{
  "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": 0.014107840401785698,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4091.0,
      "completions/mean_length": 603.2777709960938,
      "completions/mean_terminated_length": 553.2979125976562,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 9.333310000058333e-05,
      "grad_norm": 0.15226596593856812,
      "learning_rate": 2e-07,
      "loss": 0.0169,
      "num_tokens": 80610803.0,
      "reward": 0.4960327446460724,
      "reward_std": 0.26209649443626404,
      "rewards/simpleverify_reward/mean": 0.49603271484375,
      "rewards/simpleverify_reward/std": 0.4999862313270569,
      "step": 1
    },
    {
      "clip_ratio/high_max": 0.0026855107498704456,
      "clip_ratio/high_mean": 0.0011256248108111322,
      "clip_ratio/low_mean": 0.0006116732183727436,
      "clip_ratio/low_min": 7.207221642602235e-05,
      "clip_ratio/region_mean": 0.001737298061925685,
      "epoch": 0.00018666620000116666,
      "grad_norm": 0.1652979701757431,
      "learning_rate": 2e-07,
      "loss": -0.0121,
      "step": 2
    },
    {
      "clip_ratio/high_max": 0.0025302996291429736,
      "clip_ratio/high_mean": 0.0010502484692551661,
      "clip_ratio/low_mean": 0.0006030750610079849,
      "clip_ratio/low_min": 7.160595032473793e-05,
      "clip_ratio/region_mean": 0.0016533235175302252,
      "epoch": 0.00027999930000175,
      "grad_norm": 0.13763025403022766,
      "learning_rate": 2e-07,
      "loss": -0.0305,
      "step": 3
    },
    {
      "clip_ratio/high_max": 0.0024031228022067808,
      "clip_ratio/high_mean": 0.0009716729218780529,
      "clip_ratio/low_mean": 0.0007264342748385388,
      "clip_ratio/low_min": 6.412036327674286e-05,
      "clip_ratio/region_mean": 0.0016981071676127613,
      "epoch": 0.0003733324000023333,
      "grad_norm": 0.16416049003601074,
      "learning_rate": 2e-07,
      "loss": 0.0393,
      "step": 4
    },
    {
      "clip_ratio/high_max": 0.0023153340771386866,
      "clip_ratio/high_mean": 0.0010534081775404047,
      "clip_ratio/low_mean": 0.0006291228546615457,
      "clip_ratio/low_min": 0.00013712085547012975,
      "clip_ratio/region_mean": 0.0016825310085550882,
      "epoch": 0.0004666655000029167,
      "grad_norm": 0.15439161658287048,
      "learning_rate": 2e-07,
      "loss": -0.0196,
      "step": 5
    },
    {
      "clip_ratio/high_max": 0.002705680140934419,
      "clip_ratio/high_mean": 0.0010525900652282871,
      "clip_ratio/low_mean": 0.000656371860713989,
      "clip_ratio/low_min": 3.9551418922201265e-05,
      "clip_ratio/region_mean": 0.0017089618850150146,
      "epoch": 0.0005599986000035,
      "grad_norm": 0.1429436206817627,
      "learning_rate": 2e-07,
      "loss": 0.0147,
      "step": 6
    },
    {
      "clip_ratio/high_max": 0.00227601443475578,
      "clip_ratio/high_mean": 0.0010625544418871868,
      "clip_ratio/low_mean": 0.0006774849589419318,
      "clip_ratio/low_min": 8.50881888254662e-05,
      "clip_ratio/region_mean": 0.001740039384458214,
      "epoch": 0.0006533317000040833,
      "grad_norm": 0.14794810116291046,
      "learning_rate": 2e-07,
      "loss": 0.0189,
      "step": 7
    },
    {
      "clip_ratio/high_max": 0.002208251135016326,
      "clip_ratio/high_mean": 0.0010921508619503584,
      "clip_ratio/low_mean": 0.0006793623051635223,
      "clip_ratio/low_min": 5.477833929035114e-05,
      "clip_ratio/region_mean": 0.0017715131471049972,
      "epoch": 0.0007466648000046666,
      "grad_norm": 0.16203421354293823,
      "learning_rate": 2e-07,
      "loss": -0.0032,
      "step": 8
    },
    {
      "clip_ratio/high_max": 0.0027384060667827725,
      "clip_ratio/high_mean": 0.0011402233831177,
      "clip_ratio/low_mean": 0.0005811858845845563,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0017214092804351822,
      "epoch": 0.00083999790000525,
      "grad_norm": 0.13111692667007446,
      "learning_rate": 2e-07,
      "loss": -0.0567,
      "step": 9
    },
    {
      "clip_ratio/high_max": 0.0020794088050024584,
      "clip_ratio/high_mean": 0.0009608974251023028,
      "clip_ratio/low_mean": 0.0006140016066638054,
      "clip_ratio/low_min": 8.490507389069535e-05,
      "clip_ratio/region_mean": 0.001574899062688928,
      "epoch": 0.0009333310000058334,
      "grad_norm": 0.1865895688533783,
      "learning_rate": 2e-07,
      "loss": 0.0087,
      "step": 10
    },
    {
      "clip_ratio/high_max": 0.00221535810851492,
      "clip_ratio/high_mean": 0.0010552943858783692,
      "clip_ratio/low_mean": 0.0007242449482873781,
      "clip_ratio/low_min": 9.243800741387531e-05,
      "clip_ratio/region_mean": 0.0017795393578126095,
      "epoch": 0.0010266641000064166,
      "grad_norm": 0.14398416876792908,
      "learning_rate": 2e-07,
      "loss": 0.0471,
      "step": 11
    },
    {
      "clip_ratio/high_max": 0.002243391500087455,
      "clip_ratio/high_mean": 0.0010248201979266014,
      "clip_ratio/low_mean": 0.0007454685382981552,
      "clip_ratio/low_min": 0.00011981024090346182,
      "clip_ratio/region_mean": 0.0017702887053019367,
      "epoch": 0.001119997200007,
      "grad_norm": 0.14180755615234375,
      "learning_rate": 2e-07,
      "loss": 0.0314,
      "step": 12
    },
    {
      "clip_ratio/high_max": 0.002350613405724289,
      "clip_ratio/high_mean": 0.0009637280236347578,
      "clip_ratio/low_mean": 0.0005558926386584062,
      "clip_ratio/low_min": 5.653571406583069e-05,
      "clip_ratio/region_mean": 0.0015196206295513548,
      "epoch": 0.0012133303000075833,
      "grad_norm": 0.13647836446762085,
      "learning_rate": 2e-07,
      "loss": -0.0054,
      "step": 13
    },
    {
      "clip_ratio/high_max": 0.002185715718951542,
      "clip_ratio/high_mean": 0.0009792264754651114,
      "clip_ratio/low_mean": 0.000533153691321786,
      "clip_ratio/low_min": 7.11764050720376e-06,
      "clip_ratio/region_mean": 0.0015123801786103286,
      "epoch": 0.0013066634000081666,
      "grad_norm": 0.1443215310573578,
      "learning_rate": 2e-07,
      "loss": 0.0061,
      "step": 14
    },
    {
      "clip_ratio/high_max": 0.002351396622543689,
      "clip_ratio/high_mean": 0.0008825419790809974,
      "clip_ratio/low_mean": 0.0006741069546478684,
      "clip_ratio/low_min": 8.389318554691272e-05,
      "clip_ratio/region_mean": 0.001556648945552297,
      "epoch": 0.00139999650000875,
      "grad_norm": 0.12755635380744934,
      "learning_rate": 2e-07,
      "loss": 0.0334,
      "step": 15
    },
    {
      "clip_ratio/high_max": 0.002210871047282126,
      "clip_ratio/high_mean": 0.0009745259776536841,
      "clip_ratio/low_mean": 0.0006068867678550305,
      "clip_ratio/low_min": 4.074454409419559e-05,
      "clip_ratio/region_mean": 0.0015814127618796192,
      "epoch": 0.0014933296000093333,
      "grad_norm": 0.1446833461523056,
      "learning_rate": 2e-07,
      "loss": -0.015,
      "step": 16
    },
    {
      "clip_ratio/high_max": 0.0026980257243849337,
      "clip_ratio/high_mean": 0.0010633438287186436,
      "clip_ratio/low_mean": 0.0006677285546174971,
      "clip_ratio/low_min": 6.359473536576843e-05,
      "clip_ratio/region_mean": 0.0017310723778791726,
      "epoch": 0.0015866627000099165,
      "grad_norm": 0.14644832909107208,
      "learning_rate": 2e-07,
      "loss": 0.024,
      "step": 17
    },
    {
      "clip_ratio/high_max": 0.0018859548945329152,
      "clip_ratio/high_mean": 0.0009480064527451759,
      "clip_ratio/low_mean": 0.0006601967706956202,
      "clip_ratio/low_min": 9.549986953061307e-05,
      "clip_ratio/region_mean": 0.0016082032525446266,
      "epoch": 0.0016799958000105,
      "grad_norm": 0.16266238689422607,
      "learning_rate": 2e-07,
      "loss": 0.034,
      "step": 18
    },
    {
      "clip_ratio/high_max": 0.0025572568993084133,
      "clip_ratio/high_mean": 0.0010283998526574578,
      "clip_ratio/low_mean": 0.0005791197681901394,
      "clip_ratio/low_min": 4.354961674835067e-05,
      "clip_ratio/region_mean": 0.0016075196363090072,
      "epoch": 0.0017733289000110833,
      "grad_norm": 0.14081984758377075,
      "learning_rate": 2e-07,
      "loss": -0.0026,
      "step": 19
    },
    {
      "clip_ratio/high_max": 0.0023484854900743812,
      "clip_ratio/high_mean": 0.001032120424497407,
      "clip_ratio/low_mean": 0.0006547435968968784,
      "clip_ratio/low_min": 5.282235906634014e-05,
      "clip_ratio/region_mean": 0.0016868639941094443,
      "epoch": 0.0018666620000116667,
      "grad_norm": 0.15375037491321564,
      "learning_rate": 2e-07,
      "loss": 0.0094,
      "step": 20
    },
    {
      "clip_ratio/high_max": 0.0022490218543680385,
      "clip_ratio/high_mean": 0.000980297973001143,
      "clip_ratio/low_mean": 0.0006408726767404005,
      "clip_ratio/low_min": 3.1734762160340324e-05,
      "clip_ratio/region_mean": 0.0016211706679314375,
      "epoch": 0.00195999510001225,
      "grad_norm": 0.13868862390518188,
      "learning_rate": 2e-07,
      "loss": 0.0058,
      "step": 21
    },
    {
      "clip_ratio/high_max": 0.002334155586140696,
      "clip_ratio/high_mean": 0.001086789890905493,
      "clip_ratio/low_mean": 0.00071046191987989,
      "clip_ratio/low_min": 2.1609082068607677e-05,
      "clip_ratio/region_mean": 0.001797251810785383,
      "epoch": 0.002053328200012833,
      "grad_norm": 0.13397537171840668,
      "learning_rate": 2e-07,
      "loss": -0.0264,
      "step": 22
    },
    {
      "clip_ratio/high_max": 0.0025217489528586157,
      "clip_ratio/high_mean": 0.0010892995578615228,
      "clip_ratio/low_mean": 0.0007800756138749421,
      "clip_ratio/low_min": 0.00014082737106946297,
      "clip_ratio/region_mean": 0.0018693751990213059,
      "epoch": 0.0021466613000134167,
      "grad_norm": 0.16504544019699097,
      "learning_rate": 2e-07,
      "loss": 0.0375,
      "step": 23
    },
    {
      "clip_ratio/high_max": 0.002318485625437461,
      "clip_ratio/high_mean": 0.0010083773577207467,
      "clip_ratio/low_mean": 0.0006978539258852834,
      "clip_ratio/low_min": 0.0001557414971102844,
      "clip_ratio/region_mean": 0.0017062312763300724,
      "epoch": 0.002239994400014,
      "grad_norm": 0.14871977269649506,
      "learning_rate": 2e-07,
      "loss": 0.0237,
      "step": 24
    },
    {
      "clip_ratio/high_max": 0.0019595956327975728,
      "clip_ratio/high_mean": 0.0008987899727799231,
      "clip_ratio/low_mean": 0.0007496341422665864,
      "clip_ratio/low_min": 5.087932458991418e-05,
      "clip_ratio/region_mean": 0.0016484241568832658,
      "epoch": 0.002333327500014583,
      "grad_norm": 0.14867891371250153,
      "learning_rate": 2e-07,
      "loss": 0.0181,
      "step": 25
    },
    {
      "clip_ratio/high_max": 0.0021967895445413888,
      "clip_ratio/high_mean": 0.0010050516320916358,
      "clip_ratio/low_mean": 0.0006741976321791299,
      "clip_ratio/low_min": 4.255769363226136e-05,
      "clip_ratio/region_mean": 0.0016792492679087445,
      "epoch": 0.0024266606000151666,
      "grad_norm": 0.1324433982372284,
      "learning_rate": 2e-07,
      "loss": 0.016,
      "step": 26
    },
    {
      "clip_ratio/high_max": 0.00221184497786453,
      "clip_ratio/high_mean": 0.0009845319473242853,
      "clip_ratio/low_mean": 0.0006456787523347884,
      "clip_ratio/low_min": 3.370817330505815e-05,
      "clip_ratio/region_mean": 0.001630210656003328,
      "epoch": 0.00251999370001575,
      "grad_norm": 0.2621995806694031,
      "learning_rate": 2e-07,
      "loss": 0.0267,
      "step": 27
    },
    {
      "clip_ratio/high_max": 0.0025492762797512114,
      "clip_ratio/high_mean": 0.0010747178639576305,
      "clip_ratio/low_mean": 0.0007755294536764268,
      "clip_ratio/low_min": 0.00011764569444494555,
      "clip_ratio/region_mean": 0.0018502473467378877,
      "epoch": 0.002613326800016333,
      "grad_norm": 0.14637550711631775,
      "learning_rate": 2e-07,
      "loss": 0.0296,
      "step": 28
    },
    {
      "clip_ratio/high_max": 0.002191332503571175,
      "clip_ratio/high_mean": 0.0009977854570024647,
      "clip_ratio/low_mean": 0.0007603040994581534,
      "clip_ratio/low_min": 0.0001385093892167788,
      "clip_ratio/region_mean": 0.001758089529175777,
      "epoch": 0.0027066599000169166,
      "grad_norm": 0.16185365617275238,
      "learning_rate": 2e-07,
      "loss": 0.04,
      "step": 29
    },
    {
      "clip_ratio/high_max": 0.002307657116034534,
      "clip_ratio/high_mean": 0.0009033352707774611,
      "clip_ratio/low_mean": 0.0007147880496631842,
      "clip_ratio/low_min": 8.216399965021992e-05,
      "clip_ratio/region_mean": 0.0016181233077077195,
      "epoch": 0.0027999930000175,
      "grad_norm": 0.13148848712444305,
      "learning_rate": 2e-07,
      "loss": 0.038,
      "step": 30
    },
    {
      "clip_ratio/high_max": 0.0021877511389902793,
      "clip_ratio/high_mean": 0.0010329049073334318,
      "clip_ratio/low_mean": 0.000748579832361429,
      "clip_ratio/low_min": 6.69975906930631e-05,
      "clip_ratio/region_mean": 0.0017814847378758714,
      "epoch": 0.002893326100018083,
      "grad_norm": 0.17129682004451752,
      "learning_rate": 2e-07,
      "loss": 0.0117,
      "step": 31
    },
    {
      "clip_ratio/high_max": 0.0022434907587012276,
      "clip_ratio/high_mean": 0.0009733073347888421,
      "clip_ratio/low_mean": 0.000713086366886273,
      "clip_ratio/low_min": 1.114876886276761e-05,
      "clip_ratio/region_mean": 0.001686393705313094,
      "epoch": 0.0029866592000186666,
      "grad_norm": 0.14859792590141296,
      "learning_rate": 2e-07,
      "loss": 0.0567,
      "step": 32
    },
    {
      "clip_ratio/high_max": 0.0021690325884264894,
      "clip_ratio/high_mean": 0.001026012907459517,
      "clip_ratio/low_mean": 0.0007430598598148208,
      "clip_ratio/low_min": 5.558419979934115e-05,
      "clip_ratio/region_mean": 0.0017690727909212,
      "epoch": 0.00307999230001925,
      "grad_norm": 0.16069963574409485,
      "learning_rate": 2e-07,
      "loss": 0.0226,
      "step": 33
    },
    {
      "clip_ratio/high_max": 0.0023200569703476503,
      "clip_ratio/high_mean": 0.0009928549370670225,
      "clip_ratio/low_mean": 0.000743487267754972,
      "clip_ratio/low_min": 0.00010463964463269804,
      "clip_ratio/region_mean": 0.001736342215735931,
      "epoch": 0.003173325400019833,
      "grad_norm": 0.17957302927970886,
      "learning_rate": 2e-07,
      "loss": 0.0358,
      "step": 34
    },
    {
      "clip_ratio/high_max": 0.002232205333712045,
      "clip_ratio/high_mean": 0.0009406781464349478,
      "clip_ratio/low_mean": 0.0007508251910621766,
      "clip_ratio/low_min": 3.246802953071892e-05,
      "clip_ratio/region_mean": 0.001691503362962976,
      "epoch": 0.0032666585000204165,
      "grad_norm": 0.18125486373901367,
      "learning_rate": 2e-07,
      "loss": 0.0335,
      "step": 35
    },
    {
      "clip_ratio/high_max": 0.00237008101248648,
      "clip_ratio/high_mean": 0.0010432500639581122,
      "clip_ratio/low_mean": 0.0007043413716019131,
      "clip_ratio/low_min": 4.8047357267932966e-05,
      "clip_ratio/region_mean": 0.0017475914864917286,
      "epoch": 0.003359991600021,
      "grad_norm": 0.15145115554332733,
      "learning_rate": 2e-07,
      "loss": 0.0241,
      "step": 36
    },
    {
      "clip_ratio/high_max": 0.002563024976552697,
      "clip_ratio/high_mean": 0.0010309857952961465,
      "clip_ratio/low_mean": 0.0007508490234613419,
      "clip_ratio/low_min": 0.00011208651358174393,
      "clip_ratio/region_mean": 0.0017818348496803083,
      "epoch": 0.0034533247000215835,
      "grad_norm": 0.26259833574295044,
      "learning_rate": 2e-07,
      "loss": 0.041,
      "step": 37
    },
    {
      "clip_ratio/high_max": 0.002667009917786345,
      "clip_ratio/high_mean": 0.0011350483546266332,
      "clip_ratio/low_mean": 0.0006800539285904961,
      "clip_ratio/low_min": 4.993234142602887e-05,
      "clip_ratio/region_mean": 0.0018151022668462247,
      "epoch": 0.0035466578000221665,
      "grad_norm": 0.1589832454919815,
      "learning_rate": 2e-07,
      "loss": -0.0055,
      "step": 38
    },
    {
      "clip_ratio/high_max": 0.0022534245072165504,
      "clip_ratio/high_mean": 0.0010167706041102065,
      "clip_ratio/low_mean": 0.000752102965634549,
      "clip_ratio/low_min": 0.00010989894872182049,
      "clip_ratio/region_mean": 0.0017688735752017237,
      "epoch": 0.00363999090002275,
      "grad_norm": 0.16235077381134033,
      "learning_rate": 2e-07,
      "loss": 0.0104,
      "step": 39
    },
    {
      "clip_ratio/high_max": 0.0021170013278606348,
      "clip_ratio/high_mean": 0.0009705373049655464,
      "clip_ratio/low_mean": 0.0007387842024400015,
      "clip_ratio/low_min": 8.674604123370955e-05,
      "clip_ratio/region_mean": 0.001709321528323926,
      "epoch": 0.0037333240000233334,
      "grad_norm": 0.1307630091905594,
      "learning_rate": 2e-07,
      "loss": 0.0193,
      "step": 40
    },
    {
      "clip_ratio/high_max": 0.0028063174031558447,
      "clip_ratio/high_mean": 0.0011612276648520492,
      "clip_ratio/low_mean": 0.0007333334087888943,
      "clip_ratio/low_min": 0.00012489808705140604,
      "clip_ratio/region_mean": 0.001894561035442166,
      "epoch": 0.0038266571000239165,
      "grad_norm": 0.1325671523809433,
      "learning_rate": 2e-07,
      "loss": -0.0054,
      "step": 41
    },
    {
      "clip_ratio/high_max": 0.0023343516513705254,
      "clip_ratio/high_mean": 0.0009843094485404436,
      "clip_ratio/low_mean": 0.0009499793850409333,
      "clip_ratio/low_min": 8.664441884320695e-05,
      "clip_ratio/region_mean": 0.0019342888408573344,
      "epoch": 0.0039199902000245,
      "grad_norm": 0.14978283643722534,
      "learning_rate": 2e-07,
      "loss": 0.0338,
      "step": 42
    },
    {
      "clip_ratio/high_max": 0.0026751063196570612,
      "clip_ratio/high_mean": 0.0012017712615488563,
      "clip_ratio/low_mean": 0.0008109274294838542,
      "clip_ratio/low_min": 0.00011104511941084638,
      "clip_ratio/region_mean": 0.0020126986855757423,
      "epoch": 0.004013323300025083,
      "grad_norm": 0.1430795043706894,
      "learning_rate": 2e-07,
      "loss": -0.0006,
      "step": 43
    },
    {
      "clip_ratio/high_max": 0.002226410506409593,
      "clip_ratio/high_mean": 0.001006771088214009,
      "clip_ratio/low_mean": 0.0008320151646330487,
      "clip_ratio/low_min": 0.00018646756507223472,
      "clip_ratio/region_mean": 0.0018387862655799836,
      "epoch": 0.004106656400025666,
      "grad_norm": 0.13031642138957977,
      "learning_rate": 2e-07,
      "loss": 0.0042,
      "step": 44
    },
    {
      "clip_ratio/high_max": 0.002572059296653606,
      "clip_ratio/high_mean": 0.001111016956201638,
      "clip_ratio/low_mean": 0.0009562791892676614,
      "clip_ratio/low_min": 5.3831755849387264e-05,
      "clip_ratio/region_mean": 0.002067296125460416,
      "epoch": 0.00419998950002625,
      "grad_norm": 0.14828446507453918,
      "learning_rate": 2e-07,
      "loss": 0.0178,
      "step": 45
    },
    {
      "clip_ratio/high_max": 0.0025222725889761932,
      "clip_ratio/high_mean": 0.0010423919484310318,
      "clip_ratio/low_mean": 0.0007909676660347031,
      "clip_ratio/low_min": 9.384907298226608e-05,
      "clip_ratio/region_mean": 0.0018333595871808939,
      "epoch": 0.004293322600026833,
      "grad_norm": 0.15505465865135193,
      "learning_rate": 2e-07,
      "loss": 0.0439,
      "step": 46
    },
    {
      "clip_ratio/high_max": 0.0021047551636002026,
      "clip_ratio/high_mean": 0.0009077926306417794,
      "clip_ratio/low_mean": 0.0007585885159642203,
      "clip_ratio/low_min": 7.39135175535921e-05,
      "clip_ratio/region_mean": 0.0016663811438775156,
      "epoch": 0.004386655700027417,
      "grad_norm": 0.16200260818004608,
      "learning_rate": 2e-07,
      "loss": 0.0603,
      "step": 47
    },
    {
      "clip_ratio/high_max": 0.00229677894822089,
      "clip_ratio/high_mean": 0.001016259386233287,
      "clip_ratio/low_mean": 0.0008135440075420775,
      "clip_ratio/low_min": 6.104169733589515e-05,
      "clip_ratio/region_mean": 0.0018298033683095127,
      "epoch": 0.004479988800028,
      "grad_norm": 0.15192489326000214,
      "learning_rate": 2e-07,
      "loss": 0.0274,
      "step": 48
    },
    {
      "clip_ratio/high_max": 0.0027774704940384254,
      "clip_ratio/high_mean": 0.0010080403280881,
      "clip_ratio/low_mean": 0.0008196654034691164,
      "clip_ratio/low_min": 9.272444185626227e-05,
      "clip_ratio/region_mean": 0.0018277057315572165,
      "epoch": 0.004573321900028583,
      "grad_norm": 0.17384760081768036,
      "learning_rate": 2e-07,
      "loss": 0.0526,
      "step": 49
    },
    {
      "clip_ratio/high_max": 0.002093526069074869,
      "clip_ratio/high_mean": 0.0009535997196508106,
      "clip_ratio/low_mean": 0.0007246116292662919,
      "clip_ratio/low_min": 0.00012367929457468563,
      "clip_ratio/region_mean": 0.0016782113889348693,
      "epoch": 0.004666655000029166,
      "grad_norm": 0.4138626456260681,
      "learning_rate": 2e-07,
      "loss": 0.0422,
      "step": 50
    },
    {
      "clip_ratio/high_max": 0.0021515874068427365,
      "clip_ratio/high_mean": 0.0009167434800474439,
      "clip_ratio/low_mean": 0.0008631627897557337,
      "clip_ratio/low_min": 0.00015628979235771112,
      "clip_ratio/region_mean": 0.0017799062552512623,
      "epoch": 0.00475998810002975,
      "grad_norm": 0.1734093278646469,
      "learning_rate": 2e-07,
      "loss": 0.0585,
      "step": 51
    },
    {
      "clip_ratio/high_max": 0.0027632777564576827,
      "clip_ratio/high_mean": 0.0011283850835752673,
      "clip_ratio/low_mean": 0.000805856216175016,
      "clip_ratio/low_min": 0.00010226385984424269,
      "clip_ratio/region_mean": 0.0019342413506819867,
      "epoch": 0.004853321200030333,
      "grad_norm": 0.19594521820545197,
      "learning_rate": 2e-07,
      "loss": 0.016,
      "step": 52
    },
    {
      "clip_ratio/high_max": 0.0022071929124649614,
      "clip_ratio/high_mean": 0.0010580600246612448,
      "clip_ratio/low_mean": 0.0008659018130856566,
      "clip_ratio/low_min": 6.15788230788894e-05,
      "clip_ratio/region_mean": 0.0019239617977291346,
      "epoch": 0.004946654300030917,
      "grad_norm": 0.17863456904888153,
      "learning_rate": 2e-07,
      "loss": 0.0264,
      "step": 53
    },
    {
      "clip_ratio/high_max": 0.0024368626982322894,
      "clip_ratio/high_mean": 0.0011928184467251413,
      "clip_ratio/low_mean": 0.000822635385702597,
      "clip_ratio/low_min": 0.00013990535080665722,
      "clip_ratio/region_mean": 0.0020154538433416747,
      "epoch": 0.0050399874000315,
      "grad_norm": 0.19694636762142181,
      "learning_rate": 2e-07,
      "loss": 0.0011,
      "step": 54
    },
    {
      "clip_ratio/high_max": 0.002929450958617963,
      "clip_ratio/high_mean": 0.0012396831334626768,
      "clip_ratio/low_mean": 0.0007807874735590303,
      "clip_ratio/low_min": 0.00013336174606592976,
      "clip_ratio/region_mean": 0.0020204705942887813,
      "epoch": 0.005133320500032083,
      "grad_norm": 0.19725419580936432,
      "learning_rate": 2e-07,
      "loss": 0.0115,
      "step": 55
    },
    {
      "clip_ratio/high_max": 0.0028225080750416964,
      "clip_ratio/high_mean": 0.0012325172683631536,
      "clip_ratio/low_mean": 0.0008001118712854804,
      "clip_ratio/low_min": 7.073291999404319e-05,
      "clip_ratio/region_mean": 0.0020326290978118777,
      "epoch": 0.005226653600032666,
      "grad_norm": 0.1624283641576767,
      "learning_rate": 2e-07,
      "loss": -0.0038,
      "step": 56
    },
    {
      "clip_ratio/high_max": 0.002502915078366641,
      "clip_ratio/high_mean": 0.0010232139175059274,
      "clip_ratio/low_mean": 0.000877360380400205,
      "clip_ratio/low_min": 9.261917966796318e-05,
      "clip_ratio/region_mean": 0.0019005742578883655,
      "epoch": 0.00531998670003325,
      "grad_norm": 0.44605982303619385,
      "learning_rate": 2e-07,
      "loss": 0.0394,
      "step": 57
    },
    {
      "clip_ratio/high_max": 0.0020510404065134935,
      "clip_ratio/high_mean": 0.0009520262228761567,
      "clip_ratio/low_mean": 0.0009041506746143568,
      "clip_ratio/low_min": 5.323639379639644e-05,
      "clip_ratio/region_mean": 0.0018561769029474817,
      "epoch": 0.005413319800033833,
      "grad_norm": 0.19620570540428162,
      "learning_rate": 2e-07,
      "loss": 0.0312,
      "step": 58
    },
    {
      "clip_ratio/high_max": 0.0022402981703635305,
      "clip_ratio/high_mean": 0.0010909843804256525,
      "clip_ratio/low_mean": 0.0009064340847544372,
      "clip_ratio/low_min": 9.927446353685809e-05,
      "clip_ratio/region_mean": 0.0019974184833699837,
      "epoch": 0.005506652900034417,
      "grad_norm": 0.16989979147911072,
      "learning_rate": 2e-07,
      "loss": 0.0298,
      "step": 59
    },
    {
      "clip_ratio/high_max": 0.0024603563506389037,
      "clip_ratio/high_mean": 0.001084091894881567,
      "clip_ratio/low_mean": 0.0008537646262993803,
      "clip_ratio/low_min": 7.753918544040062e-05,
      "clip_ratio/region_mean": 0.001937856519361958,
      "epoch": 0.005599986000035,
      "grad_norm": 0.1661187708377838,
      "learning_rate": 2e-07,
      "loss": 0.0143,
      "step": 60
    },
    {
      "clip_ratio/high_max": 0.0027738240751205012,
      "clip_ratio/high_mean": 0.0011560479215404484,
      "clip_ratio/low_mean": 0.0008643481487524696,
      "clip_ratio/low_min": 0.00015047538181534037,
      "clip_ratio/region_mean": 0.0020203961175866425,
      "epoch": 0.005693319100035584,
      "grad_norm": 0.15792235732078552,
      "learning_rate": 2e-07,
      "loss": 0.0124,
      "step": 61
    },
    {
      "clip_ratio/high_max": 0.0023871076045907103,
      "clip_ratio/high_mean": 0.0011370957072358578,
      "clip_ratio/low_mean": 0.0007909991363703739,
      "clip_ratio/low_min": 5.895521371712675e-05,
      "clip_ratio/region_mean": 0.001928094839968253,
      "epoch": 0.005786652200036166,
      "grad_norm": 0.1416006088256836,
      "learning_rate": 2e-07,
      "loss": -0.022,
      "step": 62
    },
    {
      "clip_ratio/high_max": 0.0024896654213080183,
      "clip_ratio/high_mean": 0.0010819306517078076,
      "clip_ratio/low_mean": 0.0008097823738353327,
      "clip_ratio/low_min": 0.00011734104282368207,
      "clip_ratio/region_mean": 0.0018917130655609071,
      "epoch": 0.00587998530003675,
      "grad_norm": 0.1736774444580078,
      "learning_rate": 2e-07,
      "loss": 0.028,
      "step": 63
    },
    {
      "clip_ratio/high_max": 0.002121022858773358,
      "clip_ratio/high_mean": 0.0010597049058560515,
      "clip_ratio/low_mean": 0.0008689436963322805,
      "clip_ratio/low_min": 0.00020803285497095203,
      "clip_ratio/region_mean": 0.00192864854761865,
      "epoch": 0.005973318400037333,
      "grad_norm": 0.22265668213367462,
      "learning_rate": 2e-07,
      "loss": 0.0379,
      "step": 64
    },
    {
      "clip_ratio/high_max": 0.0023637892700207885,
      "clip_ratio/high_mean": 0.0009820849154493771,
      "clip_ratio/low_mean": 0.0009203073786920868,
      "clip_ratio/low_min": 0.00013381684539126582,
      "clip_ratio/region_mean": 0.0019023923159693368,
      "epoch": 0.006066651500037917,
      "grad_norm": 0.2035197913646698,
      "learning_rate": 2e-07,
      "loss": 0.0696,
      "step": 65
    },
    {
      "clip_ratio/high_max": 0.002492961139068939,
      "clip_ratio/high_mean": 0.0012293810032133479,
      "clip_ratio/low_mean": 0.0007596666455356171,
      "clip_ratio/low_min": 0.0001599594024810358,
      "clip_ratio/region_mean": 0.0019890476323780604,
      "epoch": 0.0061599846000385,
      "grad_norm": 0.17650087177753448,
      "learning_rate": 2e-07,
      "loss": 0.0158,
      "step": 66
    },
    {
      "clip_ratio/high_max": 0.0028149780118837953,
      "clip_ratio/high_mean": 0.0010748904351203237,
      "clip_ratio/low_mean": 0.000826733357826015,
      "clip_ratio/low_min": 0.00010900974393734941,
      "clip_ratio/region_mean": 0.0019016238293261267,
      "epoch": 0.0062533177000390835,
      "grad_norm": 0.2179858386516571,
      "learning_rate": 2e-07,
      "loss": 0.0391,
      "step": 67
    },
    {
      "clip_ratio/high_max": 0.0023134970833780244,
      "clip_ratio/high_mean": 0.0010798194380186033,
      "clip_ratio/low_mean": 0.0008778970168350497,
      "clip_ratio/low_min": 5.8156663726549596e-05,
      "clip_ratio/region_mean": 0.001957716500328388,
      "epoch": 0.006346650800039666,
      "grad_norm": 0.2374267876148224,
      "learning_rate": 2e-07,
      "loss": 0.0024,
      "step": 68
    },
    {
      "clip_ratio/high_max": 0.0027998356890748255,
      "clip_ratio/high_mean": 0.0012960523454239592,
      "clip_ratio/low_mean": 0.0009323103022325085,
      "clip_ratio/low_min": 9.667921585787553e-05,
      "clip_ratio/region_mean": 0.0022283626240096055,
      "epoch": 0.00643998390004025,
      "grad_norm": 0.1723237782716751,
      "learning_rate": 2e-07,
      "loss": -0.0295,
      "step": 69
    },
    {
      "clip_ratio/high_max": 0.0027361434331396595,
      "clip_ratio/high_mean": 0.0012135108772781678,
      "clip_ratio/low_mean": 0.0008462146015517646,
      "clip_ratio/low_min": 1.4838556126051117e-05,
      "clip_ratio/region_mean": 0.00205972545518307,
      "epoch": 0.006533317000040833,
      "grad_norm": 0.2730659544467926,
      "learning_rate": 2e-07,
      "loss": 0.0066,
      "step": 70
    },
    {
      "clip_ratio/high_max": 0.002428738422167953,
      "clip_ratio/high_mean": 0.0011149525598739274,
      "clip_ratio/low_mean": 0.0009069315674423706,
      "clip_ratio/low_min": 0.00010064037815027405,
      "clip_ratio/region_mean": 0.0020218841309542768,
      "epoch": 0.0066266501000414165,
      "grad_norm": 0.18444810807704926,
      "learning_rate": 2e-07,
      "loss": -0.0091,
      "step": 71
    },
    {
      "clip_ratio/high_max": 0.0028033852941007353,
      "clip_ratio/high_mean": 0.00131632607372012,
      "clip_ratio/low_mean": 0.0009276634955313057,
      "clip_ratio/low_min": 2.9113659365975764e-05,
      "clip_ratio/region_mean": 0.0022439895474235527,
      "epoch": 0.006719983200042,
      "grad_norm": 0.1775394082069397,
      "learning_rate": 2e-07,
      "loss": -0.0155,
      "step": 72
    },
    {
      "clip_ratio/high_max": 0.0024941975352703594,
      "clip_ratio/high_mean": 0.001106993600842543,
      "clip_ratio/low_mean": 0.000981330216745846,
      "clip_ratio/low_min": 0.00012341036017460283,
      "clip_ratio/region_mean": 0.0020883238248643465,
      "epoch": 0.0068133163000425835,
      "grad_norm": 0.17234064638614655,
      "learning_rate": 2e-07,
      "loss": 0.0579,
      "step": 73
    },
    {
      "clip_ratio/high_max": 0.0026957338413922116,
      "clip_ratio/high_mean": 0.001078817767847795,
      "clip_ratio/low_mean": 0.0009087666549021378,
      "clip_ratio/low_min": 0.00010553940501267789,
      "clip_ratio/region_mean": 0.001987584364542272,
      "epoch": 0.006906649400043167,
      "grad_norm": 0.14620539546012878,
      "learning_rate": 2e-07,
      "loss": 0.0073,
      "step": 74
    },
    {
      "clip_ratio/high_max": 0.002455393645504955,
      "clip_ratio/high_mean": 0.001171944120869739,
      "clip_ratio/low_mean": 0.0012243612691236194,
      "clip_ratio/low_min": 0.00021858633954252582,
      "clip_ratio/region_mean": 0.002396305375441443,
      "epoch": 0.0069999825000437495,
      "grad_norm": 0.1882891207933426,
      "learning_rate": 2e-07,
      "loss": 0.0386,
      "step": 75
    },
    {
      "clip_ratio/high_max": 0.0024321619712281972,
      "clip_ratio/high_mean": 0.001136313752795104,
      "clip_ratio/low_mean": 0.0009440828944207169,
      "clip_ratio/low_min": 0.00016096510080387816,
      "clip_ratio/region_mean": 0.0020803966108360328,
      "epoch": 0.007093315600044333,
      "grad_norm": 0.1752462089061737,
      "learning_rate": 2e-07,
      "loss": 0.0489,
      "step": 76
    },
    {
      "clip_ratio/high_max": 0.0024777910803095438,
      "clip_ratio/high_mean": 0.0011775482307712082,
      "clip_ratio/low_mean": 0.0011148723133374006,
      "clip_ratio/low_min": 0.00014076209481572732,
      "clip_ratio/region_mean": 0.002292420467711054,
      "epoch": 0.0071866487000449165,
      "grad_norm": 0.1601407527923584,
      "learning_rate": 2e-07,
      "loss": 0.056,
      "step": 77
    },
    {
      "clip_ratio/high_max": 0.00286518858774798,
      "clip_ratio/high_mean": 0.0011782766887336038,
      "clip_ratio/low_mean": 0.0010658108549250755,
      "clip_ratio/low_min": 0.00020794519969058456,
      "clip_ratio/region_mean": 0.0022440875836764462,
      "epoch": 0.0072799818000455,
      "grad_norm": 0.1464841067790985,
      "learning_rate": 2e-07,
      "loss": -0.0047,
      "step": 78
    },
    {
      "clip_ratio/high_max": 0.0026522570697125047,
      "clip_ratio/high_mean": 0.0011561137689568568,
      "clip_ratio/low_mean": 0.0011050398024963215,
      "clip_ratio/low_min": 0.0001377565286020399,
      "clip_ratio/region_mean": 0.002261153560539242,
      "epoch": 0.007373314900046083,
      "grad_norm": 0.16872893273830414,
      "learning_rate": 2e-07,
      "loss": 0.0167,
      "step": 79
    },
    {
      "clip_ratio/high_max": 0.0020787146131624468,
      "clip_ratio/high_mean": 0.0010273715779476333,
      "clip_ratio/low_mean": 0.001056640008755494,
      "clip_ratio/low_min": 0.00013105883408570662,
      "clip_ratio/region_mean": 0.0020840116194449365,
      "epoch": 0.007466648000046667,
      "grad_norm": 0.1522258073091507,
      "learning_rate": 2e-07,
      "loss": 0.0243,
      "step": 80
    },
    {
      "clip_ratio/high_max": 0.0025840453890850767,
      "clip_ratio/high_mean": 0.0011914781789528206,
      "clip_ratio/low_mean": 0.00096780594685697,
      "clip_ratio/low_min": 8.13832211861154e-05,
      "clip_ratio/region_mean": 0.0021592840930679813,
      "epoch": 0.0075599811000472495,
      "grad_norm": 0.1554807871580124,
      "learning_rate": 2e-07,
      "loss": -0.0174,
      "step": 81
    },
    {
      "clip_ratio/high_max": 0.0025976478500524536,
      "clip_ratio/high_mean": 0.0011098824033979326,
      "clip_ratio/low_mean": 0.0010079027779283933,
      "clip_ratio/low_min": 0.00018711211305344477,
      "clip_ratio/region_mean": 0.002117785144946538,
      "epoch": 0.007653314200047833,
      "grad_norm": 0.16818466782569885,
      "learning_rate": 2e-07,
      "loss": 0.0013,
      "step": 82
    },
    {
      "clip_ratio/high_max": 0.002760782968834974,
      "clip_ratio/high_mean": 0.0012953164550708607,
      "clip_ratio/low_mean": 0.0010259411537845153,
      "clip_ratio/low_min": 0.00020376176507852506,
      "clip_ratio/region_mean": 0.0023212575761135668,
      "epoch": 0.007746647300048416,
      "grad_norm": 0.15922905504703522,
      "learning_rate": 2e-07,
      "loss": 0.0185,
      "step": 83
    },
    {
      "clip_ratio/high_max": 0.0022610355663346127,
      "clip_ratio/high_mean": 0.0010640630425768904,
      "clip_ratio/low_mean": 0.0011177770211361349,
      "clip_ratio/low_min": 0.00017762661718734307,
      "clip_ratio/region_mean": 0.002181840070988983,
      "epoch": 0.007839980400049,
      "grad_norm": 0.2317257821559906,
      "learning_rate": 2e-07,
      "loss": 0.0707,
      "step": 84
    },
    {
      "clip_ratio/high_max": 0.003170649491949007,
      "clip_ratio/high_mean": 0.0012081483073416166,
      "clip_ratio/low_mean": 0.0009731504978844896,
      "clip_ratio/low_min": 6.705739633616759e-05,
      "clip_ratio/region_mean": 0.002181298768846318,
      "epoch": 0.007933313500049582,
      "grad_norm": 0.1538148671388626,
      "learning_rate": 2e-07,
      "loss": -0.0345,
      "step": 85
    },
    {
      "clip_ratio/high_max": 0.00311738379241433,
      "clip_ratio/high_mean": 0.0014117482569417916,
      "clip_ratio/low_mean": 0.0009917117859004065,
      "clip_ratio/low_min": 0.00012142241030232981,
      "clip_ratio/region_mean": 0.0024034599846345372,
      "epoch": 0.008026646600050166,
      "grad_norm": 0.15156802535057068,
      "learning_rate": 2e-07,
      "loss": -0.0178,
      "step": 86
    },
    {
      "clip_ratio/high_max": 0.0026232885938952677,
      "clip_ratio/high_mean": 0.0012325879106356297,
      "clip_ratio/low_mean": 0.0010174159961024998,
      "clip_ratio/low_min": 8.909288317227038e-05,
      "clip_ratio/region_mean": 0.0022500038976431824,
      "epoch": 0.00811997970005075,
      "grad_norm": 0.15562191605567932,
      "learning_rate": 2e-07,
      "loss": -0.0129,
      "step": 87
    },
    {
      "clip_ratio/high_max": 0.0027344549307599664,
      "clip_ratio/high_mean": 0.0011531643067428377,
      "clip_ratio/low_mean": 0.001031320858601248,
      "clip_ratio/low_min": 0.00019616128975030733,
      "clip_ratio/region_mean": 0.002184485136240255,
      "epoch": 0.008213312800051333,
      "grad_norm": 0.1790563017129898,
      "learning_rate": 2e-07,
      "loss": 0.0112,
      "step": 88
    },
    {
      "clip_ratio/high_max": 0.0028811536758439615,
      "clip_ratio/high_mean": 0.0011734828731277958,
      "clip_ratio/low_mean": 0.0010850944672711194,
      "clip_ratio/low_min": 0.00019698643245646963,
      "clip_ratio/region_mean": 0.0022585772967431694,
      "epoch": 0.008306645900051916,
      "grad_norm": 0.1686941534280777,
      "learning_rate": 2e-07,
      "loss": 0.0511,
      "step": 89
    },
    {
      "clip_ratio/high_max": 0.002771753519482445,
      "clip_ratio/high_mean": 0.0011782679739553714,
      "clip_ratio/low_mean": 0.0010731514885264914,
      "clip_ratio/low_min": 0.000161624574502639,
      "clip_ratio/region_mean": 0.0022514195006806403,
      "epoch": 0.0083999790000525,
      "grad_norm": 0.1549367606639862,
      "learning_rate": 2e-07,
      "loss": 0.0436,
      "step": 90
    },
    {
      "clip_ratio/high_max": 0.0026062028628075495,
      "clip_ratio/high_mean": 0.0012258525712240953,
      "clip_ratio/low_mean": 0.0011274315911578014,
      "clip_ratio/low_min": 0.00011721917962859152,
      "clip_ratio/region_mean": 0.0023532842023996636,
      "epoch": 0.008493312100053083,
      "grad_norm": 0.23962625861167908,
      "learning_rate": 2e-07,
      "loss": 0.024,
      "step": 91
    },
    {
      "clip_ratio/high_max": 0.0024852457499946468,
      "clip_ratio/high_mean": 0.001242582053237129,
      "clip_ratio/low_mean": 0.0010324958821001928,
      "clip_ratio/low_min": 9.696555480331881e-05,
      "clip_ratio/region_mean": 0.0022750778443878517,
      "epoch": 0.008586645200053667,
      "grad_norm": 0.15057489275932312,
      "learning_rate": 2e-07,
      "loss": 0.0038,
      "step": 92
    },
    {
      "clip_ratio/high_max": 0.0029352035126066767,
      "clip_ratio/high_mean": 0.001217487242684001,
      "clip_ratio/low_mean": 0.001007187383947894,
      "clip_ratio/low_min": 4.805749995284714e-05,
      "clip_ratio/region_mean": 0.0022246746957534924,
      "epoch": 0.00867997830005425,
      "grad_norm": 0.1444324553012848,
      "learning_rate": 2e-07,
      "loss": 0.0091,
      "step": 93
    },
    {
      "clip_ratio/high_max": 0.0031350492281490006,
      "clip_ratio/high_mean": 0.001457300822949037,
      "clip_ratio/low_mean": 0.0008478179879602976,
      "clip_ratio/low_min": 4.969928068021545e-05,
      "clip_ratio/region_mean": 0.0023051187745295465,
      "epoch": 0.008773311400054834,
      "grad_norm": 0.18100248277187347,
      "learning_rate": 2e-07,
      "loss": -0.0343,
      "step": 94
    },
    {
      "clip_ratio/high_max": 0.002497330387996044,
      "clip_ratio/high_mean": 0.0011044251623388845,
      "clip_ratio/low_mean": 0.0009866000782494666,
      "clip_ratio/low_min": 6.684048094030004e-05,
      "clip_ratio/region_mean": 0.0020910252424073406,
      "epoch": 0.008866644500055417,
      "grad_norm": 0.1613749861717224,
      "learning_rate": 2e-07,
      "loss": 0.0099,
      "step": 95
    },
    {
      "clip_ratio/high_max": 0.0024407687997154426,
      "clip_ratio/high_mean": 0.0011559821032278705,
      "clip_ratio/low_mean": 0.0010629022708599223,
      "clip_ratio/low_min": 0.00016844186484377133,
      "clip_ratio/region_mean": 0.002218884401372634,
      "epoch": 0.008959977600056,
      "grad_norm": 0.2290535867214203,
      "learning_rate": 2e-07,
      "loss": 0.0888,
      "step": 96
    },
    {
      "clip_ratio/high_max": 0.002623085805680603,
      "clip_ratio/high_mean": 0.0011537889222381637,
      "clip_ratio/low_mean": 0.000994703579635825,
      "clip_ratio/low_min": 0.00012388513187033823,
      "clip_ratio/region_mean": 0.0021484925237018615,
      "epoch": 0.009053310700056582,
      "grad_norm": 0.14506809413433075,
      "learning_rate": 2e-07,
      "loss": 0.0327,
      "step": 97
    },
    {
      "clip_ratio/high_max": 0.0028433686966309324,
      "clip_ratio/high_mean": 0.0011988236910838168,
      "clip_ratio/low_mean": 0.0010734581337601412,
      "clip_ratio/low_min": 0.00014010912127560005,
      "clip_ratio/region_mean": 0.0022722818393958732,
      "epoch": 0.009146643800057166,
      "grad_norm": 0.1923784464597702,
      "learning_rate": 2e-07,
      "loss": 0.0362,
      "step": 98
    },
    {
      "clip_ratio/high_max": 0.0027167624139110558,
      "clip_ratio/high_mean": 0.0011705067881848663,
      "clip_ratio/low_mean": 0.001112714220653288,
      "clip_ratio/low_min": 0.0001699766189631191,
      "clip_ratio/region_mean": 0.002283220979734324,
      "epoch": 0.00923997690005775,
      "grad_norm": 0.2344072312116623,
      "learning_rate": 2e-07,
      "loss": -0.0199,
      "step": 99
    },
    {
      "clip_ratio/high_max": 0.0027516422705957666,
      "clip_ratio/high_mean": 0.0013628134729515295,
      "clip_ratio/low_mean": 0.0011274837270320859,
      "clip_ratio/low_min": 0.00020209298600093462,
      "clip_ratio/region_mean": 0.0024902972363634035,
      "epoch": 0.009333310000058333,
      "grad_norm": 0.18619844317436218,
      "learning_rate": 2e-07,
      "loss": -0.0015,
      "step": 100
    },
    {
      "clip_ratio/high_max": 0.002597353857709095,
      "clip_ratio/high_mean": 0.0012452992887119763,
      "clip_ratio/low_mean": 0.001088854076442658,
      "clip_ratio/low_min": 8.280910878966097e-05,
      "clip_ratio/region_mean": 0.0023341533160419203,
      "epoch": 0.009426643100058916,
      "grad_norm": 0.2183188945055008,
      "learning_rate": 2e-07,
      "loss": -0.0352,
      "step": 101
    },
    {
      "clip_ratio/high_max": 0.0025321473585790955,
      "clip_ratio/high_mean": 0.001090346704586409,
      "clip_ratio/low_mean": 0.0013514034617401194,
      "clip_ratio/low_min": 0.000209757589345827,
      "clip_ratio/region_mean": 0.0024417501699645072,
      "epoch": 0.0095199762000595,
      "grad_norm": 0.22511126101016998,
      "learning_rate": 2e-07,
      "loss": 0.0642,
      "step": 102
    },
    {
      "clip_ratio/high_max": 0.0028341261204332113,
      "clip_ratio/high_mean": 0.0013259261286293622,
      "clip_ratio/low_mean": 0.001099737613913021,
      "clip_ratio/low_min": 9.952640039045946e-05,
      "clip_ratio/region_mean": 0.0024256637261714786,
      "epoch": 0.009613309300060083,
      "grad_norm": 0.21416018903255463,
      "learning_rate": 2e-07,
      "loss": 0.0043,
      "step": 103
    },
    {
      "clip_ratio/high_max": 0.0024637576898385305,
      "clip_ratio/high_mean": 0.0011640440516202943,
      "clip_ratio/low_mean": 0.0011428451743995538,
      "clip_ratio/low_min": 0.00018180822644353611,
      "clip_ratio/region_mean": 0.00230688918964006,
      "epoch": 0.009706642400060667,
      "grad_norm": 0.16819307208061218,
      "learning_rate": 2e-07,
      "loss": 0.0199,
      "step": 104
    },
    {
      "clip_ratio/high_max": 0.002184862667490961,
      "clip_ratio/high_mean": 0.0011315882438793778,
      "clip_ratio/low_mean": 0.0012017831759294495,
      "clip_ratio/low_min": 0.00017777476750779897,
      "clip_ratio/region_mean": 0.0023333714561886154,
      "epoch": 0.00979997550006125,
      "grad_norm": 0.17144903540611267,
      "learning_rate": 2e-07,
      "loss": 0.041,
      "step": 105
    },
    {
      "clip_ratio/high_max": 0.002373758194153197,
      "clip_ratio/high_mean": 0.0011477002808533143,
      "clip_ratio/low_mean": 0.0011392829364922363,
      "clip_ratio/low_min": 0.0001842488763941219,
      "clip_ratio/region_mean": 0.002286983173689805,
      "epoch": 0.009893308600061834,
      "grad_norm": 0.2242686152458191,
      "learning_rate": 2e-07,
      "loss": 0.0315,
      "step": 106
    },
    {
      "clip_ratio/high_max": 0.0027733788228943013,
      "clip_ratio/high_mean": 0.001306910955463536,
      "clip_ratio/low_mean": 0.0012386434391373768,
      "clip_ratio/low_min": 0.00022783445183449658,
      "clip_ratio/region_mean": 0.002545554409152828,
      "epoch": 0.009986641700062417,
      "grad_norm": 0.18035157024860382,
      "learning_rate": 2e-07,
      "loss": 0.0333,
      "step": 107
    },
    {
      "clip_ratio/high_max": 0.002564405724115204,
      "clip_ratio/high_mean": 0.0012918792199343443,
      "clip_ratio/low_mean": 0.001098064603866078,
      "clip_ratio/low_min": 0.00011617127438512398,
      "clip_ratio/region_mean": 0.002389943845628295,
      "epoch": 0.010079974800063,
      "grad_norm": 0.17409373819828033,
      "learning_rate": 2e-07,
      "loss": -0.0138,
      "step": 108
    },
    {
      "clip_ratio/high_max": 0.0032434069144073874,
      "clip_ratio/high_mean": 0.0013272350370243657,
      "clip_ratio/low_mean": 0.0012174488892924273,
      "clip_ratio/low_min": 0.00018728227405517828,
      "clip_ratio/region_mean": 0.0025446839063079096,
      "epoch": 0.010173307900063584,
      "grad_norm": 0.18501029908657074,
      "learning_rate": 2e-07,
      "loss": 0.009,
      "step": 109
    },
    {
      "clip_ratio/high_max": 0.0028590106303454377,
      "clip_ratio/high_mean": 0.0012671758013311774,
      "clip_ratio/low_mean": 0.0011612375856202561,
      "clip_ratio/low_min": 0.00019318097838549875,
      "clip_ratio/region_mean": 0.002428413434245158,
      "epoch": 0.010266641000064166,
      "grad_norm": 0.18641002476215363,
      "learning_rate": 2e-07,
      "loss": 0.023,
      "step": 110
    },
    {
      "clip_ratio/high_max": 0.002582947810878977,
      "clip_ratio/high_mean": 0.0012354759601294063,
      "clip_ratio/low_mean": 0.0011541565854713554,
      "clip_ratio/low_min": 0.00017510279212729074,
      "clip_ratio/region_mean": 0.002389632565609645,
      "epoch": 0.010359974100064749,
      "grad_norm": 0.18417418003082275,
      "learning_rate": 2e-07,
      "loss": 0.0087,
      "step": 111
    },
    {
      "clip_ratio/high_max": 0.0027545609045773745,
      "clip_ratio/high_mean": 0.0013644360078615136,
      "clip_ratio/low_mean": 0.0013211760779086035,
      "clip_ratio/low_min": 0.00025255313357774867,
      "clip_ratio/region_mean": 0.0026856120821321383,
      "epoch": 0.010453307200065333,
      "grad_norm": 0.22844615578651428,
      "learning_rate": 2e-07,
      "loss": 0.0051,
      "step": 112
    },
    {
      "clip_ratio/high_max": 0.0027774928603321314,
      "clip_ratio/high_mean": 0.0011485788563732058,
      "clip_ratio/low_mean": 0.0013238698338682298,
      "clip_ratio/low_min": 0.00020535209114314057,
      "clip_ratio/region_mean": 0.002472448664775584,
      "epoch": 0.010546640300065916,
      "grad_norm": 0.20752160251140594,
      "learning_rate": 2e-07,
      "loss": 0.0515,
      "step": 113
    },
    {
      "clip_ratio/high_max": 0.0028086688034818508,
      "clip_ratio/high_mean": 0.0013008714631723706,
      "clip_ratio/low_mean": 0.0012286788114579394,
      "clip_ratio/low_min": 0.00018464175900589908,
      "clip_ratio/region_mean": 0.0025295503219240345,
      "epoch": 0.0106399734000665,
      "grad_norm": 0.20691971480846405,
      "learning_rate": 2e-07,
      "loss": -0.007,
      "step": 114
    },
    {
      "clip_ratio/high_max": 0.0027543717005755752,
      "clip_ratio/high_mean": 0.0012179336099507054,
      "clip_ratio/low_mean": 0.001310126459429739,
      "clip_ratio/low_min": 0.00026240361603413476,
      "clip_ratio/region_mean": 0.0025280600166297518,
      "epoch": 0.010733306500067083,
      "grad_norm": 0.2247685343027115,
      "learning_rate": 2e-07,
      "loss": 0.0688,
      "step": 115
    },
    {
      "clip_ratio/high_max": 0.002797228764393367,
      "clip_ratio/high_mean": 0.0014182783925207332,
      "clip_ratio/low_mean": 0.001260365705093136,
      "clip_ratio/low_min": 0.00015520531178481178,
      "clip_ratio/region_mean": 0.0026786440357682295,
      "epoch": 0.010826639600067666,
      "grad_norm": 0.2570752501487732,
      "learning_rate": 2e-07,
      "loss": -0.0156,
      "step": 116
    },
    {
      "clip_ratio/high_max": 0.0026659176000976004,
      "clip_ratio/high_mean": 0.0013909117515140679,
      "clip_ratio/low_mean": 0.001155127742094919,
      "clip_ratio/low_min": 5.526294989977032e-05,
      "clip_ratio/region_mean": 0.0025460394681431353,
      "epoch": 0.01091997270006825,
      "grad_norm": 0.1940942108631134,
      "learning_rate": 2e-07,
      "loss": -0.0116,
      "step": 117
    },
    {
      "clip_ratio/high_max": 0.002885510170017369,
      "clip_ratio/high_mean": 0.0013137201385688968,
      "clip_ratio/low_mean": 0.0013080732351227198,
      "clip_ratio/low_min": 0.00019464237175270682,
      "clip_ratio/region_mean": 0.0026217933336738497,
      "epoch": 0.011013305800068833,
      "grad_norm": 0.18525971472263336,
      "learning_rate": 2e-07,
      "loss": 0.018,
      "step": 118
    },
    {
      "clip_ratio/high_max": 0.0029662559754797257,
      "clip_ratio/high_mean": 0.0013661800585396122,
      "clip_ratio/low_mean": 0.0011154318531225726,
      "clip_ratio/low_min": 1.9042744497710373e-05,
      "clip_ratio/region_mean": 0.0024816118166199885,
      "epoch": 0.011106638900069417,
      "grad_norm": 0.1879681497812271,
      "learning_rate": 2e-07,
      "loss": 0.0006,
      "step": 119
    },
    {
      "clip_ratio/high_max": 0.002786269164062105,
      "clip_ratio/high_mean": 0.001217325418110704,
      "clip_ratio/low_mean": 0.0014205829211277887,
      "clip_ratio/low_min": 0.00019812230584648205,
      "clip_ratio/region_mean": 0.002637908371980302,
      "epoch": 0.01119997200007,
      "grad_norm": 0.28733617067337036,
      "learning_rate": 2e-07,
      "loss": 0.0575,
      "step": 120
    },
    {
      "clip_ratio/high_max": 0.002727212238823995,
      "clip_ratio/high_mean": 0.0013546798982133623,
      "clip_ratio/low_mean": 0.0013883120300306473,
      "clip_ratio/low_min": 0.00026377217727713287,
      "clip_ratio/region_mean": 0.002742991920968052,
      "epoch": 0.011293305100070584,
      "grad_norm": 0.22074785828590393,
      "learning_rate": 2e-07,
      "loss": -0.006,
      "step": 121
    },
    {
      "clip_ratio/high_max": 0.0029078946536174044,
      "clip_ratio/high_mean": 0.0013981953234178945,
      "clip_ratio/low_mean": 0.0013565840417868458,
      "clip_ratio/low_min": 0.00022218512822291814,
      "clip_ratio/region_mean": 0.0027547793652047403,
      "epoch": 0.011386638200071167,
      "grad_norm": 0.19470542669296265,
      "learning_rate": 2e-07,
      "loss": -0.0086,
      "step": 122
    },
    {
      "clip_ratio/high_max": 0.0028591438531293534,
      "clip_ratio/high_mean": 0.0013676728012796957,
      "clip_ratio/low_mean": 0.0012662382287089713,
      "clip_ratio/low_min": 0.00018946400723507395,
      "clip_ratio/region_mean": 0.002633911033626646,
      "epoch": 0.011479971300071749,
      "grad_norm": 0.19274753332138062,
      "learning_rate": 2e-07,
      "loss": 0.0167,
      "step": 123
    },
    {
      "clip_ratio/high_max": 0.0029422046500258148,
      "clip_ratio/high_mean": 0.0013169669873605017,
      "clip_ratio/low_mean": 0.0013506649956980255,
      "clip_ratio/low_min": 0.00023921645424707094,
      "clip_ratio/region_mean": 0.0026676319976104423,
      "epoch": 0.011573304400072332,
      "grad_norm": 0.23007743060588837,
      "learning_rate": 2e-07,
      "loss": 0.0198,
      "step": 124
    },
    {
      "clip_ratio/high_max": 0.002652174654940609,
      "clip_ratio/high_mean": 0.0012871359722339548,
      "clip_ratio/low_mean": 0.0013283246153150685,
      "clip_ratio/low_min": 0.000243618713284377,
      "clip_ratio/region_mean": 0.0026154605802730657,
      "epoch": 0.011666637500072916,
      "grad_norm": 0.16703875362873077,
      "learning_rate": 2e-07,
      "loss": 0.0011,
      "step": 125
    },
    {
      "clip_ratio/high_max": 0.0029051582096144557,
      "clip_ratio/high_mean": 0.0012591703780344687,
      "clip_ratio/low_mean": 0.0014325643896881957,
      "clip_ratio/low_min": 0.0001781174023562926,
      "clip_ratio/region_mean": 0.002691734698601067,
      "epoch": 0.0117599706000735,
      "grad_norm": 0.22993162274360657,
      "learning_rate": 2e-07,
      "loss": 0.0398,
      "step": 126
    },
    {
      "clip_ratio/high_max": 0.0025598183419788256,
      "clip_ratio/high_mean": 0.0012333964768913575,
      "clip_ratio/low_mean": 0.0011834727411041968,
      "clip_ratio/low_min": 0.0001432362869309145,
      "clip_ratio/region_mean": 0.0024168692616513,
      "epoch": 0.011853303700074083,
      "grad_norm": 0.19572004675865173,
      "learning_rate": 2e-07,
      "loss": -0.0058,
      "step": 127
    },
    {
      "clip_ratio/high_max": 0.0031218914373312145,
      "clip_ratio/high_mean": 0.0014380813263414893,
      "clip_ratio/low_mean": 0.0013279849590617232,
      "clip_ratio/low_min": 0.00020982310161343776,
      "clip_ratio/region_mean": 0.0027660662817652337,
      "epoch": 0.011946636800074666,
      "grad_norm": 0.21303395926952362,
      "learning_rate": 2e-07,
      "loss": -0.0043,
      "step": 128
    },
    {
      "clip_ratio/high_max": 0.001784255731763551,
      "clip_ratio/high_mean": 0.0007330932057811879,
      "clip_ratio/low_mean": 0.0006113292001828086,
      "clip_ratio/low_min": 5.269098801363725e-05,
      "clip_ratio/region_mean": 0.001344422413239954,
      "completions/clipped_ratio": 0.014020647321428603,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4094.0,
      "completions/mean_length": 611.9296875,
      "completions/mean_terminated_length": 562.3861083984375,
      "completions/min_length": 53.0,
      "completions/min_terminated_length": 53.0,
      "epoch": 0.01203996990007525,
      "grad_norm": 0.12000353634357452,
      "learning_rate": 2e-07,
      "loss": 0.0347,
      "num_tokens": 162255295.0,
      "reward": 0.557076632976532,
      "reward_std": 0.2059343457221985,
      "rewards/simpleverify_reward/mean": 0.5570765733718872,
      "rewards/simpleverify_reward/std": 0.49673375487327576,
      "step": 129
    },
    {
      "clip_ratio/high_max": 0.002099405366607243,
      "clip_ratio/high_mean": 0.0008241080176958349,
      "clip_ratio/low_mean": 0.0005344934438653581,
      "clip_ratio/low_min": 4.057550813740818e-05,
      "clip_ratio/region_mean": 0.0013586014865722973,
      "epoch": 0.012133303000075833,
      "grad_norm": 0.11841220408678055,
      "learning_rate": 2e-07,
      "loss": 0.0357,
      "step": 130
    },
    {
      "clip_ratio/high_max": 0.001901704141346272,
      "clip_ratio/high_mean": 0.0008093671131064184,
      "clip_ratio/low_mean": 0.0005851987843925599,
      "clip_ratio/low_min": 5.283442442305386e-05,
      "clip_ratio/region_mean": 0.0013945658938609995,
      "epoch": 0.012226636100076417,
      "grad_norm": 6.780872344970703,
      "learning_rate": 2e-07,
      "loss": 0.0187,
      "step": 131
    },
    {
      "clip_ratio/high_max": 0.0022469941977760755,
      "clip_ratio/high_mean": 0.0008135619664244587,
      "clip_ratio/low_mean": 0.0005735903341701487,
      "clip_ratio/low_min": 4.25398102379404e-05,
      "clip_ratio/region_mean": 0.0013871522860426921,
      "epoch": 0.012319969200077,
      "grad_norm": 0.1178605929017067,
      "learning_rate": 2e-07,
      "loss": -0.0102,
      "step": 132
    },
    {
      "clip_ratio/high_max": 0.0020471107054618187,
      "clip_ratio/high_mean": 0.0008086670477496227,
      "clip_ratio/low_mean": 0.0004901428465018398,
      "clip_ratio/low_min": 2.6928429178951774e-05,
      "clip_ratio/region_mean": 0.0012988099042559043,
      "epoch": 0.012413302300077584,
      "grad_norm": 0.11176750063896179,
      "learning_rate": 2e-07,
      "loss": -0.0025,
      "step": 133
    },
    {
      "clip_ratio/high_max": 0.0017681449535302818,
      "clip_ratio/high_mean": 0.0007636647005710984,
      "clip_ratio/low_mean": 0.0006020760283718118,
      "clip_ratio/low_min": 1.3985231817059685e-05,
      "clip_ratio/region_mean": 0.0013657407362188678,
      "epoch": 0.012506635400078167,
      "grad_norm": 0.11252443492412567,
      "learning_rate": 2e-07,
      "loss": 0.0274,
      "step": 134
    },
    {
      "clip_ratio/high_max": 0.0018361956281296443,
      "clip_ratio/high_mean": 0.0007644933739356929,
      "clip_ratio/low_mean": 0.0006281385358306579,
      "clip_ratio/low_min": 4.9927264626603574e-05,
      "clip_ratio/region_mean": 0.0013926318824815098,
      "epoch": 0.01259996850007875,
      "grad_norm": 0.11987116932868958,
      "learning_rate": 2e-07,
      "loss": 0.0246,
      "step": 135
    },
    {
      "clip_ratio/high_max": 0.0019423902776907198,
      "clip_ratio/high_mean": 0.0008311068831972079,
      "clip_ratio/low_mean": 0.0005593588757619727,
      "clip_ratio/low_min": 9.836912431637757e-05,
      "clip_ratio/region_mean": 0.00139046576077817,
      "epoch": 0.012693301600079332,
      "grad_norm": 0.11899188905954361,
      "learning_rate": 2e-07,
      "loss": 0.0239,
      "step": 136
    },
    {
      "clip_ratio/high_max": 0.0020093353305128403,
      "clip_ratio/high_mean": 0.0007919129893707577,
      "clip_ratio/low_mean": 0.000594694507526583,
      "clip_ratio/low_min": 5.4855976486578584e-05,
      "clip_ratio/region_mean": 0.0013866074878023937,
      "epoch": 0.012786634700079916,
      "grad_norm": 0.12157698720693588,
      "learning_rate": 2e-07,
      "loss": 0.0142,
      "step": 137
    },
    {
      "clip_ratio/high_max": 0.0018474461394362152,
      "clip_ratio/high_mean": 0.0007798396964062704,
      "clip_ratio/low_mean": 0.0005679676087311236,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013478073306032456,
      "epoch": 0.0128799678000805,
      "grad_norm": 0.12331555038690567,
      "learning_rate": 2e-07,
      "loss": 0.0101,
      "step": 138
    },
    {
      "clip_ratio/high_max": 0.0017495603024144657,
      "clip_ratio/high_mean": 0.0007733914480922977,
      "clip_ratio/low_mean": 0.0005664287837134907,
      "clip_ratio/low_min": 1.3557483725890052e-05,
      "clip_ratio/region_mean": 0.0013398202245298307,
      "epoch": 0.012973300900081083,
      "grad_norm": 0.11285652220249176,
      "learning_rate": 2e-07,
      "loss": 0.0114,
      "step": 139
    },
    {
      "clip_ratio/high_max": 0.002214077645476209,
      "clip_ratio/high_mean": 0.0008908995805541053,
      "clip_ratio/low_mean": 0.0005530921607714845,
      "clip_ratio/low_min": 4.997755695512751e-05,
      "clip_ratio/region_mean": 0.0014439917504205368,
      "epoch": 0.013066634000081666,
      "grad_norm": 0.12912720441818237,
      "learning_rate": 2e-07,
      "loss": -0.0256,
      "step": 140
    },
    {
      "clip_ratio/high_max": 0.001933634397573769,
      "clip_ratio/high_mean": 0.0008633529432700016,
      "clip_ratio/low_mean": 0.0006306193026830442,
      "clip_ratio/low_min": 5.216099998506252e-05,
      "clip_ratio/region_mean": 0.001493972224125173,
      "epoch": 0.01315996710008225,
      "grad_norm": 0.12150504440069199,
      "learning_rate": 2e-07,
      "loss": 0.0459,
      "step": 141
    },
    {
      "clip_ratio/high_max": 0.002056179382634582,
      "clip_ratio/high_mean": 0.0008379270657314919,
      "clip_ratio/low_mean": 0.0005806022827528068,
      "clip_ratio/low_min": 2.367632168898126e-05,
      "clip_ratio/region_mean": 0.0014185293439368252,
      "epoch": 0.013253300200082833,
      "grad_norm": 0.13066498935222626,
      "learning_rate": 2e-07,
      "loss": 0.0426,
      "step": 142
    },
    {
      "clip_ratio/high_max": 0.0017760896917025093,
      "clip_ratio/high_mean": 0.0007030675151327159,
      "clip_ratio/low_mean": 0.0008029214277485153,
      "clip_ratio/low_min": 0.00010373762961535249,
      "clip_ratio/region_mean": 0.0015059889337862842,
      "epoch": 0.013346633300083417,
      "grad_norm": 0.11980723589658737,
      "learning_rate": 2e-07,
      "loss": 0.056,
      "step": 143
    },
    {
      "clip_ratio/high_max": 0.0019900166189472657,
      "clip_ratio/high_mean": 0.0008574035437050043,
      "clip_ratio/low_mean": 0.000552692679775646,
      "clip_ratio/low_min": 3.0324592898978153e-05,
      "clip_ratio/region_mean": 0.001410096236213576,
      "epoch": 0.013439966400084,
      "grad_norm": 0.10925982892513275,
      "learning_rate": 2e-07,
      "loss": 0.004,
      "step": 144
    },
    {
      "clip_ratio/high_max": 0.0017764489020919427,
      "clip_ratio/high_mean": 0.000811282296126592,
      "clip_ratio/low_mean": 0.000644706280581886,
      "clip_ratio/low_min": 4.615522448148113e-05,
      "clip_ratio/region_mean": 0.001455988545785658,
      "epoch": 0.013533299500084583,
      "grad_norm": 0.14364492893218994,
      "learning_rate": 2e-07,
      "loss": 0.0263,
      "step": 145
    },
    {
      "clip_ratio/high_max": 0.0018374718092672992,
      "clip_ratio/high_mean": 0.0007956195859151194,
      "clip_ratio/low_mean": 0.0006395709906428237,
      "clip_ratio/low_min": 6.809621663705911e-05,
      "clip_ratio/region_mean": 0.0014351905592775438,
      "epoch": 0.013626632600085167,
      "grad_norm": 0.12205006182193756,
      "learning_rate": 2e-07,
      "loss": 0.033,
      "step": 146
    },
    {
      "clip_ratio/high_max": 0.00192593449173728,
      "clip_ratio/high_mean": 0.0007942908159748185,
      "clip_ratio/low_mean": 0.0006335229209071258,
      "clip_ratio/low_min": 6.25474003754789e-05,
      "clip_ratio/region_mean": 0.0014278137605288066,
      "epoch": 0.01371996570008575,
      "grad_norm": 0.1163218766450882,
      "learning_rate": 2e-07,
      "loss": 0.0294,
      "step": 147
    },
    {
      "clip_ratio/high_max": 0.002195060260419268,
      "clip_ratio/high_mean": 0.0009122201390709961,
      "clip_ratio/low_mean": 0.0005158637350177742,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014280838549893815,
      "epoch": 0.013813298800086334,
      "grad_norm": 0.11541525274515152,
      "learning_rate": 2e-07,
      "loss": -0.0046,
      "step": 148
    },
    {
      "clip_ratio/high_max": 0.0020206489534757566,
      "clip_ratio/high_mean": 0.0007737030800853972,
      "clip_ratio/low_mean": 0.0005801492370665073,
      "clip_ratio/low_min": 3.292215751571348e-05,
      "clip_ratio/region_mean": 0.0013538523198803887,
      "epoch": 0.013906631900086916,
      "grad_norm": 0.11246857792139053,
      "learning_rate": 2e-07,
      "loss": 0.0041,
      "step": 149
    },
    {
      "clip_ratio/high_max": 0.0018048350248136558,
      "clip_ratio/high_mean": 0.000699517995599308,
      "clip_ratio/low_mean": 0.0006342549932014663,
      "clip_ratio/low_min": 2.725708964135265e-05,
      "clip_ratio/region_mean": 0.0013337729797058273,
      "epoch": 0.013999965000087499,
      "grad_norm": 0.11919964849948883,
      "learning_rate": 2e-07,
      "loss": 0.004,
      "step": 150
    },
    {
      "clip_ratio/high_max": 0.002169116876757471,
      "clip_ratio/high_mean": 0.0009271192247979343,
      "clip_ratio/low_mean": 0.0005849077242601197,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001512026967247948,
      "epoch": 0.014093298100088083,
      "grad_norm": 0.11215604096651077,
      "learning_rate": 2e-07,
      "loss": 0.0042,
      "step": 151
    },
    {
      "clip_ratio/high_max": 0.0017692481487756595,
      "clip_ratio/high_mean": 0.0007387256428046385,
      "clip_ratio/low_mean": 0.0005889445837965468,
      "clip_ratio/low_min": 1.3363267498789355e-05,
      "clip_ratio/region_mean": 0.0013276701720315032,
      "epoch": 0.014186631200088666,
      "grad_norm": 0.12634488940238953,
      "learning_rate": 2e-07,
      "loss": 0.0216,
      "step": 152
    },
    {
      "clip_ratio/high_max": 0.0023092168776202016,
      "clip_ratio/high_mean": 0.0009610258930479176,
      "clip_ratio/low_mean": 0.0005577738083957229,
      "clip_ratio/low_min": 1.2768130545737222e-05,
      "clip_ratio/region_mean": 0.001518799712357577,
      "epoch": 0.01427996430008925,
      "grad_norm": 0.12360531091690063,
      "learning_rate": 2e-07,
      "loss": -0.0018,
      "step": 153
    },
    {
      "clip_ratio/high_max": 0.002036969286564272,
      "clip_ratio/high_mean": 0.0007977804089023266,
      "clip_ratio/low_mean": 0.000683551774272928,
      "clip_ratio/low_min": 0.00014017854618941783,
      "clip_ratio/region_mean": 0.001481332212279085,
      "epoch": 0.014373297400089833,
      "grad_norm": 0.12436694651842117,
      "learning_rate": 2e-07,
      "loss": 0.0487,
      "step": 154
    },
    {
      "clip_ratio/high_max": 0.0018554799644334707,
      "clip_ratio/high_mean": 0.0007821693252481055,
      "clip_ratio/low_mean": 0.0006520995912069338,
      "clip_ratio/low_min": 1.504573901911499e-05,
      "clip_ratio/region_mean": 0.0014342689501063433,
      "epoch": 0.014466630500090416,
      "grad_norm": 0.13415321707725525,
      "learning_rate": 2e-07,
      "loss": 0.0595,
      "step": 155
    },
    {
      "clip_ratio/high_max": 0.0019837784639094025,
      "clip_ratio/high_mean": 0.0007853263778088149,
      "clip_ratio/low_mean": 0.000601817437200225,
      "clip_ratio/low_min": 4.322710810811259e-05,
      "clip_ratio/region_mean": 0.0013871437986381352,
      "epoch": 0.014559963600091,
      "grad_norm": 0.10944689810276031,
      "learning_rate": 2e-07,
      "loss": 0.0403,
      "step": 156
    },
    {
      "clip_ratio/high_max": 0.0019150325388181955,
      "clip_ratio/high_mean": 0.0008243473075708607,
      "clip_ratio/low_mean": 0.0006404053456208203,
      "clip_ratio/low_min": 5.4258492127701174e-05,
      "clip_ratio/region_mean": 0.0014647526768385433,
      "epoch": 0.014653296700091583,
      "grad_norm": 0.14248211681842804,
      "learning_rate": 2e-07,
      "loss": 0.0554,
      "step": 157
    },
    {
      "clip_ratio/high_max": 0.001759488815878285,
      "clip_ratio/high_mean": 0.0007669052720302716,
      "clip_ratio/low_mean": 0.000700808735928149,
      "clip_ratio/low_min": 6.52748140055337e-05,
      "clip_ratio/region_mean": 0.001467713991587516,
      "epoch": 0.014746629800092167,
      "grad_norm": 0.1275532841682434,
      "learning_rate": 2e-07,
      "loss": 0.059,
      "step": 158
    },
    {
      "clip_ratio/high_max": 0.0019940488346037455,
      "clip_ratio/high_mean": 0.0008210186497308314,
      "clip_ratio/low_mean": 0.0006319907206489006,
      "clip_ratio/low_min": 7.883350917836651e-05,
      "clip_ratio/region_mean": 0.0014530093831126578,
      "epoch": 0.01483996290009275,
      "grad_norm": 0.11434304714202881,
      "learning_rate": 2e-07,
      "loss": 0.0733,
      "step": 159
    },
    {
      "clip_ratio/high_max": 0.00192092436918756,
      "clip_ratio/high_mean": 0.0008790222673269454,
      "clip_ratio/low_mean": 0.00056511196817155,
      "clip_ratio/low_min": 4.336935035098577e-05,
      "clip_ratio/region_mean": 0.001444134279154241,
      "epoch": 0.014933296000093334,
      "grad_norm": 0.11234098672866821,
      "learning_rate": 2e-07,
      "loss": 0.034,
      "step": 160
    },
    {
      "clip_ratio/high_max": 0.0023246791679412127,
      "clip_ratio/high_mean": 0.0008866738226060988,
      "clip_ratio/low_mean": 0.000663228694065765,
      "clip_ratio/low_min": 0.00010616056715662125,
      "clip_ratio/region_mean": 0.001549902546685189,
      "epoch": 0.015026629100093917,
      "grad_norm": 0.1266254037618637,
      "learning_rate": 2e-07,
      "loss": 0.0478,
      "step": 161
    },
    {
      "clip_ratio/high_max": 0.001965323681361042,
      "clip_ratio/high_mean": 0.000820959572592983,
      "clip_ratio/low_mean": 0.0006965995326027041,
      "clip_ratio/low_min": 6.833672978245886e-05,
      "clip_ratio/region_mean": 0.0015175591324805282,
      "epoch": 0.015119962200094499,
      "grad_norm": 0.12695853412151337,
      "learning_rate": 2e-07,
      "loss": 0.0075,
      "step": 162
    },
    {
      "clip_ratio/high_max": 0.0021713865135097876,
      "clip_ratio/high_mean": 0.0009276664750359487,
      "clip_ratio/low_mean": 0.0005310947935868171,
      "clip_ratio/low_min": 6.268439938139636e-05,
      "clip_ratio/region_mean": 0.0014587612531613559,
      "epoch": 0.015213295300095082,
      "grad_norm": 0.12529891729354858,
      "learning_rate": 2e-07,
      "loss": 0.0053,
      "step": 163
    },
    {
      "clip_ratio/high_max": 0.0018675526880542748,
      "clip_ratio/high_mean": 0.0007227962632896379,
      "clip_ratio/low_mean": 0.0006287226315180305,
      "clip_ratio/low_min": 2.9932191864645574e-05,
      "clip_ratio/region_mean": 0.0013515188729797956,
      "epoch": 0.015306628400095666,
      "grad_norm": 0.12023717910051346,
      "learning_rate": 2e-07,
      "loss": 0.0749,
      "step": 164
    },
    {
      "clip_ratio/high_max": 0.002090888279781211,
      "clip_ratio/high_mean": 0.0008774506513873348,
      "clip_ratio/low_mean": 0.0005721439583794563,
      "clip_ratio/low_min": 2.457126356603112e-05,
      "clip_ratio/region_mean": 0.0014495946270471904,
      "epoch": 0.01539996150009625,
      "grad_norm": 0.11546096205711365,
      "learning_rate": 2e-07,
      "loss": 0.0076,
      "step": 165
    },
    {
      "clip_ratio/high_max": 0.0017688236985122785,
      "clip_ratio/high_mean": 0.0007386200277323951,
      "clip_ratio/low_mean": 0.0005452568257169332,
      "clip_ratio/low_min": 4.906442427454749e-05,
      "clip_ratio/region_mean": 0.0012838768343499396,
      "epoch": 0.015493294600096833,
      "grad_norm": 0.12498149275779724,
      "learning_rate": 2e-07,
      "loss": 0.0233,
      "step": 166
    },
    {
      "clip_ratio/high_max": 0.0017236603343917523,
      "clip_ratio/high_mean": 0.0007574530100100674,
      "clip_ratio/low_mean": 0.0005989382302686863,
      "clip_ratio/low_min": 7.755311025903211e-05,
      "clip_ratio/region_mean": 0.0013563912325480487,
      "epoch": 0.015586627700097416,
      "grad_norm": 0.12754815816879272,
      "learning_rate": 2e-07,
      "loss": 0.0157,
      "step": 167
    },
    {
      "clip_ratio/high_max": 0.002258755936054513,
      "clip_ratio/high_mean": 0.0008547649904357968,
      "clip_ratio/low_mean": 0.0006209034127095947,
      "clip_ratio/low_min": 2.3443568352377042e-05,
      "clip_ratio/region_mean": 0.0014756683995074127,
      "epoch": 0.015679960800098,
      "grad_norm": 0.14414598047733307,
      "learning_rate": 2e-07,
      "loss": 0.0245,
      "step": 168
    },
    {
      "clip_ratio/high_max": 0.001955513438588241,
      "clip_ratio/high_mean": 0.0008623196681583067,
      "clip_ratio/low_mean": 0.000602567555688438,
      "clip_ratio/low_min": 3.983179158240091e-05,
      "clip_ratio/region_mean": 0.0014648872165707871,
      "epoch": 0.015773293900098583,
      "grad_norm": 0.12495750188827515,
      "learning_rate": 2e-07,
      "loss": 0.0332,
      "step": 169
    },
    {
      "clip_ratio/high_max": 0.00223838776582852,
      "clip_ratio/high_mean": 0.0009298213062720606,
      "clip_ratio/low_mean": 0.0005195967887630104,
      "clip_ratio/low_min": 2.4004822989809327e-05,
      "clip_ratio/region_mean": 0.0014494181341433432,
      "epoch": 0.015866627000099165,
      "grad_norm": 0.11634866893291473,
      "learning_rate": 2e-07,
      "loss": -0.0111,
      "step": 170
    },
    {
      "clip_ratio/high_max": 0.0021104725237819366,
      "clip_ratio/high_mean": 0.0009034130289364839,
      "clip_ratio/low_mean": 0.0006394947768058046,
      "clip_ratio/low_min": 2.704045346035855e-05,
      "clip_ratio/region_mean": 0.0015429078266606666,
      "epoch": 0.01595996010009975,
      "grad_norm": 0.12048265337944031,
      "learning_rate": 2e-07,
      "loss": -0.0062,
      "step": 171
    },
    {
      "clip_ratio/high_max": 0.0020956102343916427,
      "clip_ratio/high_mean": 0.0008470688499073731,
      "clip_ratio/low_mean": 0.0005501982650457649,
      "clip_ratio/low_min": 1.2948000403412152e-05,
      "clip_ratio/region_mean": 0.0013972670894872863,
      "epoch": 0.016053293200100332,
      "grad_norm": 0.11529058963060379,
      "learning_rate": 2e-07,
      "loss": 0.0049,
      "step": 172
    },
    {
      "clip_ratio/high_max": 0.0017215226071130019,
      "clip_ratio/high_mean": 0.000741100457162247,
      "clip_ratio/low_mean": 0.0005466114726004889,
      "clip_ratio/low_min": 8.460390927211847e-05,
      "clip_ratio/region_mean": 0.0012877119443146512,
      "epoch": 0.016146626300100917,
      "grad_norm": 0.19731692969799042,
      "learning_rate": 2e-07,
      "loss": -0.0122,
      "step": 173
    },
    {
      "clip_ratio/high_max": 0.0020964827090210747,
      "clip_ratio/high_mean": 0.0008398496756854001,
      "clip_ratio/low_mean": 0.000642816225081333,
      "clip_ratio/low_min": 4.039527357235784e-05,
      "clip_ratio/region_mean": 0.0014826658516540192,
      "epoch": 0.0162399594001015,
      "grad_norm": 2.250884532928467,
      "learning_rate": 2e-07,
      "loss": 0.0139,
      "step": 174
    },
    {
      "clip_ratio/high_max": 0.0017920345781021751,
      "clip_ratio/high_mean": 0.0007806333560438361,
      "clip_ratio/low_mean": 0.0005344555156625574,
      "clip_ratio/low_min": 2.5148067834379617e-05,
      "clip_ratio/region_mean": 0.0013150888698874041,
      "epoch": 0.016333292500102084,
      "grad_norm": 0.11930711567401886,
      "learning_rate": 2e-07,
      "loss": 0.0729,
      "step": 175
    },
    {
      "clip_ratio/high_max": 0.0021007739487686194,
      "clip_ratio/high_mean": 0.0008999269703053869,
      "clip_ratio/low_mean": 0.0006451310036936775,
      "clip_ratio/low_min": 4.622362757800147e-05,
      "clip_ratio/region_mean": 0.0015450579521711916,
      "epoch": 0.016426625600102666,
      "grad_norm": 0.1278805285692215,
      "learning_rate": 2e-07,
      "loss": -0.0563,
      "step": 176
    },
    {
      "clip_ratio/high_max": 0.0018664096351130866,
      "clip_ratio/high_mean": 0.0008674918408360099,
      "clip_ratio/low_mean": 0.0006662578452960588,
      "clip_ratio/low_min": 9.164878065348603e-05,
      "clip_ratio/region_mean": 0.0015337497497966979,
      "epoch": 0.01651995870010325,
      "grad_norm": 0.1221580058336258,
      "learning_rate": 2e-07,
      "loss": 0.0413,
      "step": 177
    },
    {
      "clip_ratio/high_max": 0.0024445316157652996,
      "clip_ratio/high_mean": 0.00103787755506346,
      "clip_ratio/low_mean": 0.0004956101593052153,
      "clip_ratio/low_min": 2.184457662224304e-05,
      "clip_ratio/region_mean": 0.001533487724373117,
      "epoch": 0.016613291800103833,
      "grad_norm": 0.1286056935787201,
      "learning_rate": 2e-07,
      "loss": -0.01,
      "step": 178
    },
    {
      "clip_ratio/high_max": 0.002251833699119743,
      "clip_ratio/high_mean": 0.0008355304053111468,
      "clip_ratio/low_mean": 0.0006643825654464308,
      "clip_ratio/low_min": 9.426724409422604e-05,
      "clip_ratio/region_mean": 0.0014999129198258743,
      "epoch": 0.016706624900104418,
      "grad_norm": 0.1179148331284523,
      "learning_rate": 2e-07,
      "loss": 0.062,
      "step": 179
    },
    {
      "clip_ratio/high_max": 0.0020663910036091693,
      "clip_ratio/high_mean": 0.0008590448924223892,
      "clip_ratio/low_mean": 0.0006636037269345252,
      "clip_ratio/low_min": 4.826983877137536e-05,
      "clip_ratio/region_mean": 0.0015226486430037767,
      "epoch": 0.016799958000105,
      "grad_norm": 0.12851257622241974,
      "learning_rate": 2e-07,
      "loss": 0.0184,
      "step": 180
    },
    {
      "clip_ratio/high_max": 0.002138312134775333,
      "clip_ratio/high_mean": 0.000860536572872661,
      "clip_ratio/low_mean": 0.0006943785938346991,
      "clip_ratio/low_min": 9.249441563952132e-05,
      "clip_ratio/region_mean": 0.0015549151648883708,
      "epoch": 0.016893291100105585,
      "grad_norm": 0.12586717307567596,
      "learning_rate": 2e-07,
      "loss": 0.0697,
      "step": 181
    },
    {
      "clip_ratio/high_max": 0.001994305133848684,
      "clip_ratio/high_mean": 0.0008847359622450313,
      "clip_ratio/low_mean": 0.0006013852180331014,
      "clip_ratio/low_min": 2.4066374862741213e-05,
      "clip_ratio/region_mean": 0.0014861211602692492,
      "epoch": 0.016986624200106167,
      "grad_norm": 0.12542015314102173,
      "learning_rate": 2e-07,
      "loss": -0.0015,
      "step": 182
    },
    {
      "clip_ratio/high_max": 0.0021351301948016044,
      "clip_ratio/high_mean": 0.0008703667645022506,
      "clip_ratio/low_mean": 0.0005913864242756972,
      "clip_ratio/low_min": 2.936852160928538e-05,
      "clip_ratio/region_mean": 0.0014617531596741173,
      "epoch": 0.017079957300106748,
      "grad_norm": 0.12585563957691193,
      "learning_rate": 2e-07,
      "loss": 0.0139,
      "step": 183
    },
    {
      "clip_ratio/high_max": 0.001900650306197349,
      "clip_ratio/high_mean": 0.000849069129799318,
      "clip_ratio/low_mean": 0.0005743024203184177,
      "clip_ratio/low_min": 4.715670183941256e-05,
      "clip_ratio/region_mean": 0.0014233715446607675,
      "epoch": 0.017173290400107333,
      "grad_norm": 0.12186791747808456,
      "learning_rate": 2e-07,
      "loss": 0.0206,
      "step": 184
    },
    {
      "clip_ratio/high_max": 0.0019776165863731876,
      "clip_ratio/high_mean": 0.0007868615903134923,
      "clip_ratio/low_mean": 0.0005875941787962802,
      "clip_ratio/low_min": 5.011553002987057e-05,
      "clip_ratio/region_mean": 0.0013744557945756242,
      "epoch": 0.017266623500107915,
      "grad_norm": 0.10793115943670273,
      "learning_rate": 2e-07,
      "loss": 0.056,
      "step": 185
    },
    {
      "clip_ratio/high_max": 0.0021568940683209803,
      "clip_ratio/high_mean": 0.0009200328386214096,
      "clip_ratio/low_mean": 0.0006038145170350617,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0015238473424687982,
      "epoch": 0.0173599566001085,
      "grad_norm": 0.11519882082939148,
      "learning_rate": 2e-07,
      "loss": -0.0292,
      "step": 186
    },
    {
      "clip_ratio/high_max": 0.0019966778563684784,
      "clip_ratio/high_mean": 0.0008219665505748708,
      "clip_ratio/low_mean": 0.0006578429274668451,
      "clip_ratio/low_min": 8.048551444517216e-05,
      "clip_ratio/region_mean": 0.0014798094925936311,
      "epoch": 0.017453289700109082,
      "grad_norm": 0.1287655085325241,
      "learning_rate": 2e-07,
      "loss": 0.0465,
      "step": 187
    },
    {
      "clip_ratio/high_max": 0.0021091887829243205,
      "clip_ratio/high_mean": 0.0008488497842336074,
      "clip_ratio/low_mean": 0.0006047210217730026,
      "clip_ratio/low_min": 2.9717120924033225e-05,
      "clip_ratio/region_mean": 0.0014535707741742954,
      "epoch": 0.017546622800109667,
      "grad_norm": 0.12241791933774948,
      "learning_rate": 2e-07,
      "loss": 0.029,
      "step": 188
    },
    {
      "clip_ratio/high_max": 0.0023509508682764135,
      "clip_ratio/high_mean": 0.0008480851465719752,
      "clip_ratio/low_mean": 0.0007244535954669118,
      "clip_ratio/low_min": 3.68049904864165e-05,
      "clip_ratio/region_mean": 0.0015725387493148446,
      "epoch": 0.01763995590011025,
      "grad_norm": 0.1332457959651947,
      "learning_rate": 2e-07,
      "loss": 0.046,
      "step": 189
    },
    {
      "clip_ratio/high_max": 0.0018754965713014826,
      "clip_ratio/high_mean": 0.0008037635889195371,
      "clip_ratio/low_mean": 0.0005728645019189571,
      "clip_ratio/low_min": 3.0046778192627244e-05,
      "clip_ratio/region_mean": 0.0013766280790150631,
      "epoch": 0.017733289000110834,
      "grad_norm": 0.1131281703710556,
      "learning_rate": 2e-07,
      "loss": -0.0006,
      "step": 190
    },
    {
      "clip_ratio/high_max": 0.0019312634904053994,
      "clip_ratio/high_mean": 0.0008665046079840977,
      "clip_ratio/low_mean": 0.0005508429767360212,
      "clip_ratio/low_min": 1.4019739865034353e-05,
      "clip_ratio/region_mean": 0.0014173475792631507,
      "epoch": 0.017826622100111416,
      "grad_norm": 0.11831708252429962,
      "learning_rate": 2e-07,
      "loss": 0.0125,
      "step": 191
    },
    {
      "clip_ratio/high_max": 0.0016764222746132873,
      "clip_ratio/high_mean": 0.0007296729600057006,
      "clip_ratio/low_mean": 0.0006575298739335267,
      "clip_ratio/low_min": 6.532936185976723e-05,
      "clip_ratio/region_mean": 0.0013872028393961955,
      "epoch": 0.017919955200112,
      "grad_norm": 0.10915565490722656,
      "learning_rate": 2e-07,
      "loss": 0.0278,
      "step": 192
    },
    {
      "clip_ratio/high_max": 0.0020736096957989503,
      "clip_ratio/high_mean": 0.0008751838431635406,
      "clip_ratio/low_mean": 0.0006219078331923811,
      "clip_ratio/low_min": 5.614155998046044e-05,
      "clip_ratio/region_mean": 0.0014970917254686356,
      "epoch": 0.018013288300112583,
      "grad_norm": 0.12327812612056732,
      "learning_rate": 2e-07,
      "loss": 0.0206,
      "step": 193
    },
    {
      "clip_ratio/high_max": 0.0019329669885337353,
      "clip_ratio/high_mean": 0.0008085431254585274,
      "clip_ratio/low_mean": 0.0005968813748040702,
      "clip_ratio/low_min": 6.745711471012328e-05,
      "clip_ratio/region_mean": 0.0014054245002625976,
      "epoch": 0.018106621400113165,
      "grad_norm": 0.10631323605775833,
      "learning_rate": 2e-07,
      "loss": 0.0183,
      "step": 194
    },
    {
      "clip_ratio/high_max": 0.0019297026810818352,
      "clip_ratio/high_mean": 0.0008301530360768083,
      "clip_ratio/low_mean": 0.0005512141869985498,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013813671976095065,
      "epoch": 0.01819995450011375,
      "grad_norm": 0.11766605079174042,
      "learning_rate": 2e-07,
      "loss": 0.0104,
      "step": 195
    },
    {
      "clip_ratio/high_max": 0.0018602242234919686,
      "clip_ratio/high_mean": 0.0007717592852714006,
      "clip_ratio/low_mean": 0.000565861793802469,
      "clip_ratio/low_min": 2.5805120458244346e-05,
      "clip_ratio/region_mean": 0.0013376210663409438,
      "epoch": 0.01829328760011433,
      "grad_norm": 0.11108557134866714,
      "learning_rate": 2e-07,
      "loss": 0.0552,
      "step": 196
    },
    {
      "clip_ratio/high_max": 0.0018241533398395404,
      "clip_ratio/high_mean": 0.0007565808900835691,
      "clip_ratio/low_mean": 0.0005454191395983798,
      "clip_ratio/low_min": 6.979340923862765e-06,
      "clip_ratio/region_mean": 0.0013020000369579066,
      "epoch": 0.018386620700114917,
      "grad_norm": 0.11559087038040161,
      "learning_rate": 2e-07,
      "loss": -0.0046,
      "step": 197
    },
    {
      "clip_ratio/high_max": 0.0016000511604943313,
      "clip_ratio/high_mean": 0.0007448696287610801,
      "clip_ratio/low_mean": 0.000572046064917231,
      "clip_ratio/low_min": 6.896324248373276e-05,
      "clip_ratio/region_mean": 0.0013169156518415548,
      "epoch": 0.0184799538001155,
      "grad_norm": 0.11472797393798828,
      "learning_rate": 2e-07,
      "loss": 0.0171,
      "step": 198
    },
    {
      "clip_ratio/high_max": 0.0018787748158501927,
      "clip_ratio/high_mean": 0.000733202389710641,
      "clip_ratio/low_mean": 0.0007538214013038669,
      "clip_ratio/low_min": 4.63871319880127e-05,
      "clip_ratio/region_mean": 0.001487023735535331,
      "epoch": 0.018573286900116084,
      "grad_norm": 0.11530959606170654,
      "learning_rate": 2e-07,
      "loss": 0.0682,
      "step": 199
    },
    {
      "clip_ratio/high_max": 0.002174064182327129,
      "clip_ratio/high_mean": 0.0008117097750073299,
      "clip_ratio/low_mean": 0.0005790070249531709,
      "clip_ratio/low_min": 1.6009220416890457e-05,
      "clip_ratio/region_mean": 0.0013907168176956475,
