 0.11266744136810303,
      "learning_rate": 1e-06,
      "loss": 0.0367,
      "step": 1274
    },
    {
      "clip_ratio/high_max": 0.0026573524592095055,
      "clip_ratio/high_mean": 0.0012090996824554168,
      "clip_ratio/low_mean": 0.0011447728320490569,
      "clip_ratio/low_min": 1.5903307939879596e-05,
      "clip_ratio/region_mean": 0.0023538724781246856,
      "epoch": 0.11899970250074375,
      "grad_norm": 0.11570925265550613,
      "learning_rate": 1e-06,
      "loss": 0.0172,
      "step": 1275
    },
    {
      "clip_ratio/high_max": 0.002645457032485865,
      "clip_ratio/high_mean": 0.0011059771932195872,
      "clip_ratio/low_mean": 0.0014449966365646105,
      "clip_ratio/low_min": 9.428643625142286e-05,
      "clip_ratio/region_mean": 0.0025509738188702613,
      "epoch": 0.11909303560074433,
      "grad_norm": 0.11842282116413116,
      "learning_rate": 1e-06,
      "loss": 0.0711,
      "step": 1276
    },
    {
      "clip_ratio/high_max": 0.00260804715071572,
      "clip_ratio/high_mean": 0.0012167907734692562,
      "clip_ratio/low_mean": 0.0014779315315536223,
      "clip_ratio/low_min": 0.0003104298266407568,
      "clip_ratio/region_mean": 0.0026947223668685183,
      "epoch": 0.11918636870074492,
      "grad_norm": 0.11389115452766418,
      "learning_rate": 1e-06,
      "loss": 0.0603,
      "step": 1277
    },
    {
      "clip_ratio/high_max": 0.003054427172173746,
      "clip_ratio/high_mean": 0.0012806193590222392,
      "clip_ratio/low_mean": 0.0013454707659548149,
      "clip_ratio/low_min": 0.00016149640941875987,
      "clip_ratio/region_mean": 0.0026260901577188633,
      "epoch": 0.1192797018007455,
      "grad_norm": 0.11626116186380386,
      "learning_rate": 1e-06,
      "loss": 0.0025,
      "step": 1278
    },
    {
      "clip_ratio/high_max": 0.002863746318325866,
      "clip_ratio/high_mean": 0.0013735457505390514,
      "clip_ratio/low_mean": 0.001146861814049771,
      "clip_ratio/low_min": 0.0001406564133503707,
      "clip_ratio/region_mean": 0.002520407513657119,
      "epoch": 0.11937303490074608,
      "grad_norm": 0.11570712178945541,
      "learning_rate": 1e-06,
      "loss": -0.042,
      "step": 1279
    },
    {
      "clip_ratio/high_max": 0.0033707413786032703,
      "clip_ratio/high_mean": 0.0013473365615936927,
      "clip_ratio/low_mean": 0.0014435419070650823,
      "clip_ratio/low_min": 0.0001292692049901234,
      "clip_ratio/region_mean": 0.0027908784395549446,
      "epoch": 0.11946636800074667,
      "grad_norm": 0.11858441680669785,
      "learning_rate": 1e-06,
      "loss": 0.0331,
      "step": 1280
    },
    {
      "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": 0.010393415178571397,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4091.0,
      "completions/mean_length": 610.109375,
      "completions/mean_terminated_length": 573.4985961914062,
      "completions/min_length": 6.0,
      "completions/min_terminated_length": 6.0,
      "epoch": 0.11955970110074725,
      "grad_norm": 0.12895292043685913,
      "learning_rate": 1e-06,
      "loss": 0.0104,
      "num_tokens": 890648536.0,
      "reward": 0.6309814453125,
      "reward_std": 0.17484650015830994,
      "rewards/simpleverify_reward/mean": 0.6309814453125,
      "rewards/simpleverify_reward/std": 0.4825412333011627,
      "step": 1281
    },
    {
      "clip_ratio/high_max": 0.0021441451826831326,
      "clip_ratio/high_mean": 0.0008176259252650198,
      "clip_ratio/low_mean": 0.00047146658016572474,
      "clip_ratio/low_min": 1.3306365872267634e-05,
      "clip_ratio/region_mean": 0.0012890925172541756,
      "epoch": 0.11965303420074783,
      "grad_norm": 0.10670824348926544,
      "learning_rate": 1e-06,
      "loss": 0.0576,
      "step": 1282
    },
    {
      "clip_ratio/high_max": 0.0020660920708905905,
      "clip_ratio/high_mean": 0.0008382567266380647,
      "clip_ratio/low_mean": 0.0005422829344752245,
      "clip_ratio/low_min": 9.95539994619321e-06,
      "clip_ratio/region_mean": 0.001380539673846215,
      "epoch": 0.11974636730074842,
      "grad_norm": 0.12438701838254929,
      "learning_rate": 1e-06,
      "loss": 0.0313,
      "step": 1283
    },
    {
      "clip_ratio/high_max": 0.0019648446977953427,
      "clip_ratio/high_mean": 0.0008790952506387839,
      "clip_ratio/low_mean": 0.00047001554048620164,
      "clip_ratio/low_min": 1.4626725715061184e-05,
      "clip_ratio/region_mean": 0.001349110811133869,
      "epoch": 0.119839700400749,
      "grad_norm": 0.12401069700717926,
      "learning_rate": 1e-06,
      "loss": 0.0185,
      "step": 1284
    },
    {
      "clip_ratio/high_max": 0.0021877586259506643,
      "clip_ratio/high_mean": 0.0008226343379647005,
      "clip_ratio/low_mean": 0.000532995886601384,
      "clip_ratio/low_min": 1.253761274710996e-05,
      "clip_ratio/region_mean": 0.0013556302292272449,
      "epoch": 0.11993303350074958,
      "grad_norm": 0.1298038363456726,
      "learning_rate": 1e-06,
      "loss": 0.0493,
      "step": 1285
    },
    {
      "clip_ratio/high_max": 0.0021752143802586943,
      "clip_ratio/high_mean": 0.000922163588256808,
      "clip_ratio/low_mean": 0.000500899364851648,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014230629240046255,
      "epoch": 0.12002636660075017,
      "grad_norm": 0.11620011180639267,
      "learning_rate": 1e-06,
      "loss": 0.0086,
      "step": 1286
    },
    {
      "clip_ratio/high_max": 0.002193513824749971,
      "clip_ratio/high_mean": 0.0008912166158552282,
      "clip_ratio/low_mean": 0.0007291550282388926,
      "clip_ratio/low_min": 0.00010152971844945569,
      "clip_ratio/region_mean": 0.0016203715968003962,
      "epoch": 0.12011969970075075,
      "grad_norm": 0.12693192064762115,
      "learning_rate": 1e-06,
      "loss": 0.0181,
      "step": 1287
    },
    {
      "clip_ratio/high_max": 0.0026443946044309996,
      "clip_ratio/high_mean": 0.0009856653232418466,
      "clip_ratio/low_mean": 0.0007984113972270279,
      "clip_ratio/low_min": 9.48485912886099e-05,
      "clip_ratio/region_mean": 0.0017840767213783693,
      "epoch": 0.12021303280075134,
      "grad_norm": 0.1853368878364563,
      "learning_rate": 1e-06,
      "loss": 0.029,
      "step": 1288
    },
    {
      "clip_ratio/high_max": 0.0019395440285734367,
      "clip_ratio/high_mean": 0.0006901731085235951,
      "clip_ratio/low_mean": 0.0007944506596686551,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014846237972960807,
      "epoch": 0.12030636590075192,
      "grad_norm": 0.12624883651733398,
      "learning_rate": 1e-06,
      "loss": 0.0699,
      "step": 1289
    },
    {
      "clip_ratio/high_max": 0.0022364586984622292,
      "clip_ratio/high_mean": 0.0008985355580080068,
      "clip_ratio/low_mean": 0.0009325439787062351,
      "clip_ratio/low_min": 0.000146565743307292,
      "clip_ratio/region_mean": 0.0018310795276192948,
      "epoch": 0.1203996990007525,
      "grad_norm": 0.11929628252983093,
      "learning_rate": 1e-06,
      "loss": 0.0377,
      "step": 1290
    },
    {
      "clip_ratio/high_max": 0.00248417829425307,
      "clip_ratio/high_mean": 0.0009137222423305502,
      "clip_ratio/low_mean": 0.0009736206557136029,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0018873429216910154,
      "epoch": 0.12049303210075309,
      "grad_norm": 0.11287343502044678,
      "learning_rate": 1e-06,
      "loss": 0.0326,
      "step": 1291
    },
    {
      "clip_ratio/high_max": 0.0019625572094810195,
      "clip_ratio/high_mean": 0.0007450074826920172,
      "clip_ratio/low_mean": 0.0010170580317208078,
      "clip_ratio/low_min": 8.558083754905965e-05,
      "clip_ratio/region_mean": 0.0017620654907659627,
      "epoch": 0.12058636520075366,
      "grad_norm": 0.11487818509340286,
      "learning_rate": 1e-06,
      "loss": 0.0153,
      "step": 1292
    },
    {
      "clip_ratio/high_max": 0.002077179447951494,
      "clip_ratio/high_mean": 0.00080206192433252,
      "clip_ratio/low_mean": 0.0010252702631987631,
      "clip_ratio/low_min": 8.367015288968105e-05,
      "clip_ratio/region_mean": 0.001827332191169262,
      "epoch": 0.12067969830075424,
      "grad_norm": 0.11239241808652878,
      "learning_rate": 1e-06,
      "loss": 0.0353,
      "step": 1293
    },
    {
      "clip_ratio/high_max": 0.002465377656335477,
      "clip_ratio/high_mean": 0.000920115138796973,
      "clip_ratio/low_mean": 0.0009740576242620591,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0018941727612400427,
      "epoch": 0.12077303140075484,
      "grad_norm": 0.11380409449338913,
      "learning_rate": 1e-06,
      "loss": 0.0114,
      "step": 1294
    },
    {
      "clip_ratio/high_max": 0.002330126349988859,
      "clip_ratio/high_mean": 0.0009716566182760289,
      "clip_ratio/low_mean": 0.000978649110038532,
      "clip_ratio/low_min": 5.766382582805818e-05,
      "clip_ratio/region_mean": 0.0019503056755638681,
      "epoch": 0.12086636450075541,
      "grad_norm": 0.11873907595872879,
      "learning_rate": 1e-06,
      "loss": 0.0209,
      "step": 1295
    },
    {
      "clip_ratio/high_max": 0.0023141233978094533,
      "clip_ratio/high_mean": 0.0009618253352527972,
      "clip_ratio/low_mean": 0.001166330632258905,
      "clip_ratio/low_min": 0.00019162415537721245,
      "clip_ratio/region_mean": 0.0021281559238559566,
      "epoch": 0.12095969760075599,
      "grad_norm": 0.12207131087779999,
      "learning_rate": 1e-06,
      "loss": 0.0916,
      "step": 1296
    },
    {
      "clip_ratio/high_max": 0.001938506571605103,
      "clip_ratio/high_mean": 0.0008880145978764631,
      "clip_ratio/low_mean": 0.0009675995497673284,
      "clip_ratio/low_min": 3.249285146011971e-05,
      "clip_ratio/region_mean": 0.0018556141731096432,
      "epoch": 0.12105303070075658,
      "grad_norm": 0.10858555138111115,
      "learning_rate": 1e-06,
      "loss": 0.023,
      "step": 1297
    },
    {
      "clip_ratio/high_max": 0.002441810844175052,
      "clip_ratio/high_mean": 0.0010267351590300677,
      "clip_ratio/low_mean": 0.000797704598880955,
      "clip_ratio/low_min": 5.952290121058468e-05,
      "clip_ratio/region_mean": 0.0018244397615490016,
      "epoch": 0.12114636380075716,
      "grad_norm": 0.13026843965053558,
      "learning_rate": 1e-06,
      "loss": -0.0014,
      "step": 1298
    },
    {
      "clip_ratio/high_max": 0.002252244605188025,
      "clip_ratio/high_mean": 0.0009366441827296512,
      "clip_ratio/low_mean": 0.0008289946645163582,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0017656388445175253,
      "epoch": 0.12123969690075775,
      "grad_norm": 0.10747717320919037,
      "learning_rate": 1e-06,
      "loss": 0.0268,
      "step": 1299
    },
    {
      "clip_ratio/high_max": 0.0024801314139040187,
      "clip_ratio/high_mean": 0.0010120064071088564,
      "clip_ratio/low_mean": 0.0009798703740671044,
      "clip_ratio/low_min": 7.715442734479439e-05,
      "clip_ratio/region_mean": 0.0019918768157367595,
      "epoch": 0.12133303000075833,
      "grad_norm": 0.12325803935527802,
      "learning_rate": 1e-06,
      "loss": 0.0242,
      "step": 1300
    },
    {
      "clip_ratio/high_max": 0.002263571754156146,
      "clip_ratio/high_mean": 0.0009484489419264719,
      "clip_ratio/low_mean": 0.0010041467139672022,
      "clip_ratio/low_min": 9.184146256302483e-05,
      "clip_ratio/region_mean": 0.0019525956304278225,
      "epoch": 0.12142636310075891,
      "grad_norm": 0.10906504839658737,
      "learning_rate": 1e-06,
      "loss": 0.063,
      "step": 1301
    },
    {
      "clip_ratio/high_max": 0.0026338738825870678,
      "clip_ratio/high_mean": 0.0010177921139984392,
      "clip_ratio/low_mean": 0.001031638255881262,
      "clip_ratio/low_min": 6.40285793451767e-05,
      "clip_ratio/region_mean": 0.0020494303535087965,
      "epoch": 0.1215196962007595,
      "grad_norm": 0.10667446255683899,
      "learning_rate": 1e-06,
      "loss": 0.0439,
      "step": 1302
    },
    {
      "clip_ratio/high_max": 0.0025169359578285366,
      "clip_ratio/high_mean": 0.0009745193019625731,
      "clip_ratio/low_mean": 0.0009110706087085418,
      "clip_ratio/low_min": 5.024115671403706e-05,
      "clip_ratio/region_mean": 0.0018855899252230301,
      "epoch": 0.12161302930076008,
      "grad_norm": 0.11458733677864075,
      "learning_rate": 1e-06,
      "loss": 0.0413,
      "step": 1303
    },
    {
      "clip_ratio/high_max": 0.002306732454599114,
      "clip_ratio/high_mean": 0.0010140952526853653,
      "clip_ratio/low_mean": 0.0008844761159707559,
      "clip_ratio/low_min": 5.024313759349752e-05,
      "clip_ratio/region_mean": 0.001898571390483994,
      "epoch": 0.12170636240076066,
      "grad_norm": 0.11792048811912537,
      "learning_rate": 1e-06,
      "loss": 0.0082,
      "step": 1304
    },
    {
      "clip_ratio/high_max": 0.002436463786580134,
      "clip_ratio/high_mean": 0.0010538268361415248,
      "clip_ratio/low_mean": 0.0009685346358310198,
      "clip_ratio/low_min": 1.5679879652452655e-05,
      "clip_ratio/region_mean": 0.0020223614701535553,
      "epoch": 0.12179969550076125,
      "grad_norm": 0.10799770057201385,
      "learning_rate": 1e-06,
      "loss": -0.0223,
      "step": 1305
    },
    {
      "clip_ratio/high_max": 0.0023058362348820083,
      "clip_ratio/high_mean": 0.0009102488857024582,
      "clip_ratio/low_mean": 0.000975988652498927,
      "clip_ratio/low_min": 8.764481026446447e-05,
      "clip_ratio/region_mean": 0.0018862375291064382,
      "epoch": 0.12189302860076183,
      "grad_norm": 0.11240687221288681,
      "learning_rate": 1e-06,
      "loss": 0.0533,
      "step": 1306
    },
    {
      "clip_ratio/high_max": 0.002587798604508862,
      "clip_ratio/high_mean": 0.0010444677336636232,
      "clip_ratio/low_mean": 0.0010610118843032978,
      "clip_ratio/low_min": 3.502708932501264e-05,
      "clip_ratio/region_mean": 0.0021054796015960164,
      "epoch": 0.12198636170076241,
      "grad_norm": 0.11873338371515274,
      "learning_rate": 1e-06,
      "loss": 0.0419,
      "step": 1307
    },
    {
      "clip_ratio/high_max": 0.002238122084236238,
      "clip_ratio/high_mean": 0.0009666623318480561,
      "clip_ratio/low_mean": 0.0010871769409277476,
      "clip_ratio/low_min": 5.963993498880882e-05,
      "clip_ratio/region_mean": 0.002053839292784687,
      "epoch": 0.122079694800763,
      "grad_norm": 0.10468167811632156,
      "learning_rate": 1e-06,
      "loss": 0.0155,
      "step": 1308
    },
    {
      "clip_ratio/high_max": 0.0020813558730878867,
      "clip_ratio/high_mean": 0.0009170425855700159,
      "clip_ratio/low_mean": 0.00087155876099132,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0017886013665702194,
      "epoch": 0.12217302790076358,
      "grad_norm": 0.28226950764656067,
      "learning_rate": 1e-06,
      "loss": -0.0454,
      "step": 1309
    },
    {
      "clip_ratio/high_max": 0.0025746532119228505,
      "clip_ratio/high_mean": 0.001176062723970972,
      "clip_ratio/low_mean": 0.0009494975365669234,
      "clip_ratio/low_min": 1.5875031749601476e-05,
      "clip_ratio/region_mean": 0.0021255602769088,
      "epoch": 0.12226636100076417,
      "grad_norm": 0.11189974099397659,
      "learning_rate": 1e-06,
      "loss": -0.0338,
      "step": 1310
    },
    {
      "clip_ratio/high_max": 0.0022610522937611677,
      "clip_ratio/high_mean": 0.0009601425845175982,
      "clip_ratio/low_mean": 0.0011916314469999634,
      "clip_ratio/low_min": 6.783997559978161e-05,
      "clip_ratio/region_mean": 0.0021517740169656463,
      "epoch": 0.12235969410076475,
      "grad_norm": 0.1321498602628708,
      "learning_rate": 1e-06,
      "loss": 0.0396,
      "step": 1311
    },
    {
      "clip_ratio/high_max": 0.0026759172178572044,
      "clip_ratio/high_mean": 0.001046733363182284,
      "clip_ratio/low_mean": 0.0011467236690805294,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0021934570249868557,
      "epoch": 0.12245302720076533,
      "grad_norm": 0.11425404995679855,
      "learning_rate": 1e-06,
      "loss": 0.0316,
      "step": 1312
    },
    {
      "clip_ratio/high_max": 0.003096200482104905,
      "clip_ratio/high_mean": 0.0012247566446603741,
      "clip_ratio/low_mean": 0.0009124176203840761,
      "clip_ratio/low_min": 3.974411629315e-05,
      "clip_ratio/region_mean": 0.0021371742550400086,
      "epoch": 0.12254636030076592,
      "grad_norm": 0.11611877381801605,
      "learning_rate": 1e-06,
      "loss": -0.0697,
      "step": 1313
    },
    {
      "clip_ratio/high_max": 0.0021622707026835997,
      "clip_ratio/high_mean": 0.0009445622126804665,
      "clip_ratio/low_mean": 0.0010839642454811838,
      "clip_ratio/low_min": 6.705146370222792e-05,
      "clip_ratio/region_mean": 0.0020285264326957986,
      "epoch": 0.1226396934007665,
      "grad_norm": 0.10304926335811615,
      "learning_rate": 1e-06,
      "loss": 0.0155,
      "step": 1314
    },
    {
      "clip_ratio/high_max": 0.0023880083099356852,
      "clip_ratio/high_mean": 0.0011002809715137118,
      "clip_ratio/low_mean": 0.00112236069253413,
      "clip_ratio/low_min": 9.272780152969062e-05,
