{
  "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": 0.013933454241071397,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4083.0,
      "completions/mean_length": 601.7027587890625,
      "completions/mean_terminated_length": 552.3270874023438,
      "completions/min_length": 2.0,
      "completions/min_terminated_length": 2.0,
      "epoch": 9.333310000058333e-05,
      "grad_norm": 0.14953841269016266,
      "learning_rate": 2e-07,
      "loss": -0.0262,
      "num_tokens": 80430161.0,
      "reward": 0.4950823187828064,
      "reward_std": 0.2626723647117615,
      "rewards/simpleverify_reward/mean": 0.4950823187828064,
      "rewards/simpleverify_reward/std": 0.49997806549072266,
      "step": 1
    },
    {
      "clip_ratio/high_max": 0.0023674857075093314,
      "clip_ratio/high_mean": 0.0009939373121596873,
      "clip_ratio/low_mean": 0.0006238104006115464,
      "clip_ratio/low_min": 6.543002746184357e-05,
      "clip_ratio/region_mean": 0.0016177476973098237,
      "epoch": 0.00018666620000116666,
      "grad_norm": 0.16591979563236237,
      "learning_rate": 2e-07,
      "loss": 0.0125,
      "step": 2
    },
    {
      "clip_ratio/high_max": 0.0021884036796109285,
      "clip_ratio/high_mean": 0.0010375111578468932,
      "clip_ratio/low_mean": 0.0006382719457178609,
      "clip_ratio/low_min": 8.395045188080985e-05,
      "clip_ratio/region_mean": 0.001675783089012839,
      "epoch": 0.00027999930000175,
      "grad_norm": 0.16085569560527802,
      "learning_rate": 2e-07,
      "loss": 0.0068,
      "step": 3
    },
    {
      "clip_ratio/high_max": 0.0021159901880309917,
      "clip_ratio/high_mean": 0.0009920538850565208,
      "clip_ratio/low_mean": 0.0005990383360767737,
      "clip_ratio/low_min": 8.886166506272275e-05,
      "clip_ratio/region_mean": 0.001591092222952284,
      "epoch": 0.0003733324000023333,
      "grad_norm": 0.1453714370727539,
      "learning_rate": 2e-07,
      "loss": 0.0124,
      "step": 4
    },
    {
      "clip_ratio/high_max": 0.0024020678029046394,
      "clip_ratio/high_mean": 0.001057566871168092,
      "clip_ratio/low_mean": 0.0006378542566380929,
      "clip_ratio/low_min": 4.592448840412544e-05,
      "clip_ratio/region_mean": 0.0016954211314441636,
      "epoch": 0.0004666655000029167,
      "grad_norm": 0.1448395699262619,
      "learning_rate": 2e-07,
      "loss": -0.0184,
      "step": 5
    },
    {
      "clip_ratio/high_max": 0.00210578952828655,
      "clip_ratio/high_mean": 0.0009746707728481852,
      "clip_ratio/low_mean": 0.00069473342045967,
      "clip_ratio/low_min": 6.13690126556321e-05,
      "clip_ratio/region_mean": 0.0016694041842129081,
      "epoch": 0.0005599986000035,
      "grad_norm": 0.13367842137813568,
      "learning_rate": 2e-07,
      "loss": 0.0233,
      "step": 6
    },
    {
      "clip_ratio/high_max": 0.0024697580374777317,
      "clip_ratio/high_mean": 0.0011314713956380729,
      "clip_ratio/low_mean": 0.0006404539362847572,
      "clip_ratio/low_min": 0.00011031753092538565,
      "clip_ratio/region_mean": 0.0017719253592076711,
      "epoch": 0.0006533317000040833,
      "grad_norm": 0.15834608674049377,
      "learning_rate": 2e-07,
      "loss": -0.0267,
      "step": 7
    },
    {
      "clip_ratio/high_max": 0.002535952859034296,
      "clip_ratio/high_mean": 0.0012183077778900042,
      "clip_ratio/low_mean": 0.0005654168326145737,
      "clip_ratio/low_min": 6.856378513475647e-05,
      "clip_ratio/region_mean": 0.0017837245904956944,
      "epoch": 0.0007466648000046666,
      "grad_norm": 0.14437466859817505,
      "learning_rate": 2e-07,
      "loss": -0.0465,
      "step": 8
    },
    {
      "clip_ratio/high_max": 0.0026118963869521394,
      "clip_ratio/high_mean": 0.0011256630386924371,
      "clip_ratio/low_mean": 0.000591609572438756,
      "clip_ratio/low_min": 3.871378703479422e-05,
      "clip_ratio/region_mean": 0.0017172726074932143,
      "epoch": 0.00083999790000525,
      "grad_norm": 0.14675189554691315,
      "learning_rate": 2e-07,
      "loss": -0.0058,
      "step": 9
    },
    {
      "clip_ratio/high_max": 0.0019322549269418232,
      "clip_ratio/high_mean": 0.0008848520192259457,
      "clip_ratio/low_mean": 0.0005785529883723939,
      "clip_ratio/low_min": 2.1938327336101793e-05,
      "clip_ratio/region_mean": 0.0014634050130553078,
      "epoch": 0.0009333310000058334,
      "grad_norm": 0.13194601237773895,
      "learning_rate": 2e-07,
      "loss": 0.0501,
      "step": 10
    },
    {
      "clip_ratio/high_max": 0.0020083620183868334,
      "clip_ratio/high_mean": 0.000981784389296081,
      "clip_ratio/low_mean": 0.0006944317246961873,
      "clip_ratio/low_min": 6.862139434815617e-05,
      "clip_ratio/region_mean": 0.0016762160885264166,
      "epoch": 0.0010266641000064166,
      "grad_norm": 0.14319021999835968,
      "learning_rate": 2e-07,
      "loss": 0.0196,
      "step": 11
    },
    {
      "clip_ratio/high_max": 0.002448038212605752,
      "clip_ratio/high_mean": 0.0011525647059897892,
      "clip_ratio/low_mean": 0.0005976697352707561,
      "clip_ratio/low_min": 1.5153352251218166e-05,
      "clip_ratio/region_mean": 0.001750234452629229,
      "epoch": 0.001119997200007,
      "grad_norm": 0.16065634787082672,
      "learning_rate": 2e-07,
      "loss": 0.0127,
      "step": 12
    },
    {
      "clip_ratio/high_max": 0.0023032343451632187,
      "clip_ratio/high_mean": 0.001108757896872703,
      "clip_ratio/low_mean": 0.0005706423480660305,
      "clip_ratio/low_min": 4.988859018340008e-05,
      "clip_ratio/region_mean": 0.001679400258581154,
      "epoch": 0.0012133303000075833,
      "grad_norm": 0.1447317898273468,
      "learning_rate": 2e-07,
      "loss": -0.0149,
      "step": 13
    },
    {
      "clip_ratio/high_max": 0.002321246785868425,
      "clip_ratio/high_mean": 0.0010930707976513077,
      "clip_ratio/low_mean": 0.0006298797507042764,
      "clip_ratio/low_min": 5.399934616434621e-05,
      "clip_ratio/region_mean": 0.0017229505247087218,
      "epoch": 0.0013066634000081666,
      "grad_norm": 0.1313619613647461,
      "learning_rate": 2e-07,
      "loss": -0.0108,
      "step": 14
    },
    {
      "clip_ratio/high_max": 0.002160714073397685,
      "clip_ratio/high_mean": 0.0009533318316243822,
      "clip_ratio/low_mean": 0.0005689996214641724,
      "clip_ratio/low_min": 7.197210106824059e-05,
      "clip_ratio/region_mean": 0.0015223314840113744,
      "epoch": 0.00139999650000875,
      "grad_norm": 0.1434275507926941,
      "learning_rate": 2e-07,
      "loss": 0.0045,
      "step": 15
    },
    {
      "clip_ratio/high_max": 0.0019111685505777132,
      "clip_ratio/high_mean": 0.0008887380445230519,
      "clip_ratio/low_mean": 0.0006624179059144808,
      "clip_ratio/low_min": 1.147315288108075e-05,
      "clip_ratio/region_mean": 0.0015511559322476387,
      "epoch": 0.0014933296000093333,
      "grad_norm": 0.13989700376987457,
      "learning_rate": 2e-07,
      "loss": 0.0664,
      "step": 16
    },
    {
      "clip_ratio/high_max": 0.0026097571462742053,
      "clip_ratio/high_mean": 0.0009490021038800478,
      "clip_ratio/low_mean": 0.0006101581711845938,
      "clip_ratio/low_min": 9.664449862611946e-06,
      "clip_ratio/region_mean": 0.0015591602568747476,
      "epoch": 0.0015866627000099165,
      "grad_norm": 0.1435522586107254,
      "learning_rate": 2e-07,
      "loss": -0.0178,
      "step": 17
    },
    {
      "clip_ratio/high_max": 0.0019821005407720804,
      "clip_ratio/high_mean": 0.0009335906197520671,
      "clip_ratio/low_mean": 0.000633852641840349,
      "clip_ratio/low_min": 5.833512113895267e-05,
      "clip_ratio/region_mean": 0.001567443265230395,
      "epoch": 0.0016799958000105,
      "grad_norm": 0.14138367772102356,
      "learning_rate": 2e-07,
      "loss": -0.0139,
      "step": 18
    },
    {
      "clip_ratio/high_max": 0.0025178020441671833,
      "clip_ratio/high_mean": 0.0010550906445132568,
      "clip_ratio/low_mean": 0.0005183770508665475,
      "clip_ratio/low_min": 1.2480031728046015e-05,
      "clip_ratio/region_mean": 0.0015734676635474898,
      "epoch": 0.0017733289000110833,
      "grad_norm": 0.1399834007024765,
      "learning_rate": 2e-07,
      "loss": -0.0378,
      "step": 19
    },
    {
      "clip_ratio/high_max": 0.002387506792729255,
      "clip_ratio/high_mean": 0.0010503932608116884,
      "clip_ratio/low_mean": 0.000715991109245806,
      "clip_ratio/low_min": 8.918568164517637e-05,
      "clip_ratio/region_mean": 0.0017663843827904202,
      "epoch": 0.0018666620000116667,
      "grad_norm": 0.15333129465579987,
      "learning_rate": 2e-07,
      "loss": 0.0301,
      "step": 20
    },
    {
      "clip_ratio/high_max": 0.002245577925350517,
      "clip_ratio/high_mean": 0.0009637679431762081,
      "clip_ratio/low_mean": 0.0006616623913942021,
      "clip_ratio/low_min": 6.358617520163534e-05,
      "clip_ratio/region_mean": 0.001625430340936873,
      "epoch": 0.00195999510001225,
      "grad_norm": 0.14982850849628448,
      "learning_rate": 2e-07,
      "loss": 0.0291,
      "step": 21
    },
    {
      "clip_ratio/high_max": 0.0019911075214622542,
      "clip_ratio/high_mean": 0.0009537351870676503,
      "clip_ratio/low_mean": 0.0007553755731350975,
      "clip_ratio/low_min": 7.43609730307071e-05,
      "clip_ratio/region_mean": 0.001709110765659716,
      "epoch": 0.002053328200012833,
      "grad_norm": 0.14227502048015594,
      "learning_rate": 2e-07,
      "loss": 0.0702,
      "step": 22
    },
    {
      "clip_ratio/high_max": 0.0021435838352772407,
      "clip_ratio/high_mean": 0.0010525440629862715,
      "clip_ratio/low_mean": 0.000745167237255373,
      "clip_ratio/low_min": 6.530354949063621e-05,
      "clip_ratio/region_mean": 0.0017977112947846763,
      "epoch": 0.0021466613000134167,
      "grad_norm": 0.15410882234573364,
      "learning_rate": 2e-07,
      "loss": 0.0263,
      "step": 23
    },
    {
      "clip_ratio/high_max": 0.001867049442807911,
      "clip_ratio/high_mean": 0.0008090599167189794,
      "clip_ratio/low_mean": 0.0007187115988926962,
      "clip_ratio/low_min": 8.171320223482326e-05,
      "clip_ratio/region_mean": 0.0015277715574484318,
      "epoch": 0.002239994400014,
      "grad_norm": 0.16155502200126648,
      "learning_rate": 2e-07,
      "loss": 0.064,
      "step": 24
    },
    {
      "clip_ratio/high_max": 0.002423106889182236,
      "clip_ratio/high_mean": 0.0010662513122952078,
      "clip_ratio/low_mean": 0.0007340449556068052,
      "clip_ratio/low_min": 7.112937873898773e-05,
      "clip_ratio/region_mean": 0.0018002962897298858,
      "epoch": 0.002333327500014583,
      "grad_norm": 0.17242395877838135,
      "learning_rate": 2e-07,
      "loss": -0.0207,
      "step": 25
    },
    {
      "clip_ratio/high_max": 0.002586542977951467,
      "clip_ratio/high_mean": 0.001085506853996776,
      "clip_ratio/low_mean": 0.0007136358653951902,
      "clip_ratio/low_min": 1.0444518920849077e-05,
      "clip_ratio/region_mean": 0.0017991427084780298,
      "epoch": 0.0024266606000151666,
      "grad_norm": 0.18845485150814056,
      "learning_rate": 2e-07,
      "loss": 0.0296,
      "step": 26
    },
    {
      "clip_ratio/high_max": 0.0023713085320196114,
      "clip_ratio/high_mean": 0.0009943550103344023,
      "clip_ratio/low_mean": 0.0006678636436845409,
      "clip_ratio/low_min": 9.117938679992221e-05,
      "clip_ratio/region_mean": 0.0016622186740278266,
      "epoch": 0.00251999370001575,
      "grad_norm": 0.17658445239067078,
      "learning_rate": 2e-07,
      "loss": 0.0373,
      "step": 27
    },
    {
      "clip_ratio/high_max": 0.0025220852476195432,
      "clip_ratio/high_mean": 0.0010478980548214167,
      "clip_ratio/low_mean": 0.0006360245952237165,
      "clip_ratio/low_min": 3.55375468643615e-05,
      "clip_ratio/region_mean": 0.0016839226373122074,
      "epoch": 0.002613326800016333,
      "grad_norm": 0.1478639543056488,
      "learning_rate": 2e-07,
      "loss": 0.0018,
      "step": 28
    },
    {
      "clip_ratio/high_max": 0.002461256823153235,
      "clip_ratio/high_mean": 0.0010364703557570465,
      "clip_ratio/low_mean": 0.0006398533205356216,
      "clip_ratio/low_min": 6.13540842095972e-05,
      "clip_ratio/region_mean": 0.0016763236781116575,
      "epoch": 0.0027066599000169166,
      "grad_norm": 0.18225984275341034,
      "learning_rate": 2e-07,
      "loss": 0.0185,
      "step": 29
    },
    {
      "clip_ratio/high_max": 0.0022175155536388047,
      "clip_ratio/high_mean": 0.0009533763677609386,
      "clip_ratio/low_mean": 0.0007033304373180727,
      "clip_ratio/low_min": 7.825453212717548e-05,
      "clip_ratio/region_mean": 0.0016567068196309265,
      "epoch": 0.0027999930000175,
      "grad_norm": 0.16387026011943817,
      "learning_rate": 2e-07,
      "loss": 0.0298,
      "step": 30
    },
    {
      "clip_ratio/high_max": 0.0026038878422696143,
      "clip_ratio/high_mean": 0.0011194687758688815,
      "clip_ratio/low_mean": 0.0006538700235978467,
      "clip_ratio/low_min": 6.658352776867105e-05,
      "clip_ratio/region_mean": 0.00177333879400976,
      "epoch": 0.002893326100018083,
      "grad_norm": 0.18538165092468262,
      "learning_rate": 2e-07,
      "loss": 0.0081,
      "step": 31
    },
    {
      "clip_ratio/high_max": 0.0023883673711679876,
      "clip_ratio/high_mean": 0.0010355769118177705,
      "clip_ratio/low_mean": 0.0007208803926914698,
      "clip_ratio/low_min": 3.0472242997348076e-05,
      "clip_ratio/region_mean": 0.0017564572917763144,
      "epoch": 0.0029866592000186666,
      "grad_norm": 0.16681787371635437,
      "learning_rate": 2e-07,
      "loss": 0.0573,
      "step": 32
    },
    {
      "clip_ratio/high_max": 0.002104593542753719,
      "clip_ratio/high_mean": 0.0010913532332779141,
      "clip_ratio/low_mean": 0.0007352181401074631,
      "clip_ratio/low_min": 7.196445312729338e-05,
      "clip_ratio/region_mean": 0.001826571358833462,
      "epoch": 0.00307999230001925,
      "grad_norm": 0.14422070980072021,
      "learning_rate": 2e-07,
      "loss": 0.0205,
      "step": 33
    },
    {
      "clip_ratio/high_max": 0.0021195796398387756,
      "clip_ratio/high_mean": 0.0009154372000921285,
      "clip_ratio/low_mean": 0.000656920085020829,
      "clip_ratio/low_min": 0.0001107642665374442,
      "clip_ratio/region_mean": 0.001572357265104074,
      "epoch": 0.003173325400019833,
      "grad_norm": 0.1587039828300476,
      "learning_rate": 2e-07,
      "loss": 0.0571,
      "step": 34
    },
    {
      "clip_ratio/high_max": 0.0023674454096180853,
      "clip_ratio/high_mean": 0.0010550709630479105,
      "clip_ratio/low_mean": 0.0006784659908589674,
      "clip_ratio/low_min": 8.873475235304795e-05,
      "clip_ratio/region_mean": 0.0017335369120701216,
      "epoch": 0.0032666585000204165,
      "grad_norm": 0.16123159229755402,
      "learning_rate": 2e-07,
      "loss": 0.0068,
      "step": 35
    },
    {
      "clip_ratio/high_max": 0.002620395869598724,
      "clip_ratio/high_mean": 0.0011347207546350546,
      "clip_ratio/low_mean": 0.0006833997340436326,
      "clip_ratio/low_min": 5.905487614654703e-05,
      "clip_ratio/region_mean": 0.0018181204359279945,
      "epoch": 0.003359991600021,
      "grad_norm": 0.1757831871509552,
      "learning_rate": 2e-07,
      "loss": 0.0076,
      "step": 36
    },
    {
      "clip_ratio/high_max": 0.0022089821359259076,
      "clip_ratio/high_mean": 0.0009705943375593051,
      "clip_ratio/low_mean": 0.000560308015337796,
      "clip_ratio/low_min": 5.188483737583738e-05,
      "clip_ratio/region_mean": 0.0015309023292502388,
      "epoch": 0.0034533247000215835,
      "grad_norm": 0.18159349262714386,
      "learning_rate": 2e-07,
      "loss": 0.0043,
      "step": 37
    },
    {
      "clip_ratio/high_max": 0.0025637145117798354,
      "clip_ratio/high_mean": 0.001121771392718074,
      "clip_ratio/low_mean": 0.0006521710820379667,
      "clip_ratio/low_min": 5.358485850592842e-05,
      "clip_ratio/region_mean": 0.0017739424729370512,
      "epoch": 0.0035466578000221665,
      "grad_norm": 0.1653040200471878,
      "learning_rate": 2e-07,
      "loss": -0.0042,
      "step": 38
    },
    {
      "clip_ratio/high_max": 0.0021728387437178753,
      "clip_ratio/high_mean": 0.001027424295898527,
      "clip_ratio/low_mean": 0.0007209866234916262,
      "clip_ratio/low_min": 9.615711951482808e-05,
      "clip_ratio/region_mean": 0.0017484109484939836,
      "epoch": 0.00363999090002275,
      "grad_norm": 0.16213110089302063,
      "learning_rate": 2e-07,
      "loss": 0.0103,
      "step": 39
    },
    {
      "clip_ratio/high_max": 0.0021183517455938272,
      "clip_ratio/high_mean": 0.0008936427548178472,
      "clip_ratio/low_mean": 0.0009624898648326052,
      "clip_ratio/low_min": 5.6695236708037555e-05,
      "clip_ratio/region_mean": 0.001856132599641569,
      "epoch": 0.0037333240000233334,
      "grad_norm": 0.12478988617658615,
      "learning_rate": 2e-07,
      "loss": 0.0472,
      "step": 40
    },
    {
      "clip_ratio/high_max": 0.0021446100327011663,
      "clip_ratio/high_mean": 0.0010357052451581694,
      "clip_ratio/low_mean": 0.0007963624830154004,
      "clip_ratio/low_min": 8.249898837675573e-05,
      "clip_ratio/region_mean": 0.0018320677627343684,
      "epoch": 0.0038266571000239165,
      "grad_norm": 0.1299549639225006,
      "learning_rate": 2e-07,
      "loss": 0.0334,
      "step": 41
    },
    {
      "clip_ratio/high_max": 0.002538864970119903,
      "clip_ratio/high_mean": 0.0010702273939386941,
      "clip_ratio/low_mean": 0.0009539508901070803,
      "clip_ratio/low_min": 0.0001460920484532835,
      "clip_ratio/region_mean": 0.002024178254941944,
      "epoch": 0.0039199902000245,
      "grad_norm": 0.1413993090391159,
      "learning_rate": 2e-07,
      "loss": 0.0193,
      "step": 42
    },
    {
      "clip_ratio/high_max": 0.00302773411385715,
      "clip_ratio/high_mean": 0.0012631381869141478,
      "clip_ratio/low_mean": 0.0007151913468987914,
      "clip_ratio/low_min": 7.079160786815919e-05,
      "clip_ratio/region_mean": 0.001978329528355971,
      "epoch": 0.004013323300025083,
      "grad_norm": 0.12021080404520035,
      "learning_rate": 2e-07,
      "loss": -0.0386,
      "step": 43
    },
    {
      "clip_ratio/high_max": 0.0023914417688502,
      "clip_ratio/high_mean": 0.0010761782687040977,
      "clip_ratio/low_mean": 0.0008260987979156198,
      "clip_ratio/low_min": 0.00010776017188618425,
      "clip_ratio/region_mean": 0.00190227702842094,
      "epoch": 0.004106656400025666,
      "grad_norm": 0.1382819563150406,
      "learning_rate": 2e-07,
      "loss": -0.0023,
      "step": 44
    },
    {
      "clip_ratio/high_max": 0.002267268253490329,
      "clip_ratio/high_mean": 0.0010841776711458806,
      "clip_ratio/low_mean": 0.0008521507879777346,
      "clip_ratio/low_min": 0.00012050447639921913,
      "clip_ratio/region_mean": 0.0019363284955034032,
      "epoch": 0.00419998950002625,
      "grad_norm": 0.16588380932807922,
      "learning_rate": 2e-07,
      "loss": 0.0398,
      "step": 45
    },
    {
      "clip_ratio/high_max": 0.002457712238538079,
      "clip_ratio/high_mean": 0.0011450489255366847,
      "clip_ratio/low_mean": 0.0007951563256938243,
      "clip_ratio/low_min": 0.00013263345408631722,
      "clip_ratio/region_mean": 0.001940205242135562,
      "epoch": 0.004293322600026833,
      "grad_norm": 0.14558298885822296,
      "learning_rate": 2e-07,
      "loss": 0.013,
      "step": 46
    },
    {
      "clip_ratio/high_max": 0.0022139805550978053,
      "clip_ratio/high_mean": 0.000999439473162056,
      "clip_ratio/low_mean": 0.0008757558680372313,
      "clip_ratio/low_min": 0.000175554148881929,
      "clip_ratio/region_mean": 0.0018751953502942342,
      "epoch": 0.004386655700027417,
      "grad_norm": 0.17660871148109436,
      "learning_rate": 2e-07,
      "loss": 0.0469,
      "step": 47
    },
    {
      "clip_ratio/high_max": 0.0027948246570304036,
      "clip_ratio/high_mean": 0.0011936235314351507,
      "clip_ratio/low_mean": 0.0007576054340461269,
      "clip_ratio/low_min": 7.088794109222363e-05,
      "clip_ratio/region_mean": 0.0019512289145495743,
      "epoch": 0.004479988800028,
      "grad_norm": 0.17675215005874634,
      "learning_rate": 2e-07,
      "loss": -0.0025,
      "step": 48
    },
    {
      "clip_ratio/high_max": 0.002381072859861888,
      "clip_ratio/high_mean": 0.0009864217863650993,
      "clip_ratio/low_mean": 0.0007424233099300181,
      "clip_ratio/low_min": 8.64379644553992e-05,
      "clip_ratio/region_mean": 0.00172884514904581,
      "epoch": 0.004573321900028583,
      "grad_norm": 0.1627051830291748,
      "learning_rate": 2e-07,
      "loss": 0.0385,
      "step": 49
    },
    {
      "clip_ratio/high_max": 0.002706680417759344,
      "clip_ratio/high_mean": 0.0011382067441445542,
      "clip_ratio/low_mean": 0.0008244439577538287,
      "clip_ratio/low_min": 8.638664075988345e-05,
      "clip_ratio/region_mean": 0.001962650756468065,
      "epoch": 0.004666655000029166,
      "grad_norm": 0.16825319826602936,
      "learning_rate": 2e-07,
      "loss": -0.0247,
      "step": 50
    },
    {
      "clip_ratio/high_max": 0.0023495928835473023,
      "clip_ratio/high_mean": 0.0011310262416373007,
      "clip_ratio/low_mean": 0.0007959395843499806,
      "clip_ratio/low_min": 8.145416813931661e-05,
      "clip_ratio/region_mean": 0.0019269658223493025,
      "epoch": 0.00475998810002975,
      "grad_norm": 0.17190200090408325,
      "learning_rate": 2e-07,
      "loss": -0.0028,
      "step": 51
    },
    {
      "clip_ratio/high_max": 0.0025433526243432425,
      "clip_ratio/high_mean": 0.0010059376454591984,
      "clip_ratio/low_mean": 0.0007976649030752014,
      "clip_ratio/low_min": 0.00011158106644870713,
      "clip_ratio/region_mean": 0.0018036025830951985,
      "epoch": 0.004853321200030333,
      "grad_norm": 0.16411852836608887,
      "learning_rate": 2e-07,
      "loss": 0.0346,
      "step": 52
    },
    {
      "clip_ratio/high_max": 0.002570785647549201,
      "clip_ratio/high_mean": 0.0011279989157628734,
      "clip_ratio/low_mean": 0.0008269209793070331,
      "clip_ratio/low_min": 0.0001437667115169461,
      "clip_ratio/region_mean": 0.0019549198914319277,
      "epoch": 0.004946654300030917,
      "grad_norm": 0.23368988931179047,
      "learning_rate": 2e-07,
      "loss": 0.0347,
      "step": 53
    },
    {
      "clip_ratio/high_max": 0.00221728650649311,
      "clip_ratio/high_mean": 0.0010440790247230325,
      "clip_ratio/low_mean": 0.0008208208382711746,
      "clip_ratio/low_min": 0.00015387419443868566,
      "clip_ratio/region_mean": 0.001864899881184101,
      "epoch": 0.0050399874000315,
      "grad_norm": 0.16691303253173828,
      "learning_rate": 2e-07,
      "loss": 0.0353,
      "step": 54
    },
    {
      "clip_ratio/high_max": 0.0021591855911538005,
      "clip_ratio/high_mean": 0.0009948813494702335,
      "clip_ratio/low_mean": 0.0007651457453903276,
      "clip_ratio/low_min": 7.640478452231036e-05,
      "clip_ratio/region_mean": 0.0017600271021365188,
      "epoch": 0.005133320500032083,
      "grad_norm": 0.19582928717136383,
      "learning_rate": 2e-07,
      "loss": 0.0382,
      "step": 55
    },
    {
      "clip_ratio/high_max": 0.002834614584571682,
      "clip_ratio/high_mean": 0.0011490672804939095,
      "clip_ratio/low_mean": 0.000831111219667946,
      "clip_ratio/low_min": 0.00013497215422830777,
      "clip_ratio/region_mean": 0.0019801784947048873,
      "epoch": 0.005226653600032666,
      "grad_norm": 0.16688285768032074,
      "learning_rate": 2e-07,
      "loss": 0.0097,
      "step": 56
    },
    {
      "clip_ratio/high_max": 0.0026971597981173545,
      "clip_ratio/high_mean": 0.0011881121790793259,
      "clip_ratio/low_mean": 0.0008297745735035278,
      "clip_ratio/low_min": 0.00011190869054189534,
      "clip_ratio/region_mean": 0.002017886727117002,
      "epoch": 0.00531998670003325,
      "grad_norm": 0.18028266727924347,
      "learning_rate": 2e-07,
      "loss": 0.0035,
      "step": 57
    },
    {
      "clip_ratio/high_max": 0.0023480103263864294,
      "clip_ratio/high_mean": 0.0010957255362882279,
      "clip_ratio/low_mean": 0.0008130651513056364,
      "clip_ratio/low_min": 7.304040173039539e-05,
      "clip_ratio/region_mean": 0.0019087906766799279,
      "epoch": 0.005413319800033833,
      "grad_norm": 0.19899523258209229,
      "learning_rate": 2e-07,
      "loss": 0.0106,
      "step": 58
    },
    {
      "clip_ratio/high_max": 0.002623686406877823,
      "clip_ratio/high_mean": 0.0010664626006473554,
      "clip_ratio/low_mean": 0.0008946610705606872,
      "clip_ratio/low_min": 0.00011749729765142547,
      "clip_ratio/region_mean": 0.0019611237148637883,
      "epoch": 0.005506652900034417,
      "grad_norm": 0.2230866253376007,
      "learning_rate": 2e-07,
      "loss": 0.0208,
      "step": 59
    },
    {
      "clip_ratio/high_max": 0.0027665546294883825,
      "clip_ratio/high_mean": 0.0011527124734129757,
      "clip_ratio/low_mean": 0.0009560649377817754,
      "clip_ratio/low_min": 7.160534823924536e-05,
      "clip_ratio/region_mean": 0.0021087773420731537,
      "epoch": 0.005599986000035,
      "grad_norm": 0.20928668975830078,
      "learning_rate": 2e-07,
      "loss": 0.0183,
      "step": 60
    },
    {
      "clip_ratio/high_max": 0.0025118674675468355,
      "clip_ratio/high_mean": 0.0012051414450979792,
      "clip_ratio/low_mean": 0.0008169338907464407,
      "clip_ratio/low_min": 8.125139174808282e-05,
      "clip_ratio/region_mean": 0.0020220753285684623,
      "epoch": 0.005693319100035584,
      "grad_norm": 0.19858625531196594,
      "learning_rate": 2e-07,
      "loss": 0.0223,
      "step": 61
    },
    {
      "clip_ratio/high_max": 0.0023063628177624196,
      "clip_ratio/high_mean": 0.000974755666902638,
      "clip_ratio/low_mean": 0.0009981992589018773,
      "clip_ratio/low_min": 0.00015467244065803243,
      "clip_ratio/region_mean": 0.0019729549676412717,
      "epoch": 0.005786652200036166,
      "grad_norm": 0.24347659945487976,
      "learning_rate": 2e-07,
      "loss": 0.082,
      "step": 62
    },
    {
      "clip_ratio/high_max": 0.0023434290196746588,
      "clip_ratio/high_mean": 0.0010790873930091038,
      "clip_ratio/low_mean": 0.0009798472019610927,
      "clip_ratio/low_min": 0.00010796214883157518,
      "clip_ratio/region_mean": 0.0020589346531778574,
      "epoch": 0.00587998530003675,
      "grad_norm": 0.19212107360363007,
      "learning_rate": 2e-07,
      "loss": 0.0528,
      "step": 63
    },
    {
      "clip_ratio/high_max": 0.0021897237020311877,
      "clip_ratio/high_mean": 0.0009583683568052948,
      "clip_ratio/low_mean": 0.0008091209365375107,
      "clip_ratio/low_min": 2.683438106032554e-05,
      "clip_ratio/region_mean": 0.001767489273333922,
      "epoch": 0.005973318400037333,
      "grad_norm": 0.20925861597061157,
      "learning_rate": 2e-07,
      "loss": 0.0446,
      "step": 64
    },
    {
      "clip_ratio/high_max": 0.002384451530815568,
      "clip_ratio/high_mean": 0.0010315646941307932,
      "clip_ratio/low_mean": 0.0008973966396297328,
      "clip_ratio/low_min": 0.0001905183048620529,
      "clip_ratio/region_mean": 0.001928961333760526,
      "epoch": 0.006066651500037917,
      "grad_norm": 0.20721594989299774,
      "learning_rate": 2e-07,
      "loss": 0.0384,
      "step": 65
    },
    {
      "clip_ratio/high_max": 0.002292082950589247,
      "clip_ratio/high_mean": 0.0011816332225862425,
      "clip_ratio/low_mean": 0.0008940716670622351,
      "clip_ratio/low_min": 0.0001223996837325103,
      "clip_ratio/region_mean": 0.0020757048987434246,
      "epoch": 0.0061599846000385,
      "grad_norm": 0.18144945800304413,
      "learning_rate": 2e-07,
      "loss": 0.0435,
      "step": 66
    },
    {
      "clip_ratio/high_max": 0.00263256916514365,
      "clip_ratio/high_mean": 0.0012009260281047318,
      "clip_ratio/low_mean": 0.0010232093536615139,
      "clip_ratio/low_min": 0.00014230040051188553,
      "clip_ratio/region_mean": 0.002224135365395341,
      "epoch": 0.0062533177000390835,
      "grad_norm": 0.17394821345806122,
      "learning_rate": 2e-07,
      "loss": 0.0125,
      "step": 67
    },
    {
      "clip_ratio/high_max": 0.0025809501530602574,
      "clip_ratio/high_mean": 0.0011921191107830964,
      "clip_ratio/low_mean": 0.0008526073615939822,
      "clip_ratio/low_min": 0.00013056372790742898,
      "clip_ratio/region_mean": 0.0020447264687391,
      "epoch": 0.006346650800039666,
      "grad_norm": 0.23051761090755463,
      "learning_rate": 2e-07,
      "loss": 0.002,
      "step": 68
    },
    {
      "clip_ratio/high_max": 0.0025625708913139533,
      "clip_ratio/high_mean": 0.0011680446605168981,
      "clip_ratio/low_mean": 0.0009182084868371021,
      "clip_ratio/low_min": 0.0001425448208465241,
      "clip_ratio/region_mean": 0.0020862531673628837,
      "epoch": 0.00643998390004025,
      "grad_norm": 0.1754886507987976,
      "learning_rate": 2e-07,
      "loss": 0.0332,
      "step": 69
    },
    {
      "clip_ratio/high_max": 0.0025144152823486365,
      "clip_ratio/high_mean": 0.0012188743203296326,
      "clip_ratio/low_mean": 0.0008123854950099485,
      "clip_ratio/low_min": 5.107884408062091e-05,
      "clip_ratio/region_mean": 0.002031259769864846,
      "epoch": 0.006533317000040833,
      "grad_norm": 0.1733425408601761,
      "learning_rate": 2e-07,
      "loss": -0.0094,
      "step": 70
    },
    {
      "clip_ratio/high_max": 0.0026027825952041894,
      "clip_ratio/high_mean": 0.0011562062136363238,
      "clip_ratio/low_mean": 0.0008388588776142569,
      "clip_ratio/low_min": 8.64647195157886e-05,
      "clip_ratio/region_mean": 0.0019950651258113794,
      "epoch": 0.0066266501000414165,
      "grad_norm": 0.15402637422084808,
      "learning_rate": 2e-07,
      "loss": -0.0268,
      "step": 71
    },
    {
      "clip_ratio/high_max": 0.0027323203757987358,
      "clip_ratio/high_mean": 0.0011127118887088727,
      "clip_ratio/low_mean": 0.0009276796990889125,
      "clip_ratio/low_min": 0.00011783379432017682,
      "clip_ratio/region_mean": 0.002040391605987679,
      "epoch": 0.006719983200042,
      "grad_norm": 0.14106644690036774,
      "learning_rate": 2e-07,
      "loss": 0.0246,
      "step": 72
    },
    {
      "clip_ratio/high_max": 0.0025552997904014774,
      "clip_ratio/high_mean": 0.0012162266830273438,
      "clip_ratio/low_mean": 0.0010613461454340722,
      "clip_ratio/low_min": 4.4688086290989304e-05,
      "clip_ratio/region_mean": 0.0022775727848056704,
      "epoch": 0.0068133163000425835,
      "grad_norm": 0.1692935973405838,
      "learning_rate": 2e-07,
      "loss": 0.0199,
      "step": 73
    },
    {
      "clip_ratio/high_max": 0.002438432005874347,
      "clip_ratio/high_mean": 0.0010961007137666456,
      "clip_ratio/low_mean": 0.0009506063834123779,
      "clip_ratio/low_min": 9.589870523996069e-05,
      "clip_ratio/region_mean": 0.002046707144472748,
      "epoch": 0.006906649400043167,
      "grad_norm": 0.13591258227825165,
      "learning_rate": 2e-07,
      "loss": -0.0085,
      "step": 74
    },
    {
      "clip_ratio/high_max": 0.002877588711271528,
      "clip_ratio/high_mean": 0.001249594170076307,
      "clip_ratio/low_mean": 0.0009949232189683244,
      "clip_ratio/low_min": 0.00010380656294728396,
      "clip_ratio/region_mean": 0.0022445174035965465,
      "epoch": 0.0069999825000437495,
      "grad_norm": 0.15854483842849731,
      "learning_rate": 2e-07,
      "loss": 0.0233,
      "step": 75
    },
    {
      "clip_ratio/high_max": 0.0024982274771900848,
      "clip_ratio/high_mean": 0.0012117296500946395,
      "clip_ratio/low_mean": 0.0010544225078774616,
      "clip_ratio/low_min": 0.00010851422484847717,
      "clip_ratio/region_mean": 0.0022661521143163554,
      "epoch": 0.007093315600044333,
      "grad_norm": 0.1535879522562027,
      "learning_rate": 2e-07,
      "loss": -0.0224,
      "step": 76
    },
    {
      "clip_ratio/high_max": 0.002386713145824615,
      "clip_ratio/high_mean": 0.0011644631485978607,
      "clip_ratio/low_mean": 0.0010858478963200469,
      "clip_ratio/low_min": 0.00015373233145510312,
      "clip_ratio/region_mean": 0.002250311074021738,
      "epoch": 0.0071866487000449165,
      "grad_norm": 0.1576538383960724,
      "learning_rate": 2e-07,
      "loss": 0.0255,
      "step": 77
    },
    {
      "clip_ratio/high_max": 0.002220553367806133,
      "clip_ratio/high_mean": 0.0010531980151426978,
      "clip_ratio/low_mean": 0.0011598556411627214,
      "clip_ratio/low_min": 0.0002525006675568875,
      "clip_ratio/region_mean": 0.0022130536526674405,
      "epoch": 0.0072799818000455,
      "grad_norm": 0.17964158952236176,
      "learning_rate": 2e-07,
      "loss": 0.0435,
      "step": 78
    },
    {
      "clip_ratio/high_max": 0.002580029242380988,
      "clip_ratio/high_mean": 0.001158521707111504,
      "clip_ratio/low_mean": 0.0011037067124561872,
      "clip_ratio/low_min": 0.00012353784586593974,
      "clip_ratio/region_mean": 0.002262228386825882,
      "epoch": 0.007373314900046083,
      "grad_norm": 0.16844771802425385,
      "learning_rate": 2e-07,
      "loss": 0.0034,
      "step": 79
    },
    {
      "clip_ratio/high_max": 0.0026624569291016087,
      "clip_ratio/high_mean": 0.0011551221468835138,
      "clip_ratio/low_mean": 0.001111339279304957,
      "clip_ratio/low_min": 0.000121137491078116,
      "clip_ratio/region_mean": 0.002266461400722619,
      "epoch": 0.007466648000046667,
      "grad_norm": 0.13643594086170197,
      "learning_rate": 2e-07,
      "loss": -0.0177,
      "step": 80
    },
    {
      "clip_ratio/high_max": 0.0027351634416845627,
      "clip_ratio/high_mean": 0.0012743008373945486,
      "clip_ratio/low_mean": 0.001009280480502639,
      "clip_ratio/low_min": 0.00012832949869334698,
      "clip_ratio/region_mean": 0.002283581306983251,
      "epoch": 0.0075599811000472495,
      "grad_norm": 0.1346885859966278,
      "learning_rate": 2e-07,
      "loss": 0.0206,
      "step": 81
    },
    {
      "clip_ratio/high_max": 0.002482824827893637,
      "clip_ratio/high_mean": 0.0011054424139729235,
      "clip_ratio/low_mean": 0.0008900915636331774,
      "clip_ratio/low_min": 9.853973824647255e-05,
      "clip_ratio/region_mean": 0.0019955339885200374,
      "epoch": 0.007653314200047833,
      "grad_norm": 0.17153213918209076,
      "learning_rate": 2e-07,
      "loss": 0.0439,
      "step": 82
    },
    {
      "clip_ratio/high_max": 0.0027423274441389367,
      "clip_ratio/high_mean": 0.0010962784908770118,
      "clip_ratio/low_mean": 0.0010538176647969522,
      "clip_ratio/low_min": 0.0001511997870693449,
      "clip_ratio/region_mean": 0.0021500961593119428,
      "epoch": 0.007746647300048416,
      "grad_norm": 0.2059258222579956,
      "learning_rate": 2e-07,
      "loss": 0.0421,
      "step": 83
    },
    {
      "clip_ratio/high_max": 0.002741073549259454,
      "clip_ratio/high_mean": 0.0012883245362900198,
      "clip_ratio/low_mean": 0.0011239956693316344,
      "clip_ratio/low_min": 0.00011476413237687666,
      "clip_ratio/region_mean": 0.0024123201801558025,
      "epoch": 0.007839980400049,
      "grad_norm": 0.1896880716085434,
      "learning_rate": 2e-07,
      "loss": 0.0026,
      "step": 84
    },
    {
      "clip_ratio/high_max": 0.002554102691647131,
      "clip_ratio/high_mean": 0.0010734221432358027,
      "clip_ratio/low_mean": 0.0011634019265329698,
      "clip_ratio/low_min": 9.160513491224265e-05,
      "clip_ratio/region_mean": 0.002236824067949783,
      "epoch": 0.007933313500049582,
      "grad_norm": 0.20716962218284607,
      "learning_rate": 2e-07,
      "loss": 0.0526,
      "step": 85
    },
    {
      "clip_ratio/high_max": 0.002843539434252307,
      "clip_ratio/high_mean": 0.0013428274978650734,
      "clip_ratio/low_mean": 0.0010562507377471775,
      "clip_ratio/low_min": 0.00012423711450537667,
      "clip_ratio/region_mean": 0.0023990782283362933,
      "epoch": 0.008026646600050166,
      "grad_norm": 0.21359005570411682,
      "learning_rate": 2e-07,
      "loss": -0.0102,
      "step": 86
    },
    {
      "clip_ratio/high_max": 0.0025335026111861225,
      "clip_ratio/high_mean": 0.0011242671971558593,
      "clip_ratio/low_mean": 0.001072051458322676,
      "clip_ratio/low_min": 0.00014780018227611436,
      "clip_ratio/region_mean": 0.002196318717324175,
      "epoch": 0.00811997970005075,
      "grad_norm": 0.18297268450260162,
      "learning_rate": 2e-07,
      "loss": 0.0414,
      "step": 87
    },
    {
      "clip_ratio/high_max": 0.003101074842561502,
      "clip_ratio/high_mean": 0.0013181200993130915,
      "clip_ratio/low_mean": 0.0010754356235338491,
      "clip_ratio/low_min": 0.00012925146711495472,
      "clip_ratio/region_mean": 0.002393555703747552,
      "epoch": 0.008213312800051333,
      "grad_norm": 0.1821269690990448,
      "learning_rate": 2e-07,
      "loss": 0.0263,
      "step": 88
    },
    {
      "clip_ratio/high_max": 0.0029333929778658785,
      "clip_ratio/high_mean": 0.001314161727350438,
      "clip_ratio/low_mean": 0.0011944041834794916,
      "clip_ratio/low_min": 0.00015262290435202885,
      "clip_ratio/region_mean": 0.0025085660236072727,
      "epoch": 0.008306645900051916,
      "grad_norm": 0.2102108597755432,
      "learning_rate": 2e-07,
      "loss": 0.0119,
      "step": 89
    },
    {
      "clip_ratio/high_max": 0.0030170710451784544,
      "clip_ratio/high_mean": 0.001282726396311773,
      "clip_ratio/low_mean": 0.0010507773695280775,
      "clip_ratio/low_min": 0.0001308621458520065,
      "clip_ratio/region_mean": 0.0023335037330980413,
      "epoch": 0.0083999790000525,
      "grad_norm": 0.15292580425739288,
      "learning_rate": 2e-07,
      "loss": -0.0058,
      "step": 90
    },
    {
      "clip_ratio/high_max": 0.0030129971128189936,
      "clip_ratio/high_mean": 0.0013702320720767602,
      "clip_ratio/low_mean": 0.001032977601425955,
      "clip_ratio/low_min": 0.00014014928092365153,
      "clip_ratio/region_mean": 0.0024032096698647365,
      "epoch": 0.008493312100053083,
      "grad_norm": 0.16533470153808594,
      "learning_rate": 2e-07,
      "loss": -0.0434,
      "step": 91
    },
    {
      "clip_ratio/high_max": 0.0023833426675992087,
      "clip_ratio/high_mean": 0.001035780762322247,
      "clip_ratio/low_mean": 0.0010435842268634588,
      "clip_ratio/low_min": 6.538681736856233e-05,
      "clip_ratio/region_mean": 0.0020793649237020873,
      "epoch": 0.008586645200053667,
      "grad_norm": 0.16801509261131287,
      "learning_rate": 2e-07,
      "loss": 0.0787,
      "step": 92
    },
    {
      "clip_ratio/high_max": 0.0026365415324107744,
      "clip_ratio/high_mean": 0.0011868597866850905,
      "clip_ratio/low_mean": 0.0010226778304058826,
      "clip_ratio/low_min": 0.00010679325168894138,
      "clip_ratio/region_mean": 0.0022095375825301744,
      "epoch": 0.00867997830005425,
      "grad_norm": 0.1672240048646927,
      "learning_rate": 2e-07,
      "loss": 0.0142,
      "step": 93
    },
    {
      "clip_ratio/high_max": 0.0027250569037278183,
      "clip_ratio/high_mean": 0.0013217675768828485,
      "clip_ratio/low_mean": 0.000998929939669324,
      "clip_ratio/low_min": 6.232082614587853e-05,
      "clip_ratio/region_mean": 0.0023206975020002574,
      "epoch": 0.008773311400054834,
      "grad_norm": 0.1793237030506134,
      "learning_rate": 2e-07,
      "loss": -0.0144,
      "step": 94
    },
    {
      "clip_ratio/high_max": 0.0027768419167841785,
      "clip_ratio/high_mean": 0.0012436797042028047,
      "clip_ratio/low_mean": 0.0009854092913883505,
      "clip_ratio/low_min": 0.00013467337521433365,
      "clip_ratio/region_mean": 0.002229089048341848,
      "epoch": 0.008866644500055417,
      "grad_norm": 0.18953968584537506,
      "learning_rate": 2e-07,
      "loss": 0.0018,
      "step": 95
    },
    {
      "clip_ratio/high_max": 0.0027178080927114934,
      "clip_ratio/high_mean": 0.0012212964938953519,
      "clip_ratio/low_mean": 0.000985382550425129,
      "clip_ratio/low_min": 0.0001628349718885147,
      "clip_ratio/region_mean": 0.0022066790479584597,
      "epoch": 0.008959977600056,
      "grad_norm": 0.1701854169368744,
      "learning_rate": 2e-07,
      "loss": -0.027,
      "step": 96
    },
    {
      "clip_ratio/high_max": 0.0024119935842463747,
      "clip_ratio/high_mean": 0.0010568742145551369,
      "clip_ratio/low_mean": 0.0011819798237411305,
      "clip_ratio/low_min": 0.00012788825915777124,
      "clip_ratio/region_mean": 0.0022388540382962674,
      "epoch": 0.009053310700056582,
      "grad_norm": 0.18675607442855835,
      "learning_rate": 2e-07,
      "loss": 0.0293,
      "step": 97
    },
    {
      "clip_ratio/high_max": 0.0035491284070303664,
      "clip_ratio/high_mean": 0.0013820905624015722,
      "clip_ratio/low_mean": 0.0009762960398802534,
      "clip_ratio/low_min": 0.00016453116586490069,
      "clip_ratio/region_mean": 0.0023583865622640587,
      "epoch": 0.009146643800057166,
      "grad_norm": 0.16908271610736847,
      "learning_rate": 2e-07,
      "loss": -0.0105,
      "step": 98
    },
    {
      "clip_ratio/high_max": 0.00247835525078699,
      "clip_ratio/high_mean": 0.0011156640684930608,
      "clip_ratio/low_mean": 0.001052439238264924,
      "clip_ratio/low_min": 8.926506234274711e-05,
      "clip_ratio/region_mean": 0.0021681033103959635,
      "epoch": 0.00923997690005775,
      "grad_norm": 0.2073219120502472,
      "learning_rate": 2e-07,
      "loss": 0.0423,
      "step": 99
    },
    {
      "clip_ratio/high_max": 0.002534984640078619,
      "clip_ratio/high_mean": 0.0012455285832402296,
      "clip_ratio/low_mean": 0.0011557196667126846,
      "clip_ratio/low_min": 0.00010639028550940566,
      "clip_ratio/region_mean": 0.002401248253590893,
      "epoch": 0.009333310000058333,
      "grad_norm": 0.19808122515678406,
      "learning_rate": 2e-07,
      "loss": 0.0224,
      "step": 100
    },
    {
      "clip_ratio/high_max": 0.0024680399073986337,
      "clip_ratio/high_mean": 0.0010831113177118823,
      "clip_ratio/low_mean": 0.0012592012317327317,
      "clip_ratio/low_min": 0.00017032107734848978,
      "clip_ratio/region_mean": 0.00234231253125472,
      "epoch": 0.009426643100058916,
      "grad_norm": 0.19438901543617249,
      "learning_rate": 2e-07,
      "loss": 0.0343,
      "step": 101
    },
    {
      "clip_ratio/high_max": 0.0026824113374459557,
      "clip_ratio/high_mean": 0.0011952072600251995,
      "clip_ratio/low_mean": 0.0012860456881753635,
      "clip_ratio/low_min": 0.00022265155894274358,
      "clip_ratio/region_mean": 0.002481252930010669,
      "epoch": 0.0095199762000595,
      "grad_norm": 0.21726852655410767,
      "learning_rate": 2e-07,
      "loss": 0.0397,
      "step": 102
    },
    {
      "clip_ratio/high_max": 0.002726063357840758,
      "clip_ratio/high_mean": 0.0011511658522067592,
      "clip_ratio/low_mean": 0.0011307314161967952,
      "clip_ratio/low_min": 0.0001876334790722467,
      "clip_ratio/region_mean": 0.002281897257489618,
      "epoch": 0.009613309300060083,
      "grad_norm": 0.18289121985435486,
      "learning_rate": 2e-07,
      "loss": 0.0206,
      "step": 103
    },
    {
      "clip_ratio/high_max": 0.0025665276989457197,
      "clip_ratio/high_mean": 0.0010960943291138392,
      "clip_ratio/low_mean": 0.0011031528047169559,
      "clip_ratio/low_min": 0.0001309262715949444,
      "clip_ratio/region_mean": 0.0021992471301928163,
      "epoch": 0.009706642400060667,
      "grad_norm": 0.18796053528785706,
      "learning_rate": 2e-07,
      "loss": 0.0077,
      "step": 104
    },
    {
      "clip_ratio/high_max": 0.002689894405193627,
      "clip_ratio/high_mean": 0.001097467466024682,
      "clip_ratio/low_mean": 0.001141650674981065,
      "clip_ratio/low_min": 0.00011748064662242541,
      "clip_ratio/region_mean": 0.002239118199213408,
      "epoch": 0.00979997550006125,
      "grad_norm": 0.18031446635723114,
      "learning_rate": 2e-07,
      "loss": 0.0174,
      "step": 105
    },
    {
      "clip_ratio/high_max": 0.0029994639844517224,
      "clip_ratio/high_mean": 0.0012087695286027156,
      "clip_ratio/low_mean": 0.0014255132009566296,
      "clip_ratio/low_min": 0.00014565794845111668,
      "clip_ratio/region_mean": 0.002634282733197324,
      "epoch": 0.009893308600061834,
      "grad_norm": 0.2437736988067627,
      "learning_rate": 2e-07,
      "loss": 0.0285,
      "step": 106
    },
    {
      "clip_ratio/high_max": 0.002619189559482038,
      "clip_ratio/high_mean": 0.0011916592484340072,
      "clip_ratio/low_mean": 0.0012260313760634745,
      "clip_ratio/low_min": 0.00012317240907577798,
      "clip_ratio/region_mean": 0.002417690571746789,
      "epoch": 0.009986641700062417,
      "grad_norm": 0.19500799477100372,
      "learning_rate": 2e-07,
      "loss": 0.0023,
      "step": 107
    },
    {
      "clip_ratio/high_max": 0.002805651289236266,
      "clip_ratio/high_mean": 0.0012430563256202731,
      "clip_ratio/low_mean": 0.001070772581442725,
      "clip_ratio/low_min": 0.00013049281460553175,
      "clip_ratio/region_mean": 0.0023138288815971464,
      "epoch": 0.010079974800063,
      "grad_norm": 0.197968527674675,
      "learning_rate": 2e-07,
      "loss": 0.0135,
      "step": 108
    },
    {
      "clip_ratio/high_max": 0.002827042633725796,
      "clip_ratio/high_mean": 0.001283066547330236,
      "clip_ratio/low_mean": 0.001106328918467625,
      "clip_ratio/low_min": 0.00013226754708739463,
      "clip_ratio/region_mean": 0.0023893954712548293,
      "epoch": 0.010173307900063584,
      "grad_norm": 0.1845165491104126,
      "learning_rate": 2e-07,
      "loss": -0.023,
      "step": 109
    },
    {
      "clip_ratio/high_max": 0.0026356971357017756,
      "clip_ratio/high_mean": 0.0012250515246705618,
      "clip_ratio/low_mean": 0.0012772790651069954,
      "clip_ratio/low_min": 0.00022481046380562475,
      "clip_ratio/region_mean": 0.0025023304842761718,
      "epoch": 0.010266641000064166,
      "grad_norm": 0.2182450294494629,
      "learning_rate": 2e-07,
      "loss": 0.0135,
      "step": 110
    },
    {
      "clip_ratio/high_max": 0.003072882151172962,
      "clip_ratio/high_mean": 0.001378587996441638,
      "clip_ratio/low_mean": 0.0012424594551703194,
      "clip_ratio/low_min": 0.00019686294808707316,
      "clip_ratio/region_mean": 0.002621047489810735,
      "epoch": 0.010359974100064749,
      "grad_norm": 0.19440597295761108,
      "learning_rate": 2e-07,
      "loss": -0.0176,
      "step": 111
    },
    {
      "clip_ratio/high_max": 0.002709905631490983,
      "clip_ratio/high_mean": 0.0011709596219589002,
      "clip_ratio/low_mean": 0.0012642902474908624,
      "clip_ratio/low_min": 0.00017267084967897972,
      "clip_ratio/region_mean": 0.0024352498949156143,
      "epoch": 0.010453307200065333,
      "grad_norm": 0.18936507403850555,
      "learning_rate": 2e-07,
      "loss": 0.0282,
      "step": 112
    },
    {
      "clip_ratio/high_max": 0.002843185699020978,
      "clip_ratio/high_mean": 0.0012608690267370548,
      "clip_ratio/low_mean": 0.0013796827042824589,
      "clip_ratio/low_min": 0.0002849881884685601,
      "clip_ratio/region_mean": 0.0026405517710372806,
      "epoch": 0.010546640300065916,
      "grad_norm": 0.2426442950963974,
      "learning_rate": 2e-07,
      "loss": 0.0825,
      "step": 113
    },
    {
      "clip_ratio/high_max": 0.002851191529771313,
      "clip_ratio/high_mean": 0.0014006964629516006,
      "clip_ratio/low_mean": 0.0012772772097378038,
      "clip_ratio/low_min": 0.0002610153442219598,
      "clip_ratio/region_mean": 0.0026779736508615315,
      "epoch": 0.0106399734000665,
      "grad_norm": 0.24099399149417877,
      "learning_rate": 2e-07,
      "loss": 0.0139,
      "step": 114
    },
    {
      "clip_ratio/high_max": 0.0023237135137605947,
      "clip_ratio/high_mean": 0.0010651344891812187,
      "clip_ratio/low_mean": 0.0012888269666291308,
      "clip_ratio/low_min": 0.00019807125499937683,
      "clip_ratio/region_mean": 0.0023539614558103494,
      "epoch": 0.010733306500067083,
      "grad_norm": 0.18726374208927155,
      "learning_rate": 2e-07,
      "loss": 0.0387,
      "step": 115
    },
    {
      "clip_ratio/high_max": 0.003235339478123933,
      "clip_ratio/high_mean": 0.0015591698756907135,
      "clip_ratio/low_mean": 0.0009970408154913457,
      "clip_ratio/low_min": 8.346320646523964e-05,
      "clip_ratio/region_mean": 0.002556210725742858,
      "epoch": 0.010826639600067666,
      "grad_norm": 0.16004793345928192,
      "learning_rate": 2e-07,
      "loss": -0.0522,
      "step": 116
    },
    {
      "clip_ratio/high_max": 0.0033125573536381125,
      "clip_ratio/high_mean": 0.0014769402769161388,
      "clip_ratio/low_mean": 0.0013356961062527262,
      "clip_ratio/low_min": 0.00014130645104160067,
      "clip_ratio/region_mean": 0.0028126363977207802,
      "epoch": 0.01091997270006825,
      "grad_norm": 0.24664698541164398,
      "learning_rate": 2e-07,
      "loss": 0.0161,
      "step": 117
    },
    {
      "clip_ratio/high_max": 0.0027916423860006034,
      "clip_ratio/high_mean": 0.001320090850640554,
      "clip_ratio/low_mean": 0.0012178942088212352,
      "clip_ratio/low_min": 0.00011255316167080309,
      "clip_ratio/region_mean": 0.0025379850339959376,
      "epoch": 0.011013305800068833,
      "grad_norm": 0.23122738301753998,
      "learning_rate": 2e-07,
      "loss": 0.0094,
      "step": 118
    },
    {
      "clip_ratio/high_max": 0.003184327499184292,
      "clip_ratio/high_mean": 0.0014856331144983415,
      "clip_ratio/low_mean": 0.0011788228257501032,
      "clip_ratio/low_min": 0.00020759128165082075,
      "clip_ratio/region_mean": 0.0026644559839041904,
      "epoch": 0.011106638900069417,
      "grad_norm": 0.1840520203113556,
      "learning_rate": 2e-07,
      "loss": -0.0093,
      "step": 119
    },
    {
      "clip_ratio/high_max": 0.0029894941035308875,
      "clip_ratio/high_mean": 0.0013333193819562439,
      "clip_ratio/low_mean": 0.0012309773919696454,
      "clip_ratio/low_min": 0.00013832677723257802,
      "clip_ratio/region_mean": 0.0025642967157182284,
      "epoch": 0.01119997200007,
      "grad_norm": 0.19213904440402985,
      "learning_rate": 2e-07,
      "loss": -0.0044,
      "step": 120
    },
    {
      "clip_ratio/high_max": 0.002906564681325108,
      "clip_ratio/high_mean": 0.0013738416928390507,
      "clip_ratio/low_mean": 0.0012525788151833694,
      "clip_ratio/low_min": 0.0001482012066844618,
      "clip_ratio/region_mean": 0.0026264205807819963,
      "epoch": 0.011293305100070584,
      "grad_norm": 0.2320069968700409,
      "learning_rate": 2e-07,
      "loss": 0.0125,
      "step": 121
    },
    {
      "clip_ratio/high_max": 0.0030602143888245337,
      "clip_ratio/high_mean": 0.0014149211710901,
      "clip_ratio/low_mean": 0.0012173053855804028,
      "clip_ratio/low_min": 0.0001835508919612039,
      "clip_ratio/region_mean": 0.0026322265912313014,
      "epoch": 0.011386638200071167,
      "grad_norm": 0.21284720301628113,
      "learning_rate": 2e-07,
      "loss": -0.0294,
      "step": 122
    },
    {
      "clip_ratio/high_max": 0.0031788112537469715,
      "clip_ratio/high_mean": 0.0014349647535709664,
      "clip_ratio/low_mean": 0.0012942128341819625,
      "clip_ratio/low_min": 0.000158605927026656,
      "clip_ratio/region_mean": 0.0027291775913909078,
      "epoch": 0.011479971300071749,
      "grad_norm": 0.2327825278043747,
      "learning_rate": 2e-07,
      "loss": 0.0084,
      "step": 123
    },
    {
      "clip_ratio/high_max": 0.003305037462268956,
      "clip_ratio/high_mean": 0.0013898545439587906,
      "clip_ratio/low_mean": 0.0014036611064511817,
      "clip_ratio/low_min": 0.00019112394238618435,
      "clip_ratio/region_mean": 0.0027935156322200783,
      "epoch": 0.011573304400072332,
      "grad_norm": 0.2331952601671219,
      "learning_rate": 2e-07,
      "loss": 0.0311,
      "step": 124
    },
    {
      "clip_ratio/high_max": 0.003134739337838255,
      "clip_ratio/high_mean": 0.0013305547217896674,
      "clip_ratio/low_mean": 0.0013800325832562521,
      "clip_ratio/low_min": 0.0002458781782479491,
      "clip_ratio/region_mean": 0.0027105873377877288,
      "epoch": 0.011666637500072916,
      "grad_norm": 0.17725017666816711,
      "learning_rate": 2e-07,
      "loss": 0.011,
      "step": 125
    },
    {
      "clip_ratio/high_max": 0.00263468536286382,
      "clip_ratio/high_mean": 0.0011493472047732212,
      "clip_ratio/low_mean": 0.0013665114602190442,
      "clip_ratio/low_min": 0.00023296094877878204,
      "clip_ratio/region_mean": 0.0025158586868201382,
      "epoch": 0.0117599706000735,
      "grad_norm": 0.21296899020671844,
      "learning_rate": 2e-07,
      "loss": -0.0004,
      "step": 126
    },
    {
      "clip_ratio/high_max": 0.002760658295301255,
      "clip_ratio/high_mean": 0.0012749816851282958,
      "clip_ratio/low_mean": 0.001276443770620972,
      "clip_ratio/low_min": 0.00023521079128840938,
      "clip_ratio/region_mean": 0.002551425430283416,
      "epoch": 0.011853303700074083,
      "grad_norm": 0.17043305933475494,
      "learning_rate": 2e-07,
      "loss": 0.0375,
      "step": 127
    },
    {
      "clip_ratio/high_max": 0.0031045092109707184,
      "clip_ratio/high_mean": 0.0014013611144036986,
      "clip_ratio/low_mean": 0.001528628639789531,
      "clip_ratio/low_min": 0.0002908705291702063,
      "clip_ratio/region_mean": 0.002929989743279293,
      "epoch": 0.011946636800074666,
      "grad_norm": 0.22638551890850067,
      "learning_rate": 2e-07,
      "loss": -0.0057,
      "step": 128
    },
    {
      "clip_ratio/high_max": 0.00232501098071225,
      "clip_ratio/high_mean": 0.0009063930956472177,
      "clip_ratio/low_mean": 0.0006178411276778206,
      "clip_ratio/low_min": 4.4985728891333565e-05,
      "clip_ratio/region_mean": 0.0015242342196870595,
      "completions/clipped_ratio": 0.014003208705357095,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4089.0,
      "completions/mean_length": 612.0515747070312,
      "completions/mean_terminated_length": 562.572265625,
      "completions/min_length": 4.0,
      "completions/min_terminated_length": 4.0,
      "epoch": 0.01203996990007525,
      "grad_norm": 0.11548373103141785,
      "learning_rate": 2e-07,
      "loss": -0.0007,
      "num_tokens": 162088634.0,
      "reward": 0.557320773601532,
      "reward_std": 0.20648711919784546,
      "rewards/simpleverify_reward/mean": 0.5573207139968872,
      "rewards/simpleverify_reward/std": 0.4967055320739746,
      "step": 129
    },
    {
      "clip_ratio/high_max": 0.0018056633925880305,
      "clip_ratio/high_mean": 0.0007321788743865909,
      "clip_ratio/low_mean": 0.0005952819738013204,
      "clip_ratio/low_min": 2.6674157197703607e-05,
      "clip_ratio/region_mean": 0.00132746088274871,
      "epoch": 0.012133303000075833,
      "grad_norm": 0.10720103979110718,
      "learning_rate": 2e-07,
      "loss": 0.0511,
      "step": 130
    },
    {
      "clip_ratio/high_max": 0.001899360511742998,
      "clip_ratio/high_mean": 0.000749359508517955,
      "clip_ratio/low_mean": 0.0005399876754381694,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012893471721326932,
      "epoch": 0.012226636100076417,
      "grad_norm": 0.11088676750659943,
      "learning_rate": 2e-07,
      "loss": 0.0457,
      "step": 131
    },
    {
      "clip_ratio/high_max": 0.0019340096077939961,
      "clip_ratio/high_mean": 0.0008524430086254142,
      "clip_ratio/low_mean": 0.0005190552565181861,
      "clip_ratio/low_min": 5.66173875995446e-05,
      "clip_ratio/region_mean": 0.0013714982669625897,
      "epoch": 0.012319969200077,
      "grad_norm": 0.12459676712751389,
      "learning_rate": 2e-07,
      "loss": -0.0413,
      "step": 132
    },
    {
      "clip_ratio/high_max": 0.0020766235393239185,
      "clip_ratio/high_mean": 0.0008440274596068775,
      "clip_ratio/low_mean": 0.0005440281615847198,
      "clip_ratio/low_min": 2.679387034731917e-05,
      "clip_ratio/region_mean": 0.0013880556398362387,
      "epoch": 0.012413302300077584,
      "grad_norm": 0.1213875338435173,
      "learning_rate": 2e-07,
      "loss": 0.016,
      "step": 133
    },
    {
      "clip_ratio/high_max": 0.0019092861621174961,
      "clip_ratio/high_mean": 0.0008111224851745646,
      "clip_ratio/low_mean": 0.0006635082054344821,
      "clip_ratio/low_min": 5.902294378756778e-05,
      "clip_ratio/region_mean": 0.0014746306696906686,
      "epoch": 0.012506635400078167,
      "grad_norm": 0.12240087240934372,
      "learning_rate": 2e-07,
      "loss": 0.0521,
      "step": 134
    },
    {
      "clip_ratio/high_max": 0.0022147839845274575,
      "clip_ratio/high_mean": 0.0009147003984253388,
      "clip_ratio/low_mean": 0.0005792223582830047,
      "clip_ratio/low_min": 3.486750210868195e-05,
      "clip_ratio/region_mean": 0.0014939227621653117,
      "epoch": 0.01259996850007875,
      "grad_norm": 0.12430458515882492,
      "learning_rate": 2e-07,
      "loss": 0.0088,
      "step": 135
    },
    {
      "clip_ratio/high_max": 0.0020741950575029477,
      "clip_ratio/high_mean": 0.0008437033011432504,
      "clip_ratio/low_mean": 0.0006329828993330011,
      "clip_ratio/low_min": 7.527784418925876e-05,
      "clip_ratio/region_mean": 0.0014766861750104,
      "epoch": 0.012693301600079332,
      "grad_norm": 0.1303962767124176,
      "learning_rate": 2e-07,
      "loss": 0.0376,
      "step": 136
    },
    {
      "clip_ratio/high_max": 0.002193069230997935,
      "clip_ratio/high_mean": 0.0008065390229603508,
      "clip_ratio/low_mean": 0.000517238368956896,
      "clip_ratio/low_min": 4.489570528676268e-05,
      "clip_ratio/region_mean": 0.0013237773891887628,
      "epoch": 0.012786634700079916,
      "grad_norm": 0.11874948441982269,
      "learning_rate": 2e-07,
      "loss": 0.0032,
      "step": 137
    },
    {
      "clip_ratio/high_max": 0.0021708905915147625,
      "clip_ratio/high_mean": 0.0007834745156287681,
      "clip_ratio/low_mean": 0.0006067644280847162,
      "clip_ratio/low_min": 7.887519996074843e-05,
      "clip_ratio/region_mean": 0.001390238932799548,
      "epoch": 0.0128799678000805,
      "grad_norm": 0.12342286109924316,
      "learning_rate": 2e-07,
      "loss": 0.0361,
      "step": 138
    },
    {
      "clip_ratio/high_max": 0.0021549754237639718,
      "clip_ratio/high_mean": 0.000825220446131425,
      "clip_ratio/low_mean": 0.0006075554483686574,
      "clip_ratio/low_min": 3.948605626646895e-05,
      "clip_ratio/region_mean": 0.0014327758763101883,
      "epoch": 0.012973300900081083,
      "grad_norm": 0.11775846779346466,
      "learning_rate": 2e-07,
      "loss": 0.023,
      "step": 139
    },
    {
      "clip_ratio/high_max": 0.00231831432756735,
      "clip_ratio/high_mean": 0.0009050001281138975,
      "clip_ratio/low_mean": 0.0006249633875086147,
      "clip_ratio/low_min": 3.1702074920758605e-05,
      "clip_ratio/region_mean": 0.0015299634833354503,
      "epoch": 0.013066634000081666,
      "grad_norm": 0.12300993502140045,
      "learning_rate": 2e-07,
      "loss": 0.0158,
      "step": 140
    },
    {
      "clip_ratio/high_max": 0.002264536487928126,
      "clip_ratio/high_mean": 0.0009316449559264584,
      "clip_ratio/low_mean": 0.0005919352079217788,
      "clip_ratio/low_min": 5.5487436839030124e-05,
      "clip_ratio/region_mean": 0.001523580176581163,
      "epoch": 0.01315996710008225,
      "grad_norm": 0.1228451356291771,
      "learning_rate": 2e-07,
      "loss": -0.0034,
      "step": 141
    },
    {
      "clip_ratio/high_max": 0.001788812551239971,
      "clip_ratio/high_mean": 0.000803649241788662,
      "clip_ratio/low_mean": 0.0005823452993354294,
      "clip_ratio/low_min": 3.0763343602302484e-05,
      "clip_ratio/region_mean": 0.0013859945756848902,
      "epoch": 0.013253300200082833,
      "grad_norm": 0.13015413284301758,
      "learning_rate": 2e-07,
      "loss": 0.0245,
      "step": 142
    },
    {
      "clip_ratio/high_max": 0.0020430958247743547,
      "clip_ratio/high_mean": 0.0008549613594368566,
      "clip_ratio/low_mean": 0.000667634887577151,
      "clip_ratio/low_min": 6.104574094933923e-05,
      "clip_ratio/region_mean": 0.0015225962197291665,
      "epoch": 0.013346633300083417,
      "grad_norm": 0.1261974275112152,
      "learning_rate": 2e-07,
      "loss": 0.0207,
      "step": 143
    },
    {
      "clip_ratio/high_max": 0.00218324024535832,
      "clip_ratio/high_mean": 0.0009062221979547758,
      "clip_ratio/low_mean": 0.0006309419629815238,
      "clip_ratio/low_min": 3.0008367502887268e-05,
      "clip_ratio/region_mean": 0.0015371641857200302,
      "epoch": 0.013439966400084,
      "grad_norm": 0.13090796768665314,
      "learning_rate": 2e-07,
      "loss": -0.0454,
      "step": 144
    },
    {
      "clip_ratio/high_max": 0.0018428340117679909,
      "clip_ratio/high_mean": 0.0008301965517603094,
      "clip_ratio/low_mean": 0.0006295781695371261,
      "clip_ratio/low_min": 7.841734441171866e-05,
      "clip_ratio/region_mean": 0.0014597747212974355,
      "epoch": 0.013533299500084583,
      "grad_norm": 0.12244794517755508,
      "learning_rate": 2e-07,
      "loss": 0.0488,
      "step": 145
    },
    {
      "clip_ratio/high_max": 0.0023128381071728654,
      "clip_ratio/high_mean": 0.0009522552863927558,
      "clip_ratio/low_mean": 0.0005213593412918271,
      "clip_ratio/low_min": 4.9851912990561686e-05,
      "clip_ratio/region_mean": 0.0014736146149516571,
      "epoch": 0.013626632600085167,
      "grad_norm": 0.12503549456596375,
      "learning_rate": 2e-07,
      "loss": 0.0071,
      "step": 146
    },
    {
      "clip_ratio/high_max": 0.001932383507664781,
      "clip_ratio/high_mean": 0.0007960152215673588,
      "clip_ratio/low_mean": 0.0006826122607890284,
      "clip_ratio/low_min": 4.7681163778179325e-05,
      "clip_ratio/region_mean": 0.0014786274623475038,
      "epoch": 0.01371996570008575,
      "grad_norm": 0.1202053651213646,
      "learning_rate": 2e-07,
      "loss": 0.0391,
      "step": 147
    },
    {
      "clip_ratio/high_max": 0.0017457220310461707,
      "clip_ratio/high_mean": 0.0007050544427329442,
      "clip_ratio/low_mean": 0.0005960238204352208,
      "clip_ratio/low_min": 4.33173481724225e-05,
      "clip_ratio/region_mean": 0.0013010782822675537,
      "epoch": 0.013813298800086334,
      "grad_norm": 0.11331025511026382,
      "learning_rate": 2e-07,
      "loss": 0.0495,
      "step": 148
    },
    {
      "clip_ratio/high_max": 0.0022634210690739565,
      "clip_ratio/high_mean": 0.0008236529283749405,
      "clip_ratio/low_mean": 0.0006043082776159281,
      "clip_ratio/low_min": 3.8978926568233874e-05,
      "clip_ratio/region_mean": 0.0014279611787060276,
      "epoch": 0.013906631900086916,
      "grad_norm": 0.12493271380662918,
      "learning_rate": 2e-07,
      "loss": 0.0366,
      "step": 149
    },
    {
      "clip_ratio/high_max": 0.001948405279108556,
      "clip_ratio/high_mean": 0.0008463402809866238,
      "clip_ratio/low_mean": 0.0006194850448082434,
      "clip_ratio/low_min": 4.4843030991614796e-05,
      "clip_ratio/region_mean": 0.0014658253494417295,
      "epoch": 0.013999965000087499,
      "grad_norm": 0.11433596163988113,
      "learning_rate": 2e-07,
      "loss": 0.0382,
      "step": 150
    },
    {
      "clip_ratio/high_max": 0.001643922398216091,
      "clip_ratio/high_mean": 0.0007427159853250487,
      "clip_ratio/low_mean": 0.00062657557282364,
      "clip_ratio/low_min": 3.7957225686113816e-05,
      "clip_ratio/region_mean": 0.0013692915454157628,
      "epoch": 0.014093298100088083,
      "grad_norm": 0.1152142584323883,
      "learning_rate": 2e-07,
      "loss": 0.0254,
      "step": 151
    },
    {
      "clip_ratio/high_max": 0.002095764662954025,
      "clip_ratio/high_mean": 0.0008691585862834472,
      "clip_ratio/low_mean": 0.0004901157299173065,
      "clip_ratio/low_min": 2.459009465383133e-05,
      "clip_ratio/region_mean": 0.0013592743343906477,
      "epoch": 0.014186631200088666,
      "grad_norm": 0.12261440604925156,
      "learning_rate": 2e-07,
      "loss": 0.0003,
      "step": 152
    },
    {
      "clip_ratio/high_max": 0.001958136970642954,
      "clip_ratio/high_mean": 0.0007773633205943042,
      "clip_ratio/low_mean": 0.0006693352206639247,
      "clip_ratio/low_min": 3.299753188912291e-05,
      "clip_ratio/region_mean": 0.0014466985558101442,
      "epoch": 0.01427996430008925,
      "grad_norm": 0.12206938117742538,
      "learning_rate": 2e-07,
      "loss": 0.0449,
      "step": 153
    },
    {
      "clip_ratio/high_max": 0.0017215214429597836,
      "clip_ratio/high_mean": 0.0006703513117827242,
      "clip_ratio/low_mean": 0.0006140235982456943,
      "clip_ratio/low_min": 7.891191398812225e-05,
      "clip_ratio/region_mean": 0.001284374902752461,
      "epoch": 0.014373297400089833,
      "grad_norm": 0.12928135693073273,
      "learning_rate": 2e-07,
      "loss": 0.0666,
      "step": 154
    },
    {
      "clip_ratio/high_max": 0.0025190896849380806,
      "clip_ratio/high_mean": 0.0010315882609575056,
      "clip_ratio/low_mean": 0.000549425041754148,
      "clip_ratio/low_min": 4.4392332711140625e-05,
      "clip_ratio/region_mean": 0.00158101328270277,
      "epoch": 0.014466630500090416,
      "grad_norm": 0.11839871853590012,
      "learning_rate": 2e-07,
      "loss": 0.0097,
      "step": 155
    },
    {
      "clip_ratio/high_max": 0.002192861051298678,
      "clip_ratio/high_mean": 0.0007855405292502837,
      "clip_ratio/low_mean": 0.0005968113728158642,
      "clip_ratio/low_min": 2.736394071689574e-05,
      "clip_ratio/region_mean": 0.001382351911161095,
      "epoch": 0.014559963600091,
      "grad_norm": 0.12960529327392578,
      "learning_rate": 2e-07,
      "loss": 0.0402,
      "step": 156
    },
    {
      "clip_ratio/high_max": 0.0022708648903062567,
      "clip_ratio/high_mean": 0.0008667979527672287,
      "clip_ratio/low_mean": 0.0005383280395108159,
      "clip_ratio/low_min": 2.439804211462615e-05,
      "clip_ratio/region_mean": 0.001405126036843285,
      "epoch": 0.014653296700091583,
      "grad_norm": 0.11870219558477402,
      "learning_rate": 2e-07,
      "loss": -0.012,
      "step": 157
    },
    {
      "clip_ratio/high_max": 0.001813713042793097,
      "clip_ratio/high_mean": 0.0007951536545078852,
      "clip_ratio/low_mean": 0.0005980955738777993,
      "clip_ratio/low_min": 3.533307335601421e-05,
      "clip_ratio/region_mean": 0.001393249214743264,
      "epoch": 0.014746629800092167,
      "grad_norm": 0.17155663669109344,
      "learning_rate": 2e-07,
      "loss": 0.0321,
      "step": 158
    },
    {
      "clip_ratio/high_max": 0.0020153238510829397,
      "clip_ratio/high_mean": 0.0009111322378885234,
      "clip_ratio/low_mean": 0.0006379829883371713,
      "clip_ratio/low_min": 8.379660630453145e-05,
      "clip_ratio/region_mean": 0.0015491152043978218,
      "epoch": 0.01483996290009275,
      "grad_norm": 0.12098103761672974,
      "learning_rate": 2e-07,
      "loss": 0.0349,
      "step": 159
    },
    {
      "clip_ratio/high_max": 0.002073839037620928,
      "clip_ratio/high_mean": 0.0007979708934726659,
      "clip_ratio/low_mean": 0.00058883255951514,
      "clip_ratio/low_min": 2.1562566871580202e-05,
      "clip_ratio/region_mean": 0.0013868034657207318,
      "epoch": 0.014933296000093334,
      "grad_norm": 0.12484041601419449,
      "learning_rate": 2e-07,
      "loss": 0.0343,
      "step": 160
    },
    {
      "clip_ratio/high_max": 0.0020564257065416314,
      "clip_ratio/high_mean": 0.0007869898327044211,
      "clip_ratio/low_mean": 0.0006445478393288795,
      "clip_ratio/low_min": 5.639357368636411e-05,
      "clip_ratio/region_mean": 0.0014315376720333006,
      "epoch": 0.015026629100093917,
      "grad_norm": 0.12660476565361023,
      "learning_rate": 2e-07,
      "loss": -0.0019,
      "step": 161
    },
    {
      "clip_ratio/high_max": 0.001999727690417785,
      "clip_ratio/high_mean": 0.000846094626467675,
      "clip_ratio/low_mean": 0.0005975343974569114,
      "clip_ratio/low_min": 4.258763010511757e-05,
      "clip_ratio/region_mean": 0.0014436290512094274,
      "epoch": 0.015119962200094499,
      "grad_norm": 0.13701540231704712,
      "learning_rate": 2e-07,
      "loss": 0.0211,
      "step": 162
    },
    {
      "clip_ratio/high_max": 0.0019190769125998486,
      "clip_ratio/high_mean": 0.000797158378190943,
      "clip_ratio/low_mean": 0.0005433618653114536,
      "clip_ratio/low_min": 2.7918146315641934e-05,
      "clip_ratio/region_mean": 0.001340520229859976,
      "epoch": 0.015213295300095082,
      "grad_norm": 0.11606060713529587,
      "learning_rate": 2e-07,
      "loss": 0.0183,
      "step": 163
    },
    {
      "clip_ratio/high_max": 0.002203612013545353,
      "clip_ratio/high_mean": 0.0008608292901044479,
      "clip_ratio/low_mean": 0.0006327167684503365,
      "clip_ratio/low_min": 2.1316264792403672e-05,
      "clip_ratio/region_mean": 0.0014935460130800493,
      "epoch": 0.015306628400095666,
      "grad_norm": 0.11794206500053406,
      "learning_rate": 2e-07,
      "loss": 0.0264,
      "step": 164
    },
    {
      "clip_ratio/high_max": 0.0024271376241813414,
      "clip_ratio/high_mean": 0.0008782749355304986,
      "clip_ratio/low_mean": 0.0006297012096183607,
      "clip_ratio/low_min": 6.613056939386297e-06,
      "clip_ratio/region_mean": 0.0015079761542438064,
      "epoch": 0.01539996150009625,
      "grad_norm": 0.11385703831911087,
      "learning_rate": 2e-07,
      "loss": -0.0237,
      "step": 165
    },
    {
      "clip_ratio/high_max": 0.001960954876267351,
      "clip_ratio/high_mean": 0.0008519470029568765,
      "clip_ratio/low_mean": 0.0005204352673899848,
      "clip_ratio/low_min": 4.249007997714216e-05,
      "clip_ratio/region_mean": 0.0013723822885367554,
      "epoch": 0.015493294600096833,
      "grad_norm": 0.1304963231086731,
      "learning_rate": 2e-07,
      "loss": -0.0087,
      "step": 166
    },
    {
      "clip_ratio/high_max": 0.002020803585764952,
      "clip_ratio/high_mean": 0.00089911196664616,
      "clip_ratio/low_mean": 0.0005822664370498387,
      "clip_ratio/low_min": 3.342315949339536e-05,
      "clip_ratio/region_mean": 0.001481378436437808,
      "epoch": 0.015586627700097416,
      "grad_norm": 0.12180845439434052,
      "learning_rate": 2e-07,
      "loss": 0.0062,
      "step": 167
    },
    {
      "clip_ratio/high_max": 0.002204894812166458,
      "clip_ratio/high_mean": 0.0008095046287053265,
      "clip_ratio/low_mean": 0.0005879498394278926,
      "clip_ratio/low_min": 4.449742209544638e-05,
      "clip_ratio/region_mean": 0.0013974544708617032,
      "epoch": 0.015679960800098,
      "grad_norm": 0.1236138641834259,
      "learning_rate": 2e-07,
      "loss": -0.0035,
      "step": 168
    },
    {
      "clip_ratio/high_max": 0.002182902149797883,
      "clip_ratio/high_mean": 0.0009125107626459794,
      "clip_ratio/low_mean": 0.0005880029348190874,
      "clip_ratio/low_min": 8.073392109508859e-05,
      "clip_ratio/region_mean": 0.0015005137320258655,
      "epoch": 0.015773293900098583,
      "grad_norm": 0.11757367104291916,
      "learning_rate": 2e-07,
      "loss": -0.0114,
      "step": 169
    },
    {
      "clip_ratio/high_max": 0.0018806407606462017,
      "clip_ratio/high_mean": 0.0008008478471310809,
      "clip_ratio/low_mean": 0.0005428344657048001,
      "clip_ratio/low_min": 4.654940858017653e-05,
      "clip_ratio/region_mean": 0.0013436823355732486,
      "epoch": 0.015866627000099165,
      "grad_norm": 0.12251515686511993,
      "learning_rate": 2e-07,
      "loss": 0.0393,
      "step": 170
    },
    {
      "clip_ratio/high_max": 0.002171648222429212,
      "clip_ratio/high_mean": 0.0009175659051834373,
      "clip_ratio/low_mean": 0.0007178434643719811,
      "clip_ratio/low_min": 4.9187318836629856e-05,
      "clip_ratio/region_mean": 0.0016354093968402594,
      "epoch": 0.01595996010009975,
      "grad_norm": 0.12177026271820068,
      "learning_rate": 2e-07,
      "loss": 0.043,
      "step": 171
    },
    {
      "clip_ratio/high_max": 0.002654982323292643,
      "clip_ratio/high_mean": 0.0009469276774325408,
      "clip_ratio/low_mean": 0.0006065974885132164,
      "clip_ratio/low_min": 3.3059307952498784e-05,
      "clip_ratio/region_mean": 0.0015535251477558631,
      "epoch": 0.016053293200100332,
      "grad_norm": 0.13682252168655396,
      "learning_rate": 2e-07,
      "loss": 0.0542,
      "step": 172
    },
    {
      "clip_ratio/high_max": 0.0023487524631491397,
      "clip_ratio/high_mean": 0.0009592491569492267,
      "clip_ratio/low_mean": 0.000556267376850883,
      "clip_ratio/low_min": 1.2698090358753689e-05,
      "clip_ratio/region_mean": 0.0015155165310716256,
      "epoch": 0.016146626300100917,
      "grad_norm": 0.12156112492084503,
      "learning_rate": 2e-07,
      "loss": 0.024,
      "step": 173
    },
    {
      "clip_ratio/high_max": 0.0018505962652852759,
      "clip_ratio/high_mean": 0.0008832064231683034,
      "clip_ratio/low_mean": 0.0005731603655476647,
      "clip_ratio/low_min": 6.192695309437113e-05,
      "clip_ratio/region_mean": 0.0014563667537004221,
      "epoch": 0.0162399594001015,
      "grad_norm": 0.12489704042673111,
      "learning_rate": 2e-07,
      "loss": 0.0087,
      "step": 174
    },
    {
      "clip_ratio/high_max": 0.002171798922063317,
      "clip_ratio/high_mean": 0.0008508539922331693,
      "clip_ratio/low_mean": 0.0006780292915209429,
      "clip_ratio/low_min": 4.7501392145932186e-05,
      "clip_ratio/region_mean": 0.001528883287392091,
      "epoch": 0.016333292500102084,
      "grad_norm": 0.13400530815124512,
      "learning_rate": 2e-07,
      "loss": 0.0532,
      "step": 175
    },
    {
      "clip_ratio/high_max": 0.002305213231011294,
      "clip_ratio/high_mean": 0.0008562942002754426,
      "clip_ratio/low_mean": 0.0005815803388031782,
      "clip_ratio/low_min": 6.998276694503147e-05,
      "clip_ratio/region_mean": 0.0014378745509020519,
      "epoch": 0.016426625600102666,
      "grad_norm": 0.11236870288848877,
      "learning_rate": 2e-07,
      "loss": 0.043,
      "step": 176
    },
    {
      "clip_ratio/high_max": 0.0018417850660625845,
      "clip_ratio/high_mean": 0.000804103725386085,
      "clip_ratio/low_mean": 0.0007310412802326027,
      "clip_ratio/low_min": 3.313874276500428e-05,
      "clip_ratio/region_mean": 0.0015351450128946453,
      "epoch": 0.01651995870010325,
      "grad_norm": 0.12231137603521347,
      "learning_rate": 2e-07,
      "loss": 0.0236,
      "step": 177
    },
    {
      "clip_ratio/high_max": 0.002042430314759258,
      "clip_ratio/high_mean": 0.0009092611999221845,
      "clip_ratio/low_mean": 0.000634656498732511,
      "clip_ratio/low_min": 6.356720950861927e-05,
      "clip_ratio/region_mean": 0.0015439177223015577,
      "epoch": 0.016613291800103833,
      "grad_norm": 0.1261111944913864,
      "learning_rate": 2e-07,
      "loss": 0.0479,
      "step": 178
    },
    {
      "clip_ratio/high_max": 0.002036279100138927,
      "clip_ratio/high_mean": 0.0008984946543932892,
      "clip_ratio/low_mean": 0.0005924105644226074,
      "clip_ratio/low_min": 5.5581668675586116e-05,
      "clip_ratio/region_mean": 0.0014909052333678119,
      "epoch": 0.016706624900104418,
      "grad_norm": 0.11070719361305237,
      "learning_rate": 2e-07,
      "loss": 0.0142,
      "step": 179
    },
    {
      "clip_ratio/high_max": 0.0020525919608189724,
      "clip_ratio/high_mean": 0.0008605773182353005,
      "clip_ratio/low_mean": 0.0006487906503025442,
      "clip_ratio/low_min": 2.7856665838044137e-05,
      "clip_ratio/region_mean": 0.0015093679394340143,
      "epoch": 0.016799958000105,
      "grad_norm": 0.12303735315799713,
      "learning_rate": 2e-07,
      "loss": 0.0351,
      "step": 180
    },
    {
      "clip_ratio/high_max": 0.002129068205249496,
      "clip_ratio/high_mean": 0.0009720463349367492,
      "clip_ratio/low_mean": 0.0005559332394113881,
      "clip_ratio/low_min": 5.655848144670017e-05,
      "clip_ratio/region_mean": 0.001527979602542473,
      "epoch": 0.016893291100105585,
      "grad_norm": 0.11540050804615021,
      "learning_rate": 2e-07,
      "loss": -0.0366,
      "step": 181
    },
    {
      "clip_ratio/high_max": 0.0020038939765072428,
      "clip_ratio/high_mean": 0.0007371270830844878,
      "clip_ratio/low_mean": 0.0005834991679876111,
      "clip_ratio/low_min": 1.9800412701442838e-05,
      "clip_ratio/region_mean": 0.0013206262374296784,
      "epoch": 0.016986624200106167,
      "grad_norm": 0.1305420696735382,
      "learning_rate": 2e-07,
      "loss": 0.0584,
      "step": 182
    },
    {
      "clip_ratio/high_max": 0.0018414657206449192,
      "clip_ratio/high_mean": 0.0008148505439748988,
      "clip_ratio/low_mean": 0.0006569972038050764,
      "clip_ratio/low_min": 5.621243781206431e-05,
      "clip_ratio/region_mean": 0.0014718477468704805,
      "epoch": 0.017079957300106748,
      "grad_norm": 0.1262456476688385,
      "learning_rate": 2e-07,
      "loss": 0.0285,
      "step": 183
    },
    {
      "clip_ratio/high_max": 0.0019878515377058648,
      "clip_ratio/high_mean": 0.0008784572219155962,
      "clip_ratio/low_mean": 0.0006598397776542697,
      "clip_ratio/low_min": 3.8797970773885027e-05,
      "clip_ratio/region_mean": 0.001538297008664813,
      "epoch": 0.017173290400107333,
      "grad_norm": 0.13227629661560059,
      "learning_rate": 2e-07,
      "loss": 0.0264,
      "step": 184
    },
    {
      "clip_ratio/high_max": 0.0021797280860482715,
      "clip_ratio/high_mean": 0.0008352215572813293,
      "clip_ratio/low_mean": 0.0006388653982867254,
      "clip_ratio/low_min": 7.673253639950417e-05,
      "clip_ratio/region_mean": 0.001474086948292097,
      "epoch": 0.017266623500107915,
      "grad_norm": 0.12080742418766022,
      "learning_rate": 2e-07,
      "loss": 0.0371,
      "step": 185
    },
    {
      "clip_ratio/high_max": 0.0018475940742064267,
      "clip_ratio/high_mean": 0.0007771433411107864,
      "clip_ratio/low_mean": 0.0007134704446798423,
      "clip_ratio/low_min": 0.00010657935035851551,
      "clip_ratio/region_mean": 0.001490613791247597,
      "epoch": 0.0173599566001085,
      "grad_norm": 0.12375640124082565,
      "learning_rate": 2e-07,
      "loss": 0.0561,
      "step": 186
    },
    {
      "clip_ratio/high_max": 0.0020230036607244983,
      "clip_ratio/high_mean": 0.0009091730371437734,
      "clip_ratio/low_mean": 0.0006899904965393944,
      "clip_ratio/low_min": 2.9107782211212907e-05,
      "clip_ratio/region_mean": 0.0015991635445971042,
      "epoch": 0.017453289700109082,
      "grad_norm": 0.12571005523204803,
      "learning_rate": 2e-07,
      "loss": 0.0092,
      "step": 187
    },
    {
      "clip_ratio/high_max": 0.002062592528091045,
      "clip_ratio/high_mean": 0.0008402757284784457,
      "clip_ratio/low_mean": 0.0005597691742877942,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014000449009472504,
      "epoch": 0.017546622800109667,
      "grad_norm": 0.11693722754716873,
      "learning_rate": 2e-07,
      "loss": 0.0278,
      "step": 188
    },
    {
      "clip_ratio/high_max": 0.0019465201330604032,
      "clip_ratio/high_mean": 0.0009197594208671944,
      "clip_ratio/low_mean": 0.0006881533590785693,
      "clip_ratio/low_min": 9.600930297892774e-05,
      "clip_ratio/region_mean": 0.0016079127744887955,
      "epoch": 0.01763995590011025,
      "grad_norm": 0.12828868627548218,
      "learning_rate": 2e-07,
      "loss": -0.0006,
      "step": 189
    },
    {
      "clip_ratio/high_max": 0.0020874080291832797,
      "clip_ratio/high_mean": 0.0007725537889200496,
      "clip_ratio/low_mean": 0.0005197366672291537,
      "clip_ratio/low_min": 3.6643272323999554e-05,
      "clip_ratio/region_mean": 0.001292290435230825,
      "epoch": 0.017733289000110834,
      "grad_norm": 0.10893333703279495,
      "learning_rate": 2e-07,
      "loss": 0.0169,
      "step": 190
    },
    {
      "clip_ratio/high_max": 0.002281424618558958,
      "clip_ratio/high_mean": 0.0009387596983287949,
      "clip_ratio/low_mean": 0.0006478988307208056,
      "clip_ratio/low_min": 3.0447034077951685e-05,
      "clip_ratio/region_mean": 0.001586658549058484,
      "epoch": 0.017826622100111416,
      "grad_norm": 0.12853072583675385,
      "learning_rate": 2e-07,
      "loss": 0.007,
      "step": 191
    },
    {
      "clip_ratio/high_max": 0.0021231984719634056,
      "clip_ratio/high_mean": 0.000808759628853295,
      "clip_ratio/low_mean": 0.0007177643765317043,
      "clip_ratio/low_min": 4.869007261731895e-05,
      "clip_ratio/region_mean": 0.0015265239671862219,
      "epoch": 0.017919955200112,
      "grad_norm": 0.11824563145637512,
      "learning_rate": 2e-07,
      "loss": 0.0364,
      "step": 192
    },
    {
      "clip_ratio/high_max": 0.002120645051036263,
      "clip_ratio/high_mean": 0.0008683730820848723,
      "clip_ratio/low_mean": 0.0006714710198139073,
      "clip_ratio/low_min": 5.060790681454819e-05,
      "clip_ratio/region_mean": 0.0015398441319121048,
      "epoch": 0.018013288300112583,
      "grad_norm": 0.12373674660921097,
      "learning_rate": 2e-07,
      "loss": 0.0492,
      "step": 193
    },
    {
      "clip_ratio/high_max": 0.001904488555737771,
      "clip_ratio/high_mean": 0.0008250911832874408,
      "clip_ratio/low_mean": 0.0007683680996706244,
      "clip_ratio/low_min": 0.00011069276388298022,
      "clip_ratio/region_mean": 0.0015934593175188638,
      "epoch": 0.018106621400113165,
      "grad_norm": 0.12099580466747284,
      "learning_rate": 2e-07,
      "loss": 0.0522,
      "step": 194
    },
    {
      "clip_ratio/high_max": 0.0019143188110319898,
      "clip_ratio/high_mean": 0.0008691905422892887,
      "clip_ratio/low_mean": 0.0007370821895165136,
      "clip_ratio/low_min": 5.501925807038788e-05,
      "clip_ratio/region_mean": 0.0016062727518146858,
      "epoch": 0.01819995450011375,
      "grad_norm": 0.1140805333852768,
      "learning_rate": 2e-07,
      "loss": 0.0469,
      "step": 195
    },
    {
      "clip_ratio/high_max": 0.0023856419502408244,
      "clip_ratio/high_mean": 0.0009381688960274914,
      "clip_ratio/low_mean": 0.0006135028197604697,
      "clip_ratio/low_min": 1.7375590687151998e-05,
      "clip_ratio/region_mean": 0.0015516717030550353,
      "epoch": 0.01829328760011433,
      "grad_norm": 0.12470970302820206,
      "learning_rate": 2e-07,
      "loss": -0.0014,
      "step": 196
    },
    {
      "clip_ratio/high_max": 0.0019531519392330665,
      "clip_ratio/high_mean": 0.0008460121443931712,
      "clip_ratio/low_mean": 0.0005158997146281763,
      "clip_ratio/low_min": 1.3069845408608671e-05,
      "clip_ratio/region_mean": 0.001361911854473874,
      "epoch": 0.018386620700114917,
      "grad_norm": 0.11249268800020218,
      "learning_rate": 2e-07,
      "loss": 0.012,
      "step": 197
    },
    {
      "clip_ratio/high_max": 0.0018231346657557879,
      "clip_ratio/high_mean": 0.000771814208746946,
      "clip_ratio/low_mean": 0.0006186212776810862,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013904354855185375,
      "epoch": 0.0184799538001155,
      "grad_norm": 0.10832629352807999,
      "learning_rate": 2e-07,
      "loss": -0.0003,
      "step": 198
    },
    {
      "clip_ratio/high_max": 0.0018588646562420763,
      "clip_ratio/high_mean": 0.0008382239229831612,
      "clip_ratio/low_mean": 0.0006132038415671559,
      "clip_ratio/low_min": 3.903640526914387e-05,
      "clip_ratio/region_mean": 0.0014514277936541475,
      "epoch": 0.018573286900116084,
      "grad_norm": 0.13379481434822083,
      "learning_rate": 2e-07,
      "loss": 0.0241,
      "step": 199
    },
    {
      "clip_ratio/high_max": 0.0018978752123075537,
      "clip_ratio/high_mean": 0.0008271708757092711,
      "clip_ratio/low_mean": 0.0005572783848037943,
      "clip_ratio/low_min": 7.607373572682263e-05,