      "epoch": 0.018666620000116665,
      "grad_norm": 0.13620182871818542,
      "learning_rate": 2e-07,
      "loss": 0.0161,
      "step": 200
    },
    {
      "clip_ratio/high_max": 0.0022332727239700034,
      "clip_ratio/high_mean": 0.0008888625179679366,
      "clip_ratio/low_mean": 0.0006720081582898274,
      "clip_ratio/low_min": 4.810716382053215e-05,
      "clip_ratio/region_mean": 0.0015608706744387746,
      "epoch": 0.01875995310011725,
      "grad_norm": 0.1197165995836258,
      "learning_rate": 2e-07,
      "loss": 0.0713,
      "step": 201
    },
    {
      "clip_ratio/high_max": 0.0021171529006096534,
      "clip_ratio/high_mean": 0.0009134918227573507,
      "clip_ratio/low_mean": 0.0006080609291529981,
      "clip_ratio/low_min": 4.032635115436278e-05,
      "clip_ratio/region_mean": 0.0015215527782856952,
      "epoch": 0.018853286200117832,
      "grad_norm": 0.12558649480342865,
      "learning_rate": 2e-07,
      "loss": 0.057,
      "step": 202
    },
    {
      "clip_ratio/high_max": 0.001816671861888608,
      "clip_ratio/high_mean": 0.0007296011772268685,
      "clip_ratio/low_mean": 0.0006923889523022808,
      "clip_ratio/low_min": 7.941850981296739e-05,
      "clip_ratio/region_mean": 0.0014219901386240963,
      "epoch": 0.018946619300118418,
      "grad_norm": 0.11568861454725266,
      "learning_rate": 2e-07,
      "loss": 0.0494,
      "step": 203
    },
    {
      "clip_ratio/high_max": 0.0021382658305810764,
      "clip_ratio/high_mean": 0.0008898287469492061,
      "clip_ratio/low_mean": 0.0005603459685517009,
      "clip_ratio/low_min": 6.999934339546598e-05,
      "clip_ratio/region_mean": 0.0014501747136819176,
      "epoch": 0.019039952400119,
      "grad_norm": 0.11714370548725128,
      "learning_rate": 2e-07,
      "loss": 0.0178,
      "step": 204
    },
    {
      "clip_ratio/high_max": 0.00179005935206078,
      "clip_ratio/high_mean": 0.00077575969407917,
      "clip_ratio/low_mean": 0.0006000151151965838,
      "clip_ratio/low_min": 7.392168663500343e-05,
      "clip_ratio/region_mean": 0.0013757748165517114,
      "epoch": 0.019133285500119585,
      "grad_norm": 0.125470370054245,
      "learning_rate": 2e-07,
      "loss": 0.0517,
      "step": 205
    },
    {
      "clip_ratio/high_max": 0.001654505012993468,
      "clip_ratio/high_mean": 0.0007185303638834739,
      "clip_ratio/low_mean": 0.0006323754241748247,
      "clip_ratio/low_min": 5.656904886564007e-05,
      "clip_ratio/region_mean": 0.0013509057862393092,
      "epoch": 0.019226618600120166,
      "grad_norm": 0.11505354195833206,
      "learning_rate": 2e-07,
      "loss": 0.0449,
      "step": 206
    },
    {
      "clip_ratio/high_max": 0.0017064742241927888,
      "clip_ratio/high_mean": 0.0007828243415133329,
      "clip_ratio/low_mean": 0.0006331469085125718,
      "clip_ratio/low_min": 6.827588549640495e-05,
      "clip_ratio/region_mean": 0.001415971255482873,
      "epoch": 0.019319951700120748,
      "grad_norm": 0.10872121155261993,
      "learning_rate": 2e-07,
      "loss": 0.0203,
      "step": 207
    },
    {
      "clip_ratio/high_max": 0.0020829406639677472,
      "clip_ratio/high_mean": 0.0009138266286754515,
      "clip_ratio/low_mean": 0.0005890915581403533,
      "clip_ratio/low_min": 1.3334755749383476e-05,
      "clip_ratio/region_mean": 0.001502918174082879,
      "epoch": 0.019413284800121333,
      "grad_norm": 0.11202314496040344,
      "learning_rate": 2e-07,
      "loss": 0.0047,
      "step": 208
    },
    {
      "clip_ratio/high_max": 0.002092193597491132,
      "clip_ratio/high_mean": 0.0007727962038188707,
      "clip_ratio/low_mean": 0.0005881238721485715,
      "clip_ratio/low_min": 1.8502072634873912e-05,
      "clip_ratio/region_mean": 0.0013609200468636118,
      "epoch": 0.019506617900121915,
      "grad_norm": 0.12486797571182251,
      "learning_rate": 2e-07,
      "loss": 0.0047,
      "step": 209
    },
    {
      "clip_ratio/high_max": 0.0021771567699033767,
      "clip_ratio/high_mean": 0.0008790578212938271,
      "clip_ratio/low_mean": 0.0006164459973660996,
      "clip_ratio/low_min": 5.278173648548545e-05,
      "clip_ratio/region_mean": 0.0014955038495827466,
      "epoch": 0.0195999510001225,
      "grad_norm": 0.12480311095714569,
      "learning_rate": 2e-07,
      "loss": 0.0349,
      "step": 210
    },
    {
      "clip_ratio/high_max": 0.002391279565927107,
      "clip_ratio/high_mean": 0.0008715305011719465,
      "clip_ratio/low_mean": 0.0006326712973532267,
      "clip_ratio/low_min": 2.483539628883591e-05,
      "clip_ratio/region_mean": 0.0015042017912492156,
      "epoch": 0.019693284100123082,
      "grad_norm": 0.12396135181188583,
      "learning_rate": 2e-07,
      "loss": -0.0096,
      "step": 211
    },
    {
      "clip_ratio/high_max": 0.001972062160348287,
      "clip_ratio/high_mean": 0.000841363966173958,
      "clip_ratio/low_mean": 0.0005959939471722464,
      "clip_ratio/low_min": 2.3692191462032497e-05,
      "clip_ratio/region_mean": 0.001437357896065805,
      "epoch": 0.019786617200123667,
      "grad_norm": 0.12970447540283203,
      "learning_rate": 2e-07,
      "loss": 0.0062,
      "step": 212
    },
    {
      "clip_ratio/high_max": 0.0020741428234032355,
      "clip_ratio/high_mean": 0.0009173517100862227,
      "clip_ratio/low_mean": 0.0006286472653300734,
      "clip_ratio/low_min": 5.0465879212424625e-05,
      "clip_ratio/region_mean": 0.0015459989808732644,
      "epoch": 0.01987995030012425,
      "grad_norm": 0.1226431280374527,
      "learning_rate": 2e-07,
      "loss": 0.0055,
      "step": 213
    },
    {
      "clip_ratio/high_max": 0.0019818857763311826,
      "clip_ratio/high_mean": 0.0008492987453792011,
      "clip_ratio/low_mean": 0.000629013577963633,
      "clip_ratio/low_min": 4.6589530938945245e-05,
      "clip_ratio/region_mean": 0.001478312329709297,
      "epoch": 0.019973283400124834,
      "grad_norm": 0.11172264814376831,
      "learning_rate": 2e-07,
      "loss": 0.0389,
      "step": 214
    },
    {
      "clip_ratio/high_max": 0.002069979236694053,
      "clip_ratio/high_mean": 0.000865060013893526,
      "clip_ratio/low_mean": 0.0005486258087330498,
      "clip_ratio/low_min": 2.34817125601694e-05,
      "clip_ratio/region_mean": 0.0014136857935227454,
      "epoch": 0.020066616500125416,
      "grad_norm": 0.12068255990743637,
      "learning_rate": 2e-07,
      "loss": 0.0359,
      "step": 215
    },
    {
      "clip_ratio/high_max": 0.0019663180137285963,
      "clip_ratio/high_mean": 0.0008473750822304282,
      "clip_ratio/low_mean": 0.0007438137436110992,
      "clip_ratio/low_min": 7.713813101872802e-05,
      "clip_ratio/region_mean": 0.0015911888549453579,
      "epoch": 0.020159949600126,
      "grad_norm": 0.12602101266384125,
      "learning_rate": 2e-07,
      "loss": 0.0466,
      "step": 216
    },
    {
      "clip_ratio/high_max": 0.0020827313237532508,
      "clip_ratio/high_mean": 0.0008149411751219304,
      "clip_ratio/low_mean": 0.0005110658830744796,
      "clip_ratio/low_min": 3.48286448570434e-05,
      "clip_ratio/region_mean": 0.0013260070591059048,
      "epoch": 0.020253282700126583,
      "grad_norm": 0.11434406042098999,
      "learning_rate": 2e-07,
      "loss": -0.0277,
      "step": 217
    },
    {
      "clip_ratio/high_max": 0.0019906498891941737,
      "clip_ratio/high_mean": 0.0009144391351583181,
      "clip_ratio/low_mean": 0.0006791747746319743,
      "clip_ratio/low_min": 1.315789450018201e-05,
      "clip_ratio/region_mean": 0.0015936139388941228,
      "epoch": 0.020346615800127168,
      "grad_norm": 0.12674777209758759,
      "learning_rate": 2e-07,
      "loss": 0.0021,
      "step": 218
    },
    {
      "clip_ratio/high_max": 0.0018587054801173508,
      "clip_ratio/high_mean": 0.0008060272903094301,
      "clip_ratio/low_mean": 0.0007025926606729627,
      "clip_ratio/low_min": 5.370995995690464e-05,
      "clip_ratio/region_mean": 0.0015086199418874457,
      "epoch": 0.02043994890012775,
      "grad_norm": 0.11981428414583206,
      "learning_rate": 2e-07,
      "loss": 0.048,
      "step": 219
    },
    {
      "clip_ratio/high_max": 0.002145351372746518,
      "clip_ratio/high_mean": 0.0009035408475028817,
      "clip_ratio/low_mean": 0.0006624667430514819,
      "clip_ratio/low_min": 3.271596688136924e-05,
      "clip_ratio/region_mean": 0.0015660075914638583,
      "epoch": 0.02053328200012833,
      "grad_norm": 0.12608177959918976,
      "learning_rate": 2e-07,
      "loss": -0.0036,
      "step": 220
    },
    {
      "clip_ratio/high_max": 0.0023064735723892227,
      "clip_ratio/high_mean": 0.0009404887641721871,
      "clip_ratio/low_mean": 0.0006884559879836161,
      "clip_ratio/low_min": 2.2530487967742374e-05,
      "clip_ratio/region_mean": 0.0016289447667077184,
      "epoch": 0.020626615100128916,
      "grad_norm": 0.13023404777050018,
      "learning_rate": 2e-07,
      "loss": 0.0106,
      "step": 221
    },
    {
      "clip_ratio/high_max": 0.0019826841926260386,
      "clip_ratio/high_mean": 0.0008284481846203562,
      "clip_ratio/low_mean": 0.0006198056271387031,
      "clip_ratio/low_min": 7.347455539274961e-05,
      "clip_ratio/region_mean": 0.001448253788112197,
      "epoch": 0.020719948200129498,
      "grad_norm": 0.130168154835701,
      "learning_rate": 2e-07,
      "loss": 0.0399,
      "step": 222
    },
    {
      "clip_ratio/high_max": 0.0017674262198852375,
      "clip_ratio/high_mean": 0.0007272366019606125,
      "clip_ratio/low_mean": 0.0005965747932350496,
      "clip_ratio/low_min": 2.0964268514944706e-05,
      "clip_ratio/region_mean": 0.0013238114006526303,
      "epoch": 0.020813281300130083,
      "grad_norm": 0.12362027168273926,
      "learning_rate": 2e-07,
      "loss": 0.0214,
      "step": 223
    },
    {
      "clip_ratio/high_max": 0.001974437616809155,
      "clip_ratio/high_mean": 0.0008042374165597721,
      "clip_ratio/low_mean": 0.0005606582571999752,
      "clip_ratio/low_min": 2.183406104450114e-05,
      "clip_ratio/region_mean": 0.0013648956883116625,
      "epoch": 0.020906614400130665,
      "grad_norm": 0.12424493581056595,
      "learning_rate": 2e-07,
      "loss": -0.006,
      "step": 224
    },
    {
      "clip_ratio/high_max": 0.0022053325810702518,
      "clip_ratio/high_mean": 0.0009020308098115493,
      "clip_ratio/low_mean": 0.0006508156320705893,
      "clip_ratio/low_min": 6.897086586832302e-05,
      "clip_ratio/region_mean": 0.0015528464136878029,
      "epoch": 0.02099994750013125,
      "grad_norm": 0.1252783089876175,
      "learning_rate": 2e-07,
      "loss": 0.0173,
      "step": 225
    },
    {
      "clip_ratio/high_max": 0.0017065121937775984,
      "clip_ratio/high_mean": 0.0006967523586354218,
      "clip_ratio/low_mean": 0.0007028692743915599,
      "clip_ratio/low_min": 7.727163165327511e-05,
      "clip_ratio/region_mean": 0.0013996216148370877,
      "epoch": 0.021093280600131832,
      "grad_norm": 0.12578731775283813,
      "learning_rate": 2e-07,
      "loss": 0.0664,
      "step": 226
    },
    {
      "clip_ratio/high_max": 0.0019523410956026055,
      "clip_ratio/high_mean": 0.0008163893962773727,
      "clip_ratio/low_mean": 0.0006067543345125159,
      "clip_ratio/low_min": 2.7364272682461888e-05,
      "clip_ratio/region_mean": 0.001423143741703825,
      "epoch": 0.021186613700132417,
      "grad_norm": 0.116533063352108,
      "learning_rate": 2e-07,
      "loss": 0.0355,
      "step": 227
    },
    {
      "clip_ratio/high_max": 0.0020167624861642253,
      "clip_ratio/high_mean": 0.0008077914826571941,
      "clip_ratio/low_mean": 0.0007490758625863236,
      "clip_ratio/low_min": 9.619301545171766e-05,
      "clip_ratio/region_mean": 0.0015568673479720019,
      "epoch": 0.021279946800133,
      "grad_norm": 0.12544459104537964,
      "learning_rate": 2e-07,
      "loss": 0.0459,
      "step": 228
    },
    {
      "clip_ratio/high_max": 0.002426959756121505,
      "clip_ratio/high_mean": 0.0010647100280039012,
      "clip_ratio/low_mean": 0.0007087066551321186,
      "clip_ratio/low_min": 5.299648728396278e-05,
      "clip_ratio/region_mean": 0.0017734167122398503,
      "epoch": 0.021373279900133584,
      "grad_norm": 0.1109149381518364,
      "learning_rate": 2e-07,
      "loss": -0.0055,
      "step": 229
    },
    {
      "clip_ratio/high_max": 0.0021228285440884065,
      "clip_ratio/high_mean": 0.0009695321532490198,
      "clip_ratio/low_mean": 0.0006713399761792971,
      "clip_ratio/low_min": 9.498201325186528e-05,
      "clip_ratio/region_mean": 0.001640872153075179,
      "epoch": 0.021466613000134166,
      "grad_norm": 0.1239905133843422,
      "learning_rate": 2e-07,
      "loss": -0.0334,
      "step": 230
    },
    {
      "clip_ratio/high_max": 0.002044136206677649,
      "clip_ratio/high_mean": 0.000907914338313276,
      "clip_ratio/low_mean": 0.0005890498614462558,
      "clip_ratio/low_min": 7.365920646407176e-05,
      "clip_ratio/region_mean": 0.0014969642215874046,
      "epoch": 0.02155994610013475,
      "grad_norm": 0.14024090766906738,
      "learning_rate": 2e-07,
      "loss": -0.0074,
      "step": 231
    },
    {
      "clip_ratio/high_max": 0.002295651338499738,
      "clip_ratio/high_mean": 0.0008678561080159852,
      "clip_ratio/low_mean": 0.0006381597686413443,
      "clip_ratio/low_min": 2.9640562388522085e-05,
      "clip_ratio/region_mean": 0.001506015865743393,
      "epoch": 0.021653279200135333,
      "grad_norm": 0.12719973921775818,
      "learning_rate": 2e-07,
      "loss": 0.0464,
      "step": 232
    },
    {
      "clip_ratio/high_max": 0.0018199050609837286,
      "clip_ratio/high_mean": 0.0007057171333144652,
      "clip_ratio/low_mean": 0.0005441948096631677,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012499119475251064,
      "epoch": 0.021746612300135915,
      "grad_norm": 0.11361807584762573,
      "learning_rate": 2e-07,
      "loss": 0.0467,
      "step": 233
    },
    {
      "clip_ratio/high_max": 0.0018442862856318243,
      "clip_ratio/high_mean": 0.0008334170324815204,
      "clip_ratio/low_mean": 0.0006894128564454149,
      "clip_ratio/low_min": 5.868424705113284e-05,
      "clip_ratio/region_mean": 0.0015228298907459248,
      "epoch": 0.0218399454001365,
      "grad_norm": 0.11941342800855637,
      "learning_rate": 2e-07,
      "loss": 0.034,
      "step": 234
    },
    {
      "clip_ratio/high_max": 0.0023222617237479426,
      "clip_ratio/high_mean": 0.0008665252553328173,
      "clip_ratio/low_mean": 0.0006782530235796003,
      "clip_ratio/low_min": 5.201616841077339e-05,
      "clip_ratio/region_mean": 0.0015447782752744388,
      "epoch": 0.02193327850013708,
      "grad_norm": 0.12980884313583374,
      "learning_rate": 2e-07,
      "loss": 0.0232,
      "step": 235
    },
    {
      "clip_ratio/high_max": 0.002173518791096285,
      "clip_ratio/high_mean": 0.0008693928975844756,
      "clip_ratio/low_mean": 0.0005926298354097526,
      "clip_ratio/low_min": 3.802351511694724e-05,
      "clip_ratio/region_mean": 0.0014620227375417016,
      "epoch": 0.022026611600137667,
      "grad_norm": 0.11835992336273193,
      "learning_rate": 2e-07,
      "loss": 0.007,
      "step": 236
    },
    {
      "clip_ratio/high_max": 0.002036824640526902,
      "clip_ratio/high_mean": 0.0008447859781881562,
      "clip_ratio/low_mean": 0.0005561790476349415,
      "clip_ratio/low_min": 3.0056125979172066e-05,
      "clip_ratio/region_mean": 0.001400965040375013,
      "epoch": 0.02211994470013825,
      "grad_norm": 0.12677739560604095,
      "learning_rate": 2e-07,
      "loss": 0.0413,
      "step": 237
    },
    {
      "clip_ratio/high_max": 0.002024779278144706,
      "clip_ratio/high_mean": 0.0008605479779362213,
      "clip_ratio/low_mean": 0.000603546957790968,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014640948866144754,
      "epoch": 0.022213277800138834,
      "grad_norm": 0.12738028168678284,
      "learning_rate": 2e-07,
      "loss": 0.003,
      "step": 238
    },
    {
      "clip_ratio/high_max": 0.0022869312233524397,
      "clip_ratio/high_mean": 0.0009744043636601418,
      "clip_ratio/low_mean": 0.0006235647360881558,
      "clip_ratio/low_min": 8.00459529273212e-05,
      "clip_ratio/region_mean": 0.0015979691233951598,
      "epoch": 0.022306610900139415,
      "grad_norm": 0.11834923923015594,
      "learning_rate": 2e-07,
      "loss": 0.0093,
      "step": 239
    },
    {
      "clip_ratio/high_max": 0.002176742971641943,
      "clip_ratio/high_mean": 0.0009521244392090011,
      "clip_ratio/low_mean": 0.0006671634837402962,
      "clip_ratio/low_min": 1.589117709954735e-05,
      "clip_ratio/region_mean": 0.0016192878865695093,
      "epoch": 0.02239994400014,
      "grad_norm": 0.11782267689704895,
      "learning_rate": 2e-07,
      "loss": 0.0234,
      "step": 240
    },
    {
      "clip_ratio/high_max": 0.0018703921305132098,
      "clip_ratio/high_mean": 0.0007780053701935685,
      "clip_ratio/low_mean": 0.0006393818130163709,
      "clip_ratio/low_min": 3.492377709335415e-05,
      "clip_ratio/region_mean": 0.0014173871895764023,
      "epoch": 0.022493277100140582,
      "grad_norm": 0.12588801980018616,
      "learning_rate": 2e-07,
      "loss": 0.0652,
      "step": 241
    },
    {
      "clip_ratio/high_max": 0.0018498727258702274,
      "clip_ratio/high_mean": 0.0008320328215631889,
      "clip_ratio/low_mean": 0.0006495431707662647,
      "clip_ratio/low_min": 2.240544927190058e-05,
      "clip_ratio/region_mean": 0.0014815760077908635,
      "epoch": 0.022586610200141168,
      "grad_norm": 0.12297002971172333,
      "learning_rate": 2e-07,
      "loss": 0.0517,
      "step": 242
    },
    {
      "clip_ratio/high_max": 0.0025394732219865546,
      "clip_ratio/high_mean": 0.0009917907082126476,
      "clip_ratio/low_mean": 0.0006418006814783439,
      "clip_ratio/low_min": 1.5122187505767215e-05,
      "clip_ratio/region_mean": 0.0016335914115188643,
      "epoch": 0.02267994330014175,
      "grad_norm": 0.1303921788930893,
      "learning_rate": 2e-07,
      "loss": 0.0123,
      "step": 243
    },
    {
      "clip_ratio/high_max": 0.0018134244055545423,
      "clip_ratio/high_mean": 0.0008182700239558471,
      "clip_ratio/low_mean": 0.0006754147943865974,
      "clip_ratio/low_min": 7.968447880557505e-05,
      "clip_ratio/region_mean": 0.0014936848237994127,
      "epoch": 0.022773276400142334,
      "grad_norm": 0.11415337771177292,
      "learning_rate": 2e-07,
      "loss": 0.065,
      "step": 244
    },
    {
      "clip_ratio/high_max": 0.0019734601955860853,
      "clip_ratio/high_mean": 0.0007973790052346885,
      "clip_ratio/low_mean": 0.0007755887327220989,
      "clip_ratio/low_min": 0.00012020656322420109,
      "clip_ratio/region_mean": 0.0015729677324998192,
      "epoch": 0.022866609500142916,
      "grad_norm": 0.12819279730319977,
      "learning_rate": 2e-07,
      "loss": 0.0787,
      "step": 245
    },
    {
      "clip_ratio/high_max": 0.0021143411067896523,
      "clip_ratio/high_mean": 0.0008259684655058663,
      "clip_ratio/low_mean": 0.0007045072779874317,
      "clip_ratio/low_min": 2.680677607713733e-05,
      "clip_ratio/region_mean": 0.0015304757507692557,
      "epoch": 0.022959942600143498,
      "grad_norm": 0.11841915547847748,
      "learning_rate": 2e-07,
      "loss": 0.0555,
      "step": 246
    },
    {
      "clip_ratio/high_max": 0.00227278806414688,
      "clip_ratio/high_mean": 0.0009006211002997588,
      "clip_ratio/low_mean": 0.0006637595542997587,
      "clip_ratio/low_min": 1.3397641851042863e-05,
      "clip_ratio/region_mean": 0.0015643806364096235,
      "epoch": 0.023053275700144083,
      "grad_norm": 0.13094264268875122,
      "learning_rate": 2e-07,
      "loss": 0.001,
      "step": 247
    },
    {
      "clip_ratio/high_max": 0.0017917007025971543,
      "clip_ratio/high_mean": 0.0008561914746678667,
      "clip_ratio/low_mean": 0.0006776778118364746,
      "clip_ratio/low_min": 9.029080320033245e-05,
      "clip_ratio/region_mean": 0.0015338692792283837,
      "epoch": 0.023146608800144665,
      "grad_norm": 0.13803403079509735,
      "learning_rate": 2e-07,
      "loss": 0.0164,
      "step": 248
    },
    {
      "clip_ratio/high_max": 0.002043408567260485,
      "clip_ratio/high_mean": 0.0009841881419561105,
      "clip_ratio/low_mean": 0.0006766336173313903,
      "clip_ratio/low_min": 3.073063726333203e-05,
      "clip_ratio/region_mean": 0.001660821755649522,
      "epoch": 0.02323994190014525,
      "grad_norm": 0.11938658356666565,
      "learning_rate": 2e-07,
      "loss": 0.0092,
      "step": 249
    },
    {
      "clip_ratio/high_max": 0.001939498797582928,
      "clip_ratio/high_mean": 0.0008849788864608854,
      "clip_ratio/low_mean": 0.0006844468753115507,
      "clip_ratio/low_min": 7.482086039090063e-05,
      "clip_ratio/region_mean": 0.0015694257599534467,
      "epoch": 0.023333275000145832,
      "grad_norm": 0.13686634600162506,
      "learning_rate": 2e-07,
      "loss": -0.0155,
      "step": 250
    },
    {
      "clip_ratio/high_max": 0.0020375457461341284,
      "clip_ratio/high_mean": 0.0008434641786152497,
      "clip_ratio/low_mean": 0.000673469254252268,
      "clip_ratio/low_min": 6.995611875026952e-05,
      "clip_ratio/region_mean": 0.0015169333855737932,
      "epoch": 0.023426608100146417,
      "grad_norm": 0.12419265508651733,
      "learning_rate": 2e-07,
      "loss": 0.0366,
      "step": 251
    },
    {
      "clip_ratio/high_max": 0.001976864852622384,
      "clip_ratio/high_mean": 0.0007229638449643971,
      "clip_ratio/low_mean": 0.0006403792831406463,
      "clip_ratio/low_min": 3.325263060105499e-05,
      "clip_ratio/region_mean": 0.0013633431335620116,
      "epoch": 0.023519941200147,
      "grad_norm": 0.13820812106132507,
      "learning_rate": 2e-07,
      "loss": 0.0486,
      "step": 252
    },
    {
      "clip_ratio/high_max": 0.0022484115324914455,
      "clip_ratio/high_mean": 0.0009520504554529907,
      "clip_ratio/low_mean": 0.0006318347568594618,
      "clip_ratio/low_min": 2.1632093194057234e-05,
      "clip_ratio/region_mean": 0.0015838852123124525,
      "epoch": 0.023613274300147584,
      "grad_norm": 0.11094287782907486,
      "learning_rate": 2e-07,
      "loss": -0.0021,
      "step": 253
    },
    {
      "clip_ratio/high_max": 0.0020970325131202117,
      "clip_ratio/high_mean": 0.0009178951549984049,
      "clip_ratio/low_mean": 0.0006947758975002216,
      "clip_ratio/low_min": 8.198030263883993e-05,
      "clip_ratio/region_mean": 0.0016126710834214464,
      "epoch": 0.023706607400148166,
      "grad_norm": 0.13793335855007172,
      "learning_rate": 2e-07,
      "loss": 0.0663,
      "step": 254
    },
    {
      "clip_ratio/high_max": 0.002247452164738206,
      "clip_ratio/high_mean": 0.0009144013238255866,
      "clip_ratio/low_mean": 0.0005964958008917165,
      "clip_ratio/low_min": 4.1346617308590794e-05,
      "clip_ratio/region_mean": 0.00151089714927366,
      "epoch": 0.02379994050014875,
      "grad_norm": 0.12533582746982574,
      "learning_rate": 2e-07,
      "loss": 0.0329,
      "step": 255
    },
    {
      "clip_ratio/high_max": 0.002352266419620719,
      "clip_ratio/high_mean": 0.0010341808338125702,
      "clip_ratio/low_mean": 0.0006419627470677369,
      "clip_ratio/low_min": 1.1469994205981493e-05,
      "clip_ratio/region_mean": 0.0016761435545049608,
      "epoch": 0.023893273600149333,
      "grad_norm": 0.11967840790748596,
      "learning_rate": 2e-07,
      "loss": -0.0008,
      "step": 256
    },
    {
      "clip_ratio/high_max": 0.0018839719341485761,
      "clip_ratio/high_mean": 0.0007135008636396378,
      "clip_ratio/low_mean": 0.0005426309635367943,
      "clip_ratio/low_min": 8.57927261677105e-06,
      "clip_ratio/region_mean": 0.001256131839909358,
      "completions/clipped_ratio": 0.0160609654017857,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4096.0,
      "completions/mean_length": 624.572998046875,
      "completions/mean_terminated_length": 567.9083862304688,
      "completions/min_length": 81.0,
      "completions/min_terminated_length": 81.0,
      "epoch": 0.023986606700149918,
      "grad_norm": 0.11500854045152664,
      "learning_rate": 2e-07,
      "loss": 0.0634,
      "num_tokens": 245222416.0,
      "reward": 0.56463623046875,
      "reward_std": 0.20198029279708862,
      "rewards/simpleverify_reward/mean": 0.56463623046875,
      "rewards/simpleverify_reward/std": 0.49580687284469604,
      "step": 257
    },
    {
      "clip_ratio/high_max": 0.0020199282880639657,
      "clip_ratio/high_mean": 0.0008201083528547315,
      "clip_ratio/low_mean": 0.00047565761997248046,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012957659782841802,
      "epoch": 0.0240799398001505,
      "grad_norm": 0.1208253875374794,
      "learning_rate": 2e-07,
      "loss": -0.0123,
      "step": 258
    },
    {
      "clip_ratio/high_max": 0.001963495298696216,
      "clip_ratio/high_mean": 0.0007769777894282015,
      "clip_ratio/low_mean": 0.0006154828006401658,
      "clip_ratio/low_min": 3.069697959290352e-05,
      "clip_ratio/region_mean": 0.001392460588249378,
      "epoch": 0.02417327290015108,
      "grad_norm": 0.11618202924728394,
      "learning_rate": 2e-07,
      "loss": 0.0545,
      "step": 259
    },
    {
      "clip_ratio/high_max": 0.001976386509340955,
      "clip_ratio/high_mean": 0.0008198244486266049,
      "clip_ratio/low_mean": 0.0005461222081066808,
      "clip_ratio/low_min": 2.5431217181903776e-05,
      "clip_ratio/region_mean": 0.0013659466712852009,
      "epoch": 0.024266606000151666,
      "grad_norm": 0.11154364049434662,
      "learning_rate": 2e-07,
      "loss": 0.028,
      "step": 260
    },
    {
      "clip_ratio/high_max": 0.0018495485601306427,
      "clip_ratio/high_mean": 0.000679276070513879,
      "clip_ratio/low_mean": 0.0005829149340570439,
      "clip_ratio/low_min": 7.651429677935084e-05,
      "clip_ratio/region_mean": 0.0012621909845620394,
      "epoch": 0.024359939100152248,
      "grad_norm": 0.4491668939590454,
      "learning_rate": 2e-07,
      "loss": 0.0628,
      "step": 261
    },
    {
      "clip_ratio/high_max": 0.0018992861478182022,
      "clip_ratio/high_mean": 0.0006883132709845086,
      "clip_ratio/low_mean": 0.0006296134815784171,
      "clip_ratio/low_min": 4.2889173528237734e-05,
      "clip_ratio/region_mean": 0.0013179267371015158,
      "epoch": 0.024453272200152833,
      "grad_norm": 0.11347917467355728,
      "learning_rate": 2e-07,
      "loss": 0.0586,
      "step": 262
    },
    {
      "clip_ratio/high_max": 0.0017797858381527476,
      "clip_ratio/high_mean": 0.0007452798672602512,
      "clip_ratio/low_mean": 0.000546596672393207,
      "clip_ratio/low_min": 3.882692544721067e-05,
      "clip_ratio/region_mean": 0.0012918765569338575,
      "epoch": 0.024546605300153415,
      "grad_norm": 0.11700635403394699,
      "learning_rate": 2e-07,
      "loss": 0.0273,
      "step": 263
    },
    {
      "clip_ratio/high_max": 0.0018411456439935137,
      "clip_ratio/high_mean": 0.0007784780245856382,
      "clip_ratio/low_mean": 0.000527014772160328,
      "clip_ratio/low_min": 3.753527744265739e-05,
      "clip_ratio/region_mean": 0.0013054928167548496,
      "epoch": 0.024639938400154,
      "grad_norm": 0.12003087252378464,
      "learning_rate": 2e-07,
      "loss": 0.0119,
      "step": 264
    },
    {
      "clip_ratio/high_max": 0.0022165566369949374,
      "clip_ratio/high_mean": 0.0008499307905367459,
      "clip_ratio/low_mean": 0.0005198766684770817,
      "clip_ratio/low_min": 6.738482807122637e-05,
      "clip_ratio/region_mean": 0.0013698074690182693,
      "epoch": 0.024733271500154582,
      "grad_norm": 0.12093736976385117,
      "learning_rate": 2e-07,
      "loss": 0.0082,
      "step": 265
    },
    {
      "clip_ratio/high_max": 0.0018259815697092563,
      "clip_ratio/high_mean": 0.0007838963738322491,
      "clip_ratio/low_mean": 0.0006334642166621052,
      "clip_ratio/low_min": 7.806645044183824e-06,
      "clip_ratio/region_mean": 0.0014173605595715344,
      "epoch": 0.024826604600155167,
      "grad_norm": 0.12317376583814621,
      "learning_rate": 2e-07,
      "loss": 0.0203,
      "step": 266
    },
    {
      "clip_ratio/high_max": 0.0022587031780858524,
      "clip_ratio/high_mean": 0.0008465351620543515,
      "clip_ratio/low_mean": 0.0005003897140340996,
      "clip_ratio/low_min": 5.588116619037464e-05,
      "clip_ratio/region_mean": 0.0013469249061017763,
      "epoch": 0.02491993770015575,
      "grad_norm": 0.13149158656597137,
      "learning_rate": 2e-07,
      "loss": 0.0193,
      "step": 267
    },
    {
      "clip_ratio/high_max": 0.00210473397601163,
      "clip_ratio/high_mean": 0.0007792920096107991,
      "clip_ratio/low_mean": 0.0005549281613639323,
      "clip_ratio/low_min": 4.625537621905096e-05,
      "clip_ratio/region_mean": 0.0013342201673367526,
      "epoch": 0.025013270800156334,
      "grad_norm": 0.11912455409765244,
      "learning_rate": 2e-07,
      "loss": 0.0332,
      "step": 268
    },
    {
      "clip_ratio/high_max": 0.0020448992763704155,
      "clip_ratio/high_mean": 0.0007903182545305754,
      "clip_ratio/low_mean": 0.0005470241758303018,
      "clip_ratio/low_min": 1.4524750440614298e-05,
      "clip_ratio/region_mean": 0.0013373424408200663,
      "epoch": 0.025106603900156916,
      "grad_norm": 0.11905215680599213,
      "learning_rate": 2e-07,
      "loss": 0.0681,
      "step": 269
    },
    {
      "clip_ratio/high_max": 0.0014461008613579907,
      "clip_ratio/high_mean": 0.0006477457636719919,
      "clip_ratio/low_mean": 0.0006582269779755734,
      "clip_ratio/low_min": 3.421683322812896e-05,
      "clip_ratio/region_mean": 0.0013059727461950388,
      "epoch": 0.0251999370001575,
      "grad_norm": 0.11372499167919159,
      "learning_rate": 2e-07,
      "loss": 0.0561,
      "step": 270
    },
    {
      "clip_ratio/high_max": 0.0017878697617561556,
      "clip_ratio/high_mean": 0.0007543820247519761,
      "clip_ratio/low_mean": 0.0005058662263763836,
      "clip_ratio/low_min": 3.363247105880873e-05,
      "clip_ratio/region_mean": 0.0012602482420334127,
      "epoch": 0.025293270100158083,
      "grad_norm": 0.1179540678858757,
      "learning_rate": 2e-07,
      "loss": 0.0371,
      "step": 271
    },
    {
      "clip_ratio/high_max": 0.0017493020968686324,
      "clip_ratio/high_mean": 0.0007540766355305095,
      "clip_ratio/low_mean": 0.0005946931278231204,
      "clip_ratio/low_min": 7.5796783221449e-05,
      "clip_ratio/region_mean": 0.0013487697469827253,
      "epoch": 0.025386603200158665,
      "grad_norm": 0.12303470820188522,
      "learning_rate": 2e-07,
      "loss": 0.0453,
      "step": 272
    },
    {
      "clip_ratio/high_max": 0.0018768651243590284,
      "clip_ratio/high_mean": 0.0007730286706646439,
      "clip_ratio/low_mean": 0.0006108778288762551,
      "clip_ratio/low_min": 2.951593887701165e-05,
      "clip_ratio/region_mean": 0.0013839064704370685,
      "epoch": 0.02547993630015925,
      "grad_norm": 0.13033203780651093,
      "learning_rate": 2e-07,
      "loss": 0.0211,
      "step": 273
    },
    {
      "clip_ratio/high_max": 0.00197576292703161,
      "clip_ratio/high_mean": 0.0009061270029633306,
      "clip_ratio/low_mean": 0.0005172456221771426,
      "clip_ratio/low_min": 2.4377088266192004e-05,
      "clip_ratio/region_mean": 0.0014233726142265368,
      "epoch": 0.02557326940015983,
      "grad_norm": 0.12400084733963013,
      "learning_rate": 2e-07,
      "loss": -0.0233,
      "step": 274
    },
    {
      "clip_ratio/high_max": 0.0020519799400062766,
      "clip_ratio/high_mean": 0.0007785065954521997,
      "clip_ratio/low_mean": 0.0004813198793272022,
      "clip_ratio/low_min": 2.377148121013306e-05,
      "clip_ratio/region_mean": 0.0012598264547705185,
      "epoch": 0.025666602500160417,
      "grad_norm": 0.1072271540760994,
      "learning_rate": 2e-07,
      "loss": 0.019,
      "step": 275
    },
    {
      "clip_ratio/high_max": 0.0017076392396120355,
      "clip_ratio/high_mean": 0.0007884213264333084,
      "clip_ratio/low_mean": 0.000621120158029953,
      "clip_ratio/low_min": 5.097129178466275e-05,
      "clip_ratio/region_mean": 0.0014095414844632614,
      "epoch": 0.025759935600161,
      "grad_norm": 0.13034513592720032,
      "learning_rate": 2e-07,
      "loss": 0.0026,
      "step": 276
    },
    {
      "clip_ratio/high_max": 0.001769192298525013,
      "clip_ratio/high_mean": 0.0007256751177919796,
      "clip_ratio/low_mean": 0.0006207737815202563,
      "clip_ratio/low_min": 3.349593316670507e-05,
      "clip_ratio/region_mean": 0.0013464488984027412,
      "epoch": 0.025853268700161584,
      "grad_norm": 0.12212289869785309,
      "learning_rate": 2e-07,
      "loss": 0.0235,
      "step": 277
    },
    {
      "clip_ratio/high_max": 0.0020236209165886976,
      "clip_ratio/high_mean": 0.0007744238591840258,
      "clip_ratio/low_mean": 0.0006517259444080992,
      "clip_ratio/low_min": 4.1901329495885875e-05,
      "clip_ratio/region_mean": 0.0014261497926781885,
      "epoch": 0.025946601800162165,
      "grad_norm": 0.12455925345420837,
      "learning_rate": 2e-07,
      "loss": 0.0616,
      "step": 278
    },
    {
      "clip_ratio/high_max": 0.00199477250862401,
      "clip_ratio/high_mean": 0.0008391673800360877,
      "clip_ratio/low_mean": 0.0005476566584547982,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013868240384908859,
      "epoch": 0.02603993490016275,
      "grad_norm": 0.11874571442604065,
      "learning_rate": 2e-07,
      "loss": 0.0277,
      "step": 279
    },
    {
      "clip_ratio/high_max": 0.0021788684753119014,
      "clip_ratio/high_mean": 0.0008542817795387236,
      "clip_ratio/low_mean": 0.0005357002028176794,
      "clip_ratio/low_min": 2.6899075237452053e-05,
      "clip_ratio/region_mean": 0.0013899819750804454,
      "epoch": 0.026133268000163332,
      "grad_norm": 0.12170732766389847,
      "learning_rate": 2e-07,
      "loss": 0.0168,
      "step": 280
    },
    {
      "clip_ratio/high_max": 0.0020501477592915762,
      "clip_ratio/high_mean": 0.000721589800377842,
      "clip_ratio/low_mean": 0.0006146431642264361,
      "clip_ratio/low_min": 7.955637329359888e-05,
      "clip_ratio/region_mean": 0.0013362329518713523,
      "epoch": 0.026226601100163918,
      "grad_norm": 0.12555696070194244,
      "learning_rate": 2e-07,
      "loss": 0.0949,
      "step": 281
    },
    {
      "clip_ratio/high_max": 0.0022244991560000926,
      "clip_ratio/high_mean": 0.0008334208596352255,
      "clip_ratio/low_mean": 0.000513205976858444,
      "clip_ratio/low_min": 5.205479101277888e-05,
      "clip_ratio/region_mean": 0.0013466268428601325,
      "epoch": 0.0263199342001645,
      "grad_norm": 0.11201972514390945,
      "learning_rate": 2e-07,
      "loss": -0.0102,
      "step": 282
    },
    {
      "clip_ratio/high_max": 0.0019736876784008928,
      "clip_ratio/high_mean": 0.000796609245298896,
      "clip_ratio/low_mean": 0.0005864941977051785,
      "clip_ratio/low_min": 4.224031090416247e-05,
      "clip_ratio/region_mean": 0.0013831034484610427,
      "epoch": 0.026413267300165084,
      "grad_norm": 0.12162583321332932,
      "learning_rate": 2e-07,
      "loss": 0.0265,
      "step": 283
    },
    {
      "clip_ratio/high_max": 0.002068604364467319,
      "clip_ratio/high_mean": 0.000845280812427518,
      "clip_ratio/low_mean": 0.0005790795057691867,
      "clip_ratio/low_min": 1.198236168420408e-05,
      "clip_ratio/region_mean": 0.0014243603254726622,
      "epoch": 0.026506600400165666,
      "grad_norm": 0.11316550523042679,
      "learning_rate": 2e-07,
      "loss": 0.0104,
      "step": 284
    },
    {
      "clip_ratio/high_max": 0.002168106057069963,
      "clip_ratio/high_mean": 0.0008575835363444639,
      "clip_ratio/low_mean": 0.00046572769178965245,
      "clip_ratio/low_min": 1.3009991562284995e-05,
      "clip_ratio/region_mean": 0.001323311236774316,
      "epoch": 0.026599933500166248,
      "grad_norm": 0.09966593235731125,
      "learning_rate": 2e-07,
      "loss": -0.0008,
      "step": 285
    },
    {
      "clip_ratio/high_max": 0.0022890284017194062,
      "clip_ratio/high_mean": 0.0007924565652501769,
      "clip_ratio/low_mean": 0.000595366280322196,
      "clip_ratio/low_min": 6.697939079458592e-05,
      "clip_ratio/region_mean": 0.001387822841934394,
      "epoch": 0.026693266600166833,
      "grad_norm": 0.11711356043815613,
      "learning_rate": 2e-07,
      "loss": -0.0254,
      "step": 286
    },
    {
      "clip_ratio/high_max": 0.0020460956075112335,
      "clip_ratio/high_mean": 0.0009111475010286085,
      "clip_ratio/low_mean": 0.0005603526178674656,
      "clip_ratio/low_min": 4.2565307467157254e-05,
      "clip_ratio/region_mean": 0.0014715000688738655,
      "epoch": 0.026786599700167415,
      "grad_norm": 0.12362494319677353,
      "learning_rate": 2e-07,
      "loss": -0.0175,
      "step": 287
    },
    {
      "clip_ratio/high_max": 0.002082897630316438,
      "clip_ratio/high_mean": 0.0008626818107586587,
      "clip_ratio/low_mean": 0.0006432107165892376,
      "clip_ratio/low_min": 6.818192377977539e-05,
      "clip_ratio/region_mean": 0.0015058925091580022,
      "epoch": 0.026879932800168,
      "grad_norm": 0.13926564157009125,
      "learning_rate": 2e-07,
      "loss": 0.0225,
      "step": 288
    },
    {
      "clip_ratio/high_max": 0.0016591042767686304,
      "clip_ratio/high_mean": 0.0007356801124842605,
      "clip_ratio/low_mean": 0.0006420888676075265,
      "clip_ratio/low_min": 7.559329151263228e-05,
      "clip_ratio/region_mean": 0.0013777689782727975,
      "epoch": 0.026973265900168582,
      "grad_norm": 0.11378282308578491,
      "learning_rate": 2e-07,
      "loss": 0.0273,
      "step": 289
    },
    {
      "clip_ratio/high_max": 0.001975459399545798,
      "clip_ratio/high_mean": 0.0007609944350406295,
      "clip_ratio/low_mean": 0.0006458952648245031,
      "clip_ratio/low_min": 8.118589175865054e-05,
      "clip_ratio/region_mean": 0.0014068896780372597,
      "epoch": 0.027066599000169167,
      "grad_norm": 0.12239658087491989,
      "learning_rate": 2e-07,
      "loss": 0.0178,
      "step": 290
    },
    {
      "clip_ratio/high_max": 0.0019237046362832189,
      "clip_ratio/high_mean": 0.00080548742243991,
      "clip_ratio/low_mean": 0.0005979554644000018,
      "clip_ratio/low_min": 2.6338419047533534e-05,
      "clip_ratio/region_mean": 0.0014034428786544595,
      "epoch": 0.02715993210016975,
      "grad_norm": 0.12757523357868195,
      "learning_rate": 2e-07,
      "loss": 0.0361,
      "step": 291
    },
    {
      "clip_ratio/high_max": 0.002089562356559327,
      "clip_ratio/high_mean": 0.0008999970268632751,
      "clip_ratio/low_mean": 0.0005720423478123848,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001472039395594038,
      "epoch": 0.027253265200170334,
      "grad_norm": 0.13246272504329681,
      "learning_rate": 2e-07,
      "loss": -0.0256,
      "step": 292
    },
    {
      "clip_ratio/high_max": 0.0019675435578392353,
      "clip_ratio/high_mean": 0.0008336705650435761,
      "clip_ratio/low_mean": 0.0006249542948353337,
      "clip_ratio/low_min": 1.942260769283166e-05,
      "clip_ratio/region_mean": 0.0014586248762498144,
      "epoch": 0.027346598300170916,
      "grad_norm": 0.1290530413389206,
      "learning_rate": 2e-07,
      "loss": 0.0003,
      "step": 293
    },
    {
      "clip_ratio/high_max": 0.001981994937523268,
      "clip_ratio/high_mean": 0.0008153691960615106,
      "clip_ratio/low_mean": 0.0006392068844434107,
      "clip_ratio/low_min": 5.741790300817229e-05,
      "clip_ratio/region_mean": 0.0014545760714099742,
      "epoch": 0.0274399314001715,
      "grad_norm": 0.12548260390758514,
      "learning_rate": 2e-07,
      "loss": 0.0588,
      "step": 294
    },
    {
      "clip_ratio/high_max": 0.002162057840905618,
      "clip_ratio/high_mean": 0.0008298467564600287,
      "clip_ratio/low_mean": 0.0005505874732989469,
      "clip_ratio/low_min": 5.910718118684599e-05,
      "clip_ratio/region_mean": 0.0013804342488583643,
      "epoch": 0.027533264500172083,
      "grad_norm": 0.11832530796527863,
      "learning_rate": 2e-07,
      "loss": -0.0042,
      "step": 295
    },
    {
      "clip_ratio/high_max": 0.001881218639027793,
      "clip_ratio/high_mean": 0.0007035325634205947,
      "clip_ratio/low_mean": 0.0006120294356151135,
      "clip_ratio/low_min": 3.050314262509346e-05,
      "clip_ratio/region_mean": 0.0013155620035831816,
      "epoch": 0.027626597600172668,
      "grad_norm": 0.11982741206884384,
      "learning_rate": 2e-07,
      "loss": 0.0259,
      "step": 296
    },
    {
      "clip_ratio/high_max": 0.0019271934943390079,
      "clip_ratio/high_mean": 0.000762846093493863,
      "clip_ratio/low_mean": 0.0004931095863867085,
      "clip_ratio/low_min": 1.4945002476451918e-05,
      "clip_ratio/region_mean": 0.0012559556344058365,
      "epoch": 0.02771993070017325,
      "grad_norm": 0.12474443763494492,
      "learning_rate": 2e-07,
      "loss": -0.0155,
      "step": 297
    },
    {
      "clip_ratio/high_max": 0.0017164243763545528,
      "clip_ratio/high_mean": 0.0007956518056744244,
      "clip_ratio/low_mean": 0.0006176739188958891,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014133257500361651,
      "epoch": 0.02781326380017383,
      "grad_norm": 0.12053424119949341,
      "learning_rate": 2e-07,
      "loss": 0.0178,
      "step": 298
    },
    {
      "clip_ratio/high_max": 0.002117894357070327,
      "clip_ratio/high_mean": 0.0008695551005075686,
      "clip_ratio/low_mean": 0.0005955539336355287,
      "clip_ratio/low_min": 5.094632888358319e-05,
      "clip_ratio/region_mean": 0.0014651090059487615,
      "epoch": 0.027906596900174416,
      "grad_norm": 0.12493390589952469,
      "learning_rate": 2e-07,
      "loss": -0.0111,
      "step": 299
    },
    {
      "clip_ratio/high_max": 0.0017723021519486792,
      "clip_ratio/high_mean": 0.0007359522596743773,
      "clip_ratio/low_mean": 0.0005927807542320807,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001328733007539995,
      "epoch": 0.027999930000174998,
      "grad_norm": 0.11270361393690109,
      "learning_rate": 2e-07,
      "loss": 0.027,
      "step": 300
    },
    {
      "clip_ratio/high_max": 0.001885232632048428,
      "clip_ratio/high_mean": 0.0007097050356605905,
      "clip_ratio/low_mean": 0.000500872033626365,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012105771129427012,
      "epoch": 0.028093263100175583,
      "grad_norm": 0.11546891182661057,
      "learning_rate": 2e-07,
      "loss": -0.0078,
      "step": 301
    },
    {
      "clip_ratio/high_max": 0.0020113050850341097,
      "clip_ratio/high_mean": 0.0007935145658848342,
      "clip_ratio/low_mean": 0.0006199763811309822,
      "clip_ratio/low_min": 4.739719042845536e-05,
      "clip_ratio/region_mean": 0.0014134909397398587,
      "epoch": 0.028186596200176165,
      "grad_norm": 0.11855800449848175,
      "learning_rate": 2e-07,
      "loss": 0.0093,
      "step": 302
    },
    {
      "clip_ratio/high_max": 0.0016922742797760293,
      "clip_ratio/high_mean": 0.0007418187815346755,
      "clip_ratio/low_mean": 0.000576145540435391,
      "clip_ratio/low_min": 8.622129644209053e-05,
      "clip_ratio/region_mean": 0.0013179643246985506,
      "epoch": 0.02827992930017675,
      "grad_norm": 0.11983189731836319,
      "learning_rate": 2e-07,
      "loss": 0.0435,
      "step": 303
    },
    {
      "clip_ratio/high_max": 0.0017247748328372836,
      "clip_ratio/high_mean": 0.0006810644117649645,
      "clip_ratio/low_mean": 0.0006676435987174045,
      "clip_ratio/low_min": 1.668891854933463e-05,
      "clip_ratio/region_mean": 0.001348708010482369,
      "epoch": 0.028373262400177332,
      "grad_norm": 0.1171589195728302,
      "learning_rate": 2e-07,
      "loss": 0.0802,
      "step": 304
    },
    {
      "clip_ratio/high_max": 0.0017667813444859348,
      "clip_ratio/high_mean": 0.0007061848082230426,
      "clip_ratio/low_mean": 0.0006128011073087691,
      "clip_ratio/low_min": 7.494501551263966e-05,
      "clip_ratio/region_mean": 0.0013189858982514124,
      "epoch": 0.028466595500177917,
      "grad_norm": 0.1098601296544075,
      "learning_rate": 2e-07,
      "loss": 0.0461,
      "step": 305
    },
    {
      "clip_ratio/high_max": 0.0019367154745850712,
      "clip_ratio/high_mean": 0.0007358881030086195,
      "clip_ratio/low_mean": 0.0005631079966406105,
      "clip_ratio/low_min": 5.482938468048815e-05,
      "clip_ratio/region_mean": 0.0012989960923732724,
      "epoch": 0.0285599286001785,
      "grad_norm": 0.14602519571781158,
      "learning_rate": 2e-07,
      "loss": 0.0485,
      "step": 306
    },
    {
      "clip_ratio/high_max": 0.001934049476403743,
      "clip_ratio/high_mean": 0.0007644662800885271,
      "clip_ratio/low_mean": 0.0005840450530740782,
      "clip_ratio/low_min": 3.194714190613013e-05,
      "clip_ratio/region_mean": 0.0013485113558999728,
      "epoch": 0.028653261700179084,
      "grad_norm": 0.11243382096290588,
      "learning_rate": 2e-07,
      "loss": 0.0134,
      "step": 307
    },
    {
      "clip_ratio/high_max": 0.0018117145846190397,
      "clip_ratio/high_mean": 0.0007272939483300433,
      "clip_ratio/low_mean": 0.000588181259445264,
      "clip_ratio/low_min": 2.4352177206310444e-05,
      "clip_ratio/region_mean": 0.0013154752232367173,
      "epoch": 0.028746594800179666,
      "grad_norm": 0.11952472478151321,
      "learning_rate": 2e-07,
      "loss": 0.031,
      "step": 308
    },
    {
      "clip_ratio/high_max": 0.0019460992734821048,
      "clip_ratio/high_mean": 0.0007769055373501033,
      "clip_ratio/low_mean": 0.0005817851870233426,
      "clip_ratio/low_min": 8.295551469927887e-05,
      "clip_ratio/region_mean": 0.0013586907080025412,
      "epoch": 0.02883992790018025,
      "grad_norm": 0.12298327684402466,
      "learning_rate": 2e-07,
      "loss": 0.0289,
      "step": 309
    },
    {
      "clip_ratio/high_max": 0.002010919059102889,
      "clip_ratio/high_mean": 0.0008190365260816179,
      "clip_ratio/low_mean": 0.0006089615490054712,
      "clip_ratio/low_min": 5.207685626373859e-05,
      "clip_ratio/region_mean": 0.0014279980823630467,
      "epoch": 0.028933261000180833,
      "grad_norm": 0.11988940089941025,
      "learning_rate": 2e-07,
      "loss": 0.0283,
      "step": 310
    },
    {
      "clip_ratio/high_max": 0.0017923747000168078,
      "clip_ratio/high_mean": 0.0007273753617482726,
      "clip_ratio/low_mean": 0.0006182983888720628,
      "clip_ratio/low_min": 2.9629219170601573e-05,
      "clip_ratio/region_mean": 0.0013456737251544837,
      "epoch": 0.029026594100181415,
      "grad_norm": 0.11644458770751953,
      "learning_rate": 2e-07,
      "loss": 0.0216,
      "step": 311
    },
    {
      "clip_ratio/high_max": 0.00213154007360572,
      "clip_ratio/high_mean": 0.0008717468808754347,
      "clip_ratio/low_mean": 0.000591704045291408,
      "clip_ratio/low_min": 4.444415844773175e-05,
      "clip_ratio/region_mean": 0.0014634509207098745,
      "epoch": 0.029119927200182,
      "grad_norm": 0.1220645010471344,
      "learning_rate": 2e-07,
      "loss": 0.0159,
      "step": 312
    },
    {
      "clip_ratio/high_max": 0.0018709412033786066,
      "clip_ratio/high_mean": 0.0007958844744280213,
      "clip_ratio/low_mean": 0.000547395866306033,
      "clip_ratio/low_min": 5.651607898471411e-05,
      "clip_ratio/region_mean": 0.0013432803862087894,
      "epoch": 0.02921326030018258,
      "grad_norm": 0.12182912975549698,
      "learning_rate": 2e-07,
      "loss": 0.0179,
      "step": 313
    },
    {
      "clip_ratio/high_max": 0.0021812400191265624,
      "clip_ratio/high_mean": 0.0008657605922053335,
      "clip_ratio/low_mean": 0.0006336235774142551,
      "clip_ratio/low_min": 2.370547372265719e-05,
      "clip_ratio/region_mean": 0.0014993842123658396,
      "epoch": 0.029306593400183167,
      "grad_norm": 0.13201750814914703,
      "learning_rate": 2e-07,
      "loss": -0.0119,
      "step": 314
    },
    {
      "clip_ratio/high_max": 0.0018607751626404934,
      "clip_ratio/high_mean": 0.0008000515354069648,
      "clip_ratio/low_mean": 0.0005376875606089015,
      "clip_ratio/low_min": 2.385868447163375e-05,
      "clip_ratio/region_mean": 0.0013377391223912127,
      "epoch": 0.02939992650018375,
      "grad_norm": 0.1170421838760376,
      "learning_rate": 2e-07,
      "loss": -0.0161,
      "step": 315
    },
    {
      "clip_ratio/high_max": 0.001861179025581805,
      "clip_ratio/high_mean": 0.0007701203685428482,
      "clip_ratio/low_mean": 0.00055040425468178,
      "clip_ratio/low_min": 2.3599748601554893e-05,
      "clip_ratio/region_mean": 0.001320524654147448,
      "epoch": 0.029493259600184334,
      "grad_norm": 0.1363784670829773,
      "learning_rate": 2e-07,
      "loss": 0.061,
      "step": 316
    },
    {
      "clip_ratio/high_max": 0.0016596122513874434,
      "clip_ratio/high_mean": 0.0006897079992995714,
      "clip_ratio/low_mean": 0.0006067104877729435,
      "clip_ratio/low_min": 2.9315197025425732e-05,
      "clip_ratio/region_mean": 0.0012964184752490837,
      "epoch": 0.029586592700184915,
      "grad_norm": 0.12399421632289886,
      "learning_rate": 2e-07,
      "loss": 0.052,
      "step": 317
    },
    {
      "clip_ratio/high_max": 0.001756465331709478,
      "clip_ratio/high_mean": 0.0007147569340304472,
      "clip_ratio/low_mean": 0.0006465763053711271,
      "clip_ratio/low_min": 2.2465852453024127e-05,
      "clip_ratio/region_mean": 0.0013613332375825848,
      "epoch": 0.0296799258001855,
      "grad_norm": 0.1299685686826706,
      "learning_rate": 2e-07,
      "loss": 0.0476,
      "step": 318
    },
    {
      "clip_ratio/high_max": 0.0018803434613801073,
      "clip_ratio/high_mean": 0.000824014428872033,
      "clip_ratio/low_mean": 0.0006059326715330826,
      "clip_ratio/low_min": 5.092688661534339e-05,
      "clip_ratio/region_mean": 0.0014299470785772428,
      "epoch": 0.029773258900186082,
      "grad_norm": 0.11528966575860977,
      "learning_rate": 2e-07,
      "loss": -0.0083,
      "step": 319
    },
    {
      "clip_ratio/high_max": 0.001972535806999076,
      "clip_ratio/high_mean": 0.0008278733785118675,
      "clip_ratio/low_mean": 0.0006067261183488881,
      "clip_ratio/low_min": 3.0108059036138002e-05,
      "clip_ratio/region_mean": 0.001434599471394904,
      "epoch": 0.029866592000186667,
      "grad_norm": 0.11708053946495056,
      "learning_rate": 2e-07,
      "loss": 0.0415,
      "step": 320
    },
    {
      "clip_ratio/high_max": 0.0020763563370564952,
      "clip_ratio/high_mean": 0.0008158107484632637,
      "clip_ratio/low_mean": 0.0006800573701184476,
      "clip_ratio/low_min": 5.878196043340722e-05,
      "clip_ratio/region_mean": 0.0014958680803829338,
      "epoch": 0.02995992510018725,
      "grad_norm": 0.13091234862804413,
      "learning_rate": 2e-07,
      "loss": 0.076,
      "step": 321
    },
    {
      "clip_ratio/high_max": 0.002138528216164559,
      "clip_ratio/high_mean": 0.0008708736786502413,
      "clip_ratio/low_mean": 0.0005694980063708499,
      "clip_ratio/low_min": 2.0395849332999205e-05,
      "clip_ratio/region_mean": 0.0014403717177629005,
      "epoch": 0.030053258200187834,
      "grad_norm": 0.11137208342552185,
      "learning_rate": 2e-07,
      "loss": 0.0081,
      "step": 322
    },
    {
      "clip_ratio/high_max": 0.002068605197564466,
      "clip_ratio/high_mean": 0.0008424160223512445,
      "clip_ratio/low_mean": 0.0005714419839932816,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014138580081635155,
      "epoch": 0.030146591300188416,
      "grad_norm": 0.12551407516002655,
      "learning_rate": 2e-07,
      "loss": 0.0279,
      "step": 323
    },
    {
      "clip_ratio/high_max": 0.0018103445327142254,
      "clip_ratio/high_mean": 0.0007343616525758989,
      "clip_ratio/low_mean": 0.0006544732777911122,
      "clip_ratio/low_min": 2.798298555717338e-05,
      "clip_ratio/region_mean": 0.0013888349203625694,
      "epoch": 0.030239924400188998,
      "grad_norm": 0.1211436465382576,
      "learning_rate": 2e-07,
      "loss": 0.031,
      "step": 324
    },
    {
      "clip_ratio/high_max": 0.0020055357745150104,
      "clip_ratio/high_mean": 0.0008711673071957193,
      "clip_ratio/low_mean": 0.0005298917421896476,
      "clip_ratio/low_min": 1.4243390978663228e-05,
      "clip_ratio/region_mean": 0.0014010590712132398,
      "epoch": 0.030333257500189583,
      "grad_norm": 0.13711117208003998,
      "learning_rate": 2e-07,
      "loss": -0.022,
      "step": 325
    },
    {
      "clip_ratio/high_max": 0.0018533126713009551,
      "clip_ratio/high_mean": 0.0007326084505621111,
      "clip_ratio/low_mean": 0.0006404056166502414,
      "clip_ratio/low_min": 5.2162255087750964e-05,
      "clip_ratio/region_mean": 0.001373014096316183,
      "epoch": 0.030426590600190165,
      "grad_norm": 0.11760517954826355,
      "learning_rate": 2e-07,
      "loss": 0.049,
      "step": 326
    },
    {
      "clip_ratio/high_max": 0.0018047416233457625,
      "clip_ratio/high_mean": 0.0007827441459085094,
      "clip_ratio/low_mean": 0.0005671492308465531,
      "clip_ratio/low_min": 3.614993238443276e-05,
      "clip_ratio/region_mean": 0.0013498934204108082,
      "epoch": 0.03051992370019075,
      "grad_norm": 0.11555701494216919,
      "learning_rate": 2e-07,
      "loss": 0.0177,
      "step": 327
    },
    {
      "clip_ratio/high_max": 0.0017075175055651926,
      "clip_ratio/high_mean": 0.0007701397462369641,
      "clip_ratio/low_mean": 0.0007354669214691967,
      "clip_ratio/low_min": 7.073225606291089e-05,
      "clip_ratio/region_mean": 0.0015056066513352562,
      "epoch": 0.030613256800191332,
      "grad_norm": 0.1212574914097786,
      "learning_rate": 2e-07,
      "loss": 0.0526,
      "step": 328
    },
    {
      "clip_ratio/high_max": 0.0020462254105950706,
      "clip_ratio/high_mean": 0.0009032924881466897,
      "clip_ratio/low_mean": 0.0005376549534048536,
      "clip_ratio/low_min": 5.068782320449827e-05,
      "clip_ratio/region_mean": 0.001440947424271144,
      "epoch": 0.030706589900191917,
      "grad_norm": 0.12562961876392365,
      "learning_rate": 2e-07,
      "loss": -0.0429,
      "step": 329
    },
    {
      "clip_ratio/high_max": 0.002181030620704405,
      "clip_ratio/high_mean": 0.000819687740658992,
      "clip_ratio/low_mean": 0.0006825181417298154,
      "clip_ratio/low_min": 5.209079790802207e-05,
      "clip_ratio/region_mean": 0.0015022058432805352,
      "epoch": 0.0307999230001925,
      "grad_norm": 0.12798555195331573,
      "learning_rate": 2e-07,
      "loss": 0.0583,
      "step": 330
    },
    {
      "clip_ratio/high_max": 0.0021890079624427017,
      "clip_ratio/high_mean": 0.0008083746370175504,
      "clip_ratio/low_mean": 0.0006119201716501266,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001420294811396161,
      "epoch": 0.030893256100193084,
      "grad_norm": 0.13179506361484528,
      "learning_rate": 2e-07,
      "loss": 0.0636,
      "step": 331
    },
    {
      "clip_ratio/high_max": 0.0024998585577122867,
      "clip_ratio/high_mean": 0.0009136358130490407,
      "clip_ratio/low_mean": 0.0006552305185323348,
      "clip_ratio/low_min": 6.915092399140121e-05,
      "clip_ratio/region_mean": 0.0015688663406763226,
      "epoch": 0.030986589200193666,
      "grad_norm": 0.1430823802947998,
      "learning_rate": 2e-07,
      "loss": -0.0113,
      "step": 332
    },
    {
      "clip_ratio/high_max": 0.002172136850276729,
      "clip_ratio/high_mean": 0.0009052669865923235,
      "clip_ratio/low_mean": 0.0006395005293597933,
      "clip_ratio/low_min": 4.831981368624838e-05,
      "clip_ratio/region_mean": 0.0015447675323230214,
      "epoch": 0.03107992230019425,
      "grad_norm": 0.13516907393932343,
      "learning_rate": 2e-07,
      "loss": -0.0033,
      "step": 333
    },
    {
      "clip_ratio/high_max": 0.0021146919461898506,
      "clip_ratio/high_mean": 0.0008844261210469995,
      "clip_ratio/low_mean": 0.0006489717516160454,
      "clip_ratio/low_min": 5.190768752072472e-05,
      "clip_ratio/region_mean": 0.0015333978735725395,
      "epoch": 0.031173255400194833,
      "grad_norm": 0.13142113387584686,
      "learning_rate": 2e-07,
      "loss": 0.0429,
      "step": 334
    },
    {
      "clip_ratio/high_max": 0.0020546290834317915,
      "clip_ratio/high_mean": 0.0008162078083842061,
      "clip_ratio/low_mean": 0.0006236929057195084,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014399007304746192,
      "epoch": 0.03126658850019542,
      "grad_norm": 0.13078740239143372,
      "learning_rate": 2e-07,
      "loss": 0.0355,
      "step": 335
    },
    {
      "clip_ratio/high_max": 0.0019496910244924948,
      "clip_ratio/high_mean": 0.0007712158467256813,
      "clip_ratio/low_mean": 0.0006502433552668663,
      "clip_ratio/low_min": 1.723840341583127e-05,
      "clip_ratio/region_mean": 0.001421459201083053,
      "epoch": 0.031359921600196,
      "grad_norm": 0.12030063569545746,
      "learning_rate": 2e-07,
      "loss": 0.0269,
      "step": 336
    },
    {
      "clip_ratio/high_max": 0.0020667543685704004,
      "clip_ratio/high_mean": 0.0008630554075352848,
      "clip_ratio/low_mean": 0.0006681880677206209,
      "clip_ratio/low_min": 4.004978291050065e-05,
      "clip_ratio/region_mean": 0.001531243422505213,
      "epoch": 0.03145325470019658,
      "grad_norm": 0.12424676865339279,
      "learning_rate": 2e-07,
      "loss": 0.0351,
      "step": 337
    },
    {
      "clip_ratio/high_max": 0.0019960505560447928,
      "clip_ratio/high_mean": 0.0008136813394230558,
      "clip_ratio/low_mean": 0.0006493733471870655,
      "clip_ratio/low_min": 2.502357165212743e-05,
      "clip_ratio/region_mean": 0.001463054730265867,
      "epoch": 0.031546587800197166,
      "grad_norm": 0.140573650598526,
      "learning_rate": 2e-07,
      "loss": 0.0039,
      "step": 338
    },
    {
      "clip_ratio/high_max": 0.0019912030111299828,
      "clip_ratio/high_mean": 0.0008389609683945309,
      "clip_ratio/low_mean": 0.0007777182163408725,
      "clip_ratio/low_min": 4.299430929677328e-05,
      "clip_ratio/region_mean": 0.001616679241124075,
      "epoch": 0.03163992090019775,
      "grad_norm": 0.12600019574165344,
      "learning_rate": 2e-07,
      "loss": 0.0752,
      "step": 339
    },
    {
      "clip_ratio/high_max": 0.00190631156146992,
      "clip_ratio/high_mean": 0.0006942794880160363,
      "clip_ratio/low_mean": 0.0006744509610143723,
      "clip_ratio/low_min": 2.434991802147124e-05,
      "clip_ratio/region_mean": 0.0013687304490304086,
      "epoch": 0.03173325400019833,
      "grad_norm": 0.10787362605333328,
      "learning_rate": 2e-07,
      "loss": 0.0604,
      "step": 340
    },
    {
      "clip_ratio/high_max": 0.0018717912207648624,
      "clip_ratio/high_mean": 0.0007432868496834999,
      "clip_ratio/low_mean": 0.0006416139949578792,
      "clip_ratio/low_min": 4.470630483410787e-05,
      "clip_ratio/region_mean": 0.0013849008792021777,
      "epoch": 0.031826587100198915,
      "grad_norm": 0.12344107776880264,
      "learning_rate": 2e-07,
      "loss": 0.0076,
      "step": 341
    },
    {
      "clip_ratio/high_max": 0.0018016068970609922,
      "clip_ratio/high_mean": 0.0008173807727871463,
      "clip_ratio/low_mean": 0.0006208045751918689,
      "clip_ratio/low_min": 6.176316765049705e-05,
      "clip_ratio/region_mean": 0.0014381853397935629,
      "epoch": 0.0319199202001995,
      "grad_norm": 0.12946541607379913,
      "learning_rate": 2e-07,
      "loss": 0.0364,
      "step": 342
    },
    {
      "clip_ratio/high_max": 0.00202441870351322,
      "clip_ratio/high_mean": 0.0008188404790416826,
      "clip_ratio/low_mean": 0.000643654088889889,
      "clip_ratio/low_min": 6.226074674486881e-05,
      "clip_ratio/region_mean": 0.0014624945470131934,
      "epoch": 0.032013253300200085,
      "grad_norm": 0.11710294336080551,
      "learning_rate": 2e-07,
      "loss": 0.0114,
      "step": 343
    },
    {
      "clip_ratio/high_max": 0.002013855533732567,
      "clip_ratio/high_mean": 0.0007497915321437176,
      "clip_ratio/low_mean": 0.00063042807050806,
      "clip_ratio/low_min": 0.00011657851246127393,
      "clip_ratio/region_mean": 0.0013802195790049154,
      "epoch": 0.032106586400200664,
      "grad_norm": 0.13373452425003052,
      "learning_rate": 2e-07,
      "loss": 0.0569,
      "step": 344
    },
    {
      "clip_ratio/high_max": 0.002242884671431966,
      "clip_ratio/high_mean": 0.0009183049169223523,
      "clip_ratio/low_mean": 0.0005564682596741477,
      "clip_ratio/low_min": 6.230210510693723e-05,
      "clip_ratio/region_mean": 0.0014747731875104364,
      "epoch": 0.03219991950020125,
      "grad_norm": 0.12011953443288803,
      "learning_rate": 2e-07,
      "loss": -0.0222,
      "step": 345
    },
    {
      "clip_ratio/high_max": 0.0020708401934825815,
      "clip_ratio/high_mean": 0.0009507345657766564,
      "clip_ratio/low_mean": 0.000621335919277044,
      "clip_ratio/low_min": 2.5207879843947012e-05,
      "clip_ratio/region_mean": 0.001572070483234711,
      "epoch": 0.032293252600201834,
      "grad_norm": 0.11543308198451996,
      "learning_rate": 2e-07,
      "loss": -0.0009,
      "step": 346
    },
    {
      "clip_ratio/high_max": 0.0023103153507690877,
      "clip_ratio/high_mean": 0.0008825328077364247,
      "clip_ratio/low_mean": 0.0006463153167715063,
      "clip_ratio/low_min": 5.598203915724298e-05,
      "clip_ratio/region_mean": 0.0015288480899471324,
      "epoch": 0.03238658570020242,
      "grad_norm": 0.11768263578414917,
      "learning_rate": 2e-07,
      "loss": -0.0143,
      "step": 347
    },
    {
      "clip_ratio/high_max": 0.002000804648560006,
      "clip_ratio/high_mean": 0.0007938522703625495,
      "clip_ratio/low_mean": 0.0005484688372234814,
      "clip_ratio/low_min": 4.504949993133778e-05,
      "clip_ratio/region_mean": 0.0013423211094050203,
      "epoch": 0.032479918800203,
      "grad_norm": 0.11947911232709885,
      "learning_rate": 2e-07,
      "loss": 0.0346,
      "step": 348
    },
    {
      "clip_ratio/high_max": 0.0020290339962230064,
      "clip_ratio/high_mean": 0.0007647377096873242,
      "clip_ratio/low_mean": 0.0006393402381945634,
      "clip_ratio/low_min": 5.114381019666325e-05,
      "clip_ratio/region_mean": 0.0014040779569768347,
      "epoch": 0.03257325190020358,
      "grad_norm": 0.11520770192146301,
      "learning_rate": 2e-07,
      "loss": 0.0267,
      "step": 349
    },
    {
      "clip_ratio/high_max": 0.0017773850668163504,
      "clip_ratio/high_mean": 0.0007189684774857596,
      "clip_ratio/low_mean": 0.0005938802150922129,
      "clip_ratio/low_min": 7.89358964539133e-05,
      "clip_ratio/region_mean": 0.0013128486643836368,
      "epoch": 0.03266658500020417,
      "grad_norm": 0.12005266547203064,
      "learning_rate": 2e-07,
      "loss": 0.0186,
      "step": 350
    },
    {
      "clip_ratio/high_max": 0.0018330966267967597,
      "clip_ratio/high_mean": 0.000767098650612752,
      "clip_ratio/low_mean": 0.0006052745466149645,
      "clip_ratio/low_min": 1.3572203897638246e-05,
      "clip_ratio/region_mean": 0.00137237318631378,
      "epoch": 0.032759918100204746,
      "grad_norm": 0.14219240844249725,
      "learning_rate": 2e-07,
      "loss": 0.0296,
      "step": 351
    },
    {
      "clip_ratio/high_max": 0.0017666100829956122,
      "clip_ratio/high_mean": 0.000725057820091024,
      "clip_ratio/low_mean": 0.0006462834753619973,
      "clip_ratio/low_min": 4.317881075621699e-05,
      "clip_ratio/region_mean": 0.0013713412663491908,
      "epoch": 0.03285325120020533,
      "grad_norm": 0.10977889597415924,
      "learning_rate": 2e-07,
      "loss": 0.0229,
      "step": 352
    },
    {
      "clip_ratio/high_max": 0.002389262012002291,
      "clip_ratio/high_mean": 0.0009287488846894121,
      "clip_ratio/low_mean": 0.0005842693053637049,
      "clip_ratio/low_min": 2.9629880373249762e-05,
      "clip_ratio/region_mean": 0.0015130181636777706,
      "epoch": 0.03294658430020592,
      "grad_norm": 0.11733007431030273,
      "learning_rate": 2e-07,
      "loss": 0.0063,
      "step": 353
    },
    {
      "clip_ratio/high_max": 0.001907180507259909,
      "clip_ratio/high_mean": 0.0008123285824694904,
      "clip_ratio/low_mean": 0.0005535774234886048,
      "clip_ratio/low_min": 2.4707741431484465e-05,
      "clip_ratio/region_mean": 0.0013659059986821376,
      "epoch": 0.0330399174002065,
      "grad_norm": 0.11988719552755356,
      "learning_rate": 2e-07,
      "loss": -0.0011,
      "step": 354
    },
    {
      "clip_ratio/high_max": 0.002105914223648142,
      "clip_ratio/high_mean": 0.0008266113309218781,
      "clip_ratio/low_mean": 0.0006236892741071642,
      "clip_ratio/low_min": 7.565508985862834e-05,
      "clip_ratio/region_mean": 0.0014503005950246006,
      "epoch": 0.03313325050020708,
      "grad_norm": 0.13023196160793304,
      "learning_rate": 2e-07,
      "loss": 0.0471,
      "step": 355
    },
    {
      "clip_ratio/high_max": 0.0018886301113525406,
      "clip_ratio/high_mean": 0.0007371505671471823,
      "clip_ratio/low_mean": 0.0006209818593561067,
      "clip_ratio/low_min": 5.636145715470775e-05,
      "clip_ratio/region_mean": 0.0013581323983089533,
      "epoch": 0.033226583600207665,
      "grad_norm": 0.12149716168642044,
      "learning_rate": 2e-07,
      "loss": 0.0286,
      "step": 356
    },
    {
      "clip_ratio/high_max": 0.0019131158514937852,
      "clip_ratio/high_mean": 0.0007662280495424056,
      "clip_ratio/low_mean": 0.000597304282564437,
      "clip_ratio/low_min": 8.841419912641868e-06,
      "clip_ratio/region_mean": 0.0013635323193739168,
      "epoch": 0.03331991670020825,
      "grad_norm": 0.12149664014577866,
      "learning_rate": 2e-07,
      "loss": 0.0352,
      "step": 357
    },
    {
      "clip_ratio/high_max": 0.0020080751564819366,
      "clip_ratio/high_mean": 0.0007916517643025145,
      "clip_ratio/low_mean": 0.0006037095026840689,
      "clip_ratio/low_min": 1.8100608031090815e-05,
      "clip_ratio/region_mean": 0.0013953612506156787,
      "epoch": 0.033413249800208836,
      "grad_norm": 0.11034026741981506,
      "learning_rate": 2e-07,
      "loss": 0.0381,
      "step": 358
    },
    {
      "clip_ratio/high_max": 0.002269225449708756,
      "clip_ratio/high_mean": 0.0009011512047436554,
      "clip_ratio/low_mean": 0.0005662503208441194,
      "clip_ratio/low_min": 4.208002246741671e-05,
      "clip_ratio/region_mean": 0.0014674015510536265,
      "epoch": 0.033506582900209414,
      "grad_norm": 0.12639440596103668,
      "learning_rate": 2e-07,
      "loss": -0.0078,
      "step": 359
    },
    {
      "clip_ratio/high_max": 0.002129264823452104,
      "clip_ratio/high_mean": 0.0008123151183099253,
      "clip_ratio/low_mean": 0.000670363697281573,
      "clip_ratio/low_min": 1.3682136341230944e-05,
      "clip_ratio/region_mean": 0.0014826787883066572,
      "epoch": 0.03359991600021,
      "grad_norm": 0.12230025231838226,
      "learning_rate": 2e-07,
      "loss": 0.0259,
      "step": 360
    },
    {
      "clip_ratio/high_max": 0.001760990751790814,
      "clip_ratio/high_mean": 0.0008231172523665009,
      "clip_ratio/low_mean": 0.0006312998539215187,
      "clip_ratio/low_min": 6.47276833660726e-05,
      "clip_ratio/region_mean": 0.001454417080822168,
      "epoch": 0.033693249100210584,
      "grad_norm": 0.12162677198648453,
      "learning_rate": 2e-07,
      "loss": 0.0564,
      "step": 361
    },
    {
      "clip_ratio/high_max": 0.002056452227407135,
      "clip_ratio/high_mean": 0.0008314186634379439,
      "clip_ratio/low_mean": 0.0006108053003117675,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001442223943740828,
      "epoch": 0.03378658220021117,
      "grad_norm": 0.12398241460323334,
      "learning_rate": 2e-07,
      "loss": 0.021,
      "step": 362
    },
    {
      "clip_ratio/high_max": 0.0020690746678155847,
      "clip_ratio/high_mean": 0.0008090111314231763,
      "clip_ratio/low_mean": 0.0007044975100143347,
      "clip_ratio/low_min": 0.00014991661100793863,
      "clip_ratio/region_mean": 0.0015135086287045851,
      "epoch": 0.03387991530021175,
      "grad_norm": 0.14264896512031555,
      "learning_rate": 2e-07,
      "loss": 0.0604,
      "step": 363
    },
    {
      "clip_ratio/high_max": 0.002066791814286262,
      "clip_ratio/high_mean": 0.0008508820974384435,
      "clip_ratio/low_mean": 0.0006410474834410707,
      "clip_ratio/low_min": 4.581278335535899e-05,
      "clip_ratio/region_mean": 0.0014919295645086095,
      "epoch": 0.03397324840021233,
      "grad_norm": 0.1389528065919876,
      "learning_rate": 2e-07,
      "loss": 0.0173,
      "step": 364
    },
    {
      "clip_ratio/high_max": 0.0020607311598723754,
      "clip_ratio/high_mean": 0.0008336198898177827,
      "clip_ratio/low_mean": 0.0006827998149674386,
      "clip_ratio/low_min": 3.025066371264984e-05,
      "clip_ratio/region_mean": 0.001516419662948465,
      "epoch": 0.03406658150021292,
      "grad_norm": 0.13245995342731476,
      "learning_rate": 2e-07,
      "loss": 0.0293,
      "step": 365
    },
    {
      "clip_ratio/high_max": 0.0016272594257316086,
      "clip_ratio/high_mean": 0.0006732027550242492,
      "clip_ratio/low_mean": 0.0007372142172243912,
      "clip_ratio/low_min": 0.00017340998419967946,
      "clip_ratio/region_mean": 0.001410416945873294,
      "epoch": 0.034159914600213497,
      "grad_norm": 0.1343669593334198,
      "learning_rate": 2e-07,
      "loss": 0.0843,
      "step": 366
    },
    {
      "clip_ratio/high_max": 0.0018048632009595167,
      "clip_ratio/high_mean": 0.0007258457371790428,
      "clip_ratio/low_mean": 0.0006483133802248631,
      "clip_ratio/low_min": 2.721192686294671e-05,
      "clip_ratio/region_mean": 0.0013741591101279482,
      "epoch": 0.03425324770021408,
      "grad_norm": 0.10857783257961273,
      "learning_rate": 2e-07,
      "loss": 0.0613,
      "step": 367
    },
    {
      "clip_ratio/high_max": 0.001979690645384835,
      "clip_ratio/high_mean": 0.0007917734492366435,
      "clip_ratio/low_mean": 0.0005602649962384021,
      "clip_ratio/low_min": 3.9397029468091205e-05,
      "clip_ratio/region_mean": 0.0013520384127332363,
      "epoch": 0.03434658080021467,
      "grad_norm": 0.12216323614120483,
      "learning_rate": 2e-07,
      "loss": 0.0275,
      "step": 368
    },
    {
      "clip_ratio/high_max": 0.0019470178194751497,
      "clip_ratio/high_mean": 0.0007820853443263331,
      "clip_ratio/low_mean": 0.0006729179413014208,
      "clip_ratio/low_min": 8.100918239506427e-05,
      "clip_ratio/region_mean": 0.001455003279261291,
      "epoch": 0.03443991390021525,
      "grad_norm": 0.1256723552942276,
      "learning_rate": 2e-07,
      "loss": 0.0141,
      "step": 369
    },
    {
      "clip_ratio/high_max": 0.0020400792091095354,
      "clip_ratio/high_mean": 0.000811651443655137,
      "clip_ratio/low_mean": 0.0007086436889949255,
      "clip_ratio/low_min": 6.742117057001451e-05,
      "clip_ratio/region_mean": 0.0015202951472019777,
      "epoch": 0.03453324700021583,
      "grad_norm": 0.12908712029457092,
      "learning_rate": 2e-07,
      "loss": 0.0543,
      "step": 370
    },
    {
      "clip_ratio/high_max": 0.0021758182047051378,
      "clip_ratio/high_mean": 0.0008371064213861246,
      "clip_ratio/low_mean": 0.0006683509545837296,
      "clip_ratio/low_min": 3.573279445845401e-05,
      "clip_ratio/region_mean": 0.001505457370512886,
      "epoch": 0.034626580100216416,
      "grad_norm": 0.12797218561172485,
      "learning_rate": 2e-07,
      "loss": 0.0561,
      "step": 371
    },
    {
      "clip_ratio/high_max": 0.0016280414820357691,
      "clip_ratio/high_mean": 0.0006990388064878061,
      "clip_ratio/low_mean": 0.0007220758470793953,
      "clip_ratio/low_min": 5.1524481023079716e-05,
      "clip_ratio/region_mean": 0.0014211146954039577,
      "epoch": 0.034719913200217,
      "grad_norm": 0.11436526477336884,
      "learning_rate": 2e-07,
      "loss": 0.0401,
      "step": 372
    },
    {
      "clip_ratio/high_max": 0.0019686389787239023,
      "clip_ratio/high_mean": 0.0008020481036510319,
      "clip_ratio/low_mean": 0.0006287805044848938,
      "clip_ratio/low_min": 5.300663633533986e-05,
      "clip_ratio/region_mean": 0.0014308286226878408,
      "epoch": 0.034813246300217586,
      "grad_norm": 0.12753590941429138,
      "learning_rate": 2e-07,
      "loss": 0.0134,
      "step": 373
    },
    {
      "clip_ratio/high_max": 0.00219043673860142,
      "clip_ratio/high_mean": 0.0009402333143953001,
      "clip_ratio/low_mean": 0.0006243069046831806,
      "clip_ratio/low_min": 5.383817006077152e-05,
      "clip_ratio/region_mean": 0.001564540227263933,
      "epoch": 0.034906579400218164,
      "grad_norm": 0.1635570526123047,
      "learning_rate": 2e-07,
      "loss": 0.0325,
      "step": 374
    },
    {
      "clip_ratio/high_max": 0.0019958456105086952,
      "clip_ratio/high_mean": 0.0008614963007858023,
      "clip_ratio/low_mean": 0.0006324863716145046,
      "clip_ratio/low_min": 1.5405472368001938e-05,
      "clip_ratio/region_mean": 0.0014939826942281798,
      "epoch": 0.03499991250021875,
      "grad_norm": 0.11014176160097122,
      "learning_rate": 2e-07,
      "loss": 0.0061,
      "step": 375
    },
    {
      "clip_ratio/high_max": 0.001989554257306736,
      "clip_ratio/high_mean": 0.0008578917222621385,
      "clip_ratio/low_mean": 0.000605685790105781,
      "clip_ratio/low_min": 4.614793988366728e-05,
      "clip_ratio/region_mean": 0.0014635774787166156,
      "epoch": 0.035093245600219335,
      "grad_norm": 0.1236497312784195,
      "learning_rate": 2e-07,
      "loss": 0.0505,
      "step": 376
    },
    {
      "clip_ratio/high_max": 0.001994188980461331,
      "clip_ratio/high_mean": 0.0008141411526594311,
      "clip_ratio/low_mean": 0.000618780763943505,
      "clip_ratio/low_min": 1.2005378266621847e-05,
      "clip_ratio/region_mean": 0.0014329219120554626,
      "epoch": 0.03518657870021991,
      "grad_norm": 0.11784907430410385,
      "learning_rate": 2e-07,
      "loss": 0.0392,
      "step": 377
    },
    {
      "clip_ratio/high_max": 0.0019694275615620427,
      "clip_ratio/high_mean": 0.00090624990662036,
      "clip_ratio/low_mean": 0.000524325178048457,
      "clip_ratio/low_min": 4.2793630200321786e-05,
      "clip_ratio/region_mean": 0.0014305751174106263,
      "epoch": 0.0352799118002205,
      "grad_norm": 0.11589766293764114,
      "learning_rate": 2e-07,
      "loss": -0.0072,
      "step": 378
    },
    {
      "clip_ratio/high_max": 0.0020863029421889223,
      "clip_ratio/high_mean": 0.0008276191092591034,
      "clip_ratio/low_mean": 0.0006072749047234538,
      "clip_ratio/low_min": 2.4620095700811362e-05,
      "clip_ratio/region_mean": 0.0014348940203490201,
      "epoch": 0.03537324490022108,
      "grad_norm": 0.12050627171993256,
      "learning_rate": 2e-07,
      "loss": 0.0111,
      "step": 379
    },
    {
      "clip_ratio/high_max": 0.0018348816483921837,
      "clip_ratio/high_mean": 0.0008027445455809357,
      "clip_ratio/low_mean": 0.0006470960997830844,
      "clip_ratio/low_min": 9.941148164216429e-06,
      "clip_ratio/region_mean": 0.0014498406380880624,
      "epoch": 0.03546657800022167,
      "grad_norm": 0.11710581183433533,
      "learning_rate": 2e-07,
      "loss": 0.0451,
      "step": 380
    },
    {
      "clip_ratio/high_max": 0.0018553924019215629,
      "clip_ratio/high_mean": 0.0007251129045471316,
      "clip_ratio/low_mean": 0.0006450925693570753,
      "clip_ratio/low_min": 2.951593887701165e-05,
      "clip_ratio/region_mean": 0.0013702054748137016,
      "epoch": 0.03555991110022225,
      "grad_norm": 0.1148415207862854,
      "learning_rate": 2e-07,
      "loss": 0.0364,
      "step": 381
    },
    {
      "clip_ratio/high_max": 0.002188382735766936,
      "clip_ratio/high_mean": 0.0007418805289489683,
      "clip_ratio/low_mean": 0.0006719032444379991,
      "clip_ratio/low_min": 8.273737421404803e-05,
      "clip_ratio/region_mean": 0.001413783771567978,
      "epoch": 0.03565324420022283,
      "grad_norm": 0.11965974420309067,
      "learning_rate": 2e-07,
      "loss": 0.0286,
      "step": 382
    },
    {
      "clip_ratio/high_max": 0.0022877613118907902,
      "clip_ratio/high_mean": 0.0008502288783347467,
      "clip_ratio/low_mean": 0.0006915737740200711,
      "clip_ratio/low_min": 6.654474600509275e-05,
      "clip_ratio/region_mean": 0.0015418026559927966,
      "epoch": 0.03574657730022342,
      "grad_norm": 0.12980860471725464,
      "learning_rate": 2e-07,
      "loss": 0.0482,
      "step": 383
    },
    {
      "clip_ratio/high_max": 0.001956745942152338,
      "clip_ratio/high_mean": 0.0007399788755719783,
      "clip_ratio/low_mean": 0.0006785868736187695,
      "clip_ratio/low_min": 1.5672016161261126e-05,
      "clip_ratio/region_mean": 0.0014185657564667054,
      "epoch": 0.035839910400224,
      "grad_norm": 0.11257439106702805,
      "learning_rate": 2e-07,
      "loss": 0.0451,
      "step": 384
    },
    {
      "clip_ratio/high_max": 0.001635877739317948,
      "clip_ratio/high_mean": 0.0007231750005303184,
      "clip_ratio/low_mean": 0.000614899397987756,
      "clip_ratio/low_min": 9.094878168980358e-05,
      "clip_ratio/region_mean": 0.0013380743876041379,
      "completions/clipped_ratio": 0.0156947544642857,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4092.0,
      "completions/mean_length": 632.9285888671875,
      "completions/mean_terminated_length": 577.7098388671875,
      "completions/min_length": 81.0,
      "completions/min_terminated_length": 81.0,
      "epoch": 0.03593324350022458,
      "grad_norm": 0.11997140198945999,
      "learning_rate": 2e-07,
      "loss": 0.0316,
      "num_tokens": 329261056.0,
      "reward": 0.5730765461921692,
      "reward_std": 0.1984192281961441,
      "rewards/simpleverify_reward/mean": 0.5730765461921692,
      "rewards/simpleverify_reward/std": 0.49463316798210144,
      "step": 385
    },
    {
      "clip_ratio/high_max": 0.0018876111207646318,
      "clip_ratio/high_mean": 0.000837262807181105,
      "clip_ratio/low_mean": 0.0005572338650381425,
      "clip_ratio/low_min": 2.6356775379099417e-05,
      "clip_ratio/region_mean": 0.0013944966776762158,
      "epoch": 0.036026576600225166,
      "grad_norm": 0.12326093018054962,
      "learning_rate": 2e-07,
      "loss": 0.0043,
      "step": 386
    },
    {
      "clip_ratio/high_max": 0.0017761959315976128,
      "clip_ratio/high_mean": 0.00077988690645725,
      "clip_ratio/low_mean": 0.0005185645404708339,
      "clip_ratio/low_min": 7.549017573182937e-05,
      "clip_ratio/region_mean": 0.0012984514578420203,
      "epoch": 0.03611990970022575,
      "grad_norm": 0.11433762311935425,
      "learning_rate": 2e-07,
      "loss": 0.0206,
      "step": 387
    },
    {
      "clip_ratio/high_max": 0.0018871435531764291,
      "clip_ratio/high_mean": 0.0007079850911395624,
      "clip_ratio/low_mean": 0.0006058954168111086,
      "clip_ratio/low_min": 2.947328903246671e-05,
      "clip_ratio/region_mean": 0.001313880507950671,
      "epoch": 0.03621324280022633,
      "grad_norm": 0.12256833165884018,
      "learning_rate": 2e-07,
      "loss": 0.0531,
      "step": 388
    },
    {
      "clip_ratio/high_max": 0.0015593749121762812,
      "clip_ratio/high_mean": 0.0006488196850114036,
      "clip_ratio/low_mean": 0.0006126592525106389,
      "clip_ratio/low_min": 4.342332704254659e-05,
      "clip_ratio/region_mean": 0.0012614789739018306,
      "epoch": 0.036306575900226914,
      "grad_norm": 0.11836711317300797,
      "learning_rate": 2e-07,
      "loss": 0.0541,
      "step": 389
    },
    {
      "clip_ratio/high_max": 0.0019476094930723775,
      "clip_ratio/high_mean": 0.0007355644811468665,
      "clip_ratio/low_mean": 0.0005683511153620202,
      "clip_ratio/low_min": 1.9876078113156836e-05,
      "clip_ratio/region_mean": 0.001303915589232929,
      "epoch": 0.0363999090002275,
      "grad_norm": 0.11679317057132721,
      "learning_rate": 2e-07,
      "loss": 0.0444,
      "step": 390
    },
    {
      "clip_ratio/high_max": 0.0021670229361916427,
      "clip_ratio/high_mean": 0.0008395259283133782,
      "clip_ratio/low_mean": 0.0005811416976939654,
      "clip_ratio/low_min": 1.2460127436497714e-05,
      "clip_ratio/region_mean": 0.0014206675768946297,
      "epoch": 0.036493242100228085,
      "grad_norm": 0.12928101420402527,
      "learning_rate": 2e-07,
      "loss": 0.0187,
      "step": 391
    },
    {
      "clip_ratio/high_max": 0.0018397084531898145,
      "clip_ratio/high_mean": 0.0007999890422070166,
      "clip_ratio/low_mean": 0.0005516105229617096,
      "clip_ratio/low_min": 1.4873869986331556e-05,
      "clip_ratio/region_mean": 0.0013515995560737792,
      "epoch": 0.03658657520022866,
      "grad_norm": 0.12298496067523956,
      "learning_rate": 2e-07,
      "loss": 0.0206,
      "step": 392
    },
    {
      "clip_ratio/high_max": 0.0020783258150913753,
      "clip_ratio/high_mean": 0.0008299843302665977,
      "clip_ratio/low_mean": 0.0004634065562640899,
      "clip_ratio/low_min": 7.659314178454224e-06,
      "clip_ratio/region_mean": 0.0012933908692502882,
      "epoch": 0.03667990830022925,
      "grad_norm": 0.1105446144938469,
      "learning_rate": 2e-07,
      "loss": 0.032,
      "step": 393
    },
    {
      "clip_ratio/high_max": 0.00172527633185382,
      "clip_ratio/high_mean": 0.0006747788793290965,
      "clip_ratio/low_mean": 0.0005321496355463751,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012069285476172809,
      "epoch": 0.036773241400229834,
      "grad_norm": 0.11346527189016342,
      "learning_rate": 2e-07,
      "loss": 0.0242,
      "step": 394
    },
    {
      "clip_ratio/high_max": 0.0018345289754506666,
      "clip_ratio/high_mean": 0.0007844047468097415,
      "clip_ratio/low_mean": 0.00048737414454080863,
      "clip_ratio/low_min": 2.3439461983798537e-05,
      "clip_ratio/region_mean": 0.0012717788813461084,
      "epoch": 0.03686657450023042,
      "grad_norm": 0.11031324416399002,
      "learning_rate": 2e-07,
      "loss": 0.0234,
      "step": 395
    },
    {
      "clip_ratio/high_max": 0.0018091752281179652,
      "clip_ratio/high_mean": 0.0007829425576346694,
      "clip_ratio/low_mean": 0.0005732427343900781,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013561852865677793,
      "epoch": 0.036959907600231,
      "grad_norm": 0.119163878262043,
      "learning_rate": 2e-07,
      "loss": 0.0337,
      "step": 396
    },
    {
      "clip_ratio/high_max": 0.001953605533344671,
      "clip_ratio/high_mean": 0.0008116526842059102,
      "clip_ratio/low_mean": 0.0005036395250499481,
      "clip_ratio/low_min": 2.3932848307595123e-05,
      "clip_ratio/region_mean": 0.0013152922001609113,
      "epoch": 0.03705324070023158,
      "grad_norm": 0.12695623934268951,
      "learning_rate": 2e-07,
      "loss": -0.0113,
      "step": 397
    },
    {
      "clip_ratio/high_max": 0.0017585911191417836,
      "clip_ratio/high_mean": 0.0007527170328103239,
      "clip_ratio/low_mean": 0.0005569904315052554,
      "clip_ratio/low_min": 7.520036706409883e-05,
      "clip_ratio/region_mean": 0.001309707480686484,
      "epoch": 0.03714657380023217,
      "grad_norm": 0.11844083666801453,
      "learning_rate": 2e-07,
      "loss": 0.0252,
      "step": 398
    },
    {
      "clip_ratio/high_max": 0.0017968105894397013,
      "clip_ratio/high_mean": 0.0006859022851131158,
      "clip_ratio/low_mean": 0.0005486042391567025,
      "clip_ratio/low_min": 2.9215374524937943e-05,
      "clip_ratio/region_mean": 0.0012345065370027442,
      "epoch": 0.03723990690023275,
      "grad_norm": 0.10583288222551346,
      "learning_rate": 2e-07,
      "loss": 0.0466,