      "clip_ratio/region_mean": 0.00222264166950481,
      "epoch": 0.12273302650076708,
      "grad_norm": 0.11256153881549835,
      "learning_rate": 1e-06,
      "loss": 0.0183,
      "step": 1315
    },
    {
      "clip_ratio/high_max": 0.0027116526107420214,
      "clip_ratio/high_mean": 0.0011230716700083576,
      "clip_ratio/low_mean": 0.0009181561144941952,
      "clip_ratio/low_min": 4.2745424252643716e-05,
      "clip_ratio/region_mean": 0.002041227839072235,
      "epoch": 0.12282635960076767,
      "grad_norm": 0.11524578183889389,
      "learning_rate": 1e-06,
      "loss": -0.0165,
      "step": 1316
    },
    {
      "clip_ratio/high_max": 0.0024223047657869756,
      "clip_ratio/high_mean": 0.0010719097845139913,
      "clip_ratio/low_mean": 0.0011505577494972385,
      "clip_ratio/low_min": 0.00012231938217155403,
      "clip_ratio/region_mean": 0.002222467490355484,
      "epoch": 0.12291969270076825,
      "grad_norm": 0.12907569110393524,
      "learning_rate": 1e-06,
      "loss": 0.0264,
      "step": 1317
    },
    {
      "clip_ratio/high_max": 0.0030504561436828226,
      "clip_ratio/high_mean": 0.0014051681791897863,
      "clip_ratio/low_mean": 0.000994932164758211,
      "clip_ratio/low_min": 5.6225260777864605e-05,
      "clip_ratio/region_mean": 0.0024001003766898066,
      "epoch": 0.12301302580076884,
      "grad_norm": 0.17135463654994965,
      "learning_rate": 1e-06,
      "loss": -0.0574,
      "step": 1318
    },
    {
      "clip_ratio/high_max": 0.0025851281607174315,
      "clip_ratio/high_mean": 0.0010976346493407618,
      "clip_ratio/low_mean": 0.0010628374002408236,
      "clip_ratio/low_min": 3.79289504053304e-05,
      "clip_ratio/region_mean": 0.00216047209687531,
      "epoch": 0.12310635890076942,
      "grad_norm": 0.203459694981575,
      "learning_rate": 1e-06,
      "loss": -0.0079,
      "step": 1319
    },
    {
      "clip_ratio/high_max": 0.002792992665490601,
      "clip_ratio/high_mean": 0.0011231363314436749,
      "clip_ratio/low_mean": 0.0008654042858324829,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0019885405999957584,
      "epoch": 0.12319969200077,
      "grad_norm": 0.10876962542533875,
      "learning_rate": 1e-06,
      "loss": -0.0287,
      "step": 1320
    },
    {
      "clip_ratio/high_max": 0.0026682554234866984,
      "clip_ratio/high_mean": 0.0010714533273130655,
      "clip_ratio/low_mean": 0.0011184101076651132,
      "clip_ratio/low_min": 3.549926077539567e-05,
      "clip_ratio/region_mean": 0.002189863436797168,
      "epoch": 0.12329302510077059,
      "grad_norm": 0.11900845915079117,
      "learning_rate": 1e-06,
      "loss": 0.0228,
      "step": 1321
    },
    {
      "clip_ratio/high_max": 0.002558654232416302,
      "clip_ratio/high_mean": 0.0009916140752466163,
      "clip_ratio/low_mean": 0.0010297972567059333,
      "clip_ratio/low_min": 1.213356608786853e-05,
      "clip_ratio/region_mean": 0.002021411324676592,
      "epoch": 0.12338635820077117,
      "grad_norm": 0.1073676273226738,
      "learning_rate": 1e-06,
      "loss": 0.003,
      "step": 1322
    },
    {
      "clip_ratio/high_max": 0.0022912902059033513,
      "clip_ratio/high_mean": 0.0009251749106624629,
      "clip_ratio/low_mean": 0.001135120135586476,
      "clip_ratio/low_min": 0.00013762794424110325,
      "clip_ratio/region_mean": 0.002060295082628727,
      "epoch": 0.12347969130077174,
      "grad_norm": 0.10651320964097977,
      "learning_rate": 1e-06,
      "loss": 0.0268,
      "step": 1323
    },
    {
      "clip_ratio/high_max": 0.002627836300234776,
      "clip_ratio/high_mean": 0.0011033288683393039,
      "clip_ratio/low_mean": 0.0011243516546528554,
      "clip_ratio/low_min": 6.528768608404789e-05,
      "clip_ratio/region_mean": 0.002227680539363064,
      "epoch": 0.12357302440077234,
      "grad_norm": 0.11595786362886429,
      "learning_rate": 1e-06,
      "loss": -0.0092,
      "step": 1324
    },
    {
      "clip_ratio/high_max": 0.0026489586161915213,
      "clip_ratio/high_mean": 0.0010106006066052942,
      "clip_ratio/low_mean": 0.001140249964009854,
      "clip_ratio/low_min": 6.696042328258045e-05,
      "clip_ratio/region_mean": 0.002150850610632915,
      "epoch": 0.12366635750077291,
      "grad_norm": 0.12186706066131592,
      "learning_rate": 1e-06,
      "loss": 0.032,
      "step": 1325
    },
    {
      "clip_ratio/high_max": 0.0028390686929924414,
      "clip_ratio/high_mean": 0.0011158923498442164,
      "clip_ratio/low_mean": 0.0010702023264457239,
      "clip_ratio/low_min": 9.896701521938667e-05,
      "clip_ratio/region_mean": 0.0021860946581000462,
      "epoch": 0.12375969060077349,
      "grad_norm": 0.11678916215896606,
      "learning_rate": 1e-06,
      "loss": 0.0145,
      "step": 1326
    },
    {
      "clip_ratio/high_max": 0.002581896107585635,
      "clip_ratio/high_mean": 0.0011386568912712391,
      "clip_ratio/low_mean": 0.001268626656383276,
      "clip_ratio/low_min": 9.548227535560727e-05,
      "clip_ratio/region_mean": 0.002407283529464621,
      "epoch": 0.12385302370077408,
      "grad_norm": 0.15045490860939026,
      "learning_rate": 1e-06,
      "loss": 0.0264,
      "step": 1327
    },
    {
      "clip_ratio/high_max": 0.002736391448706854,
      "clip_ratio/high_mean": 0.0010880596546485322,
      "clip_ratio/low_mean": 0.0011997807741863653,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002287840448843781,
      "epoch": 0.12394635680077466,
      "grad_norm": 0.11760014295578003,
      "learning_rate": 1e-06,
      "loss": 0.0395,
      "step": 1328
    },
    {
      "clip_ratio/high_max": 0.002846799194230698,
      "clip_ratio/high_mean": 0.0012203809965285473,
      "clip_ratio/low_mean": 0.0012402048487274442,
      "clip_ratio/low_min": 2.7209867766941898e-05,
      "clip_ratio/region_mean": 0.0024605858488939703,
      "epoch": 0.12403968990077525,
      "grad_norm": 0.13172033429145813,
      "learning_rate": 1e-06,
      "loss": -0.0044,
      "step": 1329
    },
    {
      "clip_ratio/high_max": 0.0025657784717623144,
      "clip_ratio/high_mean": 0.001073271872883197,
      "clip_ratio/low_mean": 0.0010268364057992585,
      "clip_ratio/low_min": 3.929303238692228e-05,
      "clip_ratio/region_mean": 0.0021001082786824554,
      "epoch": 0.12413302300077583,
      "grad_norm": 0.11676289886236191,
      "learning_rate": 1e-06,
      "loss": -0.002,
      "step": 1330
    },
    {
      "clip_ratio/high_max": 0.0024948178688646294,
      "clip_ratio/high_mean": 0.0010577664543234278,
      "clip_ratio/low_mean": 0.001128869207605021,
      "clip_ratio/low_min": 0.00012567300018417882,
      "clip_ratio/region_mean": 0.0021866356328246184,
      "epoch": 0.12422635610077641,
      "grad_norm": 0.11228536814451218,
      "learning_rate": 1e-06,
      "loss": 0.0427,
      "step": 1331
    },
    {
      "clip_ratio/high_max": 0.0026571896523819305,
      "clip_ratio/high_mean": 0.0011416672205086797,
      "clip_ratio/low_mean": 0.0011031921858375426,
      "clip_ratio/low_min": 0.00010886806194321252,
      "clip_ratio/region_mean": 0.0022448594390880316,
      "epoch": 0.124319689200777,
      "grad_norm": 0.1288970559835434,
      "learning_rate": 1e-06,
      "loss": 0.0124,
      "step": 1332
    },
    {
      "clip_ratio/high_max": 0.0025320590284536593,
      "clip_ratio/high_mean": 0.0011570885690161958,
      "clip_ratio/low_mean": 0.001041901847202098,
      "clip_ratio/low_min": 6.738956108165439e-05,
      "clip_ratio/region_mean": 0.002198990448960103,
      "epoch": 0.12441302230077758,
      "grad_norm": 0.1124814823269844,
      "learning_rate": 1e-06,
      "loss": 0.0224,
      "step": 1333
    },
    {
      "clip_ratio/high_max": 0.0026128546305699274,
      "clip_ratio/high_mean": 0.0009582051643519662,
      "clip_ratio/low_mean": 0.0013204697515902808,
      "clip_ratio/low_min": 3.88923472200986e-05,
      "clip_ratio/region_mean": 0.0022786749395891093,
      "epoch": 0.12450635540077816,
      "grad_norm": 0.12329450994729996,
      "learning_rate": 1e-06,
      "loss": 0.0299,
      "step": 1334
    },
    {
      "clip_ratio/high_max": 0.0023214472603285685,
      "clip_ratio/high_mean": 0.0010030869634647388,
      "clip_ratio/low_mean": 0.0011128095429739915,
      "clip_ratio/low_min": 2.2425547285820358e-05,
      "clip_ratio/region_mean": 0.0021158965246286243,
      "epoch": 0.12459968850077875,
      "grad_norm": 0.11730413138866425,
      "learning_rate": 1e-06,
      "loss": 0.0309,
      "step": 1335
    },
    {
      "clip_ratio/high_max": 0.002982100468216231,
      "clip_ratio/high_mean": 0.0011101754644187167,
      "clip_ratio/low_mean": 0.001293740890105255,
      "clip_ratio/low_min": 0.00015990870997484308,
      "clip_ratio/region_mean": 0.002403916332696099,
      "epoch": 0.12469302160077933,
      "grad_norm": 0.1133042648434639,
      "learning_rate": 1e-06,
      "loss": 0.0572,
      "step": 1336
    },
    {
      "clip_ratio/high_max": 0.003016605398443062,
      "clip_ratio/high_mean": 0.001397381358401617,
      "clip_ratio/low_mean": 0.0010754951090348186,
      "clip_ratio/low_min": 2.4752474928391166e-05,
      "clip_ratio/region_mean": 0.002472876527463086,
      "epoch": 0.12478635470077991,
      "grad_norm": 0.1099381148815155,
      "learning_rate": 1e-06,
      "loss": -0.0368,
      "step": 1337
    },
    {
      "clip_ratio/high_max": 0.002582431581686251,
      "clip_ratio/high_mean": 0.0010401414583611768,
      "clip_ratio/low_mean": 0.0011927328123420011,
      "clip_ratio/low_min": 8.804158096609171e-05,
      "clip_ratio/region_mean": 0.002232874285255093,
      "epoch": 0.1248796878007805,
      "grad_norm": 0.11148440837860107,
      "learning_rate": 1e-06,
      "loss": 0.0108,
      "step": 1338
    },
    {
      "clip_ratio/high_max": 0.00257693241655943,
      "clip_ratio/high_mean": 0.001114319193220581,
      "clip_ratio/low_mean": 0.001178469881779165,
      "clip_ratio/low_min": 5.861662430106662e-05,
      "clip_ratio/region_mean": 0.0022927890604478307,
      "epoch": 0.12497302090078108,
      "grad_norm": 0.11407836526632309,
      "learning_rate": 1e-06,
      "loss": -0.0098,
      "step": 1339
    },
    {
      "clip_ratio/high_max": 0.0026051498207380064,
      "clip_ratio/high_mean": 0.00100246686997707,
      "clip_ratio/low_mean": 0.0010983349638991058,
      "clip_ratio/low_min": 1.4856192137813196e-05,
      "clip_ratio/region_mean": 0.0021008018447901122,
      "epoch": 0.12506635400078167,
      "grad_norm": 0.13212084770202637,
      "learning_rate": 1e-06,
      "loss": 0.0502,
      "step": 1340
    },
    {
      "clip_ratio/high_max": 0.002599393861601129,
      "clip_ratio/high_mean": 0.0011785814094764646,
      "clip_ratio/low_mean": 0.0012800695167243248,
      "clip_ratio/low_min": 2.0906680219923146e-05,
      "clip_ratio/region_mean": 0.002458650960761588,
      "epoch": 0.12515968710078224,
      "grad_norm": 0.11319679021835327,
      "learning_rate": 1e-06,
      "loss": 0.047,
      "step": 1341
    },
    {
      "clip_ratio/high_max": 0.0027756354538723826,
      "clip_ratio/high_mean": 0.0012592410421348177,
      "clip_ratio/low_mean": 0.0011250367824686691,
      "clip_ratio/low_min": 0.0001464491397200618,
      "clip_ratio/region_mean": 0.002384277780947741,
      "epoch": 0.12525302020078283,
      "grad_norm": 0.12402558326721191,
      "learning_rate": 1e-06,
      "loss": 0.013,
      "step": 1342
    },
    {
      "clip_ratio/high_max": 0.0027977512509096414,
      "clip_ratio/high_mean": 0.0012480715158744715,
      "clip_ratio/low_mean": 0.001040811019265675,
      "clip_ratio/low_min": 3.241995727876201e-05,
      "clip_ratio/region_mean": 0.0022888825405971147,
      "epoch": 0.12534635330078342,
      "grad_norm": 0.10401278734207153,
      "learning_rate": 1e-06,
      "loss": 0.0065,
      "step": 1343
    },
    {
      "clip_ratio/high_max": 0.002564290538430214,
      "clip_ratio/high_mean": 0.0010519442257646006,
      "clip_ratio/low_mean": 0.0012405525976646459,
      "clip_ratio/low_min": 8.702085415279726e-05,
      "clip_ratio/region_mean": 0.002292496785230469,
      "epoch": 0.125439686400784,
      "grad_norm": 0.12406987696886063,
      "learning_rate": 1e-06,
      "loss": 0.0553,
      "step": 1344
    },
    {
      "clip_ratio/high_max": 0.002811659906001296,
      "clip_ratio/high_mean": 0.001144557125371648,
      "clip_ratio/low_mean": 0.0011629606287897332,
      "clip_ratio/low_min": 5.1769700803561136e-05,
      "clip_ratio/region_mean": 0.002307517708686646,
      "epoch": 0.12553301950078458,
      "grad_norm": 0.7004154324531555,
      "learning_rate": 1e-06,
      "loss": 0.0141,
      "step": 1345
    },
    {
      "clip_ratio/high_max": 0.002468482041876996,
      "clip_ratio/high_mean": 0.0010542313702899264,
      "clip_ratio/low_mean": 0.0012123147243983112,
      "clip_ratio/low_min": 0.00010982124877045862,
      "clip_ratio/region_mean": 0.002266546136524994,
      "epoch": 0.12562635260078517,
      "grad_norm": 0.11669385433197021,
      "learning_rate": 1e-06,
      "loss": 0.0351,
      "step": 1346
    },
    {
      "clip_ratio/high_max": 0.0033084197420976125,
      "clip_ratio/high_mean": 0.001157682894699974,
      "clip_ratio/low_mean": 0.001303948385611875,
      "clip_ratio/low_min": 1.775568125594873e-05,
      "clip_ratio/region_mean": 0.0024616312512080185,
      "epoch": 0.12571968570078576,
      "grad_norm": 0.12311021238565445,
      "learning_rate": 1e-06,
      "loss": 0.0588,
      "step": 1347
    },
    {
      "clip_ratio/high_max": 0.0027056929393438622,
      "clip_ratio/high_mean": 0.00103837785354699,
      "clip_ratio/low_mean": 0.0013868059759261087,
      "clip_ratio/low_min": 0.00017004779147100635,
      "clip_ratio/region_mean": 0.0024251838476629928,
      "epoch": 0.12581301880078632,
      "grad_norm": 0.11250880360603333,
      "learning_rate": 1e-06,
      "loss": 0.0258,
      "step": 1348
    },
    {
      "clip_ratio/high_max": 0.0029295459971763194,
      "clip_ratio/high_mean": 0.0010823124976013787,
      "clip_ratio/low_mean": 0.0012509830557974055,
      "clip_ratio/low_min": 6.736807517881971e-05,
      "clip_ratio/region_mean": 0.002333295517018996,
      "epoch": 0.12590635190078692,
      "grad_norm": 0.11140339821577072,
      "learning_rate": 1e-06,
      "loss": 0.0555,
      "step": 1349
    },
    {
      "clip_ratio/high_max": 0.0024087074416456744,
      "clip_ratio/high_mean": 0.0011355404021742288,
      "clip_ratio/low_mean": 0.0012424959204508923,
      "clip_ratio/low_min": 4.464145695237676e-05,
      "clip_ratio/region_mean": 0.0023780363189871423,
      "epoch": 0.1259996850007875,
      "grad_norm": 0.11859416961669922,
      "learning_rate": 1e-06,
      "loss": 0.0102,
      "step": 1350
    },
    {
      "clip_ratio/high_max": 0.0030166213764459826,
      "clip_ratio/high_mean": 0.001319939794484526,
      "clip_ratio/low_mean": 0.0012165483130957,
      "clip_ratio/low_min": 8.977844845503569e-05,
      "clip_ratio/region_mean": 0.0025364881366840564,
      "epoch": 0.12609301810078807,
      "grad_norm": 0.12291578948497772,
      "learning_rate": 1e-06,
      "loss": 0.0153,
      "step": 1351
    },
    {
      "clip_ratio/high_max": 0.0028500072367023677,
      "clip_ratio/high_mean": 0.0012187771644676104,
      "clip_ratio/low_mean": 0.0011386931510060094,
      "clip_ratio/low_min": 7.347841528826393e-05,
      "clip_ratio/region_mean": 0.0023574703227495775,
      "epoch": 0.12618635120078867,
      "grad_norm": 0.11126212030649185,
      "learning_rate": 1e-06,
      "loss": 0.0068,
      "step": 1352
    },
    {
      "clip_ratio/high_max": 0.002567450312199071,
      "clip_ratio/high_mean": 0.0011300108053546865,
      "clip_ratio/low_mean": 0.0011173318707733415,
      "clip_ratio/low_min": 4.81106253573671e-05,
      "clip_ratio/region_mean": 0.002247342694317922,
      "epoch": 0.12627968430078926,
      "grad_norm": 0.11562218517065048,
      "learning_rate": 1e-06,
      "loss": 0.0556,
      "step": 1353
    },
    {
      "clip_ratio/high_max": 0.0024769176670815796,
      "clip_ratio/high_mean": 0.0010596116371743847,
      "clip_ratio/low_mean": 0.0012322688598942477,
      "clip_ratio/low_min": 8.583437556808349e-05,
      "clip_ratio/region_mean": 0.0022918804534128867,
      "epoch": 0.12637301740078982,
      "grad_norm": 0.11048205941915512,
      "learning_rate": 1e-06,
      "loss": 0.0201,
      "step": 1354
    },
    {
      "clip_ratio/high_max": 0.003350231003423687,
      "clip_ratio/high_mean": 0.0013644994469359517,
      "clip_ratio/low_mean": 0.001189818680359167,
      "clip_ratio/low_min": 0.00012383401372062508,
      "clip_ratio/region_mean": 0.0025543181182001717,
      "epoch": 0.12646635050079041,
      "grad_norm": 0.10970748215913773,
      "learning_rate": 1e-06,
      "loss": 0.0236,
      "step": 1355
    },
    {
      "clip_ratio/high_max": 0.0025176360650220886,
      "clip_ratio/high_mean": 0.0011429897749621887,
      "clip_ratio/low_mean": 0.0010753201167972293,
      "clip_ratio/low_min": 7.076898509694729e-05,
      "clip_ratio/region_mean": 0.002218309928139206,