      "clip_ratio/region_mean": 0.0013844492386851925,
      "epoch": 0.018666620000116665,
      "grad_norm": 0.12732315063476562,
      "learning_rate": 2e-07,
      "loss": 0.0319,
      "step": 200
    },
    {
      "clip_ratio/high_max": 0.0018908710262621753,
      "clip_ratio/high_mean": 0.0008043178959269426,
      "clip_ratio/low_mean": 0.0006495732359326212,
      "clip_ratio/low_min": 6.671647952316562e-06,
      "clip_ratio/region_mean": 0.0014538910872943234,
      "epoch": 0.01875995310011725,
      "grad_norm": 0.1388690173625946,
      "learning_rate": 2e-07,
      "loss": 0.0744,
      "step": 201
    },
    {
      "clip_ratio/high_max": 0.0022086134558776394,
      "clip_ratio/high_mean": 0.0010252107313135639,
      "clip_ratio/low_mean": 0.0006244538890314288,
      "clip_ratio/low_min": 8.090225765045034e-05,
      "clip_ratio/region_mean": 0.0016496646276209503,
      "epoch": 0.018853286200117832,
      "grad_norm": 0.13050539791584015,
      "learning_rate": 2e-07,
      "loss": 0.0184,
      "step": 202
    },
    {
      "clip_ratio/high_max": 0.0024375929788220674,
      "clip_ratio/high_mean": 0.0008924123594624689,
      "clip_ratio/low_mean": 0.0006478424302258645,
      "clip_ratio/low_min": 8.190616108549875e-05,
      "clip_ratio/region_mean": 0.0015402547833218705,
      "epoch": 0.018946619300118418,
      "grad_norm": 0.12808597087860107,
      "learning_rate": 2e-07,
      "loss": 0.0373,
      "step": 203
    },
    {
      "clip_ratio/high_max": 0.002246012882096693,
      "clip_ratio/high_mean": 0.0009331771743745776,
      "clip_ratio/low_mean": 0.0006590158027393045,
      "clip_ratio/low_min": 5.869673532288289e-05,
      "clip_ratio/region_mean": 0.0015921929807518609,
      "epoch": 0.019039952400119,
      "grad_norm": 0.12071757018566132,
      "learning_rate": 2e-07,
      "loss": 0.0255,
      "step": 204
    },
    {
      "clip_ratio/high_max": 0.0019939406774938107,
      "clip_ratio/high_mean": 0.000842538730466913,
      "clip_ratio/low_mean": 0.000595607759350969,
      "clip_ratio/low_min": 3.1035665415402036e-05,
      "clip_ratio/region_mean": 0.0014381464861799031,
      "epoch": 0.019133285500119585,
      "grad_norm": 0.14199955761432648,
      "learning_rate": 2e-07,
      "loss": 0.0055,
      "step": 205
    },
    {
      "clip_ratio/high_max": 0.0021363764099078253,
      "clip_ratio/high_mean": 0.0007927258275230997,
      "clip_ratio/low_mean": 0.0005810762522742152,
      "clip_ratio/low_min": 2.1845507944817655e-05,
      "clip_ratio/region_mean": 0.0013738020788878202,
      "epoch": 0.019226618600120166,
      "grad_norm": 0.12020599842071533,
      "learning_rate": 2e-07,
      "loss": -0.0025,
      "step": 206
    },
    {
      "clip_ratio/high_max": 0.0020698091757367365,
      "clip_ratio/high_mean": 0.0008564557629142655,
      "clip_ratio/low_mean": 0.0006409840661945054,
      "clip_ratio/low_min": 6.717782616760815e-05,
      "clip_ratio/region_mean": 0.0014974398145568557,
      "epoch": 0.019319951700120748,
      "grad_norm": 0.11984051764011383,
      "learning_rate": 2e-07,
      "loss": 0.0589,
      "step": 207
    },
    {
      "clip_ratio/high_max": 0.0018970263517985586,
      "clip_ratio/high_mean": 0.0008585091727582039,
      "clip_ratio/low_mean": 0.0006195463920448674,
      "clip_ratio/low_min": 7.11634302206221e-05,
      "clip_ratio/region_mean": 0.0014780555866309442,
      "epoch": 0.019413284800121333,
      "grad_norm": 0.11766231060028076,
      "learning_rate": 2e-07,
      "loss": 0.0307,
      "step": 208
    },
    {
      "clip_ratio/high_max": 0.0020743853601743467,
      "clip_ratio/high_mean": 0.000938547178520821,
      "clip_ratio/low_mean": 0.0005018305428166059,
      "clip_ratio/low_min": 1.1007397006324027e-05,
      "clip_ratio/region_mean": 0.0014403777313418686,
      "epoch": 0.019506617900121915,
      "grad_norm": 0.17046383023262024,
      "learning_rate": 2e-07,
      "loss": -0.0306,
      "step": 209
    },
    {
      "clip_ratio/high_max": 0.0023688607616350055,
      "clip_ratio/high_mean": 0.0009493983488937374,
      "clip_ratio/low_mean": 0.0006116517097325413,
      "clip_ratio/low_min": 7.67191659178934e-05,
      "clip_ratio/region_mean": 0.0015610500631737523,
      "epoch": 0.0195999510001225,
      "grad_norm": 0.12418784201145172,
      "learning_rate": 2e-07,
      "loss": 0.004,
      "step": 210
    },
    {
      "clip_ratio/high_max": 0.0020592273795045912,
      "clip_ratio/high_mean": 0.0008802560405456461,
      "clip_ratio/low_mean": 0.0005679554888047278,
      "clip_ratio/low_min": 8.43796442495659e-06,
      "clip_ratio/region_mean": 0.001448211547540268,
      "epoch": 0.019693284100123082,
      "grad_norm": 0.12844562530517578,
      "learning_rate": 2e-07,
      "loss": -0.0161,
      "step": 211
    },
    {
      "clip_ratio/high_max": 0.0016921541209740099,
      "clip_ratio/high_mean": 0.0006915236772329081,
      "clip_ratio/low_mean": 0.0005233117135503562,
      "clip_ratio/low_min": 1.605445686436724e-05,
      "clip_ratio/region_mean": 0.0012148354035161901,
      "epoch": 0.019786617200123667,
      "grad_norm": 0.11651170998811722,
      "learning_rate": 2e-07,
      "loss": 0.0371,
      "step": 212
    },
    {
      "clip_ratio/high_max": 0.002091900125378743,
      "clip_ratio/high_mean": 0.000989441541605629,
      "clip_ratio/low_mean": 0.0005216923248099192,
      "clip_ratio/low_min": 4.924762106384151e-05,
      "clip_ratio/region_mean": 0.0015111338761926163,
      "epoch": 0.01987995030012425,
      "grad_norm": 0.1365940421819687,
      "learning_rate": 2e-07,
      "loss": -0.0398,
      "step": 213
    },
    {
      "clip_ratio/high_max": 0.0019792670027527492,
      "clip_ratio/high_mean": 0.0008368796552531421,
      "clip_ratio/low_mean": 0.0006006825406075222,
      "clip_ratio/low_min": 8.510277257300913e-05,
      "clip_ratio/region_mean": 0.0014375622085935902,
      "epoch": 0.019973283400124834,
      "grad_norm": 0.12004130333662033,
      "learning_rate": 2e-07,
      "loss": 0.0118,
      "step": 214
    },
    {
      "clip_ratio/high_max": 0.0021902737134951167,
      "clip_ratio/high_mean": 0.000975384384219069,
      "clip_ratio/low_mean": 0.0005957031271464075,
      "clip_ratio/low_min": 1.4733615898876451e-05,
      "clip_ratio/region_mean": 0.00157108751591295,
      "epoch": 0.020066616500125416,
      "grad_norm": 0.1309654414653778,
      "learning_rate": 2e-07,
      "loss": -0.0069,
      "step": 215
    },
    {
      "clip_ratio/high_max": 0.0023474106055800803,
      "clip_ratio/high_mean": 0.0009294964311266085,
      "clip_ratio/low_mean": 0.0005873216287000105,
      "clip_ratio/low_min": 3.043337164854165e-05,
      "clip_ratio/region_mean": 0.001516818068921566,
      "epoch": 0.020159949600126,
      "grad_norm": 0.1190454363822937,
      "learning_rate": 2e-07,
      "loss": 0.0231,
      "step": 216
    },
    {
      "clip_ratio/high_max": 0.0019075889940722845,
      "clip_ratio/high_mean": 0.0007962704221426975,
      "clip_ratio/low_mean": 0.0006732344918418676,
      "clip_ratio/low_min": 3.263189910285291e-05,
      "clip_ratio/region_mean": 0.0014695049176225439,
      "epoch": 0.020253282700126583,
      "grad_norm": 0.11360644549131393,
      "learning_rate": 2e-07,
      "loss": 0.0529,
      "step": 217
    },
    {
      "clip_ratio/high_max": 0.002196177352743689,
      "clip_ratio/high_mean": 0.000924994150409475,
      "clip_ratio/low_mean": 0.0006425815399779822,
      "clip_ratio/low_min": 4.389654623082606e-05,
      "clip_ratio/region_mean": 0.0015675757022108883,
      "epoch": 0.020346615800127168,
      "grad_norm": 0.1343088448047638,
      "learning_rate": 2e-07,
      "loss": 0.019,
      "step": 218
    },
    {
      "clip_ratio/high_max": 0.002262892019643914,
      "clip_ratio/high_mean": 0.0008878271401044913,
      "clip_ratio/low_mean": 0.0006303579539235216,
      "clip_ratio/low_min": 7.65380800658022e-05,
      "clip_ratio/region_mean": 0.0015181850831140764,
      "epoch": 0.02043994890012775,
      "grad_norm": 0.1264265477657318,
      "learning_rate": 2e-07,
      "loss": 0.0236,
      "step": 219
    },
    {
      "clip_ratio/high_max": 0.0021603289133054204,
      "clip_ratio/high_mean": 0.0009070491578313522,
      "clip_ratio/low_mean": 0.000757922709453851,
      "clip_ratio/low_min": 4.2304596718167886e-05,
      "clip_ratio/region_mean": 0.001664971852733288,
      "epoch": 0.02053328200012833,
      "grad_norm": 0.12694722414016724,
      "learning_rate": 2e-07,
      "loss": 0.0311,
      "step": 220
    },
    {
      "clip_ratio/high_max": 0.0022762834596505854,
      "clip_ratio/high_mean": 0.0009774646732694237,
      "clip_ratio/low_mean": 0.0006077966099837795,
      "clip_ratio/low_min": 2.3159584088716656e-05,
      "clip_ratio/region_mean": 0.0015852612705202773,
      "epoch": 0.020626615100128916,
      "grad_norm": 0.12244313955307007,
      "learning_rate": 2e-07,
      "loss": -0.019,
      "step": 221
    },
    {
      "clip_ratio/high_max": 0.002211397029896034,
      "clip_ratio/high_mean": 0.0009040622499014717,
      "clip_ratio/low_mean": 0.0006667512880085269,
      "clip_ratio/low_min": 7.68256049923366e-05,
      "clip_ratio/region_mean": 0.0015708135033491999,
      "epoch": 0.020719948200129498,
      "grad_norm": 0.13032586872577667,
      "learning_rate": 2e-07,
      "loss": 0.0241,
      "step": 222
    },
    {
      "clip_ratio/high_max": 0.002108948800014332,
      "clip_ratio/high_mean": 0.0008103989730443573,
      "clip_ratio/low_mean": 0.000653546971079777,
      "clip_ratio/low_min": 6.348203896777704e-05,
      "clip_ratio/region_mean": 0.0014639459222962614,
      "epoch": 0.020813281300130083,
      "grad_norm": 0.12284176796674728,
      "learning_rate": 2e-07,
      "loss": 0.0439,
      "step": 223
    },
    {
      "clip_ratio/high_max": 0.00211102441244293,
      "clip_ratio/high_mean": 0.0007945753404783318,
      "clip_ratio/low_mean": 0.0006232873874978395,
      "clip_ratio/low_min": 4.631489900930319e-05,
      "clip_ratio/region_mean": 0.0014178627243381925,
      "epoch": 0.020906614400130665,
      "grad_norm": 0.11898179352283478,
      "learning_rate": 2e-07,
      "loss": 0.0375,
      "step": 224
    },
    {
      "clip_ratio/high_max": 0.002252078615128994,
      "clip_ratio/high_mean": 0.0009375910904054763,
      "clip_ratio/low_mean": 0.0006963056184758898,
      "clip_ratio/low_min": 8.316086405102396e-05,
      "clip_ratio/region_mean": 0.0016338967507181223,
      "epoch": 0.02099994750013125,
      "grad_norm": 0.12768003344535828,
      "learning_rate": 2e-07,
      "loss": 0.0252,
      "step": 225
    },
    {
      "clip_ratio/high_max": 0.002265541013912298,
      "clip_ratio/high_mean": 0.0008136722208291758,
      "clip_ratio/low_mean": 0.0006160023294796702,
      "clip_ratio/low_min": 4.2888646476058057e-05,
      "clip_ratio/region_mean": 0.0014296745357569307,
      "epoch": 0.021093280600131832,
      "grad_norm": 0.11961844563484192,
      "learning_rate": 2e-07,
      "loss": 0.0348,
      "step": 226
    },
    {
      "clip_ratio/high_max": 0.0019697210809681565,
      "clip_ratio/high_mean": 0.0008097562622424448,
      "clip_ratio/low_mean": 0.0006163530852063559,
      "clip_ratio/low_min": 1.7831669538281858e-05,
      "clip_ratio/region_mean": 0.001426109352905769,
      "epoch": 0.021186613700132417,
      "grad_norm": 0.12004849314689636,
      "learning_rate": 2e-07,
      "loss": 0.0196,
      "step": 227
    },
    {
      "clip_ratio/high_max": 0.002094672596285818,
      "clip_ratio/high_mean": 0.0008744771039346233,
      "clip_ratio/low_mean": 0.0006770050185878063,
      "clip_ratio/low_min": 7.927943534014048e-05,
      "clip_ratio/region_mean": 0.0015514821570832282,
      "epoch": 0.021279946800133,
      "grad_norm": 0.12620028853416443,
      "learning_rate": 2e-07,
      "loss": 0.0378,
      "step": 228
    },
    {
      "clip_ratio/high_max": 0.001894623928819783,
      "clip_ratio/high_mean": 0.0008117662764561828,
      "clip_ratio/low_mean": 0.000755739845772041,
      "clip_ratio/low_min": 9.920384854922304e-05,
      "clip_ratio/region_mean": 0.0015675060858484358,
      "epoch": 0.021373279900133584,
      "grad_norm": 0.12599003314971924,
      "learning_rate": 2e-07,
      "loss": 0.0801,
      "step": 229
    },
    {
      "clip_ratio/high_max": 0.0024509444119757973,
      "clip_ratio/high_mean": 0.0009406036078871693,
      "clip_ratio/low_mean": 0.0006328536401269957,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0015734572552901227,
      "epoch": 0.021466613000134166,
      "grad_norm": 0.1274123638868332,
      "learning_rate": 2e-07,
      "loss": -0.0088,
      "step": 230
    },
    {
      "clip_ratio/high_max": 0.002168775081372587,
      "clip_ratio/high_mean": 0.000913401207071729,
      "clip_ratio/low_mean": 0.0006764365334674949,
      "clip_ratio/low_min": 2.962235430459259e-05,
      "clip_ratio/region_mean": 0.0015898377751000226,
      "epoch": 0.02155994610013475,
      "grad_norm": 0.12550295889377594,
      "learning_rate": 2e-07,
      "loss": 0.0083,
      "step": 231
    },
    {
      "clip_ratio/high_max": 0.0023953377967700362,
      "clip_ratio/high_mean": 0.0009201346529152943,
      "clip_ratio/low_mean": 0.0005647012367262505,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014848358841845766,
      "epoch": 0.021653279200135333,
      "grad_norm": 0.12987202405929565,
      "learning_rate": 2e-07,
      "loss": 0.0124,
      "step": 232
    },
    {
      "clip_ratio/high_max": 0.0022483248612843454,
      "clip_ratio/high_mean": 0.0009150952646450605,
      "clip_ratio/low_mean": 0.0006199993486006861,
      "clip_ratio/low_min": 7.445794835803099e-06,
      "clip_ratio/region_mean": 0.0015350945977843367,
      "epoch": 0.021746612300135915,
      "grad_norm": 0.12124481052160263,
      "learning_rate": 2e-07,
      "loss": 0.0006,
      "step": 233
    },
    {
      "clip_ratio/high_max": 0.0023239919464685954,
      "clip_ratio/high_mean": 0.0009098473856283817,
      "clip_ratio/low_mean": 0.0007513733671657974,
      "clip_ratio/low_min": 3.521126927807927e-05,
      "clip_ratio/region_mean": 0.001661220765527105,
      "epoch": 0.0218399454001365,
      "grad_norm": 0.1301000863313675,
      "learning_rate": 2e-07,
      "loss": 0.0346,
      "step": 234
    },
    {
      "clip_ratio/high_max": 0.0019248932585469447,
      "clip_ratio/high_mean": 0.0007889168855399475,
      "clip_ratio/low_mean": 0.0006668601799901808,
      "clip_ratio/low_min": 5.919584600633243e-05,
      "clip_ratio/region_mean": 0.0014557770737155806,
      "epoch": 0.02193327850013708,
      "grad_norm": 0.1178794875741005,
      "learning_rate": 2e-07,
      "loss": 0.0583,
      "step": 235
    },
    {
      "clip_ratio/high_max": 0.002305488622369012,
      "clip_ratio/high_mean": 0.0008776024496910395,
      "clip_ratio/low_mean": 0.0006285295276029501,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0015061319572851062,
      "epoch": 0.022026611600137667,
      "grad_norm": 0.13015718758106232,
      "learning_rate": 2e-07,
      "loss": 0.0349,
      "step": 236
    },
    {
      "clip_ratio/high_max": 0.0018065210570057388,
      "clip_ratio/high_mean": 0.0007725634404778248,
      "clip_ratio/low_mean": 0.000714817699190462,
      "clip_ratio/low_min": 7.064191595418379e-05,
      "clip_ratio/region_mean": 0.0014873811414872762,
      "epoch": 0.02211994470013825,
      "grad_norm": 0.12058298289775848,
      "learning_rate": 2e-07,
      "loss": 0.0614,
      "step": 237
    },
    {
      "clip_ratio/high_max": 0.0021439868505694903,
      "clip_ratio/high_mean": 0.0009421758077223785,
      "clip_ratio/low_mean": 0.0006501825992017984,
      "clip_ratio/low_min": 5.7884625221049646e-05,
      "clip_ratio/region_mean": 0.0015923583996482193,
      "epoch": 0.022213277800138834,
      "grad_norm": 0.12698669731616974,
      "learning_rate": 2e-07,
      "loss": 0.0132,
      "step": 238
    },
    {
      "clip_ratio/high_max": 0.0018056137632811442,
      "clip_ratio/high_mean": 0.0007831873281247681,
      "clip_ratio/low_mean": 0.0007068192389851902,
      "clip_ratio/low_min": 6.146418309072033e-05,
      "clip_ratio/region_mean": 0.0014900065507390536,
      "epoch": 0.022306610900139415,
      "grad_norm": 0.1340022087097168,
      "learning_rate": 2e-07,
      "loss": 0.0789,
      "step": 239
    },
    {
      "clip_ratio/high_max": 0.0019963944105256815,
      "clip_ratio/high_mean": 0.0008376951664104126,
      "clip_ratio/low_mean": 0.000524087370649795,
      "clip_ratio/low_min": 1.9165900084772147e-05,
      "clip_ratio/region_mean": 0.0013617825279652607,
      "epoch": 0.02239994400014,
      "grad_norm": 0.11847320944070816,
      "learning_rate": 2e-07,
      "loss": -0.0115,
      "step": 240
    },
    {
      "clip_ratio/high_max": 0.0018225862440885976,
      "clip_ratio/high_mean": 0.0007996987224032637,
      "clip_ratio/low_mean": 0.0006301447447185637,
      "clip_ratio/low_min": 8.690410140843596e-05,
      "clip_ratio/region_mean": 0.0014298434434749652,
      "epoch": 0.022493277100140582,
      "grad_norm": 0.11881936341524124,
      "learning_rate": 2e-07,
      "loss": 0.0153,
      "step": 241
    },
    {
      "clip_ratio/high_max": 0.0022151446355564985,
      "clip_ratio/high_mean": 0.0008623783942312002,
      "clip_ratio/low_mean": 0.0007498102095269132,
      "clip_ratio/low_min": 6.236381432245253e-05,
      "clip_ratio/region_mean": 0.001612188592844177,
      "epoch": 0.022586610200141168,
      "grad_norm": 0.12661243975162506,
      "learning_rate": 2e-07,
      "loss": 0.0523,
      "step": 242
    },
    {
      "clip_ratio/high_max": 0.0022538316989084706,
      "clip_ratio/high_mean": 0.0009073834698938299,
      "clip_ratio/low_mean": 0.0006987808628764469,
      "clip_ratio/low_min": 8.240480292442953e-05,
      "clip_ratio/region_mean": 0.0016061643327702768,
      "epoch": 0.02267994330014175,
      "grad_norm": 0.12892471253871918,
      "learning_rate": 2e-07,
      "loss": -0.001,
      "step": 243
    },
    {
      "clip_ratio/high_max": 0.001967452837561723,
      "clip_ratio/high_mean": 0.0009143860334006604,
      "clip_ratio/low_mean": 0.000711192606104305,
      "clip_ratio/low_min": 8.397249530389672e-05,
      "clip_ratio/region_mean": 0.001625578646780923,
      "epoch": 0.022773276400142334,
      "grad_norm": 0.13051381707191467,
      "learning_rate": 2e-07,
      "loss": 0.0363,
      "step": 244
    },
    {
      "clip_ratio/high_max": 0.0019133603418595158,
      "clip_ratio/high_mean": 0.0009222814060194651,
      "clip_ratio/low_mean": 0.0006695762713206932,
      "clip_ratio/low_min": 8.68677007019869e-05,
      "clip_ratio/region_mean": 0.0015918576791591477,
      "epoch": 0.022866609500142916,
      "grad_norm": 0.1326800286769867,
      "learning_rate": 2e-07,
      "loss": 0.0302,
      "step": 245
    },
    {
      "clip_ratio/high_max": 0.0018020188254013192,
      "clip_ratio/high_mean": 0.0008461367906420492,
      "clip_ratio/low_mean": 0.0006817813409725204,
      "clip_ratio/low_min": 4.238460496708285e-05,
      "clip_ratio/region_mean": 0.0015279181388905272,
      "epoch": 0.022959942600143498,
      "grad_norm": 0.13283300399780273,
      "learning_rate": 2e-07,
      "loss": 0.038,
      "step": 246
    },
    {
      "clip_ratio/high_max": 0.0017917208351718727,
      "clip_ratio/high_mean": 0.0007762907625874504,
      "clip_ratio/low_mean": 0.0007857133132347371,
      "clip_ratio/low_min": 0.00012034440169372829,
      "clip_ratio/region_mean": 0.0015620040830981452,
      "epoch": 0.023053275700144083,
      "grad_norm": 0.12876766920089722,
      "learning_rate": 2e-07,
      "loss": 0.0771,
      "step": 247
    },
    {
      "clip_ratio/high_max": 0.0019660468969959766,
      "clip_ratio/high_mean": 0.0008463696940452792,
      "clip_ratio/low_mean": 0.0006220601255790825,
      "clip_ratio/low_min": 0.00011619218639680184,
      "clip_ratio/region_mean": 0.0014684298184874933,
      "epoch": 0.023146608800144665,
      "grad_norm": 0.1330253779888153,
      "learning_rate": 2e-07,
      "loss": 0.0379,
      "step": 248
    },
    {
      "clip_ratio/high_max": 0.0020015579539176542,
      "clip_ratio/high_mean": 0.0009329316962976009,
      "clip_ratio/low_mean": 0.0006521208051708527,
      "clip_ratio/low_min": 2.6911314762401162e-05,
      "clip_ratio/region_mean": 0.001585052494192496,
      "epoch": 0.02323994190014525,
      "grad_norm": 0.1300746500492096,
      "learning_rate": 2e-07,
      "loss": 0.0627,
      "step": 249
    },
    {
      "clip_ratio/high_max": 0.0021018820552853867,
      "clip_ratio/high_mean": 0.0008103759328150772,
      "clip_ratio/low_mean": 0.0006727500585839152,
      "clip_ratio/low_min": 2.696406954783015e-05,
      "clip_ratio/region_mean": 0.0014831259759375826,
      "epoch": 0.023333275000145832,
      "grad_norm": 0.12445419281721115,
      "learning_rate": 2e-07,
      "loss": 0.0522,
      "step": 250
    },
    {
      "clip_ratio/high_max": 0.0021770705752715003,
      "clip_ratio/high_mean": 0.000824666729386081,
      "clip_ratio/low_mean": 0.0006186014716149657,
      "clip_ratio/low_min": 4.268763132131426e-05,
      "clip_ratio/region_mean": 0.0014432682219194248,
      "epoch": 0.023426608100146417,
      "grad_norm": 0.11207612603902817,
      "learning_rate": 2e-07,
      "loss": 0.0217,
      "step": 251
    },
    {
      "clip_ratio/high_max": 0.002213042385847075,
      "clip_ratio/high_mean": 0.0009350182481284719,
      "clip_ratio/low_mean": 0.0006762640168744838,
      "clip_ratio/low_min": 2.5805120458244346e-05,
      "clip_ratio/region_mean": 0.0016112822813738603,
      "epoch": 0.023519941200147,
      "grad_norm": 0.1253548264503479,
      "learning_rate": 2e-07,
      "loss": -0.0054,
      "step": 252
    },
    {
      "clip_ratio/high_max": 0.0018784883941407315,
      "clip_ratio/high_mean": 0.0007941289841255639,
      "clip_ratio/low_mean": 0.0006680781734758057,
      "clip_ratio/low_min": 1.177246213046601e-05,
      "clip_ratio/region_mean": 0.0014622071612393484,
      "epoch": 0.023613274300147584,
      "grad_norm": 0.5220147967338562,
      "learning_rate": 2e-07,
      "loss": 0.0434,
      "step": 253
    },
    {
      "clip_ratio/high_max": 0.0024451772187603638,
      "clip_ratio/high_mean": 0.0009733298647915944,
      "clip_ratio/low_mean": 0.0007166906198108336,
      "clip_ratio/low_min": 8.868995791999623e-05,
      "clip_ratio/region_mean": 0.0016900204645935446,
      "epoch": 0.023706607400148166,
      "grad_norm": 0.12459203600883484,
      "learning_rate": 2e-07,
      "loss": 0.0523,
      "step": 254
    },
    {
      "clip_ratio/high_max": 0.001992321362195071,
      "clip_ratio/high_mean": 0.0008766978153289529,
      "clip_ratio/low_mean": 0.0006099466163504985,
      "clip_ratio/low_min": 1.991079989238642e-05,
      "clip_ratio/region_mean": 0.001486644414399052,
      "epoch": 0.02379994050014875,
      "grad_norm": 0.13075274229049683,
      "learning_rate": 2e-07,
      "loss": 0.0133,
      "step": 255
    },
    {
      "clip_ratio/high_max": 0.002099009267112706,
      "clip_ratio/high_mean": 0.0009792022465262562,
      "clip_ratio/low_mean": 0.0005995883657305967,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0015787906158948317,
      "epoch": 0.023893273600149333,
      "grad_norm": 0.12362360209226608,
      "learning_rate": 2e-07,
      "loss": -0.0122,
      "step": 256
    },
    {
      "clip_ratio/high_max": 0.001869269890448777,
      "clip_ratio/high_mean": 0.0007553544837719528,
      "clip_ratio/low_mean": 0.0005070197767054196,
      "clip_ratio/low_min": 2.2053752218198497e-05,
      "clip_ratio/region_mean": 0.0012623742550204042,
      "completions/clipped_ratio": 0.014761788504464302,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4093.0,
      "completions/mean_length": 621.0927734375,
      "completions/mean_terminated_length": 569.0284423828125,
      "completions/min_length": 20.0,
      "completions/min_terminated_length": 20.0,
      "epoch": 0.023986606700149918,
      "grad_norm": 0.11561097949743271,
      "learning_rate": 2e-07,
      "loss": -0.0013,
      "num_tokens": 244656625.0,
      "reward": 0.5687430500984192,
      "reward_std": 0.19936078786849976,
      "rewards/simpleverify_reward/mean": 0.5687430500984192,
      "rewards/simpleverify_reward/std": 0.4952539801597595,
      "step": 257
    },
    {
      "clip_ratio/high_max": 0.0019854989732266404,
      "clip_ratio/high_mean": 0.0007974641721375519,
      "clip_ratio/low_mean": 0.0005593140012933873,
      "clip_ratio/low_min": 8.648782022646628e-05,
      "clip_ratio/region_mean": 0.0013567781716119498,
      "epoch": 0.0240799398001505,
      "grad_norm": 0.1243252232670784,
      "learning_rate": 2e-07,
      "loss": 0.0187,
      "step": 258
    },
    {
      "clip_ratio/high_max": 0.0016719138839107472,
      "clip_ratio/high_mean": 0.0007781998083373765,
      "clip_ratio/low_mean": 0.00047932440702425083,
      "clip_ratio/low_min": 7.351211479544872e-06,
      "clip_ratio/region_mean": 0.0012575241962622385,
      "epoch": 0.02417327290015108,
      "grad_norm": 0.2903256118297577,
      "learning_rate": 2e-07,
      "loss": -0.002,
      "step": 259
    },
    {
      "clip_ratio/high_max": 0.001957925262104254,
      "clip_ratio/high_mean": 0.0007761007163935574,
      "clip_ratio/low_mean": 0.000615967179328436,
      "clip_ratio/low_min": 1.0657345228537451e-05,
      "clip_ratio/region_mean": 0.0013920679084549192,
      "epoch": 0.024266606000151666,
      "grad_norm": 0.12541061639785767,
      "learning_rate": 2e-07,
      "loss": 0.0234,
      "step": 260
    },
    {
      "clip_ratio/high_max": 0.001798011990103987,
      "clip_ratio/high_mean": 0.0006852715532659204,
      "clip_ratio/low_mean": 0.0004933090949634789,
      "clip_ratio/low_min": 4.658103716792539e-05,
      "clip_ratio/region_mean": 0.0011785806746047456,
      "epoch": 0.024359939100152248,
      "grad_norm": 0.1138421967625618,
      "learning_rate": 2e-07,
      "loss": 0.0117,
      "step": 261
    },
    {
      "clip_ratio/high_max": 0.0017228373762918636,
      "clip_ratio/high_mean": 0.0006643414053542074,
      "clip_ratio/low_mean": 0.000559452207198774,
      "clip_ratio/low_min": 3.1677656807005405e-05,
      "clip_ratio/region_mean": 0.0012237936098244973,
      "epoch": 0.024453272200152833,
      "grad_norm": 0.10744740813970566,
      "learning_rate": 2e-07,
      "loss": 0.0388,
      "step": 262
    },
    {
      "clip_ratio/high_max": 0.0017706188336887863,
      "clip_ratio/high_mean": 0.0006612868101001368,
      "clip_ratio/low_mean": 0.0005929264798396616,
      "clip_ratio/low_min": 3.248440771130845e-05,
      "clip_ratio/region_mean": 0.0012542132753878832,
      "epoch": 0.024546605300153415,
      "grad_norm": 0.1202259212732315,
      "learning_rate": 2e-07,
      "loss": 0.0312,
      "step": 263
    },
    {
      "clip_ratio/high_max": 0.0015295374068955425,
      "clip_ratio/high_mean": 0.0006629402414546348,
      "clip_ratio/low_mean": 0.00047803110737731913,
      "clip_ratio/low_min": 5.417177453637123e-05,
      "clip_ratio/region_mean": 0.0011409713224566076,
      "epoch": 0.024639938400154,
      "grad_norm": 0.10814613103866577,
      "learning_rate": 2e-07,
      "loss": 0.037,
      "step": 264
    },
    {
      "clip_ratio/high_max": 0.0019400609708100092,
      "clip_ratio/high_mean": 0.0007856115789763862,
      "clip_ratio/low_mean": 0.0005478906596181332,
      "clip_ratio/low_min": 4.0669911868462805e-05,
      "clip_ratio/region_mean": 0.001333502215857152,
      "epoch": 0.024733271500154582,
      "grad_norm": 0.12329860776662827,
      "learning_rate": 2e-07,
      "loss": -0.007,
      "step": 265
    },
    {
      "clip_ratio/high_max": 0.001895403016533237,
      "clip_ratio/high_mean": 0.0007664403710805345,
      "clip_ratio/low_mean": 0.0006475420977949398,
      "clip_ratio/low_min": 5.263374896458117e-05,
      "clip_ratio/region_mean": 0.001413982427038718,
      "epoch": 0.024826604600155167,
      "grad_norm": 0.12039011716842651,
      "learning_rate": 2e-07,
      "loss": 0.0695,
      "step": 266
    },
    {
      "clip_ratio/high_max": 0.0016763722815085202,
      "clip_ratio/high_mean": 0.0008385848814214114,
      "clip_ratio/low_mean": 0.0005155388389539439,
      "clip_ratio/low_min": 4.5927168685011566e-05,
      "clip_ratio/region_mean": 0.0013541237312892918,
      "epoch": 0.02491993770015575,
      "grad_norm": 0.10723930597305298,
      "learning_rate": 2e-07,
      "loss": 0.0061,
      "step": 267
    },
    {
      "clip_ratio/high_max": 0.0018994116835528985,
      "clip_ratio/high_mean": 0.0006988602644923958,
      "clip_ratio/low_mean": 0.0005986795495118713,
      "clip_ratio/low_min": 3.375337473698892e-05,
      "clip_ratio/region_mean": 0.0012975398312846664,
      "epoch": 0.025013270800156334,
      "grad_norm": 0.11861869692802429,
      "learning_rate": 2e-07,
      "loss": 0.0176,
      "step": 268
    },
    {
      "clip_ratio/high_max": 0.002124772989191115,
      "clip_ratio/high_mean": 0.0007490121952287154,
      "clip_ratio/low_mean": 0.0005637270305669517,
      "clip_ratio/low_min": 3.450834901741473e-05,
      "clip_ratio/region_mean": 0.0013127392194292042,
      "epoch": 0.025106603900156916,
      "grad_norm": 0.12164826691150665,
      "learning_rate": 2e-07,
      "loss": -0.006,
      "step": 269
    },
    {
      "clip_ratio/high_max": 0.0016789172404969577,
      "clip_ratio/high_mean": 0.0007443660251738038,
      "clip_ratio/low_mean": 0.0005670521550200647,
      "clip_ratio/low_min": 4.031072785437573e-05,
      "clip_ratio/region_mean": 0.0013114181820128579,
      "epoch": 0.0251999370001575,
      "grad_norm": 0.1176343485713005,
      "learning_rate": 2e-07,
      "loss": -0.0064,
      "step": 270
    },
    {
      "clip_ratio/high_max": 0.0015200042435026262,
      "clip_ratio/high_mean": 0.0006772066226403695,
      "clip_ratio/low_mean": 0.0005106960088596679,
      "clip_ratio/low_min": 2.700678578548832e-05,
      "clip_ratio/region_mean": 0.0011879026351380162,
      "epoch": 0.025293270100158083,
      "grad_norm": 0.10999931395053864,
      "learning_rate": 2e-07,
      "loss": 0.0421,
      "step": 271
    },
    {
      "clip_ratio/high_max": 0.002017531413002871,
      "clip_ratio/high_mean": 0.0008346976010216167,
      "clip_ratio/low_mean": 0.0005491766050909064,
      "clip_ratio/low_min": 5.048585626354907e-05,
      "clip_ratio/region_mean": 0.0013838742015650496,
      "epoch": 0.025386603200158665,
      "grad_norm": 0.12427344173192978,
      "learning_rate": 2e-07,
      "loss": 0.0225,
      "step": 272
    },
    {
      "clip_ratio/high_max": 0.0016355127081624232,
      "clip_ratio/high_mean": 0.0006829547037341399,
      "clip_ratio/low_mean": 0.0005896083912375616,
      "clip_ratio/low_min": 3.99093514715787e-05,
      "clip_ratio/region_mean": 0.0012725631022476591,
      "epoch": 0.02547993630015925,
      "grad_norm": 0.12157445400953293,
      "learning_rate": 2e-07,
      "loss": 0.0417,
      "step": 273
    },
    {
      "clip_ratio/high_max": 0.002293092074978631,
      "clip_ratio/high_mean": 0.0008798660164757166,
      "clip_ratio/low_mean": 0.0006503572803921998,
      "clip_ratio/low_min": 2.285192022100091e-05,
      "clip_ratio/region_mean": 0.0015302232495741919,
      "epoch": 0.02557326940015983,
      "grad_norm": 0.11832218617200851,
      "learning_rate": 2e-07,
      "loss": 0.0249,
      "step": 274
    },
    {
      "clip_ratio/high_max": 0.0018742052270681597,
      "clip_ratio/high_mean": 0.0008379823393624974,
      "clip_ratio/low_mean": 0.0006239262675080681,
      "clip_ratio/low_min": 6.075673991290387e-05,
      "clip_ratio/region_mean": 0.0014619086068705656,
      "epoch": 0.025666602500160417,
      "grad_norm": 0.11675229668617249,
      "learning_rate": 2e-07,
      "loss": 0.0438,
      "step": 275
    },
    {
      "clip_ratio/high_max": 0.002153520952560939,
      "clip_ratio/high_mean": 0.0007728609525656793,
      "clip_ratio/low_mean": 0.00061302209905989,
      "clip_ratio/low_min": 5.2356802370923106e-05,
      "clip_ratio/region_mean": 0.0013858830898243468,
      "epoch": 0.025759935600161,
      "grad_norm": 0.13468341529369354,
      "learning_rate": 2e-07,
      "loss": 0.0585,
      "step": 276
    },
    {
      "clip_ratio/high_max": 0.0017808724733185954,
      "clip_ratio/high_mean": 0.0006449294978665421,
      "clip_ratio/low_mean": 0.0005734244505219976,
      "clip_ratio/low_min": 2.304761619598139e-05,
      "clip_ratio/region_mean": 0.0012183539365651086,
      "epoch": 0.025853268700161584,
      "grad_norm": 0.1159195601940155,
      "learning_rate": 2e-07,
      "loss": 0.0783,
      "step": 277
    },
    {
      "clip_ratio/high_max": 0.0018481601946405135,
      "clip_ratio/high_mean": 0.0008243634620157536,
      "clip_ratio/low_mean": 0.0006029856831446523,
      "clip_ratio/low_min": 3.171281332470244e-05,
      "clip_ratio/region_mean": 0.00142734913242748,
      "epoch": 0.025946601800162165,
      "grad_norm": 0.12292173504829407,
      "learning_rate": 2e-07,
      "loss": 0.0196,
      "step": 278
    },
    {
      "clip_ratio/high_max": 0.0022643869488092605,
      "clip_ratio/high_mean": 0.0009244856701116078,
      "clip_ratio/low_mean": 0.0005498422669916181,
      "clip_ratio/low_min": 1.2386048183543608e-05,
      "clip_ratio/region_mean": 0.0014743279461981729,
      "epoch": 0.02603993490016275,
      "grad_norm": 0.11086355894804001,
      "learning_rate": 2e-07,
      "loss": -0.025,
      "step": 279
    },
    {
      "clip_ratio/high_max": 0.0020471166353672743,
      "clip_ratio/high_mean": 0.0008659021477797069,
      "clip_ratio/low_mean": 0.0005174417233320128,
      "clip_ratio/low_min": 1.4501159967039712e-05,
      "clip_ratio/region_mean": 0.0013833439043082763,
      "epoch": 0.026133268000163332,
      "grad_norm": 0.11316519230604172,
      "learning_rate": 2e-07,
      "loss": -0.0122,
      "step": 280
    },
    {
      "clip_ratio/high_max": 0.001924006577610271,
      "clip_ratio/high_mean": 0.0007099168178683612,
      "clip_ratio/low_mean": 0.0005460791708173929,
      "clip_ratio/low_min": 1.7977699826587923e-05,
      "clip_ratio/region_mean": 0.0012559959905047435,
      "epoch": 0.026226601100163918,
      "grad_norm": 0.11418233066797256,
      "learning_rate": 2e-07,
      "loss": 0.0407,
      "step": 281
    },
    {
      "clip_ratio/high_max": 0.0018654860323294997,
      "clip_ratio/high_mean": 0.0006909910862304969,
      "clip_ratio/low_mean": 0.0005937097366768285,
      "clip_ratio/low_min": 5.021708057029173e-05,
      "clip_ratio/region_mean": 0.001284700814721873,
      "epoch": 0.0263199342001645,
      "grad_norm": 0.11748393625020981,
      "learning_rate": 2e-07,
      "loss": 0.0488,
      "step": 282
    },
    {
      "clip_ratio/high_max": 0.002000603635678999,
      "clip_ratio/high_mean": 0.0008267343291663565,
      "clip_ratio/low_mean": 0.0005999288496241206,
      "clip_ratio/low_min": 7.297427600860829e-05,
      "clip_ratio/region_mean": 0.0014266631951613817,
      "epoch": 0.026413267300165084,
      "grad_norm": 0.12817393243312836,
      "learning_rate": 2e-07,
      "loss": 0.0094,
      "step": 283
    },
    {
      "clip_ratio/high_max": 0.0020890901796519756,
      "clip_ratio/high_mean": 0.0007941197418404045,
      "clip_ratio/low_mean": 0.0006186597793202964,
      "clip_ratio/low_min": 3.2501159239473054e-05,
      "clip_ratio/region_mean": 0.0014127795366221108,
      "epoch": 0.026506600400165666,
      "grad_norm": 0.11483299732208252,
      "learning_rate": 2e-07,
      "loss": 0.0202,
      "step": 284
    },
    {
      "clip_ratio/high_max": 0.001989562915696297,
      "clip_ratio/high_mean": 0.0007614011028636014,
      "clip_ratio/low_mean": 0.0005384645783124142,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012998657039133832,
      "epoch": 0.026599933500166248,
      "grad_norm": 0.12066849321126938,
      "learning_rate": 2e-07,
      "loss": -0.0087,
      "step": 285
    },
    {
      "clip_ratio/high_max": 0.0018384189170319587,
      "clip_ratio/high_mean": 0.0007701898084633285,
      "clip_ratio/low_mean": 0.0005567612979575642,
      "clip_ratio/low_min": 3.270080742368009e-05,
      "clip_ratio/region_mean": 0.001326951154624112,
      "epoch": 0.026693266600166833,
      "grad_norm": 0.11334282904863358,
      "learning_rate": 2e-07,
      "loss": 0.0134,
      "step": 286
    },
    {
      "clip_ratio/high_max": 0.0018156390724470839,
      "clip_ratio/high_mean": 0.0007659326784050791,
      "clip_ratio/low_mean": 0.0006194413454068126,
      "clip_ratio/low_min": 4.5179614062362816e-05,
      "clip_ratio/region_mean": 0.0013853740274498705,
      "epoch": 0.026786599700167415,
      "grad_norm": 0.1245957687497139,
      "learning_rate": 2e-07,
      "loss": 0.038,
      "step": 287
    },
    {
      "clip_ratio/high_max": 0.0019307895199744962,
      "clip_ratio/high_mean": 0.0007282035548996646,
      "clip_ratio/low_mean": 0.0005799779301014496,
      "clip_ratio/low_min": 1.5599001926602796e-05,
      "clip_ratio/region_mean": 0.001308181534113828,
      "epoch": 0.026879932800168,
      "grad_norm": 0.11065205931663513,
      "learning_rate": 2e-07,
      "loss": 0.0183,
      "step": 288
    },
    {
      "clip_ratio/high_max": 0.0016762155864853412,
      "clip_ratio/high_mean": 0.0006930882755113998,
      "clip_ratio/low_mean": 0.0006148903239591164,
      "clip_ratio/low_min": 5.532817067432916e-05,
      "clip_ratio/region_mean": 0.0013079785894660745,
      "epoch": 0.026973265900168582,
      "grad_norm": 0.10208636522293091,
      "learning_rate": 2e-07,
      "loss": 0.0828,
      "step": 289
    },
    {
      "clip_ratio/high_max": 0.0019060141748923343,
      "clip_ratio/high_mean": 0.0008040141065066564,
      "clip_ratio/low_mean": 0.0006279657500272151,
      "clip_ratio/low_min": 1.1474206075945403e-05,
      "clip_ratio/region_mean": 0.001431979766493896,
      "epoch": 0.027066599000169167,
      "grad_norm": 0.129505455493927,
      "learning_rate": 2e-07,
      "loss": 0.0046,
      "step": 290
    },
    {
      "clip_ratio/high_max": 0.001824366489017848,
      "clip_ratio/high_mean": 0.0008061655498750042,
      "clip_ratio/low_mean": 0.0006316633989627007,
      "clip_ratio/low_min": 1.6209748082474107e-05,
      "clip_ratio/region_mean": 0.0014378289561136626,
      "epoch": 0.02715993210016975,
      "grad_norm": 0.12492282688617706,
      "learning_rate": 2e-07,
      "loss": 0.031,
      "step": 291
    },
    {
      "clip_ratio/high_max": 0.0021610963594866917,
      "clip_ratio/high_mean": 0.0007835951673769159,
      "clip_ratio/low_mean": 0.0005685682899638778,
      "clip_ratio/low_min": 3.461108917690581e-05,
      "clip_ratio/region_mean": 0.0013521634646167513,
      "epoch": 0.027253265200170334,
      "grad_norm": 0.12403958290815353,
      "learning_rate": 2e-07,
      "loss": 0.0248,
      "step": 292
    },
    {
      "clip_ratio/high_max": 0.0020282550576666836,
      "clip_ratio/high_mean": 0.0007788134425936732,
      "clip_ratio/low_mean": 0.0006941737656234181,
      "clip_ratio/low_min": 7.969918806338683e-05,
      "clip_ratio/region_mean": 0.0014729871872987133,
      "epoch": 0.027346598300170916,
      "grad_norm": 0.11742532253265381,
      "learning_rate": 2e-07,
      "loss": 0.0258,
      "step": 293
    },
    {
      "clip_ratio/high_max": 0.00199810119374888,
      "clip_ratio/high_mean": 0.0007621298209414817,
      "clip_ratio/low_mean": 0.0006303685840975959,
      "clip_ratio/low_min": 5.319286719895899e-05,
      "clip_ratio/region_mean": 0.0013924984014010988,
      "epoch": 0.0274399314001715,
      "grad_norm": 0.11730988323688507,
      "learning_rate": 2e-07,
      "loss": 0.0623,
      "step": 294
    },
    {
      "clip_ratio/high_max": 0.0017734961038513575,
      "clip_ratio/high_mean": 0.0007222091408038978,
      "clip_ratio/low_mean": 0.0006572656675416511,
      "clip_ratio/low_min": 2.2484709916170686e-05,
      "clip_ratio/region_mean": 0.0013794747937936336,
      "epoch": 0.027533264500172083,
      "grad_norm": 0.11441951990127563,
      "learning_rate": 2e-07,
      "loss": 0.0486,
      "step": 295
    },
    {
      "clip_ratio/high_max": 0.001923352807352785,
      "clip_ratio/high_mean": 0.0007743161822872935,
      "clip_ratio/low_mean": 0.0006506190547952428,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014249352243496105,
      "epoch": 0.027626597600172668,
      "grad_norm": 0.10988679528236389,
      "learning_rate": 2e-07,
      "loss": 0.0228,
      "step": 296
    },
    {
      "clip_ratio/high_max": 0.0019848877855110914,
      "clip_ratio/high_mean": 0.0008030367553146789,
      "clip_ratio/low_mean": 0.0005408591969171539,
      "clip_ratio/low_min": 8.588704076828435e-06,
      "clip_ratio/region_mean": 0.0013438959686027374,
      "epoch": 0.02771993070017325,
      "grad_norm": 0.126237690448761,
      "learning_rate": 2e-07,
      "loss": 0.0167,
      "step": 297
    },
    {
      "clip_ratio/high_max": 0.0017423484932805877,
      "clip_ratio/high_mean": 0.0007889506468927721,
      "clip_ratio/low_mean": 0.0005747848390456056,
      "clip_ratio/low_min": 3.9272506000997964e-05,
      "clip_ratio/region_mean": 0.0013637354932143353,
      "epoch": 0.02781326380017383,
      "grad_norm": 0.12455515563488007,
      "learning_rate": 2e-07,
      "loss": 0.02,
      "step": 298
    },
    {
      "clip_ratio/high_max": 0.0017230886624020059,
      "clip_ratio/high_mean": 0.0007314204813155811,
      "clip_ratio/low_mean": 0.0005347597507352475,
      "clip_ratio/low_min": 1.9311653886688873e-05,
      "clip_ratio/region_mean": 0.0012661802393267862,
      "epoch": 0.027906596900174416,
      "grad_norm": 0.11264623701572418,
      "learning_rate": 2e-07,
      "loss": 0.0329,
      "step": 299
    },
    {
      "clip_ratio/high_max": 0.0019663340426632203,
      "clip_ratio/high_mean": 0.0007762718187223072,
      "clip_ratio/low_mean": 0.0006374502590915654,
      "clip_ratio/low_min": 6.776236750738462e-05,
      "clip_ratio/region_mean": 0.0014137220787233673,
      "epoch": 0.027999930000174998,
      "grad_norm": 0.12365193665027618,
      "learning_rate": 2e-07,
      "loss": 0.0544,
      "step": 300
    },
    {
      "clip_ratio/high_max": 0.0020610824067262,
      "clip_ratio/high_mean": 0.0008462089499516878,
      "clip_ratio/low_mean": 0.0005537785564229125,
      "clip_ratio/low_min": 6.071273764973739e-05,
      "clip_ratio/region_mean": 0.0013999874936416745,
      "epoch": 0.028093263100175583,
      "grad_norm": 0.11349142342805862,
      "learning_rate": 2e-07,
      "loss": 0.0063,
      "step": 301
    },
    {
      "clip_ratio/high_max": 0.0018935884545498993,
      "clip_ratio/high_mean": 0.0008074876404862152,
      "clip_ratio/low_mean": 0.0006114487805461977,
      "clip_ratio/low_min": 8.214577064791229e-05,
      "clip_ratio/region_mean": 0.00141893643012736,
      "epoch": 0.028186596200176165,
      "grad_norm": 0.12265170365571976,
      "learning_rate": 2e-07,
      "loss": 0.0331,
      "step": 302
    },
    {
      "clip_ratio/high_max": 0.0017851639713626355,
      "clip_ratio/high_mean": 0.0007438326447299914,
      "clip_ratio/low_mean": 0.0006346934405883076,
      "clip_ratio/low_min": 2.319697887287475e-05,
      "clip_ratio/region_mean": 0.0013785260234726593,
      "epoch": 0.02827992930017675,
      "grad_norm": 0.1156851202249527,
      "learning_rate": 2e-07,
      "loss": 0.0363,
      "step": 303
    },
    {
      "clip_ratio/high_max": 0.0015497145541303325,
      "clip_ratio/high_mean": 0.0006460076001530979,
      "clip_ratio/low_mean": 0.0005720689350710018,
      "clip_ratio/low_min": 4.790229741047369e-05,
      "clip_ratio/region_mean": 0.0012180765334051102,
      "epoch": 0.028373262400177332,
      "grad_norm": 0.10869140923023224,
      "learning_rate": 2e-07,
      "loss": 0.0559,
      "step": 304
    },
    {
      "clip_ratio/high_max": 0.002169876534026116,
      "clip_ratio/high_mean": 0.0009460025539738126,
      "clip_ratio/low_mean": 0.0004782475689353305,
      "clip_ratio/low_min": 4.207418533042073e-05,
      "clip_ratio/region_mean": 0.0014242500983527862,
      "epoch": 0.028466595500177917,
      "grad_norm": 0.12141937017440796,
      "learning_rate": 2e-07,
      "loss": -0.0167,
      "step": 305
    },
    {
      "clip_ratio/high_max": 0.00216663414175855,
      "clip_ratio/high_mean": 0.0008627387142041698,
      "clip_ratio/low_mean": 0.0006097215100453468,
      "clip_ratio/low_min": 5.1454970616759965e-05,
      "clip_ratio/region_mean": 0.001472460226068506,
      "epoch": 0.0285599286001785,
      "grad_norm": 0.12035830318927765,
      "learning_rate": 2e-07,
      "loss": 0.0161,
      "step": 306
    },
    {
      "clip_ratio/high_max": 0.0017779905247152783,
      "clip_ratio/high_mean": 0.000807691261798027,
      "clip_ratio/low_mean": 0.0005866352566954447,
      "clip_ratio/low_min": 2.2033443201507907e-05,
      "clip_ratio/region_mean": 0.0013943265585112385,
      "epoch": 0.028653261700179084,
      "grad_norm": 0.12182717025279999,
      "learning_rate": 2e-07,
      "loss": 0.0173,
      "step": 307
    },
    {
      "clip_ratio/high_max": 0.0019325420835230034,
      "clip_ratio/high_mean": 0.0007482777709810762,
      "clip_ratio/low_mean": 0.0005826978385812254,
      "clip_ratio/low_min": 2.8758774533343967e-05,
      "clip_ratio/region_mean": 0.0013309756213857327,
      "epoch": 0.028746594800179666,
      "grad_norm": 0.1085725948214531,
      "learning_rate": 2e-07,
      "loss": 0.0103,
      "step": 308
    },
    {
      "clip_ratio/high_max": 0.0022622082105954178,
      "clip_ratio/high_mean": 0.000824645881948527,
      "clip_ratio/low_mean": 0.0006643894121225458,
      "clip_ratio/low_min": 4.437986081029521e-05,
      "clip_ratio/region_mean": 0.0014890353195369244,
      "epoch": 0.02883992790018025,
      "grad_norm": 0.12374410778284073,
      "learning_rate": 2e-07,
      "loss": 0.055,
      "step": 309
    },
    {
      "clip_ratio/high_max": 0.0016471276539959945,
      "clip_ratio/high_mean": 0.0007477908857254079,
      "clip_ratio/low_mean": 0.0006039272857378819,
      "clip_ratio/low_min": 3.150043085042853e-05,
      "clip_ratio/region_mean": 0.0013517181905626785,
      "epoch": 0.028933261000180833,
      "grad_norm": 0.11700389534235,
      "learning_rate": 2e-07,
      "loss": -0.0052,
      "step": 310
    },
    {
      "clip_ratio/high_max": 0.0019830786986858584,
      "clip_ratio/high_mean": 0.0007303611819224898,
      "clip_ratio/low_mean": 0.0005711381818400696,
      "clip_ratio/low_min": 4.232197807141347e-05,
      "clip_ratio/region_mean": 0.001301499352848623,
      "epoch": 0.029026594100181415,
      "grad_norm": 0.1179599016904831,
      "learning_rate": 2e-07,
      "loss": 0.0273,
      "step": 311
    },
    {
      "clip_ratio/high_max": 0.0016685055888956413,
      "clip_ratio/high_mean": 0.0007133502240321832,
      "clip_ratio/low_mean": 0.0005924419310758822,
      "clip_ratio/low_min": 3.695352324939449e-05,
      "clip_ratio/region_mean": 0.0013057921787549276,
      "epoch": 0.029119927200182,
      "grad_norm": 0.13482874631881714,
      "learning_rate": 2e-07,
      "loss": -0.0159,
      "step": 312
    },
    {
      "clip_ratio/high_max": 0.0018655500462045893,
      "clip_ratio/high_mean": 0.0008256774217443308,
      "clip_ratio/low_mean": 0.0005759813893746468,
      "clip_ratio/low_min": 7.257852757902583e-05,
      "clip_ratio/region_mean": 0.001401658810209483,
      "epoch": 0.02921326030018258,
      "grad_norm": 0.10839033871889114,
      "learning_rate": 2e-07,
      "loss": -0.0024,
      "step": 313
    },
    {
      "clip_ratio/high_max": 0.0017268187111767475,
      "clip_ratio/high_mean": 0.0007236371584440349,
      "clip_ratio/low_mean": 0.0006265372248890344,
      "clip_ratio/low_min": 7.67276760598179e-05,
      "clip_ratio/region_mean": 0.0013501744251698256,
      "epoch": 0.029306593400183167,
      "grad_norm": 0.12443891912698746,
      "learning_rate": 2e-07,
      "loss": 0.0066,
      "step": 314
    },
    {
      "clip_ratio/high_max": 0.0018528828441048972,
      "clip_ratio/high_mean": 0.0007677442517888267,
      "clip_ratio/low_mean": 0.0005768253167843795,
      "clip_ratio/low_min": 3.8201259485504124e-05,
      "clip_ratio/region_mean": 0.0013445695803966373,
      "epoch": 0.02939992650018375,
      "grad_norm": 0.1159597635269165,
      "learning_rate": 2e-07,
      "loss": 0.0137,
      "step": 315
    },
    {
      "clip_ratio/high_max": 0.001895471923489822,
      "clip_ratio/high_mean": 0.0008120604124997044,
      "clip_ratio/low_mean": 0.0005665475355272065,
      "clip_ratio/low_min": 3.500260572764091e-05,
      "clip_ratio/region_mean": 0.0013786079653073102,
      "epoch": 0.029493259600184334,
      "grad_norm": 0.1261255443096161,
      "learning_rate": 2e-07,
      "loss": 0.0135,
      "step": 316
    },
    {
      "clip_ratio/high_max": 0.001565489117638208,
      "clip_ratio/high_mean": 0.0006448101321439026,
      "clip_ratio/low_mean": 0.0006233360254555009,
      "clip_ratio/low_min": 2.731101449171547e-05,
      "clip_ratio/region_mean": 0.0012681461230386049,
      "epoch": 0.029586592700184915,
      "grad_norm": 0.11905649304389954,
      "learning_rate": 2e-07,
      "loss": 0.0274,
      "step": 317
    },
    {
      "clip_ratio/high_max": 0.0018058292116620578,
      "clip_ratio/high_mean": 0.0006378151356329909,
      "clip_ratio/low_mean": 0.0005901934309804346,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001228008546604542,
      "epoch": 0.0296799258001855,
      "grad_norm": 0.1080046221613884,
      "learning_rate": 2e-07,
      "loss": 0.0645,
      "step": 318
    },
    {
      "clip_ratio/high_max": 0.0020870286753051914,
      "clip_ratio/high_mean": 0.0008321259974763962,
      "clip_ratio/low_mean": 0.0006464874877565308,
      "clip_ratio/low_min": 4.716136936622206e-05,
      "clip_ratio/region_mean": 0.0014786135143367574,
      "epoch": 0.029773258900186082,
      "grad_norm": 0.12716934084892273,
      "learning_rate": 2e-07,
      "loss": 0.0362,
      "step": 319
    },
    {
      "clip_ratio/high_max": 0.0019575896440073848,
      "clip_ratio/high_mean": 0.0008432189861196093,
      "clip_ratio/low_mean": 0.0005437746713141678,
      "clip_ratio/low_min": 1.0867674973269459e-05,
      "clip_ratio/region_mean": 0.0013869936738046817,
      "epoch": 0.029866592000186667,
      "grad_norm": 0.12483929842710495,
      "learning_rate": 2e-07,
      "loss": -0.0296,
      "step": 320
    },
    {
      "clip_ratio/high_max": 0.0019093683076789603,
      "clip_ratio/high_mean": 0.0008273908515548101,
      "clip_ratio/low_mean": 0.0006479590902017662,
      "clip_ratio/low_min": 5.760748535976745e-05,
      "clip_ratio/region_mean": 0.0014753499235666823,
      "epoch": 0.02995992510018725,
      "grad_norm": 0.1262880563735962,
      "learning_rate": 2e-07,
      "loss": 0.0281,
      "step": 321
    },
    {
      "clip_ratio/high_max": 0.0021952798051643185,
      "clip_ratio/high_mean": 0.0009407220150023932,
      "clip_ratio/low_mean": 0.0005884859983780188,
      "clip_ratio/low_min": 2.574689278844744e-05,
      "clip_ratio/region_mean": 0.0015292080242943484,
      "epoch": 0.030053258200187834,
      "grad_norm": 0.13950613141059875,
      "learning_rate": 2e-07,
      "loss": 0.0026,
      "step": 322
    },
    {
      "clip_ratio/high_max": 0.0018082228489220142,
      "clip_ratio/high_mean": 0.0007628774783370318,
      "clip_ratio/low_mean": 0.0005792008296339191,
      "clip_ratio/low_min": 1.193659318232676e-05,
      "clip_ratio/region_mean": 0.0013420783216133714,
      "epoch": 0.030146591300188416,
      "grad_norm": 0.125337615609169,
      "learning_rate": 2e-07,
      "loss": 0.0502,
      "step": 323
    },
    {
      "clip_ratio/high_max": 0.0020202920968586113,
      "clip_ratio/high_mean": 0.000845012425997993,
      "clip_ratio/low_mean": 0.0006102746265241876,
      "clip_ratio/low_min": 7.77556579123484e-06,
      "clip_ratio/region_mean": 0.0014552870670740958,
      "epoch": 0.030239924400188998,
      "grad_norm": 0.1325664073228836,
      "learning_rate": 2e-07,
      "loss": 0.0041,
      "step": 324
    },
    {
      "clip_ratio/high_max": 0.0018722272507147864,
      "clip_ratio/high_mean": 0.0007003525897744112,
      "clip_ratio/low_mean": 0.0005809882077301154,
      "clip_ratio/low_min": 1.833382157201413e-05,
      "clip_ratio/region_mean": 0.0012813407665817067,
      "epoch": 0.030333257500189583,
      "grad_norm": 0.11880411952733994,
      "learning_rate": 2e-07,
      "loss": 0.0233,
      "step": 325
    },
    {
      "clip_ratio/high_max": 0.0016914101070142351,
      "clip_ratio/high_mean": 0.0007185336926340824,
      "clip_ratio/low_mean": 0.0006415384577849181,
      "clip_ratio/low_min": 4.44346405856777e-05,
      "clip_ratio/region_mean": 0.0013600721358670853,
      "epoch": 0.030426590600190165,
      "grad_norm": 0.11393184959888458,
      "learning_rate": 2e-07,
      "loss": 0.042,
      "step": 326
    },
    {
      "clip_ratio/high_max": 0.0018389952201687265,
      "clip_ratio/high_mean": 0.0007157902073231526,
      "clip_ratio/low_mean": 0.0007002808142715367,
      "clip_ratio/low_min": 2.883483648474794e-05,
      "clip_ratio/region_mean": 0.0014160710270516574,
      "epoch": 0.03051992370019075,
      "grad_norm": 0.12140263617038727,
      "learning_rate": 2e-07,
      "loss": 0.0598,
      "step": 327
    },
    {
      "clip_ratio/high_max": 0.0018691142286115792,
      "clip_ratio/high_mean": 0.000827059517177986,
      "clip_ratio/low_mean": 0.0006826757971793995,
      "clip_ratio/low_min": 5.599279666057555e-05,
      "clip_ratio/region_mean": 0.0015097352843440603,
      "epoch": 0.030613256800191332,
      "grad_norm": 0.12040097266435623,
      "learning_rate": 2e-07,
      "loss": 0.0204,
      "step": 328
    },
    {
      "clip_ratio/high_max": 0.0020709427626570687,
      "clip_ratio/high_mean": 0.0008130800179060316,
      "clip_ratio/low_mean": 0.0007018190626695286,
      "clip_ratio/low_min": 8.159587923728395e-05,
      "clip_ratio/region_mean": 0.0015148990787565708,
      "epoch": 0.030706589900191917,
      "grad_norm": 0.11802371591329575,
      "learning_rate": 2e-07,
      "loss": 0.0607,
      "step": 329
    },
    {
      "clip_ratio/high_max": 0.0017908496265590657,
      "clip_ratio/high_mean": 0.000838683801703155,
      "clip_ratio/low_mean": 0.0007185102494986495,
      "clip_ratio/low_min": 5.549161687667947e-05,
      "clip_ratio/region_mean": 0.0015571940093650483,
      "epoch": 0.0307999230001925,
      "grad_norm": 0.13418221473693848,
      "learning_rate": 2e-07,
      "loss": 0.0283,
      "step": 330
    },
    {
      "clip_ratio/high_max": 0.0019069183654210065,
      "clip_ratio/high_mean": 0.0007655143290321575,
      "clip_ratio/low_mean": 0.0007304333967113052,
      "clip_ratio/low_min": 0.00010650184276528307,
      "clip_ratio/region_mean": 0.0014959477412048727,
      "epoch": 0.030893256100193084,
      "grad_norm": 0.13436955213546753,
      "learning_rate": 2e-07,
      "loss": 0.0441,
      "step": 331
    },
    {
      "clip_ratio/high_max": 0.002172822358261328,
      "clip_ratio/high_mean": 0.0008424574225500692,
      "clip_ratio/low_mean": 0.000788283223300823,
      "clip_ratio/low_min": 7.499276216549333e-05,
      "clip_ratio/region_mean": 0.0016307406694977544,
      "epoch": 0.030986589200193666,
      "grad_norm": 0.14253520965576172,
      "learning_rate": 2e-07,
      "loss": 0.0264,
      "step": 332
    },
    {
      "clip_ratio/high_max": 0.0022013826019247063,
      "clip_ratio/high_mean": 0.0008953339474828681,
      "clip_ratio/low_mean": 0.0007051754437270574,
      "clip_ratio/low_min": 1.4181982805894222e-05,
      "clip_ratio/region_mean": 0.0016005094184947666,
      "epoch": 0.03107992230019425,
      "grad_norm": 0.13072951138019562,
      "learning_rate": 2e-07,
      "loss": 0.0567,
      "step": 333
    },
    {
      "clip_ratio/high_max": 0.0017931079673871864,
      "clip_ratio/high_mean": 0.0008081988426056341,
      "clip_ratio/low_mean": 0.000618670737821958,
      "clip_ratio/low_min": 8.229092509282054e-05,
      "clip_ratio/region_mean": 0.0014268696068029385,
      "epoch": 0.031173255400194833,
      "grad_norm": 0.13211628794670105,
      "learning_rate": 2e-07,
      "loss": 0.077,
      "step": 334
    },
    {
      "clip_ratio/high_max": 0.0017426550184609368,
      "clip_ratio/high_mean": 0.0008040963293751702,
      "clip_ratio/low_mean": 0.0005453411849885015,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013494375089067034,
      "epoch": 0.03126658850019542,
      "grad_norm": 0.11757729202508926,
      "learning_rate": 2e-07,
      "loss": 0.0053,
      "step": 335
    },
    {
      "clip_ratio/high_max": 0.0017707709448586684,
      "clip_ratio/high_mean": 0.0007418416262225946,
      "clip_ratio/low_mean": 0.0006487011178251123,
      "clip_ratio/low_min": 5.6116896303137764e-05,
      "clip_ratio/region_mean": 0.0013905427294957917,
      "epoch": 0.031359921600196,
      "grad_norm": 0.13273580372333527,
      "learning_rate": 2e-07,
      "loss": 0.0761,
      "step": 336
    },
    {
      "clip_ratio/high_max": 0.0020378922345116735,
      "clip_ratio/high_mean": 0.0009189400407194626,
      "clip_ratio/low_mean": 0.0006542112496390473,
      "clip_ratio/low_min": 2.9296424145286437e-05,
      "clip_ratio/region_mean": 0.0015731512903585099,
      "epoch": 0.03145325470019658,
      "grad_norm": 0.12876418232917786,
      "learning_rate": 2e-07,
      "loss": -0.035,
      "step": 337
    },
    {
      "clip_ratio/high_max": 0.0021753712971985806,
      "clip_ratio/high_mean": 0.0008455993611278245,
      "clip_ratio/low_mean": 0.0006070604049455142,
      "clip_ratio/low_min": 1.780763113856665e-05,
      "clip_ratio/region_mean": 0.0014526597769872751,
      "epoch": 0.031546587800197166,
      "grad_norm": 0.13564316928386688,
      "learning_rate": 2e-07,
      "loss": 0.0391,
      "step": 338
    },
    {
      "clip_ratio/high_max": 0.0023537035667686723,
      "clip_ratio/high_mean": 0.0009317334988736548,
      "clip_ratio/low_mean": 0.0006164165497466456,
      "clip_ratio/low_min": 7.392971565423068e-05,
      "clip_ratio/region_mean": 0.0015481500340683851,
      "epoch": 0.03163992090019775,
      "grad_norm": 0.12651567161083221,
      "learning_rate": 2e-07,
      "loss": -0.0261,
      "step": 339
    },
    {
      "clip_ratio/high_max": 0.0018078884768328862,
      "clip_ratio/high_mean": 0.0006821720926382113,
      "clip_ratio/low_mean": 0.0007266493194038048,
      "clip_ratio/low_min": 2.1878348434256623e-05,
      "clip_ratio/region_mean": 0.0014088214193179738,
      "epoch": 0.03173325400019833,
      "grad_norm": 0.12444819509983063,
      "learning_rate": 2e-07,
      "loss": 0.0829,
      "step": 340
    },
    {
      "clip_ratio/high_max": 0.0019344561915204395,
      "clip_ratio/high_mean": 0.0007698418703512289,
      "clip_ratio/low_mean": 0.0005962260884189163,
      "clip_ratio/low_min": 2.3273132683243603e-05,
      "clip_ratio/region_mean": 0.0013660680087923538,
      "epoch": 0.031826587100198915,
      "grad_norm": 0.11317906528711319,
      "learning_rate": 2e-07,
      "loss": 0.0177,
      "step": 341
    },
    {
      "clip_ratio/high_max": 0.0019452507694950327,
      "clip_ratio/high_mean": 0.0008471414002997335,
      "clip_ratio/low_mean": 0.0006604988084291108,
      "clip_ratio/low_min": 5.4606490266451146e-05,
      "clip_ratio/region_mean": 0.0015076401978149079,
      "epoch": 0.0319199202001995,
      "grad_norm": 0.13797108829021454,
      "learning_rate": 2e-07,
      "loss": 0.0243,
      "step": 342
    },
    {
      "clip_ratio/high_max": 0.0017152908258140087,
      "clip_ratio/high_mean": 0.0007821099370630691,
      "clip_ratio/low_mean": 0.0005885351965844166,
      "clip_ratio/low_min": 5.3610104259860236e-05,
      "clip_ratio/region_mean": 0.0013706451463804115,
      "epoch": 0.032013253300200085,
      "grad_norm": 0.11515862494707108,
      "learning_rate": 2e-07,
      "loss": 0.0174,
      "step": 343
    },
    {
      "clip_ratio/high_max": 0.0018824800936272368,
      "clip_ratio/high_mean": 0.0007774492987664416,
      "clip_ratio/low_mean": 0.0006851958914921852,
      "clip_ratio/low_min": 3.6656313568528276e-05,
      "clip_ratio/region_mean": 0.0014626452102675103,
      "epoch": 0.032106586400200664,
      "grad_norm": 0.12402620166540146,
      "learning_rate": 2e-07,
      "loss": 0.0242,
      "step": 344
    },
    {
      "clip_ratio/high_max": 0.0026173783553531393,
      "clip_ratio/high_mean": 0.0008851697493810207,
      "clip_ratio/low_mean": 0.000640038117126096,
      "clip_ratio/low_min": 1.6873649656190537e-05,
      "clip_ratio/region_mean": 0.0015252078919729684,
      "epoch": 0.03219991950020125,
      "grad_norm": 0.15637467801570892,
      "learning_rate": 2e-07,
      "loss": 0.0251,
      "step": 345
    },
    {
      "clip_ratio/high_max": 0.002263232228870038,
      "clip_ratio/high_mean": 0.0009399782029504422,
      "clip_ratio/low_mean": 0.0006482475000666454,
      "clip_ratio/low_min": 7.782343345752452e-06,
      "clip_ratio/region_mean": 0.0015882257102930453,
      "epoch": 0.032293252600201834,
      "grad_norm": 0.1303851306438446,
      "learning_rate": 2e-07,
      "loss": 0.0257,
      "step": 346
    },
    {
      "clip_ratio/high_max": 0.0019814482548099477,
      "clip_ratio/high_mean": 0.0007946911409817403,
      "clip_ratio/low_mean": 0.0006722885691488045,
      "clip_ratio/low_min": 5.543444149225252e-05,
      "clip_ratio/region_mean": 0.0014669797601527534,
      "epoch": 0.03238658570020242,
      "grad_norm": 0.12173054367303848,
      "learning_rate": 2e-07,
      "loss": 0.0302,
      "step": 347
    },
    {
      "clip_ratio/high_max": 0.0018946742129628547,
      "clip_ratio/high_mean": 0.0007601962588523747,
      "clip_ratio/low_mean": 0.0006497679405583767,
      "clip_ratio/low_min": 2.7570488327910425e-05,
      "clip_ratio/region_mean": 0.0014099641848588362,
      "epoch": 0.032479918800203,
      "grad_norm": 0.1303040236234665,
      "learning_rate": 2e-07,
      "loss": 0.0383,
      "step": 348
    },
    {
      "clip_ratio/high_max": 0.0017901070350490045,
      "clip_ratio/high_mean": 0.0007549113397544716,
      "clip_ratio/low_mean": 0.0006227148787729675,
      "clip_ratio/low_min": 4.3878568249056116e-05,
      "clip_ratio/region_mean": 0.001377626191242598,
      "epoch": 0.03257325190020358,
      "grad_norm": 0.1619393229484558,
      "learning_rate": 2e-07,
      "loss": 0.0362,
      "step": 349
    },
    {
      "clip_ratio/high_max": 0.0020116166924708523,
      "clip_ratio/high_mean": 0.0008072157988863182,
      "clip_ratio/low_mean": 0.0006152933747216593,
      "clip_ratio/low_min": 1.0111632036569063e-05,
      "clip_ratio/region_mean": 0.0014225091581465676,
      "epoch": 0.03266658500020417,
      "grad_norm": 0.1221124455332756,
      "learning_rate": 2e-07,
      "loss": 0.0143,
      "step": 350
    },
    {
      "clip_ratio/high_max": 0.0021453488297993317,
      "clip_ratio/high_mean": 0.0007960320326674264,
      "clip_ratio/low_mean": 0.0005874770631635329,
      "clip_ratio/low_min": 3.421721794438781e-05,
      "clip_ratio/region_mean": 0.0013835090794600546,
      "epoch": 0.032759918100204746,
      "grad_norm": 0.12113963812589645,
      "learning_rate": 2e-07,
      "loss": 0.0125,
      "step": 351
    },
    {
      "clip_ratio/high_max": 0.0023286609139177017,
      "clip_ratio/high_mean": 0.0008069346658885479,
      "clip_ratio/low_mean": 0.0006730368531862041,
      "clip_ratio/low_min": 2.5416436074010562e-05,
      "clip_ratio/region_mean": 0.0014799715063418262,
      "epoch": 0.03285325120020533,
      "grad_norm": 0.12016429007053375,
      "learning_rate": 2e-07,
      "loss": 0.0323,
      "step": 352
    },
    {
      "clip_ratio/high_max": 0.002018118157138815,
      "clip_ratio/high_mean": 0.0007823203650332289,
      "clip_ratio/low_mean": 0.0006056782867744914,
      "clip_ratio/low_min": 3.2891550290514715e-05,
      "clip_ratio/region_mean": 0.0013879986508982256,
      "epoch": 0.03294658430020592,
      "grad_norm": 0.12529417872428894,
      "learning_rate": 2e-07,
      "loss": -0.008,
      "step": 353
    },
    {
      "clip_ratio/high_max": 0.001547041121739312,
      "clip_ratio/high_mean": 0.0007216818921733648,
      "clip_ratio/low_mean": 0.0006577965104952455,
      "clip_ratio/low_min": 1.9187643374607433e-05,
      "clip_ratio/region_mean": 0.0013794783808407374,
      "epoch": 0.0330399174002065,
      "grad_norm": 0.11982711404561996,
      "learning_rate": 2e-07,
      "loss": 0.01,
      "step": 354
    },
    {
      "clip_ratio/high_max": 0.002014764970226679,
      "clip_ratio/high_mean": 0.0008688471989444224,
      "clip_ratio/low_mean": 0.0006997004511504201,
      "clip_ratio/low_min": 4.0232356695923954e-05,
      "clip_ratio/region_mean": 0.0015685476246289909,
      "epoch": 0.03313325050020708,
      "grad_norm": 0.1305162012577057,
      "learning_rate": 2e-07,
      "loss": 0.0095,
      "step": 355
    },
    {
      "clip_ratio/high_max": 0.0019054939584748354,
      "clip_ratio/high_mean": 0.0007127008466341067,
      "clip_ratio/low_mean": 0.0006586289127881173,
      "clip_ratio/low_min": 4.5386538658931386e-05,
      "clip_ratio/region_mean": 0.001371329777612118,
      "epoch": 0.033226583600207665,
      "grad_norm": 0.11985760927200317,
      "learning_rate": 2e-07,
      "loss": 0.0155,
      "step": 356
    },
    {
      "clip_ratio/high_max": 0.0020804283922188915,
      "clip_ratio/high_mean": 0.0009287571774621028,
      "clip_ratio/low_mean": 0.0006215613921085605,
      "clip_ratio/low_min": 3.508260124363005e-05,
      "clip_ratio/region_mean": 0.0015503185350098647,
      "epoch": 0.03331991670020825,
      "grad_norm": 0.13267309963703156,
      "learning_rate": 2e-07,
      "loss": 0.0086,
      "step": 357
    },
    {
      "clip_ratio/high_max": 0.001969245964573929,
      "clip_ratio/high_mean": 0.0007912969977041939,
      "clip_ratio/low_mean": 0.0006782705168006942,
      "clip_ratio/low_min": 9.580519053997705e-05,
      "clip_ratio/region_mean": 0.0014695674908580258,
      "epoch": 0.033413249800208836,
      "grad_norm": 0.11836139857769012,
      "learning_rate": 2e-07,
      "loss": 0.0727,
      "step": 358
    },
    {
      "clip_ratio/high_max": 0.0019048401991312858,
      "clip_ratio/high_mean": 0.0007870481495046988,
      "clip_ratio/low_mean": 0.0007177717307058629,
      "clip_ratio/low_min": 6.116804524936015e-05,
      "clip_ratio/region_mean": 0.00150481985474471,
      "epoch": 0.033506582900209414,
      "grad_norm": 0.13217952847480774,
      "learning_rate": 2e-07,
      "loss": 0.0114,
      "step": 359
    },
    {
      "clip_ratio/high_max": 0.0020297840783314314,
      "clip_ratio/high_mean": 0.0008608384832768934,
      "clip_ratio/low_mean": 0.0006077831158108893,
      "clip_ratio/low_min": 7.204610938060796e-06,
      "clip_ratio/region_mean": 0.0014686216236441396,
      "epoch": 0.03359991600021,
      "grad_norm": 0.12482540309429169,
      "learning_rate": 2e-07,
      "loss": -0.0304,
      "step": 360
    },
    {
      "clip_ratio/high_max": 0.0020188749713270226,
      "clip_ratio/high_mean": 0.0008818371061352082,
      "clip_ratio/low_mean": 0.0006707772008667234,
      "clip_ratio/low_min": 1.3745326214120723e-05,
      "clip_ratio/region_mean": 0.0015526143433817197,
      "epoch": 0.033693249100210584,
      "grad_norm": 0.141623392701149,
      "learning_rate": 2e-07,
      "loss": 0.0005,
      "step": 361
    },
    {
      "clip_ratio/high_max": 0.002167911152355373,
      "clip_ratio/high_mean": 0.0008037817915464984,
      "clip_ratio/low_mean": 0.0007586861047457205,
      "clip_ratio/low_min": 8.293248174595647e-05,
      "clip_ratio/region_mean": 0.0015624679108441342,
      "epoch": 0.03378658220021117,
      "grad_norm": 0.13175365328788757,
      "learning_rate": 2e-07,
      "loss": 0.0022,
      "step": 362
    },
    {
      "clip_ratio/high_max": 0.002149682135495823,
      "clip_ratio/high_mean": 0.0008718295575818047,
      "clip_ratio/low_mean": 0.0006655684242105053,
      "clip_ratio/low_min": 4.600217471306678e-05,
      "clip_ratio/region_mean": 0.0015373979949799832,
      "epoch": 0.03387991530021175,
      "grad_norm": 0.12787693738937378,
      "learning_rate": 2e-07,
      "loss": 0.0078,
      "step": 363
    },
    {
      "clip_ratio/high_max": 0.002148786064935848,
      "clip_ratio/high_mean": 0.0008514384680893272,
      "clip_ratio/low_mean": 0.0005827631025567825,
      "clip_ratio/low_min": 2.6737967345979996e-05,
      "clip_ratio/region_mean": 0.001434201574738836,
      "epoch": 0.03397324840021233,
      "grad_norm": 0.11575324833393097,
      "learning_rate": 2e-07,
      "loss": -0.0104,
      "step": 364
    },
    {
      "clip_ratio/high_max": 0.0017832515404734295,
      "clip_ratio/high_mean": 0.000741971110983286,
      "clip_ratio/low_mean": 0.0006728530370310182,
      "clip_ratio/low_min": 4.173791239736602e-05,
      "clip_ratio/region_mean": 0.0014148241207294632,
      "epoch": 0.03406658150021292,
      "grad_norm": 0.12349911779165268,
      "learning_rate": 2e-07,
      "loss": 0.05,
      "step": 365
    },
    {
      "clip_ratio/high_max": 0.0020913054868287873,
      "clip_ratio/high_mean": 0.0008945612680690829,
      "clip_ratio/low_mean": 0.0006574874569196254,
      "clip_ratio/low_min": 8.562474067730363e-05,
      "clip_ratio/region_mean": 0.0015520487213507295,
      "epoch": 0.034159914600213497,
      "grad_norm": 0.1272130161523819,
      "learning_rate": 2e-07,
      "loss": 0.029,
      "step": 366
    },
    {
      "clip_ratio/high_max": 0.002231886228400981,
      "clip_ratio/high_mean": 0.0008604073518654332,
      "clip_ratio/low_mean": 0.00061496202579292,
      "clip_ratio/low_min": 7.722076452409965e-05,
      "clip_ratio/region_mean": 0.001475369390391279,
      "epoch": 0.03425324770021408,
      "grad_norm": 0.12255969643592834,
      "learning_rate": 2e-07,
      "loss": 0.0272,
      "step": 367
    },
    {
      "clip_ratio/high_max": 0.0022909300387254916,
      "clip_ratio/high_mean": 0.0009478352003498003,
      "clip_ratio/low_mean": 0.0006015002454660134,
      "clip_ratio/low_min": 2.1068046407890506e-05,
      "clip_ratio/region_mean": 0.0015493354767386336,
      "epoch": 0.03434658080021467,
      "grad_norm": 0.11591565608978271,
      "learning_rate": 2e-07,
      "loss": -0.0231,
      "step": 368
    },
    {
      "clip_ratio/high_max": 0.001848685697041219,
      "clip_ratio/high_mean": 0.0006901904180267593,
      "clip_ratio/low_mean": 0.0006117131761129713,
      "clip_ratio/low_min": 2.7364272682461888e-05,
      "clip_ratio/region_mean": 0.0013019035723118577,
      "epoch": 0.03443991390021525,
      "grad_norm": 0.13268209993839264,
      "learning_rate": 2e-07,
      "loss": 0.0548,
      "step": 369
    },
    {
      "clip_ratio/high_max": 0.0018065693584503606,
      "clip_ratio/high_mean": 0.0007710626978223445,
      "clip_ratio/low_mean": 0.0006208758277352899,
      "clip_ratio/low_min": 4.0096635530062485e-05,
      "clip_ratio/region_mean": 0.0013919385346525814,
      "epoch": 0.03453324700021583,
      "grad_norm": 0.13073807954788208,
      "learning_rate": 2e-07,
      "loss": 0.0264,
      "step": 370
    },
    {
      "clip_ratio/high_max": 0.0020543116224871483,
      "clip_ratio/high_mean": 0.000831001202641346,
      "clip_ratio/low_mean": 0.0006559370012837462,
      "clip_ratio/low_min": 0.00013855951692676172,
      "clip_ratio/region_mean": 0.0014869382248434704,
      "epoch": 0.034626580100216416,
      "grad_norm": 0.12477888911962509,
      "learning_rate": 2e-07,
      "loss": 0.016,
      "step": 371
    },
    {
      "clip_ratio/high_max": 0.0019062135470448993,
      "clip_ratio/high_mean": 0.0007313645546673797,
      "clip_ratio/low_mean": 0.0007595551542181056,
      "clip_ratio/low_min": 4.2784248762473e-05,
      "clip_ratio/region_mean": 0.0014909196688677184,
      "epoch": 0.034719913200217,
      "grad_norm": 0.137606680393219,
      "learning_rate": 2e-07,
      "loss": 0.0851,
      "step": 372
    },
    {
      "clip_ratio/high_max": 0.0021088054418214597,
      "clip_ratio/high_mean": 0.0007991455604496878,
      "clip_ratio/low_mean": 0.0006149913479021052,
      "clip_ratio/low_min": 4.018994059151737e-05,
      "clip_ratio/region_mean": 0.0014141369138087612,
      "epoch": 0.034813246300217586,
      "grad_norm": 0.14011959731578827,
      "learning_rate": 2e-07,
      "loss": 0.0172,
      "step": 373
    },
    {
      "clip_ratio/high_max": 0.0023670054724789225,
      "clip_ratio/high_mean": 0.0008459534492430976,
      "clip_ratio/low_mean": 0.0007747523177386029,
      "clip_ratio/low_min": 5.465014874062035e-05,
      "clip_ratio/region_mean": 0.0016207057778956369,
      "epoch": 0.034906579400218164,
      "grad_norm": 0.13037236034870148,
      "learning_rate": 2e-07,
      "loss": 0.086,
      "step": 374
    },
    {
      "clip_ratio/high_max": 0.001871685693913605,
      "clip_ratio/high_mean": 0.0008009878729353659,
      "clip_ratio/low_mean": 0.0006968768784645363,
      "clip_ratio/low_min": 5.2148810937069356e-05,
      "clip_ratio/region_mean": 0.0014978647741372697,
      "epoch": 0.03499991250021875,
      "grad_norm": 0.1299564242362976,
      "learning_rate": 2e-07,
      "loss": 0.0311,
      "step": 375
    },
    {
      "clip_ratio/high_max": 0.0021227499019005336,
      "clip_ratio/high_mean": 0.0007546021952293813,
      "clip_ratio/low_mean": 0.0006144433600638877,
      "clip_ratio/low_min": 1.6617921573924832e-05,
      "clip_ratio/region_mean": 0.0013690455634787213,
      "epoch": 0.035093245600219335,
      "grad_norm": 0.11728532612323761,
      "learning_rate": 2e-07,
      "loss": 0.0031,
      "step": 376
    },
    {
      "clip_ratio/high_max": 0.002051748873782344,
      "clip_ratio/high_mean": 0.0008261672301159706,
      "clip_ratio/low_mean": 0.0007225545632536523,
      "clip_ratio/low_min": 4.1859238081087824e-05,
      "clip_ratio/region_mean": 0.0015487217824556865,
      "epoch": 0.03518657870021991,
      "grad_norm": 0.12600870430469513,
      "learning_rate": 2e-07,
      "loss": 0.0312,
      "step": 377
    },
    {
      "clip_ratio/high_max": 0.00213628694837098,
      "clip_ratio/high_mean": 0.0008693533509358531,
      "clip_ratio/low_mean": 0.0005532468549063196,
      "clip_ratio/low_min": 3.526476893966901e-05,
      "clip_ratio/region_mean": 0.0014226001985662151,
      "epoch": 0.0352799118002205,
      "grad_norm": 0.12610547244548798,
      "learning_rate": 2e-07,
      "loss": 0.0139,
      "step": 378
    },
    {
      "clip_ratio/high_max": 0.0018962830072268844,
      "clip_ratio/high_mean": 0.0007201219759735977,
      "clip_ratio/low_mean": 0.0007967113342601806,
      "clip_ratio/low_min": 4.1063118260353804e-05,
      "clip_ratio/region_mean": 0.0015168333120527677,
      "epoch": 0.03537324490022108,
      "grad_norm": 0.1254897266626358,
      "learning_rate": 2e-07,
      "loss": 0.0975,
      "step": 379
    },
    {
      "clip_ratio/high_max": 0.0017949985558516346,
      "clip_ratio/high_mean": 0.0007229140628624009,
      "clip_ratio/low_mean": 0.0006714106793879182,
      "clip_ratio/low_min": 5.0748721150739584e-05,
      "clip_ratio/region_mean": 0.0013943247358838562,
      "epoch": 0.03546657800022167,
      "grad_norm": 0.12176269292831421,
      "learning_rate": 2e-07,
      "loss": 0.0224,
      "step": 380
    },
    {
      "clip_ratio/high_max": 0.0017871931595436763,
      "clip_ratio/high_mean": 0.000768938456531032,
      "clip_ratio/low_mean": 0.0006647947375313379,
      "clip_ratio/low_min": 2.8913120331708342e-05,
      "clip_ratio/region_mean": 0.0014337332249851897,
      "epoch": 0.03555991110022225,
      "grad_norm": 0.12029475718736649,
      "learning_rate": 2e-07,
      "loss": 0.0625,
      "step": 381
    },
    {
      "clip_ratio/high_max": 0.001985241331567522,
      "clip_ratio/high_mean": 0.0007566600397694856,
      "clip_ratio/low_mean": 0.0007062429140205495,
      "clip_ratio/low_min": 7.911537795735057e-05,
      "clip_ratio/region_mean": 0.0014629029283241834,
      "epoch": 0.03565324420022283,
      "grad_norm": 0.13246503472328186,
      "learning_rate": 2e-07,
      "loss": 0.0402,
      "step": 382
    },
    {
      "clip_ratio/high_max": 0.0020245888954377733,
      "clip_ratio/high_mean": 0.0008176612100214697,
      "clip_ratio/low_mean": 0.0006221003422979265,
      "clip_ratio/low_min": 3.41115874107345e-05,
      "clip_ratio/region_mean": 0.0014397615486814175,
      "epoch": 0.03574657730022342,
      "grad_norm": 0.13743485510349274,
      "learning_rate": 2e-07,
      "loss": 0.0211,
      "step": 383
    },
    {
      "clip_ratio/high_max": 0.001962187910976354,
      "clip_ratio/high_mean": 0.0007629390056536067,
      "clip_ratio/low_mean": 0.0005997011248837225,
      "clip_ratio/low_min": 2.7695125027094036e-05,
      "clip_ratio/region_mean": 0.001362640134175308,
      "epoch": 0.035839910400224,
      "grad_norm": 0.11758792400360107,
      "learning_rate": 2e-07,
      "loss": 0.0215,
      "step": 384
    },
    {
      "clip_ratio/high_max": 0.0012347276169748511,
      "clip_ratio/high_mean": 0.0005384833093557972,
      "clip_ratio/low_mean": 0.0006538678735523717,
      "clip_ratio/low_min": 3.101048423559405e-05,
      "clip_ratio/region_mean": 0.001192351228382904,
      "completions/clipped_ratio": 0.017011369977678603,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4079.0,
      "completions/mean_length": 638.9855346679688,
      "completions/mean_terminated_length": 579.1593017578125,
      "completions/min_length": 74.0,
      "completions/min_terminated_length": 74.0,
      "epoch": 0.03593324350022458,
      "grad_norm": 0.11270938813686371,
      "learning_rate": 2e-07,
      "loss": 0.0941,
      "num_tokens": 329389926.0,
      "reward": 0.5735124945640564,
      "reward_std": 0.1990089863538742,
      "rewards/simpleverify_reward/mean": 0.5735124945640564,
      "rewards/simpleverify_reward/std": 0.49456849694252014,
      "step": 385
    },
    {
      "clip_ratio/high_max": 0.0017514900355308782,
      "clip_ratio/high_mean": 0.0007251979614011361,
      "clip_ratio/low_mean": 0.0005968792029307224,
      "clip_ratio/low_min": 3.261834626755444e-05,
      "clip_ratio/region_mean": 0.0013220772161730565,
      "epoch": 0.036026576600225166,
      "grad_norm": 0.12380381673574448,
      "learning_rate": 2e-07,
      "loss": 0.0412,
      "step": 386
    },
    {
      "clip_ratio/high_max": 0.002276794650242664,
      "clip_ratio/high_mean": 0.0009244169214071007,
      "clip_ratio/low_mean": 0.00047346900919365,
      "clip_ratio/low_min": 1.272394092666218e-05,
      "clip_ratio/region_mean": 0.0013978859351482242,
      "epoch": 0.03611990970022575,
      "grad_norm": 0.12662142515182495,
      "learning_rate": 2e-07,
      "loss": -0.0081,
      "step": 387
    },
    {
      "clip_ratio/high_max": 0.001588627810633625,
      "clip_ratio/high_mean": 0.000698016050591832,
      "clip_ratio/low_mean": 0.0005534559049920063,
      "clip_ratio/low_min": 9.988600959331961e-05,
      "clip_ratio/region_mean": 0.001251471916475566,
      "epoch": 0.03621324280022633,
      "grad_norm": 0.12301915884017944,
      "learning_rate": 2e-07,
      "loss": 0.0302,
      "step": 388
    },
    {
      "clip_ratio/high_max": 0.001849981887062313,
      "clip_ratio/high_mean": 0.0006917185710335616,
      "clip_ratio/low_mean": 0.0005260355801510741,
      "clip_ratio/low_min": 5.9715281167882495e-05,
      "clip_ratio/region_mean": 0.0012177541539131198,
      "epoch": 0.036306575900226914,
      "grad_norm": 0.11322467029094696,
      "learning_rate": 2e-07,
      "loss": 0.0204,
      "step": 389
    },
    {
      "clip_ratio/high_max": 0.00219392205690383,
      "clip_ratio/high_mean": 0.0008677933637954993,
      "clip_ratio/low_mean": 0.0005832514461872051,
      "clip_ratio/low_min": 1.4460897546086926e-05,
      "clip_ratio/region_mean": 0.0014510447945212945,
      "epoch": 0.0363999090002275,
      "grad_norm": 0.11516296118497849,
      "learning_rate": 2e-07,
      "loss": 0.0073,
      "step": 390
    },
    {
      "clip_ratio/high_max": 0.0017264818234252743,
      "clip_ratio/high_mean": 0.0007142381400626618,
      "clip_ratio/low_mean": 0.0006461076209234307,
      "clip_ratio/low_min": 5.025524296797812e-05,
      "clip_ratio/region_mean": 0.0013603457882709336,
      "epoch": 0.036493242100228085,
      "grad_norm": 0.1377992182970047,
      "learning_rate": 2e-07,
      "loss": 0.0675,
      "step": 391
    },
    {
      "clip_ratio/high_max": 0.002028475490078563,
      "clip_ratio/high_mean": 0.0007738176045677392,
      "clip_ratio/low_mean": 0.0005608174833469093,
      "clip_ratio/low_min": 3.70880579794175e-05,
      "clip_ratio/region_mean": 0.001334635104285553,
      "epoch": 0.03658657520022866,
      "grad_norm": 0.11884529888629913,
      "learning_rate": 2e-07,
      "loss": 0.047,
      "step": 392
    },
    {
      "clip_ratio/high_max": 0.0017152601503767073,
      "clip_ratio/high_mean": 0.0007617962055519456,
      "clip_ratio/low_mean": 0.000550656874111155,
      "clip_ratio/low_min": 1.617773887119256e-05,
      "clip_ratio/region_mean": 0.001312453063292196,
      "epoch": 0.03667990830022925,
      "grad_norm": 0.12086061388254166,
      "learning_rate": 2e-07,
      "loss": 0.0209,
      "step": 393
    },
    {
      "clip_ratio/high_max": 0.0020684396877186373,
      "clip_ratio/high_mean": 0.0007977561308507575,
      "clip_ratio/low_mean": 0.0005664418085871148,
      "clip_ratio/low_min": 1.528864959254861e-05,
      "clip_ratio/region_mean": 0.0013641979458043352,
      "epoch": 0.036773241400229834,
      "grad_norm": 0.11817000061273575,
      "learning_rate": 2e-07,
      "loss": -0.0086,
      "step": 394
    },
    {
      "clip_ratio/high_max": 0.002025673231401015,
      "clip_ratio/high_mean": 0.0008083892971626483,
      "clip_ratio/low_mean": 0.0005080500877738814,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013164394185878336,
      "epoch": 0.03686657450023042,
      "grad_norm": 0.11603293567895889,
      "learning_rate": 2e-07,
      "loss": 0.0043,
      "step": 395
    },
    {
      "clip_ratio/high_max": 0.0019589182011259254,
      "clip_ratio/high_mean": 0.000726783418940613,
      "clip_ratio/low_mean": 0.0006322262561297975,
      "clip_ratio/low_min": 3.554187878762605e-05,
      "clip_ratio/region_mean": 0.0013590096750704106,
      "epoch": 0.036959907600231,
      "grad_norm": 0.12061294913291931,
      "learning_rate": 2e-07,
      "loss": 0.0534,
      "step": 396
    },
    {
      "clip_ratio/high_max": 0.0017086494881368708,
      "clip_ratio/high_mean": 0.0006746254966856213,
      "clip_ratio/low_mean": 0.0006281117020989768,
      "clip_ratio/low_min": 6.663306521659251e-05,
      "clip_ratio/region_mean": 0.0013027372006035876,
      "epoch": 0.03705324070023158,
      "grad_norm": 0.12303686141967773,
      "learning_rate": 2e-07,
      "loss": 0.0367,
      "step": 397
    },
    {
      "clip_ratio/high_max": 0.0017040939419530332,
      "clip_ratio/high_mean": 0.000678899274134892,
      "clip_ratio/low_mean": 0.0005510039609362138,
      "clip_ratio/low_min": 2.4588600354036316e-05,
      "clip_ratio/region_mean": 0.0012299032059672754,
      "epoch": 0.03714657380023217,
      "grad_norm": 0.10987848788499832,
      "learning_rate": 2e-07,
      "loss": 0.0317,
      "step": 398
    },
    {
      "clip_ratio/high_max": 0.0016458437348774169,
      "clip_ratio/high_mean": 0.0007616901166329626,
      "clip_ratio/low_mean": 0.0005956320401310222,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013573221021943027,
      "epoch": 0.03723990690023275,
      "grad_norm": 0.11941926926374435,