      "step": 399
    },
    {
      "clip_ratio/high_max": 0.0019447361191851087,
      "clip_ratio/high_mean": 0.000772352710555424,
      "clip_ratio/low_mean": 0.0005394804793468211,
      "clip_ratio/low_min": 8.99151200428605e-06,
      "clip_ratio/region_mean": 0.0013118331917212345,
      "epoch": 0.03733324000023333,
      "grad_norm": 0.13289691507816315,
      "learning_rate": 2e-07,
      "loss": 0.0227,
      "step": 400
    },
    {
      "clip_ratio/high_max": 0.001714615078526549,
      "clip_ratio/high_mean": 0.0007293125145224622,
      "clip_ratio/low_mean": 0.0006347885318973567,
      "clip_ratio/low_min": 3.9188170376291964e-05,
      "clip_ratio/region_mean": 0.0013641010191349778,
      "epoch": 0.037426573100233916,
      "grad_norm": 0.13370080292224884,
      "learning_rate": 2e-07,
      "loss": 0.0714,
      "step": 401
    },
    {
      "clip_ratio/high_max": 0.0021376897420850582,
      "clip_ratio/high_mean": 0.0007666979872738011,
      "clip_ratio/low_mean": 0.0006158499963930808,
      "clip_ratio/low_min": 6.278149157878943e-05,
      "clip_ratio/region_mean": 0.001382547983666882,
      "epoch": 0.0375199062002345,
      "grad_norm": 0.11720848828554153,
      "learning_rate": 2e-07,
      "loss": 0.0251,
      "step": 402
    },
    {
      "clip_ratio/high_max": 0.002159803800168447,
      "clip_ratio/high_mean": 0.0008087530459306436,
      "clip_ratio/low_mean": 0.0005690839152521221,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013778369793726597,
      "epoch": 0.03761323930023508,
      "grad_norm": 0.12078811228275299,
      "learning_rate": 2e-07,
      "loss": -0.0064,
      "step": 403
    },
    {
      "clip_ratio/high_max": 0.0018039014466921799,
      "clip_ratio/high_mean": 0.0006723776714352425,
      "clip_ratio/low_mean": 0.0005232569683357724,
      "clip_ratio/low_min": 3.764524899452226e-05,
      "clip_ratio/region_mean": 0.0011956346570514143,
      "epoch": 0.037706572400235665,
      "grad_norm": 0.10372593253850937,
      "learning_rate": 2e-07,
      "loss": 0.0313,
      "step": 404
    },
    {
      "clip_ratio/high_max": 0.0018867071048589423,
      "clip_ratio/high_mean": 0.0007387079403997632,
      "clip_ratio/low_mean": 0.0005530236103368225,
      "clip_ratio/low_min": 5.546703960135346e-05,
      "clip_ratio/region_mean": 0.001291731583478395,
      "epoch": 0.03779990550023625,
      "grad_norm": 0.11051561683416367,
      "learning_rate": 2e-07,
      "loss": -0.0101,
      "step": 405
    },
    {
      "clip_ratio/high_max": 0.0021502488598343916,
      "clip_ratio/high_mean": 0.0008747991450945847,
      "clip_ratio/low_mean": 0.0005174204534341698,
      "clip_ratio/low_min": 2.7098690225102473e-05,
      "clip_ratio/region_mean": 0.0013922196158091538,
      "epoch": 0.037893238600236835,
      "grad_norm": 0.11935614794492722,
      "learning_rate": 2e-07,
      "loss": -0.007,
      "step": 406
    },
    {
      "clip_ratio/high_max": 0.001992880235775374,
      "clip_ratio/high_mean": 0.0007544078580394853,
      "clip_ratio/low_mean": 0.0006092137364248629,
      "clip_ratio/low_min": 5.675428292306606e-05,
      "clip_ratio/region_mean": 0.0013636215808219276,
      "epoch": 0.03798657170023741,
      "grad_norm": 0.10517723113298416,
      "learning_rate": 2e-07,
      "loss": 0.0558,
      "step": 407
    },
    {
      "clip_ratio/high_max": 0.0019211721009924076,
      "clip_ratio/high_mean": 0.0008471281707898015,
      "clip_ratio/low_mean": 0.0005720361732528545,
      "clip_ratio/low_min": 5.742740813730052e-05,
      "clip_ratio/region_mean": 0.0014191643422236666,
      "epoch": 0.038079904800238,
      "grad_norm": 0.1262596845626831,
      "learning_rate": 2e-07,
      "loss": 0.0383,
      "step": 408
    },
    {
      "clip_ratio/high_max": 0.0016142095810209867,
      "clip_ratio/high_mean": 0.0006396558183041634,
      "clip_ratio/low_mean": 0.0006194958350533852,
      "clip_ratio/low_min": 8.077622715063626e-05,
      "clip_ratio/region_mean": 0.0012591516679094639,
      "epoch": 0.038173237900238584,
      "grad_norm": 0.11597229540348053,
      "learning_rate": 2e-07,
      "loss": 0.0736,
      "step": 409
    },
    {
      "clip_ratio/high_max": 0.00210810285716434,
      "clip_ratio/high_mean": 0.0008145096126099816,
      "clip_ratio/low_mean": 0.0005393694573285757,
      "clip_ratio/low_min": 1.512834114691941e-05,
      "clip_ratio/region_mean": 0.001353879109956324,
      "epoch": 0.03826657100023917,
      "grad_norm": 0.1308620125055313,
      "learning_rate": 2e-07,
      "loss": -0.0094,
      "step": 410
    },
    {
      "clip_ratio/high_max": 0.0018993276898982003,
      "clip_ratio/high_mean": 0.0007938734706840478,
      "clip_ratio/low_mean": 0.0006028143270668807,
      "clip_ratio/low_min": 7.225111221487168e-05,
      "clip_ratio/region_mean": 0.0013966878068458755,
      "epoch": 0.03835990410023975,
      "grad_norm": 0.1226753443479538,
      "learning_rate": 2e-07,
      "loss": -0.0169,
      "step": 411
    },
    {
      "clip_ratio/high_max": 0.0016973646415863186,
      "clip_ratio/high_mean": 0.0007062099475660943,
      "clip_ratio/low_mean": 0.0005961841598036699,
      "clip_ratio/low_min": 2.399502136540832e-05,
      "clip_ratio/region_mean": 0.0013023941064602695,
      "epoch": 0.03845323720024033,
      "grad_norm": 0.1270218789577484,
      "learning_rate": 2e-07,
      "loss": -0.0047,
      "step": 412
    },
    {
      "clip_ratio/high_max": 0.0015025190659798682,
      "clip_ratio/high_mean": 0.0006012071989971446,
      "clip_ratio/low_mean": 0.0005003771575502469,
      "clip_ratio/low_min": 7.64181895647198e-05,
      "clip_ratio/region_mean": 0.0011015843447239604,
      "epoch": 0.03854657030024092,
      "grad_norm": 0.10597111284732819,
      "learning_rate": 2e-07,
      "loss": 0.0363,
      "step": 413
    },
    {
      "clip_ratio/high_max": 0.001914199863676913,
      "clip_ratio/high_mean": 0.000794652392869466,
      "clip_ratio/low_mean": 0.0006189051773617393,
      "clip_ratio/low_min": 2.7015345040126704e-05,
      "clip_ratio/region_mean": 0.0014135575402178802,
      "epoch": 0.038639903400241496,
      "grad_norm": 0.10367751866579056,
      "learning_rate": 2e-07,
      "loss": -0.0202,
      "step": 414
    },
    {
      "clip_ratio/high_max": 0.001779600846930407,
      "clip_ratio/high_mean": 0.0007130969661375275,
      "clip_ratio/low_mean": 0.0005086125875095604,
      "clip_ratio/low_min": 5.81720041736844e-06,
      "clip_ratio/region_mean": 0.0012217095281812362,
      "epoch": 0.03873323650024208,
      "grad_norm": 0.11533833295106888,
      "learning_rate": 2e-07,
      "loss": 0.0465,
      "step": 415
    },
    {
      "clip_ratio/high_max": 0.0016242836391029414,
      "clip_ratio/high_mean": 0.0007737649066257291,
      "clip_ratio/low_mean": 0.0005529297131943167,
      "clip_ratio/low_min": 6.7501891862775665e-06,
      "clip_ratio/region_mean": 0.0013266946043586358,
      "epoch": 0.038826569600242666,
      "grad_norm": 0.10784076899290085,
      "learning_rate": 2e-07,
      "loss": -0.0102,
      "step": 416
    },
    {
      "clip_ratio/high_max": 0.0018035570028587244,
      "clip_ratio/high_mean": 0.0006998252010816941,
      "clip_ratio/low_mean": 0.0006647147238254547,
      "clip_ratio/low_min": 5.3284436489775544e-05,
      "clip_ratio/region_mean": 0.0013645399267261382,
      "epoch": 0.03891990270024325,
      "grad_norm": 0.11329121887683868,
      "learning_rate": 2e-07,
      "loss": 0.0544,
      "step": 417
    },
    {
      "clip_ratio/high_max": 0.0017844442882051226,
      "clip_ratio/high_mean": 0.0007359397441177862,
      "clip_ratio/low_mean": 0.0004905389296254725,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012264786892046686,
      "epoch": 0.03901323580024383,
      "grad_norm": 0.11630301177501678,
      "learning_rate": 2e-07,
      "loss": -0.0011,
      "step": 418
    },
    {
      "clip_ratio/high_max": 0.0016670763689035084,
      "clip_ratio/high_mean": 0.0006667568459306494,
      "clip_ratio/low_mean": 0.0005660979950334877,
      "clip_ratio/low_min": 1.1857332538056653e-05,
      "clip_ratio/region_mean": 0.0012328548473306,
      "epoch": 0.039106568900244415,
      "grad_norm": 0.11150956153869629,
      "learning_rate": 2e-07,
      "loss": 0.0417,
      "step": 419
    },
    {
      "clip_ratio/high_max": 0.001763537966326112,
      "clip_ratio/high_mean": 0.0006895848982821917,
      "clip_ratio/low_mean": 0.0005921732745264308,
      "clip_ratio/low_min": 6.7146538640372455e-06,
      "clip_ratio/region_mean": 0.0012817582064599264,
      "epoch": 0.039199902000245,
      "grad_norm": 0.12021953612565994,
      "learning_rate": 2e-07,
      "loss": 0.0052,
      "step": 420
    },
    {
      "clip_ratio/high_max": 0.00216739912139019,
      "clip_ratio/high_mean": 0.0008490982108924072,
      "clip_ratio/low_mean": 0.0006336785463645356,
      "clip_ratio/low_min": 7.203700442914851e-05,
      "clip_ratio/region_mean": 0.0014827767517999746,
      "epoch": 0.039293235100245585,
      "grad_norm": 0.128702774643898,
      "learning_rate": 2e-07,
      "loss": 0.0316,
      "step": 421
    },
    {
      "clip_ratio/high_max": 0.001965448034752626,
      "clip_ratio/high_mean": 0.0007909856703918194,
      "clip_ratio/low_mean": 0.0006021543667884544,
      "clip_ratio/low_min": 4.835252730117645e-05,
      "clip_ratio/region_mean": 0.0013931400353612844,
      "epoch": 0.039386568200246164,
      "grad_norm": 0.12577465176582336,
      "learning_rate": 2e-07,
      "loss": 0.0147,
      "step": 422
    },
    {
      "clip_ratio/high_max": 0.00230452606047038,
      "clip_ratio/high_mean": 0.000896001100045396,
      "clip_ratio/low_mean": 0.0006176184015203035,
      "clip_ratio/low_min": 5.063801654614508e-05,
      "clip_ratio/region_mean": 0.0015136195033846889,
      "epoch": 0.03947990130024675,
      "grad_norm": 0.12363224476575851,
      "learning_rate": 2e-07,
      "loss": -0.006,
      "step": 423
    },
    {
      "clip_ratio/high_max": 0.0017180107897729613,
      "clip_ratio/high_mean": 0.0006837930686742766,
      "clip_ratio/low_mean": 0.0005640370090986835,
      "clip_ratio/low_min": 4.2053748984471895e-05,
      "clip_ratio/region_mean": 0.0012478301068767905,
      "epoch": 0.039573234400247334,
      "grad_norm": 0.12319812923669815,
      "learning_rate": 2e-07,
      "loss": 0.0538,
      "step": 424
    },
    {
      "clip_ratio/high_max": 0.001999053834879305,
      "clip_ratio/high_mean": 0.000756128078137408,
      "clip_ratio/low_mean": 0.0005654994674841873,
      "clip_ratio/low_min": 7.502082371502183e-05,
      "clip_ratio/region_mean": 0.0013216275401646271,
      "epoch": 0.03966656750024792,
      "grad_norm": 0.11434979736804962,
      "learning_rate": 2e-07,
      "loss": 0.08,
      "step": 425
    },
    {
      "clip_ratio/high_max": 0.0016790965091786347,
      "clip_ratio/high_mean": 0.0007002053353062365,
      "clip_ratio/low_mean": 0.0006208872709976276,
      "clip_ratio/low_min": 4.2947947804350406e-05,
      "clip_ratio/region_mean": 0.0013210925899329595,
      "epoch": 0.0397599006002485,
      "grad_norm": 0.12547720968723297,
      "learning_rate": 2e-07,
      "loss": 0.0344,
      "step": 426
    },
    {
      "clip_ratio/high_max": 0.0018979049782501534,
      "clip_ratio/high_mean": 0.0007053877670841757,
      "clip_ratio/low_mean": 0.0006482241024059476,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013536118967749644,
      "epoch": 0.03985323370024908,
      "grad_norm": 0.11440374702215195,
      "learning_rate": 2e-07,
      "loss": 0.0433,
      "step": 427
    },
    {
      "clip_ratio/high_max": 0.0014545097728841938,
      "clip_ratio/high_mean": 0.0006040916487108916,
      "clip_ratio/low_mean": 0.0006497247122752015,
      "clip_ratio/low_min": 1.0072521945403423e-05,
      "clip_ratio/region_mean": 0.001253816360986093,
      "epoch": 0.03994656680024967,
      "grad_norm": 0.1268068253993988,
      "learning_rate": 2e-07,
      "loss": 0.076,
      "step": 428
    },
    {
      "clip_ratio/high_max": 0.001509308163804235,
      "clip_ratio/high_mean": 0.0005857292799191782,
      "clip_ratio/low_mean": 0.0006329973984975368,
      "clip_ratio/low_min": 1.8884697055909783e-05,
      "clip_ratio/region_mean": 0.0012187266547698528,
      "epoch": 0.040039899900250246,
      "grad_norm": 0.11423606425523758,
      "learning_rate": 2e-07,
      "loss": 0.0533,
      "step": 429
    },
    {
      "clip_ratio/high_max": 0.0019502655923133716,
      "clip_ratio/high_mean": 0.0008069239993346855,
      "clip_ratio/low_mean": 0.0005672048828273546,
      "clip_ratio/low_min": 1.593168417457491e-05,
      "clip_ratio/region_mean": 0.0013741288748860825,
      "epoch": 0.04013323300025083,
      "grad_norm": 0.12582477927207947,
      "learning_rate": 2e-07,
      "loss": 0.006,
      "step": 430
    },
    {
      "clip_ratio/high_max": 0.0017096993869927246,
      "clip_ratio/high_mean": 0.0007167305338953156,
      "clip_ratio/low_mean": 0.0006739218351867748,
      "clip_ratio/low_min": 0.00015516630355705274,
      "clip_ratio/region_mean": 0.0013906523527111858,
      "epoch": 0.04022656610025142,
      "grad_norm": 0.12487882375717163,
      "learning_rate": 2e-07,
      "loss": 0.0914,
      "step": 431
    },
    {
      "clip_ratio/high_max": 0.0019112973131996114,
      "clip_ratio/high_mean": 0.0007482011678803246,
      "clip_ratio/low_mean": 0.0005619742469207267,
      "clip_ratio/low_min": 2.5127331355179194e-05,
      "clip_ratio/region_mean": 0.0013101754084345885,
      "epoch": 0.040319899200252,
      "grad_norm": 0.1234482005238533,
      "learning_rate": 2e-07,
      "loss": 0.0304,
      "step": 432
    },
    {
      "clip_ratio/high_max": 0.00199937034631148,
      "clip_ratio/high_mean": 0.0008280788570118602,
      "clip_ratio/low_mean": 0.0005384793967095902,
      "clip_ratio/low_min": 1.2583048373926431e-05,
      "clip_ratio/region_mean": 0.0013665582591784187,
      "epoch": 0.04041323230025258,
      "grad_norm": 0.11249708384275436,
      "learning_rate": 2e-07,
      "loss": 0.0107,
      "step": 433
    },
    {
      "clip_ratio/high_max": 0.0019216128148400458,
      "clip_ratio/high_mean": 0.000743208044241328,
      "clip_ratio/low_mean": 0.0005600183617389121,
      "clip_ratio/low_min": 4.955810436513275e-05,
      "clip_ratio/region_mean": 0.0013032264250796288,
      "epoch": 0.040506565400253165,
      "grad_norm": 0.1126217320561409,
      "learning_rate": 2e-07,
      "loss": 0.0311,
      "step": 434
    },
    {
      "clip_ratio/high_max": 0.0017897943944262806,
      "clip_ratio/high_mean": 0.0007111694994819118,
      "clip_ratio/low_mean": 0.0005982841976219788,
      "clip_ratio/low_min": 8.257147419499233e-05,
      "clip_ratio/region_mean": 0.0013094537243887316,
      "epoch": 0.04059989850025375,
      "grad_norm": 0.1288425475358963,
      "learning_rate": 2e-07,
      "loss": 0.0627,
      "step": 435
    },
    {
      "clip_ratio/high_max": 0.00198351360813831,
      "clip_ratio/high_mean": 0.0008419586083618924,
      "clip_ratio/low_mean": 0.000520566155501001,
      "clip_ratio/low_min": 1.3493091501004528e-05,
      "clip_ratio/region_mean": 0.0013625247520394623,
      "epoch": 0.040693231600254336,
      "grad_norm": 0.12404875457286835,
      "learning_rate": 2e-07,
      "loss": -0.0074,
      "step": 436
    },
    {
      "clip_ratio/high_max": 0.002239898378320504,
      "clip_ratio/high_mean": 0.0009122826268139761,
      "clip_ratio/low_mean": 0.00048747577056929003,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013997583810123615,
      "epoch": 0.040786564700254914,
      "grad_norm": 0.11860135942697525,
      "learning_rate": 2e-07,
      "loss": -0.0181,
      "step": 437
    },
    {
      "clip_ratio/high_max": 0.0019366519190953113,
      "clip_ratio/high_mean": 0.0007867393214837648,
      "clip_ratio/low_mean": 0.0006420954059649375,
      "clip_ratio/low_min": 7.760135940770851e-05,
      "clip_ratio/region_mean": 0.001428834737453144,
      "epoch": 0.0408798978002555,
      "grad_norm": 0.13247065246105194,
      "learning_rate": 2e-07,
      "loss": 0.0136,
      "step": 438
    },
    {
      "clip_ratio/high_max": 0.0017299235769314691,
      "clip_ratio/high_mean": 0.0007306657516892301,
      "clip_ratio/low_mean": 0.000673707900205045,
      "clip_ratio/low_min": 8.215314664994366e-05,
      "clip_ratio/region_mean": 0.0014043736664461903,
      "epoch": 0.040973230900256084,
      "grad_norm": 0.124836266040802,
      "learning_rate": 2e-07,
      "loss": 0.0509,
      "step": 439
    },
    {
      "clip_ratio/high_max": 0.0019744774835999124,
      "clip_ratio/high_mean": 0.0007914960115158465,
      "clip_ratio/low_mean": 0.0005792353731521871,
      "clip_ratio/low_min": 7.542397679571877e-05,
      "clip_ratio/region_mean": 0.0013707314028579276,
      "epoch": 0.04106656400025666,
      "grad_norm": 0.11174217611551285,
      "learning_rate": 2e-07,
      "loss": 0.0532,
      "step": 440
    },
    {
      "clip_ratio/high_max": 0.0020874797010037582,
      "clip_ratio/high_mean": 0.0008413058922087657,
      "clip_ratio/low_mean": 0.0006269640816753963,
      "clip_ratio/low_min": 3.314004925414338e-05,
      "clip_ratio/region_mean": 0.0014682699766126461,
      "epoch": 0.04115989710025725,
      "grad_norm": 0.12802769243717194,
      "learning_rate": 2e-07,
      "loss": 0.0781,
      "step": 441
    },
    {
      "clip_ratio/high_max": 0.0018837543611880392,
      "clip_ratio/high_mean": 0.0007623668952874141,
      "clip_ratio/low_mean": 0.0005598945790552534,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013222614979895297,
      "epoch": 0.04125323020025783,
      "grad_norm": 0.12944675981998444,
      "learning_rate": 2e-07,
      "loss": 0.0376,
      "step": 442
    },
    {
      "clip_ratio/high_max": 0.0019327346344653051,
      "clip_ratio/high_mean": 0.0008591074183641467,
      "clip_ratio/low_mean": 0.0006016092311256216,
      "clip_ratio/low_min": 5.037430673837662e-05,
      "clip_ratio/region_mean": 0.00146071665949421,
      "epoch": 0.04134656330025842,
      "grad_norm": 0.12969927489757538,
      "learning_rate": 2e-07,
      "loss": -0.0024,
      "step": 443
    },
    {
      "clip_ratio/high_max": 0.001821817520976765,
      "clip_ratio/high_mean": 0.0007717122698522871,
      "clip_ratio/low_mean": 0.000641424101559096,
      "clip_ratio/low_min": 4.92533117721905e-05,
      "clip_ratio/region_mean": 0.0014131363968772348,
      "epoch": 0.041439896400258996,
      "grad_norm": 0.12749607861042023,
      "learning_rate": 2e-07,
      "loss": 0.0339,
      "step": 444
    },
    {
      "clip_ratio/high_max": 0.001941720984177664,
      "clip_ratio/high_mean": 0.0008374235530936858,
      "clip_ratio/low_mean": 0.0005205985971770133,
      "clip_ratio/low_min": 2.4299011784023605e-05,
      "clip_ratio/region_mean": 0.0013580221602751408,
      "epoch": 0.04153322950025958,
      "grad_norm": 0.13302521407604218,
      "learning_rate": 2e-07,
      "loss": 0.035,
      "step": 445
    },
    {
      "clip_ratio/high_max": 0.0020225475091137923,
      "clip_ratio/high_mean": 0.0007231357540149475,
      "clip_ratio/low_mean": 0.0005122848124301527,
      "clip_ratio/low_min": 4.80782582599204e-05,
      "clip_ratio/region_mean": 0.001235420579178026,
      "epoch": 0.04162656260026017,
      "grad_norm": 0.11125293374061584,
      "learning_rate": 2e-07,
      "loss": 0.0232,
      "step": 446
    },
    {
      "clip_ratio/high_max": 0.00214793391933199,
      "clip_ratio/high_mean": 0.0009180108863802161,
      "clip_ratio/low_mean": 0.0005739794632972917,
      "clip_ratio/low_min": 2.6883111786446534e-05,
      "clip_ratio/region_mean": 0.0014919903333066031,
      "epoch": 0.04171989570026075,
      "grad_norm": 0.1331784725189209,
      "learning_rate": 2e-07,
      "loss": -0.0276,
      "step": 447
    },
    {
      "clip_ratio/high_max": 0.0019525597926985938,
      "clip_ratio/high_mean": 0.0008614203106844798,
      "clip_ratio/low_mean": 0.0005691061542165698,
      "clip_ratio/low_min": 4.080146027263254e-05,
      "clip_ratio/region_mean": 0.001430526466720039,
      "epoch": 0.04181322880026133,
      "grad_norm": 0.11646457016468048,
      "learning_rate": 2e-07,
      "loss": -0.0075,
      "step": 448
    },
    {
      "clip_ratio/high_max": 0.0016937920481723268,
      "clip_ratio/high_mean": 0.0007698446988797514,
      "clip_ratio/low_mean": 0.000697033019605442,
      "clip_ratio/low_min": 9.306134415965062e-06,
      "clip_ratio/region_mean": 0.001466877707571257,
      "epoch": 0.041906561900261916,
      "grad_norm": 0.11478401720523834,
      "learning_rate": 2e-07,
      "loss": 0.0131,
      "step": 449
    },
    {
      "clip_ratio/high_max": 0.0016763952407927718,
      "clip_ratio/high_mean": 0.0007130775848054327,
      "clip_ratio/low_mean": 0.0005509589773282642,
      "clip_ratio/low_min": 1.3105473044561222e-05,
      "clip_ratio/region_mean": 0.001264036549400771,
      "epoch": 0.0419998950002625,
      "grad_norm": 0.12680761516094208,
      "learning_rate": 2e-07,
      "loss": 0.0403,
      "step": 450
    },
    {
      "clip_ratio/high_max": 0.0018596082627482247,
      "clip_ratio/high_mean": 0.0008023961645449162,
      "clip_ratio/low_mean": 0.0006026724131515948,
      "clip_ratio/low_min": 3.8710002627340145e-05,
      "clip_ratio/region_mean": 0.0014050685858819634,
      "epoch": 0.042093228100263086,
      "grad_norm": 0.13138644397258759,
      "learning_rate": 2e-07,
      "loss": 0.0515,
      "step": 451
    },
    {
      "clip_ratio/high_max": 0.0014278760972956661,
      "clip_ratio/high_mean": 0.000624245611106744,
      "clip_ratio/low_mean": 0.0007028806039670599,
      "clip_ratio/low_min": 8.194201291189529e-05,
      "clip_ratio/region_mean": 0.0013271262214402668,
      "epoch": 0.042186561200263664,
      "grad_norm": 0.1271778643131256,
      "learning_rate": 2e-07,
      "loss": 0.0911,
      "step": 452
    },
    {
      "clip_ratio/high_max": 0.002128368207195308,
      "clip_ratio/high_mean": 0.0008931682132242713,
      "clip_ratio/low_mean": 0.0006133725819381652,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001506540778791532,
      "epoch": 0.04227989430026425,
      "grad_norm": 0.12002625316381454,
      "learning_rate": 2e-07,
      "loss": 0.0447,
      "step": 453
    },
    {
      "clip_ratio/high_max": 0.0016965694958344102,
      "clip_ratio/high_mean": 0.0007292480495380005,
      "clip_ratio/low_mean": 0.0006118449573477847,
      "clip_ratio/low_min": 4.237728899170179e-05,
      "clip_ratio/region_mean": 0.0013410930259851739,
      "epoch": 0.042373227400264835,
      "grad_norm": 0.1293649524450302,
      "learning_rate": 2e-07,
      "loss": -0.0072,
      "step": 454
    },
    {
      "clip_ratio/high_max": 0.001799706464225892,
      "clip_ratio/high_mean": 0.0007703606115683215,
      "clip_ratio/low_mean": 0.0006758462677680654,
      "clip_ratio/low_min": 5.7804901189228985e-05,
      "clip_ratio/region_mean": 0.0014462068756984081,
      "epoch": 0.04246656050026541,
      "grad_norm": 0.12729597091674805,
      "learning_rate": 2e-07,
      "loss": 0.0361,
      "step": 455
    },
    {
      "clip_ratio/high_max": 0.002166321442928165,
      "clip_ratio/high_mean": 0.0008543400144844782,
      "clip_ratio/low_mean": 0.0006130776746431366,
      "clip_ratio/low_min": 3.2258063583867624e-05,
      "clip_ratio/region_mean": 0.0014674177145934664,
      "epoch": 0.042559893600266,
      "grad_norm": 0.13109572231769562,
      "learning_rate": 2e-07,
      "loss": 0.0448,
      "step": 456
    },
    {
      "clip_ratio/high_max": 0.0021004257214372046,
      "clip_ratio/high_mean": 0.0008129820271278732,
      "clip_ratio/low_mean": 0.0005972016897430876,
      "clip_ratio/low_min": 2.0955032596248202e-05,
      "clip_ratio/region_mean": 0.0014101837623456959,
      "epoch": 0.04265322670026658,
      "grad_norm": 0.11769860982894897,
      "learning_rate": 2e-07,
      "loss": 0.0177,
      "step": 457
    },
    {
      "clip_ratio/high_max": 0.0017277467231906485,
      "clip_ratio/high_mean": 0.0007483531317120651,
      "clip_ratio/low_mean": 0.0005988680877635488,
      "clip_ratio/low_min": 1.4288980310084298e-05,
      "clip_ratio/region_mean": 0.0013472212121996563,
      "epoch": 0.04274655980026717,
      "grad_norm": 0.12136774510145187,
      "learning_rate": 2e-07,
      "loss": 0.0323,
      "step": 458
    },
    {
      "clip_ratio/high_max": 0.0019920104241464287,
      "clip_ratio/high_mean": 0.0008281200898636598,
      "clip_ratio/low_mean": 0.0006895135193190072,
      "clip_ratio/low_min": 4.762592197948834e-05,
      "clip_ratio/region_mean": 0.001517633609182667,
      "epoch": 0.04283989290026775,
      "grad_norm": 0.12881548702716827,
      "learning_rate": 2e-07,
      "loss": 0.0369,
      "step": 459
    },
    {
      "clip_ratio/high_max": 0.0018852931025321595,
      "clip_ratio/high_mean": 0.0008347364746441599,
      "clip_ratio/low_mean": 0.000606104918915662,
      "clip_ratio/low_min": 1.300457734032534e-05,
      "clip_ratio/region_mean": 0.0014408413953788113,
      "epoch": 0.04293322600026833,
      "grad_norm": 0.126173734664917,
      "learning_rate": 2e-07,
      "loss": 0.0458,
      "step": 460
    },
    {
      "clip_ratio/high_max": 0.0019430297397775576,
      "clip_ratio/high_mean": 0.0007843109597160947,
      "clip_ratio/low_mean": 0.0005729915283154696,
      "clip_ratio/low_min": 2.122961996064987e-05,
      "clip_ratio/region_mean": 0.0013573024698416702,
      "epoch": 0.04302655910026892,
      "grad_norm": 0.11492270231246948,
      "learning_rate": 2e-07,
      "loss": 0.0278,
      "step": 461
    },
    {
      "clip_ratio/high_max": 0.0019511612335918471,
      "clip_ratio/high_mean": 0.0007482991186407162,
      "clip_ratio/low_mean": 0.0005886743383598514,
      "clip_ratio/low_min": 2.108345324813854e-05,
      "clip_ratio/region_mean": 0.0013369734551815782,
      "epoch": 0.0431198922002695,
      "grad_norm": 0.13352049887180328,
      "learning_rate": 2e-07,
      "loss": 0.0189,
      "step": 462
    },
    {
      "clip_ratio/high_max": 0.002021753120061476,
      "clip_ratio/high_mean": 0.0007751320263196249,
      "clip_ratio/low_mean": 0.0006295952043728903,
      "clip_ratio/low_min": 8.166732186509762e-06,
      "clip_ratio/region_mean": 0.001404727234330494,
      "epoch": 0.04321322530027008,
      "grad_norm": 0.12256651371717453,
      "learning_rate": 2e-07,
      "loss": 0.0199,
      "step": 463
    },
    {
      "clip_ratio/high_max": 0.002125372953742044,
      "clip_ratio/high_mean": 0.0008464869752060622,
      "clip_ratio/low_mean": 0.0005628256531053921,
      "clip_ratio/low_min": 4.4712321141560096e-05,
      "clip_ratio/region_mean": 0.001409312626492465,
      "epoch": 0.043306558400270666,
      "grad_norm": 0.1265394240617752,
      "learning_rate": 2e-07,
      "loss": 0.0051,
      "step": 464
    },
    {
      "clip_ratio/high_max": 0.002220640206360258,
      "clip_ratio/high_mean": 0.0008117698871501489,
      "clip_ratio/low_mean": 0.0006259317251533503,
      "clip_ratio/low_min": 2.27531127166003e-05,
      "clip_ratio/region_mean": 0.0014377016232174356,
      "epoch": 0.04339989150027125,
      "grad_norm": 0.12159605324268341,
      "learning_rate": 2e-07,
      "loss": 0.0544,
      "step": 465
    },
    {
      "clip_ratio/high_max": 0.001920515984238591,
      "clip_ratio/high_mean": 0.0007843609191695577,
      "clip_ratio/low_mean": 0.0006304565013124375,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014148173941066489,
      "epoch": 0.04349322460027183,
      "grad_norm": 0.13625863194465637,
      "learning_rate": 2e-07,
      "loss": 0.0622,
      "step": 466
    },
    {
      "clip_ratio/high_max": 0.0020645483091357164,
      "clip_ratio/high_mean": 0.0008827263627608772,
      "clip_ratio/low_mean": 0.0006521402965518064,
      "clip_ratio/low_min": 3.399605520826299e-05,
      "clip_ratio/region_mean": 0.0015348666638601571,
      "epoch": 0.043586557700272414,
      "grad_norm": 0.12838351726531982,
      "learning_rate": 2e-07,
      "loss": 0.0022,
      "step": 467
    },
    {
      "clip_ratio/high_max": 0.0017020577724906616,
      "clip_ratio/high_mean": 0.0006898002202433418,
      "clip_ratio/low_mean": 0.0006109080713940784,
      "clip_ratio/low_min": 3.2897947676246986e-05,
      "clip_ratio/region_mean": 0.001300708288908936,
      "epoch": 0.043679890800273,
      "grad_norm": 0.12890274822711945,
      "learning_rate": 2e-07,
      "loss": 0.0334,
      "step": 468
    },
    {
      "clip_ratio/high_max": 0.001804167539376067,
      "clip_ratio/high_mean": 0.0008270563594123814,
      "clip_ratio/low_mean": 0.0006516645971714752,
      "clip_ratio/low_min": 5.964106367173372e-05,
      "clip_ratio/region_mean": 0.001478720940212952,
      "epoch": 0.043773223900273585,
      "grad_norm": 0.13219425082206726,
      "learning_rate": 2e-07,
      "loss": 0.0302,
      "step": 469
    },
    {
      "clip_ratio/high_max": 0.00205077524879016,
      "clip_ratio/high_mean": 0.0007775441445119213,
      "clip_ratio/low_mean": 0.0005900697451579617,
      "clip_ratio/low_min": 2.8003352781524882e-05,
      "clip_ratio/region_mean": 0.0013676139060407877,
      "epoch": 0.04386655700027416,
      "grad_norm": 0.12591680884361267,
      "learning_rate": 2e-07,
      "loss": 0.0352,
      "step": 470
    },
    {
      "clip_ratio/high_max": 0.001639964582864195,
      "clip_ratio/high_mean": 0.0007065572135616094,
      "clip_ratio/low_mean": 0.0006671074734185822,
      "clip_ratio/low_min": 8.493865789205302e-05,
      "clip_ratio/region_mean": 0.001373664716084022,
      "epoch": 0.04395989010027475,
      "grad_norm": 0.12724579870700836,
      "learning_rate": 2e-07,
      "loss": 0.0751,
      "step": 471
    },
    {
      "clip_ratio/high_max": 0.0019803974428214133,
      "clip_ratio/high_mean": 0.0007915250698715681,
      "clip_ratio/low_mean": 0.0006204102937772404,
      "clip_ratio/low_min": 3.233541428926401e-05,
      "clip_ratio/region_mean": 0.001411935365467798,
      "epoch": 0.044053223200275334,
      "grad_norm": 0.12191016227006912,
      "learning_rate": 2e-07,
      "loss": 0.0444,
      "step": 472
    },
    {
      "clip_ratio/high_max": 0.002042929372692015,
      "clip_ratio/high_mean": 0.0009011866104629007,
      "clip_ratio/low_mean": 0.0005229233393038157,
      "clip_ratio/low_min": 2.307359318365343e-05,
      "clip_ratio/region_mean": 0.0014241099415812641,
      "epoch": 0.04414655630027592,
      "grad_norm": 0.12842029333114624,
      "learning_rate": 2e-07,
      "loss": -0.0266,
      "step": 473
    },
    {
      "clip_ratio/high_max": 0.0021136288487468846,
      "clip_ratio/high_mean": 0.0007393581581709441,
      "clip_ratio/low_mean": 0.0005775156187155517,
      "clip_ratio/low_min": 2.6750150027510244e-05,
      "clip_ratio/region_mean": 0.0013168737896194216,
      "epoch": 0.0442398894002765,
      "grad_norm": 0.12079551070928574,
      "learning_rate": 2e-07,
      "loss": 0.0465,
      "step": 474
    },
    {
      "clip_ratio/high_max": 0.001752253936501802,
      "clip_ratio/high_mean": 0.0007918350561340048,
      "clip_ratio/low_mean": 0.0005751688222517259,
      "clip_ratio/low_min": 1.2891914593637921e-05,
      "clip_ratio/region_mean": 0.0013670038679265417,
      "epoch": 0.04433322250027708,
      "grad_norm": 0.12179074436426163,
      "learning_rate": 2e-07,
      "loss": 0.0168,
      "step": 475
    },
    {
      "clip_ratio/high_max": 0.0018314347471459769,
      "clip_ratio/high_mean": 0.0007210937892523361,
      "clip_ratio/low_mean": 0.000608924852713244,
      "clip_ratio/low_min": 3.547241522028344e-05,
      "clip_ratio/region_mean": 0.0013300186074047815,
      "epoch": 0.04442655560027767,
      "grad_norm": 0.13796447217464447,
      "learning_rate": 2e-07,
      "loss": 0.022,
      "step": 476
    },
    {
      "clip_ratio/high_max": 0.001912835294206161,
      "clip_ratio/high_mean": 0.0007472723336832132,
      "clip_ratio/low_mean": 0.0006029669657436898,
      "clip_ratio/low_min": 2.3364485969068483e-05,
      "clip_ratio/region_mean": 0.001350239344901638,
      "epoch": 0.04451988870027825,
      "grad_norm": 0.1278499811887741,
      "learning_rate": 2e-07,
      "loss": 0.015,
      "step": 477
    },
    {
      "clip_ratio/high_max": 0.0021084704567329027,
      "clip_ratio/high_mean": 0.0007543496121797943,
      "clip_ratio/low_mean": 0.0006371656218107091,
      "clip_ratio/low_min": 1.177246213046601e-05,
      "clip_ratio/region_mean": 0.0013915152194385882,
      "epoch": 0.04461322180027883,
      "grad_norm": 0.12245044857263565,
      "learning_rate": 2e-07,
      "loss": 0.0325,
      "step": 478
    },
    {
      "clip_ratio/high_max": 0.0019993680471088737,
      "clip_ratio/high_mean": 0.0008241827636084054,
      "clip_ratio/low_mean": 0.000601893492785166,
      "clip_ratio/low_min": 3.5972205296275206e-05,
      "clip_ratio/region_mean": 0.0014260762509366032,
      "epoch": 0.044706554900279416,
      "grad_norm": 0.1255422979593277,
      "learning_rate": 2e-07,
      "loss": -0.0137,
      "step": 479
    },
    {
      "clip_ratio/high_max": 0.0018301896343473345,
      "clip_ratio/high_mean": 0.000773581545217894,
      "clip_ratio/low_mean": 0.0005611393589788349,
      "clip_ratio/low_min": 2.8306192689342424e-05,
      "clip_ratio/region_mean": 0.001334720913291676,
      "epoch": 0.04479988800028,
      "grad_norm": 0.11499013006687164,
      "learning_rate": 2e-07,
      "loss": 0.0049,
      "step": 480
    },
    {
      "clip_ratio/high_max": 0.0018726084963418543,
      "clip_ratio/high_mean": 0.0007928112136141863,
      "clip_ratio/low_mean": 0.0006376321052812273,
      "clip_ratio/low_min": 3.402401307539549e-05,
      "clip_ratio/region_mean": 0.0014304432916105725,
      "epoch": 0.04489322110028058,
      "grad_norm": 0.12581494450569153,
      "learning_rate": 2e-07,
      "loss": 0.0433,
      "step": 481
    },
    {
      "clip_ratio/high_max": 0.0018266648694407195,
      "clip_ratio/high_mean": 0.0007048752722766949,
      "clip_ratio/low_mean": 0.000612429848388274,
      "clip_ratio/low_min": 4.617186277755536e-05,
      "clip_ratio/region_mean": 0.0013173050938348752,
      "epoch": 0.044986554200281165,
      "grad_norm": 0.11227978765964508,
      "learning_rate": 2e-07,
      "loss": 0.013,
      "step": 482
    },
    {
      "clip_ratio/high_max": 0.002026835409196792,
      "clip_ratio/high_mean": 0.0008249577622336801,
      "clip_ratio/low_mean": 0.000664360634800687,
      "clip_ratio/low_min": 5.187642636883538e-05,
      "clip_ratio/region_mean": 0.0014893184088577982,
      "epoch": 0.04507988730028175,
      "grad_norm": 0.13401319086551666,
      "learning_rate": 2e-07,
      "loss": 0.0283,
      "step": 483
    },
    {
      "clip_ratio/high_max": 0.00200418126405566,
      "clip_ratio/high_mean": 0.0007258249979713582,
      "clip_ratio/low_mean": 0.0006042447566869669,
      "clip_ratio/low_min": 1.4137072867015377e-05,
      "clip_ratio/region_mean": 0.0013300697755767033,
      "epoch": 0.045173220400282335,
      "grad_norm": 0.1273982673883438,
      "learning_rate": 2e-07,
      "loss": 0.0032,
      "step": 484
    },
    {
      "clip_ratio/high_max": 0.0019962828628194984,
      "clip_ratio/high_mean": 0.0007988323086465243,
      "clip_ratio/low_mean": 0.000614897369814571,
      "clip_ratio/low_min": 6.21268527538632e-05,
      "clip_ratio/region_mean": 0.0014137296966509894,
      "epoch": 0.04526655350028291,
      "grad_norm": 0.11907685548067093,
      "learning_rate": 2e-07,
      "loss": 0.0212,
      "step": 485
    },
    {
      "clip_ratio/high_max": 0.002219936446635984,
      "clip_ratio/high_mean": 0.0008455584866169374,
      "clip_ratio/low_mean": 0.0006325342674244894,
      "clip_ratio/low_min": 3.939645739592379e-05,
      "clip_ratio/region_mean": 0.0014780927376705222,
      "epoch": 0.0453598866002835,
      "grad_norm": 0.13313397765159607,
      "learning_rate": 2e-07,
      "loss": 0.0277,
      "step": 486
    },
    {
      "clip_ratio/high_max": 0.0018361723159614485,
      "clip_ratio/high_mean": 0.0008283569550258107,
      "clip_ratio/low_mean": 0.0005664485033776145,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013948054547654465,
      "epoch": 0.045453219700284084,
      "grad_norm": 0.13463589549064636,
      "learning_rate": 2e-07,
      "loss": -0.0271,
      "step": 487
    },
    {
      "clip_ratio/high_max": 0.0019077291108260397,
      "clip_ratio/high_mean": 0.0007643712706340011,
      "clip_ratio/low_mean": 0.0006722425578118418,
      "clip_ratio/low_min": 2.313957884325646e-05,
      "clip_ratio/region_mean": 0.0014366138166224118,
      "epoch": 0.04554655280028467,
      "grad_norm": 0.12350380420684814,
      "learning_rate": 2e-07,
      "loss": 0.0377,
      "step": 488
    },
    {
      "clip_ratio/high_max": 0.001878851544461213,
      "clip_ratio/high_mean": 0.0007357447684626095,
      "clip_ratio/low_mean": 0.0006696215423289686,
      "clip_ratio/low_min": 1.1759172593883704e-05,
      "clip_ratio/region_mean": 0.0014053662998776417,
      "epoch": 0.04563988590028525,
      "grad_norm": 0.12656685709953308,
      "learning_rate": 2e-07,
      "loss": 0.0696,
      "step": 489
    },
    {
      "clip_ratio/high_max": 0.002309049385075923,
      "clip_ratio/high_mean": 0.0008815994933684124,
      "clip_ratio/low_mean": 0.0006200631687534042,
      "clip_ratio/low_min": 5.387371584220091e-05,
      "clip_ratio/region_mean": 0.0015016626712167636,
      "epoch": 0.04573321900028583,
      "grad_norm": 0.12792600691318512,
      "learning_rate": 2e-07,
      "loss": 0.0118,
      "step": 490
    },
    {
      "clip_ratio/high_max": 0.001952918028109707,
      "clip_ratio/high_mean": 0.0007988641318661394,
      "clip_ratio/low_mean": 0.0006136745596450055,
      "clip_ratio/low_min": 3.3151954994536936e-05,
      "clip_ratio/region_mean": 0.0014125387242529541,
      "epoch": 0.04582655210028642,
      "grad_norm": 0.1305781602859497,
      "learning_rate": 2e-07,
      "loss": 0.0059,
      "step": 491
    },
    {
      "clip_ratio/high_max": 0.0018082264323311392,
      "clip_ratio/high_mean": 0.0007484291072614724,
      "clip_ratio/low_mean": 0.0007289647001016419,
      "clip_ratio/low_min": 9.058684463525424e-05,
      "clip_ratio/region_mean": 0.0014773938310099766,
      "epoch": 0.045919885200286996,
      "grad_norm": 0.12669751048088074,
      "learning_rate": 2e-07,
      "loss": 0.0522,
      "step": 492
    },
    {
      "clip_ratio/high_max": 0.00223208568058908,
      "clip_ratio/high_mean": 0.0010526750411372632,
      "clip_ratio/low_mean": 0.0006104895664975629,
      "clip_ratio/low_min": 1.1200716471648775e-05,
      "clip_ratio/region_mean": 0.0016631646431051195,
      "epoch": 0.04601321830028758,
      "grad_norm": 0.17110952734947205,
      "learning_rate": 2e-07,
      "loss": -0.0142,
      "step": 493
    },
    {
      "clip_ratio/high_max": 0.0019754916247620713,
      "clip_ratio/high_mean": 0.000790720036093262,
      "clip_ratio/low_mean": 0.000616987883404363,
      "clip_ratio/low_min": 2.3951964976731688e-05,
      "clip_ratio/region_mean": 0.0014077079031267203,
      "epoch": 0.046106551400288166,
      "grad_norm": 0.12436029314994812,
      "learning_rate": 2e-07,
      "loss": 0.026,
      "step": 494
    },
    {
      "clip_ratio/high_max": 0.0019275807462690864,
      "clip_ratio/high_mean": 0.000853837718750583,
      "clip_ratio/low_mean": 0.0006897648054291494,
      "clip_ratio/low_min": 4.1779740968195256e-05,
      "clip_ratio/region_mean": 0.001543602513265796,
      "epoch": 0.04619988450028875,
      "grad_norm": 0.12672999501228333,
      "learning_rate": 2e-07,
      "loss": 0.0268,
      "step": 495
    },
    {
      "clip_ratio/high_max": 0.002022351596679073,
      "clip_ratio/high_mean": 0.0008107790399662917,
      "clip_ratio/low_mean": 0.0005935219105595024,
      "clip_ratio/low_min": 4.6087600367172854e-05,
      "clip_ratio/region_mean": 0.0014043009650777094,
      "epoch": 0.04629321760028933,
      "grad_norm": 0.13803862035274506,
      "learning_rate": 2e-07,
      "loss": 0.0553,
      "step": 496
    },
    {
      "clip_ratio/high_max": 0.0022692137499689125,
      "clip_ratio/high_mean": 0.0008730502522666939,
      "clip_ratio/low_mean": 0.0006377903373504523,
      "clip_ratio/low_min": 3.6505057323665824e-05,
      "clip_ratio/region_mean": 0.001510840593255125,
      "epoch": 0.046386550700289915,
      "grad_norm": 0.11997704207897186,
      "learning_rate": 2e-07,
      "loss": 0.0386,
      "step": 497
    },
    {
      "clip_ratio/high_max": 0.0017912539587996434,
      "clip_ratio/high_mean": 0.0007183847937994869,
      "clip_ratio/low_mean": 0.0005708549106202554,
      "clip_ratio/low_min": 5.4810121582704596e-05,
      "clip_ratio/region_mean": 0.0012892397171526682,
      "epoch": 0.0464798838002905,
      "grad_norm": 0.13851787149906158,
      "learning_rate": 2e-07,
      "loss": -0.007,
      "step": 498
    },
    {
      "clip_ratio/high_max": 0.002143704092304688,
      "clip_ratio/high_mean": 0.0008559335401514545,
      "clip_ratio/low_mean": 0.0006546061895278399,
      "clip_ratio/low_min": 5.927369147684658e-05,
      "clip_ratio/region_mean": 0.0015105397360457573,
      "epoch": 0.046573216900291085,
      "grad_norm": 0.12724709510803223,
      "learning_rate": 2e-07,
      "loss": 0.0162,
      "step": 499
    },
    {
      "clip_ratio/high_max": 0.0018135844547941815,
      "clip_ratio/high_mean": 0.0008107461299005081,
      "clip_ratio/low_mean": 0.0005898757226532325,
      "clip_ratio/low_min": 2.2519459889736027e-05,
      "clip_ratio/region_mean": 0.0014006218661961611,
      "epoch": 0.046666550000291664,
      "grad_norm": 0.12625931203365326,
      "learning_rate": 2e-07,
      "loss": 0.0485,
      "step": 500
    },
    {
      "clip_ratio/high_max": 0.0018712252604018431,
      "clip_ratio/high_mean": 0.0008269804593510344,
      "clip_ratio/low_mean": 0.0006532924689963693,
      "clip_ratio/low_min": 1.26237127915374e-05,
      "clip_ratio/region_mean": 0.0014802729310758878,
      "epoch": 0.04675988310029225,
      "grad_norm": 0.1275644749403,
      "learning_rate": 2e-07,
      "loss": -0.0084,
      "step": 501
    },
    {
      "clip_ratio/high_max": 0.0021732505156251136,
      "clip_ratio/high_mean": 0.0008898263495211722,
      "clip_ratio/low_mean": 0.0006084626156734885,
      "clip_ratio/low_min": 2.1192829990468454e-05,
      "clip_ratio/region_mean": 0.0014982889697421342,
      "epoch": 0.046853216200292834,
      "grad_norm": 0.14466458559036255,
      "learning_rate": 2e-07,
      "loss": 0.0107,
      "step": 502
    },
    {
      "clip_ratio/high_max": 0.0020997343817725778,
      "clip_ratio/high_mean": 0.0008563275205233367,
      "clip_ratio/low_mean": 0.0006268360793910688,
      "clip_ratio/low_min": 7.52789687794575e-05,
      "clip_ratio/region_mean": 0.0014831635926384479,
      "epoch": 0.04694654930029342,
      "grad_norm": 0.12120368331670761,
      "learning_rate": 2e-07,
      "loss": 0.0222,
      "step": 503
    },
    {
      "clip_ratio/high_max": 0.0020162120927125216,
      "clip_ratio/high_mean": 0.0009255284076061798,
      "clip_ratio/low_mean": 0.0006706384956487454,
      "clip_ratio/low_min": 2.7927195333177224e-05,
      "clip_ratio/region_mean": 0.0015961669123498723,
      "epoch": 0.047039882400294,
      "grad_norm": 0.12308359146118164,
      "learning_rate": 2e-07,
      "loss": -0.0094,
      "step": 504
    },
    {
      "clip_ratio/high_max": 0.0023234796535689384,
      "clip_ratio/high_mean": 0.000791755930549698,
      "clip_ratio/low_mean": 0.0006560724268638296,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014478283555945382,
      "epoch": 0.04713321550029458,
      "grad_norm": 0.13322095572948456,
      "learning_rate": 2e-07,
      "loss": 0.0711,
      "step": 505
    },
    {
      "clip_ratio/high_max": 0.0017675724739092402,
      "clip_ratio/high_mean": 0.0007076291722114547,
      "clip_ratio/low_mean": 0.0006863769012852572,
      "clip_ratio/low_min": 8.11994168543606e-05,
      "clip_ratio/region_mean": 0.0013940060598542914,
      "epoch": 0.04722654860029517,
      "grad_norm": 0.12100698053836823,
      "learning_rate": 2e-07,
      "loss": 0.0464,
      "step": 506
    },
    {
      "clip_ratio/high_max": 0.0021689559798687696,
      "clip_ratio/high_mean": 0.0008927038761612494,
      "clip_ratio/low_mean": 0.0006382088777172612,
      "clip_ratio/low_min": 3.605661368055735e-05,
      "clip_ratio/region_mean": 0.0015309127411455847,
      "epoch": 0.047319881700295746,
      "grad_norm": 0.13588377833366394,
      "learning_rate": 2e-07,
      "loss": 0.0159,
      "step": 507
    },
    {
      "clip_ratio/high_max": 0.002147663697542157,
      "clip_ratio/high_mean": 0.0008934457691793796,
      "clip_ratio/low_mean": 0.0006903692901687464,
      "clip_ratio/low_min": 6.498480297523201e-05,
      "clip_ratio/region_mean": 0.0015838150793570094,
      "epoch": 0.04741321480029633,
      "grad_norm": 0.14163455367088318,
      "learning_rate": 2e-07,
      "loss": 0.0405,
      "step": 508
    },
    {
      "clip_ratio/high_max": 0.0017830312644946389,
      "clip_ratio/high_mean": 0.0007750870954623679,
      "clip_ratio/low_mean": 0.0005964169172330003,
      "clip_ratio/low_min": 5.2187920118740294e-05,
      "clip_ratio/region_mean": 0.001371504014969105,
      "epoch": 0.04750654790029692,
      "grad_norm": 0.12221848219633102,
      "learning_rate": 2e-07,
      "loss": 0.0046,
      "step": 509
    },
    {
      "clip_ratio/high_max": 0.002102970647683833,
      "clip_ratio/high_mean": 0.0008855807791405823,
      "clip_ratio/low_mean": 0.0007151324825827032,
      "clip_ratio/low_min": 9.362271612189943e-05,
      "clip_ratio/region_mean": 0.0016007132217055187,
      "epoch": 0.0475998810002975,
      "grad_norm": 0.1492527425289154,
      "learning_rate": 2e-07,
      "loss": 0.021,
      "step": 510
    },
    {
      "clip_ratio/high_max": 0.0019890679941454437,
      "clip_ratio/high_mean": 0.0007588792395836208,
      "clip_ratio/low_mean": 0.0006563334909515106,
      "clip_ratio/low_min": 7.98090077296365e-05,
      "clip_ratio/region_mean": 0.0014152127405395731,
      "epoch": 0.04769321410029808,
      "grad_norm": 0.13701818883419037,
      "learning_rate": 2e-07,
      "loss": 0.0621,
      "step": 511
    },
    {
      "clip_ratio/high_max": 0.002095494943205267,
      "clip_ratio/high_mean": 0.0007698805056861602,
      "clip_ratio/low_mean": 0.0006854003895568894,
      "clip_ratio/low_min": 8.843113027978688e-05,
      "clip_ratio/region_mean": 0.001455280838854378,
      "epoch": 0.047786547200298665,
      "grad_norm": 0.11331798881292343,
      "learning_rate": 2e-07,
      "loss": 0.0215,
      "step": 512
    },
    {
      "clip_ratio/high_max": 0.001661100690398598,
      "clip_ratio/high_mean": 0.0006640887950197794,
      "clip_ratio/low_mean": 0.0005831441058035125,
      "clip_ratio/low_min": 6.20927876298083e-05,
      "clip_ratio/region_mean": 0.00124723292174167,
      "completions/clipped_ratio": 0.0172206333705357,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4092.0,
      "completions/mean_length": 652.1428833007812,
      "completions/mean_terminated_length": 591.7982788085938,
      "completions/min_length": 83.0,
      "completions/min_terminated_length": 83.0,
      "epoch": 0.04787988030029925,
      "grad_norm": 0.11295594274997711,
      "learning_rate": 2e-07,
      "loss": 0.0083,
      "num_tokens": 415518197.0,
      "reward": 0.5720999836921692,
      "reward_std": 0.19469255208969116,
      "rewards/simpleverify_reward/mean": 0.5720999836921692,
      "rewards/simpleverify_reward/std": 0.4947764575481415,
      "step": 513
    },
    {
      "clip_ratio/high_max": 0.0017237266001757234,
      "clip_ratio/high_mean": 0.0005975122312520398,
      "clip_ratio/low_mean": 0.000616979179540067,
      "clip_ratio/low_min": 1.0918937732640188e-05,
      "clip_ratio/region_mean": 0.0012144914289820008,
      "epoch": 0.047973213400299836,
      "grad_norm": 0.1252632439136505,
      "learning_rate": 2e-07,
      "loss": 0.0313,
      "step": 514
    },
    {
      "clip_ratio/high_max": 0.0017588489426998422,
      "clip_ratio/high_mean": 0.0006889515407237923,
      "clip_ratio/low_mean": 0.0005534208667086205,
      "clip_ratio/low_min": 3.1923004826239776e-05,
      "clip_ratio/region_mean": 0.001242372381966561,
      "epoch": 0.048066546500300414,
      "grad_norm": 0.1317816972732544,
      "learning_rate": 2e-07,
      "loss": 0.0252,
      "step": 515
    },
    {
      "clip_ratio/high_max": 0.001726904469251167,
      "clip_ratio/high_mean": 0.0006845847510703607,
      "clip_ratio/low_mean": 0.0005103389612486353,
      "clip_ratio/low_min": 2.303974179085344e-05,
      "clip_ratio/region_mean": 0.0011949236977670807,
      "epoch": 0.048159879600301,
      "grad_norm": 0.10822305828332901,
      "learning_rate": 2e-07,
      "loss": 0.0156,
      "step": 516
    },
    {
      "clip_ratio/high_max": 0.0015383017744170502,
      "clip_ratio/high_mean": 0.000589987213970744,
      "clip_ratio/low_mean": 0.0005662164348905208,
      "clip_ratio/low_min": 4.35765632573748e-05,
      "clip_ratio/region_mean": 0.0011562036561372224,
      "epoch": 0.048253212700301584,
      "grad_norm": 0.12652388215065002,
      "learning_rate": 2e-07,
      "loss": 0.0794,
      "step": 517
    },
    {
      "clip_ratio/high_max": 0.001607385140232509,
      "clip_ratio/high_mean": 0.0006812076535425149,
      "clip_ratio/low_mean": 0.0005548001608985942,
      "clip_ratio/low_min": 9.63701731961919e-05,
      "clip_ratio/region_mean": 0.0012360078035271727,
      "epoch": 0.04834654580030216,
      "grad_norm": 0.1202060654759407,
      "learning_rate": 2e-07,
      "loss": 0.0507,
      "step": 518
    },
    {
      "clip_ratio/high_max": 0.0014725189357704949,
      "clip_ratio/high_mean": 0.0006108946126914816,
      "clip_ratio/low_mean": 0.0005467043720273068,
      "clip_ratio/low_min": 5.570644498220645e-05,
      "clip_ratio/region_mean": 0.001157598991994746,
      "epoch": 0.04843987890030275,
      "grad_norm": 0.10508166253566742,
      "learning_rate": 2e-07,
      "loss": 0.0384,
      "step": 519
    },
    {
      "clip_ratio/high_max": 0.0015348132474173326,
      "clip_ratio/high_mean": 0.000690805882186396,
      "clip_ratio/low_mean": 0.0006186803429955035,
      "clip_ratio/low_min": 1.8996959624928422e-05,
      "clip_ratio/region_mean": 0.0013094862370053306,
      "epoch": 0.04853321200030333,
      "grad_norm": 0.12275245040655136,
      "learning_rate": 2e-07,
      "loss": 0.0352,
      "step": 520
    },
    {
      "clip_ratio/high_max": 0.0016642865593894385,
      "clip_ratio/high_mean": 0.0006561715599673335,
      "clip_ratio/low_mean": 0.00048237445480481256,
      "clip_ratio/low_min": 2.0643663447117433e-05,
      "clip_ratio/region_mean": 0.0011385460202291142,
      "epoch": 0.04862654510030392,
      "grad_norm": 0.10232160985469818,
      "learning_rate": 2e-07,
      "loss": 0.0025,
      "step": 521
    },
    {
      "clip_ratio/high_max": 0.002190479352066177,
      "clip_ratio/high_mean": 0.0007919492927612737,
      "clip_ratio/low_mean": 0.0005792472438770346,
      "clip_ratio/low_min": 3.406218002055539e-05,
      "clip_ratio/region_mean": 0.0013711965366383083,
      "epoch": 0.048719878200304496,
      "grad_norm": 0.12254737317562103,
      "learning_rate": 2e-07,
      "loss": 0.023,
      "step": 522
    },
    {
      "clip_ratio/high_max": 0.002001780132559361,
      "clip_ratio/high_mean": 0.0007607927418575855,
      "clip_ratio/low_mean": 0.0006321199807644007,
      "clip_ratio/low_min": 6.249587386264466e-05,
      "clip_ratio/region_mean": 0.001392912738083396,
      "epoch": 0.04881321130030508,
      "grad_norm": 0.13201932609081268,
      "learning_rate": 2e-07,
      "loss": 0.0609,
      "step": 523
    },
    {
      "clip_ratio/high_max": 0.0016624363634036854,
      "clip_ratio/high_mean": 0.0006359516473821714,
      "clip_ratio/low_mean": 0.0005255334808680345,
      "clip_ratio/low_min": 6.80784614814911e-05,
      "clip_ratio/region_mean": 0.0011614851209742483,
      "epoch": 0.04890654440030567,
      "grad_norm": 0.12014492601156235,
      "learning_rate": 2e-07,
      "loss": 0.0531,
      "step": 524
    },
    {
      "clip_ratio/high_max": 0.0016420011743321083,
      "clip_ratio/high_mean": 0.0007468117182725109,
      "clip_ratio/low_mean": 0.000538583000889048,
      "clip_ratio/low_min": 1.2393416909617372e-05,
      "clip_ratio/region_mean": 0.0012853947337134741,
      "epoch": 0.04899987750030625,
      "grad_norm": 0.12996400892734528,
      "learning_rate": 2e-07,
      "loss": -0.0127,
      "step": 525
    },
    {
      "clip_ratio/high_max": 0.0015967537183314562,
      "clip_ratio/high_mean": 0.0006850626268715132,
      "clip_ratio/low_mean": 0.0005046642399975099,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0011897268777829595,
      "epoch": 0.04909321060030683,
      "grad_norm": 0.12281105667352676,
      "learning_rate": 2e-07,
      "loss": 0.0048,
      "step": 526
    },
    {
      "clip_ratio/high_max": 0.0017729788814904168,
      "clip_ratio/high_mean": 0.0006798362901463406,
      "clip_ratio/low_mean": 0.0006540745143865934,
      "clip_ratio/low_min": 4.6668398681504186e-05,
      "clip_ratio/region_mean": 0.001333910804532934,
      "epoch": 0.049186543700307415,
      "grad_norm": 0.12828707695007324,
      "learning_rate": 2e-07,
      "loss": 0.0805,
      "step": 527
    },
    {
      "clip_ratio/high_max": 0.0015139818424358964,
      "clip_ratio/high_mean": 0.0006359000462907716,
      "clip_ratio/low_mean": 0.0005450275330076693,
      "clip_ratio/low_min": 2.8674121494987048e-05,
      "clip_ratio/region_mean": 0.001180927600216819,
      "epoch": 0.049279876800308,
      "grad_norm": 0.11533678323030472,
      "learning_rate": 2e-07,
      "loss": 0.0313,
      "step": 528
    },
    {
      "clip_ratio/high_max": 0.0017079887220461387,
      "clip_ratio/high_mean": 0.0006885365946800448,
      "clip_ratio/low_mean": 0.0005163939740668866,
      "clip_ratio/low_min": 2.235165311503806e-05,
      "clip_ratio/region_mean": 0.0012049305405525956,
      "epoch": 0.049373209900308586,
      "grad_norm": 0.12229184806346893,
      "learning_rate": 2e-07,
      "loss": 0.0058,
      "step": 529
    },
    {
      "clip_ratio/high_max": 0.001500551814388018,
      "clip_ratio/high_mean": 0.0005652915615428356,
      "clip_ratio/low_mean": 0.0006068389120628126,
      "clip_ratio/low_min": 4.8852284180611605e-05,
      "clip_ratio/region_mean": 0.0011721304690581746,
      "epoch": 0.049466543000309164,
      "grad_norm": 0.12109557539224625,
      "learning_rate": 2e-07,
      "loss": 0.0607,
      "step": 530
    },
    {
      "clip_ratio/high_max": 0.0016181935388885904,
      "clip_ratio/high_mean": 0.0006836248903709929,
      "clip_ratio/low_mean": 0.0005544928280869499,
      "clip_ratio/low_min": 1.6956049876171164e-05,
      "clip_ratio/region_mean": 0.0012381177257339004,
      "epoch": 0.04955987610030975,
      "grad_norm": 0.1258392482995987,
      "learning_rate": 2e-07,
      "loss": 0.0716,
      "step": 531
    },
    {
      "clip_ratio/high_max": 0.002019554107391741,
      "clip_ratio/high_mean": 0.0007489765057471232,
      "clip_ratio/low_mean": 0.0005585811013588682,
      "clip_ratio/low_min": 1.2324985618761275e-05,
      "clip_ratio/region_mean": 0.0013075576316623483,
      "epoch": 0.049653209200310335,
      "grad_norm": 0.11476071923971176,
      "learning_rate": 2e-07,
      "loss": -0.0045,
      "step": 532
    },
    {
      "clip_ratio/high_max": 0.0016391516983276233,
      "clip_ratio/high_mean": 0.0006915751600899966,
      "clip_ratio/low_mean": 0.0005424370228865882,
      "clip_ratio/low_min": 2.657572167663602e-05,
      "clip_ratio/region_mean": 0.0012340122048044577,
      "epoch": 0.04974654230031091,
      "grad_norm": 0.11577029526233673,
      "learning_rate": 2e-07,
      "loss": -0.0018,
      "step": 533
    },
    {
      "clip_ratio/high_max": 0.0018789951136568561,
      "clip_ratio/high_mean": 0.0007453808593709255,
      "clip_ratio/low_mean": 0.0006554177307407372,
      "clip_ratio/low_min": 2.5383565116499085e-05,
      "clip_ratio/region_mean": 0.0014007985810167156,
      "epoch": 0.0498398754003115,
      "grad_norm": 0.1314806491136551,
      "learning_rate": 2e-07,
      "loss": 0.0223,
      "step": 534
    },
    {
      "clip_ratio/high_max": 0.002133504436642397,
      "clip_ratio/high_mean": 0.0007812856729287887,
      "clip_ratio/low_mean": 0.0005383214374887757,
      "clip_ratio/low_min": 1.1285662367299665e-05,
      "clip_ratio/region_mean": 0.0013196071231504902,
      "epoch": 0.04993320850031208,
      "grad_norm": 0.11995318531990051,
      "learning_rate": 2e-07,
      "loss": 0.0001,
      "step": 535
    },
    {
      "clip_ratio/high_max": 0.0017285073772654869,
      "clip_ratio/high_mean": 0.0007229851980810054,
      "clip_ratio/low_mean": 0.000613003843682236,
      "clip_ratio/low_min": 2.2883815290697385e-05,
      "clip_ratio/region_mean": 0.001335989021754358,
      "epoch": 0.05002654160031267,
      "grad_norm": 0.12192007154226303,
      "learning_rate": 2e-07,
      "loss": 0.024,
      "step": 536
    },
    {
      "clip_ratio/high_max": 0.0019033665012102574,
      "clip_ratio/high_mean": 0.0007032163939584279,
      "clip_ratio/low_mean": 0.0005144267479408882,
      "clip_ratio/low_min": 1.3531067452277057e-05,
      "clip_ratio/region_mean": 0.0012176431227999274,
      "epoch": 0.05011987470031325,
      "grad_norm": 0.11885754764080048,
      "learning_rate": 2e-07,
      "loss": 0.0197,
      "step": 537
    },
    {
      "clip_ratio/high_max": 0.001647905221034307,
      "clip_ratio/high_mean": 0.0007719422883383231,
      "clip_ratio/low_mean": 0.000595572904785513,
      "clip_ratio/low_min": 3.1016971661301795e-05,
      "clip_ratio/region_mean": 0.0013675152040377725,
      "epoch": 0.05021320780031383,
      "grad_norm": 0.12711986899375916,
      "learning_rate": 2e-07,
      "loss": 0.0374,
      "step": 538
    },
    {
      "clip_ratio/high_max": 0.0018654368395800702,
      "clip_ratio/high_mean": 0.0007804810084053315,
      "clip_ratio/low_mean": 0.0006269362656894373,
      "clip_ratio/low_min": 1.0798203220474534e-05,
      "clip_ratio/region_mean": 0.0014074173013796099,
      "epoch": 0.05030654090031442,
      "grad_norm": 0.12740099430084229,
      "learning_rate": 2e-07,
      "loss": 0.0439,
      "step": 539
    },
    {
      "clip_ratio/high_max": 0.0016882554409676231,
      "clip_ratio/high_mean": 0.0006842413677077275,
      "clip_ratio/low_mean": 0.0004812871993635781,
      "clip_ratio/low_min": 3.226926401111996e-05,
      "clip_ratio/region_mean": 0.001165528577985242,
      "epoch": 0.050399874000315,
      "grad_norm": 0.13205616176128387,
      "learning_rate": 2e-07,
      "loss": 0.0016,
      "step": 540
    },
    {
      "clip_ratio/high_max": 0.0018944383846246637,
      "clip_ratio/high_mean": 0.0007249890186358243,
      "clip_ratio/low_mean": 0.0005709368660973269,
      "clip_ratio/low_min": 1.4272664884629194e-05,
      "clip_ratio/region_mean": 0.0012959258710907307,
      "epoch": 0.05049320710031558,
      "grad_norm": 0.12349730730056763,
      "learning_rate": 2e-07,
      "loss": 0.0517,
      "step": 541
    },
    {
      "clip_ratio/high_max": 0.0016102362715173513,
      "clip_ratio/high_mean": 0.000684143047692487,
      "clip_ratio/low_mean": 0.0005657093151967274,
      "clip_ratio/low_min": 5.466116499519558e-05,
      "clip_ratio/region_mean": 0.0012498523828980979,
      "epoch": 0.050586540200316166,
      "grad_norm": 0.12686222791671753,
      "learning_rate": 2e-07,
      "loss": 0.0378,
      "step": 542
    },
    {
      "clip_ratio/high_max": 0.0019019496394321322,
      "clip_ratio/high_mean": 0.0007148446602514014,
      "clip_ratio/low_mean": 0.0006074918919694028,
      "clip_ratio/low_min": 2.6286372758477228e-05,
      "clip_ratio/region_mean": 0.0013223365785961505,
      "epoch": 0.05067987330031675,
      "grad_norm": 0.13016310334205627,
      "learning_rate": 2e-07,
      "loss": -0.0042,
      "step": 543
    },
    {
      "clip_ratio/high_max": 0.0018126615032088012,
      "clip_ratio/high_mean": 0.0007476470436813543,
      "clip_ratio/low_mean": 0.0005630906052829232,
      "clip_ratio/low_min": 3.707310406753095e-05,
      "clip_ratio/region_mean": 0.0013107376398693305,
      "epoch": 0.05077320640031733,
      "grad_norm": 0.11862743645906448,
      "learning_rate": 2e-07,
      "loss": 0.0189,
      "step": 544
    },
    {
      "clip_ratio/high_max": 0.0016176494245883077,
      "clip_ratio/high_mean": 0.0007058940082060872,
      "clip_ratio/low_mean": 0.0004515109249041416,
      "clip_ratio/low_min": 5.132849582878407e-05,
      "clip_ratio/region_mean": 0.0011574049458431546,
      "epoch": 0.050866539500317914,
      "grad_norm": 0.1153007298707962,
      "learning_rate": 2e-07,
      "loss": -0.0393,
      "step": 545
    },
    {
      "clip_ratio/high_max": 0.001659826284594601,
      "clip_ratio/high_mean": 0.0006493270520877559,
      "clip_ratio/low_mean": 0.0005628662484014058,
      "clip_ratio/low_min": 1.3584003681899048e-05,
      "clip_ratio/region_mean": 0.0012121932923037093,
      "epoch": 0.0509598726003185,
      "grad_norm": 0.11391019076108932,
      "learning_rate": 2e-07,
      "loss": 0.0296,
      "step": 546
    },
    {
      "clip_ratio/high_max": 0.0019514466475811787,
      "clip_ratio/high_mean": 0.0007983858886291273,
      "clip_ratio/low_mean": 0.0005713520640711067,
      "clip_ratio/low_min": 2.3665277694817632e-05,
      "clip_ratio/region_mean": 0.0013697379836230539,
      "epoch": 0.051053205700319085,
      "grad_norm": 0.11803116649389267,
      "learning_rate": 2e-07,
      "loss": -0.0045,
      "step": 547
    },
    {
      "clip_ratio/high_max": 0.0017589134949957952,
      "clip_ratio/high_mean": 0.0006785076411688351,
      "clip_ratio/low_mean": 0.0005395087882789085,
      "clip_ratio/low_min": 2.339071943424642e-05,
      "clip_ratio/region_mean": 0.0012180164594610687,
      "epoch": 0.05114653880031966,
      "grad_norm": 0.11099693924188614,
      "learning_rate": 2e-07,
      "loss": 0.0513,
      "step": 548
    },
    {
      "clip_ratio/high_max": 0.0016770981237641536,
      "clip_ratio/high_mean": 0.0007816170564183267,
      "clip_ratio/low_mean": 0.0006341719736155937,
      "clip_ratio/low_min": 1.9083969164057635e-05,
      "clip_ratio/region_mean": 0.0014157890364003833,
      "epoch": 0.05123987190032025,
      "grad_norm": 0.12385471165180206,
      "learning_rate": 2e-07,
      "loss": 0.0413,
      "step": 549
    },
    {
      "clip_ratio/high_max": 0.001685597060713917,
      "clip_ratio/high_mean": 0.0006680236219835933,
      "clip_ratio/low_mean": 0.0005954735115665244,
      "clip_ratio/low_min": 3.962612299801549e-05,
      "clip_ratio/region_mean": 0.0012634971280931495,
      "epoch": 0.05133320500032083,
      "grad_norm": 0.1261381059885025,
      "learning_rate": 2e-07,
      "loss": 0.0389,
      "step": 550
    },
    {
      "clip_ratio/high_max": 0.0016241915363934822,
      "clip_ratio/high_mean": 0.0006705939649691572,
      "clip_ratio/low_mean": 0.0006389973968907725,
      "clip_ratio/low_min": 4.383204850455513e-05,
      "clip_ratio/region_mean": 0.0013095914073346648,
      "epoch": 0.05142653810032142,
      "grad_norm": 0.11627063155174255,
      "learning_rate": 2e-07,
      "loss": 0.01,
      "step": 551
    },
    {
      "clip_ratio/high_max": 0.001547732565086335,
      "clip_ratio/high_mean": 0.0006917518730915617,
      "clip_ratio/low_mean": 0.0005334458301149425,
      "clip_ratio/low_min": 1.0277914952894207e-05,
      "clip_ratio/region_mean": 0.0012251977095729671,
      "epoch": 0.051519871200322,
      "grad_norm": 0.12772083282470703,
      "learning_rate": 2e-07,
      "loss": 0.0272,
      "step": 552
    },
    {
      "clip_ratio/high_max": 0.001941527210874483,
      "clip_ratio/high_mean": 0.0007605968257848872,
      "clip_ratio/low_mean": 0.0005486251939146314,
      "clip_ratio/low_min": 4.6300952817546204e-05,
      "clip_ratio/region_mean": 0.001309222021518508,
      "epoch": 0.05161320430032258,
      "grad_norm": 0.11804698407649994,
      "learning_rate": 2e-07,
      "loss": -0.0103,
      "step": 553
    },
    {
      "clip_ratio/high_max": 0.002328872938960558,
      "clip_ratio/high_mean": 0.0008920800373743987,
      "clip_ratio/low_mean": 0.0005771943724539597,
      "clip_ratio/low_min": 4.11948522014427e-05,
      "clip_ratio/region_mean": 0.001469274426199263,
      "epoch": 0.05170653740032317,
      "grad_norm": 0.12142713367938995,
      "learning_rate": 2e-07,
      "loss": 0.0009,
      "step": 554
    },
    {
      "clip_ratio/high_max": 0.0018062348626699531,
      "clip_ratio/high_mean": 0.0007341348309637397,
      "clip_ratio/low_mean": 0.0005699974499293603,
      "clip_ratio/low_min": 4.115113461011788e-05,
      "clip_ratio/region_mean": 0.0013041322636127006,
      "epoch": 0.05179987050032375,
      "grad_norm": 0.12030376493930817,
      "learning_rate": 2e-07,
      "loss": 0.0273,
      "step": 555
    },
    {
      "clip_ratio/high_max": 0.001751141437125625,
      "clip_ratio/high_mean": 0.0006809760661781183,
      "clip_ratio/low_mean": 0.0006588429841940524,
      "clip_ratio/low_min": 3.0098226488917135e-05,
      "clip_ratio/region_mean": 0.001339819031272782,
      "epoch": 0.05189320360032433,
      "grad_norm": 0.12279978394508362,
      "learning_rate": 2e-07,
      "loss": 0.054,
      "step": 556
    },
    {
      "clip_ratio/high_max": 0.0018652261060196906,
      "clip_ratio/high_mean": 0.000785793181421468,
      "clip_ratio/low_mean": 0.0006476215894508641,
      "clip_ratio/low_min": 5.609282607110799e-05,
      "clip_ratio/region_mean": 0.0014334147635963745,
      "epoch": 0.051986536700324916,
      "grad_norm": 0.1273386925458908,
      "learning_rate": 2e-07,
      "loss": 0.0093,
      "step": 557
    },
    {
      "clip_ratio/high_max": 0.0017728582897689193,
      "clip_ratio/high_mean": 0.0007740818782622227,
      "clip_ratio/low_mean": 0.0005255322676021024,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012996141485928092,
      "epoch": 0.0520798698003255,
      "grad_norm": 0.12609295547008514,
      "learning_rate": 2e-07,
      "loss": -0.0068,
      "step": 558
    },
    {
      "clip_ratio/high_max": 0.001737559650791809,
      "clip_ratio/high_mean": 0.0007005978313827654,
      "clip_ratio/low_mean": 0.0005938601543675759,
      "clip_ratio/low_min": 7.650905536138453e-05,
      "clip_ratio/region_mean": 0.0012944579902978148,
      "epoch": 0.05217320290032608,
      "grad_norm": 0.11379167437553406,
      "learning_rate": 2e-07,
      "loss": 0.0742,
      "step": 559
    },
    {
      "clip_ratio/high_max": 0.0019275162121630274,
      "clip_ratio/high_mean": 0.0007835304459149484,
      "clip_ratio/low_mean": 0.0005804659122077283,
      "clip_ratio/low_min": 3.123789429082535e-05,
      "clip_ratio/region_mean": 0.0013639963835885283,
      "epoch": 0.052266536000326665,
      "grad_norm": 0.12291675806045532,
      "learning_rate": 2e-07,
      "loss": -0.0034,
      "step": 560
    },
    {
      "clip_ratio/high_max": 0.0019921707862522453,
      "clip_ratio/high_mean": 0.0007690047405048972,
      "clip_ratio/low_mean": 0.0005607053590210853,
      "clip_ratio/low_min": 1.0079019375552889e-05,
      "clip_ratio/region_mean": 0.001329710092250025,
      "epoch": 0.05235986910032725,
      "grad_norm": 0.12805572152137756,
      "learning_rate": 2e-07,
      "loss": 0.035,
      "step": 561
    },
    {
      "clip_ratio/high_max": 0.0020256716925359797,
      "clip_ratio/high_mean": 0.0007080993491399568,
      "clip_ratio/low_mean": 0.000642150219391624,
      "clip_ratio/low_min": 9.197429972118698e-05,
      "clip_ratio/region_mean": 0.0013502495785360225,
      "epoch": 0.052453202200327835,
      "grad_norm": 0.12678885459899902,
      "learning_rate": 2e-07,
      "loss": 0.0345,
      "step": 562
    },
    {
      "clip_ratio/high_max": 0.0018501561826269608,
      "clip_ratio/high_mean": 0.0007906521295808489,
      "clip_ratio/low_mean": 0.0006130010578999645,
      "clip_ratio/low_min": 1.2789032552973367e-05,
      "clip_ratio/region_mean": 0.0014036531865713187,
      "epoch": 0.05254653530032841,
      "grad_norm": 0.12275071442127228,
      "learning_rate": 2e-07,
      "loss": 0.0255,
      "step": 563
    },
    {
      "clip_ratio/high_max": 0.001977594532945659,
      "clip_ratio/high_mean": 0.0007286468371603405,
      "clip_ratio/low_mean": 0.0005730532539018895,
      "clip_ratio/low_min": 1.5687750419601798e-05,
      "clip_ratio/region_mean": 0.0013017000492254738,
      "epoch": 0.052639868400329,
      "grad_norm": 0.3113510012626648,
      "learning_rate": 2e-07,
      "loss": 0.0266,
      "step": 564
    },
    {
      "clip_ratio/high_max": 0.0019253962746006437,
      "clip_ratio/high_mean": 0.0007782668708387064,
      "clip_ratio/low_mean": 0.0004541981934380601,
      "clip_ratio/low_min": 1.1832638847408816e-05,
      "clip_ratio/region_mean": 0.001232465041539399,
      "epoch": 0.052733201500329584,
      "grad_norm": 0.11122290045022964,
      "learning_rate": 2e-07,
      "loss": 0.0027,
      "step": 565
    },
    {
      "clip_ratio/high_max": 0.0019160892043146305,
      "clip_ratio/high_mean": 0.0007441970956278965,
      "clip_ratio/low_mean": 0.0005536141543416306,
      "clip_ratio/low_min": 4.994019036530517e-05,
      "clip_ratio/region_mean": 0.001297811235417612,
      "epoch": 0.05282653460033017,
      "grad_norm": 0.12345101684331894,
      "learning_rate": 2e-07,
      "loss": 0.029,
      "step": 566
    },
    {
      "clip_ratio/high_max": 0.001711590462946333,
      "clip_ratio/high_mean": 0.0007046318169159349,
      "clip_ratio/low_mean": 0.0005403607283369638,
      "clip_ratio/low_min": 2.1772672880615573e-05,
      "clip_ratio/region_mean": 0.0012449925488908775,
      "epoch": 0.05291986770033075,
      "grad_norm": 0.11366830766201019,
      "learning_rate": 2e-07,
      "loss": 0.033,
      "step": 567
    },
    {
      "clip_ratio/high_max": 0.0018906180885096546,
      "clip_ratio/high_mean": 0.0007381432924375986,
      "clip_ratio/low_mean": 0.0006687447166768834,
      "clip_ratio/low_min": 2.9912986065028235e-05,
      "clip_ratio/region_mean": 0.0014068880373088177,
      "epoch": 0.05301320080033133,
      "grad_norm": 0.11527183651924133,
      "learning_rate": 2e-07,
      "loss": 0.0396,
      "step": 568
    },
    {
      "clip_ratio/high_max": 0.002100765923387371,
      "clip_ratio/high_mean": 0.0008215222424041713,
      "clip_ratio/low_mean": 0.0007018314790911973,
      "clip_ratio/low_min": 7.120884220057633e-06,
      "clip_ratio/region_mean": 0.001523353723314358,
      "epoch": 0.05310653390033192,
      "grad_norm": 0.12579979002475739,
      "learning_rate": 2e-07,
      "loss": 0.0299,
      "step": 569
    },
    {
      "clip_ratio/high_max": 0.0018478761703590862,
      "clip_ratio/high_mean": 0.000703203606462921,
      "clip_ratio/low_mean": 0.0006114704010542482,
      "clip_ratio/low_min": 4.962616185366642e-05,
      "clip_ratio/region_mean": 0.0013146739911462646,
      "epoch": 0.053199867000332496,
      "grad_norm": 0.1293213814496994,
      "learning_rate": 2e-07,
      "loss": 0.0452,
      "step": 570
    },
    {
      "clip_ratio/high_max": 0.0018802962549671065,
      "clip_ratio/high_mean": 0.0007975716343935346,
      "clip_ratio/low_mean": 0.000529888029632275,
      "clip_ratio/low_min": 1.4272664884629194e-05,
      "clip_ratio/region_mean": 0.0013274596531118732,
      "epoch": 0.05329320010033308,
      "grad_norm": 0.12362080812454224,
      "learning_rate": 2e-07,
      "loss": 0.0125,
      "step": 571
    },
    {
      "clip_ratio/high_max": 0.0020141180029895622,
      "clip_ratio/high_mean": 0.0007748335974611109,
      "clip_ratio/low_mean": 0.0006557353281095857,
      "clip_ratio/low_min": 1.909253296616953e-05,
      "clip_ratio/region_mean": 0.0014305689328466542,
      "epoch": 0.053386533200333666,
      "grad_norm": 0.12238020449876785,
      "learning_rate": 2e-07,
      "loss": 0.0195,
      "step": 572
    },
    {
      "clip_ratio/high_max": 0.0019384488332434557,
      "clip_ratio/high_mean": 0.0007668384714634158,
      "clip_ratio/low_mean": 0.0006219646838871995,
      "clip_ratio/low_min": 3.567332350939978e-05,
      "clip_ratio/region_mean": 0.0013888031753594987,
      "epoch": 0.05347986630033425,
      "grad_norm": 0.11997241526842117,
      "learning_rate": 2e-07,
      "loss": 0.0426,
      "step": 573
    },
    {
      "clip_ratio/high_max": 0.0017065440297301393,
      "clip_ratio/high_mean": 0.0006765083517166204,
      "clip_ratio/low_mean": 0.0005677262388417148,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012442345978342928,
      "epoch": 0.05357319940033483,
      "grad_norm": 0.11231635510921478,
      "learning_rate": 2e-07,
      "loss": 0.0367,
      "step": 574
    },
    {
      "clip_ratio/high_max": 0.001864747053332394,
      "clip_ratio/high_mean": 0.0007696370557823684,
      "clip_ratio/low_mean": 0.0005909162719035521,
      "clip_ratio/low_min": 6.291837507887976e-05,
      "clip_ratio/region_mean": 0.001360553338599857,
      "epoch": 0.053666532500335415,
      "grad_norm": 0.1277708113193512,
      "learning_rate": 2e-07,
      "loss": 0.049,
      "step": 575
    },
    {
      "clip_ratio/high_max": 0.0015508401738770772,
      "clip_ratio/high_mean": 0.0006332397433652659,
      "clip_ratio/low_mean": 0.0005332851887942525,
      "clip_ratio/low_min": 4.6439768993877806e-05,
      "clip_ratio/region_mean": 0.001166524933069013,
      "epoch": 0.053759865600336,
      "grad_norm": 0.11868428438901901,
      "learning_rate": 2e-07,
      "loss": 0.0228,
      "step": 576
    },
    {
      "clip_ratio/high_max": 0.001946644792042207,
      "clip_ratio/high_mean": 0.0007400521008094074,
      "clip_ratio/low_mean": 0.0005837154021719471,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013237675084383227,
      "epoch": 0.053853198700336585,
      "grad_norm": 0.13686397671699524,
      "learning_rate": 2e-07,
      "loss": 0.0301,
      "step": 577
    },
    {
      "clip_ratio/high_max": 0.0015608372632414103,
      "clip_ratio/high_mean": 0.0006582285877811955,
      "clip_ratio/low_mean": 0.0006902497334522195,
      "clip_ratio/low_min": 4.6427281631622463e-05,
      "clip_ratio/region_mean": 0.0013484783048625104,
      "epoch": 0.053946531800337164,
      "grad_norm": 0.13206499814987183,
      "learning_rate": 2e-07,
      "loss": 0.069,
      "step": 578
    },
    {
      "clip_ratio/high_max": 0.0020299409370636567,
      "clip_ratio/high_mean": 0.0007910716558399145,
      "clip_ratio/low_mean": 0.0006031796146999113,
      "clip_ratio/low_min": 7.095907039911253e-05,
      "clip_ratio/region_mean": 0.0013942512450739741,
      "epoch": 0.05403986490033775,
      "grad_norm": 0.12364768981933594,
      "learning_rate": 2e-07,
      "loss": 0.0306,
      "step": 579
    },
    {
      "clip_ratio/high_max": 0.002113464906869922,
      "clip_ratio/high_mean": 0.0008170472119672922,
      "clip_ratio/low_mean": 0.0005592982024609228,
      "clip_ratio/low_min": 6.888969437568448e-05,
      "clip_ratio/region_mean": 0.001376345411699731,
      "epoch": 0.054133198000338334,
      "grad_norm": 0.13236679136753082,
      "learning_rate": 2e-07,
      "loss": 0.0065,
      "step": 580
    },
    {
      "clip_ratio/high_max": 0.0018834772781701759,
      "clip_ratio/high_mean": 0.0006586236304428894,
      "clip_ratio/low_mean": 0.0006315196424111491,
      "clip_ratio/low_min": 2.9235992769827135e-05,
      "clip_ratio/region_mean": 0.0012901432673970703,
      "epoch": 0.05422653110033892,
      "grad_norm": 0.11762931942939758,
      "learning_rate": 2e-07,
      "loss": 0.0778,
      "step": 581
    },
    {
      "clip_ratio/high_max": 0.001979979882889893,
      "clip_ratio/high_mean": 0.0007834097814338747,
      "clip_ratio/low_mean": 0.0005905541183892637,
      "clip_ratio/low_min": 7.776623624522472e-05,
      "clip_ratio/region_mean": 0.0013739638743572868,
      "epoch": 0.0543198642003395,
      "grad_norm": 0.13116592168807983,
      "learning_rate": 2e-07,
      "loss": 0.0576,
      "step": 582
    },
    {
      "clip_ratio/high_max": 0.001894597789942054,
      "clip_ratio/high_mean": 0.0007478521602024557,
      "clip_ratio/low_mean": 0.0005253698182059452,
      "clip_ratio/low_min": 1.6646690710331313e-05,
      "clip_ratio/region_mean": 0.0012732219620374963,
      "epoch": 0.05441319730034008,
      "grad_norm": 0.12515588104724884,
      "learning_rate": 2e-07,
      "loss": 0.0151,
      "step": 583
    },
    {
      "clip_ratio/high_max": 0.001880470743344631,
      "clip_ratio/high_mean": 0.0007337635379371932,
      "clip_ratio/low_mean": 0.0006381958919519093,
      "clip_ratio/low_min": 9.437063181394478e-05,
      "clip_ratio/region_mean": 0.0013719593844143674,
      "epoch": 0.05450653040034067,
      "grad_norm": 0.18464471399784088,
      "learning_rate": 2e-07,
      "loss": 0.0784,
      "step": 584
    },
    {
      "clip_ratio/high_max": 0.002296121288964059,
      "clip_ratio/high_mean": 0.000849091944473912,
      "clip_ratio/low_mean": 0.0005523095387616195,
      "clip_ratio/low_min": 3.928477372028283e-05,
      "clip_ratio/region_mean": 0.001401401503244415,
      "epoch": 0.054599863500341246,
      "grad_norm": 0.13381274044513702,
      "learning_rate": 2e-07,
      "loss": -0.0017,
      "step": 585
    },
    {
      "clip_ratio/high_max": 0.0021165946454857476,
      "clip_ratio/high_mean": 0.0007287215194082819,
      "clip_ratio/low_mean": 0.0006423675531550543,
      "clip_ratio/low_min": 3.622138683567755e-05,
      "clip_ratio/region_mean": 0.0013710890889342409,
      "epoch": 0.05469319660034183,
      "grad_norm": 0.1129380315542221,
      "learning_rate": 2e-07,
      "loss": 0.0417,
      "step": 586
    },
    {
      "clip_ratio/high_max": 0.0021159143070690334,
      "clip_ratio/high_mean": 0.000821098079541116,
      "clip_ratio/low_mean": 0.0005949813203187659,
      "clip_ratio/low_min": 1.9906841316696955e-05,
      "clip_ratio/region_mean": 0.001416079368937062,
      "epoch": 0.054786529700342416,
      "grad_norm": 0.13925187289714813,
      "learning_rate": 2e-07,
      "loss": 0.0206,
      "step": 587
    },
    {
      "clip_ratio/high_max": 0.0016702330503903795,
      "clip_ratio/high_mean": 0.0007274825493368553,
      "clip_ratio/low_mean": 0.0007227761498143082,
      "clip_ratio/low_min": 6.622693763347343e-05,
      "clip_ratio/region_mean": 0.0014502586782327853,
      "epoch": 0.054879862800343,
      "grad_norm": 0.14801770448684692,
      "learning_rate": 2e-07,
      "loss": 0.0419,
      "step": 588
    },
    {
      "clip_ratio/high_max": 0.001920305279782042,
      "clip_ratio/high_mean": 0.0007233480228023836,
      "clip_ratio/low_mean": 0.0006516732264572056,
      "clip_ratio/low_min": 4.07285961046e-05,
      "clip_ratio/region_mean": 0.0013750212674494833,
      "epoch": 0.05497319590034358,
      "grad_norm": 0.1267736256122589,
      "learning_rate": 2e-07,
      "loss": 0.0766,
      "step": 589
    },
    {
      "clip_ratio/high_max": 0.002247139454993885,
      "clip_ratio/high_mean": 0.0008423924518865533,
      "clip_ratio/low_mean": 0.000602574042204651,
      "clip_ratio/low_min": 4.9910197958524805e-05,
      "clip_ratio/region_mean": 0.001444966510462109,
      "epoch": 0.055066529000344165,
      "grad_norm": 0.1370629519224167,
      "learning_rate": 2e-07,
      "loss": 0.0242,
      "step": 590
    },
    {
      "clip_ratio/high_max": 0.001926904900756199,
      "clip_ratio/high_mean": 0.0007684007177886087,
      "clip_ratio/low_mean": 0.0006107104454713408,
      "clip_ratio/low_min": 7.084257958922535e-05,
      "clip_ratio/region_mean": 0.0013791111705359071,
      "epoch": 0.05515986210034475,
      "grad_norm": 0.1302701234817505,
      "learning_rate": 2e-07,
      "loss": 0.0357,
      "step": 591
    },
    {
      "clip_ratio/high_max": 0.001458942253520945,
      "clip_ratio/high_mean": 0.0006639108632953139,
      "clip_ratio/low_mean": 0.0005597411009148345,
      "clip_ratio/low_min": 1.5107565559446812e-05,
      "clip_ratio/region_mean": 0.001223651986947516,
      "epoch": 0.055253195200345336,
      "grad_norm": 0.12280702590942383,
      "learning_rate": 2e-07,
      "loss": 0.0461,
      "step": 592
    },
    {
      "clip_ratio/high_max": 0.002324761400814168,
      "clip_ratio/high_mean": 0.000818258475192124,
      "clip_ratio/low_mean": 0.0005714063581763185,
      "clip_ratio/low_min": 7.952549276524223e-05,
      "clip_ratio/region_mean": 0.001389664837915916,
      "epoch": 0.055346528300345914,
      "grad_norm": 0.1272321194410324,
      "learning_rate": 2e-07,
      "loss": 0.0473,
      "step": 593
    },
    {
      "clip_ratio/high_max": 0.002146025733964052,
      "clip_ratio/high_mean": 0.0008538049933122238,
      "clip_ratio/low_mean": 0.0006849107248854125,
      "clip_ratio/low_min": 9.263393803848885e-05,
      "clip_ratio/region_mean": 0.001538715725473594,
      "epoch": 0.0554398614003465,
      "grad_norm": 0.13797812163829803,
      "learning_rate": 2e-07,
      "loss": 0.0251,
      "step": 594
    },
    {
      "clip_ratio/high_max": 0.0020570386623148806,
      "clip_ratio/high_mean": 0.000757381420044112,
      "clip_ratio/low_mean": 0.0005548200570046902,
      "clip_ratio/low_min": 1.9564877220545895e-05,
      "clip_ratio/region_mean": 0.001312201471591834,
      "epoch": 0.055533194500347084,
      "grad_norm": 0.12918128073215485,
      "learning_rate": 2e-07,
      "loss": 0.0191,
      "step": 595
    },
    {
      "clip_ratio/high_max": 0.001484809909015894,
      "clip_ratio/high_mean": 0.0006596066650672583,
      "clip_ratio/low_mean": 0.0006142302136140643,
      "clip_ratio/low_min": 6.065852994652232e-05,
      "clip_ratio/region_mean": 0.0012738368786813226,
      "epoch": 0.05562652760034766,
      "grad_norm": 0.1280878633260727,
      "learning_rate": 2e-07,
      "loss": 0.0129,
      "step": 596
    },
    {
      "clip_ratio/high_max": 0.0016571496526012197,
      "clip_ratio/high_mean": 0.0006969525056774728,
      "clip_ratio/low_mean": 0.0005855164017702918,
      "clip_ratio/low_min": 2.7480021344672423e-05,
      "clip_ratio/region_mean": 0.001282468918361701,
      "epoch": 0.05571986070034825,
      "grad_norm": 0.12600445747375488,
      "learning_rate": 2e-07,
      "loss": 0.026,
      "step": 597
    },
    {
      "clip_ratio/high_max": 0.0017546714225318283,
      "clip_ratio/high_mean": 0.0007153079295676434,
      "clip_ratio/low_mean": 0.0006462242308771238,
      "clip_ratio/low_min": 3.9743220440868754e-05,
      "clip_ratio/region_mean": 0.0013615321440738626,
      "epoch": 0.05581319380034883,
      "grad_norm": 0.12563100457191467,
      "learning_rate": 2e-07,
      "loss": 0.0247,
      "step": 598
    },
    {
      "clip_ratio/high_max": 0.001701915629382711,
      "clip_ratio/high_mean": 0.0008425342675764114,
      "clip_ratio/low_mean": 0.0005406459322330193,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013831802243657876,
      "epoch": 0.05590652690034942,
      "grad_norm": 0.11960609257221222,
      "learning_rate": 2e-07,
      "loss": -0.0095,
      "step": 599
    },
    {
      "clip_ratio/high_max": 0.0017502158334536944,
      "clip_ratio/high_mean": 0.0006924674089532346,
      "clip_ratio/low_mean": 0.0005254591114862706,
      "clip_ratio/low_min": 3.9098690649552736e-05,
      "clip_ratio/region_mean": 0.0012179265067970846,
      "epoch": 0.055999860000349996,