      "epoch": 0.126559683600791,
      "grad_norm": 0.11352907866239548,
      "learning_rate": 1e-06,
      "loss": -0.0035,
      "step": 1356
    },
    {
      "clip_ratio/high_max": 0.0023531259030278306,
      "clip_ratio/high_mean": 0.000930058822632418,
      "clip_ratio/low_mean": 0.0013118899005348794,
      "clip_ratio/low_min": 0.00024105198644974735,
      "clip_ratio/region_mean": 0.0022419487650040537,
      "epoch": 0.12665301670079157,
      "grad_norm": 0.12025987356901169,
      "learning_rate": 1e-06,
      "loss": 0.0609,
      "step": 1357
    },
    {
      "clip_ratio/high_max": 0.003036089015949983,
      "clip_ratio/high_mean": 0.0013386768150667194,
      "clip_ratio/low_mean": 0.0012784345708496403,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002617111320432741,
      "epoch": 0.12674634980079216,
      "grad_norm": 0.12024588137865067,
      "learning_rate": 1e-06,
      "loss": 0.0641,
      "step": 1358
    },
    {
      "clip_ratio/high_max": 0.0031052927297423594,
      "clip_ratio/high_mean": 0.001301228203374194,
      "clip_ratio/low_mean": 0.0010590280271571828,
      "clip_ratio/low_min": 0.00010009702145907795,
      "clip_ratio/region_mean": 0.0023602563160238788,
      "epoch": 0.12683968290079276,
      "grad_norm": 0.11043490469455719,
      "learning_rate": 1e-06,
      "loss": 0.0179,
      "step": 1359
    },
    {
      "clip_ratio/high_max": 0.0034211751553812064,
      "clip_ratio/high_mean": 0.0014332157734315842,
      "clip_ratio/low_mean": 0.001094557130272733,
      "clip_ratio/low_min": 9.345641774416436e-05,
      "clip_ratio/region_mean": 0.002527772892790381,
      "epoch": 0.12693301600079332,
      "grad_norm": 0.10914299637079239,
      "learning_rate": 1e-06,
      "loss": -0.0266,
      "step": 1360
    },
    {
      "clip_ratio/high_max": 0.0026519842140260153,
      "clip_ratio/high_mean": 0.0012206122300995048,
      "clip_ratio/low_mean": 0.0013386475147854071,
      "clip_ratio/low_min": 0.00025493222619843436,
      "clip_ratio/region_mean": 0.0025592597739887424,
      "epoch": 0.1270263491007939,
      "grad_norm": 0.1634318232536316,
      "learning_rate": 1e-06,
      "loss": 0.0312,
      "step": 1361
    },
    {
      "clip_ratio/high_max": 0.002511231454263907,
      "clip_ratio/high_mean": 0.0010970595558319474,
      "clip_ratio/low_mean": 0.00125238616601564,
      "clip_ratio/low_min": 4.7654333684477024e-05,
      "clip_ratio/region_mean": 0.002349445734580513,
      "epoch": 0.1271196822007945,
      "grad_norm": 0.10162568092346191,
      "learning_rate": 1e-06,
      "loss": 0.0267,
      "step": 1362
    },
    {
      "clip_ratio/high_max": 0.0026206374532193877,
      "clip_ratio/high_mean": 0.0012008247031189967,
      "clip_ratio/low_mean": 0.0012865560420323163,
      "clip_ratio/low_min": 3.811750502791256e-05,
      "clip_ratio/region_mean": 0.002487380821548868,
      "epoch": 0.12721301530079507,
      "grad_norm": 0.11069579422473907,
      "learning_rate": 1e-06,
      "loss": 0.0313,
      "step": 1363
    },
    {
      "clip_ratio/high_max": 0.0033561226882738993,
      "clip_ratio/high_mean": 0.001254858885658905,
      "clip_ratio/low_mean": 0.0013296573870320572,
      "clip_ratio/low_min": 2.5730752895469777e-05,
      "clip_ratio/region_mean": 0.0025845162381301634,
      "epoch": 0.12730634840079566,
      "grad_norm": 0.11410504579544067,
      "learning_rate": 1e-06,
      "loss": 0.0341,
      "step": 1364
    },
    {
      "clip_ratio/high_max": 0.002540686691645533,
      "clip_ratio/high_mean": 0.0011224654554098379,
      "clip_ratio/low_mean": 0.0013588600777438842,
      "clip_ratio/low_min": 2.04381940420717e-05,
      "clip_ratio/region_mean": 0.002481325536791701,
      "epoch": 0.12739968150079625,
      "grad_norm": 0.11087482422590256,
      "learning_rate": 1e-06,
      "loss": 0.0334,
      "step": 1365
    },
    {
      "clip_ratio/high_max": 0.002916283396189101,
      "clip_ratio/high_mean": 0.001222200724441791,
      "clip_ratio/low_mean": 0.001237593342011678,
      "clip_ratio/low_min": 7.867049771448364e-05,
      "clip_ratio/region_mean": 0.0024597941010142677,
      "epoch": 0.12749301460079684,
      "grad_norm": 0.11939911544322968,
      "learning_rate": 1e-06,
      "loss": -0.0276,
      "step": 1366
    },
    {
      "clip_ratio/high_max": 0.0029829672203049995,
      "clip_ratio/high_mean": 0.0013271419102238724,
      "clip_ratio/low_mean": 0.0014972758472140413,
      "clip_ratio/low_min": 0.00010067838593386114,
      "clip_ratio/region_mean": 0.0028244178029126488,
      "epoch": 0.1275863477007974,
      "grad_norm": 0.12010502815246582,
      "learning_rate": 1e-06,
      "loss": 0.0289,
      "step": 1367
    },
    {
      "clip_ratio/high_max": 0.0027923289526370354,
      "clip_ratio/high_mean": 0.0012110241623304319,
      "clip_ratio/low_mean": 0.0013404868750512833,
      "clip_ratio/low_min": 8.446245647064643e-05,
      "clip_ratio/region_mean": 0.0025515109882690012,
      "epoch": 0.127679680800798,
      "grad_norm": 0.10742495954036713,
      "learning_rate": 1e-06,
      "loss": 0.0024,
      "step": 1368
    },
    {
      "clip_ratio/high_max": 0.00304395620332798,
      "clip_ratio/high_mean": 0.0012475155999709386,
      "clip_ratio/low_mean": 0.0014075656727072783,
      "clip_ratio/low_min": 8.948659069574205e-05,
      "clip_ratio/region_mean": 0.0026550812617642805,
      "epoch": 0.1277730139007986,
      "grad_norm": 0.11154259741306305,
      "learning_rate": 1e-06,
      "loss": 0.0516,
      "step": 1369
    },
    {
      "clip_ratio/high_max": 0.0030153183033689857,
      "clip_ratio/high_mean": 0.0012760466379404534,
      "clip_ratio/low_mean": 0.0013798076870443765,
      "clip_ratio/low_min": 8.117053585010581e-05,
      "clip_ratio/region_mean": 0.002655854288605042,
      "epoch": 0.12786634700079916,
      "grad_norm": 0.13308484852313995,
      "learning_rate": 1e-06,
      "loss": 0.019,
      "step": 1370
    },
    {
      "clip_ratio/high_max": 0.0025975142198149115,
      "clip_ratio/high_mean": 0.0011475003520899918,
      "clip_ratio/low_mean": 0.0013063758487987798,
      "clip_ratio/low_min": 0.00011564903252292424,
      "clip_ratio/region_mean": 0.002453876171784941,
      "epoch": 0.12795968010079975,
      "grad_norm": 0.10471636056900024,
      "learning_rate": 1e-06,
      "loss": 0.0376,
      "step": 1371
    },
    {
      "clip_ratio/high_max": 0.0031849707884248346,
      "clip_ratio/high_mean": 0.0013211326076998375,
      "clip_ratio/low_mean": 0.00129524042858975,
      "clip_ratio/low_min": 3.910819395969156e-05,
      "clip_ratio/region_mean": 0.0026163729853578843,
      "epoch": 0.12805301320080034,
      "grad_norm": 0.11647000908851624,
      "learning_rate": 1e-06,
      "loss": -0.0217,
      "step": 1372
    },
    {
      "clip_ratio/high_max": 0.0031562722797389142,
      "clip_ratio/high_mean": 0.0011864872503792867,
      "clip_ratio/low_mean": 0.0011247345064475667,
      "clip_ratio/low_min": 4.94201376568526e-05,
      "clip_ratio/region_mean": 0.0023112217750167474,
      "epoch": 0.1281463463008009,
      "grad_norm": 0.1003836840391159,
      "learning_rate": 1e-06,
      "loss": 0.0153,
      "step": 1373
    },
    {
      "clip_ratio/high_max": 0.002775829896563664,
      "clip_ratio/high_mean": 0.0011705961587722413,
      "clip_ratio/low_mean": 0.0013226117662270553,
      "clip_ratio/low_min": 3.2834253943292424e-05,
      "clip_ratio/region_mean": 0.0024932079613790847,
      "epoch": 0.1282396794008015,
      "grad_norm": 0.11304599046707153,
      "learning_rate": 1e-06,
      "loss": 0.0388,
      "step": 1374
    },
    {
      "clip_ratio/high_max": 0.0027772734611062333,
      "clip_ratio/high_mean": 0.0012227170627738815,
      "clip_ratio/low_mean": 0.0012744320702040568,
      "clip_ratio/low_min": 3.273536640335806e-05,
      "clip_ratio/region_mean": 0.0024971491293399595,
      "epoch": 0.1283330125008021,
      "grad_norm": 0.11063316464424133,
      "learning_rate": 1e-06,
      "loss": 0.0009,
      "step": 1375
    },
    {
      "clip_ratio/high_max": 0.0028856489661848173,
      "clip_ratio/high_mean": 0.0011260449900873937,
      "clip_ratio/low_mean": 0.0014833531822660007,
      "clip_ratio/low_min": 0.0001267631014343351,
      "clip_ratio/region_mean": 0.0026093981650774367,
      "epoch": 0.12842634560080265,
      "grad_norm": 0.11840921640396118,
      "learning_rate": 1e-06,
      "loss": 0.0263,
      "step": 1376
    },
    {
      "clip_ratio/high_max": 0.0031462571350857615,
      "clip_ratio/high_mean": 0.0013985479417897295,
      "clip_ratio/low_mean": 0.001192144689412089,
      "clip_ratio/low_min": 1.0822510375874117e-05,
      "clip_ratio/region_mean": 0.0025906926312018186,
      "epoch": 0.12851967870080325,
      "grad_norm": 0.11033712327480316,
      "learning_rate": 1e-06,
      "loss": -0.0352,
      "step": 1377
    },
    {
      "clip_ratio/high_max": 0.002931233451818116,
      "clip_ratio/high_mean": 0.0012987254085601307,
      "clip_ratio/low_mean": 0.0013331221762200585,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0026318475356674753,
      "epoch": 0.12861301180080384,
      "grad_norm": 0.11512207239866257,
      "learning_rate": 1e-06,
      "loss": 0.0327,
      "step": 1378
    },
    {
      "clip_ratio/high_max": 0.0031872494218987413,
      "clip_ratio/high_mean": 0.0012775353898177855,
      "clip_ratio/low_mean": 0.0015626978092768695,
      "clip_ratio/low_min": 0.00022127443935460178,
      "clip_ratio/region_mean": 0.0028402332463883795,
      "epoch": 0.1287063449008044,
      "grad_norm": 0.12515591084957123,
      "learning_rate": 1e-06,
      "loss": 0.0323,
      "step": 1379
    },
    {
      "clip_ratio/high_max": 0.0031116569152800366,
      "clip_ratio/high_mean": 0.0013314692987478338,
      "clip_ratio/low_mean": 0.0014008225152792875,
      "clip_ratio/low_min": 0.0002107655855070334,
      "clip_ratio/region_mean": 0.0027322918467689306,
      "epoch": 0.128799678000805,
      "grad_norm": 0.12675832211971283,
      "learning_rate": 1e-06,
      "loss": 0.0075,
      "step": 1380
    },
    {
      "clip_ratio/high_max": 0.0027347295108484104,
      "clip_ratio/high_mean": 0.0012163412320660427,
      "clip_ratio/low_mean": 0.0012534443085314706,
      "clip_ratio/low_min": 2.838921864167787e-05,
      "clip_ratio/region_mean": 0.0024697855187696405,
      "epoch": 0.1288930111008056,
      "grad_norm": 0.12454894185066223,
      "learning_rate": 1e-06,
      "loss": -0.0154,
      "step": 1381
    },
    {
      "clip_ratio/high_max": 0.0025226335528714117,
      "clip_ratio/high_mean": 0.0011859914447995834,
      "clip_ratio/low_mean": 0.0012439866768545471,
      "clip_ratio/low_min": 6.472757559095044e-05,
      "clip_ratio/region_mean": 0.0024299781580339186,
      "epoch": 0.12898634420080615,
      "grad_norm": 0.11575935035943985,
      "learning_rate": 1e-06,
      "loss": 0.0057,
      "step": 1382
    },
    {
      "clip_ratio/high_max": 0.0022339663264574483,
      "clip_ratio/high_mean": 0.0009837511533987708,
      "clip_ratio/low_mean": 0.00159249584612553,
      "clip_ratio/low_min": 0.00019201983741368167,
      "clip_ratio/region_mean": 0.002576246981334407,
      "epoch": 0.12907967730080674,
      "grad_norm": 0.10702164471149445,
      "learning_rate": 1e-06,
      "loss": 0.0394,
      "step": 1383
    },
    {
      "clip_ratio/high_max": 0.0028238455415703356,
      "clip_ratio/high_mean": 0.0011758272848965134,
      "clip_ratio/low_mean": 0.0015015920616860967,
      "clip_ratio/low_min": 0.0001720309282973176,
      "clip_ratio/region_mean": 0.0026774193829623982,
      "epoch": 0.12917301040080734,
      "grad_norm": 0.1264890730381012,
      "learning_rate": 1e-06,
      "loss": 0.0192,
      "step": 1384
    },
    {
      "clip_ratio/high_max": 0.0032332927439711057,
      "clip_ratio/high_mean": 0.0014099479194555897,
      "clip_ratio/low_mean": 0.001346737288258737,
      "clip_ratio/low_min": 4.019809784949757e-05,
      "clip_ratio/region_mean": 0.002756685236818157,
      "epoch": 0.1292663435008079,
      "grad_norm": 0.11923909187316895,
      "learning_rate": 1e-06,
      "loss": 0.014,
      "step": 1385
    },
    {
      "clip_ratio/high_max": 0.0024510126022505574,
      "clip_ratio/high_mean": 0.0011480527973617427,
      "clip_ratio/low_mean": 0.0013162765717424918,
      "clip_ratio/low_min": 1.9516413885867223e-05,
      "clip_ratio/region_mean": 0.0024643293290864676,
      "epoch": 0.1293596766008085,
      "grad_norm": 0.12254194915294647,
      "learning_rate": 1e-06,
      "loss": 0.0514,
      "step": 1386
    },
    {
      "clip_ratio/high_max": 0.002646388740686234,
      "clip_ratio/high_mean": 0.0012281917806831188,
      "clip_ratio/low_mean": 0.0011648471627268009,
      "clip_ratio/low_min": 2.7028974727727473e-05,
      "clip_ratio/region_mean": 0.0023930389288580045,
      "epoch": 0.12945300970080909,
      "grad_norm": 0.10550342500209808,
      "learning_rate": 1e-06,
      "loss": 0.0329,
      "step": 1387
    },
    {
      "clip_ratio/high_max": 0.002958007316919975,
      "clip_ratio/high_mean": 0.0012395266312523745,
      "clip_ratio/low_mean": 0.001470461535063805,
      "clip_ratio/low_min": 0.00012581130067701451,
      "clip_ratio/region_mean": 0.002709988140850328,
      "epoch": 0.12954634280080968,
      "grad_norm": 0.1273244470357895,
      "learning_rate": 1e-06,
      "loss": 0.0328,
      "step": 1388
    },
    {
      "clip_ratio/high_max": 0.003077952773310244,
      "clip_ratio/high_mean": 0.0012885983851447236,
      "clip_ratio/low_mean": 0.0010589942867227364,
      "clip_ratio/low_min": 2.6150628400500864e-05,
      "clip_ratio/region_mean": 0.0023475926427636296,
      "epoch": 0.12963967590081024,
      "grad_norm": 0.10528501123189926,
      "learning_rate": 1e-06,
      "loss": -0.0534,
      "step": 1389
    },
    {
      "clip_ratio/high_max": 0.0023956300283316523,
      "clip_ratio/high_mean": 0.0010605086536088493,
      "clip_ratio/low_mean": 0.0013184277559048496,
      "clip_ratio/low_min": 0.00012944380068802275,
      "clip_ratio/region_mean": 0.0023789363985997625,
      "epoch": 0.12973300900081083,
      "grad_norm": 0.11130145192146301,
      "learning_rate": 1e-06,
      "loss": 0.0227,
      "step": 1390
    },
    {
      "clip_ratio/high_max": 0.0031019230737001635,
      "clip_ratio/high_mean": 0.001293247330977465,
      "clip_ratio/low_mean": 0.0016339628818968777,
      "clip_ratio/low_min": 0.00016817883260955568,
      "clip_ratio/region_mean": 0.002927210181951523,
      "epoch": 0.12982634210081143,
      "grad_norm": 0.11693202704191208,
      "learning_rate": 1e-06,
      "loss": 0.0645,
      "step": 1391
    },
    {
      "clip_ratio/high_max": 0.002797765177092515,
      "clip_ratio/high_mean": 0.0011576060387596954,
      "clip_ratio/low_mean": 0.0011010630914825015,
      "clip_ratio/low_min": 0.00010567695426288992,
      "clip_ratio/region_mean": 0.0022586691338801757,
      "epoch": 0.129919675200812,
      "grad_norm": 0.10736978054046631,
      "learning_rate": 1e-06,
      "loss": 0.0314,
      "step": 1392
    },
    {
      "clip_ratio/high_max": 0.002558309912274126,
      "clip_ratio/high_mean": 0.0011910736157005886,
      "clip_ratio/low_mean": 0.0012524053217930486,
      "clip_ratio/low_min": 5.5202819567057304e-05,
      "clip_ratio/region_mean": 0.0024434789156657644,
      "epoch": 0.13001300830081258,
      "grad_norm": 0.12168847024440765,
      "learning_rate": 1e-06,
      "loss": 0.0114,
      "step": 1393
    },
    {
      "clip_ratio/high_max": 0.002676270858501084,
      "clip_ratio/high_mean": 0.0011129300182801671,
      "clip_ratio/low_mean": 0.0015730028644611593,
      "clip_ratio/low_min": 0.00021488953279913403,
      "clip_ratio/region_mean": 0.002685932908207178,
      "epoch": 0.13010634140081317,
      "grad_norm": 0.13660931587219238,
      "learning_rate": 1e-06,
      "loss": 0.0573,
      "step": 1394
    },
    {
      "clip_ratio/high_max": 0.0026774827274493873,
      "clip_ratio/high_mean": 0.001188742447993718,
      "clip_ratio/low_mean": 0.0012503409379860386,
      "clip_ratio/low_min": 8.971944407676347e-05,
      "clip_ratio/region_mean": 0.002439083422359545,
      "epoch": 0.13019967450081374,
      "grad_norm": 0.10590992867946625,
      "learning_rate": 1e-06,
      "loss": 0.0004,
      "step": 1395
    },
    {
      "clip_ratio/high_max": 0.0027957746060565114,
      "clip_ratio/high_mean": 0.0012062489258823916,
      "clip_ratio/low_mean": 0.001335282306172303,
      "clip_ratio/low_min": 5.898510062252171e-05,
      "clip_ratio/region_mean": 0.002541531270253472,
      "epoch": 0.13029300760081433,
      "grad_norm": 0.10937392711639404,
      "learning_rate": 1e-06,
      "loss": 0.0769,
      "step": 1396
    },
    {
      "clip_ratio/high_max": 0.0025528517762722913,
      "clip_ratio/high_mean": 0.0011172767808602657,
      "clip_ratio/low_mean": 0.0010585999571048887,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002175876754336059,
      "epoch": 0.13038634070081492,