      "learning_rate": 2e-07,
      "loss": 0.0288,
      "step": 399
    },
    {
      "clip_ratio/high_max": 0.0015831498203624506,
      "clip_ratio/high_mean": 0.0006394210086000385,
      "clip_ratio/low_mean": 0.0004605914668900368,
      "clip_ratio/low_min": 1.3551604752137791e-05,
      "clip_ratio/region_mean": 0.001100012468668865,
      "epoch": 0.03733324000023333,
      "grad_norm": 0.12347234785556793,
      "learning_rate": 2e-07,
      "loss": 0.0362,
      "step": 400
    },
    {
      "clip_ratio/high_max": 0.0018264578720845748,
      "clip_ratio/high_mean": 0.0008253500200225972,
      "clip_ratio/low_mean": 0.0006199850995471934,
      "clip_ratio/low_min": 8.070744388533058e-05,
      "clip_ratio/region_mean": 0.0014453351104748435,
      "epoch": 0.037426573100233916,
      "grad_norm": 0.1205783411860466,
      "learning_rate": 2e-07,
      "loss": 0.0218,
      "step": 401
    },
    {
      "clip_ratio/high_max": 0.0017762559036782477,
      "clip_ratio/high_mean": 0.0006683251840513549,
      "clip_ratio/low_mean": 0.0006166025177662959,
      "clip_ratio/low_min": 2.9597363209177274e-05,
      "clip_ratio/region_mean": 0.0012849276772612939,
      "epoch": 0.0375199062002345,
      "grad_norm": 0.13441555202007294,
      "learning_rate": 2e-07,
      "loss": 0.0738,
      "step": 402
    },
    {
      "clip_ratio/high_max": 0.0017581367392267566,
      "clip_ratio/high_mean": 0.0006744673464709194,
      "clip_ratio/low_mean": 0.0006145869174360996,
      "clip_ratio/low_min": 5.342123768059537e-05,
      "clip_ratio/region_mean": 0.0012890542129753157,
      "epoch": 0.03761323930023508,
      "grad_norm": 0.1232827752828598,
      "learning_rate": 2e-07,
      "loss": 0.0786,
      "step": 403
    },
    {
      "clip_ratio/high_max": 0.0015349983041232917,
      "clip_ratio/high_mean": 0.0006732147876391537,
      "clip_ratio/low_mean": 0.0005914715293329209,
      "clip_ratio/low_min": 6.110829417593777e-05,
      "clip_ratio/region_mean": 0.0012646863251575269,
      "epoch": 0.037706572400235665,
      "grad_norm": 0.11538461595773697,
      "learning_rate": 2e-07,
      "loss": 0.0367,
      "step": 404
    },
    {
      "clip_ratio/high_max": 0.002222040951892268,
      "clip_ratio/high_mean": 0.0007868742013670271,
      "clip_ratio/low_mean": 0.0005668545436492423,
      "clip_ratio/low_min": 1.2475049516069703e-05,
      "clip_ratio/region_mean": 0.0013537287195504177,
      "epoch": 0.03779990550023625,
      "grad_norm": 0.1239287257194519,
      "learning_rate": 2e-07,
      "loss": 0.0066,
      "step": 405
    },
    {
      "clip_ratio/high_max": 0.0016204029780055862,
      "clip_ratio/high_mean": 0.0006828670047980268,
      "clip_ratio/low_mean": 0.0006186238288137247,
      "clip_ratio/low_min": 0.00010112248673976865,
      "clip_ratio/region_mean": 0.001301490847254172,
      "epoch": 0.037893238600236835,
      "grad_norm": 0.12326519936323166,
      "learning_rate": 2e-07,
      "loss": 0.0605,
      "step": 406
    },
    {
      "clip_ratio/high_max": 0.0019510324564180337,
      "clip_ratio/high_mean": 0.0007658493450435344,
      "clip_ratio/low_mean": 0.0005099280215290491,
      "clip_ratio/low_min": 3.564452072168933e-05,
      "clip_ratio/region_mean": 0.0012757773693010677,
      "epoch": 0.03798657170023741,
      "grad_norm": 0.12748096883296967,
      "learning_rate": 2e-07,
      "loss": -0.0211,
      "step": 407
    },
    {
      "clip_ratio/high_max": 0.0020628468482755125,
      "clip_ratio/high_mean": 0.0008341619522980182,
      "clip_ratio/low_mean": 0.0005715469487768132,
      "clip_ratio/low_min": 3.7850513763260096e-05,
      "clip_ratio/region_mean": 0.001405708899255842,
      "epoch": 0.038079904800238,
      "grad_norm": 0.12838807702064514,
      "learning_rate": 2e-07,
      "loss": 0.0197,
      "step": 408
    },
    {
      "clip_ratio/high_max": 0.0018263089768879581,
      "clip_ratio/high_mean": 0.0007088765778462403,
      "clip_ratio/low_mean": 0.0005474906483868835,
      "clip_ratio/low_min": 6.96456436344306e-06,
      "clip_ratio/region_mean": 0.0012563672098622192,
      "epoch": 0.038173237900238584,
      "grad_norm": 0.12237639725208282,
      "learning_rate": 2e-07,
      "loss": 0.0336,
      "step": 409
    },
    {
      "clip_ratio/high_max": 0.0021406182859209366,
      "clip_ratio/high_mean": 0.0008113982439681422,
      "clip_ratio/low_mean": 0.0004945800983477966,
      "clip_ratio/low_min": 2.977947679028148e-05,
      "clip_ratio/region_mean": 0.0013059783268545289,
      "epoch": 0.03826657100023917,
      "grad_norm": 0.13184009492397308,
      "learning_rate": 2e-07,
      "loss": 0.0249,
      "step": 410
    },
    {
      "clip_ratio/high_max": 0.0018464399399817921,
      "clip_ratio/high_mean": 0.0008035933788050897,
      "clip_ratio/low_mean": 0.0006142656557130977,
      "clip_ratio/low_min": 3.6554336475091986e-05,
      "clip_ratio/region_mean": 0.0014178590608935338,
      "epoch": 0.03835990410023975,
      "grad_norm": 0.12154219299554825,
      "learning_rate": 2e-07,
      "loss": 0.0115,
      "step": 411
    },
    {
      "clip_ratio/high_max": 0.0021857107130927034,
      "clip_ratio/high_mean": 0.0008745317572902422,
      "clip_ratio/low_mean": 0.0004963007122569252,
      "clip_ratio/low_min": 4.509063728619367e-05,
      "clip_ratio/region_mean": 0.001370832535030786,
      "epoch": 0.03845323720024033,
      "grad_norm": 0.12859344482421875,
      "learning_rate": 2e-07,
      "loss": 0.0282,
      "step": 412
    },
    {
      "clip_ratio/high_max": 0.0017857056700449903,
      "clip_ratio/high_mean": 0.0006907888509886106,
      "clip_ratio/low_mean": 0.0005186444832361303,
      "clip_ratio/low_min": 2.7596118343353737e-05,
      "clip_ratio/region_mean": 0.0012094333214918151,
      "epoch": 0.03854657030024092,
      "grad_norm": 0.11687982827425003,
      "learning_rate": 2e-07,
      "loss": 0.0074,
      "step": 413
    },
    {
      "clip_ratio/high_max": 0.0015598892750858795,
      "clip_ratio/high_mean": 0.0006392705681719235,
      "clip_ratio/low_mean": 0.0005820652531838277,
      "clip_ratio/low_min": 2.1591034055745695e-05,
      "clip_ratio/region_mean": 0.0012213358168082777,
      "epoch": 0.038639903400241496,
      "grad_norm": 0.11757929623126984,
      "learning_rate": 2e-07,
      "loss": 0.0331,
      "step": 414
    },
    {
      "clip_ratio/high_max": 0.0019532481601345353,
      "clip_ratio/high_mean": 0.0007526010813307948,
      "clip_ratio/low_mean": 0.000574838009015366,
      "clip_ratio/low_min": 5.15941374032991e-05,
      "clip_ratio/region_mean": 0.001327439080341719,
      "epoch": 0.03873323650024208,
      "grad_norm": 0.118524469435215,
      "learning_rate": 2e-07,
      "loss": -0.0027,
      "step": 415
    },
    {
      "clip_ratio/high_max": 0.002082292288832832,
      "clip_ratio/high_mean": 0.0007906272676336812,
      "clip_ratio/low_mean": 0.0005697506198885094,
      "clip_ratio/low_min": 7.656498382857535e-06,
      "clip_ratio/region_mean": 0.001360377878881991,
      "epoch": 0.038826569600242666,
      "grad_norm": 0.12712140381336212,
      "learning_rate": 2e-07,
      "loss": 0.0349,
      "step": 416
    },
    {
      "clip_ratio/high_max": 0.0016072593753051478,
      "clip_ratio/high_mean": 0.0006959099464438623,
      "clip_ratio/low_mean": 0.0006330057876766659,
      "clip_ratio/low_min": 3.57007274942589e-05,
      "clip_ratio/region_mean": 0.0013289156813698355,
      "epoch": 0.03891990270024325,
      "grad_norm": 0.10762687772512436,
      "learning_rate": 2e-07,
      "loss": 0.0147,
      "step": 417
    },
    {
      "clip_ratio/high_max": 0.0018354561761952937,
      "clip_ratio/high_mean": 0.0007133544168027584,
      "clip_ratio/low_mean": 0.0005252299306448549,
      "clip_ratio/low_min": 3.3713509765220806e-05,
      "clip_ratio/region_mean": 0.0012385843474476133,
      "epoch": 0.03901323580024383,
      "grad_norm": 0.10796509683132172,
      "learning_rate": 2e-07,
      "loss": 0.0242,
      "step": 418
    },
    {
      "clip_ratio/high_max": 0.0017270331918552984,
      "clip_ratio/high_mean": 0.000682954005242209,
      "clip_ratio/low_mean": 0.0006169766293169232,
      "clip_ratio/low_min": 4.547367825580295e-05,
      "clip_ratio/region_mean": 0.001299930638197111,
      "epoch": 0.039106568900244415,
      "grad_norm": 0.11778812110424042,
      "learning_rate": 2e-07,
      "loss": 0.0378,
      "step": 419
    },
    {
      "clip_ratio/high_max": 0.0015842504144529812,
      "clip_ratio/high_mean": 0.000643890118226409,
      "clip_ratio/low_mean": 0.0005384430805861484,
      "clip_ratio/low_min": 3.318064227642026e-05,
      "clip_ratio/region_mean": 0.001182333187898621,
      "epoch": 0.039199902000245,
      "grad_norm": 0.11454786360263824,
      "learning_rate": 2e-07,
      "loss": 0.0098,
      "step": 420
    },
    {
      "clip_ratio/high_max": 0.0017363987280987203,
      "clip_ratio/high_mean": 0.0007186073762568412,
      "clip_ratio/low_mean": 0.0005361959683796158,
      "clip_ratio/low_min": 2.3075503122527152e-05,
      "clip_ratio/region_mean": 0.0012548033337225206,
      "epoch": 0.039293235100245585,
      "grad_norm": 0.14187908172607422,
      "learning_rate": 2e-07,
      "loss": 0.0184,
      "step": 421
    },
    {
      "clip_ratio/high_max": 0.0019191528917872347,
      "clip_ratio/high_mean": 0.0007591036719531985,
      "clip_ratio/low_mean": 0.0005500177858266397,
      "clip_ratio/low_min": 5.3399327043734957e-05,
      "clip_ratio/region_mean": 0.0013091214386804495,
      "epoch": 0.039386568200246164,
      "grad_norm": 0.11690158396959305,
      "learning_rate": 2e-07,
      "loss": 0.0132,
      "step": 422
    },
    {
      "clip_ratio/high_max": 0.001988195777812507,
      "clip_ratio/high_mean": 0.0008226727040892001,
      "clip_ratio/low_mean": 0.0005774915989604779,
      "clip_ratio/low_min": 1.856835569924442e-05,
      "clip_ratio/region_mean": 0.0014001643066876568,
      "epoch": 0.03947990130024675,
      "grad_norm": 0.11577083170413971,
      "learning_rate": 2e-07,
      "loss": 0.0055,
      "step": 423
    },
    {
      "clip_ratio/high_max": 0.0016580955634708516,
      "clip_ratio/high_mean": 0.0006443700831368915,
      "clip_ratio/low_mean": 0.0006765044727217173,
      "clip_ratio/low_min": 7.147955420805374e-05,
      "clip_ratio/region_mean": 0.0013208745804149657,
      "epoch": 0.039573234400247334,
      "grad_norm": 0.12178140133619308,
      "learning_rate": 2e-07,
      "loss": 0.1037,
      "step": 424
    },
    {
      "clip_ratio/high_max": 0.0018633029430930037,
      "clip_ratio/high_mean": 0.0006890629301778972,
      "clip_ratio/low_mean": 0.0005968461646261858,
      "clip_ratio/low_min": 5.5288212479354115e-05,
      "clip_ratio/region_mean": 0.0012859091075370088,
      "epoch": 0.03966656750024792,
      "grad_norm": 0.11770538240671158,
      "learning_rate": 2e-07,
      "loss": 0.055,
      "step": 425
    },
    {
      "clip_ratio/high_max": 0.00172069984182599,
      "clip_ratio/high_mean": 0.0007586231167806545,
      "clip_ratio/low_mean": 0.0005650898501698975,
      "clip_ratio/low_min": 4.463002551347017e-05,
      "clip_ratio/region_mean": 0.001323712982411962,
      "epoch": 0.0397599006002485,
      "grad_norm": 0.1264885812997818,
      "learning_rate": 2e-07,
      "loss": 0.0522,
      "step": 426
    },
    {
      "clip_ratio/high_max": 0.0018600328730826732,
      "clip_ratio/high_mean": 0.0007414262381644221,
      "clip_ratio/low_mean": 0.0006611468370465445,
      "clip_ratio/low_min": 5.880843582417583e-05,
      "clip_ratio/region_mean": 0.0014025730779394507,
      "epoch": 0.03985323370024908,
      "grad_norm": 0.11060141026973724,
      "learning_rate": 2e-07,
      "loss": 0.0249,
      "step": 427
    },
    {
      "clip_ratio/high_max": 0.001553372207126813,
      "clip_ratio/high_mean": 0.0006348009728753823,
      "clip_ratio/low_mean": 0.0006448495132644894,
      "clip_ratio/low_min": 6.887811196065741e-06,
      "clip_ratio/region_mean": 0.001279650485230377,
      "epoch": 0.03994656680024967,
      "grad_norm": 0.12215851247310638,
      "learning_rate": 2e-07,
      "loss": 0.0861,
      "step": 428
    },
    {
      "clip_ratio/high_max": 0.001711247386992909,
      "clip_ratio/high_mean": 0.0007525309029006166,
      "clip_ratio/low_mean": 0.0005965703703623149,
      "clip_ratio/low_min": 0.00010234969886369072,
      "clip_ratio/region_mean": 0.001349101268715458,
      "epoch": 0.040039899900250246,
      "grad_norm": 0.1350710242986679,
      "learning_rate": 2e-07,
      "loss": 0.0131,
      "step": 429
    },
    {
      "clip_ratio/high_max": 0.00201556108368095,
      "clip_ratio/high_mean": 0.0008883250848157331,
      "clip_ratio/low_mean": 0.0005552990705837146,
      "clip_ratio/low_min": 2.6663274184102193e-05,
      "clip_ratio/region_mean": 0.0014436241508519743,
      "epoch": 0.04013323300025083,
      "grad_norm": 0.11819442361593246,
      "learning_rate": 2e-07,
      "loss": -0.0119,
      "step": 430
    },
    {
      "clip_ratio/high_max": 0.0019793869578279555,
      "clip_ratio/high_mean": 0.0008360595602425747,
      "clip_ratio/low_mean": 0.0005814457963424502,
      "clip_ratio/low_min": 4.411014833749505e-05,
      "clip_ratio/region_mean": 0.0014175053729559295,
      "epoch": 0.04022656610025142,
      "grad_norm": 0.1191720962524414,
      "learning_rate": 2e-07,
      "loss": -0.0257,
      "step": 431
    },
    {
      "clip_ratio/high_max": 0.00187696048305952,
      "clip_ratio/high_mean": 0.0007649337640032172,
      "clip_ratio/low_mean": 0.0005412335731307394,
      "clip_ratio/low_min": 2.3191123545984738e-05,
      "clip_ratio/region_mean": 0.0013061673416814301,
      "epoch": 0.040319899200252,
      "grad_norm": 0.13552697002887726,
      "learning_rate": 2e-07,
      "loss": 0.007,
      "step": 432
    },
    {
      "clip_ratio/high_max": 0.0018004282719630282,
      "clip_ratio/high_mean": 0.0007449172117048874,
      "clip_ratio/low_mean": 0.0005701249974663369,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013150422018952668,
      "epoch": 0.04041323230025258,
      "grad_norm": 0.12261927872896194,
      "learning_rate": 2e-07,
      "loss": 0.0446,
      "step": 433
    },
    {
      "clip_ratio/high_max": 0.0017152965629065875,
      "clip_ratio/high_mean": 0.0007143949951569084,
      "clip_ratio/low_mean": 0.0005856275074620498,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001300022555369651,
      "epoch": 0.040506565400253165,
      "grad_norm": 0.12421371042728424,
      "learning_rate": 2e-07,
      "loss": 0.0324,
      "step": 434
    },
    {
      "clip_ratio/high_max": 0.001589747225807514,
      "clip_ratio/high_mean": 0.000666312625980936,
      "clip_ratio/low_mean": 0.0006058425142327906,
      "clip_ratio/low_min": 4.493859159993008e-05,
      "clip_ratio/region_mean": 0.0012721551247523166,
      "epoch": 0.04059989850025375,
      "grad_norm": 0.11642207950353622,
      "learning_rate": 2e-07,
      "loss": 0.025,
      "step": 435
    },
    {
      "clip_ratio/high_max": 0.002010731812333688,
      "clip_ratio/high_mean": 0.0008159400094882585,
      "clip_ratio/low_mean": 0.0005646048348353361,
      "clip_ratio/low_min": 7.4823415161517914e-06,
      "clip_ratio/region_mean": 0.0013805448470520787,
      "epoch": 0.040693231600254336,
      "grad_norm": 0.12820373475551605,
      "learning_rate": 2e-07,
      "loss": -0.0004,
      "step": 436
    },
    {
      "clip_ratio/high_max": 0.0021220025737420656,
      "clip_ratio/high_mean": 0.000722414242773084,
      "clip_ratio/low_mean": 0.0006309702130238293,
      "clip_ratio/low_min": 5.7272294725407846e-05,
      "clip_ratio/region_mean": 0.0013533844175981358,
      "epoch": 0.040786564700254914,
      "grad_norm": 0.11796076595783234,
      "learning_rate": 2e-07,
      "loss": 0.0327,
      "step": 437
    },
    {
      "clip_ratio/high_max": 0.0021164892095839605,
      "clip_ratio/high_mean": 0.0007839306654204847,
      "clip_ratio/low_mean": 0.0006696440759696998,
      "clip_ratio/low_min": 4.658152920455905e-05,
      "clip_ratio/region_mean": 0.0014535747286572587,
      "epoch": 0.0408798978002555,
      "grad_norm": 0.1237604022026062,
      "learning_rate": 2e-07,
      "loss": 0.0097,
      "step": 438
    },
    {
      "clip_ratio/high_max": 0.0017770885024219751,
      "clip_ratio/high_mean": 0.000675656530802371,
      "clip_ratio/low_mean": 0.0006689549945804174,
      "clip_ratio/low_min": 6.909235435159644e-05,
      "clip_ratio/region_mean": 0.0013446115335682407,
      "epoch": 0.040973230900256084,
      "grad_norm": 0.12373483926057816,
      "learning_rate": 2e-07,
      "loss": 0.0653,
      "step": 439
    },
    {
      "clip_ratio/high_max": 0.0022465031543106306,
      "clip_ratio/high_mean": 0.0008405645749007817,
      "clip_ratio/low_mean": 0.0005956086788501125,
      "clip_ratio/low_min": 4.918804006592836e-05,
      "clip_ratio/region_mean": 0.0014361732282850426,
      "epoch": 0.04106656400025666,
      "grad_norm": 0.1197066679596901,
      "learning_rate": 2e-07,
      "loss": 0.0009,
      "step": 440
    },
    {
      "clip_ratio/high_max": 0.002001830449444242,
      "clip_ratio/high_mean": 0.0007812343865225557,
      "clip_ratio/low_mean": 0.0006093782812968129,
      "clip_ratio/low_min": 5.8935342167387716e-05,
      "clip_ratio/region_mean": 0.0013906126732763369,
      "epoch": 0.04115989710025725,
      "grad_norm": 0.11464092135429382,
      "learning_rate": 2e-07,
      "loss": 0.0549,
      "step": 441
    },
    {
      "clip_ratio/high_max": 0.001958455926796887,
      "clip_ratio/high_mean": 0.0008043298039410729,
      "clip_ratio/low_mean": 0.000591434658417711,
      "clip_ratio/low_min": 8.578054985264316e-05,
      "clip_ratio/region_mean": 0.001395764422341017,
      "epoch": 0.04125323020025783,
      "grad_norm": 0.12089533358812332,
      "learning_rate": 2e-07,
      "loss": 0.029,
      "step": 442
    },
    {
      "clip_ratio/high_max": 0.0018371817204752006,
      "clip_ratio/high_mean": 0.0007746384526399197,
      "clip_ratio/low_mean": 0.0006588350051970338,
      "clip_ratio/low_min": 6.700879293930484e-05,
      "clip_ratio/region_mean": 0.0014334734587464482,
      "epoch": 0.04134656330025842,
      "grad_norm": 0.15603022277355194,
      "learning_rate": 2e-07,
      "loss": 0.0327,
      "step": 443
    },
    {
      "clip_ratio/high_max": 0.0017309084105363581,
      "clip_ratio/high_mean": 0.0007445210158039117,
      "clip_ratio/low_mean": 0.0006156266663310817,
      "clip_ratio/low_min": 4.8328525735996664e-05,
      "clip_ratio/region_mean": 0.0013601476857729722,
      "epoch": 0.041439896400258996,
      "grad_norm": 0.12456014007329941,
      "learning_rate": 2e-07,
      "loss": 0.0264,
      "step": 444
    },
    {
      "clip_ratio/high_max": 0.0017974613838305231,
      "clip_ratio/high_mean": 0.0006904109686729498,
      "clip_ratio/low_mean": 0.0006568872586285579,
      "clip_ratio/low_min": 6.457977042373386e-05,
      "clip_ratio/region_mean": 0.0013472982100211084,
      "epoch": 0.04153322950025958,
      "grad_norm": 0.13176009058952332,
      "learning_rate": 2e-07,
      "loss": 0.0288,
      "step": 445
    },
    {
      "clip_ratio/high_max": 0.0018141597138310317,
      "clip_ratio/high_mean": 0.0007248572092066752,
      "clip_ratio/low_mean": 0.0005698010827472899,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012946583119628485,
      "epoch": 0.04162656260026017,
      "grad_norm": 0.11641500145196915,
      "learning_rate": 2e-07,
      "loss": 0.0187,
      "step": 446
    },
    {
      "clip_ratio/high_max": 0.0018931381491711363,
      "clip_ratio/high_mean": 0.0007787392441969132,
      "clip_ratio/low_mean": 0.0006778724127798341,
      "clip_ratio/low_min": 2.065205444523599e-05,
      "clip_ratio/region_mean": 0.0014566116660716943,
      "epoch": 0.04171989570026075,
      "grad_norm": 0.12853413820266724,
      "learning_rate": 2e-07,
      "loss": 0.0346,
      "step": 447
    },
    {
      "clip_ratio/high_max": 0.0016353964056179393,
      "clip_ratio/high_mean": 0.0007090633152984083,
      "clip_ratio/low_mean": 0.0006230837061593775,
      "clip_ratio/low_min": 5.759231135016307e-05,
      "clip_ratio/region_mean": 0.001332147036009701,
      "epoch": 0.04181322880026133,
      "grad_norm": 0.12481112778186798,
      "learning_rate": 2e-07,
      "loss": 0.0218,
      "step": 448
    },
    {
      "clip_ratio/high_max": 0.0019147114580846392,
      "clip_ratio/high_mean": 0.0007151903282647254,
      "clip_ratio/low_mean": 0.0006343818236018706,
      "clip_ratio/low_min": 1.3037129974691197e-05,
      "clip_ratio/region_mean": 0.0013495721541403327,
      "epoch": 0.041906561900261916,
      "grad_norm": 0.13248465955257416,
      "learning_rate": 2e-07,
      "loss": 0.0446,
      "step": 449
    },
    {
      "clip_ratio/high_max": 0.0018984083799296059,
      "clip_ratio/high_mean": 0.0008438753120572073,
      "clip_ratio/low_mean": 0.0006261078033276135,
      "clip_ratio/low_min": 5.055108886153903e-05,
      "clip_ratio/region_mean": 0.0014699831190227997,
      "epoch": 0.0419998950002625,
      "grad_norm": 0.12904009222984314,
      "learning_rate": 2e-07,
      "loss": 0.0165,
      "step": 450
    },
    {
      "clip_ratio/high_max": 0.002016342041315511,
      "clip_ratio/high_mean": 0.0008539397804270266,
      "clip_ratio/low_mean": 0.0005726678100472782,
      "clip_ratio/low_min": 1.2235708709340543e-05,
      "clip_ratio/region_mean": 0.001426607632311061,
      "epoch": 0.042093228100263086,
      "grad_norm": 0.13066567480564117,
      "learning_rate": 2e-07,
      "loss": 0.062,
      "step": 451
    },
    {
      "clip_ratio/high_max": 0.001846640014264267,
      "clip_ratio/high_mean": 0.0007470063410437433,
      "clip_ratio/low_mean": 0.0005799997143185465,
      "clip_ratio/low_min": 1.40860938699916e-05,
      "clip_ratio/region_mean": 0.001327006033534417,
      "epoch": 0.042186561200263664,
      "grad_norm": 0.19789563119411469,
      "learning_rate": 2e-07,
      "loss": 0.0167,
      "step": 452
    },
    {
      "clip_ratio/high_max": 0.0017684752237983048,
      "clip_ratio/high_mean": 0.0006986524131207261,
      "clip_ratio/low_mean": 0.0005649905106110964,
      "clip_ratio/low_min": 1.4070238648855593e-05,
      "clip_ratio/region_mean": 0.0012636429491976742,
      "epoch": 0.04227989430026425,
      "grad_norm": 0.12359024584293365,
      "learning_rate": 2e-07,
      "loss": 0.0069,
      "step": 453
    },
    {
      "clip_ratio/high_max": 0.001910876697365893,
      "clip_ratio/high_mean": 0.0007704495492362184,
      "clip_ratio/low_mean": 0.0005897570154047571,
      "clip_ratio/low_min": 5.442161591417971e-05,
      "clip_ratio/region_mean": 0.001360206566459965,
      "epoch": 0.042373227400264835,
      "grad_norm": 0.12701749801635742,
      "learning_rate": 2e-07,
      "loss": 0.0216,
      "step": 454
    },
    {
      "clip_ratio/high_max": 0.0018397683343209792,
      "clip_ratio/high_mean": 0.0008351807409781031,
      "clip_ratio/low_mean": 0.0006753395973646548,
      "clip_ratio/low_min": 4.957378860126482e-05,
      "clip_ratio/region_mean": 0.0015105203710845672,
      "epoch": 0.04246656050026541,
      "grad_norm": 0.12606306374073029,
      "learning_rate": 2e-07,
      "loss": -0.0086,
      "step": 455
    },
    {
      "clip_ratio/high_max": 0.00195910360707785,
      "clip_ratio/high_mean": 0.0007453814087057253,
      "clip_ratio/low_mean": 0.0006349608993332367,
      "clip_ratio/low_min": 3.224107786081731e-05,
      "clip_ratio/region_mean": 0.001380342298944015,
      "epoch": 0.042559893600266,
      "grad_norm": 0.13856789469718933,
      "learning_rate": 2e-07,
      "loss": 0.0234,
      "step": 456
    },
    {
      "clip_ratio/high_max": 0.0018492992930987384,
      "clip_ratio/high_mean": 0.0007245297456393018,
      "clip_ratio/low_mean": 0.0006384830485330895,
      "clip_ratio/low_min": 1.9154153051204048e-05,
      "clip_ratio/region_mean": 0.0013630127905344125,
      "epoch": 0.04265322670026658,
      "grad_norm": 0.1254524290561676,
      "learning_rate": 2e-07,
      "loss": 0.052,
      "step": 457
    },
    {
      "clip_ratio/high_max": 0.001859706037066644,
      "clip_ratio/high_mean": 0.0007021908331807936,
      "clip_ratio/low_mean": 0.0005660332808474777,
      "clip_ratio/low_min": 2.7907029107154813e-05,
      "clip_ratio/region_mean": 0.0012682241467700806,
      "epoch": 0.04274655980026717,
      "grad_norm": 0.11635055392980576,
      "learning_rate": 2e-07,
      "loss": 0.0508,
      "step": 458
    },
    {
      "clip_ratio/high_max": 0.001968060838407837,
      "clip_ratio/high_mean": 0.0008553091047360795,
      "clip_ratio/low_mean": 0.0005853095835846034,
      "clip_ratio/low_min": 8.647306549391942e-05,
      "clip_ratio/region_mean": 0.0014406187219719868,
      "epoch": 0.04283989290026775,
      "grad_norm": 0.12051598727703094,
      "learning_rate": 2e-07,
      "loss": 0.0097,
      "step": 459
    },
    {
      "clip_ratio/high_max": 0.0020751801930600777,
      "clip_ratio/high_mean": 0.0008141606776916888,
      "clip_ratio/low_mean": 0.0006304424659901997,
      "clip_ratio/low_min": 7.979600104590645e-05,
      "clip_ratio/region_mean": 0.0014446031200350262,
      "epoch": 0.04293322600026833,
      "grad_norm": 0.12642183899879456,
      "learning_rate": 2e-07,
      "loss": 0.077,
      "step": 460
    },
    {
      "clip_ratio/high_max": 0.001788652065442875,
      "clip_ratio/high_mean": 0.0007618489325977862,
      "clip_ratio/low_mean": 0.0006473122775787488,
      "clip_ratio/low_min": 6.924461831658846e-05,
      "clip_ratio/region_mean": 0.001409161188348662,
      "epoch": 0.04302655910026892,
      "grad_norm": 0.13254590332508087,
      "learning_rate": 2e-07,
      "loss": 0.0454,
      "step": 461
    },
    {
      "clip_ratio/high_max": 0.0018917141096608248,
      "clip_ratio/high_mean": 0.0007487091352231801,
      "clip_ratio/low_mean": 0.0006078190617699875,
      "clip_ratio/low_min": 2.7232941192778526e-05,
      "clip_ratio/region_mean": 0.0013565281915361993,
      "epoch": 0.0431198922002695,
      "grad_norm": 0.13048475980758667,
      "learning_rate": 2e-07,
      "loss": 0.0722,
      "step": 462
    },
    {
      "clip_ratio/high_max": 0.001978902240807656,
      "clip_ratio/high_mean": 0.0008076635513134534,
      "clip_ratio/low_mean": 0.0006850262207080959,
      "clip_ratio/low_min": 3.447567814873764e-05,
      "clip_ratio/region_mean": 0.0014926898074918427,
      "epoch": 0.04321322530027008,
      "grad_norm": 0.12645657360553741,
      "learning_rate": 2e-07,
      "loss": 0.0475,
      "step": 463
    },
    {
      "clip_ratio/high_max": 0.0020373752449813765,
      "clip_ratio/high_mean": 0.0008047998453548644,
      "clip_ratio/low_mean": 0.0005875231472600717,
      "clip_ratio/low_min": 1.2646702089114115e-05,
      "clip_ratio/region_mean": 0.0013923229998908937,
      "epoch": 0.043306558400270666,
      "grad_norm": 0.11570800095796585,
      "learning_rate": 2e-07,
      "loss": 0.0399,
      "step": 464
    },
    {
      "clip_ratio/high_max": 0.0018375962536083534,
      "clip_ratio/high_mean": 0.0007714734183537075,
      "clip_ratio/low_mean": 0.0006205290101206629,
      "clip_ratio/low_min": 3.364316944498569e-05,
      "clip_ratio/region_mean": 0.0013920024503022432,
      "epoch": 0.04339989150027125,
      "grad_norm": 0.12506726384162903,
      "learning_rate": 2e-07,
      "loss": 0.0256,
      "step": 465
    },
    {
      "clip_ratio/high_max": 0.0016282618453260511,
      "clip_ratio/high_mean": 0.000691588458721526,
      "clip_ratio/low_mean": 0.0005914965258853044,
      "clip_ratio/low_min": 1.9778481146204285e-05,
      "clip_ratio/region_mean": 0.0012830849846068304,
      "epoch": 0.04349322460027183,
      "grad_norm": 0.1287083625793457,
      "learning_rate": 2e-07,
      "loss": 0.0274,
      "step": 466
    },
    {
      "clip_ratio/high_max": 0.0023632442971575074,
      "clip_ratio/high_mean": 0.0010246125129924621,
      "clip_ratio/low_mean": 0.0007511674048146233,
      "clip_ratio/low_min": 5.4476713557960466e-05,
      "clip_ratio/region_mean": 0.0017757799214450642,
      "epoch": 0.043586557700272414,
      "grad_norm": 0.1350337713956833,
      "learning_rate": 2e-07,
      "loss": 0.0134,
      "step": 467
    },
    {
      "clip_ratio/high_max": 0.001926583114254754,
      "clip_ratio/high_mean": 0.0008448069820587989,
      "clip_ratio/low_mean": 0.0006421939779102104,
      "clip_ratio/low_min": 5.552802758757025e-05,
      "clip_ratio/region_mean": 0.0014870009654259775,
      "epoch": 0.043679890800273,
      "grad_norm": 0.12916550040245056,
      "learning_rate": 2e-07,
      "loss": 0.0112,
      "step": 468
    },
    {
      "clip_ratio/high_max": 0.0019348768000782002,
      "clip_ratio/high_mean": 0.0007833419513190165,
      "clip_ratio/low_mean": 0.0006311959768936504,
      "clip_ratio/low_min": 3.614551133068744e-05,
      "clip_ratio/region_mean": 0.0014145379027468152,
      "epoch": 0.043773223900273585,
      "grad_norm": 0.13057181239128113,
      "learning_rate": 2e-07,
      "loss": 0.0375,
      "step": 469
    },
    {
      "clip_ratio/high_max": 0.0017748103164194617,
      "clip_ratio/high_mean": 0.0007297284410014981,
      "clip_ratio/low_mean": 0.0005610586258626427,
      "clip_ratio/low_min": 5.169616633793339e-05,
      "clip_ratio/region_mean": 0.0012907870914204977,
      "epoch": 0.04386655700027416,
      "grad_norm": 0.2490302473306656,
      "learning_rate": 2e-07,
      "loss": 0.0355,
      "step": 470
    },
    {
      "clip_ratio/high_max": 0.002000537184358109,
      "clip_ratio/high_mean": 0.0008319806511281058,
      "clip_ratio/low_mean": 0.0005876981786059332,
      "clip_ratio/low_min": 6.802537882322213e-05,
      "clip_ratio/region_mean": 0.0014196788433764596,
      "epoch": 0.04395989010027475,
      "grad_norm": 0.13387982547283173,
      "learning_rate": 2e-07,
      "loss": 0.0093,
      "step": 471
    },
    {
      "clip_ratio/high_max": 0.0017401247241650708,
      "clip_ratio/high_mean": 0.0006841897302365396,
      "clip_ratio/low_mean": 0.0006540201975440141,
      "clip_ratio/low_min": 8.64262174218311e-05,
      "clip_ratio/region_mean": 0.001338209902314702,
      "epoch": 0.044053223200275334,
      "grad_norm": 0.11587109416723251,
      "learning_rate": 2e-07,
      "loss": 0.0266,
      "step": 472
    },
    {
      "clip_ratio/high_max": 0.0018274358517373912,
      "clip_ratio/high_mean": 0.0007513132659369148,
      "clip_ratio/low_mean": 0.0006456970659201033,
      "clip_ratio/low_min": 8.223280292440904e-05,
      "clip_ratio/region_mean": 0.0013970103136671241,
      "epoch": 0.04414655630027592,
      "grad_norm": 0.14696019887924194,
      "learning_rate": 2e-07,
      "loss": 0.0438,
      "step": 473
    },
    {
      "clip_ratio/high_max": 0.001910316183057148,
      "clip_ratio/high_mean": 0.0007853966380935162,
      "clip_ratio/low_mean": 0.0006032477294866112,
      "clip_ratio/low_min": 5.201619296713034e-05,
      "clip_ratio/region_mean": 0.0013886443375668023,
      "epoch": 0.0442398894002765,
      "grad_norm": 0.12520448863506317,
      "learning_rate": 2e-07,
      "loss": 0.0367,
      "step": 474
    },
    {
      "clip_ratio/high_max": 0.001820290541218128,
      "clip_ratio/high_mean": 0.0007888156069384422,
      "clip_ratio/low_mean": 0.0006824490264989436,
      "clip_ratio/low_min": 7.982896750036161e-05,
      "clip_ratio/region_mean": 0.0014712646589032374,
      "epoch": 0.04433322250027708,
      "grad_norm": 0.12633632123470306,
      "learning_rate": 2e-07,
      "loss": 0.0236,
      "step": 475
    },
    {
      "clip_ratio/high_max": 0.002008898776693968,
      "clip_ratio/high_mean": 0.0007447817861248041,
      "clip_ratio/low_mean": 0.0005726673516619485,
      "clip_ratio/low_min": 7.860851383156842e-05,
      "clip_ratio/region_mean": 0.0013174491250538267,
      "epoch": 0.04442655560027767,
      "grad_norm": 0.1192314401268959,
      "learning_rate": 2e-07,
      "loss": 0.0293,
      "step": 476
    },
    {
      "clip_ratio/high_max": 0.0023636059631826356,
      "clip_ratio/high_mean": 0.0008198912291845772,
      "clip_ratio/low_mean": 0.0007085239740263205,
      "clip_ratio/low_min": 6.083705375203863e-05,
      "clip_ratio/region_mean": 0.0015284151850210037,
      "epoch": 0.04451988870027825,
      "grad_norm": 0.13008737564086914,
      "learning_rate": 2e-07,
      "loss": 0.0351,
      "step": 477
    },
    {
      "clip_ratio/high_max": 0.0018168637943745125,
      "clip_ratio/high_mean": 0.0007782192096783547,
      "clip_ratio/low_mean": 0.000637017206827295,
      "clip_ratio/low_min": 4.74719518024358e-05,
      "clip_ratio/region_mean": 0.001415236427419586,
      "epoch": 0.04461322180027883,
      "grad_norm": 0.11413247138261795,
      "learning_rate": 2e-07,
      "loss": 0.0258,
      "step": 478
    },
    {
      "clip_ratio/high_max": 0.0018756001045403536,
      "clip_ratio/high_mean": 0.0008060260552156251,
      "clip_ratio/low_mean": 0.0006317216266324976,
      "clip_ratio/low_min": 2.2152676137920935e-05,
      "clip_ratio/region_mean": 0.00143774762909743,
      "epoch": 0.044706554900279416,
      "grad_norm": 0.11632099747657776,
      "learning_rate": 2e-07,
      "loss": 0.0221,
      "step": 479
    },
    {
      "clip_ratio/high_max": 0.0020333194552222267,
      "clip_ratio/high_mean": 0.0008790843785391189,
      "clip_ratio/low_mean": 0.0005179378913453547,
      "clip_ratio/low_min": 8.380262443097308e-06,
      "clip_ratio/region_mean": 0.0013970222571515478,
      "epoch": 0.04479988800028,
      "grad_norm": 0.14135634899139404,
      "learning_rate": 2e-07,
      "loss": 0.0254,
      "step": 480
    },
    {
      "clip_ratio/high_max": 0.0018009403283940628,
      "clip_ratio/high_mean": 0.0007572115646325983,
      "clip_ratio/low_mean": 0.0006490078012575395,
      "clip_ratio/low_min": 2.005515943892533e-05,
      "clip_ratio/region_mean": 0.0014062193477002438,
      "epoch": 0.04489322110028058,
      "grad_norm": 0.13307270407676697,
      "learning_rate": 2e-07,
      "loss": 0.0343,
      "step": 481
    },
    {
      "clip_ratio/high_max": 0.0019862474837282207,
      "clip_ratio/high_mean": 0.0007347618593485095,
      "clip_ratio/low_mean": 0.0004976794734830037,
      "clip_ratio/low_min": 3.0547765163646545e-05,
      "clip_ratio/region_mean": 0.0012324413437454496,
      "epoch": 0.044986554200281165,
      "grad_norm": 0.13349904119968414,
      "learning_rate": 2e-07,
      "loss": 0.0046,
      "step": 482
    },
    {
      "clip_ratio/high_max": 0.001969147240743041,
      "clip_ratio/high_mean": 0.0008334991234733025,
      "clip_ratio/low_mean": 0.0006813415075157536,
      "clip_ratio/low_min": 2.9812025786668528e-05,
      "clip_ratio/region_mean": 0.0015148406018852256,
      "epoch": 0.04507988730028175,
      "grad_norm": 0.13404598832130432,
      "learning_rate": 2e-07,
      "loss": 0.0557,
      "step": 483
    },
    {
      "clip_ratio/high_max": 0.002128822870872682,
      "clip_ratio/high_mean": 0.0009082065134862205,
      "clip_ratio/low_mean": 0.0006188216939335689,
      "clip_ratio/low_min": 2.636007047840394e-05,
      "clip_ratio/region_mean": 0.0015270282201527152,
      "epoch": 0.045173220400282335,
      "grad_norm": 0.13563790917396545,
      "learning_rate": 2e-07,
      "loss": -0.0206,
      "step": 484
    },
    {
      "clip_ratio/high_max": 0.0021564526614383794,
      "clip_ratio/high_mean": 0.0008959547922131605,
      "clip_ratio/low_mean": 0.0006271830134210177,
      "clip_ratio/low_min": 6.0532453971973155e-05,
      "clip_ratio/region_mean": 0.0015231378238240723,
      "epoch": 0.04526655350028291,
      "grad_norm": 0.1279647946357727,
      "learning_rate": 2e-07,
      "loss": -0.0132,
      "step": 485
    },
    {
      "clip_ratio/high_max": 0.002161427135433769,
      "clip_ratio/high_mean": 0.0009529424387437757,
      "clip_ratio/low_mean": 0.0005686108588633942,
      "clip_ratio/low_min": 7.374899632850429e-05,
      "clip_ratio/region_mean": 0.0015215532948786858,
      "epoch": 0.0453598866002835,
      "grad_norm": 0.1155356913805008,
      "learning_rate": 2e-07,
      "loss": 0.005,
      "step": 486
    },
    {
      "clip_ratio/high_max": 0.002026515157922404,
      "clip_ratio/high_mean": 0.0008240645165642491,
      "clip_ratio/low_mean": 0.0005802326213597553,
      "clip_ratio/low_min": 2.812505954352673e-05,
      "clip_ratio/region_mean": 0.0014042971488379408,
      "epoch": 0.045453219700284084,
      "grad_norm": 0.12698383629322052,
      "learning_rate": 2e-07,
      "loss": 0.0078,
      "step": 487
    },
    {
      "clip_ratio/high_max": 0.001922994626511354,
      "clip_ratio/high_mean": 0.0007929826406325446,
      "clip_ratio/low_mean": 0.0006118523224358796,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014048349985387176,
      "epoch": 0.04554655280028467,
      "grad_norm": 0.12232217937707901,
      "learning_rate": 2e-07,
      "loss": 0.0029,
      "step": 488
    },
    {
      "clip_ratio/high_max": 0.0020258961121726315,
      "clip_ratio/high_mean": 0.0008030399530980503,
      "clip_ratio/low_mean": 0.0007230992250697454,
      "clip_ratio/low_min": 8.407700715906685e-05,
      "clip_ratio/region_mean": 0.001526139210909605,
      "epoch": 0.04563988590028525,
      "grad_norm": 0.13492295145988464,
      "learning_rate": 2e-07,
      "loss": 0.068,
      "step": 489
    },
    {
      "clip_ratio/high_max": 0.0023484741104766726,
      "clip_ratio/high_mean": 0.000894650202099001,
      "clip_ratio/low_mean": 0.0007108736572263297,
      "clip_ratio/low_min": 7.80571426730603e-05,
      "clip_ratio/region_mean": 0.0016055238666012883,
      "epoch": 0.04573321900028583,
      "grad_norm": 0.13307319581508636,
      "learning_rate": 2e-07,
      "loss": 0.0574,
      "step": 490
    },
    {
      "clip_ratio/high_max": 0.0022369191101461183,
      "clip_ratio/high_mean": 0.0009330135417258134,
      "clip_ratio/low_mean": 0.0006291696881817188,
      "clip_ratio/low_min": 7.408109195239376e-05,
      "clip_ratio/region_mean": 0.0015621832353645004,
      "epoch": 0.04582655210028642,
      "grad_norm": 0.14723420143127441,
      "learning_rate": 2e-07,
      "loss": -0.009,
      "step": 491
    },
    {
      "clip_ratio/high_max": 0.0015179910042206757,
      "clip_ratio/high_mean": 0.0006145557508716593,
      "clip_ratio/low_mean": 0.0006580953631782904,
      "clip_ratio/low_min": 7.03976347722346e-05,
      "clip_ratio/region_mean": 0.0012726511013170239,
      "epoch": 0.045919885200286996,
      "grad_norm": 0.11829836666584015,
      "learning_rate": 2e-07,
      "loss": 0.0836,
      "step": 492
    },
    {
      "clip_ratio/high_max": 0.001707770748907933,
      "clip_ratio/high_mean": 0.0007141609257814707,
      "clip_ratio/low_mean": 0.0005698990962628159,
      "clip_ratio/low_min": 2.446541748213349e-05,
      "clip_ratio/region_mean": 0.001284059999306919,
      "epoch": 0.04601321830028758,
      "grad_norm": 0.11830785125494003,
      "learning_rate": 2e-07,
      "loss": 0.0356,
      "step": 493
    },
    {
      "clip_ratio/high_max": 0.0018666433679754846,
      "clip_ratio/high_mean": 0.0007922782351670321,
      "clip_ratio/low_mean": 0.0007456970361090498,
      "clip_ratio/low_min": 3.9176505197247025e-05,
      "clip_ratio/region_mean": 0.0015379752512671985,
      "epoch": 0.046106551400288166,
      "grad_norm": 0.12381519377231598,
      "learning_rate": 2e-07,
      "loss": 0.0311,
      "step": 494
    },
    {
      "clip_ratio/high_max": 0.001854005407949444,
      "clip_ratio/high_mean": 0.0008238007285399362,
      "clip_ratio/low_mean": 0.000575413012484205,
      "clip_ratio/low_min": 6.497345384559594e-05,
      "clip_ratio/region_mean": 0.0013992137064633425,
      "epoch": 0.04619988450028875,
      "grad_norm": 0.12948384881019592,
      "learning_rate": 2e-07,
      "loss": -0.0019,
      "step": 495
    },
    {
      "clip_ratio/high_max": 0.0020317581675044494,
      "clip_ratio/high_mean": 0.0007746997662252397,
      "clip_ratio/low_mean": 0.0006825306627433747,
      "clip_ratio/low_min": 4.632042328012176e-05,
      "clip_ratio/region_mean": 0.0014572304062312469,
      "epoch": 0.04629321760028933,
      "grad_norm": 0.13935619592666626,
      "learning_rate": 2e-07,
      "loss": 0.0482,
      "step": 496
    },
    {
      "clip_ratio/high_max": 0.002130854980350705,
      "clip_ratio/high_mean": 0.0008616955492470879,
      "clip_ratio/low_mean": 0.0006189533505676081,
      "clip_ratio/low_min": 2.6722931579570286e-05,
      "clip_ratio/region_mean": 0.0014806488834437914,
      "epoch": 0.046386550700289915,
      "grad_norm": 0.12275732308626175,
      "learning_rate": 2e-07,
      "loss": 0.0265,
      "step": 497
    },
    {
      "clip_ratio/high_max": 0.0020626810219255276,
      "clip_ratio/high_mean": 0.0007578172535431804,
      "clip_ratio/low_mean": 0.0006987713823036756,
      "clip_ratio/low_min": 2.6179177439189516e-05,
      "clip_ratio/region_mean": 0.0014565886194759514,
      "epoch": 0.0464798838002905,
      "grad_norm": 0.13679419457912445,
      "learning_rate": 2e-07,
      "loss": 0.0735,
      "step": 498
    },
    {
      "clip_ratio/high_max": 0.0018492375820642337,
      "clip_ratio/high_mean": 0.0007298536493181018,
      "clip_ratio/low_mean": 0.0006207284131960478,
      "clip_ratio/low_min": 5.88807006351999e-05,
      "clip_ratio/region_mean": 0.0013505820606951602,
      "epoch": 0.046573216900291085,
      "grad_norm": 0.1103619858622551,
      "learning_rate": 2e-07,
      "loss": 0.0195,
      "step": 499
    },
    {
      "clip_ratio/high_max": 0.0019186159843229689,
      "clip_ratio/high_mean": 0.0007655673234694405,
      "clip_ratio/low_mean": 0.0005962698664916388,
      "clip_ratio/low_min": 2.233069153589895e-05,
      "clip_ratio/region_mean": 0.0013618372031487525,
      "epoch": 0.046666550000291664,
      "grad_norm": 0.13140170276165009,
      "learning_rate": 2e-07,
      "loss": -0.0066,
      "step": 500
    },
    {
      "clip_ratio/high_max": 0.002101513062370941,
      "clip_ratio/high_mean": 0.0008340467520611128,
      "clip_ratio/low_mean": 0.0007634428402525373,
      "clip_ratio/low_min": 7.973694300744683e-05,
      "clip_ratio/region_mean": 0.0015974895904946607,
      "epoch": 0.04675988310029225,
      "grad_norm": 0.15203750133514404,
      "learning_rate": 2e-07,
      "loss": 0.0497,
      "step": 501
    },
    {
      "clip_ratio/high_max": 0.001876110654848162,
      "clip_ratio/high_mean": 0.0007428601875290042,
      "clip_ratio/low_mean": 0.0006086422536100144,
      "clip_ratio/low_min": 2.500362643331755e-05,
      "clip_ratio/region_mean": 0.0013515024475054815,
      "epoch": 0.046853216200292834,
      "grad_norm": 0.12534724175930023,
      "learning_rate": 2e-07,
      "loss": 0.0567,
      "step": 502
    },
    {
      "clip_ratio/high_max": 0.0019188530786777847,
      "clip_ratio/high_mean": 0.0008121489190671127,
      "clip_ratio/low_mean": 0.0007653781794942915,
      "clip_ratio/low_min": 3.324529461679049e-05,
      "clip_ratio/region_mean": 0.0015775270876474679,
      "epoch": 0.04694654930029342,
      "grad_norm": 0.13307712972164154,
      "learning_rate": 2e-07,
      "loss": 0.0409,
      "step": 503
    },
    {
      "clip_ratio/high_max": 0.0020770316987182014,
      "clip_ratio/high_mean": 0.0008291678932437208,
      "clip_ratio/low_mean": 0.0006928369293746073,
      "clip_ratio/low_min": 7.08294228388695e-05,
      "clip_ratio/region_mean": 0.0015220048007904552,
      "epoch": 0.047039882400294,
      "grad_norm": 0.14268989861011505,
      "learning_rate": 2e-07,
      "loss": 0.0508,
      "step": 504
    },
    {
      "clip_ratio/high_max": 0.001973775557416957,
      "clip_ratio/high_mean": 0.0007764970814605476,
      "clip_ratio/low_mean": 0.0005938445865467656,
      "clip_ratio/low_min": 1.6344141840818338e-05,
      "clip_ratio/region_mean": 0.0013703416734642815,
      "epoch": 0.04713321550029458,
      "grad_norm": 0.12510068714618683,
      "learning_rate": 2e-07,
      "loss": 0.0259,
      "step": 505
    },
    {
      "clip_ratio/high_max": 0.0017966504965443164,
      "clip_ratio/high_mean": 0.0007113698375178501,
      "clip_ratio/low_mean": 0.0006904272031533765,
      "clip_ratio/low_min": 3.632706921052886e-05,
      "clip_ratio/region_mean": 0.0014017970315762796,
      "epoch": 0.04722654860029517,
      "grad_norm": 0.12421339750289917,
      "learning_rate": 2e-07,
      "loss": 0.0028,
      "step": 506
    },
    {
      "clip_ratio/high_max": 0.0018278961688338313,
      "clip_ratio/high_mean": 0.0008187573967006756,
      "clip_ratio/low_mean": 0.0005875160941286595,
      "clip_ratio/low_min": 2.2852533220429905e-05,
      "clip_ratio/region_mean": 0.0014062735026527662,
      "epoch": 0.047319881700295746,
      "grad_norm": 0.13031218945980072,
      "learning_rate": 2e-07,
      "loss": 0.0302,
      "step": 507
    },
    {
      "clip_ratio/high_max": 0.002324550488992827,
      "clip_ratio/high_mean": 0.0009599067179806298,
      "clip_ratio/low_mean": 0.0007103462903614854,
      "clip_ratio/low_min": 6.337150261970237e-05,
      "clip_ratio/region_mean": 0.001670253011980094,
      "epoch": 0.04741321480029633,
      "grad_norm": 0.1300336718559265,
      "learning_rate": 2e-07,
      "loss": 0.0031,
      "step": 508
    },
    {
      "clip_ratio/high_max": 0.001830149587476626,
      "clip_ratio/high_mean": 0.0007993463223101571,
      "clip_ratio/low_mean": 0.0006755232680006884,
      "clip_ratio/low_min": 5.068012615083717e-05,
      "clip_ratio/region_mean": 0.0014748695975868031,
      "epoch": 0.04750654790029692,
      "grad_norm": 0.13169723749160767,
      "learning_rate": 2e-07,
      "loss": 0.032,
      "step": 509
    },
    {
      "clip_ratio/high_max": 0.002151258486264851,
      "clip_ratio/high_mean": 0.0009018862911034375,
      "clip_ratio/low_mean": 0.0007169297323343926,
      "clip_ratio/low_min": 7.104249743861146e-05,
      "clip_ratio/region_mean": 0.0016188160407182295,
      "epoch": 0.0475998810002975,
      "grad_norm": 0.13975879549980164,
      "learning_rate": 2e-07,
      "loss": 0.0441,
      "step": 510
    },
    {
      "clip_ratio/high_max": 0.0020038730472151656,
      "clip_ratio/high_mean": 0.0007748464831820456,
      "clip_ratio/low_mean": 0.0005797157123197394,
      "clip_ratio/low_min": 3.269920216553146e-05,
      "clip_ratio/region_mean": 0.001354562209598953,
      "epoch": 0.04769321410029808,
      "grad_norm": 0.1201063022017479,
      "learning_rate": 2e-07,
      "loss": 0.0087,
      "step": 511
    },
    {
      "clip_ratio/high_max": 0.0017223360810021404,
      "clip_ratio/high_mean": 0.0007924489473225549,
      "clip_ratio/low_mean": 0.0007499489820474992,
      "clip_ratio/low_min": 4.7501595872745384e-05,
      "clip_ratio/region_mean": 0.0015423979239130858,
      "epoch": 0.047786547200298665,
      "grad_norm": 0.1441613733768463,
      "learning_rate": 2e-07,
      "loss": 0.0207,
      "step": 512
    },
    {
      "clip_ratio/high_max": 0.0016911438033275772,
      "clip_ratio/high_mean": 0.0006324619535007514,
      "clip_ratio/low_mean": 0.000622469604422804,
      "clip_ratio/low_min": 4.368683403299656e-05,
      "clip_ratio/region_mean": 0.0012549315360956825,
      "completions/clipped_ratio": 0.018702915736607095,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4090.0,
      "completions/mean_length": 660.1011962890625,
      "completions/mean_terminated_length": 594.6150512695312,
      "completions/min_length": 83.0,
      "completions/min_terminated_length": 83.0,
      "epoch": 0.04787988030029925,
      "grad_norm": 0.11298026889562607,
      "learning_rate": 2e-07,
      "loss": 0.0524,
      "num_tokens": 416559796.0,
      "reward": 0.5731375813484192,
      "reward_std": 0.19086571037769318,
      "rewards/simpleverify_reward/mean": 0.5731375813484192,
      "rewards/simpleverify_reward/std": 0.49462413787841797,
      "step": 513
    },
    {
      "clip_ratio/high_max": 0.0019055615885008592,
      "clip_ratio/high_mean": 0.0007541301165474579,
      "clip_ratio/low_mean": 0.0005483079567056848,
      "clip_ratio/low_min": 1.864558544184547e-05,
      "clip_ratio/region_mean": 0.0013024380714341532,
      "epoch": 0.047973213400299836,
      "grad_norm": 0.12759138643741608,
      "learning_rate": 2e-07,
      "loss": 0.0207,
      "step": 514
    },
    {
      "clip_ratio/high_max": 0.0016372005666198675,
      "clip_ratio/high_mean": 0.000622099862084724,
      "clip_ratio/low_mean": 0.00048604997391521465,
      "clip_ratio/low_min": 1.1920656106667593e-05,
      "clip_ratio/region_mean": 0.0011081498632847797,
      "epoch": 0.048066546500300414,
      "grad_norm": 0.1298171728849411,
      "learning_rate": 2e-07,
      "loss": 0.0416,
      "step": 515
    },
    {
      "clip_ratio/high_max": 0.0017211995655088685,
      "clip_ratio/high_mean": 0.0007311028307412926,
      "clip_ratio/low_mean": 0.000658808905427577,
      "clip_ratio/low_min": 6.318408759398153e-05,
      "clip_ratio/region_mean": 0.0013899117293476593,
      "epoch": 0.048159879600301,
      "grad_norm": 0.13067112863063812,
      "learning_rate": 2e-07,
      "loss": 0.028,
      "step": 516
    },
    {
      "clip_ratio/high_max": 0.0015548435003438499,
      "clip_ratio/high_mean": 0.0006100687151047168,
      "clip_ratio/low_mean": 0.00044122221970610553,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0010512909284443595,
      "epoch": 0.048253212700301584,
      "grad_norm": 0.12154652178287506,
      "learning_rate": 2e-07,
      "loss": 0.0501,
      "step": 517
    },
    {
      "clip_ratio/high_max": 0.001699821645161137,
      "clip_ratio/high_mean": 0.000649929081191658,
      "clip_ratio/low_mean": 0.0006470609423558926,
      "clip_ratio/low_min": 8.591075311414897e-05,
      "clip_ratio/region_mean": 0.0012969900053576566,
      "epoch": 0.04834654580030216,
      "grad_norm": 0.12324988096952438,
      "learning_rate": 2e-07,
      "loss": 0.0241,
      "step": 518
    },
    {
      "clip_ratio/high_max": 0.001591528758581262,
      "clip_ratio/high_mean": 0.0006743817330061574,
      "clip_ratio/low_mean": 0.0005555367597480654,
      "clip_ratio/low_min": 2.5526946046738885e-05,
      "clip_ratio/region_mean": 0.0012299184745643288,
      "epoch": 0.04843987890030275,
      "grad_norm": 0.13422206044197083,
      "learning_rate": 2e-07,
      "loss": -0.0069,
      "step": 519
    },
    {
      "clip_ratio/high_max": 0.0019250004115747288,
      "clip_ratio/high_mean": 0.0007246539571497124,
      "clip_ratio/low_mean": 0.0005635598245135043,
      "clip_ratio/low_min": 2.576258066255832e-05,
      "clip_ratio/region_mean": 0.0012882137962151319,
      "epoch": 0.04853321200030333,
      "grad_norm": 0.12279489636421204,
      "learning_rate": 2e-07,
      "loss": 0.0115,
      "step": 520
    },
    {
      "clip_ratio/high_max": 0.0017109660293499473,
      "clip_ratio/high_mean": 0.0006368041376845213,
      "clip_ratio/low_mean": 0.0004745522910525324,
      "clip_ratio/low_min": 1.6133210465341108e-05,
      "clip_ratio/region_mean": 0.0011113564323750325,
      "epoch": 0.04862654510030392,
      "grad_norm": 0.11207243800163269,
      "learning_rate": 2e-07,
      "loss": 0.0104,
      "step": 521
    },
    {
      "clip_ratio/high_max": 0.0017926863001775928,
      "clip_ratio/high_mean": 0.0007263516181410523,
      "clip_ratio/low_mean": 0.000540116906449839,
      "clip_ratio/low_min": 3.0086114747973625e-05,
      "clip_ratio/region_mean": 0.0012664685127674602,
      "epoch": 0.048719878200304496,
      "grad_norm": 0.11876726895570755,
      "learning_rate": 2e-07,
      "loss": 0.0663,
      "step": 522
    },
    {
      "clip_ratio/high_max": 0.0017169080274470616,
      "clip_ratio/high_mean": 0.0006668853802693775,
      "clip_ratio/low_mean": 0.0006589068561879685,
      "clip_ratio/low_min": 0.00010109489358001156,
      "clip_ratio/region_mean": 0.0013257922510092612,
      "epoch": 0.04881321130030508,
      "grad_norm": 0.12012317776679993,
      "learning_rate": 2e-07,
      "loss": 0.0462,
      "step": 523
    },
    {
      "clip_ratio/high_max": 0.0015614154617651366,
      "clip_ratio/high_mean": 0.0006649482511420501,
      "clip_ratio/low_mean": 0.0006062602205929579,
      "clip_ratio/low_min": 2.778395173663739e-05,
      "clip_ratio/region_mean": 0.0012712084680970293,
      "epoch": 0.04890654440030567,
      "grad_norm": 0.12514448165893555,
      "learning_rate": 2e-07,
      "loss": 0.0412,
      "step": 524
    },
    {
      "clip_ratio/high_max": 0.0018573427332739811,
      "clip_ratio/high_mean": 0.0006457889085140778,
      "clip_ratio/low_mean": 0.0006450058335758513,
      "clip_ratio/low_min": 6.813176878495142e-05,
      "clip_ratio/region_mean": 0.0012907947530038655,
      "epoch": 0.04899987750030625,
      "grad_norm": 0.1253548413515091,
      "learning_rate": 2e-07,
      "loss": 0.0747,
      "step": 525
    },
    {
      "clip_ratio/high_max": 0.0014719585560669657,
      "clip_ratio/high_mean": 0.000570067892113002,
      "clip_ratio/low_mean": 0.0005554877479880815,
      "clip_ratio/low_min": 7.219591225293698e-06,
      "clip_ratio/region_mean": 0.0011255556055402849,
      "epoch": 0.04909321060030683,
      "grad_norm": 0.10819262266159058,
      "learning_rate": 2e-07,
      "loss": 0.026,
      "step": 526
    },
    {
      "clip_ratio/high_max": 0.0014960130320105236,
      "clip_ratio/high_mean": 0.0005884772908757441,
      "clip_ratio/low_mean": 0.0005537784272746649,
      "clip_ratio/low_min": 2.4256875803985167e-05,
      "clip_ratio/region_mean": 0.0011422557108744513,
      "epoch": 0.049186543700307415,
      "grad_norm": 0.10986540466547012,
      "learning_rate": 2e-07,
      "loss": 0.0513,
      "step": 527
    },
    {
      "clip_ratio/high_max": 0.001744572651659837,
      "clip_ratio/high_mean": 0.0006841859394626226,
      "clip_ratio/low_mean": 0.0005065137061137648,
      "clip_ratio/low_min": 1.9027771941182436e-05,
      "clip_ratio/region_mean": 0.0011906996624020394,
      "epoch": 0.049279876800308,
      "grad_norm": 0.11253663152456284,
      "learning_rate": 2e-07,
      "loss": 0.0474,
      "step": 528
    },
    {
      "clip_ratio/high_max": 0.0016298773407470435,
      "clip_ratio/high_mean": 0.0006067223093850771,
      "clip_ratio/low_mean": 0.0004987436504961806,
      "clip_ratio/low_min": 6.978742749197409e-05,
      "clip_ratio/region_mean": 0.001105465940781869,
      "epoch": 0.049373209900308586,
      "grad_norm": 0.11536478996276855,
      "learning_rate": 2e-07,
      "loss": 0.027,
      "step": 529
    },
    {
      "clip_ratio/high_max": 0.0018762354884529486,
      "clip_ratio/high_mean": 0.0006536356813739985,
      "clip_ratio/low_mean": 0.00045648969808098627,
      "clip_ratio/low_min": 1.2295888154767454e-05,
      "clip_ratio/region_mean": 0.0011101254021923523,
      "epoch": 0.049466543000309164,
      "grad_norm": 0.10952523350715637,
      "learning_rate": 2e-07,
      "loss": 0.0148,
      "step": 530
    },
    {
      "clip_ratio/high_max": 0.0016240243530774023,
      "clip_ratio/high_mean": 0.0005951501116214786,
      "clip_ratio/low_mean": 0.0005810797229059972,
      "clip_ratio/low_min": 2.2846100819151616e-05,
      "clip_ratio/region_mean": 0.0011762298381654546,
      "epoch": 0.04955987610030975,
      "grad_norm": 0.13476504385471344,
      "learning_rate": 2e-07,
      "loss": 0.0776,
      "step": 531
    },
    {
      "clip_ratio/high_max": 0.001935601689183386,
      "clip_ratio/high_mean": 0.0007952528394525871,
      "clip_ratio/low_mean": 0.0005942847137703211,
      "clip_ratio/low_min": 7.807414840499405e-05,
      "clip_ratio/region_mean": 0.001389537559589371,
      "epoch": 0.049653209200310335,
      "grad_norm": 0.11563518643379211,
      "learning_rate": 2e-07,
      "loss": 0.0307,
      "step": 532
    },
    {
      "clip_ratio/high_max": 0.002030391689913813,
      "clip_ratio/high_mean": 0.0007907604704087134,
      "clip_ratio/low_mean": 0.0005345317167666508,
      "clip_ratio/low_min": 2.198042784584686e-05,
      "clip_ratio/region_mean": 0.0013252921962703113,
      "epoch": 0.04974654230031091,
      "grad_norm": 0.10787410289049149,
      "learning_rate": 2e-07,
      "loss": 0.046,
      "step": 533
    },
    {
      "clip_ratio/high_max": 0.0020212958770571277,
      "clip_ratio/high_mean": 0.0007454073511325987,
      "clip_ratio/low_mean": 0.0006577837302756961,
      "clip_ratio/low_min": 2.8121484319854062e-05,
      "clip_ratio/region_mean": 0.0014031910795893054,
      "epoch": 0.0498398754003115,
      "grad_norm": 0.1376996487379074,
      "learning_rate": 2e-07,
      "loss": 0.0364,
      "step": 534
    },
    {
      "clip_ratio/high_max": 0.001841231744037941,
      "clip_ratio/high_mean": 0.0007891688310337486,
      "clip_ratio/low_mean": 0.0005850360666954657,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013742048795393202,
      "epoch": 0.04993320850031208,
      "grad_norm": 0.12365517765283585,
      "learning_rate": 2e-07,
      "loss": 0.0242,
      "step": 535
    },
    {
      "clip_ratio/high_max": 0.0014932702761143446,
      "clip_ratio/high_mean": 0.0006284396331466269,
      "clip_ratio/low_mean": 0.0005191584123167559,
      "clip_ratio/low_min": 1.891498322947882e-05,
      "clip_ratio/region_mean": 0.0011475980827526655,
      "epoch": 0.05002654160031267,
      "grad_norm": 0.11342525482177734,
      "learning_rate": 2e-07,
      "loss": 0.0695,
      "step": 536
    },
    {
      "clip_ratio/high_max": 0.0017290584873990156,
      "clip_ratio/high_mean": 0.0006354221168294316,
      "clip_ratio/low_mean": 0.0006204359378898516,
      "clip_ratio/low_min": 4.611405347532127e-05,
      "clip_ratio/region_mean": 0.0012558580820041243,
      "epoch": 0.05011987470031325,
      "grad_norm": 0.12601055204868317,
      "learning_rate": 2e-07,
      "loss": 0.0645,
      "step": 537
    },
    {
      "clip_ratio/high_max": 0.0018686095827433746,
      "clip_ratio/high_mean": 0.0007850421243347228,
      "clip_ratio/low_mean": 0.0005586308434430975,
      "clip_ratio/low_min": 3.90221607631247e-05,
      "clip_ratio/region_mean": 0.0013436729859677143,
      "epoch": 0.05021320780031383,
      "grad_norm": 0.1223674863576889,
      "learning_rate": 2e-07,
      "loss": 0.0117,
      "step": 538
    },
    {
      "clip_ratio/high_max": 0.0019604140288720373,
      "clip_ratio/high_mean": 0.0008119478243315825,
      "clip_ratio/low_mean": 0.0005584951350101619,
      "clip_ratio/low_min": 5.867901927558705e-05,
      "clip_ratio/region_mean": 0.0013704429693461861,
      "epoch": 0.05030654090031442,
      "grad_norm": 0.11562816053628922,
      "learning_rate": 2e-07,
      "loss": 0.036,
      "step": 539
    },
    {
      "clip_ratio/high_max": 0.001785804211976938,
      "clip_ratio/high_mean": 0.0006332191069304827,
      "clip_ratio/low_mean": 0.0006834329633420566,
      "clip_ratio/low_min": 8.132418406603392e-05,
      "clip_ratio/region_mean": 0.0013166520657250658,
      "epoch": 0.050399874000315,
      "grad_norm": 0.12420156598091125,
      "learning_rate": 2e-07,
      "loss": 0.0722,
      "step": 540
    },
    {
      "clip_ratio/high_max": 0.0018473132804501802,
      "clip_ratio/high_mean": 0.0006577056992682628,
      "clip_ratio/low_mean": 0.0005769932586190407,
      "clip_ratio/low_min": 1.3372419743973296e-05,
      "clip_ratio/region_mean": 0.0012346989460638724,
      "epoch": 0.05049320710031558,
      "grad_norm": 0.12634967267513275,
      "learning_rate": 2e-07,
      "loss": 0.0417,
      "step": 541
    },
    {
      "clip_ratio/high_max": 0.0018358995475864504,
      "clip_ratio/high_mean": 0.0007257254765136167,
      "clip_ratio/low_mean": 0.0004934849885103176,
      "clip_ratio/low_min": 1.8340243059356e-05,
      "clip_ratio/region_mean": 0.0012192104513815138,
      "epoch": 0.050586540200316166,
      "grad_norm": 0.12871892750263214,
      "learning_rate": 2e-07,
      "loss": 0.0321,
      "step": 542
    },
    {
      "clip_ratio/high_max": 0.0021494842985703144,
      "clip_ratio/high_mean": 0.0007976802480698097,
      "clip_ratio/low_mean": 0.0006469649861173821,
      "clip_ratio/low_min": 2.588775987533154e-05,
      "clip_ratio/region_mean": 0.0014446452478296123,
      "epoch": 0.05067987330031675,
      "grad_norm": 0.12188766151666641,
      "learning_rate": 2e-07,
      "loss": 0.0186,
      "step": 543
    },
    {
      "clip_ratio/high_max": 0.0019197439614799805,
      "clip_ratio/high_mean": 0.0008248587164416676,
      "clip_ratio/low_mean": 0.0006082845939090475,
      "clip_ratio/low_min": 2.5058481696760282e-05,
      "clip_ratio/region_mean": 0.0014331432757899165,
      "epoch": 0.05077320640031733,
      "grad_norm": 0.12502016127109528,
      "learning_rate": 2e-07,
      "loss": 0.0155,
      "step": 544
    },
    {
      "clip_ratio/high_max": 0.0016668248135829344,
      "clip_ratio/high_mean": 0.0006620520434807986,
      "clip_ratio/low_mean": 0.0005633309820041177,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001225383035489358,
      "epoch": 0.050866539500317914,
      "grad_norm": 0.12126310914754868,
      "learning_rate": 2e-07,
      "loss": 0.029,
      "step": 545
    },
    {
      "clip_ratio/high_max": 0.0021015980728407158,
      "clip_ratio/high_mean": 0.0007989244022610364,
      "clip_ratio/low_mean": 0.000507291098983842,
      "clip_ratio/low_min": 3.895943063980667e-05,
      "clip_ratio/region_mean": 0.0013062154794170056,
      "epoch": 0.0509598726003185,
      "grad_norm": 0.122885562479496,
      "learning_rate": 2e-07,
      "loss": -0.0154,
      "step": 546
    },
    {
      "clip_ratio/high_max": 0.0019345288310432807,
      "clip_ratio/high_mean": 0.0007570865909656277,
      "clip_ratio/low_mean": 0.0005317979698702402,
      "clip_ratio/low_min": 1.387963584420504e-05,
      "clip_ratio/region_mean": 0.0012888845812994987,
      "epoch": 0.051053205700319085,
      "grad_norm": 0.11875979602336884,
      "learning_rate": 2e-07,
      "loss": -0.0209,
      "step": 547
    },
    {
      "clip_ratio/high_max": 0.001721780694424524,
      "clip_ratio/high_mean": 0.0006966763148739119,
      "clip_ratio/low_mean": 0.0005951242510491284,
      "clip_ratio/low_min": 7.561992242699489e-05,
      "clip_ratio/region_mean": 0.0012918005922983866,
      "epoch": 0.05114653880031966,
      "grad_norm": 0.12873409688472748,
      "learning_rate": 2e-07,
      "loss": 0.014,
      "step": 548
    },
    {
      "clip_ratio/high_max": 0.001902618914755294,
      "clip_ratio/high_mean": 0.0008150464182108408,
      "clip_ratio/low_mean": 0.000650896815386659,
      "clip_ratio/low_min": 3.164745066897012e-05,
      "clip_ratio/region_mean": 0.0014659432272310369,
      "epoch": 0.05123987190032025,
      "grad_norm": 0.1314297765493393,
      "learning_rate": 2e-07,
      "loss": 0.0092,
      "step": 549
    },
    {
      "clip_ratio/high_max": 0.00191223432921106,
      "clip_ratio/high_mean": 0.0007700695114181144,
      "clip_ratio/low_mean": 0.0006386641962308204,
      "clip_ratio/low_min": 5.1340840400371235e-05,
      "clip_ratio/region_mean": 0.0014087336967349984,
      "epoch": 0.05133320500032083,
      "grad_norm": 0.13911126554012299,
      "learning_rate": 2e-07,
      "loss": 0.013,
      "step": 550
    },
    {
      "clip_ratio/high_max": 0.0014529107575071976,
      "clip_ratio/high_mean": 0.0006132005491963355,
      "clip_ratio/low_mean": 0.0005745126145484392,
      "clip_ratio/low_min": 7.918378514659707e-05,
      "clip_ratio/region_mean": 0.001187713183753658,
      "epoch": 0.05142653810032142,
      "grad_norm": 0.20155708491802216,
      "learning_rate": 2e-07,
      "loss": 0.0718,
      "step": 551
    },
    {
      "clip_ratio/high_max": 0.0018723777902778238,
      "clip_ratio/high_mean": 0.0007526285298808943,
      "clip_ratio/low_mean": 0.0005221480087129748,
      "clip_ratio/low_min": 5.5972776863200124e-05,
      "clip_ratio/region_mean": 0.0012747765467793215,
      "epoch": 0.051519871200322,
      "grad_norm": 0.11362409591674805,
      "learning_rate": 2e-07,
      "loss": 0.0351,
      "step": 552
    },
    {
      "clip_ratio/high_max": 0.0018042937081190757,
      "clip_ratio/high_mean": 0.0006608404291910119,
      "clip_ratio/low_mean": 0.0005771404048573459,
      "clip_ratio/low_min": 3.3334152249153703e-05,
      "clip_ratio/region_mean": 0.0012379808067635167,
      "epoch": 0.05161320430032258,
      "grad_norm": 0.10544995218515396,
      "learning_rate": 2e-07,
      "loss": 0.0311,
      "step": 553
    },
    {
      "clip_ratio/high_max": 0.0016912070532271173,
      "clip_ratio/high_mean": 0.0006509279810416047,
      "clip_ratio/low_mean": 0.000695123821060406,
      "clip_ratio/low_min": 2.047275847871788e-05,
      "clip_ratio/region_mean": 0.0013460518493957352,
      "epoch": 0.05170653740032317,
      "grad_norm": 0.11964976042509079,
      "learning_rate": 2e-07,
      "loss": 0.0577,
      "step": 554
    },
    {
      "clip_ratio/high_max": 0.0017991704298765399,
      "clip_ratio/high_mean": 0.0007979949150467291,
      "clip_ratio/low_mean": 0.0005872214151168009,
      "clip_ratio/low_min": 2.8045772523910273e-05,
      "clip_ratio/region_mean": 0.0013852163283445407,
      "epoch": 0.05179987050032375,
      "grad_norm": 0.11670426279306412,
      "learning_rate": 2e-07,
      "loss": 0.0152,
      "step": 555
    },
    {
      "clip_ratio/high_max": 0.001659480061789509,
      "clip_ratio/high_mean": 0.0007044650037641986,
      "clip_ratio/low_mean": 0.0005288314732752042,
      "clip_ratio/low_min": 7.4201589086442254e-06,
      "clip_ratio/region_mean": 0.0012332964761299081,
      "epoch": 0.05189320360032433,
      "grad_norm": 0.12758934497833252,
      "learning_rate": 2e-07,
      "loss": 0.0153,
      "step": 556
    },
    {
      "clip_ratio/high_max": 0.0020512506234808825,
      "clip_ratio/high_mean": 0.000795040607044939,
      "clip_ratio/low_mean": 0.0006537424542329973,
      "clip_ratio/low_min": 3.822591133939568e-05,
      "clip_ratio/region_mean": 0.0014487830449070316,
      "epoch": 0.051986536700324916,
      "grad_norm": 0.1316671073436737,
      "learning_rate": 2e-07,
      "loss": 0.0267,
      "step": 557
    },
    {
      "clip_ratio/high_max": 0.0016326837831002194,
      "clip_ratio/high_mean": 0.0006808873986301478,
      "clip_ratio/low_mean": 0.0005960292837698944,
      "clip_ratio/low_min": 4.069219994562445e-05,
      "clip_ratio/region_mean": 0.0012769166642101482,
      "epoch": 0.0520798698003255,
      "grad_norm": 0.11492060124874115,
      "learning_rate": 2e-07,
      "loss": 0.079,
      "step": 558
    },
    {
      "clip_ratio/high_max": 0.0017714321620587725,
      "clip_ratio/high_mean": 0.0007082804895617301,
      "clip_ratio/low_mean": 0.0005819697053084383,
      "clip_ratio/low_min": 6.389534155459842e-05,
      "clip_ratio/region_mean": 0.0012902501948701683,
      "epoch": 0.05217320290032608,
      "grad_norm": 0.11201989650726318,
      "learning_rate": 2e-07,
      "loss": 0.0321,
      "step": 559
    },
    {
      "clip_ratio/high_max": 0.0017779856352717616,
      "clip_ratio/high_mean": 0.0007113968331395881,
      "clip_ratio/low_mean": 0.0005475915659189923,
      "clip_ratio/low_min": 6.314742131507955e-05,
      "clip_ratio/region_mean": 0.0012589883735927287,
      "epoch": 0.052266536000326665,
      "grad_norm": 0.1309257596731186,
      "learning_rate": 2e-07,
      "loss": 0.0169,
      "step": 560
    },
    {
      "clip_ratio/high_max": 0.001847168525273446,
      "clip_ratio/high_mean": 0.0007185839604062494,
      "clip_ratio/low_mean": 0.000633893912890926,
      "clip_ratio/low_min": 1.582679215061944e-05,
      "clip_ratio/region_mean": 0.0013524778696591966,
      "epoch": 0.05235986910032725,
      "grad_norm": 0.13159914314746857,
      "learning_rate": 2e-07,
      "loss": 0.0626,
      "step": 561
    },
    {
      "clip_ratio/high_max": 0.0018328269470657688,
      "clip_ratio/high_mean": 0.0007086717923812103,
      "clip_ratio/low_mean": 0.0005212823052715976,
      "clip_ratio/low_min": 4.080983126186766e-05,
      "clip_ratio/region_mean": 0.0012299541049287654,
      "epoch": 0.052453202200327835,
      "grad_norm": 0.1301041692495346,
      "learning_rate": 2e-07,
      "loss": 0.0029,
      "step": 562
    },
    {
      "clip_ratio/high_max": 0.001789040383300744,
      "clip_ratio/high_mean": 0.0007790057497913949,
      "clip_ratio/low_mean": 0.0006246452521736501,
      "clip_ratio/low_min": 2.373538245592499e-05,
      "clip_ratio/region_mean": 0.0014036510074220132,
      "epoch": 0.05254653530032841,
      "grad_norm": 0.12613432109355927,
      "learning_rate": 2e-07,
      "loss": 0.0164,
      "step": 563
    },
    {
      "clip_ratio/high_max": 0.0018007719663728494,
      "clip_ratio/high_mean": 0.0007018050800979836,
      "clip_ratio/low_mean": 0.0006099563579482492,
      "clip_ratio/low_min": 2.6959542992699426e-05,
      "clip_ratio/region_mean": 0.0013117614398652222,
      "epoch": 0.052639868400329,
      "grad_norm": 0.11805761605501175,
      "learning_rate": 2e-07,
      "loss": 0.0537,
      "step": 564
    },
    {
      "clip_ratio/high_max": 0.0016851529762789141,
      "clip_ratio/high_mean": 0.0006174919744807994,
      "clip_ratio/low_mean": 0.0004897001808785717,
      "clip_ratio/low_min": 5.278716344037093e-06,
      "clip_ratio/region_mean": 0.0011071921144321095,
      "epoch": 0.052733201500329584,
      "grad_norm": 0.11520353704690933,
      "learning_rate": 2e-07,
      "loss": 0.0168,
      "step": 565
    },
    {
      "clip_ratio/high_max": 0.001998689662286779,
      "clip_ratio/high_mean": 0.0008338744646607665,
      "clip_ratio/low_mean": 0.0005769850076831062,
      "clip_ratio/low_min": 3.468655540928012e-05,
      "clip_ratio/region_mean": 0.0014108594914432615,
      "epoch": 0.05282653460033017,
      "grad_norm": 0.11920414865016937,
      "learning_rate": 2e-07,
      "loss": -0.0154,
      "step": 566
    },
    {
      "clip_ratio/high_max": 0.002038974289462203,
      "clip_ratio/high_mean": 0.0007023693287919741,
      "clip_ratio/low_mean": 0.0006350495123115252,
      "clip_ratio/low_min": 6.761611621186603e-05,
      "clip_ratio/region_mean": 0.0013374188638408668,
      "epoch": 0.05291986770033075,
      "grad_norm": 0.12366802245378494,
      "learning_rate": 2e-07,
      "loss": -0.0109,
      "step": 567
    },
    {
      "clip_ratio/high_max": 0.0017269053059862927,
      "clip_ratio/high_mean": 0.0007129967470973497,
      "clip_ratio/low_mean": 0.000608542128247791,
      "clip_ratio/low_min": 1.4095624464971479e-05,
      "clip_ratio/region_mean": 0.001321538889897056,
      "epoch": 0.05301320080033133,
      "grad_norm": 0.11472231894731522,
      "learning_rate": 2e-07,
      "loss": 0.0095,
      "step": 568
    },
    {
      "clip_ratio/high_max": 0.0016702533030183986,
      "clip_ratio/high_mean": 0.0006925598663656274,
      "clip_ratio/low_mean": 0.0006427852840715786,
      "clip_ratio/low_min": 5.117778346175328e-05,
      "clip_ratio/region_mean": 0.0013353451649891213,
      "epoch": 0.05310653390033192,
      "grad_norm": 0.14368966221809387,
      "learning_rate": 2e-07,
      "loss": 0.0202,
      "step": 569
    },
    {
      "clip_ratio/high_max": 0.0018115360544470605,
      "clip_ratio/high_mean": 0.0006607777377212187,
      "clip_ratio/low_mean": 0.0005787943264294881,
      "clip_ratio/low_min": 2.473641598044196e-05,
      "clip_ratio/region_mean": 0.0012395720623317175,
      "epoch": 0.053199867000332496,
      "grad_norm": 0.1197221577167511,
      "learning_rate": 2e-07,
      "loss": 0.0699,
      "step": 570
    },
    {
      "clip_ratio/high_max": 0.0020126455965510104,
      "clip_ratio/high_mean": 0.000775036467530299,
      "clip_ratio/low_mean": 0.0005871908851986518,
      "clip_ratio/low_min": 9.262003914045636e-06,
      "clip_ratio/region_mean": 0.0013622273909277283,
      "epoch": 0.05329320010033308,
      "grad_norm": 0.13638238608837128,
      "learning_rate": 2e-07,
      "loss": 0.0142,
      "step": 571
    },
    {
      "clip_ratio/high_max": 0.001846505590947345,
      "clip_ratio/high_mean": 0.0007671996118006064,
      "clip_ratio/low_mean": 0.0004907596371594991,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001257959254871821,
      "epoch": 0.053386533200333666,
      "grad_norm": 0.13579873740673065,
      "learning_rate": 2e-07,
      "loss": -0.0004,
      "step": 572
    },
    {
      "clip_ratio/high_max": 0.001885782661702251,
      "clip_ratio/high_mean": 0.0007782633765600622,
      "clip_ratio/low_mean": 0.0005505429435288534,
      "clip_ratio/low_min": 3.887061848217854e-05,
      "clip_ratio/region_mean": 0.0013288063455547672,
      "epoch": 0.05347986630033425,
      "grad_norm": 0.22227318584918976,
      "learning_rate": 2e-07,
      "loss": 0.0468,
      "step": 573
    },
    {
      "clip_ratio/high_max": 0.0017666459643805865,
      "clip_ratio/high_mean": 0.0007799595659889746,
      "clip_ratio/low_mean": 0.0004781320076290285,
      "clip_ratio/low_min": 1.042709391185781e-05,
      "clip_ratio/region_mean": 0.0012580915936268866,
      "epoch": 0.05357319940033483,
      "grad_norm": 0.11867934465408325,
      "learning_rate": 2e-07,
      "loss": -0.0119,
      "step": 574
    },
    {
      "clip_ratio/high_max": 0.0019866141883539967,
      "clip_ratio/high_mean": 0.0008548714358767029,
      "clip_ratio/low_mean": 0.000600242141445051,
      "clip_ratio/low_min": 3.095135798503179e-05,
      "clip_ratio/region_mean": 0.001455113582778722,
      "epoch": 0.053666532500335415,
      "grad_norm": 0.1356223076581955,
      "learning_rate": 2e-07,
      "loss": -0.0001,
      "step": 575
    },
    {
      "clip_ratio/high_max": 0.00195651211834047,
      "clip_ratio/high_mean": 0.0007460907036147546,
      "clip_ratio/low_mean": 0.0006365838853525929,
      "clip_ratio/low_min": 4.306820119381882e-05,
      "clip_ratio/region_mean": 0.0013826745744154323,
      "epoch": 0.053759865600336,
      "grad_norm": 0.11269514262676239,
      "learning_rate": 2e-07,
      "loss": 0.0246,
      "step": 576
    },
    {
      "clip_ratio/high_max": 0.0016697847859177273,
      "clip_ratio/high_mean": 0.0007288893521035789,
      "clip_ratio/low_mean": 0.0005168548964320507,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012457442680897657,
      "epoch": 0.053853198700336585,
      "grad_norm": 0.1243629902601242,
      "learning_rate": 2e-07,
      "loss": 0.0475,
      "step": 577
    },
    {
      "clip_ratio/high_max": 0.0017798299031710485,
      "clip_ratio/high_mean": 0.000710913129751134,
      "clip_ratio/low_mean": 0.000506110159221862,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012170232585049234,
      "epoch": 0.053946531800337164,
      "grad_norm": 0.12458079308271408,
      "learning_rate": 2e-07,
      "loss": 0.0161,
      "step": 578
    },
    {
      "clip_ratio/high_max": 0.00162797112352564,
      "clip_ratio/high_mean": 0.0006646018855462899,
      "clip_ratio/low_mean": 0.0005998745705255715,
      "clip_ratio/low_min": 5.250122012512293e-05,
      "clip_ratio/region_mean": 0.0012644764319702517,
      "epoch": 0.05403986490033775,
      "grad_norm": 0.11783482134342194,
      "learning_rate": 2e-07,
      "loss": 0.0373,
      "step": 579
    },
    {
      "clip_ratio/high_max": 0.001879115923657082,
      "clip_ratio/high_mean": 0.0007565552077721804,
      "clip_ratio/low_mean": 0.0005385502927310881,
      "clip_ratio/low_min": 5.771285850642016e-05,
      "clip_ratio/region_mean": 0.0012951054886798374,
      "epoch": 0.054133198000338334,
      "grad_norm": 0.13198161125183105,
      "learning_rate": 2e-07,
      "loss": 0.0335,
      "step": 580
    },
    {
      "clip_ratio/high_max": 0.0021892019794904627,
      "clip_ratio/high_mean": 0.0009171991750918096,
      "clip_ratio/low_mean": 0.0006238217756617814,
      "clip_ratio/low_min": 3.529979449012899e-05,
      "clip_ratio/region_mean": 0.0015410209671244957,
      "epoch": 0.05422653110033892,
      "grad_norm": 0.13487371802330017,
      "learning_rate": 2e-07,
      "loss": -0.0103,
      "step": 581
    },
    {
      "clip_ratio/high_max": 0.0017096548253903165,
      "clip_ratio/high_mean": 0.0007594519738631789,
      "clip_ratio/low_mean": 0.0006225819361134199,
      "clip_ratio/low_min": 3.124610702798236e-05,
      "clip_ratio/region_mean": 0.0013820339372614399,
      "epoch": 0.0543198642003395,
      "grad_norm": 0.13045914471149445,
      "learning_rate": 2e-07,
      "loss": 0.0313,
      "step": 582
    },
    {
      "clip_ratio/high_max": 0.0014533554276567884,
      "clip_ratio/high_mean": 0.000575455122088897,
      "clip_ratio/low_mean": 0.0006742003333783941,
      "clip_ratio/low_min": 1.7319468042842345e-05,
      "clip_ratio/region_mean": 0.0012496554481913336,
      "epoch": 0.05441319730034008,
      "grad_norm": 0.12129105627536774,
      "learning_rate": 2e-07,
      "loss": 0.0665,
      "step": 583
    },
    {
      "clip_ratio/high_max": 0.0017846442024165299,
      "clip_ratio/high_mean": 0.0006911709606356453,
      "clip_ratio/low_mean": 0.0005766718677477911,
      "clip_ratio/low_min": 1.2530072126537561e-05,
      "clip_ratio/region_mean": 0.0012678428065555636,
      "epoch": 0.05450653040034067,
      "grad_norm": 0.1220710501074791,
      "learning_rate": 2e-07,
      "loss": 0.0306,
      "step": 584
    },
    {
      "clip_ratio/high_max": 0.00198998495034175,
      "clip_ratio/high_mean": 0.0006400764304999029,
      "clip_ratio/low_mean": 0.0006634789551753784,
      "clip_ratio/low_min": 6.018608110025525e-05,
      "clip_ratio/region_mean": 0.0013035553965892177,
      "epoch": 0.054599863500341246,
      "grad_norm": 0.12754133343696594,
      "learning_rate": 2e-07,
      "loss": 0.0773,
      "step": 585
    },
    {
      "clip_ratio/high_max": 0.0016538534982828423,
      "clip_ratio/high_mean": 0.0006879127586216782,
      "clip_ratio/low_mean": 0.0005469334355439059,
      "clip_ratio/low_min": 1.4794650269323029e-05,
      "clip_ratio/region_mean": 0.0012348462259978987,
      "epoch": 0.05469319660034183,
      "grad_norm": 0.12297696620225906,
      "learning_rate": 2e-07,
      "loss": 0.0469,
      "step": 586
    },
    {
      "clip_ratio/high_max": 0.0020761688247148413,
      "clip_ratio/high_mean": 0.0008023149021028075,
      "clip_ratio/low_mean": 0.000612718193224282,
      "clip_ratio/low_min": 2.556498657213524e-05,
      "clip_ratio/region_mean": 0.0014150330935081001,
      "epoch": 0.054786529700342416,
      "grad_norm": 0.13738387823104858,
      "learning_rate": 2e-07,
      "loss": 0.0554,
      "step": 587
    },
    {
      "clip_ratio/high_max": 0.0017503084018244408,
      "clip_ratio/high_mean": 0.0007874890934544965,
      "clip_ratio/low_mean": 0.0005550610330828931,
      "clip_ratio/low_min": 7.897397154010832e-06,
      "clip_ratio/region_mean": 0.001342550134722842,
      "epoch": 0.054879862800343,
      "grad_norm": 0.13236290216445923,
      "learning_rate": 2e-07,
      "loss": 0.0027,
      "step": 588
    },
    {
      "clip_ratio/high_max": 0.0015410939558933023,
      "clip_ratio/high_mean": 0.0006149955115688499,
      "clip_ratio/low_mean": 0.0006659924847554066,
      "clip_ratio/low_min": 2.988053620356368e-05,
      "clip_ratio/region_mean": 0.0012809879881388042,
      "epoch": 0.05497319590034358,
      "grad_norm": 0.12689785659313202,
      "learning_rate": 2e-07,
      "loss": 0.0316,
      "step": 589
    },
    {
      "clip_ratio/high_max": 0.001959101267857477,
      "clip_ratio/high_mean": 0.0007448444430337986,
      "clip_ratio/low_mean": 0.0006252952262002509,
      "clip_ratio/low_min": 1.6075102394097485e-05,
      "clip_ratio/region_mean": 0.0013701396565011237,
      "epoch": 0.055066529000344165,
      "grad_norm": 0.13592302799224854,
      "learning_rate": 2e-07,
      "loss": 0.0153,
      "step": 590
    },
    {
      "clip_ratio/high_max": 0.0020989665572415106,
      "clip_ratio/high_mean": 0.0008433330694970209,
      "clip_ratio/low_mean": 0.0006176371016408666,
      "clip_ratio/low_min": 6.281680452957517e-05,
      "clip_ratio/region_mean": 0.001460970175685361,
      "epoch": 0.05515986210034475,
      "grad_norm": 0.1321668177843094,
      "learning_rate": 2e-07,
      "loss": 0.0081,
      "step": 591
    },
    {
      "clip_ratio/high_max": 0.0016573472021264024,
      "clip_ratio/high_mean": 0.0006624462021136424,
      "clip_ratio/low_mean": 0.0005255823480183608,
      "clip_ratio/low_min": 2.5123720661213156e-05,
      "clip_ratio/region_mean": 0.0011880285710503813,
      "epoch": 0.055253195200345336,
      "grad_norm": 0.13149040937423706,
      "learning_rate": 2e-07,
      "loss": 0.0419,
      "step": 592
    },
    {
      "clip_ratio/high_max": 0.0017793898659874685,
      "clip_ratio/high_mean": 0.0007033273050183197,
      "clip_ratio/low_mean": 0.0006222679530765163,
      "clip_ratio/low_min": 2.470067011017818e-05,
      "clip_ratio/region_mean": 0.0013255952471808996,
      "epoch": 0.055346528300345914,
      "grad_norm": 0.14036960899829865,
      "learning_rate": 2e-07,
      "loss": 0.02,
      "step": 593
    },
    {
      "clip_ratio/high_max": 0.0020325880068412516,
      "clip_ratio/high_mean": 0.0007809740709490143,
      "clip_ratio/low_mean": 0.0006450348955695517,
      "clip_ratio/low_min": 2.497957757441327e-05,
      "clip_ratio/region_mean": 0.001426008966518566,
      "epoch": 0.0554398614003465,
      "grad_norm": 0.2676650881767273,
      "learning_rate": 2e-07,
      "loss": 0.0211,
      "step": 594
    },
    {
      "clip_ratio/high_max": 0.0018841320234059822,
      "clip_ratio/high_mean": 0.0006703415783704259,
      "clip_ratio/low_mean": 0.0005237162185949273,
      "clip_ratio/low_min": 5.951671209913911e-05,
      "clip_ratio/region_mean": 0.0011940578151552472,
      "epoch": 0.055533194500347084,
      "grad_norm": 0.14318114519119263,
      "learning_rate": 2e-07,
      "loss": 0.0364,
      "step": 595
    },
    {
      "clip_ratio/high_max": 0.001886978108814219,
      "clip_ratio/high_mean": 0.0007561022484878777,
      "clip_ratio/low_mean": 0.000568112930523057,
      "clip_ratio/low_min": 5.2477713325060904e-05,
      "clip_ratio/region_mean": 0.0013242152017483022,
      "epoch": 0.05562652760034766,
      "grad_norm": 0.12458319962024689,
      "learning_rate": 2e-07,
      "loss": 0.0009,
      "step": 596
    },
    {
      "clip_ratio/high_max": 0.0017968566571653355,
      "clip_ratio/high_mean": 0.0007810509523551445,
      "clip_ratio/low_mean": 0.0006321854143607197,
      "clip_ratio/low_min": 2.5635767087806016e-05,
      "clip_ratio/region_mean": 0.0014132363648968749,
      "epoch": 0.05571986070034825,
      "grad_norm": 0.13053551316261292,
      "learning_rate": 2e-07,
      "loss": 0.0165,
      "step": 597
    },
    {
      "clip_ratio/high_max": 0.0016252153509412892,
      "clip_ratio/high_mean": 0.0006437623396777781,
      "clip_ratio/low_mean": 0.0005544756704694009,
      "clip_ratio/low_min": 1.5311121387640014e-05,
      "clip_ratio/region_mean": 0.0011982380019617267,
      "epoch": 0.05581319380034883,
      "grad_norm": 0.1327916532754898,
      "learning_rate": 2e-07,
      "loss": 0.0263,
      "step": 598
    },
    {
      "clip_ratio/high_max": 0.0018848180334316567,
      "clip_ratio/high_mean": 0.000723632696463028,
      "clip_ratio/low_mean": 0.0005847063603141578,
      "clip_ratio/low_min": 8.272667400888167e-06,
      "clip_ratio/region_mean": 0.001308339062234154,
      "epoch": 0.05590652690034942,
      "grad_norm": 0.1310209333896637,
      "learning_rate": 2e-07,
      "loss": 0.041,
      "step": 599
    },
    {
      "clip_ratio/high_max": 0.001695720995485317,
      "clip_ratio/high_mean": 0.0006634865485466435,
      "clip_ratio/low_mean": 0.000634342611192551,
      "clip_ratio/low_min": 7.913289664429612e-05,