      "grad_norm": 0.12083174288272858,
      "learning_rate": 2e-07,
      "loss": 0.0446,
      "step": 600
    },
    {
      "clip_ratio/high_max": 0.0017851490556495264,
      "clip_ratio/high_mean": 0.0007400912472803611,
      "clip_ratio/low_mean": 0.0006195292617121595,
      "clip_ratio/low_min": 5.454041729535675e-05,
      "clip_ratio/region_mean": 0.0013596205062640365,
      "epoch": 0.05609319310035058,
      "grad_norm": 0.12879344820976257,
      "learning_rate": 2e-07,
      "loss": 0.0557,
      "step": 601
    },
    {
      "clip_ratio/high_max": 0.00202664191419899,
      "clip_ratio/high_mean": 0.0008406742454099003,
      "clip_ratio/low_mean": 0.0005972513536107726,
      "clip_ratio/low_min": 1.4888041732774582e-05,
      "clip_ratio/region_mean": 0.001437925617210567,
      "epoch": 0.05618652620035117,
      "grad_norm": 0.13380761444568634,
      "learning_rate": 2e-07,
      "loss": 0.018,
      "step": 602
    },
    {
      "clip_ratio/high_max": 0.0018286904160049744,
      "clip_ratio/high_mean": 0.0008291263493447332,
      "clip_ratio/low_mean": 0.000586018886679085,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014151452414807864,
      "epoch": 0.05627985930035175,
      "grad_norm": 0.1243838295340538,
      "learning_rate": 2e-07,
      "loss": -0.0056,
      "step": 603
    },
    {
      "clip_ratio/high_max": 0.002021389314904809,
      "clip_ratio/high_mean": 0.000783167670306284,
      "clip_ratio/low_mean": 0.0006176439237606246,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014008116158947814,
      "epoch": 0.05637319240035233,
      "grad_norm": 0.13788427412509918,
      "learning_rate": 2e-07,
      "loss": 0.0089,
      "step": 604
    },
    {
      "clip_ratio/high_max": 0.002049003989668563,
      "clip_ratio/high_mean": 0.0008164793744072085,
      "clip_ratio/low_mean": 0.0006003318676448544,
      "clip_ratio/low_min": 1.78271507138561e-05,
      "clip_ratio/region_mean": 0.0014168112757033668,
      "epoch": 0.056466525500352915,
      "grad_norm": 0.1401062160730362,
      "learning_rate": 2e-07,
      "loss": 0.0345,
      "step": 605
    },
    {
      "clip_ratio/high_max": 0.002008176270464901,
      "clip_ratio/high_mean": 0.0007043196419544984,
      "clip_ratio/low_mean": 0.000647723391011823,
      "clip_ratio/low_min": 1.3793864127364941e-05,
      "clip_ratio/region_mean": 0.0013520430475182366,
      "epoch": 0.0565598586003535,
      "grad_norm": 0.13014359772205353,
      "learning_rate": 2e-07,
      "loss": -0.0041,
      "step": 606
    },
    {
      "clip_ratio/high_max": 0.0017567013164807577,
      "clip_ratio/high_mean": 0.0007358157290582312,
      "clip_ratio/low_mean": 0.0005898358031117823,
      "clip_ratio/low_min": 5.9480782510945573e-05,
      "clip_ratio/region_mean": 0.001325651533989003,
      "epoch": 0.056653191700354086,
      "grad_norm": 0.1213982030749321,
      "learning_rate": 2e-07,
      "loss": 0.056,
      "step": 607
    },
    {
      "clip_ratio/high_max": 0.001961809586646268,
      "clip_ratio/high_mean": 0.0007007364365563262,
      "clip_ratio/low_mean": 0.000553050128473842,
      "clip_ratio/low_min": 4.1119532397715375e-05,
      "clip_ratio/region_mean": 0.0012537865732156206,
      "epoch": 0.056746524800354664,
      "grad_norm": 0.1423816680908203,
      "learning_rate": 2e-07,
      "loss": 0.0004,
      "step": 608
    },
    {
      "clip_ratio/high_max": 0.0020472863943723496,
      "clip_ratio/high_mean": 0.0007904565791250207,
      "clip_ratio/low_mean": 0.000658993001707131,
      "clip_ratio/low_min": 2.641157880134415e-05,
      "clip_ratio/region_mean": 0.0014494495699182153,
      "epoch": 0.05683985790035525,
      "grad_norm": 0.12972383201122284,
      "learning_rate": 2e-07,
      "loss": 0.0263,
      "step": 609
    },
    {
      "clip_ratio/high_max": 0.00197420613039867,
      "clip_ratio/high_mean": 0.0007404360676446231,
      "clip_ratio/low_mean": 0.0007119301062630257,
      "clip_ratio/low_min": 5.044778299634345e-05,
      "clip_ratio/region_mean": 0.0014523661739076488,
      "epoch": 0.056933191000355834,
      "grad_norm": 0.12125332653522491,
      "learning_rate": 2e-07,
      "loss": 0.0261,
      "step": 610
    },
    {
      "clip_ratio/high_max": 0.0016314583299390506,
      "clip_ratio/high_mean": 0.0006676061620964902,
      "clip_ratio/low_mean": 0.000494060466735391,
      "clip_ratio/low_min": 3.808809742622543e-05,
      "clip_ratio/region_mean": 0.001161666619736934,
      "epoch": 0.05702652410035641,
      "grad_norm": 0.11677919328212738,
      "learning_rate": 2e-07,
      "loss": -0.0053,
      "step": 611
    },
    {
      "clip_ratio/high_max": 0.0019200336428184528,
      "clip_ratio/high_mean": 0.0008373005730391014,
      "clip_ratio/low_mean": 0.0005993667964503402,
      "clip_ratio/low_min": 5.141816745890537e-05,
      "clip_ratio/region_mean": 0.0014366673422046006,
      "epoch": 0.057119857200357,
      "grad_norm": 0.1325366199016571,
      "learning_rate": 2e-07,
      "loss": 0.0112,
      "step": 612
    },
    {
      "clip_ratio/high_max": 0.0022988273776718415,
      "clip_ratio/high_mean": 0.0008544237734895432,
      "clip_ratio/low_mean": 0.0006186852151586208,
      "clip_ratio/low_min": 1.9818200598820113e-05,
      "clip_ratio/region_mean": 0.0014731090086570475,
      "epoch": 0.05721319030035758,
      "grad_norm": 0.13329392671585083,
      "learning_rate": 2e-07,
      "loss": 0.0079,
      "step": 613
    },
    {
      "clip_ratio/high_max": 0.001607274854904972,
      "clip_ratio/high_mean": 0.0006836909906269284,
      "clip_ratio/low_mean": 0.0005559453538808157,
      "clip_ratio/low_min": 4.1066603444051e-05,
      "clip_ratio/region_mean": 0.0012396363636071328,
      "epoch": 0.05730652340035817,
      "grad_norm": 0.12452827394008636,
      "learning_rate": 2e-07,
      "loss": 0.0205,
      "step": 614
    },
    {
      "clip_ratio/high_max": 0.0019441236399870832,
      "clip_ratio/high_mean": 0.0008244753080361988,
      "clip_ratio/low_mean": 0.0005469589377753437,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001371434216707712,
      "epoch": 0.05739985650035875,
      "grad_norm": 0.1297132670879364,
      "learning_rate": 2e-07,
      "loss": -0.027,
      "step": 615
    },
    {
      "clip_ratio/high_max": 0.0019316154903208371,
      "clip_ratio/high_mean": 0.0007169001255533658,
      "clip_ratio/low_mean": 0.0006500572326331167,
      "clip_ratio/low_min": 3.724763382706442e-05,
      "clip_ratio/region_mean": 0.0013669573127117474,
      "epoch": 0.05749318960035933,
      "grad_norm": 0.13498789072036743,
      "learning_rate": 2e-07,
      "loss": 0.0422,
      "step": 616
    },
    {
      "clip_ratio/high_max": 0.0017218805551237892,
      "clip_ratio/high_mean": 0.0006264360190471052,
      "clip_ratio/low_mean": 0.0006759300686098868,
      "clip_ratio/low_min": 4.004026050097309e-05,
      "clip_ratio/region_mean": 0.001302366072195582,
      "epoch": 0.05758652270035992,
      "grad_norm": 0.12367643415927887,
      "learning_rate": 2e-07,
      "loss": 0.0372,
      "step": 617
    },
    {
      "clip_ratio/high_max": 0.0018927859782706946,
      "clip_ratio/high_mean": 0.0007719259720033733,
      "clip_ratio/low_mean": 0.0006304375892796088,
      "clip_ratio/low_min": 6.857335120002972e-05,
      "clip_ratio/region_mean": 0.0014023635449120775,
      "epoch": 0.0576798558003605,
      "grad_norm": 0.20969240367412567,
      "learning_rate": 2e-07,
      "loss": 0.0395,
      "step": 618
    },
    {
      "clip_ratio/high_max": 0.001919278882269282,
      "clip_ratio/high_mean": 0.000784878313424997,
      "clip_ratio/low_mean": 0.0005481541775225196,
      "clip_ratio/low_min": 4.427554631547537e-05,
      "clip_ratio/region_mean": 0.0013330324582057074,
      "epoch": 0.05777318890036108,
      "grad_norm": 0.12936751544475555,
      "learning_rate": 2e-07,
      "loss": -0.0004,
      "step": 619
    },
    {
      "clip_ratio/high_max": 0.001853934198152274,
      "clip_ratio/high_mean": 0.000756432087655412,
      "clip_ratio/low_mean": 0.0005492968357430073,
      "clip_ratio/low_min": 5.417522515926976e-05,
      "clip_ratio/region_mean": 0.001305728899751557,
      "epoch": 0.057866522000361666,
      "grad_norm": 0.11905515938997269,
      "learning_rate": 2e-07,
      "loss": 0.0187,
      "step": 620
    },
    {
      "clip_ratio/high_max": 0.0016429902607342228,
      "clip_ratio/high_mean": 0.0006806379860790912,
      "clip_ratio/low_mean": 0.0006305058595899027,
      "clip_ratio/low_min": 8.865139261615695e-05,
      "clip_ratio/region_mean": 0.0013111438165651634,
      "epoch": 0.05795985510036225,
      "grad_norm": 0.14776545763015747,
      "learning_rate": 2e-07,
      "loss": 0.0198,
      "step": 621
    },
    {
      "clip_ratio/high_max": 0.0019432760600466281,
      "clip_ratio/high_mean": 0.0007690458769502584,
      "clip_ratio/low_mean": 0.0006771973912691465,
      "clip_ratio/low_min": 7.531232040491886e-05,
      "clip_ratio/region_mean": 0.001446243255486479,
      "epoch": 0.05805318820036283,
      "grad_norm": 0.11562264710664749,
      "learning_rate": 2e-07,
      "loss": 0.0229,
      "step": 622
    },
    {
      "clip_ratio/high_max": 0.001964599148777779,
      "clip_ratio/high_mean": 0.0007723728667770047,
      "clip_ratio/low_mean": 0.0005966082489976543,
      "clip_ratio/low_min": 0.00010300356461812044,
      "clip_ratio/region_mean": 0.0013689811130461749,
      "epoch": 0.058146521300363414,
      "grad_norm": 0.13284693658351898,
      "learning_rate": 2e-07,
      "loss": 0.0567,
      "step": 623
    },
    {
      "clip_ratio/high_max": 0.0020104213690501638,
      "clip_ratio/high_mean": 0.0008271292572317179,
      "clip_ratio/low_mean": 0.0006113947401900077,
      "clip_ratio/low_min": 2.2827407519798726e-05,
      "clip_ratio/region_mean": 0.001438524017430609,
      "epoch": 0.058239854400364,
      "grad_norm": 0.13532742857933044,
      "learning_rate": 2e-07,
      "loss": 0.0416,
      "step": 624
    },
    {
      "clip_ratio/high_max": 0.0020523898565443233,
      "clip_ratio/high_mean": 0.0007984798667166615,
      "clip_ratio/low_mean": 0.0006914174209669,
      "clip_ratio/low_min": 4.993927313989843e-05,
      "clip_ratio/region_mean": 0.0014898972876835614,
      "epoch": 0.058333187500364585,
      "grad_norm": 0.13844189047813416,
      "learning_rate": 2e-07,
      "loss": 0.0361,
      "step": 625
    },
    {
      "clip_ratio/high_max": 0.0023537332672276534,
      "clip_ratio/high_mean": 0.0008083535030891653,
      "clip_ratio/low_mean": 0.000564597527954902,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001372951013763668,
      "epoch": 0.05842652060036516,
      "grad_norm": 0.9572961926460266,
      "learning_rate": 2e-07,
      "loss": 0.049,
      "step": 626
    },
    {
      "clip_ratio/high_max": 0.0019701937708305195,
      "clip_ratio/high_mean": 0.0007563625840703025,
      "clip_ratio/low_mean": 0.0006133209008112317,
      "clip_ratio/low_min": 4.470934345590649e-05,
      "clip_ratio/region_mean": 0.0013696834648726508,
      "epoch": 0.05851985370036575,
      "grad_norm": 0.13144297897815704,
      "learning_rate": 2e-07,
      "loss": 0.0306,
      "step": 627
    },
    {
      "clip_ratio/high_max": 0.002237796004919801,
      "clip_ratio/high_mean": 0.000969190637988504,
      "clip_ratio/low_mean": 0.0005686430158675648,
      "clip_ratio/low_min": 2.095059880957706e-05,
      "clip_ratio/region_mean": 0.001537833668407984,
      "epoch": 0.05861318680036633,
      "grad_norm": 0.1319931000471115,
      "learning_rate": 2e-07,
      "loss": -0.052,
      "step": 628
    },
    {
      "clip_ratio/high_max": 0.002166531510738423,
      "clip_ratio/high_mean": 0.0007745832235741545,
      "clip_ratio/low_mean": 0.0006726450701535214,
      "clip_ratio/low_min": 2.0113709979341365e-05,
      "clip_ratio/region_mean": 0.0014472282819042448,
      "epoch": 0.05870651990036692,
      "grad_norm": 0.12749607861042023,
      "learning_rate": 2e-07,
      "loss": -0.0006,
      "step": 629
    },
    {
      "clip_ratio/high_max": 0.0021250838217383716,
      "clip_ratio/high_mean": 0.0008440735055046389,
      "clip_ratio/low_mean": 0.0006307784060481936,
      "clip_ratio/low_min": 6.43731809759629e-05,
      "clip_ratio/region_mean": 0.00147485194975161,
      "epoch": 0.0587998530003675,
      "grad_norm": 0.12356182932853699,
      "learning_rate": 2e-07,
      "loss": -0.0004,
      "step": 630
    },
    {
      "clip_ratio/high_max": 0.0019235118888900615,
      "clip_ratio/high_mean": 0.0007689325975661632,
      "clip_ratio/low_mean": 0.0007173232024797471,
      "clip_ratio/low_min": 4.3901057324546855e-05,
      "clip_ratio/region_mean": 0.0014862557654851116,
      "epoch": 0.05889318610036808,
      "grad_norm": 0.13854312896728516,
      "learning_rate": 2e-07,
      "loss": 0.0306,
      "step": 631
    },
    {
      "clip_ratio/high_max": 0.0018317053436476272,
      "clip_ratio/high_mean": 0.0007822150928404881,
      "clip_ratio/low_mean": 0.0006304732542048441,
      "clip_ratio/low_min": 1.80792594619561e-05,
      "clip_ratio/region_mean": 0.0014126883797871415,
      "epoch": 0.05898651920036867,
      "grad_norm": 0.12596453726291656,
      "learning_rate": 2e-07,
      "loss": 0.0126,
      "step": 632
    },
    {
      "clip_ratio/high_max": 0.001970906312635634,
      "clip_ratio/high_mean": 0.0007788934872223763,
      "clip_ratio/low_mean": 0.0007234407094074413,
      "clip_ratio/low_min": 6.702151040371973e-05,
      "clip_ratio/region_mean": 0.0015023341911728494,
      "epoch": 0.05907985230036925,
      "grad_norm": 0.12849193811416626,
      "learning_rate": 2e-07,
      "loss": 0.0854,
      "step": 633
    },
    {
      "clip_ratio/high_max": 0.0018440183775965124,
      "clip_ratio/high_mean": 0.0007803206408425467,
      "clip_ratio/low_mean": 0.0006907630377099849,
      "clip_ratio/low_min": 1.703229281702079e-05,
      "clip_ratio/region_mean": 0.0014710836330777965,
      "epoch": 0.05917318540036983,
      "grad_norm": 0.1286572962999344,
      "learning_rate": 2e-07,
      "loss": 0.011,
      "step": 634
    },
    {
      "clip_ratio/high_max": 0.0019412162801017985,
      "clip_ratio/high_mean": 0.0007511263193009654,
      "clip_ratio/low_mean": 0.000684510347127798,
      "clip_ratio/low_min": 4.662322589865653e-05,
      "clip_ratio/region_mean": 0.0014356366882566363,
      "epoch": 0.059266518500370416,
      "grad_norm": 0.13404014706611633,
      "learning_rate": 2e-07,
      "loss": 0.0323,
      "step": 635
    },
    {
      "clip_ratio/high_max": 0.0015266533373505808,
      "clip_ratio/high_mean": 0.0006573283280886244,
      "clip_ratio/low_mean": 0.0007011635007074801,
      "clip_ratio/low_min": 2.815088282659417e-05,
      "clip_ratio/region_mean": 0.0013584918160631787,
      "epoch": 0.059359851600371,
      "grad_norm": 0.11963405460119247,
      "learning_rate": 2e-07,
      "loss": 0.0402,
      "step": 636
    },
    {
      "clip_ratio/high_max": 0.002044441967882449,
      "clip_ratio/high_mean": 0.0008332400466315448,
      "clip_ratio/low_mean": 0.0006260903501242865,
      "clip_ratio/low_min": 3.764297889574664e-05,
      "clip_ratio/region_mean": 0.001459330422221683,
      "epoch": 0.05945318470037158,
      "grad_norm": 0.1403578370809555,
      "learning_rate": 2e-07,
      "loss": 0.0323,
      "step": 637
    },
    {
      "clip_ratio/high_max": 0.001747186659486033,
      "clip_ratio/high_mean": 0.0007683554540562909,
      "clip_ratio/low_mean": 0.0007259731373778777,
      "clip_ratio/low_min": 9.530715442451765e-05,
      "clip_ratio/region_mean": 0.0014943286187190097,
      "epoch": 0.059546517800372165,
      "grad_norm": 0.15727828443050385,
      "learning_rate": 2e-07,
      "loss": 0.0381,
      "step": 638
    },
    {
      "clip_ratio/high_max": 0.0020102968665014487,
      "clip_ratio/high_mean": 0.0007979989732120885,
      "clip_ratio/low_mean": 0.0005875053593626944,
      "clip_ratio/low_min": 1.1825922229036223e-05,
      "clip_ratio/region_mean": 0.001385504350764677,
      "epoch": 0.05963985090037275,
      "grad_norm": 0.12717203795909882,
      "learning_rate": 2e-07,
      "loss": 0.0188,
      "step": 639
    },
    {
      "clip_ratio/high_max": 0.0016796312702354044,
      "clip_ratio/high_mean": 0.0006957236291782465,
      "clip_ratio/low_mean": 0.0006574747694685357,
      "clip_ratio/low_min": 8.163578058884013e-05,
      "clip_ratio/region_mean": 0.0013531984041037504,
      "epoch": 0.059733184000373335,
      "grad_norm": 0.11941295862197876,
      "learning_rate": 2e-07,
      "loss": 0.0223,
      "step": 640
    },
    {
      "clip_ratio/high_max": 0.0017423394383513369,
      "clip_ratio/high_mean": 0.0007042491397442063,
      "clip_ratio/low_mean": 0.000573540504774428,
      "clip_ratio/low_min": 4.313974295655498e-05,
      "clip_ratio/region_mean": 0.001277789669984486,
      "completions/clipped_ratio": 0.016802106584821397,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4090.0,
      "completions/mean_length": 657.5347900390625,
      "completions/mean_terminated_length": 598.7739868164062,
      "completions/min_length": 81.0,
      "completions/min_terminated_length": 81.0,
      "epoch": 0.05982651710037391,
      "grad_norm": 0.13230295479297638,
      "learning_rate": 2e-07,
      "loss": 0.0184,
      "num_tokens": 502405925.0,
      "reward": 0.5842459797859192,
      "reward_std": 0.19038790464401245,
      "rewards/simpleverify_reward/mean": 0.5842459797859192,
      "rewards/simpleverify_reward/std": 0.49285364151000977,
      "step": 641
    },
    {
      "clip_ratio/high_max": 0.0015028251145849936,
      "clip_ratio/high_mean": 0.0006032494839018909,
      "clip_ratio/low_mean": 0.0006449195443565259,
      "clip_ratio/low_min": 4.8747007895144634e-05,
      "clip_ratio/region_mean": 0.0012481690100685228,
      "epoch": 0.0599198502003745,
      "grad_norm": 0.13166922330856323,
      "learning_rate": 2e-07,
      "loss": 0.0487,
      "step": 642
    },
    {
      "clip_ratio/high_max": 0.001954842133272905,
      "clip_ratio/high_mean": 0.0007006585929048015,
      "clip_ratio/low_mean": 0.00046967056550784037,
      "clip_ratio/low_min": 1.3560425031755585e-05,
      "clip_ratio/region_mean": 0.0011703291711455677,
      "epoch": 0.060013183300375084,
      "grad_norm": 0.1293753981590271,
      "learning_rate": 2e-07,
      "loss": 0.0022,
      "step": 643
    },
    {
      "clip_ratio/high_max": 0.0019306345930090174,
      "clip_ratio/high_mean": 0.000710837999577052,
      "clip_ratio/low_mean": 0.00047347288273158483,
      "clip_ratio/low_min": 6.865114301035646e-06,
      "clip_ratio/region_mean": 0.0011843108586617745,
      "epoch": 0.06010651640037567,
      "grad_norm": 0.12771207094192505,
      "learning_rate": 2e-07,
      "loss": -0.0067,
      "step": 644
    },
    {
      "clip_ratio/high_max": 0.001788378882338293,
      "clip_ratio/high_mean": 0.0007058359806251246,
      "clip_ratio/low_mean": 0.0005115430540172383,
      "clip_ratio/low_min": 3.835004372376716e-05,
      "clip_ratio/region_mean": 0.0012173790128144901,
      "epoch": 0.06019984950037625,
      "grad_norm": 0.48159095644950867,
      "learning_rate": 2e-07,
      "loss": 0.0321,
      "step": 645
    },
    {
      "clip_ratio/high_max": 0.0021168722305446863,
      "clip_ratio/high_mean": 0.0007490512161894003,
      "clip_ratio/low_mean": 0.0006361779996950645,
      "clip_ratio/low_min": 3.291979146524682e-05,
      "clip_ratio/region_mean": 0.0013852292540832423,
      "epoch": 0.06029318260037683,
      "grad_norm": 0.1200612485408783,
      "learning_rate": 2e-07,
      "loss": 0.0187,
      "step": 646
    },
    {
      "clip_ratio/high_max": 0.0016230874316534027,
      "clip_ratio/high_mean": 0.0006015648868924472,
      "clip_ratio/low_mean": 0.0006159587674119393,
      "clip_ratio/low_min": 2.6342974706494715e-05,
      "clip_ratio/region_mean": 0.0012175236188340932,
      "epoch": 0.06038651570037742,
      "grad_norm": 0.11347278207540512,
      "learning_rate": 2e-07,
      "loss": 0.0471,
      "step": 647
    },
    {
      "clip_ratio/high_max": 0.0018738950711849611,
      "clip_ratio/high_mean": 0.0007123055756892427,
      "clip_ratio/low_mean": 0.0005526820277736988,
      "clip_ratio/low_min": 1.7337031749775633e-05,
      "clip_ratio/region_mean": 0.0012649875934584998,
      "epoch": 0.060479848800377996,
      "grad_norm": 0.15207113325595856,
      "learning_rate": 2e-07,
      "loss": 0.0579,
      "step": 648
    },
    {
      "clip_ratio/high_max": 0.0016506957617821172,
      "clip_ratio/high_mean": 0.0006782404234400019,
      "clip_ratio/low_mean": 0.0005686398226316669,
      "clip_ratio/low_min": 2.8563290470629e-05,
      "clip_ratio/region_mean": 0.001246880266990047,
      "epoch": 0.06057318190037858,
      "grad_norm": 0.12372089922428131,
      "learning_rate": 2e-07,
      "loss": 0.0521,
      "step": 649
    },
    {
      "clip_ratio/high_max": 0.001653977349633351,
      "clip_ratio/high_mean": 0.0007160591285355622,
      "clip_ratio/low_mean": 0.0005693523125955835,
      "clip_ratio/low_min": 1.0982253115798812e-05,
      "clip_ratio/region_mean": 0.0012854114393121563,
      "epoch": 0.060666515000379166,
      "grad_norm": 0.12325287610292435,
      "learning_rate": 2e-07,
      "loss": 0.0323,
      "step": 650
    },
    {
      "clip_ratio/high_max": 0.002118610129400622,
      "clip_ratio/high_mean": 0.0008132473249133909,
      "clip_ratio/low_mean": 0.0005348450949895778,
      "clip_ratio/low_min": 1.1079595424234867e-05,
      "clip_ratio/region_mean": 0.0013480924390023574,
      "epoch": 0.06075984810037975,
      "grad_norm": 0.12609155476093292,
      "learning_rate": 2e-07,
      "loss": -0.0298,
      "step": 651
    },
    {
      "clip_ratio/high_max": 0.0018145137692044955,
      "clip_ratio/high_mean": 0.0006364323307934683,
      "clip_ratio/low_mean": 0.0005615529062197311,
      "clip_ratio/low_min": 2.166505146306008e-05,
      "clip_ratio/region_mean": 0.001197985217004316,
      "epoch": 0.06085318120038033,
      "grad_norm": 0.13217772543430328,
      "learning_rate": 2e-07,
      "loss": 0.062,
      "step": 652
    },
    {
      "clip_ratio/high_max": 0.001685916467977222,
      "clip_ratio/high_mean": 0.0006090159859013511,
      "clip_ratio/low_mean": 0.0006306676805252209,
      "clip_ratio/low_min": 5.871406028745696e-05,
      "clip_ratio/region_mean": 0.0012396836245898157,
      "epoch": 0.060946514300380915,
      "grad_norm": 0.12306054681539536,
      "learning_rate": 2e-07,
      "loss": 0.0656,
      "step": 653
    },
    {
      "clip_ratio/high_max": 0.0016424743953393772,
      "clip_ratio/high_mean": 0.0006845913958386518,
      "clip_ratio/low_mean": 0.0005167244721633324,
      "clip_ratio/low_min": 2.889035204134416e-05,
      "clip_ratio/region_mean": 0.001201315870275721,
      "epoch": 0.0610398474003815,
      "grad_norm": 0.11775021255016327,
      "learning_rate": 2e-07,
      "loss": 0.0117,
      "step": 654
    },
    {
      "clip_ratio/high_max": 0.0020380984351504594,
      "clip_ratio/high_mean": 0.0007839371555746766,
      "clip_ratio/low_mean": 0.0006122116101323627,
      "clip_ratio/low_min": 5.395538300945191e-05,
      "clip_ratio/region_mean": 0.0013961487748019863,
      "epoch": 0.061133180500382085,
      "grad_norm": 0.14710205793380737,
      "learning_rate": 2e-07,
      "loss": 0.0476,
      "step": 655
    },
    {
      "clip_ratio/high_max": 0.0017588314403838012,
      "clip_ratio/high_mean": 0.0007149065477278782,
      "clip_ratio/low_mean": 0.000559953332412988,
      "clip_ratio/low_min": 8.326056558871642e-05,
      "clip_ratio/region_mean": 0.0012748598455800675,
      "epoch": 0.061226513600382663,
      "grad_norm": 0.12796972692012787,
      "learning_rate": 2e-07,
      "loss": 0.0619,
      "step": 656
    },
    {
      "clip_ratio/high_max": 0.0014832530505373143,
      "clip_ratio/high_mean": 0.0006230037251953036,
      "clip_ratio/low_mean": 0.0005755038291681558,
      "clip_ratio/low_min": 8.719855759409256e-05,
      "clip_ratio/region_mean": 0.0011985075871052686,
      "epoch": 0.06131984670038325,
      "grad_norm": 0.11228270828723907,
      "learning_rate": 2e-07,
      "loss": 0.036,
      "step": 657
    },
    {
      "clip_ratio/high_max": 0.0018529851477069315,
      "clip_ratio/high_mean": 0.0006681571121589513,
      "clip_ratio/low_mean": 0.0005821256563649513,
      "clip_ratio/low_min": 2.235556621599244e-05,
      "clip_ratio/region_mean": 0.0012502827557909768,
      "epoch": 0.061413179800383834,
      "grad_norm": 52775.59765625,
      "learning_rate": 2e-07,
      "loss": 2.0578,
      "step": 658
    },
    {
      "clip_ratio/high_max": 0.0015632145241397666,
      "clip_ratio/high_mean": 0.0006187711987877265,
      "clip_ratio/low_mean": 0.0005859623215656029,
      "clip_ratio/low_min": 3.3528843232488725e-05,
      "clip_ratio/region_mean": 0.0012047335112583824,
      "epoch": 0.06150651290038442,
      "grad_norm": 0.12432112544775009,
      "learning_rate": 2e-07,
      "loss": 0.0526,
      "step": 659
    },
    {
      "clip_ratio/high_max": 0.0014263695156842005,
      "clip_ratio/high_mean": 0.0006495874622487463,
      "clip_ratio/low_mean": 0.00048281699082508567,
      "clip_ratio/low_min": 4.417094805830857e-05,
      "clip_ratio/region_mean": 0.0011324044462526217,
      "epoch": 0.061599846000385,
      "grad_norm": 0.11659005284309387,
      "learning_rate": 2e-07,
      "loss": -0.0104,
      "step": 660
    },
    {
      "clip_ratio/high_max": 0.0016166997447726317,
      "clip_ratio/high_mean": 0.0007174753482104279,
      "clip_ratio/low_mean": 0.0005444566204459989,
      "clip_ratio/low_min": 3.9566070881846827e-05,
      "clip_ratio/region_mean": 0.001261931967746932,
      "epoch": 0.06169317910038558,
      "grad_norm": 0.11360806971788406,
      "learning_rate": 2e-07,
      "loss": 0.0204,
      "step": 661
    },
    {
      "clip_ratio/high_max": 0.0020287233346607536,
      "clip_ratio/high_mean": 0.0007829574824427254,
      "clip_ratio/low_mean": 0.0005669868078257423,
      "clip_ratio/low_min": 2.9407152396743186e-05,
      "clip_ratio/region_mean": 0.0013499443084583618,
      "epoch": 0.06178651220038617,
      "grad_norm": 0.11427122354507446,
      "learning_rate": 2e-07,
      "loss": 0.0314,
      "step": 662
    },
    {
      "clip_ratio/high_max": 0.0018698536368901841,
      "clip_ratio/high_mean": 0.0007680224589421414,
      "clip_ratio/low_mean": 0.000497693049510417,
      "clip_ratio/low_min": 1.540927041787654e-05,
      "clip_ratio/region_mean": 0.0012657155166380107,
      "epoch": 0.061879845300386746,
      "grad_norm": 0.12936750054359436,
      "learning_rate": 2e-07,
      "loss": 0.0193,
      "step": 663
    },
    {
      "clip_ratio/high_max": 0.002091225585900247,
      "clip_ratio/high_mean": 0.0007886120911280159,
      "clip_ratio/low_mean": 0.0004546863688119629,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012432984440238215,
      "epoch": 0.06197317840038733,
      "grad_norm": 0.10685745626688004,
      "learning_rate": 2e-07,
      "loss": -0.0091,
      "step": 664
    },
    {
      "clip_ratio/high_max": 0.0016517172953172121,
      "clip_ratio/high_mean": 0.0006277057273109676,
      "clip_ratio/low_mean": 0.0005898472163607948,
      "clip_ratio/low_min": 7.325894785026321e-05,
      "clip_ratio/region_mean": 0.001217552930029342,
      "epoch": 0.062066511500387916,
      "grad_norm": 0.12509962916374207,
      "learning_rate": 2e-07,
      "loss": 0.0568,
      "step": 665
    },
    {
      "clip_ratio/high_max": 0.0017785399031708948,
      "clip_ratio/high_mean": 0.0006465633487096056,
      "clip_ratio/low_mean": 0.00047769745833647903,
      "clip_ratio/low_min": 2.0256680272723315e-05,
      "clip_ratio/region_mean": 0.0011242608015891165,
      "epoch": 0.0621598446003885,
      "grad_norm": 0.14455284178256989,
      "learning_rate": 2e-07,
      "loss": 0.0412,
      "step": 666
    },
    {
      "clip_ratio/high_max": 0.001821024139644578,
      "clip_ratio/high_mean": 0.0008029854543565307,
      "clip_ratio/low_mean": 0.0005656461144099012,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013686315724044107,
      "epoch": 0.06225317770038908,
      "grad_norm": 0.12351208925247192,
      "learning_rate": 2e-07,
      "loss": -0.0174,
      "step": 667
    },
    {
      "clip_ratio/high_max": 0.0019680398763739504,
      "clip_ratio/high_mean": 0.0008126700558932498,
      "clip_ratio/low_mean": 0.0005225878221608582,
      "clip_ratio/low_min": 1.5672016161261126e-05,
      "clip_ratio/region_mean": 0.0013352578826015815,
      "epoch": 0.062346510800389665,
      "grad_norm": 0.13760676980018616,
      "learning_rate": 2e-07,
      "loss": 0.0136,
      "step": 668
    },
    {
      "clip_ratio/high_max": 0.001881914162368048,
      "clip_ratio/high_mean": 0.0007741589997749543,
      "clip_ratio/low_mean": 0.0005514615650099586,
      "clip_ratio/low_min": 7.84289113653358e-06,
      "clip_ratio/region_mean": 0.0013256205784273334,
      "epoch": 0.06243984390039025,
      "grad_norm": 0.13342776894569397,
      "learning_rate": 2e-07,
      "loss": 0.02,
      "step": 669
    },
    {
      "clip_ratio/high_max": 0.001754728626110591,
      "clip_ratio/high_mean": 0.0006540088870679028,
      "clip_ratio/low_mean": 0.0006097197365306783,
      "clip_ratio/low_min": 4.9522039262228645e-05,
      "clip_ratio/region_mean": 0.00126372862723656,
      "epoch": 0.06253317700039084,
      "grad_norm": 0.1284882128238678,
      "learning_rate": 2e-07,
      "loss": 0.0101,
      "step": 670
    },
    {
      "clip_ratio/high_max": 0.0019851217948598787,
      "clip_ratio/high_mean": 0.000803604707471095,
      "clip_ratio/low_mean": 0.0005087060053483583,
      "clip_ratio/low_min": 2.229356141469907e-05,
      "clip_ratio/region_mean": 0.0013123106655257288,
      "epoch": 0.06262651010039141,
      "grad_norm": 0.14094722270965576,
      "learning_rate": 2e-07,
      "loss": -0.0074,
      "step": 671
    },
    {
      "clip_ratio/high_max": 0.0016339335852535442,
      "clip_ratio/high_mean": 0.0007240754148369888,
      "clip_ratio/low_mean": 0.0005846838666911935,
      "clip_ratio/low_min": 3.610417934396537e-05,
      "clip_ratio/region_mean": 0.001308759266976267,
      "epoch": 0.062719843200392,
      "grad_norm": 0.12171252816915512,
      "learning_rate": 2e-07,
      "loss": 0.0019,
      "step": 672
    },
    {
      "clip_ratio/high_max": 0.0016549150641367305,
      "clip_ratio/high_mean": 0.0006692086608381942,
      "clip_ratio/low_mean": 0.0006425303654395975,
      "clip_ratio/low_min": 4.715068916993914e-05,
      "clip_ratio/region_mean": 0.0013117390481056646,
      "epoch": 0.06281317630039258,
      "grad_norm": 0.11812646687030792,
      "learning_rate": 2e-07,
      "loss": 0.0799,
      "step": 673
    },
    {
      "clip_ratio/high_max": 0.0018441741267452016,
      "clip_ratio/high_mean": 0.0007506917554565007,
      "clip_ratio/low_mean": 0.0004898564029645058,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012405481575115118,
      "epoch": 0.06290650940039316,
      "grad_norm": 0.11893141269683838,
      "learning_rate": 2e-07,
      "loss": -0.0029,
      "step": 674
    },
    {
      "clip_ratio/high_max": 0.001666164167545503,
      "clip_ratio/high_mean": 0.000742921574783395,
      "clip_ratio/low_mean": 0.0006051517193554901,
      "clip_ratio/low_min": 7.174543225119123e-05,
      "clip_ratio/region_mean": 0.001348073285043938,
      "epoch": 0.06299984250039375,
      "grad_norm": 0.20682616531848907,
      "learning_rate": 2e-07,
      "loss": 0.0202,
      "step": 675
    },
    {
      "clip_ratio/high_max": 0.0018505779844417702,
      "clip_ratio/high_mean": 0.0006919997986187809,
      "clip_ratio/low_mean": 0.0006685145599476527,
      "clip_ratio/low_min": 3.8661462895106524e-05,
      "clip_ratio/region_mean": 0.0013605143976747058,
      "epoch": 0.06309317560039433,
      "grad_norm": 0.1127462238073349,
      "learning_rate": 2e-07,
      "loss": 0.0575,
      "step": 676
    },
    {
      "clip_ratio/high_max": 0.001542382062325487,
      "clip_ratio/high_mean": 0.0006228030470083468,
      "clip_ratio/low_mean": 0.0005404314233601326,
      "clip_ratio/low_min": 4.3086947698611766e-05,
      "clip_ratio/region_mean": 0.0011632344612735324,
      "epoch": 0.06318650870039491,
      "grad_norm": 0.13076160848140717,
      "learning_rate": 2e-07,
      "loss": 0.0045,
      "step": 677
    },
    {
      "clip_ratio/high_max": 0.0021443464283947833,
      "clip_ratio/high_mean": 0.0008728145439818036,
      "clip_ratio/low_mean": 0.0005523702911887085,
      "clip_ratio/low_min": 3.79922021238599e-05,
      "clip_ratio/region_mean": 0.0014251848406274803,
      "epoch": 0.0632798418003955,
      "grad_norm": 0.1288592368364334,
      "learning_rate": 2e-07,
      "loss": -0.0118,
      "step": 678
    },
    {
      "clip_ratio/high_max": 0.0020120497902098577,
      "clip_ratio/high_mean": 0.0007102653780748369,
      "clip_ratio/low_mean": 0.000562560423531977,
      "clip_ratio/low_min": 4.000227272626944e-05,
      "clip_ratio/region_mean": 0.0012728257825074252,
      "epoch": 0.06337317490039608,
      "grad_norm": 0.1331200897693634,
      "learning_rate": 2e-07,
      "loss": 0.0519,
      "step": 679
    },
    {
      "clip_ratio/high_max": 0.0018288054161530454,
      "clip_ratio/high_mean": 0.0007199072488219826,
      "clip_ratio/low_mean": 0.0005980715468467679,
      "clip_ratio/low_min": 4.696734413300874e-05,
      "clip_ratio/region_mean": 0.0013179787783883512,
      "epoch": 0.06346650800039666,
      "grad_norm": 0.12625592947006226,
      "learning_rate": 2e-07,
      "loss": 0.0412,
      "step": 680
    },
    {
      "clip_ratio/high_max": 0.0021106762360432185,
      "clip_ratio/high_mean": 0.0007806417006577249,
      "clip_ratio/low_mean": 0.0005319642650647438,
      "clip_ratio/low_min": 3.516345350362826e-05,
      "clip_ratio/region_mean": 0.0013126059420756064,
      "epoch": 0.06355984110039725,
      "grad_norm": 0.13658370077610016,
      "learning_rate": 2e-07,
      "loss": 0.0018,
      "step": 681
    },
    {
      "clip_ratio/high_max": 0.0015075959672685713,
      "clip_ratio/high_mean": 0.0006276505018831813,
      "clip_ratio/low_mean": 0.0006489465158665553,
      "clip_ratio/low_min": 3.836808809865033e-05,
      "clip_ratio/region_mean": 0.0012765970350301359,
      "epoch": 0.06365317420039783,
      "grad_norm": 0.13418620824813843,
      "learning_rate": 2e-07,
      "loss": 0.0537,
      "step": 682
    },
    {
      "clip_ratio/high_max": 0.0016228008389589377,
      "clip_ratio/high_mean": 0.0006652680986007908,
      "clip_ratio/low_mean": 0.0005927661004534457,
      "clip_ratio/low_min": 1.394466744386591e-05,
      "clip_ratio/region_mean": 0.0012580341863213107,
      "epoch": 0.06374650730039842,
      "grad_norm": 0.12442555278539658,
      "learning_rate": 2e-07,
      "loss": 0.0231,
      "step": 683
    },
    {
      "clip_ratio/high_max": 0.0018634249390743207,
      "clip_ratio/high_mean": 0.0006525746757688466,
      "clip_ratio/low_mean": 0.0005686860476998845,
      "clip_ratio/low_min": 1.0129660040547606e-05,
      "clip_ratio/region_mean": 0.0012212607252877206,
      "epoch": 0.063839840400399,
      "grad_norm": 0.12511055171489716,
      "learning_rate": 2e-07,
      "loss": 0.0395,
      "step": 684
    },
    {
      "clip_ratio/high_max": 0.0017387674888595939,
      "clip_ratio/high_mean": 0.0006673971001873724,
      "clip_ratio/low_mean": 0.0005974502801109338,
      "clip_ratio/low_min": 2.1564604139712173e-05,
      "clip_ratio/region_mean": 0.0012648473857552744,
      "epoch": 0.06393317350039958,
      "grad_norm": 0.12611344456672668,
      "learning_rate": 2e-07,
      "loss": 0.0707,
      "step": 685
    },
    {
      "clip_ratio/high_max": 0.0017114603106165305,
      "clip_ratio/high_mean": 0.0007179043768701376,
      "clip_ratio/low_mean": 0.0005226764351391466,
      "clip_ratio/low_min": 1.4891589671606198e-05,
      "clip_ratio/region_mean": 0.001240580815647263,
      "epoch": 0.06402650660040017,
      "grad_norm": 0.1261724978685379,
      "learning_rate": 2e-07,
      "loss": 0.005,
      "step": 686
    },
    {
      "clip_ratio/high_max": 0.001738532566378126,
      "clip_ratio/high_mean": 0.0006687697177767404,
      "clip_ratio/low_mean": 0.0005617700389848324,
      "clip_ratio/low_min": 2.4767730792518705e-05,
      "clip_ratio/region_mean": 0.0012305397758609615,
      "epoch": 0.06411983970040075,
      "grad_norm": 0.14246691763401031,
      "learning_rate": 2e-07,
      "loss": 0.0376,
      "step": 687
    },
    {
      "clip_ratio/high_max": 0.001610835715837311,
      "clip_ratio/high_mean": 0.0007581183181173401,
      "clip_ratio/low_mean": 0.0005493717580975499,
      "clip_ratio/low_min": 2.5688450477900915e-05,
      "clip_ratio/region_mean": 0.0013074900780338794,
      "epoch": 0.06421317280040133,
      "grad_norm": 0.11837201565504074,
      "learning_rate": 2e-07,
      "loss": 0.0017,
      "step": 688
    },
    {
      "clip_ratio/high_max": 0.0017353488874505274,
      "clip_ratio/high_mean": 0.000733640423277393,
      "clip_ratio/low_mean": 0.0005343306884242338,
      "clip_ratio/low_min": 6.563397755598999e-05,
      "clip_ratio/region_mean": 0.0012679711071541533,
      "epoch": 0.06430650590040192,
      "grad_norm": 0.12705519795417786,
      "learning_rate": 2e-07,
      "loss": -0.0146,
      "step": 689
    },
    {
      "clip_ratio/high_max": 0.001730902753479313,
      "clip_ratio/high_mean": 0.0006527771220135037,
      "clip_ratio/low_mean": 0.0006498619150079321,
      "clip_ratio/low_min": 7.652586282347329e-05,
      "clip_ratio/region_mean": 0.0013026390297454782,
      "epoch": 0.0643998390004025,
      "grad_norm": 0.14517691731452942,
      "learning_rate": 2e-07,
      "loss": 0.0511,
      "step": 690
    },
    {
      "clip_ratio/high_max": 0.001656091775657842,
      "clip_ratio/high_mean": 0.0006908269551786361,
      "clip_ratio/low_mean": 0.0005910973231948446,
      "clip_ratio/low_min": 3.2440868380945176e-05,
      "clip_ratio/region_mean": 0.0012819242947443854,
      "epoch": 0.06449317210040308,
      "grad_norm": 0.11404888331890106,
      "learning_rate": 2e-07,
      "loss": 0.0295,
      "step": 691
    },
    {
      "clip_ratio/high_max": 0.0016943153059401084,
      "clip_ratio/high_mean": 0.0007492045824619709,
      "clip_ratio/low_mean": 0.0006518374034385488,
      "clip_ratio/low_min": 0.00010651837510522455,
      "clip_ratio/region_mean": 0.0014010419581609312,
      "epoch": 0.06458650520040367,
      "grad_norm": 0.13084450364112854,
      "learning_rate": 2e-07,
      "loss": 0.0515,
      "step": 692
    },
    {
      "clip_ratio/high_max": 0.0013938709416834172,
      "clip_ratio/high_mean": 0.0005792533711428405,
      "clip_ratio/low_mean": 0.000583945203516123,
      "clip_ratio/low_min": 3.434501377341803e-05,
      "clip_ratio/region_mean": 0.0011631985726126004,
      "epoch": 0.06467983830040425,
      "grad_norm": 0.13028603792190552,
      "learning_rate": 2e-07,
      "loss": 0.0409,
      "step": 693
    },
    {
      "clip_ratio/high_max": 0.0020387881522765383,
      "clip_ratio/high_mean": 0.0006953164102014853,
      "clip_ratio/low_mean": 0.0005997585139994044,
      "clip_ratio/low_min": 2.0589081941579934e-05,
      "clip_ratio/region_mean": 0.0012950749405717943,
      "epoch": 0.06477317140040484,
      "grad_norm": 0.15035361051559448,
      "learning_rate": 2e-07,
      "loss": 0.0447,
      "step": 694
    },
    {
      "clip_ratio/high_max": 0.001968824606592534,
      "clip_ratio/high_mean": 0.0006885302464070264,
      "clip_ratio/low_mean": 0.0006388464607880451,
      "clip_ratio/low_min": 5.361286002880661e-05,
      "clip_ratio/region_mean": 0.0013273767217469867,
      "epoch": 0.06486650450040542,
      "grad_norm": 0.12211810052394867,
      "learning_rate": 2e-07,
      "loss": 0.0423,
      "step": 695
    },
    {
      "clip_ratio/high_max": 0.0018784432213578839,
      "clip_ratio/high_mean": 0.0007608671276102541,
      "clip_ratio/low_mean": 0.0005259094959910726,
      "clip_ratio/low_min": 6.476586167991627e-05,
      "clip_ratio/region_mean": 0.0012867766454291996,
      "epoch": 0.064959837600406,
      "grad_norm": 0.12226026505231857,
      "learning_rate": 2e-07,
      "loss": 0.0267,
      "step": 696
    },
    {
      "clip_ratio/high_max": 0.0018431671887810808,
      "clip_ratio/high_mean": 0.0007057022412482183,
      "clip_ratio/low_mean": 0.0005839042160005192,
      "clip_ratio/low_min": 5.816106386191677e-05,
      "clip_ratio/region_mean": 0.0012896064508822747,
      "epoch": 0.06505317070040659,
      "grad_norm": 0.12323998659849167,
      "learning_rate": 2e-07,
      "loss": -0.0041,
      "step": 697
    },
    {
      "clip_ratio/high_max": 0.00163398525910452,
      "clip_ratio/high_mean": 0.0007089340015227208,
      "clip_ratio/low_mean": 0.0006319398671621457,
      "clip_ratio/low_min": 8.120212078210898e-05,
      "clip_ratio/region_mean": 0.0013408738632278983,
      "epoch": 0.06514650380040717,
      "grad_norm": 0.149945467710495,
      "learning_rate": 2e-07,
      "loss": 0.0397,
      "step": 698
    },
    {
      "clip_ratio/high_max": 0.001924309523019474,
      "clip_ratio/high_mean": 0.0007362278865912231,
      "clip_ratio/low_mean": 0.0006118863766459981,
      "clip_ratio/low_min": 5.929132476012455e-05,
      "clip_ratio/region_mean": 0.0013481142668752,
      "epoch": 0.06523983690040774,
      "grad_norm": 0.13071078062057495,
      "learning_rate": 2e-07,
      "loss": 0.0419,
      "step": 699
    },
    {
      "clip_ratio/high_max": 0.0016351238264178392,
      "clip_ratio/high_mean": 0.0006699943733110558,
      "clip_ratio/low_mean": 0.0005900290379940998,
      "clip_ratio/low_min": 4.705017909145681e-05,
      "clip_ratio/region_mean": 0.0012600233785633463,
      "epoch": 0.06533317000040834,
      "grad_norm": 0.1272680014371872,
      "learning_rate": 2e-07,
      "loss": 0.0632,
      "step": 700
    },
    {
      "clip_ratio/high_max": 0.0018430365162203088,
      "clip_ratio/high_mean": 0.000714188628080592,
      "clip_ratio/low_mean": 0.0006304321350398823,
      "clip_ratio/low_min": 5.406531727203401e-05,
      "clip_ratio/region_mean": 0.0013446207849483471,
      "epoch": 0.06542650310040891,
      "grad_norm": 0.12821176648139954,
      "learning_rate": 2e-07,
      "loss": 0.0542,
      "step": 701
    },
    {
      "clip_ratio/high_max": 0.0017104860598919913,
      "clip_ratio/high_mean": 0.0007120731152099324,
      "clip_ratio/low_mean": 0.000566356209674268,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012784293430740945,
      "epoch": 0.06551983620040949,
      "grad_norm": 0.12871773540973663,
      "learning_rate": 2e-07,
      "loss": -0.0011,
      "step": 702
    },
    {
      "clip_ratio/high_max": 0.0017650730878813192,
      "clip_ratio/high_mean": 0.0007162299425544916,
      "clip_ratio/low_mean": 0.00052325281285448,
      "clip_ratio/low_min": 1.2744698324240744e-05,
      "clip_ratio/region_mean": 0.0012394827026582789,
      "epoch": 0.06561316930041008,
      "grad_norm": 0.1262146383523941,
      "learning_rate": 2e-07,
      "loss": 0.008,
      "step": 703
    },
    {
      "clip_ratio/high_max": 0.0017712773187668063,
      "clip_ratio/high_mean": 0.0006911707832841785,
      "clip_ratio/low_mean": 0.0005888854225304385,
      "clip_ratio/low_min": 2.155915899493266e-05,
      "clip_ratio/region_mean": 0.0012800561744370498,
      "epoch": 0.06570650240041066,
      "grad_norm": 0.12825819849967957,
      "learning_rate": 2e-07,
      "loss": 0.0453,
      "step": 704
    },
    {
      "clip_ratio/high_max": 0.0018428367911837995,
      "clip_ratio/high_mean": 0.0006955708922760095,
      "clip_ratio/low_mean": 0.0005074369155408931,
      "clip_ratio/low_min": 5.127897748025134e-05,
      "clip_ratio/region_mean": 0.0012030078469251748,
      "epoch": 0.06579983550041126,
      "grad_norm": 0.13235251605510712,
      "learning_rate": 2e-07,
      "loss": 0.0508,
      "step": 705
    },
    {
      "clip_ratio/high_max": 0.0018140952415706124,
      "clip_ratio/high_mean": 0.0007767200331727508,
      "clip_ratio/low_mean": 0.00055802962378948,
      "clip_ratio/low_min": 1.4016595741850324e-05,
      "clip_ratio/region_mean": 0.0013347496387723368,
      "epoch": 0.06589316860041183,
      "grad_norm": 0.12588077783584595,
      "learning_rate": 2e-07,
      "loss": 0.0285,
      "step": 706
    },
    {
      "clip_ratio/high_max": 0.0020187348272884265,
      "clip_ratio/high_mean": 0.0007664247641514521,
      "clip_ratio/low_mean": 0.0005913617524129222,
      "clip_ratio/low_min": 2.1236834072624333e-05,
      "clip_ratio/region_mean": 0.0013577864847320598,
      "epoch": 0.06598650170041241,
      "grad_norm": 0.12371828407049179,
      "learning_rate": 2e-07,
      "loss": 0.0063,
      "step": 707
    },
    {
      "clip_ratio/high_max": 0.001911364270199556,
      "clip_ratio/high_mean": 0.0007227292880997993,
      "clip_ratio/low_mean": 0.0005666977522196248,
      "clip_ratio/low_min": 2.8496522645582445e-05,
      "clip_ratio/region_mean": 0.0012894270548713394,
      "epoch": 0.066079834800413,
      "grad_norm": 0.4781041443347931,
      "learning_rate": 2e-07,
      "loss": 0.0267,
      "step": 708
    },
    {
      "clip_ratio/high_max": 0.0016880758485058323,
      "clip_ratio/high_mean": 0.0006627570710406872,
      "clip_ratio/low_mean": 0.0005344714281818597,
      "clip_ratio/low_min": 2.2407637516153045e-05,
      "clip_ratio/region_mean": 0.0011972284883086104,
      "epoch": 0.06617316790041358,
      "grad_norm": 0.12130901962518692,
      "learning_rate": 2e-07,
      "loss": 0.0156,
      "step": 709
    },
    {
      "clip_ratio/high_max": 0.0017600160208530724,
      "clip_ratio/high_mean": 0.0006227733556443127,
      "clip_ratio/low_mean": 0.0006084926553739933,
      "clip_ratio/low_min": 1.196401262859581e-05,
      "clip_ratio/region_mean": 0.0012312660583120305,
      "epoch": 0.06626650100041416,
      "grad_norm": 0.14432811737060547,
      "learning_rate": 2e-07,
      "loss": 0.0349,
      "step": 710
    },
    {
      "clip_ratio/high_max": 0.001989369331568014,
      "clip_ratio/high_mean": 0.0007471108274330618,
      "clip_ratio/low_mean": 0.000570840547879925,
      "clip_ratio/low_min": 4.3036417991970666e-05,
      "clip_ratio/region_mean": 0.0013179513553041033,
      "epoch": 0.06635983410041475,
      "grad_norm": 0.1312975436449051,
      "learning_rate": 2e-07,
      "loss": -0.0153,
      "step": 711
    },
    {
      "clip_ratio/high_max": 0.0018217051874671597,
      "clip_ratio/high_mean": 0.0006972681658226065,
      "clip_ratio/low_mean": 0.0005065220320830122,
      "clip_ratio/low_min": 1.062383125827182e-05,
      "clip_ratio/region_mean": 0.0012037902197334915,
      "epoch": 0.06645316720041533,
      "grad_norm": 0.13196122646331787,
      "learning_rate": 2e-07,
      "loss": 0.0017,
      "step": 712
    },
    {
      "clip_ratio/high_max": 0.0014731160190422088,
      "clip_ratio/high_mean": 0.0006288127842708491,
      "clip_ratio/low_mean": 0.0006960149603401078,
      "clip_ratio/low_min": 7.496079433622072e-05,
      "clip_ratio/region_mean": 0.0013248277464299463,
      "epoch": 0.06654650030041591,
      "grad_norm": 0.16227781772613525,
      "learning_rate": 2e-07,
      "loss": 0.0752,
      "step": 713
    },
    {
      "clip_ratio/high_max": 0.001821120207750937,
      "clip_ratio/high_mean": 0.0007104326596163446,
      "clip_ratio/low_mean": 0.0005290385552143562,
      "clip_ratio/low_min": 4.164237361692358e-05,
      "clip_ratio/region_mean": 0.0012394712393870577,
      "epoch": 0.0666398334004165,
      "grad_norm": 0.11802949011325836,
      "learning_rate": 2e-07,
      "loss": 0.0259,
      "step": 714
    },
    {
      "clip_ratio/high_max": 0.0016361718080588616,
      "clip_ratio/high_mean": 0.0006976287877478171,
      "clip_ratio/low_mean": 0.0005578648951996001,
      "clip_ratio/low_min": 6.286701591307065e-05,
      "clip_ratio/region_mean": 0.0012554936984088272,
      "epoch": 0.06673316650041708,
      "grad_norm": 0.12575367093086243,
      "learning_rate": 2e-07,
      "loss": 0.01,
      "step": 715
    },
    {
      "clip_ratio/high_max": 0.0015306192872230895,
      "clip_ratio/high_mean": 0.0006829078611190198,
      "clip_ratio/low_mean": 0.0005652276231558062,
      "clip_ratio/low_min": 2.6371308194939047e-05,
      "clip_ratio/region_mean": 0.0012481355042837095,
      "epoch": 0.06682649960041767,
      "grad_norm": 0.12255307286977768,
      "learning_rate": 2e-07,
      "loss": 0.0426,
      "step": 716
    },
    {
      "clip_ratio/high_max": 0.0017676871648291126,
      "clip_ratio/high_mean": 0.0006988621153141139,
      "clip_ratio/low_mean": 0.000594995113715413,
      "clip_ratio/low_min": 3.6264593290979974e-05,
      "clip_ratio/region_mean": 0.0012938572035636753,
      "epoch": 0.06691983270041825,
      "grad_norm": 0.13913819193840027,
      "learning_rate": 2e-07,
      "loss": 0.011,
      "step": 717
    },
    {
      "clip_ratio/high_max": 0.0016347115742973983,
      "clip_ratio/high_mean": 0.0006760210362699581,
      "clip_ratio/low_mean": 0.0004997788200853392,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0011757998508983292,
      "epoch": 0.06701316580041883,
      "grad_norm": 0.1278361827135086,
      "learning_rate": 2e-07,
      "loss": -0.006,
      "step": 718
    },
    {
      "clip_ratio/high_max": 0.0019817051470454317,
      "clip_ratio/high_mean": 0.0008013378246687353,
      "clip_ratio/low_mean": 0.0006236618937691674,
      "clip_ratio/low_min": 8.782880286162253e-05,
      "clip_ratio/region_mean": 0.001424999711161945,
      "epoch": 0.06710649890041942,
      "grad_norm": 0.1471550017595291,
      "learning_rate": 2e-07,
      "loss": 0.0135,
      "step": 719
    },
    {
      "clip_ratio/high_max": 0.0017789040539355483,
      "clip_ratio/high_mean": 0.0006382274532370502,
      "clip_ratio/low_mean": 0.000589313547607162,
      "clip_ratio/low_min": 2.098758523061406e-05,
      "clip_ratio/region_mean": 0.0012275410153961275,
      "epoch": 0.06719983200042,
      "grad_norm": 0.13642792403697968,
      "learning_rate": 2e-07,
      "loss": 0.0552,
      "step": 720
    },
    {
      "clip_ratio/high_max": 0.002038842605543323,
      "clip_ratio/high_mean": 0.0008691268412803765,
      "clip_ratio/low_mean": 0.0006305976894509513,
      "clip_ratio/low_min": 6.795874242015998e-05,
      "clip_ratio/region_mean": 0.0014997245161794126,
      "epoch": 0.06729316510042058,
      "grad_norm": 0.14861653745174408,
      "learning_rate": 2e-07,
      "loss": 0.0272,
      "step": 721
    },
    {
      "clip_ratio/high_max": 0.0020597925831680186,
      "clip_ratio/high_mean": 0.0008074911420408171,
      "clip_ratio/low_mean": 0.0005606143495242577,
      "clip_ratio/low_min": 8.225849342125002e-06,
      "clip_ratio/region_mean": 0.001368105451547308,
      "epoch": 0.06738649820042117,
      "grad_norm": 0.12199034541845322,
      "learning_rate": 2e-07,
      "loss": -0.0107,
      "step": 722
    },
    {
      "clip_ratio/high_max": 0.0017646953674557153,
      "clip_ratio/high_mean": 0.000686372845848382,
      "clip_ratio/low_mean": 0.0005738396848755656,
      "clip_ratio/low_min": 1.3830493116984144e-05,
      "clip_ratio/region_mean": 0.0012602125243574847,
      "epoch": 0.06747983130042175,
      "grad_norm": 0.13809935748577118,
      "learning_rate": 2e-07,
      "loss": 0.032,
      "step": 723
    },
    {
      "clip_ratio/high_max": 0.002041535968601238,
      "clip_ratio/high_mean": 0.0008074734596448252,
      "clip_ratio/low_mean": 0.0005946322085037536,
      "clip_ratio/low_min": 2.385093739576405e-05,
      "clip_ratio/region_mean": 0.0014021056776982732,
      "epoch": 0.06757316440042234,
      "grad_norm": 0.13424062728881836,
      "learning_rate": 2e-07,
      "loss": 0.002,
      "step": 724
    },
    {
      "clip_ratio/high_max": 0.0016238933603744954,
      "clip_ratio/high_mean": 0.0006851082889625104,
      "clip_ratio/low_mean": 0.0006468245919677429,
      "clip_ratio/low_min": 8.485943908453919e-05,
      "clip_ratio/region_mean": 0.0013319329264049884,
      "epoch": 0.06766649750042292,
      "grad_norm": 0.12736429274082184,
      "learning_rate": 2e-07,
      "loss": 0.0593,
      "step": 725
    },
    {
      "clip_ratio/high_max": 0.001720933745673392,
      "clip_ratio/high_mean": 0.0006456746932599344,
      "clip_ratio/low_mean": 0.0006141784378996817,
      "clip_ratio/low_min": 6.234898955881363e-05,
      "clip_ratio/region_mean": 0.0012598531138792168,
      "epoch": 0.0677598306004235,
      "grad_norm": 0.13584652543067932,
      "learning_rate": 2e-07,
      "loss": 0.0867,
      "step": 726
    },
    {
      "clip_ratio/high_max": 0.0020131024430156685,
      "clip_ratio/high_mean": 0.0008426957574556582,
      "clip_ratio/low_mean": 0.0005707887848984683,
      "clip_ratio/low_min": 4.9046240746974945e-05,
      "clip_ratio/region_mean": 0.0014134845769149251,
      "epoch": 0.06785316370042409,
      "grad_norm": 0.13958778977394104,
      "learning_rate": 2e-07,
      "loss": -0.0093,
      "step": 727
    },
    {
      "clip_ratio/high_max": 0.0016818938711367082,
      "clip_ratio/high_mean": 0.000640437532638316,
      "clip_ratio/low_mean": 0.000573838988202624,
      "clip_ratio/low_min": 5.9265707477607066e-05,
      "clip_ratio/region_mean": 0.0012142765044700354,
      "epoch": 0.06794649680042467,
      "grad_norm": 0.12061227113008499,
      "learning_rate": 2e-07,
      "loss": 0.015,
      "step": 728
    },
    {
      "clip_ratio/high_max": 0.0019786486045632046,
      "clip_ratio/high_mean": 0.0007174556922109332,
      "clip_ratio/low_mean": 0.0006398026271199342,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013572583229688462,
      "epoch": 0.06803982990042524,
      "grad_norm": 0.1313309520483017,
      "learning_rate": 2e-07,
      "loss": 0.0345,
      "step": 729
    },
    {
      "clip_ratio/high_max": 0.0019008902963832952,
      "clip_ratio/high_mean": 0.000787861865319428,
      "clip_ratio/low_mean": 0.000585956115173758,
      "clip_ratio/low_min": 1.3196790860092733e-05,
      "clip_ratio/region_mean": 0.0013738179841311648,
      "epoch": 0.06813316300042584,
      "grad_norm": 0.14793342351913452,
      "learning_rate": 2e-07,
      "loss": -0.0028,
      "step": 730
    },
    {
      "clip_ratio/high_max": 0.00202564479332068,
      "clip_ratio/high_mean": 0.0007611770670337137,
      "clip_ratio/low_mean": 0.0006485042886197334,
      "clip_ratio/low_min": 5.51178136447561e-05,
      "clip_ratio/region_mean": 0.0014096813465585,
      "epoch": 0.06822649610042641,
      "grad_norm": 0.12728330492973328,
      "learning_rate": 2e-07,
      "loss": 0.0236,
      "step": 731
    },
    {
      "clip_ratio/high_max": 0.0019234822502767202,
      "clip_ratio/high_mean": 0.0008350364496436669,
      "clip_ratio/low_mean": 0.0005902909360884223,
      "clip_ratio/low_min": 8.934953257266898e-06,
      "clip_ratio/region_mean": 0.001425327380275121,
      "epoch": 0.06831982920042699,
      "grad_norm": 0.1414061337709427,
      "learning_rate": 2e-07,
      "loss": -0.0035,
      "step": 732
    },
    {
      "clip_ratio/high_max": 0.0014034231171535794,
      "clip_ratio/high_mean": 0.0006174422105686972,
      "clip_ratio/low_mean": 0.0007025871491350699,
      "clip_ratio/low_min": 4.7604851715732366e-05,
      "clip_ratio/region_mean": 0.0013200293942645658,
      "epoch": 0.06841316230042759,
      "grad_norm": 0.13389013707637787,
      "learning_rate": 2e-07,
      "loss": 0.0664,
      "step": 733
    },
    {
      "clip_ratio/high_max": 0.0015746317149023525,
      "clip_ratio/high_mean": 0.0006251774302654667,
      "clip_ratio/low_mean": 0.0006905611389811384,
      "clip_ratio/low_min": 6.208332160895225e-05,
      "clip_ratio/region_mean": 0.0013157385546946898,
      "epoch": 0.06850649540042816,
      "grad_norm": 0.14052222669124603,
      "learning_rate": 2e-07,
      "loss": 0.0632,
      "step": 734
    },
    {
      "clip_ratio/high_max": 0.0017099685937864706,
      "clip_ratio/high_mean": 0.0006722791913489345,
      "clip_ratio/low_mean": 0.0006368850608851062,
      "clip_ratio/low_min": 7.924424699012889e-05,
      "clip_ratio/region_mean": 0.001309164239501115,
      "epoch": 0.06859982850042876,
      "grad_norm": 0.12538683414459229,
      "learning_rate": 2e-07,
      "loss": 0.0256,
      "step": 735
    },
    {
      "clip_ratio/high_max": 0.0017369605229760054,
      "clip_ratio/high_mean": 0.0007407784160022857,
      "clip_ratio/low_mean": 0.0005957555713393958,
      "clip_ratio/low_min": 1.813960261642933e-05,
      "clip_ratio/region_mean": 0.001336533976427745,
      "epoch": 0.06869316160042933,
      "grad_norm": 0.1312275528907776,
      "learning_rate": 2e-07,
      "loss": 0.0153,
      "step": 736
    },
    {
      "clip_ratio/high_max": 0.0017714449350023642,
      "clip_ratio/high_mean": 0.000799140289927891,
      "clip_ratio/low_mean": 0.0006108619681981509,
      "clip_ratio/low_min": 2.4706812837393954e-05,
      "clip_ratio/region_mean": 0.0014100022617640207,
      "epoch": 0.06878649470042991,
      "grad_norm": 0.1298689991235733,
      "learning_rate": 2e-07,
      "loss": 0.0091,
      "step": 737
    },
    {
      "clip_ratio/high_max": 0.0018455002209520899,
      "clip_ratio/high_mean": 0.0008113680378301069,
      "clip_ratio/low_mean": 0.0006094640157243703,
      "clip_ratio/low_min": 4.715655268228147e-05,
      "clip_ratio/region_mean": 0.0014208320862962864,
      "epoch": 0.0688798278004305,
      "grad_norm": 0.14072157442569733,
      "learning_rate": 2e-07,
      "loss": 0.0135,
      "step": 738
    },
    {
      "clip_ratio/high_max": 0.0017453860637033358,
      "clip_ratio/high_mean": 0.0006908440591359977,
      "clip_ratio/low_mean": 0.0006311995175565244,
      "clip_ratio/low_min": 3.4417424103594385e-05,
      "clip_ratio/region_mean": 0.001322043601248879,
      "epoch": 0.06897316090043108,
      "grad_norm": 0.13882027566432953,
      "learning_rate": 2e-07,
      "loss": 0.0228,
      "step": 739
    },
    {
      "clip_ratio/high_max": 0.0016288513934341609,
      "clip_ratio/high_mean": 0.0006995230523898499,
      "clip_ratio/low_mean": 0.0005564735402003862,
      "clip_ratio/low_min": 3.338638362038182e-05,
      "clip_ratio/region_mean": 0.0012559966198750772,
      "epoch": 0.06906649400043166,
      "grad_norm": 0.13416001200675964,
      "learning_rate": 2e-07,
      "loss": -0.0091,
      "step": 740
    },
    {
      "clip_ratio/high_max": 0.0018814712093444541,
      "clip_ratio/high_mean": 0.0007645155583304586,
      "clip_ratio/low_mean": 0.0005276770343698445,
      "clip_ratio/low_min": 2.2476402591564693e-05,
      "clip_ratio/region_mean": 0.0012921925845148508,
      "epoch": 0.06915982710043225,
      "grad_norm": 0.13226832449436188,
      "learning_rate": 2e-07,
      "loss": -0.0145,
      "step": 741
    },
    {
      "clip_ratio/high_max": 0.00182180222691386,
      "clip_ratio/high_mean": 0.0007294012557395035,
      "clip_ratio/low_mean": 0.0005697359756595688,
      "clip_ratio/low_min": 2.4528826543246396e-05,
      "clip_ratio/region_mean": 0.0012991372532269452,
      "epoch": 0.06925316020043283,
      "grad_norm": 0.12990514934062958,
      "learning_rate": 2e-07,
      "loss": 0.0266,
      "step": 742
    },
    {
      "clip_ratio/high_max": 0.0017791721893445356,
      "clip_ratio/high_mean": 0.0006149688942969078,
      "clip_ratio/low_mean": 0.0005969194844510639,
      "clip_ratio/low_min": 7.071129130054032e-05,
      "clip_ratio/region_mean": 0.0012118883787479717,
      "epoch": 0.06934649330043341,
      "grad_norm": 0.14736603200435638,
      "learning_rate": 2e-07,
      "loss": 0.0594,
      "step": 743
    },
    {
      "clip_ratio/high_max": 0.0019202605362806935,
      "clip_ratio/high_mean": 0.0007219611052278196,
      "clip_ratio/low_mean": 0.0005373491130740149,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012593102328537498,
      "epoch": 0.069439826400434,
      "grad_norm": 0.13976521790027618,
      "learning_rate": 2e-07,
      "loss": 0.0286,
      "step": 744
    },
    {
      "clip_ratio/high_max": 0.0022700840345351025,
      "clip_ratio/high_mean": 0.0009299338234995957,
      "clip_ratio/low_mean": 0.0005541553782677511,
      "clip_ratio/low_min": 1.394466744386591e-05,
      "clip_ratio/region_mean": 0.0014840891817584634,
      "epoch": 0.06953315950043458,
      "grad_norm": 0.1326330453157425,
      "learning_rate": 2e-07,
      "loss": 0.012,
      "step": 745
    },
    {
      "clip_ratio/high_max": 0.0019038873942918144,
      "clip_ratio/high_mean": 0.0007835072738089366,
      "clip_ratio/low_mean": 0.0005991257921778015,
      "clip_ratio/low_min": 3.882667351717828e-05,
      "clip_ratio/region_mean": 0.0013826330578012858,
      "epoch": 0.06962649260043517,
      "grad_norm": 0.13354718685150146,
      "learning_rate": 2e-07,
      "loss": 0.0364,
      "step": 746
    },
    {
      "clip_ratio/high_max": 0.00188977029392845,
      "clip_ratio/high_mean": 0.0007578237382404041,
      "clip_ratio/low_mean": 0.0006561072568729287,
      "clip_ratio/low_min": 6.512451818707632e-06,
      "clip_ratio/region_mean": 0.001413931000570301,
      "epoch": 0.06971982570043575,
      "grad_norm": 0.14631761610507965,
      "learning_rate": 2e-07,
      "loss": 0.0255,
      "step": 747
    },
    {
      "clip_ratio/high_max": 0.0020120538902119733,
      "clip_ratio/high_mean": 0.0007912606961326674,
      "clip_ratio/low_mean": 0.0006326311649900163,
      "clip_ratio/low_min": 2.893444434448611e-05,
      "clip_ratio/region_mean": 0.001423891844751779,
      "epoch": 0.06981315880043633,
      "grad_norm": 0.12877687811851501,
      "learning_rate": 2e-07,
      "loss": 0.0365,
      "step": 748
    },
    {
      "clip_ratio/high_max": 0.0020629137798096053,
      "clip_ratio/high_mean": 0.000723976931112702,
      "clip_ratio/low_mean": 0.0005688386463589268,
      "clip_ratio/low_min": 1.9869094103341922e-05,
      "clip_ratio/region_mean": 0.0012928155774716288,
      "epoch": 0.06990649190043692,
      "grad_norm": 0.15203729271888733,
      "learning_rate": 2e-07,
      "loss": -0.029,
      "step": 749
    },
    {
      "clip_ratio/high_max": 0.0015529661468463019,
      "clip_ratio/high_mean": 0.0005806366698379861,
      "clip_ratio/low_mean": 0.0006421755033443333,
      "clip_ratio/low_min": 3.512858438625699e-05,
      "clip_ratio/region_mean": 0.0012228121631778777,
      "epoch": 0.0699998250004375,
      "grad_norm": 0.12965691089630127,
      "learning_rate": 2e-07,
      "loss": 0.0547,
      "step": 750
    },
    {
      "clip_ratio/high_max": 0.002022711021709256,
      "clip_ratio/high_mean": 0.0008650339932501083,
      "clip_ratio/low_mean": 0.000626831464614952,
      "clip_ratio/low_min": 5.443232021207223e-05,
      "clip_ratio/region_mean": 0.0014918654960638378,
      "epoch": 0.07009315810043808,
      "grad_norm": 0.15232199430465698,
      "learning_rate": 2e-07,
      "loss": 0.026,
      "step": 751
    },
    {
      "clip_ratio/high_max": 0.0019984413738711737,
      "clip_ratio/high_mean": 0.0008110612689051777,
      "clip_ratio/low_mean": 0.0006659698628936894,
      "clip_ratio/low_min": 2.1532819118874613e-05,
      "clip_ratio/region_mean": 0.0014770311427128036,
      "epoch": 0.07018649120043867,
      "grad_norm": 0.14948713779449463,
      "learning_rate": 2e-07,
      "loss": -0.0221,
      "step": 752
    },
    {
      "clip_ratio/high_max": 0.0017223160830326378,
      "clip_ratio/high_mean": 0.0006585423780052224,
      "clip_ratio/low_mean": 0.0006180987074912991,
      "clip_ratio/low_min": 6.511421997856814e-05,
      "clip_ratio/region_mean": 0.0012766411091433838,
      "epoch": 0.07027982430043925,
      "grad_norm": 0.12757332623004913,
      "learning_rate": 2e-07,
      "loss": 0.0249,
      "step": 753
    },
    {
      "clip_ratio/high_max": 0.002022508248046506,
      "clip_ratio/high_mean": 0.0008284197156172013,
      "clip_ratio/low_mean": 0.0006186634236655664,
      "clip_ratio/low_min": 3.2501298846909776e-05,
      "clip_ratio/region_mean": 0.0014470831374637783,
      "epoch": 0.07037315740043983,
      "grad_norm": 10.3920259475708,
      "learning_rate": 2e-07,
      "loss": 0.0343,
      "step": 754
    },
    {
      "clip_ratio/high_max": 0.0015992866137821693,
      "clip_ratio/high_mean": 0.0007028676827758318,
      "clip_ratio/low_mean": 0.0006047942206350854,
      "clip_ratio/low_min": 2.5946865207515657e-05,
      "clip_ratio/region_mean": 0.001307661907048896,
      "epoch": 0.07046649050044042,
      "grad_norm": 0.14464056491851807,
      "learning_rate": 2e-07,
      "loss": 0.0255,
      "step": 755
    },
    {
      "clip_ratio/high_max": 0.002156022634153487,
      "clip_ratio/high_mean": 0.0008191678261937341,
      "clip_ratio/low_mean": 0.0006043455796316266,
      "clip_ratio/low_min": 1.908193053168361e-05,
      "clip_ratio/region_mean": 0.0014235134003683925,
      "epoch": 0.070559823600441,
      "grad_norm": 0.13640077412128448,
      "learning_rate": 2e-07,
      "loss": -0.0086,
      "step": 756
    },
    {
      "clip_ratio/high_max": 0.0016338919376721606,
      "clip_ratio/high_mean": 0.0007774683890602319,
      "clip_ratio/low_mean": 0.0007251419847307261,
      "clip_ratio/low_min": 3.3545678888913244e-05,
      "clip_ratio/region_mean": 0.0015026103537820745,
      "epoch": 0.07065315670044159,
      "grad_norm": 0.14856377243995667,
      "learning_rate": 2e-07,
      "loss": 0.0562,
      "step": 757
    },
    {
      "clip_ratio/high_max": 0.0019688043394126,
      "clip_ratio/high_mean": 0.0008163420116034104,
      "clip_ratio/low_mean": 0.0005960196012892993,
      "clip_ratio/low_min": 1.1966302736254875e-05,
      "clip_ratio/region_mean": 0.0014123615910648368,
      "epoch": 0.07074648980044217,
      "grad_norm": 0.12315496802330017,
      "learning_rate": 2e-07,
      "loss": 0.0196,
      "step": 758
    },
    {
      "clip_ratio/high_max": 0.0016924047267821152,
      "clip_ratio/high_mean": 0.0006796423795094597,
      "clip_ratio/low_mean": 0.0006029579089954495,
      "clip_ratio/low_min": 1.5539212199655594e-05,
      "clip_ratio/region_mean": 0.0012826003003283404,
      "epoch": 0.07083982290044274,
      "grad_norm": 0.13579337298870087,
      "learning_rate": 2e-07,
      "loss": 0.0471,
      "step": 759
    },
    {
      "clip_ratio/high_max": 0.0017405014441465028,
      "clip_ratio/high_mean": 0.0007377229321718914,
      "clip_ratio/low_mean": 0.0007337011684285244,
      "clip_ratio/low_min": 1.540927041787654e-05,
      "clip_ratio/region_mean": 0.001471424096962437,
      "epoch": 0.07093315600044334,
      "grad_norm": 0.15686245262622833,
      "learning_rate": 2e-07,
      "loss": 0.0408,
      "step": 760
    },
    {
      "clip_ratio/high_max": 0.0016048759425757453,
      "clip_ratio/high_mean": 0.0006105501306592487,
      "clip_ratio/low_mean": 0.0006372321549861226,
      "clip_ratio/low_min": 9.380648134538205e-05,
      "clip_ratio/region_mean": 0.0012477823001972865,
      "epoch": 0.07102648910044392,
      "grad_norm": 0.12125812470912933,
      "learning_rate": 2e-07,
      "loss": 0.0567,
      "step": 761
    },
    {
      "clip_ratio/high_max": 0.001938916746439645,
      "clip_ratio/high_mean": 0.0007488416513297125,
      "clip_ratio/low_mean": 0.0006219257575139636,
      "clip_ratio/low_min": 2.036825753748417e-05,
      "clip_ratio/region_mean": 0.001370767451589927,
      "epoch": 0.0711198222004445,
      "grad_norm": 0.14363320171833038,
      "learning_rate": 2e-07,
      "loss": 0.0269,
      "step": 762
    },
    {
      "clip_ratio/high_max": 0.0020458885628613643,
      "clip_ratio/high_mean": 0.0008150991016009357,
      "clip_ratio/low_mean": 0.000612141808232991,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014272409171098843,
      "epoch": 0.07121315530044509,
      "grad_norm": 0.15316857397556305,
      "learning_rate": 2e-07,
      "loss": -0.0045,
      "step": 763
    },
    {
      "clip_ratio/high_max": 0.0016988413808576297,
      "clip_ratio/high_mean": 0.0007218188902697875,
      "clip_ratio/low_mean": 0.0006334005747703486,
      "clip_ratio/low_min": 3.572069272195222e-05,
      "clip_ratio/region_mean": 0.0013552194541261997,
      "epoch": 0.07130648840044566,
      "grad_norm": 0.1329914629459381,
      "learning_rate": 2e-07,
      "loss": 0.0404,
      "step": 764
    },
    {
      "clip_ratio/high_max": 0.001977858726604609,
      "clip_ratio/high_mean": 0.0008104218886728631,
      "clip_ratio/low_mean": 0.0007157653344620485,
      "clip_ratio/low_min": 7.466999159078114e-05,
      "clip_ratio/region_mean": 0.0015261872104019858,
      "epoch": 0.07139982150044624,
      "grad_norm": 0.14950889348983765,
      "learning_rate": 2e-07,
      "loss": 0.0242,
      "step": 765
    },
    {
      "clip_ratio/high_max": 0.0019842466499540024,
      "clip_ratio/high_mean": 0.0008427213015238522,
      "clip_ratio/low_mean": 0.0006352626105581294,
      "clip_ratio/low_min": 8.567565873818239e-05,
      "clip_ratio/region_mean": 0.0014779839511902537,
      "epoch": 0.07149315460044683,
      "grad_norm": 0.13594745099544525,
      "learning_rate": 2e-07,
      "loss": 0.0006,
      "step": 766
    },
    {
      "clip_ratio/high_max": 0.0016343000897904858,
      "clip_ratio/high_mean": 0.0007064003239065642,
      "clip_ratio/low_mean": 0.0006763603469153168,
      "clip_ratio/low_min": 4.872680074186064e-05,
      "clip_ratio/region_mean": 0.0013827606671839021,
      "epoch": 0.07158648770044741,
      "grad_norm": 0.154115691781044,
      "learning_rate": 2e-07,
      "loss": 0.0322,
      "step": 767
    },
    {
      "clip_ratio/high_max": 0.0015900861526461085,
      "clip_ratio/high_mean": 0.0006840725200163433,
      "clip_ratio/low_mean": 0.0006002959125908092,
      "clip_ratio/low_min": 2.858479001588421e-05,
      "clip_ratio/region_mean": 0.0012843684744439088,
      "epoch": 0.071679820800448,
      "grad_norm": 0.14167453348636627,
      "learning_rate": 2e-07,
      "loss": -0.0003,
      "step": 768
    },
    {
      "clip_ratio/high_max": 0.0014781792742724065,
      "clip_ratio/high_mean": 0.0006099792053646524,
      "clip_ratio/low_mean": 0.0005983139417367056,
      "clip_ratio/low_min": 0.00010939509866148,
      "clip_ratio/region_mean": 0.001208293135277927,
      "completions/clipped_ratio": 0.016095842633928603,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4096.0,
      "completions/mean_length": 655.1669921875,
      "completions/mean_terminated_length": 598.8778076171875,
      "completions/min_length": 83.0,
      "completions/min_terminated_length": 83.0,
      "epoch": 0.07177315390044858,
      "grad_norm": 0.26202720403671265,
      "learning_rate": 2e-07,
      "loss": 0.0504,
      "num_tokens": 589071875.0,
      "reward": 0.5863386392593384,
      "reward_std": 0.18439003825187683,
      "rewards/simpleverify_reward/mean": 0.5863385796546936,
      "rewards/simpleverify_reward/std": 0.4924914240837097,
      "step": 769
    },
    {
      "clip_ratio/high_max": 0.001833040838391753,
      "clip_ratio/high_mean": 0.0006734365324518876,
      "clip_ratio/low_mean": 0.0005811282735521672,
      "clip_ratio/low_min": 3.7520137993851677e-05,
      "clip_ratio/region_mean": 0.0012545647950901184,
      "epoch": 0.07186648700044916,
      "grad_norm": 0.1269025355577469,
      "learning_rate": 2e-07,
      "loss": 0.0286,
      "step": 770
    },
    {
      "clip_ratio/high_max": 0.00182122028854792,
      "clip_ratio/high_mean": 0.0006383624313457403,
      "clip_ratio/low_mean": 0.000556662345843506,
      "clip_ratio/low_min": 1.9364750187378377e-05,
      "clip_ratio/region_mean": 0.001195024793560151,
      "epoch": 0.07195982010044975,
      "grad_norm": 0.11978539079427719,
      "learning_rate": 2e-07,
      "loss": 0.0575,
      "step": 771
    },
    {
      "clip_ratio/high_max": 0.001550647026306251,
      "clip_ratio/high_mean": 0.0006025546626915457,
      "clip_ratio/low_mean": 0.0006839850393589586,
      "clip_ratio/low_min": 6.36908062006114e-05,
      "clip_ratio/region_mean": 0.0012865396711276844,
      "epoch": 0.07205315320045033,
      "grad_norm": 0.1369551420211792,
      "learning_rate": 2e-07,
      "loss": 0.0525,
      "step": 772
    },
    {
      "clip_ratio/high_max": 0.0016724560773582198,
      "clip_ratio/high_mean": 0.0006427054249797948,
      "clip_ratio/low_mean": 0.000574533078179229,
      "clip_ratio/low_min": 2.587933704489842e-05,
      "clip_ratio/region_mean": 0.0012172385067970026,
      "epoch": 0.07214648630045091,
      "grad_norm": 0.12382771074771881,
      "learning_rate": 2e-07,
      "loss": 0.0534,
      "step": 773
    },
    {
      "clip_ratio/high_max": 0.0014508609019685537,
      "clip_ratio/high_mean": 0.0005469740954140434,
      "clip_ratio/low_mean": 0.000522126578289317,
      "clip_ratio/low_min": 1.5952016838127747e-05,
      "clip_ratio/region_mean": 0.0010691006846172968,
      "epoch": 0.0722398194004515,
      "grad_norm": 0.127375990152359,
      "learning_rate": 2e-07,
      "loss": 0.0347,
      "step": 774
    },
    {
      "clip_ratio/high_max": 0.0018920573565992527,
      "clip_ratio/high_mean": 0.000626171366093331,
      "clip_ratio/low_mean": 0.000507831189679564,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0011340025703248102,
      "epoch": 0.07233315250045208,
      "grad_norm": 0.14250198006629944,
      "learning_rate": 2e-07,
      "loss": 0.028,
      "step": 775
    },
    {
      "clip_ratio/high_max": 0.0019099104247288778,
      "clip_ratio/high_mean": 0.0007119679230527254,
      "clip_ratio/low_mean": 0.0005120594614709262,
      "clip_ratio/low_min": 1.3845812645740807e-05,
      "clip_ratio/region_mean": 0.0012240273717907257,
      "epoch": 0.07242648560045266,
      "grad_norm": 0.12332292646169662,
      "learning_rate": 2e-07,
      "loss": 0.0167,
      "step": 776
    },
    {
      "clip_ratio/high_max": 0.0013264350236568134,
      "clip_ratio/high_mean": 0.0006094816935728886,
      "clip_ratio/low_mean": 0.0005187598162592622,
      "clip_ratio/low_min": 7.307377472898224e-06,
      "clip_ratio/region_mean": 0.001128241518017603,
      "epoch": 0.07251981870045325,
      "grad_norm": 0.1331176906824112,
      "learning_rate": 2e-07,
      "loss": 0.0383,
      "step": 777
    },
    {
      "clip_ratio/high_max": 0.0019108845372102223,
      "clip_ratio/high_mean": 0.0007144267619878519,
      "clip_ratio/low_mean": 0.0005685477426595753,
      "clip_ratio/low_min": 4.417019135871669e-05,
      "clip_ratio/region_mean": 0.0012829745028284378,
      "epoch": 0.07261315180045383,
      "grad_norm": 0.12833134829998016,
      "learning_rate": 2e-07,
      "loss": 0.0012,
      "step": 778
    },
    {
      "clip_ratio/high_max": 0.0017454239714425057,
      "clip_ratio/high_mean": 0.0006432412901631324,
      "clip_ratio/low_mean": 0.0006263824925554218,
      "clip_ratio/low_min": 3.6387573345564306e-05,
      "clip_ratio/region_mean": 0.0012696237827185541,
      "epoch": 0.07270648490045442,
      "grad_norm": 0.12894085049629211,
      "learning_rate": 2e-07,
      "loss": 0.0122,
      "step": 779
    },
    {
      "clip_ratio/high_max": 0.0016816244096844457,
      "clip_ratio/high_mean": 0.0006803845089962124,
      "clip_ratio/low_mean": 0.0006154627244541189,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012958472834725399,
      "epoch": 0.072799818000455,
      "grad_norm": 0.13945753872394562,
      "learning_rate": 2e-07,
      "loss": 0.0019,
      "step": 780
    },
    {
      "clip_ratio/high_max": 0.00214164052522392,
      "clip_ratio/high_mean": 0.000725825233530486,
      "clip_ratio/low_mean": 0.0005934840664849617,
      "clip_ratio/low_min": 5.610407379208482e-05,
      "clip_ratio/region_mean": 0.0013193092854635324,
      "epoch": 0.07289315110045558,
      "grad_norm": 0.14117878675460815,
      "learning_rate": 2e-07,
      "loss": 0.0464,
      "step": 781
    },
    {
      "clip_ratio/high_max": 0.001704036974842893,
      "clip_ratio/high_mean": 0.0006747729139533476,
      "clip_ratio/low_mean": 0.0005418484035999427,
      "clip_ratio/low_min": 3.411008037801366e-05,
      "clip_ratio/region_mean": 0.0012166213418822736,
      "epoch": 0.07298648420045617,
      "grad_norm": 0.14113466441631317,
      "learning_rate": 2e-07,
      "loss": 0.0151,
      "step": 782
    },
    {
      "clip_ratio/high_max": 0.002116542586009018,
      "clip_ratio/high_mean": 0.0007058271839923691,
      "clip_ratio/low_mean": 0.0005910425716137979,
      "clip_ratio/low_min": 4.877468018094078e-05,
      "clip_ratio/region_mean": 0.0012968697810720187,
      "epoch": 0.07307981730045675,
      "grad_norm": 0.1459830105304718,
      "learning_rate": 2e-07,
      "loss": 0.0238,
      "step": 783
    },
    {
      "clip_ratio/high_max": 0.0014133827571640722,
      "clip_ratio/high_mean": 0.0006136717420304194,
      "clip_ratio/low_mean": 0.0005624677369269193,
      "clip_ratio/low_min": 4.925401572108967e-05,
      "clip_ratio/region_mean": 0.0011761394889617804,
      "epoch": 0.07317315040045733,
      "grad_norm": 0.12120173871517181,
      "learning_rate": 2e-07,
      "loss": 0.0521,
      "step": 784
    },
    {
      "clip_ratio/high_max": 0.0018333422958676238,
      "clip_ratio/high_mean": 0.0007060539956000866,
      "clip_ratio/low_mean": 0.0004661673738155514,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0011722213748726062,
      "epoch": 0.07326648350045792,
      "grad_norm": 0.12322816997766495,
      "learning_rate": 2e-07,
      "loss": 0.0133,
      "step": 785
    },
    {
      "clip_ratio/high_max": 0.0017948177992366254,
      "clip_ratio/high_mean": 0.0007219899707706645,
      "clip_ratio/low_mean": 0.0005412137170424103,
      "clip_ratio/low_min": 1.2440286809578538e-05,
      "clip_ratio/region_mean": 0.0012632036850845907,
      "epoch": 0.0733598166004585,
      "grad_norm": 0.13310644030570984,
      "learning_rate": 2e-07,
      "loss": 0.0018,
      "step": 786
    },
    {
      "clip_ratio/high_max": 0.0015695174006395973,
      "clip_ratio/high_mean": 0.000673003023621277,
      "clip_ratio/low_mean": 0.0004890238133157254,
      "clip_ratio/low_min": 1.121881177823525e-05,
      "clip_ratio/region_mean": 0.0011620268087426666,
      "epoch": 0.07345314970045909,
      "grad_norm": 0.14041544497013092,
      "learning_rate": 2e-07,
      "loss": -0.0158,
      "step": 787
    },
    {
      "clip_ratio/high_max": 0.001891879248432815,
      "clip_ratio/high_mean": 0.00075017050767201,
      "clip_ratio/low_mean": 0.0005772367640020093,
      "clip_ratio/low_min": 3.1890142963675316e-05,
      "clip_ratio/region_mean": 0.001327407248027157,
      "epoch": 0.07354648280045967,
      "grad_norm": 0.12373622506856918,
      "learning_rate": 2e-07,
      "loss": -0.0021,
      "step": 788
    },
    {
      "clip_ratio/high_max": 0.0015318896639655577,
      "clip_ratio/high_mean": 0.0006084103624743875,
      "clip_ratio/low_mean": 0.000576900224587007,
      "clip_ratio/low_min": 2.884675814129878e-05,
      "clip_ratio/region_mean": 0.0011853106116177514,
      "epoch": 0.07363981590046025,
      "grad_norm": 0.13347403705120087,
      "learning_rate": 2e-07,
      "loss": 0.0136,
      "step": 789
    },
    {
      "clip_ratio/high_max": 0.0014818500094406772,
      "clip_ratio/high_mean": 0.0006361109790304909,
      "clip_ratio/low_mean": 0.0005940767323409091,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001230187677720096,
      "epoch": 0.07373314900046084,
      "grad_norm": 0.13543841242790222,
      "learning_rate": 2e-07,
      "loss": 0.0334,
      "step": 790
    },
    {
      "clip_ratio/high_max": 0.0016123496534419246,
      "clip_ratio/high_mean": 0.0006192747023305856,
      "clip_ratio/low_mean": 0.0005097080393170472,
      "clip_ratio/low_min": 1.60503332153894e-05,
      "clip_ratio/region_mean": 0.0011289827234577388,
      "epoch": 0.07382648210046142,
      "grad_norm": 0.13138028979301453,
      "learning_rate": 2e-07,
      "loss": 0.0016,
      "step": 791
    },
    {
      "clip_ratio/high_max": 0.0013765665898972657,
      "clip_ratio/high_mean": 0.0005335067362466361,
      "clip_ratio/low_mean": 0.0005916447280469583,
      "clip_ratio/low_min": 1.4912908227415755e-05,
      "clip_ratio/region_mean": 0.0011251514588366263,
      "epoch": 0.073919815200462,
      "grad_norm": 0.12243971973657608,
      "learning_rate": 2e-07,
      "loss": 0.0593,
      "step": 792
    },
    {
      "clip_ratio/high_max": 0.0020504188869381323,
      "clip_ratio/high_mean": 0.0007492648092011223,
      "clip_ratio/low_mean": 0.000585534574383928,
      "clip_ratio/low_min": 1.0848811143659987e-05,
      "clip_ratio/region_mean": 0.0013347993699426297,
      "epoch": 0.07401314830046259,
      "grad_norm": 0.13791204988956451,
      "learning_rate": 2e-07,
      "loss": 0.0106,
      "step": 793
    },
    {
      "clip_ratio/high_max": 0.001704961214272771,
      "clip_ratio/high_mean": 0.000613057600276079,
      "clip_ratio/low_mean": 0.0005092905284982407,
      "clip_ratio/low_min": 3.165330281262868e-05,
      "clip_ratio/region_mean": 0.0011223481196793728,
      "epoch": 0.07410648140046316,
      "grad_norm": 0.1350066214799881,
      "learning_rate": 2e-07,
      "loss": 0.0459,
      "step": 794
    },
    {
      "clip_ratio/high_max": 0.001634477433981374,
      "clip_ratio/high_mean": 0.0006938577207620256,
      "clip_ratio/low_mean": 0.0004946283625031356,
      "clip_ratio/low_min": 3.927860234398395e-05,
      "clip_ratio/region_mean": 0.0011884860905411188,
      "epoch": 0.07419981450046374,
      "grad_norm": 0.13871221244335175,
      "learning_rate": 2e-07,
      "loss": 0.0161,
      "step": 795
    },
    {
      "clip_ratio/high_max": 0.0015516856583417393,
      "clip_ratio/high_mean": 0.0005660045890181209,
      "clip_ratio/low_mean": 0.0006167932133394061,
      "clip_ratio/low_min": 3.514307172736153e-05,
      "clip_ratio/region_mean": 0.0011827978414657991,
      "epoch": 0.07429314760046433,
      "grad_norm": 0.14665979146957397,
      "learning_rate": 2e-07,
      "loss": 0.0708,
      "step": 796
    },
    {
      "clip_ratio/high_max": 0.0017520424480608199,
      "clip_ratio/high_mean": 0.0006769001111024409,
      "clip_ratio/low_mean": 0.0005800953513244167,
      "clip_ratio/low_min": 2.6594133487378713e-05,
      "clip_ratio/region_mean": 0.001256995466974331,
      "epoch": 0.07438648070046491,
      "grad_norm": 0.13437144458293915,
      "learning_rate": 2e-07,
      "loss": 0.0665,
      "step": 797
    },
    {
      "clip_ratio/high_max": 0.001794855787011329,
      "clip_ratio/high_mean": 0.0007487581333407434,
      "clip_ratio/low_mean": 0.0005620388692477718,
      "clip_ratio/low_min": 3.1401965316035785e-05,
      "clip_ratio/region_mean": 0.0013107969825796317,
      "epoch": 0.0744798138004655,
      "grad_norm": 0.13425087928771973,
      "learning_rate": 2e-07,
      "loss": -0.0077,
      "step": 798
    },
    {
      "clip_ratio/high_max": 0.001946188356669154,
      "clip_ratio/high_mean": 0.0007347673763433704,
      "clip_ratio/low_mean": 0.0005433606193037122,
      "clip_ratio/low_min": 4.901195143247605e-05,
      "clip_ratio/region_mean": 0.0012781279838236514,
      "epoch": 0.07457314690046608,
      "grad_norm": 0.13724960386753082,
      "learning_rate": 2e-07,
      "loss": 0.0125,
      "step": 799
    },
    {
      "clip_ratio/high_max": 0.0015965724996931385,
      "clip_ratio/high_mean": 0.0006302674692051369,
      "clip_ratio/low_mean": 0.0005463216002681293,