      "grad_norm": 0.1044696792960167,
      "learning_rate": 1e-06,
      "loss": -0.0065,
      "step": 1397
    },
    {
      "clip_ratio/high_max": 0.0028716621491184924,
      "clip_ratio/high_mean": 0.0011923000347451307,
      "clip_ratio/low_mean": 0.001309829756792169,
      "clip_ratio/low_min": 8.934361176216044e-05,
      "clip_ratio/region_mean": 0.0025021297988132574,
      "epoch": 0.1304796738008155,
      "grad_norm": 0.11332632601261139,
      "learning_rate": 1e-06,
      "loss": 0.0237,
      "step": 1398
    },
    {
      "clip_ratio/high_max": 0.0028542759173433296,
      "clip_ratio/high_mean": 0.0012202570687804837,
      "clip_ratio/low_mean": 0.001396773132000817,
      "clip_ratio/low_min": 0.0001337286812486127,
      "clip_ratio/region_mean": 0.0026170302226091735,
      "epoch": 0.13057300690081608,
      "grad_norm": 0.13376747071743011,
      "learning_rate": 1e-06,
      "loss": 0.0681,
      "step": 1399
    },
    {
      "clip_ratio/high_max": 0.0029794814909109846,
      "clip_ratio/high_mean": 0.0011996722350886557,
      "clip_ratio/low_mean": 0.0012152929084550124,
      "clip_ratio/low_min": 6.035111073288135e-05,
      "clip_ratio/region_mean": 0.0024149651508196257,
      "epoch": 0.13066634000081667,
      "grad_norm": 0.10504157096147537,
      "learning_rate": 1e-06,
      "loss": 0.0247,
      "step": 1400
    },
    {
      "clip_ratio/high_max": 0.0029307726144907065,
      "clip_ratio/high_mean": 0.0012254597204446327,
      "clip_ratio/low_mean": 0.0013834683486493304,
      "clip_ratio/low_min": 0.00013271760235511465,
      "clip_ratio/region_mean": 0.002608928072731942,
      "epoch": 0.13075967310081724,
      "grad_norm": 0.10274302959442139,
      "learning_rate": 1e-06,
      "loss": 0.014,
      "step": 1401
    },
    {
      "clip_ratio/high_max": 0.003067772966460325,
      "clip_ratio/high_mean": 0.001243198294105241,
      "clip_ratio/low_mean": 0.0015190639351203572,
      "clip_ratio/low_min": 0.00016442992273368873,
      "clip_ratio/region_mean": 0.0027622622656053863,
      "epoch": 0.13085300620081783,
      "grad_norm": 0.1279619336128235,
      "learning_rate": 1e-06,
      "loss": 0.0397,
      "step": 1402
    },
    {
      "clip_ratio/high_max": 0.002966751955682412,
      "clip_ratio/high_mean": 0.001153536890342366,
      "clip_ratio/low_mean": 0.0013457574150379514,
      "clip_ratio/low_min": 4.862488731305348e-05,
      "clip_ratio/region_mean": 0.0024992943144752644,
      "epoch": 0.13094633930081842,
      "grad_norm": 0.11048737168312073,
      "learning_rate": 1e-06,
      "loss": 0.0449,
      "step": 1403
    },
    {
      "clip_ratio/high_max": 0.003070895698328968,
      "clip_ratio/high_mean": 0.0012803471254301257,
      "clip_ratio/low_mean": 0.0011865049600601196,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0024668520854902454,
      "epoch": 0.13103967240081899,
      "grad_norm": 0.12111610919237137,
      "learning_rate": 1e-06,
      "loss": -0.0102,
      "step": 1404
    },
    {
      "clip_ratio/high_max": 0.0026759948523249477,
      "clip_ratio/high_mean": 0.0010618627202347852,
      "clip_ratio/low_mean": 0.0013095025860820897,
      "clip_ratio/low_min": 3.4460575989214703e-05,
      "clip_ratio/region_mean": 0.0023713653499726206,
      "epoch": 0.13113300550081958,
      "grad_norm": 0.11323264986276627,
      "learning_rate": 1e-06,
      "loss": 0.0327,
      "step": 1405
    },
    {
      "clip_ratio/high_max": 0.0035132480843458325,
      "clip_ratio/high_mean": 0.0014271228756115306,
      "clip_ratio/low_mean": 0.0014637651584052946,
      "clip_ratio/low_min": 0.00010082941844302695,
      "clip_ratio/region_mean": 0.002890888041292783,
      "epoch": 0.13122633860082017,
      "grad_norm": 0.12540501356124878,
      "learning_rate": 1e-06,
      "loss": 0.0593,
      "step": 1406
    },
    {
      "clip_ratio/high_max": 0.00321574870031327,
      "clip_ratio/high_mean": 0.0012367431954771746,
      "clip_ratio/low_mean": 0.001250624565727776,
      "clip_ratio/low_min": 0.00011548271868377924,
      "clip_ratio/region_mean": 0.0024873677612049505,
      "epoch": 0.13131967170082076,
      "grad_norm": 0.11678268760442734,
      "learning_rate": 1e-06,
      "loss": 0.0024,
      "step": 1407
    },
    {
      "clip_ratio/high_max": 0.0026184236703556962,
      "clip_ratio/high_mean": 0.0011091383639723063,
      "clip_ratio/low_mean": 0.0014941797962819692,
      "clip_ratio/low_min": 0.00021953478790237568,
      "clip_ratio/region_mean": 0.002603318222099915,
      "epoch": 0.13141300480082133,
      "grad_norm": 0.1242443323135376,
      "learning_rate": 1e-06,
      "loss": 0.0732,
      "step": 1408
    },
    {
      "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": 0.00946044921875,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4096.0,
      "completions/mean_length": 607.646240234375,
      "completions/mean_terminated_length": 574.3297119140625,
      "completions/min_length": 5.0,
      "completions/min_terminated_length": 5.0,
      "epoch": 0.13150633790082192,
      "grad_norm": 0.1468316614627838,
      "learning_rate": 1e-06,
      "loss": 0.0461,
      "num_tokens": 971711087.0,
      "reward": 0.6355940103530884,
      "reward_std": 0.17177210748195648,
      "rewards/simpleverify_reward/mean": 0.6355939507484436,
      "rewards/simpleverify_reward/std": 0.48126524686813354,
      "step": 1409
    },
    {
      "clip_ratio/high_max": 0.0022117213666206226,
      "clip_ratio/high_mean": 0.0009094587112485897,
      "clip_ratio/low_mean": 0.0004979919094694196,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014074506143515464,
      "epoch": 0.1315996710008225,
      "grad_norm": 0.11225530505180359,
      "learning_rate": 1e-06,
      "loss": -0.0413,
      "step": 1410
    },
    {
      "clip_ratio/high_max": 0.0019903382162738126,
      "clip_ratio/high_mean": 0.0007690000547881937,
      "clip_ratio/low_mean": 0.0005090371278129169,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012780371725966688,
      "epoch": 0.13169300410082307,
      "grad_norm": 0.1273522526025772,
      "learning_rate": 1e-06,
      "loss": -0.0041,
      "step": 1411
    },
    {
      "clip_ratio/high_max": 0.0022538252487720456,
      "clip_ratio/high_mean": 0.000918977599212667,
      "clip_ratio/low_mean": 0.0005195677422307199,
      "clip_ratio/low_min": 3.350308179506101e-05,
      "clip_ratio/region_mean": 0.0014385453359864186,
      "epoch": 0.13178633720082367,
      "grad_norm": 0.1204623281955719,
      "learning_rate": 1e-06,
      "loss": 0.0407,
      "step": 1412
    },
    {
      "clip_ratio/high_max": 0.00257959209557157,
      "clip_ratio/high_mean": 0.0009780170239537256,
      "clip_ratio/low_mean": 0.0005461268738145009,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0015241438704833854,
      "epoch": 0.13187967030082426,
      "grad_norm": 0.12016411870718002,
      "learning_rate": 1e-06,
      "loss": 0.0234,
      "step": 1413
    },
    {
      "clip_ratio/high_max": 0.0020601605137926526,
      "clip_ratio/high_mean": 0.0008132116072374629,
      "clip_ratio/low_mean": 0.000520435108228412,
      "clip_ratio/low_min": 3.0433066967816558e-05,
      "clip_ratio/region_mean": 0.001333646718194359,
      "epoch": 0.13197300340082482,
      "grad_norm": 0.14665919542312622,
      "learning_rate": 1e-06,
      "loss": 0.0206,
      "step": 1414
    },
    {
      "clip_ratio/high_max": 0.0022333878878271207,
      "clip_ratio/high_mean": 0.0009283408799092285,
      "clip_ratio/low_mean": 0.0006677346827927977,
      "clip_ratio/low_min": 8.469847489323001e-05,
      "clip_ratio/region_mean": 0.0015960755918058567,
      "epoch": 0.13206633650082542,
      "grad_norm": 0.11612524837255478,
      "learning_rate": 1e-06,
      "loss": -0.0059,
      "step": 1415
    },
    {
      "clip_ratio/high_max": 0.0019573812824091874,
      "clip_ratio/high_mean": 0.000728739829355618,
      "clip_ratio/low_mean": 0.0008410110503973556,
      "clip_ratio/low_min": 7.067221031320514e-05,
      "clip_ratio/region_mean": 0.0015697508424636908,
      "epoch": 0.132159669600826,
      "grad_norm": 0.12085966765880585,
      "learning_rate": 1e-06,
      "loss": 0.0448,
      "step": 1416
    },
    {
      "clip_ratio/high_max": 0.0018550842796685174,
      "clip_ratio/high_mean": 0.0008167285559466109,
      "clip_ratio/low_mean": 0.0007674849348404678,
      "clip_ratio/low_min": 4.4999127567280084e-05,
      "clip_ratio/region_mean": 0.001584213474416174,
      "epoch": 0.13225300270082657,
      "grad_norm": 0.11525612324476242,
      "learning_rate": 1e-06,
      "loss": 0.0088,
      "step": 1417
    },
    {
      "clip_ratio/high_max": 0.0021248445118544623,
      "clip_ratio/high_mean": 0.0009030141845869366,
      "clip_ratio/low_mean": 0.0008802323900454212,
      "clip_ratio/low_min": 9.565523214405403e-05,
      "clip_ratio/region_mean": 0.0017832465600804426,
      "epoch": 0.13234633580082716,
      "grad_norm": 0.12166012078523636,
      "learning_rate": 1e-06,
      "loss": 0.0266,
      "step": 1418
    },
    {
      "clip_ratio/high_max": 0.0019606359201134183,
      "clip_ratio/high_mean": 0.0008451259836874669,
      "clip_ratio/low_mean": 0.0008642487882752903,
      "clip_ratio/low_min": 4.388017623568885e-05,
      "clip_ratio/region_mean": 0.0017093747446779162,
      "epoch": 0.13243966890082776,
      "grad_norm": 0.10902386903762817,
      "learning_rate": 1e-06,
      "loss": -0.0215,
      "step": 1419
    },
    {
      "clip_ratio/high_max": 0.002401111130893696,
      "clip_ratio/high_mean": 0.0009743445334606804,
      "clip_ratio/low_mean": 0.0009989414484152803,
      "clip_ratio/low_min": 0.00011687158257700503,
      "clip_ratio/region_mean": 0.001973285965505056,
      "epoch": 0.13253300200082832,
      "grad_norm": 0.12161514908075333,
      "learning_rate": 1e-06,
      "loss": 0.0177,
      "step": 1420
    },
    {
      "clip_ratio/high_max": 0.0022329996463668067,
      "clip_ratio/high_mean": 0.0009630080312490463,
      "clip_ratio/low_mean": 0.0009733226579555776,
      "clip_ratio/low_min": 1.4371119505085517e-05,
      "clip_ratio/region_mean": 0.001936330649186857,
      "epoch": 0.1326263351008289,
      "grad_norm": 0.1233842521905899,
      "learning_rate": 1e-06,
      "loss": 0.0047,
      "step": 1421
    },
    {
      "clip_ratio/high_max": 0.002122777914337348,
      "clip_ratio/high_mean": 0.0009246743356925435,
      "clip_ratio/low_mean": 0.0009864262956398306,
      "clip_ratio/low_min": 3.7579444324364886e-05,
      "clip_ratio/region_mean": 0.0019111006549792364,
      "epoch": 0.1327196682008295,
      "grad_norm": 0.12592491507530212,
      "learning_rate": 1e-06,
      "loss": 0.0466,
      "step": 1422
    },
    {
      "clip_ratio/high_max": 0.0025194279587594792,
      "clip_ratio/high_mean": 0.0009719051213323837,
      "clip_ratio/low_mean": 0.0009411266473762225,
      "clip_ratio/low_min": 1.1363636076566763e-05,
      "clip_ratio/region_mean": 0.0019130317741655745,
      "epoch": 0.13281300130083007,
      "grad_norm": 0.10780708491802216,
      "learning_rate": 1e-06,
      "loss": 0.0007,
      "step": 1423
    },
    {
      "clip_ratio/high_max": 0.002110450623149518,
      "clip_ratio/high_mean": 0.0009039778142323485,
      "clip_ratio/low_mean": 0.0008634897039883072,
      "clip_ratio/low_min": 3.06673209706787e-05,
      "clip_ratio/region_mean": 0.0017674674600129947,
      "epoch": 0.13290633440083066,
      "grad_norm": 0.1022372916340828,
      "learning_rate": 1e-06,
      "loss": 0.0045,
      "step": 1424
    },
    {
      "clip_ratio/high_max": 0.002416127477772534,
      "clip_ratio/high_mean": 0.0009341938730358379,
      "clip_ratio/low_mean": 0.000875459831149783,
      "clip_ratio/low_min": 0.00011759636254282668,
      "clip_ratio/region_mean": 0.001809653709642589,
      "epoch": 0.13299966750083125,
      "grad_norm": 0.10229035466909409,
      "learning_rate": 1e-06,
      "loss": 0.0153,
      "step": 1425
    },
    {
      "clip_ratio/high_max": 0.0023262972608790733,
      "clip_ratio/high_mean": 0.000938324024900794,
      "clip_ratio/low_mean": 0.0010679275219445117,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002006251539569348,
      "epoch": 0.13309300060083182,
      "grad_norm": 0.11472427845001221,
      "learning_rate": 1e-06,
      "loss": 0.0285,
      "step": 1426
    },
    {
      "clip_ratio/high_max": 0.002210192436905345,
      "clip_ratio/high_mean": 0.0008469325894111535,
      "clip_ratio/low_mean": 0.0009266447996196803,
      "clip_ratio/low_min": 0.00010994085187121527,
      "clip_ratio/region_mean": 0.0017735773653839715,
      "epoch": 0.1331863337008324,
      "grad_norm": 0.11633387953042984,
      "learning_rate": 1e-06,
      "loss": 0.0626,
      "step": 1427
    },
    {
      "clip_ratio/high_max": 0.00241406295390334,
      "clip_ratio/high_mean": 0.0009293564216932282,
      "clip_ratio/low_mean": 0.0008625709851912688,
      "clip_ratio/low_min": 3.370303511474049e-05,
      "clip_ratio/region_mean": 0.0017919274541782215,
      "epoch": 0.133279666800833,
      "grad_norm": 0.10554017871618271,
      "learning_rate": 1e-06,
      "loss": -0.018,
      "step": 1428
    },
    {
      "clip_ratio/high_max": 0.002312235134013463,
      "clip_ratio/high_mean": 0.000986177175946068,
      "clip_ratio/low_mean": 0.000980331202299567,
      "clip_ratio/low_min": 6.621233842452057e-05,
      "clip_ratio/region_mean": 0.001966508374607656,
      "epoch": 0.1333729999008336,
      "grad_norm": 0.10500352829694748,
      "learning_rate": 1e-06,
      "loss": 0.0311,
      "step": 1429
    },
    {
      "clip_ratio/high_max": 0.0022750381322111934,
      "clip_ratio/high_mean": 0.000987979199635447,
      "clip_ratio/low_mean": 0.000954465547692962,
      "clip_ratio/low_min": 5.3228823162498884e-05,
      "clip_ratio/region_mean": 0.0019424447673372924,
      "epoch": 0.13346633300083416,
      "grad_norm": 0.12010016292333603,
      "learning_rate": 1e-06,
      "loss": -0.006,
      "step": 1430
    },
    {
      "clip_ratio/high_max": 0.0026293498958693817,
      "clip_ratio/high_mean": 0.001012986609566724,
      "clip_ratio/low_mean": 0.0010003645529650385,
      "clip_ratio/low_min": 0.00010023885806731414,
      "clip_ratio/region_mean": 0.002013351164350752,
      "epoch": 0.13355966610083475,
      "grad_norm": 0.22450974583625793,
      "learning_rate": 1e-06,
      "loss": -0.0008,
      "step": 1431
    },
    {
      "clip_ratio/high_max": 0.0023389422058244236,
      "clip_ratio/high_mean": 0.0010190101493208203,
      "clip_ratio/low_mean": 0.0010142018472834025,
      "clip_ratio/low_min": 7.786815240251599e-05,
      "clip_ratio/region_mean": 0.002033211989328265,
      "epoch": 0.13365299920083534,
      "grad_norm": 0.1232704147696495,
      "learning_rate": 1e-06,
      "loss": 0.0446,
      "step": 1432
    },
    {
      "clip_ratio/high_max": 0.002686832784092985,
      "clip_ratio/high_mean": 0.0010405555131001165,
      "clip_ratio/low_mean": 0.0011612515736487694,
      "clip_ratio/low_min": 5.750603577325819e-05,
      "clip_ratio/region_mean": 0.0022018070885678753,
      "epoch": 0.1337463323008359,
      "grad_norm": 0.11670401692390442,
      "learning_rate": 1e-06,
      "loss": 0.023,
      "step": 1433
    },
    {
      "clip_ratio/high_max": 0.0025915017977240495,
      "clip_ratio/high_mean": 0.0010605784591461997,
      "clip_ratio/low_mean": 0.0010589270295895403,
      "clip_ratio/low_min": 7.438726788677741e-05,
      "clip_ratio/region_mean": 0.002119505465088878,
      "epoch": 0.1338396654008365,
      "grad_norm": 0.1217108964920044,
      "learning_rate": 1e-06,
      "loss": 0.0312,
      "step": 1434
    },
    {
      "clip_ratio/high_max": 0.0023957593148224987,
      "clip_ratio/high_mean": 0.0008220075787903625,
      "clip_ratio/low_mean": 0.0010528042148507666,
      "clip_ratio/low_min": 3.618992559495382e-05,
      "clip_ratio/region_mean": 0.0018748117799987085,
      "epoch": 0.1339329985008371,
      "grad_norm": 0.10655663162469864,
      "learning_rate": 1e-06,
      "loss": 0.0313,
      "step": 1435
    },
    {
      "clip_ratio/high_max": 0.0024075108449324034,
      "clip_ratio/high_mean": 0.000968636930338107,
      "clip_ratio/low_mean": 0.0010758108910522424,
      "clip_ratio/low_min": 7.344112054852303e-05,
      "clip_ratio/region_mean": 0.0020444478213903494,
      "epoch": 0.13402633160083766,
      "grad_norm": 0.10565336793661118,
      "learning_rate": 1e-06,
      "loss": 0.0212,
      "step": 1436
    },
    {
      "clip_ratio/high_max": 0.0023795274828444235,
      "clip_ratio/high_mean": 0.0009553498221066548,
      "clip_ratio/low_mean": 0.0011769353768613655,
      "clip_ratio/low_min": 9.175698505714536e-05,
      "clip_ratio/region_mean": 0.002132285233528819,
      "epoch": 0.13411966470083825,
      "grad_norm": 0.11005101352930069,
      "learning_rate": 1e-06,
      "loss": 0.0308,
      "step": 1437
    },
    {
      "clip_ratio/high_max": 0.0025167810235871,
      "clip_ratio/high_mean": 0.0010111615592904855,