      "clip_ratio/region_mean": 0.001297829148825258,
      "epoch": 0.055999860000349996,
      "grad_norm": 0.12018702179193497,
      "learning_rate": 2e-07,
      "loss": 0.0418,
      "step": 600
    },
    {
      "clip_ratio/high_max": 0.001900447517982684,
      "clip_ratio/high_mean": 0.0007841793922125362,
      "clip_ratio/low_mean": 0.0006151568468339974,
      "clip_ratio/low_min": 4.4292556594882626e-05,
      "clip_ratio/region_mean": 0.0013993362008477561,
      "epoch": 0.05609319310035058,
      "grad_norm": 0.12365878373384476,
      "learning_rate": 2e-07,
      "loss": 0.0075,
      "step": 601
    },
    {
      "clip_ratio/high_max": 0.0019290830059617292,
      "clip_ratio/high_mean": 0.0007831463481124956,
      "clip_ratio/low_mean": 0.0007195020843937527,
      "clip_ratio/low_min": 5.172137980480329e-05,
      "clip_ratio/region_mean": 0.0015026484688860364,
      "epoch": 0.05618652620035117,
      "grad_norm": 0.14077097177505493,
      "learning_rate": 2e-07,
      "loss": 0.0376,
      "step": 602
    },
    {
      "clip_ratio/high_max": 0.0017942325648618862,
      "clip_ratio/high_mean": 0.0007575634645036189,
      "clip_ratio/low_mean": 0.0005991123907733709,
      "clip_ratio/low_min": 0.0001274592223126092,
      "clip_ratio/region_mean": 0.001356675897113746,
      "epoch": 0.05627985930035175,
      "grad_norm": 0.12890395522117615,
      "learning_rate": 2e-07,
      "loss": 0.0328,
      "step": 603
    },
    {
      "clip_ratio/high_max": 0.0018646691314643249,
      "clip_ratio/high_mean": 0.0007725319755991222,
      "clip_ratio/low_mean": 0.0007225594108604128,
      "clip_ratio/low_min": 4.432194145920221e-05,
      "clip_ratio/region_mean": 0.001495091404649429,
      "epoch": 0.05637319240035233,
      "grad_norm": 0.12693729996681213,
      "learning_rate": 2e-07,
      "loss": 0.0305,
      "step": 604
    },
    {
      "clip_ratio/high_max": 0.002063531155727105,
      "clip_ratio/high_mean": 0.0007943812506709946,
      "clip_ratio/low_mean": 0.0006294220856943866,
      "clip_ratio/low_min": 2.5925908630597405e-05,
      "clip_ratio/region_mean": 0.00142380334000336,
      "epoch": 0.056466525500352915,
      "grad_norm": 0.1365271508693695,
      "learning_rate": 2e-07,
      "loss": -0.0021,
      "step": 605
    },
    {
      "clip_ratio/high_max": 0.00203251661878312,
      "clip_ratio/high_mean": 0.0007879346158006229,
      "clip_ratio/low_mean": 0.0004991922824046924,
      "clip_ratio/low_min": 4.6887322241673246e-05,
      "clip_ratio/region_mean": 0.0012871269209426828,
      "epoch": 0.0565598586003535,
      "grad_norm": 0.1278432458639145,
      "learning_rate": 2e-07,
      "loss": -0.0027,
      "step": 606
    },
    {
      "clip_ratio/high_max": 0.0015390693515655585,
      "clip_ratio/high_mean": 0.0005903260589548154,
      "clip_ratio/low_mean": 0.0005913725435675588,
      "clip_ratio/low_min": 4.17025075876154e-05,
      "clip_ratio/region_mean": 0.0011816985679615755,
      "epoch": 0.056653191700354086,
      "grad_norm": 0.11410504579544067,
      "learning_rate": 2e-07,
      "loss": 0.047,
      "step": 607
    },
    {
      "clip_ratio/high_max": 0.0017402319754182827,
      "clip_ratio/high_mean": 0.0006966765085962834,
      "clip_ratio/low_mean": 0.0005274328523228178,
      "clip_ratio/low_min": 2.7827270059788134e-05,
      "clip_ratio/region_mean": 0.00122410936455708,
      "epoch": 0.056746524800354664,
      "grad_norm": 0.11616390943527222,
      "learning_rate": 2e-07,
      "loss": 0.0202,
      "step": 608
    },
    {
      "clip_ratio/high_max": 0.0017816999170463532,
      "clip_ratio/high_mean": 0.0006182619736136985,
      "clip_ratio/low_mean": 0.000609972744314291,
      "clip_ratio/low_min": 4.807841924048262e-05,
      "clip_ratio/region_mean": 0.0012282347270229366,
      "epoch": 0.05683985790035525,
      "grad_norm": 0.11660334467887878,
      "learning_rate": 2e-07,
      "loss": 0.0494,
      "step": 609
    },
    {
      "clip_ratio/high_max": 0.0017853262434073258,
      "clip_ratio/high_mean": 0.0007639398354513105,
      "clip_ratio/low_mean": 0.0007102946292434353,
      "clip_ratio/low_min": 6.503276290459326e-05,
      "clip_ratio/region_mean": 0.001474234501074534,
      "epoch": 0.056933191000355834,
      "grad_norm": 0.1354941427707672,
      "learning_rate": 2e-07,
      "loss": 0.049,
      "step": 610
    },
    {
      "clip_ratio/high_max": 0.0018278978750458919,
      "clip_ratio/high_mean": 0.0007430641799146542,
      "clip_ratio/low_mean": 0.0006183151544973953,
      "clip_ratio/low_min": 3.4503143979236484e-05,
      "clip_ratio/region_mean": 0.0013613793125841767,
      "epoch": 0.05702652410035641,
      "grad_norm": 0.12802274525165558,
      "learning_rate": 2e-07,
      "loss": 0.0351,
      "step": 611
    },
    {
      "clip_ratio/high_max": 0.0016272912689601071,
      "clip_ratio/high_mean": 0.0006205138251971221,
      "clip_ratio/low_mean": 0.0005882887417101301,
      "clip_ratio/low_min": 1.2939958651259076e-05,
      "clip_ratio/region_mean": 0.0012088025723642204,
      "epoch": 0.057119857200357,
      "grad_norm": 0.11734262853860855,
      "learning_rate": 2e-07,
      "loss": 0.0348,
      "step": 612
    },
    {
      "clip_ratio/high_max": 0.0021973373877699487,
      "clip_ratio/high_mean": 0.0007850227539165644,
      "clip_ratio/low_mean": 0.0005910487889195792,
      "clip_ratio/low_min": 2.1779372218588833e-05,
      "clip_ratio/region_mean": 0.0013760715373791754,
      "epoch": 0.05721319030035758,
      "grad_norm": 0.13653187453746796,
      "learning_rate": 2e-07,
      "loss": 0.0116,
      "step": 613
    },
    {
      "clip_ratio/high_max": 0.0020950166654074565,
      "clip_ratio/high_mean": 0.0008593393977207597,
      "clip_ratio/low_mean": 0.00056025269714155,
      "clip_ratio/low_min": 2.3286560463020578e-05,
      "clip_ratio/region_mean": 0.001419592103047762,
      "epoch": 0.05730652340035817,
      "grad_norm": 0.12896187603473663,
      "learning_rate": 2e-07,
      "loss": -0.0116,
      "step": 614
    },
    {
      "clip_ratio/high_max": 0.0016556828504690202,
      "clip_ratio/high_mean": 0.0006919518855283968,
      "clip_ratio/low_mean": 0.0006706585518259089,
      "clip_ratio/low_min": 1.2437811165000312e-05,
      "clip_ratio/region_mean": 0.0013626104082504753,
      "epoch": 0.05739985650035875,
      "grad_norm": 0.1294972002506256,
      "learning_rate": 2e-07,
      "loss": -0.0025,
      "step": 615
    },
    {
      "clip_ratio/high_max": 0.0018003187396971043,
      "clip_ratio/high_mean": 0.0007296469157154206,
      "clip_ratio/low_mean": 0.0006821004117227858,
      "clip_ratio/low_min": 4.4877334403281566e-05,
      "clip_ratio/region_mean": 0.001411747307429323,
      "epoch": 0.05749318960035933,
      "grad_norm": 0.13182489573955536,
      "learning_rate": 2e-07,
      "loss": 0.0563,
      "step": 616
    },
    {
      "clip_ratio/high_max": 0.002149923333490733,
      "clip_ratio/high_mean": 0.0007671562889299821,
      "clip_ratio/low_mean": 0.000634258379250241,
      "clip_ratio/low_min": 1.1388484381313901e-05,
      "clip_ratio/region_mean": 0.0014014146436238661,
      "epoch": 0.05758652270035992,
      "grad_norm": 0.12806399166584015,
      "learning_rate": 2e-07,
      "loss": 0.0765,
      "step": 617
    },
    {
      "clip_ratio/high_max": 0.0020226039923727512,
      "clip_ratio/high_mean": 0.0008018541338969953,
      "clip_ratio/low_mean": 0.0005924443748881458,
      "clip_ratio/low_min": 5.686851091013523e-05,
      "clip_ratio/region_mean": 0.0013942985133326147,
      "epoch": 0.0576798558003605,
      "grad_norm": 0.1382153481245041,
      "learning_rate": 2e-07,
      "loss": 0.0074,
      "step": 618
    },
    {
      "clip_ratio/high_max": 0.0019411146749916952,
      "clip_ratio/high_mean": 0.0007067885544529418,
      "clip_ratio/low_mean": 0.0006499896626337431,
      "clip_ratio/low_min": 7.562792507087579e-05,
      "clip_ratio/region_mean": 0.001356778204353759,
      "epoch": 0.05777318890036108,
      "grad_norm": 0.14665408432483673,
      "learning_rate": 2e-07,
      "loss": 0.0307,
      "step": 619
    },
    {
      "clip_ratio/high_max": 0.0017691556677164044,
      "clip_ratio/high_mean": 0.0007072527023410657,
      "clip_ratio/low_mean": 0.000624091499048518,
      "clip_ratio/low_min": 6.261970247578574e-05,
      "clip_ratio/region_mean": 0.0013313442104845308,
      "epoch": 0.057866522000361666,
      "grad_norm": 0.13146257400512695,
      "learning_rate": 2e-07,
      "loss": 0.0507,
      "step": 620
    },
    {
      "clip_ratio/high_max": 0.0016596964760537958,
      "clip_ratio/high_mean": 0.0006650236400673748,
      "clip_ratio/low_mean": 0.0006698264733131509,
      "clip_ratio/low_min": 5.13114532623149e-05,
      "clip_ratio/region_mean": 0.0013348501197469886,
      "epoch": 0.05795985510036225,
      "grad_norm": 0.13904964923858643,
      "learning_rate": 2e-07,
      "loss": 0.0179,
      "step": 621
    },
    {
      "clip_ratio/high_max": 0.002203146941610612,
      "clip_ratio/high_mean": 0.0008818303649604786,
      "clip_ratio/low_mean": 0.0005728210853703786,
      "clip_ratio/low_min": 1.4572161489923019e-05,
      "clip_ratio/region_mean": 0.0014546514248650055,
      "epoch": 0.05805318820036283,
      "grad_norm": 0.15285640954971313,
      "learning_rate": 2e-07,
      "loss": 0.0136,
      "step": 622
    },
    {
      "clip_ratio/high_max": 0.0018832642526831478,
      "clip_ratio/high_mean": 0.0007876799973018933,
      "clip_ratio/low_mean": 0.0006289450611802749,
      "clip_ratio/low_min": 5.1864752094843425e-05,
      "clip_ratio/region_mean": 0.0014166250875859987,
      "epoch": 0.058146521300363414,
      "grad_norm": 0.12940692901611328,
      "learning_rate": 2e-07,
      "loss": -0.0043,
      "step": 623
    },
    {
      "clip_ratio/high_max": 0.002043551048700465,
      "clip_ratio/high_mean": 0.0008772184410190675,
      "clip_ratio/low_mean": 0.0006694986923321267,
      "clip_ratio/low_min": 5.122583570482675e-05,
      "clip_ratio/region_mean": 0.0015467170960619114,
      "epoch": 0.058239854400364,
      "grad_norm": 0.1330651193857193,
      "learning_rate": 2e-07,
      "loss": -0.0152,
      "step": 624
    },
    {
      "clip_ratio/high_max": 0.0019444019526417833,
      "clip_ratio/high_mean": 0.000901491723197978,
      "clip_ratio/low_mean": 0.0006607248060390702,
      "clip_ratio/low_min": 8.575434003432747e-05,
      "clip_ratio/region_mean": 0.0015622165446984582,
      "epoch": 0.058333187500364585,
      "grad_norm": 0.13738784193992615,
      "learning_rate": 2e-07,
      "loss": 0.029,
      "step": 625
    },
    {
      "clip_ratio/high_max": 0.0019095624738838524,
      "clip_ratio/high_mean": 0.0007395011580229038,
      "clip_ratio/low_mean": 0.0005824506743010716,
      "clip_ratio/low_min": 3.587809260352515e-05,
      "clip_ratio/region_mean": 0.0013219518259575125,
      "epoch": 0.05842652060036516,
      "grad_norm": 0.14015622437000275,
      "learning_rate": 2e-07,
      "loss": 0.0295,
      "step": 626
    },
    {
      "clip_ratio/high_max": 0.0015879261518421117,
      "clip_ratio/high_mean": 0.0007069680050335592,
      "clip_ratio/low_mean": 0.0005264173141767969,
      "clip_ratio/low_min": 3.0555547709809616e-05,
      "clip_ratio/region_mean": 0.0012333853264863137,
      "epoch": 0.05851985370036575,
      "grad_norm": 0.11589527875185013,
      "learning_rate": 2e-07,
      "loss": 0.005,
      "step": 627
    },
    {
      "clip_ratio/high_max": 0.0018926439806818962,
      "clip_ratio/high_mean": 0.0007253129351738608,
      "clip_ratio/low_mean": 0.0005649846516462276,
      "clip_ratio/low_min": 1.7246136849280447e-05,
      "clip_ratio/region_mean": 0.0012902975795441307,
      "epoch": 0.05861318680036633,
      "grad_norm": 0.12498581409454346,
      "learning_rate": 2e-07,
      "loss": 0.0129,
      "step": 628
    },
    {
      "clip_ratio/high_max": 0.0018813434326148126,
      "clip_ratio/high_mean": 0.0007009445853327634,
      "clip_ratio/low_mean": 0.0006813356885686517,
      "clip_ratio/low_min": 2.2374528271029703e-05,
      "clip_ratio/region_mean": 0.0013822802793583833,
      "epoch": 0.05870651990036692,
      "grad_norm": 0.13449352979660034,
      "learning_rate": 2e-07,
      "loss": 0.0606,
      "step": 629
    },
    {
      "clip_ratio/high_max": 0.0019149374747939873,
      "clip_ratio/high_mean": 0.0007418008281092625,
      "clip_ratio/low_mean": 0.0007568519413325703,
      "clip_ratio/low_min": 6.313886842690408e-05,
      "clip_ratio/region_mean": 0.0014986527676228434,
      "epoch": 0.0587998530003675,
      "grad_norm": 0.12492045760154724,
      "learning_rate": 2e-07,
      "loss": 0.024,
      "step": 630
    },
    {
      "clip_ratio/high_max": 0.0020977575113647617,
      "clip_ratio/high_mean": 0.0007916204049251974,
      "clip_ratio/low_mean": 0.0007588077005493687,
      "clip_ratio/low_min": 0.00013757063788943924,
      "clip_ratio/region_mean": 0.001550428096379619,
      "epoch": 0.05889318610036808,
      "grad_norm": 0.135748952627182,
      "learning_rate": 2e-07,
      "loss": 0.0745,
      "step": 631
    },
    {
      "clip_ratio/high_max": 0.0018270688451593742,
      "clip_ratio/high_mean": 0.0007102314011717681,
      "clip_ratio/low_mean": 0.0006292733178270282,
      "clip_ratio/low_min": 4.093898769497173e-05,
      "clip_ratio/region_mean": 0.0013395047244557645,
      "epoch": 0.05898651920036867,
      "grad_norm": 0.13410218060016632,
      "learning_rate": 2e-07,
      "loss": 0.0397,
      "step": 632
    },
    {
      "clip_ratio/high_max": 0.002197666333813686,
      "clip_ratio/high_mean": 0.000817728256151895,
      "clip_ratio/low_mean": 0.0005857736214238685,
      "clip_ratio/low_min": 7.592322617711034e-06,
      "clip_ratio/region_mean": 0.0014035018903086893,
      "epoch": 0.05907985230036925,
      "grad_norm": 0.13063833117485046,
      "learning_rate": 2e-07,
      "loss": -0.0181,
      "step": 633
    },
    {
      "clip_ratio/high_max": 0.002088592984364368,
      "clip_ratio/high_mean": 0.0008108243673632387,
      "clip_ratio/low_mean": 0.0006597821193281561,
      "clip_ratio/low_min": 1.3757428860117216e-05,
      "clip_ratio/region_mean": 0.0014706064612255432,
      "epoch": 0.05917318540036983,
      "grad_norm": 0.12496549636125565,
      "learning_rate": 2e-07,
      "loss": 0.0244,
      "step": 634
    },
    {
      "clip_ratio/high_max": 0.002147826955479104,
      "clip_ratio/high_mean": 0.0008981159353425028,
      "clip_ratio/low_mean": 0.0007368638689513318,
      "clip_ratio/low_min": 0.00012901648096885765,
      "clip_ratio/region_mean": 0.0016349798170267604,
      "epoch": 0.059266518500370416,
      "grad_norm": 0.15332888066768646,
      "learning_rate": 2e-07,
      "loss": 0.0002,
      "step": 635
    },
    {
      "clip_ratio/high_max": 0.0017043730949808378,
      "clip_ratio/high_mean": 0.0006608036728721345,
      "clip_ratio/low_mean": 0.0005998108481435338,
      "clip_ratio/low_min": 2.775927168841008e-05,
      "clip_ratio/region_mean": 0.0012606145319296047,
      "epoch": 0.059359851600371,
      "grad_norm": 0.1403980404138565,
      "learning_rate": 2e-07,
      "loss": 0.0598,
      "step": 636
    },
    {
      "clip_ratio/high_max": 0.001959842113137711,
      "clip_ratio/high_mean": 0.000792916431237245,
      "clip_ratio/low_mean": 0.0005838958913955139,
      "clip_ratio/low_min": 6.341314929159125e-06,
      "clip_ratio/region_mean": 0.0013768123390036635,
      "epoch": 0.05945318470037158,
      "grad_norm": 0.13317140936851501,
      "learning_rate": 2e-07,
      "loss": 0.0459,
      "step": 637
    },
    {
      "clip_ratio/high_max": 0.0017596183279238176,
      "clip_ratio/high_mean": 0.0006951760715310229,
      "clip_ratio/low_mean": 0.0007069658277032431,
      "clip_ratio/low_min": 8.743433954805369e-05,
      "clip_ratio/region_mean": 0.0014021418974152766,
      "epoch": 0.059546517800372165,
      "grad_norm": 0.12893326580524445,
      "learning_rate": 2e-07,
      "loss": 0.0465,
      "step": 638
    },
    {
      "clip_ratio/high_max": 0.0020533813476504292,
      "clip_ratio/high_mean": 0.0007459484040737152,
      "clip_ratio/low_mean": 0.000673320573696401,
      "clip_ratio/low_min": 3.2872610972844996e-05,
      "clip_ratio/region_mean": 0.0014192689704941586,
      "epoch": 0.05963985090037275,
      "grad_norm": 0.14024290442466736,
      "learning_rate": 2e-07,
      "loss": 0.0161,
      "step": 639
    },
    {
      "clip_ratio/high_max": 0.0020172522781649604,
      "clip_ratio/high_mean": 0.000765625454732799,
      "clip_ratio/low_mean": 0.0005502803778654197,
      "clip_ratio/low_min": 3.56140335497912e-05,
      "clip_ratio/region_mean": 0.0013159058325982187,
      "epoch": 0.059733184000373335,
      "grad_norm": 0.12708166241645813,
      "learning_rate": 2e-07,
      "loss": 0.0182,
      "step": 640
    },
    {
      "clip_ratio/high_max": 0.02092636685119942,
      "clip_ratio/high_mean": 0.00911651787464507,
      "clip_ratio/low_mean": 0.0026331456101615913,
      "clip_ratio/low_min": 0.00020501024118857458,
      "clip_ratio/region_mean": 0.011749663448426872,
      "completions/clipped_ratio": 0.016339983258928603,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4094.0,
      "completions/mean_length": 662.2559814453125,
      "completions/mean_terminated_length": 605.2166748046875,
      "completions/min_length": 81.0,
      "completions/min_terminated_length": 81.0,
      "epoch": 0.05982651710037391,
      "grad_norm": 1365884.75,
      "learning_rate": 2e-07,
      "loss": 754.9741,
      "num_tokens": 503988990.0,
      "reward": 0.5851876735687256,
      "reward_std": 0.1897149533033371,
      "rewards/simpleverify_reward/mean": 0.5851876139640808,
      "rewards/simpleverify_reward/std": 0.4926918148994446,
      "step": 641
    },
    {
      "clip_ratio/high_max": 0.0017065773863578215,
      "clip_ratio/high_mean": 0.0006681604663754115,
      "clip_ratio/low_mean": 0.0006310067692538723,
      "clip_ratio/low_min": 6.089785983931506e-05,
      "clip_ratio/region_mean": 0.0012991672447242308,
      "epoch": 0.0599198502003745,
      "grad_norm": 0.12068770825862885,
      "learning_rate": 2e-07,
      "loss": 0.0108,
      "step": 642
    },
    {
      "clip_ratio/high_max": 0.001730965515889693,
      "clip_ratio/high_mean": 0.0006250574406294618,
      "clip_ratio/low_mean": 0.0005252438168099616,
      "clip_ratio/low_min": 2.9053457183181308e-05,
      "clip_ratio/region_mean": 0.0011503012428875081,
      "epoch": 0.060013183300375084,
      "grad_norm": 0.125808447599411,
      "learning_rate": 2e-07,
      "loss": 0.0274,
      "step": 643
    },
    {
      "clip_ratio/high_max": 0.0016850394531502388,
      "clip_ratio/high_mean": 0.000668474083795445,
      "clip_ratio/low_mean": 0.0005000874962206581,
      "clip_ratio/low_min": 2.4826216758810915e-05,
      "clip_ratio/region_mean": 0.0011685615972965024,
      "epoch": 0.06010651640037567,
      "grad_norm": 0.12118154019117355,
      "learning_rate": 2e-07,
      "loss": 0.0184,
      "step": 644
    },
    {
      "clip_ratio/high_max": 0.0016316668734361883,
      "clip_ratio/high_mean": 0.0006467286038969178,
      "clip_ratio/low_mean": 0.0006818644997110823,
      "clip_ratio/low_min": 3.6188573176332284e-05,
      "clip_ratio/region_mean": 0.0013285931381687988,
      "epoch": 0.06019984950037625,
      "grad_norm": 0.12603475153446198,
      "learning_rate": 2e-07,
      "loss": 0.0395,
      "step": 645
    },
    {
      "clip_ratio/high_max": 0.0018834678157872986,
      "clip_ratio/high_mean": 0.0006996198872002424,
      "clip_ratio/low_mean": 0.0005479102946992498,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012475301919039339,
      "epoch": 0.06029318260037683,
      "grad_norm": 0.13647961616516113,
      "learning_rate": 2e-07,
      "loss": -0.003,
      "step": 646
    },
    {
      "clip_ratio/high_max": 0.0015827391944185365,
      "clip_ratio/high_mean": 0.0006524945520141046,
      "clip_ratio/low_mean": 0.0005707615746359807,
      "clip_ratio/low_min": 4.483800012167194e-05,
      "clip_ratio/region_mean": 0.001223256123921601,
      "epoch": 0.06038651570037742,
      "grad_norm": 0.10979334264993668,
      "learning_rate": 2e-07,
      "loss": 0.0373,
      "step": 647
    },
    {
      "clip_ratio/high_max": 0.0016456763150927145,
      "clip_ratio/high_mean": 0.000672917876727297,
      "clip_ratio/low_mean": 0.0005004310442018323,
      "clip_ratio/low_min": 1.699293170531746e-05,
      "clip_ratio/region_mean": 0.0011733489191101398,
      "epoch": 0.060479848800377996,
      "grad_norm": 0.12378764152526855,
      "learning_rate": 2e-07,
      "loss": 0.0409,
      "step": 648
    },
    {
      "clip_ratio/high_max": 0.0017563787478138693,
      "clip_ratio/high_mean": 0.0006613577461394016,
      "clip_ratio/low_mean": 0.0005320533109625103,
      "clip_ratio/low_min": 3.86052270187065e-05,
      "clip_ratio/region_mean": 0.0011934110407310072,
      "epoch": 0.06057318190037858,
      "grad_norm": 0.12648127973079681,
      "learning_rate": 2e-07,
      "loss": 0.0262,
      "step": 649
    },
    {
      "clip_ratio/high_max": 0.0014960420594434254,
      "clip_ratio/high_mean": 0.0005957888351986185,
      "clip_ratio/low_mean": 0.0005056591426182422,
      "clip_ratio/low_min": 1.1140819879074115e-05,
      "clip_ratio/region_mean": 0.0011014479714503977,
      "epoch": 0.060666515000379166,
      "grad_norm": 0.1355755478143692,
      "learning_rate": 2e-07,
      "loss": 0.0558,
      "step": 650
    },
    {
      "clip_ratio/high_max": 0.001664666098804446,
      "clip_ratio/high_mean": 0.0006345188267005142,
      "clip_ratio/low_mean": 0.0005502725643964368,
      "clip_ratio/low_min": 5.613666053250199e-05,
      "clip_ratio/region_mean": 0.0011847913883684669,
      "epoch": 0.06075984810037975,
      "grad_norm": 0.12586739659309387,
      "learning_rate": 2e-07,
      "loss": 0.0562,
      "step": 651
    },
    {
      "clip_ratio/high_max": 0.0016897981622605585,
      "clip_ratio/high_mean": 0.0007013797530817101,
      "clip_ratio/low_mean": 0.0005595267984972452,
      "clip_ratio/low_min": 2.9481141609721817e-05,
      "clip_ratio/region_mean": 0.0012609065634023864,
      "epoch": 0.06085318120038033,
      "grad_norm": 0.1216101348400116,
      "learning_rate": 2e-07,
      "loss": -0.0016,
      "step": 652
    },
    {
      "clip_ratio/high_max": 0.001654162851991714,
      "clip_ratio/high_mean": 0.0006733025825269578,
      "clip_ratio/low_mean": 0.0005089970859444293,
      "clip_ratio/low_min": 4.363052357803099e-05,
      "clip_ratio/region_mean": 0.0011822996602859348,
      "epoch": 0.060946514300380915,
      "grad_norm": 0.12671025097370148,
      "learning_rate": 2e-07,
      "loss": 0.0067,
      "step": 653
    },
    {
      "clip_ratio/high_max": 0.0017454118642490357,
      "clip_ratio/high_mean": 0.0006835994390712585,
      "clip_ratio/low_mean": 0.0005551656822717632,
      "clip_ratio/low_min": 7.006811210885644e-05,
      "clip_ratio/region_mean": 0.001238765129528474,
      "epoch": 0.0610398474003815,
      "grad_norm": 0.12396043539047241,
      "learning_rate": 2e-07,
      "loss": 0.0216,
      "step": 654
    },
    {
      "clip_ratio/high_max": 0.0016575774898228701,
      "clip_ratio/high_mean": 0.0006655197103100363,
      "clip_ratio/low_mean": 0.0005959520467513357,
      "clip_ratio/low_min": 3.256022864661645e-05,
      "clip_ratio/region_mean": 0.0012614717707037926,
      "epoch": 0.061133180500382085,
      "grad_norm": 0.12199550122022629,
      "learning_rate": 2e-07,
      "loss": 0.0425,
      "step": 655
    },
    {
      "clip_ratio/high_max": 0.0017090075853047892,
      "clip_ratio/high_mean": 0.0007437635576934554,
      "clip_ratio/low_mean": 0.0005538780487768236,
      "clip_ratio/low_min": 2.8759850465576164e-05,
      "clip_ratio/region_mean": 0.001297641640121583,
      "epoch": 0.061226513600382663,
      "grad_norm": 0.11475273966789246,
      "learning_rate": 2e-07,
      "loss": 0.0198,
      "step": 656
    },
    {
      "clip_ratio/high_max": 0.0017478534391557332,
      "clip_ratio/high_mean": 0.0007449047625414096,
      "clip_ratio/low_mean": 0.0005980523692414863,
      "clip_ratio/low_min": 2.178457680201973e-05,
      "clip_ratio/region_mean": 0.0013429571117740124,
      "epoch": 0.06131984670038325,
      "grad_norm": 0.13247263431549072,
      "learning_rate": 2e-07,
      "loss": 0.0265,
      "step": 657
    },
    {
      "clip_ratio/high_max": 0.0017484819836681709,
      "clip_ratio/high_mean": 0.0007402138317047502,
      "clip_ratio/low_mean": 0.0006166663679323392,
      "clip_ratio/low_min": 5.5167659411381464e-05,
      "clip_ratio/region_mean": 0.0013568802060035523,
      "epoch": 0.061413179800383834,
      "grad_norm": 0.13908669352531433,
      "learning_rate": 2e-07,
      "loss": 0.024,
      "step": 658
    },
    {
      "clip_ratio/high_max": 0.0016893646388780326,
      "clip_ratio/high_mean": 0.0006303880654741079,
      "clip_ratio/low_mean": 0.0005771830274170497,
      "clip_ratio/low_min": 5.259279078018153e-05,
      "clip_ratio/region_mean": 0.001207571112900041,
      "epoch": 0.06150651290038442,
      "grad_norm": 0.11770395934581757,
      "learning_rate": 2e-07,
      "loss": 0.0121,
      "step": 659
    },
    {
      "clip_ratio/high_max": 0.0014463627194345463,
      "clip_ratio/high_mean": 0.0006558750883414177,
      "clip_ratio/low_mean": 0.00056148011390178,
      "clip_ratio/low_min": 4.235309825162403e-05,
      "clip_ratio/region_mean": 0.0012173551876912825,
      "epoch": 0.061599846000385,
      "grad_norm": 0.13160111010074615,
      "learning_rate": 2e-07,
      "loss": -0.006,
      "step": 660
    },
    {
      "clip_ratio/high_max": 0.0018279202849953435,
      "clip_ratio/high_mean": 0.0006532464030897245,
      "clip_ratio/low_mean": 0.0005032659555581631,
      "clip_ratio/low_min": 1.4927155461919028e-05,
      "clip_ratio/region_mean": 0.0011565123531909194,
      "epoch": 0.06169317910038558,
      "grad_norm": 0.13015127182006836,
      "learning_rate": 2e-07,
      "loss": 0.0182,
      "step": 661
    },
    {
      "clip_ratio/high_max": 0.0016299131784762722,
      "clip_ratio/high_mean": 0.0006979461595619796,
      "clip_ratio/low_mean": 0.0006059737606847193,
      "clip_ratio/low_min": 2.8777673378499458e-05,
      "clip_ratio/region_mean": 0.0013039199329796247,
      "epoch": 0.06178651220038617,
      "grad_norm": 0.13408970832824707,
      "learning_rate": 2e-07,
      "loss": 0.0214,
      "step": 662
    },
    {
      "clip_ratio/high_max": 0.0014583126212528441,
      "clip_ratio/high_mean": 0.0005836872824147576,
      "clip_ratio/low_mean": 0.0005877462754142471,
      "clip_ratio/low_min": 4.274965976946987e-05,
      "clip_ratio/region_mean": 0.0011714335705619305,
      "epoch": 0.061879845300386746,
      "grad_norm": 0.12468250840902328,
      "learning_rate": 2e-07,
      "loss": 0.0419,
      "step": 663
    },
    {
      "clip_ratio/high_max": 0.001667812051891815,
      "clip_ratio/high_mean": 0.0006553807925229194,
      "clip_ratio/low_mean": 0.000523083528605639,
      "clip_ratio/low_min": 2.0741557818837464e-05,
      "clip_ratio/region_mean": 0.0011784643247665372,
      "epoch": 0.06197317840038733,
      "grad_norm": 0.12835747003555298,
      "learning_rate": 2e-07,
      "loss": 0.0224,
      "step": 664
    },
    {
      "clip_ratio/high_max": 0.0015729515907878522,
      "clip_ratio/high_mean": 0.0006172027096909005,
      "clip_ratio/low_mean": 0.0005488729864282504,
      "clip_ratio/low_min": 6.383155687217368e-05,
      "clip_ratio/region_mean": 0.0011660757008939981,
      "epoch": 0.062066511500387916,
      "grad_norm": 0.12002723664045334,
      "learning_rate": 2e-07,
      "loss": -0.0239,
      "step": 665
    },
    {
      "clip_ratio/high_max": 0.0021446828759508207,
      "clip_ratio/high_mean": 0.0007378095051535638,
      "clip_ratio/low_mean": 0.0006026764294801978,
      "clip_ratio/low_min": 6.826732806075597e-05,
      "clip_ratio/region_mean": 0.0013404859419097193,
      "epoch": 0.0621598446003885,
      "grad_norm": 0.1323888599872589,
      "learning_rate": 2e-07,
      "loss": 0.0659,
      "step": 666
    },
    {
      "clip_ratio/high_max": 0.0017468734258727636,
      "clip_ratio/high_mean": 0.00072161966272688,
      "clip_ratio/low_mean": 0.000522592412380618,
      "clip_ratio/low_min": 4.996178722649347e-05,
      "clip_ratio/region_mean": 0.0012442120678315405,
      "epoch": 0.06225317770038908,
      "grad_norm": 0.16321566700935364,
      "learning_rate": 2e-07,
      "loss": -0.0122,
      "step": 667
    },
    {
      "clip_ratio/high_max": 0.0018500303012842778,
      "clip_ratio/high_mean": 0.0007944196950120386,
      "clip_ratio/low_mean": 0.0005760900894529186,
      "clip_ratio/low_min": 7.073568031046307e-05,
      "clip_ratio/region_mean": 0.0013705097990168724,
      "epoch": 0.062346510800389665,
      "grad_norm": 0.7605500221252441,
      "learning_rate": 2e-07,
      "loss": 0.0373,
      "step": 668
    },
    {
      "clip_ratio/high_max": 0.0016664655340719037,
      "clip_ratio/high_mean": 0.0006709124663757393,
      "clip_ratio/low_mean": 0.0005034664127379074,
      "clip_ratio/low_min": 5.518204488907941e-05,
      "clip_ratio/region_mean": 0.0011743788891180884,
      "epoch": 0.06243984390039025,
      "grad_norm": 0.12057474255561829,
      "learning_rate": 2e-07,
      "loss": 0.0196,
      "step": 669
    },
    {
      "clip_ratio/high_max": 0.0017185471770062577,
      "clip_ratio/high_mean": 0.0006968451434659073,
      "clip_ratio/low_mean": 0.0005092984847578919,
      "clip_ratio/low_min": 1.0111632036569063e-05,
      "clip_ratio/region_mean": 0.001206143591844011,
      "epoch": 0.06253317700039084,
      "grad_norm": 0.1370396912097931,
      "learning_rate": 2e-07,
      "loss": 0.0033,
      "step": 670
    },
    {
      "clip_ratio/high_max": 0.0020873833491350524,
      "clip_ratio/high_mean": 0.0008032144323806278,
      "clip_ratio/low_mean": 0.0005407195385487285,
      "clip_ratio/low_min": 4.871517649007728e-05,
      "clip_ratio/region_mean": 0.0013439339491014834,
      "epoch": 0.06262651010039141,
      "grad_norm": 0.12908096611499786,
      "learning_rate": 2e-07,
      "loss": -0.0074,
      "step": 671
    },
    {
      "clip_ratio/high_max": 0.0018211700589745305,
      "clip_ratio/high_mean": 0.0006363991524267476,
      "clip_ratio/low_mean": 0.0005653623211401282,
      "clip_ratio/low_min": 3.167420618410688e-05,
      "clip_ratio/region_mean": 0.001201761497213738,
      "epoch": 0.062719843200392,
      "grad_norm": 0.12195020914077759,
      "learning_rate": 2e-07,
      "loss": 0.0639,
      "step": 672
    },
    {
      "clip_ratio/high_max": 0.0016658248496241868,
      "clip_ratio/high_mean": 0.0005900564055991708,
      "clip_ratio/low_mean": 0.0005537913511943771,
      "clip_ratio/low_min": 2.931248218374094e-05,
      "clip_ratio/region_mean": 0.0011438477467891062,
      "epoch": 0.06281317630039258,
      "grad_norm": 0.11666692793369293,
      "learning_rate": 2e-07,
      "loss": 0.06,
      "step": 673
    },
    {
      "clip_ratio/high_max": 0.0018279250944033265,
      "clip_ratio/high_mean": 0.0007008269276411738,
      "clip_ratio/low_mean": 0.000625688227955834,
      "clip_ratio/low_min": 3.0054607577767456e-05,
      "clip_ratio/region_mean": 0.0013265151865198277,
      "epoch": 0.06290650940039316,
      "grad_norm": 0.1199314072728157,
      "learning_rate": 2e-07,
      "loss": -0.0018,
      "step": 674
    },
    {
      "clip_ratio/high_max": 0.0017797584223444574,
      "clip_ratio/high_mean": 0.0007540653004980413,
      "clip_ratio/low_mean": 0.0006237299348867964,
      "clip_ratio/low_min": 8.825190889183432e-06,
      "clip_ratio/region_mean": 0.0013777952262898907,
      "epoch": 0.06299984250039375,
      "grad_norm": 0.13348956406116486,
      "learning_rate": 2e-07,
      "loss": 0.0296,
      "step": 675
    },
    {
      "clip_ratio/high_max": 0.0017820864013629034,
      "clip_ratio/high_mean": 0.0006629771332882228,
      "clip_ratio/low_mean": 0.0006046263324606116,
      "clip_ratio/low_min": 8.266373879450839e-05,
      "clip_ratio/region_mean": 0.001267603463929845,
      "epoch": 0.06309317560039433,
      "grad_norm": 0.132685124874115,
      "learning_rate": 2e-07,
      "loss": 0.0548,
      "step": 676
    },
    {
      "clip_ratio/high_max": 0.0014455714917858131,
      "clip_ratio/high_mean": 0.0006452912239183206,
      "clip_ratio/low_mean": 0.00047958471623132937,
      "clip_ratio/low_min": 1.3478542314260267e-05,
      "clip_ratio/region_mean": 0.0011248759328736924,
      "epoch": 0.06318650870039491,
      "grad_norm": 0.12158458679914474,
      "learning_rate": 2e-07,
      "loss": 0.0445,
      "step": 677
    },
    {
      "clip_ratio/high_max": 0.0019001661603397224,
      "clip_ratio/high_mean": 0.0008478759682475356,
      "clip_ratio/low_mean": 0.0006295389466686174,
      "clip_ratio/low_min": 4.7775852181075606e-05,
      "clip_ratio/region_mean": 0.001477414905821206,
      "epoch": 0.0632798418003955,
      "grad_norm": 0.23240794241428375,
      "learning_rate": 2e-07,
      "loss": 0.004,
      "step": 678
    },
    {
      "clip_ratio/high_max": 0.0016498203549417667,
      "clip_ratio/high_mean": 0.0006674472469967441,
      "clip_ratio/low_mean": 0.0005517329627764411,
      "clip_ratio/low_min": 2.261870986330905e-05,
      "clip_ratio/region_mean": 0.0012191802125016693,
      "epoch": 0.06337317490039608,
      "grad_norm": 0.2108023464679718,
      "learning_rate": 2e-07,
      "loss": 0.0185,
      "step": 679
    },
    {
      "clip_ratio/high_max": 0.0017059472775144968,
      "clip_ratio/high_mean": 0.000640398689029098,
      "clip_ratio/low_mean": 0.0005386439320318459,
      "clip_ratio/low_min": 7.18225692253327e-06,
      "clip_ratio/region_mean": 0.0011790426124207443,
      "epoch": 0.06346650800039666,
      "grad_norm": 0.1245657354593277,
      "learning_rate": 2e-07,
      "loss": 0.0511,
      "step": 680
    },
    {
      "clip_ratio/high_max": 0.0017104010839830153,
      "clip_ratio/high_mean": 0.0006297570889728377,
      "clip_ratio/low_mean": 0.0006337284339679172,
      "clip_ratio/low_min": 5.7636620113044046e-05,
      "clip_ratio/region_mean": 0.0012634855374926701,
      "epoch": 0.06355984110039725,
      "grad_norm": 0.14375777542591095,
      "learning_rate": 2e-07,
      "loss": 0.0539,
      "step": 681
    },
    {
      "clip_ratio/high_max": 0.0017551425698911771,
      "clip_ratio/high_mean": 0.0007165225979406387,
      "clip_ratio/low_mean": 0.0005489909472089494,
      "clip_ratio/low_min": 2.4218548787757754e-05,
      "clip_ratio/region_mean": 0.0012655135687964503,
      "epoch": 0.06365317420039783,
      "grad_norm": 0.13683193922042847,
      "learning_rate": 2e-07,
      "loss": 0.0323,
      "step": 682
    },
    {
      "clip_ratio/high_max": 0.001880586234619841,
      "clip_ratio/high_mean": 0.0008188173505914165,
      "clip_ratio/low_mean": 0.0006308059873845195,
      "clip_ratio/low_min": 1.7472742911195382e-05,
      "clip_ratio/region_mean": 0.0014496233598038089,
      "epoch": 0.06374650730039842,
      "grad_norm": 0.1362380087375641,
      "learning_rate": 2e-07,
      "loss": 0.0069,
      "step": 683
    },
    {
      "clip_ratio/high_max": 0.0015462803930859081,
      "clip_ratio/high_mean": 0.000618541651419946,
      "clip_ratio/low_mean": 0.0004311111606511986,
      "clip_ratio/low_min": 1.6496749594807625e-05,
      "clip_ratio/region_mean": 0.0010496528157091234,
      "epoch": 0.063839840400399,
      "grad_norm": 0.1300773173570633,
      "learning_rate": 2e-07,
      "loss": -0.001,
      "step": 684
    },
    {
      "clip_ratio/high_max": 0.0015001613028289285,
      "clip_ratio/high_mean": 0.0005908993643970462,
      "clip_ratio/low_mean": 0.0006145246552478056,
      "clip_ratio/low_min": 4.9877981837198604e-05,
      "clip_ratio/region_mean": 0.0012054240323777776,
      "epoch": 0.06393317350039958,
      "grad_norm": 0.1277017742395401,
      "learning_rate": 2e-07,
      "loss": 0.067,
      "step": 685
    },
    {
      "clip_ratio/high_max": 0.0015584733391733607,
      "clip_ratio/high_mean": 0.0006159597569421749,
      "clip_ratio/low_mean": 0.0005733204889111221,
      "clip_ratio/low_min": 2.2012056433595717e-05,
      "clip_ratio/region_mean": 0.0011892802431248128,
      "epoch": 0.06402650660040017,
      "grad_norm": 0.12499699741601944,
      "learning_rate": 2e-07,
      "loss": 0.0366,
      "step": 686
    },
    {
      "clip_ratio/high_max": 0.0014135846504359506,
      "clip_ratio/high_mean": 0.0006369060192810139,
      "clip_ratio/low_mean": 0.0006140184996183962,
      "clip_ratio/low_min": 4.3716231630241964e-05,
      "clip_ratio/region_mean": 0.0012509245425462723,
      "epoch": 0.06411983970040075,
      "grad_norm": 0.12887609004974365,
      "learning_rate": 2e-07,
      "loss": 0.0461,
      "step": 687
    },
    {
      "clip_ratio/high_max": 0.0015638781624147668,
      "clip_ratio/high_mean": 0.0006727978343405994,
      "clip_ratio/low_mean": 0.0006178403964440804,
      "clip_ratio/low_min": 7.245242341014091e-05,
      "clip_ratio/region_mean": 0.0012906382289656904,
      "epoch": 0.06421317280040133,
      "grad_norm": 0.1270231157541275,
      "learning_rate": 2e-07,
      "loss": 0.0253,
      "step": 688
    },
    {
      "clip_ratio/high_max": 0.0020093826460652053,
      "clip_ratio/high_mean": 0.0008021069625101518,
      "clip_ratio/low_mean": 0.0004748574183395249,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012769644090440124,
      "epoch": 0.06430650590040192,
      "grad_norm": 0.12813836336135864,
      "learning_rate": 2e-07,
      "loss": -0.0216,
      "step": 689
    },
    {
      "clip_ratio/high_max": 0.001896862388093723,
      "clip_ratio/high_mean": 0.0008131685135595035,
      "clip_ratio/low_mean": 0.0006969935402594274,
      "clip_ratio/low_min": 1.859549229266122e-05,
      "clip_ratio/region_mean": 0.0015101620447239839,
      "epoch": 0.0643998390004025,
      "grad_norm": 0.1347668319940567,
      "learning_rate": 2e-07,
      "loss": 0.0181,
      "step": 690
    },
    {
      "clip_ratio/high_max": 0.0017879898769024294,
      "clip_ratio/high_mean": 0.0007061422984406818,
      "clip_ratio/low_mean": 0.000609958908171393,
      "clip_ratio/low_min": 1.1524985893629491e-05,
      "clip_ratio/region_mean": 0.0013161012102500536,
      "epoch": 0.06449317210040308,
      "grad_norm": 0.12205696851015091,
      "learning_rate": 2e-07,
      "loss": 0.0285,
      "step": 691
    },
    {
      "clip_ratio/high_max": 0.001683655777014792,
      "clip_ratio/high_mean": 0.0006340133713820251,
      "clip_ratio/low_mean": 0.0006758243880540249,
      "clip_ratio/low_min": 3.171433763782261e-05,
      "clip_ratio/region_mean": 0.0013098377785354387,
      "epoch": 0.06458650520040367,
      "grad_norm": 0.12861458957195282,
      "learning_rate": 2e-07,
      "loss": 0.0646,
      "step": 692
    },
    {
      "clip_ratio/high_max": 0.0014577286237908993,
      "clip_ratio/high_mean": 0.0005960850976407528,
      "clip_ratio/low_mean": 0.0005952550645815791,
      "clip_ratio/low_min": 7.587713753309799e-06,
      "clip_ratio/region_mean": 0.0011913401795027312,
      "epoch": 0.06467983830040425,
      "grad_norm": 0.13748180866241455,
      "learning_rate": 2e-07,
      "loss": 0.0428,
      "step": 693
    },
    {
      "clip_ratio/high_max": 0.00193388285151741,
      "clip_ratio/high_mean": 0.0007328521787712816,
      "clip_ratio/low_mean": 0.0005002969328415929,
      "clip_ratio/low_min": 3.787717196246376e-05,
      "clip_ratio/region_mean": 0.0012331491270742845,
      "epoch": 0.06477317140040484,
      "grad_norm": 0.13457660377025604,
      "learning_rate": 2e-07,
      "loss": -0.0163,
      "step": 694
    },
    {
      "clip_ratio/high_max": 0.0017190680810017511,
      "clip_ratio/high_mean": 0.000632153736660257,
      "clip_ratio/low_mean": 0.0005849529879924376,
      "clip_ratio/low_min": 1.9975170289399102e-05,
      "clip_ratio/region_mean": 0.0012171067064628005,
      "epoch": 0.06486650450040542,
      "grad_norm": 0.12993580102920532,
      "learning_rate": 2e-07,
      "loss": -0.0064,
      "step": 695
    },
    {
      "clip_ratio/high_max": 0.0017197706110891886,
      "clip_ratio/high_mean": 0.0007023792641120963,
      "clip_ratio/low_mean": 0.0005865202474524267,
      "clip_ratio/low_min": 2.6220986001135316e-05,
      "clip_ratio/region_mean": 0.0012888994860986713,
      "epoch": 0.064959837600406,
      "grad_norm": 0.12869040668010712,
      "learning_rate": 2e-07,
      "loss": 0.0276,
      "step": 696
    },
    {
      "clip_ratio/high_max": 0.001507964789198013,
      "clip_ratio/high_mean": 0.0006283692819124553,
      "clip_ratio/low_mean": 0.0005688575326985301,
      "clip_ratio/low_min": 2.0697924355772557e-05,
      "clip_ratio/region_mean": 0.0011972268330282532,
      "epoch": 0.06505317070040659,
      "grad_norm": 0.11785142868757248,
      "learning_rate": 2e-07,
      "loss": 0.0408,
      "step": 697
    },
    {
      "clip_ratio/high_max": 0.0016889129983610474,
      "clip_ratio/high_mean": 0.0007024408359939116,
      "clip_ratio/low_mean": 0.0005552773691306356,
      "clip_ratio/low_min": 5.5123628953879233e-05,
      "clip_ratio/region_mean": 0.0012577181914821267,
      "epoch": 0.06514650380040717,
      "grad_norm": 0.12636211514472961,
      "learning_rate": 2e-07,
      "loss": 0.0415,
      "step": 698
    },
    {
      "clip_ratio/high_max": 0.0014897844994266052,
      "clip_ratio/high_mean": 0.0005816352086185361,
      "clip_ratio/low_mean": 0.0005174009265829227,
      "clip_ratio/low_min": 8.71930842549773e-06,
      "clip_ratio/region_mean": 0.0010990361461153952,
      "epoch": 0.06523983690040774,
      "grad_norm": 0.49638545513153076,
      "learning_rate": 2e-07,
      "loss": 0.0151,
      "step": 699
    },
    {
      "clip_ratio/high_max": 0.0017284897548961453,
      "clip_ratio/high_mean": 0.0007320513868762646,
      "clip_ratio/low_mean": 0.000541347915714141,
      "clip_ratio/low_min": 1.617494854144752e-05,
      "clip_ratio/region_mean": 0.0012733993062283844,
      "epoch": 0.06533317000040834,
      "grad_norm": 0.12663838267326355,
      "learning_rate": 2e-07,
      "loss": -0.0085,
      "step": 700
    },
    {
      "clip_ratio/high_max": 0.0016152882526512258,
      "clip_ratio/high_mean": 0.0007114342261047568,
      "clip_ratio/low_mean": 0.0005025990249123424,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012140332291892264,
      "epoch": 0.06542650310040891,
      "grad_norm": 0.12812025845050812,
      "learning_rate": 2e-07,
      "loss": -0.0069,
      "step": 701
    },
    {
      "clip_ratio/high_max": 0.0017815071441873442,
      "clip_ratio/high_mean": 0.0007084357184794499,
      "clip_ratio/low_mean": 0.0004825739351872471,
      "clip_ratio/low_min": 4.561720834317384e-05,
      "clip_ratio/region_mean": 0.001191009665490128,
      "epoch": 0.06551983620040949,
      "grad_norm": 0.12003355473279953,
      "learning_rate": 2e-07,
      "loss": -0.0175,
      "step": 702
    },
    {
      "clip_ratio/high_max": 0.0018161366242566146,
      "clip_ratio/high_mean": 0.0007496271882700967,
      "clip_ratio/low_mean": 0.0006222048523341073,
      "clip_ratio/low_min": 2.633242002048064e-05,
      "clip_ratio/region_mean": 0.0013718320115003735,
      "epoch": 0.06561316930041008,
      "grad_norm": 0.13450071215629578,
      "learning_rate": 2e-07,
      "loss": -0.0127,
      "step": 703
    },
    {
      "clip_ratio/high_max": 0.0017458758593420498,
      "clip_ratio/high_mean": 0.0007060937950882362,
      "clip_ratio/low_mean": 0.0006095738663134398,
      "clip_ratio/low_min": 3.218835217921878e-05,
      "clip_ratio/region_mean": 0.0013156676359358244,
      "epoch": 0.06570650240041066,
      "grad_norm": 0.12530018389225006,
      "learning_rate": 2e-07,
      "loss": 0.04,
      "step": 704
    },
    {
      "clip_ratio/high_max": 0.0017650343725108542,
      "clip_ratio/high_mean": 0.0007810108945704997,
      "clip_ratio/low_mean": 0.0006335267644317355,
      "clip_ratio/low_min": 5.295045866660075e-05,
      "clip_ratio/region_mean": 0.0014145376953820232,
      "epoch": 0.06579983550041126,
      "grad_norm": 0.13335835933685303,
      "learning_rate": 2e-07,
      "loss": -0.0044,
      "step": 705
    },
    {
      "clip_ratio/high_max": 0.0015114101370272692,
      "clip_ratio/high_mean": 0.0005972737362753833,
      "clip_ratio/low_mean": 0.0006492882639577147,
      "clip_ratio/low_min": 0.00011737395561794983,
      "clip_ratio/region_mean": 0.0012465620238799602,
      "epoch": 0.06589316860041183,
      "grad_norm": 0.13296709954738617,
      "learning_rate": 2e-07,
      "loss": 0.058,
      "step": 706
    },
    {
      "clip_ratio/high_max": 0.0016603402837063186,
      "clip_ratio/high_mean": 0.0006937317521078512,
      "clip_ratio/low_mean": 0.0006222367301234044,
      "clip_ratio/low_min": 3.281970475654816e-05,
      "clip_ratio/region_mean": 0.0013159684713173192,
      "epoch": 0.06598650170041241,
      "grad_norm": 0.14746566116809845,
      "learning_rate": 2e-07,
      "loss": 0.0298,
      "step": 707
    },
    {
      "clip_ratio/high_max": 0.001845924802182708,
      "clip_ratio/high_mean": 0.0006878824387968052,
      "clip_ratio/low_mean": 0.0004872417857768596,
      "clip_ratio/low_min": 3.313130946480669e-05,
      "clip_ratio/region_mean": 0.0011751242418540642,
      "epoch": 0.066079834800413,
      "grad_norm": 0.11855975538492203,
      "learning_rate": 2e-07,
      "loss": -0.0128,
      "step": 708
    },
    {
      "clip_ratio/high_max": 0.001873504548711935,
      "clip_ratio/high_mean": 0.0006899400505062658,
      "clip_ratio/low_mean": 0.000627187599093304,
      "clip_ratio/low_min": 6.876307270431425e-05,
      "clip_ratio/region_mean": 0.0013171276696084533,
      "epoch": 0.06617316790041358,
      "grad_norm": 0.1277121752500534,
      "learning_rate": 2e-07,
      "loss": 0.0491,
      "step": 709
    },
    {
      "clip_ratio/high_max": 0.0016110573924379423,
      "clip_ratio/high_mean": 0.0006285007930273423,
      "clip_ratio/low_mean": 0.0005979634715913562,
      "clip_ratio/low_min": 4.5567341658170335e-05,
      "clip_ratio/region_mean": 0.0012264642609807197,
      "epoch": 0.06626650100041416,
      "grad_norm": 0.13598451018333435,
      "learning_rate": 2e-07,
      "loss": 0.0458,
      "step": 710
    },
    {
      "clip_ratio/high_max": 0.0013013172792852856,
      "clip_ratio/high_mean": 0.0005796274335807539,
      "clip_ratio/low_mean": 0.0005775121721853793,
      "clip_ratio/low_min": 2.177660553570604e-05,
      "clip_ratio/region_mean": 0.001157139635324711,
      "epoch": 0.06635983410041475,
      "grad_norm": 0.12078677117824554,
      "learning_rate": 2e-07,
      "loss": 0.0655,
      "step": 711
    },
    {
      "clip_ratio/high_max": 0.0018404439324513078,
      "clip_ratio/high_mean": 0.0007353419869104982,
      "clip_ratio/low_mean": 0.0005537161050597206,
      "clip_ratio/low_min": 9.481189408688806e-06,
      "clip_ratio/region_mean": 0.0012890580655948725,
      "epoch": 0.06645316720041533,
      "grad_norm": 0.23469290137290955,
      "learning_rate": 2e-07,
      "loss": 0.0517,
      "step": 712
    },
    {
      "clip_ratio/high_max": 0.0019216766449972056,
      "clip_ratio/high_mean": 0.0007578448276035488,
      "clip_ratio/low_mean": 0.000612449114669289,
      "clip_ratio/low_min": 5.650384355249116e-05,
      "clip_ratio/region_mean": 0.0013702939395443536,
      "epoch": 0.06654650030041591,
      "grad_norm": 0.15581178665161133,
      "learning_rate": 2e-07,
      "loss": 0.0482,
      "step": 713
    },
    {
      "clip_ratio/high_max": 0.0018119904343620874,
      "clip_ratio/high_mean": 0.0008236179146479117,
      "clip_ratio/low_mean": 0.0005594272793132404,
      "clip_ratio/low_min": 2.0195907836750848e-05,
      "clip_ratio/region_mean": 0.0013830451789544895,
      "epoch": 0.0666398334004165,
      "grad_norm": 0.13393065333366394,
      "learning_rate": 2e-07,
      "loss": 0.0061,
      "step": 714
    },
    {
      "clip_ratio/high_max": 0.0019005545946129132,
      "clip_ratio/high_mean": 0.000769074416894,
      "clip_ratio/low_mean": 0.0004924691852465912,
      "clip_ratio/low_min": 2.4428376491414383e-05,
      "clip_ratio/region_mean": 0.0012615436098712962,
      "epoch": 0.06673316650041708,
      "grad_norm": 0.13768470287322998,
      "learning_rate": 2e-07,
      "loss": 0.0413,
      "step": 715
    },
    {
      "clip_ratio/high_max": 0.001969527846085839,
      "clip_ratio/high_mean": 0.0007563246090285247,
      "clip_ratio/low_mean": 0.0004865717237407807,
      "clip_ratio/low_min": 1.941896516655106e-05,
      "clip_ratio/region_mean": 0.0012428963200363796,
      "epoch": 0.06682649960041767,
      "grad_norm": 0.12603184580802917,
      "learning_rate": 2e-07,
      "loss": -0.0039,
      "step": 716
    },
    {
      "clip_ratio/high_max": 0.001646428612730233,
      "clip_ratio/high_mean": 0.0006939051108929561,
      "clip_ratio/low_mean": 0.0006199538838700391,
      "clip_ratio/low_min": 5.3864967412664555e-05,
      "clip_ratio/region_mean": 0.0013138589820300695,
      "epoch": 0.06691983270041825,
      "grad_norm": 0.1386903077363968,
      "learning_rate": 2e-07,
      "loss": 0.0503,
      "step": 717
    },
    {
      "clip_ratio/high_max": 0.0017478908612247324,
      "clip_ratio/high_mean": 0.0007568989344690635,
      "clip_ratio/low_mean": 0.0005725580067519331,
      "clip_ratio/low_min": 8.82643689692486e-06,
      "clip_ratio/region_mean": 0.001329456914390903,
      "epoch": 0.06701316580041883,
      "grad_norm": 0.13218489289283752,
      "learning_rate": 2e-07,
      "loss": 0.0129,
      "step": 718
    },
    {
      "clip_ratio/high_max": 0.0016431936201115604,
      "clip_ratio/high_mean": 0.0007291721158253495,
      "clip_ratio/low_mean": 0.000700981112458976,
      "clip_ratio/low_min": 2.0619502265617484e-05,
      "clip_ratio/region_mean": 0.0014301532282843255,
      "epoch": 0.06710649890041942,
      "grad_norm": 0.1383633017539978,
      "learning_rate": 2e-07,
      "loss": 0.0333,
      "step": 719
    },
    {
      "clip_ratio/high_max": 0.0016926482785493135,
      "clip_ratio/high_mean": 0.0006537069566547871,
      "clip_ratio/low_mean": 0.0005763051558460575,
      "clip_ratio/low_min": 3.150811744490056e-05,
      "clip_ratio/region_mean": 0.0012300121379666962,
      "epoch": 0.06719983200042,
      "grad_norm": 0.1416458934545517,
      "learning_rate": 2e-07,
      "loss": 0.0253,
      "step": 720
    },
    {
      "clip_ratio/high_max": 0.0016349463185179047,
      "clip_ratio/high_mean": 0.0006912409116921481,
      "clip_ratio/low_mean": 0.0006255785419853055,
      "clip_ratio/low_min": 2.5650052975834114e-05,
      "clip_ratio/region_mean": 0.001316819430940086,
      "epoch": 0.06729316510042058,
      "grad_norm": 0.1343315839767456,
      "learning_rate": 2e-07,
      "loss": 0.041,
      "step": 721
    },
    {
      "clip_ratio/high_max": 0.001746447385812644,
      "clip_ratio/high_mean": 0.0007376395542451064,
      "clip_ratio/low_mean": 0.0006119174759078305,
      "clip_ratio/low_min": 2.7068214876635466e-05,
      "clip_ratio/region_mean": 0.0013495570783561561,
      "epoch": 0.06738649820042117,
      "grad_norm": 2.9352288246154785,
      "learning_rate": 2e-07,
      "loss": 0.0137,
      "step": 722
    },
    {
      "clip_ratio/high_max": 0.0019403832702664658,
      "clip_ratio/high_mean": 0.0007071226418702281,
      "clip_ratio/low_mean": 0.0006266819455049699,
      "clip_ratio/low_min": 4.775853449245915e-05,
      "clip_ratio/region_mean": 0.0013338045646378305,
      "epoch": 0.06747983130042175,
      "grad_norm": 0.14023274183273315,
      "learning_rate": 2e-07,
      "loss": 0.0682,
      "step": 723
    },
    {
      "clip_ratio/high_max": 0.0016476722776133101,
      "clip_ratio/high_mean": 0.0005884115435037529,
      "clip_ratio/low_mean": 0.0006121876922406955,
      "clip_ratio/low_min": 3.521393546179752e-05,
      "clip_ratio/region_mean": 0.0012005992502963636,
      "epoch": 0.06757316440042234,
      "grad_norm": 0.14161323010921478,
      "learning_rate": 2e-07,
      "loss": 0.0554,
      "step": 724
    },
    {
      "clip_ratio/high_max": 0.0018050209037028253,
      "clip_ratio/high_mean": 0.0007605813470945577,
      "clip_ratio/low_mean": 0.0006543144563693204,
      "clip_ratio/low_min": 6.010193828842603e-05,
      "clip_ratio/region_mean": 0.0014148957889119629,
      "epoch": 0.06766649750042292,
      "grad_norm": 0.12920735776424408,
      "learning_rate": 2e-07,
      "loss": 0.0284,
      "step": 725
    },
    {
      "clip_ratio/high_max": 0.0019291339049232192,
      "clip_ratio/high_mean": 0.0007724874012637883,
      "clip_ratio/low_mean": 0.0007200568106782157,
      "clip_ratio/low_min": 2.381763533776393e-05,
      "clip_ratio/region_mean": 0.0014925442155799828,
      "epoch": 0.0677598306004235,
      "grad_norm": 0.14308056235313416,
      "learning_rate": 2e-07,
      "loss": 0.0175,
      "step": 726
    },
    {
      "clip_ratio/high_max": 0.001391034875268815,
      "clip_ratio/high_mean": 0.0006132711023383308,
      "clip_ratio/low_mean": 0.0005933129032200668,
      "clip_ratio/low_min": 3.510344413371058e-05,
      "clip_ratio/region_mean": 0.0012065840237482917,
      "epoch": 0.06785316370042409,
      "grad_norm": 0.13062018156051636,
      "learning_rate": 2e-07,
      "loss": 0.0274,
      "step": 727
    },
    {
      "clip_ratio/high_max": 0.0018009515624726191,
      "clip_ratio/high_mean": 0.0006586129838979105,
      "clip_ratio/low_mean": 0.0005433078795249457,
      "clip_ratio/low_min": 1.1495309991005342e-05,
      "clip_ratio/region_mean": 0.0012019208952551708,
      "epoch": 0.06794649680042467,
      "grad_norm": 0.1303359419107437,
      "learning_rate": 2e-07,
      "loss": 0.0192,
      "step": 728
    },
    {
      "clip_ratio/high_max": 0.001653441442613257,
      "clip_ratio/high_mean": 0.0006880047203594586,
      "clip_ratio/low_mean": 0.0005780893825431122,
      "clip_ratio/low_min": 1.7994701465795515e-05,
      "clip_ratio/region_mean": 0.0012660941101785284,
      "epoch": 0.06803982990042524,
      "grad_norm": 0.1346747875213623,
      "learning_rate": 2e-07,
      "loss": 0.0268,
      "step": 729
    },
    {
      "clip_ratio/high_max": 0.0015159739559749141,
      "clip_ratio/high_mean": 0.000616999542216945,
      "clip_ratio/low_mean": 0.0006180608252179809,
      "clip_ratio/low_min": 2.564760325185489e-05,
      "clip_ratio/region_mean": 0.0012350603719823994,
      "epoch": 0.06813316300042584,
      "grad_norm": 0.13803623616695404,
      "learning_rate": 2e-07,
      "loss": 0.0537,
      "step": 730
    },
    {
      "clip_ratio/high_max": 0.0019053148243983742,
      "clip_ratio/high_mean": 0.0007460387405444635,
      "clip_ratio/low_mean": 0.0006647058489761548,
      "clip_ratio/low_min": 2.9260299925226718e-05,
      "clip_ratio/region_mean": 0.0014107445676927455,
      "epoch": 0.06822649610042641,
      "grad_norm": 0.1356225609779358,
      "learning_rate": 2e-07,
      "loss": 0.0147,
      "step": 731
    },
    {
      "clip_ratio/high_max": 0.0021733314206358045,
      "clip_ratio/high_mean": 0.0008002834438229911,
      "clip_ratio/low_mean": 0.0005339936342352303,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013342770726012532,
      "epoch": 0.06831982920042699,
      "grad_norm": 0.1248110979795456,
      "learning_rate": 2e-07,
      "loss": 0.0104,
      "step": 732
    },
    {
      "clip_ratio/high_max": 0.002110526907927124,
      "clip_ratio/high_mean": 0.000795112533523934,
      "clip_ratio/low_mean": 0.0006017726063873852,
      "clip_ratio/low_min": 5.0137175549025415e-05,
      "clip_ratio/region_mean": 0.0013968851199024357,
      "epoch": 0.06841316230042759,
      "grad_norm": 0.1425507813692093,
      "learning_rate": 2e-07,
      "loss": 0.0267,
      "step": 733
    },
    {
      "clip_ratio/high_max": 0.0015512536410824396,
      "clip_ratio/high_mean": 0.0007362874002865283,
      "clip_ratio/low_mean": 0.0005592849620370544,
      "clip_ratio/low_min": 2.2278916731011122e-05,
      "clip_ratio/region_mean": 0.0012955723323102575,
      "epoch": 0.06850649540042816,
      "grad_norm": 0.1322236955165863,
      "learning_rate": 2e-07,
      "loss": -0.0164,
      "step": 734
    },
    {
      "clip_ratio/high_max": 0.001973512833501445,
      "clip_ratio/high_mean": 0.0008434585961367702,
      "clip_ratio/low_mean": 0.0005515567390830256,
      "clip_ratio/low_min": 1.741917549225036e-05,
      "clip_ratio/region_mean": 0.0013950153079349548,
      "epoch": 0.06859982850042876,
      "grad_norm": 0.13598982989788055,
      "learning_rate": 2e-07,
      "loss": -0.0372,
      "step": 735
    },
    {
      "clip_ratio/high_max": 0.0013755441686953418,
      "clip_ratio/high_mean": 0.0006037279854353983,
      "clip_ratio/low_mean": 0.000685150738718221,
      "clip_ratio/low_min": 8.081283158389851e-05,
      "clip_ratio/region_mean": 0.0012888787205156405,
      "epoch": 0.06869316160042933,
      "grad_norm": 0.1304323375225067,
      "learning_rate": 2e-07,
      "loss": 0.0555,
      "step": 736
    },
    {
      "clip_ratio/high_max": 0.0016776171778474236,
      "clip_ratio/high_mean": 0.0006565636558661936,
      "clip_ratio/low_mean": 0.0006106670543886139,
      "clip_ratio/low_min": 6.424415823857998e-05,
      "clip_ratio/region_mean": 0.0012672307129832916,
      "epoch": 0.06878649470042991,
      "grad_norm": 0.14045096933841705,
      "learning_rate": 2e-07,
      "loss": 0.0346,
      "step": 737
    },
    {
      "clip_ratio/high_max": 0.0017824553833634127,
      "clip_ratio/high_mean": 0.0007497723127016798,
      "clip_ratio/low_mean": 0.0006868544642202323,
      "clip_ratio/low_min": 9.35509324335726e-05,
      "clip_ratio/region_mean": 0.0014366267641889863,
      "epoch": 0.0688798278004305,
      "grad_norm": 0.1476656198501587,
      "learning_rate": 2e-07,
      "loss": 0.0276,
      "step": 738
    },
    {
      "clip_ratio/high_max": 0.002014551526372088,
      "clip_ratio/high_mean": 0.0007785520538163837,
      "clip_ratio/low_mean": 0.0005678825891664019,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001346434644801775,
      "epoch": 0.06897316090043108,
      "grad_norm": 0.14279600977897644,
      "learning_rate": 2e-07,
      "loss": 0.0142,
      "step": 739
    },
    {
      "clip_ratio/high_max": 0.0016068922923295759,
      "clip_ratio/high_mean": 0.0006672596909993445,
      "clip_ratio/low_mean": 0.0005846841195307206,
      "clip_ratio/low_min": 3.3891572456923313e-05,
      "clip_ratio/region_mean": 0.001251943816896528,
      "epoch": 0.06906649400043166,
      "grad_norm": 0.1329497992992401,
      "learning_rate": 2e-07,
      "loss": -0.0003,
      "step": 740
    },
    {
      "clip_ratio/high_max": 0.0015477959932468366,
      "clip_ratio/high_mean": 0.0006884727881697472,
      "clip_ratio/low_mean": 0.0006761211188859306,
      "clip_ratio/low_min": 9.686158227850683e-05,
      "clip_ratio/region_mean": 0.0013645939288835507,
      "epoch": 0.06915982710043225,
      "grad_norm": 0.15340709686279297,
      "learning_rate": 2e-07,
      "loss": 0.0343,
      "step": 741
    },
    {
      "clip_ratio/high_max": 0.0017472034596721642,
      "clip_ratio/high_mean": 0.0005598792449745815,
      "clip_ratio/low_mean": 0.0006305084971245378,
      "clip_ratio/low_min": 2.0184221284580417e-05,
      "clip_ratio/region_mean": 0.0011903877566510346,
      "epoch": 0.06925316020043283,
      "grad_norm": 0.13781733810901642,
      "learning_rate": 2e-07,
      "loss": 0.1057,
      "step": 742
    },
    {
      "clip_ratio/high_max": 0.0018353771847614553,
      "clip_ratio/high_mean": 0.0007695300155319273,
      "clip_ratio/low_mean": 0.0006667081979685463,
      "clip_ratio/low_min": 1.2948000403412152e-05,
      "clip_ratio/region_mean": 0.0014362382571562193,
      "epoch": 0.06934649330043341,
      "grad_norm": 0.14211416244506836,
      "learning_rate": 2e-07,
      "loss": 0.0463,
      "step": 743
    },
    {
      "clip_ratio/high_max": 0.001881918633444002,
      "clip_ratio/high_mean": 0.0007042689558147686,
      "clip_ratio/low_mean": 0.0006600547994821682,
      "clip_ratio/low_min": 7.30643650967977e-05,
      "clip_ratio/region_mean": 0.0013643237507494632,
      "epoch": 0.069439826400434,
      "grad_norm": 0.17888714373111725,
      "learning_rate": 2e-07,
      "loss": 0.042,
      "step": 744
    },
    {
      "clip_ratio/high_max": 0.0019346333065186627,
      "clip_ratio/high_mean": 0.0007357829872489674,
      "clip_ratio/low_mean": 0.0006854591501905816,
      "clip_ratio/low_min": 4.964719664712902e-05,
      "clip_ratio/region_mean": 0.001421242137439549,
      "epoch": 0.06953315950043458,
      "grad_norm": 0.1444707065820694,
      "learning_rate": 2e-07,
      "loss": 0.0527,
      "step": 745
    },
    {
      "clip_ratio/high_max": 0.0020131122364546172,
      "clip_ratio/high_mean": 0.000841406850668136,
      "clip_ratio/low_mean": 0.0006184665116961696,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014598733541788533,
      "epoch": 0.06962649260043517,
      "grad_norm": 0.12694089114665985,
      "learning_rate": 2e-07,
      "loss": 0.0101,
      "step": 746
    },
    {
      "clip_ratio/high_max": 0.002002824559895089,
      "clip_ratio/high_mean": 0.0007816623128746869,
      "clip_ratio/low_mean": 0.0005684689558620448,
      "clip_ratio/low_min": 2.1011274839111138e-05,
      "clip_ratio/region_mean": 0.0013501312641892582,
      "epoch": 0.06971982570043575,
      "grad_norm": 0.13734646141529083,
      "learning_rate": 2e-07,
      "loss": 0.0347,
      "step": 747
    },
    {
      "clip_ratio/high_max": 0.0019175229899701662,
      "clip_ratio/high_mean": 0.0008016608317120699,
      "clip_ratio/low_mean": 0.0005673322029906558,
      "clip_ratio/low_min": 5.7647043831821065e-05,
      "clip_ratio/region_mean": 0.001368993031064747,
      "epoch": 0.06981315880043633,
      "grad_norm": 0.1341647356748581,
      "learning_rate": 2e-07,
      "loss": -0.0121,
      "step": 748
    },
    {
      "clip_ratio/high_max": 0.0019190673956472892,
      "clip_ratio/high_mean": 0.0006641351255893824,
      "clip_ratio/low_mean": 0.0006390485723386519,
      "clip_ratio/low_min": 0.0001085847761714831,
      "clip_ratio/region_mean": 0.0013031837152084336,
      "epoch": 0.06990649190043692,
      "grad_norm": 0.16204993426799774,
      "learning_rate": 2e-07,
      "loss": 0.0677,
      "step": 749
    },
    {
      "clip_ratio/high_max": 0.0018352304796280805,
      "clip_ratio/high_mean": 0.0007655756344320253,
      "clip_ratio/low_mean": 0.0005637933927573613,
      "clip_ratio/low_min": 1.9287762370368e-05,
      "clip_ratio/region_mean": 0.0013293690353748389,
      "epoch": 0.0699998250004375,
      "grad_norm": 0.18594947457313538,
      "learning_rate": 2e-07,
      "loss": 0.007,
      "step": 750
    },
    {
      "clip_ratio/high_max": 0.0021123119950061664,
      "clip_ratio/high_mean": 0.0007741561348666437,
      "clip_ratio/low_mean": 0.0007044008216325892,
      "clip_ratio/low_min": 1.152073764387751e-05,
      "clip_ratio/region_mean": 0.0014785569364903495,
      "epoch": 0.07009315810043808,
      "grad_norm": 0.13006354868412018,
      "learning_rate": 2e-07,
      "loss": 0.0321,
      "step": 751
    },
    {
      "clip_ratio/high_max": 0.0016299027010973077,
      "clip_ratio/high_mean": 0.0006894369453220861,
      "clip_ratio/low_mean": 0.0007583912774862256,
      "clip_ratio/low_min": 7.340219508478185e-05,
      "clip_ratio/region_mean": 0.0014478282209893223,
      "epoch": 0.07018649120043867,
      "grad_norm": 0.13340875506401062,
      "learning_rate": 2e-07,
      "loss": 0.0718,
      "step": 752
    },
    {
      "clip_ratio/high_max": 0.001568788105942076,
      "clip_ratio/high_mean": 0.0006704993847961305,
      "clip_ratio/low_mean": 0.0006226609420991736,
      "clip_ratio/low_min": 2.049232989520533e-05,
      "clip_ratio/region_mean": 0.0012931603196193464,
      "epoch": 0.07027982430043925,
      "grad_norm": 0.13387636840343475,
      "learning_rate": 2e-07,
      "loss": 0.0221,
      "step": 753
    },
    {
      "clip_ratio/high_max": 0.0017044080814230256,
      "clip_ratio/high_mean": 0.0007106898701749742,
      "clip_ratio/low_mean": 0.0006341700745906564,
      "clip_ratio/low_min": 4.087597244506469e-05,
      "clip_ratio/region_mean": 0.0013448599747789558,
      "epoch": 0.07037315740043983,
      "grad_norm": 0.13436150550842285,
      "learning_rate": 2e-07,
      "loss": 0.032,
      "step": 754
    },
    {
      "clip_ratio/high_max": 0.0017210624610015657,
      "clip_ratio/high_mean": 0.0006696337695757393,
      "clip_ratio/low_mean": 0.0007029233656794531,
      "clip_ratio/low_min": 6.71645193506265e-05,
      "clip_ratio/region_mean": 0.001372557133436203,
      "epoch": 0.07046649050044042,
      "grad_norm": 0.13905030488967896,
      "learning_rate": 2e-07,
      "loss": 0.0192,
      "step": 755
    },
    {
      "clip_ratio/high_max": 0.0018812806592904963,
      "clip_ratio/high_mean": 0.0007288844662980409,
      "clip_ratio/low_mean": 0.0006820002581662266,
      "clip_ratio/low_min": 3.229341291444143e-05,
      "clip_ratio/region_mean": 0.0014108846917224582,
      "epoch": 0.070559823600441,
      "grad_norm": 0.1712380200624466,
      "learning_rate": 2e-07,
      "loss": 0.0515,
      "step": 756
    },
    {
      "clip_ratio/high_max": 0.0019677303098433185,
      "clip_ratio/high_mean": 0.0008468619143968681,
      "clip_ratio/low_mean": 0.0007824374160918524,
      "clip_ratio/low_min": 1.0798203220474534e-05,
      "clip_ratio/region_mean": 0.0016292993386741728,
      "epoch": 0.07065315670044159,
      "grad_norm": 0.14097215235233307,
      "learning_rate": 2e-07,
      "loss": 0.0403,
      "step": 757
    },
    {
      "clip_ratio/high_max": 0.001998222178372089,
      "clip_ratio/high_mean": 0.0007868848406360485,
      "clip_ratio/low_mean": 0.0005887957786399056,
      "clip_ratio/low_min": 3.083038791373838e-05,
      "clip_ratio/region_mean": 0.0013756806292803958,
      "epoch": 0.07074648980044217,
      "grad_norm": 0.13767503201961517,
      "learning_rate": 2e-07,
      "loss": 0.0105,
      "step": 758
    },
    {
      "clip_ratio/high_max": 0.0017852562014013529,
      "clip_ratio/high_mean": 0.0006847150671092095,
      "clip_ratio/low_mean": 0.0007243162854138063,
      "clip_ratio/low_min": 1.058245834428817e-05,
      "clip_ratio/region_mean": 0.0014090313998167403,
      "epoch": 0.07083982290044274,
      "grad_norm": 0.13729645311832428,
      "learning_rate": 2e-07,
      "loss": 0.0393,
      "step": 759
    },
    {
      "clip_ratio/high_max": 0.0017310409639321733,
      "clip_ratio/high_mean": 0.0007158482267186628,
      "clip_ratio/low_mean": 0.0007941653584566666,
      "clip_ratio/low_min": 0.00011437252760515548,
      "clip_ratio/region_mean": 0.0015100135642569512,
      "epoch": 0.07093315600044334,
      "grad_norm": 0.17227871716022491,
      "learning_rate": 2e-07,
      "loss": 0.0624,
      "step": 760
    },
    {
      "clip_ratio/high_max": 0.0020095400941499975,
      "clip_ratio/high_mean": 0.0008180303320841631,
      "clip_ratio/low_mean": 0.0006249801717785886,
      "clip_ratio/low_min": 9.709491678222548e-06,
      "clip_ratio/region_mean": 0.0014430104820348788,
      "epoch": 0.07102648910044392,
      "grad_norm": 0.13231320679187775,
      "learning_rate": 2e-07,
      "loss": 0.0189,
      "step": 761
    },
    {
      "clip_ratio/high_max": 0.002000831071200082,
      "clip_ratio/high_mean": 0.0007673213367525022,
      "clip_ratio/low_mean": 0.0006424330531444866,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014097543462412432,
      "epoch": 0.0711198222004445,
      "grad_norm": 0.12706294655799866,
      "learning_rate": 2e-07,
      "loss": 0.0207,
      "step": 762
    },
    {
      "clip_ratio/high_max": 0.002017152917687781,
      "clip_ratio/high_mean": 0.0007408308883896098,
      "clip_ratio/low_mean": 0.0006969236601435114,
      "clip_ratio/low_min": 3.259520508436253e-05,
      "clip_ratio/region_mean": 0.0014377545085153542,
      "epoch": 0.07121315530044509,
      "grad_norm": 0.1454247534275055,
      "learning_rate": 2e-07,
      "loss": 0.0456,
      "step": 763
    },
    {
      "clip_ratio/high_max": 0.00197572779507027,
      "clip_ratio/high_mean": 0.0007024952356005087,
      "clip_ratio/low_mean": 0.0006915584126545582,
      "clip_ratio/low_min": 8.96700112207327e-06,
      "clip_ratio/region_mean": 0.0013940536446170881,
      "epoch": 0.07130648840044566,
      "grad_norm": 0.26601114869117737,
      "learning_rate": 2e-07,
      "loss": 0.023,
      "step": 764
    },
    {
      "clip_ratio/high_max": 0.0017416523187421262,
      "clip_ratio/high_mean": 0.0007268990266311448,
      "clip_ratio/low_mean": 0.0006505915353045566,
      "clip_ratio/low_min": 6.869563367217779e-05,
      "clip_ratio/region_mean": 0.001377490541926818,
      "epoch": 0.07139982150044624,
      "grad_norm": 0.15248876810073853,
      "learning_rate": 2e-07,
      "loss": 0.0485,
      "step": 765
    },
    {
      "clip_ratio/high_max": 0.0017295719881076366,
      "clip_ratio/high_mean": 0.0007227960995805915,
      "clip_ratio/low_mean": 0.0005879171567357844,
      "clip_ratio/low_min": 4.8788484491524287e-05,
      "clip_ratio/region_mean": 0.001310713265411323,
      "epoch": 0.07149315460044683,
      "grad_norm": 0.13423849642276764,
      "learning_rate": 2e-07,
      "loss": 0.0284,
      "step": 766
    },
    {
      "clip_ratio/high_max": 0.001580485695740208,
      "clip_ratio/high_mean": 0.0007052026430756086,
      "clip_ratio/low_mean": 0.0006351879883368383,
      "clip_ratio/low_min": 1.1011275091732386e-05,
      "clip_ratio/region_mean": 0.0013403906195890158,
      "epoch": 0.07158648770044741,
      "grad_norm": 0.13993693888187408,
      "learning_rate": 2e-07,
      "loss": 0.0155,
      "step": 767
    },
    {
      "clip_ratio/high_max": 0.0016208321358135436,
      "clip_ratio/high_mean": 0.0006385864789990592,
      "clip_ratio/low_mean": 0.0005598166471827426,
      "clip_ratio/low_min": 3.3498910852358676e-05,
      "clip_ratio/region_mean": 0.0011984031079919077,
      "epoch": 0.071679820800448,
      "grad_norm": 0.12588836252689362,
      "learning_rate": 2e-07,
      "loss": -0.0034,
      "step": 768
    },
    {
      "clip_ratio/high_max": 0.0016640617031953298,
      "clip_ratio/high_mean": 0.0006651537350990111,
      "clip_ratio/low_mean": 0.0005679716614395147,
      "clip_ratio/low_min": 2.9024866307736374e-05,
      "clip_ratio/region_mean": 0.0012331254038144834,
      "completions/clipped_ratio": 0.0189296177455357,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4094.0,
      "completions/mean_length": 669.2849731445312,
      "completions/mean_terminated_length": 603.1669311523438,
      "completions/min_length": 83.0,
      "completions/min_terminated_length": 83.0,
      "epoch": 0.07177315390044858,
      "grad_norm": 0.1200176328420639,
      "learning_rate": 2e-07,
      "loss": 0.0144,
      "num_tokens": 592274102.0,
      "reward": 0.587533175945282,
      "reward_std": 0.18658646941184998,
      "rewards/simpleverify_reward/mean": 0.5875331163406372,
      "rewards/simpleverify_reward/std": 0.49228036403656006,
      "step": 769
    },
    {
      "clip_ratio/high_max": 0.001763664997270098,
      "clip_ratio/high_mean": 0.0007165318029365153,
      "clip_ratio/low_mean": 0.0005440120407911309,
      "clip_ratio/low_min": 2.7551244784262963e-05,
      "clip_ratio/region_mean": 0.0012605438860191498,
      "epoch": 0.07186648700044916,
      "grad_norm": 0.11535928398370743,
      "learning_rate": 2e-07,
      "loss": 0.005,
      "step": 770
    },
    {
      "clip_ratio/high_max": 0.0018081527596223168,
      "clip_ratio/high_mean": 0.000701039403793402,
      "clip_ratio/low_mean": 0.0006027344516041921,
      "clip_ratio/low_min": 4.069938586326316e-05,
      "clip_ratio/region_mean": 0.0013037738572165836,
      "epoch": 0.07195982010044975,
      "grad_norm": 0.12335245311260223,
      "learning_rate": 2e-07,
      "loss": 0.0147,
      "step": 771
    },
    {
      "clip_ratio/high_max": 0.0017272335280722473,
      "clip_ratio/high_mean": 0.0007435985626216279,
      "clip_ratio/low_mean": 0.0006387972207448911,
      "clip_ratio/low_min": 5.4254132010100875e-05,
      "clip_ratio/region_mean": 0.001382395756081678,
      "epoch": 0.07205315320045033,
      "grad_norm": 0.1265745460987091,
      "learning_rate": 2e-07,
      "loss": 0.0006,
      "step": 772
    },
    {
      "clip_ratio/high_max": 0.0016171671450138092,
      "clip_ratio/high_mean": 0.0006421653197321575,
      "clip_ratio/low_mean": 0.0006703893322992371,
      "clip_ratio/low_min": 5.29526369064115e-06,
      "clip_ratio/region_mean": 0.0013125546574883629,
      "epoch": 0.07214648630045091,
      "grad_norm": 0.13422124087810516,
      "learning_rate": 2e-07,
      "loss": 0.065,
      "step": 773
    },
    {
      "clip_ratio/high_max": 0.0017161291470983997,
      "clip_ratio/high_mean": 0.0006915295398357557,
      "clip_ratio/low_mean": 0.0005328520865077735,
      "clip_ratio/low_min": 3.22438149851223e-05,
      "clip_ratio/region_mean": 0.0012243816418049391,
      "epoch": 0.0722398194004515,
      "grad_norm": 0.11311989277601242,
      "learning_rate": 2e-07,
      "loss": 0.0057,
      "step": 774
    },
    {
      "clip_ratio/high_max": 0.0017800446366891265,
      "clip_ratio/high_mean": 0.0007017651259957347,
      "clip_ratio/low_mean": 0.0005871846533409553,
      "clip_ratio/low_min": 1.553567017253954e-05,
      "clip_ratio/region_mean": 0.0012889497775177006,
      "epoch": 0.07233315250045208,
      "grad_norm": 0.12425410747528076,
      "learning_rate": 2e-07,
      "loss": 0.003,
      "step": 775
    },
    {
      "clip_ratio/high_max": 0.0019921678758691996,
      "clip_ratio/high_mean": 0.000781892782470095,
      "clip_ratio/low_mean": 0.0005476402147905901,
      "clip_ratio/low_min": 2.1736652342951857e-05,
      "clip_ratio/region_mean": 0.001329533006355632,
      "epoch": 0.07242648560045266,
      "grad_norm": 0.1242922991514206,
      "learning_rate": 2e-07,
      "loss": 0.0344,
      "step": 776
    },
    {
      "clip_ratio/high_max": 0.0019104493585473392,
      "clip_ratio/high_mean": 0.0007157452164392453,
      "clip_ratio/low_mean": 0.000570622438317514,
      "clip_ratio/low_min": 3.897562783095054e-05,
      "clip_ratio/region_mean": 0.0012863676456618123,
      "epoch": 0.07251981870045325,
      "grad_norm": 0.1277121901512146,
      "learning_rate": 2e-07,
      "loss": 0.0198,
      "step": 777
    },
    {
      "clip_ratio/high_max": 0.001965167684829794,
      "clip_ratio/high_mean": 0.0007945667421154212,
      "clip_ratio/low_mean": 0.000632874977782194,
      "clip_ratio/low_min": 6.881707122374792e-05,
      "clip_ratio/region_mean": 0.0014274417262640782,
      "epoch": 0.07261315180045383,
      "grad_norm": 0.15136922895908356,
      "learning_rate": 2e-07,
      "loss": 0.0025,
      "step": 778
    },
    {
      "clip_ratio/high_max": 0.001287887331272941,
      "clip_ratio/high_mean": 0.0005273313017823966,
      "clip_ratio/low_mean": 0.0006005700561217964,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0011279013415332884,
      "epoch": 0.07270648490045442,
      "grad_norm": 0.13333232700824738,
      "learning_rate": 2e-07,
      "loss": 0.0026,
      "step": 779
    },
    {
      "clip_ratio/high_max": 0.0015332795992435422,
      "clip_ratio/high_mean": 0.0007034673071757425,
      "clip_ratio/low_mean": 0.0005831103248965519,
      "clip_ratio/low_min": 9.016199510369916e-05,
      "clip_ratio/region_mean": 0.0012865776297985576,
      "epoch": 0.072799818000455,
      "grad_norm": 0.1275341957807541,
      "learning_rate": 2e-07,
      "loss": -0.0002,
      "step": 780
    },
    {
      "clip_ratio/high_max": 0.0018385609946562909,
      "clip_ratio/high_mean": 0.0007549962556367973,
      "clip_ratio/low_mean": 0.00048272770436597057,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012377239618217573,
      "epoch": 0.07289315110045558,
      "grad_norm": 0.14282125234603882,
      "learning_rate": 2e-07,
      "loss": 0.0097,
      "step": 781
    },
    {
      "clip_ratio/high_max": 0.0016916198947001249,
      "clip_ratio/high_mean": 0.0006690671652904712,
      "clip_ratio/low_mean": 0.0004747746179418755,
      "clip_ratio/low_min": 2.428127481834963e-05,
      "clip_ratio/region_mean": 0.001143841800512746,
      "epoch": 0.07298648420045617,
      "grad_norm": 0.14204253256320953,
      "learning_rate": 2e-07,
      "loss": 0.0424,
      "step": 782
    },
    {
      "clip_ratio/high_max": 0.001592929838807322,
      "clip_ratio/high_mean": 0.000590239208577259,
      "clip_ratio/low_mean": 0.0006100029895605985,
      "clip_ratio/low_min": 5.1313657422724646e-05,
      "clip_ratio/region_mean": 0.0012002422008663416,
      "epoch": 0.07307981730045675,
      "grad_norm": 0.12809215486049652,
      "learning_rate": 2e-07,
      "loss": 0.0622,
      "step": 783
    },
    {
      "clip_ratio/high_max": 0.0015120770040084608,
      "clip_ratio/high_mean": 0.0006210517603904009,
      "clip_ratio/low_mean": 0.0005937460355198709,
      "clip_ratio/low_min": 1.650528247409966e-05,
      "clip_ratio/region_mean": 0.0012147977722634096,
      "epoch": 0.07317315040045733,
      "grad_norm": 0.14840084314346313,
      "learning_rate": 2e-07,
      "loss": 0.0408,
      "step": 784
    },
    {
      "clip_ratio/high_max": 0.001665672487433767,
      "clip_ratio/high_mean": 0.0006532960924232611,
      "clip_ratio/low_mean": 0.0005215191958996002,
      "clip_ratio/low_min": 1.5711413652752526e-05,
      "clip_ratio/region_mean": 0.0011748152755899355,
      "epoch": 0.07326648350045792,
      "grad_norm": 0.12252987176179886,
      "learning_rate": 2e-07,
      "loss": 0.0083,
      "step": 785
    },
    {
      "clip_ratio/high_max": 0.002016483079387399,
      "clip_ratio/high_mean": 0.0007688053024139663,
      "clip_ratio/low_mean": 0.0006342743154164054,
      "clip_ratio/low_min": 2.9696710043936037e-05,
      "clip_ratio/region_mean": 0.0014030796301085502,
      "epoch": 0.0733598166004585,
      "grad_norm": 0.12238584458827972,
      "learning_rate": 2e-07,
      "loss": 0.0244,
      "step": 786
    },
    {
      "clip_ratio/high_max": 0.0013633124290208798,
      "clip_ratio/high_mean": 0.000596500642132014,
      "clip_ratio/low_mean": 0.0005269209823381971,
      "clip_ratio/low_min": 2.2610221094510052e-05,
      "clip_ratio/region_mean": 0.001123421603551833,
      "epoch": 0.07345314970045909,
      "grad_norm": 0.13153524696826935,
      "learning_rate": 2e-07,
      "loss": 0.0264,
      "step": 787
    },
    {
      "clip_ratio/high_max": 0.001768229736626381,
      "clip_ratio/high_mean": 0.000666464155074209,
      "clip_ratio/low_mean": 0.0006321265200313064,
      "clip_ratio/low_min": 5.978787885396741e-05,
      "clip_ratio/region_mean": 0.0012985906651010737,
      "epoch": 0.07354648280045967,
      "grad_norm": 0.13322320580482483,
      "learning_rate": 2e-07,
      "loss": 0.0572,
      "step": 788
    },
    {
      "clip_ratio/high_max": 0.0018353796331211925,
      "clip_ratio/high_mean": 0.0006070550098229432,
      "clip_ratio/low_mean": 0.0005546537267946405,
      "clip_ratio/low_min": 1.0217427188763395e-05,
      "clip_ratio/region_mean": 0.0011617087184276897,
      "epoch": 0.07363981590046025,
      "grad_norm": 65.43255615234375,
      "learning_rate": 2e-07,
      "loss": 0.0636,
      "step": 789
    },
    {
      "clip_ratio/high_max": 0.001764729244314367,
      "clip_ratio/high_mean": 0.0006605897297049523,
      "clip_ratio/low_mean": 0.0005762765531471814,
      "clip_ratio/low_min": 1.3343134014576208e-05,
      "clip_ratio/region_mean": 0.0012368662683002185,
      "epoch": 0.07373314900046084,
      "grad_norm": 0.13482068479061127,
      "learning_rate": 2e-07,
      "loss": 0.0425,
      "step": 790
    },
    {
      "clip_ratio/high_max": 0.0014388743256859016,
      "clip_ratio/high_mean": 0.00052253001013014,
      "clip_ratio/low_mean": 0.0005727292355004465,
      "clip_ratio/low_min": 6.32050041531329e-05,
      "clip_ratio/region_mean": 0.0010952592419926077,
      "epoch": 0.07382648210046142,
      "grad_norm": 0.11618407815694809,
      "learning_rate": 2e-07,
      "loss": 0.0309,
      "step": 791
    },
    {
      "clip_ratio/high_max": 0.0016239406540989876,
      "clip_ratio/high_mean": 0.0007450235389114823,
      "clip_ratio/low_mean": 0.0005221978426561691,
      "clip_ratio/low_min": 1.3851324638380902e-05,
      "clip_ratio/region_mean": 0.0012672213488258421,
      "epoch": 0.073919815200462,
      "grad_norm": 0.13668769598007202,
      "learning_rate": 2e-07,
      "loss": -0.013,
      "step": 792
    },
    {
      "clip_ratio/high_max": 0.001792459050193429,
      "clip_ratio/high_mean": 0.0007293201470019994,
      "clip_ratio/low_mean": 0.0005229202092777996,
      "clip_ratio/low_min": 5.167751442058943e-05,
      "clip_ratio/region_mean": 0.0012522403922048397,
      "epoch": 0.07401314830046259,
      "grad_norm": 0.15190726518630981,
      "learning_rate": 2e-07,
      "loss": 0.0099,
      "step": 793
    },
    {
      "clip_ratio/high_max": 0.0016551038643228821,
      "clip_ratio/high_mean": 0.000632282426522579,
      "clip_ratio/low_mean": 0.0005150629094714532,
      "clip_ratio/low_min": 1.3241525266494136e-05,
      "clip_ratio/region_mean": 0.0011473453196231276,
      "epoch": 0.07410648140046316,
      "grad_norm": 0.13538256287574768,
      "learning_rate": 2e-07,
      "loss": 0.0317,
      "step": 794
    },
    {
      "clip_ratio/high_max": 0.0015021612744021695,
      "clip_ratio/high_mean": 0.0005892269764444791,
      "clip_ratio/low_mean": 0.0005791236362711061,
      "clip_ratio/low_min": 2.0741913431265857e-05,
      "clip_ratio/region_mean": 0.0011683506199915428,
      "epoch": 0.07419981450046374,
      "grad_norm": 0.13134124875068665,
      "learning_rate": 2e-07,
      "loss": 0.0637,
      "step": 795
    },
    {
      "clip_ratio/high_max": 0.0015224536873574834,
      "clip_ratio/high_mean": 0.0006306667846729397,
      "clip_ratio/low_mean": 0.0006323348025034647,
      "clip_ratio/low_min": 6.654258049820783e-05,
      "clip_ratio/region_mean": 0.001263001560801058,
      "epoch": 0.07429314760046433,
      "grad_norm": 0.12769021093845367,
      "learning_rate": 2e-07,
      "loss": 0.0623,
      "step": 796
    },
    {
      "clip_ratio/high_max": 0.0019472003514238168,
      "clip_ratio/high_mean": 0.0006880204455228522,
      "clip_ratio/low_mean": 0.0005959361151326448,
      "clip_ratio/low_min": 4.098026738574845e-05,
      "clip_ratio/region_mean": 0.0012839565824833699,
      "epoch": 0.07438648070046491,
      "grad_norm": 0.1261204332113266,
      "learning_rate": 2e-07,
      "loss": 0.0118,
      "step": 797
    },
    {
      "clip_ratio/high_max": 0.001734211400616914,
      "clip_ratio/high_mean": 0.0006724927679897519,
      "clip_ratio/low_mean": 0.0005937544665357564,
      "clip_ratio/low_min": 7.51308962207986e-05,
      "clip_ratio/region_mean": 0.0012662472327065188,
      "epoch": 0.0744798138004655,
      "grad_norm": 0.1381601244211197,
      "learning_rate": 2e-07,
      "loss": 0.0085,
      "step": 798
    },
    {
      "clip_ratio/high_max": 0.0017473062398494221,
      "clip_ratio/high_mean": 0.0007460927481588442,
      "clip_ratio/low_mean": 0.000571088321521529,
      "clip_ratio/low_min": 4.5364177822193597e-05,
      "clip_ratio/region_mean": 0.0013171810387575533,
      "epoch": 0.07457314690046608,
      "grad_norm": 0.12908893823623657,
      "learning_rate": 2e-07,