      "clip_ratio/low_min": 5.143058479006868e-05,
      "clip_ratio/region_mean": 0.001176589066744782,
      "epoch": 0.07466648000046666,
      "grad_norm": 0.11962824314832687,
      "learning_rate": 2e-07,
      "loss": 0.0504,
      "step": 800
    },
    {
      "clip_ratio/high_max": 0.0016645022114971653,
      "clip_ratio/high_mean": 0.0007076521997078089,
      "clip_ratio/low_mean": 0.0005040593468947918,
      "clip_ratio/low_min": 8.934953257266898e-06,
      "clip_ratio/region_mean": 0.0012117115511500742,
      "epoch": 0.07475981310046725,
      "grad_norm": 0.1560024917125702,
      "learning_rate": 2e-07,
      "loss": 0.0008,
      "step": 801
    },
    {
      "clip_ratio/high_max": 0.0018497305864002556,
      "clip_ratio/high_mean": 0.0007217662023322191,
      "clip_ratio/low_mean": 0.0005779963767054141,
      "clip_ratio/low_min": 2.8836620913352817e-05,
      "clip_ratio/region_mean": 0.001299762570852181,
      "epoch": 0.07485314620046783,
      "grad_norm": 0.1296125203371048,
      "learning_rate": 2e-07,
      "loss": 0.0353,
      "step": 802
    },
    {
      "clip_ratio/high_max": 0.001809755529393442,
      "clip_ratio/high_mean": 0.000774874904891476,
      "clip_ratio/low_mean": 0.00046711757022421807,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012419924642017577,
      "epoch": 0.07494647930046841,
      "grad_norm": 0.132086381316185,
      "learning_rate": 2e-07,
      "loss": -0.0093,
      "step": 803
    },
    {
      "clip_ratio/high_max": 0.0016314685854013078,
      "clip_ratio/high_mean": 0.0005580781798926182,
      "clip_ratio/low_mean": 0.0005056617710579303,
      "clip_ratio/low_min": 1.0420139915368054e-05,
      "clip_ratio/region_mean": 0.001063739946403075,
      "epoch": 0.075039812400469,
      "grad_norm": 0.11413397639989853,
      "learning_rate": 2e-07,
      "loss": 0.0254,
      "step": 804
    },
    {
      "clip_ratio/high_max": 0.0018310889063286595,
      "clip_ratio/high_mean": 0.000756471248678281,
      "clip_ratio/low_mean": 0.0005501477389771026,
      "clip_ratio/low_min": 1.0255989764118567e-05,
      "clip_ratio/region_mean": 0.0013066189567325637,
      "epoch": 0.07513314550046958,
      "grad_norm": 0.20393221080303192,
      "learning_rate": 2e-07,
      "loss": 0.0235,
      "step": 805
    },
    {
      "clip_ratio/high_max": 0.0017719959178066347,
      "clip_ratio/high_mean": 0.0007169086129579227,
      "clip_ratio/low_mean": 0.0005473223227454582,
      "clip_ratio/low_min": 7.12463261152152e-05,
      "clip_ratio/region_mean": 0.0012642309302464128,
      "epoch": 0.07522647860047016,
      "grad_norm": 0.1374519020318985,
      "learning_rate": 2e-07,
      "loss": 0.0248,
      "step": 806
    },
    {
      "clip_ratio/high_max": 0.0019289104820927605,
      "clip_ratio/high_mean": 0.0008027928815863561,
      "clip_ratio/low_mean": 0.0006491938584076706,
      "clip_ratio/low_min": 4.7994041779020336e-05,
      "clip_ratio/region_mean": 0.0014519867581839208,
      "epoch": 0.07531981170047075,
      "grad_norm": 0.14597781002521515,
      "learning_rate": 2e-07,
      "loss": 0.018,
      "step": 807
    },
    {
      "clip_ratio/high_max": 0.0015129840139707085,
      "clip_ratio/high_mean": 0.000685712479025824,
      "clip_ratio/low_mean": 0.0005088247417006642,
      "clip_ratio/low_min": 1.3300702448759694e-05,
      "clip_ratio/region_mean": 0.0011945371952606365,
      "epoch": 0.07541314480047133,
      "grad_norm": 0.14136047661304474,
      "learning_rate": 2e-07,
      "loss": -0.0001,
      "step": 808
    },
    {
      "clip_ratio/high_max": 0.0018651897044037469,
      "clip_ratio/high_mean": 0.0007652069580217358,
      "clip_ratio/low_mean": 0.0005746390761487419,
      "clip_ratio/low_min": 2.3448023966921028e-05,
      "clip_ratio/region_mean": 0.0013398460396274459,
      "epoch": 0.07550647790047192,
      "grad_norm": 0.147970050573349,
      "learning_rate": 2e-07,
      "loss": 0.0163,
      "step": 809
    },
    {
      "clip_ratio/high_max": 0.001958991510036867,
      "clip_ratio/high_mean": 0.0007688003424846102,
      "clip_ratio/low_mean": 0.0005585069393418962,
      "clip_ratio/low_min": 4.189849005342694e-05,
      "clip_ratio/region_mean": 0.0013273073091113474,
      "epoch": 0.0755998110004725,
      "grad_norm": 0.1367771178483963,
      "learning_rate": 2e-07,
      "loss": 0.0197,
      "step": 810
    },
    {
      "clip_ratio/high_max": 0.0018569914245745167,
      "clip_ratio/high_mean": 0.0007290806024684571,
      "clip_ratio/low_mean": 0.0006079063759898418,
      "clip_ratio/low_min": 2.486642233634484e-05,
      "clip_ratio/region_mean": 0.0013369870102906134,
      "epoch": 0.07569314410047308,
      "grad_norm": 0.14639969170093536,
      "learning_rate": 2e-07,
      "loss": 0.0253,
      "step": 811
    },
    {
      "clip_ratio/high_max": 0.0017062740498658968,
      "clip_ratio/high_mean": 0.0007819854372428381,
      "clip_ratio/low_mean": 0.0005987690437905258,
      "clip_ratio/low_min": 5.9143076214240864e-05,
      "clip_ratio/region_mean": 0.001380754492856795,
      "epoch": 0.07578647720047367,
      "grad_norm": 0.14234429597854614,
      "learning_rate": 2e-07,
      "loss": 0.0389,
      "step": 812
    },
    {
      "clip_ratio/high_max": 0.0013804529189656023,
      "clip_ratio/high_mean": 0.0005912401793466415,
      "clip_ratio/low_mean": 0.0005607520051853498,
      "clip_ratio/low_min": 4.339407678344287e-05,
      "clip_ratio/region_mean": 0.001151992164523108,
      "epoch": 0.07587981030047425,
      "grad_norm": 0.13619458675384521,
      "learning_rate": 2e-07,
      "loss": 0.0306,
      "step": 813
    },
    {
      "clip_ratio/high_max": 0.0016600908857071772,
      "clip_ratio/high_mean": 0.0005965907712379703,
      "clip_ratio/low_mean": 0.0006012896628817543,
      "clip_ratio/low_min": 3.727036346390378e-05,
      "clip_ratio/region_mean": 0.0011978804213867988,
      "epoch": 0.07597314340047483,
      "grad_norm": 0.16401319205760956,
      "learning_rate": 2e-07,
      "loss": 0.0725,
      "step": 814
    },
    {
      "clip_ratio/high_max": 0.001683846869127592,
      "clip_ratio/high_mean": 0.0006842536131443921,
      "clip_ratio/low_mean": 0.0006626198091908009,
      "clip_ratio/low_min": 6.617076633119723e-05,
      "clip_ratio/region_mean": 0.0013468734323396347,
      "epoch": 0.07606647650047542,
      "grad_norm": 0.13338203728199005,
      "learning_rate": 2e-07,
      "loss": 0.0045,
      "step": 815
    },
    {
      "clip_ratio/high_max": 0.0018879020935855806,
      "clip_ratio/high_mean": 0.0008024603939702502,
      "clip_ratio/low_mean": 0.000514691010266688,
      "clip_ratio/low_min": 1.3703135664400179e-05,
      "clip_ratio/region_mean": 0.0013171513855922967,
      "epoch": 0.076159809600476,
      "grad_norm": 0.14281673729419708,
      "learning_rate": 2e-07,
      "loss": -0.0192,
      "step": 816
    },
    {
      "clip_ratio/high_max": 0.0017880633677123114,
      "clip_ratio/high_mean": 0.0007443195099767763,
      "clip_ratio/low_mean": 0.0005984746940157493,
      "clip_ratio/low_min": 8.708844870852772e-05,
      "clip_ratio/region_mean": 0.0013427941958070733,
      "epoch": 0.07625314270047658,
      "grad_norm": 0.1438835710287094,
      "learning_rate": 2e-07,
      "loss": -0.0193,
      "step": 817
    },
    {
      "clip_ratio/high_max": 0.0019252267738920636,
      "clip_ratio/high_mean": 0.000655231240671128,
      "clip_ratio/low_mean": 0.0006179340252856491,
      "clip_ratio/low_min": 3.0273673473857343e-05,
      "clip_ratio/region_mean": 0.0012731652641377877,
      "epoch": 0.07634647580047717,
      "grad_norm": 0.12540386617183685,
      "learning_rate": 2e-07,
      "loss": 0.0657,
      "step": 818
    },
    {
      "clip_ratio/high_max": 0.0015632547838322353,
      "clip_ratio/high_mean": 0.0006705824234813917,
      "clip_ratio/low_mean": 0.0005352399584808154,
      "clip_ratio/low_min": 5.693432467523962e-05,
      "clip_ratio/region_mean": 0.001205822394695133,
      "epoch": 0.07643980890047775,
      "grad_norm": 0.13703253865242004,
      "learning_rate": 2e-07,
      "loss": 0.0456,
      "step": 819
    },
    {
      "clip_ratio/high_max": 0.00192898230307037,
      "clip_ratio/high_mean": 0.0007037546911305981,
      "clip_ratio/low_mean": 0.0005784247268820764,
      "clip_ratio/low_min": 4.272923251846805e-05,
      "clip_ratio/region_mean": 0.0012821794080082327,
      "epoch": 0.07653314200047834,
      "grad_norm": 0.11834394931793213,
      "learning_rate": 2e-07,
      "loss": 0.0421,
      "step": 820
    },
    {
      "clip_ratio/high_max": 0.0015736531204311177,
      "clip_ratio/high_mean": 0.0006688269968435634,
      "clip_ratio/low_mean": 0.000613948071077175,
      "clip_ratio/low_min": 8.350497682840796e-05,
      "clip_ratio/region_mean": 0.0012827750470023602,
      "epoch": 0.07662647510047892,
      "grad_norm": 0.13649001717567444,
      "learning_rate": 2e-07,
      "loss": 0.0446,
      "step": 821
    },
    {
      "clip_ratio/high_max": 0.0016398711704823654,
      "clip_ratio/high_mean": 0.0006595290196855785,
      "clip_ratio/low_mean": 0.0005351198815333191,
      "clip_ratio/low_min": 4.1091743696597405e-05,
      "clip_ratio/region_mean": 0.0011946489175898023,
      "epoch": 0.0767198082004795,
      "grad_norm": 0.12645286321640015,
      "learning_rate": 2e-07,
      "loss": 0.0187,
      "step": 822
    },
    {
      "clip_ratio/high_max": 0.0016935367311816663,
      "clip_ratio/high_mean": 0.0006942493946553441,
      "clip_ratio/low_mean": 0.0005594274443865288,
      "clip_ratio/low_min": 1.0724090316216461e-05,
      "clip_ratio/region_mean": 0.001253676844498841,
      "epoch": 0.07681314130048009,
      "grad_norm": 0.12123214453458786,
      "learning_rate": 2e-07,
      "loss": 0.0188,
      "step": 823
    },
    {
      "clip_ratio/high_max": 0.0015939523400447797,
      "clip_ratio/high_mean": 0.0006969505539018428,
      "clip_ratio/low_mean": 0.0005984740364510799,
      "clip_ratio/low_min": 1.2327415788604412e-05,
      "clip_ratio/region_mean": 0.0012954245758010074,
      "epoch": 0.07690647440048066,
      "grad_norm": 0.12751084566116333,
      "learning_rate": 2e-07,
      "loss": 0.0542,
      "step": 824
    },
    {
      "clip_ratio/high_max": 0.0018998469022335485,
      "clip_ratio/high_mean": 0.000678361635436886,
      "clip_ratio/low_mean": 0.0004997128567083564,
      "clip_ratio/low_min": 1.1328620530548505e-05,
      "clip_ratio/region_mean": 0.0011780744971474633,
      "epoch": 0.07699980750048124,
      "grad_norm": 0.13260550796985626,
      "learning_rate": 2e-07,
      "loss": 0.0053,
      "step": 825
    },
    {
      "clip_ratio/high_max": 0.002143698133295402,
      "clip_ratio/high_mean": 0.0008798874350759434,
      "clip_ratio/low_mean": 0.0006661234074272215,
      "clip_ratio/low_min": 7.995417763595469e-05,
      "clip_ratio/region_mean": 0.001546010793390451,
      "epoch": 0.07709314060048184,
      "grad_norm": 0.15077175199985504,
      "learning_rate": 2e-07,
      "loss": 0.0419,
      "step": 826
    },
    {
      "clip_ratio/high_max": 0.0018457735095580574,
      "clip_ratio/high_mean": 0.0007108824775059475,
      "clip_ratio/low_mean": 0.000641125325273606,
      "clip_ratio/low_min": 2.2254446776059922e-05,
      "clip_ratio/region_mean": 0.0013520078027795535,
      "epoch": 0.07718647370048241,
      "grad_norm": 0.12772871553897858,
      "learning_rate": 2e-07,
      "loss": 0.0187,
      "step": 827
    },
    {
      "clip_ratio/high_max": 0.0016927984052017564,
      "clip_ratio/high_mean": 0.0005870232362212846,
      "clip_ratio/low_mean": 0.0005677641602233052,
      "clip_ratio/low_min": 8.983358929981478e-05,
      "clip_ratio/region_mean": 0.0011547874091775157,
      "epoch": 0.07727980680048299,
      "grad_norm": 0.12485478818416595,
      "learning_rate": 2e-07,
      "loss": 0.0766,
      "step": 828
    },
    {
      "clip_ratio/high_max": 0.001904539625684265,
      "clip_ratio/high_mean": 0.0007107686105882749,
      "clip_ratio/low_mean": 0.0005826346487083356,
      "clip_ratio/low_min": 5.827071981912013e-05,
      "clip_ratio/region_mean": 0.0012934032674820628,
      "epoch": 0.07737313990048358,
      "grad_norm": 0.13496677577495575,
      "learning_rate": 2e-07,
      "loss": 0.0224,
      "step": 829
    },
    {
      "clip_ratio/high_max": 0.0015324577943829354,
      "clip_ratio/high_mean": 0.0006205835179571295,
      "clip_ratio/low_mean": 0.0006622182881983463,
      "clip_ratio/low_min": 4.898440874967491e-05,
      "clip_ratio/region_mean": 0.0012828018097934546,
      "epoch": 0.07746647300048416,
      "grad_norm": 0.1365133672952652,
      "learning_rate": 2e-07,
      "loss": 0.0514,
      "step": 830
    },
    {
      "clip_ratio/high_max": 0.001999100459215697,
      "clip_ratio/high_mean": 0.0007701770973653765,
      "clip_ratio/low_mean": 0.0005273240471979079,
      "clip_ratio/low_min": 5.404704097600188e-06,
      "clip_ratio/region_mean": 0.0012975011559319682,
      "epoch": 0.07755980610048475,
      "grad_norm": 0.12909482419490814,
      "learning_rate": 2e-07,
      "loss": -0.0458,
      "step": 831
    },
    {
      "clip_ratio/high_max": 0.001708604901068611,
      "clip_ratio/high_mean": 0.0007225973040476674,
      "clip_ratio/low_mean": 0.0006624727629969129,
      "clip_ratio/low_min": 8.105641882139025e-05,
      "clip_ratio/region_mean": 0.0013850700815964956,
      "epoch": 0.07765313920048533,
      "grad_norm": 0.15218068659305573,
      "learning_rate": 2e-07,
      "loss": 0.017,
      "step": 832
    },
    {
      "clip_ratio/high_max": 0.0018833624417311512,
      "clip_ratio/high_mean": 0.0007042548495519441,
      "clip_ratio/low_mean": 0.0006081519522922463,
      "clip_ratio/low_min": 3.810309226537356e-05,
      "clip_ratio/region_mean": 0.0013124067809258122,
      "epoch": 0.07774647230048591,
      "grad_norm": 0.14196233451366425,
      "learning_rate": 2e-07,
      "loss": 0.0507,
      "step": 833
    },
    {
      "clip_ratio/high_max": 0.002149450345314108,
      "clip_ratio/high_mean": 0.0007868572229199344,
      "clip_ratio/low_mean": 0.0005962424675090006,
      "clip_ratio/low_min": 2.8472801204770803e-05,
      "clip_ratio/region_mean": 0.0013830996977048926,
      "epoch": 0.0778398054004865,
      "grad_norm": 0.13571864366531372,
      "learning_rate": 2e-07,
      "loss": -0.0178,
      "step": 834
    },
    {
      "clip_ratio/high_max": 0.0019375562405912206,
      "clip_ratio/high_mean": 0.0007950454019010067,
      "clip_ratio/low_mean": 0.0006569811812369153,
      "clip_ratio/low_min": 4.515250566328177e-05,
      "clip_ratio/region_mean": 0.001452026583137922,
      "epoch": 0.07793313850048708,
      "grad_norm": 0.13022808730602264,
      "learning_rate": 2e-07,
      "loss": -0.0233,
      "step": 835
    },
    {
      "clip_ratio/high_max": 0.0018788620400300715,
      "clip_ratio/high_mean": 0.000750087898268248,
      "clip_ratio/low_mean": 0.000557503704840201,
      "clip_ratio/low_min": 2.6566921405901667e-05,
      "clip_ratio/region_mean": 0.0013075916431262158,
      "epoch": 0.07802647160048766,
      "grad_norm": 0.14658649265766144,
      "learning_rate": 2e-07,
      "loss": 0.0006,
      "step": 836
    },
    {
      "clip_ratio/high_max": 0.0019153979192196857,
      "clip_ratio/high_mean": 0.0008173178539436776,
      "clip_ratio/low_mean": 0.0005796231771455496,
      "clip_ratio/low_min": 5.3002538152213674e-05,
      "clip_ratio/region_mean": 0.0013969410356367007,
      "epoch": 0.07811980470048825,
      "grad_norm": 0.15041302144527435,
      "learning_rate": 2e-07,
      "loss": 0.0165,
      "step": 837
    },
    {
      "clip_ratio/high_max": 0.0014782971047679894,
      "clip_ratio/high_mean": 0.0007079317510942928,
      "clip_ratio/low_mean": 0.0005419213994173333,
      "clip_ratio/low_min": 1.3417776244750712e-05,
      "clip_ratio/region_mean": 0.0012498531505116262,
      "epoch": 0.07821313780048883,
      "grad_norm": 0.13171188533306122,
      "learning_rate": 2e-07,
      "loss": 0.0184,
      "step": 838
    },
    {
      "clip_ratio/high_max": 0.0018026324905804358,
      "clip_ratio/high_mean": 0.0007265883568834397,
      "clip_ratio/low_mean": 0.0006411815256797126,
      "clip_ratio/low_min": 3.8851818317198195e-05,
      "clip_ratio/region_mean": 0.0013677699134859722,
      "epoch": 0.07830647090048942,
      "grad_norm": 0.14654722809791565,
      "learning_rate": 2e-07,
      "loss": 0.0288,
      "step": 839
    },
    {
      "clip_ratio/high_max": 0.0016917094653763343,
      "clip_ratio/high_mean": 0.0006608433304791106,
      "clip_ratio/low_mean": 0.0006033857534930576,
      "clip_ratio/low_min": 4.684438317781314e-05,
      "clip_ratio/region_mean": 0.0012642290748772211,
      "epoch": 0.07839980400049,
      "grad_norm": 0.3462652266025543,
      "learning_rate": 2e-07,
      "loss": 0.0416,
      "step": 840
    },
    {
      "clip_ratio/high_max": 0.0015994928035070188,
      "clip_ratio/high_mean": 0.0006402182398232981,
      "clip_ratio/low_mean": 0.0006774969060643343,
      "clip_ratio/low_min": 3.367299677847768e-05,
      "clip_ratio/region_mean": 0.001317715155892074,
      "epoch": 0.07849313710049058,
      "grad_norm": 0.14348195493221283,
      "learning_rate": 2e-07,
      "loss": 0.0296,
      "step": 841
    },
    {
      "clip_ratio/high_max": 0.0019061489292653278,
      "clip_ratio/high_mean": 0.0006882521347506554,
      "clip_ratio/low_mean": 0.0005911034722885233,
      "clip_ratio/low_min": 2.8200566703162622e-05,
      "clip_ratio/region_mean": 0.0012793556379619986,
      "epoch": 0.07858647020049117,
      "grad_norm": 0.11689718067646027,
      "learning_rate": 2e-07,
      "loss": 0.042,
      "step": 842
    },
    {
      "clip_ratio/high_max": 0.0018843109064619057,
      "clip_ratio/high_mean": 0.0006780731910112081,
      "clip_ratio/low_mean": 0.0005604768794000847,
      "clip_ratio/low_min": 1.3935339666204527e-05,
      "clip_ratio/region_mean": 0.001238550103153102,
      "epoch": 0.07867980330049175,
      "grad_norm": 0.16318903863430023,
      "learning_rate": 2e-07,
      "loss": 0.0321,
      "step": 843
    },
    {
      "clip_ratio/high_max": 0.0017581611864443403,
      "clip_ratio/high_mean": 0.0006828794575994834,
      "clip_ratio/low_mean": 0.0005826273081765976,
      "clip_ratio/low_min": 1.7171543277072487e-05,
      "clip_ratio/region_mean": 0.0012655067694140598,
      "epoch": 0.07877313640049233,
      "grad_norm": 0.13932915031909943,
      "learning_rate": 2e-07,
      "loss": 0.015,
      "step": 844
    },
    {
      "clip_ratio/high_max": 0.0019657473458210006,
      "clip_ratio/high_mean": 0.0007430771947838366,
      "clip_ratio/low_mean": 0.0005935587523708818,
      "clip_ratio/low_min": 2.2613558030570857e-05,
      "clip_ratio/region_mean": 0.0013366359671636019,
      "epoch": 0.07886646950049292,
      "grad_norm": 0.12274309992790222,
      "learning_rate": 2e-07,
      "loss": 0.0315,
      "step": 845
    },
    {
      "clip_ratio/high_max": 0.0019313524098834023,
      "clip_ratio/high_mean": 0.0007779531060805311,
      "clip_ratio/low_mean": 0.0005629645743283618,
      "clip_ratio/low_min": 4.183203145657899e-05,
      "clip_ratio/region_mean": 0.0013409176644927356,
      "epoch": 0.0789598026004935,
      "grad_norm": 0.13740064203739166,
      "learning_rate": 2e-07,
      "loss": 0.0123,
      "step": 846
    },
    {
      "clip_ratio/high_max": 0.0020123430440435186,
      "clip_ratio/high_mean": 0.0007768597861286253,
      "clip_ratio/low_mean": 0.0006079615832277341,
      "clip_ratio/low_min": 1.5139281003939686e-05,
      "clip_ratio/region_mean": 0.0013848213602614123,
      "epoch": 0.07905313570049408,
      "grad_norm": 0.15318091213703156,
      "learning_rate": 2e-07,
      "loss": 0.0285,
      "step": 847
    },
    {
      "clip_ratio/high_max": 0.001977508349227719,
      "clip_ratio/high_mean": 0.000745036208172678,
      "clip_ratio/low_mean": 0.0006471419737863471,
      "clip_ratio/low_min": 5.3680588280258235e-05,
      "clip_ratio/region_mean": 0.0013921782119723503,
      "epoch": 0.07914646880049467,
      "grad_norm": 0.15552359819412231,
      "learning_rate": 2e-07,
      "loss": 0.0388,
      "step": 848
    },
    {
      "clip_ratio/high_max": 0.0019778237692662515,
      "clip_ratio/high_mean": 0.000709802889105049,
      "clip_ratio/low_mean": 0.0005543161478271941,
      "clip_ratio/low_min": 5.338838582247263e-05,
      "clip_ratio/region_mean": 0.0012641190514841583,
      "epoch": 0.07923980190049525,
      "grad_norm": 0.13178296387195587,
      "learning_rate": 2e-07,
      "loss": -0.0052,
      "step": 849
    },
    {
      "clip_ratio/high_max": 0.002191538871556986,
      "clip_ratio/high_mean": 0.0008601342469773954,
      "clip_ratio/low_mean": 0.000563039459848369,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014231736640795134,
      "epoch": 0.07933313500049584,
      "grad_norm": 0.14099419116973877,
      "learning_rate": 2e-07,
      "loss": -0.0091,
      "step": 850
    },
    {
      "clip_ratio/high_max": 0.0019141512239002623,
      "clip_ratio/high_mean": 0.0008350371917913435,
      "clip_ratio/low_mean": 0.0006411176746041747,
      "clip_ratio/low_min": 3.245910193072632e-05,
      "clip_ratio/region_mean": 0.0014761548554815818,
      "epoch": 0.07942646810049642,
      "grad_norm": 0.13953916728496552,
      "learning_rate": 2e-07,
      "loss": -0.0036,
      "step": 851
    },
    {
      "clip_ratio/high_max": 0.001725200087093981,
      "clip_ratio/high_mean": 0.0006680435326416045,
      "clip_ratio/low_mean": 0.0006771515527361771,
      "clip_ratio/low_min": 7.713025706834742e-05,
      "clip_ratio/region_mean": 0.0013451951017486863,
      "epoch": 0.079519801200497,
      "grad_norm": 0.1532098650932312,
      "learning_rate": 2e-07,
      "loss": 0.0464,
      "step": 852
    },
    {
      "clip_ratio/high_max": 0.00156048374628881,
      "clip_ratio/high_mean": 0.0005825934267704724,
      "clip_ratio/low_mean": 0.0006045477475709049,
      "clip_ratio/low_min": 2.661591952346498e-05,
      "clip_ratio/region_mean": 0.0011871411534229992,
      "epoch": 0.07961313430049759,
      "grad_norm": 0.1271926909685135,
      "learning_rate": 2e-07,
      "loss": 0.0462,
      "step": 853
    },
    {
      "clip_ratio/high_max": 0.00171384729037527,
      "clip_ratio/high_mean": 0.0007462814282916952,
      "clip_ratio/low_mean": 0.0006080436096453923,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013543250461225398,
      "epoch": 0.07970646740049817,
      "grad_norm": 0.1508963257074356,
      "learning_rate": 2e-07,
      "loss": 0.0279,
      "step": 854
    },
    {
      "clip_ratio/high_max": 0.001662860951910261,
      "clip_ratio/high_mean": 0.000676789535646094,
      "clip_ratio/low_mean": 0.0006402832259482238,
      "clip_ratio/low_min": 3.708753501996398e-05,
      "clip_ratio/region_mean": 0.001317072757956339,
      "epoch": 0.07979980050049874,
      "grad_norm": 0.14977407455444336,
      "learning_rate": 2e-07,
      "loss": 0.0088,
      "step": 855
    },
    {
      "clip_ratio/high_max": 0.0018918046516773757,
      "clip_ratio/high_mean": 0.0006645467674388783,
      "clip_ratio/low_mean": 0.0005667572959282552,
      "clip_ratio/low_min": 2.745173424045788e-05,
      "clip_ratio/region_mean": 0.001231304067914607,
      "epoch": 0.07989313360049934,
      "grad_norm": 0.14309249818325043,
      "learning_rate": 2e-07,
      "loss": 0.0489,
      "step": 856
    },
    {
      "clip_ratio/high_max": 0.0022195544152054936,
      "clip_ratio/high_mean": 0.0007853569968574448,
      "clip_ratio/low_mean": 0.0005403354780355585,
      "clip_ratio/low_min": 1.2442763363651466e-05,
      "clip_ratio/region_mean": 0.0013256925049063284,
      "epoch": 0.07998646670049991,
      "grad_norm": 0.1526111364364624,
      "learning_rate": 2e-07,
      "loss": 0.0345,
      "step": 857
    },
    {
      "clip_ratio/high_max": 0.0017888219554151874,
      "clip_ratio/high_mean": 0.0006484762934633181,
      "clip_ratio/low_mean": 0.0006968006819079164,
      "clip_ratio/low_min": 5.11996208842902e-05,
      "clip_ratio/region_mean": 0.0013452769671857823,
      "epoch": 0.08007979980050049,
      "grad_norm": 0.15145811438560486,
      "learning_rate": 2e-07,
      "loss": 0.0494,
      "step": 858
    },
    {
      "clip_ratio/high_max": 0.002114544444339117,
      "clip_ratio/high_mean": 0.0008518222293787403,
      "clip_ratio/low_mean": 0.0005744349846281693,
      "clip_ratio/low_min": 5.09886049258057e-05,
      "clip_ratio/region_mean": 0.0014262572549341712,
      "epoch": 0.08017313290050108,
      "grad_norm": 0.15437942743301392,
      "learning_rate": 2e-07,
      "loss": -0.0257,
      "step": 859
    },
    {
      "clip_ratio/high_max": 0.0017277696606470272,
      "clip_ratio/high_mean": 0.0007308081858354853,
      "clip_ratio/low_mean": 0.0006812798474129522,
      "clip_ratio/low_min": 5.3489121455641e-05,
      "clip_ratio/region_mean": 0.0014120880405243952,
      "epoch": 0.08026646600050166,
      "grad_norm": 0.1509794443845749,
      "learning_rate": 2e-07,
      "loss": 0.0339,
      "step": 860
    },
    {
      "clip_ratio/high_max": 0.0016461503655591514,
      "clip_ratio/high_mean": 0.0006396495082299225,
      "clip_ratio/low_mean": 0.0006666440040135058,
      "clip_ratio/low_min": 4.958574572810903e-05,
      "clip_ratio/region_mean": 0.0013062935031484812,
      "epoch": 0.08035979910050225,
      "grad_norm": 0.1817036122083664,
      "learning_rate": 2e-07,
      "loss": 0.0629,
      "step": 861
    },
    {
      "clip_ratio/high_max": 0.0018003068435064051,
      "clip_ratio/high_mean": 0.0006791081668779952,
      "clip_ratio/low_mean": 0.0007458238414983498,
      "clip_ratio/low_min": 1.593168417457491e-05,
      "clip_ratio/region_mean": 0.0014249320047383662,
      "epoch": 0.08045313220050283,
      "grad_norm": 0.13310229778289795,
      "learning_rate": 2e-07,
      "loss": 0.0466,
      "step": 862
    },
    {
      "clip_ratio/high_max": 0.0019318575650686398,
      "clip_ratio/high_mean": 0.0008484066456730943,
      "clip_ratio/low_mean": 0.0007339136136579327,
      "clip_ratio/low_min": 7.082555111992406e-05,
      "clip_ratio/region_mean": 0.0015823202884348575,
      "epoch": 0.08054646530050341,
      "grad_norm": 0.1393742859363556,
      "learning_rate": 2e-07,
      "loss": 0.039,
      "step": 863
    },
    {
      "clip_ratio/high_max": 0.0019195258173567709,
      "clip_ratio/high_mean": 0.0007930360061436659,
      "clip_ratio/low_mean": 0.0006757417713743052,
      "clip_ratio/low_min": 7.871581146901008e-05,
      "clip_ratio/region_mean": 0.001468777802074328,
      "epoch": 0.080639798400504,
      "grad_norm": 0.15871849656105042,
      "learning_rate": 2e-07,
      "loss": 0.0162,
      "step": 864
    },
    {
      "clip_ratio/high_max": 0.0018783809391607065,
      "clip_ratio/high_mean": 0.0007554160856670933,
      "clip_ratio/low_mean": 0.0006238715595827671,
      "clip_ratio/low_min": 1.7748117898008786e-05,
      "clip_ratio/region_mean": 0.001379287670715712,
      "epoch": 0.08073313150050458,
      "grad_norm": 0.23202764987945557,
      "learning_rate": 2e-07,
      "loss": 0.0565,
      "step": 865
    },
    {
      "clip_ratio/high_max": 0.001651904014579486,
      "clip_ratio/high_mean": 0.0006512316067528445,
      "clip_ratio/low_mean": 0.0005772025942860637,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001228434204676887,
      "epoch": 0.08082646460050516,
      "grad_norm": 0.16133476793766022,
      "learning_rate": 2e-07,
      "loss": 0.025,
      "step": 866
    },
    {
      "clip_ratio/high_max": 0.001793093641026644,
      "clip_ratio/high_mean": 0.0007651549894944765,
      "clip_ratio/low_mean": 0.0005958176006970461,
      "clip_ratio/low_min": 5.548317130887881e-05,
      "clip_ratio/region_mean": 0.0013609725938295014,
      "epoch": 0.08091979770050575,
      "grad_norm": 0.14940930902957916,
      "learning_rate": 2e-07,
      "loss": 0.0234,
      "step": 867
    },
    {
      "clip_ratio/high_max": 0.0018528346117818728,
      "clip_ratio/high_mean": 0.0007613141278852709,
      "clip_ratio/low_mean": 0.0006358465052471729,
      "clip_ratio/low_min": 2.1828223907505162e-05,
      "clip_ratio/region_mean": 0.0013971606604172848,
      "epoch": 0.08101313080050633,
      "grad_norm": 0.14557217061519623,
      "learning_rate": 2e-07,
      "loss": 0.0407,
      "step": 868
    },
    {
      "clip_ratio/high_max": 0.0014650764242105652,
      "clip_ratio/high_mean": 0.0006130330029918696,
      "clip_ratio/low_mean": 0.0006353680910251569,
      "clip_ratio/low_min": 2.386406958976295e-05,
      "clip_ratio/region_mean": 0.0012484010694606695,
      "epoch": 0.08110646390050691,
      "grad_norm": 0.1532893180847168,
      "learning_rate": 2e-07,
      "loss": 0.0673,
      "step": 869
    },
    {
      "clip_ratio/high_max": 0.0020706517170765437,
      "clip_ratio/high_mean": 0.000806891957836342,
      "clip_ratio/low_mean": 0.0006271975435083732,
      "clip_ratio/low_min": 5.02255834362586e-05,
      "clip_ratio/region_mean": 0.001434089477697853,
      "epoch": 0.0811997970005075,
      "grad_norm": 0.14128327369689941,
      "learning_rate": 2e-07,
      "loss": 0.0055,
      "step": 870
    },
    {
      "clip_ratio/high_max": 0.00215466323425062,
      "clip_ratio/high_mean": 0.0007797104026394663,
      "clip_ratio/low_mean": 0.0005364497510527144,
      "clip_ratio/low_min": 3.28055130012217e-05,
      "clip_ratio/region_mean": 0.0013161601491447072,
      "epoch": 0.08129313010050808,
      "grad_norm": 0.13566707074642181,
      "learning_rate": 2e-07,
      "loss": -0.0016,
      "step": 871
    },
    {
      "clip_ratio/high_max": 0.0018439627201587427,
      "clip_ratio/high_mean": 0.0007913589215604588,
      "clip_ratio/low_mean": 0.0006693749437545193,
      "clip_ratio/low_min": 2.8048916647094302e-05,
      "clip_ratio/region_mean": 0.001460733823478222,
      "epoch": 0.08138646320050867,
      "grad_norm": 0.13910485804080963,
      "learning_rate": 2e-07,
      "loss": 0.015,
      "step": 872
    },
    {
      "clip_ratio/high_max": 0.0018143208872061223,
      "clip_ratio/high_mean": 0.0007449587137671188,
      "clip_ratio/low_mean": 0.0005542302405956434,
      "clip_ratio/low_min": 1.4334862498799339e-05,
      "clip_ratio/region_mean": 0.0012991889379918575,
      "epoch": 0.08147979630050925,
      "grad_norm": 0.15003639459609985,
      "learning_rate": 2e-07,
      "loss": 0.0362,
      "step": 873
    },
    {
      "clip_ratio/high_max": 0.0019059238329646178,
      "clip_ratio/high_mean": 0.0007537580986536341,
      "clip_ratio/low_mean": 0.0006323008783510886,
      "clip_ratio/low_min": 2.662209499249002e-05,
      "clip_ratio/region_mean": 0.0013860589497198816,
      "epoch": 0.08157312940050983,
      "grad_norm": 0.14419548213481903,
      "learning_rate": 2e-07,
      "loss": 0.0322,
      "step": 874
    },
    {
      "clip_ratio/high_max": 0.002204798685852438,
      "clip_ratio/high_mean": 0.0008017190884856973,
      "clip_ratio/low_mean": 0.0007860062178224325,
      "clip_ratio/low_min": 8.801034073258052e-05,
      "clip_ratio/region_mean": 0.0015877252990321722,
      "epoch": 0.08166646250051042,
      "grad_norm": 0.17921356856822968,
      "learning_rate": 2e-07,
      "loss": 0.1084,
      "step": 875
    },
    {
      "clip_ratio/high_max": 0.0019459210961940698,
      "clip_ratio/high_mean": 0.0007523648646383663,
      "clip_ratio/low_mean": 0.0007814995824446669,
      "clip_ratio/low_min": 4.3082956835860386e-05,
      "clip_ratio/region_mean": 0.0015338644116127398,
      "epoch": 0.081759795600511,
      "grad_norm": 0.15163950622081757,
      "learning_rate": 2e-07,
      "loss": 0.0799,
      "step": 876
    },
    {
      "clip_ratio/high_max": 0.0018663075170479715,
      "clip_ratio/high_mean": 0.0007977694494911702,
      "clip_ratio/low_mean": 0.0006706421827402664,
      "clip_ratio/low_min": 5.3953120186633896e-05,
      "clip_ratio/region_mean": 0.0014684116322314367,
      "epoch": 0.08185312870051158,
      "grad_norm": 0.1420414000749588,
      "learning_rate": 2e-07,
      "loss": 0.0079,
      "step": 877
    },
    {
      "clip_ratio/high_max": 0.0018510253357817419,
      "clip_ratio/high_mean": 0.0007594293128931895,
      "clip_ratio/low_mean": 0.000539151182238129,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012985804823983926,
      "epoch": 0.08194646180051217,
      "grad_norm": 0.13674955070018768,
      "learning_rate": 2e-07,
      "loss": -0.0191,
      "step": 878
    },
    {
      "clip_ratio/high_max": 0.0018398605025140569,
      "clip_ratio/high_mean": 0.0007376902549367514,
      "clip_ratio/low_mean": 0.0006626245349252713,
      "clip_ratio/low_min": 3.782463409152115e-05,
      "clip_ratio/region_mean": 0.0014003147844050545,
      "epoch": 0.08203979490051275,
      "grad_norm": 0.13474315404891968,
      "learning_rate": 2e-07,
      "loss": 0.0137,
      "step": 879
    },
    {
      "clip_ratio/high_max": 0.001908114572870545,
      "clip_ratio/high_mean": 0.0008513419215887552,
      "clip_ratio/low_mean": 0.0006196317171998089,
      "clip_ratio/low_min": 4.35024348917068e-05,
      "clip_ratio/region_mean": 0.0014709736096847337,
      "epoch": 0.08213312800051333,
      "grad_norm": 0.1517268717288971,
      "learning_rate": 2e-07,
      "loss": 0.0053,
      "step": 880
    },
    {
      "clip_ratio/high_max": 0.0018969643861055374,
      "clip_ratio/high_mean": 0.0007638317492819624,
      "clip_ratio/low_mean": 0.0006869660555821611,
      "clip_ratio/low_min": 8.024174894671887e-05,
      "clip_ratio/region_mean": 0.0014507977830362506,
      "epoch": 0.08222646110051392,
      "grad_norm": 0.1525135636329651,
      "learning_rate": 2e-07,
      "loss": 0.0244,
      "step": 881
    },
    {
      "clip_ratio/high_max": 0.0020202956366119906,
      "clip_ratio/high_mean": 0.000902481988305226,
      "clip_ratio/low_mean": 0.0005666356714755238,
      "clip_ratio/low_min": 2.2552351765625644e-05,
      "clip_ratio/region_mean": 0.001469117636588635,
      "epoch": 0.0823197942005145,
      "grad_norm": 0.14354459941387177,
      "learning_rate": 2e-07,
      "loss": -0.0433,
      "step": 882
    },
    {
      "clip_ratio/high_max": 0.0018588870407256763,
      "clip_ratio/high_mean": 0.0006928618195161107,
      "clip_ratio/low_mean": 0.0006357043785101268,
      "clip_ratio/low_min": 2.6517920559854247e-05,
      "clip_ratio/region_mean": 0.001328566202573711,
      "epoch": 0.08241312730051509,
      "grad_norm": 0.1518329679965973,
      "learning_rate": 2e-07,
      "loss": 0.0594,
      "step": 883
    },
    {
      "clip_ratio/high_max": 0.0021137019102752674,
      "clip_ratio/high_mean": 0.0007751684588583885,
      "clip_ratio/low_mean": 0.0006132919837682493,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013884604632039554,
      "epoch": 0.08250646040051567,
      "grad_norm": 0.13898968696594238,
      "learning_rate": 2e-07,
      "loss": 0.0177,
      "step": 884
    },
    {
      "clip_ratio/high_max": 0.001791020251403097,
      "clip_ratio/high_mean": 0.0007508067064918578,
      "clip_ratio/low_mean": 0.0007330464632104849,
      "clip_ratio/low_min": 4.32692831964232e-05,
      "clip_ratio/region_mean": 0.0014838531860732473,
      "epoch": 0.08259979350051624,
      "grad_norm": 0.15600574016571045,
      "learning_rate": 2e-07,
      "loss": 0.0355,
      "step": 885
    },
    {
      "clip_ratio/high_max": 0.0017020944360410795,
      "clip_ratio/high_mean": 0.0007278479934029747,
      "clip_ratio/low_mean": 0.0006418489738280186,
      "clip_ratio/low_min": 2.0341134131740546e-05,
      "clip_ratio/region_mean": 0.0013696969726879615,
      "epoch": 0.08269312660051684,
      "grad_norm": 0.12929055094718933,
      "learning_rate": 2e-07,
      "loss": 0.0119,
      "step": 886
    },
    {
      "clip_ratio/high_max": 0.0022671491096843965,
      "clip_ratio/high_mean": 0.0008537097673979588,
      "clip_ratio/low_mean": 0.0006784275210520718,
      "clip_ratio/low_min": 4.352334690338466e-05,
      "clip_ratio/region_mean": 0.0015321372702601366,
      "epoch": 0.08278645970051741,
      "grad_norm": 0.14595265686511993,
      "learning_rate": 2e-07,
      "loss": -0.0096,
      "step": 887
    },
    {
      "clip_ratio/high_max": 0.0017630117872613482,
      "clip_ratio/high_mean": 0.0007386234210571274,
      "clip_ratio/low_mean": 0.0006645461653533857,
      "clip_ratio/low_min": 2.484032665961422e-05,
      "clip_ratio/region_mean": 0.0014031695791345555,
      "epoch": 0.08287979280051799,
      "grad_norm": 0.1422441005706787,
      "learning_rate": 2e-07,
      "loss": 0.013,
      "step": 888
    },
    {
      "clip_ratio/high_max": 0.0019285959569970146,
      "clip_ratio/high_mean": 0.0008281491354864556,
      "clip_ratio/low_mean": 0.0007437372078129556,
      "clip_ratio/low_min": 5.040440555603709e-05,
      "clip_ratio/region_mean": 0.0015718863724032417,
      "epoch": 0.08297312590051859,
      "grad_norm": 0.15252764523029327,
      "learning_rate": 2e-07,
      "loss": 0.054,
      "step": 889
    },
    {
      "clip_ratio/high_max": 0.0020421528461156413,
      "clip_ratio/high_mean": 0.0007464885329682147,
      "clip_ratio/low_mean": 0.0008284678406198509,
      "clip_ratio/low_min": 0.00014415232089959318,
      "clip_ratio/region_mean": 0.001574956411786843,
      "epoch": 0.08306645900051916,
      "grad_norm": 0.15723568201065063,
      "learning_rate": 2e-07,
      "loss": 0.0743,
      "step": 890
    },
    {
      "clip_ratio/high_max": 0.001906704950670246,
      "clip_ratio/high_mean": 0.0007403245836030692,
      "clip_ratio/low_mean": 0.0005811370210722089,
      "clip_ratio/low_min": 3.818219556706026e-05,
      "clip_ratio/region_mean": 0.0013214616192271933,
      "epoch": 0.08315979210051976,
      "grad_norm": 0.14343716204166412,
      "learning_rate": 2e-07,
      "loss": 0.0262,
      "step": 891
    },
    {
      "clip_ratio/high_max": 0.0018963750953844283,
      "clip_ratio/high_mean": 0.0006949220623937435,
      "clip_ratio/low_mean": 0.0006278076334638172,
      "clip_ratio/low_min": 5.868816606380278e-05,
      "clip_ratio/region_mean": 0.0013227296913100872,
      "epoch": 0.08325312520052033,
      "grad_norm": 0.15836207568645477,
      "learning_rate": 2e-07,
      "loss": 0.0529,
      "step": 892
    },
    {
      "clip_ratio/high_max": 0.001993356410821434,
      "clip_ratio/high_mean": 0.0008299777800857555,
      "clip_ratio/low_mean": 0.0005853865186509211,
      "clip_ratio/low_min": 2.148838211724069e-05,
      "clip_ratio/region_mean": 0.0014153643060126342,
      "epoch": 0.08334645830052091,
      "grad_norm": 0.1637830287218094,
      "learning_rate": 2e-07,
      "loss": 0.0236,
      "step": 893
    },
    {
      "clip_ratio/high_max": 0.001752648033289006,
      "clip_ratio/high_mean": 0.0007815269127604552,
      "clip_ratio/low_mean": 0.0006834592313680332,
      "clip_ratio/low_min": 5.323157529346645e-05,
      "clip_ratio/region_mean": 0.00146498616959434,
      "epoch": 0.0834397914005215,
      "grad_norm": 0.15151366591453552,
      "learning_rate": 2e-07,
      "loss": -0.0119,
      "step": 894
    },
    {
      "clip_ratio/high_max": 0.001985197661269922,
      "clip_ratio/high_mean": 0.0008489346164424205,
      "clip_ratio/low_mean": 0.0007390038481389638,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001587938462762395,
      "epoch": 0.08353312450052208,
      "grad_norm": 0.2500661611557007,
      "learning_rate": 2e-07,
      "loss": 0.0179,
      "step": 895
    },
    {
      "clip_ratio/high_max": 0.0020402373702381738,
      "clip_ratio/high_mean": 0.0007440393565047998,
      "clip_ratio/low_mean": 0.0007472659308405127,
      "clip_ratio/low_min": 1.4595982975151855e-05,
      "clip_ratio/region_mean": 0.0014913052691554185,
      "epoch": 0.08362645760052266,
      "grad_norm": 0.18095657229423523,
      "learning_rate": 2e-07,
      "loss": 0.0501,
      "step": 896
    },
    {
      "clip_ratio/high_max": 0.0015967284089128952,
      "clip_ratio/high_mean": 0.0005814898977405392,
      "clip_ratio/low_mean": 0.0005112015578561113,
      "clip_ratio/low_min": 1.4768431356060319e-05,
      "clip_ratio/region_mean": 0.0010926914346782723,
      "completions/clipped_ratio": 0.0156773158482143,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4096.0,
      "completions/mean_length": 656.5914306640625,
      "completions/mean_terminated_length": 601.811767578125,
      "completions/min_length": 83.0,
      "completions/min_terminated_length": 83.0,
      "epoch": 0.08371979070052325,
      "grad_norm": 0.13549181818962097,
      "learning_rate": 2e-07,
      "loss": 0.0215,
      "num_tokens": 675767717.0,
      "reward": 0.5926164984703064,
      "reward_std": 0.18299156427383423,
      "rewards/simpleverify_reward/mean": 0.5926164984703064,
      "rewards/simpleverify_reward/std": 0.491349458694458,
      "step": 897
    },
    {
      "clip_ratio/high_max": 0.001561397162731737,
      "clip_ratio/high_mean": 0.0006934684515726985,
      "clip_ratio/low_mean": 0.0005822423872814397,
      "clip_ratio/low_min": 1.4548417311743833e-05,
      "clip_ratio/region_mean": 0.0012757108597725164,
      "epoch": 0.08381312380052383,
      "grad_norm": 0.13175863027572632,
      "learning_rate": 2e-07,
      "loss": -0.0201,
      "step": 898
    },
    {
      "clip_ratio/high_max": 0.0015439948147104587,
      "clip_ratio/high_mean": 0.0005826326914757374,
      "clip_ratio/low_mean": 0.0005805851342302049,
      "clip_ratio/low_min": 1.5687750419601798e-05,
      "clip_ratio/region_mean": 0.0011632178320724051,
      "epoch": 0.08390645690052441,
      "grad_norm": 0.12933337688446045,
      "learning_rate": 2e-07,
      "loss": 0.0585,
      "step": 899
    },
    {
      "clip_ratio/high_max": 0.0017352116883557756,
      "clip_ratio/high_mean": 0.0005850824372828356,
      "clip_ratio/low_mean": 0.0006023151599947596,
      "clip_ratio/low_min": 6.37005514363409e-05,
      "clip_ratio/region_mean": 0.0011873975745402277,
      "epoch": 0.083999790000525,
      "grad_norm": 0.13575293123722076,
      "learning_rate": 2e-07,
      "loss": 0.0718,
      "step": 900
    },
    {
      "clip_ratio/high_max": 0.0015213125698210206,
      "clip_ratio/high_mean": 0.0005570867942878976,
      "clip_ratio/low_mean": 0.0005752322904299945,
      "clip_ratio/low_min": 3.7523769606195856e-05,
      "clip_ratio/region_mean": 0.0011323190919938497,
      "epoch": 0.08409312310052558,
      "grad_norm": 0.1411878764629364,
      "learning_rate": 2e-07,
      "loss": 0.0434,
      "step": 901
    },
    {
      "clip_ratio/high_max": 0.0017054592608474195,
      "clip_ratio/high_mean": 0.0006156637937237974,
      "clip_ratio/low_mean": 0.000586325616495742,
      "clip_ratio/low_min": 1.627604251552839e-05,
      "clip_ratio/region_mean": 0.0012019894347758964,
      "epoch": 0.08418645620052617,
      "grad_norm": 0.49078813195228577,
      "learning_rate": 2e-07,
      "loss": 0.0353,
      "step": 902
    },
    {
      "clip_ratio/high_max": 0.0015669461790821515,
      "clip_ratio/high_mean": 0.0005726688368667965,
      "clip_ratio/low_mean": 0.0005506213110493263,
      "clip_ratio/low_min": 3.536513486324111e-05,
      "clip_ratio/region_mean": 0.0011232901561015751,
      "epoch": 0.08427978930052675,
      "grad_norm": 0.13290376961231232,
      "learning_rate": 2e-07,
      "loss": 0.0641,
      "step": 903
    },
    {
      "clip_ratio/high_max": 0.0017148500992334448,
      "clip_ratio/high_mean": 0.0007217345191747881,
      "clip_ratio/low_mean": 0.0006534508639788328,
      "clip_ratio/low_min": 9.391899766342249e-05,
      "clip_ratio/region_mean": 0.0013751853948633652,
      "epoch": 0.08437312240052733,
      "grad_norm": 0.13851337134838104,
      "learning_rate": 2e-07,
      "loss": 0.015,
      "step": 904
    },
    {
      "clip_ratio/high_max": 0.0018928054450952914,
      "clip_ratio/high_mean": 0.0006379991118592443,
      "clip_ratio/low_mean": 0.0005193380475247977,
      "clip_ratio/low_min": 4.041206420879462e-05,
      "clip_ratio/region_mean": 0.0011573371302802116,
      "epoch": 0.08446645550052792,
      "grad_norm": 0.12437933683395386,
      "learning_rate": 2e-07,
      "loss": 0.0377,
      "step": 905
    },
    {
      "clip_ratio/high_max": 0.0018234359740745276,
      "clip_ratio/high_mean": 0.0007438947432092391,
      "clip_ratio/low_mean": 0.0006263666309678229,
      "clip_ratio/low_min": 7.627149534528144e-05,
      "clip_ratio/region_mean": 0.0013702613978239242,
      "epoch": 0.0845597886005285,
      "grad_norm": 0.15691876411437988,
      "learning_rate": 2e-07,
      "loss": 0.0225,
      "step": 906
    },
    {
      "clip_ratio/high_max": 0.0018110176170011982,
      "clip_ratio/high_mean": 0.00074298206527601,
      "clip_ratio/low_mean": 0.0005523205900317407,
      "clip_ratio/low_min": 5.725006531065446e-05,
      "clip_ratio/region_mean": 0.0012953026380273513,
      "epoch": 0.08465312170052908,
      "grad_norm": 0.14186254143714905,
      "learning_rate": 2e-07,
      "loss": -0.0018,
      "step": 907
    },
    {
      "clip_ratio/high_max": 0.001703721773083089,
      "clip_ratio/high_mean": 0.0007271396261785412,
      "clip_ratio/low_mean": 0.0005605312971965759,
      "clip_ratio/low_min": 3.665535768959671e-05,
      "clip_ratio/region_mean": 0.0012876709406555165,
      "epoch": 0.08474645480052967,
      "grad_norm": 0.14035288989543915,
      "learning_rate": 2e-07,
      "loss": 0.0427,
      "step": 908
    },
    {
      "clip_ratio/high_max": 0.002129588607203914,
      "clip_ratio/high_mean": 0.0007434429717250168,
      "clip_ratio/low_mean": 0.0005603019963018596,
      "clip_ratio/low_min": 1.1499540050863288e-05,
      "clip_ratio/region_mean": 0.0013037449643888976,
      "epoch": 0.08483978790053025,
      "grad_norm": 0.1578233242034912,
      "learning_rate": 2e-07,
      "loss": 0.0126,
      "step": 909
    },
    {
      "clip_ratio/high_max": 0.0014504656683129724,
      "clip_ratio/high_mean": 0.0006057084792701062,
      "clip_ratio/low_mean": 0.0005344997198335477,
      "clip_ratio/low_min": 1.5630205780325923e-05,
      "clip_ratio/region_mean": 0.0011402082127460744,
      "epoch": 0.08493312100053083,
      "grad_norm": 0.1403988003730774,
      "learning_rate": 2e-07,
      "loss": 0.0395,
      "step": 910
    },
    {
      "clip_ratio/high_max": 0.0021517268651223276,
      "clip_ratio/high_mean": 0.0008307988973683678,
      "clip_ratio/low_mean": 0.00044699527188640786,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012777941628883127,
      "epoch": 0.08502645410053142,
      "grad_norm": 0.1737595647573471,
      "learning_rate": 2e-07,
      "loss": -0.0401,
      "step": 911
    },
    {
      "clip_ratio/high_max": 0.0014656700823252322,
      "clip_ratio/high_mean": 0.000561972681680345,
      "clip_ratio/low_mean": 0.0005172374958419823,
      "clip_ratio/low_min": 2.4955081244115718e-05,
      "clip_ratio/region_mean": 0.0010792101893457584,
      "epoch": 0.085119787200532,
      "grad_norm": 0.15598918497562408,
      "learning_rate": 2e-07,
      "loss": 0.0624,
      "step": 912
    },
    {
      "clip_ratio/high_max": 0.0016532461559108924,
      "clip_ratio/high_mean": 0.000719524068699684,
      "clip_ratio/low_mean": 0.0006259554556891089,
      "clip_ratio/low_min": 2.483536627551075e-05,
      "clip_ratio/region_mean": 0.001345479511655867,
      "epoch": 0.08521312030053259,
      "grad_norm": 0.1374732404947281,
      "learning_rate": 2e-07,
      "loss": 0.0207,
      "step": 913
    },
    {
      "clip_ratio/high_max": 0.0017545416776556522,
      "clip_ratio/high_mean": 0.0006950801780476468,
      "clip_ratio/low_mean": 0.000522357374393323,
      "clip_ratio/low_min": 3.0222437999327667e-05,
      "clip_ratio/region_mean": 0.0012174375478934962,
      "epoch": 0.08530645340053317,
      "grad_norm": 0.1726432889699936,
      "learning_rate": 2e-07,
      "loss": 0.0266,
      "step": 914
    },
    {
      "clip_ratio/high_max": 0.0015062741804285906,
      "clip_ratio/high_mean": 0.000599268561018107,
      "clip_ratio/low_mean": 0.0006061369331291644,
      "clip_ratio/low_min": 8.265898941317573e-05,
      "clip_ratio/region_mean": 0.001205405485961819,
      "epoch": 0.08539978650053374,
      "grad_norm": 0.14759540557861328,
      "learning_rate": 2e-07,
      "loss": 0.0693,
      "step": 915
    },
    {
      "clip_ratio/high_max": 0.0016175219025171828,
      "clip_ratio/high_mean": 0.0006114437546784757,
      "clip_ratio/low_mean": 0.0006954297114134533,
      "clip_ratio/low_min": 7.193934288807213e-05,
      "clip_ratio/region_mean": 0.0013068734624539502,
      "epoch": 0.08549311960053434,
      "grad_norm": 0.12956063449382782,
      "learning_rate": 2e-07,
      "loss": 0.0369,
      "step": 916
    },
    {
      "clip_ratio/high_max": 0.0017409465108357836,
      "clip_ratio/high_mean": 0.0006867565411994292,
      "clip_ratio/low_mean": 0.00053917412787996,
      "clip_ratio/low_min": 5.930920133323525e-05,
      "clip_ratio/region_mean": 0.00122593068954302,
      "epoch": 0.08558645270053492,
      "grad_norm": 0.13957950472831726,
      "learning_rate": 2e-07,
      "loss": -0.0067,
      "step": 917
    },
    {
      "clip_ratio/high_max": 0.0015139422357606236,
      "clip_ratio/high_mean": 0.0005297754378261743,
      "clip_ratio/low_mean": 0.0006165146146486222,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001146290062024491,
      "epoch": 0.0856797858005355,
      "grad_norm": 0.13851527869701385,
      "learning_rate": 2e-07,
      "loss": 0.0616,
      "step": 918
    },
    {
      "clip_ratio/high_max": 0.0019366443011676893,
      "clip_ratio/high_mean": 0.000681002318742685,
      "clip_ratio/low_mean": 0.0005957832890999271,
      "clip_ratio/low_min": 2.7754431357607245e-05,
      "clip_ratio/region_mean": 0.001276785580557771,
      "epoch": 0.08577311890053609,
      "grad_norm": 0.13460753858089447,
      "learning_rate": 2e-07,
      "loss": 0.0231,
      "step": 919
    },
    {
      "clip_ratio/high_max": 0.0016042291608755477,
      "clip_ratio/high_mean": 0.0006273482495089411,
      "clip_ratio/low_mean": 0.0006225861143320799,
      "clip_ratio/low_min": 4.503178297454724e-05,
      "clip_ratio/region_mean": 0.0012499343538365792,
      "epoch": 0.08586645200053666,
      "grad_norm": 0.14184603095054626,
      "learning_rate": 2e-07,
      "loss": 0.0489,
      "step": 920
    },
    {
      "clip_ratio/high_max": 0.001942801729455823,
      "clip_ratio/high_mean": 0.0007226038778753718,
      "clip_ratio/low_mean": 0.0006403596162272152,
      "clip_ratio/low_min": 3.048480903089512e-05,
      "clip_ratio/region_mean": 0.00136296348500764,
      "epoch": 0.08595978510053724,
      "grad_norm": 0.15107688307762146,
      "learning_rate": 2e-07,
      "loss": 0.0196,
      "step": 921
    },
    {
      "clip_ratio/high_max": 0.0020201020161039196,
      "clip_ratio/high_mean": 0.000785386486313655,
      "clip_ratio/low_mean": 0.0005606232361969887,
      "clip_ratio/low_min": 3.248440771130845e-05,
      "clip_ratio/region_mean": 0.0013460097361530643,
      "epoch": 0.08605311820053783,
      "grad_norm": 0.14862816035747528,
      "learning_rate": 2e-07,
      "loss": -0.0069,
      "step": 922
    },
    {
      "clip_ratio/high_max": 0.001336767956672702,
      "clip_ratio/high_mean": 0.0005826861670357175,
      "clip_ratio/low_mean": 0.0006115518899605377,
      "clip_ratio/low_min": 3.524709609337151e-05,
      "clip_ratio/region_mean": 0.001194238069729181,
      "epoch": 0.08614645130053841,
      "grad_norm": 0.1520920693874359,
      "learning_rate": 2e-07,
      "loss": 0.0586,
      "step": 923
    },
    {
      "clip_ratio/high_max": 0.0017420677686459385,
      "clip_ratio/high_mean": 0.0006739973923686193,
      "clip_ratio/low_mean": 0.0006116251734056277,
      "clip_ratio/low_min": 0.00010688203474273905,
      "clip_ratio/region_mean": 0.001285622583964141,
      "epoch": 0.086239784400539,
      "grad_norm": 0.1415053904056549,
      "learning_rate": 2e-07,
      "loss": 0.0079,
      "step": 924
    },
    {
      "clip_ratio/high_max": 0.0019110435059701558,
      "clip_ratio/high_mean": 0.0007354313183896011,
      "clip_ratio/low_mean": 0.000587212964092032,
      "clip_ratio/low_min": 2.368580180700519e-05,
      "clip_ratio/region_mean": 0.0013226442824816331,
      "epoch": 0.08633311750053958,
      "grad_norm": 0.1487334817647934,
      "learning_rate": 2e-07,
      "loss": 0.0482,
      "step": 925
    },
    {
      "clip_ratio/high_max": 0.0017633367679081857,
      "clip_ratio/high_mean": 0.0007152704256441211,
      "clip_ratio/low_mean": 0.0006217048030521255,
      "clip_ratio/low_min": 1.1040452591259964e-05,
      "clip_ratio/region_mean": 0.0013369752196012996,
      "epoch": 0.08642645060054016,
      "grad_norm": 0.14829230308532715,
      "learning_rate": 2e-07,
      "loss": -0.006,
      "step": 926
    },
    {
      "clip_ratio/high_max": 0.001627738049137406,
      "clip_ratio/high_mean": 0.0006572049569513183,
      "clip_ratio/low_mean": 0.000583134360567783,
      "clip_ratio/low_min": 2.636748286022339e-05,
      "clip_ratio/region_mean": 0.0012403393193380907,
      "epoch": 0.08651978370054075,
      "grad_norm": 0.15884599089622498,
      "learning_rate": 2e-07,
      "loss": 0.0419,
      "step": 927
    },
    {
      "clip_ratio/high_max": 0.0018461713116266765,
      "clip_ratio/high_mean": 0.0007027570391073823,
      "clip_ratio/low_mean": 0.0005533672092497,
      "clip_ratio/low_min": 1.4204545550455805e-05,
      "clip_ratio/region_mean": 0.0012561242692754604,
      "epoch": 0.08661311680054133,
      "grad_norm": 0.148577019572258,
      "learning_rate": 2e-07,
      "loss": 0.0203,
      "step": 928
    },
    {
      "clip_ratio/high_max": 0.0017364769119012635,
      "clip_ratio/high_mean": 0.0006874520076962654,
      "clip_ratio/low_mean": 0.0006706906260660617,
      "clip_ratio/low_min": 1.5424482626258396e-05,
      "clip_ratio/region_mean": 0.0013581426392192952,
      "epoch": 0.08670644990054191,
      "grad_norm": 0.14356404542922974,
      "learning_rate": 2e-07,
      "loss": 0.0074,
      "step": 929
    },
    {
      "clip_ratio/high_max": 0.0018763012012641411,
      "clip_ratio/high_mean": 0.0006698812630929751,
      "clip_ratio/low_mean": 0.0006113684539741371,
      "clip_ratio/low_min": 4.465650363272289e-05,
      "clip_ratio/region_mean": 0.0012812497334380168,
      "epoch": 0.0867997830005425,
      "grad_norm": 0.13560567796230316,
      "learning_rate": 2e-07,
      "loss": 0.0246,
      "step": 930
    },
    {
      "clip_ratio/high_max": 0.0016894715663511306,
      "clip_ratio/high_mean": 0.0006424582534236833,
      "clip_ratio/low_mean": 0.0005979287079753703,
      "clip_ratio/low_min": 4.0012211684370413e-05,
      "clip_ratio/region_mean": 0.001240386969584506,
      "epoch": 0.08689311610054308,
      "grad_norm": 0.1492682844400406,
      "learning_rate": 2e-07,
      "loss": 0.057,
      "step": 931
    },
    {
      "clip_ratio/high_max": 0.0016340763722837437,
      "clip_ratio/high_mean": 0.0006762046014046064,
      "clip_ratio/low_mean": 0.0005550609121200978,
      "clip_ratio/low_min": 3.698825275932904e-05,
      "clip_ratio/region_mean": 0.0012312655126152094,
      "epoch": 0.08698644920054366,
      "grad_norm": 0.14825674891471863,
      "learning_rate": 2e-07,
      "loss": 0.0285,
      "step": 932
    },
    {
      "clip_ratio/high_max": 0.0018011686115642078,
      "clip_ratio/high_mean": 0.0006909989351697732,
      "clip_ratio/low_mean": 0.0006165472168504493,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013075461465632543,
      "epoch": 0.08707978230054425,
      "grad_norm": 0.13232611119747162,
      "learning_rate": 2e-07,
      "loss": 0.0085,
      "step": 933
    },
    {
      "clip_ratio/high_max": 0.0017766154232958797,
      "clip_ratio/high_mean": 0.0007537573073932435,
      "clip_ratio/low_mean": 0.0005564579169003991,
      "clip_ratio/low_min": 3.840309182123747e-05,
      "clip_ratio/region_mean": 0.001310215226112632,
      "epoch": 0.08717311540054483,
      "grad_norm": 0.15140919387340546,
      "learning_rate": 2e-07,
      "loss": -0.0191,
      "step": 934
    },
    {
      "clip_ratio/high_max": 0.0015247852716129273,
      "clip_ratio/high_mean": 0.0005935785629844759,
      "clip_ratio/low_mean": 0.0006426573763747001,
      "clip_ratio/low_min": 1.0676460988179315e-05,
      "clip_ratio/region_mean": 0.0012362359411781654,
      "epoch": 0.08726644850054542,
      "grad_norm": 0.13850785791873932,
      "learning_rate": 2e-07,
      "loss": 0.0525,
      "step": 935
    },
    {
      "clip_ratio/high_max": 0.001841538236476481,
      "clip_ratio/high_mean": 0.0006383438649208983,
      "clip_ratio/low_mean": 0.0006129048979346408,
      "clip_ratio/low_min": 3.213452964700991e-05,
      "clip_ratio/region_mean": 0.0012512487919593696,
      "epoch": 0.087359781600546,
      "grad_norm": 0.40165892243385315,
      "learning_rate": 2e-07,
      "loss": 0.0563,
      "step": 936
    },
    {
      "clip_ratio/high_max": 0.0017364050072501414,
      "clip_ratio/high_mean": 0.0007075999419612344,
      "clip_ratio/low_mean": 0.0006564254217664711,
      "clip_ratio/low_min": 1.262116347788833e-05,
      "clip_ratio/region_mean": 0.0013640253637277056,
      "epoch": 0.08745311470054658,
      "grad_norm": 0.14047060906887054,
      "learning_rate": 2e-07,
      "loss": 0.0173,
      "step": 937
    },
    {
      "clip_ratio/high_max": 0.0014446389286604244,
      "clip_ratio/high_mean": 0.0005970032543700654,
      "clip_ratio/low_mean": 0.0005993042232148582,
      "clip_ratio/low_min": 8.530094419256784e-06,
      "clip_ratio/region_mean": 0.0011963074684899766,
      "epoch": 0.08754644780054717,
      "grad_norm": 0.13327822089195251,
      "learning_rate": 2e-07,
      "loss": 0.0001,
      "step": 938
    },
    {
      "clip_ratio/high_max": 0.0017155137720692437,
      "clip_ratio/high_mean": 0.0007171968845796073,
      "clip_ratio/low_mean": 0.0006034867337803007,
      "clip_ratio/low_min": 3.735063910426106e-05,
      "clip_ratio/region_mean": 0.0013206836229073815,
      "epoch": 0.08763978090054775,
      "grad_norm": 0.14642290771007538,
      "learning_rate": 2e-07,
      "loss": 0.0222,
      "step": 939
    },
    {
      "clip_ratio/high_max": 0.0018498821045795921,
      "clip_ratio/high_mean": 0.0006654855114902603,
      "clip_ratio/low_mean": 0.0006289547391133965,
      "clip_ratio/low_min": 2.3649324248253834e-05,
      "clip_ratio/region_mean": 0.0012944402733410243,
      "epoch": 0.08773311400054833,
      "grad_norm": 0.15709646046161652,
      "learning_rate": 2e-07,
      "loss": 0.0301,
      "step": 940
    },
    {
      "clip_ratio/high_max": 0.0018532064714236185,
      "clip_ratio/high_mean": 0.0008154071911121719,
      "clip_ratio/low_mean": 0.0006354513379847049,
      "clip_ratio/low_min": 3.778658174269367e-05,
      "clip_ratio/region_mean": 0.0014508585336443502,
      "epoch": 0.08782644710054892,
      "grad_norm": 0.14968709647655487,
      "learning_rate": 2e-07,
      "loss": 0.0133,
      "step": 941
    },
    {
      "clip_ratio/high_max": 0.001614033906662371,
      "clip_ratio/high_mean": 0.0006580384579137899,
      "clip_ratio/low_mean": 0.0006329300194920506,
      "clip_ratio/low_min": 6.168903746583965e-05,
      "clip_ratio/region_mean": 0.001290968488319777,
      "epoch": 0.0879197802005495,
      "grad_norm": 0.1360132247209549,
      "learning_rate": 2e-07,
      "loss": 0.0583,
      "step": 942
    },
    {
      "clip_ratio/high_max": 0.0014058155975362752,
      "clip_ratio/high_mean": 0.0005821979393658694,
      "clip_ratio/low_mean": 0.0005943457090324955,
      "clip_ratio/low_min": 2.31089234148385e-05,
      "clip_ratio/region_mean": 0.0011765436684072483,
      "epoch": 0.08801311330055009,
      "grad_norm": 0.144170343875885,
      "learning_rate": 2e-07,
      "loss": 0.0568,
      "step": 943
    },
    {
      "clip_ratio/high_max": 0.0019847943767672405,
      "clip_ratio/high_mean": 0.0007670282193430467,
      "clip_ratio/low_mean": 0.0005996203517497634,
      "clip_ratio/low_min": 5.718206739402376e-05,
      "clip_ratio/region_mean": 0.00136664858655422,
      "epoch": 0.08810644640055067,
      "grad_norm": 0.1375730335712433,
      "learning_rate": 2e-07,
      "loss": -0.0014,
      "step": 944
    },
    {
      "clip_ratio/high_max": 0.0017257658546441235,
      "clip_ratio/high_mean": 0.0006997886466706404,
      "clip_ratio/low_mean": 0.0006797026635467773,
      "clip_ratio/low_min": 1.1316313248244114e-05,
      "clip_ratio/region_mean": 0.0013794913284073118,
      "epoch": 0.08819977950055125,
      "grad_norm": 0.15689490735530853,
      "learning_rate": 2e-07,
      "loss": 0.0053,
      "step": 945
    },
    {
      "clip_ratio/high_max": 0.0018375839390500914,
      "clip_ratio/high_mean": 0.000675853121720138,
      "clip_ratio/low_mean": 0.0005929541903242352,
      "clip_ratio/low_min": 1.6348418284906074e-05,
      "clip_ratio/region_mean": 0.0012688073184108362,
      "epoch": 0.08829311260055184,
      "grad_norm": 0.1540026068687439,
      "learning_rate": 2e-07,
      "loss": 0.0408,
      "step": 946
    },
    {
      "clip_ratio/high_max": 0.0017043523512256797,
      "clip_ratio/high_mean": 0.0006297641994024161,
      "clip_ratio/low_mean": 0.000565444415769889,
      "clip_ratio/low_min": 9.851828508544713e-06,
      "clip_ratio/region_mean": 0.001195208591525443,
      "epoch": 0.08838644570055242,
      "grad_norm": 0.1712838113307953,
      "learning_rate": 2e-07,
      "loss": 0.0378,
      "step": 947
    },
    {
      "clip_ratio/high_max": 0.002181917781854281,
      "clip_ratio/high_mean": 0.0008172517746061203,
      "clip_ratio/low_mean": 0.0006702996561216423,
      "clip_ratio/low_min": 8.762372362980386e-05,
      "clip_ratio/region_mean": 0.0014875514170853421,
      "epoch": 0.088479778800553,
      "grad_norm": 0.14389191567897797,
      "learning_rate": 2e-07,
      "loss": -0.0139,
      "step": 948
    },
    {
      "clip_ratio/high_max": 0.0016152310636243783,
      "clip_ratio/high_mean": 0.0006794294713472482,
      "clip_ratio/low_mean": 0.0006726663141307654,
      "clip_ratio/low_min": 5.0409030336595606e-05,
      "clip_ratio/region_mean": 0.0013520957800210454,
      "epoch": 0.08857311190055359,
      "grad_norm": 0.15391457080841064,
      "learning_rate": 2e-07,
      "loss": 0.0575,
      "step": 949
    },
    {
      "clip_ratio/high_max": 0.0014913881677784957,
      "clip_ratio/high_mean": 0.0006032635674273479,
      "clip_ratio/low_mean": 0.0006028328989486909,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012060964509146288,
      "epoch": 0.08866644500055416,
      "grad_norm": 0.155614972114563,
      "learning_rate": 2e-07,
      "loss": 0.0718,
      "step": 950
    },
    {
      "clip_ratio/high_max": 0.001612062729691388,
      "clip_ratio/high_mean": 0.0006614865287701832,
      "clip_ratio/low_mean": 0.0005185445534152677,
      "clip_ratio/low_min": 9.370314728585072e-06,
      "clip_ratio/region_mean": 0.001180031082185451,
      "epoch": 0.08875977810055474,
      "grad_norm": 0.1615762710571289,
      "learning_rate": 2e-07,
      "loss": 0.0624,
      "step": 951
    },
    {
      "clip_ratio/high_max": 0.0019262257046648301,
      "clip_ratio/high_mean": 0.0008171762674464844,
      "clip_ratio/low_mean": 0.0006965325646888232,
      "clip_ratio/low_min": 3.5699980799108744e-05,
      "clip_ratio/region_mean": 0.0015137088412302546,
      "epoch": 0.08885311120055533,
      "grad_norm": 0.14786235988140106,
      "learning_rate": 2e-07,
      "loss": 0.0195,
      "step": 952
    },
    {
      "clip_ratio/high_max": 0.001610243140021339,
      "clip_ratio/high_mean": 0.0006459336646003067,
      "clip_ratio/low_mean": 0.0006756033235433279,
      "clip_ratio/low_min": 5.798095298814587e-05,
      "clip_ratio/region_mean": 0.0013215369908721186,
      "epoch": 0.08894644430055591,
      "grad_norm": 0.15719041228294373,
      "learning_rate": 2e-07,
      "loss": 0.0422,
      "step": 953
    },
    {
      "clip_ratio/high_max": 0.0016098885935207363,
      "clip_ratio/high_mean": 0.0006598408817808377,
      "clip_ratio/low_mean": 0.0005663799929607194,
      "clip_ratio/low_min": 2.0966119336662814e-05,
      "clip_ratio/region_mean": 0.0012262208583706524,
      "epoch": 0.0890397774005565,
      "grad_norm": 0.1461481899023056,
      "learning_rate": 2e-07,
      "loss": 0.0566,
      "step": 954
    },
    {
      "clip_ratio/high_max": 0.0018223091537947766,
      "clip_ratio/high_mean": 0.0007399610276479507,
      "clip_ratio/low_mean": 0.0006216908459464321,
      "clip_ratio/low_min": 5.9917666931141866e-05,
      "clip_ratio/region_mean": 0.0013616518990602344,
      "epoch": 0.08913311050055708,
      "grad_norm": 0.14125525951385498,
      "learning_rate": 2e-07,
      "loss": 0.0134,
      "step": 955
    },
    {
      "clip_ratio/high_max": 0.0016872727501322515,
      "clip_ratio/high_mean": 0.0006801241656830825,
      "clip_ratio/low_mean": 0.0007370338880718919,
      "clip_ratio/low_min": 5.667260666086804e-05,
      "clip_ratio/region_mean": 0.001417158084223047,
      "epoch": 0.08922644360055766,
      "grad_norm": 0.14837798476219177,
      "learning_rate": 2e-07,
      "loss": 0.0236,
      "step": 956
    },
    {
      "clip_ratio/high_max": 0.002018110408243956,
      "clip_ratio/high_mean": 0.00075513698220675,
      "clip_ratio/low_mean": 0.0006421748475986533,
      "clip_ratio/low_min": 5.32309350091964e-05,
      "clip_ratio/region_mean": 0.0013973118329886347,
      "epoch": 0.08931977670055825,
      "grad_norm": 0.1685246229171753,
      "learning_rate": 2e-07,
      "loss": 0.0322,
      "step": 957
    },
    {
      "clip_ratio/high_max": 0.0017048562804120593,
      "clip_ratio/high_mean": 0.0007253068815771258,
      "clip_ratio/low_mean": 0.0006515228888019919,
      "clip_ratio/low_min": 5.554386461881222e-05,
      "clip_ratio/region_mean": 0.0013768297831120435,
      "epoch": 0.08941310980055883,
      "grad_norm": 0.15923207998275757,
      "learning_rate": 2e-07,
      "loss": 0.0435,
      "step": 958
    },
    {
      "clip_ratio/high_max": 0.0016913980143726803,
      "clip_ratio/high_mean": 0.0006519774433400016,
      "clip_ratio/low_mean": 0.00058609993175196,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012380773605400464,
      "epoch": 0.08950644290055941,
      "grad_norm": 0.1433023363351822,
      "learning_rate": 2e-07,
      "loss": 0.0412,
      "step": 959
    },
    {
      "clip_ratio/high_max": 0.00195053845163784,
      "clip_ratio/high_mean": 0.000752691155867069,
      "clip_ratio/low_mean": 0.0006733030058967415,
      "clip_ratio/low_min": 1.896813409985043e-05,
      "clip_ratio/region_mean": 0.0014259941781347152,
      "epoch": 0.08959977600056,
      "grad_norm": 0.17645296454429626,
      "learning_rate": 2e-07,
      "loss": 0.0259,
      "step": 960
    },
    {
      "clip_ratio/high_max": 0.0017333344658254646,
      "clip_ratio/high_mean": 0.0007236578121592174,
      "clip_ratio/low_mean": 0.0007232475527416682,
      "clip_ratio/low_min": 4.7980017370719e-05,
      "clip_ratio/region_mean": 0.001446905360353412,
      "epoch": 0.08969310910056058,
      "grad_norm": 0.14295274019241333,
      "learning_rate": 2e-07,
      "loss": 0.03,
      "step": 961
    },
    {
      "clip_ratio/high_max": 0.001791419112123549,
      "clip_ratio/high_mean": 0.0007514136323152343,
      "clip_ratio/low_mean": 0.0007780562318657758,
      "clip_ratio/low_min": 3.87216769013321e-05,
      "clip_ratio/region_mean": 0.0015294698387151584,
      "epoch": 0.08978644220056116,
      "grad_norm": 0.14367815852165222,
      "learning_rate": 2e-07,
      "loss": 0.0282,
      "step": 962
    },
    {
      "clip_ratio/high_max": 0.0016306404977513012,
      "clip_ratio/high_mean": 0.0006500556573882932,
      "clip_ratio/low_mean": 0.0006211377840372734,
      "clip_ratio/low_min": 2.5136391741398256e-05,
      "clip_ratio/region_mean": 0.0012711934286926407,
      "epoch": 0.08987977530056175,
      "grad_norm": 1.6643041372299194,
      "learning_rate": 2e-07,
      "loss": 0.0363,
      "step": 963
    },
    {
      "clip_ratio/high_max": 0.0017155869318230543,
      "clip_ratio/high_mean": 0.0007564597945020068,
      "clip_ratio/low_mean": 0.0005712039474019548,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001327663761912845,
      "epoch": 0.08997310840056233,
      "grad_norm": 0.15755465626716614,
      "learning_rate": 2e-07,
      "loss": 0.0056,
      "step": 964
    },
    {
      "clip_ratio/high_max": 0.001731225576804718,
      "clip_ratio/high_mean": 0.0006712662543577608,
      "clip_ratio/low_mean": 0.0006580202807526803,
      "clip_ratio/low_min": 6.380548438755795e-05,
      "clip_ratio/region_mean": 0.0013292865223775152,
      "epoch": 0.09006644150056292,
      "grad_norm": 0.1681397706270218,
      "learning_rate": 2e-07,
      "loss": 0.0549,
      "step": 965
    },
    {
      "clip_ratio/high_max": 0.001717697818094166,
      "clip_ratio/high_mean": 0.000690625671268208,
      "clip_ratio/low_mean": 0.0006659329774265643,
      "clip_ratio/low_min": 9.188556759909261e-05,
      "clip_ratio/region_mean": 0.0013565586268668994,
      "epoch": 0.0901597746005635,
      "grad_norm": 0.22851037979125977,
      "learning_rate": 2e-07,
      "loss": 0.0239,
      "step": 966
    },
    {
      "clip_ratio/high_max": 0.0018179745893576182,
      "clip_ratio/high_mean": 0.0007173036992753623,
      "clip_ratio/low_mean": 0.000673287051540683,
      "clip_ratio/low_min": 4.505121614784002e-05,
      "clip_ratio/region_mean": 0.0013905907835578546,
      "epoch": 0.09025310770056408,
      "grad_norm": 0.1608322411775589,
      "learning_rate": 2e-07,
      "loss": 0.025,
      "step": 967
    },
    {
      "clip_ratio/high_max": 0.0018123205118172336,
      "clip_ratio/high_mean": 0.0007438417105731787,
      "clip_ratio/low_mean": 0.0006748748455720488,
      "clip_ratio/low_min": 4.9847900754684815e-05,
      "clip_ratio/region_mean": 0.0014187165506882593,
      "epoch": 0.09034644080056467,
      "grad_norm": 0.16142162680625916,
      "learning_rate": 2e-07,
      "loss": 0.023,
      "step": 968
    },
    {
      "clip_ratio/high_max": 0.0018675397732295096,
      "clip_ratio/high_mean": 0.0008375347533728927,
      "clip_ratio/low_mean": 0.0006306738359853625,
      "clip_ratio/low_min": 5.7487067806505365e-05,
      "clip_ratio/region_mean": 0.0014682086257380433,
      "epoch": 0.09043977390056525,
      "grad_norm": 0.1536380797624588,
      "learning_rate": 2e-07,
      "loss": -0.0093,
      "step": 969
    },
    {
      "clip_ratio/high_max": 0.002178411694330862,
      "clip_ratio/high_mean": 0.0007840615362511016,
      "clip_ratio/low_mean": 0.0005862502966920147,
      "clip_ratio/low_min": 4.741355496662436e-05,
      "clip_ratio/region_mean": 0.0013703118347621057,
      "epoch": 0.09053310700056583,
      "grad_norm": 0.1530255675315857,
      "learning_rate": 2e-07,
      "loss": 0.0087,
      "step": 970
    },
    {
      "clip_ratio/high_max": 0.0015990673746273387,
      "clip_ratio/high_mean": 0.000661393032714841,
      "clip_ratio/low_mean": 0.0007368735641648527,
      "clip_ratio/low_min": 7.986077889654553e-05,
      "clip_ratio/region_mean": 0.001398266620526556,
      "epoch": 0.09062644010056642,
      "grad_norm": 0.24544879794120789,
      "learning_rate": 2e-07,
      "loss": 0.0474,
      "step": 971
    },
    {
      "clip_ratio/high_max": 0.002109720906446455,
      "clip_ratio/high_mean": 0.0008268377505373792,
      "clip_ratio/low_mean": 0.0006866824141980032,
      "clip_ratio/low_min": 8.871440695656929e-05,
      "clip_ratio/region_mean": 0.0015135201974771917,
      "epoch": 0.090719773200567,
      "grad_norm": 0.18482695519924164,
      "learning_rate": 2e-07,
      "loss": -0.0128,
      "step": 972
    },
    {
      "clip_ratio/high_max": 0.0018456605030223727,
      "clip_ratio/high_mean": 0.0007896169390733121,
      "clip_ratio/low_mean": 0.0005981198628433049,
      "clip_ratio/low_min": 2.581577791715972e-05,
      "clip_ratio/region_mean": 0.0013877368401153944,
      "epoch": 0.09081310630056758,
      "grad_norm": 0.1758248209953308,
      "learning_rate": 2e-07,
      "loss": -0.0153,
      "step": 973
    },
    {
      "clip_ratio/high_max": 0.002118102536769584,
      "clip_ratio/high_mean": 0.0007917348539194791,
      "clip_ratio/low_mean": 0.0007140970428736182,
      "clip_ratio/low_min": 8.483541705572861e-05,
      "clip_ratio/region_mean": 0.0015058318895171396,
      "epoch": 0.09090643940056817,
      "grad_norm": 0.1552230417728424,
      "learning_rate": 2e-07,
      "loss": 0.0516,
      "step": 974
    },
    {
      "clip_ratio/high_max": 0.0017773111467249691,
      "clip_ratio/high_mean": 0.000749592878491967,
      "clip_ratio/low_mean": 0.0006149510190880392,
      "clip_ratio/low_min": 9.192528523271903e-06,
      "clip_ratio/region_mean": 0.0013645438884850591,
      "epoch": 0.09099977250056875,
      "grad_norm": 0.14404024183750153,
      "learning_rate": 2e-07,
      "loss": 0.0324,
      "step": 975
    },
    {
      "clip_ratio/high_max": 0.0019166903948644176,
      "clip_ratio/high_mean": 0.0008207044575101463,
      "clip_ratio/low_mean": 0.0006006146222716779,
      "clip_ratio/low_min": 3.535164341883501e-05,
      "clip_ratio/region_mean": 0.0014213190734153613,
      "epoch": 0.09109310560056934,
      "grad_norm": 0.15472853183746338,
      "learning_rate": 2e-07,
      "loss": -0.0117,
      "step": 976
    },
    {
      "clip_ratio/high_max": 0.0019044246728299186,
      "clip_ratio/high_mean": 0.0007340698757616337,
      "clip_ratio/low_mean": 0.0005961064734947286,
      "clip_ratio/low_min": 6.175304224598221e-05,
      "clip_ratio/region_mean": 0.0013301763756317087,
      "epoch": 0.09118643870056992,
      "grad_norm": 0.14880219101905823,
      "learning_rate": 2e-07,
      "loss": 0.0318,
      "step": 977
    },
    {
      "clip_ratio/high_max": 0.0018744719527603593,
      "clip_ratio/high_mean": 0.0007697995133639779,
      "clip_ratio/low_mean": 0.0006657738267676905,
      "clip_ratio/low_min": 5.0981372623937204e-05,
      "clip_ratio/region_mean": 0.0014355733255797531,
      "epoch": 0.0912797718005705,
      "grad_norm": 0.1656811535358429,
      "learning_rate": 2e-07,
      "loss": 0.0674,
      "step": 978
    },
    {
      "clip_ratio/high_max": 0.0016899645197554491,
      "clip_ratio/high_mean": 0.0007351214553636964,
      "clip_ratio/low_mean": 0.000683677448250819,
      "clip_ratio/low_min": 4.567634550767252e-05,
      "clip_ratio/region_mean": 0.0014187989218044095,
      "epoch": 0.09137310490057109,
      "grad_norm": 0.14926370978355408,
      "learning_rate": 2e-07,
      "loss": 0.0221,
      "step": 979
    },
    {
      "clip_ratio/high_max": 0.0017840222681115847,
      "clip_ratio/high_mean": 0.0007128581091819797,
      "clip_ratio/low_mean": 0.000630498865575646,
      "clip_ratio/low_min": 4.008272935607238e-05,
      "clip_ratio/region_mean": 0.0013433570056804456,
      "epoch": 0.09146643800057166,
      "grad_norm": 0.19268134236335754,
      "learning_rate": 2e-07,
      "loss": 0.0213,
      "step": 980
    },
    {
      "clip_ratio/high_max": 0.002111333727953024,
      "clip_ratio/high_mean": 0.000782511975558009,
      "clip_ratio/low_mean": 0.0007024190308584366,
      "clip_ratio/low_min": 1.5723269825684838e-05,
      "clip_ratio/region_mean": 0.0014849309955025092,
      "epoch": 0.09155977110057224,
      "grad_norm": 28.13702964782715,
      "learning_rate": 2e-07,
      "loss": 0.0576,
      "step": 981
    },
    {
      "clip_ratio/high_max": 0.0022352999440045096,
      "clip_ratio/high_mean": 0.0008797888294793665,
      "clip_ratio/low_mean": 0.0006075310084270313,
      "clip_ratio/low_min": 1.3507672520063352e-05,
      "clip_ratio/region_mean": 0.001487319816078525,
      "epoch": 0.09165310420057284,
      "grad_norm": 0.1435876339673996,
      "learning_rate": 2e-07,
      "loss": -0.0289,
      "step": 982
    },
    {
      "clip_ratio/high_max": 0.0019384174447623082,
      "clip_ratio/high_mean": 0.0007688148034503683,
      "clip_ratio/low_mean": 0.0006346751433738973,
      "clip_ratio/low_min": 1.4269406165112741e-05,
      "clip_ratio/region_mean": 0.0014034899431862868,
      "epoch": 0.09174643730057341,
      "grad_norm": 0.18740825355052948,
      "learning_rate": 2e-07,
      "loss": 0.0169,
      "step": 983
    },
    {
      "clip_ratio/high_max": 0.0017731858606566675,
      "clip_ratio/high_mean": 0.0006949472763153608,
      "clip_ratio/low_mean": 0.0005882402692805044,
      "clip_ratio/low_min": 3.688629385578679e-05,
      "clip_ratio/region_mean": 0.0012831875501433387,
      "epoch": 0.09183977040057399,
      "grad_norm": 0.1613827645778656,
      "learning_rate": 2e-07,
      "loss": 0.0085,
      "step": 984
    },
    {
      "clip_ratio/high_max": 0.0020426520059118047,
      "clip_ratio/high_mean": 0.0008113142121146666,
      "clip_ratio/low_mean": 0.0006762327111573541,
      "clip_ratio/low_min": 3.87813352062949e-05,
      "clip_ratio/region_mean": 0.0014875469387334306,
      "epoch": 0.09193310350057458,
      "grad_norm": 0.165876105427742,
      "learning_rate": 2e-07,
      "loss": 0.0427,
      "step": 985
    },
    {
      "clip_ratio/high_max": 0.002096603697282262,
      "clip_ratio/high_mean": 0.0008325785547640407,
      "clip_ratio/low_mean": 0.0006260246409510728,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014586031684302725,
      "epoch": 0.09202643660057516,
      "grad_norm": 0.1517435759305954,
      "learning_rate": 2e-07,
      "loss": 0.0032,
      "step": 986
    },
    {
      "clip_ratio/high_max": 0.001742502488923492,
      "clip_ratio/high_mean": 0.0006964906460780185,
      "clip_ratio/low_mean": 0.0006305426832113881,
      "clip_ratio/low_min": 3.177606595272664e-05,
      "clip_ratio/region_mean": 0.001327033340203343,
      "epoch": 0.09211976970057575,
      "grad_norm": 0.16995000839233398,
      "learning_rate": 2e-07,
      "loss": 0.0204,
      "step": 987
    },
    {
      "clip_ratio/high_max": 0.0018151459298678674,
      "clip_ratio/high_mean": 0.0007264230598593713,
      "clip_ratio/low_mean": 0.0007662876778340433,
      "clip_ratio/low_min": 5.200099622015841e-06,
      "clip_ratio/region_mean": 0.0014927107258699834,
      "epoch": 0.09221310280057633,
      "grad_norm": 0.1759267896413803,
      "learning_rate": 2e-07,
      "loss": 0.0761,
      "step": 988
    },
    {
      "clip_ratio/high_max": 0.0018290148946107365,
      "clip_ratio/high_mean": 0.000724421381164575,
      "clip_ratio/low_mean": 0.0007785979050822789,
      "clip_ratio/low_min": 9.506228798272787e-05,
      "clip_ratio/region_mean": 0.0015030193208076525,
      "epoch": 0.09230643590057691,
      "grad_norm": 0.17499110102653503,
      "learning_rate": 2e-07,
      "loss": 0.0818,
      "step": 989
    },
    {
      "clip_ratio/high_max": 0.0019003119887202047,
      "clip_ratio/high_mean": 0.0007314792746910825,
      "clip_ratio/low_mean": 0.0006544136304000858,
      "clip_ratio/low_min": 2.379772013227921e-05,
      "clip_ratio/region_mean": 0.0013858929160051048,
      "epoch": 0.0923997690005775,
      "grad_norm": 0.1619679480791092,
      "learning_rate": 2e-07,
      "loss": 0.0232,
      "step": 990
    },
    {
      "clip_ratio/high_max": 0.0018052139894280117,
      "clip_ratio/high_mean": 0.0007053463323245523,
      "clip_ratio/low_mean": 0.000662964037474012,
      "clip_ratio/low_min": 3.8276586565189064e-05,
      "clip_ratio/region_mean": 0.0013683103970834054,
      "epoch": 0.09249310210057808,
      "grad_norm": 0.17500336468219757,
      "learning_rate": 2e-07,
      "loss": 0.0354,
      "step": 991
    },
    {
      "clip_ratio/high_max": 0.0020604409037332516,
      "clip_ratio/high_mean": 0.0007385460885416251,
      "clip_ratio/low_mean": 0.0007158915032050572,
      "clip_ratio/low_min": 7.487781113013625e-05,
      "clip_ratio/region_mean": 0.0014544375844707247,
      "epoch": 0.09258643520057866,
      "grad_norm": 1.2302303314208984,
      "learning_rate": 2e-07,
      "loss": 0.0624,
      "step": 992
    },
    {
      "clip_ratio/high_max": 0.0020206824847264215,
      "clip_ratio/high_mean": 0.0007982680399436504,
      "clip_ratio/low_mean": 0.0007925058853288647,
      "clip_ratio/low_min": 0.00013087082334095612,
      "clip_ratio/region_mean": 0.0015907739398244303,
      "epoch": 0.09267976830057925,
      "grad_norm": 0.1701882779598236,
      "learning_rate": 2e-07,
      "loss": 0.0476,
      "step": 993
    },
    {
      "clip_ratio/high_max": 0.001924390446220059,
      "clip_ratio/high_mean": 0.0007263246188813355,
      "clip_ratio/low_mean": 0.0007194406643975526,
      "clip_ratio/low_min": 6.150864010123769e-05,
      "clip_ratio/region_mean": 0.0014457652687269729,
      "epoch": 0.09277310140057983,
      "grad_norm": 0.17477288842201233,
      "learning_rate": 2e-07,
      "loss": 0.0256,
      "step": 994
    },
    {
      "clip_ratio/high_max": 0.0016744578788348008,
      "clip_ratio/high_mean": 0.0007657353689864976,
      "clip_ratio/low_mean": 0.0006010684746797779,
      "clip_ratio/low_min": 3.2638732591294684e-05,
      "clip_ratio/region_mean": 0.0013668038627656642,
      "epoch": 0.09286643450058042,
      "grad_norm": 0.15913796424865723,
      "learning_rate": 2e-07,
      "loss": -0.0048,
      "step": 995
    },
    {
      "clip_ratio/high_max": 0.0017527682794025168,
      "clip_ratio/high_mean": 0.0007131708371161949,
      "clip_ratio/low_mean": 0.0008000614998309175,
      "clip_ratio/low_min": 5.500524912349647e-05,
      "clip_ratio/region_mean": 0.0015132323278521653,
      "epoch": 0.092959767600581,
      "grad_norm": 0.17258119583129883,
      "learning_rate": 2e-07,
      "loss": 0.0848,
      "step": 996
    },
    {
      "clip_ratio/high_max": 0.0018024387463810854,
      "clip_ratio/high_mean": 0.0007004461422184249,
      "clip_ratio/low_mean": 0.0006805818802604335,
      "clip_ratio/low_min": 2.8755463063134812e-05,
      "clip_ratio/region_mean": 0.0013810280506731942,
      "epoch": 0.09305310070058158,
      "grad_norm": 0.1578313410282135,
      "learning_rate": 2e-07,
      "loss": 0.0205,
      "step": 997
    },
    {
      "clip_ratio/high_max": 0.001954502578882966,
      "clip_ratio/high_mean": 0.0006651413123108796,
      "clip_ratio/low_mean": 0.0007015267970018613,
      "clip_ratio/low_min": 8.887940566637553e-06,
      "clip_ratio/region_mean": 0.0013666680933965836,
      "epoch": 0.09314643380058217,
      "grad_norm": 0.1596735715866089,
      "learning_rate": 2e-07,
      "loss": 0.0523,
      "step": 998
    },
    {
      "clip_ratio/high_max": 0.0016801849633338861,
      "clip_ratio/high_mean": 0.0007377110505331075,
      "clip_ratio/low_mean": 0.000856043277963181,
      "clip_ratio/low_min": 0.00011845880544569809,
      "clip_ratio/region_mean": 0.0015937543375912355,
      "epoch": 0.09323976690058275,
      "grad_norm": 0.15979592502117157,
      "learning_rate": 2e-07,
      "loss": 0.0379,
      "step": 999
    },
    {
      "clip_ratio/high_max": 0.0020866238337475806,
      "clip_ratio/high_mean": 0.0007494851415685844,
      "clip_ratio/low_mean": 0.0007071653726598015,
      "clip_ratio/low_min": 6.123017919890117e-05,
      "clip_ratio/region_mean": 0.00145665050149546,
      "epoch": 0.09333310000058333,
      "grad_norm": 0.16106240451335907,
      "learning_rate": 2e-07,
      "loss": 0.0436,
      "step": 1000
    },
    {
      "clip_ratio/high_max": 0.0016557607741560787,
      "clip_ratio/high_mean": 0.0006794122955398052,
      "clip_ratio/low_mean": 0.0008124851428874535,