      "clip_ratio/low_mean": 0.0010541302799538244,
      "clip_ratio/low_min": 8.229420927818865e-05,
      "clip_ratio/region_mean": 0.002065291781036649,
      "epoch": 0.13421299780083884,
      "grad_norm": 0.11551311612129211,
      "learning_rate": 1e-06,
      "loss": 0.0004,
      "step": 1438
    },
    {
      "clip_ratio/high_max": 0.002602444546937477,
      "clip_ratio/high_mean": 0.0010254999961034628,
      "clip_ratio/low_mean": 0.001137688261223957,
      "clip_ratio/low_min": 1.6807853171485476e-05,
      "clip_ratio/region_mean": 0.002163188299164176,
      "epoch": 0.1343063309008394,
      "grad_norm": 0.11096356064081192,
      "learning_rate": 1e-06,
      "loss": 0.0092,
      "step": 1439
    },
    {
      "clip_ratio/high_max": 0.0026612578876665793,
      "clip_ratio/high_mean": 0.001025422296152101,
      "clip_ratio/low_mean": 0.0010505605787329841,
      "clip_ratio/low_min": 0.0001303464887314476,
      "clip_ratio/region_mean": 0.0020759829130838625,
      "epoch": 0.13439966400084,
      "grad_norm": 0.1314217746257782,
      "learning_rate": 1e-06,
      "loss": 0.0076,
      "step": 1440
    },
    {
      "clip_ratio/high_max": 0.002779732611088548,
      "clip_ratio/high_mean": 0.0010996875644195825,
      "clip_ratio/low_mean": 0.0011635952268989058,
      "clip_ratio/low_min": 0.00017972051682590973,
      "clip_ratio/region_mean": 0.0022632827967754565,
      "epoch": 0.1344929971008406,
      "grad_norm": 0.12370234727859497,
      "learning_rate": 1e-06,
      "loss": -0.0031,
      "step": 1441
    },
    {
      "clip_ratio/high_max": 0.0025649454910308123,
      "clip_ratio/high_mean": 0.0009810930150706554,
      "clip_ratio/low_mean": 0.0012442515981092583,
      "clip_ratio/low_min": 0.00017127721184806433,
      "clip_ratio/region_mean": 0.0022253446441027336,
      "epoch": 0.13458633020084115,
      "grad_norm": 0.11214728653430939,
      "learning_rate": 1e-06,
      "loss": 0.0249,
      "step": 1442
    },
    {
      "clip_ratio/high_max": 0.0024004285878618248,
      "clip_ratio/high_mean": 0.0009427154527656967,
      "clip_ratio/low_mean": 0.0010575019568932476,
      "clip_ratio/low_min": 1.5299878214136697e-05,
      "clip_ratio/region_mean": 0.0020002174060209654,
      "epoch": 0.13467966330084175,
      "grad_norm": 0.10256022959947586,
      "learning_rate": 1e-06,
      "loss": 0.0311,
      "step": 1443
    },
    {
      "clip_ratio/high_max": 0.0022697398671880364,
      "clip_ratio/high_mean": 0.0008995703392429277,
      "clip_ratio/low_mean": 0.0013505923016055021,
      "clip_ratio/low_min": 0.00016542463890800718,
      "clip_ratio/region_mean": 0.002250162622658536,
      "epoch": 0.13477299640084234,
      "grad_norm": 0.10748632997274399,
      "learning_rate": 1e-06,
      "loss": 0.0301,
      "step": 1444
    },
    {
      "clip_ratio/high_max": 0.0025347609735035803,
      "clip_ratio/high_mean": 0.0010447489330545068,
      "clip_ratio/low_mean": 0.0010094405279232888,
      "clip_ratio/low_min": 7.571061723865569e-05,
      "clip_ratio/region_mean": 0.0020541894700727426,
      "epoch": 0.1348663295008429,
      "grad_norm": 0.12649357318878174,
      "learning_rate": 1e-06,
      "loss": -0.0102,
      "step": 1445
    },
    {
      "clip_ratio/high_max": 0.002281164677697234,
      "clip_ratio/high_mean": 0.0009125149135797983,
      "clip_ratio/low_mean": 0.000942053011385724,
      "clip_ratio/low_min": 3.705899871420115e-05,
      "clip_ratio/region_mean": 0.0018545679340604693,
      "epoch": 0.1349596626008435,
      "grad_norm": 0.10778260976076126,
      "learning_rate": 1e-06,
      "loss": 0.0189,
      "step": 1446
    },
    {
      "clip_ratio/high_max": 0.0028327962281764485,
      "clip_ratio/high_mean": 0.0010599613597150892,
      "clip_ratio/low_mean": 0.0008716511892998824,
      "clip_ratio/low_min": 2.902926098613534e-05,
      "clip_ratio/region_mean": 0.0019316125544719398,
      "epoch": 0.1350529957008441,
      "grad_norm": 0.20406658947467804,
      "learning_rate": 1e-06,
      "loss": 0.0024,
      "step": 1447
    },
    {
      "clip_ratio/high_max": 0.002531581892981194,
      "clip_ratio/high_mean": 0.0010299961377313593,
      "clip_ratio/low_mean": 0.0010565808552200906,
      "clip_ratio/low_min": 8.090556821116479e-05,
      "clip_ratio/region_mean": 0.002086576983856503,
      "epoch": 0.13514632880084468,
      "grad_norm": 0.1103234514594078,
      "learning_rate": 1e-06,
      "loss": -0.0025,
      "step": 1448
    },
    {
      "clip_ratio/high_max": 0.0022429615928558633,
      "clip_ratio/high_mean": 0.0009579505167494062,
      "clip_ratio/low_mean": 0.0008745914383325726,
      "clip_ratio/low_min": 3.975093386543449e-05,
      "clip_ratio/region_mean": 0.0018325419077882543,
      "epoch": 0.13523966190084524,
      "grad_norm": 0.12768018245697021,
      "learning_rate": 1e-06,
      "loss": 0.0167,
      "step": 1449
    },
    {
      "clip_ratio/high_max": 0.0022056354937376454,
      "clip_ratio/high_mean": 0.0008714211489859736,
      "clip_ratio/low_mean": 0.0011531706077221315,
      "clip_ratio/low_min": 8.396076736971736e-05,
      "clip_ratio/region_mean": 0.002024591783992946,
      "epoch": 0.13533299500084583,
      "grad_norm": 0.10748114436864853,
      "learning_rate": 1e-06,
      "loss": 0.0463,
      "step": 1450
    },
    {
      "clip_ratio/high_max": 0.002638293561176397,
      "clip_ratio/high_mean": 0.0010356989405408967,
      "clip_ratio/low_mean": 0.0010219905525445938,
      "clip_ratio/low_min": 6.249376747291535e-05,
      "clip_ratio/region_mean": 0.0020576894530677237,
      "epoch": 0.13542632810084643,
      "grad_norm": 0.11492206901311874,
      "learning_rate": 1e-06,
      "loss": 0.0375,
      "step": 1451
    },
    {
      "clip_ratio/high_max": 0.0023746957813273184,
      "clip_ratio/high_mean": 0.0010006988632085267,
      "clip_ratio/low_mean": 0.0008632588123873575,
      "clip_ratio/low_min": 9.69443135545589e-06,
      "clip_ratio/region_mean": 0.0018639576956047677,
      "epoch": 0.135519661200847,
      "grad_norm": 0.10269959270954132,
      "learning_rate": 1e-06,
      "loss": -0.014,
      "step": 1452
    },
    {
      "clip_ratio/high_max": 0.0024743874309933744,
      "clip_ratio/high_mean": 0.0009452612412133021,
      "clip_ratio/low_mean": 0.001193292595417006,
      "clip_ratio/low_min": 0.00012857609362981748,
      "clip_ratio/region_mean": 0.002138553863915149,
      "epoch": 0.13561299430084758,
      "grad_norm": 0.12056542187929153,
      "learning_rate": 1e-06,
      "loss": 0.0745,
      "step": 1453
    },
    {
      "clip_ratio/high_max": 0.0022832017712062225,
      "clip_ratio/high_mean": 0.001005373411317123,
      "clip_ratio/low_mean": 0.0011942303499381524,
      "clip_ratio/low_min": 0.00011587541666813195,
      "clip_ratio/region_mean": 0.0021996038121869788,
      "epoch": 0.13570632740084818,
      "grad_norm": 0.1196768581867218,
      "learning_rate": 1e-06,
      "loss": 0.0431,
      "step": 1454
    },
    {
      "clip_ratio/high_max": 0.002098278739140369,
      "clip_ratio/high_mean": 0.0009257079072995111,
      "clip_ratio/low_mean": 0.0012094331978005357,
      "clip_ratio/low_min": 0.0001223248591486481,
      "clip_ratio/region_mean": 0.0021351410687202588,
      "epoch": 0.13579966050084874,
      "grad_norm": 0.11572129279375076,
      "learning_rate": 1e-06,
      "loss": 0.0511,
      "step": 1455
    },
    {
      "clip_ratio/high_max": 0.002783639749395661,
      "clip_ratio/high_mean": 0.001167096932476852,
      "clip_ratio/low_mean": 0.0011270478389633354,
      "clip_ratio/low_min": 1.1636566341621801e-05,
      "clip_ratio/region_mean": 0.002294144738698378,
      "epoch": 0.13589299360084933,
      "grad_norm": 0.12415316700935364,
      "learning_rate": 1e-06,
      "loss": 0.0077,
      "step": 1456
    },
    {
      "clip_ratio/high_max": 0.0024204809160437435,
      "clip_ratio/high_mean": 0.0009866714590316406,
      "clip_ratio/low_mean": 0.0012838316506531555,
      "clip_ratio/low_min": 5.947602039668709e-05,
      "clip_ratio/region_mean": 0.0022705030933138914,
      "epoch": 0.13598632670084992,
      "grad_norm": 0.11749020963907242,
      "learning_rate": 1e-06,
      "loss": 0.0451,
      "step": 1457
    },
    {
      "clip_ratio/high_max": 0.0023182419390650466,
      "clip_ratio/high_mean": 0.0009759142149050604,
      "clip_ratio/low_mean": 0.0013810494820063468,
      "clip_ratio/low_min": 0.00014673938130727038,
      "clip_ratio/region_mean": 0.0023569636905449443,
      "epoch": 0.1360796598008505,
      "grad_norm": 0.1164017990231514,
      "learning_rate": 1e-06,
      "loss": 0.0705,
      "step": 1458
    },
    {
      "clip_ratio/high_max": 0.002677210701222066,
      "clip_ratio/high_mean": 0.0011295473705104087,
      "clip_ratio/low_mean": 0.0009461676654609619,
      "clip_ratio/low_min": 5.197474092710763e-05,
      "clip_ratio/region_mean": 0.0020757149904966354,
      "epoch": 0.13617299290085108,
      "grad_norm": 0.11543598771095276,
      "learning_rate": 1e-06,
      "loss": 0.0161,
      "step": 1459
    },
    {
      "clip_ratio/high_max": 0.0027790833119070157,
      "clip_ratio/high_mean": 0.0011419239217502763,
      "clip_ratio/low_mean": 0.001205698001285782,
      "clip_ratio/low_min": 0.00013721889263251796,
      "clip_ratio/region_mean": 0.002347621863009408,
      "epoch": 0.13626632600085167,
      "grad_norm": 0.12189850211143494,
      "learning_rate": 1e-06,
      "loss": 0.0283,
      "step": 1460
    },
    {
      "clip_ratio/high_max": 0.0031833853718126193,
      "clip_ratio/high_mean": 0.0012375878359307535,
      "clip_ratio/low_mean": 0.0010633088550093817,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0023008967109490186,
      "epoch": 0.13635965910085224,
      "grad_norm": 0.14021095633506775,
      "learning_rate": 1e-06,
      "loss": -0.0025,
      "step": 1461
    },
    {
      "clip_ratio/high_max": 0.003089932339207735,
      "clip_ratio/high_mean": 0.0011884087252838071,
      "clip_ratio/low_mean": 0.001165329995274078,
      "clip_ratio/low_min": 7.758036554150749e-05,
      "clip_ratio/region_mean": 0.0023537386950920336,
      "epoch": 0.13645299220085283,
      "grad_norm": 0.1187484860420227,
      "learning_rate": 1e-06,
      "loss": 0.0065,
      "step": 1462
    },
    {
      "clip_ratio/high_max": 0.0027623161076917313,
      "clip_ratio/high_mean": 0.0011216348339075921,
      "clip_ratio/low_mean": 0.0011028113585780375,
      "clip_ratio/low_min": 2.3593809601152316e-05,
      "clip_ratio/region_mean": 0.0022244461797527038,
      "epoch": 0.13654632530085342,
      "grad_norm": 0.12906920909881592,
      "learning_rate": 1e-06,
      "loss": -0.0003,
      "step": 1463
    },
    {
      "clip_ratio/high_max": 0.0027788856968982145,
      "clip_ratio/high_mean": 0.0011064249811170157,
      "clip_ratio/low_mean": 0.0011159217938256916,
      "clip_ratio/low_min": 6.800706432841253e-05,
      "clip_ratio/region_mean": 0.002222346760390792,
      "epoch": 0.13663965840085399,
      "grad_norm": 0.11796051263809204,
      "learning_rate": 1e-06,
      "loss": 0.0246,
      "step": 1464
    },
    {
      "clip_ratio/high_max": 0.0029790025073452853,
      "clip_ratio/high_mean": 0.0011487963602121454,
      "clip_ratio/low_mean": 0.001116381197789451,
      "clip_ratio/low_min": 8.464285565423779e-05,
      "clip_ratio/region_mean": 0.0022651775580015965,
      "epoch": 0.13673299150085458,
      "grad_norm": 0.1100466251373291,
      "learning_rate": 1e-06,
      "loss": 0.0041,
      "step": 1465
    },
    {
      "clip_ratio/high_max": 0.002850481600034982,
      "clip_ratio/high_mean": 0.0013040837438893504,
      "clip_ratio/low_mean": 0.0009520533167233225,
      "clip_ratio/low_min": 3.74925002688542e-05,
      "clip_ratio/region_mean": 0.0022561370860785246,
      "epoch": 0.13682632460085517,
      "grad_norm": 0.33849474787712097,
      "learning_rate": 1e-06,
      "loss": -0.0064,
      "step": 1466
    },
    {
      "clip_ratio/high_max": 0.0026202483277302235,
      "clip_ratio/high_mean": 0.001034944554703543,
      "clip_ratio/low_mean": 0.0010917742984020151,
      "clip_ratio/low_min": 3.7937848901492544e-05,
      "clip_ratio/region_mean": 0.0021267188494675793,
      "epoch": 0.13691965770085573,
      "grad_norm": 0.11754457652568817,
      "learning_rate": 1e-06,
      "loss": 0.0232,
      "step": 1467
    },
    {
      "clip_ratio/high_max": 0.0027402813138905913,
      "clip_ratio/high_mean": 0.0010319926659576595,
      "clip_ratio/low_mean": 0.0012252390952198766,
      "clip_ratio/low_min": 0.0001071486112778075,
      "clip_ratio/region_mean": 0.0022572317320737056,
      "epoch": 0.13701299080085633,
      "grad_norm": 0.1115499809384346,
      "learning_rate": 1e-06,
      "loss": 0.0781,
      "step": 1468
    },
    {
      "clip_ratio/high_max": 0.0022908212267793715,
      "clip_ratio/high_mean": 0.0009174980950774625,
      "clip_ratio/low_mean": 0.0010252227693854365,
      "clip_ratio/low_min": 2.6415891625219956e-05,
      "clip_ratio/region_mean": 0.001942720904480666,
      "epoch": 0.13710632390085692,
      "grad_norm": 0.09845107793807983,
      "learning_rate": 1e-06,
      "loss": 0.036,
      "step": 1469
    },
    {
      "clip_ratio/high_max": 0.0025174013135256246,
      "clip_ratio/high_mean": 0.0010821056366694393,
      "clip_ratio/low_mean": 0.0010607309122860897,
      "clip_ratio/low_min": 5.6766577472444624e-05,
      "clip_ratio/region_mean": 0.002142836521670688,
      "epoch": 0.1371996570008575,
      "grad_norm": 0.11507207900285721,
      "learning_rate": 1e-06,
      "loss": 0.0527,
      "step": 1470
    },
    {
      "clip_ratio/high_max": 0.0028368353232508525,
      "clip_ratio/high_mean": 0.0010975784716720227,
      "clip_ratio/low_mean": 0.0011960793635807931,
      "clip_ratio/low_min": 4.760220690513961e-05,
      "clip_ratio/region_mean": 0.002293657817062922,
      "epoch": 0.13729299010085808,
      "grad_norm": 0.10873386263847351,
      "learning_rate": 1e-06,
      "loss": 0.0425,
      "step": 1471
    },
    {
      "clip_ratio/high_max": 0.0027898061234736815,
      "clip_ratio/high_mean": 0.001167829723272007,
      "clip_ratio/low_mean": 0.0011882341605087277,
      "clip_ratio/low_min": 1.1750328667403664e-05,
      "clip_ratio/region_mean": 0.002356063916522544,
      "epoch": 0.13738632320085867,
      "grad_norm": 0.2642475366592407,
      "learning_rate": 1e-06,
      "loss": 0.0214,
      "step": 1472
    },
    {
      "clip_ratio/high_max": 0.0027806581929326057,
      "clip_ratio/high_mean": 0.0010844345415534917,
      "clip_ratio/low_mean": 0.0010767722087621223,
      "clip_ratio/low_min": 3.2729547456256114e-05,
      "clip_ratio/region_mean": 0.00216120682307519,
      "epoch": 0.13747965630085926,
      "grad_norm": 0.11807902902364731,
      "learning_rate": 1e-06,
      "loss": 0.0583,
      "step": 1473
    },
    {
      "clip_ratio/high_max": 0.00230437903519487,
      "clip_ratio/high_mean": 0.0009912665336742066,
      "clip_ratio/low_mean": 0.0013206935072958004,
      "clip_ratio/low_min": 0.00017362347898597363,
      "clip_ratio/region_mean": 0.0023119600300560705,
      "epoch": 0.13757298940085982,
      "grad_norm": 0.10598843544721603,
      "learning_rate": 1e-06,
      "loss": 0.0528,
      "step": 1474
    },
    {
      "clip_ratio/high_max": 0.0026677254936657846,
      "clip_ratio/high_mean": 0.001104568629671121,
      "clip_ratio/low_mean": 0.0013112452252244111,
      "clip_ratio/low_min": 0.00015924924537102925,
      "clip_ratio/region_mean": 0.002415813876723405,
      "epoch": 0.13766632250086042,
      "grad_norm": 0.13652527332305908,
      "learning_rate": 1e-06,
      "loss": 0.0274,
      "step": 1475
    },
    {
      "clip_ratio/high_max": 0.002653229093994014,
      "clip_ratio/high_mean": 0.0010956492460536538,
      "clip_ratio/low_mean": 0.0011827794260170776,
      "clip_ratio/low_min": 2.0404831957421266e-05,
      "clip_ratio/region_mean": 0.0022784286556998268,
      "epoch": 0.137759655600861,
      "grad_norm": 0.14880774915218353,
      "learning_rate": 1e-06,
      "loss": 0.0736,
      "step": 1476
    },
    {
      "clip_ratio/high_max": 0.0027769236112362705,
      "clip_ratio/high_mean": 0.0012398618237057235,
      "clip_ratio/low_mean": 0.0010940074280370027,
      "clip_ratio/low_min": 6.257114364416339e-05,
      "clip_ratio/region_mean": 0.0023338692844845355,
      "epoch": 0.13785298870086157,
      "grad_norm": 0.12175989896059036,
      "learning_rate": 1e-06,
      "loss": 0.0544,
      "step": 1477
    },
    {
      "clip_ratio/high_max": 0.002621554202050902,
      "clip_ratio/high_mean": 0.0011173183247592533,
      "clip_ratio/low_mean": 0.0010841846651601372,
      "clip_ratio/low_min": 2.900824893004028e-05,
      "clip_ratio/region_mean": 0.00220150296081556,
      "epoch": 0.13794632180086216,
      "grad_norm": 0.11229871958494186,
      "learning_rate": 1e-06,
      "loss": 0.0081,
      "step": 1478
    },
    {
      "clip_ratio/high_max": 0.0025504994409857318,
      "clip_ratio/high_mean": 0.0010641595035849605,