      "loss": 0.049,
      "step": 799
    },
    {
      "clip_ratio/high_max": 0.001583841149113141,
      "clip_ratio/high_mean": 0.0006087311021474306,
      "clip_ratio/low_mean": 0.0005442203791972133,
      "clip_ratio/low_min": 7.766869202896487e-06,
      "clip_ratio/region_mean": 0.0011529514704307076,
      "epoch": 0.07466648000046666,
      "grad_norm": 0.12730640172958374,
      "learning_rate": 2e-07,
      "loss": 0.0448,
      "step": 800
    },
    {
      "clip_ratio/high_max": 0.0015075810879352503,
      "clip_ratio/high_mean": 0.0005928674850110838,
      "clip_ratio/low_mean": 0.0004950751208525617,
      "clip_ratio/low_min": 1.340626386081567e-05,
      "clip_ratio/region_mean": 0.001087942593585467,
      "epoch": 0.07475981310046725,
      "grad_norm": 0.13703522086143494,
      "learning_rate": 2e-07,
      "loss": 0.034,
      "step": 801
    },
    {
      "clip_ratio/high_max": 0.0019027512244065292,
      "clip_ratio/high_mean": 0.0007680161215830594,
      "clip_ratio/low_mean": 0.0005871154407941503,
      "clip_ratio/low_min": 7.348618510150118e-06,
      "clip_ratio/region_mean": 0.0013551315969380084,
      "epoch": 0.07485314620046783,
      "grad_norm": 0.13827338814735413,
      "learning_rate": 2e-07,
      "loss": 0.016,
      "step": 802
    },
    {
      "clip_ratio/high_max": 0.0018460044448147528,
      "clip_ratio/high_mean": 0.0007641971424163785,
      "clip_ratio/low_mean": 0.0005808871537738014,
      "clip_ratio/low_min": 4.96315406053327e-05,
      "clip_ratio/region_mean": 0.0013450842780002858,
      "epoch": 0.07494647930046841,
      "grad_norm": 0.13513021171092987,
      "learning_rate": 2e-07,
      "loss": 0.0117,
      "step": 803
    },
    {
      "clip_ratio/high_max": 0.0016978867060970515,
      "clip_ratio/high_mean": 0.0007051718757793424,
      "clip_ratio/low_mean": 0.0005716891691918136,
      "clip_ratio/low_min": 2.6544778847892303e-05,
      "clip_ratio/region_mean": 0.001276861054066103,
      "epoch": 0.075039812400469,
      "grad_norm": 0.11753594130277634,
      "learning_rate": 2e-07,
      "loss": 0.029,
      "step": 804
    },
    {
      "clip_ratio/high_max": 0.0017336773889837787,
      "clip_ratio/high_mean": 0.0006946772664377932,
      "clip_ratio/low_mean": 0.0007058975515974453,
      "clip_ratio/low_min": 3.879847463394981e-05,
      "clip_ratio/region_mean": 0.0014005748089402914,
      "epoch": 0.07513314550046958,
      "grad_norm": 0.2023734301328659,
      "learning_rate": 2e-07,
      "loss": 0.0475,
      "step": 805
    },
    {
      "clip_ratio/high_max": 0.0016371474011975806,
      "clip_ratio/high_mean": 0.0006527393597934861,
      "clip_ratio/low_mean": 0.0005765201185568003,
      "clip_ratio/low_min": 1.821468913476565e-05,
      "clip_ratio/region_mean": 0.0012292595019971486,
      "epoch": 0.07522647860047016,
      "grad_norm": 0.11682592332363129,
      "learning_rate": 2e-07,
      "loss": 0.0137,
      "step": 806
    },
    {
      "clip_ratio/high_max": 0.0018218369878013618,
      "clip_ratio/high_mean": 0.0007625634534633718,
      "clip_ratio/low_mean": 0.0005656765097228345,
      "clip_ratio/low_min": 3.354207910888363e-05,
      "clip_ratio/region_mean": 0.001328239970462164,
      "epoch": 0.07531981170047075,
      "grad_norm": 0.17023275792598724,
      "learning_rate": 2e-07,
      "loss": 0.0284,
      "step": 807
    },
    {
      "clip_ratio/high_max": 0.0018063690622511785,
      "clip_ratio/high_mean": 0.0006768521107005654,
      "clip_ratio/low_mean": 0.0004902261634924798,
      "clip_ratio/low_min": 1.7428766568627907e-05,
      "clip_ratio/region_mean": 0.0011670782514556777,
      "epoch": 0.07541314480047133,
      "grad_norm": 0.1293930858373642,
      "learning_rate": 2e-07,
      "loss": 0.0438,
      "step": 808
    },
    {
      "clip_ratio/high_max": 0.001562705099786399,
      "clip_ratio/high_mean": 0.0006287382111622719,
      "clip_ratio/low_mean": 0.0005736205957873608,
      "clip_ratio/low_min": 3.597545855882345e-05,
      "clip_ratio/region_mean": 0.0012023587769363075,
      "epoch": 0.07550647790047192,
      "grad_norm": 0.12865273654460907,
      "learning_rate": 2e-07,
      "loss": 0.0381,
      "step": 809
    },
    {
      "clip_ratio/high_max": 0.0014954010766814463,
      "clip_ratio/high_mean": 0.0005929134431426064,
      "clip_ratio/low_mean": 0.0005462050958158216,
      "clip_ratio/low_min": 3.391011523490306e-05,
      "clip_ratio/region_mean": 0.0011391185471438803,
      "epoch": 0.0755998110004725,
      "grad_norm": 0.1434391736984253,
      "learning_rate": 2e-07,
      "loss": 0.0626,
      "step": 810
    },
    {
      "clip_ratio/high_max": 0.001866494865680579,
      "clip_ratio/high_mean": 0.0007073636807035655,
      "clip_ratio/low_mean": 0.0006035722271917621,
      "clip_ratio/low_min": 4.886163333139848e-05,
      "clip_ratio/region_mean": 0.0013109359315421898,
      "epoch": 0.07569314410047308,
      "grad_norm": 0.15212330222129822,
      "learning_rate": 2e-07,
      "loss": 0.0444,
      "step": 811
    },
    {
      "clip_ratio/high_max": 0.0017575124693394173,
      "clip_ratio/high_mean": 0.0007391291783278575,
      "clip_ratio/low_mean": 0.0005912526721658651,
      "clip_ratio/low_min": 2.2563160200661514e-05,
      "clip_ratio/region_mean": 0.0013303818413987756,
      "epoch": 0.07578647720047367,
      "grad_norm": 0.1445869654417038,
      "learning_rate": 2e-07,
      "loss": 0.0394,
      "step": 812
    },
    {
      "clip_ratio/high_max": 0.0016174005722859874,
      "clip_ratio/high_mean": 0.0006395413811333128,
      "clip_ratio/low_mean": 0.000532825183654495,
      "clip_ratio/low_min": 1.6974470781860873e-05,
      "clip_ratio/region_mean": 0.001172366552054882,
      "epoch": 0.07587981030047425,
      "grad_norm": 0.13306879997253418,
      "learning_rate": 2e-07,
      "loss": 0.0018,
      "step": 813
    },
    {
      "clip_ratio/high_max": 0.0018803581697284244,
      "clip_ratio/high_mean": 0.0006576155683433171,
      "clip_ratio/low_mean": 0.000547018185898196,
      "clip_ratio/low_min": 2.537104592192918e-05,
      "clip_ratio/region_mean": 0.001204633754241513,
      "epoch": 0.07597314340047483,
      "grad_norm": 0.1316138356924057,
      "learning_rate": 2e-07,
      "loss": 0.035,
      "step": 814
    },
    {
      "clip_ratio/high_max": 0.0017649402070674114,
      "clip_ratio/high_mean": 0.0007271963440871332,
      "clip_ratio/low_mean": 0.0006332378252409399,
      "clip_ratio/low_min": 3.3307031117146835e-05,
      "clip_ratio/region_mean": 0.0013604341620521154,
      "epoch": 0.07606647650047542,
      "grad_norm": 0.13097789883613586,
      "learning_rate": 2e-07,
      "loss": -0.0045,
      "step": 815
    },
    {
      "clip_ratio/high_max": 0.0019263663198216818,
      "clip_ratio/high_mean": 0.0007784564841131214,
      "clip_ratio/low_mean": 0.0006007261818012921,
      "clip_ratio/low_min": 1.2354220416455064e-05,
      "clip_ratio/region_mean": 0.001379182685923297,
      "epoch": 0.076159809600476,
      "grad_norm": 0.13646312057971954,
      "learning_rate": 2e-07,
      "loss": 0.0056,
      "step": 816
    },
    {
      "clip_ratio/high_max": 0.0018164188477385323,
      "clip_ratio/high_mean": 0.0006681560880679172,
      "clip_ratio/low_mean": 0.0006493937935374561,
      "clip_ratio/low_min": 4.98636691190768e-05,
      "clip_ratio/region_mean": 0.0013175498897908255,
      "epoch": 0.07625314270047658,
      "grad_norm": 0.13613185286521912,
      "learning_rate": 2e-07,
      "loss": 0.0688,
      "step": 817
    },
    {
      "clip_ratio/high_max": 0.0013788427932013292,
      "clip_ratio/high_mean": 0.000611609628322185,
      "clip_ratio/low_mean": 0.0006212674070411595,
      "clip_ratio/low_min": 3.884965644829208e-05,
      "clip_ratio/region_mean": 0.0012328770390013233,
      "epoch": 0.07634647580047717,
      "grad_norm": 0.12307032942771912,
      "learning_rate": 2e-07,
      "loss": 0.037,
      "step": 818
    },
    {
      "clip_ratio/high_max": 0.002161408028769074,
      "clip_ratio/high_mean": 0.0008264908301498508,
      "clip_ratio/low_mean": 0.0005874209418834653,
      "clip_ratio/low_min": 1.5090803117345786e-05,
      "clip_ratio/region_mean": 0.0014139117483864538,
      "epoch": 0.07643980890047775,
      "grad_norm": 0.13738411664962769,
      "learning_rate": 2e-07,
      "loss": 0.0343,
      "step": 819
    },
    {
      "clip_ratio/high_max": 0.001655316460528411,
      "clip_ratio/high_mean": 0.0005889028934689122,
      "clip_ratio/low_mean": 0.0006206248781381873,
      "clip_ratio/low_min": 4.959434409101959e-05,
      "clip_ratio/region_mean": 0.0012095277743355837,
      "epoch": 0.07653314200047834,
      "grad_norm": 0.1456535905599594,
      "learning_rate": 2e-07,
      "loss": 0.0566,
      "step": 820
    },
    {
      "clip_ratio/high_max": 0.0014790482928219717,
      "clip_ratio/high_mean": 0.0005915695764997508,
      "clip_ratio/low_mean": 0.0006586634935956681,
      "clip_ratio/low_min": 4.391547417981201e-05,
      "clip_ratio/region_mean": 0.0012502330719144084,
      "epoch": 0.07662647510047892,
      "grad_norm": 0.12696410715579987,
      "learning_rate": 2e-07,
      "loss": 0.0455,
      "step": 821
    },
    {
      "clip_ratio/high_max": 0.001555921964609297,
      "clip_ratio/high_mean": 0.0006570272526005283,
      "clip_ratio/low_mean": 0.0006139335309853777,
      "clip_ratio/low_min": 3.152605677314568e-05,
      "clip_ratio/region_mean": 0.0012709607617580332,
      "epoch": 0.0767198082004795,
      "grad_norm": 0.12894754111766815,
      "learning_rate": 2e-07,
      "loss": 0.0272,
      "step": 822
    },
    {
      "clip_ratio/high_max": 0.0014002352254465222,
      "clip_ratio/high_mean": 0.0006081001383790863,
      "clip_ratio/low_mean": 0.0005030052043366595,
      "clip_ratio/low_min": 5.296463177728583e-05,
      "clip_ratio/region_mean": 0.0011111053354397882,
      "epoch": 0.07681314130048009,
      "grad_norm": 0.12044192850589752,
      "learning_rate": 2e-07,
      "loss": 0.0091,
      "step": 823
    },
    {
      "clip_ratio/high_max": 0.0014157791265461128,
      "clip_ratio/high_mean": 0.0005488197130034678,
      "clip_ratio/low_mean": 0.0006328679864964215,
      "clip_ratio/low_min": 3.568117699614959e-05,
      "clip_ratio/region_mean": 0.001181687715870794,
      "epoch": 0.07690647440048066,
      "grad_norm": 0.12149026989936829,
      "learning_rate": 2e-07,
      "loss": 0.0641,
      "step": 824
    },
    {
      "clip_ratio/high_max": 0.0016838320625538472,
      "clip_ratio/high_mean": 0.0006304349844867829,
      "clip_ratio/low_mean": 0.0006053441138647031,
      "clip_ratio/low_min": 2.5909308078553295e-05,
      "clip_ratio/region_mean": 0.0012357791201793589,
      "epoch": 0.07699980750048124,
      "grad_norm": 0.13744395971298218,
      "learning_rate": 2e-07,
      "loss": 0.0477,
      "step": 825
    },
    {
      "clip_ratio/high_max": 0.0016691182463546284,
      "clip_ratio/high_mean": 0.0006874650243844371,
      "clip_ratio/low_mean": 0.0005815828972117743,
      "clip_ratio/low_min": 2.5036773877218366e-05,
      "clip_ratio/region_mean": 0.0012690479125012644,
      "epoch": 0.07709314060048184,
      "grad_norm": 0.20148490369319916,
      "learning_rate": 2e-07,
      "loss": 0.0438,
      "step": 826
    },
    {
      "clip_ratio/high_max": 0.0018083069153362885,
      "clip_ratio/high_mean": 0.0007352850598181249,
      "clip_ratio/low_mean": 0.00063953405515349,
      "clip_ratio/low_min": 4.0536031519877724e-05,
      "clip_ratio/region_mean": 0.0013748191340710036,
      "epoch": 0.07718647370048241,
      "grad_norm": 0.12896673381328583,
      "learning_rate": 2e-07,
      "loss": 0.0193,
      "step": 827
    },
    {
      "clip_ratio/high_max": 0.002085554788209265,
      "clip_ratio/high_mean": 0.0007741647568764165,
      "clip_ratio/low_mean": 0.0006427722582884599,
      "clip_ratio/low_min": 2.2887622435519006e-05,
      "clip_ratio/region_mean": 0.0014169370551826432,
      "epoch": 0.07727980680048299,
      "grad_norm": 0.12418148666620255,
      "learning_rate": 2e-07,
      "loss": 0.0451,
      "step": 828
    },
    {
      "clip_ratio/high_max": 0.001683254464296624,
      "clip_ratio/high_mean": 0.0006877275372971781,
      "clip_ratio/low_mean": 0.0006713811671943404,
      "clip_ratio/low_min": 2.333029351575533e-05,
      "clip_ratio/region_mean": 0.001359108733595349,
      "epoch": 0.07737313990048358,
      "grad_norm": 0.1289340853691101,
      "learning_rate": 2e-07,
      "loss": 0.052,
      "step": 829
    },
    {
      "clip_ratio/high_max": 0.0017290256982960273,
      "clip_ratio/high_mean": 0.0006129594457888743,
      "clip_ratio/low_mean": 0.0005570537887251703,
      "clip_ratio/low_min": 1.430860811524326e-05,
      "clip_ratio/region_mean": 0.0011700132417900022,
      "epoch": 0.07746647300048416,
      "grad_norm": 0.12778276205062866,
      "learning_rate": 2e-07,
      "loss": -0.0117,
      "step": 830
    },
    {
      "clip_ratio/high_max": 0.0019265570081188343,
      "clip_ratio/high_mean": 0.000739794782930403,
      "clip_ratio/low_mean": 0.0006098155099607538,
      "clip_ratio/low_min": 1.3625462997879367e-05,
      "clip_ratio/region_mean": 0.0013496102874341886,
      "epoch": 0.07755980610048475,
      "grad_norm": 0.13921457529067993,
      "learning_rate": 2e-07,
      "loss": -0.0001,
      "step": 831
    },
    {
      "clip_ratio/high_max": 0.0017783025687094778,
      "clip_ratio/high_mean": 0.0007399083333439194,
      "clip_ratio/low_mean": 0.0006000764351483667,
      "clip_ratio/low_min": 4.019117295683827e-05,
      "clip_ratio/region_mean": 0.0013399847630353179,
      "epoch": 0.07765313920048533,
      "grad_norm": 0.12935948371887207,
      "learning_rate": 2e-07,
      "loss": 0.0075,
      "step": 832
    },
    {
      "clip_ratio/high_max": 0.0018224665182060562,
      "clip_ratio/high_mean": 0.000690434679199825,
      "clip_ratio/low_mean": 0.0006447398927775794,
      "clip_ratio/low_min": 4.348593256509048e-05,
      "clip_ratio/region_mean": 0.001335174594714772,
      "epoch": 0.07774647230048591,
      "grad_norm": 0.13611753284931183,
      "learning_rate": 2e-07,
      "loss": 0.0346,
      "step": 833
    },
    {
      "clip_ratio/high_max": 0.0017993394139921293,
      "clip_ratio/high_mean": 0.0007234451495605754,
      "clip_ratio/low_mean": 0.0006524875216200599,
      "clip_ratio/low_min": 7.403199288091855e-05,
      "clip_ratio/region_mean": 0.0013759326284343842,
      "epoch": 0.0778398054004865,
      "grad_norm": 0.1413203477859497,
      "learning_rate": 2e-07,
      "loss": 0.0374,
      "step": 834
    },
    {
      "clip_ratio/high_max": 0.001584028846991714,
      "clip_ratio/high_mean": 0.0006908150317030959,
      "clip_ratio/low_mean": 0.0006102843035478145,
      "clip_ratio/low_min": 6.74017219353118e-05,
      "clip_ratio/region_mean": 0.001301099324336974,
      "epoch": 0.07793313850048708,
      "grad_norm": 0.14717626571655273,
      "learning_rate": 2e-07,
      "loss": 0.0372,
      "step": 835
    },
    {
      "clip_ratio/high_max": 0.0015361522528110072,
      "clip_ratio/high_mean": 0.0006697593089484144,
      "clip_ratio/low_mean": 0.0007000555451668333,
      "clip_ratio/low_min": 6.222843421710422e-05,
      "clip_ratio/region_mean": 0.0013698148650291841,
      "epoch": 0.07802647160048766,
      "grad_norm": 0.13847097754478455,
      "learning_rate": 2e-07,
      "loss": 0.0679,
      "step": 836
    },
    {
      "clip_ratio/high_max": 0.0017886962668853812,
      "clip_ratio/high_mean": 0.0007371825886366423,
      "clip_ratio/low_mean": 0.0005855020826857071,
      "clip_ratio/low_min": 5.6827787375368644e-05,
      "clip_ratio/region_mean": 0.0013226846676843707,
      "epoch": 0.07811980470048825,
      "grad_norm": 0.1522608995437622,
      "learning_rate": 2e-07,
      "loss": 0.0296,
      "step": 837
    },
    {
      "clip_ratio/high_max": 0.0015483665993087925,
      "clip_ratio/high_mean": 0.0006435153063648613,
      "clip_ratio/low_mean": 0.0005492567715918995,
      "clip_ratio/low_min": 3.705377639562357e-05,
      "clip_ratio/region_mean": 0.0011927720552193932,
      "epoch": 0.07821313780048883,
      "grad_norm": 0.13875828683376312,
      "learning_rate": 2e-07,
      "loss": 0.0453,
      "step": 838
    },
    {
      "clip_ratio/high_max": 0.0016914433545025531,
      "clip_ratio/high_mean": 0.0006929924966243561,
      "clip_ratio/low_mean": 0.0006704943316435674,
      "clip_ratio/low_min": 5.085479915578617e-05,
      "clip_ratio/region_mean": 0.0013634868191729765,
      "epoch": 0.07830647090048942,
      "grad_norm": 0.13252674043178558,
      "learning_rate": 2e-07,
      "loss": 0.0263,
      "step": 839
    },
    {
      "clip_ratio/high_max": 0.001797823129891185,
      "clip_ratio/high_mean": 0.0006902333789184922,
      "clip_ratio/low_mean": 0.0005146300554770278,
      "clip_ratio/low_min": 3.8217634028114844e-05,
      "clip_ratio/region_mean": 0.0012048634453094564,
      "epoch": 0.07839980400049,
      "grad_norm": 0.13485558331012726,
      "learning_rate": 2e-07,
      "loss": 0.03,
      "step": 840
    },
    {
      "clip_ratio/high_max": 0.0017605207067390438,
      "clip_ratio/high_mean": 0.0006810703071096214,
      "clip_ratio/low_mean": 0.0005693670418622787,
      "clip_ratio/low_min": 2.475845394656062e-05,
      "clip_ratio/region_mean": 0.001250437355338363,
      "epoch": 0.07849313710049058,
      "grad_norm": 0.1558636724948883,
      "learning_rate": 2e-07,
      "loss": 0.0377,
      "step": 841
    },
    {
      "clip_ratio/high_max": 0.001225426221935777,
      "clip_ratio/high_mean": 0.0005472269513120409,
      "clip_ratio/low_mean": 0.0005325346273821197,
      "clip_ratio/low_min": 2.735143334575696e-05,
      "clip_ratio/region_mean": 0.0010797615723276976,
      "epoch": 0.07858647020049117,
      "grad_norm": 0.12045590579509735,
      "learning_rate": 2e-07,
      "loss": 0.0297,
      "step": 842
    },
    {
      "clip_ratio/high_max": 0.001892310603579972,
      "clip_ratio/high_mean": 0.0008108117772280821,
      "clip_ratio/low_mean": 0.0005895059375689016,
      "clip_ratio/low_min": 3.2782509151729755e-05,
      "clip_ratio/region_mean": 0.0014003177020640578,
      "epoch": 0.07867980330049175,
      "grad_norm": 0.14394766092300415,
      "learning_rate": 2e-07,
      "loss": 0.008,
      "step": 843
    },
    {
      "clip_ratio/high_max": 0.0015954730024532182,
      "clip_ratio/high_mean": 0.0006656981067862944,
      "clip_ratio/low_mean": 0.0005600689346465515,
      "clip_ratio/low_min": 6.268016750254901e-05,
      "clip_ratio/region_mean": 0.0012257670605322346,
      "epoch": 0.07877313640049233,
      "grad_norm": 0.14831216633319855,
      "learning_rate": 2e-07,
      "loss": 0.0364,
      "step": 844
    },
    {
      "clip_ratio/high_max": 0.002108348962792661,
      "clip_ratio/high_mean": 0.0007428614298987668,
      "clip_ratio/low_mean": 0.0006216907886482659,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013645522230945062,
      "epoch": 0.07886646950049292,
      "grad_norm": 0.1329721361398697,
      "learning_rate": 2e-07,
      "loss": -0.0198,
      "step": 845
    },
    {
      "clip_ratio/high_max": 0.0015819431573618203,
      "clip_ratio/high_mean": 0.0006584189086424885,
      "clip_ratio/low_mean": 0.0006012320409354288,
      "clip_ratio/low_min": 6.011156438034959e-05,
      "clip_ratio/region_mean": 0.0012596509368449915,
      "epoch": 0.0789598026004935,
      "grad_norm": 0.14300298690795898,
      "learning_rate": 2e-07,
      "loss": 0.039,
      "step": 846
    },
    {
      "clip_ratio/high_max": 0.0016432298325526062,
      "clip_ratio/high_mean": 0.0007691864539083326,
      "clip_ratio/low_mean": 0.0005871288349226234,
      "clip_ratio/low_min": 8.327190334966872e-05,
      "clip_ratio/region_mean": 0.0013563152715505566,
      "epoch": 0.07905313570049408,
      "grad_norm": 1.0942280292510986,
      "learning_rate": 2e-07,
      "loss": 0.0337,
      "step": 847
    },
    {
      "clip_ratio/high_max": 0.002003811692702584,
      "clip_ratio/high_mean": 0.0008154770657711197,
      "clip_ratio/low_mean": 0.0006275693067436805,
      "clip_ratio/low_min": 6.367930200212868e-05,
      "clip_ratio/region_mean": 0.0014430463306780439,
      "epoch": 0.07914646880049467,
      "grad_norm": 0.12842611968517303,
      "learning_rate": 2e-07,
      "loss": -0.0011,
      "step": 848
    },
    {
      "clip_ratio/high_max": 0.0023378841069643386,
      "clip_ratio/high_mean": 0.0008084991222858662,
      "clip_ratio/low_mean": 0.0005760022086178651,
      "clip_ratio/low_min": 1.062383125827182e-05,
      "clip_ratio/region_mean": 0.0013845013636455406,
      "epoch": 0.07923980190049525,
      "grad_norm": 0.1393127292394638,
      "learning_rate": 2e-07,
      "loss": -0.0049,
      "step": 849
    },
    {
      "clip_ratio/high_max": 0.001980731678486336,
      "clip_ratio/high_mean": 0.0007093695840012515,
      "clip_ratio/low_mean": 0.0006512841009680415,
      "clip_ratio/low_min": 7.900724313003593e-05,
      "clip_ratio/region_mean": 0.0013606537104351446,
      "epoch": 0.07933313500049584,
      "grad_norm": 0.1291321963071823,
      "learning_rate": 2e-07,
      "loss": 0.0587,
      "step": 850
    },
    {
      "clip_ratio/high_max": 0.0020913483822369017,
      "clip_ratio/high_mean": 0.0007465839371434413,
      "clip_ratio/low_mean": 0.0006139702927612234,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013605542371806223,
      "epoch": 0.07942646810049642,
      "grad_norm": 0.13774874806404114,
      "learning_rate": 2e-07,
      "loss": 0.0335,
      "step": 851
    },
    {
      "clip_ratio/high_max": 0.0016417938531958498,
      "clip_ratio/high_mean": 0.0006433386115531903,
      "clip_ratio/low_mean": 0.0007103466268745251,
      "clip_ratio/low_min": 0.0001104758148358087,
      "clip_ratio/region_mean": 0.0013536852493416518,
      "epoch": 0.079519801200497,
      "grad_norm": 0.13146109879016876,
      "learning_rate": 2e-07,
      "loss": 0.0146,
      "step": 852
    },
    {
      "clip_ratio/high_max": 0.0016960887514869682,
      "clip_ratio/high_mean": 0.0006667942943749949,
      "clip_ratio/low_mean": 0.0006191753309394699,
      "clip_ratio/low_min": 2.8034493880113587e-05,
      "clip_ratio/region_mean": 0.0012859696144005284,
      "epoch": 0.07961313430049759,
      "grad_norm": 0.14730513095855713,
      "learning_rate": 2e-07,
      "loss": 0.0516,
      "step": 853
    },
    {
      "clip_ratio/high_max": 0.0018062445415125694,
      "clip_ratio/high_mean": 0.0007630339205206838,
      "clip_ratio/low_mean": 0.00066736639746523,
      "clip_ratio/low_min": 4.1812202653090935e-05,
      "clip_ratio/region_mean": 0.001430400265235221,
      "epoch": 0.07970646740049817,
      "grad_norm": 0.1876087635755539,
      "learning_rate": 2e-07,
      "loss": 0.0382,
      "step": 854
    },
    {
      "clip_ratio/high_max": 0.0018276439514011145,
      "clip_ratio/high_mean": 0.0007223620868899161,
      "clip_ratio/low_mean": 0.0005319120364219998,
      "clip_ratio/low_min": 3.890041625709273e-05,
      "clip_ratio/region_mean": 0.0012542741496872623,
      "epoch": 0.07979980050049874,
      "grad_norm": 0.3433104455471039,
      "learning_rate": 2e-07,
      "loss": 0.0101,
      "step": 855
    },
    {
      "clip_ratio/high_max": 0.0016408365445386153,
      "clip_ratio/high_mean": 0.0006067716803954681,
      "clip_ratio/low_mean": 0.0006541430766446865,
      "clip_ratio/low_min": 3.3152620744658634e-05,
      "clip_ratio/region_mean": 0.0012609147634066176,
      "epoch": 0.07989313360049934,
      "grad_norm": 0.15551145374774933,
      "learning_rate": 2e-07,
      "loss": 0.0506,
      "step": 856
    },
    {
      "clip_ratio/high_max": 0.001711485194391571,
      "clip_ratio/high_mean": 0.0008184422476915643,
      "clip_ratio/low_mean": 0.0005334352727004443,
      "clip_ratio/low_min": 5.369946939026704e-05,
      "clip_ratio/region_mean": 0.0013518775303964503,
      "epoch": 0.07998646670049991,
      "grad_norm": 0.14987154304981232,
      "learning_rate": 2e-07,
      "loss": 0.0044,
      "step": 857
    },
    {
      "clip_ratio/high_max": 0.0015381181401608046,
      "clip_ratio/high_mean": 0.0006723325132043101,
      "clip_ratio/low_mean": 0.0006101987401052611,
      "clip_ratio/low_min": 1.3241525266494136e-05,
      "clip_ratio/region_mean": 0.001282531302422285,
      "epoch": 0.08007979980050049,
      "grad_norm": 0.12890847027301788,
      "learning_rate": 2e-07,
      "loss": 0.0486,
      "step": 858
    },
    {
      "clip_ratio/high_max": 0.0018899553833762184,
      "clip_ratio/high_mean": 0.0008515239642292727,
      "clip_ratio/low_mean": 0.0006195432670210721,
      "clip_ratio/low_min": 1.5033072486403398e-05,
      "clip_ratio/region_mean": 0.0014710672257933766,
      "epoch": 0.08017313290050108,
      "grad_norm": 0.5196543335914612,
      "learning_rate": 2e-07,
      "loss": 0.0174,
      "step": 859
    },
    {
      "clip_ratio/high_max": 0.001675735657045152,
      "clip_ratio/high_mean": 0.0006546287941091578,
      "clip_ratio/low_mean": 0.0007412694076265325,
      "clip_ratio/low_min": 0.00011557375773918466,
      "clip_ratio/region_mean": 0.0013958981980977114,
      "epoch": 0.08026646600050166,
      "grad_norm": 0.14806358516216278,
      "learning_rate": 2e-07,
      "loss": 0.0824,
      "step": 860
    },
    {
      "clip_ratio/high_max": 0.002012482080317568,
      "clip_ratio/high_mean": 0.0007685529762966326,
      "clip_ratio/low_mean": 0.0007797358339303173,
      "clip_ratio/low_min": 9.013973067339975e-05,
      "clip_ratio/region_mean": 0.0015482887865800876,
      "epoch": 0.08035979910050225,
      "grad_norm": 0.1390140801668167,
      "learning_rate": 2e-07,
      "loss": 0.0786,
      "step": 861
    },
    {
      "clip_ratio/high_max": 0.001979123044293374,
      "clip_ratio/high_mean": 0.0008341717712028185,
      "clip_ratio/low_mean": 0.0005610369353235001,
      "clip_ratio/low_min": 1.775568125594873e-05,
      "clip_ratio/region_mean": 0.0013952087028883398,
      "epoch": 0.08045313220050283,
      "grad_norm": 0.14272533357143402,
      "learning_rate": 2e-07,
      "loss": -0.0057,
      "step": 862
    },
    {
      "clip_ratio/high_max": 0.0018688918753468897,
      "clip_ratio/high_mean": 0.0007769048606860451,
      "clip_ratio/low_mean": 0.0007264294918059022,
      "clip_ratio/low_min": 1.4714797998749418e-05,
      "clip_ratio/region_mean": 0.0015033343188406434,
      "epoch": 0.08054646530050341,
      "grad_norm": 0.15064172446727753,
      "learning_rate": 2e-07,
      "loss": 0.0556,
      "step": 863
    },
    {
      "clip_ratio/high_max": 0.0019289929732622113,
      "clip_ratio/high_mean": 0.0006883197856950574,
      "clip_ratio/low_mean": 0.0006164780979815987,
      "clip_ratio/low_min": 7.705895131948637e-05,
      "clip_ratio/region_mean": 0.0013047978936810978,
      "epoch": 0.080639798400504,
      "grad_norm": 0.14954252541065216,
      "learning_rate": 2e-07,
      "loss": 0.0629,
      "step": 864
    },
    {
      "clip_ratio/high_max": 0.0017198956957145128,
      "clip_ratio/high_mean": 0.0006002512454870157,
      "clip_ratio/low_mean": 0.0006767428003513487,
      "clip_ratio/low_min": 3.0250856980273966e-05,
      "clip_ratio/region_mean": 0.0012769940112775657,
      "epoch": 0.08073313150050458,
      "grad_norm": 0.1485782265663147,
      "learning_rate": 2e-07,
      "loss": 0.0776,
      "step": 865
    },
    {
      "clip_ratio/high_max": 0.001844557893491583,
      "clip_ratio/high_mean": 0.0006985152731431299,
      "clip_ratio/low_mean": 0.000572817625652533,
      "clip_ratio/low_min": 1.9512285689415876e-05,
      "clip_ratio/region_mean": 0.0012713329160760622,
      "epoch": 0.08082646460050516,
      "grad_norm": 0.12726767361164093,
      "learning_rate": 2e-07,
      "loss": 0.0308,
      "step": 866
    },
    {
      "clip_ratio/high_max": 0.001900109571579378,
      "clip_ratio/high_mean": 0.0007454441038134973,
      "clip_ratio/low_mean": 0.0006937586458661826,
      "clip_ratio/low_min": 7.015682240307797e-05,
      "clip_ratio/region_mean": 0.0014392027514986694,
      "epoch": 0.08091979770050575,
      "grad_norm": 0.12965478003025055,
      "learning_rate": 2e-07,
      "loss": 0.0143,
      "step": 867
    },
    {
      "clip_ratio/high_max": 0.001997934221435571,
      "clip_ratio/high_mean": 0.0008330866985488683,
      "clip_ratio/low_mean": 0.0005939876173215453,
      "clip_ratio/low_min": 7.09348896634765e-05,
      "clip_ratio/region_mean": 0.0014270743304223288,
      "epoch": 0.08101313080050633,
      "grad_norm": 0.14231403172016144,
      "learning_rate": 2e-07,
      "loss": -0.0501,
      "step": 868
    },
    {
      "clip_ratio/high_max": 0.0017240982197108679,
      "clip_ratio/high_mean": 0.0007752552810416091,
      "clip_ratio/low_mean": 0.0005868253047083272,
      "clip_ratio/low_min": 2.007709554163739e-05,
      "clip_ratio/region_mean": 0.0013620805875689257,
      "epoch": 0.08110646390050691,
      "grad_norm": 0.13820980489253998,
      "learning_rate": 2e-07,
      "loss": 0.0259,
      "step": 869
    },
    {
      "clip_ratio/high_max": 0.0019745566314668395,
      "clip_ratio/high_mean": 0.0007456436433130875,
      "clip_ratio/low_mean": 0.0006063898872525897,
      "clip_ratio/low_min": 2.5769651074369904e-05,
      "clip_ratio/region_mean": 0.0013520335451175924,
      "epoch": 0.0811997970005075,
      "grad_norm": 0.14774057269096375,
      "learning_rate": 2e-07,
      "loss": -0.0127,
      "step": 870
    },
    {
      "clip_ratio/high_max": 0.0017938436831173021,
      "clip_ratio/high_mean": 0.0007533786119893193,
      "clip_ratio/low_mean": 0.0006193013759911992,
      "clip_ratio/low_min": 6.230970575415995e-05,
      "clip_ratio/region_mean": 0.001372679998894455,
      "epoch": 0.08129313010050808,
      "grad_norm": 0.13127848505973816,
      "learning_rate": 2e-07,
      "loss": 0.0167,
      "step": 871
    },
    {
      "clip_ratio/high_max": 0.0016195896459976211,
      "clip_ratio/high_mean": 0.0006557989345310489,
      "clip_ratio/low_mean": 0.0006329556072159903,
      "clip_ratio/low_min": 2.4389313693973236e-05,
      "clip_ratio/region_mean": 0.0012887545053672511,
      "epoch": 0.08138646320050867,
      "grad_norm": 0.14775978028774261,
      "learning_rate": 2e-07,
      "loss": 0.0072,
      "step": 872
    },
    {
      "clip_ratio/high_max": 0.002060043469100492,
      "clip_ratio/high_mean": 0.0008124862033582758,
      "clip_ratio/low_mean": 0.0006765411544620292,
      "clip_ratio/low_min": 4.907749462290667e-05,
      "clip_ratio/region_mean": 0.0014890273596392944,
      "epoch": 0.08147979630050925,
      "grad_norm": 0.1471288800239563,
      "learning_rate": 2e-07,
      "loss": 0.0266,
      "step": 873
    },
    {
      "clip_ratio/high_max": 0.0014006509009050205,
      "clip_ratio/high_mean": 0.000629991080131731,
      "clip_ratio/low_mean": 0.0006208190370671218,
      "clip_ratio/low_min": 1.1877613360411488e-05,
      "clip_ratio/region_mean": 0.0012508101353887469,
      "epoch": 0.08157312940050983,
      "grad_norm": 0.1477607935667038,
      "learning_rate": 2e-07,
      "loss": 0.0438,
      "step": 874
    },
    {
      "clip_ratio/high_max": 0.0018564271194918547,
      "clip_ratio/high_mean": 0.0007484257548640016,
      "clip_ratio/low_mean": 0.0006713709681207547,
      "clip_ratio/low_min": 6.827870947745396e-05,
      "clip_ratio/region_mean": 0.001419796721165767,
      "epoch": 0.08166646250051042,
      "grad_norm": 0.14852215349674225,
      "learning_rate": 2e-07,
      "loss": 0.002,
      "step": 875
    },
    {
      "clip_ratio/high_max": 0.0017884806729853153,
      "clip_ratio/high_mean": 0.0006731024604960112,
      "clip_ratio/low_mean": 0.0006758268045814475,
      "clip_ratio/low_min": 3.679217661556322e-05,
      "clip_ratio/region_mean": 0.0013489292105077766,
      "epoch": 0.081759795600511,
      "grad_norm": 0.15335319936275482,
      "learning_rate": 2e-07,
      "loss": 0.0503,
      "step": 876
    },
    {
      "clip_ratio/high_max": 0.0019437867013039067,
      "clip_ratio/high_mean": 0.000774052869019215,
      "clip_ratio/low_mean": 0.0006866722815175308,
      "clip_ratio/low_min": 3.823641600320116e-05,
      "clip_ratio/region_mean": 0.001460725128708873,
      "epoch": 0.08185312870051158,
      "grad_norm": 0.15180355310440063,
      "learning_rate": 2e-07,
      "loss": 0.0248,
      "step": 877
    },
    {
      "clip_ratio/high_max": 0.001648773206397891,
      "clip_ratio/high_mean": 0.000675855781082646,
      "clip_ratio/low_mean": 0.0005633903510897653,
      "clip_ratio/low_min": 5.451296783576254e-05,
      "clip_ratio/region_mean": 0.0012392461685521994,
      "epoch": 0.08194646180051217,
      "grad_norm": 0.17971192300319672,
      "learning_rate": 2e-07,
      "loss": 0.0467,
      "step": 878
    },
    {
      "clip_ratio/high_max": 0.0021123115402588155,
      "clip_ratio/high_mean": 0.0007828916368453065,
      "clip_ratio/low_mean": 0.000799987308710115,
      "clip_ratio/low_min": 8.088581671472639e-05,
      "clip_ratio/region_mean": 0.0015828789619263262,
      "epoch": 0.08203979490051275,
      "grad_norm": 0.16863180696964264,
      "learning_rate": 2e-07,
      "loss": 0.0538,
      "step": 879
    },
    {
      "clip_ratio/high_max": 0.001910745704662986,
      "clip_ratio/high_mean": 0.0007282940996446996,
      "clip_ratio/low_mean": 0.0006974485531827668,
      "clip_ratio/low_min": 4.059912225784501e-05,
      "clip_ratio/region_mean": 0.0014257426701078657,
      "epoch": 0.08213312800051333,
      "grad_norm": 0.1560388058423996,
      "learning_rate": 2e-07,
      "loss": 0.0371,
      "step": 880
    },
    {
      "clip_ratio/high_max": 0.0017949828252312727,
      "clip_ratio/high_mean": 0.0007138938981370302,
      "clip_ratio/low_mean": 0.0007347150403802516,
      "clip_ratio/low_min": 2.5444866878387984e-05,
      "clip_ratio/region_mean": 0.0014486089821730275,
      "epoch": 0.08222646110051392,
      "grad_norm": 0.15449275076389313,
      "learning_rate": 2e-07,
      "loss": 0.0503,
      "step": 881
    },
    {
      "clip_ratio/high_max": 0.0018755537530523725,
      "clip_ratio/high_mean": 0.0007707539934926899,
      "clip_ratio/low_mean": 0.0007557611788797658,
      "clip_ratio/low_min": 9.487800525675993e-05,
      "clip_ratio/region_mean": 0.0015265151596395299,
      "epoch": 0.0823197942005145,
      "grad_norm": 0.14759862422943115,
      "learning_rate": 2e-07,
      "loss": 0.0436,
      "step": 882
    },
    {
      "clip_ratio/high_max": 0.0016725193599995691,
      "clip_ratio/high_mean": 0.0006895127080497332,
      "clip_ratio/low_mean": 0.000665772467982606,
      "clip_ratio/low_min": 1.0169215784117114e-05,
      "clip_ratio/region_mean": 0.0013552851814893074,
      "epoch": 0.08241312730051509,
      "grad_norm": 0.14946848154067993,
      "learning_rate": 2e-07,
      "loss": 0.0167,
      "step": 883
    },
    {
      "clip_ratio/high_max": 0.0018691809018491767,
      "clip_ratio/high_mean": 0.0007826018154446501,
      "clip_ratio/low_mean": 0.0006689381716569187,
      "clip_ratio/low_min": 2.4245207896456122e-05,
      "clip_ratio/region_mean": 0.0014515399852825794,
      "epoch": 0.08250646040051567,
      "grad_norm": 0.15613532066345215,
      "learning_rate": 2e-07,
      "loss": 0.0197,
      "step": 884
    },
    {
      "clip_ratio/high_max": 0.0018033101987384725,
      "clip_ratio/high_mean": 0.00068618035675172,
      "clip_ratio/low_mean": 0.0006260787340579554,
      "clip_ratio/low_min": 3.101827678619884e-05,
      "clip_ratio/region_mean": 0.0013122591008141171,
      "epoch": 0.08259979350051624,
      "grad_norm": 0.15417198836803436,
      "learning_rate": 2e-07,
      "loss": 0.0415,
      "step": 885
    },
    {
      "clip_ratio/high_max": 0.0014340401685331017,
      "clip_ratio/high_mean": 0.0005341353835319751,
      "clip_ratio/low_mean": 0.0007240354243549518,
      "clip_ratio/low_min": 5.067976417194586e-05,
      "clip_ratio/region_mean": 0.001258170828805305,
      "epoch": 0.08269312660051684,
      "grad_norm": 0.15052969753742218,
      "learning_rate": 2e-07,
      "loss": 0.1043,
      "step": 886
    },
    {
      "clip_ratio/high_max": 0.0015787077973072883,
      "clip_ratio/high_mean": 0.0007242591291287681,
      "clip_ratio/low_mean": 0.0006903689554746961,
      "clip_ratio/low_min": 3.094790872637532e-05,
      "clip_ratio/region_mean": 0.0014146280809654854,
      "epoch": 0.08278645970051741,
      "grad_norm": 0.15324755012989044,
      "learning_rate": 2e-07,
      "loss": 0.0139,
      "step": 887
    },
    {
      "clip_ratio/high_max": 0.0018118570296792313,
      "clip_ratio/high_mean": 0.0007107348083081888,
      "clip_ratio/low_mean": 0.0006355828336381819,
      "clip_ratio/low_min": 3.053248656215146e-05,
      "clip_ratio/region_mean": 0.0013463176510413177,
      "epoch": 0.08287979280051799,
      "grad_norm": 0.15231993794441223,
      "learning_rate": 2e-07,
      "loss": 0.0326,
      "step": 888
    },
    {
      "clip_ratio/high_max": 0.001823573427827796,
      "clip_ratio/high_mean": 0.0007488795381505042,
      "clip_ratio/low_mean": 0.0007158957960200496,
      "clip_ratio/low_min": 3.773344087676378e-05,
      "clip_ratio/region_mean": 0.0014647753232566174,
      "epoch": 0.08297312590051859,
      "grad_norm": 0.15197741985321045,
      "learning_rate": 2e-07,
      "loss": 0.026,
      "step": 889
    },
    {
      "clip_ratio/high_max": 0.0021500605798792094,
      "clip_ratio/high_mean": 0.0008346428749064216,
      "clip_ratio/low_mean": 0.0006667869165539742,
      "clip_ratio/low_min": 6.639120147156063e-05,
      "clip_ratio/region_mean": 0.0015014297896414064,
      "epoch": 0.08306645900051916,
      "grad_norm": 0.16495245695114136,
      "learning_rate": 2e-07,
      "loss": 0.0614,
      "step": 890
    },
    {
      "clip_ratio/high_max": 0.0018786937398544978,
      "clip_ratio/high_mean": 0.0007208866736618802,
      "clip_ratio/low_mean": 0.0006879121774545638,
      "clip_ratio/low_min": 2.4550824491598178e-05,
      "clip_ratio/region_mean": 0.0014087988383835182,
      "epoch": 0.08315979210051976,
      "grad_norm": 0.14222539961338043,
      "learning_rate": 2e-07,
      "loss": 0.0472,
      "step": 891
    },
    {
      "clip_ratio/high_max": 0.0018867180260713212,
      "clip_ratio/high_mean": 0.0007152818816393847,
      "clip_ratio/low_mean": 0.0006859085910946305,
      "clip_ratio/low_min": 2.0654330000979826e-05,
      "clip_ratio/region_mean": 0.0014011904459039215,
      "epoch": 0.08325312520052033,
      "grad_norm": 0.15165096521377563,
      "learning_rate": 2e-07,
      "loss": 0.0126,
      "step": 892
    },
    {
      "clip_ratio/high_max": 0.0018001270400418434,
      "clip_ratio/high_mean": 0.0007458786594725098,
      "clip_ratio/low_mean": 0.0007364626853814116,
      "clip_ratio/low_min": 1.8780048776534386e-05,
      "clip_ratio/region_mean": 0.0014823413148405962,
      "epoch": 0.08334645830052091,
      "grad_norm": 0.158020481467247,
      "learning_rate": 2e-07,
      "loss": 0.0347,
      "step": 893
    },
    {
      "clip_ratio/high_max": 0.0016442542146251071,
      "clip_ratio/high_mean": 0.0007394768999802181,
      "clip_ratio/low_mean": 0.0006795691297156736,
      "clip_ratio/low_min": 2.5206694772350602e-05,
      "clip_ratio/region_mean": 0.0014190459914971143,
      "epoch": 0.0834397914005215,
      "grad_norm": 0.22650913894176483,
      "learning_rate": 2e-07,
      "loss": 0.0074,
      "step": 894
    },
    {
      "clip_ratio/high_max": 0.0018098328328051139,
      "clip_ratio/high_mean": 0.0007236579522214015,
      "clip_ratio/low_mean": 0.000725617581338156,
      "clip_ratio/low_min": 2.7409633730712812e-05,
      "clip_ratio/region_mean": 0.0014492755435639992,
      "epoch": 0.08353312450052208,
      "grad_norm": 0.15240046381950378,
      "learning_rate": 2e-07,
      "loss": 0.029,
      "step": 895
    },
    {
      "clip_ratio/high_max": 0.0018638131441548467,
      "clip_ratio/high_mean": 0.0007621964232384926,
      "clip_ratio/low_mean": 0.0007263141533258022,
      "clip_ratio/low_min": 2.9648386771441437e-05,
      "clip_ratio/region_mean": 0.001488510566559853,
      "epoch": 0.08362645760052266,
      "grad_norm": 0.1562882363796234,
      "learning_rate": 2e-07,
      "loss": 0.028,
      "step": 896
    },
    {
      "clip_ratio/high_max": 0.0016560972198931267,
      "clip_ratio/high_mean": 0.0006526611077788402,
      "clip_ratio/low_mean": 0.00044857291049993364,
      "clip_ratio/low_min": 1.9857408915413544e-05,
      "clip_ratio/region_mean": 0.0011012340219167527,
      "completions/clipped_ratio": 0.0175258091517857,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4093.0,
      "completions/mean_length": 693.3145751953125,
      "completions/mean_terminated_length": 632.6159057617188,
      "completions/min_length": 73.0,
      "completions/min_terminated_length": 73.0,
      "epoch": 0.08371979070052325,
      "grad_norm": 0.13171540200710297,
      "learning_rate": 2e-07,
      "loss": -0.0333,
      "num_tokens": 683181651.0,
      "reward": 0.5909947156906128,
      "reward_std": 0.18449048697948456,
      "rewards/simpleverify_reward/mean": 0.5909947156906128,
      "rewards/simpleverify_reward/std": 0.4916522800922394,
      "step": 897
    },
    {
      "clip_ratio/high_max": 0.0012316569664108101,
      "clip_ratio/high_mean": 0.00048433541087433696,
      "clip_ratio/low_mean": 0.000601938466388674,
      "clip_ratio/low_min": 5.258713645162061e-05,
      "clip_ratio/region_mean": 0.0010862738854484633,
      "epoch": 0.08381312380052383,
      "grad_norm": 0.11051229387521744,
      "learning_rate": 2e-07,
      "loss": 0.0634,
      "step": 898
    },
    {
      "clip_ratio/high_max": 0.001546220068121329,
      "clip_ratio/high_mean": 0.0005836970358359395,
      "clip_ratio/low_mean": 0.0006119621484685922,
      "clip_ratio/low_min": 1.1283625099167693e-05,
      "clip_ratio/region_mean": 0.001195659177028574,
      "epoch": 0.08390645690052441,
      "grad_norm": 0.1331675797700882,
      "learning_rate": 2e-07,
      "loss": 0.0292,
      "step": 899
    },
    {
      "clip_ratio/high_max": 0.0018290210373379523,
      "clip_ratio/high_mean": 0.0006926975593160023,
      "clip_ratio/low_mean": 0.000570325897570001,
      "clip_ratio/low_min": 1.014281042444054e-05,
      "clip_ratio/region_mean": 0.0012630234450625721,
      "epoch": 0.083999790000525,
      "grad_norm": 0.13456912338733673,
      "learning_rate": 2e-07,
      "loss": 0.0141,
      "step": 900
    },
    {
      "clip_ratio/high_max": 0.0016368049691664055,
      "clip_ratio/high_mean": 0.0005792823758383747,
      "clip_ratio/low_mean": 0.0005743690871895524,
      "clip_ratio/low_min": 6.18761255282152e-05,
      "clip_ratio/region_mean": 0.0011536514575709589,
      "epoch": 0.08409312310052558,
      "grad_norm": 0.13325537741184235,
      "learning_rate": 2e-07,
      "loss": 0.0562,
      "step": 901
    },
    {
      "clip_ratio/high_max": 0.0016441021907667164,
      "clip_ratio/high_mean": 0.000682180736475857,
      "clip_ratio/low_mean": 0.0005876615796296392,
      "clip_ratio/low_min": 6.639639286731835e-05,
      "clip_ratio/region_mean": 0.001269842279725708,
      "epoch": 0.08418645620052617,
      "grad_norm": 0.13410881161689758,
      "learning_rate": 2e-07,
      "loss": 0.036,
      "step": 902
    },
    {
      "clip_ratio/high_max": 0.0014794917096878635,
      "clip_ratio/high_mean": 0.0006082955871988815,
      "clip_ratio/low_mean": 0.0005183369721635245,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0011266325745964423,
      "epoch": 0.08427978930052675,
      "grad_norm": 0.17643125355243683,
      "learning_rate": 2e-07,
      "loss": 0.0128,
      "step": 903
    },
    {
      "clip_ratio/high_max": 0.0018354681833443465,
      "clip_ratio/high_mean": 0.0006911804730407312,
      "clip_ratio/low_mean": 0.0006056933525542263,
      "clip_ratio/low_min": 3.297692819614895e-05,
      "clip_ratio/region_mean": 0.0012968737974006217,
      "epoch": 0.08437312240052733,
      "grad_norm": 0.14177632331848145,
      "learning_rate": 2e-07,
      "loss": 0.0076,
      "step": 904
    },
    {
      "clip_ratio/high_max": 0.0015734645057818852,
      "clip_ratio/high_mean": 0.0006471936403613654,
      "clip_ratio/low_mean": 0.00044559212528838543,
      "clip_ratio/low_min": 2.3994695766305085e-05,
      "clip_ratio/region_mean": 0.0010927857583737932,
      "epoch": 0.08446645550052792,
      "grad_norm": 0.1294097900390625,
      "learning_rate": 2e-07,
      "loss": 0.0556,
      "step": 905
    },
    {
      "clip_ratio/high_max": 0.0016185065942408983,
      "clip_ratio/high_mean": 0.0006577680896953098,
      "clip_ratio/low_mean": 0.0005718813936255174,
      "clip_ratio/low_min": 1.945429903571494e-05,
      "clip_ratio/region_mean": 0.0012296495042392053,
      "epoch": 0.0845597886005285,
      "grad_norm": 0.12381117045879364,
      "learning_rate": 2e-07,
      "loss": 0.0312,
      "step": 906
    },
    {
      "clip_ratio/high_max": 0.001384539053105982,
      "clip_ratio/high_mean": 0.0006249527596082771,
      "clip_ratio/low_mean": 0.000523399712619721,
      "clip_ratio/low_min": 1.9171779058524407e-05,
      "clip_ratio/region_mean": 0.001148352494055871,
      "epoch": 0.08465312170052908,
      "grad_norm": 0.1327299028635025,
      "learning_rate": 2e-07,
      "loss": 0.0317,
      "step": 907
    },
    {
      "clip_ratio/high_max": 0.0016575021654716693,
      "clip_ratio/high_mean": 0.0007232843272504397,
      "clip_ratio/low_mean": 0.0005636911209876416,
      "clip_ratio/low_min": 3.611651118262671e-05,
      "clip_ratio/region_mean": 0.0012869754500570707,
      "epoch": 0.08474645480052967,
      "grad_norm": 0.13217133283615112,
      "learning_rate": 2e-07,
      "loss": 0.0362,
      "step": 908
    },
    {
      "clip_ratio/high_max": 0.001459163748222636,
      "clip_ratio/high_mean": 0.000605471712333383,
      "clip_ratio/low_mean": 0.0005223097605266958,
      "clip_ratio/low_min": 1.0770290828077123e-05,
      "clip_ratio/region_mean": 0.001127781502873404,
      "epoch": 0.08483978790053025,
      "grad_norm": 0.12879282236099243,
      "learning_rate": 2e-07,
      "loss": 0.0025,
      "step": 909
    },
    {
      "clip_ratio/high_max": 0.0016396696446463466,
      "clip_ratio/high_mean": 0.000699904059729306,
      "clip_ratio/low_mean": 0.0005736393550250796,
      "clip_ratio/low_min": 5.5327671361737885e-05,
      "clip_ratio/region_mean": 0.0012735434429487213,
      "epoch": 0.08493312100053083,
      "grad_norm": 0.13327962160110474,
      "learning_rate": 2e-07,
      "loss": 0.0159,
      "step": 910
    },
    {
      "clip_ratio/high_max": 0.001338091547950171,
      "clip_ratio/high_mean": 0.0006124109331722138,
      "clip_ratio/low_mean": 0.0005062381969764829,
      "clip_ratio/low_min": 3.639639999164501e-05,
      "clip_ratio/region_mean": 0.001118649135605665,
      "epoch": 0.08502645410053142,
      "grad_norm": 0.12741810083389282,
      "learning_rate": 2e-07,
      "loss": 0.0399,
      "step": 911
    },
    {
      "clip_ratio/high_max": 0.0016357092608814128,
      "clip_ratio/high_mean": 0.0006429650420614053,
      "clip_ratio/low_mean": 0.0006365568369801622,
      "clip_ratio/low_min": 1.9909477941837395e-05,
      "clip_ratio/region_mean": 0.0012795218062819913,
      "epoch": 0.085119787200532,
      "grad_norm": 0.13313420116901398,
      "learning_rate": 2e-07,
      "loss": 0.0496,
      "step": 912
    },
    {
      "clip_ratio/high_max": 0.0013013774641876807,
      "clip_ratio/high_mean": 0.0005311715563038888,
      "clip_ratio/low_mean": 0.0005567028892983217,
      "clip_ratio/low_min": 2.4046942598943133e-05,
      "clip_ratio/region_mean": 0.0010878744542424101,
      "epoch": 0.08521312030053259,
      "grad_norm": 0.12633016705513,
      "learning_rate": 2e-07,
      "loss": 0.0547,
      "step": 913
    },
    {
      "clip_ratio/high_max": 0.0016045389311329927,
      "clip_ratio/high_mean": 0.0006457148965637316,
      "clip_ratio/low_mean": 0.0005750907694164198,
      "clip_ratio/low_min": 1.975659870367963e-05,
      "clip_ratio/region_mean": 0.0012208056650706567,
      "epoch": 0.08530645340053317,
      "grad_norm": 0.14885802567005157,
      "learning_rate": 2e-07,
      "loss": 0.0405,
      "step": 914
    },
    {
      "clip_ratio/high_max": 0.0015958873882482294,
      "clip_ratio/high_mean": 0.0006219446295290254,
      "clip_ratio/low_mean": 0.0006039345562385279,
      "clip_ratio/low_min": 1.7715419744490646e-05,
      "clip_ratio/region_mean": 0.0012258791757631116,
      "epoch": 0.08539978650053374,
      "grad_norm": 0.14801421761512756,
      "learning_rate": 2e-07,
      "loss": 0.0227,
      "step": 915
    },
    {
      "clip_ratio/high_max": 0.0017836761944636237,
      "clip_ratio/high_mean": 0.0006767797167412937,
      "clip_ratio/low_mean": 0.0005639445716951741,
      "clip_ratio/low_min": 3.646466348072863e-05,
      "clip_ratio/region_mean": 0.0012407242975314148,
      "epoch": 0.08549311960053434,
      "grad_norm": 0.1382058560848236,
      "learning_rate": 2e-07,
      "loss": 0.035,
      "step": 916
    },
    {
      "clip_ratio/high_max": 0.0019303390145068988,
      "clip_ratio/high_mean": 0.0006446091765610618,
      "clip_ratio/low_mean": 0.0005069432818345376,
      "clip_ratio/low_min": 1.9383164726605173e-05,
      "clip_ratio/region_mean": 0.0011515524638525676,
      "epoch": 0.08558645270053492,
      "grad_norm": 0.12561194598674774,
      "learning_rate": 2e-07,
      "loss": 0.0076,
      "step": 917
    },
    {
      "clip_ratio/high_max": 0.0016396929386246484,
      "clip_ratio/high_mean": 0.0006356117628456559,
      "clip_ratio/low_mean": 0.0005789197766716825,
      "clip_ratio/low_min": 1.4504525097436272e-05,
      "clip_ratio/region_mean": 0.0012145315668021794,
      "epoch": 0.0856797858005355,
      "grad_norm": 0.12058184295892715,
      "learning_rate": 2e-07,
      "loss": 0.0243,
      "step": 918
    },
    {
      "clip_ratio/high_max": 0.0014865816010569688,
      "clip_ratio/high_mean": 0.0006612684783249279,
      "clip_ratio/low_mean": 0.0005225264426371723,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001183794907774427,
      "epoch": 0.08577311890053609,
      "grad_norm": 0.13732269406318665,
      "learning_rate": 2e-07,
      "loss": 0.0079,
      "step": 919
    },
    {
      "clip_ratio/high_max": 0.0014245239854062675,
      "clip_ratio/high_mean": 0.0006365222707245266,
      "clip_ratio/low_mean": 0.0006876149236632045,
      "clip_ratio/low_min": 4.5640611460839864e-05,
      "clip_ratio/region_mean": 0.0013241371998446994,
      "epoch": 0.08586645200053666,
      "grad_norm": 0.12787336111068726,
      "learning_rate": 2e-07,
      "loss": 0.0305,
      "step": 920
    },
    {
      "clip_ratio/high_max": 0.0017049480084097013,
      "clip_ratio/high_mean": 0.0006316717317531584,
      "clip_ratio/low_mean": 0.0005368405563785927,
      "clip_ratio/low_min": 3.286567243776517e-05,
      "clip_ratio/region_mean": 0.00116851229176973,
      "epoch": 0.08595978510053724,
      "grad_norm": 0.12538205087184906,
      "learning_rate": 2e-07,
      "loss": 0.0451,
      "step": 921
    },
    {
      "clip_ratio/high_max": 0.0017987938990700059,
      "clip_ratio/high_mean": 0.000727051061403472,
      "clip_ratio/low_mean": 0.0004899194418612751,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012169704787083901,
      "epoch": 0.08605311820053783,
      "grad_norm": 0.13710756599903107,
      "learning_rate": 2e-07,
      "loss": 0.0062,
      "step": 922
    },
    {
      "clip_ratio/high_max": 0.0016849308740347624,
      "clip_ratio/high_mean": 0.0006324390815279912,
      "clip_ratio/low_mean": 0.000549695181689458,
      "clip_ratio/low_min": 2.8599823963304516e-05,
      "clip_ratio/region_mean": 0.0011821342886833008,
      "epoch": 0.08614645130053841,
      "grad_norm": 0.1363169103860855,
      "learning_rate": 2e-07,
      "loss": 0.0498,
      "step": 923
    },
    {
      "clip_ratio/high_max": 0.0013095399353915127,
      "clip_ratio/high_mean": 0.000587751136663428,
      "clip_ratio/low_mean": 0.0004892511037724034,
      "clip_ratio/low_min": 3.272365074735717e-05,
      "clip_ratio/region_mean": 0.0010770022236101795,
      "epoch": 0.086239784400539,
      "grad_norm": 0.13535773754119873,
      "learning_rate": 2e-07,
      "loss": 0.0496,
      "step": 924
    },
    {
      "clip_ratio/high_max": 0.0017012190692184959,
      "clip_ratio/high_mean": 0.0006338730900097289,
      "clip_ratio/low_mean": 0.0006506138779514004,
      "clip_ratio/low_min": 6.710718434987939e-05,
      "clip_ratio/region_mean": 0.0012844869925174862,
      "epoch": 0.08633311750053958,
      "grad_norm": 0.14865043759346008,
      "learning_rate": 2e-07,
      "loss": 0.0538,
      "step": 925
    },
    {
      "clip_ratio/high_max": 0.001827272502850974,
      "clip_ratio/high_mean": 0.0007094328302628128,
      "clip_ratio/low_mean": 0.0006520816878037294,
      "clip_ratio/low_min": 8.030322533159051e-06,
      "clip_ratio/region_mean": 0.0013615145253424998,
      "epoch": 0.08642645060054016,
      "grad_norm": 0.14650647342205048,
      "learning_rate": 2e-07,
      "loss": 0.0351,
      "step": 926
    },
    {
      "clip_ratio/high_max": 0.002131748879037332,
      "clip_ratio/high_mean": 0.0007151886584324529,
      "clip_ratio/low_mean": 0.0006508305814350024,
      "clip_ratio/low_min": 4.6251254389062524e-05,
      "clip_ratio/region_mean": 0.0013660192526003812,
      "epoch": 0.08651978370054075,
      "grad_norm": 0.14973606169223785,
      "learning_rate": 2e-07,
      "loss": 0.0594,
      "step": 927
    },
    {
      "clip_ratio/high_max": 0.0015337518671003636,
      "clip_ratio/high_mean": 0.0006350528683469747,
      "clip_ratio/low_mean": 0.0005688353803634527,
      "clip_ratio/low_min": 7.010342687863158e-05,
      "clip_ratio/region_mean": 0.0012038882341585122,
      "epoch": 0.08661311680054133,
      "grad_norm": 0.1481391042470932,
      "learning_rate": 2e-07,
      "loss": 0.0297,
      "step": 928
    },
    {
      "clip_ratio/high_max": 0.0013615010975627229,
      "clip_ratio/high_mean": 0.0005450303506222554,
      "clip_ratio/low_mean": 0.0006698200668324716,
      "clip_ratio/low_min": 0.0001279893012906541,
      "clip_ratio/region_mean": 0.0012148504392825998,
      "epoch": 0.08670644990054191,
      "grad_norm": 0.15031468868255615,
      "learning_rate": 2e-07,
      "loss": 0.1025,
      "step": 929
    },
    {
      "clip_ratio/high_max": 0.0017725435245665722,
      "clip_ratio/high_mean": 0.0007050289477774641,
      "clip_ratio/low_mean": 0.000619553843534959,
      "clip_ratio/low_min": 2.2806201286584837e-05,
      "clip_ratio/region_mean": 0.0013245827940409072,
      "epoch": 0.0867997830005425,
      "grad_norm": 0.1373024731874466,
      "learning_rate": 2e-07,
      "loss": 0.0409,
      "step": 930
    },
    {
      "clip_ratio/high_max": 0.0020070315003977157,
      "clip_ratio/high_mean": 0.0008343212612089701,
      "clip_ratio/low_mean": 0.0005558394204854267,
      "clip_ratio/low_min": 7.678482052142499e-05,
      "clip_ratio/region_mean": 0.0013901606907893438,
      "epoch": 0.08689311610054308,
      "grad_norm": 0.14910583198070526,
      "learning_rate": 2e-07,
      "loss": -0.0223,
      "step": 931
    },
    {
      "clip_ratio/high_max": 0.001787763940228615,
      "clip_ratio/high_mean": 0.0007375061795755755,
      "clip_ratio/low_mean": 0.0005720901608583517,
      "clip_ratio/low_min": 3.441156150074676e-05,
      "clip_ratio/region_mean": 0.0013095963113300968,
      "epoch": 0.08698644920054366,
      "grad_norm": 0.13903598487377167,
      "learning_rate": 2e-07,
      "loss": -0.0026,
      "step": 932
    },
    {
      "clip_ratio/high_max": 0.0017603152555238921,
      "clip_ratio/high_mean": 0.0006573434729943983,
      "clip_ratio/low_mean": 0.0005951918428763747,
      "clip_ratio/low_min": 4.925007124256808e-05,
      "clip_ratio/region_mean": 0.0012525353231467307,
      "epoch": 0.08707978230054425,
      "grad_norm": 0.1309700757265091,
      "learning_rate": 2e-07,
      "loss": 0.0323,
      "step": 933
    },
    {
      "clip_ratio/high_max": 0.0014851174819341395,
      "clip_ratio/high_mean": 0.0006932877495273715,
      "clip_ratio/low_mean": 0.0005705613793907105,
      "clip_ratio/low_min": 4.488106060307473e-05,
      "clip_ratio/region_mean": 0.001263849171664333,
      "epoch": 0.08717311540054483,
      "grad_norm": 0.13729554414749146,
      "learning_rate": 2e-07,
      "loss": 0.0158,
      "step": 934
    },
    {
      "clip_ratio/high_max": 0.0017485947500972543,
      "clip_ratio/high_mean": 0.0007261312421178445,
      "clip_ratio/low_mean": 0.0006434208994505752,
      "clip_ratio/low_min": 5.5449204410251696e-05,
      "clip_ratio/region_mean": 0.001369552184769418,
      "epoch": 0.08726644850054542,
      "grad_norm": 0.13647888600826263,
      "learning_rate": 2e-07,
      "loss": 0.0512,
      "step": 935
    },
    {
      "clip_ratio/high_max": 0.0014082616762607358,
      "clip_ratio/high_mean": 0.0005941977287875488,
      "clip_ratio/low_mean": 0.0006057078635421931,
      "clip_ratio/low_min": 4.207480469631264e-05,
      "clip_ratio/region_mean": 0.001199905622343067,
      "epoch": 0.087359781600546,
      "grad_norm": 0.12021670490503311,
      "learning_rate": 2e-07,
      "loss": 0.0202,
      "step": 936
    },
    {
      "clip_ratio/high_max": 0.0014971503624110483,
      "clip_ratio/high_mean": 0.0006213501619640738,
      "clip_ratio/low_mean": 0.0007087758913257858,
      "clip_ratio/low_min": 5.9460407101141755e-05,
      "clip_ratio/region_mean": 0.0013301260405569337,
      "epoch": 0.08745311470054658,
      "grad_norm": 0.1369185745716095,
      "learning_rate": 2e-07,
      "loss": 0.0434,
      "step": 937
    },
    {
      "clip_ratio/high_max": 0.00167594023514539,
      "clip_ratio/high_mean": 0.0006369892980728764,
      "clip_ratio/low_mean": 0.0005752286551796715,
      "clip_ratio/low_min": 1.2628814147319645e-05,
      "clip_ratio/region_mean": 0.001212217946886085,
      "epoch": 0.08754644780054717,
      "grad_norm": 0.1603764295578003,
      "learning_rate": 2e-07,
      "loss": 0.0219,
      "step": 938
    },
    {
      "clip_ratio/high_max": 0.00185001769932569,
      "clip_ratio/high_mean": 0.0007100316797732376,
      "clip_ratio/low_mean": 0.0005651447208947502,
      "clip_ratio/low_min": 8.640950909466483e-06,
      "clip_ratio/region_mean": 0.0012751764043059666,
      "epoch": 0.08763978090054775,
      "grad_norm": 0.1361202746629715,
      "learning_rate": 2e-07,
      "loss": -0.0021,
      "step": 939
    },
    {
      "clip_ratio/high_max": 0.0017439968542021234,
      "clip_ratio/high_mean": 0.0006408352073776769,
      "clip_ratio/low_mean": 0.0006287747082751594,
      "clip_ratio/low_min": 2.891475651267683e-05,
      "clip_ratio/region_mean": 0.0012696098783635534,
      "epoch": 0.08773311400054833,
      "grad_norm": 0.1413341909646988,
      "learning_rate": 2e-07,
      "loss": 0.0326,
      "step": 940
    },
    {
      "clip_ratio/high_max": 0.0017212278908118606,
      "clip_ratio/high_mean": 0.0006696018208458554,
      "clip_ratio/low_mean": 0.0005703463830286637,
      "clip_ratio/low_min": 2.417275118204998e-05,
      "clip_ratio/region_mean": 0.001239948207512498,
      "epoch": 0.08782644710054892,
      "grad_norm": 0.15333615243434906,
      "learning_rate": 2e-07,
      "loss": 0.0331,
      "step": 941
    },
    {
      "clip_ratio/high_max": 0.0017269724812649656,
      "clip_ratio/high_mean": 0.0006890201184432954,
      "clip_ratio/low_mean": 0.0006185145830386318,
      "clip_ratio/low_min": 2.2830275156593416e-05,
      "clip_ratio/region_mean": 0.001307534705119906,
      "epoch": 0.0879197802005495,
      "grad_norm": 0.12947024405002594,
      "learning_rate": 2e-07,
      "loss": 0.0166,
      "step": 942
    },
    {
      "clip_ratio/high_max": 0.001715404443530133,
      "clip_ratio/high_mean": 0.0006204548408277333,
      "clip_ratio/low_mean": 0.0005898995459574508,
      "clip_ratio/low_min": 2.2046743652026635e-05,
      "clip_ratio/region_mean": 0.0012103544031560887,
      "epoch": 0.08801311330055009,
      "grad_norm": 0.15068522095680237,
      "learning_rate": 2e-07,
      "loss": 0.0237,
      "step": 943
    },
    {
      "clip_ratio/high_max": 0.0016891044288058765,
      "clip_ratio/high_mean": 0.0007275959396793041,
      "clip_ratio/low_mean": 0.0005888412961212453,
      "clip_ratio/low_min": 9.14544943952933e-06,
      "clip_ratio/region_mean": 0.0013164372503524646,
      "epoch": 0.08810644640055067,
      "grad_norm": 0.1549796313047409,
      "learning_rate": 2e-07,
      "loss": 0.0392,
      "step": 944
    },
    {
      "clip_ratio/high_max": 0.0020497103323577903,
      "clip_ratio/high_mean": 0.0008110955805022968,
      "clip_ratio/low_mean": 0.0006500741073978133,
      "clip_ratio/low_min": 3.300243042758666e-05,
      "clip_ratio/region_mean": 0.0014611696969950572,
      "epoch": 0.08819977950055125,
      "grad_norm": 0.16115222871303558,
      "learning_rate": 2e-07,
      "loss": 0.0074,
      "step": 945
    },
    {
      "clip_ratio/high_max": 0.0019432917761150748,
      "clip_ratio/high_mean": 0.0007601940524182282,
      "clip_ratio/low_mean": 0.0005579055095950025,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013180995592847466,
      "epoch": 0.08829311260055184,
      "grad_norm": 0.14384886622428894,
      "learning_rate": 2e-07,
      "loss": -0.0176,
      "step": 946
    },
    {
      "clip_ratio/high_max": 0.0019829376233246876,
      "clip_ratio/high_mean": 0.0007140566958696581,
      "clip_ratio/low_mean": 0.0005057172093074769,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012197739088151138,
      "epoch": 0.08838644570055242,
      "grad_norm": 0.13894817233085632,
      "learning_rate": 2e-07,
      "loss": 0.0374,
      "step": 947
    },
    {
      "clip_ratio/high_max": 0.0015101680801308248,
      "clip_ratio/high_mean": 0.0006568424823854002,
      "clip_ratio/low_mean": 0.0006320193861029111,
      "clip_ratio/low_min": 8.233397693402367e-05,
      "clip_ratio/region_mean": 0.001288861869397806,
      "epoch": 0.088479778800553,
      "grad_norm": 0.14588098227977753,
      "learning_rate": 2e-07,
      "loss": 0.0289,
      "step": 948
    },
    {
      "clip_ratio/high_max": 0.0017957466625375673,
      "clip_ratio/high_mean": 0.0007309983657250996,
      "clip_ratio/low_mean": 0.0006404835730791092,
      "clip_ratio/low_min": 7.05012625985546e-05,
      "clip_ratio/region_mean": 0.0013714819397137035,
      "epoch": 0.08857311190055359,
      "grad_norm": 0.14395838975906372,
      "learning_rate": 2e-07,
      "loss": 0.0442,
      "step": 949
    },
    {
      "clip_ratio/high_max": 0.0015422342694364488,
      "clip_ratio/high_mean": 0.0006393678486347198,
      "clip_ratio/low_mean": 0.0005715184206565027,
      "clip_ratio/low_min": 1.9817986412817845e-05,
      "clip_ratio/region_mean": 0.0012108862792956643,
      "epoch": 0.08866644500055416,
      "grad_norm": 0.1354590803384781,
      "learning_rate": 2e-07,
      "loss": 0.0281,
      "step": 950
    },
    {
      "clip_ratio/high_max": 0.002122895653883461,
      "clip_ratio/high_mean": 0.0008152450664056232,
      "clip_ratio/low_mean": 0.0005847554530191701,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014000005394336767,
      "epoch": 0.08875977810055474,
      "grad_norm": 0.14133866131305695,
      "learning_rate": 2e-07,
      "loss": 0.0383,
      "step": 951
    },
    {
      "clip_ratio/high_max": 0.0018833830145013053,
      "clip_ratio/high_mean": 0.0008094449585769325,
      "clip_ratio/low_mean": 0.000754854501792579,
      "clip_ratio/low_min": 6.446466704801423e-05,
      "clip_ratio/region_mean": 0.0015642994767404161,
      "epoch": 0.08885311120055533,
      "grad_norm": 0.14470089972019196,
      "learning_rate": 2e-07,
      "loss": 0.0115,
      "step": 952
    },
    {
      "clip_ratio/high_max": 0.0018304592394997599,
      "clip_ratio/high_mean": 0.0007313287478609709,
      "clip_ratio/low_mean": 0.0006170689212012803,
      "clip_ratio/low_min": 1.1741499292838853e-05,
      "clip_ratio/region_mean": 0.0013483976508723572,
      "epoch": 0.08894644430055591,
      "grad_norm": 0.1376315802335739,
      "learning_rate": 2e-07,
      "loss": 0.0291,
      "step": 953
    },
    {
      "clip_ratio/high_max": 0.0016200674144783989,
      "clip_ratio/high_mean": 0.0006944479609956034,
      "clip_ratio/low_mean": 0.0006019007887516636,
      "clip_ratio/low_min": 1.0088780982187018e-05,
      "clip_ratio/region_mean": 0.0012963487206434365,
      "epoch": 0.0890397774005565,
      "grad_norm": 0.1357940286397934,
      "learning_rate": 2e-07,
      "loss": 0.005,
      "step": 954
    },
    {
      "clip_ratio/high_max": 0.0015606282177031972,
      "clip_ratio/high_mean": 0.0006005847390042618,
      "clip_ratio/low_mean": 0.0005312463963491609,
      "clip_ratio/low_min": 1.215480369864963e-05,
      "clip_ratio/region_mean": 0.0011318311371724121,
      "epoch": 0.08913311050055708,
      "grad_norm": 0.13029451668262482,
      "learning_rate": 2e-07,
      "loss": -0.0155,
      "step": 955
    },
    {
      "clip_ratio/high_max": 0.0017927694389072713,
      "clip_ratio/high_mean": 0.0007009340861259261,
      "clip_ratio/low_mean": 0.000638322975646588,
      "clip_ratio/low_min": 3.661770688268007e-05,
      "clip_ratio/region_mean": 0.0013392570508585777,
      "epoch": 0.08922644360055766,
      "grad_norm": 0.15635481476783752,
      "learning_rate": 2e-07,
      "loss": 0.0138,
      "step": 956
    },
    {
      "clip_ratio/high_max": 0.0020249964618415106,
      "clip_ratio/high_mean": 0.0007233247033582302,
      "clip_ratio/low_mean": 0.0006676106404484017,
      "clip_ratio/low_min": 2.1915166144026443e-05,
      "clip_ratio/region_mean": 0.0013909353365306742,
      "epoch": 0.08931977670055825,
      "grad_norm": 0.14826840162277222,
      "learning_rate": 2e-07,
      "loss": 0.0081,
      "step": 957
    },
    {
      "clip_ratio/high_max": 0.0015558527138637146,
      "clip_ratio/high_mean": 0.000683901034790324,
      "clip_ratio/low_mean": 0.0006652513166045537,
      "clip_ratio/low_min": 4.6724190724489745e-05,
      "clip_ratio/region_mean": 0.0013491523422999308,
      "epoch": 0.08941310980055883,
      "grad_norm": 0.144377201795578,
      "learning_rate": 2e-07,
      "loss": 0.0721,
      "step": 958
    },
    {
      "clip_ratio/high_max": 0.0017109764012275264,
      "clip_ratio/high_mean": 0.0006485602607426699,
      "clip_ratio/low_mean": 0.0007003342125244671,
      "clip_ratio/low_min": 3.6682793506770395e-05,
      "clip_ratio/region_mean": 0.0013488944678101689,
      "epoch": 0.08950644290055941,
      "grad_norm": 0.15789814293384552,
      "learning_rate": 2e-07,
      "loss": 0.0403,
      "step": 959
    },
    {
      "clip_ratio/high_max": 0.0018197315039287787,
      "clip_ratio/high_mean": 0.0007248766050906852,
      "clip_ratio/low_mean": 0.000606198409514036,
      "clip_ratio/low_min": 1.2729124136967584e-05,
      "clip_ratio/region_mean": 0.0013310750218806788,
      "epoch": 0.08959977600056,
      "grad_norm": 0.1431267261505127,
      "learning_rate": 2e-07,
      "loss": 0.0447,
      "step": 960
    },
    {
      "clip_ratio/high_max": 0.001526966687379172,
      "clip_ratio/high_mean": 0.0006514838023576885,
      "clip_ratio/low_mean": 0.0006190362310007913,
      "clip_ratio/low_min": 2.126883828168502e-05,
      "clip_ratio/region_mean": 0.0012705200242635328,
      "epoch": 0.08969310910056058,
      "grad_norm": 0.1427212804555893,
      "learning_rate": 2e-07,
      "loss": 0.0496,
      "step": 961
    },
    {
      "clip_ratio/high_max": 0.0015224709204630926,
      "clip_ratio/high_mean": 0.0006256362039493979,
      "clip_ratio/low_mean": 0.0006114253646956058,
      "clip_ratio/low_min": 3.632313018897548e-05,
      "clip_ratio/region_mean": 0.001237061576830456,
      "epoch": 0.08978644220056116,
      "grad_norm": 0.1447361409664154,
      "learning_rate": 2e-07,
      "loss": 0.0384,
      "step": 962
    },
    {
      "clip_ratio/high_max": 0.0017098629650718067,
      "clip_ratio/high_mean": 0.0006859605318823014,
      "clip_ratio/low_mean": 0.0005490450348588638,
      "clip_ratio/low_min": 2.386863070569234e-05,
      "clip_ratio/region_mean": 0.0012350055658316705,
      "epoch": 0.08987977530056175,
      "grad_norm": 1.3041605949401855,
      "learning_rate": 2e-07,
      "loss": 0.0336,
      "step": 963
    },
    {
      "clip_ratio/high_max": 0.0018612694220792037,
      "clip_ratio/high_mean": 0.0006058393337298185,
      "clip_ratio/low_mean": 0.0005430824721770477,
      "clip_ratio/low_min": 1.2744698324240744e-05,
      "clip_ratio/region_mean": 0.0011489218013593927,
      "epoch": 0.08997310840056233,
      "grad_norm": 0.13747842609882355,
      "learning_rate": 2e-07,
      "loss": 0.0623,
      "step": 964
    },
    {
      "clip_ratio/high_max": 0.0018122640140063595,
      "clip_ratio/high_mean": 0.0007432564925693441,
      "clip_ratio/low_mean": 0.0005991596044623293,
      "clip_ratio/low_min": 4.3590611312538385e-05,
      "clip_ratio/region_mean": 0.0013424160715658218,
      "epoch": 0.09006644150056292,
      "grad_norm": 0.1335994154214859,
      "learning_rate": 2e-07,
      "loss": 0.0045,
      "step": 965
    },
    {
      "clip_ratio/high_max": 0.001826896026614122,
      "clip_ratio/high_mean": 0.0007491540145565523,
      "clip_ratio/low_mean": 0.0006790126553823939,
      "clip_ratio/low_min": 2.9523570447054226e-05,
      "clip_ratio/region_mean": 0.0014281667063187342,
      "epoch": 0.0901597746005635,
      "grad_norm": 0.15497714281082153,
      "learning_rate": 2e-07,
      "loss": 0.0311,
      "step": 966
    },
    {
      "clip_ratio/high_max": 0.001737251728627598,
      "clip_ratio/high_mean": 0.0006904335887156776,
      "clip_ratio/low_mean": 0.0005882085733901476,
      "clip_ratio/low_min": 8.813500153337372e-05,
      "clip_ratio/region_mean": 0.0012786421793862246,
      "epoch": 0.09025310770056408,
      "grad_norm": 0.1342792510986328,
      "learning_rate": 2e-07,
      "loss": 0.0671,
      "step": 967
    },
    {
      "clip_ratio/high_max": 0.0018149910429201555,
      "clip_ratio/high_mean": 0.0007157150294005987,
      "clip_ratio/low_mean": 0.0005523388044821331,
      "clip_ratio/low_min": 4.987630745745264e-06,
      "clip_ratio/region_mean": 0.001268053809326375,
      "epoch": 0.09034644080056467,
      "grad_norm": 0.1338386982679367,
      "learning_rate": 2e-07,
      "loss": 0.0237,
      "step": 968
    },
    {
      "clip_ratio/high_max": 0.0017770997328625526,
      "clip_ratio/high_mean": 0.0007023067373665981,
      "clip_ratio/low_mean": 0.0005684520961040107,
      "clip_ratio/low_min": 1.171289386547869e-05,
      "clip_ratio/region_mean": 0.0012707587775366846,
      "epoch": 0.09043977390056525,
      "grad_norm": 0.14405693113803864,
      "learning_rate": 2e-07,
      "loss": 0.0249,
      "step": 969
    },
    {
      "clip_ratio/high_max": 0.001679560162301641,
      "clip_ratio/high_mean": 0.0006905743957759114,
      "clip_ratio/low_mean": 0.0005830924365000101,
      "clip_ratio/low_min": 3.5374699109524954e-05,
      "clip_ratio/region_mean": 0.0012736668359139003,
      "epoch": 0.09053310700056583,
      "grad_norm": 0.8259018063545227,
      "learning_rate": 2e-07,
      "loss": 0.025,
      "step": 970
    },
    {
      "clip_ratio/high_max": 0.0017475907079642639,
      "clip_ratio/high_mean": 0.0007005008719715988,
      "clip_ratio/low_mean": 0.0005397357708716299,
      "clip_ratio/low_min": 2.332093754375819e-05,
      "clip_ratio/region_mean": 0.0012402366410242394,
      "epoch": 0.09062644010056642,
      "grad_norm": 0.14208810031414032,
      "learning_rate": 2e-07,
      "loss": 0.0035,
      "step": 971
    },
    {
      "clip_ratio/high_max": 0.0016138025239342824,
      "clip_ratio/high_mean": 0.0006210274350451073,
      "clip_ratio/low_mean": 0.0007686681119594141,
      "clip_ratio/low_min": 7.396710861939937e-05,
      "clip_ratio/region_mean": 0.0013896955097152386,
      "epoch": 0.090719773200567,
      "grad_norm": 0.15578195452690125,
      "learning_rate": 2e-07,
      "loss": 0.0477,
      "step": 972
    },
    {
      "clip_ratio/high_max": 0.0016197395088966005,
      "clip_ratio/high_mean": 0.0006766420756321168,
      "clip_ratio/low_mean": 0.0005795812576252501,
      "clip_ratio/low_min": 2.3780301489750855e-05,
      "clip_ratio/region_mean": 0.0012562233459902927,
      "epoch": 0.09081310630056758,
      "grad_norm": 0.14359670877456665,
      "learning_rate": 2e-07,
      "loss": 0.0479,
      "step": 973
    },
    {
      "clip_ratio/high_max": 0.002236423817521427,
      "clip_ratio/high_mean": 0.0007784818935760995,
      "clip_ratio/low_mean": 0.00065988097776426,
      "clip_ratio/low_min": 4.9225084694626275e-05,
      "clip_ratio/region_mean": 0.0014383628949872218,
      "epoch": 0.09090643940056817,
      "grad_norm": 0.1559831202030182,
      "learning_rate": 2e-07,
      "loss": 0.0336,
      "step": 974
    },
    {
      "clip_ratio/high_max": 0.0017459721348132007,
      "clip_ratio/high_mean": 0.0007116125016182195,
      "clip_ratio/low_mean": 0.0005034045825595967,
      "clip_ratio/low_min": 1.4509576431009918e-05,
      "clip_ratio/region_mean": 0.0012150170550739858,
      "epoch": 0.09099977250056875,
      "grad_norm": 0.14853475987911224,
      "learning_rate": 2e-07,
      "loss": -0.0235,
      "step": 975
    },
    {
      "clip_ratio/high_max": 0.0019015687321370933,
      "clip_ratio/high_mean": 0.000772454404796008,
      "clip_ratio/low_mean": 0.0006130928877610131,
      "clip_ratio/low_min": 6.95139578965609e-06,
      "clip_ratio/region_mean": 0.0013855473043804523,
      "epoch": 0.09109310560056934,
      "grad_norm": 0.15120293200016022,
      "learning_rate": 2e-07,
      "loss": 0.0229,
      "step": 976
    },
    {
      "clip_ratio/high_max": 0.0015068525608512573,
      "clip_ratio/high_mean": 0.0006119116042100359,
      "clip_ratio/low_mean": 0.0006469875588663854,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012588991630764212,
      "epoch": 0.09118643870056992,
      "grad_norm": 0.14164192974567413,
      "learning_rate": 2e-07,
      "loss": 0.0475,
      "step": 977
    },
    {
      "clip_ratio/high_max": 0.0017150776475318708,
      "clip_ratio/high_mean": 0.0007344686237047426,
      "clip_ratio/low_mean": 0.0006252166194826714,
      "clip_ratio/low_min": 8.17527779872762e-06,
      "clip_ratio/region_mean": 0.0013596852477348875,
      "epoch": 0.0912797718005705,
      "grad_norm": 0.143987238407135,
      "learning_rate": 2e-07,
      "loss": 0.0031,
      "step": 978
    },
    {
      "clip_ratio/high_max": 0.0016577611313550733,
      "clip_ratio/high_mean": 0.0007134181360015646,
      "clip_ratio/low_mean": 0.0005907669346925104,
      "clip_ratio/low_min": 5.184766268939711e-05,
      "clip_ratio/region_mean": 0.0013041850907029584,
      "epoch": 0.09137310490057109,
      "grad_norm": 0.14742669463157654,
      "learning_rate": 2e-07,
      "loss": 0.0162,
      "step": 979
    },
    {
      "clip_ratio/high_max": 0.0019714172631211113,
      "clip_ratio/high_mean": 0.0007283400027517928,
      "clip_ratio/low_mean": 0.0006567300588358194,
      "clip_ratio/low_min": 4.029608408018248e-05,
      "clip_ratio/region_mean": 0.0013850700524926651,
      "epoch": 0.09146643800057166,
      "grad_norm": 0.16006894409656525,
      "learning_rate": 2e-07,
      "loss": 0.0347,
      "step": 980
    },
    {
      "clip_ratio/high_max": 0.00166111431644822,
      "clip_ratio/high_mean": 0.0007188373247117852,
      "clip_ratio/low_mean": 0.0006070865529181901,
      "clip_ratio/low_min": 2.476297777320724e-05,
      "clip_ratio/region_mean": 0.0013259238803584594,
      "epoch": 0.09155977110057224,
      "grad_norm": 0.144860178232193,
      "learning_rate": 2e-07,
      "loss": 0.0599,
      "step": 981
    },
    {
      "clip_ratio/high_max": 0.0017787624110496836,
      "clip_ratio/high_mean": 0.0006380644599630614,
      "clip_ratio/low_mean": 0.0005485832753038267,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0011866476852446795,
      "epoch": 0.09165310420057284,
      "grad_norm": 0.13645587861537933,
      "learning_rate": 2e-07,
      "loss": -0.0041,
      "step": 982
    },
    {
      "clip_ratio/high_max": 0.0016415845420851838,
      "clip_ratio/high_mean": 0.0007056201520754257,
      "clip_ratio/low_mean": 0.0006400940783350961,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001345714208582649,
      "epoch": 0.09174643730057341,
      "grad_norm": 0.14309969544410706,
      "learning_rate": 2e-07,
      "loss": -0.0419,
      "step": 983
    },
    {
      "clip_ratio/high_max": 0.0018460395440342836,
      "clip_ratio/high_mean": 0.0007390852915705182,
      "clip_ratio/low_mean": 0.0006256327988012345,
      "clip_ratio/low_min": 9.77937725110678e-06,
      "clip_ratio/region_mean": 0.001364718107652152,
      "epoch": 0.09183977040057399,
      "grad_norm": 0.16194909811019897,
      "learning_rate": 2e-07,
      "loss": 0.0488,
      "step": 984
    },
    {
      "clip_ratio/high_max": 0.0016744554959586821,
      "clip_ratio/high_mean": 0.000622940982793807,
      "clip_ratio/low_mean": 0.0005605103960988345,
      "clip_ratio/low_min": 2.8809553441533353e-05,
      "clip_ratio/region_mean": 0.0011834513570647687,
      "epoch": 0.09193310350057458,
      "grad_norm": 0.13443738222122192,
      "learning_rate": 2e-07,
      "loss": 0.0267,
      "step": 985
    },
    {
      "clip_ratio/high_max": 0.0014915238753019366,
      "clip_ratio/high_mean": 0.0005742997709603515,
      "clip_ratio/low_mean": 0.0005802489740744932,
      "clip_ratio/low_min": 2.3241779217642033e-05,
      "clip_ratio/region_mean": 0.00115454872866394,
      "epoch": 0.09202643660057516,
      "grad_norm": 0.13556648790836334,
      "learning_rate": 2e-07,
      "loss": 0.0538,
      "step": 986
    },
    {
      "clip_ratio/high_max": 0.0017074177194444928,
      "clip_ratio/high_mean": 0.0007071668587741442,
      "clip_ratio/low_mean": 0.0006908290124556515,
      "clip_ratio/low_min": 7.401355560432421e-05,
      "clip_ratio/region_mean": 0.001397995845763944,
      "epoch": 0.09211976970057575,
      "grad_norm": 0.22078122198581696,
      "learning_rate": 2e-07,
      "loss": 0.0436,
      "step": 987
    },
    {
      "clip_ratio/high_max": 0.0018324677294003777,
      "clip_ratio/high_mean": 0.0007154002159950323,
      "clip_ratio/low_mean": 0.0006683971587335691,
      "clip_ratio/low_min": 4.0759900002740324e-05,
      "clip_ratio/region_mean": 0.0013837973892805167,
      "epoch": 0.09221310280057633,
      "grad_norm": 0.1451905369758606,
      "learning_rate": 2e-07,
      "loss": 0.0278,
      "step": 988
    },
    {
      "clip_ratio/high_max": 0.0020742138804052956,
      "clip_ratio/high_mean": 0.0008382299147342565,
      "clip_ratio/low_mean": 0.0006021280514687533,
      "clip_ratio/low_min": 3.286960145487683e-05,
      "clip_ratio/region_mean": 0.0014403579698409885,
      "epoch": 0.09230643590057691,
      "grad_norm": 0.14585813879966736,
      "learning_rate": 2e-07,
      "loss": -0.0088,
      "step": 989
    },
    {
      "clip_ratio/high_max": 0.0016401061075157486,
      "clip_ratio/high_mean": 0.0006616678638238227,
      "clip_ratio/low_mean": 0.0007205850324680796,
      "clip_ratio/low_min": 3.407484200579347e-05,
      "clip_ratio/region_mean": 0.0013822528962919023,
      "epoch": 0.0923997690005775,
      "grad_norm": 0.21004173159599304,
      "learning_rate": 2e-07,
      "loss": 0.0501,
      "step": 990
    },
    {
      "clip_ratio/high_max": 0.001992966113903094,
      "clip_ratio/high_mean": 0.0007904664817033336,
      "clip_ratio/low_mean": 0.0006689060101052746,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0014593724445148837,
      "epoch": 0.09249310210057808,
      "grad_norm": 0.17767773568630219,
      "learning_rate": 2e-07,
      "loss": 0.0468,
      "step": 991
    },
    {
      "clip_ratio/high_max": 0.0017025673387252027,
      "clip_ratio/high_mean": 0.0006677370520264958,
      "clip_ratio/low_mean": 0.000675117062201025,
      "clip_ratio/low_min": 4.993695711164037e-05,
      "clip_ratio/region_mean": 0.0013428540805762168,
      "epoch": 0.09258643520057866,
      "grad_norm": 0.16823220252990723,
      "learning_rate": 2e-07,
      "loss": 0.0569,
      "step": 992
    },
    {
      "clip_ratio/high_max": 0.001995711438212311,
      "clip_ratio/high_mean": 0.0007550971040473087,
      "clip_ratio/low_mean": 0.0007045860766083933,
      "clip_ratio/low_min": 3.3524544051033445e-05,
      "clip_ratio/region_mean": 0.0014596832006645855,
      "epoch": 0.09267976830057925,
      "grad_norm": 0.6557042002677917,
      "learning_rate": 2e-07,
      "loss": 0.0396,
      "step": 993
    },
    {
      "clip_ratio/high_max": 0.0015517973006353714,
      "clip_ratio/high_mean": 0.0006013079510012176,
      "clip_ratio/low_mean": 0.0007357747108471813,
      "clip_ratio/low_min": 4.014886644654325e-05,
      "clip_ratio/region_mean": 0.0013370826782193035,
      "epoch": 0.09277310140057983,
      "grad_norm": 0.15774820744991302,
      "learning_rate": 2e-07,
      "loss": 0.0793,
      "step": 994
    },
    {
      "clip_ratio/high_max": 0.00193346312516951,
      "clip_ratio/high_mean": 0.0006697505014017224,
      "clip_ratio/low_mean": 0.0006344943794829305,
      "clip_ratio/low_min": 3.7387299016700126e-05,
      "clip_ratio/region_mean": 0.001304244831771939,
      "epoch": 0.09286643450058042,
      "grad_norm": 0.15775588154792786,
      "learning_rate": 2e-07,
      "loss": 0.0672,
      "step": 995
    },
    {
      "clip_ratio/high_max": 0.0015834565965633374,
      "clip_ratio/high_mean": 0.0006258201337914215,
      "clip_ratio/low_mean": 0.0007221523264888674,
      "clip_ratio/low_min": 0.00011272557094343938,
      "clip_ratio/region_mean": 0.0013479724584612995,
      "epoch": 0.092959767600581,
      "grad_norm": 0.18795281648635864,
      "learning_rate": 2e-07,
      "loss": 0.1025,
      "step": 996
    },
    {
      "clip_ratio/high_max": 0.0020258818367437925,
      "clip_ratio/high_mean": 0.0007455363183908048,
      "clip_ratio/low_mean": 0.0005791101830254775,
      "clip_ratio/low_min": 6.646107976848725e-06,
      "clip_ratio/region_mean": 0.001324646465945989,
      "epoch": 0.09305310070058158,
      "grad_norm": 0.17034779489040375,
      "learning_rate": 2e-07,
      "loss": 0.0394,
      "step": 997
    },
    {
      "clip_ratio/high_max": 0.0017022054889821447,
      "clip_ratio/high_mean": 0.0006251930335565703,
      "clip_ratio/low_mean": 0.0007103255993570201,
      "clip_ratio/low_min": 1.2003072697552852e-05,
      "clip_ratio/region_mean": 0.0013355186201806646,
      "epoch": 0.09314643380058217,
      "grad_norm": 0.1744387447834015,
      "learning_rate": 2e-07,
      "loss": 0.0541,
      "step": 998
    },
    {
      "clip_ratio/high_max": 0.0017306126392213628,
      "clip_ratio/high_mean": 0.0008039728636504151,
      "clip_ratio/low_mean": 0.00067266517180542,
      "clip_ratio/low_min": 7.050772228467395e-05,
      "clip_ratio/region_mean": 0.0014766380190849304,
      "epoch": 0.09323976690058275,
      "grad_norm": 0.16662435233592987,
      "learning_rate": 2e-07,
      "loss": 0.0177,
      "step": 999
    },
    {
      "clip_ratio/high_max": 0.0015837332321098074,
      "clip_ratio/high_mean": 0.0006577183075933135,
      "clip_ratio/low_mean": 0.0005895754638913786,
      "clip_ratio/low_min": 2.6663136850402225e-05,
      "clip_ratio/region_mean": 0.001247293796041049,
      "epoch": 0.09333310000058333,
      "grad_norm": 0.16519631445407867,
      "learning_rate": 2e-07,