      "clip_ratio/low_min": 0.00010920055774477078,
      "clip_ratio/region_mean": 0.0014918974229658488,
      "epoch": 0.09342643310058392,
      "grad_norm": 0.18092547357082367,
      "learning_rate": 2e-07,
      "loss": 0.0612,
      "step": 1001
    },
    {
      "clip_ratio/high_max": 0.0020951323549525114,
      "clip_ratio/high_mean": 0.0007371590199909406,
      "clip_ratio/low_mean": 0.0007138944347389042,
      "clip_ratio/low_min": 5.461011733132182e-05,
      "clip_ratio/region_mean": 0.0014510534674627706,
      "epoch": 0.0935197662005845,
      "grad_norm": 0.16525115072727203,
      "learning_rate": 2e-07,
      "loss": 0.0251,
      "step": 1002
    },
    {
      "clip_ratio/high_max": 0.0019485964076011442,
      "clip_ratio/high_mean": 0.0007863827977416804,
      "clip_ratio/low_mean": 0.0007287699718290241,
      "clip_ratio/low_min": 3.737904626177624e-05,
      "clip_ratio/region_mean": 0.0015151527732086834,
      "epoch": 0.09361309930058508,
      "grad_norm": 0.16803322732448578,
      "learning_rate": 2e-07,
      "loss": -0.0095,
      "step": 1003
    },
    {
      "clip_ratio/high_max": 0.0019915703451260924,
      "clip_ratio/high_mean": 0.0008003491057024803,
      "clip_ratio/low_mean": 0.0007947855947350035,
      "clip_ratio/low_min": 7.038913645374123e-05,
      "clip_ratio/region_mean": 0.0015951346904330421,
      "epoch": 0.09370643240058567,
      "grad_norm": 3.764392852783203,
      "learning_rate": 2e-07,
      "loss": 0.0487,
      "step": 1004
    },
    {
      "clip_ratio/high_max": 0.0020382414404593874,
      "clip_ratio/high_mean": 0.0007909505857242038,
      "clip_ratio/low_mean": 0.0007304107766685775,
      "clip_ratio/low_min": 2.398311517026741e-05,
      "clip_ratio/region_mean": 0.0015213614024105482,
      "epoch": 0.09379976550058625,
      "grad_norm": 0.16409805417060852,
      "learning_rate": 2e-07,
      "loss": 0.0088,
      "step": 1005
    },
    {
      "clip_ratio/high_max": 0.0018765366257866845,
      "clip_ratio/high_mean": 0.000726656991901109,
      "clip_ratio/low_mean": 0.0006164400983834639,
      "clip_ratio/low_min": 1.1461580470495392e-05,
      "clip_ratio/region_mean": 0.0013430970757326577,
      "epoch": 0.09389309860058684,
      "grad_norm": 0.15302081406116486,
      "learning_rate": 2e-07,
      "loss": 0.0313,
      "step": 1006
    },
    {
      "clip_ratio/high_max": 0.0017205978510901332,
      "clip_ratio/high_mean": 0.0007287298803930753,
      "clip_ratio/low_mean": 0.0007563193721580319,
      "clip_ratio/low_min": 4.80368830722e-05,
      "clip_ratio/region_mean": 0.0014850492698315065,
      "epoch": 0.09398643170058742,
      "grad_norm": 0.17403312027454376,
      "learning_rate": 2e-07,
      "loss": 0.0297,
      "step": 1007
    },
    {
      "clip_ratio/high_max": 0.0020732058510475326,
      "clip_ratio/high_mean": 0.0008300708550450508,
      "clip_ratio/low_mean": 0.0007659287148271687,
      "clip_ratio/low_min": 1.0414931239211e-05,
      "clip_ratio/region_mean": 0.001595999587152619,
      "epoch": 0.094079764800588,
      "grad_norm": 0.16306549310684204,
      "learning_rate": 2e-07,
      "loss": 0.0102,
      "step": 1008
    },
    {
      "clip_ratio/high_max": 0.0018988859956152737,
      "clip_ratio/high_mean": 0.0007440997032972518,
      "clip_ratio/low_mean": 0.0007344037239818135,
      "clip_ratio/low_min": 5.233309275354259e-05,
      "clip_ratio/region_mean": 0.0014785034290980548,
      "epoch": 0.09417309790058859,
      "grad_norm": 0.14677399396896362,
      "learning_rate": 2e-07,
      "loss": 0.0521,
      "step": 1009
    },
    {
      "clip_ratio/high_max": 0.0020322283598943613,
      "clip_ratio/high_mean": 0.0008096237033896614,
      "clip_ratio/low_mean": 0.0008060116597334854,
      "clip_ratio/low_min": 4.864781476499047e-05,
      "clip_ratio/region_mean": 0.0016156353667611256,
      "epoch": 0.09426643100058917,
      "grad_norm": 0.14751096069812775,
      "learning_rate": 2e-07,
      "loss": 0.0084,
      "step": 1010
    },
    {
      "clip_ratio/high_max": 0.0020679688423115294,
      "clip_ratio/high_mean": 0.0007567625016235979,
      "clip_ratio/low_mean": 0.0007551411108579487,
      "clip_ratio/low_min": 5.103127841721289e-05,
      "clip_ratio/region_mean": 0.0015119036106625572,
      "epoch": 0.09435976410058974,
      "grad_norm": 0.16788513958454132,
      "learning_rate": 2e-07,
      "loss": 0.078,
      "step": 1011
    },
    {
      "clip_ratio/high_max": 0.001995256494410569,
      "clip_ratio/high_mean": 0.0007811438445060048,
      "clip_ratio/low_mean": 0.0006943780554138357,
      "clip_ratio/low_min": 4.351900042820489e-05,
      "clip_ratio/region_mean": 0.0014755218944628723,
      "epoch": 0.09445309720059034,
      "grad_norm": 0.15616944432258606,
      "learning_rate": 2e-07,
      "loss": 0.012,
      "step": 1012
    },
    {
      "clip_ratio/high_max": 0.0021542187605518848,
      "clip_ratio/high_mean": 0.0008820974653644953,
      "clip_ratio/low_mean": 0.0007092805553838843,
      "clip_ratio/low_min": 1.4964683032303583e-05,
      "clip_ratio/region_mean": 0.0015913780589471571,
      "epoch": 0.09454643030059091,
      "grad_norm": 0.1882270723581314,
      "learning_rate": 2e-07,
      "loss": -0.0067,
      "step": 1013
    },
    {
      "clip_ratio/high_max": 0.0021625988119922113,
      "clip_ratio/high_mean": 0.0008375363977393135,
      "clip_ratio/low_mean": 0.0008140048921632115,
      "clip_ratio/low_min": 4.327881197241368e-05,
      "clip_ratio/region_mean": 0.0016515413153683767,
      "epoch": 0.09463976340059149,
      "grad_norm": 0.19054551422595978,
      "learning_rate": 2e-07,
      "loss": 0.0203,
      "step": 1014
    },
    {
      "clip_ratio/high_max": 0.0020210101502016187,
      "clip_ratio/high_mean": 0.0008207140981539851,
      "clip_ratio/low_mean": 0.0007094963348208694,
      "clip_ratio/low_min": 9.103827869694214e-05,
      "clip_ratio/region_mean": 0.0015302104657166637,
      "epoch": 0.09473309650059208,
      "grad_norm": 0.16385230422019958,
      "learning_rate": 2e-07,
      "loss": -0.0076,
      "step": 1015
    },
    {
      "clip_ratio/high_max": 0.0017702915502013639,
      "clip_ratio/high_mean": 0.000703186757164076,
      "clip_ratio/low_mean": 0.0007607234929309925,
      "clip_ratio/low_min": 4.91570235681138e-05,
      "clip_ratio/region_mean": 0.001463910230086185,
      "epoch": 0.09482642960059266,
      "grad_norm": 0.1446237415075302,
      "learning_rate": 2e-07,
      "loss": 0.0382,
      "step": 1016
    },
    {
      "clip_ratio/high_max": 0.0020887565697194077,
      "clip_ratio/high_mean": 0.0007949076889417483,
      "clip_ratio/low_mean": 0.0008456218329229159,
      "clip_ratio/low_min": 9.0389453816897e-05,
      "clip_ratio/region_mean": 0.0016405294918513391,
      "epoch": 0.09491976270059325,
      "grad_norm": 0.19028033316135406,
      "learning_rate": 2e-07,
      "loss": 0.0384,
      "step": 1017
    },
    {
      "clip_ratio/high_max": 0.0022450946125900373,
      "clip_ratio/high_mean": 0.000900813869520789,
      "clip_ratio/low_mean": 0.0007954278171382612,
      "clip_ratio/low_min": 3.768257647607243e-05,
      "clip_ratio/region_mean": 0.0016962417139438912,
      "epoch": 0.09501309580059383,
      "grad_norm": 0.16988860070705414,
      "learning_rate": 2e-07,
      "loss": -0.0293,
      "step": 1018
    },
    {
      "clip_ratio/high_max": 0.002386932697845623,
      "clip_ratio/high_mean": 0.0009201758530252846,
      "clip_ratio/low_mean": 0.0007499026087316452,
      "clip_ratio/low_min": 1.173488544736756e-05,
      "clip_ratio/region_mean": 0.0016700784326530993,
      "epoch": 0.09510642890059441,
      "grad_norm": 0.16819550096988678,
      "learning_rate": 2e-07,
      "loss": 0.0309,
      "step": 1019
    },
    {
      "clip_ratio/high_max": 0.0018833024332707282,
      "clip_ratio/high_mean": 0.0007875569090174395,
      "clip_ratio/low_mean": 0.0006861471774755046,
      "clip_ratio/low_min": 5.8686335250968114e-05,
      "clip_ratio/region_mean": 0.0014737041092303116,
      "epoch": 0.095199762000595,
      "grad_norm": 0.17758208513259888,
      "learning_rate": 2e-07,
      "loss": -0.0057,
      "step": 1020
    },
    {
      "clip_ratio/high_max": 0.002236204112705309,
      "clip_ratio/high_mean": 0.0009477347593929153,
      "clip_ratio/low_mean": 0.0007580286746815545,
      "clip_ratio/low_min": 3.737293081940152e-05,
      "clip_ratio/region_mean": 0.0017057634468073957,
      "epoch": 0.09529309510059558,
      "grad_norm": 0.19571329653263092,
      "learning_rate": 2e-07,
      "loss": -0.005,
      "step": 1021
    },
    {
      "clip_ratio/high_max": 0.0019461091578705236,
      "clip_ratio/high_mean": 0.0007506560923502548,
      "clip_ratio/low_mean": 0.0007778410472383257,
      "clip_ratio/low_min": 3.863439451379236e-05,
      "clip_ratio/region_mean": 0.0015284971450455487,
      "epoch": 0.09538642820059616,
      "grad_norm": 0.1953987181186676,
      "learning_rate": 2e-07,
      "loss": 0.0273,
      "step": 1022
    },
    {
      "clip_ratio/high_max": 0.0021502482049982063,
      "clip_ratio/high_mean": 0.0008394458454858977,
      "clip_ratio/low_mean": 0.0006919594370629056,
      "clip_ratio/low_min": 2.0791749193449505e-05,
      "clip_ratio/region_mean": 0.0015314052361645736,
      "epoch": 0.09547976130059675,
      "grad_norm": 0.16121304035186768,
      "learning_rate": 2e-07,
      "loss": 0.0185,
      "step": 1023
    },
    {
      "clip_ratio/high_max": 0.002215524022176396,
      "clip_ratio/high_mean": 0.0008673295287735527,
      "clip_ratio/low_mean": 0.0008442235412076116,
      "clip_ratio/low_min": 3.6828641896136105e-05,
      "clip_ratio/region_mean": 0.0017115530718001537,
      "epoch": 0.09557309440059733,
      "grad_norm": 0.18938623368740082,
      "learning_rate": 2e-07,
      "loss": 0.0186,
      "step": 1024
    },
    {
      "clip_ratio/high_max": 0.0014378484320332063,
      "clip_ratio/high_mean": 0.0005517959430108021,
      "clip_ratio/low_mean": 0.0005131368152433424,
      "clip_ratio/low_min": 2.5095361706917174e-05,
      "clip_ratio/region_mean": 0.0010649327632563654,
      "completions/clipped_ratio": 0.016357421875,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4079.0,
      "completions/mean_length": 688.0979614257812,
      "completions/mean_terminated_length": 631.4264526367188,
      "completions/min_length": 83.0,
      "completions/min_terminated_length": 83.0,
      "epoch": 0.09566642750059791,
      "grad_norm": 0.14708003401756287,
      "learning_rate": 2e-07,
      "loss": 0.0151,
      "num_tokens": 766251397.0,
      "reward": 0.5881609320640564,
      "reward_std": 0.18022732436656952,
      "rewards/simpleverify_reward/mean": 0.5881609320640564,
      "rewards/simpleverify_reward/std": 0.49216827750205994,
      "step": 1025
    },
    {
      "clip_ratio/high_max": 0.0016916839849727694,
      "clip_ratio/high_mean": 0.0006159574913908727,
      "clip_ratio/low_mean": 0.0005496037592820358,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0011655612179310992,
      "epoch": 0.0957597606005985,
      "grad_norm": 0.13866794109344482,
      "learning_rate": 2e-07,
      "loss": 0.0299,
      "step": 1026
    },
    {
      "clip_ratio/high_max": 0.001847016901592724,
      "clip_ratio/high_mean": 0.0006025774873705814,
      "clip_ratio/low_mean": 0.0005515253305929946,
      "clip_ratio/low_min": 2.3036706807033625e-05,
      "clip_ratio/region_mean": 0.0011541028252395336,
      "epoch": 0.09585309370059908,
      "grad_norm": 0.16881100833415985,
      "learning_rate": 2e-07,
      "loss": 0.026,
      "step": 1027
    },
    {
      "clip_ratio/high_max": 0.0020663442264776677,
      "clip_ratio/high_mean": 0.0007692217004660051,
      "clip_ratio/low_mean": 0.000668367174512241,
      "clip_ratio/low_min": 9.465446510148467e-05,
      "clip_ratio/region_mean": 0.001437588878616225,
      "epoch": 0.09594642680059967,
      "grad_norm": 0.17618006467819214,
      "learning_rate": 2e-07,
      "loss": 0.0337,
      "step": 1028
    },
    {
      "clip_ratio/high_max": 0.0014562933647539467,
      "clip_ratio/high_mean": 0.0006174530481075635,
      "clip_ratio/low_mean": 0.000542192741704639,
      "clip_ratio/low_min": 3.596656915760832e-05,
      "clip_ratio/region_mean": 0.0011596457989071496,
      "epoch": 0.09603975990060025,
      "grad_norm": 0.1466275453567505,
      "learning_rate": 2e-07,
      "loss": 0.0063,
      "step": 1029
    },
    {
      "clip_ratio/high_max": 0.0014505838953482453,
      "clip_ratio/high_mean": 0.0005131844172865385,
      "clip_ratio/low_mean": 0.000622073781414656,
      "clip_ratio/low_min": 0.00011859360529342666,
      "clip_ratio/region_mean": 0.0011352581896062475,
      "epoch": 0.09613309300060083,
      "grad_norm": 0.16999980807304382,
      "learning_rate": 2e-07,
      "loss": 0.0387,
      "step": 1030
    },
    {
      "clip_ratio/high_max": 0.0016901072849577758,
      "clip_ratio/high_mean": 0.0005895062386116479,
      "clip_ratio/low_mean": 0.0005215560777287465,
      "clip_ratio/low_min": 3.083405044890242e-05,
      "clip_ratio/region_mean": 0.0011110623308923095,
      "epoch": 0.09622642610060142,
      "grad_norm": 0.14095626771450043,
      "learning_rate": 2e-07,
      "loss": 0.0006,
      "step": 1031
    },
    {
      "clip_ratio/high_max": 0.0016323715353792068,
      "clip_ratio/high_mean": 0.0005746517363149906,
      "clip_ratio/low_mean": 0.0006463962690759217,
      "clip_ratio/low_min": 3.839696910290513e-05,
      "clip_ratio/region_mean": 0.0012210479653731454,
      "epoch": 0.096319759200602,
      "grad_norm": 0.15852895379066467,
      "learning_rate": 2e-07,
      "loss": 0.0734,
      "step": 1032
    },
    {
      "clip_ratio/high_max": 0.0015259204265021253,
      "clip_ratio/high_mean": 0.0005827600234624697,
      "clip_ratio/low_mean": 0.0006413541332221939,
      "clip_ratio/low_min": 5.0354283303022385e-05,
      "clip_ratio/region_mean": 0.0012241141666891053,
      "epoch": 0.09641309230060258,
      "grad_norm": 0.15097637474536896,
      "learning_rate": 2e-07,
      "loss": 0.0675,
      "step": 1033
    },
    {
      "clip_ratio/high_max": 0.0020330803672550246,
      "clip_ratio/high_mean": 0.0007633451423316728,
      "clip_ratio/low_mean": 0.000565596298656601,
      "clip_ratio/low_min": 5.0420063416822813e-05,
      "clip_ratio/region_mean": 0.0013289414491737261,
      "epoch": 0.09650642540060317,
      "grad_norm": 0.1422506868839264,
      "learning_rate": 2e-07,
      "loss": 0.0398,
      "step": 1034
    },
    {
      "clip_ratio/high_max": 0.0015215708226605784,
      "clip_ratio/high_mean": 0.0006347874132188736,
      "clip_ratio/low_mean": 0.0005298105015754118,
      "clip_ratio/low_min": 2.170218613173347e-05,
      "clip_ratio/region_mean": 0.0011645979102468118,
      "epoch": 0.09659975850060375,
      "grad_norm": 0.18003129959106445,
      "learning_rate": 2e-07,
      "loss": 0.0208,
      "step": 1035
    },
    {
      "clip_ratio/high_max": 0.0017026555506163277,
      "clip_ratio/high_mean": 0.0006326746042759623,
      "clip_ratio/low_mean": 0.0005475996194945765,
      "clip_ratio/low_min": 4.200718103675172e-05,
      "clip_ratio/region_mean": 0.0011802742155850865,
      "epoch": 0.09669309160060433,
      "grad_norm": 0.15974678099155426,
      "learning_rate": 2e-07,
      "loss": 0.0267,
      "step": 1036
    },
    {
      "clip_ratio/high_max": 0.0016561401025683153,
      "clip_ratio/high_mean": 0.00062518098820874,
      "clip_ratio/low_mean": 0.0005852482408954529,
      "clip_ratio/low_min": 1.565239108458627e-05,
      "clip_ratio/region_mean": 0.0012104292254662141,
      "epoch": 0.09678642470060492,
      "grad_norm": 0.14771315455436707,
      "learning_rate": 2e-07,
      "loss": 0.0343,
      "step": 1037
    },
    {
      "clip_ratio/high_max": 0.0015022968254925217,
      "clip_ratio/high_mean": 0.0005291304896672955,
      "clip_ratio/low_mean": 0.0005519391706911847,
      "clip_ratio/low_min": 3.993748669017805e-05,
      "clip_ratio/region_mean": 0.0010810696403495967,
      "epoch": 0.0968797578006055,
      "grad_norm": 0.1412869542837143,
      "learning_rate": 2e-07,
      "loss": 0.0392,
      "step": 1038
    },
    {
      "clip_ratio/high_max": 0.0014179872414388228,
      "clip_ratio/high_mean": 0.0005276464544294868,
      "clip_ratio/low_mean": 0.0006172272169351345,
      "clip_ratio/low_min": 1.4540123629558366e-05,
      "clip_ratio/region_mean": 0.001144873684097547,
      "epoch": 0.09697309090060609,
      "grad_norm": 0.1414092481136322,
      "learning_rate": 2e-07,
      "loss": 0.018,
      "step": 1039
    },
    {
      "clip_ratio/high_max": 0.0020093211278435774,
      "clip_ratio/high_mean": 0.0007387639780063182,
      "clip_ratio/low_mean": 0.0006546789954882115,
      "clip_ratio/low_min": 3.0385104764718562e-05,
      "clip_ratio/region_mean": 0.0013934429716755403,
      "epoch": 0.09706642400060667,
      "grad_norm": 3.05383038520813,
      "learning_rate": 2e-07,
      "loss": 0.0136,
      "step": 1040
    },
    {
      "clip_ratio/high_max": 0.0016524317688890733,
      "clip_ratio/high_mean": 0.0006180343461892335,
      "clip_ratio/low_mean": 0.0005607486473309109,
      "clip_ratio/low_min": 3.5719126572075766e-05,
      "clip_ratio/region_mean": 0.0011787830226239748,
      "epoch": 0.09715975710060724,
      "grad_norm": 0.1433306336402893,
      "learning_rate": 2e-07,
      "loss": 0.0271,
      "step": 1041
    },
    {
      "clip_ratio/high_max": 0.001474804103054339,
      "clip_ratio/high_mean": 0.0005959991613053717,
      "clip_ratio/low_mean": 0.0005221336359682027,
      "clip_ratio/low_min": 5.6562392273917794e-05,
      "clip_ratio/region_mean": 0.0011181327827216592,
      "epoch": 0.09725309020060784,
      "grad_norm": 0.15571217238903046,
      "learning_rate": 2e-07,
      "loss": 0.0555,
      "step": 1042
    },
    {
      "clip_ratio/high_max": 0.0019341195475135464,
      "clip_ratio/high_mean": 0.0007099760241544573,
      "clip_ratio/low_mean": 0.0006023020487191388,
      "clip_ratio/low_min": 3.740999909496168e-05,
      "clip_ratio/region_mean": 0.0013122780510457233,
      "epoch": 0.09734642330060841,
      "grad_norm": 0.15605802834033966,
      "learning_rate": 2e-07,
      "loss": 0.0397,
      "step": 1043
    },
    {
      "clip_ratio/high_max": 0.0014168736597639509,
      "clip_ratio/high_mean": 0.0006161271030578064,
      "clip_ratio/low_mean": 0.0005508987687790068,
      "clip_ratio/low_min": 2.1357391233323142e-05,
      "clip_ratio/region_mean": 0.0011670258463709615,
      "epoch": 0.09743975640060899,
      "grad_norm": 0.1509365737438202,
      "learning_rate": 2e-07,
      "loss": 0.0231,
      "step": 1044
    },
    {
      "clip_ratio/high_max": 0.0014546292750310386,
      "clip_ratio/high_mean": 0.000653802472697862,
      "clip_ratio/low_mean": 0.000603642183705233,
      "clip_ratio/low_min": 2.830098856065888e-05,
      "clip_ratio/region_mean": 0.001257444659131579,
      "epoch": 0.09753308950060958,
      "grad_norm": 0.1463029384613037,
      "learning_rate": 2e-07,
      "loss": 0.0454,
      "step": 1045
    },
    {
      "clip_ratio/high_max": 0.0015412387001561,
      "clip_ratio/high_mean": 0.0006065310626581777,
      "clip_ratio/low_mean": 0.000608464297329192,
      "clip_ratio/low_min": 3.5031098377658054e-05,
      "clip_ratio/region_mean": 0.001214995347254444,
      "epoch": 0.09762642260061016,
      "grad_norm": 0.14445355534553528,
      "learning_rate": 2e-07,
      "loss": 0.0199,
      "step": 1046
    },
    {
      "clip_ratio/high_max": 0.00156498274373007,
      "clip_ratio/high_mean": 0.0006398326586349867,
      "clip_ratio/low_mean": 0.0006145226343505783,
      "clip_ratio/low_min": 2.3263812181539834e-05,
      "clip_ratio/region_mean": 0.0012543552911665756,
      "epoch": 0.09771975570061076,
      "grad_norm": 0.1488150656223297,
      "learning_rate": 2e-07,
      "loss": 0.0458,
      "step": 1047
    },
    {
      "clip_ratio/high_max": 0.001422135090251686,
      "clip_ratio/high_mean": 0.0005962453124084277,
      "clip_ratio/low_mean": 0.0006148298289190279,
      "clip_ratio/low_min": 3.244934441681835e-05,
      "clip_ratio/region_mean": 0.0012110751304135192,
      "epoch": 0.09781308880061133,
      "grad_norm": 0.13644738495349884,
      "learning_rate": 2e-07,
      "loss": -0.0012,
      "step": 1048
    },
    {
      "clip_ratio/high_max": 0.0013715420027438086,
      "clip_ratio/high_mean": 0.0005221882256591925,
      "clip_ratio/low_mean": 0.0005905131720282952,
      "clip_ratio/low_min": 3.7213456380413845e-05,
      "clip_ratio/region_mean": 0.001112701396777993,
      "epoch": 0.09790642190061191,
      "grad_norm": 0.15375658869743347,
      "learning_rate": 2e-07,
      "loss": 0.0334,
      "step": 1049
    },
    {
      "clip_ratio/high_max": 0.00188410504051717,
      "clip_ratio/high_mean": 0.0006943056087038713,
      "clip_ratio/low_mean": 0.0006372497073243721,
      "clip_ratio/low_min": 6.70334502501646e-05,
      "clip_ratio/region_mean": 0.0013315552969288547,
      "epoch": 0.0979997550006125,
      "grad_norm": 0.16149811446666718,
      "learning_rate": 2e-07,
      "loss": 0.0166,
      "step": 1050
    },
    {
      "clip_ratio/high_max": 0.0018606667290441692,
      "clip_ratio/high_mean": 0.0006596406346943695,
      "clip_ratio/low_mean": 0.0005451956212709774,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012048362514178734,
      "epoch": 0.09809308810061308,
      "grad_norm": 0.1412322074174881,
      "learning_rate": 2e-07,
      "loss": 0.0422,
      "step": 1051
    },
    {
      "clip_ratio/high_max": 0.0019422017503529787,
      "clip_ratio/high_mean": 0.0007313859550777124,
      "clip_ratio/low_mean": 0.0006135300377536623,
      "clip_ratio/low_min": 6.0183759160281625e-05,
      "clip_ratio/region_mean": 0.0013449159487208817,
      "epoch": 0.09818642120061366,
      "grad_norm": 0.13570831716060638,
      "learning_rate": 2e-07,
      "loss": 0.0228,
      "step": 1052
    },
    {
      "clip_ratio/high_max": 0.0017667753782006912,
      "clip_ratio/high_mean": 0.0007219247872853884,
      "clip_ratio/low_mean": 0.000667163996695308,
      "clip_ratio/low_min": 4.954661289957585e-05,
      "clip_ratio/region_mean": 0.0013890887676097918,
      "epoch": 0.09827975430061425,
      "grad_norm": 0.1552492082118988,
      "learning_rate": 2e-07,
      "loss": 0.0316,
      "step": 1053
    },
    {
      "clip_ratio/high_max": 0.0016986169466690626,
      "clip_ratio/high_mean": 0.0007095016753737582,
      "clip_ratio/low_mean": 0.0005949293345111073,
      "clip_ratio/low_min": 4.4419772166293114e-05,
      "clip_ratio/region_mean": 0.0013044310398981906,
      "epoch": 0.09837308740061483,
      "grad_norm": 0.15365970134735107,
      "learning_rate": 2e-07,
      "loss": 0.0154,
      "step": 1054
    },
    {
      "clip_ratio/high_max": 0.0015401641285279766,
      "clip_ratio/high_mean": 0.0005732785207328561,
      "clip_ratio/low_mean": 0.0005696142725355458,
      "clip_ratio/low_min": 9.837872312346008e-06,
      "clip_ratio/region_mean": 0.0011428928119130433,
      "epoch": 0.09846642050061541,
      "grad_norm": 0.1418396532535553,
      "learning_rate": 2e-07,
      "loss": 0.0677,
      "step": 1055
    },
    {
      "clip_ratio/high_max": 0.0017675054623396136,
      "clip_ratio/high_mean": 0.0007238244215841405,
      "clip_ratio/low_mean": 0.000682338139085914,
      "clip_ratio/low_min": 1.3356760973692872e-05,
      "clip_ratio/region_mean": 0.001406162580678938,
      "epoch": 0.098559753600616,
      "grad_norm": 0.1694512516260147,
      "learning_rate": 2e-07,
      "loss": 0.0506,
      "step": 1056
    },
    {
      "clip_ratio/high_max": 0.001602050873771077,
      "clip_ratio/high_mean": 0.0006504069660877576,
      "clip_ratio/low_mean": 0.0007078447015373968,
      "clip_ratio/low_min": 3.176004975102842e-05,
      "clip_ratio/region_mean": 0.0013582516767201014,
      "epoch": 0.09865308670061658,
      "grad_norm": 0.1421012580394745,
      "learning_rate": 2e-07,
      "loss": 0.0602,
      "step": 1057
    },
    {
      "clip_ratio/high_max": 0.0018375961171841482,
      "clip_ratio/high_mean": 0.0006802187417633832,
      "clip_ratio/low_mean": 0.0006417808872356545,
      "clip_ratio/low_min": 6.562881571881007e-05,
      "clip_ratio/region_mean": 0.00132199962172308,
      "epoch": 0.09874641980061717,
      "grad_norm": 0.15694449841976166,
      "learning_rate": 2e-07,
      "loss": 0.0567,
      "step": 1058
    },
    {
      "clip_ratio/high_max": 0.0018998623345396481,
      "clip_ratio/high_mean": 0.0007419255198328756,
      "clip_ratio/low_mean": 0.0005810023740195902,
      "clip_ratio/low_min": 3.517110508255428e-05,
      "clip_ratio/region_mean": 0.0013229279247752856,
      "epoch": 0.09883975290061775,
      "grad_norm": 0.15664304792881012,
      "learning_rate": 2e-07,
      "loss": -0.0069,
      "step": 1059
    },
    {
      "clip_ratio/high_max": 0.0015013605880085379,
      "clip_ratio/high_mean": 0.0005992483238514978,
      "clip_ratio/low_mean": 0.0006321663640846964,
      "clip_ratio/low_min": 4.217208243062487e-05,
      "clip_ratio/region_mean": 0.001231414709764067,
      "epoch": 0.09893308600061833,
      "grad_norm": 0.1460362821817398,
      "learning_rate": 2e-07,
      "loss": 0.0253,
      "step": 1060
    },
    {
      "clip_ratio/high_max": 0.0017318265308858827,
      "clip_ratio/high_mean": 0.0006700886997350608,
      "clip_ratio/low_mean": 0.0005704220639017876,
      "clip_ratio/low_min": 1.4589169040846173e-05,
      "clip_ratio/region_mean": 0.0012405107445374597,
      "epoch": 0.09902641910061892,
      "grad_norm": 0.14607422053813934,
      "learning_rate": 2e-07,
      "loss": -0.0176,
      "step": 1061
    },
    {
      "clip_ratio/high_max": 0.0013816305981890764,
      "clip_ratio/high_mean": 0.0005875156748516019,
      "clip_ratio/low_mean": 0.0006704420693495194,
      "clip_ratio/low_min": 1.3275275705382228e-05,
      "clip_ratio/region_mean": 0.0012579577305587009,
      "epoch": 0.0991197522006195,
      "grad_norm": 0.15838906168937683,
      "learning_rate": 2e-07,
      "loss": 0.0446,
      "step": 1062
    },
    {
      "clip_ratio/high_max": 0.0018588349339552224,
      "clip_ratio/high_mean": 0.0006482922017312376,
      "clip_ratio/low_mean": 0.0005395031039370224,
      "clip_ratio/low_min": 3.416464733163593e-05,
      "clip_ratio/region_mean": 0.001187795296573313,
      "epoch": 0.09921308530062008,
      "grad_norm": 0.14904262125492096,
      "learning_rate": 2e-07,
      "loss": 0.0281,
      "step": 1063
    },
    {
      "clip_ratio/high_max": 0.0014360553868755233,
      "clip_ratio/high_mean": 0.0005475255038618343,
      "clip_ratio/low_mean": 0.0005829582687510992,
      "clip_ratio/low_min": 4.5051278902974445e-05,
      "clip_ratio/region_mean": 0.0011304837571515236,
      "epoch": 0.09930641840062067,
      "grad_norm": 0.14753474295139313,
      "learning_rate": 2e-07,
      "loss": 0.0431,
      "step": 1064
    },
    {
      "clip_ratio/high_max": 0.0017909514353959821,
      "clip_ratio/high_mean": 0.0007480057265638607,
      "clip_ratio/low_mean": 0.0005338946066331118,
      "clip_ratio/low_min": 7.827175977581646e-06,
      "clip_ratio/region_mean": 0.001281900335015962,
      "epoch": 0.09939975150062125,
      "grad_norm": 0.14933542907238007,
      "learning_rate": 2e-07,
      "loss": 0.0148,
      "step": 1065
    },
    {
      "clip_ratio/high_max": 0.0015598027457599528,
      "clip_ratio/high_mean": 0.0005854885503140395,
      "clip_ratio/low_mean": 0.0006075235323805828,
      "clip_ratio/low_min": 4.125160376133863e-05,
      "clip_ratio/region_mean": 0.0011930120635952335,
      "epoch": 0.09949308460062183,
      "grad_norm": 0.15162643790245056,
      "learning_rate": 2e-07,
      "loss": 0.0148,
      "step": 1066
    },
    {
      "clip_ratio/high_max": 0.0018379451939836144,
      "clip_ratio/high_mean": 0.0007593542541144416,
      "clip_ratio/low_mean": 0.00048340085140807787,
      "clip_ratio/low_min": 2.776235487544909e-05,
      "clip_ratio/region_mean": 0.001242755082785152,
      "epoch": 0.09958641770062242,
      "grad_norm": 0.15261171758174896,
      "learning_rate": 2e-07,
      "loss": -0.0019,
      "step": 1067
    },
    {
      "clip_ratio/high_max": 0.0018035454377240967,
      "clip_ratio/high_mean": 0.0007400907215924235,
      "clip_ratio/low_mean": 0.0006519323096654261,
      "clip_ratio/low_min": 6.042232962499838e-05,
      "clip_ratio/region_mean": 0.0013920230449002702,
      "epoch": 0.099679750800623,
      "grad_norm": 0.15740974247455597,
      "learning_rate": 2e-07,
      "loss": 0.0137,
      "step": 1068
    },
    {
      "clip_ratio/high_max": 0.0015695099282311276,
      "clip_ratio/high_mean": 0.0006296430733527814,
      "clip_ratio/low_mean": 0.0005989285436953651,
      "clip_ratio/low_min": 1.1606313819356728e-05,
      "clip_ratio/region_mean": 0.0012285716184123885,
      "epoch": 0.09977308390062359,
      "grad_norm": 0.14155597984790802,
      "learning_rate": 2e-07,
      "loss": 0.019,
      "step": 1069
    },
    {
      "clip_ratio/high_max": 0.0012968215960427187,
      "clip_ratio/high_mean": 0.0005502943440660601,
      "clip_ratio/low_mean": 0.0005429208395071328,
      "clip_ratio/low_min": 1.1134865417261608e-05,
      "clip_ratio/region_mean": 0.001093215174478246,
      "epoch": 0.09986641700062417,
      "grad_norm": 0.2143881767988205,
      "learning_rate": 2e-07,
      "loss": 0.1044,
      "step": 1070
    },
    {
      "clip_ratio/high_max": 0.0017457262438256294,
      "clip_ratio/high_mean": 0.0007524430911871605,
      "clip_ratio/low_mean": 0.0005688552232641086,
      "clip_ratio/low_min": 6.22768475295743e-05,
      "clip_ratio/region_mean": 0.001321298292168649,
      "epoch": 0.09995975010062474,
      "grad_norm": 0.15124933421611786,
      "learning_rate": 2e-07,
      "loss": -0.0014,
      "step": 1071
    },
    {
      "clip_ratio/high_max": 0.0016318767447955906,
      "clip_ratio/high_mean": 0.0006549804020323791,
      "clip_ratio/low_mean": 0.0006409282141248696,
      "clip_ratio/low_min": 2.285254595335573e-05,
      "clip_ratio/region_mean": 0.0012959085797774605,
      "epoch": 0.10005308320062534,
      "grad_norm": 0.16364982724189758,
      "learning_rate": 2e-07,
      "loss": 0.0451,
      "step": 1072
    },
    {
      "clip_ratio/high_max": 0.0016330828293575905,
      "clip_ratio/high_mean": 0.0006716552852594759,
      "clip_ratio/low_mean": 0.0005879046075278893,
      "clip_ratio/low_min": 1.1852835086756386e-05,
      "clip_ratio/region_mean": 0.0012595598818734288,
      "epoch": 0.10014641630062592,
      "grad_norm": 0.15425899624824524,
      "learning_rate": 2e-07,
      "loss": -0.0054,
      "step": 1073
    },
    {
      "clip_ratio/high_max": 0.0015259459360095207,
      "clip_ratio/high_mean": 0.0005894996120332507,
      "clip_ratio/low_mean": 0.0005918595070397714,
      "clip_ratio/low_min": 3.4677268558880314e-05,
      "clip_ratio/region_mean": 0.0011813591518148314,
      "epoch": 0.1002397494006265,
      "grad_norm": 0.17031630873680115,
      "learning_rate": 2e-07,
      "loss": 0.0419,
      "step": 1074
    },
    {
      "clip_ratio/high_max": 0.0016506117572134826,
      "clip_ratio/high_mean": 0.000685876505485794,
      "clip_ratio/low_mean": 0.0005948870493739378,
      "clip_ratio/low_min": 9.391915136802709e-05,
      "clip_ratio/region_mean": 0.0012807635539502371,
      "epoch": 0.10033308250062709,
      "grad_norm": 0.15664374828338623,
      "learning_rate": 2e-07,
      "loss": -0.0001,
      "step": 1075
    },
    {
      "clip_ratio/high_max": 0.0019362687889952213,
      "clip_ratio/high_mean": 0.0007669846654607682,
      "clip_ratio/low_mean": 0.0006705073956254637,
      "clip_ratio/low_min": 4.813044870388694e-05,
      "clip_ratio/region_mean": 0.0014374920720001683,
      "epoch": 0.10042641560062766,
      "grad_norm": 0.16379493474960327,
      "learning_rate": 2e-07,
      "loss": -0.0203,
      "step": 1076
    },
    {
      "clip_ratio/high_max": 0.0015932394926494453,
      "clip_ratio/high_mean": 0.0006472947925431072,
      "clip_ratio/low_mean": 0.0006747439892933471,
      "clip_ratio/low_min": 5.611099550151266e-05,
      "clip_ratio/region_mean": 0.0013220387845649384,
      "epoch": 0.10051974870062824,
      "grad_norm": 0.1649751365184784,
      "learning_rate": 2e-07,
      "loss": 0.0826,
      "step": 1077
    },
    {
      "clip_ratio/high_max": 0.0016202120714297052,
      "clip_ratio/high_mean": 0.0007010794843154144,
      "clip_ratio/low_mean": 0.000568507890420733,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012695873774646316,
      "epoch": 0.10061308180062883,
      "grad_norm": 0.1702614277601242,
      "learning_rate": 2e-07,
      "loss": 0.0217,
      "step": 1078
    },
    {
      "clip_ratio/high_max": 0.001876426969829481,
      "clip_ratio/high_mean": 0.0006912707776791649,
      "clip_ratio/low_mean": 0.0008076408494162024,
      "clip_ratio/low_min": 8.027134299481986e-05,
      "clip_ratio/region_mean": 0.0014989116534707136,
      "epoch": 0.10070641490062941,
      "grad_norm": 0.21598941087722778,
      "learning_rate": 2e-07,
      "loss": 0.0417,
      "step": 1079
    },
    {
      "clip_ratio/high_max": 0.0017965964398172218,
      "clip_ratio/high_mean": 0.000657634476738167,
      "clip_ratio/low_mean": 0.0006064373192202765,
      "clip_ratio/low_min": 2.0789444533875212e-05,
      "clip_ratio/region_mean": 0.0012640717868634965,
      "epoch": 0.10079974800063,
      "grad_norm": 0.14918962121009827,
      "learning_rate": 2e-07,
      "loss": 0.015,
      "step": 1080
    },
    {
      "clip_ratio/high_max": 0.0017111210108851083,
      "clip_ratio/high_mean": 0.0006135367730166763,
      "clip_ratio/low_mean": 0.0006410542355297366,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012545910285552964,
      "epoch": 0.10089308110063058,
      "grad_norm": 0.1647917479276657,
      "learning_rate": 2e-07,
      "loss": 0.0282,
      "step": 1081
    },
    {
      "clip_ratio/high_max": 0.0015425382734974846,
      "clip_ratio/high_mean": 0.0006584089769603452,
      "clip_ratio/low_mean": 0.0005921895553910872,
      "clip_ratio/low_min": 4.2094071432075e-05,
      "clip_ratio/region_mean": 0.0012505985541793052,
      "epoch": 0.10098641420063116,
      "grad_norm": 0.15945541858673096,
      "learning_rate": 2e-07,
      "loss": 0.0432,
      "step": 1082
    },
    {
      "clip_ratio/high_max": 0.001761048817570554,
      "clip_ratio/high_mean": 0.0007012805508566089,
      "clip_ratio/low_mean": 0.0007137244738260051,
      "clip_ratio/low_min": 2.256865263916552e-05,
      "clip_ratio/region_mean": 0.001415005033777561,
      "epoch": 0.10107974730063175,
      "grad_norm": 0.14704836905002594,
      "learning_rate": 2e-07,
      "loss": 0.0533,
      "step": 1083
    },
    {
      "clip_ratio/high_max": 0.0015764176932862028,
      "clip_ratio/high_mean": 0.0006854046205262421,
      "clip_ratio/low_mean": 0.0007194344634626759,
      "clip_ratio/low_min": 8.922711094783153e-05,
      "clip_ratio/region_mean": 0.0014048390912648756,
      "epoch": 0.10117308040063233,
      "grad_norm": 0.17536237835884094,
      "learning_rate": 2e-07,
      "loss": 0.0222,
      "step": 1084
    },
    {
      "clip_ratio/high_max": 0.0017117588940891437,
      "clip_ratio/high_mean": 0.000690675136866048,
      "clip_ratio/low_mean": 0.0005924012857576599,
      "clip_ratio/low_min": 3.3768368666642345e-05,
      "clip_ratio/region_mean": 0.0012830764353566337,
      "epoch": 0.10126641350063291,
      "grad_norm": 0.17821721732616425,
      "learning_rate": 2e-07,
      "loss": 0.0327,
      "step": 1085
    },
    {
      "clip_ratio/high_max": 0.0018025294339167885,
      "clip_ratio/high_mean": 0.0006769746760255657,
      "clip_ratio/low_mean": 0.0005648236710840138,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012417983489285689,
      "epoch": 0.1013597466006335,
      "grad_norm": 0.15017281472682953,
      "learning_rate": 2e-07,
      "loss": -0.0209,
      "step": 1086
    },
    {
      "clip_ratio/high_max": 0.0018446145331836306,
      "clip_ratio/high_mean": 0.000690034501531045,
      "clip_ratio/low_mean": 0.0007388792801066302,
      "clip_ratio/low_min": 6.953795582376188e-05,
      "clip_ratio/region_mean": 0.001428913776180707,
      "epoch": 0.10145307970063408,
      "grad_norm": 0.1970624029636383,
      "learning_rate": 2e-07,
      "loss": 0.0478,
      "step": 1087
    },
    {
      "clip_ratio/high_max": 0.0018227329856017604,
      "clip_ratio/high_mean": 0.000725278579920996,
      "clip_ratio/low_mean": 0.0006709175900141418,
      "clip_ratio/low_min": 8.060100117290858e-05,
      "clip_ratio/region_mean": 0.0013961961813038215,
      "epoch": 0.10154641280063466,
      "grad_norm": 0.1950201541185379,
      "learning_rate": 2e-07,
      "loss": 0.0387,
      "step": 1088
    },
    {
      "clip_ratio/high_max": 0.0018493605966796167,
      "clip_ratio/high_mean": 0.0007223429856821895,
      "clip_ratio/low_mean": 0.0006925458728801459,
      "clip_ratio/low_min": 1.3185654097469524e-05,
      "clip_ratio/region_mean": 0.0014148888767522294,
      "epoch": 0.10163974590063525,
      "grad_norm": 0.15911564230918884,
      "learning_rate": 2e-07,
      "loss": 0.0596,
      "step": 1089
    },
    {
      "clip_ratio/high_max": 0.0018189161346526816,
      "clip_ratio/high_mean": 0.0007318314656004077,
      "clip_ratio/low_mean": 0.0005715087754651904,
      "clip_ratio/low_min": 1.1160714166180696e-05,
      "clip_ratio/region_mean": 0.0013033402501605451,
      "epoch": 0.10173307900063583,
      "grad_norm": 0.1550421267747879,
      "learning_rate": 2e-07,
      "loss": 0.0214,
      "step": 1090
    },
    {
      "clip_ratio/high_max": 0.0020656078595493454,
      "clip_ratio/high_mean": 0.0007536990287917433,
      "clip_ratio/low_mean": 0.0006875927410874283,
      "clip_ratio/low_min": 4.433202730069752e-05,
      "clip_ratio/region_mean": 0.0014412917735171504,
      "epoch": 0.10182641210063642,
      "grad_norm": 0.18259114027023315,
      "learning_rate": 2e-07,
      "loss": 0.0568,
      "step": 1091
    },
    {
      "clip_ratio/high_max": 0.0016649528333800845,
      "clip_ratio/high_mean": 0.000697522410973761,
      "clip_ratio/low_mean": 0.000618533170381852,
      "clip_ratio/low_min": 3.604501762310974e-05,
      "clip_ratio/region_mean": 0.0013160555790818762,
      "epoch": 0.101919745200637,
      "grad_norm": 0.15836119651794434,
      "learning_rate": 2e-07,
      "loss": 0.027,
      "step": 1092
    },
    {
      "clip_ratio/high_max": 0.001766547851730138,
      "clip_ratio/high_mean": 0.0006421936432161601,
      "clip_ratio/low_mean": 0.0007076363917803974,
      "clip_ratio/low_min": 0.00010495582228031708,
      "clip_ratio/region_mean": 0.0013498299995262641,
      "epoch": 0.10201307830063758,
      "grad_norm": 0.14460568130016327,
      "learning_rate": 2e-07,
      "loss": 0.0669,
      "step": 1093
    },
    {
      "clip_ratio/high_max": 0.00136424141965108,
      "clip_ratio/high_mean": 0.0005403467648648075,
      "clip_ratio/low_mean": 0.000626366099822917,
      "clip_ratio/low_min": 1.607096965017263e-05,
      "clip_ratio/region_mean": 0.0011667128565022722,
      "epoch": 0.10210641140063817,
      "grad_norm": 0.19492022693157196,
      "learning_rate": 2e-07,
      "loss": 0.0428,
      "step": 1094
    },
    {
      "clip_ratio/high_max": 0.0018926275733974762,
      "clip_ratio/high_mean": 0.0007042887791612884,
      "clip_ratio/low_mean": 0.0008054274203459499,
      "clip_ratio/low_min": 7.806214580341475e-05,
      "clip_ratio/region_mean": 0.001509716206783196,
      "epoch": 0.10219974450063875,
      "grad_norm": 0.45484256744384766,
      "learning_rate": 2e-07,
      "loss": 0.0508,
      "step": 1095
    },
    {
      "clip_ratio/high_max": 0.0016730453353375196,
      "clip_ratio/high_mean": 0.0007238493126351386,
      "clip_ratio/low_mean": 0.0007824249933037208,
      "clip_ratio/low_min": 6.230577309906948e-05,
      "clip_ratio/region_mean": 0.0015062742895679548,
      "epoch": 0.10229307760063933,
      "grad_norm": 0.19504110515117645,
      "learning_rate": 2e-07,
      "loss": 0.0564,
      "step": 1096
    },
    {
      "clip_ratio/high_max": 0.0016367621938115917,
      "clip_ratio/high_mean": 0.0006565264311575447,
      "clip_ratio/low_mean": 0.0006940491894056322,
      "clip_ratio/low_min": 5.03113533341093e-05,
      "clip_ratio/region_mean": 0.001350575632386608,
      "epoch": 0.10238641070063992,
      "grad_norm": 0.1701657623052597,
      "learning_rate": 2e-07,
      "loss": 0.0313,
      "step": 1097
    },
    {
      "clip_ratio/high_max": 0.0014567341258953093,
      "clip_ratio/high_mean": 0.000606280497777334,
      "clip_ratio/low_mean": 0.0007119195470295381,
      "clip_ratio/low_min": 7.631135667907074e-05,
      "clip_ratio/region_mean": 0.0013182000438973773,
      "epoch": 0.1024797438006405,
      "grad_norm": 0.16686387360095978,
      "learning_rate": 2e-07,
      "loss": 0.0671,
      "step": 1098
    },
    {
      "clip_ratio/high_max": 0.0017143516070063924,
      "clip_ratio/high_mean": 0.0007066034768286045,
      "clip_ratio/low_mean": 0.0007160510558605893,
      "clip_ratio/low_min": 3.743508477782598e-05,
      "clip_ratio/region_mean": 0.001422654513589805,
      "epoch": 0.10257307690064109,
      "grad_norm": 0.1850610077381134,
      "learning_rate": 2e-07,
      "loss": 0.0465,
      "step": 1099
    },
    {
      "clip_ratio/high_max": 0.001641176117118448,
      "clip_ratio/high_mean": 0.0006625574769714149,
      "clip_ratio/low_mean": 0.0005664665659423918,
      "clip_ratio/low_min": 8.286926458822563e-06,
      "clip_ratio/region_mean": 0.0012290240374568384,
      "epoch": 0.10266641000064167,
      "grad_norm": 0.15729431807994843,
      "learning_rate": 2e-07,
      "loss": -0.0214,
      "step": 1100
    },
    {
      "clip_ratio/high_max": 0.002012389933952363,
      "clip_ratio/high_mean": 0.0007761736633256078,
      "clip_ratio/low_mean": 0.0008028139891393948,
      "clip_ratio/low_min": 2.559916174504906e-05,
      "clip_ratio/region_mean": 0.001578987699758727,
      "epoch": 0.10275974310064225,
      "grad_norm": 0.17352890968322754,
      "learning_rate": 2e-07,
      "loss": 0.0186,
      "step": 1101
    },
    {
      "clip_ratio/high_max": 0.0017241790119442157,
      "clip_ratio/high_mean": 0.000714992094799527,
      "clip_ratio/low_mean": 0.0008037690622586524,
      "clip_ratio/low_min": 3.547297637851443e-05,
      "clip_ratio/region_mean": 0.0015187611934379674,
      "epoch": 0.10285307620064284,
      "grad_norm": 0.17286644876003265,
      "learning_rate": 2e-07,
      "loss": 0.0481,
      "step": 1102
    },
    {
      "clip_ratio/high_max": 0.001707520892523462,
      "clip_ratio/high_mean": 0.000703600146152894,
      "clip_ratio/low_mean": 0.0006809779943068861,
      "clip_ratio/low_min": 8.261368566309102e-05,
      "clip_ratio/region_mean": 0.0013845781249983702,
      "epoch": 0.10294640930064342,
      "grad_norm": 0.17523880302906036,
      "learning_rate": 2e-07,
      "loss": 0.0115,
      "step": 1103
    },
    {
      "clip_ratio/high_max": 0.001992955556488596,
      "clip_ratio/high_mean": 0.0007888808995630825,
      "clip_ratio/low_mean": 0.0006802679417887703,
      "clip_ratio/low_min": 4.4974053707846906e-05,
      "clip_ratio/region_mean": 0.0014691487922391389,
      "epoch": 0.103039742400644,
      "grad_norm": 0.15377196669578552,
      "learning_rate": 2e-07,
      "loss": -0.0228,
      "step": 1104
    },
    {
      "clip_ratio/high_max": 0.0017611919465707615,
      "clip_ratio/high_mean": 0.0007069728162605315,
      "clip_ratio/low_mean": 0.0006792380218030303,
      "clip_ratio/low_min": 8.428774526691996e-05,
      "clip_ratio/region_mean": 0.0013862108462490141,
      "epoch": 0.10313307550064459,
      "grad_norm": 0.17648661136627197,
      "learning_rate": 2e-07,
      "loss": -0.0061,
      "step": 1105
    },
    {
      "clip_ratio/high_max": 0.002141889137419639,
      "clip_ratio/high_mean": 0.0007625833859492559,
      "clip_ratio/low_mean": 0.0007133835661079502,
      "clip_ratio/low_min": 1.6414969650213607e-05,
      "clip_ratio/region_mean": 0.0014759669284103438,
      "epoch": 0.10322640860064516,
      "grad_norm": 0.1829444020986557,
      "learning_rate": 2e-07,
      "loss": 0.0316,
      "step": 1106
    },
    {
      "clip_ratio/high_max": 0.0018212226295872824,
      "clip_ratio/high_mean": 0.0006597093133677845,
      "clip_ratio/low_mean": 0.0006008648970237118,
      "clip_ratio/low_min": 3.7670837627956644e-05,
      "clip_ratio/region_mean": 0.0012605742122104857,
      "epoch": 0.10331974170064574,
      "grad_norm": 0.15556700527668,
      "learning_rate": 2e-07,
      "loss": -0.0026,
      "step": 1107
    },
    {
      "clip_ratio/high_max": 0.0016642345799482428,
      "clip_ratio/high_mean": 0.0006623064437007997,
      "clip_ratio/low_mean": 0.0006644109416811261,
      "clip_ratio/low_min": 1.240325491380645e-05,
      "clip_ratio/region_mean": 0.0013267173744679894,
      "epoch": 0.10341307480064633,
      "grad_norm": 0.17202286422252655,
      "learning_rate": 2e-07,
      "loss": 0.0375,
      "step": 1108
    },
    {
      "clip_ratio/high_max": 0.002002046487177722,
      "clip_ratio/high_mean": 0.0008412695588049246,
      "clip_ratio/low_mean": 0.0006451919844039367,
      "clip_ratio/low_min": 2.2739675841876306e-05,
      "clip_ratio/region_mean": 0.0014864615150145255,
      "epoch": 0.10350640790064691,
      "grad_norm": 0.18759506940841675,
      "learning_rate": 2e-07,
      "loss": -0.0077,
      "step": 1109
    },
    {
      "clip_ratio/high_max": 0.0018822737656591926,
      "clip_ratio/high_mean": 0.0006427048492696485,
      "clip_ratio/low_mean": 0.0008205131143768085,
      "clip_ratio/low_min": 8.546868457415258e-05,
      "clip_ratio/region_mean": 0.001463217951823026,
      "epoch": 0.1035997410006475,
      "grad_norm": 0.17778731882572174,
      "learning_rate": 2e-07,
      "loss": 0.0364,
      "step": 1110
    },
    {
      "clip_ratio/high_max": 0.0017383560407324694,
      "clip_ratio/high_mean": 0.0006919644165463978,
      "clip_ratio/low_mean": 0.0007098606256477069,
      "clip_ratio/low_min": 2.107077671098523e-05,
      "clip_ratio/region_mean": 0.0014018250367371365,
      "epoch": 0.10369307410064808,
      "grad_norm": 0.2000223845243454,
      "learning_rate": 2e-07,
      "loss": 0.0144,
      "step": 1111
    },
    {
      "clip_ratio/high_max": 0.0019446625155978836,
      "clip_ratio/high_mean": 0.0007200771960924612,
      "clip_ratio/low_mean": 0.0007276775231730426,
      "clip_ratio/low_min": 2.4101731469272636e-05,
      "clip_ratio/region_mean": 0.001447754715627525,
      "epoch": 0.10378640720064866,
      "grad_norm": 0.18549001216888428,
      "learning_rate": 2e-07,
      "loss": 0.0233,
      "step": 1112
    },
    {
      "clip_ratio/high_max": 0.001537330710561946,
      "clip_ratio/high_mean": 0.0006239347985683708,
      "clip_ratio/low_mean": 0.0007345005942624994,
      "clip_ratio/low_min": 4.676222533817054e-05,
      "clip_ratio/region_mean": 0.0013584354455815628,
      "epoch": 0.10387974030064925,
      "grad_norm": 0.23638804256916046,
      "learning_rate": 2e-07,
      "loss": 0.061,
      "step": 1113
    },
    {
      "clip_ratio/high_max": 0.0017658633842074778,
      "clip_ratio/high_mean": 0.0006900691842020024,
      "clip_ratio/low_mean": 0.0008230751318478724,
      "clip_ratio/low_min": 1.2465097825042903e-05,
      "clip_ratio/region_mean": 0.0015131443142308854,
      "epoch": 0.10397307340064983,
      "grad_norm": 0.20945629477500916,
      "learning_rate": 2e-07,
      "loss": 0.0856,
      "step": 1114
    },
    {
      "clip_ratio/high_max": 0.0017384473740094109,
      "clip_ratio/high_mean": 0.0007189507987277466,
      "clip_ratio/low_mean": 0.0007073538436088711,
      "clip_ratio/low_min": 6.58914814266609e-05,
      "clip_ratio/region_mean": 0.0014263046177802607,
      "epoch": 0.10406640650065041,
      "grad_norm": 0.19514112174510956,
      "learning_rate": 2e-07,
      "loss": -0.0075,
      "step": 1115
    },
    {
      "clip_ratio/high_max": 0.00187939171155449,
      "clip_ratio/high_mean": 0.0006622743076150073,
      "clip_ratio/low_mean": 0.0007319939122680807,
      "clip_ratio/low_min": 2.0377427972562145e-05,
      "clip_ratio/region_mean": 0.0013942682235210668,
      "epoch": 0.104159739600651,
      "grad_norm": 0.18565185368061066,
      "learning_rate": 2e-07,
      "loss": 0.0356,
      "step": 1116
    },
    {
      "clip_ratio/high_max": 0.0020871375454589725,
      "clip_ratio/high_mean": 0.0008166047882696148,
      "clip_ratio/low_mean": 0.0006817918165324954,
      "clip_ratio/low_min": 1.577486182213761e-05,
      "clip_ratio/region_mean": 0.0014983966320869513,
      "epoch": 0.10425307270065158,
      "grad_norm": 0.2912517488002777,
      "learning_rate": 2e-07,
      "loss": 0.0403,
      "step": 1117
    },
    {
      "clip_ratio/high_max": 0.0017056409305951092,
      "clip_ratio/high_mean": 0.0007120789287000662,
      "clip_ratio/low_mean": 0.0008236580524680903,
      "clip_ratio/low_min": 2.836718522303272e-05,
      "clip_ratio/region_mean": 0.001535737028461881,
      "epoch": 0.10434640580065216,
      "grad_norm": 0.19938957691192627,
      "learning_rate": 2e-07,
      "loss": 0.029,
      "step": 1118
    },
    {
      "clip_ratio/high_max": 0.001769970214809291,
      "clip_ratio/high_mean": 0.000710178956069285,
      "clip_ratio/low_mean": 0.0007748451625957387,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014850241495878436,
      "epoch": 0.10443973890065275,
      "grad_norm": 0.34391912817955017,
      "learning_rate": 2e-07,
      "loss": 0.0379,
      "step": 1119
    },
    {
      "clip_ratio/high_max": 0.0017779520894691814,
      "clip_ratio/high_mean": 0.0007098604437487666,
      "clip_ratio/low_mean": 0.0008456395662506111,
      "clip_ratio/low_min": 2.8922179808432702e-05,
      "clip_ratio/region_mean": 0.0015554999699816108,
      "epoch": 0.10453307200065333,
      "grad_norm": 0.17450092732906342,
      "learning_rate": 2e-07,
      "loss": 0.0215,
      "step": 1120
    },
    {
      "clip_ratio/high_max": 0.0022155993938213214,
      "clip_ratio/high_mean": 0.0008303496852022363,
      "clip_ratio/low_mean": 0.0006930597101018066,
      "clip_ratio/low_min": 6.0944692449993454e-05,
      "clip_ratio/region_mean": 0.0015234094244078733,
      "epoch": 0.10462640510065392,
      "grad_norm": 0.22590035200119019,
      "learning_rate": 2e-07,
      "loss": -0.022,
      "step": 1121
    },
    {
      "clip_ratio/high_max": 0.002001709464821033,
      "clip_ratio/high_mean": 0.0007593416630697902,
      "clip_ratio/low_mean": 0.000666139983877656,
      "clip_ratio/low_min": 1.8341892427997664e-05,
      "clip_ratio/region_mean": 0.0014254816487664357,
      "epoch": 0.1047197382006545,
      "grad_norm": 0.16287989914417267,
      "learning_rate": 2e-07,
      "loss": 0.0096,
      "step": 1122
    },
    {
      "clip_ratio/high_max": 0.0015243976158672012,
      "clip_ratio/high_mean": 0.0006965569973544916,
      "clip_ratio/low_mean": 0.0007482387263735291,
      "clip_ratio/low_min": 4.736040500574745e-05,
      "clip_ratio/region_mean": 0.0014447957291849889,
      "epoch": 0.10481307130065508,
      "grad_norm": 0.18563826382160187,
      "learning_rate": 2e-07,
      "loss": 0.0294,
      "step": 1123
    },
    {
      "clip_ratio/high_max": 0.0020910659368382767,
      "clip_ratio/high_mean": 0.000823540220153518,
      "clip_ratio/low_mean": 0.0007974171621754067,
      "clip_ratio/low_min": 7.90133026384865e-05,
      "clip_ratio/region_mean": 0.0016209574023378082,
      "epoch": 0.10490640440065567,
      "grad_norm": 0.23470395803451538,
      "learning_rate": 2e-07,
      "loss": 0.0054,
      "step": 1124
    },
    {
      "clip_ratio/high_max": 0.001761332263413351,
      "clip_ratio/high_mean": 0.0007156250412663212,
      "clip_ratio/low_mean": 0.0009009028854052303,
      "clip_ratio/low_min": 2.2285612431005575e-05,
      "clip_ratio/region_mean": 0.0016165279594133608,
      "epoch": 0.10499973750065625,
      "grad_norm": 0.2094983160495758,
      "learning_rate": 2e-07,
      "loss": 0.0297,
      "step": 1125
    },
    {
      "clip_ratio/high_max": 0.0015303577783924993,
      "clip_ratio/high_mean": 0.0006309596046776278,
      "clip_ratio/low_mean": 0.0008965284941950813,
      "clip_ratio/low_min": 3.1694267818238586e-05,
      "clip_ratio/region_mean": 0.001527488089777762,
      "epoch": 0.10509307060065683,
      "grad_norm": 0.1982315480709076,
      "learning_rate": 2e-07,
      "loss": 0.0372,
      "step": 1126
    },
    {
      "clip_ratio/high_max": 0.0019632382827694528,
      "clip_ratio/high_mean": 0.0007322807578020729,
      "clip_ratio/low_mean": 0.0006698686320305569,
      "clip_ratio/low_min": 1.1208751857338939e-05,
      "clip_ratio/region_mean": 0.001402149413479492,
      "epoch": 0.10518640370065742,
      "grad_norm": 0.172402024269104,
      "learning_rate": 2e-07,
      "loss": 0.0207,
      "step": 1127
    },
    {
      "clip_ratio/high_max": 0.0017424712277716026,
      "clip_ratio/high_mean": 0.0007824306776456069,
      "clip_ratio/low_mean": 0.0007622028570040129,
      "clip_ratio/low_min": 4.890175569016719e-05,
      "clip_ratio/region_mean": 0.0015446335055457894,
      "epoch": 0.105279736800658,
      "grad_norm": 0.21946778893470764,
      "learning_rate": 2e-07,
      "loss": 0.0057,
      "step": 1128
    },
    {
      "clip_ratio/high_max": 0.0023641102452529594,
      "clip_ratio/high_mean": 0.0008045875656534918,
      "clip_ratio/low_mean": 0.0007482615528715542,
      "clip_ratio/low_min": 8.049485768424347e-05,
      "clip_ratio/region_mean": 0.0015528491567238234,
      "epoch": 0.10537306990065858,
      "grad_norm": 0.19112466275691986,
      "learning_rate": 2e-07,
      "loss": 0.0511,
      "step": 1129
    },
    {
      "clip_ratio/high_max": 0.0019674875256896485,
      "clip_ratio/high_mean": 0.0008085221561486833,
      "clip_ratio/low_mean": 0.0009789776304387487,
      "clip_ratio/low_min": 0.00016185067761398386,
      "clip_ratio/region_mean": 0.001787499786587432,
      "epoch": 0.10546640300065917,
      "grad_norm": 0.23398177325725555,
      "learning_rate": 2e-07,
      "loss": 0.0401,
      "step": 1130
    },
    {
      "clip_ratio/high_max": 0.0020986026611353736,
      "clip_ratio/high_mean": 0.0008616377217549598,
      "clip_ratio/low_mean": 0.0007748301904939581,
      "clip_ratio/low_min": 5.428488657344133e-05,
      "clip_ratio/region_mean": 0.0016364678958780132,
      "epoch": 0.10555973610065975,
      "grad_norm": 0.33156293630599976,
      "learning_rate": 2e-07,
      "loss": -0.0161,
      "step": 1131
    },
    {
      "clip_ratio/high_max": 0.0019223284252802841,
      "clip_ratio/high_mean": 0.0007875180253904546,
      "clip_ratio/low_mean": 0.0007947207832330605,
      "clip_ratio/low_min": 0.00012073359448550036,
      "clip_ratio/region_mean": 0.001582238735863939,
      "epoch": 0.10565306920066034,
      "grad_norm": 0.20530462265014648,
      "learning_rate": 2e-07,
      "loss": 0.0257,
      "step": 1132
    },
    {
      "clip_ratio/high_max": 0.0020733819001179654,
      "clip_ratio/high_mean": 0.0007886611747380812,
      "clip_ratio/low_mean": 0.0008109310183499474,
      "clip_ratio/low_min": 9.737064829096198e-05,
      "clip_ratio/region_mean": 0.0015995922294678167,
      "epoch": 0.10574640230066092,
      "grad_norm": 0.18688048422336578,
      "learning_rate": 2e-07,
      "loss": 0.0081,
      "step": 1133
    },
    {
      "clip_ratio/high_max": 0.002172916974814143,
      "clip_ratio/high_mean": 0.0008290860896522645,
      "clip_ratio/low_mean": 0.0009553911440889351,
      "clip_ratio/low_min": 3.9817372453399e-05,
      "clip_ratio/region_mean": 0.0017844772009993903,
      "epoch": 0.1058397354006615,
      "grad_norm": 0.22315232455730438,
      "learning_rate": 2e-07,
      "loss": 0.0062,
      "step": 1134
    },
    {
      "clip_ratio/high_max": 0.001972141813894268,
      "clip_ratio/high_mean": 0.0008083875654847361,
      "clip_ratio/low_mean": 0.0009335084541817196,
      "clip_ratio/low_min": 6.0593289163080044e-05,
      "clip_ratio/region_mean": 0.001741896012390498,
      "epoch": 0.10593306850066209,
      "grad_norm": 0.20710480213165283,
      "learning_rate": 2e-07,
      "loss": 0.0344,
      "step": 1135
    },
    {
      "clip_ratio/high_max": 0.0021570565149886534,
      "clip_ratio/high_mean": 0.0008218284074246185,
      "clip_ratio/low_mean": 0.0008251939470937941,
      "clip_ratio/low_min": 3.1045416108099744e-05,
      "clip_ratio/region_mean": 0.0016470223854412325,
      "epoch": 0.10602640160066266,
      "grad_norm": 0.1891990602016449,
      "learning_rate": 2e-07,
      "loss": 0.0141,
      "step": 1136
    },
    {
      "clip_ratio/high_max": 0.0017614163334656041,
      "clip_ratio/high_mean": 0.0007281454963958822,
      "clip_ratio/low_mean": 0.0008820163839118322,
      "clip_ratio/low_min": 3.826721331279259e-05,
      "clip_ratio/region_mean": 0.0016101618894026615,
      "epoch": 0.10611973470066324,
      "grad_norm": 0.18992166221141815,
      "learning_rate": 2e-07,
      "loss": 0.017,
      "step": 1137
    },
    {
      "clip_ratio/high_max": 0.0022039963005227037,
      "clip_ratio/high_mean": 0.0008524529403075576,
      "clip_ratio/low_mean": 0.0009391076455358416,
      "clip_ratio/low_min": 7.969427315401845e-05,
      "clip_ratio/region_mean": 0.001791560571291484,
      "epoch": 0.10621306780066384,
      "grad_norm": 0.20301789045333862,
      "learning_rate": 2e-07,
      "loss": 0.0247,
      "step": 1138
    },
    {
      "clip_ratio/high_max": 0.001920036505907774,
      "clip_ratio/high_mean": 0.0007118490293578361,
      "clip_ratio/low_mean": 0.0009270587270293618,
      "clip_ratio/low_min": 4.3461019231472164e-05,
      "clip_ratio/region_mean": 0.001638907786400523,
      "epoch": 0.10630640090066441,
      "grad_norm": 0.2717629373073578,
      "learning_rate": 2e-07,
      "loss": 0.0717,
      "step": 1139
    },
    {
      "clip_ratio/high_max": 0.0019034584765904583,
      "clip_ratio/high_mean": 0.0008074801407929044,
      "clip_ratio/low_mean": 0.0009448026539757848,
      "clip_ratio/low_min": 5.116897591506131e-05,
      "clip_ratio/region_mean": 0.0017522827838547528,
      "epoch": 0.10639973400066499,
      "grad_norm": 0.2513815462589264,
      "learning_rate": 2e-07,
      "loss": 0.0234,
      "step": 1140
    },
    {
      "clip_ratio/high_max": 0.001943527862749761,
      "clip_ratio/high_mean": 0.0007663091050744697,
      "clip_ratio/low_mean": 0.000956200664404605,
      "clip_ratio/low_min": 3.385154104762478e-05,
      "clip_ratio/region_mean": 0.0017225097726623062,
      "epoch": 0.10649306710066558,
      "grad_norm": 0.20724967122077942,
      "learning_rate": 2e-07,
      "loss": 0.0531,
      "step": 1141
    },
    {
      "clip_ratio/high_max": 0.0020496167890087236,
      "clip_ratio/high_mean": 0.0008580640715081245,
      "clip_ratio/low_mean": 0.0009527589772915235,
      "clip_ratio/low_min": 6.408581884898013e-05,
      "clip_ratio/region_mean": 0.0018108230287907645,
      "epoch": 0.10658640020066616,
      "grad_norm": 0.2833152413368225,
      "learning_rate": 2e-07,
      "loss": 0.0301,
      "step": 1142
    },
    {
      "clip_ratio/high_max": 0.002170580206438899,
      "clip_ratio/high_mean": 0.0008358599425264401,
      "clip_ratio/low_mean": 0.0010058011503133457,
      "clip_ratio/low_min": 0.0001087575797100726,
      "clip_ratio/region_mean": 0.0018416610328131355,
      "epoch": 0.10667973330066675,
      "grad_norm": 0.19138747453689575,
      "learning_rate": 2e-07,
      "loss": 0.0499,
      "step": 1143
    },
    {
      "clip_ratio/high_max": 0.002069901420327369,
      "clip_ratio/high_mean": 0.0007908684237918351,
      "clip_ratio/low_mean": 0.0007923690918687498,
      "clip_ratio/low_min": 3.8937671888561454e-05,
      "clip_ratio/region_mean": 0.0015832375138415955,
      "epoch": 0.10677306640066733,
      "grad_norm": 0.18338420987129211,
      "learning_rate": 2e-07,
      "loss": 0.0305,
      "step": 1144
    },
    {
      "clip_ratio/high_max": 0.002282039749843534,
      "clip_ratio/high_mean": 0.0008119083031488117,
      "clip_ratio/low_mean": 0.0008889147084119031,
      "clip_ratio/low_min": 5.3181777730060276e-05,
      "clip_ratio/region_mean": 0.0017008229697239585,
      "epoch": 0.10686639950066791,
      "grad_norm": 0.21848715841770172,
      "learning_rate": 2e-07,
      "loss": 0.0322,
      "step": 1145
    },
    {
      "clip_ratio/high_max": 0.0019890168769052252,
      "clip_ratio/high_mean": 0.0008314633214467904,
      "clip_ratio/low_mean": 0.0010063690697279526,
      "clip_ratio/low_min": 0.00013259013758215588,
      "clip_ratio/region_mean": 0.0018378323293291032,
      "epoch": 0.1069597326006685,
      "grad_norm": 0.2766454815864563,
      "learning_rate": 2e-07,
      "loss": 0.0752,
      "step": 1146
    },
    {
      "clip_ratio/high_max": 0.0021620424813590944,
      "clip_ratio/high_mean": 0.0009013813578349072,
      "clip_ratio/low_mean": 0.0009818292510317406,
      "clip_ratio/low_min": 7.670309787499718e-05,
      "clip_ratio/region_mean": 0.0018832106215995736,
      "epoch": 0.10705306570066908,
      "grad_norm": 0.2228546440601349,
      "learning_rate": 2e-07,
      "loss": 0.0089,
      "step": 1147
    },
    {
      "clip_ratio/high_max": 0.002279377687955275,
      "clip_ratio/high_mean": 0.0008424243824265432,
      "clip_ratio/low_mean": 0.0008772078363108449,
      "clip_ratio/low_min": 8.314251317642629e-05,
      "clip_ratio/region_mean": 0.0017196322296513245,
      "epoch": 0.10714639880066966,
      "grad_norm": 0.2301560491323471,
      "learning_rate": 2e-07,
      "loss": 0.0306,
      "step": 1148
    },
    {
      "clip_ratio/high_max": 0.002117458076099865,
      "clip_ratio/high_mean": 0.0009613349138817284,
      "clip_ratio/low_mean": 0.001009680585411843,
      "clip_ratio/low_min": 9.428792418475496e-05,
      "clip_ratio/region_mean": 0.001971015488379635,
      "epoch": 0.10723973190067025,
      "grad_norm": 0.35168761014938354,
      "learning_rate": 2e-07,
      "loss": 0.0301,
      "step": 1149
    },
    {
      "clip_ratio/high_max": 0.0018279521609656513,
      "clip_ratio/high_mean": 0.0007901179360487731,
      "clip_ratio/low_mean": 0.0010681857711460907,
      "clip_ratio/low_min": 0.00014211980123945978,
      "clip_ratio/region_mean": 0.0018583037162898108,
      "epoch": 0.10733306500067083,
      "grad_norm": 0.2210843563079834,
      "learning_rate": 2e-07,
      "loss": 0.0344,
      "step": 1150
    },
    {
      "clip_ratio/high_max": 0.002192511448811274,
      "clip_ratio/high_mean": 0.0009225484973285347,
      "clip_ratio/low_mean": 0.0009286007571063237,
      "clip_ratio/low_min": 5.789871829620097e-05,
      "clip_ratio/region_mean": 0.0018511492744437419,
      "epoch": 0.10742639810067142,
      "grad_norm": 0.37375393509864807,
      "learning_rate": 2e-07,
      "loss": 0.0197,
      "step": 1151
    },
    {
      "clip_ratio/high_max": 0.002026788191869855,
      "clip_ratio/high_mean": 0.0007743613568891305,
      "clip_ratio/low_mean": 0.0010105150704475818,
      "clip_ratio/low_min": 9.71479212239501e-05,
      "clip_ratio/region_mean": 0.0017848763818619773,
      "epoch": 0.107519731200672,
      "grad_norm": 0.23327729105949402,
      "learning_rate": 2e-07,
      "loss": 0.0185,
      "step": 1152
    },
    {
      "clip_ratio/high_max": 0.0019002621484105475,
      "clip_ratio/high_mean": 0.0006500720155599993,
      "clip_ratio/low_mean": 0.0006044011634003255,
      "clip_ratio/low_min": 2.437122202536557e-05,
      "clip_ratio/region_mean": 0.0012544731580419466,
      "completions/clipped_ratio": 0.015712193080357095,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4088.0,
      "completions/mean_length": 656.460205078125,
      "completions/mean_terminated_length": 601.5548706054688,
      "completions/min_length": 88.0,
      "completions/min_terminated_length": 88.0,
      "epoch": 0.10761306430067258,
      "grad_norm": 0.19238293170928955,
      "learning_rate": 2e-07,
      "loss": 0.0171,
      "num_tokens": 852865584.0,
      "reward": 0.5996355414390564,
      "reward_std": 0.17621906101703644,
      "rewards/simpleverify_reward/mean": 0.5996355414390564,
      "rewards/simpleverify_reward/std": 0.48997434973716736,
      "step": 1153
    },
    {
      "clip_ratio/high_max": 0.0018897384725278243,
      "clip_ratio/high_mean": 0.000760492597692064,
      "clip_ratio/low_mean": 0.0006038603478373261,
      "clip_ratio/low_min": 4.387695298646577e-05,
      "clip_ratio/region_mean": 0.0013643529418914113,
      "epoch": 0.10770639740067317,
      "grad_norm": 0.20492057502269745,
      "learning_rate": 2e-07,
      "loss": -0.0486,
      "step": 1154
    },
    {
      "clip_ratio/high_max": 0.0017187149096571375,
      "clip_ratio/high_mean": 0.0007300019533431623,
      "clip_ratio/low_mean": 0.0005704309360226034,
      "clip_ratio/low_min": 2.6425207579450216e-05,
      "clip_ratio/region_mean": 0.001300432879361324,
      "epoch": 0.10779973050067375,
      "grad_norm": 0.1889190822839737,
      "learning_rate": 2e-07,
      "loss": 0.0121,
      "step": 1155
    },
    {
      "clip_ratio/high_max": 0.0016163798409252195,
      "clip_ratio/high_mean": 0.0006204793471624725,
      "clip_ratio/low_mean": 0.0006403167190001113,
      "clip_ratio/low_min": 1.3572203897638246e-05,
      "clip_ratio/region_mean": 0.0012607961034518667,
      "epoch": 0.10789306360067433,
      "grad_norm": 0.24750067293643951,
      "learning_rate": 2e-07,
      "loss": 0.0597,
      "step": 1156
    },
    {
      "clip_ratio/high_max": 0.001811950085539138,
      "clip_ratio/high_mean": 0.00066639986471273,
      "clip_ratio/low_mean": 0.0006902259792695986,
      "clip_ratio/low_min": 2.602916629257379e-05,
      "clip_ratio/region_mean": 0.0013566258421633393,
      "epoch": 0.10798639670067492,
      "grad_norm": 0.18738169968128204,
      "learning_rate": 2e-07,
      "loss": 0.0484,
      "step": 1157
    },
    {
      "clip_ratio/high_max": 0.001550313172629103,
      "clip_ratio/high_mean": 0.0006352991385938367,
      "clip_ratio/low_mean": 0.0005363966229197104,
      "clip_ratio/low_min": 7.243434174597496e-05,
      "clip_ratio/region_mean": 0.0011716957633325364,
      "epoch": 0.1080797298006755,
      "grad_norm": 0.1862281709909439,
      "learning_rate": 2e-07,
      "loss": 0.0125,
      "step": 1158
    },
    {
      "clip_ratio/high_max": 0.001688683551037684,
      "clip_ratio/high_mean": 0.0006329928164632292,
      "clip_ratio/low_mean": 0.0006799435850552982,
      "clip_ratio/low_min": 1.8463810192770325e-05,
      "clip_ratio/region_mean": 0.0013129363942425698,
      "epoch": 0.10817306290067608,
      "grad_norm": 0.17455722391605377,
      "learning_rate": 2e-07,
      "loss": 0.0346,
      "step": 1159
    },
    {
      "clip_ratio/high_max": 0.0019503886287566274,
      "clip_ratio/high_mean": 0.0007601020006404724,
      "clip_ratio/low_mean": 0.0006450956025219057,
      "clip_ratio/low_min": 9.329564090876374e-05,
      "clip_ratio/region_mean": 0.0014051976322662085,
      "epoch": 0.10826639600067667,
      "grad_norm": 0.1794072836637497,
      "learning_rate": 2e-07,
      "loss": 0.0426,
      "step": 1160
    },
    {
      "clip_ratio/high_max": 0.0014136854551907163,
      "clip_ratio/high_mean": 0.000550233527974342,
      "clip_ratio/low_mean": 0.0006850391746411333,
      "clip_ratio/low_min": 2.255142680951394e-05,
      "clip_ratio/region_mean": 0.0012352727171673905,
      "epoch": 0.10835972910067725,
      "grad_norm": 0.20358531177043915,
      "learning_rate": 2e-07,
      "loss": 0.0768,
      "step": 1161
    },
    {
      "clip_ratio/high_max": 0.0015740208255010657,
      "clip_ratio/high_mean": 0.0006260943364395644,
      "clip_ratio/low_mean": 0.0006881153221911518,
      "clip_ratio/low_min": 6.587641291844193e-05,
      "clip_ratio/region_mean": 0.0013142096613592003,
      "epoch": 0.10845306220067784,
      "grad_norm": 0.19229905307292938,
      "learning_rate": 2e-07,
      "loss": 0.0671,
      "step": 1162
    },
    {
      "clip_ratio/high_max": 0.0016955044611677295,
      "clip_ratio/high_mean": 0.0006433852768168435,
      "clip_ratio/low_mean": 0.0005789099323010305,
      "clip_ratio/low_min": 4.275378159945831e-05,
      "clip_ratio/region_mean": 0.0012222952173033264,
      "epoch": 0.10854639530067842,
      "grad_norm": 0.20612914860248566,
      "learning_rate": 2e-07,
      "loss": 0.0108,
      "step": 1163
    },
    {
      "clip_ratio/high_max": 0.0017925937536347192,
      "clip_ratio/high_mean": 0.0007002661423030077,
      "clip_ratio/low_mean": 0.0006234129841686809,
      "clip_ratio/low_min": 5.0848529099312145e-05,
      "clip_ratio/region_mean": 0.001323679131019162,
      "epoch": 0.108639728400679,
      "grad_norm": 0.19809873402118683,
      "learning_rate": 2e-07,
      "loss": 0.008,
      "step": 1164
    },
    {
      "clip_ratio/high_max": 0.0014247491762944264,
      "clip_ratio/high_mean": 0.0006378434991347603,
      "clip_ratio/low_mean": 0.0005748375770053826,
      "clip_ratio/low_min": 1.252003221452469e-05,
      "clip_ratio/region_mean": 0.0012126810906920582,
      "epoch": 0.10873306150067959,
      "grad_norm": 0.17962507903575897,
      "learning_rate": 2e-07,
      "loss": 0.0193,
      "step": 1165
    },
    {
      "clip_ratio/high_max": 0.001734929290250875,
      "clip_ratio/high_mean": 0.0006868735126772663,
      "clip_ratio/low_mean": 0.0006244975884328596,
      "clip_ratio/low_min": 3.598973034968367e-05,
      "clip_ratio/region_mean": 0.001311371110205073,
      "epoch": 0.10882639460068017,
      "grad_norm": 0.16323807835578918,
      "learning_rate": 2e-07,
      "loss": -0.0118,
      "step": 1166
    },
    {
      "clip_ratio/high_max": 0.0016580265000811778,
      "clip_ratio/high_mean": 0.0005845399855388678,
      "clip_ratio/low_mean": 0.0006818801812187303,
      "clip_ratio/low_min": 1.3584003681899048e-05,
      "clip_ratio/region_mean": 0.00126642014583922,
      "epoch": 0.10891972770068074,
      "grad_norm": 0.18846657872200012,
      "learning_rate": 2e-07,
      "loss": 0.0193,
      "step": 1167
    },
    {
      "clip_ratio/high_max": 0.0018638455439941026,
      "clip_ratio/high_mean": 0.0006850944500911282,
      "clip_ratio/low_mean": 0.0007037348332232796,
      "clip_ratio/low_min": 6.323905518001993e-05,
      "clip_ratio/region_mean": 0.0013888292924093548,
      "epoch": 0.10901306080068134,
      "grad_norm": 0.16910623013973236,
      "learning_rate": 2e-07,
      "loss": 0.0255,
      "step": 1168
    },
    {
      "clip_ratio/high_max": 0.00180743131932104,
      "clip_ratio/high_mean": 0.0006637911028519738,
      "clip_ratio/low_mean": 0.0005263801376713673,
      "clip_ratio/low_min": 1.6765021428000182e-05,
      "clip_ratio/region_mean": 0.0011901712459803093,
      "epoch": 0.10910639390068191,
      "grad_norm": 0.33869290351867676,
      "learning_rate": 2e-07,
      "loss": 0.0528,
      "step": 1169
    },
    {
      "clip_ratio/high_max": 0.00174643629725324,
      "clip_ratio/high_mean": 0.000640493006358156,
      "clip_ratio/low_mean": 0.0007910332915344043,
      "clip_ratio/low_min": 7.310097953450168e-05,
      "clip_ratio/region_mean": 0.0014315263033495285,
      "epoch": 0.10919972700068249,
      "grad_norm": 0.1833248883485794,
      "learning_rate": 2e-07,
      "loss": 0.0275,
      "step": 1170
    },
    {
      "clip_ratio/high_max": 0.0015297609716071747,
      "clip_ratio/high_mean": 0.0005749658475906472,
      "clip_ratio/low_mean": 0.0006821286942795268,
      "clip_ratio/low_min": 3.819135508820182e-05,
      "clip_ratio/region_mean": 0.0012570945291372482,
      "epoch": 0.10929306010068308,
      "grad_norm": 0.18745556473731995,
      "learning_rate": 2e-07,
      "loss": 0.0596,
      "step": 1171
    },
    {
      "clip_ratio/high_max": 0.0019604101762524806,
      "clip_ratio/high_mean": 0.0008546398858015891,
      "clip_ratio/low_mean": 0.0006497148024209309,
      "clip_ratio/low_min": 3.786220077017788e-05,
      "clip_ratio/region_mean": 0.0015043546845845412,
      "epoch": 0.10938639320068366,
      "grad_norm": 0.17636573314666748,
      "learning_rate": 2e-07,
      "loss": -0.0058,
      "step": 1172
    },
    {
      "clip_ratio/high_max": 0.0018086004092765506,
      "clip_ratio/high_mean": 0.0006847701824881369,
      "clip_ratio/low_mean": 0.0008049473399296403,
      "clip_ratio/low_min": 6.556480184372049e-05,
      "clip_ratio/region_mean": 0.0014897175133228302,
      "epoch": 0.10947972630068425,
      "grad_norm": 0.19096620380878448,
      "learning_rate": 2e-07,
      "loss": 0.0473,
      "step": 1173
    },
    {
      "clip_ratio/high_max": 0.0017770928861864377,
      "clip_ratio/high_mean": 0.0006894767902849708,
      "clip_ratio/low_mean": 0.0006302645597315859,
      "clip_ratio/low_min": 2.0465381112444447e-05,
      "clip_ratio/region_mean": 0.0013197413754824083,
      "epoch": 0.10957305940068483,
      "grad_norm": 0.20893307030200958,
      "learning_rate": 2e-07,
      "loss": 0.0178,
      "step": 1174
    },
    {
      "clip_ratio/high_max": 0.0016911543934838846,
      "clip_ratio/high_mean": 0.0005927487700319034,
      "clip_ratio/low_mean": 0.0006785031237086514,
      "clip_ratio/low_min": 3.034847122762585e-05,
      "clip_ratio/region_mean": 0.0012712519310298376,
      "epoch": 0.10966639250068541,
      "grad_norm": 0.21008335053920746,
      "learning_rate": 2e-07,
      "loss": 0.0643,
      "step": 1175
    },
    {
      "clip_ratio/high_max": 0.001634020129131386,
      "clip_ratio/high_mean": 0.0006209048897289904,
      "clip_ratio/low_mean": 0.0006434713050111895,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.00126437619474018,
      "epoch": 0.109759725600686,
      "grad_norm": 0.20011335611343384,
      "learning_rate": 2e-07,
      "loss": 0.0437,
      "step": 1176
    },
    {
      "clip_ratio/high_max": 0.0017903684783959761,
      "clip_ratio/high_mean": 0.0006056546844774857,
      "clip_ratio/low_mean": 0.0006902671630086843,
      "clip_ratio/low_min": 8.607829840912018e-05,
      "clip_ratio/region_mean": 0.001295921829296276,
      "epoch": 0.10985305870068658,
      "grad_norm": 0.17649950087070465,
      "learning_rate": 2e-07,
      "loss": 0.0388,
      "step": 1177
    },
    {
      "clip_ratio/high_max": 0.0016608631194685586,
      "clip_ratio/high_mean": 0.0006518034433611319,
      "clip_ratio/low_mean": 0.0006805760567658581,
      "clip_ratio/low_min": 2.285192022100091e-05,
      "clip_ratio/region_mean": 0.0013323795028554741,
      "epoch": 0.10994639180068716,
      "grad_norm": 0.19707824289798737,
      "learning_rate": 2e-07,
      "loss": 0.0451,
      "step": 1178
    },
    {
      "clip_ratio/high_max": 0.001679947799857473,
      "clip_ratio/high_mean": 0.0006905553500473616,
      "clip_ratio/low_mean": 0.0005742215962527553,
      "clip_ratio/low_min": 2.733165729296161e-05,
      "clip_ratio/region_mean": 0.0012647769908653572,
      "epoch": 0.11003972490068775,
      "grad_norm": 0.1662975698709488,
      "learning_rate": 2e-07,
      "loss": 0.0112,
      "step": 1179
    },
    {
      "clip_ratio/high_max": 0.0021835309962625615,
      "clip_ratio/high_mean": 0.0007844407446100377,
      "clip_ratio/low_mean": 0.0006690054578939453,
      "clip_ratio/low_min": 4.135922063142061e-05,
      "clip_ratio/region_mean": 0.0014534462316078134,
      "epoch": 0.11013305800068833,
      "grad_norm": 0.17501528561115265,
      "learning_rate": 2e-07,
      "loss": 0.0322,
      "step": 1180
    },
    {
      "clip_ratio/high_max": 0.0012176905438536778,
      "clip_ratio/high_mean": 0.0005316880015016068,
      "clip_ratio/low_mean": 0.0006258552421058994,
      "clip_ratio/low_min": 1.2475049516069703e-05,
      "clip_ratio/region_mean": 0.0011575432436075062,
      "epoch": 0.11022639110068891,
      "grad_norm": 0.19051356613636017,
      "learning_rate": 2e-07,
      "loss": 0.029,
      "step": 1181
    },
    {
      "clip_ratio/high_max": 0.0016504912528034765,
      "clip_ratio/high_mean": 0.0007145509316615062,
      "clip_ratio/low_mean": 0.0006099364782130579,
      "clip_ratio/low_min": 3.292226665507769e-05,
      "clip_ratio/region_mean": 0.001324487428064458,
      "epoch": 0.1103197242006895,
      "grad_norm": 0.18952608108520508,
      "learning_rate": 2e-07,
      "loss": 0.0054,
      "step": 1182
    },
    {
      "clip_ratio/high_max": 0.0017306630943494383,
      "clip_ratio/high_mean": 0.0006773532932129456,
      "clip_ratio/low_mean": 0.0006516767771245213,
      "clip_ratio/low_min": 4.406255902722478e-05,
      "clip_ratio/region_mean": 0.0013290300848893821,
      "epoch": 0.11041305730069008,
      "grad_norm": 0.6571484804153442,
      "learning_rate": 2e-07,
      "loss": 0.0374,
      "step": 1183
    },
    {
      "clip_ratio/high_max": 0.00160444683933747,
      "clip_ratio/high_mean": 0.0006001115707476856,
      "clip_ratio/low_mean": 0.0006514978431368945,
      "clip_ratio/low_min": 3.748431390704354e-05,
      "clip_ratio/region_mean": 0.0012516094284364954,
      "epoch": 0.11050639040069067,
      "grad_norm": 0.1889439970254898,
      "learning_rate": 2e-07,
      "loss": 0.0266,
      "step": 1184
    },
    {
      "clip_ratio/high_max": 0.0015110461863514502,
      "clip_ratio/high_mean": 0.0006771017433493398,
      "clip_ratio/low_mean": 0.0007011533907643752,
      "clip_ratio/low_min": 2.269559627166018e-05,
      "clip_ratio/region_mean": 0.0013782551213807892,
      "epoch": 0.11059972350069125,
      "grad_norm": 0.3795429766178131,
      "learning_rate": 2e-07,
      "loss": 0.0591,
      "step": 1185
    },
    {
      "clip_ratio/high_max": 0.0016939643828663975,
      "clip_ratio/high_mean": 0.0007446527306456119,
      "clip_ratio/low_mean": 0.0006936214413144626,
      "clip_ratio/low_min": 6.161633882584283e-05,
      "clip_ratio/region_mean": 0.0014382741392182652,
      "epoch": 0.11069305660069183,
      "grad_norm": 0.17510807514190674,
      "learning_rate": 2e-07,
      "loss": 0.0186,
      "step": 1186
    },
    {
      "clip_ratio/high_max": 0.0016916420354391448,
      "clip_ratio/high_mean": 0.0006877633022668306,
      "clip_ratio/low_mean": 0.0006478916893684072,
      "clip_ratio/low_min": 4.485635872697458e-05,
      "clip_ratio/region_mean": 0.0013356550007301848,
      "epoch": 0.11078638970069242,
      "grad_norm": 0.19438563287258148,
      "learning_rate": 2e-07,
      "loss": 0.0085,
      "step": 1187
    },
    {
      "clip_ratio/high_max": 0.001742381566145923,
      "clip_ratio/high_mean": 0.0006968320249143289,
      "clip_ratio/low_mean": 0.0007700505957473069,
      "clip_ratio/low_min": 2.0587669951055432e-05,
      "clip_ratio/region_mean": 0.001466882629756583,
      "epoch": 0.110879722800693,
      "grad_norm": 0.18888793885707855,
      "learning_rate": 2e-07,
      "loss": 0.0299,
      "step": 1188
    },
    {
      "clip_ratio/high_max": 0.0018652331600605976,
      "clip_ratio/high_mean": 0.0007013054255367024,
      "clip_ratio/low_mean": 0.0007786355727148475,
      "clip_ratio/low_min": 9.107377900363645e-05,
      "clip_ratio/region_mean": 0.0014799410018895287,
      "epoch": 0.11097305590069358,
      "grad_norm": 0.1984153538942337,
      "learning_rate": 2e-07,
      "loss": 0.0069,
      "step": 1189
    },
    {
      "clip_ratio/high_max": 0.0017905516324390192,
      "clip_ratio/high_mean": 0.0007216577887447784,
      "clip_ratio/low_mean": 0.0007792749565851409,
      "clip_ratio/low_min": 7.929065304779215e-05,
      "clip_ratio/region_mean": 0.0015009327544248663,
      "epoch": 0.11106638900069417,
      "grad_norm": 0.21126650273799896,
      "learning_rate": 2e-07,
      "loss": 0.0422,
      "step": 1190
    },
    {
      "clip_ratio/high_max": 0.002048670910880901,
      "clip_ratio/high_mean": 0.0007061627829898498,
      "clip_ratio/low_mean": 0.0006752127701474819,
      "clip_ratio/low_min": 6.775066867703572e-05,
      "clip_ratio/region_mean": 0.00138137554313289,
      "epoch": 0.11115972210069475,
      "grad_norm": 0.19271402060985565,
      "learning_rate": 2e-07,
      "loss": 0.0361,
      "step": 1191
    },
    {
      "clip_ratio/high_max": 0.001685273316979874,
      "clip_ratio/high_mean": 0.0006654012759099714,
      "clip_ratio/low_mean": 0.0006931820407771738,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013585832784883678,
      "epoch": 0.11125305520069532,
      "grad_norm": 0.198637455701828,
      "learning_rate": 2e-07,
      "loss": 0.0042,
      "step": 1192
    },
    {
      "clip_ratio/high_max": 0.001722113858704688,
      "clip_ratio/high_mean": 0.0006931632315172465,
      "clip_ratio/low_mean": 0.0006796923298679758,
      "clip_ratio/low_min": 6.91401955918991e-05,
      "clip_ratio/region_mean": 0.001372855535009876,
      "epoch": 0.11134638830069592,
      "grad_norm": 0.18219062685966492,
      "learning_rate": 2e-07,
      "loss": 0.0074,
      "step": 1193
    },
    {
      "clip_ratio/high_max": 0.002046237208560342,
      "clip_ratio/high_mean": 0.0007659142074771808,
      "clip_ratio/low_mean": 0.0007704471181568806,
      "clip_ratio/low_min": 3.65534197044326e-05,
      "clip_ratio/region_mean": 0.001536361323815072,
      "epoch": 0.1114397214006965,
      "grad_norm": 0.2089175432920456,
      "learning_rate": 2e-07,
      "loss": 0.0592,
      "step": 1194
    },
    {
      "clip_ratio/high_max": 0.0019044145519728772,
      "clip_ratio/high_mean": 0.0007285121937457006,
      "clip_ratio/low_mean": 0.0007503263477701694,
      "clip_ratio/low_min": 3.495569853839697e-05,
      "clip_ratio/region_mean": 0.0014788385669817217,
      "epoch": 0.11153305450069709,
      "grad_norm": 0.27354249358177185,
      "learning_rate": 2e-07,
      "loss": 0.0253,
      "step": 1195
    },
    {
      "clip_ratio/high_max": 0.0019455743131402414,
      "clip_ratio/high_mean": 0.0006315421251201769,
      "clip_ratio/low_mean": 0.0006557920091836422,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012873341402155347,
      "epoch": 0.11162638760069767,
      "grad_norm": 0.20190535485744476,
      "learning_rate": 2e-07,
      "loss": 0.0308,
      "step": 1196
    },
    {
      "clip_ratio/high_max": 0.0018181820450990926,
      "clip_ratio/high_mean": 0.000710436375811696,
      "clip_ratio/low_mean": 0.0006786940184611012,
      "clip_ratio/low_min": 3.301770811958704e-05,
      "clip_ratio/region_mean": 0.001389130367897451,
      "epoch": 0.11171972070069824,
      "grad_norm": 0.2243601679801941,
      "learning_rate": 2e-07,
      "loss": 0.0351,
      "step": 1197
    },
    {
      "clip_ratio/high_max": 0.0019020231993636116,
      "clip_ratio/high_mean": 0.0007015543069428531,
      "clip_ratio/low_mean": 0.0006950501265237108,
      "clip_ratio/low_min": 2.49451204581419e-05,
      "clip_ratio/region_mean": 0.0013966044461994898,
      "epoch": 0.11181305380069884,
      "grad_norm": 0.2290676385164261,
      "learning_rate": 2e-07,
      "loss": 0.0718,
      "step": 1198
    },
    {
      "clip_ratio/high_max": 0.001877194405096816,
      "clip_ratio/high_mean": 0.0006861620950076031,
      "clip_ratio/low_mean": 0.0007457264309778111,
      "clip_ratio/low_min": 3.0743220122531056e-05,
      "clip_ratio/region_mean": 0.001431888493243605,
      "epoch": 0.11190638690069941,
      "grad_norm": 0.20612452924251556,
      "learning_rate": 2e-07,
      "loss": 0.022,
      "step": 1199
    },
    {
      "clip_ratio/high_max": 0.0015688790663261898,