      "clip_ratio/low_mean": 0.001272096731554484,
      "clip_ratio/low_min": 0.00011690111205098219,
      "clip_ratio/region_mean": 0.002336256300623063,
      "epoch": 0.13803965490086276,
      "grad_norm": 0.10911792516708374,
      "learning_rate": 1e-06,
      "loss": 0.0363,
      "step": 1479
    },
    {
      "clip_ratio/high_max": 0.0027662291686283424,
      "clip_ratio/high_mean": 0.0009855065327428747,
      "clip_ratio/low_mean": 0.0012573996973515023,
      "clip_ratio/low_min": 0.00013462905553751625,
      "clip_ratio/region_mean": 0.0022429062591982074,
      "epoch": 0.13813298800086332,
      "grad_norm": 0.11720386892557144,
      "learning_rate": 1e-06,
      "loss": 0.0873,
      "step": 1480
    },
    {
      "clip_ratio/high_max": 0.002455437512253411,
      "clip_ratio/high_mean": 0.0011465769639471546,
      "clip_ratio/low_mean": 0.0008920716918510152,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0020386486503412016,
      "epoch": 0.1382263211008639,
      "grad_norm": 0.10856595635414124,
      "learning_rate": 1e-06,
      "loss": -0.0525,
      "step": 1481
    },
    {
      "clip_ratio/high_max": 0.003157646337058395,
      "clip_ratio/high_mean": 0.0012697432248387486,
      "clip_ratio/low_mean": 0.0013415203011390986,
      "clip_ratio/low_min": 0.00017994404333876446,
      "clip_ratio/region_mean": 0.002611263498693006,
      "epoch": 0.1383196542008645,
      "grad_norm": 0.11082890629768372,
      "learning_rate": 1e-06,
      "loss": 0.0241,
      "step": 1482
    },
    {
      "clip_ratio/high_max": 0.002796586908516474,
      "clip_ratio/high_mean": 0.001134596750489436,
      "clip_ratio/low_mean": 0.0012173211980552878,
      "clip_ratio/low_min": 5.783602773590246e-05,
      "clip_ratio/region_mean": 0.0023519179740105756,
      "epoch": 0.13841298730086507,
      "grad_norm": 0.11337212473154068,
      "learning_rate": 1e-06,
      "loss": 0.0156,
      "step": 1483
    },
    {
      "clip_ratio/high_max": 0.002386477601248771,
      "clip_ratio/high_mean": 0.0011547439389687497,
      "clip_ratio/low_mean": 0.0011973719647357939,
      "clip_ratio/low_min": 5.4087871831143275e-05,
      "clip_ratio/region_mean": 0.002352115901885554,
      "epoch": 0.13850632040086566,
      "grad_norm": 0.12178612500429153,
      "learning_rate": 1e-06,
      "loss": -0.0184,
      "step": 1484
    },
    {
      "clip_ratio/high_max": 0.0028518163599073887,
      "clip_ratio/high_mean": 0.0011635217379080132,
      "clip_ratio/low_mean": 0.0015868476548348553,
      "clip_ratio/low_min": 9.053309167939005e-05,
      "clip_ratio/region_mean": 0.0027503694145707414,
      "epoch": 0.13859965350086625,
      "grad_norm": 0.8915780782699585,
      "learning_rate": 1e-06,
      "loss": 0.0271,
      "step": 1485
    },
    {
      "clip_ratio/high_max": 0.0028316673924564384,
      "clip_ratio/high_mean": 0.0012044939321640413,
      "clip_ratio/low_mean": 0.0013307863246154739,
      "clip_ratio/low_min": 6.622794171562418e-05,
      "clip_ratio/region_mean": 0.0025352802622364834,
      "epoch": 0.13869298660086682,
      "grad_norm": 0.12048197537660599,
      "learning_rate": 1e-06,
      "loss": 0.0169,
      "step": 1486
    },
    {
      "clip_ratio/high_max": 0.00242381803036551,
      "clip_ratio/high_mean": 0.0009514506655250443,
      "clip_ratio/low_mean": 0.0012668999952438753,
      "clip_ratio/low_min": 6.188119004946202e-05,
      "clip_ratio/region_mean": 0.0022183506589499302,
      "epoch": 0.1387863197008674,
      "grad_norm": 0.11273396760225296,
      "learning_rate": 1e-06,
      "loss": 0.0679,
      "step": 1487
    },
    {
      "clip_ratio/high_max": 0.002115559844241943,
      "clip_ratio/high_mean": 0.0009105337558139581,
      "clip_ratio/low_mean": 0.0012671837903326377,
      "clip_ratio/low_min": 6.36501745248097e-05,
      "clip_ratio/region_mean": 0.00217771756433649,
      "epoch": 0.138879652800868,
      "grad_norm": 0.11106456071138382,
      "learning_rate": 1e-06,
      "loss": 0.0883,
      "step": 1488
    },
    {
      "clip_ratio/high_max": 0.0032058905926533043,
      "clip_ratio/high_mean": 0.0013475653340719873,
      "clip_ratio/low_mean": 0.001286232351048966,
      "clip_ratio/low_min": 6.045325608283747e-05,
      "clip_ratio/region_mean": 0.0026337976596551016,
      "epoch": 0.13897298590086857,
      "grad_norm": 0.13243578374385834,
      "learning_rate": 1e-06,
      "loss": 0.0016,
      "step": 1489
    },
    {
      "clip_ratio/high_max": 0.0030218889587558806,
      "clip_ratio/high_mean": 0.0014174635944073088,
      "clip_ratio/low_mean": 0.0013734282765653916,
      "clip_ratio/low_min": 6.388055044226348e-05,
      "clip_ratio/region_mean": 0.0027908918709727004,
      "epoch": 0.13906631900086916,
      "grad_norm": 0.13378465175628662,
      "learning_rate": 1e-06,
      "loss": 0.0032,
      "step": 1490
    },
    {
      "clip_ratio/high_max": 0.002750161314907018,
      "clip_ratio/high_mean": 0.0012205466300656553,
      "clip_ratio/low_mean": 0.0012897806554974522,
      "clip_ratio/low_min": 3.115206618531374e-05,
      "clip_ratio/region_mean": 0.0025103273073909804,
      "epoch": 0.13915965210086975,
      "grad_norm": 0.1216592937707901,
      "learning_rate": 1e-06,
      "loss": 0.0075,
      "step": 1491
    },
    {
      "clip_ratio/high_max": 0.0034090596018359065,
      "clip_ratio/high_mean": 0.0013427475350908935,
      "clip_ratio/low_mean": 0.0013731910985370632,
      "clip_ratio/low_min": 0.00012055199294991326,
      "clip_ratio/region_mean": 0.0027159386372659355,
      "epoch": 0.13925298520087034,
      "grad_norm": 0.12644340097904205,
      "learning_rate": 1e-06,
      "loss": 0.035,
      "step": 1492
    },
    {
      "clip_ratio/high_max": 0.0028981095310882665,
      "clip_ratio/high_mean": 0.0012044994709867751,
      "clip_ratio/low_mean": 0.0014194349605531897,
      "clip_ratio/low_min": 7.9481867942377e-05,
      "clip_ratio/region_mean": 0.002623934495204594,
      "epoch": 0.1393463183008709,
      "grad_norm": 0.10122072696685791,
      "learning_rate": 1e-06,
      "loss": 0.0344,
      "step": 1493
    },
    {
      "clip_ratio/high_max": 0.0027495212052599527,
      "clip_ratio/high_mean": 0.0010657707225618651,
      "clip_ratio/low_mean": 0.0014343884904519655,
      "clip_ratio/low_min": 8.432873619312886e-05,
      "clip_ratio/region_mean": 0.0025001592221087776,
      "epoch": 0.1394396514008715,
      "grad_norm": 0.1175919622182846,
      "learning_rate": 1e-06,
      "loss": 0.0458,
      "step": 1494
    },
    {
      "clip_ratio/high_max": 0.003198013157089008,
      "clip_ratio/high_mean": 0.0012178584383946145,
      "clip_ratio/low_mean": 0.001467868009058293,
      "clip_ratio/low_min": 0.00019013058044947684,
      "clip_ratio/region_mean": 0.0026857264747377485,
      "epoch": 0.1395329845008721,
      "grad_norm": 0.11551834642887115,
      "learning_rate": 1e-06,
      "loss": 0.0376,
      "step": 1495
    },
    {
      "clip_ratio/high_max": 0.002495275213732384,
      "clip_ratio/high_mean": 0.001112371477574925,
      "clip_ratio/low_mean": 0.0016496615135110915,
      "clip_ratio/low_min": 0.0002636298904690193,
      "clip_ratio/region_mean": 0.002762032934697345,
      "epoch": 0.13962631760087266,
      "grad_norm": 0.12206330895423889,
      "learning_rate": 1e-06,
      "loss": 0.0396,
      "step": 1496
    },
    {
      "clip_ratio/high_max": 0.0031529958941973746,
      "clip_ratio/high_mean": 0.0012376550475892145,
      "clip_ratio/low_mean": 0.0014256401354941772,
      "clip_ratio/low_min": 0.00013022826624364825,
      "clip_ratio/region_mean": 0.0026632951630745083,
      "epoch": 0.13971965070087325,
      "grad_norm": 0.11085369437932968,
      "learning_rate": 1e-06,
      "loss": 0.0231,
      "step": 1497
    },
    {
      "clip_ratio/high_max": 0.00304369097284507,
      "clip_ratio/high_mean": 0.0012894755527668167,
      "clip_ratio/low_mean": 0.001411107596140937,
      "clip_ratio/low_min": 5.437935033114627e-05,
      "clip_ratio/region_mean": 0.0027005832016584463,
      "epoch": 0.13981298380087384,
      "grad_norm": 0.10914954543113708,
      "learning_rate": 1e-06,
      "loss": -0.024,
      "step": 1498
    },
    {
      "clip_ratio/high_max": 0.003024964840733446,
      "clip_ratio/high_mean": 0.0011884650120919105,
      "clip_ratio/low_mean": 0.0015281092637451366,
      "clip_ratio/low_min": 0.00015683392666687723,
      "clip_ratio/region_mean": 0.002716574199439492,
      "epoch": 0.1399063169008744,
      "grad_norm": 0.12459231168031693,
      "learning_rate": 1e-06,
      "loss": 0.0287,
      "step": 1499
    },
    {
      "clip_ratio/high_max": 0.0026434208630234934,
      "clip_ratio/high_mean": 0.0011657636187010212,
      "clip_ratio/low_mean": 0.0014828504899924155,
      "clip_ratio/low_min": 0.0002036403102465556,
      "clip_ratio/region_mean": 0.0026486140995984897,
      "epoch": 0.139999650000875,
      "grad_norm": 0.11421504616737366,
      "learning_rate": 1e-06,
      "loss": 0.0112,
      "step": 1500
    },
    {
      "clip_ratio/high_max": 0.002660350342921447,
      "clip_ratio/high_mean": 0.00120506559687783,
      "clip_ratio/low_mean": 0.0013747928351222072,
      "clip_ratio/low_min": 6.180469790706411e-05,
      "clip_ratio/region_mean": 0.0025798583519645035,
      "epoch": 0.1400929831008756,
      "grad_norm": 0.12463909387588501,
      "learning_rate": 1e-06,
      "loss": 0.0279,
      "step": 1501
    },
    {
      "clip_ratio/high_max": 0.0031790221473784186,
      "clip_ratio/high_mean": 0.0013923024052928668,
      "clip_ratio/low_mean": 0.0014092396559135523,
      "clip_ratio/low_min": 5.6706932809902355e-05,
      "clip_ratio/region_mean": 0.002801542097586207,
      "epoch": 0.14018631620087615,
      "grad_norm": 0.11176576465368271,
      "learning_rate": 1e-06,
      "loss": -0.008,
      "step": 1502
    },
    {
      "clip_ratio/high_max": 0.003155170845275279,
      "clip_ratio/high_mean": 0.0014255678615882061,
      "clip_ratio/low_mean": 0.0013273939566715853,
      "clip_ratio/low_min": 0.00010759520137071377,
      "clip_ratio/region_mean": 0.002752961801888887,
      "epoch": 0.14027964930087675,
      "grad_norm": 0.12618066370487213,
      "learning_rate": 1e-06,
      "loss": 0.0259,
      "step": 1503
    },
    {
      "clip_ratio/high_max": 0.0029176129610277712,
      "clip_ratio/high_mean": 0.0011191985668119742,
      "clip_ratio/low_mean": 0.0013986341982672457,
      "clip_ratio/low_min": 4.165278369328007e-05,
      "clip_ratio/region_mean": 0.0025178326832246967,
      "epoch": 0.14037298240087734,
      "grad_norm": 0.11602681875228882,
      "learning_rate": 1e-06,
      "loss": 0.0284,
      "step": 1504
    },
    {
      "clip_ratio/high_max": 0.0029687997594010085,
      "clip_ratio/high_mean": 0.0012583686147991102,
      "clip_ratio/low_mean": 0.0013929991746408632,
      "clip_ratio/low_min": 0.0001012433231153409,
      "clip_ratio/region_mean": 0.0026513678021728992,
      "epoch": 0.1404663155008779,
      "grad_norm": 0.11358543485403061,
      "learning_rate": 1e-06,
      "loss": 0.0325,
      "step": 1505
    },
    {
      "clip_ratio/high_max": 0.0026435050822328776,
      "clip_ratio/high_mean": 0.0010515982685319614,
      "clip_ratio/low_mean": 0.0015071502548380522,
      "clip_ratio/low_min": 0.00012342986701696645,
      "clip_ratio/region_mean": 0.0025587485943106003,
      "epoch": 0.1405596486008785,
      "grad_norm": 0.12584316730499268,
      "learning_rate": 1e-06,
      "loss": 0.0688,
      "step": 1506
    },
    {
      "clip_ratio/high_max": 0.002997233343194239,
      "clip_ratio/high_mean": 0.0011706749100994784,
      "clip_ratio/low_mean": 0.0015161802621150855,
      "clip_ratio/low_min": 4.1869564483931754e-05,
      "clip_ratio/region_mean": 0.002686855135834776,
      "epoch": 0.1406529817008791,
      "grad_norm": 0.11772178113460541,
      "learning_rate": 1e-06,
      "loss": 0.054,
      "step": 1507
    },
    {
      "clip_ratio/high_max": 0.003039415714738425,
      "clip_ratio/high_mean": 0.0013107438098813873,
      "clip_ratio/low_mean": 0.001529441764432704,
      "clip_ratio/low_min": 2.7337498067936394e-05,
      "clip_ratio/region_mean": 0.0028401855743140914,
      "epoch": 0.14074631480087965,
      "grad_norm": 0.6940681338310242,
      "learning_rate": 1e-06,
      "loss": 0.058,
      "step": 1508
    },
    {
      "clip_ratio/high_max": 0.002835014762240462,
      "clip_ratio/high_mean": 0.0011606671087065479,
      "clip_ratio/low_mean": 0.001262158461031504,
      "clip_ratio/low_min": 0.0001038056561810663,
      "clip_ratio/region_mean": 0.002422825520625338,
      "epoch": 0.14083964790088024,
      "grad_norm": 0.11285444349050522,
      "learning_rate": 1e-06,
      "loss": 0.0155,
      "step": 1509
    },
    {
      "clip_ratio/high_max": 0.0027010888152290136,
      "clip_ratio/high_mean": 0.001216887823829893,
      "clip_ratio/low_mean": 0.001354956802970264,
      "clip_ratio/low_min": 0.00010493374520592624,
      "clip_ratio/region_mean": 0.002571844575868454,
      "epoch": 0.14093298100088084,
      "grad_norm": 0.11101323366165161,
      "learning_rate": 1e-06,
      "loss": 0.025,
      "step": 1510
    },
    {
      "clip_ratio/high_max": 0.002534585633839015,
      "clip_ratio/high_mean": 0.0012337300031504128,
      "clip_ratio/low_mean": 0.0013232888722995995,
      "clip_ratio/low_min": 3.3068783523049206e-05,
      "clip_ratio/region_mean": 0.0025570188809069805,
      "epoch": 0.14102631410088143,
      "grad_norm": 0.11713607609272003,
      "learning_rate": 1e-06,
      "loss": 0.0082,
      "step": 1511
    },
    {
      "clip_ratio/high_max": 0.002500711430911906,
      "clip_ratio/high_mean": 0.0011643929647107143,
      "clip_ratio/low_mean": 0.0014246238661144162,
      "clip_ratio/low_min": 0.00018839373842638452,
      "clip_ratio/region_mean": 0.0025890168617479503,
      "epoch": 0.141119647200882,
      "grad_norm": 0.42848077416419983,
      "learning_rate": 1e-06,
      "loss": 0.0301,
      "step": 1512
    },
    {
      "clip_ratio/high_max": 0.0029574047221103683,
      "clip_ratio/high_mean": 0.0013003620006202254,
      "clip_ratio/low_mean": 0.0014682605542475358,
      "clip_ratio/low_min": 0.00015262598844856257,
      "clip_ratio/region_mean": 0.0027686225657816976,
      "epoch": 0.14121298030088258,
      "grad_norm": 0.11400165408849716,
      "learning_rate": 1e-06,
      "loss": 0.0648,
      "step": 1513
    },
    {
      "clip_ratio/high_max": 0.0031129845301620662,
      "clip_ratio/high_mean": 0.0014050981408217922,
      "clip_ratio/low_mean": 0.0014090836575633148,
      "clip_ratio/low_min": 3.0443254217971116e-05,
      "clip_ratio/region_mean": 0.0028141818183939904,
      "epoch": 0.14130631340088318,
      "grad_norm": 0.11875130981206894,
      "learning_rate": 1e-06,
      "loss": 0.0443,
      "step": 1514
    },
    {
      "clip_ratio/high_max": 0.0031790507564437576,
      "clip_ratio/high_mean": 0.001355299238639418,
      "clip_ratio/low_mean": 0.001307690268731676,
      "clip_ratio/low_min": 6.134942668722942e-05,
      "clip_ratio/region_mean": 0.002662989529198967,
      "epoch": 0.14139964650088374,
      "grad_norm": 0.11250169575214386,
      "learning_rate": 1e-06,
      "loss": -0.0037,
      "step": 1515
    },
    {
      "clip_ratio/high_max": 0.0031033246414153837,
      "clip_ratio/high_mean": 0.0014096756658545928,
      "clip_ratio/low_mean": 0.0014154239870549645,
      "clip_ratio/low_min": 0.00011577975965337828,
      "clip_ratio/region_mean": 0.0028250996620045044,
      "epoch": 0.14149297960088433,
      "grad_norm": 0.11189062893390656,
      "learning_rate": 1e-06,
      "loss": -0.0219,
      "step": 1516
    },
    {
      "clip_ratio/high_max": 0.00262328968528891,
      "clip_ratio/high_mean": 0.0012249394676473457,
      "clip_ratio/low_mean": 0.0014173396011756267,
      "clip_ratio/low_min": 2.3818596673663706e-05,
      "clip_ratio/region_mean": 0.0026422790833748877,
      "epoch": 0.14158631270088493,
      "grad_norm": 0.11323901265859604,
      "learning_rate": 1e-06,
      "loss": 0.0339,
      "step": 1517
    },
    {
      "clip_ratio/high_max": 0.0030602438637288287,
      "clip_ratio/high_mean": 0.0012743712250085082,
      "clip_ratio/low_mean": 0.001624144413653994,
      "clip_ratio/low_min": 0.00015085985160112614,
      "clip_ratio/region_mean": 0.0028985156532144174,
      "epoch": 0.1416796458008855,
      "grad_norm": 0.13926741480827332,
      "learning_rate": 1e-06,
      "loss": 0.0199,
      "step": 1518
    },
    {
      "clip_ratio/high_max": 0.0027332588215358555,
      "clip_ratio/high_mean": 0.0013018932040722575,
      "clip_ratio/low_mean": 0.0014374567617778666,
      "clip_ratio/low_min": 0.00010010834012064151,
      "clip_ratio/region_mean": 0.0027393499985919334,
      "epoch": 0.14177297890088608,
      "grad_norm": 0.11344989389181137,
      "learning_rate": 1e-06,
      "loss": 0.0196,
      "step": 1519
    },
    {
      "clip_ratio/high_max": 0.003331129366415553,
      "clip_ratio/high_mean": 0.001459608472941909,