      "loss": 0.0312,
      "step": 1000
    },
    {
      "clip_ratio/high_max": 0.0018397188614471816,
      "clip_ratio/high_mean": 0.0006786323519918369,
      "clip_ratio/low_mean": 0.0007147982960304944,
      "clip_ratio/low_min": 3.5099701563012786e-05,
      "clip_ratio/region_mean": 0.0013934306480223313,
      "epoch": 0.09342643310058392,
      "grad_norm": 0.15442317724227905,
      "learning_rate": 2e-07,
      "loss": 0.0294,
      "step": 1001
    },
    {
      "clip_ratio/high_max": 0.0016074186460173223,
      "clip_ratio/high_mean": 0.0007432934926328016,
      "clip_ratio/low_mean": 0.0006852986152807716,
      "clip_ratio/low_min": 9.945174133463297e-05,
      "clip_ratio/region_mean": 0.0014285920697147958,
      "epoch": 0.0935197662005845,
      "grad_norm": 0.16437748074531555,
      "learning_rate": 2e-07,
      "loss": 0.027,
      "step": 1002
    },
    {
      "clip_ratio/high_max": 0.0017652895166975213,
      "clip_ratio/high_mean": 0.0007256365670400555,
      "clip_ratio/low_mean": 0.0006940888197277673,
      "clip_ratio/low_min": 3.884432226186618e-05,
      "clip_ratio/region_mean": 0.0014197253804013599,
      "epoch": 0.09361309930058508,
      "grad_norm": 0.15147742629051208,
      "learning_rate": 2e-07,
      "loss": 0.0209,
      "step": 1003
    },
    {
      "clip_ratio/high_max": 0.0015656403338653035,
      "clip_ratio/high_mean": 0.0006210986393853091,
      "clip_ratio/low_mean": 0.0006704529841954354,
      "clip_ratio/low_min": 1.7858314095064998e-05,
      "clip_ratio/region_mean": 0.0012915516417706385,
      "epoch": 0.09370643240058567,
      "grad_norm": 0.1535167396068573,
      "learning_rate": 2e-07,
      "loss": 0.0281,
      "step": 1004
    },
    {
      "clip_ratio/high_max": 0.0017470990351284854,
      "clip_ratio/high_mean": 0.0007216647591121728,
      "clip_ratio/low_mean": 0.0006341245734802214,
      "clip_ratio/low_min": 2.708146303120884e-05,
      "clip_ratio/region_mean": 0.0013557892962126061,
      "epoch": 0.09379976550058625,
      "grad_norm": 0.16980122029781342,
      "learning_rate": 2e-07,
      "loss": 0.0224,
      "step": 1005
    },
    {
      "clip_ratio/high_max": 0.0014837493290542625,
      "clip_ratio/high_mean": 0.0006286433053901419,
      "clip_ratio/low_mean": 0.0006663286676484859,
      "clip_ratio/low_min": 3.884534271492157e-05,
      "clip_ratio/region_mean": 0.0012949719566677231,
      "epoch": 0.09389309860058684,
      "grad_norm": 0.15000736713409424,
      "learning_rate": 2e-07,
      "loss": 0.0008,
      "step": 1006
    },
    {
      "clip_ratio/high_max": 0.00159943537437357,
      "clip_ratio/high_mean": 0.000727240692867781,
      "clip_ratio/low_mean": 0.0005816931261506397,
      "clip_ratio/low_min": 4.880149026575964e-05,
      "clip_ratio/region_mean": 0.0013089338499412406,
      "epoch": 0.09398643170058742,
      "grad_norm": 0.2467365562915802,
      "learning_rate": 2e-07,
      "loss": 0.0026,
      "step": 1007
    },
    {
      "clip_ratio/high_max": 0.001948192177223973,
      "clip_ratio/high_mean": 0.0007603163394378498,
      "clip_ratio/low_mean": 0.0007879956629039953,
      "clip_ratio/low_min": 5.997062362439465e-05,
      "clip_ratio/region_mean": 0.001548312015074771,
      "epoch": 0.094079764800588,
      "grad_norm": 0.19664718210697174,
      "learning_rate": 2e-07,
      "loss": 0.0386,
      "step": 1008
    },
    {
      "clip_ratio/high_max": 0.0014701535037602298,
      "clip_ratio/high_mean": 0.0006556087682838552,
      "clip_ratio/low_mean": 0.0007301270270545501,
      "clip_ratio/low_min": 2.053219395747874e-05,
      "clip_ratio/region_mean": 0.0013857358280802146,
      "epoch": 0.09417309790058859,
      "grad_norm": 0.16688448190689087,
      "learning_rate": 2e-07,
      "loss": 0.0373,
      "step": 1009
    },
    {
      "clip_ratio/high_max": 0.001752082313032588,
      "clip_ratio/high_mean": 0.0008138333596434677,
      "clip_ratio/low_mean": 0.0006142715483292704,
      "clip_ratio/low_min": 4.132232425035909e-05,
      "clip_ratio/region_mean": 0.0014281049407145474,
      "epoch": 0.09426643100058917,
      "grad_norm": 0.1566309928894043,
      "learning_rate": 2e-07,
      "loss": -0.0074,
      "step": 1010
    },
    {
      "clip_ratio/high_max": 0.0021022875807830133,
      "clip_ratio/high_mean": 0.0008798499784461455,
      "clip_ratio/low_mean": 0.0006395479522325331,
      "clip_ratio/low_min": 3.419388758629793e-05,
      "clip_ratio/region_mean": 0.0015193979088508058,
      "epoch": 0.09435976410058974,
      "grad_norm": 15.408679008483887,
      "learning_rate": 2e-07,
      "loss": -0.0012,
      "step": 1011
    },
    {
      "clip_ratio/high_max": 0.0022488931062980555,
      "clip_ratio/high_mean": 0.0008231203883042326,
      "clip_ratio/low_mean": 0.0007045458714856068,
      "clip_ratio/low_min": 6.297800791799091e-05,
      "clip_ratio/region_mean": 0.0015276662452379242,
      "epoch": 0.09445309720059034,
      "grad_norm": 0.17172129452228546,
      "learning_rate": 2e-07,
      "loss": 0.0516,
      "step": 1012
    },
    {
      "clip_ratio/high_max": 0.001885849102109205,
      "clip_ratio/high_mean": 0.0007454884434991982,
      "clip_ratio/low_mean": 0.0007858692370064091,
      "clip_ratio/low_min": 8.737896678212564e-05,
      "clip_ratio/region_mean": 0.0015313577387132682,
      "epoch": 0.09454643030059091,
      "grad_norm": 0.21107324957847595,
      "learning_rate": 2e-07,
      "loss": 0.0899,
      "step": 1013
    },
    {
      "clip_ratio/high_max": 0.002142695702787023,
      "clip_ratio/high_mean": 0.0008224787079598173,
      "clip_ratio/low_mean": 0.0007909259602456586,
      "clip_ratio/low_min": 6.9275625719456e-05,
      "clip_ratio/region_mean": 0.0016134046236402355,
      "epoch": 0.09463976340059149,
      "grad_norm": 0.17175063490867615,
      "learning_rate": 2e-07,
      "loss": 0.0006,
      "step": 1014
    },
    {
      "clip_ratio/high_max": 0.0017917125369422138,
      "clip_ratio/high_mean": 0.0007654903401999036,
      "clip_ratio/low_mean": 0.0008358193044841755,
      "clip_ratio/low_min": 5.6921004215837456e-05,
      "clip_ratio/region_mean": 0.001601309617399238,
      "epoch": 0.09473309650059208,
      "grad_norm": 0.16896438598632812,
      "learning_rate": 2e-07,
      "loss": 0.0602,
      "step": 1015
    },
    {
      "clip_ratio/high_max": 0.0015088408872543368,
      "clip_ratio/high_mean": 0.000706128064848599,
      "clip_ratio/low_mean": 0.0007358761886280263,
      "clip_ratio/low_min": 6.021507488185307e-05,
      "clip_ratio/region_mean": 0.001442004260752583,
      "epoch": 0.09482642960059266,
      "grad_norm": 0.18385401368141174,
      "learning_rate": 2e-07,
      "loss": 0.0075,
      "step": 1016
    },
    {
      "clip_ratio/high_max": 0.0018926592892967165,
      "clip_ratio/high_mean": 0.00077394840263878,
      "clip_ratio/low_mean": 0.0006563860533788102,
      "clip_ratio/low_min": 6.40326338725572e-05,
      "clip_ratio/region_mean": 0.0014303344651125371,
      "epoch": 0.09491976270059325,
      "grad_norm": 0.1653454303741455,
      "learning_rate": 2e-07,
      "loss": 0.0077,
      "step": 1017
    },
    {
      "clip_ratio/high_max": 0.0017751133636920713,
      "clip_ratio/high_mean": 0.0007377612637355924,
      "clip_ratio/low_mean": 0.0007535277945862617,
      "clip_ratio/low_min": 9.821678941079881e-05,
      "clip_ratio/region_mean": 0.0014912890328560024,
      "epoch": 0.09501309580059383,
      "grad_norm": 0.1792379915714264,
      "learning_rate": 2e-07,
      "loss": 0.0602,
      "step": 1018
    },
    {
      "clip_ratio/high_max": 0.0018354958374402486,
      "clip_ratio/high_mean": 0.0007327909297600854,
      "clip_ratio/low_mean": 0.0007791606894897996,
      "clip_ratio/low_min": 9.465854100199067e-05,
      "clip_ratio/region_mean": 0.0015119516210688744,
      "epoch": 0.09510642890059441,
      "grad_norm": 0.22554445266723633,
      "learning_rate": 2e-07,
      "loss": 0.0382,
      "step": 1019
    },
    {
      "clip_ratio/high_max": 0.0019489285623421893,
      "clip_ratio/high_mean": 0.0007125211504899198,
      "clip_ratio/low_mean": 0.0006913592633281951,
      "clip_ratio/low_min": 7.708815246587619e-05,
      "clip_ratio/region_mean": 0.001403880407451652,
      "epoch": 0.095199762000595,
      "grad_norm": 0.4581732451915741,
      "learning_rate": 2e-07,
      "loss": 0.005,
      "step": 1020
    },
    {
      "clip_ratio/high_max": 0.0018844361020455835,
      "clip_ratio/high_mean": 0.0007366990582795552,
      "clip_ratio/low_mean": 0.000903823612134147,
      "clip_ratio/low_min": 1.6237983800238e-05,
      "clip_ratio/region_mean": 0.0016405226597271394,
      "epoch": 0.09529309510059558,
      "grad_norm": 0.17599578201770782,
      "learning_rate": 2e-07,
      "loss": 0.0516,
      "step": 1021
    },
    {
      "clip_ratio/high_max": 0.0019190964958397672,
      "clip_ratio/high_mean": 0.0007706724791205488,
      "clip_ratio/low_mean": 0.0008597128071414772,
      "clip_ratio/low_min": 2.5530397579132114e-05,
      "clip_ratio/region_mean": 0.0016303852535202168,
      "epoch": 0.09538642820059616,
      "grad_norm": 0.19194719195365906,
      "learning_rate": 2e-07,
      "loss": 0.0501,
      "step": 1022
    },
    {
      "clip_ratio/high_max": 0.0024685868629603647,
      "clip_ratio/high_mean": 0.0008620815242466051,
      "clip_ratio/low_mean": 0.0007094381926435744,
      "clip_ratio/low_min": 4.1917113776435144e-05,
      "clip_ratio/region_mean": 0.0015715197296231054,
      "epoch": 0.09547976130059675,
      "grad_norm": 0.187911719083786,
      "learning_rate": 2e-07,
      "loss": 0.0019,
      "step": 1023
    },
    {
      "clip_ratio/high_max": 0.0018579211828182451,
      "clip_ratio/high_mean": 0.0008154256738635013,
      "clip_ratio/low_mean": 0.0007594119797431631,
      "clip_ratio/low_min": 2.96014804916922e-05,
      "clip_ratio/region_mean": 0.0015748375881230459,
      "epoch": 0.09557309440059733,
      "grad_norm": 0.1773652583360672,
      "learning_rate": 2e-07,
      "loss": 0.0377,
      "step": 1024
    },
    {
      "clip_ratio/high_max": 0.0013976690242998302,
      "clip_ratio/high_mean": 0.0005390550768424873,
      "clip_ratio/low_mean": 0.000551065691979602,
      "clip_ratio/low_min": 2.2425547285820358e-05,
      "clip_ratio/region_mean": 0.0010901207533606794,
      "completions/clipped_ratio": 0.02099609375,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4088.0,
      "completions/mean_length": 690.4118041992188,
      "completions/mean_terminated_length": 617.3742065429688,
      "completions/min_length": 83.0,
      "completions/min_terminated_length": 83.0,
      "epoch": 0.09566642750059791,
      "grad_norm": 0.13995230197906494,
      "learning_rate": 2e-07,
      "loss": 0.0476,
      "num_tokens": 773930701.0,
      "reward": 0.5898699164390564,
      "reward_std": 0.17693860828876495,
      "rewards/simpleverify_reward/mean": 0.5898699164390564,
      "rewards/simpleverify_reward/std": 0.4918592870235443,
      "step": 1025
    },
    {
      "clip_ratio/high_max": 0.0013708305050386116,
      "clip_ratio/high_mean": 0.0005564877110373345,
      "clip_ratio/low_mean": 0.0005445496390166227,
      "clip_ratio/low_min": 3.373268373252358e-05,
      "clip_ratio/region_mean": 0.0011010373491444625,
      "epoch": 0.0957597606005985,
      "grad_norm": 0.14929437637329102,
      "learning_rate": 2e-07,
      "loss": 0.0585,
      "step": 1026
    },
    {
      "clip_ratio/high_max": 0.0017153605149360374,
      "clip_ratio/high_mean": 0.0006554219262397964,
      "clip_ratio/low_mean": 0.0004980738613085123,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0011534957666299306,
      "epoch": 0.09585309370059908,
      "grad_norm": 0.14730463922023773,
      "learning_rate": 2e-07,
      "loss": -0.0194,
      "step": 1027
    },
    {
      "clip_ratio/high_max": 0.00166615027046646,
      "clip_ratio/high_mean": 0.0007327789026021492,
      "clip_ratio/low_mean": 0.0007074002787703648,
      "clip_ratio/low_min": 3.99471064156387e-05,
      "clip_ratio/region_mean": 0.0014401792286662385,
      "epoch": 0.09594642680059967,
      "grad_norm": 0.15482264757156372,
      "learning_rate": 2e-07,
      "loss": 0.0075,
      "step": 1028
    },
    {
      "clip_ratio/high_max": 0.0014134803204797208,
      "clip_ratio/high_mean": 0.0005714197950510425,
      "clip_ratio/low_mean": 0.000509914338181261,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0010813341032189783,
      "epoch": 0.09603975990060025,
      "grad_norm": 0.13401024043560028,
      "learning_rate": 2e-07,
      "loss": 0.0361,
      "step": 1029
    },
    {
      "clip_ratio/high_max": 0.0015113866866158787,
      "clip_ratio/high_mean": 0.0005519047317648074,
      "clip_ratio/low_mean": 0.0006340970085148001,
      "clip_ratio/low_min": 5.568407777900575e-05,
      "clip_ratio/region_mean": 0.0011860017657454591,
      "epoch": 0.09613309300060083,
      "grad_norm": 0.15947654843330383,
      "learning_rate": 2e-07,
      "loss": 0.0641,
      "step": 1030
    },
    {
      "clip_ratio/high_max": 0.0017595314857317135,
      "clip_ratio/high_mean": 0.0006714881651532778,
      "clip_ratio/low_mean": 0.0005206111136430991,
      "clip_ratio/low_min": 4.037277994939359e-05,
      "clip_ratio/region_mean": 0.0011920992837985978,
      "epoch": 0.09622642610060142,
      "grad_norm": 0.14622628688812256,
      "learning_rate": 2e-07,
      "loss": 0.0063,
      "step": 1031
    },
    {
      "clip_ratio/high_max": 0.0016829784653964452,
      "clip_ratio/high_mean": 0.000701106313499622,
      "clip_ratio/low_mean": 0.0005317854620443541,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012328918164712377,
      "epoch": 0.096319759200602,
      "grad_norm": 0.15084731578826904,
      "learning_rate": 2e-07,
      "loss": 0.0151,
      "step": 1032
    },
    {
      "clip_ratio/high_max": 0.001985624199733138,
      "clip_ratio/high_mean": 0.0006370335358951706,
      "clip_ratio/low_mean": 0.000595378189245821,
      "clip_ratio/low_min": 3.0260463972808793e-05,
      "clip_ratio/region_mean": 0.0012324117051321082,
      "epoch": 0.09641309230060258,
      "grad_norm": 0.1505519449710846,
      "learning_rate": 2e-07,
      "loss": 0.0456,
      "step": 1033
    },
    {
      "clip_ratio/high_max": 0.0015977936636772938,
      "clip_ratio/high_mean": 0.0006431656383938389,
      "clip_ratio/low_mean": 0.0004967154718542588,
      "clip_ratio/low_min": 3.102475056948606e-05,
      "clip_ratio/region_mean": 0.0011398811402614228,
      "epoch": 0.09650642540060317,
      "grad_norm": 0.1491953581571579,
      "learning_rate": 2e-07,
      "loss": 0.0158,
      "step": 1034
    },
    {
      "clip_ratio/high_max": 0.0015207495071081212,
      "clip_ratio/high_mean": 0.0006131693971838104,
      "clip_ratio/low_mean": 0.0005767561560787726,
      "clip_ratio/low_min": 1.4010312042955775e-05,
      "clip_ratio/region_mean": 0.001189925535072689,
      "epoch": 0.09659975850060375,
      "grad_norm": 0.15639768540859222,
      "learning_rate": 2e-07,
      "loss": 0.0477,
      "step": 1035
    },
    {
      "clip_ratio/high_max": 0.0015935265109874308,
      "clip_ratio/high_mean": 0.0005967850875094882,
      "clip_ratio/low_mean": 0.0005910684585614945,
      "clip_ratio/low_min": 4.3231441850366537e-05,
      "clip_ratio/region_mean": 0.001187853551527951,
      "epoch": 0.09669309160060433,
      "grad_norm": 0.18650835752487183,
      "learning_rate": 2e-07,
      "loss": 0.069,
      "step": 1036
    },
    {
      "clip_ratio/high_max": 0.0017091749359678943,
      "clip_ratio/high_mean": 0.0007145257477532141,
      "clip_ratio/low_mean": 0.0005595102029474219,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001274035923415795,
      "epoch": 0.09678642470060492,
      "grad_norm": 0.24907439947128296,
      "learning_rate": 2e-07,
      "loss": -0.0216,
      "step": 1037
    },
    {
      "clip_ratio/high_max": 0.0017085937906813342,
      "clip_ratio/high_mean": 0.0005706035117327701,
      "clip_ratio/low_mean": 0.0005487108974193688,
      "clip_ratio/low_min": 2.8067012863175478e-05,
      "clip_ratio/region_mean": 0.0011193144055141602,
      "epoch": 0.0968797578006055,
      "grad_norm": 0.3066822290420532,
      "learning_rate": 2e-07,
      "loss": 0.0485,
      "step": 1038
    },
    {
      "clip_ratio/high_max": 0.0019128457097394858,
      "clip_ratio/high_mean": 0.0006901382630530861,
      "clip_ratio/low_mean": 0.0005473594628710998,
      "clip_ratio/low_min": 2.7933224373555277e-05,
      "clip_ratio/region_mean": 0.0012374977413855959,
      "epoch": 0.09697309090060609,
      "grad_norm": 0.14152072370052338,
      "learning_rate": 2e-07,
      "loss": 0.0242,
      "step": 1039
    },
    {
      "clip_ratio/high_max": 0.0019373311988601927,
      "clip_ratio/high_mean": 0.0007144366827560589,
      "clip_ratio/low_mean": 0.0006691817761748098,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001383618469844805,
      "epoch": 0.09706642400060667,
      "grad_norm": 0.15431392192840576,
      "learning_rate": 2e-07,
      "loss": 0.0244,
      "step": 1040
    },
    {
      "clip_ratio/high_max": 0.0015983971788955387,
      "clip_ratio/high_mean": 0.0006523084957734682,
      "clip_ratio/low_mean": 0.0004925415369143593,
      "clip_ratio/low_min": 1.3309198948263656e-05,
      "clip_ratio/region_mean": 0.001144850073615089,
      "epoch": 0.09715975710060724,
      "grad_norm": 0.12544314563274384,
      "learning_rate": 2e-07,
      "loss": 0.0304,
      "step": 1041
    },
    {
      "clip_ratio/high_max": 0.0016927644610404968,
      "clip_ratio/high_mean": 0.0006322097342490451,
      "clip_ratio/low_mean": 0.0005311445547704352,
      "clip_ratio/low_min": 3.0010249247425236e-05,
      "clip_ratio/region_mean": 0.0011633543072093744,
      "epoch": 0.09725309020060784,
      "grad_norm": 0.15861967206001282,
      "learning_rate": 2e-07,
      "loss": 0.037,
      "step": 1042
    },
    {
      "clip_ratio/high_max": 0.0019728181177924853,
      "clip_ratio/high_mean": 0.0007186180155258626,
      "clip_ratio/low_mean": 0.000612304139394837,
      "clip_ratio/low_min": 1.2303149560466409e-05,
      "clip_ratio/region_mean": 0.0013309221394592896,
      "epoch": 0.09734642330060841,
      "grad_norm": 0.1456659436225891,
      "learning_rate": 2e-07,
      "loss": 0.0043,
      "step": 1043
    },
    {
      "clip_ratio/high_max": 0.001429147527232999,
      "clip_ratio/high_mean": 0.0005652504569297889,
      "clip_ratio/low_mean": 0.0005678042971339892,
      "clip_ratio/low_min": 1.3191220205044374e-05,
      "clip_ratio/region_mean": 0.0011330547458783258,
      "epoch": 0.09743975640060899,
      "grad_norm": 0.31245291233062744,
      "learning_rate": 2e-07,
      "loss": 0.0791,
      "step": 1044
    },
    {
      "clip_ratio/high_max": 0.001503012503235368,
      "clip_ratio/high_mean": 0.0005738440486311447,
      "clip_ratio/low_mean": 0.0005912666965741664,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.00116511074884329,
      "epoch": 0.09753308950060958,
      "grad_norm": 0.13973017036914825,
      "learning_rate": 2e-07,
      "loss": 0.0327,
      "step": 1045
    },
    {
      "clip_ratio/high_max": 0.0016222177218878642,
      "clip_ratio/high_mean": 0.0006519748549180804,
      "clip_ratio/low_mean": 0.0004923872584186029,
      "clip_ratio/low_min": 2.0903729819110595e-05,
      "clip_ratio/region_mean": 0.0011443621515354607,
      "epoch": 0.09762642260061016,
      "grad_norm": 0.12260133773088455,
      "learning_rate": 2e-07,
      "loss": -0.0103,
      "step": 1046
    },
    {
      "clip_ratio/high_max": 0.0014562792002834613,
      "clip_ratio/high_mean": 0.0006700640396957169,
      "clip_ratio/low_mean": 0.0005166578301896152,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0011867218890984077,
      "epoch": 0.09771975570061076,
      "grad_norm": 0.15883275866508484,
      "learning_rate": 2e-07,
      "loss": 0.0343,
      "step": 1047
    },
    {
      "clip_ratio/high_max": 0.0017374639755871613,
      "clip_ratio/high_mean": 0.0006556741409440292,
      "clip_ratio/low_mean": 0.0005638174307023291,
      "clip_ratio/low_min": 2.913617299782345e-05,
      "clip_ratio/region_mean": 0.001219491594383726,
      "epoch": 0.09781308880061133,
      "grad_norm": 0.1466199904680252,
      "learning_rate": 2e-07,
      "loss": 0.0112,
      "step": 1048
    },
    {
      "clip_ratio/high_max": 0.0017404112077201717,
      "clip_ratio/high_mean": 0.0006267549870244693,
      "clip_ratio/low_mean": 0.0005989712371956557,
      "clip_ratio/low_min": 1.059322039509425e-05,
      "clip_ratio/region_mean": 0.001225726242410019,
      "epoch": 0.09790642190061191,
      "grad_norm": 0.152729794383049,
      "learning_rate": 2e-07,
      "loss": -0.0074,
      "step": 1049
    },
    {
      "clip_ratio/high_max": 0.0017583181615918875,
      "clip_ratio/high_mean": 0.0006218709204404149,
      "clip_ratio/low_mean": 0.0004920797855447745,
      "clip_ratio/low_min": 4.138556505495217e-05,
      "clip_ratio/region_mean": 0.0011139507259940729,
      "epoch": 0.0979997550006125,
      "grad_norm": 0.1558413803577423,
      "learning_rate": 2e-07,
      "loss": -0.0068,
      "step": 1050
    },
    {
      "clip_ratio/high_max": 0.001681872905464843,
      "clip_ratio/high_mean": 0.0006473012481365004,
      "clip_ratio/low_mean": 0.0005469163843372371,
      "clip_ratio/low_min": 1.3194005077821203e-05,
      "clip_ratio/region_mean": 0.0011942176133743487,
      "epoch": 0.09809308810061308,
      "grad_norm": 0.15378768742084503,
      "learning_rate": 2e-07,
      "loss": 0.0227,
      "step": 1051
    },
    {
      "clip_ratio/high_max": 0.0016823123987705912,
      "clip_ratio/high_mean": 0.0006352785358103574,
      "clip_ratio/low_mean": 0.0005787915106338914,
      "clip_ratio/low_min": 3.9322143493336625e-05,
      "clip_ratio/region_mean": 0.0012140700455347542,
      "epoch": 0.09818642120061366,
      "grad_norm": 0.18295440077781677,
      "learning_rate": 2e-07,
      "loss": 0.0578,
      "step": 1052
    },
    {
      "clip_ratio/high_max": 0.00156029951540404,
      "clip_ratio/high_mean": 0.0006158499127195682,
      "clip_ratio/low_mean": 0.000605827273830073,
      "clip_ratio/low_min": 7.475710754079046e-05,
      "clip_ratio/region_mean": 0.00122167719018762,
      "epoch": 0.09827975430061425,
      "grad_norm": 0.185609370470047,
      "learning_rate": 2e-07,
      "loss": 0.052,
      "step": 1053
    },
    {
      "clip_ratio/high_max": 0.0017839683241618332,
      "clip_ratio/high_mean": 0.000639261832475313,
      "clip_ratio/low_mean": 0.000535863864570274,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0011751256861316506,
      "epoch": 0.09837308740061483,
      "grad_norm": 0.16138224303722382,
      "learning_rate": 2e-07,
      "loss": 0.0393,
      "step": 1054
    },
    {
      "clip_ratio/high_max": 0.0014318059402285144,
      "clip_ratio/high_mean": 0.0005877007552044233,
      "clip_ratio/low_mean": 0.0005861316112714121,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0011738323482859414,
      "epoch": 0.09846642050061541,
      "grad_norm": 0.15012574195861816,
      "learning_rate": 2e-07,
      "loss": 0.0659,
      "step": 1055
    },
    {
      "clip_ratio/high_max": 0.0015647463078494184,
      "clip_ratio/high_mean": 0.0005451857987281983,
      "clip_ratio/low_mean": 0.000563231964406441,
      "clip_ratio/low_min": 2.1317902792361565e-05,
      "clip_ratio/region_mean": 0.0011084177385782823,
      "epoch": 0.098559753600616,
      "grad_norm": 0.14288288354873657,
      "learning_rate": 2e-07,
      "loss": 0.0694,
      "step": 1056
    },
    {
      "clip_ratio/high_max": 0.00181792484363541,
      "clip_ratio/high_mean": 0.0006802855314163025,
      "clip_ratio/low_mean": 0.0005797089024781599,
      "clip_ratio/low_min": 9.185772796627134e-06,
      "clip_ratio/region_mean": 0.0012599944129760843,
      "epoch": 0.09865308670061658,
      "grad_norm": 0.1612895429134369,
      "learning_rate": 2e-07,
      "loss": 0.0007,
      "step": 1057
    },
    {
      "clip_ratio/high_max": 0.0016530869870621245,
      "clip_ratio/high_mean": 0.0006721153831676929,
      "clip_ratio/low_mean": 0.0005238746107352199,
      "clip_ratio/low_min": 2.754517481662333e-05,
      "clip_ratio/region_mean": 0.001195989996631397,
      "epoch": 0.09874641980061717,
      "grad_norm": 0.15619292855262756,
      "learning_rate": 2e-07,
      "loss": -0.0041,
      "step": 1058
    },
    {
      "clip_ratio/high_max": 0.0014645564697275404,
      "clip_ratio/high_mean": 0.0005740648603023146,
      "clip_ratio/low_mean": 0.0004823029157705605,
      "clip_ratio/low_min": 1.414667258359259e-05,
      "clip_ratio/region_mean": 0.0010563677751633804,
      "epoch": 0.09883975290061775,
      "grad_norm": 0.13636276125907898,
      "learning_rate": 2e-07,
      "loss": 0.0267,
      "step": 1059
    },
    {
      "clip_ratio/high_max": 0.001571941982547287,
      "clip_ratio/high_mean": 0.000631949253147468,
      "clip_ratio/low_mean": 0.0006597009651159169,
      "clip_ratio/low_min": 2.4781918909866363e-05,
      "clip_ratio/region_mean": 0.0012916501982545014,
      "epoch": 0.09893308600061833,
      "grad_norm": 0.14225031435489655,
      "learning_rate": 2e-07,
      "loss": 0.0456,
      "step": 1060
    },
    {
      "clip_ratio/high_max": 0.0019511353857524227,
      "clip_ratio/high_mean": 0.0007577137312182458,
      "clip_ratio/low_mean": 0.0006999586876190733,
      "clip_ratio/low_min": 3.5877712434739806e-05,
      "clip_ratio/region_mean": 0.001457672413380351,
      "epoch": 0.09902641910061892,
      "grad_norm": 0.1480303257703781,
      "learning_rate": 2e-07,
      "loss": 0.0174,
      "step": 1061
    },
    {
      "clip_ratio/high_max": 0.0014545251797244418,
      "clip_ratio/high_mean": 0.0005318421599440626,
      "clip_ratio/low_mean": 0.0005600913987109379,
      "clip_ratio/low_min": 2.7184005375602283e-05,
      "clip_ratio/region_mean": 0.001091933521820465,
      "epoch": 0.0991197522006195,
      "grad_norm": 0.1296086609363556,
      "learning_rate": 2e-07,
      "loss": 0.0379,
      "step": 1062
    },
    {
      "clip_ratio/high_max": 0.001769831585988868,
      "clip_ratio/high_mean": 0.0006847328713774914,
      "clip_ratio/low_mean": 0.0005841700203745859,
      "clip_ratio/low_min": 7.000138248258736e-05,
      "clip_ratio/region_mean": 0.0012689029244938865,
      "epoch": 0.09921308530062008,
      "grad_norm": 0.14934933185577393,
      "learning_rate": 2e-07,
      "loss": 0.0433,
      "step": 1063
    },
    {
      "clip_ratio/high_max": 0.0016910056801862083,
      "clip_ratio/high_mean": 0.0006449812690334511,
      "clip_ratio/low_mean": 0.00047210925731633324,
      "clip_ratio/low_min": 2.206668705184711e-05,
      "clip_ratio/region_mean": 0.0011170905527251307,
      "epoch": 0.09930641840062067,
      "grad_norm": 0.1892910897731781,
      "learning_rate": 2e-07,
      "loss": 0.0391,
      "step": 1064
    },
    {
      "clip_ratio/high_max": 0.0017985400481848046,
      "clip_ratio/high_mean": 0.0006342442629829748,
      "clip_ratio/low_mean": 0.0006132221387815662,
      "clip_ratio/low_min": 2.548469365137862e-05,
      "clip_ratio/region_mean": 0.001247466429049382,
      "epoch": 0.09939975150062125,
      "grad_norm": 0.16051152348518372,
      "learning_rate": 2e-07,
      "loss": 0.0457,
      "step": 1065
    },
    {
      "clip_ratio/high_max": 0.0015568154776701704,
      "clip_ratio/high_mean": 0.0006393065114025376,
      "clip_ratio/low_mean": 0.0004391210504763876,
      "clip_ratio/low_min": 8.713230272405781e-06,
      "clip_ratio/region_mean": 0.0010784275600599358,
      "epoch": 0.09949308460062183,
      "grad_norm": 1.3166816234588623,
      "learning_rate": 2e-07,
      "loss": -0.013,
      "step": 1066
    },
    {
      "clip_ratio/high_max": 0.001725747097225394,
      "clip_ratio/high_mean": 0.0007226662546599982,
      "clip_ratio/low_mean": 0.0005737946212320821,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012964608504262287,
      "epoch": 0.09958641770062242,
      "grad_norm": 0.2146015614271164,
      "learning_rate": 2e-07,
      "loss": 0.0369,
      "step": 1067
    },
    {
      "clip_ratio/high_max": 0.0015932645401335321,
      "clip_ratio/high_mean": 0.0006487094378826441,
      "clip_ratio/low_mean": 0.0006255900807445869,
      "clip_ratio/low_min": 2.4414345716650132e-05,
      "clip_ratio/region_mean": 0.0012742995240841992,
      "epoch": 0.099679750800623,
      "grad_norm": 0.16877827048301697,
      "learning_rate": 2e-07,
      "loss": 0.0135,
      "step": 1068
    },
    {
      "clip_ratio/high_max": 0.0017049649941327516,
      "clip_ratio/high_mean": 0.0006027634099154966,
      "clip_ratio/low_mean": 0.000525465987266216,
      "clip_ratio/low_min": 1.828036693041213e-05,
      "clip_ratio/region_mean": 0.001128229410824133,
      "epoch": 0.09977308390062359,
      "grad_norm": 0.14494383335113525,
      "learning_rate": 2e-07,
      "loss": 0.033,
      "step": 1069
    },
    {
      "clip_ratio/high_max": 0.0019533320773916785,
      "clip_ratio/high_mean": 0.0006804655768064549,
      "clip_ratio/low_mean": 0.0005800279086543014,
      "clip_ratio/low_min": 3.0525213333021384e-05,
      "clip_ratio/region_mean": 0.0012604934636328835,
      "epoch": 0.09986641700062417,
      "grad_norm": 0.18165990710258484,
      "learning_rate": 2e-07,
      "loss": 0.0411,
      "step": 1070
    },
    {
      "clip_ratio/high_max": 0.0017516920124762692,
      "clip_ratio/high_mean": 0.0006923058917891467,
      "clip_ratio/low_mean": 0.0005152330304554198,
      "clip_ratio/low_min": 1.0527201993681956e-05,
      "clip_ratio/region_mean": 0.001207538924063556,
      "epoch": 0.09995975010062474,
      "grad_norm": 0.1563708484172821,
      "learning_rate": 2e-07,
      "loss": 0.0188,
      "step": 1071
    },
    {
      "clip_ratio/high_max": 0.002205959754064679,
      "clip_ratio/high_mean": 0.0008133001065289136,
      "clip_ratio/low_mean": 0.0005205037459745654,
      "clip_ratio/low_min": 3.971318119511125e-05,
      "clip_ratio/region_mean": 0.0013338038334040903,
      "epoch": 0.10005308320062534,
      "grad_norm": 0.16933055222034454,
      "learning_rate": 2e-07,
      "loss": 0.0096,
      "step": 1072
    },
    {
      "clip_ratio/high_max": 0.0016144393266586121,
      "clip_ratio/high_mean": 0.0006797967826059903,
      "clip_ratio/low_mean": 0.000625458856120531,
      "clip_ratio/low_min": 5.390580008679535e-05,
      "clip_ratio/region_mean": 0.0013052556387265213,
      "epoch": 0.10014641630062592,
      "grad_norm": 0.15998722612857819,
      "learning_rate": 2e-07,
      "loss": 0.053,
      "step": 1073
    },
    {
      "clip_ratio/high_max": 0.001618497452000156,
      "clip_ratio/high_mean": 0.0006795561039325548,
      "clip_ratio/low_mean": 0.0005770796806245926,
      "clip_ratio/low_min": 1.8051649931294378e-05,
      "clip_ratio/region_mean": 0.0012566357836476527,
      "epoch": 0.1002397494006265,
      "grad_norm": 0.46215784549713135,
      "learning_rate": 2e-07,
      "loss": -0.0022,
      "step": 1074
    },
    {
      "clip_ratio/high_max": 0.0014677761646453291,
      "clip_ratio/high_mean": 0.0006326147122308612,
      "clip_ratio/low_mean": 0.0006362157328112517,
      "clip_ratio/low_min": 8.827174588077469e-05,
      "clip_ratio/region_mean": 0.0012688304268522188,
      "epoch": 0.10033308250062709,
      "grad_norm": 0.14772547781467438,
      "learning_rate": 2e-07,
      "loss": 0.024,
      "step": 1075
    },
    {
      "clip_ratio/high_max": 0.0017867706628749147,
      "clip_ratio/high_mean": 0.0007088584261509823,
      "clip_ratio/low_mean": 0.0006073488439142238,
      "clip_ratio/low_min": 6.200931966304779e-05,
      "clip_ratio/region_mean": 0.0013162072536943015,
      "epoch": 0.10042641560062766,
      "grad_norm": 0.16033732891082764,
      "learning_rate": 2e-07,
      "loss": 0.0076,
      "step": 1076
    },
    {
      "clip_ratio/high_max": 0.0019086736101598945,
      "clip_ratio/high_mean": 0.0007327171297220048,
      "clip_ratio/low_mean": 0.0005449875043268548,
      "clip_ratio/low_min": 1.1973180335189682e-05,
      "clip_ratio/region_mean": 0.0012777046576957218,
      "epoch": 0.10051974870062824,
      "grad_norm": 0.14922833442687988,
      "learning_rate": 2e-07,
      "loss": 0.0348,
      "step": 1077
    },
    {
      "clip_ratio/high_max": 0.001682754336798098,
      "clip_ratio/high_mean": 0.0006540556223626481,
      "clip_ratio/low_mean": 0.0006115350752224913,
      "clip_ratio/low_min": 3.2965815080387983e-05,
      "clip_ratio/region_mean": 0.001265590686671203,
      "epoch": 0.10061308180062883,
      "grad_norm": 0.15510930120944977,
      "learning_rate": 2e-07,
      "loss": 0.0303,
      "step": 1078
    },
    {
      "clip_ratio/high_max": 0.0016412366057920735,
      "clip_ratio/high_mean": 0.0006496340547528234,
      "clip_ratio/low_mean": 0.000531300976035709,
      "clip_ratio/low_min": 6.883260084578069e-06,
      "clip_ratio/region_mean": 0.0011809350253315642,
      "epoch": 0.10070641490062941,
      "grad_norm": 0.160722553730011,
      "learning_rate": 2e-07,
      "loss": 0.0446,
      "step": 1079
    },
    {
      "clip_ratio/high_max": 0.0018106453208019957,
      "clip_ratio/high_mean": 0.0006634130095335422,
      "clip_ratio/low_mean": 0.00048186040521613904,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0011452734397607855,
      "epoch": 0.10079974800063,
      "grad_norm": 0.16193906962871552,
      "learning_rate": 2e-07,
      "loss": 0.0316,
      "step": 1080
    },
    {
      "clip_ratio/high_max": 0.001604195716936374,
      "clip_ratio/high_mean": 0.0006386842724168673,
      "clip_ratio/low_mean": 0.0005794836188215413,
      "clip_ratio/low_min": 3.738424493349157e-05,
      "clip_ratio/region_mean": 0.0012181678976048715,
      "epoch": 0.10089308110063058,
      "grad_norm": 0.15314896404743195,
      "learning_rate": 2e-07,
      "loss": 0.0216,
      "step": 1081
    },
    {
      "clip_ratio/high_max": 0.001700196251476882,
      "clip_ratio/high_mean": 0.0006559405646839878,
      "clip_ratio/low_mean": 0.000527644129761029,
      "clip_ratio/low_min": 5.089099067845382e-05,
      "clip_ratio/region_mean": 0.001183584681712091,
      "epoch": 0.10098641420063116,
      "grad_norm": 0.13899900019168854,
      "learning_rate": 2e-07,
      "loss": 0.0248,
      "step": 1082
    },
    {
      "clip_ratio/high_max": 0.001700643239018973,
      "clip_ratio/high_mean": 0.0005800772114525898,
      "clip_ratio/low_mean": 0.0005704596151190344,
      "clip_ratio/low_min": 5.239350502961315e-05,
      "clip_ratio/region_mean": 0.001150536809291225,
      "epoch": 0.10107974730063175,
      "grad_norm": 0.14391295611858368,
      "learning_rate": 2e-07,
      "loss": 0.0523,
      "step": 1083
    },
    {
      "clip_ratio/high_max": 0.001693254987912951,
      "clip_ratio/high_mean": 0.0006048928216841887,
      "clip_ratio/low_mean": 0.0006519196713270503,
      "clip_ratio/low_min": 5.325371512299171e-05,
      "clip_ratio/region_mean": 0.001256812502106186,
      "epoch": 0.10117308040063233,
      "grad_norm": 0.18438707292079926,
      "learning_rate": 2e-07,
      "loss": 0.0216,
      "step": 1084
    },
    {
      "clip_ratio/high_max": 0.0018662692018551752,
      "clip_ratio/high_mean": 0.0007015835162746953,
      "clip_ratio/low_mean": 0.0005792635474790586,
      "clip_ratio/low_min": 2.3260817215486895e-05,
      "clip_ratio/region_mean": 0.0012808470746676903,
      "epoch": 0.10126641350063291,
      "grad_norm": 0.15572968125343323,
      "learning_rate": 2e-07,
      "loss": 0.0436,
      "step": 1085
    },
    {
      "clip_ratio/high_max": 0.0014514608592435252,
      "clip_ratio/high_mean": 0.0005984738600091077,
      "clip_ratio/low_mean": 0.0005457624638438574,
      "clip_ratio/low_min": 3.4351396607235074e-05,
      "clip_ratio/region_mean": 0.0011442363138485234,
      "epoch": 0.1013597466006335,
      "grad_norm": 0.16951200366020203,
      "learning_rate": 2e-07,
      "loss": 0.0354,
      "step": 1086
    },
    {
      "clip_ratio/high_max": 0.0015592558866046602,
      "clip_ratio/high_mean": 0.0006010137303746887,
      "clip_ratio/low_mean": 0.0005154142709216103,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0011164280003868043,
      "epoch": 0.10145307970063408,
      "grad_norm": 0.1528424322605133,
      "learning_rate": 2e-07,
      "loss": -0.0017,
      "step": 1087
    },
    {
      "clip_ratio/high_max": 0.001561774492074619,
      "clip_ratio/high_mean": 0.0006247370829441934,
      "clip_ratio/low_mean": 0.0006543066174344858,
      "clip_ratio/low_min": 7.471283925042371e-05,
      "clip_ratio/region_mean": 0.0012790437140210997,
      "epoch": 0.10154641280063466,
      "grad_norm": 0.15505114197731018,
      "learning_rate": 2e-07,
      "loss": 0.0563,
      "step": 1088
    },
    {
      "clip_ratio/high_max": 0.001500566337199416,
      "clip_ratio/high_mean": 0.0005511521485459525,
      "clip_ratio/low_mean": 0.0007105448621587129,
      "clip_ratio/low_min": 3.5685592592926696e-05,
      "clip_ratio/region_mean": 0.0012616970307135489,
      "epoch": 0.10163974590063525,
      "grad_norm": 0.1579626351594925,
      "learning_rate": 2e-07,
      "loss": 0.0625,
      "step": 1089
    },
    {
      "clip_ratio/high_max": 0.0014233183137548622,
      "clip_ratio/high_mean": 0.0006094261316320626,
      "clip_ratio/low_mean": 0.000625259337539319,
      "clip_ratio/low_min": 9.81181874522008e-05,
      "clip_ratio/region_mean": 0.001234685470990371,
      "epoch": 0.10173307900063583,
      "grad_norm": 0.1554982215166092,
      "learning_rate": 2e-07,
      "loss": 0.0133,
      "step": 1090
    },
    {
      "clip_ratio/high_max": 0.0017466573044657707,
      "clip_ratio/high_mean": 0.0006900563366798451,
      "clip_ratio/low_mean": 0.000565061139241152,
      "clip_ratio/low_min": 4.8456347940373234e-05,
      "clip_ratio/region_mean": 0.001255117473192513,
      "epoch": 0.10182641210063642,
      "grad_norm": 0.1822282075881958,
      "learning_rate": 2e-07,
      "loss": 0.0283,
      "step": 1091
    },
    {
      "clip_ratio/high_max": 0.001652716462558601,
      "clip_ratio/high_mean": 0.000627658413577592,
      "clip_ratio/low_mean": 0.0005839091190864565,
      "clip_ratio/low_min": 4.170819465798559e-05,
      "clip_ratio/region_mean": 0.0012115675017412286,
      "epoch": 0.101919745200637,
      "grad_norm": 0.16696639358997345,
      "learning_rate": 2e-07,
      "loss": 0.0129,
      "step": 1092
    },
    {
      "clip_ratio/high_max": 0.001645483138418058,
      "clip_ratio/high_mean": 0.000600817336817272,
      "clip_ratio/low_mean": 0.0005196066249482101,
      "clip_ratio/low_min": 1.3679142284672707e-05,
      "clip_ratio/region_mean": 0.0011204239308426622,
      "epoch": 0.10201307830063758,
      "grad_norm": 0.1599513441324234,
      "learning_rate": 2e-07,
      "loss": 0.0171,
      "step": 1093
    },
    {
      "clip_ratio/high_max": 0.0015299071328627178,
      "clip_ratio/high_mean": 0.0005785768280475168,
      "clip_ratio/low_mean": 0.0006065301568014547,
      "clip_ratio/low_min": 7.88146280683577e-06,
      "clip_ratio/region_mean": 0.0011851070012198761,
      "epoch": 0.10210641140063817,
      "grad_norm": 0.14695550501346588,
      "learning_rate": 2e-07,
      "loss": 0.0199,
      "step": 1094
    },
    {
      "clip_ratio/high_max": 0.0019350838447280694,
      "clip_ratio/high_mean": 0.0007338022969634039,
      "clip_ratio/low_mean": 0.0006955898188607534,
      "clip_ratio/low_min": 1.4534884030581452e-05,
      "clip_ratio/region_mean": 0.0014293921303760726,
      "epoch": 0.10219974450063875,
      "grad_norm": 0.16174593567848206,
      "learning_rate": 2e-07,
      "loss": 0.083,
      "step": 1095
    },
    {
      "clip_ratio/high_max": 0.001641252307308605,
      "clip_ratio/high_mean": 0.000620701682237268,
      "clip_ratio/low_mean": 0.0006615999991481658,
      "clip_ratio/low_min": 2.306206624780316e-05,
      "clip_ratio/region_mean": 0.001282301680475939,
      "epoch": 0.10229307760063933,
      "grad_norm": 0.14572051167488098,
      "learning_rate": 2e-07,
      "loss": 0.0652,
      "step": 1096
    },
    {
      "clip_ratio/high_max": 0.001657885772146983,
      "clip_ratio/high_mean": 0.0006771035150450189,
      "clip_ratio/low_mean": 0.0007343262859649258,
      "clip_ratio/low_min": 4.648864432965638e-05,
      "clip_ratio/region_mean": 0.0014114297919149976,
      "epoch": 0.10238641070063992,
      "grad_norm": 0.6493206024169922,
      "learning_rate": 2e-07,
      "loss": 0.0582,
      "step": 1097
    },
    {
      "clip_ratio/high_max": 0.0018525566192693077,
      "clip_ratio/high_mean": 0.0007341996642935555,
      "clip_ratio/low_mean": 0.0006568676835740916,
      "clip_ratio/low_min": 4.4178036205266835e-05,
      "clip_ratio/region_mean": 0.0013910673442296684,
      "epoch": 0.1024797438006405,
      "grad_norm": 0.1657799482345581,
      "learning_rate": 2e-07,
      "loss": 0.0576,
      "step": 1098
    },
    {
      "clip_ratio/high_max": 0.0016571992855460849,
      "clip_ratio/high_mean": 0.0006144828257674817,
      "clip_ratio/low_mean": 0.0007577101841889089,
      "clip_ratio/low_min": 5.179845084057888e-05,
      "clip_ratio/region_mean": 0.001372193048155168,
      "epoch": 0.10257307690064109,
      "grad_norm": 0.20611099898815155,
      "learning_rate": 2e-07,
      "loss": 0.0781,
      "step": 1099
    },
    {
      "clip_ratio/high_max": 0.001434320127373212,
      "clip_ratio/high_mean": 0.0005880656754015945,
      "clip_ratio/low_mean": 0.0006825906748417765,
      "clip_ratio/low_min": 3.599530327846878e-05,
      "clip_ratio/region_mean": 0.0012706563466053922,
      "epoch": 0.10266641000064167,
      "grad_norm": 0.17862387001514435,
      "learning_rate": 2e-07,
      "loss": 0.0793,
      "step": 1100
    },
    {
      "clip_ratio/high_max": 0.0019495309315971099,
      "clip_ratio/high_mean": 0.000805816613137722,
      "clip_ratio/low_mean": 0.0005715735478588613,
      "clip_ratio/low_min": 4.104381787328748e-05,
      "clip_ratio/region_mean": 0.0013773901591775939,
      "epoch": 0.10275974310064225,
      "grad_norm": 0.22093947231769562,
      "learning_rate": 2e-07,
      "loss": -0.0076,
      "step": 1101
    },
    {
      "clip_ratio/high_max": 0.0019233182829339057,
      "clip_ratio/high_mean": 0.0007954319789860165,
      "clip_ratio/low_mean": 0.000625573087745579,
      "clip_ratio/low_min": 2.0298797608120367e-05,
      "clip_ratio/region_mean": 0.0014210050358087756,
      "epoch": 0.10285307620064284,
      "grad_norm": 0.19207599759101868,
      "learning_rate": 2e-07,
      "loss": 0.0078,
      "step": 1102
    },
    {
      "clip_ratio/high_max": 0.0015221704234136268,
      "clip_ratio/high_mean": 0.0005945479224465089,
      "clip_ratio/low_mean": 0.0006161075580166653,
      "clip_ratio/low_min": 2.7014967599825468e-05,
      "clip_ratio/region_mean": 0.0012106554822821636,
      "epoch": 0.10294640930064342,
      "grad_norm": 0.1413605958223343,
      "learning_rate": 2e-07,
      "loss": 0.041,
      "step": 1103
    },
    {
      "clip_ratio/high_max": 0.0016122898141475162,
      "clip_ratio/high_mean": 0.0006016110264681629,
      "clip_ratio/low_mean": 0.0006949706130399136,
      "clip_ratio/low_min": 1.769786285876762e-05,
      "clip_ratio/region_mean": 0.0012965816567884758,
      "epoch": 0.103039742400644,
      "grad_norm": 0.1498638540506363,
      "learning_rate": 2e-07,
      "loss": 0.0548,
      "step": 1104
    },
    {
      "clip_ratio/high_max": 0.0017425209625798743,
      "clip_ratio/high_mean": 0.0006616099690290866,
      "clip_ratio/low_mean": 0.0006061206313461298,
      "clip_ratio/low_min": 1.1741499292838853e-05,
      "clip_ratio/region_mean": 0.0012677305967372376,
      "epoch": 0.10313307550064459,
      "grad_norm": 0.15358155965805054,
      "learning_rate": 2e-07,
      "loss": -0.0052,
      "step": 1105
    },
    {
      "clip_ratio/high_max": 0.0017331620183540508,
      "clip_ratio/high_mean": 0.0007212812506622868,
      "clip_ratio/low_mean": 0.0007488276642106939,
      "clip_ratio/low_min": 3.766162717511179e-05,
      "clip_ratio/region_mean": 0.0014701088948640972,
      "epoch": 0.10322640860064516,
      "grad_norm": 0.3596377670764923,
      "learning_rate": 2e-07,
      "loss": 0.0485,
      "step": 1106
    },
    {
      "clip_ratio/high_max": 0.0016821270546643063,
      "clip_ratio/high_mean": 0.0006388401106960373,
      "clip_ratio/low_mean": 0.0006594250371563248,
      "clip_ratio/low_min": 4.4572099795914255e-05,
      "clip_ratio/region_mean": 0.0012982651242054999,
      "epoch": 0.10331974170064574,
      "grad_norm": 0.14002206921577454,
      "learning_rate": 2e-07,
      "loss": 0.0356,
      "step": 1107
    },
    {
      "clip_ratio/high_max": 0.0016101407418318558,
      "clip_ratio/high_mean": 0.0005903952160224435,
      "clip_ratio/low_mean": 0.0007644207107659895,
      "clip_ratio/low_min": 9.530784063827014e-05,
      "clip_ratio/region_mean": 0.0013548158967751078,
      "epoch": 0.10341307480064633,
      "grad_norm": 0.17775137722492218,
      "learning_rate": 2e-07,
      "loss": 0.1128,
      "step": 1108
    },
    {
      "clip_ratio/high_max": 0.0017406380939064547,
      "clip_ratio/high_mean": 0.0007249852251334232,
      "clip_ratio/low_mean": 0.0006339689480228117,
      "clip_ratio/low_min": 5.9723689446400385e-05,
      "clip_ratio/region_mean": 0.0013589541449618991,
      "epoch": 0.10350640790064691,
      "grad_norm": 0.19935919344425201,
      "learning_rate": 2e-07,
      "loss": 0.0237,
      "step": 1109
    },
    {
      "clip_ratio/high_max": 0.0019679307042679284,
      "clip_ratio/high_mean": 0.0006746289054717636,
      "clip_ratio/low_mean": 0.0006979214067541761,
      "clip_ratio/low_min": 5.121557023812784e-05,
      "clip_ratio/region_mean": 0.0013725503122259397,
      "epoch": 0.1035997410006475,
      "grad_norm": 0.23512428998947144,
      "learning_rate": 2e-07,
      "loss": 0.0148,
      "step": 1110
    },
    {
      "clip_ratio/high_max": 0.0017864119927253341,
      "clip_ratio/high_mean": 0.0006599070266020135,
      "clip_ratio/low_mean": 0.0005742720040871063,
      "clip_ratio/low_min": 5.224253527558176e-05,
      "clip_ratio/region_mean": 0.0012341790352365933,
      "epoch": 0.10369307410064808,
      "grad_norm": 0.15648329257965088,
      "learning_rate": 2e-07,
      "loss": 0.0504,
      "step": 1111
    },
    {
      "clip_ratio/high_max": 0.0016795804840512574,
      "clip_ratio/high_mean": 0.0006713345701427897,
      "clip_ratio/low_mean": 0.000683567318446876,
      "clip_ratio/low_min": 4.23903229602729e-05,
      "clip_ratio/region_mean": 0.0013549018658522982,
      "epoch": 0.10378640720064866,
      "grad_norm": 0.17392602562904358,
      "learning_rate": 2e-07,
      "loss": 0.0135,
      "step": 1112
    },
    {
      "clip_ratio/high_max": 0.0017916250071721151,
      "clip_ratio/high_mean": 0.0007649974313608254,
      "clip_ratio/low_mean": 0.0006185337115311995,
      "clip_ratio/low_min": 3.6902183637721464e-05,
      "clip_ratio/region_mean": 0.0013835311292496044,
      "epoch": 0.10387974030064925,
      "grad_norm": 0.2709124982357025,
      "learning_rate": 2e-07,
      "loss": 0.0237,
      "step": 1113
    },
    {
      "clip_ratio/high_max": 0.0019190239436284173,
      "clip_ratio/high_mean": 0.0006751879027433461,
      "clip_ratio/low_mean": 0.0006608903404412558,
      "clip_ratio/low_min": 8.29456839710474e-05,
      "clip_ratio/region_mean": 0.0013360782431846019,
      "epoch": 0.10397307340064983,
      "grad_norm": 0.18092484772205353,
      "learning_rate": 2e-07,
      "loss": 0.0423,
      "step": 1114
    },
    {
      "clip_ratio/high_max": 0.0014537269635184202,
      "clip_ratio/high_mean": 0.0006930093031769502,
      "clip_ratio/low_mean": 0.0007284347866516327,
      "clip_ratio/low_min": 4.047339734825073e-05,
      "clip_ratio/region_mean": 0.0014214440707291942,
      "epoch": 0.10406640650065041,
      "grad_norm": 0.1914963573217392,
      "learning_rate": 2e-07,
      "loss": 0.1066,
      "step": 1115
    },
    {
      "clip_ratio/high_max": 0.0016021225055737887,
      "clip_ratio/high_mean": 0.0006459154392359778,
      "clip_ratio/low_mean": 0.0006769977626390755,
      "clip_ratio/low_min": 0.0001051740100592724,
      "clip_ratio/region_mean": 0.0013229132491687778,
      "epoch": 0.104159739600651,
      "grad_norm": 0.2495952844619751,
      "learning_rate": 2e-07,
      "loss": 0.0563,
      "step": 1116
    },
    {
      "clip_ratio/high_max": 0.0019777498237090185,
      "clip_ratio/high_mean": 0.0007893728088674834,
      "clip_ratio/low_mean": 0.0006029953219695017,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013923681581218261,
      "epoch": 0.10425307270065158,
      "grad_norm": 0.16072824597358704,
      "learning_rate": 2e-07,
      "loss": -0.0176,
      "step": 1117
    },
    {
      "clip_ratio/high_max": 0.0018720912412391044,
      "clip_ratio/high_mean": 0.0006642057987846783,
      "clip_ratio/low_mean": 0.0006460151471401332,
      "clip_ratio/low_min": 1.4228799045667984e-05,
      "clip_ratio/region_mean": 0.0013102209304634016,
      "epoch": 0.10434640580065216,
      "grad_norm": 0.16775690019130707,
      "learning_rate": 2e-07,
      "loss": 0.0311,
      "step": 1118
    },
    {
      "clip_ratio/high_max": 0.001742502186971251,
      "clip_ratio/high_mean": 0.0007207712133094901,
      "clip_ratio/low_mean": 0.0006960818463994656,
      "clip_ratio/low_min": 2.9430421363940695e-05,
      "clip_ratio/region_mean": 0.001416853083355818,
      "epoch": 0.10443973890065275,
      "grad_norm": 0.6444618701934814,
      "learning_rate": 2e-07,
      "loss": -0.0063,
      "step": 1119
    },
    {
      "clip_ratio/high_max": 0.00141055361382314,
      "clip_ratio/high_mean": 0.0006426684703910723,
      "clip_ratio/low_mean": 0.0005982020120427478,
      "clip_ratio/low_min": 2.3839796995162033e-05,
      "clip_ratio/region_mean": 0.0012408705006237142,
      "epoch": 0.10453307200065333,
      "grad_norm": 0.18336622416973114,
      "learning_rate": 2e-07,
      "loss": -0.0052,
      "step": 1120
    },
    {
      "clip_ratio/high_max": 0.0017139737574325409,
      "clip_ratio/high_mean": 0.0007289939931069966,
      "clip_ratio/low_mean": 0.0005799311393275275,
      "clip_ratio/low_min": 1.778599835233763e-05,
      "clip_ratio/region_mean": 0.0013089251406199764,
      "epoch": 0.10462640510065392,
      "grad_norm": 0.18604180216789246,
      "learning_rate": 2e-07,
      "loss": 0.0319,
      "step": 1121
    },
    {
      "clip_ratio/high_max": 0.0019018440143554471,
      "clip_ratio/high_mean": 0.0007385402004729258,
      "clip_ratio/low_mean": 0.0006917208015693177,
      "clip_ratio/low_min": 7.095688397384947e-05,
      "clip_ratio/region_mean": 0.0014302609852165915,
      "epoch": 0.1047197382006545,
      "grad_norm": 0.15553155541419983,
      "learning_rate": 2e-07,
      "loss": 0.0325,
      "step": 1122
    },
    {
      "clip_ratio/high_max": 0.0018789733039739076,
      "clip_ratio/high_mean": 0.0007071196014294401,
      "clip_ratio/low_mean": 0.0006871028799650958,
      "clip_ratio/low_min": 3.462401173237595e-05,
      "clip_ratio/region_mean": 0.0013942224904894829,
      "epoch": 0.10481307130065508,
      "grad_norm": 0.1714010089635849,
      "learning_rate": 2e-07,
      "loss": 0.0149,
      "step": 1123
    },
    {
      "clip_ratio/high_max": 0.0016275035777653102,
      "clip_ratio/high_mean": 0.0007292515292647295,
      "clip_ratio/low_mean": 0.000791360653238371,
      "clip_ratio/low_min": 8.394015003432287e-05,
      "clip_ratio/region_mean": 0.0015206121825031005,
      "epoch": 0.10490640440065567,
      "grad_norm": 0.18012382090091705,
      "learning_rate": 2e-07,
      "loss": 0.0392,
      "step": 1124
    },
    {
      "clip_ratio/high_max": 0.0018016122849076055,
      "clip_ratio/high_mean": 0.0008042313565965742,
      "clip_ratio/low_mean": 0.00068803240719717,
      "clip_ratio/low_min": 7.830328104319051e-05,
      "clip_ratio/region_mean": 0.0014922637310519349,
      "epoch": 0.10499973750065625,
      "grad_norm": 0.1693631261587143,
      "learning_rate": 2e-07,
      "loss": 0.0082,
      "step": 1125
    },
    {
      "clip_ratio/high_max": 0.0016284908888337668,
      "clip_ratio/high_mean": 0.0006352777154461364,
      "clip_ratio/low_mean": 0.0007887508982094005,
      "clip_ratio/low_min": 6.218793532752898e-05,
      "clip_ratio/region_mean": 0.0014240286000131164,
      "epoch": 0.10509307060065683,
      "grad_norm": 0.16774801909923553,
      "learning_rate": 2e-07,
      "loss": 0.0638,
      "step": 1126
    },
    {
      "clip_ratio/high_max": 0.0016479643290949753,
      "clip_ratio/high_mean": 0.0006184939456943539,
      "clip_ratio/low_mean": 0.0006981065835134359,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001316600522841327,
      "epoch": 0.10518640370065742,
      "grad_norm": 0.17191198468208313,
      "learning_rate": 2e-07,
      "loss": 0.0398,
      "step": 1127
    },
    {
      "clip_ratio/high_max": 0.0018514398179831915,
      "clip_ratio/high_mean": 0.000778455576437409,
      "clip_ratio/low_mean": 0.0006837699947936926,
      "clip_ratio/low_min": 2.872992536140373e-05,
      "clip_ratio/region_mean": 0.0014622256094298791,
      "epoch": 0.105279736800658,
      "grad_norm": 0.18933561444282532,
      "learning_rate": 2e-07,
      "loss": 0.0094,
      "step": 1128
    },
    {
      "clip_ratio/high_max": 0.001868574840045767,
      "clip_ratio/high_mean": 0.0006547029206558364,
      "clip_ratio/low_mean": 0.0006830069323768839,
      "clip_ratio/low_min": 4.284865917725256e-05,
      "clip_ratio/region_mean": 0.0013377098803175613,
      "epoch": 0.10537306990065858,
      "grad_norm": 0.20581325888633728,
      "learning_rate": 2e-07,
      "loss": 0.0508,
      "step": 1129
    },
    {
      "clip_ratio/high_max": 0.001731505701172864,
      "clip_ratio/high_mean": 0.0007339230287470855,
      "clip_ratio/low_mean": 0.0007276413107319968,
      "clip_ratio/low_min": 1.3377568393480033e-05,
      "clip_ratio/region_mean": 0.0014615643449360505,
      "epoch": 0.10546640300065917,
      "grad_norm": 0.19026395678520203,
      "learning_rate": 2e-07,
      "loss": -0.0188,
      "step": 1130
    },
    {
      "clip_ratio/high_max": 0.0017855706901173107,
      "clip_ratio/high_mean": 0.0007221573177957907,
      "clip_ratio/low_mean": 0.000752309193558176,
      "clip_ratio/low_min": 5.358645375963533e-05,
      "clip_ratio/region_mean": 0.0014744665131729562,
      "epoch": 0.10555973610065975,
      "grad_norm": 0.17866875231266022,
      "learning_rate": 2e-07,
      "loss": 0.0544,
      "step": 1131
    },
    {
      "clip_ratio/high_max": 0.0017396401963196695,
      "clip_ratio/high_mean": 0.0006553527291544015,
      "clip_ratio/low_mean": 0.0007032078810880193,
      "clip_ratio/low_min": 5.5048583817551844e-05,
      "clip_ratio/region_mean": 0.0013585606175183784,
      "epoch": 0.10565306920066034,
      "grad_norm": 0.2077604979276657,
      "learning_rate": 2e-07,
      "loss": 0.0721,
      "step": 1132
    },
    {
      "clip_ratio/high_max": 0.0019366508204257116,
      "clip_ratio/high_mean": 0.0007306157513085054,
      "clip_ratio/low_mean": 0.000763090914915665,
      "clip_ratio/low_min": 6.938521983101964e-05,
      "clip_ratio/region_mean": 0.001493706618930446,
      "epoch": 0.10574640230066092,
      "grad_norm": 0.17884354293346405,
      "learning_rate": 2e-07,
      "loss": 0.0418,
      "step": 1133
    },
    {
      "clip_ratio/high_max": 0.0018405324954073876,
      "clip_ratio/high_mean": 0.0007919335039332509,
      "clip_ratio/low_mean": 0.000879623978107702,
      "clip_ratio/low_min": 8.656440422782907e-05,
      "clip_ratio/region_mean": 0.0016715575038688257,
      "epoch": 0.1058397354006615,
      "grad_norm": 1.292534351348877,
      "learning_rate": 2e-07,
      "loss": 0.0464,
      "step": 1134
    },
    {
      "clip_ratio/high_max": 0.0018374226237938274,
      "clip_ratio/high_mean": 0.000749734355849796,
      "clip_ratio/low_mean": 0.0007330738135351567,
      "clip_ratio/low_min": 3.488685888441978e-05,
      "clip_ratio/region_mean": 0.0014828081511950586,
      "epoch": 0.10593306850066209,
      "grad_norm": 0.17767179012298584,
      "learning_rate": 2e-07,
      "loss": 0.0334,
      "step": 1135
    },
    {
      "clip_ratio/high_max": 0.0016330299913533963,
      "clip_ratio/high_mean": 0.0006284384216996841,
      "clip_ratio/low_mean": 0.0008460454155283514,
      "clip_ratio/low_min": 0.00015475264990527648,
      "clip_ratio/region_mean": 0.0014744838554179296,
      "epoch": 0.10602640160066266,
      "grad_norm": 0.32256028056144714,
      "learning_rate": 2e-07,
      "loss": 0.0845,
      "step": 1136
    },
    {
      "clip_ratio/high_max": 0.0019067546782025602,
      "clip_ratio/high_mean": 0.0008688514717505313,
      "clip_ratio/low_mean": 0.0007212979035102762,
      "clip_ratio/low_min": 1.437442460883176e-05,
      "clip_ratio/region_mean": 0.0015901494116405956,
      "epoch": 0.10611973470066324,
      "grad_norm": 0.18215949833393097,
      "learning_rate": 2e-07,
      "loss": -0.0118,
      "step": 1137
    },
    {
      "clip_ratio/high_max": 0.0022245179570745677,
      "clip_ratio/high_mean": 0.000872844597324729,
      "clip_ratio/low_mean": 0.0007488478386221686,
      "clip_ratio/low_min": 6.22961861154181e-05,
      "clip_ratio/region_mean": 0.0016216924486798234,
      "epoch": 0.10621306780066384,
      "grad_norm": 0.17662769556045532,
      "learning_rate": 2e-07,
      "loss": 0.0039,
      "step": 1138
    },
    {
      "clip_ratio/high_max": 0.0016332259547198191,
      "clip_ratio/high_mean": 0.0006142159618320875,
      "clip_ratio/low_mean": 0.0007663615488127107,
      "clip_ratio/low_min": 5.744968984799925e-05,
      "clip_ratio/region_mean": 0.0013805774942738935,
      "epoch": 0.10630640090066441,
      "grad_norm": 0.21307222545146942,
      "learning_rate": 2e-07,
      "loss": 0.0672,
      "step": 1139
    },
    {
      "clip_ratio/high_max": 0.0020056764369655866,
      "clip_ratio/high_mean": 0.0007443730701197637,
      "clip_ratio/low_mean": 0.0007626226670254255,
      "clip_ratio/low_min": 1.3833554476150312e-05,
      "clip_ratio/region_mean": 0.0015069957262312528,
      "epoch": 0.10639973400066499,
      "grad_norm": 0.2009405791759491,
      "learning_rate": 2e-07,
      "loss": 0.058,
      "step": 1140
    },
    {
      "clip_ratio/high_max": 0.0018943691247841343,
      "clip_ratio/high_mean": 0.000753516324039083,
      "clip_ratio/low_mean": 0.0007014564471319318,
      "clip_ratio/low_min": 4.9380751079297625e-05,
      "clip_ratio/region_mean": 0.001454972749343142,
      "epoch": 0.10649306710066558,
      "grad_norm": 0.20019090175628662,
      "learning_rate": 2e-07,
      "loss": 0.0113,
      "step": 1141
    },
    {
      "clip_ratio/high_max": 0.0021072390154586174,
      "clip_ratio/high_mean": 0.0007974841118993936,
      "clip_ratio/low_mean": 0.0008537994108337443,
      "clip_ratio/low_min": 4.875806735071819e-05,
      "clip_ratio/region_mean": 0.0016512835427420214,
      "epoch": 0.10658640020066616,
      "grad_norm": 0.1795814484357834,
      "learning_rate": 2e-07,
      "loss": 0.0401,
      "step": 1142
    },
    {
      "clip_ratio/high_max": 0.001778037676558597,
      "clip_ratio/high_mean": 0.0007957225243444555,
      "clip_ratio/low_mean": 0.000743653788958909,
      "clip_ratio/low_min": 6.830601250840118e-06,
      "clip_ratio/region_mean": 0.0015393763242173009,
      "epoch": 0.10667973330066675,
      "grad_norm": 0.20919446647167206,
      "learning_rate": 2e-07,
      "loss": 0.0513,
      "step": 1143
    },
    {
      "clip_ratio/high_max": 0.0016695245467417408,
      "clip_ratio/high_mean": 0.0005807170582556864,
      "clip_ratio/low_mean": 0.0008029220389289549,
      "clip_ratio/low_min": 3.820877100224607e-05,
      "clip_ratio/region_mean": 0.0013836390789947473,
      "epoch": 0.10677306640066733,
      "grad_norm": 0.23670423030853271,
      "learning_rate": 2e-07,
      "loss": 0.0718,
      "step": 1144
    },
    {
      "clip_ratio/high_max": 0.0015789384251547744,
      "clip_ratio/high_mean": 0.0006654261649146065,
      "clip_ratio/low_mean": 0.0007718578090134542,
      "clip_ratio/low_min": 6.615464008064009e-05,
      "clip_ratio/region_mean": 0.0014372839832503814,
      "epoch": 0.10686639950066791,
      "grad_norm": 2.1207847595214844,
      "learning_rate": 2e-07,
      "loss": 0.0607,
      "step": 1145
    },
    {
      "clip_ratio/high_max": 0.0017458004149375483,
      "clip_ratio/high_mean": 0.0007489466952392831,
      "clip_ratio/low_mean": 0.0008803221035122988,
      "clip_ratio/low_min": 9.561286242387723e-05,
      "clip_ratio/region_mean": 0.0016292688051180448,
      "epoch": 0.1069597326006685,
      "grad_norm": 0.23434318602085114,
      "learning_rate": 2e-07,
      "loss": 0.0441,
      "step": 1146
    },
    {
      "clip_ratio/high_max": 0.0018621850995259592,
      "clip_ratio/high_mean": 0.0007752439939849864,
      "clip_ratio/low_mean": 0.0009569797439326067,
      "clip_ratio/low_min": 4.49408098575077e-05,
      "clip_ratio/region_mean": 0.0017322237472399138,
      "epoch": 0.10705306570066908,
      "grad_norm": 0.23642611503601074,
      "learning_rate": 2e-07,
      "loss": 0.0198,
      "step": 1147
    },
    {
      "clip_ratio/high_max": 0.002140612225048244,
      "clip_ratio/high_mean": 0.0007878617288952228,
      "clip_ratio/low_mean": 0.0008089639450190589,
      "clip_ratio/low_min": 0.00010770332119136583,
      "clip_ratio/region_mean": 0.0015968256630003452,
      "epoch": 0.10714639880066966,
      "grad_norm": 0.2382020354270935,
      "learning_rate": 2e-07,
      "loss": 0.0354,
      "step": 1148
    },
    {
      "clip_ratio/high_max": 0.0017905512431752868,
      "clip_ratio/high_mean": 0.0007838075089239283,
      "clip_ratio/low_mean": 0.0008416560613113688,
      "clip_ratio/low_min": 3.822678354481468e-05,
      "clip_ratio/region_mean": 0.0016254635847872123,
      "epoch": 0.10723973190067025,
      "grad_norm": 0.22861531376838684,
      "learning_rate": 2e-07,
      "loss": 0.0223,
      "step": 1149
    },
    {
      "clip_ratio/high_max": 0.001998607265704777,
      "clip_ratio/high_mean": 0.0007658508702661493,
      "clip_ratio/low_mean": 0.0008628988343843957,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0016287497164739762,
      "epoch": 0.10733306500067083,
      "grad_norm": 0.18002702295780182,
      "learning_rate": 2e-07,
      "loss": 0.0025,
      "step": 1150
    },
    {
      "clip_ratio/high_max": 0.0020809012348763645,
      "clip_ratio/high_mean": 0.0008540978724340675,
      "clip_ratio/low_mean": 0.0008565541411371669,
      "clip_ratio/low_min": 0.00014070615179662127,
      "clip_ratio/region_mean": 0.0017106519771914463,
      "epoch": 0.10742639810067142,
      "grad_norm": 0.2044249027967453,
      "learning_rate": 2e-07,
      "loss": 0.0213,
      "step": 1151
    },
    {
      "clip_ratio/high_max": 0.0023322766355704516,
      "clip_ratio/high_mean": 0.000940882522627362,
      "clip_ratio/low_mean": 0.0008237906986323651,
      "clip_ratio/low_min": 0.00010056074552267091,
      "clip_ratio/region_mean": 0.0017646731830609497,
      "epoch": 0.107519731200672,
      "grad_norm": 0.7507470846176147,
      "learning_rate": 2e-07,
      "loss": -0.0019,
      "step": 1152
    },
    {
      "clip_ratio/high_max": 0.0016837600378494244,
      "clip_ratio/high_mean": 0.0005544483556150226,
      "clip_ratio/low_mean": 0.0006055840676708613,
      "clip_ratio/low_min": 3.713499245350249e-05,
      "clip_ratio/region_mean": 0.001160032419647905,
      "completions/clipped_ratio": 0.018476213727678603,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4096.0,
      "completions/mean_length": 642.605224609375,
      "completions/mean_terminated_length": 577.598388671875,
      "completions/min_length": 80.0,
      "completions/min_terminated_length": 80.0,
      "epoch": 0.10761306430067258,
      "grad_norm": 0.16128115355968475,
      "learning_rate": 2e-07,
      "loss": 0.0171,
      "num_tokens": 858955881.0,
      "reward": 0.5998186469078064,
      "reward_std": 0.1697637140750885,
      "rewards/simpleverify_reward/mean": 0.5998186469078064,
      "rewards/simpleverify_reward/std": 0.4899369478225708,
      "step": 1153
    },
    {
      "clip_ratio/high_max": 0.0017052963194146287,
      "clip_ratio/high_mean": 0.0006739360160281649,
      "clip_ratio/low_mean": 0.0006507485704787541,
      "clip_ratio/low_min": 6.943672815395985e-06,
      "clip_ratio/region_mean": 0.0013246845992398448,
      "epoch": 0.10770639740067317,
      "grad_norm": 0.1607077717781067,
      "learning_rate": 2e-07,
      "loss": 0.0289,
      "step": 1154
    },
    {
      "clip_ratio/high_max": 0.001727568132992019,
      "clip_ratio/high_mean": 0.0006293631804510369,
      "clip_ratio/low_mean": 0.0005630431915051304,
      "clip_ratio/low_min": 4.688851549872197e-05,
      "clip_ratio/region_mean": 0.0011924063765036408,
      "epoch": 0.10779973050067375,
      "grad_norm": 0.17281484603881836,
      "learning_rate": 2e-07,
      "loss": -0.0029,
      "step": 1155
    },
    {
      "clip_ratio/high_max": 0.0017013440738082863,
      "clip_ratio/high_mean": 0.0005897964019823121,
      "clip_ratio/low_mean": 0.0006868044674774865,
      "clip_ratio/low_min": 2.829975164786447e-05,
      "clip_ratio/region_mean": 0.0012766008549078833,
      "epoch": 0.10789306360067433,
      "grad_norm": 0.17459584772586823,
      "learning_rate": 2e-07,
      "loss": 0.0297,
      "step": 1156
    },
    {
      "clip_ratio/high_max": 0.002040089759248076,
      "clip_ratio/high_mean": 0.0007473067671526223,
      "clip_ratio/low_mean": 0.0005943110681982944,
      "clip_ratio/low_min": 1.3760458386968821e-05,
      "clip_ratio/region_mean": 0.001341617858997779,
      "epoch": 0.10798639670067492,
      "grad_norm": 0.16108620166778564,
      "learning_rate": 2e-07,
      "loss": 0.0611,
      "step": 1157
    },
    {
      "clip_ratio/high_max": 0.0015304409917007433,
      "clip_ratio/high_mean": 0.0005702020944227115,
      "clip_ratio/low_mean": 0.000645092484774068,
      "clip_ratio/low_min": 1.9607843569247052e-05,
      "clip_ratio/region_mean": 0.0012152946001151577,
      "epoch": 0.1080797298006755,
      "grad_norm": 0.16884584724903107,
      "learning_rate": 2e-07,
      "loss": 0.0399,
      "step": 1158
    },
    {
      "clip_ratio/high_max": 0.00151808327427716,
      "clip_ratio/high_mean": 0.0006391834576788824,
      "clip_ratio/low_mean": 0.0005465176336656441,
      "clip_ratio/low_min": 3.083862702624174e-05,
      "clip_ratio/region_mean": 0.0011857011159008835,
      "epoch": 0.10817306290067608,
      "grad_norm": 0.16362978518009186,
      "learning_rate": 2e-07,
      "loss": 0.0376,
      "step": 1159
    },
    {
      "clip_ratio/high_max": 0.0014961128654249478,
      "clip_ratio/high_mean": 0.0006387025296135107,
      "clip_ratio/low_mean": 0.0005922444777297642,
      "clip_ratio/low_min": 3.983666556450771e-05,
      "clip_ratio/region_mean": 0.0012309470075706486,
      "epoch": 0.10826639600067667,
      "grad_norm": 0.15502344071865082,
      "learning_rate": 2e-07,
      "loss": 0.0552,
      "step": 1160
    },
    {
      "clip_ratio/high_max": 0.0017032809009833727,
      "clip_ratio/high_mean": 0.0006181210210343124,
      "clip_ratio/low_mean": 0.0005751268481617444,
      "clip_ratio/low_min": 6.111742732173298e-05,
      "clip_ratio/region_mean": 0.0011932478919334244,
      "epoch": 0.10835972910067725,
      "grad_norm": 0.1718013435602188,
      "learning_rate": 2e-07,
      "loss": 0.0179,
      "step": 1161
    },
    {
      "clip_ratio/high_max": 0.0021555940620601177,
      "clip_ratio/high_mean": 0.0008054333811742254,
      "clip_ratio/low_mean": 0.0005906603328185156,
      "clip_ratio/low_min": 2.378686986048706e-05,
      "clip_ratio/region_mean": 0.0013960936848889105,
      "epoch": 0.10845306220067784,
      "grad_norm": 0.16806522011756897,
      "learning_rate": 2e-07,
      "loss": -0.0128,
      "step": 1162
    },
    {
      "clip_ratio/high_max": 0.0017676826282695401,
      "clip_ratio/high_mean": 0.0006460875174525427,
      "clip_ratio/low_mean": 0.0005763011640738114,
      "clip_ratio/low_min": 2.0315294023021124e-05,
      "clip_ratio/region_mean": 0.0012223886951687746,
      "epoch": 0.10854639530067842,
      "grad_norm": 0.16095001995563507,
      "learning_rate": 2e-07,
      "loss": 0.0304,
      "step": 1163
    },
    {
      "clip_ratio/high_max": 0.0018025333411060274,
      "clip_ratio/high_mean": 0.0006848933817309444,
      "clip_ratio/low_mean": 0.0006499745759356301,
      "clip_ratio/low_min": 1.7717023638397222e-05,
      "clip_ratio/region_mean": 0.0013348679785849527,
      "epoch": 0.108639728400679,
      "grad_norm": 0.17194600403308868,
      "learning_rate": 2e-07,
      "loss": 0.0482,
      "step": 1164
    },
    {
      "clip_ratio/high_max": 0.0014330134690681007,
      "clip_ratio/high_mean": 0.0006012221829223563,
      "clip_ratio/low_mean": 0.0005633944674627855,
      "clip_ratio/low_min": 1.573514600750059e-05,
      "clip_ratio/region_mean": 0.0011646166603895836,
      "epoch": 0.10873306150067959,
      "grad_norm": 0.14470773935317993,
      "learning_rate": 2e-07,
      "loss": 0.0547,
      "step": 1165
    },
    {
      "clip_ratio/high_max": 0.0015430625735461945,
      "clip_ratio/high_mean": 0.0005495188711392984,
      "clip_ratio/low_mean": 0.0006298827174759936,
      "clip_ratio/low_min": 1.441420681658201e-05,
      "clip_ratio/region_mean": 0.0011794015736086294,
      "epoch": 0.10882639460068017,
      "grad_norm": 0.16102689504623413,
      "learning_rate": 2e-07,
      "loss": 0.0674,
      "step": 1166
    },
    {
      "clip_ratio/high_max": 0.0017442243406549096,
      "clip_ratio/high_mean": 0.0006882075977046043,
      "clip_ratio/low_mean": 0.0006769624342268799,
      "clip_ratio/low_min": 4.554686984192813e-05,
      "clip_ratio/region_mean": 0.0013651700282935053,
      "epoch": 0.10891972770068074,
      "grad_norm": 0.2630913555622101,
      "learning_rate": 2e-07,
      "loss": 0.0476,
      "step": 1167
    },
    {
      "clip_ratio/high_max": 0.0012083029923815047,
      "clip_ratio/high_mean": 0.0005193826086724584,
      "clip_ratio/low_mean": 0.0006306533705355832,
      "clip_ratio/low_min": 2.6927695216727443e-05,
      "clip_ratio/region_mean": 0.0011500360087666195,
      "epoch": 0.10901306080068134,
      "grad_norm": 0.1636441946029663,
      "learning_rate": 2e-07,
      "loss": 0.0669,
      "step": 1168
    },
    {
      "clip_ratio/high_max": 0.001655586460401537,
      "clip_ratio/high_mean": 0.0006298368498391937,
      "clip_ratio/low_mean": 0.0006347403050313005,
      "clip_ratio/low_min": 4.4347297261992935e-05,
      "clip_ratio/region_mean": 0.001264577171241399,
      "epoch": 0.10910639390068191,
      "grad_norm": 0.17912589013576508,
      "learning_rate": 2e-07,
      "loss": 0.0482,
      "step": 1169
    },
    {
      "clip_ratio/high_max": 0.0019418290321482345,
      "clip_ratio/high_mean": 0.0006886320006742608,
      "clip_ratio/low_mean": 0.0005391031136241509,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012277351288503269,
      "epoch": 0.10919972700068249,
      "grad_norm": 0.4946267902851105,
      "learning_rate": 2e-07,
      "loss": 0.0226,
      "step": 1170
    },
    {
      "clip_ratio/high_max": 0.0020375708409119397,
      "clip_ratio/high_mean": 0.0006965673183003673,
      "clip_ratio/low_mean": 0.0006151668212623917,
      "clip_ratio/low_min": 3.526189721014816e-05,
      "clip_ratio/region_mean": 0.001311734136834275,
      "epoch": 0.10929306010068308,
      "grad_norm": 0.19428250193595886,
      "learning_rate": 2e-07,
      "loss": 0.034,
      "step": 1171
    },
    {
      "clip_ratio/high_max": 0.002049203059868887,
      "clip_ratio/high_mean": 0.0007376129869953729,
      "clip_ratio/low_mean": 0.0005875803271919722,
      "clip_ratio/low_min": 2.4418832254013978e-05,
      "clip_ratio/region_mean": 0.0013251933341962285,
      "epoch": 0.10938639320068366,
      "grad_norm": 0.16605006158351898,
      "learning_rate": 2e-07,
      "loss": -0.0002,
      "step": 1172
    },
    {
      "clip_ratio/high_max": 0.001794505755242426,
      "clip_ratio/high_mean": 0.0006250186506804312,
      "clip_ratio/low_mean": 0.0006042684271960752,
      "clip_ratio/low_min": 3.1561217838316225e-05,
      "clip_ratio/region_mean": 0.0012292870778765064,
      "epoch": 0.10947972630068425,
      "grad_norm": 0.16088369488716125,
      "learning_rate": 2e-07,
      "loss": 0.0336,
      "step": 1173
    },
    {
      "clip_ratio/high_max": 0.0018000064446823671,
      "clip_ratio/high_mean": 0.0006584975817531813,
      "clip_ratio/low_mean": 0.0006200137104315218,
      "clip_ratio/low_min": 1.1975474080827553e-05,
      "clip_ratio/region_mean": 0.001278511292184703,
      "epoch": 0.10957305940068483,
      "grad_norm": 0.15880903601646423,
      "learning_rate": 2e-07,
      "loss": 0.0109,
      "step": 1174
    },
    {
      "clip_ratio/high_max": 0.0017282588596572168,
      "clip_ratio/high_mean": 0.0006558646782650612,
      "clip_ratio/low_mean": 0.0006385556498571532,
      "clip_ratio/low_min": 4.382521547086071e-05,
      "clip_ratio/region_mean": 0.0012944203481310979,
      "epoch": 0.10966639250068541,
      "grad_norm": 0.18661294877529144,
      "learning_rate": 2e-07,
      "loss": -0.0031,
      "step": 1175
    },
    {
      "clip_ratio/high_max": 0.0016434299213869963,
      "clip_ratio/high_mean": 0.0006188478837430011,
      "clip_ratio/low_mean": 0.0007024453916528728,
      "clip_ratio/low_min": 3.1859116461419035e-05,
      "clip_ratio/region_mean": 0.0013212932717578951,
      "epoch": 0.109759725600686,
      "grad_norm": 0.1554040163755417,
      "learning_rate": 2e-07,
      "loss": 0.0004,
      "step": 1176
    },
    {
      "clip_ratio/high_max": 0.0016033118718041806,
      "clip_ratio/high_mean": 0.000590535453738994,
      "clip_ratio/low_mean": 0.0004960412416039617,
      "clip_ratio/low_min": 2.9591115890070796e-05,
      "clip_ratio/region_mean": 0.0010865766926144715,
      "epoch": 0.10985305870068658,
      "grad_norm": 0.1685456931591034,
      "learning_rate": 2e-07,
      "loss": 0.035,
      "step": 1177
    },
    {
      "clip_ratio/high_max": 0.0016119919200718869,
      "clip_ratio/high_mean": 0.0006994336872594431,
      "clip_ratio/low_mean": 0.0005080176961200777,
      "clip_ratio/low_min": 2.6680896553443745e-05,
      "clip_ratio/region_mean": 0.0012074513906554785,
      "epoch": 0.10994639180068716,
      "grad_norm": 0.1896088868379593,
      "learning_rate": 2e-07,
      "loss": 0.0153,
      "step": 1178
    },
    {
      "clip_ratio/high_max": 0.0016023181597120129,
      "clip_ratio/high_mean": 0.0006312606274150312,
      "clip_ratio/low_mean": 0.0006902899294800591,
      "clip_ratio/low_min": 2.462828706484288e-05,
      "clip_ratio/region_mean": 0.0013215505459811538,
      "epoch": 0.11003972490068775,
      "grad_norm": 0.1891086995601654,
      "learning_rate": 2e-07,
      "loss": 0.0219,
      "step": 1179
    },
    {
      "clip_ratio/high_max": 0.0012476910233090166,
      "clip_ratio/high_mean": 0.0004934763674100395,
      "clip_ratio/low_mean": 0.0006635324207309168,
      "clip_ratio/low_min": 4.6747450141992886e-05,
      "clip_ratio/region_mean": 0.001157008795416914,
      "epoch": 0.11013305800068833,
      "grad_norm": 0.17143650352954865,
      "learning_rate": 2e-07,
      "loss": 0.0636,
      "step": 1180
    },
    {
      "clip_ratio/high_max": 0.0017113645517383702,
      "clip_ratio/high_mean": 0.0006184773574204883,
      "clip_ratio/low_mean": 0.00048548767426837003,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0011039650380553212,
      "epoch": 0.11022639110068891,
      "grad_norm": 0.14065149426460266,
      "learning_rate": 2e-07,
      "loss": 0.0143,
      "step": 1181
    },
    {
      "clip_ratio/high_max": 0.0018538670265115798,
      "clip_ratio/high_mean": 0.0006766871865693247,
      "clip_ratio/low_mean": 0.0005326104687810584,
      "clip_ratio/low_min": 2.8964404918951914e-05,
      "clip_ratio/region_mean": 0.0012092976612620987,
      "epoch": 0.1103197242006895,
      "grad_norm": 0.16656944155693054,
      "learning_rate": 2e-07,
      "loss": 0.0152,
      "step": 1182
    },
    {
      "clip_ratio/high_max": 0.0014464103005593643,
      "clip_ratio/high_mean": 0.0005811582796013681,
      "clip_ratio/low_mean": 0.0005964988995401654,
      "clip_ratio/low_min": 5.2509241868392564e-05,
      "clip_ratio/region_mean": 0.0011776571664086077,
      "epoch": 0.11041305730069008,
      "grad_norm": 0.27208787202835083,
      "learning_rate": 2e-07,
      "loss": 0.0387,
      "step": 1183
    },
    {
      "clip_ratio/high_max": 0.001598800945430412,
      "clip_ratio/high_mean": 0.0006337869217531988,
      "clip_ratio/low_mean": 0.0005574716051341966,
      "clip_ratio/low_min": 1.708350464468822e-05,
      "clip_ratio/region_mean": 0.0011912585032405332,
      "epoch": 0.11050639040069067,
      "grad_norm": 0.18974028527736664,
      "learning_rate": 2e-07,
      "loss": 0.0206,
      "step": 1184
    },
    {
      "clip_ratio/high_max": 0.001642827779505751,
      "clip_ratio/high_mean": 0.0006317607490018418,
      "clip_ratio/low_mean": 0.0006463834033638705,
      "clip_ratio/low_min": 1.3194005077821203e-05,
      "clip_ratio/region_mean": 0.0012781441619154066,
      "epoch": 0.11059972350069125,
      "grad_norm": 0.22505322098731995,
      "learning_rate": 2e-07,
      "loss": 0.0435,
      "step": 1185
    },
    {
      "clip_ratio/high_max": 0.0018842271601897664,
      "clip_ratio/high_mean": 0.0007860207988414913,
      "clip_ratio/low_mean": 0.0006362721469486132,
      "clip_ratio/low_min": 4.6767963794991374e-05,
      "clip_ratio/region_mean": 0.0014222929603420198,
      "epoch": 0.11069305660069183,
      "grad_norm": 0.1873571276664734,
      "learning_rate": 2e-07,
      "loss": 0.0016,
      "step": 1186
    },
    {
      "clip_ratio/high_max": 0.0017817896768974606,
      "clip_ratio/high_mean": 0.0007156403808039613,
      "clip_ratio/low_mean": 0.0006722234193148324,
      "clip_ratio/low_min": 1.7146776372101158e-05,
      "clip_ratio/region_mean": 0.0013878637728339527,
      "epoch": 0.11078638970069242,
      "grad_norm": 0.16899481415748596,
      "learning_rate": 2e-07,
      "loss": 0.0343,
      "step": 1187
    },
    {
      "clip_ratio/high_max": 0.0016362050700990949,
      "clip_ratio/high_mean": 0.0006184279154695105,
      "clip_ratio/low_mean": 0.0007243590771395247,
      "clip_ratio/low_min": 1.903746488096658e-05,
      "clip_ratio/region_mean": 0.0013427869816950988,
      "epoch": 0.110879722800693,
      "grad_norm": 0.15989556908607483,
      "learning_rate": 2e-07,
      "loss": 0.0449,
      "step": 1188
    },
    {
      "clip_ratio/high_max": 0.00199316243379144,
      "clip_ratio/high_mean": 0.0006864378592581488,
      "clip_ratio/low_mean": 0.0006274419579312962,
      "clip_ratio/low_min": 6.376243982231244e-05,
      "clip_ratio/region_mean": 0.0013138798349245917,
      "epoch": 0.11097305590069358,
      "grad_norm": 0.4591924250125885,
      "learning_rate": 2e-07,
      "loss": 0.0635,
      "step": 1189
    },
    {
      "clip_ratio/high_max": 0.001966142121091252,
      "clip_ratio/high_mean": 0.0007865260558901355,
      "clip_ratio/low_mean": 0.0006146843179521966,
      "clip_ratio/low_min": 1.2047031304973643e-05,
      "clip_ratio/region_mean": 0.0014012104002176784,
      "epoch": 0.11106638900069417,
      "grad_norm": 0.21491265296936035,
      "learning_rate": 2e-07,
      "loss": 0.0188,
      "step": 1190
    },
    {
      "clip_ratio/high_max": 0.0017275051977776457,
      "clip_ratio/high_mean": 0.0006209878674781066,
      "clip_ratio/low_mean": 0.0006014812997818808,
      "clip_ratio/low_min": 1.3422098163573537e-05,
      "clip_ratio/region_mean": 0.001222469156346051,
      "epoch": 0.11115972210069475,
      "grad_norm": 0.14565059542655945,
      "learning_rate": 2e-07,
      "loss": 0.0311,
      "step": 1191
    },
    {
      "clip_ratio/high_max": 0.0018550388158473652,
      "clip_ratio/high_mean": 0.0007006270479905652,
      "clip_ratio/low_mean": 0.0006284281298576389,
      "clip_ratio/low_min": 9.268805297324434e-05,
      "clip_ratio/region_mean": 0.0013290551833051722,
      "epoch": 0.11125305520069532,
      "grad_norm": 0.5749951004981995,
      "learning_rate": 2e-07,
      "loss": 0.0004,
      "step": 1192
    },
    {
      "clip_ratio/high_max": 0.0016502425969520118,
      "clip_ratio/high_mean": 0.0006437225802073954,
      "clip_ratio/low_mean": 0.0006101977069192799,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012539203198684845,
      "epoch": 0.11134638830069592,
      "grad_norm": 0.18215207755565643,
      "learning_rate": 2e-07,
      "loss": -0.0004,
      "step": 1193
    },
    {
      "clip_ratio/high_max": 0.0017368491680826992,
      "clip_ratio/high_mean": 0.0006446158386097522,
      "clip_ratio/low_mean": 0.0006619600208068732,
      "clip_ratio/low_min": 3.10600134980632e-05,
      "clip_ratio/region_mean": 0.0013065758103039116,
      "epoch": 0.1114397214006965,
      "grad_norm": 0.16845083236694336,
      "learning_rate": 2e-07,
      "loss": 0.0352,
      "step": 1194
    },
    {
      "clip_ratio/high_max": 0.0018229290908493567,
      "clip_ratio/high_mean": 0.0006434263132177875,
      "clip_ratio/low_mean": 0.0005951566126896068,
      "clip_ratio/low_min": 1.622955096536316e-05,
      "clip_ratio/region_mean": 0.0012385829504637513,
      "epoch": 0.11153305450069709,
      "grad_norm": 0.16113053262233734,
      "learning_rate": 2e-07,
      "loss": 0.0105,
      "step": 1195
    },
    {
      "clip_ratio/high_max": 0.001678079177509062,
      "clip_ratio/high_mean": 0.0006365074259520043,
      "clip_ratio/low_mean": 0.0005578919335675891,
      "clip_ratio/low_min": 3.087181903538294e-05,
      "clip_ratio/region_mean": 0.0011943993740715086,
      "epoch": 0.11162638760069767,
      "grad_norm": 0.16549836099147797,
      "learning_rate": 2e-07,
      "loss": 0.0227,
      "step": 1196
    },
    {
      "clip_ratio/high_max": 0.0017848812021838967,
      "clip_ratio/high_mean": 0.0006092470175644848,
      "clip_ratio/low_mean": 0.0006880839155201102,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0012973309312656056,
      "epoch": 0.11171972070069824,
      "grad_norm": 0.18886782228946686,
      "learning_rate": 2e-07,
      "loss": 0.0765,
      "step": 1197
    },
    {
      "clip_ratio/high_max": 0.0017219117653439753,
      "clip_ratio/high_mean": 0.0006915204548931797,
      "clip_ratio/low_mean": 0.000730987159840879,
      "clip_ratio/low_min": 2.8415548513294198e-05,
      "clip_ratio/region_mean": 0.0014225076192815322,
      "epoch": 0.11181305380069884,
      "grad_norm": 0.21025022864341736,
      "learning_rate": 2e-07,
      "loss": 0.0243,
      "step": 1198
    },
    {
      "clip_ratio/high_max": 0.0019323795931995846,
      "clip_ratio/high_mean": 0.0007213194730866235,
      "clip_ratio/low_mean": 0.0006657858793914784,
      "clip_ratio/low_min": 0.00010046877105196472,
      "clip_ratio/region_mean": 0.001387105367030017,
      "epoch": 0.11190638690069941,
      "grad_norm": 0.18716835975646973,
      "learning_rate": 2e-07,
      "loss": 0.0293,
      "step": 1199
    },
    {
      "clip_ratio/high_max": 0.0017354464616801124,
      "clip_ratio/high_mean": 0.0007719640343566425,
      "clip_ratio/low_mean": 0.000552290217456175,
      "clip_ratio/low_min": 3.8159451833053026e-05,
      "clip_ratio/region_mean": 0.0013242542481748387,