      "clip_ratio/high_mean": 0.0006790409079258097,
      "clip_ratio/low_mean": 0.0007916213580756448,
      "clip_ratio/low_min": 8.639704719826113e-05,
      "clip_ratio/region_mean": 0.001470662267820444,
      "epoch": 0.11199972000069999,
      "grad_norm": 0.19049671292304993,
      "learning_rate": 2e-07,
      "loss": 0.0463,
      "step": 1200
    },
    {
      "clip_ratio/high_max": 0.0017373840091750026,
      "clip_ratio/high_mean": 0.0006893138870509574,
      "clip_ratio/low_mean": 0.0007801554856996518,
      "clip_ratio/low_min": 3.9624186683795415e-05,
      "clip_ratio/region_mean": 0.0014694693818455562,
      "epoch": 0.11209305310070058,
      "grad_norm": 1.0247437953948975,
      "learning_rate": 2e-07,
      "loss": 0.027,
      "step": 1201
    },
    {
      "clip_ratio/high_max": 0.0019171255153196398,
      "clip_ratio/high_mean": 0.0007347384416789282,
      "clip_ratio/low_mean": 0.0006977326065680245,
      "clip_ratio/low_min": 3.211882903997321e-05,
      "clip_ratio/region_mean": 0.0014324710573418997,
      "epoch": 0.11218638620070116,
      "grad_norm": 0.19784703850746155,
      "learning_rate": 2e-07,
      "loss": 0.0282,
      "step": 1202
    },
    {
      "clip_ratio/high_max": 0.0016217431548284367,
      "clip_ratio/high_mean": 0.0007107505480234977,
      "clip_ratio/low_mean": 0.0007161825051298365,
      "clip_ratio/low_min": 7.916795402707066e-05,
      "clip_ratio/region_mean": 0.0014269330167735461,
      "epoch": 0.11227971930070174,
      "grad_norm": 0.22832456231117249,
      "learning_rate": 2e-07,
      "loss": -0.0029,
      "step": 1203
    },
    {
      "clip_ratio/high_max": 0.0015659690252505243,
      "clip_ratio/high_mean": 0.0006774532503186492,
      "clip_ratio/low_mean": 0.0008246831148426281,
      "clip_ratio/low_min": 9.923786910803756e-05,
      "clip_ratio/region_mean": 0.0015021363651612774,
      "epoch": 0.11237305240070233,
      "grad_norm": 0.21064640581607819,
      "learning_rate": 2e-07,
      "loss": 0.0281,
      "step": 1204
    },
    {
      "clip_ratio/high_max": 0.0018564150959718972,
      "clip_ratio/high_mean": 0.0006792473377572605,
      "clip_ratio/low_mean": 0.0007403427280223696,
      "clip_ratio/low_min": 2.4791748728603125e-05,
      "clip_ratio/region_mean": 0.0014195900803315453,
      "epoch": 0.11246638550070291,
      "grad_norm": 0.19517509639263153,
      "learning_rate": 2e-07,
      "loss": 0.013,
      "step": 1205
    },
    {
      "clip_ratio/high_max": 0.001983896698220633,
      "clip_ratio/high_mean": 0.000836336228530854,
      "clip_ratio/low_mean": 0.0008409950914938236,
      "clip_ratio/low_min": 1.52587890625e-05,
      "clip_ratio/region_mean": 0.0016773313254816458,
      "epoch": 0.1125597186007035,
      "grad_norm": 0.24281498789787292,
      "learning_rate": 2e-07,
      "loss": 0.0092,
      "step": 1206
    },
    {
      "clip_ratio/high_max": 0.002194206572312396,
      "clip_ratio/high_mean": 0.0008013892238523113,
      "clip_ratio/low_mean": 0.000783125511588878,
      "clip_ratio/low_min": 0.000118052366815391,
      "clip_ratio/region_mean": 0.0015845147536310833,
      "epoch": 0.11265305170070408,
      "grad_norm": 0.20426036417484283,
      "learning_rate": 2e-07,
      "loss": -0.0153,
      "step": 1207
    },
    {
      "clip_ratio/high_max": 0.0015902157720120158,
      "clip_ratio/high_mean": 0.0006815677243139362,
      "clip_ratio/low_mean": 0.0007573332186439075,
      "clip_ratio/low_min": 5.3408847634273116e-05,
      "clip_ratio/region_mean": 0.0014389009411388543,
      "epoch": 0.11274638480070466,
      "grad_norm": 0.20530135929584503,
      "learning_rate": 2e-07,
      "loss": 0.0515,
      "step": 1208
    },
    {
      "clip_ratio/high_max": 0.0018439588639012072,
      "clip_ratio/high_mean": 0.0007493673329008743,
      "clip_ratio/low_mean": 0.0007487677066819742,
      "clip_ratio/low_min": 1.4742304301762488e-05,
      "clip_ratio/region_mean": 0.0014981350432208274,
      "epoch": 0.11283971790070525,
      "grad_norm": 0.20239122211933136,
      "learning_rate": 2e-07,
      "loss": 0.0709,
      "step": 1209
    },
    {
      "clip_ratio/high_max": 0.0018591665066196583,
      "clip_ratio/high_mean": 0.0007780405139783397,
      "clip_ratio/low_mean": 0.0007599300406582188,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0015379705546365585,
      "epoch": 0.11293305100070583,
      "grad_norm": 0.19646097719669342,
      "learning_rate": 2e-07,
      "loss": 0.0027,
      "step": 1210
    },
    {
      "clip_ratio/high_max": 0.0020803330444323365,
      "clip_ratio/high_mean": 0.0007651474443264306,
      "clip_ratio/low_mean": 0.0006152255646156846,
      "clip_ratio/low_min": 1.068924211722333e-05,
      "clip_ratio/region_mean": 0.0013803730071231257,
      "epoch": 0.11302638410070641,
      "grad_norm": 0.28694963455200195,
      "learning_rate": 2e-07,
      "loss": -0.0157,
      "step": 1211
    },
    {
      "clip_ratio/high_max": 0.0018078330758726224,
      "clip_ratio/high_mean": 0.0007627837821928551,
      "clip_ratio/low_mean": 0.00077972027247597,
      "clip_ratio/low_min": 8.40582079035812e-05,
      "clip_ratio/region_mean": 0.0015425040401169099,
      "epoch": 0.113119717200707,
      "grad_norm": 0.20485040545463562,
      "learning_rate": 2e-07,
      "loss": 0.0343,
      "step": 1212
    },
    {
      "clip_ratio/high_max": 0.0019466567609924823,
      "clip_ratio/high_mean": 0.0007239247051984421,
      "clip_ratio/low_mean": 0.0007246837212733226,
      "clip_ratio/low_min": 8.900138618628262e-05,
      "clip_ratio/region_mean": 0.0014486084037343971,
      "epoch": 0.11321305030070758,
      "grad_norm": 0.18759402632713318,
      "learning_rate": 2e-07,
      "loss": 0.0192,
      "step": 1213
    },
    {
      "clip_ratio/high_max": 0.0018263100428157486,
      "clip_ratio/high_mean": 0.000684896100210608,
      "clip_ratio/low_mean": 0.0008184543858078541,
      "clip_ratio/low_min": 5.668627272825688e-05,
      "clip_ratio/region_mean": 0.001503350489656441,
      "epoch": 0.11330638340070817,
      "grad_norm": 0.20482584834098816,
      "learning_rate": 2e-07,
      "loss": 0.0584,
      "step": 1214
    },
    {
      "clip_ratio/high_max": 0.0020009840300190262,
      "clip_ratio/high_mean": 0.0006999194465606706,
      "clip_ratio/low_mean": 0.0008477875817334279,
      "clip_ratio/low_min": 3.225402360840235e-05,
      "clip_ratio/region_mean": 0.0015477069828193635,
      "epoch": 0.11339971650070875,
      "grad_norm": 0.22164009511470795,
      "learning_rate": 2e-07,
      "loss": 0.08,
      "step": 1215
    },
    {
      "clip_ratio/high_max": 0.0020330445986473933,
      "clip_ratio/high_mean": 0.0008297775748360436,
      "clip_ratio/low_mean": 0.0008044165297178552,
      "clip_ratio/low_min": 2.7448397304397076e-05,
      "clip_ratio/region_mean": 0.0016341940936399624,
      "epoch": 0.11349304960070933,
      "grad_norm": 0.3707368075847626,
      "learning_rate": 2e-07,
      "loss": 0.0038,
      "step": 1216
    },
    {
      "clip_ratio/high_max": 0.002099720783007797,
      "clip_ratio/high_mean": 0.0008849017358443234,
      "clip_ratio/low_mean": 0.0008955090124800336,
      "clip_ratio/low_min": 8.088512367976364e-05,
      "clip_ratio/region_mean": 0.001780410711944569,
      "epoch": 0.11358638270070992,
      "grad_norm": 0.3196471333503723,
      "learning_rate": 2e-07,
      "loss": -0.005,
      "step": 1217
    },
    {
      "clip_ratio/high_max": 0.0021337432153814007,
      "clip_ratio/high_mean": 0.0008269978443422588,
      "clip_ratio/low_mean": 0.0008508307073498145,
      "clip_ratio/low_min": 5.074280579719925e-05,
      "clip_ratio/region_mean": 0.0016778285571490414,
      "epoch": 0.1136797158007105,
      "grad_norm": 0.3326951861381531,
      "learning_rate": 2e-07,
      "loss": 0.047,
      "step": 1218
    },
    {
      "clip_ratio/high_max": 0.002000450127525255,
      "clip_ratio/high_mean": 0.0008451689491266734,
      "clip_ratio/low_mean": 0.0006960581831663148,
      "clip_ratio/low_min": 0.00010058009047497762,
      "clip_ratio/region_mean": 0.0015412271532113664,
      "epoch": 0.11377304890071108,
      "grad_norm": 0.22375719249248505,
      "learning_rate": 2e-07,
      "loss": 0.0192,
      "step": 1219
    },
    {
      "clip_ratio/high_max": 0.002024498870014213,
      "clip_ratio/high_mean": 0.0008330712462338852,
      "clip_ratio/low_mean": 0.0007046140945021762,
      "clip_ratio/low_min": 1.7675340131972916e-05,
      "clip_ratio/region_mean": 0.0015376853116322309,
      "epoch": 0.11386638200071167,
      "grad_norm": 0.714872419834137,
      "learning_rate": 2e-07,
      "loss": 0.0318,
      "step": 1220
    },
    {
      "clip_ratio/high_max": 0.0020713857156806625,
      "clip_ratio/high_mean": 0.0007897193499957211,
      "clip_ratio/low_mean": 0.0009708024226711132,
      "clip_ratio/low_min": 7.287433254532516e-05,
      "clip_ratio/region_mean": 0.0017605217944947071,
      "epoch": 0.11395971510071225,
      "grad_norm": 0.4111100435256958,
      "learning_rate": 2e-07,
      "loss": 0.0545,
      "step": 1221
    },
    {
      "clip_ratio/high_max": 0.0020507228982751258,
      "clip_ratio/high_mean": 0.0007924263281893218,
      "clip_ratio/low_mean": 0.000870325202413369,
      "clip_ratio/low_min": 3.0282498300948646e-05,
      "clip_ratio/region_mean": 0.0016627515215077437,
      "epoch": 0.11405304820071283,
      "grad_norm": 0.22753064334392548,
      "learning_rate": 2e-07,
      "loss": 0.0142,
      "step": 1222
    },
    {
      "clip_ratio/high_max": 0.0019056183882639743,
      "clip_ratio/high_mean": 0.0007450067651006975,
      "clip_ratio/low_mean": 0.0008190507542167325,
      "clip_ratio/low_min": 5.385330860008253e-05,
      "clip_ratio/region_mean": 0.001564057485666126,
      "epoch": 0.11414638130071342,
      "grad_norm": 0.2049776017665863,
      "learning_rate": 2e-07,
      "loss": 0.0383,
      "step": 1223
    },
    {
      "clip_ratio/high_max": 0.0018856094902730547,
      "clip_ratio/high_mean": 0.0008538159509043908,
      "clip_ratio/low_mean": 0.0008123189745674608,
      "clip_ratio/low_min": 1.1398868991818745e-05,
      "clip_ratio/region_mean": 0.001666134900006,
      "epoch": 0.114239714400714,
      "grad_norm": 0.254228800535202,
      "learning_rate": 2e-07,
      "loss": -0.0342,
      "step": 1224
    },
    {
      "clip_ratio/high_max": 0.0018409898511890788,
      "clip_ratio/high_mean": 0.0007669665919820545,
      "clip_ratio/low_mean": 0.0007762550776533317,
      "clip_ratio/low_min": 6.346553163893986e-05,
      "clip_ratio/region_mean": 0.0015432217041961849,
      "epoch": 0.11433304750071459,
      "grad_norm": 0.19395624101161957,
      "learning_rate": 2e-07,
      "loss": 0.0313,
      "step": 1225
    },
    {
      "clip_ratio/high_max": 0.0017795385792851448,
      "clip_ratio/high_mean": 0.0006638207960349973,
      "clip_ratio/low_mean": 0.0008822498293739045,
      "clip_ratio/low_min": 4.22526900365483e-05,
      "clip_ratio/region_mean": 0.0015460706454177853,
      "epoch": 0.11442638060071517,
      "grad_norm": 0.24296225607395172,
      "learning_rate": 2e-07,
      "loss": 0.0737,
      "step": 1226
    },
    {
      "clip_ratio/high_max": 0.0017573572331457399,
      "clip_ratio/high_mean": 0.0007908931402198505,
      "clip_ratio/low_mean": 0.0008601462723163422,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001651039405260235,
      "epoch": 0.11451971370071574,
      "grad_norm": 0.2264319509267807,
      "learning_rate": 2e-07,
      "loss": 0.0174,
      "step": 1227
    },
    {
      "clip_ratio/high_max": 0.0022153178106236737,
      "clip_ratio/high_mean": 0.0009089283248613356,
      "clip_ratio/low_mean": 0.0008238453992817085,
      "clip_ratio/low_min": 1.305619389313506e-05,
      "clip_ratio/region_mean": 0.00173277373687597,
      "epoch": 0.11461304680071634,
      "grad_norm": 0.2209435999393463,
      "learning_rate": 2e-07,
      "loss": -0.0048,
      "step": 1228
    },
    {
      "clip_ratio/high_max": 0.0018664769741008058,
      "clip_ratio/high_mean": 0.0007184306732597179,
      "clip_ratio/low_mean": 0.000890397383045638,
      "clip_ratio/low_min": 8.530589002475608e-05,
      "clip_ratio/region_mean": 0.0016088280426629353,
      "epoch": 0.11470637990071691,
      "grad_norm": 0.22522087395191193,
      "learning_rate": 2e-07,
      "loss": 0.037,
      "step": 1229
    },
    {
      "clip_ratio/high_max": 0.0019802098504442256,
      "clip_ratio/high_mean": 0.000781096266109671,
      "clip_ratio/low_mean": 0.0007984326966834487,
      "clip_ratio/low_min": 7.862776419642614e-05,
      "clip_ratio/region_mean": 0.001579528943693731,
      "epoch": 0.1147997130007175,
      "grad_norm": 0.27973753213882446,
      "learning_rate": 2e-07,
      "loss": 0.0491,
      "step": 1230
    },
    {
      "clip_ratio/high_max": 0.0019337311714480165,
      "clip_ratio/high_mean": 0.000725992358638905,
      "clip_ratio/low_mean": 0.0009105347617150983,
      "clip_ratio/low_min": 8.868769236869412e-05,
      "clip_ratio/region_mean": 0.001636527136724908,
      "epoch": 0.11489304610071809,
      "grad_norm": 0.24194501340389252,
      "learning_rate": 2e-07,
      "loss": 0.0454,
      "step": 1231
    },
    {
      "clip_ratio/high_max": 0.001900083228974836,
      "clip_ratio/high_mean": 0.0007702012626396026,
      "clip_ratio/low_mean": 0.0009474192647758173,
      "clip_ratio/low_min": 6.311534752967418e-05,
      "clip_ratio/region_mean": 0.001717620536510367,
      "epoch": 0.11498637920071866,
      "grad_norm": 0.2186608910560608,
      "learning_rate": 2e-07,
      "loss": 0.0288,
      "step": 1232
    },
    {
      "clip_ratio/high_max": 0.0017413284804206342,
      "clip_ratio/high_mean": 0.0006760418291378301,
      "clip_ratio/low_mean": 0.0009517173966742121,
      "clip_ratio/low_min": 6.296036281128181e-05,
      "clip_ratio/region_mean": 0.0016277592367259786,
      "epoch": 0.11507971230071924,
      "grad_norm": 0.25317421555519104,
      "learning_rate": 2e-07,
      "loss": 0.0781,
      "step": 1233
    },
    {
      "clip_ratio/high_max": 0.001897019988973625,
      "clip_ratio/high_mean": 0.0007237795489345444,
      "clip_ratio/low_mean": 0.0010252933843730716,
      "clip_ratio/low_min": 0.00012560267714434303,
      "clip_ratio/region_mean": 0.0017490729442215525,
      "epoch": 0.11517304540071983,
      "grad_norm": 0.5316627025604248,
      "learning_rate": 2e-07,
      "loss": 0.0489,
      "step": 1234
    },
    {
      "clip_ratio/high_max": 0.002178489052312216,
      "clip_ratio/high_mean": 0.0008479114385409048,
      "clip_ratio/low_mean": 0.0009778711100807413,
      "clip_ratio/low_min": 5.8120580433751456e-05,
      "clip_ratio/region_mean": 0.0018257825940963812,
      "epoch": 0.11526637850072041,
      "grad_norm": 0.2706198990345001,
      "learning_rate": 2e-07,
      "loss": 0.0153,
      "step": 1235
    },
    {
      "clip_ratio/high_max": 0.0019815278028545436,
      "clip_ratio/high_mean": 0.0007798407968948595,
      "clip_ratio/low_mean": 0.0009915838309098035,
      "clip_ratio/low_min": 6.787551410525339e-05,
      "clip_ratio/region_mean": 0.0017714246205287054,
      "epoch": 0.115359711600721,
      "grad_norm": 0.27135396003723145,
      "learning_rate": 2e-07,
      "loss": 0.0433,
      "step": 1236
    },
    {
      "clip_ratio/high_max": 0.0022353520107571967,
      "clip_ratio/high_mean": 0.0009104317996389,
      "clip_ratio/low_mean": 0.0009735964158608112,
      "clip_ratio/low_min": 5.403306204243563e-05,
      "clip_ratio/region_mean": 0.0018840282427845523,
      "epoch": 0.11545304470072158,
      "grad_norm": 0.22792552411556244,
      "learning_rate": 2e-07,
      "loss": -0.0031,
      "step": 1237
    },
    {
      "clip_ratio/high_max": 0.0023469542757084128,
      "clip_ratio/high_mean": 0.0009543703545205062,
      "clip_ratio/low_mean": 0.0010238815448246896,
      "clip_ratio/low_min": 9.087378202821128e-05,
      "clip_ratio/region_mean": 0.001978251864784397,
      "epoch": 0.11554637780072216,
      "grad_norm": 0.2636658847332001,
      "learning_rate": 2e-07,
      "loss": 0.0291,
      "step": 1238
    },
    {
      "clip_ratio/high_max": 0.0020772560201294255,
      "clip_ratio/high_mean": 0.0008355400896107312,
      "clip_ratio/low_mean": 0.0009484115798841231,
      "clip_ratio/low_min": 5.048568709753454e-05,
      "clip_ratio/region_mean": 0.0017839516513049603,
      "epoch": 0.11563971090072275,
      "grad_norm": 0.2819897532463074,
      "learning_rate": 2e-07,
      "loss": 0.0111,
      "step": 1239
    },
    {
      "clip_ratio/high_max": 0.0021809357804158935,
      "clip_ratio/high_mean": 0.0008405055846196774,
      "clip_ratio/low_mean": 0.0010645882994140266,
      "clip_ratio/low_min": 0.00013331532500160392,
      "clip_ratio/region_mean": 0.0019050938208238222,
      "epoch": 0.11573304400072333,
      "grad_norm": 0.264545202255249,
      "learning_rate": 2e-07,
      "loss": 0.0279,
      "step": 1240
    },
    {
      "clip_ratio/high_max": 0.0022496925739687867,
      "clip_ratio/high_mean": 0.0009306902684329543,
      "clip_ratio/low_mean": 0.0011292188319202978,
      "clip_ratio/low_min": 0.00010190761440753704,
      "clip_ratio/region_mean": 0.0020599090930772945,
      "epoch": 0.11582637710072391,
      "grad_norm": 0.24554972350597382,
      "learning_rate": 2e-07,
      "loss": -0.0014,
      "step": 1241
    },
    {
      "clip_ratio/high_max": 0.0022390368467313237,
      "clip_ratio/high_mean": 0.000828416676085908,
      "clip_ratio/low_mean": 0.0010387472311776946,
      "clip_ratio/low_min": 3.668619046948152e-05,
      "clip_ratio/region_mean": 0.0018671639300009701,
      "epoch": 0.1159197102007245,
      "grad_norm": 0.22647197544574738,
      "learning_rate": 2e-07,
      "loss": 0.0207,
      "step": 1242
    },
    {
      "clip_ratio/high_max": 0.002203932628617622,
      "clip_ratio/high_mean": 0.0009421211771041271,
      "clip_ratio/low_mean": 0.0011247519796597771,
      "clip_ratio/low_min": 6.0320092416077387e-05,
      "clip_ratio/region_mean": 0.0020668731958721764,
      "epoch": 0.11601304330072508,
      "grad_norm": 0.2896707057952881,
      "learning_rate": 2e-07,
      "loss": -0.005,
      "step": 1243
    },
    {
      "clip_ratio/high_max": 0.0025299021872342564,
      "clip_ratio/high_mean": 0.0009991048427764326,
      "clip_ratio/low_mean": 0.0011080071853939444,
      "clip_ratio/low_min": 0.00010431809414512827,
      "clip_ratio/region_mean": 0.0021071120354463346,
      "epoch": 0.11610637640072566,
      "grad_norm": 0.3097783327102661,
      "learning_rate": 2e-07,
      "loss": 0.0091,
      "step": 1244
    },
    {
      "clip_ratio/high_max": 0.002371006085013505,
      "clip_ratio/high_mean": 0.0009061949276656378,
      "clip_ratio/low_mean": 0.0011595743635552935,
      "clip_ratio/low_min": 0.0001039442695400794,
      "clip_ratio/region_mean": 0.002065769280306995,
      "epoch": 0.11619970950072625,
      "grad_norm": 0.3064813017845154,
      "learning_rate": 2e-07,
      "loss": 0.0251,
      "step": 1245
    },
    {
      "clip_ratio/high_max": 0.0021198121685301885,
      "clip_ratio/high_mean": 0.000794113875599578,
      "clip_ratio/low_mean": 0.0010648207353369799,
      "clip_ratio/low_min": 2.5150904548354447e-05,
      "clip_ratio/region_mean": 0.0018589346218504943,
      "epoch": 0.11629304260072683,
      "grad_norm": 0.2669926583766937,
      "learning_rate": 2e-07,
      "loss": 0.0063,
      "step": 1246
    },
    {
      "clip_ratio/high_max": 0.0022307105900836177,
      "clip_ratio/high_mean": 0.0009355627607874339,
      "clip_ratio/low_mean": 0.0011419211368774995,
      "clip_ratio/low_min": 0.00011037421700166306,
      "clip_ratio/region_mean": 0.0020774839067598805,
      "epoch": 0.11638637570072742,
      "grad_norm": 0.36085245013237,
      "learning_rate": 2e-07,
      "loss": 0.0548,
      "step": 1247
    },
    {
      "clip_ratio/high_max": 0.002027619550062809,
      "clip_ratio/high_mean": 0.00095057726775849,
      "clip_ratio/low_mean": 0.0011686959514918271,
      "clip_ratio/low_min": 6.969452624616679e-05,
      "clip_ratio/region_mean": 0.0021192732092458755,
      "epoch": 0.116479708800728,
      "grad_norm": 0.4071381390094757,
      "learning_rate": 2e-07,
      "loss": 0.0299,
      "step": 1248
    },
    {
      "clip_ratio/high_max": 0.002617474030557787,
      "clip_ratio/high_mean": 0.0009693719202914508,
      "clip_ratio/low_mean": 0.0011475475312181516,
      "clip_ratio/low_min": 6.0778689658036456e-05,
      "clip_ratio/region_mean": 0.0021169194660615176,
      "epoch": 0.11657304190072858,
      "grad_norm": 0.33404529094696045,
      "learning_rate": 2e-07,
      "loss": 0.0039,
      "step": 1249
    },
    {
      "clip_ratio/high_max": 0.002880485095374752,
      "clip_ratio/high_mean": 0.0011259794227953535,
      "clip_ratio/low_mean": 0.0012842701544286683,
      "clip_ratio/low_min": 0.0001142452092608437,
      "clip_ratio/region_mean": 0.002410249595413916,
      "epoch": 0.11666637500072917,
      "grad_norm": 0.44753509759902954,
      "learning_rate": 2e-07,
      "loss": 0.0088,
      "step": 1250
    },
    {
      "clip_ratio/high_max": 0.0024234193697338924,
      "clip_ratio/high_mean": 0.0009820406485232525,
      "clip_ratio/low_mean": 0.0011096184953203192,
      "clip_ratio/low_min": 3.582346107577905e-05,
      "clip_ratio/region_mean": 0.0020916591529385187,
      "epoch": 0.11675970810072975,
      "grad_norm": 0.344949871301651,
      "learning_rate": 2e-07,
      "loss": -0.0198,
      "step": 1251
    },
    {
      "clip_ratio/high_max": 0.00233278968698869,
      "clip_ratio/high_mean": 0.0010195172853855183,
      "clip_ratio/low_mean": 0.0014176431031955872,
      "clip_ratio/low_min": 2.1950244445179123e-05,
      "clip_ratio/region_mean": 0.0024371604013140313,
      "epoch": 0.11685304120073033,
      "grad_norm": 0.32029810547828674,
      "learning_rate": 2e-07,
      "loss": 0.0344,
      "step": 1252
    },
    {
      "clip_ratio/high_max": 0.0024745127229834907,
      "clip_ratio/high_mean": 0.0009009738223539898,
      "clip_ratio/low_mean": 0.001625277058337815,
      "clip_ratio/low_min": 0.0002985634873766685,
      "clip_ratio/region_mean": 0.002526250886148773,
      "epoch": 0.11694637430073092,
      "grad_norm": 0.46875813603401184,
      "learning_rate": 2e-07,
      "loss": 0.0756,
      "step": 1253
    },
    {
      "clip_ratio/high_max": 0.002519101166399196,
      "clip_ratio/high_mean": 0.0010257409157929942,
      "clip_ratio/low_mean": 0.0011413073443691246,
      "clip_ratio/low_min": 6.12545636613504e-05,
      "clip_ratio/region_mean": 0.0021670482674380764,
      "epoch": 0.1170397074007315,
      "grad_norm": 0.3189603090286255,
      "learning_rate": 2e-07,
      "loss": 0.0067,
      "step": 1254
    },
    {
      "clip_ratio/high_max": 0.002456131602230016,
      "clip_ratio/high_mean": 0.0009900657387333922,
      "clip_ratio/low_mean": 0.001537556938274065,
      "clip_ratio/low_min": 0.00010477024534338852,
      "clip_ratio/region_mean": 0.002527622658817563,
      "epoch": 0.11713304050073207,
      "grad_norm": 0.3813420534133911,
      "learning_rate": 2e-07,
      "loss": 0.0401,
      "step": 1255
    },
    {
      "clip_ratio/high_max": 0.0022081926217651926,
      "clip_ratio/high_mean": 0.0009666876030678395,
      "clip_ratio/low_mean": 0.0014399002284335438,
      "clip_ratio/low_min": 0.00020513307026703842,
      "clip_ratio/region_mean": 0.0024065878460532986,
      "epoch": 0.11722637360073267,
      "grad_norm": 0.504207193851471,
      "learning_rate": 2e-07,
      "loss": -0.0039,
      "step": 1256
    },
    {
      "clip_ratio/high_max": 0.0024596137373009697,
      "clip_ratio/high_mean": 0.000986370921964408,
      "clip_ratio/low_mean": 0.0015320670936489478,
      "clip_ratio/low_min": 6.149632781671244e-05,
      "clip_ratio/region_mean": 0.0025184379919664934,
      "epoch": 0.11731970670073325,
      "grad_norm": 0.46205493807792664,
      "learning_rate": 2e-07,
      "loss": 0.0752,
      "step": 1257
    },
    {
      "clip_ratio/high_max": 0.0025536917528370395,
      "clip_ratio/high_mean": 0.0011049027634726372,
      "clip_ratio/low_mean": 0.0016272512002615258,
      "clip_ratio/low_min": 0.00017271660908591002,
      "clip_ratio/region_mean": 0.002732154040131718,
      "epoch": 0.11741303980073384,
      "grad_norm": 0.3714674413204193,
      "learning_rate": 2e-07,
      "loss": 0.0302,
      "step": 1258
    },
    {
      "clip_ratio/high_max": 0.0025925065856426954,
      "clip_ratio/high_mean": 0.0010730062967923004,
      "clip_ratio/low_mean": 0.0016265659724012949,
      "clip_ratio/low_min": 1.552795038151089e-05,
      "clip_ratio/region_mean": 0.0026995722073479556,
      "epoch": 0.11750637290073442,
      "grad_norm": 0.7046552300453186,
      "learning_rate": 2e-07,
      "loss": -0.0023,
      "step": 1259
    },
    {
      "clip_ratio/high_max": 0.002735358186328085,
      "clip_ratio/high_mean": 0.001097457914511324,
      "clip_ratio/low_mean": 0.0015978077572071925,
      "clip_ratio/low_min": 9.329971271654358e-05,
      "clip_ratio/region_mean": 0.0026952657208312303,
      "epoch": 0.117599706000735,
      "grad_norm": 0.48868218064308167,
      "learning_rate": 2e-07,
      "loss": 0.032,
      "step": 1260
    },
    {
      "clip_ratio/high_max": 0.0026208938434137963,
      "clip_ratio/high_mean": 0.001101096404454438,
      "clip_ratio/low_mean": 0.001882253673102241,
      "clip_ratio/low_min": 0.000211413343095046,
      "clip_ratio/region_mean": 0.0029833500520908274,
      "epoch": 0.11769303910073559,
      "grad_norm": 2.799860954284668,
      "learning_rate": 2e-07,
      "loss": 0.0323,
      "step": 1261
    },
    {
      "clip_ratio/high_max": 0.0031540299460175447,
      "clip_ratio/high_mean": 0.001206015947900596,
      "clip_ratio/low_mean": 0.0017915620264830068,
      "clip_ratio/low_min": 7.583280057588127e-05,
      "clip_ratio/region_mean": 0.0029975780416862108,
      "epoch": 0.11778637220073616,
      "grad_norm": 0.7450904846191406,
      "learning_rate": 2e-07,
      "loss": 0.051,
      "step": 1262
    },
    {
      "clip_ratio/high_max": 0.003167201590258628,
      "clip_ratio/high_mean": 0.0012370877011562698,
      "clip_ratio/low_mean": 0.001741114494507201,
      "clip_ratio/low_min": 0.00010033375656348653,
      "clip_ratio/region_mean": 0.002978202188387513,
      "epoch": 0.11787970530073674,
      "grad_norm": 0.38404929637908936,
      "learning_rate": 2e-07,
      "loss": 0.0149,
      "step": 1263
    },
    {
      "clip_ratio/high_max": 0.0028844203043263406,
      "clip_ratio/high_mean": 0.0011909350942005403,
      "clip_ratio/low_mean": 0.0018382909038336948,
      "clip_ratio/low_min": 0.000245137669480755,
      "clip_ratio/region_mean": 0.003029225998034235,
      "epoch": 0.11797303840073733,
      "grad_norm": 0.4256778061389923,
      "learning_rate": 2e-07,
      "loss": -0.0039,
      "step": 1264
    },
    {
      "clip_ratio/high_max": 0.0028122517105657607,
      "clip_ratio/high_mean": 0.0012796037590305787,
      "clip_ratio/low_mean": 0.0017838043859228492,
      "clip_ratio/low_min": 0.0001962625829037279,
      "clip_ratio/region_mean": 0.0030634080758318305,
      "epoch": 0.11806637150073791,
      "grad_norm": 0.5721672773361206,
      "learning_rate": 2e-07,
      "loss": 0.0035,
      "step": 1265
    },
    {
      "clip_ratio/high_max": 0.002727821694861632,
      "clip_ratio/high_mean": 0.0011192643833055627,
      "clip_ratio/low_mean": 0.0017919084712048061,
      "clip_ratio/low_min": 7.88146280683577e-05,
      "clip_ratio/region_mean": 0.0029111727853887714,
      "epoch": 0.1181597046007385,
      "grad_norm": 0.5882701873779297,
      "learning_rate": 2e-07,
      "loss": 0.0431,
      "step": 1266
    },
    {
      "clip_ratio/high_max": 0.003068051693844609,
      "clip_ratio/high_mean": 0.0013537121703848243,
      "clip_ratio/low_mean": 0.002128494350472465,
      "clip_ratio/low_min": 0.0001546155799587723,
      "clip_ratio/region_mean": 0.0034822066299966536,
      "epoch": 0.11825303770073908,
      "grad_norm": 0.5249460339546204,
      "learning_rate": 2e-07,
      "loss": 0.0302,
      "step": 1267
    },
    {
      "clip_ratio/high_max": 0.00276425524498336,
      "clip_ratio/high_mean": 0.0010690280796552543,
      "clip_ratio/low_mean": 0.0020647762939915992,
      "clip_ratio/low_min": 0.00010719466808950529,
      "clip_ratio/region_mean": 0.0031338044645963237,
      "epoch": 0.11834637080073966,
      "grad_norm": 0.4720554053783417,
      "learning_rate": 2e-07,
      "loss": 0.0449,
      "step": 1268
    },
    {
      "clip_ratio/high_max": 0.0036265780217945576,
      "clip_ratio/high_mean": 0.0014240723357943352,
      "clip_ratio/low_mean": 0.001985043694730848,
      "clip_ratio/low_min": 4.992012691218406e-05,
      "clip_ratio/region_mean": 0.0034091159905074164,
      "epoch": 0.11843970390074025,
      "grad_norm": 0.5207564234733582,
      "learning_rate": 2e-07,
      "loss": -0.0582,
      "step": 1269
    },
    {
      "clip_ratio/high_max": 0.0033109773212345317,
      "clip_ratio/high_mean": 0.001432134238712024,
      "clip_ratio/low_mean": 0.0018958529108203948,
      "clip_ratio/low_min": 7.71102168073412e-05,
      "clip_ratio/region_mean": 0.003327987200464122,
      "epoch": 0.11853303700074083,
      "grad_norm": 0.7054007053375244,
      "learning_rate": 2e-07,
      "loss": -0.0191,
      "step": 1270
    },
    {
      "clip_ratio/high_max": 0.0032682332530384883,
      "clip_ratio/high_mean": 0.001393673795973882,
      "clip_ratio/low_mean": 0.0021051197982160375,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.003498793550534174,
      "epoch": 0.11862637010074141,
      "grad_norm": 0.6108861565589905,
      "learning_rate": 2e-07,
      "loss": 0.0299,
      "step": 1271
    },
    {
      "clip_ratio/high_max": 0.002487627265509218,
      "clip_ratio/high_mean": 0.0011024959057976957,
      "clip_ratio/low_mean": 0.0022015903850842733,
      "clip_ratio/low_min": 0.00026101561161340214,
      "clip_ratio/region_mean": 0.0033040861453628168,
      "epoch": 0.118719703200742,
      "grad_norm": 1.3555997610092163,
      "learning_rate": 2e-07,
      "loss": 0.0836,
      "step": 1272
    },
    {
      "clip_ratio/high_max": 0.002986916821100749,
      "clip_ratio/high_mean": 0.0013136349589331076,
      "clip_ratio/low_mean": 0.0024058460985543206,
      "clip_ratio/low_min": 0.00019249199249316007,
      "clip_ratio/region_mean": 0.003719481101143174,
      "epoch": 0.11881303630074258,
      "grad_norm": 0.7471872568130493,
      "learning_rate": 2e-07,
      "loss": 0.0094,
      "step": 1273
    },
    {
      "clip_ratio/high_max": 0.002896909831179073,
      "clip_ratio/high_mean": 0.0012772270256391494,
      "clip_ratio/low_mean": 0.0026320864853914827,
      "clip_ratio/low_min": 0.0003585569720598869,
      "clip_ratio/region_mean": 0.003909313600161113,
      "epoch": 0.11890636940074316,
      "grad_norm": 2.183903694152832,
      "learning_rate": 2e-07,
      "loss": 0.0237,
      "step": 1274
    },
    {
      "clip_ratio/high_max": 0.0030761242160224356,
      "clip_ratio/high_mean": 0.0012256988757144427,
      "clip_ratio/low_mean": 0.002636407130921725,
      "clip_ratio/low_min": 0.0001596409874764504,
      "clip_ratio/region_mean": 0.0038621058483840898,
      "epoch": 0.11899970250074375,
      "grad_norm": 0.8792387843132019,
      "learning_rate": 2e-07,
      "loss": 0.027,
      "step": 1275
    },
    {
      "clip_ratio/high_max": 0.003158247818646487,
      "clip_ratio/high_mean": 0.001368365679809358,
      "clip_ratio/low_mean": 0.002628737478516996,
      "clip_ratio/low_min": 0.0002497493005648721,
      "clip_ratio/region_mean": 0.003997103223809972,
      "epoch": 0.11909303560074433,
      "grad_norm": 0.6177733540534973,
      "learning_rate": 2e-07,
      "loss": 0.0388,
      "step": 1276
    },
    {
      "clip_ratio/high_max": 0.0032810780394356698,
      "clip_ratio/high_mean": 0.0013804125264869072,
      "clip_ratio/low_mean": 0.00288650539732771,
      "clip_ratio/low_min": 0.00020459869847400114,
      "clip_ratio/region_mean": 0.004266917865606956,
      "epoch": 0.11918636870074492,
      "grad_norm": 1.0134904384613037,
      "learning_rate": 2e-07,
      "loss": 0.0349,
      "step": 1277
    },
    {
      "clip_ratio/high_max": 0.002939303609309718,
      "clip_ratio/high_mean": 0.0012806854101654608,
      "clip_ratio/low_mean": 0.0030248586590460036,
      "clip_ratio/low_min": 0.00018192952848039567,
      "clip_ratio/region_mean": 0.004305544163798913,
      "epoch": 0.1192797018007455,
      "grad_norm": 11.782687187194824,
      "learning_rate": 2e-07,
      "loss": 0.0426,
      "step": 1278
    },
    {
      "clip_ratio/high_max": 0.00342243084742222,
      "clip_ratio/high_mean": 0.00147415674655349,
      "clip_ratio/low_mean": 0.0028162228991277516,
      "clip_ratio/low_min": 0.00022035415895516053,
      "clip_ratio/region_mean": 0.004290379656595178,
      "epoch": 0.11937303490074608,
      "grad_norm": 1.0729273557662964,
      "learning_rate": 2e-07,
      "loss": 0.0749,
      "step": 1279
    },
    {
      "clip_ratio/high_max": 0.0031264541103155352,
      "clip_ratio/high_mean": 0.001497796238254523,
      "clip_ratio/low_mean": 0.0035184046646463685,
      "clip_ratio/low_min": 0.0007855840085539967,
      "clip_ratio/region_mean": 0.005016200899262913,
      "epoch": 0.11946636800074667,
      "grad_norm": 2.210545539855957,
      "learning_rate": 2e-07,
      "loss": 0.0771,
      "step": 1280
    },
    {
      "clip_ratio/high_max": 0.0023413691742462106,
      "clip_ratio/high_mean": 0.0010135633710888214,
      "clip_ratio/low_mean": 0.0009388794896949548,
      "clip_ratio/low_min": 4.8965136556944344e-05,
      "clip_ratio/region_mean": 0.0019524428353179246,
      "completions/clipped_ratio": 0.0215541294642857,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4082.0,
      "completions/mean_length": 671.4013671875,
      "completions/mean_terminated_length": 595.9610595703125,
      "completions/min_length": 34.0,
      "completions/min_terminated_length": 34.0,
      "epoch": 0.11955970110074725,
      "grad_norm": 0.3834778070449829,
      "learning_rate": 2e-07,
      "loss": 0.0525,
      "num_tokens": 941233261.0,
      "reward": 0.5243879556655884,
      "reward_std": 0.21293023228645325,
      "rewards/simpleverify_reward/mean": 0.5243878960609436,
      "rewards/simpleverify_reward/std": 0.49940696358680725,
      "step": 1281
    },
    {
      "clip_ratio/high_max": 0.0020347327226772904,
      "clip_ratio/high_mean": 0.0009602001373423263,
      "clip_ratio/low_mean": 0.001020225347019732,
      "clip_ratio/low_min": 0.00013646185561810853,
      "clip_ratio/region_mean": 0.0019804254843620583,
      "epoch": 0.11965303420074783,
      "grad_norm": 0.2966500520706177,
      "learning_rate": 2e-07,
      "loss": 0.0475,
      "step": 1282
    },
    {
      "clip_ratio/high_max": 0.002555000246502459,
      "clip_ratio/high_mean": 0.0010961001044051955,
      "clip_ratio/low_mean": 0.0009353373934573028,
      "clip_ratio/low_min": 8.127438377414364e-06,
      "clip_ratio/region_mean": 0.002031437477853615,
      "epoch": 0.11974636730074842,
      "grad_norm": 0.33522093296051025,
      "learning_rate": 2e-07,
      "loss": 0.0165,
      "step": 1283
    },
    {
      "clip_ratio/high_max": 0.00230565297533758,
      "clip_ratio/high_mean": 0.0009652054832258727,
      "clip_ratio/low_mean": 0.0010196077964792494,
      "clip_ratio/low_min": 0.0001025043020490557,
      "clip_ratio/region_mean": 0.0019848132506012917,
      "epoch": 0.119839700400749,
      "grad_norm": 0.5380664467811584,
      "learning_rate": 2e-07,
      "loss": 0.0765,
      "step": 1284
    },
    {
      "clip_ratio/high_max": 0.002197891481046099,
      "clip_ratio/high_mean": 0.0009522697691863868,
      "clip_ratio/low_mean": 0.0011757086867874023,
      "clip_ratio/low_min": 0.00015661427096347325,
      "clip_ratio/region_mean": 0.0021279784268699586,
      "epoch": 0.11993303350074958,
      "grad_norm": 0.43300870060920715,
      "learning_rate": 2e-07,
      "loss": 0.0827,
      "step": 1285
    },
    {
      "clip_ratio/high_max": 0.002477598929544911,
      "clip_ratio/high_mean": 0.0009411834453203483,
      "clip_ratio/low_mean": 0.000982248118816642,
      "clip_ratio/low_min": 8.634273399366066e-05,
      "clip_ratio/region_mean": 0.0019234315950598102,
      "epoch": 0.12002636660075017,
      "grad_norm": 0.35375577211380005,
      "learning_rate": 2e-07,
      "loss": 0.039,
      "step": 1286
    },
    {
      "clip_ratio/high_max": 0.002343535757972859,
      "clip_ratio/high_mean": 0.0008841321068757679,
      "clip_ratio/low_mean": 0.0011539738879946526,
      "clip_ratio/low_min": 0.00014537928745994577,
      "clip_ratio/region_mean": 0.0020381060094223358,
      "epoch": 0.12011969970075075,
      "grad_norm": 0.33422353863716125,
      "learning_rate": 2e-07,
      "loss": 0.0873,
      "step": 1287
    },
    {
      "clip_ratio/high_max": 0.0025650129027781077,
      "clip_ratio/high_mean": 0.0011427720564824995,
      "clip_ratio/low_mean": 0.001230161615239922,
      "clip_ratio/low_min": 0.00011141854884044733,
      "clip_ratio/region_mean": 0.0023729336680844426,
      "epoch": 0.12021303280075134,
      "grad_norm": 4.751442909240723,
      "learning_rate": 2e-07,
      "loss": 0.0397,
      "step": 1288
    },
    {
      "clip_ratio/high_max": 0.002297170529345749,
      "clip_ratio/high_mean": 0.0009166823238047073,
      "clip_ratio/low_mean": 0.001126035705965478,
      "clip_ratio/low_min": 7.653410921193426e-05,
      "clip_ratio/region_mean": 0.0020427180206752382,
      "epoch": 0.12030636590075192,
      "grad_norm": 0.32877787947654724,
      "learning_rate": 2e-07,
      "loss": 0.059,
      "step": 1289
    },
    {
      "clip_ratio/high_max": 0.0021408290158433374,
      "clip_ratio/high_mean": 0.0008801896019576816,
      "clip_ratio/low_mean": 0.0010973331482091453,
      "clip_ratio/low_min": 0.00011789333439082839,
      "clip_ratio/region_mean": 0.0019775227265199646,
      "epoch": 0.1203996990007525,
      "grad_norm": 0.4919995665550232,
      "learning_rate": 2e-07,
      "loss": 0.1112,
      "step": 1290
    },
    {
      "clip_ratio/high_max": 0.0022090027123340406,
      "clip_ratio/high_mean": 0.0008994097606773721,
      "clip_ratio/low_mean": 0.0011504152298584813,
      "clip_ratio/low_min": 9.001138550956966e-05,
      "clip_ratio/region_mean": 0.002049825052381493,
      "epoch": 0.12049303210075309,
      "grad_norm": 0.5051014423370361,
      "learning_rate": 2e-07,
      "loss": 0.067,
      "step": 1291
    },
    {
      "clip_ratio/high_max": 0.0023545578005723655,
      "clip_ratio/high_mean": 0.0008758909316384234,
      "clip_ratio/low_mean": 0.0013859239952580538,
      "clip_ratio/low_min": 0.00016144527398864739,
      "clip_ratio/region_mean": 0.0022618149523623288,
      "epoch": 0.12058636520075366,
      "grad_norm": 115.59944915771484,
      "learning_rate": 2e-07,
      "loss": 0.197,
      "step": 1292
    },
    {
      "clip_ratio/high_max": 0.0018417898900224827,
      "clip_ratio/high_mean": 0.0007766663547954522,
      "clip_ratio/low_mean": 0.0012268044338270556,
      "clip_ratio/low_min": 0.00018717734928941354,
      "clip_ratio/region_mean": 0.002003470784984529,
      "epoch": 0.12067969830075424,
      "grad_norm": 0.4201187789440155,
      "learning_rate": 2e-07,
      "loss": 0.1337,
      "step": 1293
    },
    {
      "clip_ratio/high_max": 0.0024212099888245575,
      "clip_ratio/high_mean": 0.0009775580874702428,
      "clip_ratio/low_mean": 0.0012244309909874573,
      "clip_ratio/low_min": 0.00010023408685810864,
      "clip_ratio/region_mean": 0.0022019890529918484,
      "epoch": 0.12077303140075484,
      "grad_norm": 0.41988644003868103,
      "learning_rate": 2e-07,
      "loss": 0.0727,
      "step": 1294
    },
    {
      "clip_ratio/high_max": 0.0020032688044011593,
      "clip_ratio/high_mean": 0.0008800951563898707,
      "clip_ratio/low_mean": 0.001249365639523603,
      "clip_ratio/low_min": 0.0001791750446500373,
      "clip_ratio/region_mean": 0.00212946083775023,
      "epoch": 0.12086636450075541,
      "grad_norm": 0.37629029154777527,
      "learning_rate": 2e-07,
      "loss": 0.0758,
      "step": 1295
    },
    {
      "clip_ratio/high_max": 0.002368358167586848,
      "clip_ratio/high_mean": 0.0010499121453904081,
      "clip_ratio/low_mean": 0.001326764813711634,
      "clip_ratio/low_min": 0.0001260784019905259,
      "clip_ratio/region_mean": 0.0023766769736539572,
      "epoch": 0.12095969760075599,
      "grad_norm": 0.5631283521652222,
      "learning_rate": 2e-07,
      "loss": 0.0986,
      "step": 1296
    },
    {
      "clip_ratio/high_max": 0.0028794024510716554,
      "clip_ratio/high_mean": 0.001141504870247445,
      "clip_ratio/low_mean": 0.0011226633050682722,
      "clip_ratio/low_min": 5.687962402589619e-05,
      "clip_ratio/region_mean": 0.002264168178953696,
      "epoch": 0.12105303070075658,
      "grad_norm": 0.3497691750526428,
      "learning_rate": 2e-07,
      "loss": -0.0331,
      "step": 1297
    },
    {
      "clip_ratio/high_max": 0.002290142307174392,
      "clip_ratio/high_mean": 0.0010665492409316357,
      "clip_ratio/low_mean": 0.0013688798935618252,
      "clip_ratio/low_min": 0.00015799380162206944,
      "clip_ratio/region_mean": 0.00243542916723527,
      "epoch": 0.12114636380075716,
      "grad_norm": 2.3204498291015625,
      "learning_rate": 2e-07,
      "loss": 0.0627,
      "step": 1298
    },
    {
      "clip_ratio/high_max": 0.0025484256220806856,
      "clip_ratio/high_mean": 0.0010651455777406227,
      "clip_ratio/low_mean": 0.0012972953445569146,
      "clip_ratio/low_min": 0.00012076652819814626,
      "clip_ratio/region_mean": 0.0023624409150215797,
      "epoch": 0.12123969690075775,
      "grad_norm": 1.3894912004470825,
      "learning_rate": 2e-07,
      "loss": 0.1373,
      "step": 1299
    },
    {
      "clip_ratio/high_max": 0.0024318516516359523,
      "clip_ratio/high_mean": 0.0010606912401271984,
      "clip_ratio/low_mean": 0.0014953310856071766,
      "clip_ratio/low_min": 0.00025038547573785763,
      "clip_ratio/region_mean": 0.0025560223875800148,
      "epoch": 0.12133303000075833,
      "grad_norm": 1.6366043090820312,
      "learning_rate": 2e-07,
      "loss": 0.0487,
      "step": 1300
    },
    {
      "clip_ratio/high_max": 0.002639939477376174,
      "clip_ratio/high_mean": 0.0010795494199555833,
      "clip_ratio/low_mean": 0.0013610879541374743,
      "clip_ratio/low_min": 0.0002206603548984276,
      "clip_ratio/region_mean": 0.0024406374141108245,
      "epoch": 0.12142636310075891,
      "grad_norm": 0.6557591557502747,
      "learning_rate": 2e-07,
      "loss": 0.0426,
      "step": 1301
    },
    {
      "clip_ratio/high_max": 0.0024565923813497648,
      "clip_ratio/high_mean": 0.0009701868584670592,
      "clip_ratio/low_mean": 0.0015762503317091614,
      "clip_ratio/low_min": 0.00013898547877033707,
      "clip_ratio/region_mean": 0.0025464371938141994,
      "epoch": 0.1215196962007595,
      "grad_norm": 0.48896560072898865,
      "learning_rate": 2e-07,
      "loss": 0.0727,
      "step": 1302
    },
    {
      "clip_ratio/high_max": 0.0026297317817807198,
      "clip_ratio/high_mean": 0.0011425617121858522,
      "clip_ratio/low_mean": 0.001752933872921858,
      "clip_ratio/low_min": 0.00023350463379756548,
      "clip_ratio/region_mean": 0.002895495606935583,
      "epoch": 0.12161302930076008,
      "grad_norm": 1.0576187372207642,
      "learning_rate": 2e-07,
      "loss": 0.0877,
      "step": 1303
    },
    {
      "clip_ratio/high_max": 0.0025416556673008017,
      "clip_ratio/high_mean": 0.0011352275032550097,
      "clip_ratio/low_mean": 0.0015676365728722885,
      "clip_ratio/low_min": 9.258618592866696e-05,
      "clip_ratio/region_mean": 0.0027028641270590015,
      "epoch": 0.12170636240076066,
      "grad_norm": 89.3762435913086,
      "learning_rate": 2e-07,
      "loss": 0.0277,
      "step": 1304
    },
    {
      "clip_ratio/high_max": 0.002416131268546451,
      "clip_ratio/high_mean": 0.0009025474937516265,
      "clip_ratio/low_mean": 0.0017851245429483242,
      "clip_ratio/low_min": 0.00012899404919153312,
      "clip_ratio/region_mean": 0.002687672051251866,
      "epoch": 0.12179969550076125,
      "grad_norm": 7.530352592468262,
      "learning_rate": 2e-07,
      "loss": 0.0824,
      "step": 1305
    },
    {
      "clip_ratio/high_max": 0.0029166760432417504,
      "clip_ratio/high_mean": 0.0010477814794285223,
      "clip_ratio/low_mean": 0.001903841271996498,
      "clip_ratio/low_min": 0.00017777964058041107,
      "clip_ratio/region_mean": 0.0029516228023567237,
      "epoch": 0.12189302860076183,
      "grad_norm": 0.7220433950424194,
      "learning_rate": 2e-07,
      "loss": 0.1223,
      "step": 1306
    },
    {
      "clip_ratio/high_max": 0.0028752483340213075,
      "clip_ratio/high_mean": 0.0010810449966811575,
      "clip_ratio/low_mean": 0.0020802442813874222,
      "clip_ratio/low_min": 0.00028315925010247156,
      "clip_ratio/region_mean": 0.00316128930717241,
      "epoch": 0.12198636170076241,
      "grad_norm": 4.103100299835205,
      "learning_rate": 2e-07,
      "loss": 0.0671,
      "step": 1307
    },
    {
      "clip_ratio/high_max": 0.0027585926873143762,
      "clip_ratio/high_mean": 0.0012272206404304598,
      "clip_ratio/low_mean": 0.002018750623392407,
      "clip_ratio/low_min": 0.0002049338654614985,
      "clip_ratio/region_mean": 0.0032459712092531845,
      "epoch": 0.122079694800763,
      "grad_norm": 2.666363477706909,
      "learning_rate": 2e-07,
      "loss": 0.0322,
      "step": 1308
    },
    {
      "clip_ratio/high_max": 0.0029222180201031733,
      "clip_ratio/high_mean": 0.0012271265277377097,
      "clip_ratio/low_mean": 0.0019240626352257095,
      "clip_ratio/low_min": 0.0003377426000952255,
      "clip_ratio/region_mean": 0.0031511891720583662,
      "epoch": 0.12217302790076358,
      "grad_norm": 5.617126941680908,
      "learning_rate": 2e-07,
      "loss": 0.0843,
      "step": 1309
    },
    {
      "clip_ratio/high_max": 0.0028127822588430718,
      "clip_ratio/high_mean": 0.0012317429609538522,
      "clip_ratio/low_mean": 0.002120734927302692,
      "clip_ratio/low_min": 0.00025279479268647265,
      "clip_ratio/region_mean": 0.0033524778846185654,
      "epoch": 0.12226636100076417,
      "grad_norm": 1.0410999059677124,
      "learning_rate": 2e-07,
      "loss": 0.1051,
      "step": 1310
    },
    {
      "clip_ratio/high_max": 0.0027450981942820363,
      "clip_ratio/high_mean": 0.0011484237693366595,
      "clip_ratio/low_mean": 0.0021880975473322906,
      "clip_ratio/low_min": 5.8360145885671955e-05,
      "clip_ratio/region_mean": 0.0033365212875651196,
      "epoch": 0.12235969410076475,
      "grad_norm": 6.011181354522705,
      "learning_rate": 2e-07,
      "loss": 0.0833,
      "step": 1311
    },
    {
      "clip_ratio/high_max": 0.00256658283615252,
      "clip_ratio/high_mean": 0.0012264629858691478,
      "clip_ratio/low_mean": 0.0025807344500208274,
      "clip_ratio/low_min": 0.0005743810470448807,
      "clip_ratio/region_mean": 0.0038071974413469434,
      "epoch": 0.12245302720076533,
      "grad_norm": 20.54705810546875,
      "learning_rate": 2e-07,
      "loss": 0.0776,
      "step": 1312
    },
    {
      "clip_ratio/high_max": 0.003388223449292127,
      "clip_ratio/high_mean": 0.001424372363544535,
      "clip_ratio/low_mean": 0.002528334269300103,
      "clip_ratio/low_min": 0.00027897344443772454,
      "clip_ratio/region_mean": 0.00395270659646485,
      "epoch": 0.12254636030076592,
      "grad_norm": 1.5548619031906128,
      "learning_rate": 2e-07,
      "loss": 0.0635,
      "step": 1313
    },
    {
      "clip_ratio/high_max": 0.003321803524158895,
      "clip_ratio/high_mean": 0.0013250306619738694,
      "clip_ratio/low_mean": 0.0023411684596794657,
      "clip_ratio/low_min": 0.000234968361837673,
      "clip_ratio/region_mean": 0.0036661991180153564,
      "epoch": 0.1226396934007665,
      "grad_norm": 2.387840986251831,
      "learning_rate": 2e-07,
      "loss": 0.0263,
      "step": 1314
    },
    {
      "clip_ratio/high_max": 0.003023161021701526,
      "clip_ratio/high_mean": 0.001289168998482637,
      "clip_ratio/low_mean": 0.0028119789676566143,
      "clip_ratio/low_min": 0.0003713697633429547,
      "clip_ratio/region_mean": 0.004101147947949357,
      "epoch": 0.12273302650076708,
      "grad_norm": 1.8666458129882812,
      "learning_rate": 2e-07,
      "loss": 0.081,
      "step": 1315
    },
    {
      "clip_ratio/high_max": 0.0033762019229470752,
      "clip_ratio/high_mean": 0.0015177727364061866,
      "clip_ratio/low_mean": 0.0030554325712728314,
      "clip_ratio/low_min": 0.0003842158694169484,
      "clip_ratio/region_mean": 0.004573205238557421,
      "epoch": 0.12282635960076767,
      "grad_norm": 1.4815889596939087,
      "learning_rate": 2e-07,
      "loss": 0.0877,
      "step": 1316
    },
    {
      "clip_ratio/high_max": 0.003608994054957293,
      "clip_ratio/high_mean": 0.0015534269768977538,
      "clip_ratio/low_mean": 0.002712101675570011,
      "clip_ratio/low_min": 0.0003946566430386156,
      "clip_ratio/region_mean": 0.00426552866701968,
      "epoch": 0.12291969270076825,
      "grad_norm": 0.7337727546691895,
      "learning_rate": 2e-07,
      "loss": 0.0169,
      "step": 1317
    },
    {
      "clip_ratio/high_max": 0.003594927504309453,
      "clip_ratio/high_mean": 0.001376797696138965,
      "clip_ratio/low_mean": 0.0034329461996094324,
      "clip_ratio/low_min": 0.0008164546125044581,
      "clip_ratio/region_mean": 0.004809743884834461,
      "epoch": 0.12301302580076884,
      "grad_norm": 1.6185722351074219,
      "learning_rate": 2e-07,
      "loss": 0.0626,
      "step": 1318
    },
    {
      "clip_ratio/high_max": 0.0028419867885531858,
      "clip_ratio/high_mean": 0.0012378473438729998,
      "clip_ratio/low_mean": 0.003184839035384357,
      "clip_ratio/low_min": 0.00015968134539434686,
      "clip_ratio/region_mean": 0.004422686353791505,
      "epoch": 0.12310635890076942,
      "grad_norm": 1.352743148803711,
      "learning_rate": 2e-07,
      "loss": 0.1029,
      "step": 1319
    },
    {
      "clip_ratio/high_max": 0.0032617323959129862,
      "clip_ratio/high_mean": 0.001372216149320593,
      "clip_ratio/low_mean": 0.0037166127876844257,
      "clip_ratio/low_min": 0.00030627874366473407,
      "clip_ratio/region_mean": 0.005088829013402574,
      "epoch": 0.12319969200077,
      "grad_norm": 1.348265528678894,
      "learning_rate": 2e-07,
      "loss": 0.0671,
      "step": 1320
    },
    {
      "clip_ratio/high_max": 0.0035115740392939188,
      "clip_ratio/high_mean": 0.0015300203376682475,
      "clip_ratio/low_mean": 0.00337849126663059,
      "clip_ratio/low_min": 0.0002684738992684288,
      "clip_ratio/region_mean": 0.004908511662506498,
      "epoch": 0.12329302510077059,
      "grad_norm": 4.012618064880371,
      "learning_rate": 2e-07,
      "loss": 0.0379,
      "step": 1321
    },
    {
      "clip_ratio/high_max": 0.0036439554241951555,
      "clip_ratio/high_mean": 0.0014297419402282685,
      "clip_ratio/low_mean": 0.003916191621101461,
      "clip_ratio/low_min": 0.0008333190125995316,
      "clip_ratio/region_mean": 0.0053459336049854755,
      "epoch": 0.12338635820077117,
      "grad_norm": 2.0804901123046875,
      "learning_rate": 2e-07,
      "loss": 0.0631,
      "step": 1322
    },
    {
      "clip_ratio/high_max": 0.003811981041508261,
      "clip_ratio/high_mean": 0.0017699788841127884,
      "clip_ratio/low_mean": 0.0032547361333854496,
      "clip_ratio/low_min": 0.00044341111424728297,
      "clip_ratio/region_mean": 0.005024715006584302,
      "epoch": 0.12347969130077174,
      "grad_norm": 1.471629023551941,
      "learning_rate": 2e-07,
      "loss": 0.0405,
      "step": 1323
    },
    {
      "clip_ratio/high_max": 0.004324477442423813,
      "clip_ratio/high_mean": 0.0018312577085453086,
      "clip_ratio/low_mean": 0.0037654339175787754,
      "clip_ratio/low_min": 0.0005252777427813271,
      "clip_ratio/region_mean": 0.005596691713435575,
      "epoch": 0.12357302440077234,
      "grad_norm": 58.86204147338867,
      "learning_rate": 2e-07,
      "loss": 0.006,
      "step": 1324
    },
    {
      "clip_ratio/high_max": 0.0036713376102852635,
      "clip_ratio/high_mean": 0.001600882660568459,
      "clip_ratio/low_mean": 0.003650217411632184,
      "clip_ratio/low_min": 0.0006687878776574507,
      "clip_ratio/region_mean": 0.005251100083114579,
      "epoch": 0.12366635750077291,
      "grad_norm": 2.301476240158081,
      "learning_rate": 2e-07,
      "loss": 0.0677,
      "step": 1325
    },
    {
      "clip_ratio/high_max": 0.004266634598025121,
      "clip_ratio/high_mean": 0.0016173775293282233,
      "clip_ratio/low_mean": 0.004164997080806643,
      "clip_ratio/low_min": 0.0004247131528245518,
      "clip_ratio/region_mean": 0.005782374617410824,
      "epoch": 0.12375969060077349,
      "grad_norm": 2.031250476837158,
      "learning_rate": 2e-07,
      "loss": 0.0861,
      "step": 1326
    },
    {
      "clip_ratio/high_max": 0.003821195219643414,
      "clip_ratio/high_mean": 0.0018147397349821404,
      "clip_ratio/low_mean": 0.004478591159568168,
      "clip_ratio/low_min": 0.000371083309801179,
      "clip_ratio/region_mean": 0.006293331156484783,
      "epoch": 0.12385302370077408,
      "grad_norm": 20.447481155395508,
      "learning_rate": 2e-07,
      "loss": 0.0841,
      "step": 1327
    },
    {
      "clip_ratio/high_max": 0.004403159429784864,
      "clip_ratio/high_mean": 0.0018187564382969867,
      "clip_ratio/low_mean": 0.004737912488053553,
      "clip_ratio/low_min": 0.0010361957074564998,
      "clip_ratio/region_mean": 0.0065566688135731965,
      "epoch": 0.12394635680077466,
      "grad_norm": 82.6592025756836,
      "learning_rate": 2e-07,
      "loss": 0.1064,
      "step": 1328
    },
    {
      "clip_ratio/high_max": 0.004200952156679705,
      "clip_ratio/high_mean": 0.0018556630348030012,
      "clip_ratio/low_mean": 0.004676060838392004,
      "clip_ratio/low_min": 0.0008026572286325973,
      "clip_ratio/region_mean": 0.006531723833177239,
      "epoch": 0.12403968990077525,
      "grad_norm": 1.5106040239334106,
      "learning_rate": 2e-07,
      "loss": 0.1013,
      "step": 1329
    },
    {
      "clip_ratio/high_max": 0.004967228669556789,
      "clip_ratio/high_mean": 0.0018556908617028967,
      "clip_ratio/low_mean": 0.004661493469029665,
      "clip_ratio/low_min": 0.0004244707524776459,
      "clip_ratio/region_mean": 0.006517184403492138,
      "epoch": 0.12413302300077583,
      "grad_norm": 578.4109497070312,
      "learning_rate": 2e-07,
      "loss": 0.129,
      "step": 1330
    },
    {
      "clip_ratio/high_max": 0.00424294667027425,
      "clip_ratio/high_mean": 0.001990495409700088,
      "clip_ratio/low_mean": 0.004988981003407389,
      "clip_ratio/low_min": 0.00045367484926828183,
      "clip_ratio/region_mean": 0.006979476340347901,
      "epoch": 0.12422635610077641,
      "grad_norm": 2.2251698970794678,
      "learning_rate": 2e-07,
      "loss": 0.0413,
      "step": 1331
    },
    {
      "clip_ratio/high_max": 0.004684070241637528,
      "clip_ratio/high_mean": 0.0019796414162556175,
      "clip_ratio/low_mean": 0.004559386943583377,
      "clip_ratio/low_min": 0.00028924037906108424,
      "clip_ratio/region_mean": 0.006539028283441439,
      "epoch": 0.124319689200777,
      "grad_norm": 6.738215446472168,
      "learning_rate": 2e-07,
      "loss": 0.0612,
      "step": 1332
    },
    {
      "clip_ratio/high_max": 0.005025810140068643,
      "clip_ratio/high_mean": 0.002267664203827735,
      "clip_ratio/low_mean": 0.00546437400043942,
      "clip_ratio/low_min": 0.001307138210904668,
      "clip_ratio/region_mean": 0.0077320382406469434,
      "epoch": 0.12441302230077758,
      "grad_norm": 3.0532329082489014,
      "learning_rate": 2e-07,
      "loss": 0.0579,
      "step": 1333
    },
    {
      "clip_ratio/high_max": 0.005922570111579262,
      "clip_ratio/high_mean": 0.0022617512004217133,
      "clip_ratio/low_mean": 0.005171626646188088,
      "clip_ratio/low_min": 0.0007059713097987697,
      "clip_ratio/region_mean": 0.00743337775929831,
      "epoch": 0.12450635540077816,
      "grad_norm": 50.08420181274414,
      "learning_rate": 2e-07,
      "loss": 0.0603,
      "step": 1334
    },
    {
      "clip_ratio/high_max": 0.005804768254165538,
      "clip_ratio/high_mean": 0.0024631434789625928,
      "clip_ratio/low_mean": 0.005061570424004458,
      "clip_ratio/low_min": 0.0004477602196857333,
      "clip_ratio/region_mean": 0.007524714048486203,
      "epoch": 0.12459968850077875,
      "grad_norm": 2.4682512283325195,
      "learning_rate": 2e-07,
      "loss": 0.0451,
      "step": 1335
    },
    {
      "clip_ratio/high_max": 0.004563208742183633,
      "clip_ratio/high_mean": 0.0021618024111376144,
      "clip_ratio/low_mean": 0.005883397767320275,
      "clip_ratio/low_min": 0.0007267982509802096,
      "clip_ratio/region_mean": 0.008045199938351288,
      "epoch": 0.12469302160077933,
      "grad_norm": 853.88720703125,
      "learning_rate": 2e-07,
      "loss": 0.1085,
      "step": 1336
    },
    {
      "clip_ratio/high_max": 0.005174192032427527,
      "clip_ratio/high_mean": 0.002181114425184205,
      "clip_ratio/low_mean": 0.006028450807207264,
      "clip_ratio/low_min": 0.0008671490359120071,
      "clip_ratio/region_mean": 0.008209565101424232,
      "epoch": 0.12478635470077991,
      "grad_norm": 1169.3795166015625,
      "learning_rate": 2e-07,
      "loss": 0.1763,
      "step": 1337
    },
    {
      "clip_ratio/high_max": 0.004815749649424106,
      "clip_ratio/high_mean": 0.002192610812926432,
      "clip_ratio/low_mean": 0.005014346505049616,
      "clip_ratio/low_min": 0.0006766083897673525,
      "clip_ratio/region_mean": 0.007206957176094875,
      "epoch": 0.1248796878007805,
      "grad_norm": 48.125980377197266,
      "learning_rate": 2e-07,
      "loss": 0.1083,
      "step": 1338
    },
    {
      "clip_ratio/high_max": 0.007460586479282938,
      "clip_ratio/high_mean": 0.0030897234319127165,
      "clip_ratio/low_mean": 0.005521428713109344,
      "clip_ratio/low_min": 0.0007562608880107291,
      "clip_ratio/region_mean": 0.008611152123194188,
      "epoch": 0.12497302090078108,
      "grad_norm": 3.5818192958831787,
      "learning_rate": 2e-07,
      "loss": 0.0763,
      "step": 1339
    },
    {
      "clip_ratio/high_max": 0.006609363699681126,
      "clip_ratio/high_mean": 0.0029561710034613498,
      "clip_ratio/low_mean": 0.005504505868884735,
      "clip_ratio/low_min": 0.0010176690375374164,
      "clip_ratio/region_mean": 0.008460676937829703,
      "epoch": 0.12506635400078167,
      "grad_norm": 3.113283634185791,
      "learning_rate": 2e-07,
      "loss": 0.0568,
      "step": 1340
    },
    {
      "clip_ratio/high_max": 0.005080006376374513,
      "clip_ratio/high_mean": 0.0024947998026618734,
      "clip_ratio/low_mean": 0.00578794079774525,
      "clip_ratio/low_min": 0.0005818089193780906,
      "clip_ratio/region_mean": 0.008282740833237767,
      "epoch": 0.12515968710078224,
      "grad_norm": 15.460991859436035,
      "learning_rate": 2e-07,
      "loss": 0.0703,
      "step": 1341
    },
    {
      "clip_ratio/high_max": 0.00700264677288942,
      "clip_ratio/high_mean": 0.002902157575590536,
      "clip_ratio/low_mean": 0.0056607086735311896,
      "clip_ratio/low_min": 0.000527001826412743,
      "clip_ratio/region_mean": 0.008562866161810234,
      "epoch": 0.12525302020078283,
      "grad_norm": 4.862478733062744,
      "learning_rate": 2e-07,
      "loss": 0.0402,
      "step": 1342
    },
    {
      "clip_ratio/high_max": 0.006221263567567803,
      "clip_ratio/high_mean": 0.002878733357647434,
      "clip_ratio/low_mean": 0.006110047164838761,
      "clip_ratio/low_min": 0.0015404175501316786,
      "clip_ratio/region_mean": 0.008988780406070873,
      "epoch": 0.12534635330078342,
      "grad_norm": 4.505019664764404,
      "learning_rate": 2e-07,
      "loss": 0.0632,
      "step": 1343
    },
    {
      "clip_ratio/high_max": 0.00627762998919934,
      "clip_ratio/high_mean": 0.0030187028241925873,
      "clip_ratio/low_mean": 0.00635311589576304,
      "clip_ratio/low_min": 0.0007405232390738092,
      "clip_ratio/region_mean": 0.009371819003717974,
      "epoch": 0.125439686400784,
      "grad_norm": 9.610197067260742,
      "learning_rate": 2e-07,
      "loss": 0.0725,
      "step": 1344
    },
    {
      "clip_ratio/high_max": 0.005965406686300412,
      "clip_ratio/high_mean": 0.0025150028814096004,
      "clip_ratio/low_mean": 0.006935847079148516,
      "clip_ratio/low_min": 0.0013464745279634371,
      "clip_ratio/region_mean": 0.0094508501351811,
      "epoch": 0.12553301950078458,
      "grad_norm": 39.79737854003906,
      "learning_rate": 2e-07,
      "loss": 0.0697,
      "step": 1345
    },
    {
      "clip_ratio/high_max": 0.00681155442725867,
      "clip_ratio/high_mean": 0.003077587200095877,
      "clip_ratio/low_mean": 0.00730896185268648,
      "clip_ratio/low_min": 0.001295210124226287,
      "clip_ratio/region_mean": 0.010386548849055544,
      "epoch": 0.12562635260078517,
      "grad_norm": 52.230079650878906,
      "learning_rate": 2e-07,
      "loss": 0.0698,
      "step": 1346
    },
    {
      "clip_ratio/high_max": 0.007904044090537354,
      "clip_ratio/high_mean": 0.0034034777054330334,
      "clip_ratio/low_mean": 0.006876679166452959,
      "clip_ratio/low_min": 0.0006258564171730541,
      "clip_ratio/region_mean": 0.010280157119268551,
      "epoch": 0.12571968570078576,
      "grad_norm": 4.530972003936768,
      "learning_rate": 2e-07,
      "loss": 0.0627,
      "step": 1347
    },
    {
      "clip_ratio/high_max": 0.007020214485237375,
      "clip_ratio/high_mean": 0.003018514769792091,
      "clip_ratio/low_mean": 0.006489370425697416,
      "clip_ratio/low_min": 0.00043017041025450453,
      "clip_ratio/region_mean": 0.009507884999038652,
      "epoch": 0.12581301880078632,
      "grad_norm": 4.551019668579102,
      "learning_rate": 2e-07,
      "loss": 0.0581,
      "step": 1348
    },
    {
      "clip_ratio/high_max": 0.007822214582120068,
      "clip_ratio/high_mean": 0.0033007864403771237,
      "clip_ratio/low_mean": 0.006442233090638183,
      "clip_ratio/low_min": 0.00027159501769347116,
      "clip_ratio/region_mean": 0.009743019443703815,
      "epoch": 0.12590635190078692,
      "grad_norm": 565.720947265625,
      "learning_rate": 2e-07,
      "loss": 0.0565,
      "step": 1349
    },
    {
      "clip_ratio/high_max": 0.007591606481582858,
      "clip_ratio/high_mean": 0.0033883271244121715,
      "clip_ratio/low_mean": 0.006876061583170667,
      "clip_ratio/low_min": 0.0005198039798415266,
      "clip_ratio/region_mean": 0.010264388780342415,
      "epoch": 0.1259996850007875,
      "grad_norm": 12.586240768432617,
      "learning_rate": 2e-07,
      "loss": 0.0306,
      "step": 1350
    },
    {
      "clip_ratio/high_max": 0.008313079713843763,
      "clip_ratio/high_mean": 0.003342870477354154,
      "clip_ratio/low_mean": 0.006762599179637618,
      "clip_ratio/low_min": 0.0004602214612532407,
      "clip_ratio/region_mean": 0.010105469758855179,
      "epoch": 0.12609301810078807,
      "grad_norm": 12.566760063171387,
      "learning_rate": 2e-07,
      "loss": 0.0581,
      "step": 1351
    },
    {
      "clip_ratio/high_max": 0.00777222377655562,
      "clip_ratio/high_mean": 0.003248009437811561,
      "clip_ratio/low_mean": 0.007745289301965386,
      "clip_ratio/low_min": 0.0016451773335575126,
      "clip_ratio/region_mean": 0.010993298725225031,
      "epoch": 0.12618635120078867,
      "grad_norm": 2.991405963897705,
      "learning_rate": 2e-07,
      "loss": 0.0585,
      "step": 1352
    },
    {
      "clip_ratio/high_max": 0.006642212421866134,
      "clip_ratio/high_mean": 0.0031359772256109864,
      "clip_ratio/low_mean": 0.0071029325044946745,
      "clip_ratio/low_min": 0.00031318347464548424,
      "clip_ratio/region_mean": 0.010238909686449915,
      "epoch": 0.12627968430078926,
      "grad_norm": 15.164664268493652,
      "learning_rate": 2e-07,
      "loss": 0.0365,
      "step": 1353
    },
    {
      "clip_ratio/high_max": 0.007622488745255396,
      "clip_ratio/high_mean": 0.0037569389678537846,
      "clip_ratio/low_mean": 0.007462243331247009,
      "clip_ratio/low_min": 0.001169490434222098,
      "clip_ratio/region_mean": 0.011219182168133557,
      "epoch": 0.12637301740078982,
      "grad_norm": 12.094339370727539,
      "learning_rate": 2e-07,
      "loss": 0.0684,
      "step": 1354
    },
    {
      "clip_ratio/high_max": 0.007589510292746127,
      "clip_ratio/high_mean": 0.003657142646261491,
      "clip_ratio/low_mean": 0.0077282383281271905,
      "clip_ratio/low_min": 0.0007491261203540489,
      "clip_ratio/region_mean": 0.011385381105355918,
      "epoch": 0.12646635050079041,
      "grad_norm": 80.28907775878906,
      "learning_rate": 2e-07,
      "loss": -0.0168,
      "step": 1355
    },
    {
      "clip_ratio/high_max": 0.008491607033647597,
      "clip_ratio/high_mean": 0.0038237879998632707,
      "clip_ratio/low_mean": 0.007797091122483835,
      "clip_ratio/low_min": 0.0015984141209628433,
      "clip_ratio/region_mean": 0.011620879406109452,
      "epoch": 0.126559683600791,
      "grad_norm": 65382.0625,
      "learning_rate": 2e-07,
      "loss": 2.3851,
      "step": 1356
    },
    {
      "clip_ratio/high_max": 0.008770831555011682,
      "clip_ratio/high_mean": 0.003798535355599597,
      "clip_ratio/low_mean": 0.007718040535110049,
      "clip_ratio/low_min": 0.0009147957498498727,
      "clip_ratio/region_mean": 0.011516576167196035,
      "epoch": 0.12665301670079157,
      "grad_norm": 17.83380126953125,
      "learning_rate": 2e-07,
      "loss": 0.0511,
      "step": 1357
    },
    {
      "clip_ratio/high_max": 0.008397737692575902,
      "clip_ratio/high_mean": 0.0038584269350394607,
      "clip_ratio/low_mean": 0.009711183636682108,
      "clip_ratio/low_min": 0.0014238382354960777,
      "clip_ratio/region_mean": 0.013569610484410077,
      "epoch": 0.12674634980079216,
      "grad_norm": 133.03173828125,
      "learning_rate": 2e-07,
      "loss": 0.1153,
      "step": 1358
    },
    {
      "clip_ratio/high_max": 0.009064075697096996,
      "clip_ratio/high_mean": 0.004104536637896672,
      "clip_ratio/low_mean": 0.008024576440220699,
      "clip_ratio/low_min": 0.0008421769452979788,
      "clip_ratio/region_mean": 0.012129112961702049,
      "epoch": 0.12683968290079276,
      "grad_norm": 13.689435005187988,
      "learning_rate": 2e-07,
      "loss": 0.0367,
      "step": 1359
    },
    {
      "clip_ratio/high_max": 0.008122974948491901,
      "clip_ratio/high_mean": 0.003686619849759154,
      "clip_ratio/low_mean": 0.007701306574745104,
      "clip_ratio/low_min": 0.001500025529821869,
      "clip_ratio/region_mean": 0.011387926497263834,
      "epoch": 0.12693301600079332,
      "grad_norm": 7.920009136199951,
      "learning_rate": 2e-07,
      "loss": 0.0752,
      "step": 1360
    },
    {
      "clip_ratio/high_max": 0.008824864358757623,
      "clip_ratio/high_mean": 0.004094178482773714,
      "clip_ratio/low_mean": 0.00784577606827952,
      "clip_ratio/low_min": 0.0011034290655516088,
      "clip_ratio/region_mean": 0.011939954536501318,
      "epoch": 0.1270263491007939,
      "grad_norm": 5.753616809844971,
      "learning_rate": 2e-07,
      "loss": 0.0769,
      "step": 1361
    },
    {
      "clip_ratio/high_max": 0.008815786874038167,
      "clip_ratio/high_mean": 0.0038370960755855776,
      "clip_ratio/low_mean": 0.00890799638000317,
      "clip_ratio/low_min": 0.0010157091783185024,
      "clip_ratio/region_mean": 0.012745092331897467,
      "epoch": 0.1271196822007945,
      "grad_norm": 4.31011438369751,
      "learning_rate": 2e-07,
      "loss": 0.0544,
      "step": 1362
    },
    {
      "clip_ratio/high_max": 0.009173411905067042,
      "clip_ratio/high_mean": 0.004206277561024763,
      "clip_ratio/low_mean": 0.008902590576326475,
      "clip_ratio/low_min": 0.0012337966018094448,
      "clip_ratio/region_mean": 0.013108868384733796,
      "epoch": 0.12721301530079507,
      "grad_norm": 113.02539825439453,
      "learning_rate": 2e-07,
      "loss": 0.0532,
      "step": 1363
    },
    {
      "clip_ratio/high_max": 0.009732156933750957,
      "clip_ratio/high_mean": 0.004296673243516125,
      "clip_ratio/low_mean": 0.009950926672900096,
      "clip_ratio/low_min": 0.0017321819614153355,
      "clip_ratio/region_mean": 0.014247599698137492,
      "epoch": 0.12730634840079566,
      "grad_norm": 25.278486251831055,
      "learning_rate": 2e-07,
      "loss": 0.0657,
      "step": 1364
    },
    {
      "clip_ratio/high_max": 0.009044782869750634,
      "clip_ratio/high_mean": 0.004483708820771426,
      "clip_ratio/low_mean": 0.009401712595717981,
      "clip_ratio/low_min": 0.0006635219742747722,
      "clip_ratio/region_mean": 0.013885421503800899,
      "epoch": 0.12739968150079625,
      "grad_norm": 4.522478103637695,
      "learning_rate": 2e-07,
      "loss": 0.0254,
      "step": 1365
    },
    {
      "clip_ratio/high_max": 0.009749944772920571,
      "clip_ratio/high_mean": 0.004411700530909002,
      "clip_ratio/low_mean": 0.009453783743083477,
      "clip_ratio/low_min": 0.0006407620458048768,
      "clip_ratio/region_mean": 0.013865483924746513,
      "epoch": 0.12749301460079684,
      "grad_norm": 170.24468994140625,
      "learning_rate": 2e-07,
      "loss": 0.0452,
      "step": 1366
    },
    {
      "clip_ratio/high_max": 0.008658615901367739,
      "clip_ratio/high_mean": 0.004075836477568373,
      "clip_ratio/low_mean": 0.010906891111517325,
      "clip_ratio/low_min": 0.0020341548915894236,
      "clip_ratio/region_mean": 0.014982727472670376,
      "epoch": 0.1275863477007974,
      "grad_norm": 7.427040100097656,
      "learning_rate": 2e-07,
      "loss": 0.1289,
      "step": 1367
    },
    {
      "clip_ratio/high_max": 0.009229083661921322,
      "clip_ratio/high_mean": 0.0038376564771169797,
      "clip_ratio/low_mean": 0.009799160587135702,
      "clip_ratio/low_min": 0.0010566769051365554,
      "clip_ratio/region_mean": 0.013636817049700767,
      "epoch": 0.127679680800798,
      "grad_norm": 15.811633110046387,
      "learning_rate": 2e-07,
      "loss": 0.0882,
      "step": 1368
    },
    {
      "clip_ratio/high_max": 0.009676406334619969,
      "clip_ratio/high_mean": 0.004735783310024999,
      "clip_ratio/low_mean": 0.01049866178072989,
      "clip_ratio/low_min": 0.0016753449526731856,
      "clip_ratio/region_mean": 0.0152344448142685,
      "epoch": 0.1277730139007986,
      "grad_norm": 5.762593746185303,
      "learning_rate": 2e-07,
      "loss": 0.0405,
      "step": 1369
    },
    {
      "clip_ratio/high_max": 0.009980883914977312,
      "clip_ratio/high_mean": 0.004616628692019731,
      "clip_ratio/low_mean": 0.008923128742026165,
      "clip_ratio/low_min": 0.00045701463386649266,
      "clip_ratio/region_mean": 0.013539757521357387,
      "epoch": 0.12786634700079916,
      "grad_norm": 4.980777740478516,
      "learning_rate": 2e-07,
      "loss": 0.0358,
      "step": 1370
    },
    {
      "clip_ratio/high_max": 0.010181256919167936,
      "clip_ratio/high_mean": 0.0046004070827621035,
      "clip_ratio/low_mean": 0.01055732331587933,
      "clip_ratio/low_min": 0.0017352494978695177,
      "clip_ratio/region_mean": 0.015157730435021222,
      "epoch": 0.12795968010079975,
      "grad_norm": 14.894510269165039,
      "learning_rate": 2e-07,
      "loss": 0.0397,
      "step": 1371
    },
    {
      "clip_ratio/high_max": 0.011247337533859536,
      "clip_ratio/high_mean": 0.005018330542952754,
      "clip_ratio/low_mean": 0.010208075880655088,
      "clip_ratio/low_min": 0.0013873384014004841,
      "clip_ratio/region_mean": 0.015226406103465706,
      "epoch": 0.12805301320080034,
      "grad_norm": 1238.2757568359375,
      "learning_rate": 2e-07,
      "loss": 0.1193,
      "step": 1372
    },
    {
      "clip_ratio/high_max": 0.010289447964169085,
      "clip_ratio/high_mean": 0.0050898346526082605,
      "clip_ratio/low_mean": 0.009937901690136641,
      "clip_ratio/low_min": 0.0003622362783062272,
      "clip_ratio/region_mean": 0.015027735847979784,
      "epoch": 0.1281463463008009,
      "grad_norm": 10.726532936096191,
      "learning_rate": 2e-07,
      "loss": 0.0353,
      "step": 1373
    },
    {
      "clip_ratio/high_max": 0.011398923001252115,
      "clip_ratio/high_mean": 0.004539710396784358,
      "clip_ratio/low_mean": 0.012131829949794337,
      "clip_ratio/low_min": 0.0021259820350678638,
      "clip_ratio/region_mean": 0.0166715404484421,
      "epoch": 0.1282396794008015,
      "grad_norm": 2891.561279296875,
      "learning_rate": 2e-07,
      "loss": 0.1399,
      "step": 1374
    },
    {
      "clip_ratio/high_max": 0.010754793969681486,
      "clip_ratio/high_mean": 0.00516165177396033,
      "clip_ratio/low_mean": 0.010866523312870413,
      "clip_ratio/low_min": 0.0013664298312505707,
      "clip_ratio/region_mean": 0.01602817513048649,
      "epoch": 0.1283330125008021,
      "grad_norm": 430.67791748046875,
      "learning_rate": 2e-07,
      "loss": 0.0588,
      "step": 1375
    },
    {
      "clip_ratio/high_max": 0.010772893438115716,
      "clip_ratio/high_mean": 0.00479254581296118,
      "clip_ratio/low_mean": 0.011534293764270842,
      "clip_ratio/low_min": 0.001417097395460587,
      "clip_ratio/region_mean": 0.016326839569956064,
      "epoch": 0.12842634560080265,
      "grad_norm": 3549.003662109375,
      "learning_rate": 2e-07,
      "loss": 0.2066,
      "step": 1376
    },
    {
      "clip_ratio/high_max": 0.012813848414225504,
      "clip_ratio/high_mean": 0.006158334595966153,
      "clip_ratio/low_mean": 0.012775158626027405,
      "clip_ratio/low_min": 0.0019102286896668375,
      "clip_ratio/region_mean": 0.018933493236545473,
      "epoch": 0.12851967870080325,
      "grad_norm": 35.26154708862305,
      "learning_rate": 2e-07,
      "loss": 0.0932,
      "step": 1377
    },
    {
      "clip_ratio/high_max": 0.013802618195768446,
      "clip_ratio/high_mean": 0.006466358056059107,
      "clip_ratio/low_mean": 0.012821750598959625,
      "clip_ratio/low_min": 0.0012362277047941461,
      "clip_ratio/region_mean": 0.019288108684122562,
      "epoch": 0.12861301180080384,
      "grad_norm": 12.446272850036621,
      "learning_rate": 2e-07,
      "loss": 0.0731,
      "step": 1378
    },
    {
      "clip_ratio/high_max": 0.013600453356048092,
      "clip_ratio/high_mean": 0.005589053893345408,
      "clip_ratio/low_mean": 0.011182608315721154,
      "clip_ratio/low_min": 0.001316051246249117,
      "clip_ratio/region_mean": 0.01677166239824146,
      "epoch": 0.1287063449008044,
      "grad_norm": 56.86370849609375,
      "learning_rate": 2e-07,
      "loss": 0.0845,
      "step": 1379
    },
    {
      "clip_ratio/high_max": 0.014078281965339556,
      "clip_ratio/high_mean": 0.005915598812862299,
      "clip_ratio/low_mean": 0.012466812884667888,
      "clip_ratio/low_min": 0.001591451422427781,
      "clip_ratio/region_mean": 0.018382411799393594,
      "epoch": 0.128799678000805,
      "grad_norm": 169.367919921875,
      "learning_rate": 2e-07,
      "loss": 0.0855,
      "step": 1380
    },
    {
      "clip_ratio/high_max": 0.01187056937487796,
      "clip_ratio/high_mean": 0.005514364718692377,
      "clip_ratio/low_mean": 0.011443059687735513,
      "clip_ratio/low_min": 0.0017501942056696862,
      "clip_ratio/region_mean": 0.01695742440642789,
      "epoch": 0.1288930111008056,
      "grad_norm": 37.27037811279297,
      "learning_rate": 2e-07,
      "loss": 0.1033,
      "step": 1381
    },
    {
      "clip_ratio/high_max": 0.013064442726317793,
      "clip_ratio/high_mean": 0.006072487230994739,
      "clip_ratio/low_mean": 0.012485475308494642,
      "clip_ratio/low_min": 0.0018954028128064238,
      "clip_ratio/region_mean": 0.018557962670456618,
      "epoch": 0.12898634420080615,
      "grad_norm": 9.110992431640625,
      "learning_rate": 2e-07,
      "loss": 0.0558,
      "step": 1382
    },
    {
      "clip_ratio/high_max": 0.014177469623973593,
      "clip_ratio/high_mean": 0.005960215989034623,
      "clip_ratio/low_mean": 0.01333567698020488,
      "clip_ratio/low_min": 0.0018166062473028433,
      "clip_ratio/region_mean": 0.019295892619993538,
      "epoch": 0.12907967730080674,
      "grad_norm": 637.1403198242188,
      "learning_rate": 2e-07,
      "loss": 0.0821,
      "step": 1383
    },
    {
      "clip_ratio/high_max": 0.013291084149386734,
      "clip_ratio/high_mean": 0.006330167132546194,
      "clip_ratio/low_mean": 0.014193860988598317,
      "clip_ratio/low_min": 0.0024563579936511815,
      "clip_ratio/region_mean": 0.02052402769913897,
      "epoch": 0.12917301040080734,
      "grad_norm": 42.615577697753906,
      "learning_rate": 2e-07,
      "loss": 0.1069,
      "step": 1384
    },
    {
      "clip_ratio/high_max": 0.013018363300943747,
      "clip_ratio/high_mean": 0.005892847708310001,
      "clip_ratio/low_mean": 0.011460623238235712,
      "clip_ratio/low_min": 0.0006662479136139154,
      "clip_ratio/region_mean": 0.01735347107751295,
      "epoch": 0.1292663435008079,
      "grad_norm": 43.0958137512207,
      "learning_rate": 2e-07,
      "loss": 0.0607,
      "step": 1385
    },
    {
      "clip_ratio/high_max": 0.013428730890154839,
      "clip_ratio/high_mean": 0.006094695927458815,
      "clip_ratio/low_mean": 0.012777787167578936,
      "clip_ratio/low_min": 0.0019133788446197286,
      "clip_ratio/region_mean": 0.018872483575250953,
      "epoch": 0.1293596766008085,
      "grad_norm": 243.92605590820312,
      "learning_rate": 2e-07,
      "loss": 0.0711,
      "step": 1386
    },
    {
      "clip_ratio/high_max": 0.014621897949837148,
      "clip_ratio/high_mean": 0.006921335094375536,
      "clip_ratio/low_mean": 0.012069863820215687,
      "clip_ratio/low_min": 0.0010350085940444842,
      "clip_ratio/region_mean": 0.018991198972798884,
      "epoch": 0.12945300970080909,
      "grad_norm": 742.0355224609375,
      "learning_rate": 2e-07,
      "loss": 0.0868,
      "step": 1387
    },
    {
      "clip_ratio/high_max": 0.01423992743366398,
      "clip_ratio/high_mean": 0.006241173599846661,
      "clip_ratio/low_mean": 0.015176182991126552,
      "clip_ratio/low_min": 0.0018747244321275502,
      "clip_ratio/region_mean": 0.021417356561869383,
      "epoch": 0.12954634280080968,
      "grad_norm": 34.0280647277832,
      "learning_rate": 2e-07,
      "loss": 0.1654,
      "step": 1388
    },
    {
      "clip_ratio/high_max": 0.014356733561726287,
      "clip_ratio/high_mean": 0.006569287637830712,
      "clip_ratio/low_mean": 0.012792830064427108,
      "clip_ratio/low_min": 0.002636040124343708,
      "clip_ratio/region_mean": 0.019362117571290582,
      "epoch": 0.12963967590081024,
      "grad_norm": 9.022438049316406,
      "learning_rate": 2e-07,
      "loss": 0.0351,
      "step": 1389
    },
    {
      "clip_ratio/high_max": 0.01657727302517742,
      "clip_ratio/high_mean": 0.00692776867072098,
      "clip_ratio/low_mean": 0.012745752144837752,
      "clip_ratio/low_min": 0.0019026008085347712,
      "clip_ratio/region_mean": 0.01967352075735107,
      "epoch": 0.12973300900081083,
      "grad_norm": 32.590484619140625,
      "learning_rate": 2e-07,
      "loss": 0.0707,
      "step": 1390
    },
    {
      "clip_ratio/high_max": 0.014896863358444534,
      "clip_ratio/high_mean": 0.006878184423840139,
      "clip_ratio/low_mean": 0.01464800105895847,
      "clip_ratio/low_min": 0.0016213481721933931,
      "clip_ratio/region_mean": 0.021526186144910753,
      "epoch": 0.12982634210081143,
      "grad_norm": 10.015687942504883,
      "learning_rate": 2e-07,
      "loss": 0.0463,
      "step": 1391
    },
    {
      "clip_ratio/high_max": 0.014706387562910095,
      "clip_ratio/high_mean": 0.006095006465329789,
      "clip_ratio/low_mean": 0.016185540473088622,
      "clip_ratio/low_min": 0.0024724976829020306,
      "clip_ratio/region_mean": 0.022280546720139682,
      "epoch": 0.129919675200812,
      "grad_norm": 69.58390808105469,
      "learning_rate": 2e-07,
      "loss": 0.0879,
      "step": 1392
    },
    {
      "clip_ratio/high_max": 0.01370748653425835,
      "clip_ratio/high_mean": 0.0062088213744573295,
      "clip_ratio/low_mean": 0.01587432128144428,
      "clip_ratio/low_min": 0.0025354807585245,
      "clip_ratio/region_mean": 0.022083142772316933,
      "epoch": 0.13001300830081258,
      "grad_norm": 87.21321868896484,
      "learning_rate": 2e-07,
      "loss": 0.079,
      "step": 1393
    },
    {
      "clip_ratio/high_max": 0.015203474977170117,
      "clip_ratio/high_mean": 0.0068955081078456715,
      "clip_ratio/low_mean": 0.016137466416694224,
      "clip_ratio/low_min": 0.0020803025981877,
      "clip_ratio/region_mean": 0.02303297503385693,
      "epoch": 0.13010634140081317,
      "grad_norm": 15.869612693786621,
      "learning_rate": 2e-07,
      "loss": 0.0779,
      "step": 1394
    },
    {
      "clip_ratio/high_max": 0.01649062510114163,
      "clip_ratio/high_mean": 0.0072498052031733096,
      "clip_ratio/low_mean": 0.015009917580755427,
      "clip_ratio/low_min": 0.0022273879148997366,
      "clip_ratio/region_mean": 0.022259722754824907,
      "epoch": 0.13019967450081374,
      "grad_norm": 24.813819885253906,
      "learning_rate": 2e-07,
      "loss": 0.0473,
      "step": 1395
    },
    {
      "clip_ratio/high_max": 0.017269184871111065,
      "clip_ratio/high_mean": 0.007246662804391235,
      "clip_ratio/low_mean": 0.015746300108730793,
      "clip_ratio/low_min": 0.001290422645979561,
      "clip_ratio/region_mean": 0.022992962913122028,
      "epoch": 0.13029300760081433,
      "grad_norm": 9.588167190551758,
      "learning_rate": 2e-07,
      "loss": 0.0787,
      "step": 1396
    },
    {
      "clip_ratio/high_max": 0.012633189035113901,
      "clip_ratio/high_mean": 0.006693540533888154,
      "clip_ratio/low_mean": 0.016628692508675158,
      "clip_ratio/low_min": 0.0026046088751172647,
      "clip_ratio/region_mean": 0.023322232766076922,
      "epoch": 0.13038634070081492,
      "grad_norm": 128.11599731445312,
      "learning_rate": 2e-07,
      "loss": 0.0712,
      "step": 1397
    },
    {
      "clip_ratio/high_max": 0.01474394096294418,
      "clip_ratio/high_mean": 0.006971714828978293,
      "clip_ratio/low_mean": 0.018531307694502175,
      "clip_ratio/low_min": 0.0033085665199905634,
      "clip_ratio/region_mean": 0.025503022479824722,
      "epoch": 0.1304796738008155,
      "grad_norm": 297.33587646484375,
      "learning_rate": 2e-07,
      "loss": 0.0789,
      "step": 1398
    },
    {
      "clip_ratio/high_max": 0.014904955809470266,
      "clip_ratio/high_mean": 0.006701694583171047,
      "clip_ratio/low_mean": 0.01561338413739577,
      "clip_ratio/low_min": 0.0015448903504875489,
      "clip_ratio/region_mean": 0.022315078764222562,
      "epoch": 0.13057300690081608,
      "grad_norm": 113.62066650390625,
      "learning_rate": 2e-07,
      "loss": 0.1132,
      "step": 1399
    },
    {
      "clip_ratio/high_max": 0.015899311227258295,
      "clip_ratio/high_mean": 0.007611666951561347,
      "clip_ratio/low_mean": 0.014763011655304581,
      "clip_ratio/low_min": 0.0024383912968914956,
      "clip_ratio/region_mean": 0.022374678927008063,
      "epoch": 0.13066634000081667,
      "grad_norm": 9.21013069152832,
      "learning_rate": 2e-07,
      "loss": 0.0487,
      "step": 1400