      "clip_ratio/low_mean": 0.0014270490228227573,
      "clip_ratio/low_min": 6.051510354154743e-05,
      "clip_ratio/region_mean": 0.0028866574430139735,
      "epoch": 0.14186631200088667,
      "grad_norm": 1.6462842226028442,
      "learning_rate": 1e-06,
      "loss": -0.0064,
      "step": 1520
    },
    {
      "clip_ratio/high_max": 0.003179820880177431,
      "clip_ratio/high_mean": 0.0013420386057987344,
      "clip_ratio/low_mean": 0.001668410384809249,
      "clip_ratio/low_min": 4.8959946070681326e-05,
      "clip_ratio/region_mean": 0.0030104489414952695,
      "epoch": 0.14195964510088724,
      "grad_norm": 0.11637075245380402,
      "learning_rate": 1e-06,
      "loss": 0.0047,
      "step": 1521
    },
    {
      "clip_ratio/high_max": 0.003015102287463378,
      "clip_ratio/high_mean": 0.0012895968175143935,
      "clip_ratio/low_mean": 0.0015557365622953512,
      "clip_ratio/low_min": 4.170837564743124e-05,
      "clip_ratio/region_mean": 0.00284533339436166,
      "epoch": 0.14205297820088783,
      "grad_norm": 0.11883708834648132,
      "learning_rate": 1e-06,
      "loss": -0.0202,
      "step": 1522
    },
    {
      "clip_ratio/high_max": 0.003301380325865466,
      "clip_ratio/high_mean": 0.0013964535792183597,
      "clip_ratio/low_mean": 0.0017771646889741533,
      "clip_ratio/low_min": 3.9759411265549716e-05,
      "clip_ratio/region_mean": 0.0031736182572785765,
      "epoch": 0.14214631130088842,
      "grad_norm": 0.10774669796228409,
      "learning_rate": 1e-06,
      "loss": 0.0109,
      "step": 1523
    },
    {
      "clip_ratio/high_max": 0.00297357883391669,
      "clip_ratio/high_mean": 0.001272311325010378,
      "clip_ratio/low_mean": 0.0017494951680419035,
      "clip_ratio/low_min": 0.00015773228733451106,
      "clip_ratio/region_mean": 0.0030218064566724934,
      "epoch": 0.142239644400889,
      "grad_norm": 0.13024604320526123,
      "learning_rate": 1e-06,
      "loss": 0.0398,
      "step": 1524
    },
    {
      "clip_ratio/high_max": 0.0027003982759197243,
      "clip_ratio/high_mean": 0.0012124937584303552,
      "clip_ratio/low_mean": 0.0016560470467084087,
      "clip_ratio/low_min": 0.00012293097734072944,
      "clip_ratio/region_mean": 0.002868540868803393,
      "epoch": 0.14233297750088958,
      "grad_norm": 0.1243739202618599,
      "learning_rate": 1e-06,
      "loss": 0.0241,
      "step": 1525
    },
    {
      "clip_ratio/high_max": 0.003458211387624033,
      "clip_ratio/high_mean": 0.0013308976413100027,
      "clip_ratio/low_mean": 0.001378816396027105,
      "clip_ratio/low_min": 6.29810829195776e-05,
      "clip_ratio/region_mean": 0.0027097140919067897,
      "epoch": 0.14242631060089017,
      "grad_norm": 0.11025545746088028,
      "learning_rate": 1e-06,
      "loss": -0.0214,
      "step": 1526
    },
    {
      "clip_ratio/high_max": 0.0028820481966249645,
      "clip_ratio/high_mean": 0.0013134671607986093,
      "clip_ratio/low_mean": 0.0015541753709840123,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0028676425718003884,
      "epoch": 0.14251964370089074,
      "grad_norm": 0.12545356154441833,
      "learning_rate": 1e-06,
      "loss": 0.0145,
      "step": 1527
    },
    {
      "clip_ratio/high_max": 0.003086242730205413,
      "clip_ratio/high_mean": 0.0013463255054375622,
      "clip_ratio/low_mean": 0.0014875338129058946,
      "clip_ratio/low_min": 6.748548912582919e-05,
      "clip_ratio/region_mean": 0.0028338592528598383,
      "epoch": 0.14261297680089133,
      "grad_norm": 0.11443391442298889,
      "learning_rate": 1e-06,
      "loss": 0.0096,
      "step": 1528
    },
    {
      "clip_ratio/high_max": 0.0029393138611339964,
      "clip_ratio/high_mean": 0.0013462018177961,
      "clip_ratio/low_mean": 0.0016546018741792068,
      "clip_ratio/low_min": 3.793287578446325e-05,
      "clip_ratio/region_mean": 0.0030008036774233915,
      "epoch": 0.14270630990089192,
      "grad_norm": 0.10528197884559631,
      "learning_rate": 1e-06,
      "loss": 0.0022,
      "step": 1529
    },
    {
      "clip_ratio/high_max": 0.0029078684747219086,
      "clip_ratio/high_mean": 0.0013432889463729225,
      "clip_ratio/low_mean": 0.001652319660934154,
      "clip_ratio/low_min": 7.108331192284822e-05,
      "clip_ratio/region_mean": 0.002995608600031119,
      "epoch": 0.14279964300089248,
      "grad_norm": 0.11933331936597824,
      "learning_rate": 1e-06,
      "loss": 0.0293,
      "step": 1530
    },
    {
      "clip_ratio/high_max": 0.0028402969110175036,
      "clip_ratio/high_mean": 0.0011570206261239946,
      "clip_ratio/low_mean": 0.0016705019297660328,
      "clip_ratio/low_min": 7.741398167127045e-05,
      "clip_ratio/region_mean": 0.0028275225777179003,
      "epoch": 0.14289297610089308,
      "grad_norm": 0.11140989512205124,
      "learning_rate": 1e-06,
      "loss": 0.0589,
      "step": 1531
    },
    {
      "clip_ratio/high_max": 0.002941440950962715,
      "clip_ratio/high_mean": 0.001299613471928751,
      "clip_ratio/low_mean": 0.0015287725800590124,
      "clip_ratio/low_min": 0.00011934255780943204,
      "clip_ratio/region_mean": 0.002828386081091594,
      "epoch": 0.14298630920089367,
      "grad_norm": 0.11770542711019516,
      "learning_rate": 1e-06,
      "loss": 0.0069,
      "step": 1532
    },
    {
      "clip_ratio/high_max": 0.0032856551406439394,
      "clip_ratio/high_mean": 0.001400948309310479,
      "clip_ratio/low_mean": 0.001484631298808381,
      "clip_ratio/low_min": 7.879864460846875e-05,
      "clip_ratio/region_mean": 0.0028855796408606693,
      "epoch": 0.14307964230089426,
      "grad_norm": 0.12146227061748505,
      "learning_rate": 1e-06,
      "loss": -0.0236,
      "step": 1533
    },
    {
      "clip_ratio/high_max": 0.003145114409562666,
      "clip_ratio/high_mean": 0.0012771767396770883,
      "clip_ratio/low_mean": 0.0015248369018081576,
      "clip_ratio/low_min": 0.00014017606190463994,
      "clip_ratio/region_mean": 0.0028020136669510975,
      "epoch": 0.14317297540089483,
      "grad_norm": 0.11149397492408752,
      "learning_rate": 1e-06,
      "loss": 0.0174,
      "step": 1534
    },
    {
      "clip_ratio/high_max": 0.003133705395157449,
      "clip_ratio/high_mean": 0.0012910643526993226,
      "clip_ratio/low_mean": 0.0016779629986558575,
      "clip_ratio/low_min": 0.00010987078348989598,
      "clip_ratio/region_mean": 0.0029690272931475192,
      "epoch": 0.14326630850089542,
      "grad_norm": 0.11300347000360489,
      "learning_rate": 1e-06,
      "loss": 0.0376,
      "step": 1535
    },
    {
      "clip_ratio/high_max": 0.0029510759777622297,
      "clip_ratio/high_mean": 0.0013167555298423395,
      "clip_ratio/low_mean": 0.0017440295559936203,
      "clip_ratio/low_min": 0.0001590667961863801,
      "clip_ratio/region_mean": 0.003060785136767663,
      "epoch": 0.143359641600896,
      "grad_norm": 0.10898974537849426,
      "learning_rate": 1e-06,
      "loss": 0.0481,
      "step": 1536
    },
    {
      "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": 0.008161272321428603,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4087.0,
      "completions/mean_length": 599.0726928710938,
      "completions/mean_terminated_length": 570.2984619140625,
      "completions/min_length": 5.0,
      "completions/min_terminated_length": 5.0,
      "epoch": 0.14345297470089657,
      "grad_norm": 0.1331760734319687,
      "learning_rate": 1e-06,
      "loss": 0.0075,
      "num_tokens": 1051773960.0,
      "reward": 0.6359427571296692,
      "reward_std": 0.16864867508411407,
      "rewards/simpleverify_reward/mean": 0.6359427571296692,
      "rewards/simpleverify_reward/std": 0.48116692900657654,
      "step": 1537
    },
    {
      "clip_ratio/high_max": 0.002019051789829973,
      "clip_ratio/high_mean": 0.0008634778732812265,
      "clip_ratio/low_mean": 0.0005345854478946421,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001398063341184752,
      "epoch": 0.14354630780089717,
      "grad_norm": 0.1310259848833084,
      "learning_rate": 1e-06,
      "loss": 0.0097,
      "step": 1538
    },
    {
      "clip_ratio/high_max": 0.002067156157863792,
      "clip_ratio/high_mean": 0.0008867731594364159,
      "clip_ratio/low_mean": 0.0004512238047027495,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001337996931397356,
      "epoch": 0.14363964090089776,
      "grad_norm": 0.11647213995456696,
      "learning_rate": 1e-06,
      "loss": 0.0193,
      "step": 1539
    },
    {
      "clip_ratio/high_max": 0.0020017999086121563,
      "clip_ratio/high_mean": 0.0007746222036075778,
      "clip_ratio/low_mean": 0.0005899308016523719,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013645530125359073,
      "epoch": 0.14373297400089832,
      "grad_norm": 0.12436878681182861,
      "learning_rate": 1e-06,
      "loss": 0.0296,
      "step": 1540
    },
    {
      "clip_ratio/high_max": 0.0017152495729533257,
      "clip_ratio/high_mean": 0.0007533674361184239,
      "clip_ratio/low_mean": 0.0006592626541532809,
      "clip_ratio/low_min": 9.738719927554484e-05,
      "clip_ratio/region_mean": 0.0014126301211945247,
      "epoch": 0.14382630710089891,
      "grad_norm": 0.11987806856632233,
      "learning_rate": 1e-06,
      "loss": -0.0035,
      "step": 1541
    },
    {
      "clip_ratio/high_max": 0.002251584461191669,
      "clip_ratio/high_mean": 0.0008071958509390242,
      "clip_ratio/low_mean": 0.000674265605994151,
      "clip_ratio/low_min": 2.117567419190891e-05,
      "clip_ratio/region_mean": 0.0014814614187343977,
      "epoch": 0.1439196402008995,
      "grad_norm": 0.11759467422962189,
      "learning_rate": 1e-06,
      "loss": 0.0596,
      "step": 1542
    },
    {
      "clip_ratio/high_max": 0.0019849513773806393,
      "clip_ratio/high_mean": 0.000808235445219907,
      "clip_ratio/low_mean": 0.0006418463817681186,
      "clip_ratio/low_min": 4.139504562772345e-05,
      "clip_ratio/region_mean": 0.0014500818433589302,
      "epoch": 0.14401297330090007,
      "grad_norm": 0.11865795403718948,
      "learning_rate": 1e-06,
      "loss": 0.0076,
      "step": 1543
    },
    {
      "clip_ratio/high_max": 0.001998230756726116,
      "clip_ratio/high_mean": 0.0008913590736483457,
      "clip_ratio/low_mean": 0.0007811305358700338,
      "clip_ratio/low_min": 4.272562546248082e-05,
      "clip_ratio/region_mean": 0.0016724896267987788,
      "epoch": 0.14410630640090066,
      "grad_norm": 0.11927706003189087,
      "learning_rate": 1e-06,
      "loss": 0.0324,
      "step": 1544
    },
    {
      "clip_ratio/high_max": 0.001980333574465476,
      "clip_ratio/high_mean": 0.000781944812842994,
      "clip_ratio/low_mean": 0.0008639046627649805,
      "clip_ratio/low_min": 3.221677434339654e-05,
      "clip_ratio/region_mean": 0.0016458494719699956,
      "epoch": 0.14419963950090126,
      "grad_norm": 0.13412626087665558,
      "learning_rate": 1e-06,
      "loss": 0.0556,
      "step": 1545
    },
    {
      "clip_ratio/high_max": 0.0020835180912399665,
      "clip_ratio/high_mean": 0.0009011451438709628,
      "clip_ratio/low_mean": 0.0007664835884497734,
      "clip_ratio/low_min": 0.00010425875916553196,
      "clip_ratio/region_mean": 0.0016676287486916408,
      "epoch": 0.14429297260090182,
      "grad_norm": 0.12752968072891235,
      "learning_rate": 1e-06,
      "loss": 0.0426,
      "step": 1546
    },
    {
      "clip_ratio/high_max": 0.001979969398234971,
      "clip_ratio/high_mean": 0.0009074920399143593,
      "clip_ratio/low_mean": 0.000613282230006007,
      "clip_ratio/low_min": 1.2810001862817444e-05,
      "clip_ratio/region_mean": 0.0015207742399070412,
      "epoch": 0.1443863057009024,
      "grad_norm": 0.10908825695514679,
      "learning_rate": 1e-06,
      "loss": -0.019,
      "step": 1547
    },
    {
      "clip_ratio/high_max": 0.0022655078428215347,
      "clip_ratio/high_mean": 0.0008852544497131021,
      "clip_ratio/low_mean": 0.0008539426307834219,
      "clip_ratio/low_min": 2.2973717932472937e-05,
      "clip_ratio/region_mean": 0.0017391971305187326,
      "epoch": 0.144479638800903,
      "grad_norm": 0.12035182118415833,
      "learning_rate": 1e-06,
      "loss": 0.0247,
      "step": 1548
    },
    {
      "clip_ratio/high_max": 0.002204020962381037,
      "clip_ratio/high_mean": 0.0008539673654013313,
      "clip_ratio/low_mean": 0.0007013692666077986,
      "clip_ratio/low_min": 1.7346656022709794e-05,
      "clip_ratio/region_mean": 0.0015553366356471088,
      "epoch": 0.14457297190090357,
      "grad_norm": 0.11636511981487274,
      "learning_rate": 1e-06,
      "loss": 0.003,
      "step": 1549
    },
    {
      "clip_ratio/high_max": 0.0024815234864945523,
      "clip_ratio/high_mean": 0.0009739296692714561,
      "clip_ratio/low_mean": 0.0008585067253079615,
      "clip_ratio/low_min": 3.0005554435774684e-05,
      "clip_ratio/region_mean": 0.0018324364355066791,
      "epoch": 0.14466630500090416,
      "grad_norm": 1.255921721458435,
      "learning_rate": 1e-06,
      "loss": 0.0294,
      "step": 1550
    },
    {
      "clip_ratio/high_max": 0.0020831542933592573,
      "clip_ratio/high_mean": 0.0008278592958959052,
      "clip_ratio/low_mean": 0.0009873319413600257,
      "clip_ratio/low_min": 7.304474638658576e-05,
      "clip_ratio/region_mean": 0.001815191215428058,
      "epoch": 0.14475963810090475,
      "grad_norm": 0.1153787150979042,
      "learning_rate": 1e-06,
      "loss": 0.0611,
      "step": 1551
    },
    {
      "clip_ratio/high_max": 0.0023547829696326517,
      "clip_ratio/high_mean": 0.0009259260932594771,
      "clip_ratio/low_mean": 0.0009883973871183116,
      "clip_ratio/low_min": 3.264272345404606e-05,
      "clip_ratio/region_mean": 0.0019143234312650748,
      "epoch": 0.14485297120090532,
      "grad_norm": 0.11677554994821548,
      "learning_rate": 1e-06,
      "loss": 0.0272,
      "step": 1552
    },
    {
      "clip_ratio/high_max": 0.0025879938693833537,
      "clip_ratio/high_mean": 0.0010390332026872784,
      "clip_ratio/low_mean": 0.0009386335623275954,
      "clip_ratio/low_min": 5.804289139632601e-05,
      "clip_ratio/region_mean": 0.0019776667177211493,
      "epoch": 0.1449463043009059,
      "grad_norm": 0.11043479293584824,
      "learning_rate": 1e-06,
      "loss": -0.0186,
      "step": 1553
    },
    {
      "clip_ratio/high_max": 0.0024974236876005307,
      "clip_ratio/high_mean": 0.001022075357468566,
      "clip_ratio/low_mean": 0.0009316568211943377,
      "clip_ratio/low_min": 1.9118997443001717e-05,
      "clip_ratio/region_mean": 0.001953732149559073,
      "epoch": 0.1450396374009065,
      "grad_norm": 0.11594738811254501,
      "learning_rate": 1e-06,
      "loss": 0.0062,
      "step": 1554
    },
    {
      "clip_ratio/high_max": 0.00220486092439387,
      "clip_ratio/high_mean": 0.0009031249464896973,
      "clip_ratio/low_mean": 0.000964019394814386,
      "clip_ratio/low_min": 5.779587445431389e-05,
      "clip_ratio/region_mean": 0.0018671443249331787,
      "epoch": 0.1451329705009071,
      "grad_norm": 0.10877743363380432,
      "learning_rate": 1e-06,
      "loss": 0.0089,
      "step": 1555
    },
    {
      "clip_ratio/high_max": 0.0022923965079826303,
      "clip_ratio/high_mean": 0.0009772972498467425,
      "clip_ratio/low_mean": 0.0011835394798254129,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0021608367533190176,
      "epoch": 0.14522630360090766,
      "grad_norm": 0.12109901756048203,
      "learning_rate": 1e-06,
      "loss": 0.0377,
      "step": 1556
    },
    {
      "clip_ratio/high_max": 0.0022736464816262014,
      "clip_ratio/high_mean": 0.0009526156591164181,
      "clip_ratio/low_mean": 0.0010804358644236345,
      "clip_ratio/low_min": 0.00014354121685755672,
      "clip_ratio/region_mean": 0.002033051503531169,
      "epoch": 0.14531963670090825,
      "grad_norm": 0.1205814853310585,
      "learning_rate": 1e-06,
      "loss": 0.0353,
      "step": 1557
    },
    {
      "clip_ratio/high_max": 0.00256652897951426,
      "clip_ratio/high_mean": 0.0011049522545363288,
      "clip_ratio/low_mean": 0.000883828453879687,
      "clip_ratio/low_min": 6.348605529638007e-05,
      "clip_ratio/region_mean": 0.0019887807648046874,
      "epoch": 0.14541296980090884,
      "grad_norm": 0.11574000865221024,
      "learning_rate": 1e-06,
      "loss": -0.0104,
      "step": 1558
    },
    {
      "clip_ratio/high_max": 0.0021898317645536736,
      "clip_ratio/high_mean": 0.0008501024622091791,
      "clip_ratio/low_mean": 0.001046256918925792,
      "clip_ratio/low_min": 3.1107282666198444e-05,
      "clip_ratio/region_mean": 0.0018963593611260876,
      "epoch": 0.1455063029009094,
      "grad_norm": 0.11880280822515488,
      "learning_rate": 1e-06,
      "loss": 0.0554,
      "step": 1559
    },
    {
      "clip_ratio/high_max": 0.0027522937962203287,
      "clip_ratio/high_mean": 0.0010890533012570813,
      "clip_ratio/low_mean": 0.0009512917822576128,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002040345105342567,
      "epoch": 0.14559963600091,
      "grad_norm": 0.10995512455701828,