      "epoch": 0.11199972000069999,
      "grad_norm": 0.1823512613773346,
      "learning_rate": 2e-07,
      "loss": -0.0054,
      "step": 1200
    },
    {
      "clip_ratio/high_max": 0.002123392197972862,
      "clip_ratio/high_mean": 0.0007648910795978736,
      "clip_ratio/low_mean": 0.000654587323879241,
      "clip_ratio/low_min": 4.306902155803982e-05,
      "clip_ratio/region_mean": 0.0014194783907441888,
      "epoch": 0.11209305310070058,
      "grad_norm": 0.16624779999256134,
      "learning_rate": 2e-07,
      "loss": 0.0073,
      "step": 1201
    },
    {
      "clip_ratio/high_max": 0.0017743766184139531,
      "clip_ratio/high_mean": 0.0006593586058443179,
      "clip_ratio/low_mean": 0.0008040177126531489,
      "clip_ratio/low_min": 1.5689720385125838e-05,
      "clip_ratio/region_mean": 0.0014633763566962443,
      "epoch": 0.11218638620070116,
      "grad_norm": 0.1570969521999359,
      "learning_rate": 2e-07,
      "loss": 0.056,
      "step": 1202
    },
    {
      "clip_ratio/high_max": 0.0020229958172421902,
      "clip_ratio/high_mean": 0.0006610530053876573,
      "clip_ratio/low_mean": 0.0006030327594999108,
      "clip_ratio/low_min": 5.476691057992866e-06,
      "clip_ratio/region_mean": 0.001264085734874243,
      "epoch": 0.11227971930070174,
      "grad_norm": 0.1563320904970169,
      "learning_rate": 2e-07,
      "loss": 0.0139,
      "step": 1203
    },
    {
      "clip_ratio/high_max": 0.0021467497608682606,
      "clip_ratio/high_mean": 0.0007964446558617055,
      "clip_ratio/low_mean": 0.0006419783203455154,
      "clip_ratio/low_min": 7.026428193057654e-05,
      "clip_ratio/region_mean": 0.0014384229725692421,
      "epoch": 0.11237305240070233,
      "grad_norm": 0.2023751139640808,
      "learning_rate": 2e-07,
      "loss": 0.0351,
      "step": 1204
    },
    {
      "clip_ratio/high_max": 0.0019305036003061105,
      "clip_ratio/high_mean": 0.0006750689281034283,
      "clip_ratio/low_mean": 0.0006261421331146266,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013012110721319914,
      "epoch": 0.11246638550070291,
      "grad_norm": 0.1906033605337143,
      "learning_rate": 2e-07,
      "loss": -0.0271,
      "step": 1205
    },
    {
      "clip_ratio/high_max": 0.0017085464678530116,
      "clip_ratio/high_mean": 0.0005854409346284228,
      "clip_ratio/low_mean": 0.0007824249878467526,
      "clip_ratio/low_min": 0.00010180927347391844,
      "clip_ratio/region_mean": 0.0013678659161087126,
      "epoch": 0.1125597186007035,
      "grad_norm": 0.2597927153110504,
      "learning_rate": 2e-07,
      "loss": 0.071,
      "step": 1206
    },
    {
      "clip_ratio/high_max": 0.001963698934559943,
      "clip_ratio/high_mean": 0.0008281957561848685,
      "clip_ratio/low_mean": 0.0006396881535692955,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001467883885197807,
      "epoch": 0.11265305170070408,
      "grad_norm": 0.19650326669216156,
      "learning_rate": 2e-07,
      "loss": -0.007,
      "step": 1207
    },
    {
      "clip_ratio/high_max": 0.0015268050628947094,
      "clip_ratio/high_mean": 0.0006416117812477751,
      "clip_ratio/low_mean": 0.000657591290291748,
      "clip_ratio/low_min": 2.282396781083662e-05,
      "clip_ratio/region_mean": 0.0012992030497116502,
      "epoch": 0.11274638480070466,
      "grad_norm": 0.19723127782344818,
      "learning_rate": 2e-07,
      "loss": 0.0356,
      "step": 1208
    },
    {
      "clip_ratio/high_max": 0.0017499780005891807,
      "clip_ratio/high_mean": 0.0006795383778808173,
      "clip_ratio/low_mean": 0.0007303121928998735,
      "clip_ratio/low_min": 4.5773445890517905e-05,
      "clip_ratio/region_mean": 0.0014098505707806908,
      "epoch": 0.11283971790070525,
      "grad_norm": 0.21628065407276154,
      "learning_rate": 2e-07,
      "loss": 0.0364,
      "step": 1209
    },
    {
      "clip_ratio/high_max": 0.0023353828728431836,
      "clip_ratio/high_mean": 0.0007169713007897371,
      "clip_ratio/low_mean": 0.000739826139579236,
      "clip_ratio/low_min": 8.280283600470284e-05,
      "clip_ratio/region_mean": 0.0014567974540113937,
      "epoch": 0.11293305100070583,
      "grad_norm": 0.1804220825433731,
      "learning_rate": 2e-07,
      "loss": 0.0159,
      "step": 1210
    },
    {
      "clip_ratio/high_max": 0.002023077664489392,
      "clip_ratio/high_mean": 0.0007972766070452053,
      "clip_ratio/low_mean": 0.0005483621807798045,
      "clip_ratio/low_min": 3.2717113754188176e-05,
      "clip_ratio/region_mean": 0.0013456387459882535,
      "epoch": 0.11302638410070641,
      "grad_norm": 0.19473648071289062,
      "learning_rate": 2e-07,
      "loss": -0.0542,
      "step": 1211
    },
    {
      "clip_ratio/high_max": 0.0018410850389045663,
      "clip_ratio/high_mean": 0.0006798792483095895,
      "clip_ratio/low_mean": 0.0007240676018227532,
      "clip_ratio/low_min": 2.9584543881355785e-05,
      "clip_ratio/region_mean": 0.001403946847858606,
      "epoch": 0.113119717200707,
      "grad_norm": 0.17801834642887115,
      "learning_rate": 2e-07,
      "loss": 0.0321,
      "step": 1212
    },
    {
      "clip_ratio/high_max": 0.0016314754975610413,
      "clip_ratio/high_mean": 0.0006564184877788648,
      "clip_ratio/low_mean": 0.0006458212155848742,
      "clip_ratio/low_min": 4.021795939479489e-05,
      "clip_ratio/region_mean": 0.0013022397106396966,
      "epoch": 0.11321305030070758,
      "grad_norm": 0.1814417839050293,
      "learning_rate": 2e-07,
      "loss": 0.052,
      "step": 1213
    },
    {
      "clip_ratio/high_max": 0.0017815642822824884,
      "clip_ratio/high_mean": 0.0006610833333979826,
      "clip_ratio/low_mean": 0.0006980185844440712,
      "clip_ratio/low_min": 4.563658148981631e-05,
      "clip_ratio/region_mean": 0.001359101905109128,
      "epoch": 0.11330638340070817,
      "grad_norm": 0.23626896739006042,
      "learning_rate": 2e-07,
      "loss": 0.0731,
      "step": 1214
    },
    {
      "clip_ratio/high_max": 0.0015849441624595784,
      "clip_ratio/high_mean": 0.0006159991407912457,
      "clip_ratio/low_mean": 0.0006856236250314396,
      "clip_ratio/low_min": 1.137397612183122e-05,
      "clip_ratio/region_mean": 0.0013016227712796535,
      "epoch": 0.11339971650070875,
      "grad_norm": 0.1933341771364212,
      "learning_rate": 2e-07,
      "loss": 0.0808,
      "step": 1215
    },
    {
      "clip_ratio/high_max": 0.0017681787358014844,
      "clip_ratio/high_mean": 0.0007517805624956964,
      "clip_ratio/low_mean": 0.0006485622716354555,
      "clip_ratio/low_min": 5.328930819814559e-05,
      "clip_ratio/region_mean": 0.001400342836859636,
      "epoch": 0.11349304960070933,
      "grad_norm": 0.22811280190944672,
      "learning_rate": 2e-07,
      "loss": 0.0458,
      "step": 1216
    },
    {
      "clip_ratio/high_max": 0.0017768497200449929,
      "clip_ratio/high_mean": 0.0006977675366215408,
      "clip_ratio/low_mean": 0.000740344501537038,
      "clip_ratio/low_min": 2.5202437427651603e-05,
      "clip_ratio/region_mean": 0.0014381120381585788,
      "epoch": 0.11358638270070992,
      "grad_norm": 0.21421846747398376,
      "learning_rate": 2e-07,
      "loss": 0.0398,
      "step": 1217
    },
    {
      "clip_ratio/high_max": 0.0018747972098935861,
      "clip_ratio/high_mean": 0.0006923552791704424,
      "clip_ratio/low_mean": 0.0006740733460901538,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.00136642867437331,
      "epoch": 0.1136797158007105,
      "grad_norm": 0.2485412061214447,
      "learning_rate": 2e-07,
      "loss": 0.0284,
      "step": 1218
    },
    {
      "clip_ratio/high_max": 0.0018189503971370868,
      "clip_ratio/high_mean": 0.0007034794780338416,
      "clip_ratio/low_mean": 0.000622761515842285,
      "clip_ratio/low_min": 2.8036334697389975e-05,
      "clip_ratio/region_mean": 0.0013262410211609676,
      "epoch": 0.11377304890071108,
      "grad_norm": 0.1935350000858307,
      "learning_rate": 2e-07,
      "loss": 0.0027,
      "step": 1219
    },
    {
      "clip_ratio/high_max": 0.0018007807702815626,
      "clip_ratio/high_mean": 0.0007380261595244519,
      "clip_ratio/low_mean": 0.0006788272421545116,
      "clip_ratio/low_min": 1.200999213324394e-05,
      "clip_ratio/region_mean": 0.001416853363480186,
      "epoch": 0.11386638200071167,
      "grad_norm": 0.19330981373786926,
      "learning_rate": 2e-07,
      "loss": 0.0168,
      "step": 1220
    },
    {
      "clip_ratio/high_max": 0.001946432650584029,
      "clip_ratio/high_mean": 0.0008022147212614072,
      "clip_ratio/low_mean": 0.0006667568250122713,
      "clip_ratio/low_min": 3.8755119931010995e-05,
      "clip_ratio/region_mean": 0.0014689715535496362,
      "epoch": 0.11395971510071225,
      "grad_norm": 0.18847449123859406,
      "learning_rate": 2e-07,
      "loss": 0.0076,
      "step": 1221
    },
    {
      "clip_ratio/high_max": 0.0016450900511699729,
      "clip_ratio/high_mean": 0.0006838346052973066,
      "clip_ratio/low_mean": 0.0007193425808509346,
      "clip_ratio/low_min": 4.710746361524798e-05,
      "clip_ratio/region_mean": 0.0014031771970621776,
      "epoch": 0.11405304820071283,
      "grad_norm": 0.27726420760154724,
      "learning_rate": 2e-07,
      "loss": 0.0122,
      "step": 1222
    },
    {
      "clip_ratio/high_max": 0.0021418637334136292,
      "clip_ratio/high_mean": 0.0007826969977031695,
      "clip_ratio/low_mean": 0.0006444951497996954,
      "clip_ratio/low_min": 1.4417531929211691e-05,
      "clip_ratio/region_mean": 0.001427192171831848,
      "epoch": 0.11414638130071342,
      "grad_norm": 0.27614083886146545,
      "learning_rate": 2e-07,
      "loss": -0.0068,
      "step": 1223
    },
    {
      "clip_ratio/high_max": 0.0015291256459022406,
      "clip_ratio/high_mean": 0.0006138509252195945,
      "clip_ratio/low_mean": 0.000735232946681208,
      "clip_ratio/low_min": 3.415183255128795e-05,
      "clip_ratio/region_mean": 0.0013490838355210144,
      "epoch": 0.114239714400714,
      "grad_norm": 0.20824365317821503,
      "learning_rate": 2e-07,
      "loss": 0.0448,
      "step": 1224
    },
    {
      "clip_ratio/high_max": 0.002354316762648523,
      "clip_ratio/high_mean": 0.0008129967191052856,
      "clip_ratio/low_mean": 0.0005285174229356926,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.00134151413658401,
      "epoch": 0.11433304750071459,
      "grad_norm": 0.17510150372982025,
      "learning_rate": 2e-07,
      "loss": -0.0365,
      "step": 1225
    },
    {
      "clip_ratio/high_max": 0.0019088539411313832,
      "clip_ratio/high_mean": 0.0007080216564645525,
      "clip_ratio/low_mean": 0.000813225031379261,
      "clip_ratio/low_min": 4.328796057961881e-05,
      "clip_ratio/region_mean": 0.0015212466387310997,
      "epoch": 0.11442638060071517,
      "grad_norm": 0.20113784074783325,
      "learning_rate": 2e-07,
      "loss": 0.0468,
      "step": 1226
    },
    {
      "clip_ratio/high_max": 0.0020745092260767706,
      "clip_ratio/high_mean": 0.0007107132914825343,
      "clip_ratio/low_mean": 0.0007181372657214524,
      "clip_ratio/low_min": 5.305122795107309e-05,
      "clip_ratio/region_mean": 0.0014288505481090397,
      "epoch": 0.11451971370071574,
      "grad_norm": 0.220927894115448,
      "learning_rate": 2e-07,
      "loss": 0.0602,
      "step": 1227
    },
    {
      "clip_ratio/high_max": 0.0016867046615516301,
      "clip_ratio/high_mean": 0.0006076824884075904,
      "clip_ratio/low_mean": 0.000760385706598754,
      "clip_ratio/low_min": 9.021905225381488e-05,
      "clip_ratio/region_mean": 0.0013680681877303869,
      "epoch": 0.11461304680071634,
      "grad_norm": 0.31231027841567993,
      "learning_rate": 2e-07,
      "loss": 0.0537,
      "step": 1228
    },
    {
      "clip_ratio/high_max": 0.0017079940444091335,
      "clip_ratio/high_mean": 0.0007021579367574304,
      "clip_ratio/low_mean": 0.0007262806084327167,
      "clip_ratio/low_min": 5.8474061006563716e-05,
      "clip_ratio/region_mean": 0.0014284385470091365,
      "epoch": 0.11470637990071691,
      "grad_norm": 0.20768561959266663,
      "learning_rate": 2e-07,
      "loss": 0.0192,
      "step": 1229
    },
    {
      "clip_ratio/high_max": 0.001813379631130374,
      "clip_ratio/high_mean": 0.0007907981821517751,
      "clip_ratio/low_mean": 0.0005893414017918985,
      "clip_ratio/low_min": 4.112740862183273e-05,
      "clip_ratio/region_mean": 0.0013801395652990323,
      "epoch": 0.1147997130007175,
      "grad_norm": 0.21587878465652466,
      "learning_rate": 2e-07,
      "loss": -0.0061,
      "step": 1230
    },
    {
      "clip_ratio/high_max": 0.001871857457445003,
      "clip_ratio/high_mean": 0.0007189674815890612,
      "clip_ratio/low_mean": 0.0007085789748089155,
      "clip_ratio/low_min": 4.5587553358927835e-05,
      "clip_ratio/region_mean": 0.001427546470949892,
      "epoch": 0.11489304610071809,
      "grad_norm": 0.26298826932907104,
      "learning_rate": 2e-07,
      "loss": -0.0019,
      "step": 1231
    },
    {
      "clip_ratio/high_max": 0.001995592585444683,
      "clip_ratio/high_mean": 0.0007535356699008844,
      "clip_ratio/low_mean": 0.000834016980661545,
      "clip_ratio/low_min": 5.5207642617460806e-05,
      "clip_ratio/region_mean": 0.0015875526405579876,
      "epoch": 0.11498637920071866,
      "grad_norm": 0.22382621467113495,
      "learning_rate": 2e-07,
      "loss": 0.0709,
      "step": 1232
    },
    {
      "clip_ratio/high_max": 0.0020703155823866837,
      "clip_ratio/high_mean": 0.0007313550704566296,
      "clip_ratio/low_mean": 0.0007691301052545896,
      "clip_ratio/low_min": 9.533536695016664e-05,
      "clip_ratio/region_mean": 0.0015004851484263781,
      "epoch": 0.11507971230071924,
      "grad_norm": 0.3064039349555969,
      "learning_rate": 2e-07,
      "loss": 0.0562,
      "step": 1233
    },
    {
      "clip_ratio/high_max": 0.0014994187768024858,
      "clip_ratio/high_mean": 0.0006033366826159181,
      "clip_ratio/low_mean": 0.0008681757535669021,
      "clip_ratio/low_min": 0.00011312712194921914,
      "clip_ratio/region_mean": 0.0014715124416397884,
      "epoch": 0.11517304540071983,
      "grad_norm": 0.20792166888713837,
      "learning_rate": 2e-07,
      "loss": 0.0658,
      "step": 1234
    },
    {
      "clip_ratio/high_max": 0.0015238021151162684,
      "clip_ratio/high_mean": 0.0006355091554723913,
      "clip_ratio/low_mean": 0.0007760861117276363,
      "clip_ratio/low_min": 2.3273132683243603e-05,
      "clip_ratio/region_mean": 0.0014115952762949746,
      "epoch": 0.11526637850072041,
      "grad_norm": 0.18855012953281403,
      "learning_rate": 2e-07,
      "loss": 0.0541,
      "step": 1235
    },
    {
      "clip_ratio/high_max": 0.001760505332640605,
      "clip_ratio/high_mean": 0.0007069724961183965,
      "clip_ratio/low_mean": 0.000678924696330796,
      "clip_ratio/low_min": 3.358627509442158e-05,
      "clip_ratio/region_mean": 0.0013858971615263727,
      "epoch": 0.115359711600721,
      "grad_norm": 0.24031035602092743,
      "learning_rate": 2e-07,
      "loss": 0.0435,
      "step": 1236
    },
    {
      "clip_ratio/high_max": 0.001999726733629359,
      "clip_ratio/high_mean": 0.0007284773710125592,
      "clip_ratio/low_mean": 0.0008245931167039089,
      "clip_ratio/low_min": 1.3343295904633123e-05,
      "clip_ratio/region_mean": 0.001553070527734235,
      "epoch": 0.11545304470072158,
      "grad_norm": 0.2353406697511673,
      "learning_rate": 2e-07,
      "loss": 0.0578,
      "step": 1237
    },
    {
      "clip_ratio/high_max": 0.002238269667941495,
      "clip_ratio/high_mean": 0.0008678373433212982,
      "clip_ratio/low_mean": 0.0008464150250802049,
      "clip_ratio/low_min": 2.5683171770651825e-05,
      "clip_ratio/region_mean": 0.0017142523574875668,
      "epoch": 0.11554637780072216,
      "grad_norm": 0.1996588557958603,
      "learning_rate": 2e-07,
      "loss": 0.0098,
      "step": 1238
    },
    {
      "clip_ratio/high_max": 0.0023110997608455364,
      "clip_ratio/high_mean": 0.0008199171279557049,
      "clip_ratio/low_mean": 0.0008518363028997555,
      "clip_ratio/low_min": 5.146158582647331e-05,
      "clip_ratio/region_mean": 0.0016717534163035452,
      "epoch": 0.11563971090072275,
      "grad_norm": 4.392289161682129,
      "learning_rate": 2e-07,
      "loss": 0.0443,
      "step": 1239
    },
    {
      "clip_ratio/high_max": 0.001825257679229253,
      "clip_ratio/high_mean": 0.0007007856834206905,
      "clip_ratio/low_mean": 0.000799260741132457,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001500046471846872,
      "epoch": 0.11573304400072333,
      "grad_norm": 0.257712721824646,
      "learning_rate": 2e-07,
      "loss": 0.0696,
      "step": 1240
    },
    {
      "clip_ratio/high_max": 0.0021302935274434276,
      "clip_ratio/high_mean": 0.0008179210799426073,
      "clip_ratio/low_mean": 0.000769412579757045,
      "clip_ratio/low_min": 6.361843406921253e-05,
      "clip_ratio/region_mean": 0.0015873336815275252,
      "epoch": 0.11582637710072391,
      "grad_norm": 0.23931963741779327,
      "learning_rate": 2e-07,
      "loss": 0.02,
      "step": 1241
    },
    {
      "clip_ratio/high_max": 0.002196750858274754,
      "clip_ratio/high_mean": 0.0008153451108228182,
      "clip_ratio/low_mean": 0.0007461098502972163,
      "clip_ratio/low_min": 2.883926390495617e-05,
      "clip_ratio/region_mean": 0.0015614549847668968,
      "epoch": 0.1159197102007245,
      "grad_norm": 0.21287751197814941,
      "learning_rate": 2e-07,
      "loss": 0.0236,
      "step": 1242
    },
    {
      "clip_ratio/high_max": 0.0019600256928242743,
      "clip_ratio/high_mean": 0.0007343806810240494,
      "clip_ratio/low_mean": 0.0009392539177497383,
      "clip_ratio/low_min": 3.688192373374477e-05,
      "clip_ratio/region_mean": 0.00167363462242065,
      "epoch": 0.11601304330072508,
      "grad_norm": 0.2388520985841751,
      "learning_rate": 2e-07,
      "loss": 0.0665,
      "step": 1243
    },
    {
      "clip_ratio/high_max": 0.002049018112302292,
      "clip_ratio/high_mean": 0.0007977996792760678,
      "clip_ratio/low_mean": 0.0009095584573515225,
      "clip_ratio/low_min": 5.842214795848122e-05,
      "clip_ratio/region_mean": 0.0017073581329896115,
      "epoch": 0.11610637640072566,
      "grad_norm": 0.24122431874275208,
      "learning_rate": 2e-07,
      "loss": 0.0196,
      "step": 1244
    },
    {
      "clip_ratio/high_max": 0.002036123725702055,
      "clip_ratio/high_mean": 0.0008964891894720495,
      "clip_ratio/low_mean": 0.0007354551507887663,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0016319443384418264,
      "epoch": 0.11619970950072625,
      "grad_norm": 0.20469529926776886,
      "learning_rate": 2e-07,
      "loss": -0.0257,
      "step": 1245
    },
    {
      "clip_ratio/high_max": 0.0019104303100903053,
      "clip_ratio/high_mean": 0.0006784113566027372,
      "clip_ratio/low_mean": 0.0008821239989629248,
      "clip_ratio/low_min": 7.028521940810606e-05,
      "clip_ratio/region_mean": 0.0015605353546561673,
      "epoch": 0.11629304260072683,
      "grad_norm": 0.22279538214206696,
      "learning_rate": 2e-07,
      "loss": 0.0453,
      "step": 1246
    },
    {
      "clip_ratio/high_max": 0.002346692497667391,
      "clip_ratio/high_mean": 0.0009934938534570392,
      "clip_ratio/low_mean": 0.0007314088952625752,
      "clip_ratio/low_min": 7.161081703088712e-05,
      "clip_ratio/region_mean": 0.001724902780551929,
      "epoch": 0.11638637570072742,
      "grad_norm": 10.260732650756836,
      "learning_rate": 2e-07,
      "loss": -0.0227,
      "step": 1247
    },
    {
      "clip_ratio/high_max": 0.0020246249841875397,
      "clip_ratio/high_mean": 0.000756393466872396,
      "clip_ratio/low_mean": 0.0008872840517142322,
      "clip_ratio/low_min": 2.3005634830042254e-05,
      "clip_ratio/region_mean": 0.0016436775185866281,
      "epoch": 0.116479708800728,
      "grad_norm": 0.2727806866168976,
      "learning_rate": 2e-07,
      "loss": 0.045,
      "step": 1248
    },
    {
      "clip_ratio/high_max": 0.0019652216797112487,
      "clip_ratio/high_mean": 0.0008002615377336042,
      "clip_ratio/low_mean": 0.0007939530096336966,
      "clip_ratio/low_min": 4.6326510528160725e-05,
      "clip_ratio/region_mean": 0.0015942145910230465,
      "epoch": 0.11657304190072858,
      "grad_norm": 0.25504693388938904,
      "learning_rate": 2e-07,
      "loss": 0.0093,
      "step": 1249
    },
    {
      "clip_ratio/high_max": 0.002215296346548712,
      "clip_ratio/high_mean": 0.0007826925266272156,
      "clip_ratio/low_mean": 0.000982078752713278,
      "clip_ratio/low_min": 6.717219548590947e-05,
      "clip_ratio/region_mean": 0.0017647712738835253,
      "epoch": 0.11666637500072917,
      "grad_norm": 0.2266179621219635,
      "learning_rate": 2e-07,
      "loss": 0.0369,
      "step": 1250
    },
    {
      "clip_ratio/high_max": 0.0019647805002023233,
      "clip_ratio/high_mean": 0.0007041130820653052,
      "clip_ratio/low_mean": 0.0007562920618511271,
      "clip_ratio/low_min": 5.909408537263516e-05,
      "clip_ratio/region_mean": 0.0014604051248170435,
      "epoch": 0.11675970810072975,
      "grad_norm": 0.29295626282691956,
      "learning_rate": 2e-07,
      "loss": 0.0724,
      "step": 1251
    },
    {
      "clip_ratio/high_max": 0.0020743414024764206,
      "clip_ratio/high_mean": 0.0008697340817889199,
      "clip_ratio/low_mean": 0.0010383620683569461,
      "clip_ratio/low_min": 5.647818124998594e-05,
      "clip_ratio/region_mean": 0.0019080961283179931,
      "epoch": 0.11685304120073033,
      "grad_norm": 12.287240028381348,
      "learning_rate": 2e-07,
      "loss": 0.0506,
      "step": 1252
    },
    {
      "clip_ratio/high_max": 0.002025371439231094,
      "clip_ratio/high_mean": 0.0007783571127220057,
      "clip_ratio/low_mean": 0.0009971768995455932,
      "clip_ratio/low_min": 1.2964115740032867e-05,
      "clip_ratio/region_mean": 0.0017755339868017472,
      "epoch": 0.11694637430073092,
      "grad_norm": 0.2508259117603302,
      "learning_rate": 2e-07,
      "loss": 0.0477,
      "step": 1253
    },
    {
      "clip_ratio/high_max": 0.002316706650162814,
      "clip_ratio/high_mean": 0.0008681285271450179,
      "clip_ratio/low_mean": 0.0009755221362865996,
      "clip_ratio/low_min": 3.444724097789731e-05,
      "clip_ratio/region_mean": 0.0018436506943544373,
      "epoch": 0.1170397074007315,
      "grad_norm": 0.26576414704322815,
      "learning_rate": 2e-07,
      "loss": 0.0055,
      "step": 1254
    },
    {
      "clip_ratio/high_max": 0.0018528344735386781,
      "clip_ratio/high_mean": 0.0008110902126645669,
      "clip_ratio/low_mean": 0.0009734508494148031,
      "clip_ratio/low_min": 6.097308823882486e-05,
      "clip_ratio/region_mean": 0.0017845410402514972,
      "epoch": 0.11713304050073207,
      "grad_norm": 0.2170669138431549,
      "learning_rate": 2e-07,
      "loss": 0.0319,
      "step": 1255
    },
    {
      "clip_ratio/high_max": 0.002197306130256038,
      "clip_ratio/high_mean": 0.0009107797322940314,
      "clip_ratio/low_mean": 0.000995673155557597,
      "clip_ratio/low_min": 7.87351109465817e-05,
      "clip_ratio/region_mean": 0.0019064528969465755,
      "epoch": 0.11722637360073267,
      "grad_norm": 0.24046719074249268,
      "learning_rate": 2e-07,
      "loss": -0.0069,
      "step": 1256
    },
    {
      "clip_ratio/high_max": 0.0022432658151956275,
      "clip_ratio/high_mean": 0.0007830854065105086,
      "clip_ratio/low_mean": 0.00100970386301924,
      "clip_ratio/low_min": 1.2016919754387345e-05,
      "clip_ratio/region_mean": 0.0017927893168234732,
      "epoch": 0.11731970670073325,
      "grad_norm": 0.9291532635688782,
      "learning_rate": 2e-07,
      "loss": 0.044,
      "step": 1257
    },
    {
      "clip_ratio/high_max": 0.002338208898436278,
      "clip_ratio/high_mean": 0.0009733000224514399,
      "clip_ratio/low_mean": 0.001056001736287726,
      "clip_ratio/low_min": 5.24069182574749e-05,
      "clip_ratio/region_mean": 0.002029301795118954,
      "epoch": 0.11741303980073384,
      "grad_norm": 0.3018883466720581,
      "learning_rate": 2e-07,
      "loss": 0.0546,
      "step": 1258
    },
    {
      "clip_ratio/high_max": 0.002101969403156545,
      "clip_ratio/high_mean": 0.0008679473103256896,
      "clip_ratio/low_mean": 0.0010254984863422578,
      "clip_ratio/low_min": 6.449223383242497e-05,
      "clip_ratio/region_mean": 0.0018934457802970428,
      "epoch": 0.11750637290073442,
      "grad_norm": 0.24048177897930145,
      "learning_rate": 2e-07,
      "loss": 0.0151,
      "step": 1259
    },
    {
      "clip_ratio/high_max": 0.0021233339502941817,
      "clip_ratio/high_mean": 0.0008342386627191445,
      "clip_ratio/low_mean": 0.001055306072885287,
      "clip_ratio/low_min": 6.914673076607869e-05,
      "clip_ratio/region_mean": 0.0018895446992246434,
      "epoch": 0.117599706000735,
      "grad_norm": 0.3301331698894501,
      "learning_rate": 2e-07,
      "loss": 0.0336,
      "step": 1260
    },
    {
      "clip_ratio/high_max": 0.0021031348514952697,
      "clip_ratio/high_mean": 0.0008741130095586414,
      "clip_ratio/low_mean": 0.0011592530045163585,
      "clip_ratio/low_min": 5.5464362958446145e-05,
      "clip_ratio/region_mean": 0.002033366014075,
      "epoch": 0.11769303910073559,
      "grad_norm": 0.3050091564655304,
      "learning_rate": 2e-07,
      "loss": 0.0383,
      "step": 1261
    },
    {
      "clip_ratio/high_max": 0.002194752509240061,
      "clip_ratio/high_mean": 0.0008979595404525753,
      "clip_ratio/low_mean": 0.001517905060609337,
      "clip_ratio/low_min": 0.00020412803496583365,
      "clip_ratio/region_mean": 0.00241586454649223,
      "epoch": 0.11778637220073616,
      "grad_norm": 0.34791383147239685,
      "learning_rate": 2e-07,
      "loss": 0.0743,
      "step": 1262
    },
    {
      "clip_ratio/high_max": 0.0024040390708250925,
      "clip_ratio/high_mean": 0.0009456051338929683,
      "clip_ratio/low_mean": 0.0011774161066568922,
      "clip_ratio/low_min": 7.642715718247928e-05,
      "clip_ratio/region_mean": 0.002123021251463797,
      "epoch": 0.11787970530073674,
      "grad_norm": 0.27156931161880493,
      "learning_rate": 2e-07,
      "loss": 0.015,
      "step": 1263
    },
    {
      "clip_ratio/high_max": 0.0021734513211413287,
      "clip_ratio/high_mean": 0.0009090211297007045,
      "clip_ratio/low_mean": 0.001424410096660722,
      "clip_ratio/low_min": 9.035143466462614e-05,
      "clip_ratio/region_mean": 0.002333431286388077,
      "epoch": 0.11797303840073733,
      "grad_norm": 0.3664061427116394,
      "learning_rate": 2e-07,
      "loss": 0.0807,
      "step": 1264
    },
    {
      "clip_ratio/high_max": 0.001962700673175277,
      "clip_ratio/high_mean": 0.0008608010120951803,
      "clip_ratio/low_mean": 0.0010642087181622628,
      "clip_ratio/low_min": 5.5411504945368506e-05,
      "clip_ratio/region_mean": 0.0019250096811447293,
      "epoch": 0.11806637150073791,
      "grad_norm": 0.34462690353393555,
      "learning_rate": 2e-07,
      "loss": 0.041,
      "step": 1265
    },
    {
      "clip_ratio/high_max": 0.0024077000343822874,
      "clip_ratio/high_mean": 0.0009383187498315237,
      "clip_ratio/low_mean": 0.00111204542190535,
      "clip_ratio/low_min": 8.336667633557227e-06,
      "clip_ratio/region_mean": 0.002050364149909001,
      "epoch": 0.1181597046007385,
      "grad_norm": 0.2464223951101303,
      "learning_rate": 2e-07,
      "loss": -0.0096,
      "step": 1266
    },
    {
      "clip_ratio/high_max": 0.0025267136152251624,
      "clip_ratio/high_mean": 0.001028686594509054,
      "clip_ratio/low_mean": 0.001256505973287858,
      "clip_ratio/low_min": 9.591557500243653e-05,
      "clip_ratio/region_mean": 0.002285192553244997,
      "epoch": 0.11825303770073908,
      "grad_norm": 0.269366055727005,
      "learning_rate": 2e-07,
      "loss": -0.004,
      "step": 1267
    },
    {
      "clip_ratio/high_max": 0.002575017075287178,
      "clip_ratio/high_mean": 0.001032883894367842,
      "clip_ratio/low_mean": 0.001359586418402614,
      "clip_ratio/low_min": 4.977024218533188e-05,
      "clip_ratio/region_mean": 0.0023924702472868375,
      "epoch": 0.11834637080073966,
      "grad_norm": 0.39204010367393494,
      "learning_rate": 2e-07,
      "loss": -0.0023,
      "step": 1268
    },
    {
      "clip_ratio/high_max": 0.002847917392500676,
      "clip_ratio/high_mean": 0.0010294341227563564,
      "clip_ratio/low_mean": 0.001372111619275529,
      "clip_ratio/low_min": 0.00013289974776853342,
      "clip_ratio/region_mean": 0.0024015457529458217,
      "epoch": 0.11843970390074025,
      "grad_norm": 0.4098057150840759,
      "learning_rate": 2e-07,
      "loss": 0.0185,
      "step": 1269
    },
    {
      "clip_ratio/high_max": 0.0024046394100878388,
      "clip_ratio/high_mean": 0.0008807622689346317,
      "clip_ratio/low_mean": 0.001354486339550931,
      "clip_ratio/low_min": 9.513880468148272e-05,
      "clip_ratio/region_mean": 0.0022352485902956687,
      "epoch": 0.11853303700074083,
      "grad_norm": 0.3981229066848755,
      "learning_rate": 2e-07,
      "loss": 0.0462,
      "step": 1270
    },
    {
      "clip_ratio/high_max": 0.002377386554144323,
      "clip_ratio/high_mean": 0.0009606256753613707,
      "clip_ratio/low_mean": 0.0014499417884508148,
      "clip_ratio/low_min": 0.00019184387747372966,
      "clip_ratio/region_mean": 0.0024105674601742066,
      "epoch": 0.11862637010074141,
      "grad_norm": 0.3201233744621277,
      "learning_rate": 2e-07,
      "loss": 0.0349,
      "step": 1271
    },
    {
      "clip_ratio/high_max": 0.0021397609780251514,
      "clip_ratio/high_mean": 0.000795558151367004,
      "clip_ratio/low_mean": 0.0012330156278039794,
      "clip_ratio/low_min": 6.209020284586586e-06,
      "clip_ratio/region_mean": 0.002028573813731782,
      "epoch": 0.118719703200742,
      "grad_norm": 0.29944702982902527,
      "learning_rate": 2e-07,
      "loss": 0.0488,
      "step": 1272
    },
    {
      "clip_ratio/high_max": 0.0021472515290952288,
      "clip_ratio/high_mean": 0.000861019795138418,
      "clip_ratio/low_mean": 0.0014865241682855412,
      "clip_ratio/low_min": 0.0002455126068525715,
      "clip_ratio/region_mean": 0.002347543944779318,
      "epoch": 0.11881303630074258,
      "grad_norm": 0.3404085040092468,
      "learning_rate": 2e-07,
      "loss": 0.0127,
      "step": 1273
    },
    {
      "clip_ratio/high_max": 0.002644624728418421,
      "clip_ratio/high_mean": 0.0010759932010842022,
      "clip_ratio/low_mean": 0.0011998535046586767,
      "clip_ratio/low_min": 5.289918954076711e-05,
      "clip_ratio/region_mean": 0.0022758467093808576,
      "epoch": 0.11890636940074316,
      "grad_norm": 0.6112203598022461,
      "learning_rate": 2e-07,
      "loss": -0.0042,
      "step": 1274
    },
    {
      "clip_ratio/high_max": 0.0028735673913615756,
      "clip_ratio/high_mean": 0.001140658583608456,
      "clip_ratio/low_mean": 0.0013515157279471168,
      "clip_ratio/low_min": 9.274819421989378e-05,
      "clip_ratio/region_mean": 0.0024921743315644562,
      "epoch": 0.11899970250074375,
      "grad_norm": 0.3619697093963623,
      "learning_rate": 2e-07,
      "loss": -0.0096,
      "step": 1275
    },
    {
      "clip_ratio/high_max": 0.002722287201322615,
      "clip_ratio/high_mean": 0.0010953694445561268,
      "clip_ratio/low_mean": 0.00137232463566761,
      "clip_ratio/low_min": 9.765392314875498e-05,
      "clip_ratio/region_mean": 0.0024676940811332315,
      "epoch": 0.11909303560074433,
      "grad_norm": 1.1415901184082031,
      "learning_rate": 2e-07,
      "loss": 0.0313,
      "step": 1276
    },
    {
      "clip_ratio/high_max": 0.002542464619182283,
      "clip_ratio/high_mean": 0.0010773795056593372,
      "clip_ratio/low_mean": 0.001582915418111952,
      "clip_ratio/low_min": 0.00014981811273173662,
      "clip_ratio/region_mean": 0.0026602949074003845,
      "epoch": 0.11918636870074492,
      "grad_norm": 0.4163925051689148,
      "learning_rate": 2e-07,
      "loss": 0.0532,
      "step": 1277
    },
    {
      "clip_ratio/high_max": 0.0024797124206088483,
      "clip_ratio/high_mean": 0.0009754664370120736,
      "clip_ratio/low_mean": 0.001676218438660726,
      "clip_ratio/low_min": 7.32098515072721e-05,
      "clip_ratio/region_mean": 0.002651684859301895,
      "epoch": 0.1192797018007455,
      "grad_norm": 0.413104385137558,
      "learning_rate": 2e-07,
      "loss": 0.0228,
      "step": 1278
    },
    {
      "clip_ratio/high_max": 0.00320190660568187,
      "clip_ratio/high_mean": 0.0012071944656781852,
      "clip_ratio/low_mean": 0.001631128525332315,
      "clip_ratio/low_min": 0.0001381863148708362,
      "clip_ratio/region_mean": 0.002838323031028267,
      "epoch": 0.11937303490074608,
      "grad_norm": 0.34816280007362366,
      "learning_rate": 2e-07,
      "loss": 0.0178,
      "step": 1279
    },
    {
      "clip_ratio/high_max": 0.003162445886118803,
      "clip_ratio/high_mean": 0.001232248883752618,
      "clip_ratio/low_mean": 0.0018059698850265704,
      "clip_ratio/low_min": 0.00021825372459716164,
      "clip_ratio/region_mean": 0.003038218754227273,
      "epoch": 0.11946636800074667,
      "grad_norm": 0.46213099360466003,
      "learning_rate": 2e-07,
      "loss": 0.0346,
      "step": 1280
    },
    {
      "clip_ratio/high_max": 0.033636262523941696,
      "clip_ratio/high_mean": 0.014187191671226174,
      "clip_ratio/low_mean": 0.0018158269340347033,
      "clip_ratio/low_min": 5.904925819777418e-05,
      "clip_ratio/region_mean": 0.01600301859434694,
      "completions/clipped_ratio": 0.023960658482142905,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4091.0,
      "completions/mean_length": 618.6232299804688,
      "completions/mean_terminated_length": 533.2575073242188,
      "completions/min_length": 58.0,
      "completions/min_terminated_length": 58.0,
      "epoch": 0.11955970110074725,
      "grad_norm": 12078193.0,
      "learning_rate": 2e-07,
      "loss": 111408.4844,
      "num_tokens": 941270536.0,
      "reward": 0.5556553602218628,
      "reward_std": 0.17502625286579132,
      "rewards/simpleverify_reward/mean": 0.5556553602218628,
      "rewards/simpleverify_reward/std": 0.4968949556350708,
      "step": 1281
    },
    {
      "clip_ratio/high_max": 0.001757148675096687,
      "clip_ratio/high_mean": 0.0006821812876296462,
      "clip_ratio/low_mean": 0.0007092216746968916,
      "clip_ratio/low_min": 1.2659509593504481e-05,
      "clip_ratio/region_mean": 0.0013914029732404742,
      "epoch": 0.11965303420074783,
      "grad_norm": 0.21127934753894806,
      "learning_rate": 2e-07,
      "loss": 0.0623,
      "step": 1282
    },
    {
      "clip_ratio/high_max": 0.0017937738593900576,
      "clip_ratio/high_mean": 0.0007236842975544278,
      "clip_ratio/low_mean": 0.000609595124842599,
      "clip_ratio/low_min": 2.893673809012398e-05,
      "clip_ratio/region_mean": 0.001333279436948942,
      "epoch": 0.11974636730074842,
      "grad_norm": 0.19094645977020264,
      "learning_rate": 2e-07,
      "loss": 0.0149,
      "step": 1283
    },
    {
      "clip_ratio/high_max": 0.0017875819758046418,
      "clip_ratio/high_mean": 0.0006865628656669287,
      "clip_ratio/low_mean": 0.0005820919504913036,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001268654828891158,
      "epoch": 0.119839700400749,
      "grad_norm": 0.27259427309036255,
      "learning_rate": 2e-07,
      "loss": 0.0542,
      "step": 1284
    },
    {
      "clip_ratio/high_max": 0.0016040740883909166,
      "clip_ratio/high_mean": 0.0007093386211636243,
      "clip_ratio/low_mean": 0.0006890046952321427,
      "clip_ratio/low_min": 2.821818270604126e-05,
      "clip_ratio/region_mean": 0.001398343334585661,
      "epoch": 0.11993303350074958,
      "grad_norm": 0.29669323563575745,
      "learning_rate": 2e-07,
      "loss": 0.0687,
      "step": 1285
    },
    {
      "clip_ratio/high_max": 0.0016907315839489456,
      "clip_ratio/high_mean": 0.0006684055915684439,
      "clip_ratio/low_mean": 0.0007403020954370731,
      "clip_ratio/low_min": 9.851828508544713e-06,
      "clip_ratio/region_mean": 0.0014087076888245065,
      "epoch": 0.12002636660075017,
      "grad_norm": 0.25619158148765564,
      "learning_rate": 2e-07,
      "loss": 0.0469,
      "step": 1286
    },
    {
      "clip_ratio/high_max": 0.0018188443209510297,
      "clip_ratio/high_mean": 0.0006201109990797704,
      "clip_ratio/low_mean": 0.0007741618210275192,
      "clip_ratio/low_min": 5.69612438994227e-05,
      "clip_ratio/region_mean": 0.001394272840116173,
      "epoch": 0.12011969970075075,
      "grad_norm": 0.2125396877527237,
      "learning_rate": 2e-07,
      "loss": 0.0564,
      "step": 1287
    },
    {
      "clip_ratio/high_max": 0.002026779613515828,
      "clip_ratio/high_mean": 0.000803885426648776,
      "clip_ratio/low_mean": 0.0006704076540700044,
      "clip_ratio/low_min": 2.8510792617453262e-05,
      "clip_ratio/region_mean": 0.001474293112551095,
      "epoch": 0.12021303280075134,
      "grad_norm": 0.2173265963792801,
      "learning_rate": 2e-07,
      "loss": 0.0251,
      "step": 1288
    },
    {
      "clip_ratio/high_max": 0.00189265031258401,
      "clip_ratio/high_mean": 0.0007191644272097619,
      "clip_ratio/low_mean": 0.0006233749118109699,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0013425393772195093,
      "epoch": 0.12030636590075192,
      "grad_norm": 0.22747761011123657,
      "learning_rate": 2e-07,
      "loss": 0.0092,
      "step": 1289
    },
    {
      "clip_ratio/high_max": 0.001521122070698766,
      "clip_ratio/high_mean": 0.0005974022587906802,
      "clip_ratio/low_mean": 0.000597670648858184,
      "clip_ratio/low_min": 6.374299391609384e-05,
      "clip_ratio/region_mean": 0.0011950728912779596,
      "epoch": 0.1203996990007525,
      "grad_norm": 0.270175576210022,
      "learning_rate": 2e-07,
      "loss": 0.0829,
      "step": 1290
    },
    {
      "clip_ratio/high_max": 0.0019364003237569705,
      "clip_ratio/high_mean": 0.0006787155243728193,
      "clip_ratio/low_mean": 0.0006841404301667353,
      "clip_ratio/low_min": 3.210352770111058e-05,
      "clip_ratio/region_mean": 0.0013628559681819752,
      "epoch": 0.12049303210075309,
      "grad_norm": 0.2402317225933075,
      "learning_rate": 2e-07,
      "loss": 0.043,
      "step": 1291
    },
    {
      "clip_ratio/high_max": 0.0018949249715660699,
      "clip_ratio/high_mean": 0.0006710470916004851,
      "clip_ratio/low_mean": 0.000702621329764952,
      "clip_ratio/low_min": 2.7315084480505902e-05,
      "clip_ratio/region_mean": 0.0013736684231844265,
      "epoch": 0.12058636520075366,
      "grad_norm": 0.3079681396484375,
      "learning_rate": 2e-07,
      "loss": 0.0306,
      "step": 1292
    },
    {
      "clip_ratio/high_max": 0.001634513377211988,
      "clip_ratio/high_mean": 0.000612127758358838,
      "clip_ratio/low_mean": 0.0007146379994082963,
      "clip_ratio/low_min": 4.088839705218561e-05,
      "clip_ratio/region_mean": 0.0013267657195683569,
      "epoch": 0.12067969830075424,
      "grad_norm": 0.23631501197814941,
      "learning_rate": 2e-07,
      "loss": 0.0818,
      "step": 1293
    },
    {
      "clip_ratio/high_max": 0.0020257626310922205,
      "clip_ratio/high_mean": 0.0007871269426686922,
      "clip_ratio/low_mean": 0.0007188580493675545,
      "clip_ratio/low_min": 4.595153313857736e-05,
      "clip_ratio/region_mean": 0.001505985015683109,
      "epoch": 0.12077303140075484,
      "grad_norm": 0.2371877133846283,
      "learning_rate": 2e-07,
      "loss": 0.024,
      "step": 1294
    },
    {
      "clip_ratio/high_max": 0.0017748676655173767,
      "clip_ratio/high_mean": 0.000702990719673835,
      "clip_ratio/low_mean": 0.0006596877556148684,
      "clip_ratio/low_min": 7.316324990824796e-05,
      "clip_ratio/region_mean": 0.0013626784493681043,
      "epoch": 0.12086636450075541,
      "grad_norm": 0.20498250424861908,
      "learning_rate": 2e-07,
      "loss": 0.0318,
      "step": 1295
    },
    {
      "clip_ratio/high_max": 0.0020530199035420083,
      "clip_ratio/high_mean": 0.0007222244967124425,
      "clip_ratio/low_mean": 0.0006987845181356533,
      "clip_ratio/low_min": 2.337336536584189e-05,
      "clip_ratio/region_mean": 0.0014210090121196117,
      "epoch": 0.12095969760075599,
      "grad_norm": 0.21127595007419586,
      "learning_rate": 2e-07,
      "loss": 0.0688,
      "step": 1296
    },
    {
      "clip_ratio/high_max": 0.0019531643301888835,
      "clip_ratio/high_mean": 0.0006723535625496879,
      "clip_ratio/low_mean": 0.0007116848373698303,
      "clip_ratio/low_min": 5.836957188876113e-05,
      "clip_ratio/region_mean": 0.0013840384199284017,
      "epoch": 0.12105303070075658,
      "grad_norm": 0.482972115278244,
      "learning_rate": 2e-07,
      "loss": 0.0362,
      "step": 1297
    },
    {
      "clip_ratio/high_max": 0.0019306067697471008,
      "clip_ratio/high_mean": 0.0007689784160902491,
      "clip_ratio/low_mean": 0.0006959293586987769,
      "clip_ratio/low_min": 3.0395374778890982e-05,
      "clip_ratio/region_mean": 0.00146490779297892,
      "epoch": 0.12114636380075716,
      "grad_norm": 0.31388309597969055,
      "learning_rate": 2e-07,
      "loss": 0.0877,
      "step": 1298
    },
    {
      "clip_ratio/high_max": 0.001762273657732294,
      "clip_ratio/high_mean": 0.0007248708125189296,
      "clip_ratio/low_mean": 0.0007124294297682354,
      "clip_ratio/low_min": 2.74315316346474e-05,
      "clip_ratio/region_mean": 0.0014373002450156491,
      "epoch": 0.12123969690075775,
      "grad_norm": 0.2976444363594055,
      "learning_rate": 2e-07,
      "loss": 0.0569,
      "step": 1299
    },
    {
      "clip_ratio/high_max": 0.0017979960175580345,
      "clip_ratio/high_mean": 0.0006309786349447677,
      "clip_ratio/low_mean": 0.0006848052034911234,
      "clip_ratio/low_min": 5.603728777714423e-05,
      "clip_ratio/region_mean": 0.0013157838329789229,
      "epoch": 0.12133303000075833,
      "grad_norm": 0.2182295024394989,
      "learning_rate": 2e-07,
      "loss": 0.0414,
      "step": 1300
    },
    {
      "clip_ratio/high_max": 0.002008143019338604,
      "clip_ratio/high_mean": 0.000882398520843708,
      "clip_ratio/low_mean": 0.0006994358900556108,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.001581834385433467,
      "epoch": 0.12142636310075891,
      "grad_norm": 0.23353268206119537,
      "learning_rate": 2e-07,
      "loss": 0.0239,
      "step": 1301
    },
    {
      "clip_ratio/high_max": 0.00187652758177137,
      "clip_ratio/high_mean": 0.0008260255526693072,
      "clip_ratio/low_mean": 0.0007375657824013615,
      "clip_ratio/low_min": 2.817170570779126e-05,
      "clip_ratio/region_mean": 0.001563591322337743,
      "epoch": 0.1215196962007595,
      "grad_norm": 0.2685752809047699,
      "learning_rate": 2e-07,
      "loss": 0.0636,
      "step": 1302
    },
    {
      "clip_ratio/high_max": 0.0020067645600647666,
      "clip_ratio/high_mean": 0.0007231156814668793,
      "clip_ratio/low_mean": 0.0008120148031593999,
      "clip_ratio/low_min": 7.850659039831953e-05,
      "clip_ratio/region_mean": 0.0015351305082731415,
      "epoch": 0.12161302930076008,
      "grad_norm": 1.0086857080459595,
      "learning_rate": 2e-07,
      "loss": 0.0683,
      "step": 1303
    },
    {
      "clip_ratio/high_max": 0.002134534122887999,
      "clip_ratio/high_mean": 0.0007982306960911956,
      "clip_ratio/low_mean": 0.0007991269303602166,
      "clip_ratio/low_min": 1.661350324866362e-05,
      "clip_ratio/region_mean": 0.0015973576228134334,
      "epoch": 0.12170636240076066,
      "grad_norm": 0.31662291288375854,
      "learning_rate": 2e-07,
      "loss": 0.0489,
      "step": 1304
    },
    {
      "clip_ratio/high_max": 0.0017364988234476186,
      "clip_ratio/high_mean": 0.0006627386810578173,
      "clip_ratio/low_mean": 0.0008237217953137588,
      "clip_ratio/low_min": 1.7952032067114487e-05,
      "clip_ratio/region_mean": 0.001486460467276629,
      "epoch": 0.12179969550076125,
      "grad_norm": 0.38843637704849243,
      "learning_rate": 2e-07,
      "loss": 0.0372,
      "step": 1305
    },
    {
      "clip_ratio/high_max": 0.0018198121397290379,
      "clip_ratio/high_mean": 0.0007805256609572098,
      "clip_ratio/low_mean": 0.0006921924505149946,
      "clip_ratio/low_min": 5.5522172260680236e-05,
      "clip_ratio/region_mean": 0.0014727181296620984,
      "epoch": 0.12189302860076183,
      "grad_norm": 0.2285003960132599,
      "learning_rate": 2e-07,
      "loss": 0.0124,
      "step": 1306
    },
    {
      "clip_ratio/high_max": 0.0022814342664787546,
      "clip_ratio/high_mean": 0.0008140117661241675,
      "clip_ratio/low_mean": 0.000778165711381007,
      "clip_ratio/low_min": 4.254353279975476e-05,
      "clip_ratio/region_mean": 0.0015921774502203334,
      "epoch": 0.12198636170076241,
      "grad_norm": 0.3073002099990845,
      "learning_rate": 2e-07,
      "loss": 0.0902,
      "step": 1307
    },
    {
      "clip_ratio/high_max": 0.0016679491782269906,
      "clip_ratio/high_mean": 0.0007282405331352493,
      "clip_ratio/low_mean": 0.0008117576289805584,
      "clip_ratio/low_min": 3.0046589927223977e-05,
      "clip_ratio/region_mean": 0.0015399981566588394,
      "epoch": 0.122079694800763,
      "grad_norm": 0.39821913838386536,
      "learning_rate": 2e-07,
      "loss": 0.0127,
      "step": 1308
    },
    {
      "clip_ratio/high_max": 0.00206142363458639,
      "clip_ratio/high_mean": 0.000798316777945729,
      "clip_ratio/low_mean": 0.0007695334861637093,
      "clip_ratio/low_min": 4.798694862984121e-05,
      "clip_ratio/region_mean": 0.0015678502168157138,
      "epoch": 0.12217302790076358,
      "grad_norm": 0.2792995870113373,
      "learning_rate": 2e-07,
      "loss": 0.0682,
      "step": 1309
    },
    {
      "clip_ratio/high_max": 0.0016825979073473718,
      "clip_ratio/high_mean": 0.0006769990586690255,
      "clip_ratio/low_mean": 0.000753710453864187,
      "clip_ratio/low_min": 4.154892667429522e-05,
      "clip_ratio/region_mean": 0.0014307094788819086,
      "epoch": 0.12226636100076417,
      "grad_norm": 0.2524963319301605,
      "learning_rate": 2e-07,
      "loss": 0.0337,
      "step": 1310
    },
    {
      "clip_ratio/high_max": 0.0021563444533967413,
      "clip_ratio/high_mean": 0.0007952545129228383,
      "clip_ratio/low_mean": 0.0008033812755456893,
      "clip_ratio/low_min": 2.5028905838553328e-05,
      "clip_ratio/region_mean": 0.001598635732079856,
      "epoch": 0.12235969410076475,
      "grad_norm": 0.3603135943412781,
      "learning_rate": 2e-07,
      "loss": -0.004,
      "step": 1311
    },
    {
      "clip_ratio/high_max": 0.0016751332441344857,
      "clip_ratio/high_mean": 0.0007291154070117045,
      "clip_ratio/low_mean": 0.0008382637497561518,
      "clip_ratio/low_min": 7.451120836776681e-06,
      "clip_ratio/region_mean": 0.0015673791676817928,
      "epoch": 0.12245302720076533,
      "grad_norm": 0.2564535439014435,
      "learning_rate": 2e-07,
      "loss": 0.052,
      "step": 1312
    },
    {
      "clip_ratio/high_max": 0.0019843452391796745,
      "clip_ratio/high_mean": 0.0007824366985005327,
      "clip_ratio/low_mean": 0.0008390289222006686,
      "clip_ratio/low_min": 5.71707514609443e-05,
      "clip_ratio/region_mean": 0.0016214656279771589,
      "epoch": 0.12254636030076592,
      "grad_norm": 0.27296802401542664,
      "learning_rate": 2e-07,
      "loss": 0.0429,
      "step": 1313
    },
    {
      "clip_ratio/high_max": 0.0018787092158163432,
      "clip_ratio/high_mean": 0.0006905629634275101,
      "clip_ratio/low_mean": 0.0007322320434468566,
      "clip_ratio/low_min": 7.550461941718822e-05,
      "clip_ratio/region_mean": 0.0014227949868654832,
      "epoch": 0.1226396934007665,
      "grad_norm": 0.242542564868927,
      "learning_rate": 2e-07,
      "loss": 0.0259,
      "step": 1314
    },
    {
      "clip_ratio/high_max": 0.001954390791070182,
      "clip_ratio/high_mean": 0.0008253508317466185,
      "clip_ratio/low_mean": 0.0008160023307937081,
      "clip_ratio/low_min": 3.258050764998188e-05,
      "clip_ratio/region_mean": 0.0016413531775469892,
      "epoch": 0.12273302650076708,
      "grad_norm": 52.56976318359375,
      "learning_rate": 2e-07,
      "loss": 0.0498,
      "step": 1315
    },
    {
      "clip_ratio/high_max": 0.0020414851533132605,
      "clip_ratio/high_mean": 0.000825727091068984,
      "clip_ratio/low_mean": 0.0009527973597869277,
      "clip_ratio/low_min": 6.130089877842693e-05,
      "clip_ratio/region_mean": 0.00177852445631288,
      "epoch": 0.12282635960076767,
      "grad_norm": 0.27530622482299805,
      "learning_rate": 2e-07,
      "loss": 0.0656,
      "step": 1316
    },
    {
      "clip_ratio/high_max": 0.001803757742891321,
      "clip_ratio/high_mean": 0.0007136169006116688,
      "clip_ratio/low_mean": 0.0009263413157896139,
      "clip_ratio/low_min": 5.682919800165109e-05,
      "clip_ratio/region_mean": 0.0016399581872974522,
      "epoch": 0.12291969270076825,
      "grad_norm": 0.28610602021217346,
      "learning_rate": 2e-07,
      "loss": 0.0514,
      "step": 1317
    },
    {
      "clip_ratio/high_max": 0.002272968915349338,
      "clip_ratio/high_mean": 0.0009091477677429793,
      "clip_ratio/low_mean": 0.0009976486107916571,
      "clip_ratio/low_min": 2.2899364921613596e-05,
      "clip_ratio/region_mean": 0.0019067964021814987,
      "epoch": 0.12301302580076884,
      "grad_norm": 0.281762957572937,
      "learning_rate": 2e-07,
      "loss": 0.0432,
      "step": 1318
    },
    {
      "clip_ratio/high_max": 0.0017071304646378849,
      "clip_ratio/high_mean": 0.0006421457019314403,
      "clip_ratio/low_mean": 0.0009136016069533071,
      "clip_ratio/low_min": 3.69376484741224e-05,
      "clip_ratio/region_mean": 0.001555747276142938,
      "epoch": 0.12310635890076942,
      "grad_norm": 0.4166424870491028,
      "learning_rate": 2e-07,
      "loss": 0.0907,
      "step": 1319
    },
    {
      "clip_ratio/high_max": 0.0020416418483364396,
      "clip_ratio/high_mean": 0.0008372932934435084,
      "clip_ratio/low_mean": 0.0008271236092696199,
      "clip_ratio/low_min": 7.730295692454092e-05,
      "clip_ratio/region_mean": 0.0016644168790662661,
      "epoch": 0.12319969200077,
      "grad_norm": 0.7874302864074707,
      "learning_rate": 2e-07,
      "loss": 0.0309,
      "step": 1320
    },
    {
      "clip_ratio/high_max": 0.002167759506846778,
      "clip_ratio/high_mean": 0.0007454313472408103,
      "clip_ratio/low_mean": 0.0009587386248313123,
      "clip_ratio/low_min": 1.3522284461942036e-05,
      "clip_ratio/region_mean": 0.0017041699720721226,
      "epoch": 0.12329302510077059,
      "grad_norm": 0.29603636264801025,
      "learning_rate": 2e-07,
      "loss": 0.0526,
      "step": 1321
    },
    {
      "clip_ratio/high_max": 0.0022808557314419886,
      "clip_ratio/high_mean": 0.0008713424695088179,
      "clip_ratio/low_mean": 0.0009923141551553272,
      "clip_ratio/low_min": 9.941825192072429e-05,
      "clip_ratio/region_mean": 0.0018636566055647563,
      "epoch": 0.12338635820077117,
      "grad_norm": 0.26004448533058167,
      "learning_rate": 2e-07,
      "loss": 0.0379,
      "step": 1322
    },
    {
      "clip_ratio/high_max": 0.0017804318013077136,
      "clip_ratio/high_mean": 0.0007413897074002307,
      "clip_ratio/low_mean": 0.0008614507332822541,
      "clip_ratio/low_min": 6.583530102943769e-05,
      "clip_ratio/region_mean": 0.001602840427949559,
      "epoch": 0.12347969130077174,
      "grad_norm": 0.25743335485458374,
      "learning_rate": 2e-07,
      "loss": 0.0132,
      "step": 1323
    },
    {
      "clip_ratio/high_max": 0.001918955189466942,
      "clip_ratio/high_mean": 0.0007236880646814825,
      "clip_ratio/low_mean": 0.0008195133468689164,
      "clip_ratio/low_min": 7.284461116796592e-05,
      "clip_ratio/region_mean": 0.001543201411550399,
      "epoch": 0.12357302440077234,
      "grad_norm": 0.35232871770858765,
      "learning_rate": 2e-07,
      "loss": 0.0933,
      "step": 1324
    },
    {
      "clip_ratio/high_max": 0.0019627074943855405,
      "clip_ratio/high_mean": 0.0006931725320100668,
      "clip_ratio/low_mean": 0.0008815954006422544,
      "clip_ratio/low_min": 2.658820267242845e-05,
      "clip_ratio/region_mean": 0.0015747679935884662,
      "epoch": 0.12366635750077291,
      "grad_norm": 0.3551845848560333,
      "learning_rate": 2e-07,
      "loss": 0.0459,
      "step": 1325
    },
    {
      "clip_ratio/high_max": 0.002006488408369478,
      "clip_ratio/high_mean": 0.0008612518067820929,
      "clip_ratio/low_mean": 0.0009049921827681828,
      "clip_ratio/low_min": 3.9592043322045356e-05,
      "clip_ratio/region_mean": 0.001766243985912297,
      "epoch": 0.12375969060077349,
      "grad_norm": 0.5212864279747009,
      "learning_rate": 2e-07,
      "loss": -0.0171,
      "step": 1326
    },
    {
      "clip_ratio/high_max": 0.002028292259637965,
      "clip_ratio/high_mean": 0.0008103689579002094,
      "clip_ratio/low_mean": 0.00113118836452486,
      "clip_ratio/low_min": 0.00011083176559623098,
      "clip_ratio/region_mean": 0.0019415573624428362,
      "epoch": 0.12385302370077408,
      "grad_norm": 0.35676780343055725,
      "learning_rate": 2e-07,
      "loss": 0.0789,
      "step": 1327
    },
    {
      "clip_ratio/high_max": 0.0018600714101921767,
      "clip_ratio/high_mean": 0.0008191145170712844,
      "clip_ratio/low_mean": 0.0011517696802911814,
      "clip_ratio/low_min": 0.00016133240569615737,
      "clip_ratio/region_mean": 0.0019708842373802327,
      "epoch": 0.12394635680077466,
      "grad_norm": 0.2637704014778137,
      "learning_rate": 2e-07,
      "loss": 0.0628,
      "step": 1328
    },
    {
      "clip_ratio/high_max": 0.0020112660276936367,
      "clip_ratio/high_mean": 0.0008812366268102778,
      "clip_ratio/low_mean": 0.0009420038386451779,
      "clip_ratio/low_min": 4.4494761823443696e-05,
      "clip_ratio/region_mean": 0.0018232404254376888,
      "epoch": 0.12403968990077525,
      "grad_norm": 0.7555397748947144,
      "learning_rate": 2e-07,
      "loss": 0.0629,
      "step": 1329
    },
    {
      "clip_ratio/high_max": 0.0023849813660490327,
      "clip_ratio/high_mean": 0.0008650260024296585,
      "clip_ratio/low_mean": 0.0010616773943183944,
      "clip_ratio/low_min": 5.0489512432250194e-05,
      "clip_ratio/region_mean": 0.0019267033858341165,
      "epoch": 0.12413302300077583,
      "grad_norm": 0.4563961625099182,
      "learning_rate": 2e-07,
      "loss": 0.0068,
      "step": 1330
    },
    {
      "clip_ratio/high_max": 0.001777242447133176,
      "clip_ratio/high_mean": 0.0007844591327739181,
      "clip_ratio/low_mean": 0.0011538661765371216,
      "clip_ratio/low_min": 3.338774877192918e-05,
      "clip_ratio/region_mean": 0.0019383253093110397,
      "epoch": 0.12422635610077641,
      "grad_norm": 1.0166248083114624,
      "learning_rate": 2e-07,
      "loss": 0.079,
      "step": 1331
    },
    {
      "clip_ratio/high_max": 0.002384343446465209,
      "clip_ratio/high_mean": 0.0009008032575366087,
      "clip_ratio/low_mean": 0.0011397356411180226,
      "clip_ratio/low_min": 3.090169866482029e-05,
      "clip_ratio/region_mean": 0.002040538915025536,
      "epoch": 0.124319689200777,
      "grad_norm": 0.4668191373348236,
      "learning_rate": 2e-07,
      "loss": 0.0284,
      "step": 1332
    },
    {
      "clip_ratio/high_max": 0.0021127900181454606,
      "clip_ratio/high_mean": 0.0009407284278495354,
      "clip_ratio/low_mean": 0.0012498247488110792,
      "clip_ratio/low_min": 0.00013673216199094895,
      "clip_ratio/region_mean": 0.00219055317575112,
      "epoch": 0.12441302230077758,
      "grad_norm": 0.9345513582229614,
      "learning_rate": 2e-07,
      "loss": 0.0425,
      "step": 1333
    },
    {
      "clip_ratio/high_max": 0.0015578489073959645,
      "clip_ratio/high_mean": 0.0005979709985695081,
      "clip_ratio/low_mean": 0.0013884701220376883,
      "clip_ratio/low_min": 5.219834201852791e-05,
      "clip_ratio/region_mean": 0.001986441100598313,
      "epoch": 0.12450635540077816,
      "grad_norm": 0.3814065754413605,
      "learning_rate": 2e-07,
      "loss": 0.075,
      "step": 1334
    },
    {
      "clip_ratio/high_max": 0.002161230044293916,
      "clip_ratio/high_mean": 0.0008774659618211444,
      "clip_ratio/low_mean": 0.0011680799834721256,
      "clip_ratio/low_min": 2.9156085474824067e-05,
      "clip_ratio/region_mean": 0.00204554594529327,
      "epoch": 0.12459968850077875,
      "grad_norm": 0.2788899540901184,
      "learning_rate": 2e-07,
      "loss": 0.0157,
      "step": 1335
    },
    {
      "clip_ratio/high_max": 0.0023304426431423053,
      "clip_ratio/high_mean": 0.0009230548748746514,
      "clip_ratio/low_mean": 0.0012638118332688464,
      "clip_ratio/low_min": 7.977026143635157e-06,
      "clip_ratio/region_mean": 0.0021868667245144024,
      "epoch": 0.12469302160077933,
      "grad_norm": 0.41839393973350525,
      "learning_rate": 2e-07,
      "loss": 0.0353,
      "step": 1336
    },
    {
      "clip_ratio/high_max": 0.0025382133026141673,
      "clip_ratio/high_mean": 0.0009690013430372346,
      "clip_ratio/low_mean": 0.0013258234248496592,
      "clip_ratio/low_min": 8.433274069830077e-05,
      "clip_ratio/region_mean": 0.0022948247205931693,
      "epoch": 0.12478635470077991,
      "grad_norm": 0.3450069725513458,
      "learning_rate": 2e-07,
      "loss": 0.0525,
      "step": 1337
    },
    {
      "clip_ratio/high_max": 0.002026578578806948,
      "clip_ratio/high_mean": 0.0007255108630488394,
      "clip_ratio/low_mean": 0.0010088756753248163,
      "clip_ratio/low_min": 5.659642101818463e-05,
      "clip_ratio/region_mean": 0.0017343865474686027,
      "epoch": 0.1248796878007805,
      "grad_norm": 0.5262999534606934,
      "learning_rate": 2e-07,
      "loss": 0.0497,
      "step": 1338
    },
    {
      "clip_ratio/high_max": 0.002392732127191266,
      "clip_ratio/high_mean": 0.0010224842626485042,
      "clip_ratio/low_mean": 0.0014065424620639533,
      "clip_ratio/low_min": 0.00013383975601755083,
      "clip_ratio/region_mean": 0.0024290266883326694,
      "epoch": 0.12497302090078108,
      "grad_norm": 1.024769902229309,
      "learning_rate": 2e-07,
      "loss": 0.0316,
      "step": 1339
    },
    {
      "clip_ratio/high_max": 0.002354182070121169,
      "clip_ratio/high_mean": 0.0009948725783033296,
      "clip_ratio/low_mean": 0.0011815804355137516,
      "clip_ratio/low_min": 9.019901244755602e-05,
      "clip_ratio/region_mean": 0.002176452981075272,
      "epoch": 0.12506635400078167,
      "grad_norm": 0.6699047684669495,
      "learning_rate": 2e-07,
      "loss": 0.0049,
      "step": 1340
    },
    {
      "clip_ratio/high_max": 0.0023776668531354517,
      "clip_ratio/high_mean": 0.0010117283309227787,
      "clip_ratio/low_mean": 0.0012840334529755637,
      "clip_ratio/low_min": 5.5601229178137146e-05,
      "clip_ratio/region_mean": 0.0022957617911743,
      "epoch": 0.12515968710078224,
      "grad_norm": 0.38643139600753784,
      "learning_rate": 2e-07,
      "loss": 0.0573,
      "step": 1341
    },
    {
      "clip_ratio/high_max": 0.0025596788618713617,
      "clip_ratio/high_mean": 0.0009837788238655776,
      "clip_ratio/low_mean": 0.0014672048382635694,
      "clip_ratio/low_min": 0.00016191880968108308,
      "clip_ratio/region_mean": 0.00245098362211138,
      "epoch": 0.12525302020078283,
      "grad_norm": 0.3206682503223419,
      "learning_rate": 2e-07,
      "loss": 0.0524,
      "step": 1342
    },
    {
      "clip_ratio/high_max": 0.002239757825009292,
      "clip_ratio/high_mean": 0.0009277489261876326,
      "clip_ratio/low_mean": 0.0013906829844927415,
      "clip_ratio/low_min": 0.00010912384095718153,
      "clip_ratio/region_mean": 0.002318431928870268,
      "epoch": 0.12534635330078342,
      "grad_norm": 0.8834324479103088,
      "learning_rate": 2e-07,
      "loss": 0.0341,
      "step": 1343
    },
    {
      "clip_ratio/high_max": 0.002785747972666286,
      "clip_ratio/high_mean": 0.0010081149157485925,
      "clip_ratio/low_mean": 0.0013623956583614927,
      "clip_ratio/low_min": 0.0002735084399319021,
      "clip_ratio/region_mean": 0.002370510555920191,
      "epoch": 0.125439686400784,
      "grad_norm": 0.3635942339897156,
      "learning_rate": 2e-07,
      "loss": 0.0492,
      "step": 1344
    },
    {
      "clip_ratio/high_max": 0.002569894986663712,
      "clip_ratio/high_mean": 0.0010378716942796018,
      "clip_ratio/low_mean": 0.0013031043745286297,
      "clip_ratio/low_min": 8.553877796657616e-05,
      "clip_ratio/region_mean": 0.0023409760906361043,
      "epoch": 0.12553301950078458,
      "grad_norm": 0.32739266753196716,
      "learning_rate": 2e-07,
      "loss": 0.0279,
      "step": 1345
    },
    {
      "clip_ratio/high_max": 0.0027577963046496734,
      "clip_ratio/high_mean": 0.0010262937685183715,
      "clip_ratio/low_mean": 0.0014175027827150188,
      "clip_ratio/low_min": 0.00010162354737985879,
      "clip_ratio/region_mean": 0.0024437965330434963,
      "epoch": 0.12562635260078517,
      "grad_norm": 0.450640469789505,
      "learning_rate": 2e-07,
      "loss": 0.0452,
      "step": 1346
    },
    {
      "clip_ratio/high_max": 0.002508274221327156,
      "clip_ratio/high_mean": 0.0010059725154860644,
      "clip_ratio/low_mean": 0.0016545239413972013,
      "clip_ratio/low_min": 7.452976387867238e-05,
      "clip_ratio/region_mean": 0.002660496385942679,
      "epoch": 0.12571968570078576,
      "grad_norm": 1.7429561614990234,
      "learning_rate": 2e-07,
      "loss": 0.0294,
      "step": 1347
    },
    {
      "clip_ratio/high_max": 0.00264312639774289,
      "clip_ratio/high_mean": 0.0009296898970205802,
      "clip_ratio/low_mean": 0.0015441433060914278,
      "clip_ratio/low_min": 0.00011590816029638518,
      "clip_ratio/region_mean": 0.0024738331776461564,
      "epoch": 0.12581301880078632,
      "grad_norm": 0.6041150689125061,
      "learning_rate": 2e-07,
      "loss": 0.0577,
      "step": 1348
    },
    {
      "clip_ratio/high_max": 0.002590553674963303,
      "clip_ratio/high_mean": 0.0010728382439992856,
      "clip_ratio/low_mean": 0.0017656338022788987,
      "clip_ratio/low_min": 1.8360751710133627e-05,
      "clip_ratio/region_mean": 0.0028384720280882902,
      "epoch": 0.12590635190078692,
      "grad_norm": 0.4069293439388275,
      "learning_rate": 2e-07,
      "loss": 0.0533,
      "step": 1349
    },
    {
      "clip_ratio/high_max": 0.0026527065710979514,
      "clip_ratio/high_mean": 0.0009589272431185236,
      "clip_ratio/low_mean": 0.0018918638124887366,
      "clip_ratio/low_min": 0.00012639217311516404,
      "clip_ratio/region_mean": 0.0028507910174084827,
      "epoch": 0.1259996850007875,
      "grad_norm": 0.6421383619308472,
      "learning_rate": 2e-07,
      "loss": 0.0635,
      "step": 1350
    },
    {
      "clip_ratio/high_max": 0.002398975771939149,
      "clip_ratio/high_mean": 0.0009691734758234816,
      "clip_ratio/low_mean": 0.0017611170187592506,
      "clip_ratio/low_min": 9.336669972981326e-05,
      "clip_ratio/region_mean": 0.002730290485487785,
      "epoch": 0.12609301810078807,
      "grad_norm": 0.4027394652366638,
      "learning_rate": 2e-07,
      "loss": 0.0323,
      "step": 1351
    },
    {
      "clip_ratio/high_max": 0.002671590023965109,
      "clip_ratio/high_mean": 0.0011251056821492966,
      "clip_ratio/low_mean": 0.0017431940541428048,
      "clip_ratio/low_min": 3.889718573191203e-05,
      "clip_ratio/region_mean": 0.002868299765395932,
      "epoch": 0.12618635120078867,
      "grad_norm": 0.47086450457572937,
      "learning_rate": 2e-07,
      "loss": 0.0264,
      "step": 1352
    },
    {
      "clip_ratio/high_max": 0.00303544523922028,
      "clip_ratio/high_mean": 0.0010380452295066789,
      "clip_ratio/low_mean": 0.0019605745728767943,
      "clip_ratio/low_min": 0.00022377767345460597,
      "clip_ratio/region_mean": 0.0029986197550897487,
      "epoch": 0.12627968430078926,
      "grad_norm": 0.42231351137161255,
      "learning_rate": 2e-07,
      "loss": 0.0537,
      "step": 1353
    },
    {
      "clip_ratio/high_max": 0.002713036992645357,
      "clip_ratio/high_mean": 0.0010575264968792908,
      "clip_ratio/low_mean": 0.002031062562309671,
      "clip_ratio/low_min": 0.0001831213776313234,
      "clip_ratio/region_mean": 0.0030885890882927924,
      "epoch": 0.12637301740078982,
      "grad_norm": 2.319950580596924,
      "learning_rate": 2e-07,
      "loss": 0.0481,
      "step": 1354
    },
    {
      "clip_ratio/high_max": 0.0026042971658171155,
      "clip_ratio/high_mean": 0.0010055225247924682,
      "clip_ratio/low_mean": 0.0022166963171912357,
      "clip_ratio/low_min": 0.00016186922948691063,
      "clip_ratio/region_mean": 0.003222218860173598,
      "epoch": 0.12646635050079041,
      "grad_norm": 0.38973361253738403,
      "learning_rate": 2e-07,
      "loss": 0.0659,
      "step": 1355
    },
    {
      "clip_ratio/high_max": 0.0028644218400586396,
      "clip_ratio/high_mean": 0.0010173107475566212,
      "clip_ratio/low_mean": 0.0021601985426968895,
      "clip_ratio/low_min": 0.00021948090397927444,
      "clip_ratio/region_mean": 0.0031775092938914895,
      "epoch": 0.126559683600791,
      "grad_norm": 0.5260111093521118,
      "learning_rate": 2e-07,
      "loss": 0.0618,
      "step": 1356
    },
    {
      "clip_ratio/high_max": 0.002534827624913305,
      "clip_ratio/high_mean": 0.0010179266955674393,
      "clip_ratio/low_mean": 0.0020294062451284844,
      "clip_ratio/low_min": 0.00017540973567520268,
      "clip_ratio/region_mean": 0.003047332924325019,
      "epoch": 0.12665301670079157,
      "grad_norm": 0.36452606320381165,
      "learning_rate": 2e-07,
      "loss": 0.0421,
      "step": 1357
    },
    {
      "clip_ratio/high_max": 0.003283579324488528,
      "clip_ratio/high_mean": 0.0011979314840573352,
      "clip_ratio/low_mean": 0.002413402657111874,
      "clip_ratio/low_min": 0.00010176395153393969,
      "clip_ratio/region_mean": 0.0036113340611336753,
      "epoch": 0.12674634980079216,
      "grad_norm": 0.6362717747688293,
      "learning_rate": 2e-07,
      "loss": 0.0543,
      "step": 1358
    },
    {
      "clip_ratio/high_max": 0.0031596681365044788,
      "clip_ratio/high_mean": 0.0012051305529894307,
      "clip_ratio/low_mean": 0.0023653525022382382,
      "clip_ratio/low_min": 0.00023573484213557094,
      "clip_ratio/region_mean": 0.0035704830297618173,
      "epoch": 0.12683968290079276,
      "grad_norm": 0.4454534649848938,
      "learning_rate": 2e-07,
      "loss": 0.0408,
      "step": 1359
    },
    {
      "clip_ratio/high_max": 0.002676119329407811,
      "clip_ratio/high_mean": 0.001154763331214781,
      "clip_ratio/low_mean": 0.0020823837694479153,
      "clip_ratio/low_min": 0.0002069328875222709,
      "clip_ratio/region_mean": 0.0032371472334489226,
      "epoch": 0.12693301600079332,
      "grad_norm": 0.5644140839576721,
      "learning_rate": 2e-07,
      "loss": 0.0541,
      "step": 1360
    },
    {
      "clip_ratio/high_max": 0.0027585992866079323,
      "clip_ratio/high_mean": 0.0011558113146747928,
      "clip_ratio/low_mean": 0.002482581745425705,
      "clip_ratio/low_min": 0.00015319200792873744,
      "clip_ratio/region_mean": 0.003638393129222095,
      "epoch": 0.1270263491007939,
      "grad_norm": 0.8527132868766785,
      "learning_rate": 2e-07,
      "loss": 0.0672,
      "step": 1361
    },
    {
      "clip_ratio/high_max": 0.003196263212885242,
      "clip_ratio/high_mean": 0.0011651565582724288,
      "clip_ratio/low_mean": 0.0023582407520734705,
      "clip_ratio/low_min": 0.0002619697497721063,
      "clip_ratio/region_mean": 0.003523397332173772,
      "epoch": 0.1271196822007945,
      "grad_norm": 0.5256268382072449,
      "learning_rate": 2e-07,
      "loss": 0.0138,
      "step": 1362
    },
    {
      "clip_ratio/high_max": 0.003100650050328113,
      "clip_ratio/high_mean": 0.0013356989111343864,
      "clip_ratio/low_mean": 0.0027006478048861027,
      "clip_ratio/low_min": 0.00011838667705887929,
      "clip_ratio/region_mean": 0.004036346756038256,
      "epoch": 0.12721301530079507,
      "grad_norm": 2.531118154525757,
      "learning_rate": 2e-07,
      "loss": 0.0278,
      "step": 1363
    },
    {
      "clip_ratio/high_max": 0.0028732038917951286,
      "clip_ratio/high_mean": 0.00128830639005173,
      "clip_ratio/low_mean": 0.002406457300821785,
      "clip_ratio/low_min": 0.00011435964916017838,
      "clip_ratio/region_mean": 0.0036947636399418116,
      "epoch": 0.12730634840079566,
      "grad_norm": 1.0263330936431885,
      "learning_rate": 2e-07,
      "loss": 0.0556,
      "step": 1364
    },
    {
      "clip_ratio/high_max": 0.0031363028538180515,
      "clip_ratio/high_mean": 0.0012643065929296426,
      "clip_ratio/low_mean": 0.0026590454654069617,
      "clip_ratio/low_min": 0.0005984568597341422,
      "clip_ratio/region_mean": 0.0039233520947163925,
      "epoch": 0.12739968150079625,
      "grad_norm": 3.830597400665283,
      "learning_rate": 2e-07,
      "loss": 0.054,
      "step": 1365
    },
    {
      "clip_ratio/high_max": 0.0027876336098415777,
      "clip_ratio/high_mean": 0.0011439816480560694,
      "clip_ratio/low_mean": 0.002571844703197712,
      "clip_ratio/low_min": 0.00014298139285529032,
      "clip_ratio/region_mean": 0.0037158263367018662,
      "epoch": 0.12749301460079684,
      "grad_norm": 114.3066635131836,
      "learning_rate": 2e-07,
      "loss": 0.048,
      "step": 1366
    },
    {
      "clip_ratio/high_max": 0.0028859059239039198,
      "clip_ratio/high_mean": 0.0013933537738921586,
      "clip_ratio/low_mean": 0.002734703251917381,
      "clip_ratio/low_min": 0.0004924963286612183,
      "clip_ratio/region_mean": 0.004128057087655179,
      "epoch": 0.1275863477007974,
      "grad_norm": 0.9545043706893921,
      "learning_rate": 2e-07,
      "loss": 0.0823,
      "step": 1367
    },
    {
      "clip_ratio/high_max": 0.0029186317697167397,
      "clip_ratio/high_mean": 0.0011734642102965154,
      "clip_ratio/low_mean": 0.0031680052561569028,
      "clip_ratio/low_min": 0.00021352353905967902,
      "clip_ratio/region_mean": 0.0043414695537649095,
      "epoch": 0.127679680800798,
      "grad_norm": 1.8541851043701172,
      "learning_rate": 2e-07,
      "loss": 0.0597,
      "step": 1368
    },
    {
      "clip_ratio/high_max": 0.0030309347494039685,
      "clip_ratio/high_mean": 0.0012215992210258264,
      "clip_ratio/low_mean": 0.002775567460048478,
      "clip_ratio/low_min": 0.0001850656008173246,
      "clip_ratio/region_mean": 0.003997166626504622,
      "epoch": 0.1277730139007986,
      "grad_norm": 0.642250657081604,
      "learning_rate": 2e-07,
      "loss": 0.0445,
      "step": 1369
    },
    {
      "clip_ratio/high_max": 0.003637999834609218,
      "clip_ratio/high_mean": 0.0015648667322238907,
      "clip_ratio/low_mean": 0.002479783237504307,
      "clip_ratio/low_min": 7.660453411517665e-05,
      "clip_ratio/region_mean": 0.004044649889692664,
      "epoch": 0.12786634700079916,
      "grad_norm": 0.5624629259109497,
      "learning_rate": 2e-07,
      "loss": 0.0314,
      "step": 1370
    },
    {
      "clip_ratio/high_max": 0.0035111106481053866,
      "clip_ratio/high_mean": 0.0016173406402231194,
      "clip_ratio/low_mean": 0.0027622288107522763,
      "clip_ratio/low_min": 0.00010209899664914701,
      "clip_ratio/region_mean": 0.004379569450975396,
      "epoch": 0.12795968010079975,
      "grad_norm": 3.477973461151123,
      "learning_rate": 2e-07,
      "loss": 0.0348,
      "step": 1371
    },
    {
      "clip_ratio/high_max": 0.003616042355133686,
      "clip_ratio/high_mean": 0.0014225406957848463,
      "clip_ratio/low_mean": 0.0027355257770977914,
      "clip_ratio/low_min": 0.00018423074652673677,
      "clip_ratio/region_mean": 0.004158066381933168,
      "epoch": 0.12805301320080034,
      "grad_norm": 0.48430582880973816,
      "learning_rate": 2e-07,
      "loss": 0.0282,
      "step": 1372
    },
    {
      "clip_ratio/high_max": 0.0038695161347277462,
      "clip_ratio/high_mean": 0.0016061990827438422,
      "clip_ratio/low_mean": 0.0022497429526993074,
      "clip_ratio/low_min": 6.129045323177706e-05,
      "clip_ratio/region_mean": 0.0038559419626835734,
      "epoch": 0.1281463463008009,
      "grad_norm": 1.27579927444458,
      "learning_rate": 2e-07,
      "loss": -0.0089,
      "step": 1373
    },
    {
      "clip_ratio/high_max": 0.0038353272393578663,
      "clip_ratio/high_mean": 0.0014430596747843083,
      "clip_ratio/low_mean": 0.0030794607591815293,
      "clip_ratio/low_min": 0.0002923455394920893,
      "clip_ratio/region_mean": 0.004522520466707647,
      "epoch": 0.1282396794008015,
      "grad_norm": 0.6043083667755127,
      "learning_rate": 2e-07,
      "loss": 0.0341,
      "step": 1374
    },
    {
      "clip_ratio/high_max": 0.0038286989874904975,
      "clip_ratio/high_mean": 0.0016365228038921487,
      "clip_ratio/low_mean": 0.0029189629494794644,
      "clip_ratio/low_min": 0.00018754915436147712,
      "clip_ratio/region_mean": 0.004555485749733634,
      "epoch": 0.1283330125008021,
      "grad_norm": 1.2715624570846558,
      "learning_rate": 2e-07,
      "loss": 0.0424,
      "step": 1375
    },
    {
      "clip_ratio/high_max": 0.003996309489593841,
      "clip_ratio/high_mean": 0.001487261146394303,
      "clip_ratio/low_mean": 0.003512060757202562,
      "clip_ratio/low_min": 0.00027828013844555244,
      "clip_ratio/region_mean": 0.004999321841751225,
      "epoch": 0.12842634560080265,
      "grad_norm": 1.0847305059432983,
      "learning_rate": 2e-07,
      "loss": 0.0616,
      "step": 1376
    },
    {
      "clip_ratio/high_max": 0.003426998940994963,
      "clip_ratio/high_mean": 0.0015868897462496534,
      "clip_ratio/low_mean": 0.003159518222673796,
      "clip_ratio/low_min": 0.0004187214744888479,
      "clip_ratio/region_mean": 0.004746407925267704,
      "epoch": 0.12851967870080325,
      "grad_norm": 0.8347870111465454,
      "learning_rate": 2e-07,
      "loss": 0.0532,
      "step": 1377
    },
    {
      "clip_ratio/high_max": 0.00401118399167899,
      "clip_ratio/high_mean": 0.0015423135591845494,
      "clip_ratio/low_mean": 0.003695669034641469,
      "clip_ratio/low_min": 0.0002078050238196738,
      "clip_ratio/region_mean": 0.005237982579274103,
      "epoch": 0.12861301180080384,
      "grad_norm": 7864.328125,
      "learning_rate": 2e-07,
      "loss": 0.2554,
      "step": 1378
    },
    {
      "clip_ratio/high_max": 0.0034559860978333745,
      "clip_ratio/high_mean": 0.0013092727658658987,
      "clip_ratio/low_mean": 0.0035334619824425317,
      "clip_ratio/low_min": 0.00045110837527317926,
      "clip_ratio/region_mean": 0.004842734691919759,
      "epoch": 0.1287063449008044,
      "grad_norm": 0.6829981207847595,
      "learning_rate": 2e-07,
      "loss": 0.06,
      "step": 1379
    },
    {
      "clip_ratio/high_max": 0.003859608063066844,
      "clip_ratio/high_mean": 0.0016222514350374695,
      "clip_ratio/low_mean": 0.00332366850489052,
      "clip_ratio/low_min": 0.0002849134907592088,
      "clip_ratio/region_mean": 0.004945919936290011,
      "epoch": 0.128799678000805,
      "grad_norm": 0.559385359287262,
      "learning_rate": 2e-07,
      "loss": 0.0263,
      "step": 1380
    },
    {
      "clip_ratio/high_max": 0.003397942375158891,
      "clip_ratio/high_mean": 0.001415162165358197,
      "clip_ratio/low_mean": 0.0032363546233682428,
      "clip_ratio/low_min": 0.0003124932190985419,
      "clip_ratio/region_mean": 0.004651516763260588,
      "epoch": 0.1288930111008056,
      "grad_norm": 0.9944037795066833,
      "learning_rate": 2e-07,
      "loss": 0.0614,
      "step": 1381
    },
    {
      "clip_ratio/high_max": 0.004276193867553957,
      "clip_ratio/high_mean": 0.0017224744697159622,
      "clip_ratio/low_mean": 0.003566123719792813,
      "clip_ratio/low_min": 0.0003244434774387628,
      "clip_ratio/region_mean": 0.005288598273182288,
      "epoch": 0.12898634420080615,
      "grad_norm": 1.682273507118225,
      "learning_rate": 2e-07,
      "loss": 0.0242,
      "step": 1382
    },
    {
      "clip_ratio/high_max": 0.0033961466906475835,
      "clip_ratio/high_mean": 0.0016357606509700418,
      "clip_ratio/low_mean": 0.003744128203834407,
      "clip_ratio/low_min": 0.0001531709531263914,
      "clip_ratio/region_mean": 0.005379888927564025,
      "epoch": 0.12907967730080674,
      "grad_norm": 0.7601098418235779,
      "learning_rate": 2e-07,
      "loss": 0.0208,
      "step": 1383
    },
    {
      "clip_ratio/high_max": 0.0040022009634412825,
      "clip_ratio/high_mean": 0.0016266211096080951,
      "clip_ratio/low_mean": 0.003614822155213915,
      "clip_ratio/low_min": 7.809624366927892e-05,
      "clip_ratio/region_mean": 0.005241443199338391,
      "epoch": 0.12917301040080734,
      "grad_norm": 1.0077459812164307,
      "learning_rate": 2e-07,
      "loss": 0.0411,
      "step": 1384
    },
    {
      "clip_ratio/high_max": 0.0045463819114957005,
      "clip_ratio/high_mean": 0.0019163090983056463,
      "clip_ratio/low_mean": 0.003707854644744657,
      "clip_ratio/low_min": 0.00029892163365730084,
      "clip_ratio/region_mean": 0.005624163881293498,
      "epoch": 0.1292663435008079,
      "grad_norm": 1.0528879165649414,
      "learning_rate": 2e-07,
      "loss": 0.0136,
      "step": 1385
    },
    {
      "clip_ratio/high_max": 0.004596721177222207,
      "clip_ratio/high_mean": 0.0019079614685324486,
      "clip_ratio/low_mean": 0.0037388546697911806,
      "clip_ratio/low_min": 0.0002499071379133966,
      "clip_ratio/region_mean": 0.005646816221997142,
      "epoch": 0.1293596766008085,
      "grad_norm": 0.7254329919815063,
      "learning_rate": 2e-07,
      "loss": 0.0007,
      "step": 1386
    },
    {
      "clip_ratio/high_max": 0.0046409419883275405,
      "clip_ratio/high_mean": 0.00197995436610654,
      "clip_ratio/low_mean": 0.004078065787325613,
      "clip_ratio/low_min": 0.00010447280783409951,
      "clip_ratio/region_mean": 0.006058020080672577,
      "epoch": 0.12945300970080909,
      "grad_norm": 5.374253273010254,
      "learning_rate": 2e-07,
      "loss": 0.0605,
      "step": 1387
    },
    {
      "clip_ratio/high_max": 0.004603522989782505,
      "clip_ratio/high_mean": 0.001997970164666185,
      "clip_ratio/low_mean": 0.003666163232992403,
      "clip_ratio/low_min": 8.293707651318982e-05,
      "clip_ratio/region_mean": 0.005664133408572525,
      "epoch": 0.12954634280080968,
      "grad_norm": 3.4913594722747803,
      "learning_rate": 2e-07,
      "loss": 0.0354,
      "step": 1388
    },
    {
      "clip_ratio/high_max": 0.004369210837467108,
      "clip_ratio/high_mean": 0.001770555285474984,
      "clip_ratio/low_mean": 0.0030628961394540966,
      "clip_ratio/low_min": 0.0001617876478121616,
      "clip_ratio/region_mean": 0.004833451297599822,
      "epoch": 0.12963967590081024,
      "grad_norm": 0.9306317567825317,
      "learning_rate": 2e-07,
      "loss": 0.0789,
      "step": 1389
    },
    {
      "clip_ratio/high_max": 0.0033555475674802437,
      "clip_ratio/high_mean": 0.0014689973068016116,
      "clip_ratio/low_mean": 0.004944380416418426,
      "clip_ratio/low_min": 0.00040157132025342435,
      "clip_ratio/region_mean": 0.006413377675926313,
      "epoch": 0.12973300900081083,
      "grad_norm": 0.6786685585975647,
      "learning_rate": 2e-07,
      "loss": 0.0502,
      "step": 1390
    },
    {
      "clip_ratio/high_max": 0.004791298517375253,
      "clip_ratio/high_mean": 0.0020858020507148467,
      "clip_ratio/low_mean": 0.004148053427343257,
      "clip_ratio/low_min": 0.00022182316024554893,
      "clip_ratio/region_mean": 0.006233855412574485,
      "epoch": 0.12982634210081143,
      "grad_norm": 3.305159330368042,
      "learning_rate": 2e-07,
      "loss": 0.0432,
      "step": 1391
    },
    {
      "clip_ratio/high_max": 0.004473034634429496,
      "clip_ratio/high_mean": 0.002165060257539153,
      "clip_ratio/low_mean": 0.004114166084036697,
      "clip_ratio/low_min": 0.00018270008877152577,
      "clip_ratio/region_mean": 0.006279226450715214,
      "epoch": 0.129919675200812,
      "grad_norm": 0.7855595350265503,
      "learning_rate": 2e-07,
      "loss": 0.0229,
      "step": 1392
    },
    {
      "clip_ratio/high_max": 0.0043141168061993085,
      "clip_ratio/high_mean": 0.0018456328489264706,
      "clip_ratio/low_mean": 0.004047504371555988,
      "clip_ratio/low_min": 0.00035311139799887314,
      "clip_ratio/region_mean": 0.005893137291423045,
      "epoch": 0.13001300830081258,
      "grad_norm": 2.176729917526245,
      "learning_rate": 2e-07,
      "loss": 0.0068,
      "step": 1393
    },
    {
      "clip_ratio/high_max": 0.0052060490706935525,
      "clip_ratio/high_mean": 0.002251189660455566,
      "clip_ratio/low_mean": 0.004593905745423399,
      "clip_ratio/low_min": 0.00034324987609579694,
      "clip_ratio/region_mean": 0.006845095427706838,
      "epoch": 0.13010634140081317,
      "grad_norm": 0.8071860074996948,
      "learning_rate": 2e-07,
      "loss": -0.0018,
      "step": 1394
    },
    {
      "clip_ratio/high_max": 0.00486210516828578,
      "clip_ratio/high_mean": 0.0021418071337393485,
      "clip_ratio/low_mean": 0.004519600552157499,
      "clip_ratio/low_min": 0.00044231839274289086,
      "clip_ratio/region_mean": 0.0066614077222766355,
      "epoch": 0.13019967450081374,
      "grad_norm": 0.8564684987068176,
      "learning_rate": 2e-07,
      "loss": 0.0233,
      "step": 1395
    },
    {
      "clip_ratio/high_max": 0.00514608999947086,
      "clip_ratio/high_mean": 0.002337209414690733,
      "clip_ratio/low_mean": 0.004481221083551645,
      "clip_ratio/low_min": 0.00038196273817447945,
      "clip_ratio/region_mean": 0.006818430440034717,
      "epoch": 0.13029300760081433,
      "grad_norm": 0.7765283584594727,
      "learning_rate": 2e-07,
      "loss": 0.0311,
      "step": 1396
    },
    {
      "clip_ratio/high_max": 0.00541700805479195,
      "clip_ratio/high_mean": 0.0022175691701704636,
      "clip_ratio/low_mean": 0.004954605275997892,
      "clip_ratio/low_min": 0.00016486383537994698,
      "clip_ratio/region_mean": 0.007172174577135593,
      "epoch": 0.13038634070081492,
      "grad_norm": 0.8650400042533875,
      "learning_rate": 2e-07,
      "loss": 0.0294,
      "step": 1397
    },
    {
      "clip_ratio/high_max": 0.004295728205761407,
      "clip_ratio/high_mean": 0.0019153212633682415,
      "clip_ratio/low_mean": 0.005195003774133511,
      "clip_ratio/low_min": 0.0008627111237728968,
      "clip_ratio/region_mean": 0.007110325008397922,
      "epoch": 0.1304796738008155,
      "grad_norm": 2.9553794860839844,
      "learning_rate": 2e-07,
      "loss": 0.0292,
      "step": 1398
    },
    {
      "clip_ratio/high_max": 0.005520305625395849,
      "clip_ratio/high_mean": 0.002344898290175479,
      "clip_ratio/low_mean": 0.005007434083381668,
      "clip_ratio/low_min": 0.0006360517054417869,
      "clip_ratio/region_mean": 0.007352332278969698,
      "epoch": 0.13057300690081608,
      "grad_norm": 0.9109849333763123,
      "learning_rate": 2e-07,
      "loss": 0.0394,
      "step": 1399
    },
    {
      "clip_ratio/high_max": 0.004168804924120195,
      "clip_ratio/high_mean": 0.0018622530005814042,
      "clip_ratio/low_mean": 0.004975227107934188,
      "clip_ratio/low_min": 0.0007623797937412746,
      "clip_ratio/region_mean": 0.006837480163085274,
      "epoch": 0.13066634000081667,
      "grad_norm": 0.7531682252883911,
      "learning_rate": 2e-07,
      "loss": 0.0893,
      "step": 1400
    },
    {
      "clip_ratio/high_max": 0.0041679345013108104,
      "clip_ratio/high_mean": 0.0018102321064361604,
      "clip_ratio/low_mean": 0.005287512714858167,
      "clip_ratio/low_min": 0.00037659023655578494,
      "clip_ratio/region_mean": 0.007097744950442575,