    },
    {
      "clip_ratio/high_max": 0.014716992038302124,
      "clip_ratio/high_mean": 0.006733620713930577,
      "clip_ratio/low_mean": 0.01628228829940781,
      "clip_ratio/low_min": 0.002814228064380586,
      "clip_ratio/region_mean": 0.023015908838715404,
      "epoch": 0.13075967310081724,
      "grad_norm": 108.51646423339844,
      "learning_rate": 2e-07,
      "loss": 0.117,
      "step": 1401
    },
    {
      "clip_ratio/high_max": 0.013829248084221035,
      "clip_ratio/high_mean": 0.006705766209051944,
      "clip_ratio/low_mean": 0.016364801966119558,
      "clip_ratio/low_min": 0.003270134395279456,
      "clip_ratio/region_mean": 0.02307056833524257,
      "epoch": 0.13085300620081783,
      "grad_norm": 184.2284393310547,
      "learning_rate": 2e-07,
      "loss": 0.1249,
      "step": 1402
    },
    {
      "clip_ratio/high_max": 0.018688655458390713,
      "clip_ratio/high_mean": 0.008420353609835729,
      "clip_ratio/low_mean": 0.015965425118338317,
      "clip_ratio/low_min": 0.0014091550474404357,
      "clip_ratio/region_mean": 0.024385778582654893,
      "epoch": 0.13094633930081842,
      "grad_norm": 22.842815399169922,
      "learning_rate": 2e-07,
      "loss": 0.0614,
      "step": 1403
    },
    {
      "clip_ratio/high_max": 0.018823303340468556,
      "clip_ratio/high_mean": 0.007889596949098632,
      "clip_ratio/low_mean": 0.017035974946338683,
      "clip_ratio/low_min": 0.0019894522556569427,
      "clip_ratio/region_mean": 0.024925571866333485,
      "epoch": 0.13103967240081899,
      "grad_norm": 3422.71630859375,
      "learning_rate": 2e-07,
      "loss": 0.1899,
      "step": 1404
    },
    {
      "clip_ratio/high_max": 0.015640896279364824,
      "clip_ratio/high_mean": 0.00706898893986363,
      "clip_ratio/low_mean": 0.016036787361372262,
      "clip_ratio/low_min": 0.001825592371460516,
      "clip_ratio/region_mean": 0.02310577651951462,
      "epoch": 0.13113300550081958,
      "grad_norm": 12.950906753540039,
      "learning_rate": 2e-07,
      "loss": 0.0788,
      "step": 1405
    },
    {
      "clip_ratio/high_max": 0.016808160347864032,
      "clip_ratio/high_mean": 0.00787089581717737,
      "clip_ratio/low_mean": 0.017841617111116648,
      "clip_ratio/low_min": 0.0020131173077970743,
      "clip_ratio/region_mean": 0.025712513248436153,
      "epoch": 0.13122633860082017,
      "grad_norm": 22.400840759277344,
      "learning_rate": 2e-07,
      "loss": 0.1057,
      "step": 1406
    },
    {
      "clip_ratio/high_max": 0.016137479367898777,
      "clip_ratio/high_mean": 0.0077819539728807285,
      "clip_ratio/low_mean": 0.018143379827961326,
      "clip_ratio/low_min": 0.00130741237080656,
      "clip_ratio/region_mean": 0.02592533396091312,
      "epoch": 0.13131967170082076,
      "grad_norm": 30.81023406982422,
      "learning_rate": 2e-07,
      "loss": 0.0573,
      "step": 1407
    },
    {
      "clip_ratio/high_max": 0.020197402860503644,
      "clip_ratio/high_mean": 0.008821286755846813,
      "clip_ratio/low_mean": 0.019611548603279516,
      "clip_ratio/low_min": 0.002650469046784565,
      "clip_ratio/region_mean": 0.028432834602426738,
      "epoch": 0.13141300480082133,
      "grad_norm": 69.15196228027344,
      "learning_rate": 2e-07,
      "loss": 0.0855,
      "step": 1408
    },
    {
      "clip_ratio/high_max": 0.0034917405719170347,
      "clip_ratio/high_mean": 0.0010317024043615675,
      "clip_ratio/low_mean": 0.002106563093548175,
      "clip_ratio/low_min": 0.0001595597536834248,
      "clip_ratio/region_mean": 0.003138265456072986,
      "completions/clipped_ratio": 0.1274239676339286,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4096.0,
      "completions/mean_length": 920.465576171875,
      "completions/mean_terminated_length": 456.736083984375,
      "completions/min_length": 7.0,
      "completions/min_terminated_length": 7.0,
      "epoch": 0.13150633790082192,
      "grad_norm": 1.2340682744979858,
      "learning_rate": 2e-07,
      "loss": 0.1062,
      "num_tokens": 1058172428.0,
      "reward": 0.1373814195394516,
      "reward_std": 0.16018612682819366,
      "rewards/simpleverify_reward/mean": 0.1373814195394516,
      "rewards/simpleverify_reward/std": 0.34425103664398193,
      "step": 1409
    },
    {
      "clip_ratio/high_max": 0.002850983593816636,
      "clip_ratio/high_mean": 0.0009008319830172695,
      "clip_ratio/low_mean": 0.0019528836965037044,
      "clip_ratio/low_min": 5.574408714892343e-05,
      "clip_ratio/region_mean": 0.0028537157631944865,
      "epoch": 0.1315996710008225,
      "grad_norm": 0.8146823644638062,
      "learning_rate": 2e-07,
      "loss": 0.1214,
      "step": 1410
    },
    {
      "clip_ratio/high_max": 0.003719995584106073,
      "clip_ratio/high_mean": 0.0011078885218012147,
      "clip_ratio/low_mean": 0.0020745110923598986,
      "clip_ratio/low_min": 0.0001590524702805851,
      "clip_ratio/region_mean": 0.0031823996250750497,
      "epoch": 0.13169300410082307,
      "grad_norm": 2.607980251312256,
      "learning_rate": 2e-07,
      "loss": 0.0782,
      "step": 1411
    },
    {
      "clip_ratio/high_max": 0.0028500656226242427,
      "clip_ratio/high_mean": 0.0009317502899648389,
      "clip_ratio/low_mean": 0.001993024183320813,
      "clip_ratio/low_min": 0.0002563478356023552,
      "clip_ratio/region_mean": 0.0029247745405882597,
      "epoch": 0.13178633720082367,
      "grad_norm": 29.320541381835938,
      "learning_rate": 2e-07,
      "loss": 0.113,
      "step": 1412
    },
    {
      "clip_ratio/high_max": 0.003154070087475702,
      "clip_ratio/high_mean": 0.000961777392149088,
      "clip_ratio/low_mean": 0.002076791035506176,
      "clip_ratio/low_min": 0.00014874911857987172,
      "clip_ratio/region_mean": 0.003038568473129999,
      "epoch": 0.13187967030082426,
      "grad_norm": 0.5086946487426758,
      "learning_rate": 2e-07,
      "loss": 0.0821,
      "step": 1413
    },
    {
      "clip_ratio/high_max": 0.002783269137580646,
      "clip_ratio/high_mean": 0.0008951761756179621,
      "clip_ratio/low_mean": 0.0019675041585287545,
      "clip_ratio/low_min": 0.00028286849965297733,
      "clip_ratio/region_mean": 0.0028626803541556,
      "epoch": 0.13197300340082482,
      "grad_norm": 3164.13232421875,
      "learning_rate": 2e-07,
      "loss": 0.2456,
      "step": 1414
    },
    {
      "clip_ratio/high_max": 0.004083576728589833,
      "clip_ratio/high_mean": 0.001235523139257566,
      "clip_ratio/low_mean": 0.002217590379586909,
      "clip_ratio/low_min": 0.000334015792759601,
      "clip_ratio/region_mean": 0.0034531135170254856,
      "epoch": 0.13206633650082542,
      "grad_norm": 5.14722204208374,
      "learning_rate": 2e-07,
      "loss": 0.0962,
      "step": 1415
    },
    {
      "clip_ratio/high_max": 0.0027193506684852764,
      "clip_ratio/high_mean": 0.0009277365134039428,
      "clip_ratio/low_mean": 0.0017397388292010874,
      "clip_ratio/low_min": 0.00011705312954291003,
      "clip_ratio/region_mean": 0.0026674753389670514,
      "epoch": 0.132159669600826,
      "grad_norm": 1.3632886409759521,
      "learning_rate": 2e-07,
      "loss": 0.1083,
      "step": 1416
    },
    {
      "clip_ratio/high_max": 0.0020166500471532345,
      "clip_ratio/high_mean": 0.0007231217823573388,
      "clip_ratio/low_mean": 0.002787073281069752,
      "clip_ratio/low_min": 0.0003263078506279271,
      "clip_ratio/region_mean": 0.003510195092530921,
      "epoch": 0.13225300270082657,
      "grad_norm": 0.9144637584686279,
      "learning_rate": 2e-07,
      "loss": 0.0776,
      "step": 1417
    },
    {
      "clip_ratio/high_max": 0.002979688288178295,
      "clip_ratio/high_mean": 0.0008559236321161734,
      "clip_ratio/low_mean": 0.002458118793583708,
      "clip_ratio/low_min": 0.00015756663469801424,
      "clip_ratio/region_mean": 0.0033140424638986588,
      "epoch": 0.13234633580082716,
      "grad_norm": 1.4139240980148315,
      "learning_rate": 2e-07,
      "loss": 0.101,
      "step": 1418
    },
    {
      "clip_ratio/high_max": 0.0034353812670815387,
      "clip_ratio/high_mean": 0.0008467616032703518,
      "clip_ratio/low_mean": 0.0025635969650465995,
      "clip_ratio/low_min": 0.00016716705567887402,
      "clip_ratio/region_mean": 0.003410358702240046,
      "epoch": 0.13243966890082776,
      "grad_norm": 0.9239667654037476,
      "learning_rate": 2e-07,
      "loss": 0.0701,
      "step": 1419
    },
    {
      "clip_ratio/high_max": 0.004143041245697532,
      "clip_ratio/high_mean": 0.0011480730445327936,
      "clip_ratio/low_mean": 0.0025625305133871734,
      "clip_ratio/low_min": 0.00026376529967819806,
      "clip_ratio/region_mean": 0.0037106035160832107,
      "epoch": 0.13253300200082832,
      "grad_norm": 2.1368558406829834,
      "learning_rate": 2e-07,
      "loss": 0.075,
      "step": 1420
    },
    {
      "clip_ratio/high_max": 0.003548359491105657,
      "clip_ratio/high_mean": 0.0010898371883740765,
      "clip_ratio/low_mean": 0.003178080325596966,
      "clip_ratio/low_min": 0.0004715784998552408,
      "clip_ratio/region_mean": 0.004267917407560162,
      "epoch": 0.1326263351008289,
      "grad_norm": 552.5911865234375,
      "learning_rate": 2e-07,
      "loss": 0.1456,
      "step": 1421
    },
    {
      "clip_ratio/high_max": 0.004039390143589117,
      "clip_ratio/high_mean": 0.001063418233570701,
      "clip_ratio/low_mean": 0.002983271326229442,
      "clip_ratio/low_min": 0.0004501670628087595,
      "clip_ratio/region_mean": 0.004046689529786818,
      "epoch": 0.1327196682008295,
      "grad_norm": 2.0642826557159424,
      "learning_rate": 2e-07,
      "loss": 0.0789,
      "step": 1422
    },
    {
      "clip_ratio/high_max": 0.0031615907719242387,
      "clip_ratio/high_mean": 0.000991053699181066,
      "clip_ratio/low_mean": 0.0032869467468117364,
      "clip_ratio/low_min": 0.00045175705326983007,
      "clip_ratio/region_mean": 0.004278000502381474,
      "epoch": 0.13281300130083007,
      "grad_norm": 2.024412155151367,
      "learning_rate": 2e-07,
      "loss": 0.0689,
      "step": 1423
    },
    {
      "clip_ratio/high_max": 0.003114478058705572,
      "clip_ratio/high_mean": 0.0009738494773046114,
      "clip_ratio/low_mean": 0.00278983851603698,
      "clip_ratio/low_min": 0.00022726818224327872,
      "clip_ratio/region_mean": 0.003763688000617549,
      "epoch": 0.13290633440083066,
      "grad_norm": 183.63143920898438,
      "learning_rate": 2e-07,
      "loss": 0.0984,
      "step": 1424
    },
    {
      "clip_ratio/high_max": 0.00428938015102176,
      "clip_ratio/high_mean": 0.0013461861744872294,
      "clip_ratio/low_mean": 0.0026578068573144265,
      "clip_ratio/low_min": 0.0001812715086089156,
      "clip_ratio/region_mean": 0.004003992929938249,
      "epoch": 0.13299966750083125,
      "grad_norm": 15.79616641998291,
      "learning_rate": 2e-07,
      "loss": 0.0864,
      "step": 1425
    },
    {
      "clip_ratio/high_max": 0.003437613297137432,
      "clip_ratio/high_mean": 0.00103465749816678,
      "clip_ratio/low_mean": 0.0031517129682470113,
      "clip_ratio/low_min": 0.0003390138936083531,
      "clip_ratio/region_mean": 0.004186370468232781,
      "epoch": 0.13309300060083182,
      "grad_norm": 3.787747383117676,
      "learning_rate": 2e-07,
      "loss": 0.0947,
      "step": 1426
    },
    {
      "clip_ratio/high_max": 0.002753906181169441,
      "clip_ratio/high_mean": 0.0008410741666011745,
      "clip_ratio/low_mean": 0.003531698872393463,
      "clip_ratio/low_min": 0.00036665747302322416,
      "clip_ratio/region_mean": 0.0043727730080718175,
      "epoch": 0.1331863337008324,
      "grad_norm": 3.0714917182922363,
      "learning_rate": 2e-07,
      "loss": 0.0946,
      "step": 1427
    },
    {
      "clip_ratio/high_max": 0.004165698293945752,
      "clip_ratio/high_mean": 0.001297348773732665,
      "clip_ratio/low_mean": 0.003802986473601777,
      "clip_ratio/low_min": 0.0004603304605552694,
      "clip_ratio/region_mean": 0.005100335270981304,
      "epoch": 0.133279666800833,
      "grad_norm": 22785.83984375,
      "learning_rate": 2e-07,
      "loss": 0.6319,
      "step": 1428
    },
    {
      "clip_ratio/high_max": 0.0024231291390606202,
      "clip_ratio/high_mean": 0.0007571321166324196,
      "clip_ratio/low_mean": 0.004258909320924431,
      "clip_ratio/low_min": 0.00042251830473105656,
      "clip_ratio/region_mean": 0.005016041497583501,
      "epoch": 0.1333729999008336,
      "grad_norm": 145.3633270263672,
      "learning_rate": 2e-07,
      "loss": 0.1133,
      "step": 1429
    },
    {
      "clip_ratio/high_max": 0.003018751896888716,
      "clip_ratio/high_mean": 0.0009828585061768536,
      "clip_ratio/low_mean": 0.003883214885718189,
      "clip_ratio/low_min": 0.000307269405311672,
      "clip_ratio/region_mean": 0.0048660733591532335,
      "epoch": 0.13346633300083416,
      "grad_norm": 2.4388821125030518,
      "learning_rate": 2e-07,
      "loss": 0.0961,
      "step": 1430
    },
    {
      "clip_ratio/high_max": 0.00415704473562073,
      "clip_ratio/high_mean": 0.0011983077292825328,
      "clip_ratio/low_mean": 0.005105378266307525,
      "clip_ratio/low_min": 0.0004039287468913244,
      "clip_ratio/region_mean": 0.006303685906459577,
      "epoch": 0.13355966610083475,
      "grad_norm": 19.223356246948242,
      "learning_rate": 2e-07,
      "loss": 0.0865,
      "step": 1431
    },
    {
      "clip_ratio/high_max": 0.004481497213419061,
      "clip_ratio/high_mean": 0.001327207506619743,
      "clip_ratio/low_mean": 0.004572874662699178,
      "clip_ratio/low_min": 0.0006425259962270502,
      "clip_ratio/region_mean": 0.005900082207517698,
      "epoch": 0.13365299920083534,
      "grad_norm": 17.14619255065918,
      "learning_rate": 2e-07,
      "loss": 0.0912,
      "step": 1432
    },
    {
      "clip_ratio/high_max": 0.004286933719413355,
      "clip_ratio/high_mean": 0.00131725390565407,
      "clip_ratio/low_mean": 0.004819051879167091,
      "clip_ratio/low_min": 0.0006973019849283446,
      "clip_ratio/region_mean": 0.006136305775726214,
      "epoch": 0.1337463323008359,
      "grad_norm": 62.88805389404297,
      "learning_rate": 2e-07,
      "loss": 0.1339,
      "step": 1433
    },
    {
      "clip_ratio/high_max": 0.003971074285800569,
      "clip_ratio/high_mean": 0.0013571663384936983,
      "clip_ratio/low_mean": 0.00425802241807105,
      "clip_ratio/low_min": 0.0008193005996872671,
      "clip_ratio/region_mean": 0.005615188696538098,
      "epoch": 0.1338396654008365,
      "grad_norm": 243487.8125,
      "learning_rate": 2e-07,
      "loss": 7.0422,
      "step": 1434
    },
    {
      "clip_ratio/high_max": 0.005954889660642948,
      "clip_ratio/high_mean": 0.0016240957629634067,
      "clip_ratio/low_mean": 0.005316458584275097,
      "clip_ratio/low_min": 0.00036492736217041966,
      "clip_ratio/region_mean": 0.006940554405446164,
      "epoch": 0.1339329985008371,
      "grad_norm": 231.15589904785156,
      "learning_rate": 2e-07,
      "loss": 0.0913,
      "step": 1435
    },
    {
      "clip_ratio/high_max": 0.004649173417419661,
      "clip_ratio/high_mean": 0.0013758723052887945,
      "clip_ratio/low_mean": 0.0038631097122561187,
      "clip_ratio/low_min": 0.00037210579102975316,
      "clip_ratio/region_mean": 0.005238982063019648,
      "epoch": 0.13402633160083766,
      "grad_norm": 1515.633056640625,
      "learning_rate": 2e-07,
      "loss": 0.1328,
      "step": 1436
    },
    {
      "clip_ratio/high_max": 0.005194587065489031,
      "clip_ratio/high_mean": 0.0016361588204745203,
      "clip_ratio/low_mean": 0.005354176755645312,
      "clip_ratio/low_min": 0.00024152064725058153,
      "clip_ratio/region_mean": 0.006990335648879409,
      "epoch": 0.13411966470083825,
      "grad_norm": 350.9219055175781,
      "learning_rate": 2e-07,
      "loss": 0.3242,
      "step": 1437
    },
    {
      "clip_ratio/high_max": 0.004842477948841406,
      "clip_ratio/high_mean": 0.0014230941214918857,
      "clip_ratio/low_mean": 0.005127488628204446,
      "clip_ratio/low_min": 0.00017847353501565522,
      "clip_ratio/region_mean": 0.00655058266420383,
      "epoch": 0.13421299780083884,
      "grad_norm": 38.4141960144043,
      "learning_rate": 2e-07,
      "loss": 0.1048,
      "step": 1438
    },
    {
      "clip_ratio/high_max": 0.010436508571729064,
      "clip_ratio/high_mean": 0.0026675398839870468,
      "clip_ratio/low_mean": 0.004330304553150199,
      "clip_ratio/low_min": 0.0002762263065960724,
      "clip_ratio/region_mean": 0.006997844422585331,
      "epoch": 0.1343063309008394,
      "grad_norm": 8097.30224609375,
      "learning_rate": 2e-07,
      "loss": 0.3944,
      "step": 1439
    },
    {
      "clip_ratio/high_max": 0.005507613372174092,
      "clip_ratio/high_mean": 0.0017703950543364044,
      "clip_ratio/low_mean": 0.004967420121829491,
      "clip_ratio/low_min": 0.00020942808077961672,
      "clip_ratio/region_mean": 0.00673781504156068,
      "epoch": 0.13439966400084,
      "grad_norm": 15.0077543258667,
      "learning_rate": 2e-07,
      "loss": 0.0849,
      "step": 1440
    },
    {
      "clip_ratio/high_max": 0.008388139598537236,
      "clip_ratio/high_mean": 0.0024348700244445354,
      "clip_ratio/low_mean": 0.004160194388532545,
      "clip_ratio/low_min": 0.0002790682738122996,
      "clip_ratio/region_mean": 0.006595064289285801,
      "epoch": 0.1344929971008406,
      "grad_norm": 16477.44921875,
      "learning_rate": 2e-07,
      "loss": 0.8173,
      "step": 1441
    },
    {
      "clip_ratio/high_max": 0.006202811571711209,
      "clip_ratio/high_mean": 0.0018789043388096616,
      "clip_ratio/low_mean": 0.004534453313681297,
      "clip_ratio/low_min": 0.00034072730068146484,
      "clip_ratio/region_mean": 0.0064133577106986195,
      "epoch": 0.13458633020084115,
      "grad_norm": 810.54443359375,
      "learning_rate": 2e-07,
      "loss": 0.1359,
      "step": 1442
    },
    {
      "clip_ratio/high_max": 0.006806824603700079,
      "clip_ratio/high_mean": 0.0017695105525490362,
      "clip_ratio/low_mean": 0.005506634224730078,
      "clip_ratio/low_min": 0.00065718778205337,
      "clip_ratio/region_mean": 0.007276144708157517,
      "epoch": 0.13467966330084175,
      "grad_norm": 1556.5670166015625,
      "learning_rate": 2e-07,
      "loss": 0.176,
      "step": 1443
    },
    {
      "clip_ratio/high_max": 0.007051138796668965,
      "clip_ratio/high_mean": 0.0022924738659639843,
      "clip_ratio/low_mean": 0.004710242588771507,
      "clip_ratio/low_min": 0.0005501996647581109,
      "clip_ratio/region_mean": 0.007002716578426771,
      "epoch": 0.13477299640084234,
      "grad_norm": 647.2376708984375,
      "learning_rate": 2e-07,
      "loss": 0.139,
      "step": 1444
    },
    {
      "clip_ratio/high_max": 0.005365365213947371,
      "clip_ratio/high_mean": 0.0014938992444513133,
      "clip_ratio/low_mean": 0.0052102112385910004,
      "clip_ratio/low_min": 0.000979726577497786,
      "clip_ratio/region_mean": 0.006704110302962363,
      "epoch": 0.1348663295008429,
      "grad_norm": 102.38212585449219,
      "learning_rate": 2e-07,
      "loss": 0.1308,
      "step": 1445
    },
    {
      "clip_ratio/high_max": 0.008468388914479874,
      "clip_ratio/high_mean": 0.002404698185273446,
      "clip_ratio/low_mean": 0.004492271735216491,
      "clip_ratio/low_min": 0.0006960736682231072,
      "clip_ratio/region_mean": 0.006896969804074615,
      "epoch": 0.1349596626008435,
      "grad_norm": 420.0313720703125,
      "learning_rate": 2e-07,
      "loss": 0.1058,
      "step": 1446
    },
    {
      "clip_ratio/high_max": 0.004974880619556643,
      "clip_ratio/high_mean": 0.0015506986710533965,
      "clip_ratio/low_mean": 0.005655403023411054,
      "clip_ratio/low_min": 0.0003711468671099283,
      "clip_ratio/region_mean": 0.0072061015671351925,
      "epoch": 0.1350529957008441,
      "grad_norm": 7671.556640625,
      "learning_rate": 2e-07,
      "loss": 0.3504,
      "step": 1447
    },
    {
      "clip_ratio/high_max": 0.007234136359329568,
      "clip_ratio/high_mean": 0.001955603372607584,
      "clip_ratio/low_mean": 0.005161738707101904,
      "clip_ratio/low_min": 0.0008712913258932531,
      "clip_ratio/region_mean": 0.00711734194192104,
      "epoch": 0.13514632880084468,
      "grad_norm": 117.27584075927734,
      "learning_rate": 2e-07,
      "loss": 0.1024,
      "step": 1448
    },
    {
      "clip_ratio/high_max": 0.006977778917644173,
      "clip_ratio/high_mean": 0.0023631368931091856,
      "clip_ratio/low_mean": 0.004765874553413596,
      "clip_ratio/low_min": 0.00035495298288878985,
      "clip_ratio/region_mean": 0.0071290116175077856,
      "epoch": 0.13523966190084524,
      "grad_norm": 1065639168.0,
      "learning_rate": 2e-07,
      "loss": 17387.8965,
      "step": 1449
    },
    {
      "clip_ratio/high_max": 0.005588789965258911,
      "clip_ratio/high_mean": 0.0016506532701896504,
      "clip_ratio/low_mean": 0.005156362938578241,
      "clip_ratio/low_min": 0.00043442121022962965,
      "clip_ratio/region_mean": 0.006807016354287043,
      "epoch": 0.13533299500084583,
      "grad_norm": 2551.2138671875,
      "learning_rate": 2e-07,
      "loss": 0.1829,
      "step": 1450
    },
    {
      "clip_ratio/high_max": 0.0067286554258316755,
      "clip_ratio/high_mean": 0.0019457521266303957,
      "clip_ratio/low_mean": 0.006285369134275243,
      "clip_ratio/low_min": 0.0004948289897583891,
      "clip_ratio/region_mean": 0.008231121086282656,
      "epoch": 0.13542632810084643,
      "grad_norm": 817.2671508789062,
      "learning_rate": 2e-07,
      "loss": 0.1417,
      "step": 1451
    },
    {
      "clip_ratio/high_max": 0.006912979333719704,
      "clip_ratio/high_mean": 0.0022599385847570375,
      "clip_ratio/low_mean": 0.004771615727804601,
      "clip_ratio/low_min": 0.00039299659692915156,
      "clip_ratio/region_mean": 0.007031554196146317,
      "epoch": 0.135519661200847,
      "grad_norm": 144.7241668701172,
      "learning_rate": 2e-07,
      "loss": 0.1248,
      "step": 1452
    },
    {
      "clip_ratio/high_max": 0.005359833252441604,
      "clip_ratio/high_mean": 0.0017729559494910063,
      "clip_ratio/low_mean": 0.007604939877637662,
      "clip_ratio/low_min": 0.0008173747446562629,
      "clip_ratio/region_mean": 0.009377895767102018,
      "epoch": 0.13561299430084758,
      "grad_norm": 325.6852111816406,
      "learning_rate": 2e-07,
      "loss": 0.1816,
      "step": 1453
    },
    {
      "clip_ratio/high_max": 0.004857336993154604,
      "clip_ratio/high_mean": 0.0020133468169660773,
      "clip_ratio/low_mean": 0.005867306841537356,
      "clip_ratio/low_min": 0.0009200707841046096,
      "clip_ratio/region_mean": 0.007880653807660565,
      "epoch": 0.13570632740084818,
      "grad_norm": 189.5345916748047,
      "learning_rate": 2e-07,
      "loss": 0.1562,
      "step": 1454
    },
    {
      "clip_ratio/high_max": 0.006058206534362398,
      "clip_ratio/high_mean": 0.002074853611702565,
      "clip_ratio/low_mean": 0.005655181797919795,
      "clip_ratio/low_min": 0.00047107947466429323,
      "clip_ratio/region_mean": 0.007730035358690657,
      "epoch": 0.13579966050084874,
      "grad_norm": 2778336.0,
      "learning_rate": 2e-07,
      "loss": 49.2133,
      "step": 1455
    },
    {
      "clip_ratio/high_max": 0.005761111759056803,
      "clip_ratio/high_mean": 0.0018612701951497002,
      "clip_ratio/low_mean": 0.004519296417129226,
      "clip_ratio/low_min": 0.00038266646515694447,
      "clip_ratio/region_mean": 0.006380566614097916,
      "epoch": 0.13589299360084933,
      "grad_norm": 5004.412109375,
      "learning_rate": 2e-07,
      "loss": 0.2914,
      "step": 1456
    },
    {
      "clip_ratio/high_max": 0.006787259022530634,
      "clip_ratio/high_mean": 0.0019501526694511995,
      "clip_ratio/low_mean": 0.0064736987187643535,
      "clip_ratio/low_min": 0.0007250098715303466,
      "clip_ratio/region_mean": 0.008423851046245545,
      "epoch": 0.13598632670084992,
      "grad_norm": 334.9818420410156,
      "learning_rate": 2e-07,
      "loss": 0.1282,
      "step": 1457
    },
    {
      "clip_ratio/high_max": 0.0068399918418435846,
      "clip_ratio/high_mean": 0.0016516001628588128,
      "clip_ratio/low_mean": 0.004827113407372963,
      "clip_ratio/low_min": 0.0007999262597877532,
      "clip_ratio/region_mean": 0.00647871351975482,
      "epoch": 0.1360796598008505,
      "grad_norm": 1324.082275390625,
      "learning_rate": 2e-07,
      "loss": 0.1698,
      "step": 1458
    },
    {
      "clip_ratio/high_max": 0.006564840652572457,
      "clip_ratio/high_mean": 0.0022351597090164432,
      "clip_ratio/low_mean": 0.0057496990921208635,
      "clip_ratio/low_min": 0.0005617207316390704,
      "clip_ratio/region_mean": 0.007984858966665342,
      "epoch": 0.13617299290085108,
      "grad_norm": 1144.6529541015625,
      "learning_rate": 2e-07,
      "loss": 0.1495,
      "step": 1459
    },
    {
      "clip_ratio/high_max": 0.007493828758015297,
      "clip_ratio/high_mean": 0.002173895605665166,
      "clip_ratio/low_mean": 0.005498423081007786,
      "clip_ratio/low_min": 0.00048703958600526676,
      "clip_ratio/region_mean": 0.007672318868571892,
      "epoch": 0.13626632600085167,
      "grad_norm": 135.51280212402344,
      "learning_rate": 2e-07,
      "loss": 0.1302,
      "step": 1460
    },
    {
      "clip_ratio/high_max": 0.008647413400467485,
      "clip_ratio/high_mean": 0.0024197340826503932,
      "clip_ratio/low_mean": 0.00645587412873283,
      "clip_ratio/low_min": 0.0010710514234233415,
      "clip_ratio/region_mean": 0.008875608153175563,
      "epoch": 0.13635965910085224,
      "grad_norm": 2367.09375,
      "learning_rate": 2e-07,
      "loss": 0.229,
      "step": 1461
    },
    {
      "clip_ratio/high_max": 0.009749329241458327,
      "clip_ratio/high_mean": 0.003116860279988032,
      "clip_ratio/low_mean": 0.005873062626051251,
      "clip_ratio/low_min": 0.000810243480373174,
      "clip_ratio/region_mean": 0.008989922949695028,
      "epoch": 0.13645299220085283,
      "grad_norm": 10801.2080078125,
      "learning_rate": 2e-07,
      "loss": 0.5577,
      "step": 1462
    },
    {
      "clip_ratio/high_max": 0.007331577799050137,
      "clip_ratio/high_mean": 0.0023855306881159777,
      "clip_ratio/low_mean": 0.0055911670497152954,
      "clip_ratio/low_min": 0.0004712052013928769,
      "clip_ratio/region_mean": 0.007976697743288241,
      "epoch": 0.13654632530085342,
      "grad_norm": 100856.0625,
      "learning_rate": 2e-07,
      "loss": 1.1465,
      "step": 1463
    },
    {
      "clip_ratio/high_max": 0.009189326759951655,
      "clip_ratio/high_mean": 0.0026437763845024165,
      "clip_ratio/low_mean": 0.0058936806744895875,
      "clip_ratio/low_min": 0.0007874863331380766,
      "clip_ratio/region_mean": 0.008537457091733813,
      "epoch": 0.13663965840085399,
      "grad_norm": 6278.16064453125,
      "learning_rate": 2e-07,
      "loss": 0.261,
      "step": 1464
    },
    {
      "clip_ratio/high_max": 0.010295358617440797,
      "clip_ratio/high_mean": 0.002946512668131618,
      "clip_ratio/low_mean": 0.005151014556759037,
      "clip_ratio/low_min": 0.0006401431728590978,
      "clip_ratio/region_mean": 0.008097527403151616,
      "epoch": 0.13673299150085458,
      "grad_norm": 10188.6435546875,
      "learning_rate": 2e-07,
      "loss": 0.3585,
      "step": 1465
    },
    {
      "clip_ratio/high_max": 0.008779369585681707,
      "clip_ratio/high_mean": 0.002560641551099252,
      "clip_ratio/low_mean": 0.005750521719164681,
      "clip_ratio/low_min": 0.00040780836570775136,
      "clip_ratio/region_mean": 0.008311163299367763,
      "epoch": 0.13682632460085517,
      "grad_norm": 226815232.0,
      "learning_rate": 2e-07,
      "loss": 13867.4434,
      "step": 1466
    },
    {
      "clip_ratio/high_max": 0.007305313571123406,
      "clip_ratio/high_mean": 0.0022002926598361228,
      "clip_ratio/low_mean": 0.004813257080968469,
      "clip_ratio/low_min": 0.0002513038016331848,
      "clip_ratio/region_mean": 0.007013549853581935,
      "epoch": 0.13691965770085573,
      "grad_norm": 3517.51611328125,
      "learning_rate": 2e-07,
      "loss": 0.1704,
      "step": 1467
    },
    {
      "clip_ratio/high_max": 0.007766131166135892,
      "clip_ratio/high_mean": 0.002154123372747563,
      "clip_ratio/low_mean": 0.006541856360854581,
      "clip_ratio/low_min": 0.0003070117181778187,
      "clip_ratio/region_mean": 0.008695979864569381,
      "epoch": 0.13701299080085633,
      "grad_norm": 5785.6201171875,
      "learning_rate": 2e-07,
      "loss": 0.3348,
      "step": 1468
    },
    {
      "clip_ratio/high_max": 0.005988854689348955,
      "clip_ratio/high_mean": 0.0018364719653618522,
      "clip_ratio/low_mean": 0.005896807721001096,
      "clip_ratio/low_min": 0.0004301241187931737,
      "clip_ratio/region_mean": 0.007733279722742736,
      "epoch": 0.13710632390085692,
      "grad_norm": 2611.37353515625,
      "learning_rate": 2e-07,
      "loss": 0.1774,
      "step": 1469
    },
    {
      "clip_ratio/high_max": 0.007534066106018145,
      "clip_ratio/high_mean": 0.002155297846911708,
      "clip_ratio/low_mean": 0.00626742652093526,
      "clip_ratio/low_min": 0.0011977599065176037,
      "clip_ratio/region_mean": 0.008422724233241752,
      "epoch": 0.1371996570008575,
      "grad_norm": 166345.890625,
      "learning_rate": 2e-07,
      "loss": 5.1383,
      "step": 1470
    },
    {
      "clip_ratio/high_max": 0.008879992747097276,
      "clip_ratio/high_mean": 0.002703597681829706,
      "clip_ratio/low_mean": 0.005348357393813785,
      "clip_ratio/low_min": 0.0007206140362541191,
      "clip_ratio/region_mean": 0.008051954777329229,
      "epoch": 0.13729299010085808,
      "grad_norm": 443.6673583984375,
      "learning_rate": 2e-07,
      "loss": 0.3003,
      "step": 1471
    },
    {
      "clip_ratio/high_max": 0.008881206857040524,
      "clip_ratio/high_mean": 0.0024145210772985592,
      "clip_ratio/low_mean": 0.007276998338056728,
      "clip_ratio/low_min": 0.001335394976194948,
      "clip_ratio/region_mean": 0.009691519488114864,
      "epoch": 0.13738632320085867,
      "grad_norm": 73148.5234375,
      "learning_rate": 2e-07,
      "loss": 7.8584,
      "step": 1472
    },
    {
      "clip_ratio/high_max": 0.008089089635177515,
      "clip_ratio/high_mean": 0.0021771364481537603,
      "clip_ratio/low_mean": 0.005132714475621469,
      "clip_ratio/low_min": 0.0003153640282107517,
      "clip_ratio/region_mean": 0.007309851018362679,
      "epoch": 0.13747965630085926,
      "grad_norm": 325.13897705078125,
      "learning_rate": 2e-07,
      "loss": 0.1234,
      "step": 1473
    },
    {
      "clip_ratio/high_max": 0.009867451473837718,
      "clip_ratio/high_mean": 0.002715134836762445,
      "clip_ratio/low_mean": 0.0059342460735933855,
      "clip_ratio/low_min": 0.00044754139162250794,
      "clip_ratio/region_mean": 0.008649381081340834,
      "epoch": 0.13757298940085982,
      "grad_norm": 10917.28125,
      "learning_rate": 2e-07,
      "loss": 0.3105,
      "step": 1474
    },
    {
      "clip_ratio/high_max": 0.009670020459452644,
      "clip_ratio/high_mean": 0.0027035189468733734,
      "clip_ratio/low_mean": 0.0054028749000281096,
      "clip_ratio/low_min": 0.0005357317677407991,
      "clip_ratio/region_mean": 0.008106393957859837,
      "epoch": 0.13766632250086042,
      "grad_norm": 7847.5185546875,
      "learning_rate": 2e-07,
      "loss": 0.4024,
      "step": 1475
    },
    {
      "clip_ratio/high_max": 0.007240221817482961,
      "clip_ratio/high_mean": 0.0021153762172616553,
      "clip_ratio/low_mean": 0.005755964710260741,
      "clip_ratio/low_min": 0.0006380534032359719,
      "clip_ratio/region_mean": 0.007871341076679528,
      "epoch": 0.137759655600861,
      "grad_norm": 735.4156494140625,
      "learning_rate": 2e-07,
      "loss": 0.12,
      "step": 1476
    },
    {
      "clip_ratio/high_max": 0.008236524234234821,
      "clip_ratio/high_mean": 0.0026749814005597727,
      "clip_ratio/low_mean": 0.005593385372776538,
      "clip_ratio/low_min": 0.0006847293261671439,
      "clip_ratio/region_mean": 0.008268366858828813,
      "epoch": 0.13785298870086157,
      "grad_norm": 21737697280.0,
      "learning_rate": 2e-07,
      "loss": 250428.8125,
      "step": 1477
    },
    {
      "clip_ratio/high_max": 0.006871360579680186,
      "clip_ratio/high_mean": 0.002191756750107743,
      "clip_ratio/low_mean": 0.005869777814950794,
      "clip_ratio/low_min": 0.0017172887346532661,
      "clip_ratio/region_mean": 0.008061534652370028,
      "epoch": 0.13794632180086216,
      "grad_norm": 2831.79736328125,
      "learning_rate": 2e-07,
      "loss": 0.3071,
      "step": 1478
    },
    {
      "clip_ratio/high_max": 0.007536492339568213,
      "clip_ratio/high_mean": 0.002407484258583281,
      "clip_ratio/low_mean": 0.006683551451715175,
      "clip_ratio/low_min": 0.0008019790502657997,
      "clip_ratio/region_mean": 0.009091035753954202,
      "epoch": 0.13803965490086276,
      "grad_norm": 13872.025390625,
      "learning_rate": 2e-07,
      "loss": 0.7143,
      "step": 1479
    },
    {
      "clip_ratio/high_max": 0.006915603065863252,
      "clip_ratio/high_mean": 0.0020499253951129504,
      "clip_ratio/low_mean": 0.0063171433575917035,
      "clip_ratio/low_min": 0.0005435060265881475,
      "clip_ratio/region_mean": 0.008367068920051679,
      "epoch": 0.13813298800086332,
      "grad_norm": 738.7655029296875,
      "learning_rate": 2e-07,
      "loss": 0.1486,
      "step": 1480
    },
    {
      "clip_ratio/high_max": 0.009973643682315014,
      "clip_ratio/high_mean": 0.002607977126899641,
      "clip_ratio/low_mean": 0.005412334241555072,
      "clip_ratio/low_min": 0.00035683299029187765,
      "clip_ratio/region_mean": 0.008020311666768976,
      "epoch": 0.1382263211008639,
      "grad_norm": 46274.46875,
      "learning_rate": 2e-07,
      "loss": 2.0843,
      "step": 1481
    },
    {
      "clip_ratio/high_max": 0.007136008018278517,
      "clip_ratio/high_mean": 0.00234859628835693,
      "clip_ratio/low_mean": 0.006437916337745264,
      "clip_ratio/low_min": 0.0011354547932569403,
      "clip_ratio/region_mean": 0.008786512407823466,
      "epoch": 0.1383196542008645,
      "grad_norm": 2590348.75,
      "learning_rate": 2e-07,
      "loss": 1902.9944,
      "step": 1482
    },
    {
      "clip_ratio/high_max": 0.010188057844061404,
      "clip_ratio/high_mean": 0.0029102276712364983,
      "clip_ratio/low_mean": 0.005978313995001372,
      "clip_ratio/low_min": 0.0005611587039311416,
      "clip_ratio/region_mean": 0.008888541749911383,
      "epoch": 0.13841298730086507,
      "grad_norm": 395.4180908203125,
      "learning_rate": 2e-07,
      "loss": 0.1518,
      "step": 1483
    },
    {
      "clip_ratio/high_max": 0.006695381147437729,
      "clip_ratio/high_mean": 0.002252870941447327,
      "clip_ratio/low_mean": 0.006109536057920195,
      "clip_ratio/low_min": 0.0010449017336213728,
      "clip_ratio/region_mean": 0.008362406893866137,
      "epoch": 0.13850632040086566,
      "grad_norm": 2135421.75,
      "learning_rate": 2e-07,
      "loss": 21.9956,
      "step": 1484
    },
    {
      "clip_ratio/high_max": 0.0073409851611359045,
      "clip_ratio/high_mean": 0.00249104151953361,
      "clip_ratio/low_mean": 0.005187874339753762,
      "clip_ratio/low_min": 0.0010463005673955195,
      "clip_ratio/region_mean": 0.007678915906581096,
      "epoch": 0.13859965350086625,
      "grad_norm": 113.12728881835938,
      "learning_rate": 2e-07,
      "loss": 0.0991,
      "step": 1485
    },
    {
      "clip_ratio/high_max": 0.007104978463758016,
      "clip_ratio/high_mean": 0.0023320781510847155,
      "clip_ratio/low_mean": 0.005304814112605527,
      "clip_ratio/low_min": 0.000515213243488688,
      "clip_ratio/region_mean": 0.007636892260052264,
      "epoch": 0.13869298660086682,
      "grad_norm": 93.32202911376953,
      "learning_rate": 2e-07,
      "loss": 0.1114,
      "step": 1486
    },
    {
      "clip_ratio/high_max": 0.008283168150228448,
      "clip_ratio/high_mean": 0.0023534151987405494,
      "clip_ratio/low_mean": 0.005452555400552228,
      "clip_ratio/low_min": 0.0006040840744390152,
      "clip_ratio/region_mean": 0.007805970861227252,
      "epoch": 0.1387863197008674,
      "grad_norm": 137090944.0,
      "learning_rate": 2e-07,
      "loss": 1623.3727,
      "step": 1487
    },
    {
      "clip_ratio/high_max": 0.008993372721306514,
      "clip_ratio/high_mean": 0.0028979981543670874,
      "clip_ratio/low_mean": 0.005086147852125578,
      "clip_ratio/low_min": 0.00031322661743615754,
      "clip_ratio/region_mean": 0.007984146068338305,
      "epoch": 0.138879652800868,
      "grad_norm": 3164.171875,
      "learning_rate": 2e-07,
      "loss": 0.2046,
      "step": 1488
    },
    {
      "clip_ratio/high_max": 0.009458193788304925,
      "clip_ratio/high_mean": 0.0028433490078896284,
      "clip_ratio/low_mean": 0.006782857395592146,
      "clip_ratio/low_min": 0.0011850148512166925,
      "clip_ratio/region_mean": 0.009626206156099215,
      "epoch": 0.13897298590086857,
      "grad_norm": 57206.9140625,
      "learning_rate": 2e-07,
      "loss": 1.2667,
      "step": 1489
    },
    {
      "clip_ratio/high_max": 0.008538940877770074,
      "clip_ratio/high_mean": 0.0031768445078341756,
      "clip_ratio/low_mean": 0.0065518994379090145,
      "clip_ratio/low_min": 0.0011620893637882546,
      "clip_ratio/region_mean": 0.009728743956657127,
      "epoch": 0.13906631900086916,
      "grad_norm": 915.1483764648438,
      "learning_rate": 2e-07,
      "loss": 0.0945,
      "step": 1490
    },
    {
      "clip_ratio/high_max": 0.005669618214596994,
      "clip_ratio/high_mean": 0.0016231675454037031,
      "clip_ratio/low_mean": 0.006512166888569482,
      "clip_ratio/low_min": 0.0009109943930525333,
      "clip_ratio/region_mean": 0.008135334486723877,
      "epoch": 0.13915965210086975,
      "grad_norm": 66290.3359375,
      "learning_rate": 2e-07,
      "loss": 1.2677,
      "step": 1491
    },
    {
      "clip_ratio/high_max": 0.009215493410010822,
      "clip_ratio/high_mean": 0.002293805588124087,
      "clip_ratio/low_mean": 0.004719295830000192,
      "clip_ratio/low_min": 0.0005806983026559465,
      "clip_ratio/region_mean": 0.007013101378106512,
      "epoch": 0.13925298520087034,
      "grad_norm": 3732.097900390625,
      "learning_rate": 2e-07,
      "loss": 0.1804,
      "step": 1492
    },
    {
      "clip_ratio/high_max": 0.00889978730265284,
      "clip_ratio/high_mean": 0.00275647769740317,
      "clip_ratio/low_mean": 0.005451131699373946,
      "clip_ratio/low_min": 0.001195424087200081,
      "clip_ratio/region_mean": 0.008207609469536692,
      "epoch": 0.1393463183008709,
      "grad_norm": 7707195.0,
      "learning_rate": 2e-07,
      "loss": 67.1128,
      "step": 1493
    },
    {
      "clip_ratio/high_max": 0.006558050285093486,
      "clip_ratio/high_mean": 0.00216191300569335,
      "clip_ratio/low_mean": 0.005828499037306756,
      "clip_ratio/low_min": 0.00047607712895114673,
      "clip_ratio/region_mean": 0.007990411890204996,
      "epoch": 0.1394396514008715,
      "grad_norm": 556.0816040039062,
      "learning_rate": 2e-07,
      "loss": 0.1524,
      "step": 1494
    },
    {
      "clip_ratio/high_max": 0.0077836069103796035,
      "clip_ratio/high_mean": 0.0023378397891065106,
      "clip_ratio/low_mean": 0.006860084584332071,
      "clip_ratio/low_min": 0.0005471100121212658,
      "clip_ratio/region_mean": 0.009197924271575175,
      "epoch": 0.1395329845008721,
      "grad_norm": 91591.8515625,
      "learning_rate": 2e-07,
      "loss": 2.206,
      "step": 1495
    },
    {
      "clip_ratio/high_max": 0.01026911816734355,
      "clip_ratio/high_mean": 0.003117845708402456,
      "clip_ratio/low_mean": 0.005843779159476981,
      "clip_ratio/low_min": 0.0008345485439349432,
      "clip_ratio/region_mean": 0.008961624902440235,
      "epoch": 0.13962631760087266,
      "grad_norm": 5883.73876953125,
      "learning_rate": 2e-07,
      "loss": 0.2737,
      "step": 1496
    },
    {
      "clip_ratio/high_max": 0.007312572153750807,
      "clip_ratio/high_mean": 0.0022731063145329244,
      "clip_ratio/low_mean": 0.005695893807569519,
      "clip_ratio/low_min": 0.0007808265363564715,
      "clip_ratio/region_mean": 0.007969000202137977,
      "epoch": 0.13971965070087325,
      "grad_norm": 24601922.0,
      "learning_rate": 2e-07,
      "loss": 899.8954,
      "step": 1497
    },
    {
      "clip_ratio/high_max": 0.009946754471457098,
      "clip_ratio/high_mean": 0.0032042041457316373,
      "clip_ratio/low_mean": 0.006703616978484206,
      "clip_ratio/low_min": 0.0004932862884743372,
      "clip_ratio/region_mean": 0.009907820902299136,
      "epoch": 0.13981298380087384,
      "grad_norm": 1514.8369140625,
      "learning_rate": 2e-07,
      "loss": 0.1572,
      "step": 1498
    },
    {
      "clip_ratio/high_max": 0.008156065683579072,
      "clip_ratio/high_mean": 0.0025624113768571988,
      "clip_ratio/low_mean": 0.0066142017603851855,
      "clip_ratio/low_min": 0.0007484292618755717,
      "clip_ratio/region_mean": 0.009176612918963656,
      "epoch": 0.1399063169008744,
      "grad_norm": 391.2881164550781,
      "learning_rate": 2e-07,
      "loss": 0.1477,
      "step": 1499
    },
    {
      "clip_ratio/high_max": 0.010827489662915468,
      "clip_ratio/high_mean": 0.0027917309962504078,
      "clip_ratio/low_mean": 0.007237174781039357,
      "clip_ratio/low_min": 0.0008522135658495245,
      "clip_ratio/region_mean": 0.010028905613580719,
      "epoch": 0.139999650000875,
      "grad_norm": 121.61569213867188,
      "learning_rate": 2e-07,
      "loss": 0.1374,
      "step": 1500
    },
    {
      "clip_ratio/high_max": 0.0081136782100657,
      "clip_ratio/high_mean": 0.0021284834438120015,
      "clip_ratio/low_mean": 0.005535592747037299,
      "clip_ratio/low_min": 0.000548481668374734,
      "clip_ratio/region_mean": 0.007664076023502275,
      "epoch": 0.1400929831008756,
      "grad_norm": 2062.8427734375,
      "learning_rate": 2e-07,
      "loss": 0.246,
      "step": 1501
    },
    {
      "clip_ratio/high_max": 0.011051118199247867,
      "clip_ratio/high_mean": 0.0031485180952586234,
      "clip_ratio/low_mean": 0.005606901933788322,
      "clip_ratio/low_min": 0.0005498235914274119,
      "clip_ratio/region_mean": 0.0087554199853912,
      "epoch": 0.14018631620087615,
      "grad_norm": 1902.2830810546875,
      "learning_rate": 2e-07,
      "loss": 0.1739,
      "step": 1502
    },
    {
      "clip_ratio/high_max": 0.010130674279935192,
      "clip_ratio/high_mean": 0.0031240616081049666,
      "clip_ratio/low_mean": 0.0064166452357312664,
      "clip_ratio/low_min": 0.00120318611516268,
      "clip_ratio/region_mean": 0.009540706989355385,
      "epoch": 0.14027964930087675,
      "grad_norm": 14640.6650390625,
      "learning_rate": 2e-07,
      "loss": 0.5543,
      "step": 1503
    },
    {
      "clip_ratio/high_max": 0.008425082065514289,
      "clip_ratio/high_mean": 0.002371139169554226,
      "clip_ratio/low_mean": 0.006036642080289312,
      "clip_ratio/low_min": 0.0004800515980605269,
      "clip_ratio/region_mean": 0.00840778139536269,
      "epoch": 0.14037298240087734,
      "grad_norm": 3871.172119140625,
      "learning_rate": 2e-07,
      "loss": 0.2088,
      "step": 1504
    },
    {
      "clip_ratio/high_max": 0.008657270496769343,
      "clip_ratio/high_mean": 0.002906339032051619,
      "clip_ratio/low_mean": 0.006226025856449269,
      "clip_ratio/low_min": 0.0004049631261295872,
      "clip_ratio/region_mean": 0.00913236491032876,
      "epoch": 0.1404663155008779,
      "grad_norm": 7535.419921875,
      "learning_rate": 2e-07,
      "loss": 0.4838,
      "step": 1505
    },
    {
      "clip_ratio/high_max": 0.007821333303581923,
      "clip_ratio/high_mean": 0.002561605546361534,
      "clip_ratio/low_mean": 0.005767920461948961,
      "clip_ratio/low_min": 0.0009528511000098661,
      "clip_ratio/region_mean": 0.00832952605560422,
      "epoch": 0.1405596486008785,
      "grad_norm": 981.5530395507812,
      "learning_rate": 2e-07,
      "loss": 0.1498,
      "step": 1506
    },
    {
      "clip_ratio/high_max": 0.008284735813504085,
      "clip_ratio/high_mean": 0.0030128685393719934,
      "clip_ratio/low_mean": 0.006027543422533199,
      "clip_ratio/low_min": 0.0007774365185468923,
      "clip_ratio/region_mean": 0.00904041191097349,
      "epoch": 0.1406529817008791,
      "grad_norm": 128695.6171875,
      "learning_rate": 2e-07,
      "loss": 3.1596,
      "step": 1507
    },
    {
      "clip_ratio/high_max": 0.011088922386988997,
      "clip_ratio/high_mean": 0.0029328191158128902,
      "clip_ratio/low_mean": 0.005733198820962571,
      "clip_ratio/low_min": 0.0009822351203183644,
      "clip_ratio/region_mean": 0.008666017965879291,
      "epoch": 0.14074631480087965,
      "grad_norm": 1932257.0,
      "learning_rate": 2e-07,
      "loss": 32.916,
      "step": 1508
    },
    {
      "clip_ratio/high_max": 0.010011933220084757,
      "clip_ratio/high_mean": 0.0031488184395129792,
      "clip_ratio/low_mean": 0.006271047313930467,
      "clip_ratio/low_min": 0.0005625791200145613,
      "clip_ratio/region_mean": 0.009419865877134725,
      "epoch": 0.14083964790088024,
      "grad_norm": 101780216.0,
      "learning_rate": 2e-07,
      "loss": 2019.588,
      "step": 1509
    },
    {
      "clip_ratio/high_max": 0.010317530031898059,
      "clip_ratio/high_mean": 0.002930962356913369,
      "clip_ratio/low_mean": 0.006052033044397831,
      "clip_ratio/low_min": 0.0001870120358944405,
      "clip_ratio/region_mean": 0.008982995495898649,
      "epoch": 0.14093298100088084,
      "grad_norm": 71608.890625,
      "learning_rate": 2e-07,
      "loss": 0.7753,
      "step": 1510
    },
    {
      "clip_ratio/high_max": 0.008234702530899085,
      "clip_ratio/high_mean": 0.0024690155260032043,
      "clip_ratio/low_mean": 0.006267877572099678,
      "clip_ratio/low_min": 0.00024385101824009325,
      "clip_ratio/region_mean": 0.008736893098102883,
      "epoch": 0.14102631410088143,
      "grad_norm": 170235.46875,
      "learning_rate": 2e-07,
      "loss": 6.2341,
      "step": 1511
    },
    {
      "clip_ratio/high_max": 0.00928757048677653,
      "clip_ratio/high_mean": 0.002830470531989704,
      "clip_ratio/low_mean": 0.006002189940772951,
      "clip_ratio/low_min": 0.00033641987829469144,
      "clip_ratio/region_mean": 0.008832660474581644,
      "epoch": 0.141119647200882,
      "grad_norm": 9152.591796875,
      "learning_rate": 2e-07,
      "loss": 0.6037,
      "step": 1512
    },
    {
      "clip_ratio/high_max": 0.006777602873626165,
      "clip_ratio/high_mean": 0.0019467606271064142,
      "clip_ratio/low_mean": 0.006000280773150735,
      "clip_ratio/low_min": 0.000853325114803738,
      "clip_ratio/region_mean": 0.007947041623992845,
      "epoch": 0.14121298030088258,
      "grad_norm": 394326.5625,
      "learning_rate": 2e-07,
      "loss": 7.1667,
      "step": 1513
    },
    {
      "clip_ratio/high_max": 0.009296341973822564,
      "clip_ratio/high_mean": 0.00279895230778493,
      "clip_ratio/low_mean": 0.0075139227556064725,
      "clip_ratio/low_min": 0.0012116295874875505,
      "clip_ratio/region_mean": 0.010312875063391402,
      "epoch": 0.14130631340088318,
      "grad_norm": 16538.107421875,
      "learning_rate": 2e-07,
      "loss": 0.8827,
      "step": 1514
    },
    {
      "clip_ratio/high_max": 0.00968799258407671,
      "clip_ratio/high_mean": 0.002912926909630187,
      "clip_ratio/low_mean": 0.006292820238741115,
      "clip_ratio/low_min": 0.0006654458593402524,
      "clip_ratio/region_mean": 0.009205747221130878,
      "epoch": 0.14139964650088374,
      "grad_norm": 9471.0537109375,
      "learning_rate": 2e-07,
      "loss": 0.5107,
      "step": 1515
    },
    {
      "clip_ratio/high_max": 0.007081362971803173,
      "clip_ratio/high_mean": 0.0022146700976009015,
      "clip_ratio/low_mean": 0.007093589854775928,
      "clip_ratio/low_min": 0.0010639836837071925,
      "clip_ratio/region_mean": 0.009308260108809918,
      "epoch": 0.14149297960088433,
      "grad_norm": 14725.2978515625,
      "learning_rate": 2e-07,
      "loss": 0.626,
      "step": 1516
    },
    {
      "clip_ratio/high_max": 0.008661045256303623,
      "clip_ratio/high_mean": 0.002396198060523602,
      "clip_ratio/low_mean": 0.005552623959374614,
      "clip_ratio/low_min": 0.00036145358899375424,
      "clip_ratio/region_mean": 0.007948821788886562,
      "epoch": 0.14158631270088493,
      "grad_norm": 6603321344.0,
      "learning_rate": 2e-07,
      "loss": 154126.8281,
      "step": 1517
    },
    {
      "clip_ratio/high_max": 0.00894778678775765,
      "clip_ratio/high_mean": 0.002777270332444459,
      "clip_ratio/low_mean": 0.0058517157231108285,
      "clip_ratio/low_min": 0.0005723015892726835,
      "clip_ratio/region_mean": 0.008628986179246567,
      "epoch": 0.1416796458008855,
      "grad_norm": 655.6632690429688,
      "learning_rate": 2e-07,
      "loss": 0.1233,
      "step": 1518
    },
    {
      "clip_ratio/high_max": 0.011683010030537844,
      "clip_ratio/high_mean": 0.002982062622322701,
      "clip_ratio/low_mean": 0.005868957348866388,
      "clip_ratio/low_min": 0.0005655200802721083,
      "clip_ratio/region_mean": 0.008851020160363987,
      "epoch": 0.14177297890088608,
      "grad_norm": 4108.5869140625,
      "learning_rate": 2e-07,
      "loss": 0.3282,
      "step": 1519
    },
    {
      "clip_ratio/high_max": 0.009060731885256246,
      "clip_ratio/high_mean": 0.002882993663661182,
      "clip_ratio/low_mean": 0.006500883842818439,
      "clip_ratio/low_min": 0.0007748263869871153,
      "clip_ratio/region_mean": 0.009383877506479621,
      "epoch": 0.14186631200088667,
      "grad_norm": 486915.40625,
      "learning_rate": 2e-07,
      "loss": 4.2782,
      "step": 1520
    },
    {
      "clip_ratio/high_max": 0.0076965129119344056,
      "clip_ratio/high_mean": 0.00240215029407409,
      "clip_ratio/low_mean": 0.006893843208672479,
      "clip_ratio/low_min": 0.0004763833676406648,
      "clip_ratio/region_mean": 0.009295993309933692,
      "epoch": 0.14195964510088724,
      "grad_norm": 4495.9638671875,
      "learning_rate": 2e-07,
      "loss": 0.2884,
      "step": 1521
    },
    {
      "clip_ratio/high_max": 0.008645318142953329,
      "clip_ratio/high_mean": 0.002517766995879356,
      "clip_ratio/low_mean": 0.006513162807095796,
      "clip_ratio/low_min": 0.0010720892714743968,
      "clip_ratio/region_mean": 0.009030929912114516,
      "epoch": 0.14205297820088783,
      "grad_norm": 99.81855773925781,
      "learning_rate": 2e-07,
      "loss": 0.1018,
      "step": 1522
    },
    {
      "clip_ratio/high_max": 0.00824895515688695,
      "clip_ratio/high_mean": 0.0025654626115283463,
      "clip_ratio/low_mean": 0.006599472995731048,
      "clip_ratio/low_min": 0.0006309193122433499,
      "clip_ratio/region_mean": 0.009164935851003975,
      "epoch": 0.14214631130088842,
      "grad_norm": 146747968.0,
      "learning_rate": 2e-07,
      "loss": 1866.9125,
      "step": 1523
    },
    {
      "clip_ratio/high_max": 0.010064619942568243,
      "clip_ratio/high_mean": 0.00298382701294031,
      "clip_ratio/low_mean": 0.007671121944440529,
      "clip_ratio/low_min": 0.0009944448429450858,
      "clip_ratio/region_mean": 0.010654948971932754,
      "epoch": 0.142239644400889,
      "grad_norm": 3083.24853515625,
      "learning_rate": 2e-07,
      "loss": 0.2349,
      "step": 1524
    },
    {
      "clip_ratio/high_max": 0.008845160758937709,
      "clip_ratio/high_mean": 0.002780696016998263,
      "clip_ratio/low_mean": 0.0065067932300735265,
      "clip_ratio/low_min": 0.000947483040363295,
      "clip_ratio/region_mean": 0.009287489228881896,
      "epoch": 0.14233297750088958,
      "grad_norm": 21589.935546875,
      "learning_rate": 2e-07,
      "loss": 1.1667,
      "step": 1525
    },
    {
      "clip_ratio/high_max": 0.009768448908289429,
      "clip_ratio/high_mean": 0.0029229416395537555,
      "clip_ratio/low_mean": 0.006703561943140812,
      "clip_ratio/low_min": 0.0009810920591917238,
      "clip_ratio/region_mean": 0.009626503800973296,
      "epoch": 0.14242631060089017,
      "grad_norm": 8000.0712890625,
      "learning_rate": 2e-07,
      "loss": 0.6816,
      "step": 1526
    },
    {
      "clip_ratio/high_max": 0.00900485587771982,
      "clip_ratio/high_mean": 0.002676327021617908,
      "clip_ratio/low_mean": 0.007134319545002654,
      "clip_ratio/low_min": 0.000811913605502923,
      "clip_ratio/region_mean": 0.009810646646656096,
      "epoch": 0.14251964370089074,
      "grad_norm": 73758.578125,
      "learning_rate": 2e-07,
      "loss": 3.4707,
      "step": 1527
    },
    {
      "clip_ratio/high_max": 0.009686201301519759,
      "clip_ratio/high_mean": 0.003278753072663676,
      "clip_ratio/low_mean": 0.006450626082369126,
      "clip_ratio/low_min": 0.00015682379671488889,
      "clip_ratio/region_mean": 0.009729379002237692,
      "epoch": 0.14261297680089133,
      "grad_norm": 807.4011840820312,
      "learning_rate": 2e-07,
      "loss": 0.1693,
      "step": 1528
    },
    {
      "clip_ratio/high_max": 0.007009586464846507,
      "clip_ratio/high_mean": 0.002023140790697653,
      "clip_ratio/low_mean": 0.005424646835308522,
      "clip_ratio/low_min": 0.0004429418868312496,
      "clip_ratio/region_mean": 0.00744778745865915,
      "epoch": 0.14270630990089192,
      "grad_norm": 61271.99609375,
      "learning_rate": 2e-07,
      "loss": 1.3766,
      "step": 1529
    },
    {
      "clip_ratio/high_max": 0.010643712928867899,
      "clip_ratio/high_mean": 0.002818359855154995,
      "clip_ratio/low_mean": 0.006773369270376861,
      "clip_ratio/low_min": 0.00038101487643871224,
      "clip_ratio/region_mean": 0.009591729118255898,
      "epoch": 0.14279964300089248,
      "grad_norm": 2024.4600830078125,
      "learning_rate": 2e-07,
      "loss": 0.2084,
      "step": 1530
    },
    {
      "clip_ratio/high_max": 0.009214299556333572,
      "clip_ratio/high_mean": 0.0031974725243344437,
      "clip_ratio/low_mean": 0.008182010235032067,
      "clip_ratio/low_min": 0.0010511075015529059,
      "clip_ratio/region_mean": 0.011379483068594709,
      "epoch": 0.14289297610089308,
      "grad_norm": 170745.96875,
      "learning_rate": 2e-07,
      "loss": 2.1218,
      "step": 1531
    },
    {
      "clip_ratio/high_max": 0.009414680651389062,
      "clip_ratio/high_mean": 0.0030728381061635446,
      "clip_ratio/low_mean": 0.0074654604541137815,
      "clip_ratio/low_min": 0.0008200504489650484,
      "clip_ratio/region_mean": 0.01053829852025956,
      "epoch": 0.14298630920089367,
      "grad_norm": 21289.640625,
      "learning_rate": 2e-07,
      "loss": 0.7571,
      "step": 1532
    },
    {
      "clip_ratio/high_max": 0.01055282712331973,
      "clip_ratio/high_mean": 0.003025742553290911,
      "clip_ratio/low_mean": 0.007302983169211075,
      "clip_ratio/low_min": 0.0006236130611796398,
      "clip_ratio/region_mean": 0.010328725766157731,
      "epoch": 0.14307964230089426,
      "grad_norm": 163816.78125,
      "learning_rate": 2e-07,
      "loss": 5.4718,
      "step": 1533
    },
    {
      "clip_ratio/high_max": 0.011372782566468231,
      "clip_ratio/high_mean": 0.0029087152870488353,
      "clip_ratio/low_mean": 0.006545605690917,
      "clip_ratio/low_min": 0.0008421165512118023,
      "clip_ratio/region_mean": 0.009454320956137963,
      "epoch": 0.14317297540089483,
      "grad_norm": 354433.9375,
      "learning_rate": 2e-07,
      "loss": 7.3524,
      "step": 1534
    },
    {
      "clip_ratio/high_max": 0.009848656656686217,
      "clip_ratio/high_mean": 0.0031519729673163965,
      "clip_ratio/low_mean": 0.0070607112284051254,
      "clip_ratio/low_min": 0.0006706478179694386,
      "clip_ratio/region_mean": 0.010212684137513861,
      "epoch": 0.14326630850089542,
      "grad_norm": 13342.822265625,
      "learning_rate": 2e-07,
      "loss": 0.6595,
      "step": 1535
    },
    {
      "clip_ratio/high_max": 0.012102187276468612,
      "clip_ratio/high_mean": 0.0030948711282690056,
      "clip_ratio/low_mean": 0.0074130619468633085,
      "clip_ratio/low_min": 0.0011056901566917077,
      "clip_ratio/region_mean": 0.010507932980544865,
      "epoch": 0.143359641600896,
      "grad_norm": 60809716.0,
      "learning_rate": 2e-07,
      "loss": 2395.5427,
      "step": 1536
    },
    {
      "clip_ratio/high_max": 0.002211614621046465,
      "clip_ratio/high_mean": 0.000705748569998832,
      "clip_ratio/low_mean": 0.002111162139044609,
      "clip_ratio/low_min": 2.3432032321579754e-05,
      "clip_ratio/region_mean": 0.002816910739056766,
      "completions/clipped_ratio": 0.10809326171875,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4096.0,
      "completions/mean_length": 879.2676391601562,
      "completions/mean_terminated_length": 489.420654296875,
      "completions/min_length": 5.0,
      "completions/min_terminated_length": 5.0,
      "epoch": 0.14345297470089657,
      "grad_norm": 8.912792205810547,
      "learning_rate": 2e-07,
      "loss": 0.0888,
      "num_tokens": 1170370290.0,
      "reward": 0.1374773383140564,
      "reward_std": 0.12984158098697662,
      "rewards/simpleverify_reward/mean": 0.1374773234128952,
      "rewards/simpleverify_reward/std": 0.34435197710990906,
      "step": 1537
    },
    {
      "clip_ratio/high_max": 0.003377609893504996,
      "clip_ratio/high_mean": 0.0008671264563417935,
      "clip_ratio/low_mean": 0.0021102764003444463,
      "clip_ratio/low_min": 8.471232831652742e-05,
      "clip_ratio/region_mean": 0.002977402815304231,
      "epoch": 0.14354630780089717,
      "grad_norm": 304.5766296386719,
      "learning_rate": 2e-07,
      "loss": 0.0585,
      "step": 1538
    },
    {
      "clip_ratio/high_max": 0.0026005116465057654,
      "clip_ratio/high_mean": 0.0007171390060989324,
      "clip_ratio/low_mean": 0.002032235912338365,
      "clip_ratio/low_min": 2.346100291106268e-05,
      "clip_ratio/region_mean": 0.0027493749366840348,
      "epoch": 0.14363964090089776,
      "grad_norm": 111.13668823242188,
      "learning_rate": 2e-07,
      "loss": 0.0978,
      "step": 1539
    },
    {
      "clip_ratio/high_max": 0.002278100657349569,
      "clip_ratio/high_mean": 0.0006155387409307878,
      "clip_ratio/low_mean": 0.0025929062394425273,
      "clip_ratio/low_min": 0.00032243828627542825,
      "clip_ratio/region_mean": 0.003208444955816958,
      "epoch": 0.14373297400089832,
      "grad_norm": 239.9208984375,
      "learning_rate": 2e-07,
      "loss": 0.134,
      "step": 1540
    },
    {
      "clip_ratio/high_max": 0.0024939209270087304,
      "clip_ratio/high_mean": 0.0006617030683173653,
      "clip_ratio/low_mean": 0.0019426922335696872,
      "clip_ratio/low_min": 2.3610215066582896e-05,
      "clip_ratio/region_mean": 0.0026043952857435215,
      "epoch": 0.14382630710089891,
      "grad_norm": 9.009964942932129,
      "learning_rate": 2e-07,
      "loss": 0.0746,
      "step": 1541
    },
    {
      "clip_ratio/high_max": 0.003134078571747523,
      "clip_ratio/high_mean": 0.0007966041393956402,
      "clip_ratio/low_mean": 0.001956724860065151,
      "clip_ratio/low_min": 8.228290266742988e-05,
      "clip_ratio/region_mean": 0.0027533290412975475,
      "epoch": 0.1439196402008995,
      "grad_norm": 164.1133575439453,
      "learning_rate": 2e-07,
      "loss": 0.0244,
      "step": 1542
    },
    {
      "clip_ratio/high_max": 0.0033183138402819168,
      "clip_ratio/high_mean": 0.0009084561879717512,
      "clip_ratio/low_mean": 0.0022759906642022543,
      "clip_ratio/low_min": 4.203094385957229e-05,
      "clip_ratio/region_mean": 0.003184446832165122,
      "epoch": 0.14401297330090007,
      "grad_norm": 13.685999870300293,
      "learning_rate": 2e-07,
      "loss": 0.0706,
      "step": 1543
    },
    {
      "clip_ratio/high_max": 0.002249881421448663,
      "clip_ratio/high_mean": 0.000603701439104043,
      "clip_ratio/low_mean": 0.0024824213614920154,
      "clip_ratio/low_min": 2.545327788538998e-05,
      "clip_ratio/region_mean": 0.003086122822423931,
      "epoch": 0.14410630640090066,
      "grad_norm": 6.723982334136963,
      "learning_rate": 2e-07,
      "loss": 0.031,
      "step": 1544
    },
    {
      "clip_ratio/high_max": 0.002946922613773495,
      "clip_ratio/high_mean": 0.0007225065901366179,
      "clip_ratio/low_mean": 0.002621623149025254,
      "clip_ratio/low_min": 9.045352271641605e-05,
      "clip_ratio/region_mean": 0.003344129756442271,
      "epoch": 0.14419963950090126,
      "grad_norm": 20375.833984375,
      "learning_rate": 2e-07,
      "loss": 0.6133,
      "step": 1545
    },
    {
      "clip_ratio/high_max": 0.0022476805788755883,
      "clip_ratio/high_mean": 0.000642785543732316,
      "clip_ratio/low_mean": 0.0026485782291274518,
      "clip_ratio/low_min": 4.6672266762470827e-05,
      "clip_ratio/region_mean": 0.0032913637332967483,
      "epoch": 0.14429297260090182,
      "grad_norm": 18.060691833496094,
      "learning_rate": 2e-07,
      "loss": 0.0299,
      "step": 1546
    },
    {
      "clip_ratio/high_max": 0.001954823801497696,
      "clip_ratio/high_mean": 0.0005951875868959178,
      "clip_ratio/low_mean": 0.002449255589453969,
      "clip_ratio/low_min": 1.5555002391920425e-05,
      "clip_ratio/region_mean": 0.003044443146791309,
      "epoch": 0.1443863057009024,
      "grad_norm": 55.120121002197266,
      "learning_rate": 2e-07,
      "loss": 0.0908,
      "step": 1547
    },
    {
      "clip_ratio/high_max": 0.0035312757827341557,
      "clip_ratio/high_mean": 0.0008054050349528552,
      "clip_ratio/low_mean": 0.004205702505714726,
      "clip_ratio/low_min": 7.32463231543079e-05,
      "clip_ratio/region_mean": 0.005011107627069578,
      "epoch": 0.144479638800903,
      "grad_norm": 2433.57080078125,
      "learning_rate": 2e-07,
      "loss": 0.1397,
      "step": 1548
    },
    {
      "clip_ratio/high_max": 0.002916299537901068,
      "clip_ratio/high_mean": 0.0007489319314117893,
      "clip_ratio/low_mean": 0.003125309718598146,
      "clip_ratio/low_min": 3.756762089324184e-05,
      "clip_ratio/region_mean": 0.003874241592711769,
      "epoch": 0.14457297190090357,
      "grad_norm": 24.147611618041992,
      "learning_rate": 2e-07,
      "loss": 0.0948,
      "step": 1549
    },
    {
      "clip_ratio/high_max": 0.004565006791381165,
      "clip_ratio/high_mean": 0.0013607368819066323,
      "clip_ratio/low_mean": 0.003185382403898984,
      "clip_ratio/low_min": 9.3478524377133e-05,
      "clip_ratio/region_mean": 0.0045461192858056165,
      "epoch": 0.14466630500090416,
      "grad_norm": 449.8078308105469,
      "learning_rate": 2e-07,
      "loss": 0.0714,
      "step": 1550
    },
    {
      "clip_ratio/high_max": 0.0029853354280930944,
      "clip_ratio/high_mean": 0.0008573930126658524,
      "clip_ratio/low_mean": 0.003532382288540248,
      "clip_ratio/low_min": 0.00013433950880425982,
      "clip_ratio/region_mean": 0.00438977537851315,
      "epoch": 0.14475963810090475,
      "grad_norm": 80.31497192382812,
      "learning_rate": 2e-07,
      "loss": 0.0962,
      "step": 1551
    },
    {
      "clip_ratio/high_max": 0.005441060227894923,
      "clip_ratio/high_mean": 0.0015295807188522303,
      "clip_ratio/low_mean": 0.0029297967412276193,
      "clip_ratio/low_min": 6.410304649762111e-05,
      "clip_ratio/region_mean": 0.0044593773782253265,
      "epoch": 0.14485297120090532,
      "grad_norm": 230446.203125,
      "learning_rate": 2e-07,
      "loss": 4.666,
      "step": 1552
    },
    {
      "clip_ratio/high_max": 0.004410355744767003,
      "clip_ratio/high_mean": 0.0011352671217537136,
      "clip_ratio/low_mean": 0.003462927110376768,
      "clip_ratio/low_min": 0.0001372272217849968,
      "clip_ratio/region_mean": 0.0045981942530488595,
      "epoch": 0.1449463043009059,
      "grad_norm": 297.504150390625,
      "learning_rate": 2e-07,
      "loss": 0.0615,
      "step": 1553
    },
    {
      "clip_ratio/high_max": 0.002862271670892369,
      "clip_ratio/high_mean": 0.0007584672930533998,
      "clip_ratio/low_mean": 0.005094815154734533,
      "clip_ratio/low_min": 0.000385858253139304,
      "clip_ratio/region_mean": 0.005853282520547509,
      "epoch": 0.1450396374009065,
      "grad_norm": 6765.0322265625,
      "learning_rate": 2e-07,
      "loss": 0.2766,
      "step": 1554
    },
    {
      "clip_ratio/high_max": 0.0031182668208202813,
      "clip_ratio/high_mean": 0.0008782948007137747,
      "clip_ratio/low_mean": 0.002892296528443694,
      "clip_ratio/low_min": 7.104596261342522e-05,
      "clip_ratio/region_mean": 0.00377059135644231,
      "epoch": 0.1451329705009071,
      "grad_norm": 1153.030029296875,
      "learning_rate": 2e-07,
      "loss": 0.1065,
      "step": 1555
    },
    {
      "clip_ratio/high_max": 0.005102578812511638,
      "clip_ratio/high_mean": 0.0014307714445749298,
      "clip_ratio/low_mean": 0.0036433572313399054,
      "clip_ratio/low_min": 0.00013421998028206872,
      "clip_ratio/region_mean": 0.005074128734122496,
      "epoch": 0.14522630360090766,
      "grad_norm": 7667.8544921875,
      "learning_rate": 2e-07,
      "loss": 0.3593,
      "step": 1556
    },
    {
      "clip_ratio/high_max": 0.0034624508325578063,
      "clip_ratio/high_mean": 0.0010738922023847408,
      "clip_ratio/low_mean": 0.00438159688928863,
      "clip_ratio/low_min": 0.0004016568691440625,
      "clip_ratio/region_mean": 0.0054554891685256734,
      "epoch": 0.14531963670090825,
      "grad_norm": 16536145.0,
      "learning_rate": 2e-07,
      "loss": 1526.3396,
      "step": 1557
    },
    {
      "clip_ratio/high_max": 0.003695548215546296,
      "clip_ratio/high_mean": 0.000976851378709398,
      "clip_ratio/low_mean": 0.0034563163098937366,
      "clip_ratio/low_min": 4.529960096988361e-05,
      "clip_ratio/region_mean": 0.004433167814568151,
      "epoch": 0.14541296980090884,
      "grad_norm": 16510.6171875,
      "learning_rate": 2e-07,
      "loss": 0.3931,
      "step": 1558
    },
    {
      "clip_ratio/high_max": 0.00559506018544198,
      "clip_ratio/high_mean": 0.00154195248387623,
      "clip_ratio/low_mean": 0.003374817155417986,
      "clip_ratio/low_min": 6.49913345114328e-05,
      "clip_ratio/region_mean": 0.004916769670671783,
      "epoch": 0.1455063029009094,
      "grad_norm": 485039232.0,
      "learning_rate": 2e-07,
      "loss": 5249.3389,
      "step": 1559
    },
    {
      "clip_ratio/high_max": 0.00534536205304903,
      "clip_ratio/high_mean": 0.0014025170357854222,
      "clip_ratio/low_mean": 0.004518730434938334,
      "clip_ratio/low_min": 0.00019520846581144724,
      "clip_ratio/region_mean": 0.0059212476189713925,
      "epoch": 0.14559963600091,
      "grad_norm": 165.0186309814453,
      "learning_rate": 2e-07,
      "loss": 0.0762,
      "step": 1560
    },
    {
      "clip_ratio/high_max": 0.005722401670936961,
      "clip_ratio/high_mean": 0.0013543949880840955,
      "clip_ratio/low_mean": 0.002925886758021079,
      "clip_ratio/low_min": 2.0229810616001487e-05,
      "clip_ratio/region_mean": 0.004280281762476079,
      "epoch": 0.1456929691009106,
      "grad_norm": 210335.40625,
      "learning_rate": 2e-07,
      "loss": 5.861,
      "step": 1561
    },
    {
      "clip_ratio/high_max": 0.004633546512195608,
      "clip_ratio/high_mean": 0.001213361195368634,
      "clip_ratio/low_mean": 0.0038611189665971324,
      "clip_ratio/low_min": 0.00012450464055291377,
      "clip_ratio/region_mean": 0.005074480002804194,
      "epoch": 0.14578630220091116,
      "grad_norm": 4127.84619140625,
      "learning_rate": 2e-07,
      "loss": 0.2817,
      "step": 1562
    },
    {
      "clip_ratio/high_max": 0.0035272110671940027,
      "clip_ratio/high_mean": 0.001039553351347422,
      "clip_ratio/low_mean": 0.00428113408270292,
      "clip_ratio/low_min": 0.0002839450671672239,
      "clip_ratio/region_mean": 0.005320687203493435,
      "epoch": 0.14587963530091175,
      "grad_norm": 25929.2109375,
      "learning_rate": 2e-07,
      "loss": 1.1931,
      "step": 1563
    },
    {
      "clip_ratio/high_max": 0.005111567632411607,
      "clip_ratio/high_mean": 0.0012572412379086018,
      "clip_ratio/low_mean": 0.004145460217841901,
      "clip_ratio/low_min": 0.00026798166800290346,
      "clip_ratio/region_mean": 0.005402701324783266,
      "epoch": 0.14597296840091234,
      "grad_norm": 1335.1209716796875,
      "learning_rate": 2e-07,
      "loss": 0.1371,
      "step": 1564
    },
    {
      "clip_ratio/high_max": 0.004718204494565725,
      "clip_ratio/high_mean": 0.0013683755532838404,
      "clip_ratio/low_mean": 0.0036812634862144478,
      "clip_ratio/low_min": 3.937769724871032e-05,
      "clip_ratio/region_mean": 0.005049638952186797,
      "epoch": 0.1460663015009129,
      "grad_norm": 747700800.0,
      "learning_rate": 2e-07,
      "loss": 6094.103,
      "step": 1565
    },
    {
      "clip_ratio/high_max": 0.0054401040833909065,
      "clip_ratio/high_mean": 0.0014174259868013905,
      "clip_ratio/low_mean": 0.003600897718570195,
      "clip_ratio/low_min": 0.0001460823605157202,
      "clip_ratio/region_mean": 0.005018323776312172,
      "epoch": 0.1461596346009135,
      "grad_norm": 932.6537475585938,
      "learning_rate": 2e-07,
      "loss": 0.0837,
      "step": 1566
    },
    {
      "clip_ratio/high_max": 0.006658624064584728,
      "clip_ratio/high_mean": 0.0014899123980285367,
      "clip_ratio/low_mean": 0.003889949934091419,
      "clip_ratio/low_min": 0.00014982879474700894,
      "clip_ratio/region_mean": 0.005379862283007242,
      "epoch": 0.1462529677009141,
      "grad_norm": 124.15176391601562,
      "learning_rate": 2e-07,
      "loss": 0.0764,
      "step": 1567
    },
    {
      "clip_ratio/high_max": 0.00475490639655618,
      "clip_ratio/high_mean": 0.0013247423648863332,
      "clip_ratio/low_mean": 0.004170502514170948,
      "clip_ratio/low_min": 0.00012030243669869378,
      "clip_ratio/region_mean": 0.005495244840858504,
      "epoch": 0.14634630080091465,
      "grad_norm": 40511.26953125,
      "learning_rate": 2e-07,
      "loss": 0.6947,
      "step": 1568
    },
    {
      "clip_ratio/high_max": 0.005593403242528439,
      "clip_ratio/high_mean": 0.0013622679089166922,
      "clip_ratio/low_mean": 0.003660749163827859,
      "clip_ratio/low_min": 4.648140566132497e-05,
      "clip_ratio/region_mean": 0.005023017001803964,
      "epoch": 0.14643963390091524,
      "grad_norm": 163.91114807128906,
      "learning_rate": 2e-07,
      "loss": 0.0626,
      "step": 1569
    },
    {
      "clip_ratio/high_max": 0.004075331264175475,
      "clip_ratio/high_mean": 0.0011435385549702914,
      "clip_ratio/low_mean": 0.004240931251842994,
      "clip_ratio/low_min": 4.470250860322267e-05,
      "clip_ratio/region_mean": 0.005384469957789406,
      "epoch": 0.14653296700091584,
      "grad_norm": 13853.1025390625,
      "learning_rate": 2e-07,
      "loss": 1.2314,
      "step": 1570
    },
    {
      "clip_ratio/high_max": 0.005531830865947995,
      "clip_ratio/high_mean": 0.001437484595044225,
      "clip_ratio/low_mean": 0.0036498199769994244,
      "clip_ratio/low_min": 3.8118207157822326e-05,
      "clip_ratio/region_mean": 0.005087304627522826,
      "epoch": 0.1466263001009164,
      "grad_norm": 1689.6385498046875,
      "learning_rate": 2e-07,
      "loss": 0.1085,
      "step": 1571
    },
    {
      "clip_ratio/high_max": 0.004857852436543908,
      "clip_ratio/high_mean": 0.0013512089280993678,
      "clip_ratio/low_mean": 0.0038360027174348943,
      "clip_ratio/low_min": 0.00026019781216746196,
      "clip_ratio/region_mean": 0.005187211616430432,
      "epoch": 0.146719633200917,
      "grad_norm": 88033776.0,
      "learning_rate": 2e-07,
      "loss": 796.0383,
      "step": 1572
    },
    {
      "clip_ratio/high_max": 0.004646780667826533,
      "clip_ratio/high_mean": 0.001323175718425773,
      "clip_ratio/low_mean": 0.004232597209920641,
      "clip_ratio/low_min": 0.00047262019506888464,
      "clip_ratio/region_mean": 0.00555577281920705,
      "epoch": 0.14681296630091759,
      "grad_norm": 63.26753616333008,
      "learning_rate": 2e-07,
      "loss": 0.0899,
      "step": 1573
    },
    {
      "clip_ratio/high_max": 0.005728037140215747,
      "clip_ratio/high_mean": 0.0014619586891058134,
      "clip_ratio/low_mean": 0.004012962152046384,
      "clip_ratio/low_min": 0.00012834234530600952,
      "clip_ratio/region_mean": 0.00547492089390289,
      "epoch": 0.14690629940091818,
      "grad_norm": 280492.1875,
      "learning_rate": 2e-07,
      "loss": 8.8764,
      "step": 1574
    },
    {
      "clip_ratio/high_max": 0.0066244946865481324,
      "clip_ratio/high_mean": 0.0017325219796475722,
      "clip_ratio/low_mean": 0.003476656274870038,
      "clip_ratio/low_min": 0.00010099716746481135,
      "clip_ratio/region_mean": 0.0052091781835770234,
      "epoch": 0.14699963250091874,
      "grad_norm": 2692.86962890625,
      "learning_rate": 2e-07,
      "loss": 0.0937,
      "step": 1575
    },
    {
      "clip_ratio/high_max": 0.004328511364292353,
      "clip_ratio/high_mean": 0.001128164745750837,
      "clip_ratio/low_mean": 0.003012695971847279,
      "clip_ratio/low_min": 0.00012139391219534446,
      "clip_ratio/region_mean": 0.004140860750339925,
      "epoch": 0.14709296560091933,
      "grad_norm": 9919.4365234375,
      "learning_rate": 2e-07,
      "loss": 0.2977,
      "step": 1576
    },
    {
      "clip_ratio/high_max": 0.0042594378246576525,
      "clip_ratio/high_mean": 0.0012430160604708362,
      "clip_ratio/low_mean": 0.00315980378218228,
      "clip_ratio/low_min": 0.0003874116810038686,
      "clip_ratio/region_mean": 0.004402819919050671,
      "epoch": 0.14718629870091993,
      "grad_norm": 20244.82421875,
      "learning_rate": 2e-07,
      "loss": 0.7428,
      "step": 1577
    },
    {
      "clip_ratio/high_max": 0.004609750802046619,
      "clip_ratio/high_mean": 0.0013378753574215807,
      "clip_ratio/low_mean": 0.003870659704261925,
      "clip_ratio/low_min": 2.023308479692787e-05,
      "clip_ratio/region_mean": 0.005208535127167124,
      "epoch": 0.1472796318009205,
      "grad_norm": 24321.505859375,
      "learning_rate": 2e-07,
      "loss": 0.6691,
      "step": 1578
    },
    {
      "clip_ratio/high_max": 0.0065661854823702015,
      "clip_ratio/high_mean": 0.0017536837694933638,
      "clip_ratio/low_mean": 0.003323837951029418,
      "clip_ratio/low_min": 0.00021239481611701194,
      "clip_ratio/region_mean": 0.005077521709608845,
      "epoch": 0.14737296490092108,
      "grad_norm": 2095457.125,
      "learning_rate": 2e-07,
      "loss": 38.7576,
      "step": 1579
    },
    {
      "clip_ratio/high_max": 0.005795391174615361,
      "clip_ratio/high_mean": 0.0015046996595629025,
      "clip_ratio/low_mean": 0.003340660172398202,
      "clip_ratio/low_min": 0.0003773459047806682,
      "clip_ratio/region_mean": 0.004845359748287592,
      "epoch": 0.14746629800092168,
      "grad_norm": 4998.470703125,
      "learning_rate": 2e-07,
      "loss": 0.1908,
      "step": 1580
    },
    {
      "clip_ratio/high_max": 0.00371054661081871,
      "clip_ratio/high_mean": 0.0011066176084568724,
      "clip_ratio/low_mean": 0.00423023896291852,
      "clip_ratio/low_min": 6.965451029827818e-05,
      "clip_ratio/region_mean": 0.005336856687790714,
      "epoch": 0.14755963110092224,
      "grad_norm": 74389.8984375,
      "learning_rate": 2e-07,
      "loss": 5.8943,
      "step": 1581
    },
    {
      "clip_ratio/high_max": 0.004457714385353029,
      "clip_ratio/high_mean": 0.001305895759287523,
      "clip_ratio/low_mean": 0.0033970124713960104,
      "clip_ratio/low_min": 0.00012230996981088538,
      "clip_ratio/region_mean": 0.004702908307081088,
      "epoch": 0.14765296420092283,
      "grad_norm": 646.9983520507812,
      "learning_rate": 2e-07,
      "loss": 0.0924,
      "step": 1582
    },
    {
      "clip_ratio/high_max": 0.0046272432955447584,
      "clip_ratio/high_mean": 0.0012296808290557237,
      "clip_ratio/low_mean": 0.004426087674801238,
      "clip_ratio/low_min": 0.000152047964547819,
      "clip_ratio/region_mean": 0.005655768472934142,
      "epoch": 0.14774629730092342,
      "grad_norm": 368296.4375,
      "learning_rate": 2e-07,
      "loss": 3.9697,
      "step": 1583
    },
    {
      "clip_ratio/high_max": 0.005422829963208642,
      "clip_ratio/high_mean": 0.0016615514396107756,
      "clip_ratio/low_mean": 0.004016717757622246,
      "clip_ratio/low_min": 7.273552637343528e-05,
      "clip_ratio/region_mean": 0.005678269153577276,
      "epoch": 0.147839630400924,
      "grad_norm": 174.88726806640625,
      "learning_rate": 2e-07,
      "loss": 0.092,
      "step": 1584
    },
    {
      "clip_ratio/high_max": 0.005313081717758905,
      "clip_ratio/high_mean": 0.0016538888139621122,
      "clip_ratio/low_mean": 0.003769687384192366,
      "clip_ratio/low_min": 0.0002925292337749852,
      "clip_ratio/region_mean": 0.00542357619269751,
      "epoch": 0.14793296350092458,
      "grad_norm": 2833930.0,
      "learning_rate": 2e-07,
      "loss": 945.7839,
      "step": 1585
    },
    {
      "clip_ratio/high_max": 0.005131533398525789,
      "clip_ratio/high_mean": 0.0016438806324003963,
      "clip_ratio/low_mean": 0.0038448995910584927,
      "clip_ratio/low_min": 9.757194493431598e-05,
      "clip_ratio/region_mean": 0.005488780167070217,
      "epoch": 0.14802629660092517,
      "grad_norm": 19251790.0,
      "learning_rate": 2e-07,
      "loss": 374.1506,
      "step": 1586
    },
    {
      "clip_ratio/high_max": 0.007890586202847771,
      "clip_ratio/high_mean": 0.0019477940386423143,
      "clip_ratio/low_mean": 0.004134977894864278,
      "clip_ratio/low_min": 9.48214074014686e-05,
      "clip_ratio/region_mean": 0.0060827720299130306,
      "epoch": 0.14811962970092574,
      "grad_norm": 277349.71875,
      "learning_rate": 2e-07,
      "loss": 5.5691,
      "step": 1587
    },
    {
      "clip_ratio/high_max": 0.006817913948907517,
      "clip_ratio/high_mean": 0.0018671789966901997,
      "clip_ratio/low_mean": 0.00415114316274412,
      "clip_ratio/low_min": 0.00019127158157061785,
      "clip_ratio/region_mean": 0.006018322164891288,
      "epoch": 0.14821296280092633,
      "grad_norm": 5144287.0,
      "learning_rate": 2e-07,
      "loss": 191.1135,
      "step": 1588
    },
    {
      "clip_ratio/high_max": 0.008147741107677575,
      "clip_ratio/high_mean": 0.001904898937937105,
      "clip_ratio/low_mean": 0.00343523077754071,
      "clip_ratio/low_min": 7.04045087331906e-05,
      "clip_ratio/region_mean": 0.005340129624528345,
      "epoch": 0.14830629590092692,
      "grad_norm": 410224.40625,
      "learning_rate": 2e-07,
      "loss": 6.3965,
      "step": 1589
    },
    {
      "clip_ratio/high_max": 0.00803140282368986,
      "clip_ratio/high_mean": 0.0018679034219530877,
      "clip_ratio/low_mean": 0.0037766193636343814,
      "clip_ratio/low_min": 0.00022736227492714534,
      "clip_ratio/region_mean": 0.0056445228547090665,
      "epoch": 0.14839962900092749,
      "grad_norm": 14322665.0,
      "learning_rate": 2e-07,
      "loss": 96144.8359,
      "step": 1590
    },
    {
      "clip_ratio/high_max": 0.004955992611940019,
      "clip_ratio/high_mean": 0.0014597349036193918,
      "clip_ratio/low_mean": 0.0037004901314503513,
      "clip_ratio/low_min": 0.0002092050272040069,
      "clip_ratio/region_mean": 0.005160225096915383,
      "epoch": 0.14849296210092808,
      "grad_norm": 253693.3125,
      "learning_rate": 2e-07,
      "loss": 15.0933,
      "step": 1591
    },
    {
      "clip_ratio/high_max": 0.005251635680906475,
      "clip_ratio/high_mean": 0.0013144236245352658,
      "clip_ratio/low_mean": 0.004352452626335435,
      "clip_ratio/low_min": 0.00034142493223043857,
      "clip_ratio/region_mean": 0.0056668763209017925,
      "epoch": 0.14858629520092867,
      "grad_norm": 494.1700134277344,
      "learning_rate": 2e-07,
      "loss": 0.1271,
      "step": 1592
    },
    {
      "clip_ratio/high_max": 0.003936445957151591,
      "clip_ratio/high_mean": 0.0012080175761184364,
      "clip_ratio/low_mean": 0.004424463950272184,
      "clip_ratio/low_min": 0.0001345091450275504,
      "clip_ratio/region_mean": 0.005632481494103558,
      "epoch": 0.14867962830092923,
      "grad_norm": 82.83440399169922,
      "learning_rate": 2e-07,
      "loss": 0.0821,
      "step": 1593
    },
    {
      "clip_ratio/high_max": 0.004486677578825038,
      "clip_ratio/high_mean": 0.001299912815738935,
      "clip_ratio/low_mean": 0.002958880224468885,
      "clip_ratio/low_min": 0.00010370916788815521,
      "clip_ratio/region_mean": 0.004258793043845799,
      "epoch": 0.14877296140092983,
      "grad_norm": 458508.65625,
      "learning_rate": 2e-07,
      "loss": 16.2921,
      "step": 1594
    },
    {
      "clip_ratio/high_max": 0.005936224195465911,
      "clip_ratio/high_mean": 0.0014894535561325029,
      "clip_ratio/low_mean": 0.00339493814681191,
      "clip_ratio/low_min": 4.909662311547436e-05,
      "clip_ratio/region_mean": 0.004884391753876116,
      "epoch": 0.14886629450093042,
      "grad_norm": 6183336.5,
      "learning_rate": 2e-07,
      "loss": 149.469,
      "step": 1595
    },
    {
      "clip_ratio/high_max": 0.006086679321015254,
      "clip_ratio/high_mean": 0.0016151971140061505,
      "clip_ratio/low_mean": 0.00464912093593739,
      "clip_ratio/low_min": 0.00021799594833282754,
      "clip_ratio/region_mean": 0.006264318260946311,
      "epoch": 0.148959627600931,
      "grad_norm": 10580483.0,
      "learning_rate": 2e-07,
      "loss": 161.0538,
      "step": 1596
    },
    {
      "clip_ratio/high_max": 0.005749824020313099,
      "clip_ratio/high_mean": 0.0013815177690048586,
      "clip_ratio/low_mean": 0.00399625002319226,
      "clip_ratio/low_min": 0.00021896869657211937,
      "clip_ratio/region_mean": 0.005377767738536932,
      "epoch": 0.14905296070093157,
      "grad_norm": 2545.24951171875,
      "learning_rate": 2e-07,
      "loss": 0.1768,
      "step": 1597
    },
    {
      "clip_ratio/high_max": 0.006102879633544944,
      "clip_ratio/high_mean": 0.0018576995244075079,
      "clip_ratio/low_mean": 0.005006935891287867,
      "clip_ratio/low_min": 0.0004831906062463531,
      "clip_ratio/region_mean": 0.006864635230158456,
      "epoch": 0.14914629380093217,
      "grad_norm": 1132.4833984375,
      "learning_rate": 2e-07,
      "loss": 0.1417,
      "step": 1598
    },
    {
      "clip_ratio/high_max": 0.005940967083006399,
      "clip_ratio/high_mean": 0.001463068410885171,
      "clip_ratio/low_mean": 0.004041787993628532,
      "clip_ratio/low_min": 0.00042293403203075286,
      "clip_ratio/region_mean": 0.005504856526385993,
      "epoch": 0.14923962690093276,
      "grad_norm": 2489.97607421875,
      "learning_rate": 2e-07,
      "loss": 0.1601,
      "step": 1599
    },
    {
      "clip_ratio/high_max": 0.003541258272889536,
      "clip_ratio/high_mean": 0.0010232240401819581,
      "clip_ratio/low_mean": 0.004104691630345769,
      "clip_ratio/low_min": 0.0002154818139388226,
      "clip_ratio/region_mean": 0.005127915603225119,
      "epoch": 0.14933296000093332,
      "grad_norm": 256.2895812988281,
      "learning_rate": 2e-07,
      "loss": 0.1075,
      "step": 1600
    },
    {
      "epoch": 0.14933296000093332,
      "step": 1600,
      "total_flos": 0.0,
      "train_loss": 349.1145901117878,
      "train_runtime": 123659.1561,
      "train_samples_per_second": 11.593,
      "train_steps_per_second": 0.013
    }
  ],
  "logging_steps": 1,
  "max_steps": 1600,
  "num_input_tokens_seen": 1170370290,
  "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
}