      "learning_rate": 1e-06,
      "loss": -0.0025,
      "step": 1560
    },
    {
      "clip_ratio/high_max": 0.00233405118342489,
      "clip_ratio/high_mean": 0.0010532149444770766,
      "clip_ratio/low_mean": 0.001044001128320815,
      "clip_ratio/low_min": 8.496898772136774e-05,
      "clip_ratio/region_mean": 0.002097216041875072,
      "epoch": 0.1456929691009106,
      "grad_norm": 0.11573732644319534,
      "learning_rate": 1e-06,
      "loss": 0.0233,
      "step": 1561
    },
    {
      "clip_ratio/high_max": 0.002588451803603675,
      "clip_ratio/high_mean": 0.0010720247009885497,
      "clip_ratio/low_mean": 0.0007863260125304805,
      "clip_ratio/low_min": 3.9687422940914985e-05,
      "clip_ratio/region_mean": 0.0018583506607683375,
      "epoch": 0.14578630220091116,
      "grad_norm": 0.1103486642241478,
      "learning_rate": 1e-06,
      "loss": -0.0265,
      "step": 1562
    },
    {
      "clip_ratio/high_max": 0.0026435923427925445,
      "clip_ratio/high_mean": 0.0010283235696988413,
      "clip_ratio/low_mean": 0.0010669130824680906,
      "clip_ratio/low_min": 5.3719360948889516e-05,
      "clip_ratio/region_mean": 0.0020952366321580485,
      "epoch": 0.14587963530091175,
      "grad_norm": 0.10596740990877151,
      "learning_rate": 1e-06,
      "loss": 0.005,
      "step": 1563
    },
    {
      "clip_ratio/high_max": 0.0024243352381745353,
      "clip_ratio/high_mean": 0.0010283890787832206,
      "clip_ratio/low_mean": 0.0011610231995291542,
      "clip_ratio/low_min": 3.0162674192979466e-05,
      "clip_ratio/region_mean": 0.0021894123128731735,
      "epoch": 0.14597296840091234,
      "grad_norm": 0.1223297044634819,
      "learning_rate": 1e-06,
      "loss": 0.0313,
      "step": 1564
    },
    {
      "clip_ratio/high_max": 0.00273451762041077,
      "clip_ratio/high_mean": 0.0011236479658691678,
      "clip_ratio/low_mean": 0.001045834957039915,
      "clip_ratio/low_min": 3.8516938730026595e-05,
      "clip_ratio/region_mean": 0.0021694829265470617,
      "epoch": 0.1460663015009129,
      "grad_norm": 0.12946964800357819,
      "learning_rate": 1e-06,
      "loss": 0.0215,
      "step": 1565
    },
    {
      "clip_ratio/high_max": 0.0027597406842687633,
      "clip_ratio/high_mean": 0.0010764291237137513,
      "clip_ratio/low_mean": 0.001110309938667342,
      "clip_ratio/low_min": 0.00017597440455574542,
      "clip_ratio/region_mean": 0.002186739075114019,
      "epoch": 0.1461596346009135,
      "grad_norm": 0.11915992945432663,
      "learning_rate": 1e-06,
      "loss": 0.029,
      "step": 1566
    },
    {
      "clip_ratio/high_max": 0.0024903367775550578,
      "clip_ratio/high_mean": 0.0010254174158035312,
      "clip_ratio/low_mean": 0.0011325118230161024,
      "clip_ratio/low_min": 0.00012716423225356266,
      "clip_ratio/region_mean": 0.0021579292151727714,
      "epoch": 0.1462529677009141,
      "grad_norm": 0.1284736692905426,
      "learning_rate": 1e-06,
      "loss": 0.0367,
      "step": 1567
    },
    {
      "clip_ratio/high_max": 0.00270240713871317,
      "clip_ratio/high_mean": 0.0011996364228252787,
      "clip_ratio/low_mean": 0.0011255001809331588,
      "clip_ratio/low_min": 1.429551684850594e-05,
      "clip_ratio/region_mean": 0.0023251365855685435,
      "epoch": 0.14634630080091465,
      "grad_norm": 1.073857307434082,
      "learning_rate": 1e-06,
      "loss": 0.014,
      "step": 1568
    },
    {
      "clip_ratio/high_max": 0.0028473604943428654,
      "clip_ratio/high_mean": 0.0010889980458159698,
      "clip_ratio/low_mean": 0.00119545605048188,
      "clip_ratio/low_min": 2.9063590773148462e-05,
      "clip_ratio/region_mean": 0.0022844540944788605,
      "epoch": 0.14643963390091524,
      "grad_norm": 0.13501380383968353,
      "learning_rate": 1e-06,
      "loss": 0.0297,
      "step": 1569
    },
    {
      "clip_ratio/high_max": 0.0028598517674254254,
      "clip_ratio/high_mean": 0.0010944512741843937,
      "clip_ratio/low_mean": 0.0011131579412904102,
      "clip_ratio/low_min": 6.923250839463435e-05,
      "clip_ratio/region_mean": 0.0022076092354836874,
      "epoch": 0.14653296700091584,
      "grad_norm": 0.12409362196922302,
      "learning_rate": 1e-06,
      "loss": 0.0017,
      "step": 1570
    },
    {
      "clip_ratio/high_max": 0.0026152804057346657,
      "clip_ratio/high_mean": 0.0009437288281333167,
      "clip_ratio/low_mean": 0.001275744660233613,
      "clip_ratio/low_min": 2.681252772163134e-05,
      "clip_ratio/region_mean": 0.0022194734192453325,
      "epoch": 0.1466263001009164,
      "grad_norm": 0.12028136849403381,
      "learning_rate": 1e-06,
      "loss": 0.0456,
      "step": 1571
    },
    {
      "clip_ratio/high_max": 0.002573876212409232,
      "clip_ratio/high_mean": 0.0010177784697589232,
      "clip_ratio/low_mean": 0.0013646343140862882,
      "clip_ratio/low_min": 8.376202458748594e-05,
      "clip_ratio/region_mean": 0.002382412800216116,
      "epoch": 0.146719633200917,
      "grad_norm": 0.10730920732021332,
      "learning_rate": 1e-06,
      "loss": 0.0449,
      "step": 1572
    },
    {
      "clip_ratio/high_max": 0.00261613750262768,
      "clip_ratio/high_mean": 0.0009601320034562377,
      "clip_ratio/low_mean": 0.0012613291401066817,
      "clip_ratio/low_min": 0.0001273709367524134,
      "clip_ratio/region_mean": 0.0022214612326934002,
      "epoch": 0.14681296630091759,
      "grad_norm": 0.17470651865005493,
      "learning_rate": 1e-06,
      "loss": 0.0471,
      "step": 1573
    },
    {
      "clip_ratio/high_max": 0.002623839107400272,
      "clip_ratio/high_mean": 0.001100221215892816,
      "clip_ratio/low_mean": 0.0012966400936420541,
      "clip_ratio/low_min": 3.383255170774646e-05,
      "clip_ratio/region_mean": 0.002396861273155082,
      "epoch": 0.14690629940091818,
      "grad_norm": 0.19125966727733612,
      "learning_rate": 1e-06,
      "loss": 0.0391,
      "step": 1574
    },
    {
      "clip_ratio/high_max": 0.002946718923340086,
      "clip_ratio/high_mean": 0.001231655018273159,
      "clip_ratio/low_mean": 0.0010425556283735204,
      "clip_ratio/low_min": 5.0680047934292816e-05,
      "clip_ratio/region_mean": 0.0022742106884834357,
      "epoch": 0.14699963250091874,
      "grad_norm": 0.10879350453615189,
      "learning_rate": 1e-06,
      "loss": -0.0079,
      "step": 1575
    },
    {
      "clip_ratio/high_max": 0.002816996639012359,
      "clip_ratio/high_mean": 0.001196005232486641,
      "clip_ratio/low_mean": 0.001053724448865978,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.002249729681352619,
      "epoch": 0.14709296560091933,
      "grad_norm": 0.11205597221851349,
      "learning_rate": 1e-06,
      "loss": 0.0073,
      "step": 1576
    },
    {
      "clip_ratio/high_max": 0.002803973609843524,
      "clip_ratio/high_mean": 0.0010040341312560486,
      "clip_ratio/low_mean": 0.001451206517231185,
      "clip_ratio/low_min": 0.00021219081463641487,
      "clip_ratio/region_mean": 0.002455240646668244,
      "epoch": 0.14718629870091993,
      "grad_norm": 2.6633191108703613,
      "learning_rate": 1e-06,
      "loss": 0.0441,
      "step": 1577
    },
    {
      "clip_ratio/high_max": 0.002892303360567894,
      "clip_ratio/high_mean": 0.001038779544614954,
      "clip_ratio/low_mean": 0.0014200555888237432,
      "clip_ratio/low_min": 9.173279977403581e-05,
      "clip_ratio/region_mean": 0.002458835078869015,
      "epoch": 0.1472796318009205,
      "grad_norm": 0.12540794909000397,
      "learning_rate": 1e-06,
      "loss": 0.0469,
      "step": 1578
    },
    {
      "clip_ratio/high_max": 0.002852613200957421,
      "clip_ratio/high_mean": 0.0012918764005007688,
      "clip_ratio/low_mean": 0.0014276863330451306,
      "clip_ratio/low_min": 6.04595315962797e-05,
      "clip_ratio/region_mean": 0.0027195628063054755,
      "epoch": 0.14737296490092108,
      "grad_norm": 0.12613168358802795,
      "learning_rate": 1e-06,
      "loss": 0.011,
      "step": 1579
    },
    {
      "clip_ratio/high_max": 0.0028884717175969854,
      "clip_ratio/high_mean": 0.001152550190454349,
      "clip_ratio/low_mean": 0.0013026039814576507,
      "clip_ratio/low_min": 8.54961144796107e-05,
      "clip_ratio/region_mean": 0.0024551541719119996,
      "epoch": 0.14746629800092168,
      "grad_norm": 0.12145470827817917,
      "learning_rate": 1e-06,
      "loss": 0.0317,
      "step": 1580
    },
    {
      "clip_ratio/high_max": 0.0025187965293298475,
      "clip_ratio/high_mean": 0.001133369209128432,
      "clip_ratio/low_mean": 0.0013474826300807763,
      "clip_ratio/low_min": 2.9797378374496475e-05,
      "clip_ratio/region_mean": 0.0024808517991914414,
      "epoch": 0.14755963110092224,
      "grad_norm": 0.11006373167037964,
      "learning_rate": 1e-06,
      "loss": 0.0404,
      "step": 1581
    },
    {
      "clip_ratio/high_max": 0.0030235302328947,
      "clip_ratio/high_mean": 0.001170645406091353,
      "clip_ratio/low_mean": 0.0011911879755643895,
      "clip_ratio/low_min": 2.788933488773182e-05,
      "clip_ratio/region_mean": 0.0023618333871127106,
      "epoch": 0.14765296420092283,
      "grad_norm": 0.11489474028348923,
      "learning_rate": 1e-06,
      "loss": 0.0102,
      "step": 1582
    },
    {
      "clip_ratio/high_max": 0.002835865416273009,
      "clip_ratio/high_mean": 0.0011893027640326181,
      "clip_ratio/low_mean": 0.0014563824988726992,
      "clip_ratio/low_min": 8.87622209120309e-05,
      "clip_ratio/region_mean": 0.0026456852647243068,
      "epoch": 0.14774629730092342,
      "grad_norm": 0.12050473690032959,
      "learning_rate": 1e-06,
      "loss": 0.0667,
      "step": 1583
    },
    {
      "clip_ratio/high_max": 0.0025018454616656527,
      "clip_ratio/high_mean": 0.0011468420671008062,
      "clip_ratio/low_mean": 0.0014014012704137713,
      "clip_ratio/low_min": 4.745633850689046e-05,
      "clip_ratio/region_mean": 0.0025482433702563867,
      "epoch": 0.147839630400924,
      "grad_norm": 0.20857176184654236,
      "learning_rate": 1e-06,
      "loss": 0.033,
      "step": 1584
    },
    {
      "clip_ratio/high_max": 0.0030475231833406724,
      "clip_ratio/high_mean": 0.00126223027746164,
      "clip_ratio/low_mean": 0.0015846530368435197,
      "clip_ratio/low_min": 4.858142347075045e-05,
      "clip_ratio/region_mean": 0.0028468833334045485,
      "epoch": 0.14793296350092458,
      "grad_norm": 0.11923615634441376,
      "learning_rate": 1e-06,
      "loss": 0.0344,
      "step": 1585
    },
    {
      "clip_ratio/high_max": 0.002954526797111612,
      "clip_ratio/high_mean": 0.0013487739634001628,
      "clip_ratio/low_mean": 0.0013275169076223392,
      "clip_ratio/low_min": 1.7720441974233836e-05,
      "clip_ratio/region_mean": 0.0026762908601085655,
      "epoch": 0.14802629660092517,
      "grad_norm": 0.12191282957792282,
      "learning_rate": 1e-06,
      "loss": -0.0257,
      "step": 1586
    },
    {
      "clip_ratio/high_max": 0.0030190691468305886,
      "clip_ratio/high_mean": 0.0012583687785081565,
      "clip_ratio/low_mean": 0.0014010791674081702,
      "clip_ratio/low_min": 0.00010601799476717133,
      "clip_ratio/region_mean": 0.002659447920450475,
      "epoch": 0.14811962970092574,
      "grad_norm": 0.1292433738708496,
      "learning_rate": 1e-06,
      "loss": 0.0325,
      "step": 1587
    },
    {
      "clip_ratio/high_max": 0.0030810479365754873,
      "clip_ratio/high_mean": 0.0013153013860573992,
      "clip_ratio/low_mean": 0.0013788374053547159,
      "clip_ratio/low_min": 7.098281093931291e-05,
      "clip_ratio/region_mean": 0.0026941387695842423,
      "epoch": 0.14821296280092633,
      "grad_norm": 0.260358601808548,
      "learning_rate": 1e-06,
      "loss": -0.0008,
      "step": 1588
    },
    {
      "clip_ratio/high_max": 0.0031403375978698023,
      "clip_ratio/high_mean": 0.0012714104523183778,
      "clip_ratio/low_mean": 0.0013542760352720506,
      "clip_ratio/low_min": 0.00017211161502928007,
      "clip_ratio/region_mean": 0.0026256864075548947,
      "epoch": 0.14830629590092692,
      "grad_norm": 0.14988058805465698,
      "learning_rate": 1e-06,
      "loss": 0.0254,
      "step": 1589
    },
    {
      "clip_ratio/high_max": 0.0026779743857332505,
      "clip_ratio/high_mean": 0.0010788335021061357,
      "clip_ratio/low_mean": 0.0014734040614712285,
      "clip_ratio/low_min": 0.00010233341527055018,
      "clip_ratio/region_mean": 0.0025522375872242264,
      "epoch": 0.14839962900092749,
      "grad_norm": 0.19826769828796387,
      "learning_rate": 1e-06,
      "loss": 0.0431,
      "step": 1590
    },
    {
      "clip_ratio/high_max": 0.002470103612722596,
      "clip_ratio/high_mean": 0.0010616986564855324,
      "clip_ratio/low_mean": 0.0014063022936170455,
      "clip_ratio/low_min": 0.00016725757814128883,
      "clip_ratio/region_mean": 0.0024680008937139064,
      "epoch": 0.14849296210092808,
      "grad_norm": 0.10588473081588745,
      "learning_rate": 1e-06,
      "loss": 0.0298,
      "step": 1591
    },
    {
      "clip_ratio/high_max": 0.0029494402988348156,
      "clip_ratio/high_mean": 0.0011926215374842286,
      "clip_ratio/low_mean": 0.0016863905257196166,
      "clip_ratio/low_min": 0.00017769355599739356,
      "clip_ratio/region_mean": 0.0028790119977202266,
      "epoch": 0.14858629520092867,
      "grad_norm": 0.11281023174524307,
      "learning_rate": 1e-06,
      "loss": 0.044,
      "step": 1592
    },
    {
      "clip_ratio/high_max": 0.003037026028323453,
      "clip_ratio/high_mean": 0.001229690187756205,
      "clip_ratio/low_mean": 0.0015455428110726643,
      "clip_ratio/low_min": 6.604961163247935e-05,
      "clip_ratio/region_mean": 0.0027752329770009965,
      "epoch": 0.14867962830092923,
      "grad_norm": 0.11929027736186981,
      "learning_rate": 1e-06,
      "loss": 0.0411,
      "step": 1593
    },
    {
      "clip_ratio/high_max": 0.0026094395070686005,
      "clip_ratio/high_mean": 0.001062958699549199,
      "clip_ratio/low_mean": 0.001433082183211809,
      "clip_ratio/low_min": 0.00010813827611855231,
      "clip_ratio/region_mean": 0.0024960408845799975,
      "epoch": 0.14877296140092983,
      "grad_norm": 0.1162814125418663,
      "learning_rate": 1e-06,
      "loss": 0.0292,
      "step": 1594
    },
    {
      "clip_ratio/high_max": 0.0026943126213154756,
      "clip_ratio/high_mean": 0.0011308098873996641,
      "clip_ratio/low_mean": 0.0013149891819921322,
      "clip_ratio/low_min": 0.00010756266055977903,
      "clip_ratio/region_mean": 0.0024457990512019023,
      "epoch": 0.14886629450093042,
      "grad_norm": 0.11057198792695999,
      "learning_rate": 1e-06,
      "loss": -0.0308,
      "step": 1595
    },
    {
      "clip_ratio/high_max": 0.003469643968855962,
      "clip_ratio/high_mean": 0.00149761811553617,
      "clip_ratio/low_mean": 0.0012887150323876995,
      "clip_ratio/low_min": 0.00010086231759487418,
      "clip_ratio/region_mean": 0.0027863332361448556,
      "epoch": 0.148959627600931,
      "grad_norm": 0.116305872797966,
      "learning_rate": 1e-06,
      "loss": -0.0246,
      "step": 1596
    },
    {
      "clip_ratio/high_max": 0.003023018791282084,
      "clip_ratio/high_mean": 0.0011794157508120406,
      "clip_ratio/low_mean": 0.0016139480576384813,
      "clip_ratio/low_min": 6.956141623959411e-05,
      "clip_ratio/region_mean": 0.0027933637175010517,
      "epoch": 0.14905296070093157,
      "grad_norm": 0.12252958863973618,
      "learning_rate": 1e-06,
      "loss": 0.0765,
      "step": 1597
    },
    {
      "clip_ratio/high_max": 0.0026197668703389354,
      "clip_ratio/high_mean": 0.001151306332758395,
      "clip_ratio/low_mean": 0.0015905627988104243,
      "clip_ratio/low_min": 0.00012925142164021963,
      "clip_ratio/region_mean": 0.0027418691679486074,
      "epoch": 0.14914629380093217,
      "grad_norm": 0.14624157547950745,
      "learning_rate": 1e-06,
      "loss": 0.0328,
      "step": 1598
    },
    {
      "clip_ratio/high_max": 0.0031123743756324984,
      "clip_ratio/high_mean": 0.0012926149393024389,
      "clip_ratio/low_mean": 0.0014306021694210358,
      "clip_ratio/low_min": 0.0001934835672727786,
      "clip_ratio/region_mean": 0.002723217046877835,
      "epoch": 0.14923962690093276,
      "grad_norm": 0.1320226639509201,
      "learning_rate": 1e-06,
      "loss": 0.016,
      "step": 1599
    },
    {
      "clip_ratio/high_max": 0.0031263567216228694,
      "clip_ratio/high_mean": 0.0013776494306512177,
      "clip_ratio/low_mean": 0.0014489430614048615,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0028265925211599097,
      "epoch": 0.14933296000093332,
      "grad_norm": 0.12342894822359085,
      "learning_rate": 1e-06,
      "loss": 0.0017,
      "step": 1600
    },
    {
      "epoch": 0.14933296000093332,
      "step": 1600,
      "total_flos": 0.0,
      "train_loss": 0.004436979327128938,
      "train_runtime": 23038.4999,
      "train_samples_per_second": 62.226,
      "train_steps_per_second": 0.069
    }
  ],
  "logging_steps": 1,
  "max_steps": 1600,
  "num_input_tokens_seen": 1051773960,
  "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
}