      "epoch": 0.13075967310081724,
      "grad_norm": 3.531359910964966,
      "learning_rate": 2e-07,
      "loss": 0.0632,
      "step": 1401
    },
    {
      "clip_ratio/high_max": 0.004772643856995273,
      "clip_ratio/high_mean": 0.0019076236640103161,
      "clip_ratio/low_mean": 0.00559662512387149,
      "clip_ratio/low_min": 0.0008603511105320649,
      "clip_ratio/region_mean": 0.007504248729674146,
      "epoch": 0.13085300620081783,
      "grad_norm": 1.369084358215332,
      "learning_rate": 2e-07,
      "loss": 0.0754,
      "step": 1402
    },
    {
      "clip_ratio/high_max": 0.005707138130674139,
      "clip_ratio/high_mean": 0.002062457409920171,
      "clip_ratio/low_mean": 0.0049517017614562064,
      "clip_ratio/low_min": 0.0004519810536294244,
      "clip_ratio/region_mean": 0.007014159156824462,
      "epoch": 0.13094633930081842,
      "grad_norm": 0.8947897553443909,
      "learning_rate": 2e-07,
      "loss": 0.0261,
      "step": 1403
    },
    {
      "clip_ratio/high_max": 0.005706018098862842,
      "clip_ratio/high_mean": 0.002277906245581107,
      "clip_ratio/low_mean": 0.005606733146123588,
      "clip_ratio/low_min": 0.001022373322484782,
      "clip_ratio/region_mean": 0.00788463931530714,
      "epoch": 0.13103967240081899,
      "grad_norm": 1.3503310680389404,
      "learning_rate": 2e-07,
      "loss": 0.0722,
      "step": 1404
    },
    {
      "clip_ratio/high_max": 0.005204361514188349,
      "clip_ratio/high_mean": 0.0021775253117084503,
      "clip_ratio/low_mean": 0.005372596890083514,
      "clip_ratio/low_min": 0.0005749110314354766,
      "clip_ratio/region_mean": 0.0075501223909668624,
      "epoch": 0.13113300550081958,
      "grad_norm": 1.8905260562896729,
      "learning_rate": 2e-07,
      "loss": 0.0344,
      "step": 1405
    },
    {
      "clip_ratio/high_max": 0.005523397616343573,
      "clip_ratio/high_mean": 0.002568270814663265,
      "clip_ratio/low_mean": 0.00610120888450183,
      "clip_ratio/low_min": 0.00024570243840571493,
      "clip_ratio/region_mean": 0.008669479633681476,
      "epoch": 0.13122633860082017,
      "grad_norm": 2.2963099479675293,
      "learning_rate": 2e-07,
      "loss": 0.0479,
      "step": 1406
    },
    {
      "clip_ratio/high_max": 0.0056981727975653484,
      "clip_ratio/high_mean": 0.0023827111508580856,
      "clip_ratio/low_mean": 0.005824722975376062,
      "clip_ratio/low_min": 0.0002989589120261371,
      "clip_ratio/region_mean": 0.00820743408985436,
      "epoch": 0.13131967170082076,
      "grad_norm": 1.7729641199111938,
      "learning_rate": 2e-07,
      "loss": 0.0417,
      "step": 1407
    },
    {
      "clip_ratio/high_max": 0.005736575796618126,
      "clip_ratio/high_mean": 0.002538405082304962,
      "clip_ratio/low_mean": 0.006702297818264924,
      "clip_ratio/low_min": 0.0005772056538262405,
      "clip_ratio/region_mean": 0.009240702929673716,
      "epoch": 0.13141300480082133,
      "grad_norm": 4.276357173919678,
      "learning_rate": 2e-07,
      "loss": 0.0561,
      "step": 1408
    },
    {
      "clip_ratio/high_max": 0.0022858290030853823,
      "clip_ratio/high_mean": 0.0007739901957393158,
      "clip_ratio/low_mean": 0.0008203464412872563,
      "clip_ratio/low_min": 9.448223863728344e-06,
      "clip_ratio/region_mean": 0.0015943366233841516,
      "completions/clipped_ratio": 0.040867396763392905,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4096.0,
      "completions/mean_length": 514.756103515625,
      "completions/mean_terminated_length": 362.1639709472656,
      "completions/min_length": 10.0,
      "completions/min_terminated_length": 10.0,
      "epoch": 0.13150633790082192,
      "grad_norm": 0.37589943408966064,
      "learning_rate": 2e-07,
      "loss": 0.0622,
      "num_tokens": 1011679701.0,
      "reward": 0.3563319742679596,
      "reward_std": 0.15777914226055145,
      "rewards/simpleverify_reward/mean": 0.3563319742679596,
      "rewards/simpleverify_reward/std": 0.4789169728755951,
      "step": 1409
    },
    {
      "clip_ratio/high_max": 0.0020147146606177557,
      "clip_ratio/high_mean": 0.0006640896626777248,
      "clip_ratio/low_mean": 0.000886892239577719,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0015509819022554439,
      "epoch": 0.1315996710008225,
      "grad_norm": 0.3647271394729614,
      "learning_rate": 2e-07,
      "loss": 0.0364,
      "step": 1410
    },
    {
      "clip_ratio/high_max": 0.0019205837525078095,
      "clip_ratio/high_mean": 0.0006850848631074768,
      "clip_ratio/low_mean": 0.0007341512482526014,
      "clip_ratio/low_min": 1.8074031686410308e-05,
      "clip_ratio/region_mean": 0.001419236108631594,
      "epoch": 0.13169300410082307,
      "grad_norm": 0.2974034547805786,
      "learning_rate": 2e-07,
      "loss": 0.0509,
      "step": 1411
    },
    {
      "clip_ratio/high_max": 0.002813302220602054,
      "clip_ratio/high_mean": 0.0009271139242628124,
      "clip_ratio/low_mean": 0.000787550066888798,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0017146640057035256,
      "epoch": 0.13178633720082367,
      "grad_norm": 0.3826490044593811,
      "learning_rate": 2e-07,
      "loss": 0.0883,
      "step": 1412
    },
    {
      "clip_ratio/high_max": 0.002181429234042298,
      "clip_ratio/high_mean": 0.0007425126314046793,
      "clip_ratio/low_mean": 0.0008070146213867702,
      "clip_ratio/low_min": 3.332349660922773e-05,
      "clip_ratio/region_mean": 0.0015495272855332587,
      "epoch": 0.13187967030082426,
      "grad_norm": 0.3387027382850647,
      "learning_rate": 2e-07,
      "loss": 0.0311,
      "step": 1413
    },
    {
      "clip_ratio/high_max": 0.001755005770974094,
      "clip_ratio/high_mean": 0.0005431728550320258,
      "clip_ratio/low_mean": 0.0007685362911615812,
      "clip_ratio/low_min": 1.966645686479751e-05,
      "clip_ratio/region_mean": 0.0013117091257299762,
      "epoch": 0.13197300340082482,
      "grad_norm": 0.3229408264160156,
      "learning_rate": 2e-07,
      "loss": 0.1079,
      "step": 1414
    },
    {
      "clip_ratio/high_max": 0.0028391996675054543,
      "clip_ratio/high_mean": 0.000890133900611545,
      "clip_ratio/low_mean": 0.0009665957732067909,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0018567296465334948,
      "epoch": 0.13206633650082542,
      "grad_norm": 2.079270124435425,
      "learning_rate": 2e-07,
      "loss": 0.0596,
      "step": 1415
    },
    {
      "clip_ratio/high_max": 0.002113057144015329,
      "clip_ratio/high_mean": 0.0007430680743709672,
      "clip_ratio/low_mean": 0.0007185060949268518,
      "clip_ratio/low_min": 3.0110419174889103e-05,
      "clip_ratio/region_mean": 0.0014615741820307449,
      "epoch": 0.132159669600826,
      "grad_norm": 0.4793534576892853,
      "learning_rate": 2e-07,
      "loss": 0.0524,
      "step": 1416
    },
    {
      "clip_ratio/high_max": 0.0019793916180788074,
      "clip_ratio/high_mean": 0.0007194257923401892,
      "clip_ratio/low_mean": 0.0009732189391797874,
      "clip_ratio/low_min": 4.096811517229071e-05,
      "clip_ratio/region_mean": 0.0016926447278819978,
      "epoch": 0.13225300270082657,
      "grad_norm": 0.5610447525978088,
      "learning_rate": 2e-07,
      "loss": 0.043,
      "step": 1417
    },
    {
      "clip_ratio/high_max": 0.0021653680778399576,
      "clip_ratio/high_mean": 0.0008574580424465239,
      "clip_ratio/low_mean": 0.0008970333965407917,
      "clip_ratio/low_min": 3.0658032301289495e-05,
      "clip_ratio/region_mean": 0.0017544914517202415,
      "epoch": 0.13234633580082716,
      "grad_norm": 0.3877805471420288,
      "learning_rate": 2e-07,
      "loss": 0.0694,
      "step": 1418
    },
    {
      "clip_ratio/high_max": 0.0021148373634787276,
      "clip_ratio/high_mean": 0.0006996362812969892,
      "clip_ratio/low_mean": 0.0011564133419597056,
      "clip_ratio/low_min": 9.15080545382807e-06,
      "clip_ratio/region_mean": 0.0018560496500867885,
      "epoch": 0.13243966890082776,
      "grad_norm": 1.9866297245025635,
      "learning_rate": 2e-07,
      "loss": 0.0636,
      "step": 1419
    },
    {
      "clip_ratio/high_max": 0.001726624119328335,
      "clip_ratio/high_mean": 0.0006377351528499275,
      "clip_ratio/low_mean": 0.0010235778099740855,
      "clip_ratio/low_min": 2.980169483635109e-05,
      "clip_ratio/region_mean": 0.0016613129700999707,
      "epoch": 0.13253300200082832,
      "grad_norm": 0.40588143467903137,
      "learning_rate": 2e-07,
      "loss": 0.0754,
      "step": 1420
    },
    {
      "clip_ratio/high_max": 0.002501332273823209,
      "clip_ratio/high_mean": 0.0008535894012311473,
      "clip_ratio/low_mean": 0.0010554007167229429,
      "clip_ratio/low_min": 6.904629026394105e-05,
      "clip_ratio/region_mean": 0.001908990103402175,
      "epoch": 0.1326263351008289,
      "grad_norm": 0.6843695640563965,
      "learning_rate": 2e-07,
      "loss": 0.0603,
      "step": 1421
    },
    {
      "clip_ratio/high_max": 0.002225620748504298,
      "clip_ratio/high_mean": 0.000803230912424624,
      "clip_ratio/low_mean": 0.0011859491969516966,
      "clip_ratio/low_min": 4.97936703141022e-05,
      "clip_ratio/region_mean": 0.0019891801348421723,
      "epoch": 0.1327196682008295,
      "grad_norm": 8.613897323608398,
      "learning_rate": 2e-07,
      "loss": 0.06,
      "step": 1422
    },
    {
      "clip_ratio/high_max": 0.0020461132371565327,
      "clip_ratio/high_mean": 0.0007648333066754276,
      "clip_ratio/low_mean": 0.0009778306066436926,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0017426638660253957,
      "epoch": 0.13281300130083007,
      "grad_norm": 4.5761308670043945,
      "learning_rate": 2e-07,
      "loss": 0.032,
      "step": 1423
    },
    {
      "clip_ratio/high_max": 0.0025704339550429722,
      "clip_ratio/high_mean": 0.0007804412794030213,
      "clip_ratio/low_mean": 0.0009155608304354246,
      "clip_ratio/low_min": 9.745828720042482e-06,
      "clip_ratio/region_mean": 0.001696002102107741,
      "epoch": 0.13290633440083066,
      "grad_norm": 0.4805845618247986,
      "learning_rate": 2e-07,
      "loss": 0.0644,
      "step": 1424
    },
    {
      "clip_ratio/high_max": 0.0024515897821402177,
      "clip_ratio/high_mean": 0.0009031936569954269,
      "clip_ratio/low_mean": 0.0009094547367567429,
      "clip_ratio/low_min": 1.952514867298305e-05,
      "clip_ratio/region_mean": 0.0018126483846572228,
      "epoch": 0.13299966750083125,
      "grad_norm": 4.029233932495117,
      "learning_rate": 2e-07,
      "loss": 0.0548,
      "step": 1425
    },
    {
      "clip_ratio/high_max": 0.0024525904373149388,
      "clip_ratio/high_mean": 0.0007474123303836677,
      "clip_ratio/low_mean": 0.0011082827040809207,
      "clip_ratio/low_min": 7.223650754895061e-05,
      "clip_ratio/region_mean": 0.0018556950381025672,
      "epoch": 0.13309300060083182,
      "grad_norm": 0.45861756801605225,
      "learning_rate": 2e-07,
      "loss": 0.0678,
      "step": 1426
    },
    {
      "clip_ratio/high_max": 0.0023402858423651196,
      "clip_ratio/high_mean": 0.0008091158251772868,
      "clip_ratio/low_mean": 0.0010660908810677938,
      "clip_ratio/low_min": 2.5805120458244346e-05,
      "clip_ratio/region_mean": 0.0018752067408058792,
      "epoch": 0.1331863337008324,
      "grad_norm": 0.40048226714134216,
      "learning_rate": 2e-07,
      "loss": 0.0239,
      "step": 1427
    },
    {
      "clip_ratio/high_max": 0.0024079250961221987,
      "clip_ratio/high_mean": 0.0008682491725267028,
      "clip_ratio/low_mean": 0.0010387228558101924,
      "clip_ratio/low_min": 2.9490405722754076e-05,
      "clip_ratio/region_mean": 0.0019069720001425594,
      "epoch": 0.133279666800833,
      "grad_norm": 0.5608670711517334,
      "learning_rate": 2e-07,
      "loss": 0.0631,
      "step": 1428
    },
    {
      "clip_ratio/high_max": 0.0025148778877337463,
      "clip_ratio/high_mean": 0.0008417230410486809,
      "clip_ratio/low_mean": 0.0009324784259661101,
      "clip_ratio/low_min": 2.0424837202881463e-05,
      "clip_ratio/region_mean": 0.0017742014315444976,
      "epoch": 0.1333729999008336,
      "grad_norm": 0.46958687901496887,
      "learning_rate": 2e-07,
      "loss": 0.011,
      "step": 1429
    },
    {
      "clip_ratio/high_max": 0.0017079925928555895,
      "clip_ratio/high_mean": 0.0006412028642444056,
      "clip_ratio/low_mean": 0.0012678189450525679,
      "clip_ratio/low_min": 2.8621583624044433e-05,
      "clip_ratio/region_mean": 0.0019090218338533305,
      "epoch": 0.13346633300083416,
      "grad_norm": 0.6317129135131836,
      "learning_rate": 2e-07,
      "loss": 0.0553,
      "step": 1430
    },
    {
      "clip_ratio/high_max": 0.0023303997877519578,
      "clip_ratio/high_mean": 0.0007982043862284627,
      "clip_ratio/low_mean": 0.0012996413061046042,
      "clip_ratio/low_min": 7.60751536290627e-05,
      "clip_ratio/region_mean": 0.002097845674143173,
      "epoch": 0.13355966610083475,
      "grad_norm": 1.3061832189559937,
      "learning_rate": 2e-07,
      "loss": 0.0499,
      "step": 1431
    },
    {
      "clip_ratio/high_max": 0.002532239435822703,
      "clip_ratio/high_mean": 0.0008975334567367099,
      "clip_ratio/low_mean": 0.0013155305150576169,
      "clip_ratio/low_min": 4.970132613379974e-05,
      "clip_ratio/region_mean": 0.0022130638972157612,
      "epoch": 0.13365299920083534,
      "grad_norm": 0.4787406325340271,
      "learning_rate": 2e-07,
      "loss": 0.0743,
      "step": 1432
    },
    {
      "clip_ratio/high_max": 0.002342156421946129,
      "clip_ratio/high_mean": 0.000860677583659708,
      "clip_ratio/low_mean": 0.00127108288825184,
      "clip_ratio/low_min": 2.7814924578706268e-05,
      "clip_ratio/region_mean": 0.002131760469637811,
      "epoch": 0.1337463323008359,
      "grad_norm": 0.664539635181427,
      "learning_rate": 2e-07,
      "loss": 0.0906,
      "step": 1433
    },
    {
      "clip_ratio/high_max": 0.002125769926351495,
      "clip_ratio/high_mean": 0.0007431493231706554,
      "clip_ratio/low_mean": 0.0011908952383237192,
      "clip_ratio/low_min": 7.470491254935041e-05,
      "clip_ratio/region_mean": 0.001934044594236184,
      "epoch": 0.1338396654008365,
      "grad_norm": 1.4063613414764404,
      "learning_rate": 2e-07,
      "loss": 0.0291,
      "step": 1434
    },
    {
      "clip_ratio/high_max": 0.0024910152569646016,
      "clip_ratio/high_mean": 0.0009417605542694218,
      "clip_ratio/low_mean": 0.0017236646863239002,
      "clip_ratio/low_min": 7.579754674225114e-05,
      "clip_ratio/region_mean": 0.002665425265149679,
      "epoch": 0.1339329985008371,
      "grad_norm": 0.8937907814979553,
      "learning_rate": 2e-07,
      "loss": 0.0184,
      "step": 1435
    },
    {
      "clip_ratio/high_max": 0.003027369653864298,
      "clip_ratio/high_mean": 0.0009681766714493278,
      "clip_ratio/low_mean": 0.00157960296201054,
      "clip_ratio/low_min": 9.461288573220372e-05,
      "clip_ratio/region_mean": 0.0025477796370978467,
      "epoch": 0.13402633160083766,
      "grad_norm": 1.5080628395080566,
      "learning_rate": 2e-07,
      "loss": 0.042,
      "step": 1436
    },
    {
      "clip_ratio/high_max": 0.0023450885964848567,
      "clip_ratio/high_mean": 0.000836309934129531,
      "clip_ratio/low_mean": 0.0016264475343632512,
      "clip_ratio/low_min": 0.0001718180501484312,
      "clip_ratio/region_mean": 0.00246275746030733,
      "epoch": 0.13411966470083825,
      "grad_norm": 0.48777467012405396,
      "learning_rate": 2e-07,
      "loss": 0.0701,
      "step": 1437
    },
    {
      "clip_ratio/high_max": 0.002487173638655804,
      "clip_ratio/high_mean": 0.0009364368706883397,
      "clip_ratio/low_mean": 0.001603741169674322,
      "clip_ratio/low_min": 0.00014974144778534537,
      "clip_ratio/region_mean": 0.0025401780658285134,
      "epoch": 0.13421299780083884,
      "grad_norm": 0.5488957762718201,
      "learning_rate": 2e-07,
      "loss": 0.0186,
      "step": 1438
    },
    {
      "clip_ratio/high_max": 0.0025934384466381744,
      "clip_ratio/high_mean": 0.0009238202983397059,
      "clip_ratio/low_mean": 0.0015067408348841127,
      "clip_ratio/low_min": 0.00013340966506802943,
      "clip_ratio/region_mean": 0.00243056112958584,
      "epoch": 0.1343063309008394,
      "grad_norm": 0.5224533677101135,
      "learning_rate": 2e-07,
      "loss": 0.042,
      "step": 1439
    },
    {
      "clip_ratio/high_max": 0.002193598715166445,
      "clip_ratio/high_mean": 0.0008002889835552196,
      "clip_ratio/low_mean": 0.0017514475293864962,
      "clip_ratio/low_min": 0.00012452206829038914,
      "clip_ratio/region_mean": 0.0025517364774714224,
      "epoch": 0.13439966400084,
      "grad_norm": 0.674601137638092,
      "learning_rate": 2e-07,
      "loss": 0.1045,
      "step": 1440
    },
    {
      "clip_ratio/high_max": 0.0026730866029538447,
      "clip_ratio/high_mean": 0.0008861470303145325,
      "clip_ratio/low_mean": 0.0016485023661516607,
      "clip_ratio/low_min": 6.800128721806686e-05,
      "clip_ratio/region_mean": 0.0025346493421238847,
      "epoch": 0.1344929971008406,
      "grad_norm": 0.7866846323013306,
      "learning_rate": 2e-07,
      "loss": 0.0488,
      "step": 1441
    },
    {
      "clip_ratio/high_max": 0.0025691538994578877,
      "clip_ratio/high_mean": 0.0009108567719522398,
      "clip_ratio/low_mean": 0.001813813349144766,
      "clip_ratio/low_min": 0.0001307161401200574,
      "clip_ratio/region_mean": 0.002724670135648921,
      "epoch": 0.13458633020084115,
      "grad_norm": 2.7574350833892822,
      "learning_rate": 2e-07,
      "loss": 0.0418,
      "step": 1442
    },
    {
      "clip_ratio/high_max": 0.0019525459065334871,
      "clip_ratio/high_mean": 0.0006550313191837631,
      "clip_ratio/low_mean": 0.0016372677018807735,
      "clip_ratio/low_min": 0.00013123841017659288,
      "clip_ratio/region_mean": 0.002292298995598685,
      "epoch": 0.13467966330084175,
      "grad_norm": 0.6903833746910095,
      "learning_rate": 2e-07,
      "loss": 0.1173,
      "step": 1443
    },
    {
      "clip_ratio/high_max": 0.0023495137538702693,
      "clip_ratio/high_mean": 0.0009579425368428929,
      "clip_ratio/low_mean": 0.0022618568400503136,
      "clip_ratio/low_min": 0.00027113845862913877,
      "clip_ratio/region_mean": 0.003219799262296874,
      "epoch": 0.13477299640084234,
      "grad_norm": 0.7423739433288574,
      "learning_rate": 2e-07,
      "loss": 0.0409,
      "step": 1444
    },
    {
      "clip_ratio/high_max": 0.0029621027715620585,
      "clip_ratio/high_mean": 0.0011092934610132943,
      "clip_ratio/low_mean": 0.0021768877595604863,
      "clip_ratio/low_min": 0.00011650138276309008,
      "clip_ratio/region_mean": 0.0032861812724149786,
      "epoch": 0.1348663295008429,
      "grad_norm": 0.5768318772315979,
      "learning_rate": 2e-07,
      "loss": 0.0201,
      "step": 1445
    },
    {
      "clip_ratio/high_max": 0.0034801488909579348,
      "clip_ratio/high_mean": 0.001034025319313514,
      "clip_ratio/low_mean": 0.0020276021750760265,
      "clip_ratio/low_min": 0.0001441427430108888,
      "clip_ratio/region_mean": 0.003061627510760445,
      "epoch": 0.1349596626008435,
      "grad_norm": 0.8390409350395203,
      "learning_rate": 2e-07,
      "loss": 0.056,
      "step": 1446
    },
    {
      "clip_ratio/high_max": 0.003055284352740273,
      "clip_ratio/high_mean": 0.0011373850738891633,
      "clip_ratio/low_mean": 0.0024477444458170794,
      "clip_ratio/low_min": 8.887905823939946e-05,
      "clip_ratio/region_mean": 0.0035851295760949142,
      "epoch": 0.1350529957008441,
      "grad_norm": 0.790241003036499,
      "learning_rate": 2e-07,
      "loss": 0.0263,
      "step": 1447
    },
    {
      "clip_ratio/high_max": 0.002895025405450724,
      "clip_ratio/high_mean": 0.001217231168084254,
      "clip_ratio/low_mean": 0.002294643269124208,
      "clip_ratio/low_min": 4.638218888430856e-05,
      "clip_ratio/region_mean": 0.0035118744053761475,
      "epoch": 0.13514632880084468,
      "grad_norm": 1.6624170541763306,
      "learning_rate": 2e-07,
      "loss": 0.0167,
      "step": 1448
    },
    {
      "clip_ratio/high_max": 0.003560240555088967,
      "clip_ratio/high_mean": 0.0011220917986065615,
      "clip_ratio/low_mean": 0.0022375651642505545,
      "clip_ratio/low_min": 0.00015427527978317812,
      "clip_ratio/region_mean": 0.0033596569555811584,
      "epoch": 0.13523966190084524,
      "grad_norm": 1.019584059715271,
      "learning_rate": 2e-07,
      "loss": 0.0959,
      "step": 1449
    },
    {
      "clip_ratio/high_max": 0.0035204305677325465,
      "clip_ratio/high_mean": 0.001129406800828292,
      "clip_ratio/low_mean": 0.0025988498418882955,
      "clip_ratio/low_min": 8.632439858047292e-05,
      "clip_ratio/region_mean": 0.0037282566918293014,
      "epoch": 0.13533299500084583,
      "grad_norm": 0.9907898902893066,
      "learning_rate": 2e-07,
      "loss": 0.0109,
      "step": 1450
    },
    {
      "clip_ratio/high_max": 0.0029726437678618822,
      "clip_ratio/high_mean": 0.001083929925925986,
      "clip_ratio/low_mean": 0.002887091693992261,
      "clip_ratio/low_min": 0.00014147655747365206,
      "clip_ratio/region_mean": 0.003971021702454891,
      "epoch": 0.13542632810084643,
      "grad_norm": 0.8106179237365723,
      "learning_rate": 2e-07,
      "loss": 0.0764,
      "step": 1451
    },
    {
      "clip_ratio/high_max": 0.0033718745289661456,
      "clip_ratio/high_mean": 0.0010835926186700817,
      "clip_ratio/low_mean": 0.0025226208599633537,
      "clip_ratio/low_min": 0.00017530148215882946,
      "clip_ratio/region_mean": 0.0036062135113752447,
      "epoch": 0.135519661200847,
      "grad_norm": 1.337110996246338,
      "learning_rate": 2e-07,
      "loss": 0.0647,
      "step": 1452
    },
    {
      "clip_ratio/high_max": 0.003224976757337572,
      "clip_ratio/high_mean": 0.001138706558776903,
      "clip_ratio/low_mean": 0.0030269080234575085,
      "clip_ratio/low_min": 0.0001649675286898855,
      "clip_ratio/region_mean": 0.004165614605881274,
      "epoch": 0.13561299430084758,
      "grad_norm": 0.8208521008491516,
      "learning_rate": 2e-07,
      "loss": 0.0281,
      "step": 1453
    },
    {
      "clip_ratio/high_max": 0.0034363482482149266,
      "clip_ratio/high_mean": 0.0012834551016567275,
      "clip_ratio/low_mean": 0.0031190614063234534,
      "clip_ratio/low_min": 0.0002975349416374229,
      "clip_ratio/region_mean": 0.004402516431582626,
      "epoch": 0.13570632740084818,
      "grad_norm": 1.2432661056518555,
      "learning_rate": 2e-07,
      "loss": 0.0953,
      "step": 1454
    },
    {
      "clip_ratio/high_max": 0.0032899245888984296,
      "clip_ratio/high_mean": 0.0011471292832538893,
      "clip_ratio/low_mean": 0.0031637828651582822,
      "clip_ratio/low_min": 0.0003822116159426514,
      "clip_ratio/region_mean": 0.004310912030632608,
      "epoch": 0.13579966050084874,
      "grad_norm": 2.820694923400879,
      "learning_rate": 2e-07,
      "loss": 0.0869,
      "step": 1455
    },
    {
      "clip_ratio/high_max": 0.003551418281858787,
      "clip_ratio/high_mean": 0.0013596752687590197,
      "clip_ratio/low_mean": 0.003230344478652114,
      "clip_ratio/low_min": 0.00015057870041346177,
      "clip_ratio/region_mean": 0.004590019838360604,
      "epoch": 0.13589299360084933,
      "grad_norm": 0.969578206539154,
      "learning_rate": 2e-07,
      "loss": 0.0679,
      "step": 1456
    },
    {
      "clip_ratio/high_max": 0.0036511849248199724,
      "clip_ratio/high_mean": 0.0013421898183878511,
      "clip_ratio/low_mean": 0.0030917273106751963,
      "clip_ratio/low_min": 5.652698382618837e-05,
      "clip_ratio/region_mean": 0.004433917158166878,
      "epoch": 0.13598632670084992,
      "grad_norm": 1.054965853691101,
      "learning_rate": 2e-07,
      "loss": 0.0287,
      "step": 1457
    },
    {
      "clip_ratio/high_max": 0.0032520052263862453,
      "clip_ratio/high_mean": 0.0011596130243560765,
      "clip_ratio/low_mean": 0.0031603337192791514,
      "clip_ratio/low_min": 0.00018933411593025085,
      "clip_ratio/region_mean": 0.00431994679820491,
      "epoch": 0.1360796598008505,
      "grad_norm": 1.4219534397125244,
      "learning_rate": 2e-07,
      "loss": 0.0943,
      "step": 1458
    },
    {
      "clip_ratio/high_max": 0.00430202076677233,
      "clip_ratio/high_mean": 0.0016392757897847332,
      "clip_ratio/low_mean": 0.0036003288405481726,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.005239604593953118,
      "epoch": 0.13617299290085108,
      "grad_norm": 43.294593811035156,
      "learning_rate": 2e-07,
      "loss": 0.0336,
      "step": 1459
    },
    {
      "clip_ratio/high_max": 0.0035026593250222504,
      "clip_ratio/high_mean": 0.0013563765496655833,
      "clip_ratio/low_mean": 0.0033182903280248865,
      "clip_ratio/low_min": 0.00013439610575005645,
      "clip_ratio/region_mean": 0.004674666924984194,
      "epoch": 0.13626632600085167,
      "grad_norm": 1.0633057355880737,
      "learning_rate": 2e-07,
      "loss": 0.0427,
      "step": 1460
    },
    {
      "clip_ratio/high_max": 0.0044785700883949175,
      "clip_ratio/high_mean": 0.0015623941544617992,
      "clip_ratio/low_mean": 0.004423938582476694,
      "clip_ratio/low_min": 0.000145254594826838,
      "clip_ratio/region_mean": 0.005986332820612006,
      "epoch": 0.13635965910085224,
      "grad_norm": 2.145371913909912,
      "learning_rate": 2e-07,
      "loss": 0.0382,
      "step": 1461
    },
    {
      "clip_ratio/high_max": 0.004140974429901689,
      "clip_ratio/high_mean": 0.0015549366071354598,
      "clip_ratio/low_mean": 0.004191668325802311,
      "clip_ratio/low_min": 8.336111932294443e-05,
      "clip_ratio/region_mean": 0.005746605005697347,
      "epoch": 0.13645299220085283,
      "grad_norm": 2.1271820068359375,
      "learning_rate": 2e-07,
      "loss": 0.0528,
      "step": 1462
    },
    {
      "clip_ratio/high_max": 0.003508572459395509,
      "clip_ratio/high_mean": 0.0014288541897258256,
      "clip_ratio/low_mean": 0.004070622875588015,
      "clip_ratio/low_min": 0.00017038987243722659,
      "clip_ratio/region_mean": 0.005499477119883522,
      "epoch": 0.13654632530085342,
      "grad_norm": 1.6256355047225952,
      "learning_rate": 2e-07,
      "loss": 0.062,
      "step": 1463
    },
    {
      "clip_ratio/high_max": 0.003687793247081572,
      "clip_ratio/high_mean": 0.0012284385920793284,
      "clip_ratio/low_mean": 0.004748032690258697,
      "clip_ratio/low_min": 0.00045663763739867136,
      "clip_ratio/region_mean": 0.0059764712932519615,
      "epoch": 0.13663965840085399,
      "grad_norm": 12.150602340698242,
      "learning_rate": 2e-07,
      "loss": 0.0869,
      "step": 1464
    },
    {
      "clip_ratio/high_max": 0.004284890856069978,
      "clip_ratio/high_mean": 0.00160679801410879,
      "clip_ratio/low_mean": 0.004744461111840792,
      "clip_ratio/low_min": 0.0005952937062829733,
      "clip_ratio/region_mean": 0.0063512590713799,
      "epoch": 0.13673299150085458,
      "grad_norm": 3.128418445587158,
      "learning_rate": 2e-07,
      "loss": 0.1109,
      "step": 1465
    },
    {
      "clip_ratio/high_max": 0.0039977570122573525,
      "clip_ratio/high_mean": 0.0013557869588112226,
      "clip_ratio/low_mean": 0.004711387358838692,
      "clip_ratio/low_min": 0.0007294126799024525,
      "clip_ratio/region_mean": 0.006067174443160184,
      "epoch": 0.13682632460085517,
      "grad_norm": 1.4236468076705933,
      "learning_rate": 2e-07,
      "loss": 0.083,
      "step": 1466
    },
    {
      "clip_ratio/high_max": 0.0042467395614949055,
      "clip_ratio/high_mean": 0.0016202096594497561,
      "clip_ratio/low_mean": 0.004201971125439741,
      "clip_ratio/low_min": 0.00028734744773828425,
      "clip_ratio/region_mean": 0.00582218095951248,
      "epoch": 0.13691965770085573,
      "grad_norm": 1095.0185546875,
      "learning_rate": 2e-07,
      "loss": 0.1467,
      "step": 1467
    },
    {
      "clip_ratio/high_max": 0.004691912108683027,
      "clip_ratio/high_mean": 0.0016341140872100368,
      "clip_ratio/low_mean": 0.005747154253185727,
      "clip_ratio/low_min": 0.0005838838196723373,
      "clip_ratio/region_mean": 0.007381268369499594,
      "epoch": 0.13701299080085633,
      "grad_norm": 1.6314975023269653,
      "learning_rate": 2e-07,
      "loss": 0.045,
      "step": 1468
    },
    {
      "clip_ratio/high_max": 0.0041639123010099865,
      "clip_ratio/high_mean": 0.0014945414804969914,
      "clip_ratio/low_mean": 0.005325760808773339,
      "clip_ratio/low_min": 0.00014301269766292535,
      "clip_ratio/region_mean": 0.006820301932748407,
      "epoch": 0.13710632390085692,
      "grad_norm": 1.2559224367141724,
      "learning_rate": 2e-07,
      "loss": 0.0375,
      "step": 1469
    },
    {
      "clip_ratio/high_max": 0.004616990147042088,
      "clip_ratio/high_mean": 0.0019184701377525926,
      "clip_ratio/low_mean": 0.005328517538146116,
      "clip_ratio/low_min": 0.0006260307491174899,
      "clip_ratio/region_mean": 0.007246987632242963,
      "epoch": 0.1371996570008575,
      "grad_norm": 1.7895684242248535,
      "learning_rate": 2e-07,
      "loss": 0.0631,
      "step": 1470
    },
    {
      "clip_ratio/high_max": 0.004513877691351809,
      "clip_ratio/high_mean": 0.0018984657799592242,
      "clip_ratio/low_mean": 0.005441672969027422,
      "clip_ratio/low_min": 0.00042876379666267894,
      "clip_ratio/region_mean": 0.0073401387489866465,
      "epoch": 0.13729299010085808,
      "grad_norm": 1.7593392133712769,
      "learning_rate": 2e-07,
      "loss": 0.0354,
      "step": 1471
    },
    {
      "clip_ratio/high_max": 0.004719357923022471,
      "clip_ratio/high_mean": 0.001891336745757144,
      "clip_ratio/low_mean": 0.005200485480600037,
      "clip_ratio/low_min": 0.00014725681103300303,
      "clip_ratio/region_mean": 0.007091822393704206,
      "epoch": 0.13738632320085867,
      "grad_norm": 3.064988613128662,
      "learning_rate": 2e-07,
      "loss": 0.034,
      "step": 1472
    },
    {
      "clip_ratio/high_max": 0.006331202792352997,
      "clip_ratio/high_mean": 0.002299361272889655,
      "clip_ratio/low_mean": 0.005316790717188269,
      "clip_ratio/low_min": 0.00024288724671350792,
      "clip_ratio/region_mean": 0.007616152142873034,
      "epoch": 0.13747965630085926,
      "grad_norm": 8.548855781555176,
      "learning_rate": 2e-07,
      "loss": 0.0353,
      "step": 1473
    },
    {
      "clip_ratio/high_max": 0.005207854323089123,
      "clip_ratio/high_mean": 0.002193677566538099,
      "clip_ratio/low_mean": 0.005998676788294688,
      "clip_ratio/low_min": 0.00036002738488605246,
      "clip_ratio/region_mean": 0.00819235443486832,
      "epoch": 0.13757298940085982,
      "grad_norm": 3.0118956565856934,
      "learning_rate": 2e-07,
      "loss": 0.046,
      "step": 1474
    },
    {
      "clip_ratio/high_max": 0.006218437614734285,
      "clip_ratio/high_mean": 0.0022107767945271917,
      "clip_ratio/low_mean": 0.0058808091198443435,
      "clip_ratio/low_min": 0.00024875648523448035,
      "clip_ratio/region_mean": 0.008091586045338772,
      "epoch": 0.13766632250086042,
      "grad_norm": 2.0009605884552,
      "learning_rate": 2e-07,
      "loss": 0.0484,
      "step": 1475
    },
    {
      "clip_ratio/high_max": 0.00552432682889048,
      "clip_ratio/high_mean": 0.0019232859303883743,
      "clip_ratio/low_mean": 0.006324873960693367,
      "clip_ratio/low_min": 0.00018492533854441717,
      "clip_ratio/region_mean": 0.008248159661889076,
      "epoch": 0.137759655600861,
      "grad_norm": 33.7970085144043,
      "learning_rate": 2e-07,
      "loss": 0.0463,
      "step": 1476
    },
    {
      "clip_ratio/high_max": 0.005923492892179638,
      "clip_ratio/high_mean": 0.002552726731664734,
      "clip_ratio/low_mean": 0.00571142508124467,
      "clip_ratio/low_min": 0.00025221707619493827,
      "clip_ratio/region_mean": 0.008264151721959934,
      "epoch": 0.13785298870086157,
      "grad_norm": 2.7130908966064453,
      "learning_rate": 2e-07,
      "loss": 0.0527,
      "step": 1477
    },
    {
      "clip_ratio/high_max": 0.005575213326665107,
      "clip_ratio/high_mean": 0.001979000269784592,
      "clip_ratio/low_mean": 0.006446830491768196,
      "clip_ratio/low_min": 0.0006341262560454197,
      "clip_ratio/region_mean": 0.008425830717897043,
      "epoch": 0.13794632180086216,
      "grad_norm": 3.3413078784942627,
      "learning_rate": 2e-07,
      "loss": 0.0913,
      "step": 1478
    },
    {
      "clip_ratio/high_max": 0.005666428143740632,
      "clip_ratio/high_mean": 0.0018616802190081216,
      "clip_ratio/low_mean": 0.006947968955500983,
      "clip_ratio/low_min": 0.0002819410183292348,
      "clip_ratio/region_mean": 0.008809649152681231,
      "epoch": 0.13803965490086276,
      "grad_norm": 1.8736939430236816,
      "learning_rate": 2e-07,
      "loss": 0.0835,
      "step": 1479
    },
    {
      "clip_ratio/high_max": 0.00663354728021659,
      "clip_ratio/high_mean": 0.0026273501680407207,
      "clip_ratio/low_mean": 0.006056972619262524,
      "clip_ratio/low_min": 0.0004918819286103826,
      "clip_ratio/region_mean": 0.008684322820045054,
      "epoch": 0.13813298800086332,
      "grad_norm": 23.508838653564453,
      "learning_rate": 2e-07,
      "loss": 0.0536,
      "step": 1480
    },
    {
      "clip_ratio/high_max": 0.006675719050690532,
      "clip_ratio/high_mean": 0.002241718721052166,
      "clip_ratio/low_mean": 0.006085971981519833,
      "clip_ratio/low_min": 0.0002589657742646523,
      "clip_ratio/region_mean": 0.008327690593432635,
      "epoch": 0.1382263211008639,
      "grad_norm": 1.6455236673355103,
      "learning_rate": 2e-07,
      "loss": 0.0328,
      "step": 1481
    },
    {
      "clip_ratio/high_max": 0.006918589846463874,
      "clip_ratio/high_mean": 0.0026504000161367003,
      "clip_ratio/low_mean": 0.007400747010251507,
      "clip_ratio/low_min": 0.0013944573365733959,
      "clip_ratio/region_mean": 0.010051146891782992,
      "epoch": 0.1383196542008645,
      "grad_norm": 2.862809419631958,
      "learning_rate": 2e-07,
      "loss": 0.072,
      "step": 1482
    },
    {
      "clip_ratio/high_max": 0.0061363898566924036,
      "clip_ratio/high_mean": 0.002340374187042471,
      "clip_ratio/low_mean": 0.006821267583291046,
      "clip_ratio/low_min": 0.0005191047603148036,
      "clip_ratio/region_mean": 0.00916164173395373,
      "epoch": 0.13841298730086507,
      "grad_norm": 6.401864528656006,
      "learning_rate": 2e-07,
      "loss": 0.0583,
      "step": 1483
    },
    {
      "clip_ratio/high_max": 0.005868579653906636,
      "clip_ratio/high_mean": 0.0024353633052669466,
      "clip_ratio/low_mean": 0.007369162238319404,
      "clip_ratio/low_min": 0.0007636391774212825,
      "clip_ratio/region_mean": 0.009804525645449758,
      "epoch": 0.13850632040086566,
      "grad_norm": 2.3226635456085205,
      "learning_rate": 2e-07,
      "loss": 0.0474,
      "step": 1484
    },
    {
      "clip_ratio/high_max": 0.0065404388442402706,
      "clip_ratio/high_mean": 0.002226689553936012,
      "clip_ratio/low_mean": 0.006948075955733657,
      "clip_ratio/low_min": 0.0003735497812158428,
      "clip_ratio/region_mean": 0.009174765640636906,
      "epoch": 0.13859965350086625,
      "grad_norm": 24.28095054626465,
      "learning_rate": 2e-07,
      "loss": 0.0374,
      "step": 1485
    },
    {
      "clip_ratio/high_max": 0.007796584439347498,
      "clip_ratio/high_mean": 0.0027821751791634597,
      "clip_ratio/low_mean": 0.008453633199678734,
      "clip_ratio/low_min": 0.00038704232429154217,
      "clip_ratio/region_mean": 0.011235808546189219,
      "epoch": 0.13869298660086682,
      "grad_norm": 4.270010471343994,
      "learning_rate": 2e-07,
      "loss": 0.0548,
      "step": 1486
    },
    {
      "clip_ratio/high_max": 0.006832428654888645,
      "clip_ratio/high_mean": 0.002934200681920629,
      "clip_ratio/low_mean": 0.007350774394581094,
      "clip_ratio/low_min": 0.0008920675900299102,
      "clip_ratio/region_mean": 0.010284974938258529,
      "epoch": 0.1387863197008674,
      "grad_norm": 22.819581985473633,
      "learning_rate": 2e-07,
      "loss": 0.0367,
      "step": 1487
    },
    {
      "clip_ratio/high_max": 0.00845759900403209,
      "clip_ratio/high_mean": 0.0031235256501531694,
      "clip_ratio/low_mean": 0.005614174922811799,
      "clip_ratio/low_min": 0.000335266646288801,
      "clip_ratio/region_mean": 0.008737700496567413,
      "epoch": 0.138879652800868,
      "grad_norm": 3.468803882598877,
      "learning_rate": 2e-07,
      "loss": 0.0248,
      "step": 1488
    },
    {
      "clip_ratio/high_max": 0.006896912178490311,
      "clip_ratio/high_mean": 0.002735484355071094,
      "clip_ratio/low_mean": 0.007968440011609346,
      "clip_ratio/low_min": 0.00043800368439406157,
      "clip_ratio/region_mean": 0.010703924344852567,
      "epoch": 0.13897298590086857,
      "grad_norm": 4.241065502166748,
      "learning_rate": 2e-07,
      "loss": 0.0701,
      "step": 1489
    },
    {
      "clip_ratio/high_max": 0.008602060668636113,
      "clip_ratio/high_mean": 0.0029603758521261625,
      "clip_ratio/low_mean": 0.007971873608767055,
      "clip_ratio/low_min": 0.0006832727885921486,
      "clip_ratio/region_mean": 0.010932249497273006,
      "epoch": 0.13906631900086916,
      "grad_norm": 5.218986988067627,
      "learning_rate": 2e-07,
      "loss": 0.0564,
      "step": 1490
    },
    {
      "clip_ratio/high_max": 0.0074678011442301795,
      "clip_ratio/high_mean": 0.003028563307452714,
      "clip_ratio/low_mean": 0.00805964546452742,
      "clip_ratio/low_min": 0.0005745011440012604,
      "clip_ratio/region_mean": 0.011088208586443216,
      "epoch": 0.13915965210086975,
      "grad_norm": 2.2884485721588135,
      "learning_rate": 2e-07,
      "loss": 0.0121,
      "step": 1491
    },
    {
      "clip_ratio/high_max": 0.0103855915076565,
      "clip_ratio/high_mean": 0.004188959836028516,
      "clip_ratio/low_mean": 0.006645009838393889,
      "clip_ratio/low_min": 0.001080509799066931,
      "clip_ratio/region_mean": 0.01083396963076666,
      "epoch": 0.13925298520087034,
      "grad_norm": 8.672272682189941,
      "learning_rate": 2e-07,
      "loss": 0.056,
      "step": 1492
    },
    {
      "clip_ratio/high_max": 0.008909284821129404,
      "clip_ratio/high_mean": 0.0031841247400734574,
      "clip_ratio/low_mean": 0.009349468600703403,
      "clip_ratio/low_min": 0.000671421985316556,
      "clip_ratio/region_mean": 0.01253359334077686,
      "epoch": 0.1393463183008709,
      "grad_norm": 4.608011722564697,
      "learning_rate": 2e-07,
      "loss": 0.0528,
      "step": 1493
    },
    {
      "clip_ratio/high_max": 0.010531258114497177,
      "clip_ratio/high_mean": 0.00379265307856258,
      "clip_ratio/low_mean": 0.007463000249117613,
      "clip_ratio/low_min": 0.0006122993363533169,
      "clip_ratio/region_mean": 0.011255653109401464,
      "epoch": 0.1394396514008715,
      "grad_norm": 6.114775657653809,
      "learning_rate": 2e-07,
      "loss": 0.0518,
      "step": 1494
    },
    {
      "clip_ratio/high_max": 0.007593485788675025,
      "clip_ratio/high_mean": 0.0027870056583196856,
      "clip_ratio/low_mean": 0.008355341502465308,
      "clip_ratio/low_min": 0.00039152655517682433,
      "clip_ratio/region_mean": 0.011142347299028188,
      "epoch": 0.1395329845008721,
      "grad_norm": 3.744758367538452,
      "learning_rate": 2e-07,
      "loss": 0.0659,
      "step": 1495
    },
    {
      "clip_ratio/high_max": 0.009614675014745444,
      "clip_ratio/high_mean": 0.0035036601730098482,
      "clip_ratio/low_mean": 0.0075600906275212765,
      "clip_ratio/low_min": 0.0006339566607493907,
      "clip_ratio/region_mean": 0.011063750804169104,
      "epoch": 0.13962631760087266,
      "grad_norm": 43.78133010864258,
      "learning_rate": 2e-07,
      "loss": 0.0662,
      "step": 1496
    },
    {
      "clip_ratio/high_max": 0.01048118996550329,
      "clip_ratio/high_mean": 0.0037377056141849607,
      "clip_ratio/low_mean": 0.009337985538877547,
      "clip_ratio/low_min": 0.0005732829886255786,
      "clip_ratio/region_mean": 0.013075691240373999,
      "epoch": 0.13971965070087325,
      "grad_norm": 10.085516929626465,
      "learning_rate": 2e-07,
      "loss": 0.0628,
      "step": 1497
    },
    {
      "clip_ratio/high_max": 0.010500032862182707,
      "clip_ratio/high_mean": 0.00373045325250132,
      "clip_ratio/low_mean": 0.009753571037435904,
      "clip_ratio/low_min": 0.0014065109280636534,
      "clip_ratio/region_mean": 0.013484024355420843,
      "epoch": 0.13981298380087384,
      "grad_norm": 9.888315200805664,
      "learning_rate": 2e-07,
      "loss": 0.0829,
      "step": 1498
    },
    {
      "clip_ratio/high_max": 0.00988983758725226,
      "clip_ratio/high_mean": 0.004135534349188674,
      "clip_ratio/low_mean": 0.008053027151618153,
      "clip_ratio/low_min": 0.0001524157851235941,
      "clip_ratio/region_mean": 0.012188561784569174,
      "epoch": 0.1399063169008744,
      "grad_norm": 3.000796318054199,
      "learning_rate": 2e-07,
      "loss": 0.0328,
      "step": 1499
    },
    {
      "clip_ratio/high_max": 0.010463965736562386,
      "clip_ratio/high_mean": 0.0040103903447743505,
      "clip_ratio/low_mean": 0.009397264599101618,
      "clip_ratio/low_min": 0.0007881463825469837,
      "clip_ratio/region_mean": 0.013407654885668308,
      "epoch": 0.139999650000875,
      "grad_norm": 5.209139347076416,
      "learning_rate": 2e-07,
      "loss": 0.0029,
      "step": 1500
    },
    {
      "clip_ratio/high_max": 0.008385888795601204,
      "clip_ratio/high_mean": 0.0036111978988628834,
      "clip_ratio/low_mean": 0.00833279881044291,
      "clip_ratio/low_min": 0.00047047092812135816,
      "clip_ratio/region_mean": 0.011943996825721115,
      "epoch": 0.1400929831008756,
      "grad_norm": 2.6238529682159424,
      "learning_rate": 2e-07,
      "loss": 0.0501,
      "step": 1501
    },
    {
      "clip_ratio/high_max": 0.00948066305136308,
      "clip_ratio/high_mean": 0.003758178456337191,
      "clip_ratio/low_mean": 0.008748326712520793,
      "clip_ratio/low_min": 0.0005665630960720591,
      "clip_ratio/region_mean": 0.01250650524161756,
      "epoch": 0.14018631620087615,
      "grad_norm": 6.539761543273926,
      "learning_rate": 2e-07,
      "loss": 0.0743,
      "step": 1502
    },
    {
      "clip_ratio/high_max": 0.010480839715455659,
      "clip_ratio/high_mean": 0.003898135262716096,
      "clip_ratio/low_mean": 0.010391399817308411,
      "clip_ratio/low_min": 0.0010799056763062254,
      "clip_ratio/region_mean": 0.014289535058196634,
      "epoch": 0.14027964930087675,
      "grad_norm": 6.7871012687683105,
      "learning_rate": 2e-07,
      "loss": 0.056,
      "step": 1503
    },
    {
      "clip_ratio/high_max": 0.011206004084669985,
      "clip_ratio/high_mean": 0.0042216691945213825,
      "clip_ratio/low_mean": 0.009597584343282506,
      "clip_ratio/low_min": 0.0016802061363705434,
      "clip_ratio/region_mean": 0.013819253770634532,
      "epoch": 0.14037298240087734,
      "grad_norm": 188.27972412109375,
      "learning_rate": 2e-07,
      "loss": 0.0669,
      "step": 1504
    },
    {
      "clip_ratio/high_max": 0.009206546877976507,
      "clip_ratio/high_mean": 0.0033995092890108936,
      "clip_ratio/low_mean": 0.010470787150552496,
      "clip_ratio/low_min": 0.0006538449379149824,
      "clip_ratio/region_mean": 0.013870296534150839,
      "epoch": 0.1404663155008779,
      "grad_norm": 4.114729404449463,
      "learning_rate": 2e-07,
      "loss": 0.0662,
      "step": 1505
    },
    {
      "clip_ratio/high_max": 0.009534433702356182,
      "clip_ratio/high_mean": 0.003739131920156069,
      "clip_ratio/low_mean": 0.01049463200615719,
      "clip_ratio/low_min": 0.0005600358708761632,
      "clip_ratio/region_mean": 0.014233763999072835,
      "epoch": 0.1405596486008785,
      "grad_norm": 7.1068549156188965,
      "learning_rate": 2e-07,
      "loss": 0.0813,
      "step": 1506
    },
    {
      "clip_ratio/high_max": 0.010350649943575263,
      "clip_ratio/high_mean": 0.0036709518535644747,
      "clip_ratio/low_mean": 0.0107872890366707,
      "clip_ratio/low_min": 0.0009237701160600409,
      "clip_ratio/region_mean": 0.014458240912063047,
      "epoch": 0.1406529817008791,
      "grad_norm": 4.928596019744873,
      "learning_rate": 2e-07,
      "loss": 0.0376,
      "step": 1507
    },
    {
      "clip_ratio/high_max": 0.011022994323866442,
      "clip_ratio/high_mean": 0.00394003411201993,
      "clip_ratio/low_mean": 0.011775011342251673,
      "clip_ratio/low_min": 0.0012715245684375986,
      "clip_ratio/region_mean": 0.01571504567982629,
      "epoch": 0.14074631480087965,
      "grad_norm": 10.586506843566895,
      "learning_rate": 2e-07,
      "loss": 0.079,
      "step": 1508
    },
    {
      "clip_ratio/high_max": 0.010411949915578589,
      "clip_ratio/high_mean": 0.004011575219919905,
      "clip_ratio/low_mean": 0.012277233676286414,
      "clip_ratio/low_min": 0.0010456988966325298,
      "clip_ratio/region_mean": 0.01628880901262164,
      "epoch": 0.14083964790088024,
      "grad_norm": 114.8277587890625,
      "learning_rate": 2e-07,
      "loss": 0.0728,
      "step": 1509
    },
    {
      "clip_ratio/high_max": 0.009721985727082938,
      "clip_ratio/high_mean": 0.00394196772685973,
      "clip_ratio/low_mean": 0.012693684577243403,
      "clip_ratio/low_min": 0.0009633996814955026,
      "clip_ratio/region_mean": 0.016635652544209734,
      "epoch": 0.14093298100088084,
      "grad_norm": 4.461319923400879,
      "learning_rate": 2e-07,
      "loss": 0.071,
      "step": 1510
    },
    {
      "clip_ratio/high_max": 0.010852181134396233,
      "clip_ratio/high_mean": 0.004392207058117492,
      "clip_ratio/low_mean": 0.008701858692802489,
      "clip_ratio/low_min": 0.00019897828315151855,
      "clip_ratio/region_mean": 0.013094065710902214,
      "epoch": 0.14102631410088143,
      "grad_norm": 4.938162803649902,
      "learning_rate": 2e-07,
      "loss": 0.0397,
      "step": 1511
    },
    {
      "clip_ratio/high_max": 0.009760048109455965,
      "clip_ratio/high_mean": 0.003953845791329513,
      "clip_ratio/low_mean": 0.01263499160995707,
      "clip_ratio/low_min": 0.001086536023649387,
      "clip_ratio/region_mean": 0.01658883731579408,
      "epoch": 0.141119647200882,
      "grad_norm": 14.981100082397461,
      "learning_rate": 2e-07,
      "loss": 0.063,
      "step": 1512
    },
    {
      "clip_ratio/high_max": 0.013405644509475678,
      "clip_ratio/high_mean": 0.004705114450189285,
      "clip_ratio/low_mean": 0.013370266067795455,
      "clip_ratio/low_min": 0.0012662416702369228,
      "clip_ratio/region_mean": 0.018075380648951977,
      "epoch": 0.14121298030088258,
      "grad_norm": 23.063703536987305,
      "learning_rate": 2e-07,
      "loss": 0.0978,
      "step": 1513
    },
    {
      "clip_ratio/high_max": 0.01309622050030157,
      "clip_ratio/high_mean": 0.004619080093107186,
      "clip_ratio/low_mean": 0.013665582868270576,
      "clip_ratio/low_min": 0.0014160636492306367,
      "clip_ratio/region_mean": 0.018284663325175643,
      "epoch": 0.14130631340088318,
      "grad_norm": 9.61037826538086,
      "learning_rate": 2e-07,
      "loss": 0.0636,
      "step": 1514
    },
    {
      "clip_ratio/high_max": 0.010971913812682033,
      "clip_ratio/high_mean": 0.004688748063927051,
      "clip_ratio/low_mean": 0.010022249130997807,
      "clip_ratio/low_min": 0.0015986244397936389,
      "clip_ratio/region_mean": 0.014710997260408476,
      "epoch": 0.14139964650088374,
      "grad_norm": 163.98851013183594,
      "learning_rate": 2e-07,
      "loss": 0.0328,
      "step": 1515
    },
    {
      "clip_ratio/high_max": 0.01266252383356914,
      "clip_ratio/high_mean": 0.004752950670081191,
      "clip_ratio/low_mean": 0.012311642232816666,
      "clip_ratio/low_min": 0.0008202619792427868,
      "clip_ratio/region_mean": 0.017064592888345942,
      "epoch": 0.14149297960088433,
      "grad_norm": 11.858915328979492,
      "learning_rate": 2e-07,
      "loss": 0.0785,
      "step": 1516
    },
    {
      "clip_ratio/high_max": 0.01245160264079459,
      "clip_ratio/high_mean": 0.004706357904069591,
      "clip_ratio/low_mean": 0.012294373140321113,
      "clip_ratio/low_min": 0.002134902752004564,
      "clip_ratio/region_mean": 0.017000731197185814,
      "epoch": 0.14158631270088493,
      "grad_norm": 8.54983139038086,
      "learning_rate": 2e-07,
      "loss": 0.0719,
      "step": 1517
    },
    {
      "clip_ratio/high_max": 0.009926143800839782,
      "clip_ratio/high_mean": 0.003591825268813409,
      "clip_ratio/low_mean": 0.01287001179298386,
      "clip_ratio/low_min": 0.00023505708668380976,
      "clip_ratio/region_mean": 0.016461836989037693,
      "epoch": 0.1416796458008855,
      "grad_norm": 42.633609771728516,
      "learning_rate": 2e-07,
      "loss": 0.097,
      "step": 1518
    },
    {
      "clip_ratio/high_max": 0.013024982617935166,
      "clip_ratio/high_mean": 0.004754815381602384,
      "clip_ratio/low_mean": 0.0128330857551191,
      "clip_ratio/low_min": 0.00032164011645363644,
      "clip_ratio/region_mean": 0.01758790109306574,
      "epoch": 0.14177297890088608,
      "grad_norm": 6.471938610076904,
      "learning_rate": 2e-07,
      "loss": 0.0448,
      "step": 1519
    },
    {
      "clip_ratio/high_max": 0.014478586497716606,
      "clip_ratio/high_mean": 0.0055814015795476735,
      "clip_ratio/low_mean": 0.012879426503786817,
      "clip_ratio/low_min": 0.001599843795702327,
      "clip_ratio/region_mean": 0.018460827763192356,
      "epoch": 0.14186631200088667,
      "grad_norm": 16.62783432006836,
      "learning_rate": 2e-07,
      "loss": 0.0601,
      "step": 1520
    },
    {
      "clip_ratio/high_max": 0.012882993323728442,
      "clip_ratio/high_mean": 0.004840794033952989,
      "clip_ratio/low_mean": 0.014288280683103949,
      "clip_ratio/low_min": 0.0013846508954884484,
      "clip_ratio/region_mean": 0.019129074295051396,
      "epoch": 0.14195964510088724,
      "grad_norm": 10.969073295593262,
      "learning_rate": 2e-07,
      "loss": 0.0709,
      "step": 1521
    },
    {
      "clip_ratio/high_max": 0.014034319610800594,
      "clip_ratio/high_mean": 0.005414353698142804,
      "clip_ratio/low_mean": 0.015940941084409133,
      "clip_ratio/low_min": 0.00034125147794838995,
      "clip_ratio/region_mean": 0.02135529473889619,
      "epoch": 0.14205297820088783,
      "grad_norm": 34.26850509643555,
      "learning_rate": 2e-07,
      "loss": 0.1027,
      "step": 1522
    },
    {
      "clip_ratio/high_max": 0.014943013578886166,
      "clip_ratio/high_mean": 0.005799706093966961,
      "clip_ratio/low_mean": 0.0159431979409419,
      "clip_ratio/low_min": 0.0019753236047108658,
      "clip_ratio/region_mean": 0.021742904267739505,
      "epoch": 0.14214631130088842,
      "grad_norm": 9.099319458007812,
      "learning_rate": 2e-07,
      "loss": 0.0793,
      "step": 1523
    },
    {
      "clip_ratio/high_max": 0.016448465175926685,
      "clip_ratio/high_mean": 0.005841576377861202,
      "clip_ratio/low_mean": 0.012623472095583566,
      "clip_ratio/low_min": 0.0012977936276001856,
      "clip_ratio/region_mean": 0.018465048517100513,
      "epoch": 0.142239644400889,
      "grad_norm": 15.552641868591309,
      "learning_rate": 2e-07,
      "loss": 0.0311,
      "step": 1524
    },
    {
      "clip_ratio/high_max": 0.012718146230326965,
      "clip_ratio/high_mean": 0.004639718637918122,
      "clip_ratio/low_mean": 0.013770155375823379,
      "clip_ratio/low_min": 0.0014278234739322215,
      "clip_ratio/region_mean": 0.01840987359173596,
      "epoch": 0.14233297750088958,
      "grad_norm": 71.0652084350586,
      "learning_rate": 2e-07,
      "loss": 0.1008,
      "step": 1525
    },
    {
      "clip_ratio/high_max": 0.013745399424806237,
      "clip_ratio/high_mean": 0.005304327511112206,
      "clip_ratio/low_mean": 0.013843146647559479,
      "clip_ratio/low_min": 0.0013580212034867145,
      "clip_ratio/region_mean": 0.01914747426053509,
      "epoch": 0.14242631060089017,
      "grad_norm": 3827.419677734375,
      "learning_rate": 2e-07,
      "loss": 0.2753,
      "step": 1526
    },
    {
      "clip_ratio/high_max": 0.01704944239463657,
      "clip_ratio/high_mean": 0.006721330850268714,
      "clip_ratio/low_mean": 0.013069258100586012,
      "clip_ratio/low_min": 0.0007864274375606328,
      "clip_ratio/region_mean": 0.01979058881988749,
      "epoch": 0.14251964370089074,
      "grad_norm": 7.572017192840576,
      "learning_rate": 2e-07,
      "loss": 0.0326,
      "step": 1527
    },
    {
      "clip_ratio/high_max": 0.016442522959550843,
      "clip_ratio/high_mean": 0.006326496739347931,
      "clip_ratio/low_mean": 0.01312543178210035,
      "clip_ratio/low_min": 0.0008171074950951152,
      "clip_ratio/region_mean": 0.019451929023489356,
      "epoch": 0.14261297680089133,
      "grad_norm": 8.53805160522461,
      "learning_rate": 2e-07,
      "loss": 0.0543,
      "step": 1528
    },
    {
      "clip_ratio/high_max": 0.014276863948907703,
      "clip_ratio/high_mean": 0.005592348927166313,
      "clip_ratio/low_mean": 0.01404675652156584,
      "clip_ratio/low_min": 0.0006839881825726479,
      "clip_ratio/region_mean": 0.019639105710666627,
      "epoch": 0.14270630990089192,
      "grad_norm": 37.78240966796875,
      "learning_rate": 2e-07,
      "loss": 0.1078,
      "step": 1529
    },
    {
      "clip_ratio/high_max": 0.015142606367589906,
      "clip_ratio/high_mean": 0.005922932890825905,
      "clip_ratio/low_mean": 0.015061702870298177,
      "clip_ratio/low_min": 0.0008201240125345066,
      "clip_ratio/region_mean": 0.020984635630156845,
      "epoch": 0.14279964300089248,
      "grad_norm": 22.309871673583984,
      "learning_rate": 2e-07,
      "loss": 0.0517,
      "step": 1530
    },
    {
      "clip_ratio/high_max": 0.01574518723646179,
      "clip_ratio/high_mean": 0.006336163976811804,
      "clip_ratio/low_mean": 0.016001800016965717,
      "clip_ratio/low_min": 0.0014258518058340997,
      "clip_ratio/region_mean": 0.02233796362997964,
      "epoch": 0.14289297610089308,
      "grad_norm": 52.65270233154297,
      "learning_rate": 2e-07,
      "loss": 0.09,
      "step": 1531
    },
    {
      "clip_ratio/high_max": 0.018542533740401268,
      "clip_ratio/high_mean": 0.007310303277336061,
      "clip_ratio/low_mean": 0.015105009370017797,
      "clip_ratio/low_min": 0.001293691952014342,
      "clip_ratio/region_mean": 0.02241531270556152,
      "epoch": 0.14298630920089367,
      "grad_norm": 10.39724349975586,
      "learning_rate": 2e-07,
      "loss": 0.0407,
      "step": 1532
    },
    {
      "clip_ratio/high_max": 0.020917464164085686,
      "clip_ratio/high_mean": 0.007530486167524941,
      "clip_ratio/low_mean": 0.014347026648465544,
      "clip_ratio/low_min": 0.0014942592242732644,
      "clip_ratio/region_mean": 0.021877513034269214,
      "epoch": 0.14307964230089426,
      "grad_norm": 20.651105880737305,
      "learning_rate": 2e-07,
      "loss": 0.0651,
      "step": 1533
    },
    {
      "clip_ratio/high_max": 0.01636326580774039,
      "clip_ratio/high_mean": 0.005423209979198873,
      "clip_ratio/low_mean": 0.018241409910842776,
      "clip_ratio/low_min": 0.002557979809353128,
      "clip_ratio/region_mean": 0.023664619715418667,
      "epoch": 0.14317297540089483,
      "grad_norm": 25.144960403442383,
      "learning_rate": 2e-07,
      "loss": 0.1248,
      "step": 1534
    },
    {
      "clip_ratio/high_max": 0.02010624815011397,
      "clip_ratio/high_mean": 0.007987363875145093,
      "clip_ratio/low_mean": 0.014099827560130507,
      "clip_ratio/low_min": 0.0022938479960430413,
      "clip_ratio/region_mean": 0.022087191173341125,
      "epoch": 0.14326630850089542,
      "grad_norm": 21.81289291381836,
      "learning_rate": 2e-07,
      "loss": 0.0541,
      "step": 1535
    },
    {
      "clip_ratio/high_max": 0.014984688896220177,
      "clip_ratio/high_mean": 0.006201296113431454,
      "clip_ratio/low_mean": 0.01496699801646173,
      "clip_ratio/low_min": 0.0006940177991054952,
      "clip_ratio/region_mean": 0.021168294362723827,
      "epoch": 0.143359641600896,
      "grad_norm": 97.85721588134766,
      "learning_rate": 2e-07,
      "loss": 0.1155,
      "step": 1536
    },
    {
      "clip_ratio/high_max": 0.0021196430916461395,
      "clip_ratio/high_mean": 0.0005031969892570487,
      "clip_ratio/low_mean": 0.0012564877797558438,
      "clip_ratio/low_min": 4.3615722461254336e-05,
      "clip_ratio/region_mean": 0.0017596847865206655,
      "completions/clipped_ratio": 0.1940220424107143,
      "completions/max_length": 4096.0,
      "completions/max_terminated_length": 4088.0,
      "completions/mean_length": 990.591796875,
      "completions/mean_terminated_length": 243.0307159423828,
      "completions/min_length": 12.0,
      "completions/min_terminated_length": 12.0,
      "epoch": 0.14345297470089657,
      "grad_norm": 2.641310930252075,
      "learning_rate": 2e-07,
      "loss": 0.0913,
      "num_tokens": 1136645105.0,
      "reward": 0.0988159254193306,
      "reward_std": 0.11764324456453323,
      "rewards/simpleverify_reward/mean": 0.09881591796875,
      "rewards/simpleverify_reward/std": 0.29841604828834534,
      "step": 1537
    },
    {
      "clip_ratio/high_max": 0.0009248777614629944,
      "clip_ratio/high_mean": 0.0002494698062491807,
      "clip_ratio/low_mean": 0.00121991393098142,
      "clip_ratio/low_min": 1.1382410320948111e-05,
      "clip_ratio/region_mean": 0.0014693837365484796,
      "epoch": 0.14354630780089717,
      "grad_norm": 0.580058217048645,
      "learning_rate": 2e-07,
      "loss": 0.088,
      "step": 1538
    },
    {
      "clip_ratio/high_max": 0.0017186277618748136,
      "clip_ratio/high_mean": 0.00043266852026135894,
      "clip_ratio/low_mean": 0.001394681527017383,
      "clip_ratio/low_min": 1.6476559721922968e-05,
      "clip_ratio/region_mean": 0.0018273500245413743,
      "epoch": 0.14363964090089776,
      "grad_norm": 4.160432815551758,
      "learning_rate": 2e-07,
      "loss": 0.0175,
      "step": 1539
    },
    {
      "clip_ratio/high_max": 0.00290394180410658,
      "clip_ratio/high_mean": 0.0005832867718709167,
      "clip_ratio/low_mean": 0.00105823777448677,
      "clip_ratio/low_min": 6.402730514309951e-05,
      "clip_ratio/region_mean": 0.0016415245645475807,
      "epoch": 0.14373297400089832,
      "grad_norm": 3.574641466140747,
      "learning_rate": 2e-07,
      "loss": 0.0506,
      "step": 1540
    },
    {
      "clip_ratio/high_max": 0.0010591922155072098,
      "clip_ratio/high_mean": 0.00030550576627774717,
      "clip_ratio/low_mean": 0.0016089271903183544,
      "clip_ratio/low_min": 3.3851657462946605e-05,
      "clip_ratio/region_mean": 0.0019144328762195073,
      "epoch": 0.14382630710089891,
      "grad_norm": 0.391309916973114,
      "learning_rate": 2e-07,
      "loss": 0.0613,
      "step": 1541
    },
    {
      "clip_ratio/high_max": 0.00243121982748562,
      "clip_ratio/high_mean": 0.0005177284097044321,
      "clip_ratio/low_mean": 0.0016252015921054408,
      "clip_ratio/low_min": 6.0420709814934526e-05,
      "clip_ratio/region_mean": 0.0021429300359159242,
      "epoch": 0.1439196402008995,
      "grad_norm": 2.6499602794647217,
      "learning_rate": 2e-07,
      "loss": 0.0113,
      "step": 1542
    },
    {
      "clip_ratio/high_max": 0.0007740434894003556,
      "clip_ratio/high_mean": 0.00018782196775646298,
      "clip_ratio/low_mean": 0.0014512754605675582,
      "clip_ratio/low_min": 2.97895689982397e-05,
      "clip_ratio/region_mean": 0.0016390974051319063,
      "epoch": 0.14401297330090007,
      "grad_norm": 1.3003000020980835,
      "learning_rate": 2e-07,
      "loss": 0.0748,
      "step": 1543
    },
    {
      "clip_ratio/high_max": 0.002311426052983734,
      "clip_ratio/high_mean": 0.00047950890302672633,
      "clip_ratio/low_mean": 0.0021022655546403257,
      "clip_ratio/low_min": 6.01604579060222e-05,
      "clip_ratio/region_mean": 0.0025817744281084742,
      "epoch": 0.14410630640090066,
      "grad_norm": 1.2963966131210327,
      "learning_rate": 2e-07,
      "loss": 0.0908,
      "step": 1544
    },
    {
      "clip_ratio/high_max": 0.0028650009371631313,
      "clip_ratio/high_mean": 0.0006087638957978925,
      "clip_ratio/low_mean": 0.001814946677768603,
      "clip_ratio/low_min": 7.642771197424736e-05,
      "clip_ratio/region_mean": 0.0024237105972133577,
      "epoch": 0.14419963950090126,
      "grad_norm": 3.2933709621429443,
      "learning_rate": 2e-07,
      "loss": 0.0244,
      "step": 1545
    },
    {
      "clip_ratio/high_max": 0.0018264889531565132,
      "clip_ratio/high_mean": 0.00040690698256184987,
      "clip_ratio/low_mean": 0.0026043957577712717,
      "clip_ratio/low_min": 0.00011290715337963775,
      "clip_ratio/region_mean": 0.0030113027460174635,
      "epoch": 0.14429297260090182,
      "grad_norm": 0.820268452167511,
      "learning_rate": 2e-07,
      "loss": 0.0889,
      "step": 1546
    },
    {
      "clip_ratio/high_max": 0.0014638961747550638,
      "clip_ratio/high_mean": 0.00040067920463116025,
      "clip_ratio/low_mean": 0.0017244839546037838,
      "clip_ratio/low_min": 1.8721270862442907e-05,
      "clip_ratio/region_mean": 0.0021251631660561543,
      "epoch": 0.1443863057009024,
      "grad_norm": 1.1142103672027588,
      "learning_rate": 2e-07,
      "loss": 0.0861,
      "step": 1547
    },
    {
      "clip_ratio/high_max": 0.0038958541372267064,
      "clip_ratio/high_mean": 0.0008711912500984909,
      "clip_ratio/low_mean": 0.0023179607960628346,
      "clip_ratio/low_min": 9.874154238787014e-05,
      "clip_ratio/region_mean": 0.003189151975675486,
      "epoch": 0.144479638800903,
      "grad_norm": 1.3785908222198486,
      "learning_rate": 2e-07,
      "loss": 0.002,
      "step": 1548
    },
    {
      "clip_ratio/high_max": 0.0017569900865055388,
      "clip_ratio/high_mean": 0.00038262602902250364,
      "clip_ratio/low_mean": 0.002074264280963689,
      "clip_ratio/low_min": 7.234633812913671e-05,
      "clip_ratio/region_mean": 0.002456890342728002,
      "epoch": 0.14457297190090357,
      "grad_norm": 1.6213676929473877,
      "learning_rate": 2e-07,
      "loss": 0.0605,
      "step": 1549
    },
    {
      "clip_ratio/high_max": 0.0017009091116051422,
      "clip_ratio/high_mean": 0.0003973875591327669,
      "clip_ratio/low_mean": 0.002339148621103959,
      "clip_ratio/low_min": 8.462114055873826e-05,
      "clip_ratio/region_mean": 0.002736536247539334,
      "epoch": 0.14466630500090416,
      "grad_norm": 2.787680149078369,
      "learning_rate": 2e-07,
      "loss": 0.1072,
      "step": 1550
    },
    {
      "clip_ratio/high_max": 0.0023180230091384146,
      "clip_ratio/high_mean": 0.0005066318562967354,
      "clip_ratio/low_mean": 0.0022704703587805852,
      "clip_ratio/low_min": 0.00015892461487965193,
      "clip_ratio/region_mean": 0.0027771022068918683,
      "epoch": 0.14475963810090475,
      "grad_norm": 1.9090454578399658,
      "learning_rate": 2e-07,
      "loss": 0.055,
      "step": 1551
    },
    {
      "clip_ratio/high_max": 0.0015037819921417395,
      "clip_ratio/high_mean": 0.0004018538354557677,
      "clip_ratio/low_mean": 0.0022508582078444306,
      "clip_ratio/low_min": 0.00012146332301199436,
      "clip_ratio/region_mean": 0.0026527121081016958,
      "epoch": 0.14485297120090532,
      "grad_norm": 3.303067207336426,
      "learning_rate": 2e-07,
      "loss": 0.0416,
      "step": 1552
    },
    {
      "clip_ratio/high_max": 0.0017093855171879113,
      "clip_ratio/high_mean": 0.00047568033909328733,
      "clip_ratio/low_mean": 0.002399211627562181,
      "clip_ratio/low_min": 8.037542920646956e-05,
      "clip_ratio/region_mean": 0.00287489188121981,
      "epoch": 0.1449463043009059,
      "grad_norm": 2.86083722114563,
      "learning_rate": 2e-07,
      "loss": 0.0625,
      "step": 1553
    },
    {
      "clip_ratio/high_max": 0.0024553460789320525,
      "clip_ratio/high_mean": 0.0005836718728460255,
      "clip_ratio/low_mean": 0.0026192884070042055,
      "clip_ratio/low_min": 6.0087362726335414e-05,
      "clip_ratio/region_mean": 0.0032029602843977045,
      "epoch": 0.1450396374009065,
      "grad_norm": 35.77680969238281,
      "learning_rate": 2e-07,
      "loss": 0.0955,
      "step": 1554
    },
    {
      "clip_ratio/high_max": 0.0029813846631441265,
      "clip_ratio/high_mean": 0.0007253582509747503,
      "clip_ratio/low_mean": 0.0024449789088976104,
      "clip_ratio/low_min": 0.00010927723269560374,
      "clip_ratio/region_mean": 0.0031703371278126724,
      "epoch": 0.1451329705009071,
      "grad_norm": 1.7170997858047485,
      "learning_rate": 2e-07,
      "loss": 0.0706,
      "step": 1555
    },
    {
      "clip_ratio/high_max": 0.001839655533331097,
      "clip_ratio/high_mean": 0.00046594555465162557,
      "clip_ratio/low_mean": 0.0028772918485628907,
      "clip_ratio/low_min": 0.00020019268504256615,
      "clip_ratio/region_mean": 0.0033432373202231247,
      "epoch": 0.14522630360090766,
      "grad_norm": 99.9493637084961,
      "learning_rate": 2e-07,
      "loss": 0.0899,
      "step": 1556
    },
    {
      "clip_ratio/high_max": 0.0028191102592245443,
      "clip_ratio/high_mean": 0.0006298077287283377,
      "clip_ratio/low_mean": 0.0025342290027765557,
      "clip_ratio/low_min": 0.0001354914406874741,
      "clip_ratio/region_mean": 0.0031640366723877378,
      "epoch": 0.14531963670090825,
      "grad_norm": 1.6621710062026978,
      "learning_rate": 2e-07,
      "loss": 0.0567,
      "step": 1557
    },
    {
      "clip_ratio/high_max": 0.0031349534160654002,
      "clip_ratio/high_mean": 0.0006469959677133374,
      "clip_ratio/low_mean": 0.0025516779605823103,
      "clip_ratio/low_min": 0.00010410030063212616,
      "clip_ratio/region_mean": 0.003198673941369634,
      "epoch": 0.14541296980090884,
      "grad_norm": 2.0807580947875977,
      "learning_rate": 2e-07,
      "loss": 0.0463,
      "step": 1558
    },
    {
      "clip_ratio/high_max": 0.0017299756855209125,
      "clip_ratio/high_mean": 0.0005205387569731101,
      "clip_ratio/low_mean": 0.0018997694769495865,
      "clip_ratio/low_min": 0.0001109719260057318,
      "clip_ratio/region_mean": 0.002420308239379665,
      "epoch": 0.1455063029009094,
      "grad_norm": 52.57670974731445,
      "learning_rate": 2e-07,
      "loss": 0.0853,
      "step": 1559
    },
    {
      "clip_ratio/high_max": 0.0033661488560028374,
      "clip_ratio/high_mean": 0.0008800770328889485,
      "clip_ratio/low_mean": 0.0021588474555755965,
      "clip_ratio/low_min": 0.00014527435632771812,
      "clip_ratio/region_mean": 0.0030389244930120185,
      "epoch": 0.14559963600091,
      "grad_norm": 6.196171760559082,
      "learning_rate": 2e-07,
      "loss": 0.0412,
      "step": 1560
    },
    {
      "clip_ratio/high_max": 0.0015093350666575134,
      "clip_ratio/high_mean": 0.0003557764500783378,
      "clip_ratio/low_mean": 0.002905678973547765,
      "clip_ratio/low_min": 0.00011970164268859662,
      "clip_ratio/region_mean": 0.003261455456595286,
      "epoch": 0.1456929691009106,
      "grad_norm": 102.10365295410156,
      "learning_rate": 2e-07,
      "loss": 0.0651,
      "step": 1561
    },
    {
      "clip_ratio/high_max": 0.002019521431066096,
      "clip_ratio/high_mean": 0.0005306261755322339,
      "clip_ratio/low_mean": 0.0019967839143646415,
      "clip_ratio/low_min": 0.00013193928316468373,
      "clip_ratio/region_mean": 0.002527410128095653,
      "epoch": 0.14578630220091116,
      "grad_norm": 4.868849754333496,
      "learning_rate": 2e-07,
      "loss": 0.0636,
      "step": 1562
    },
    {
      "clip_ratio/high_max": 0.006034212074155221,
      "clip_ratio/high_mean": 0.001083312703485717,
      "clip_ratio/low_mean": 0.002647472134412965,
      "clip_ratio/low_min": 4.128280852455646e-05,
      "clip_ratio/region_mean": 0.0037307847742340527,
      "epoch": 0.14587963530091175,
      "grad_norm": 15.132116317749023,
      "learning_rate": 2e-07,
      "loss": 0.0588,
      "step": 1563
    },
    {
      "clip_ratio/high_max": 0.003912050975486636,
      "clip_ratio/high_mean": 0.0008249418997365865,
      "clip_ratio/low_mean": 0.003138151139864931,
      "clip_ratio/low_min": 0.00023534113279310986,
      "clip_ratio/region_mean": 0.00396309289499186,
      "epoch": 0.14597296840091234,
      "grad_norm": 7.849503517150879,
      "learning_rate": 2e-07,
      "loss": 0.0895,
      "step": 1564
    },
    {
      "clip_ratio/high_max": 0.002090877253067447,
      "clip_ratio/high_mean": 0.0005327249273250345,
      "clip_ratio/low_mean": 0.0030958140960137825,
      "clip_ratio/low_min": 0.00013347401909413747,
      "clip_ratio/region_mean": 0.0036285390306147747,
      "epoch": 0.1460663015009129,
      "grad_norm": 204.26678466796875,
      "learning_rate": 2e-07,
      "loss": 0.0808,
      "step": 1565
    },
    {
      "clip_ratio/high_max": 0.0016339678209078556,
      "clip_ratio/high_mean": 0.00039930258117237827,
      "clip_ratio/low_mean": 0.002258690699818544,
      "clip_ratio/low_min": 5.310110282152891e-05,
      "clip_ratio/region_mean": 0.0026579932928143535,
      "epoch": 0.1461596346009135,
      "grad_norm": 42.09465789794922,
      "learning_rate": 2e-07,
      "loss": 0.0931,
      "step": 1566
    },
    {
      "clip_ratio/high_max": 0.002933861269866611,
      "clip_ratio/high_mean": 0.0006801888171139581,
      "clip_ratio/low_mean": 0.0025214328852598555,
      "clip_ratio/low_min": 0.0001578905362293881,
      "clip_ratio/region_mean": 0.003201621620974038,
      "epoch": 0.1462529677009141,
      "grad_norm": 3.0651299953460693,
      "learning_rate": 2e-07,
      "loss": 0.0722,
      "step": 1567
    },
    {
      "clip_ratio/high_max": 0.002410534302725864,
      "clip_ratio/high_mean": 0.0005788882303932041,
      "clip_ratio/low_mean": 0.0031551166030112654,
      "clip_ratio/low_min": 0.00013254908481030725,
      "clip_ratio/region_mean": 0.0037340048293117434,
      "epoch": 0.14634630080091465,
      "grad_norm": 6.625837326049805,
      "learning_rate": 2e-07,
      "loss": 0.1021,
      "step": 1568
    },
    {
      "clip_ratio/high_max": 0.002388019311183598,
      "clip_ratio/high_mean": 0.0005707476607312856,
      "clip_ratio/low_mean": 0.00233959115575999,
      "clip_ratio/low_min": 0.0001351745495412615,
      "clip_ratio/region_mean": 0.00291033888788661,
      "epoch": 0.14643963390091524,
      "grad_norm": 3.8021035194396973,
      "learning_rate": 2e-07,
      "loss": 0.0778,
      "step": 1569
    },
    {
      "clip_ratio/high_max": 0.003512184070132207,
      "clip_ratio/high_mean": 0.0007597188905492658,
      "clip_ratio/low_mean": 0.003070260729145957,
      "clip_ratio/low_min": 5.859381963091437e-05,
      "clip_ratio/region_mean": 0.003829979556030594,
      "epoch": 0.14653296700091584,
      "grad_norm": 123.35625457763672,
      "learning_rate": 2e-07,
      "loss": 0.0584,
      "step": 1570
    },
    {
      "clip_ratio/high_max": 0.002425365222734399,
      "clip_ratio/high_mean": 0.0006154531547508668,
      "clip_ratio/low_mean": 0.0031387264243676327,
      "clip_ratio/low_min": 0.00019874318604706787,
      "clip_ratio/region_mean": 0.0037541796336881816,
      "epoch": 0.1466263001009164,
      "grad_norm": 4.483541488647461,
      "learning_rate": 2e-07,
      "loss": 0.0511,
      "step": 1571
    },
    {
      "clip_ratio/high_max": 0.003263784194132313,
      "clip_ratio/high_mean": 0.0007810114752828667,
      "clip_ratio/low_mean": 0.0031168496534519363,
      "clip_ratio/low_min": 0.0004441272139956709,
      "clip_ratio/region_mean": 0.0038978611773927696,
      "epoch": 0.146719633200917,
      "grad_norm": 4.892777919769287,
      "learning_rate": 2e-07,
      "loss": 0.0801,
      "step": 1572
    },
    {
      "clip_ratio/high_max": 0.0026380216659163125,
      "clip_ratio/high_mean": 0.000684087528497912,
      "clip_ratio/low_mean": 0.00307053659344092,
      "clip_ratio/low_min": 4.470992280403152e-05,
      "clip_ratio/region_mean": 0.003754624216526281,
      "epoch": 0.14681296630091759,
      "grad_norm": 7.348733425140381,
      "learning_rate": 2e-07,
      "loss": 0.0826,
      "step": 1573
    },
    {
      "clip_ratio/high_max": 0.0025824330978139187,
      "clip_ratio/high_mean": 0.0006363135275933018,
      "clip_ratio/low_mean": 0.0026088758822879754,
      "clip_ratio/low_min": 8.612224155513104e-05,
      "clip_ratio/region_mean": 0.0032451892984681763,
      "epoch": 0.14690629940091818,
      "grad_norm": 4.69542932510376,
      "learning_rate": 2e-07,
      "loss": 0.1001,
      "step": 1574
    },
    {
      "clip_ratio/high_max": 0.0030242331558838487,
      "clip_ratio/high_mean": 0.0007134772458812222,
      "clip_ratio/low_mean": 0.0023354432778432965,
      "clip_ratio/low_min": 0.00026018249400294735,
      "clip_ratio/region_mean": 0.0030489204509649426,
      "epoch": 0.14699963250091874,
      "grad_norm": 7.368109703063965,
      "learning_rate": 2e-07,
      "loss": 0.0394,
      "step": 1575
    },
    {
      "clip_ratio/high_max": 0.0013022861121498863,
      "clip_ratio/high_mean": 0.0003627282846991875,
      "clip_ratio/low_mean": 0.00254511278035352,
      "clip_ratio/low_min": 0.00014610993275709916,
      "clip_ratio/region_mean": 0.002907841029809788,
      "epoch": 0.14709296560091933,
      "grad_norm": 5.674394130706787,
      "learning_rate": 2e-07,
      "loss": 0.0622,
      "step": 1576
    },
    {
      "clip_ratio/high_max": 0.002939444062576513,
      "clip_ratio/high_mean": 0.0007147967187393078,
      "clip_ratio/low_mean": 0.002912866257247515,
      "clip_ratio/low_min": 0.00011562355393834878,
      "clip_ratio/region_mean": 0.0036276629616622813,
      "epoch": 0.14718629870091993,
      "grad_norm": 7.482340335845947,
      "learning_rate": 2e-07,
      "loss": 0.0963,
      "step": 1577
    },
    {
      "clip_ratio/high_max": 0.002801228401949629,
      "clip_ratio/high_mean": 0.000751033802771417,
      "clip_ratio/low_mean": 0.0030029545741854236,
      "clip_ratio/low_min": 0.00020934944950568024,
      "clip_ratio/region_mean": 0.003753988457901869,
      "epoch": 0.1472796318009205,
      "grad_norm": 3.5337891578674316,
      "learning_rate": 2e-07,
      "loss": 0.0988,
      "step": 1578
    },
    {
      "clip_ratio/high_max": 0.00455448809225345,
      "clip_ratio/high_mean": 0.000937264690946904,
      "clip_ratio/low_mean": 0.0030893527618900407,
      "clip_ratio/low_min": 5.560707541008014e-05,
      "clip_ratio/region_mean": 0.004026617461931892,
      "epoch": 0.14737296490092108,
      "grad_norm": 4.725992202758789,
      "learning_rate": 2e-07,
      "loss": 0.0487,
      "step": 1579
    },
    {
      "clip_ratio/high_max": 0.004764191844515153,
      "clip_ratio/high_mean": 0.0010451707712491043,
      "clip_ratio/low_mean": 0.0036872572964057326,
      "clip_ratio/low_min": 0.0001870347732619848,
      "clip_ratio/region_mean": 0.0047324280749307945,
      "epoch": 0.14746629800092168,
      "grad_norm": 3.6773030757904053,
      "learning_rate": 2e-07,
      "loss": 0.0794,
      "step": 1580
    },
    {
      "clip_ratio/high_max": 0.006270758145547006,
      "clip_ratio/high_mean": 0.001358843494017492,
      "clip_ratio/low_mean": 0.0035475709082675166,
      "clip_ratio/low_min": 0.00011536174497450702,
      "clip_ratio/region_mean": 0.004906414425931871,
      "epoch": 0.14755963110092224,
      "grad_norm": 3.13504695892334,
      "learning_rate": 2e-07,
      "loss": 0.0491,
      "step": 1581
    },
    {
      "clip_ratio/high_max": 0.0037175638135522604,
      "clip_ratio/high_mean": 0.0009229039915226167,
      "clip_ratio/low_mean": 0.002810977886838373,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.003733881821972318,
      "epoch": 0.14765296420092283,
      "grad_norm": 6.711385726928711,
      "learning_rate": 2e-07,
      "loss": 0.1064,
      "step": 1582
    },
    {
      "clip_ratio/high_max": 0.0032769189565442502,
      "clip_ratio/high_mean": 0.0007121384387573926,
      "clip_ratio/low_mean": 0.0023528121964773163,
      "clip_ratio/low_min": 1.120540218835231e-05,
      "clip_ratio/region_mean": 0.0030649506152258255,
      "epoch": 0.14774629730092342,
      "grad_norm": 2.568202495574951,
      "learning_rate": 2e-07,
      "loss": 0.0369,
      "step": 1583
    },
    {
      "clip_ratio/high_max": 0.0038418287876993418,
      "clip_ratio/high_mean": 0.0008206715929190977,
      "clip_ratio/low_mean": 0.0030159057168930303,
      "clip_ratio/low_min": 6.879719876451418e-05,
      "clip_ratio/region_mean": 0.003836577307083644,
      "epoch": 0.147839630400924,
      "grad_norm": 2.4861927032470703,
      "learning_rate": 2e-07,
      "loss": 0.0732,
      "step": 1584
    },
    {
      "clip_ratio/high_max": 0.004801132787179085,
      "clip_ratio/high_mean": 0.0011252016811340582,
      "clip_ratio/low_mean": 0.004052828982821666,
      "clip_ratio/low_min": 0.00019886954305547988,
      "clip_ratio/region_mean": 0.005178030703973491,
      "epoch": 0.14793296350092458,
      "grad_norm": 16.173974990844727,
      "learning_rate": 2e-07,
      "loss": 0.084,
      "step": 1585
    },
    {
      "clip_ratio/high_max": 0.004438998192199506,
      "clip_ratio/high_mean": 0.0009170644143523532,
      "clip_ratio/low_mean": 0.003814064199104905,
      "clip_ratio/low_min": 0.00025108792033279315,
      "clip_ratio/region_mean": 0.004731128712592181,
      "epoch": 0.14802629660092517,
      "grad_norm": 3.275059461593628,
      "learning_rate": 2e-07,
      "loss": 0.043,
      "step": 1586
    },
    {
      "clip_ratio/high_max": 0.0033473419989604736,
      "clip_ratio/high_mean": 0.000780729805626379,
      "clip_ratio/low_mean": 0.0033988386785495095,
      "clip_ratio/low_min": 0.00016384675109293312,
      "clip_ratio/region_mean": 0.0041795684228418395,
      "epoch": 0.14811962970092574,
      "grad_norm": 1.7428197860717773,
      "learning_rate": 2e-07,
      "loss": 0.1016,
      "step": 1587
    },
    {
      "clip_ratio/high_max": 0.0035803153514279984,
      "clip_ratio/high_mean": 0.0007860034975237795,
      "clip_ratio/low_mean": 0.003742596185475122,
      "clip_ratio/low_min": 0.00025756657851161435,
      "clip_ratio/region_mean": 0.004528599682089407,
      "epoch": 0.14821296280092633,
      "grad_norm": 2.5137462615966797,
      "learning_rate": 2e-07,
      "loss": 0.098,
      "step": 1588
    },
    {
      "clip_ratio/high_max": 0.003256996857089689,
      "clip_ratio/high_mean": 0.0006716904331369733,
      "clip_ratio/low_mean": 0.002610788964375388,
      "clip_ratio/low_min": 0.0,
      "clip_ratio/region_mean": 0.0032824793743202463,
      "epoch": 0.14830629590092692,
      "grad_norm": 1.6252750158309937,
      "learning_rate": 2e-07,
      "loss": 0.066,
      "step": 1589
    },
    {
      "clip_ratio/high_max": 0.004591283850459149,
      "clip_ratio/high_mean": 0.000953434922962515,
      "clip_ratio/low_mean": 0.004615034311427735,
      "clip_ratio/low_min": 0.00024176068473025225,
      "clip_ratio/region_mean": 0.005568469190620817,
      "epoch": 0.14839962900092749,
      "grad_norm": 4.403492450714111,
      "learning_rate": 2e-07,
      "loss": 0.1163,
      "step": 1590
    },
    {
      "clip_ratio/high_max": 0.0022798290501668816,
      "clip_ratio/high_mean": 0.0005366639288695296,
      "clip_ratio/low_mean": 0.004208072023175191,
      "clip_ratio/low_min": 0.000287162241875194,
      "clip_ratio/region_mean": 0.004744735975691583,
      "epoch": 0.14849296210092808,
      "grad_norm": 9.639986038208008,
      "learning_rate": 2e-07,
      "loss": 0.1163,
      "step": 1591
    },
    {
      "clip_ratio/high_max": 0.0034552405231806915,
      "clip_ratio/high_mean": 0.0009680329421826173,
      "clip_ratio/low_mean": 0.004152048415562604,
      "clip_ratio/low_min": 3.4059947211062536e-05,
      "clip_ratio/region_mean": 0.0051200813613832,
      "epoch": 0.14858629520092867,
      "grad_norm": 4.676005840301514,
      "learning_rate": 2e-07,
      "loss": 0.0871,
      "step": 1592
    },
    {
      "clip_ratio/high_max": 0.0047938966781657655,
      "clip_ratio/high_mean": 0.0010236321704724105,
      "clip_ratio/low_mean": 0.005095163120131474,
      "clip_ratio/low_min": 0.00017800947671275935,
      "clip_ratio/region_mean": 0.006118795368820429,
      "epoch": 0.14867962830092923,
      "grad_norm": 2.9512834548950195,
      "learning_rate": 2e-07,
      "loss": 0.0628,
      "step": 1593
    },
    {
      "clip_ratio/high_max": 0.0031649012526031584,
      "clip_ratio/high_mean": 0.0008400449357850448,
      "clip_ratio/low_mean": 0.004872725396126043,
      "clip_ratio/low_min": 0.0001022861288220156,
      "clip_ratio/region_mean": 0.005712770340323914,
      "epoch": 0.14877296140092983,
      "grad_norm": 8.021714210510254,
      "learning_rate": 2e-07,
      "loss": 0.0876,
      "step": 1594
    },
    {
      "clip_ratio/high_max": 0.0056581776443636045,
      "clip_ratio/high_mean": 0.0012215650854159321,
      "clip_ratio/low_mean": 0.0033353065300616436,
      "clip_ratio/low_min": 4.075644028489478e-05,
      "clip_ratio/region_mean": 0.004556871608656365,
      "epoch": 0.14886629450093042,
      "grad_norm": 3.4012291431427,
      "learning_rate": 2e-07,
      "loss": 0.0767,
      "step": 1595
    },
    {
      "clip_ratio/high_max": 0.003456940128671704,
      "clip_ratio/high_mean": 0.0007819540712716844,
      "clip_ratio/low_mean": 0.0032705844787415117,
      "clip_ratio/low_min": 8.14315408206312e-05,
      "clip_ratio/region_mean": 0.004052538693940733,
      "epoch": 0.148959627600931,
      "grad_norm": 3.441681385040283,
      "learning_rate": 2e-07,
      "loss": 0.0863,
      "step": 1596
    },
    {
      "clip_ratio/high_max": 0.003477719430520665,
      "clip_ratio/high_mean": 0.0009134169715707685,
      "clip_ratio/low_mean": 0.0035796952215605415,
      "clip_ratio/low_min": 5.256518124951981e-05,
      "clip_ratio/region_mean": 0.00449311213742476,
      "epoch": 0.14905296070093157,
      "grad_norm": 27.548805236816406,
      "learning_rate": 2e-07,
      "loss": 0.0395,
      "step": 1597
    },
    {
      "clip_ratio/high_max": 0.004061659870785661,
      "clip_ratio/high_mean": 0.0010525919406063622,
      "clip_ratio/low_mean": 0.004888974126515677,
      "clip_ratio/low_min": 4.891526805295143e-05,
      "clip_ratio/region_mean": 0.005941566196270287,
      "epoch": 0.14914629380093217,
      "grad_norm": 54.571407318115234,
      "learning_rate": 2e-07,
      "loss": 0.1003,
      "step": 1598
    },
    {
      "clip_ratio/high_max": 0.0036978577336412854,
      "clip_ratio/high_mean": 0.0009518274719084729,
      "clip_ratio/low_mean": 0.003909374128852505,
      "clip_ratio/low_min": 9.167911139229545e-05,
      "clip_ratio/region_mean": 0.004861201552557759,
      "epoch": 0.14923962690093276,
      "grad_norm": 5.038246154785156,
      "learning_rate": 2e-07,
      "loss": 0.0701,
      "step": 1599
    },
    {
      "clip_ratio/high_max": 0.004392796420688683,
      "clip_ratio/high_mean": 0.0010297591570633813,
      "clip_ratio/low_mean": 0.004019362997496501,
      "clip_ratio/low_min": 8.042318040679675e-05,
      "clip_ratio/region_mean": 0.005049122250056826,
      "epoch": 0.14933296000093332,
      "grad_norm": 3.5350348949432373,
      "learning_rate": 2e-07,
      "loss": 0.1024,
      "step": 1600
    },
    {
      "epoch": 0.14933296000093332,
      "step": 1600,
      "total_flos": 0.0,
      "train_loss": 69.64168917144616,
      "train_runtime": 28121.2965,
      "train_samples_per_second": 50.979,
      "train_steps_per_second": 0.057
    }
  ],
  "logging_steps": 1,
  "max_steps": 1600,
  "num_input_tokens_seen": 1136645105,
  "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
}