{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.197845249755142,
  "eval_steps": 76,
  "global_step": 303,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000652954619653934,
      "grad_norm": 4.757781028747559,
      "learning_rate": 4.000000000000001e-06,
      "loss": 4.2047,
      "step": 1
    },
    {
      "epoch": 0.000652954619653934,
      "eval_loss": NaN,
      "eval_runtime": 704.7675,
      "eval_samples_per_second": 3.661,
      "eval_steps_per_second": 0.915,
      "step": 1
    },
    {
      "epoch": 0.001305909239307868,
      "grad_norm": 4.874630928039551,
      "learning_rate": 8.000000000000001e-06,
      "loss": 4.1653,
      "step": 2
    },
    {
      "epoch": 0.0019588638589618022,
      "grad_norm": 5.5883331298828125,
      "learning_rate": 1.2e-05,
      "loss": 4.1635,
      "step": 3
    },
    {
      "epoch": 0.002611818478615736,
      "grad_norm": 5.3879313468933105,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 3.8569,
      "step": 4
    },
    {
      "epoch": 0.00326477309826967,
      "grad_norm": 4.848824501037598,
      "learning_rate": 2e-05,
      "loss": 4.0147,
      "step": 5
    },
    {
      "epoch": 0.0039177277179236044,
      "grad_norm": 5.3052978515625,
      "learning_rate": 2.4e-05,
      "loss": 3.7956,
      "step": 6
    },
    {
      "epoch": 0.004570682337577538,
      "grad_norm": 6.782866954803467,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 4.6771,
      "step": 7
    },
    {
      "epoch": 0.005223636957231472,
      "grad_norm": 6.1247735023498535,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 3.8201,
      "step": 8
    },
    {
      "epoch": 0.005876591576885406,
      "grad_norm": 5.305412769317627,
      "learning_rate": 3.6e-05,
      "loss": 3.2011,
      "step": 9
    },
    {
      "epoch": 0.00652954619653934,
      "grad_norm": 4.974228858947754,
      "learning_rate": 4e-05,
      "loss": 3.2488,
      "step": 10
    },
    {
      "epoch": 0.007182500816193275,
      "grad_norm": 4.17997407913208,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.8667,
      "step": 11
    },
    {
      "epoch": 0.007835455435847209,
      "grad_norm": 5.494494915008545,
      "learning_rate": 4.8e-05,
      "loss": 3.0199,
      "step": 12
    },
    {
      "epoch": 0.008488410055501142,
      "grad_norm": 3.663966178894043,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 2.5652,
      "step": 13
    },
    {
      "epoch": 0.009141364675155077,
      "grad_norm": 3.196805477142334,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 2.6467,
      "step": 14
    },
    {
      "epoch": 0.009794319294809012,
      "grad_norm": 3.161735773086548,
      "learning_rate": 6e-05,
      "loss": 2.4477,
      "step": 15
    },
    {
      "epoch": 0.010447273914462945,
      "grad_norm": 4.473456859588623,
      "learning_rate": 6.400000000000001e-05,
      "loss": 2.4943,
      "step": 16
    },
    {
      "epoch": 0.01110022853411688,
      "grad_norm": 5.138904094696045,
      "learning_rate": 6.800000000000001e-05,
      "loss": 2.51,
      "step": 17
    },
    {
      "epoch": 0.011753183153770812,
      "grad_norm": 5.232083320617676,
      "learning_rate": 7.2e-05,
      "loss": 2.3384,
      "step": 18
    },
    {
      "epoch": 0.012406137773424747,
      "grad_norm": 5.67042875289917,
      "learning_rate": 7.6e-05,
      "loss": 2.3158,
      "step": 19
    },
    {
      "epoch": 0.01305909239307868,
      "grad_norm": 6.414549350738525,
      "learning_rate": 8e-05,
      "loss": 2.2479,
      "step": 20
    },
    {
      "epoch": 0.013712047012732615,
      "grad_norm": 6.064276218414307,
      "learning_rate": 8.4e-05,
      "loss": 2.689,
      "step": 21
    },
    {
      "epoch": 0.01436500163238655,
      "grad_norm": 4.989445686340332,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.9927,
      "step": 22
    },
    {
      "epoch": 0.015017956252040483,
      "grad_norm": 6.970681667327881,
      "learning_rate": 9.200000000000001e-05,
      "loss": 2.0652,
      "step": 23
    },
    {
      "epoch": 0.015670910871694418,
      "grad_norm": 5.712936878204346,
      "learning_rate": 9.6e-05,
      "loss": 1.7749,
      "step": 24
    },
    {
      "epoch": 0.01632386549134835,
      "grad_norm": 6.509803771972656,
      "learning_rate": 0.0001,
      "loss": 1.6381,
      "step": 25
    },
    {
      "epoch": 0.016976820111002284,
      "grad_norm": 9.46315860748291,
      "learning_rate": 0.00010400000000000001,
      "loss": 2.9097,
      "step": 26
    },
    {
      "epoch": 0.01762977473065622,
      "grad_norm": 7.60649299621582,
      "learning_rate": 0.00010800000000000001,
      "loss": 2.3185,
      "step": 27
    },
    {
      "epoch": 0.018282729350310153,
      "grad_norm": 4.304985046386719,
      "learning_rate": 0.00011200000000000001,
      "loss": 1.8866,
      "step": 28
    },
    {
      "epoch": 0.018935683969964087,
      "grad_norm": 4.42153787612915,
      "learning_rate": 0.000116,
      "loss": 1.9317,
      "step": 29
    },
    {
      "epoch": 0.019588638589618023,
      "grad_norm": 4.993203163146973,
      "learning_rate": 0.00012,
      "loss": 1.963,
      "step": 30
    },
    {
      "epoch": 0.020241593209271956,
      "grad_norm": 5.630634784698486,
      "learning_rate": 0.000124,
      "loss": 2.0134,
      "step": 31
    },
    {
      "epoch": 0.02089454782892589,
      "grad_norm": 4.011257648468018,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.5838,
      "step": 32
    },
    {
      "epoch": 0.021547502448579822,
      "grad_norm": 4.430102348327637,
      "learning_rate": 0.000132,
      "loss": 1.567,
      "step": 33
    },
    {
      "epoch": 0.02220045706823376,
      "grad_norm": 4.285562038421631,
      "learning_rate": 0.00013600000000000003,
      "loss": 1.5668,
      "step": 34
    },
    {
      "epoch": 0.022853411687887692,
      "grad_norm": 4.76671028137207,
      "learning_rate": 0.00014,
      "loss": 1.4504,
      "step": 35
    },
    {
      "epoch": 0.023506366307541625,
      "grad_norm": 3.6335926055908203,
      "learning_rate": 0.000144,
      "loss": 1.7653,
      "step": 36
    },
    {
      "epoch": 0.02415932092719556,
      "grad_norm": 3.863640546798706,
      "learning_rate": 0.000148,
      "loss": 1.7619,
      "step": 37
    },
    {
      "epoch": 0.024812275546849494,
      "grad_norm": 3.339837074279785,
      "learning_rate": 0.000152,
      "loss": 1.9767,
      "step": 38
    },
    {
      "epoch": 0.025465230166503428,
      "grad_norm": 3.004544734954834,
      "learning_rate": 0.00015600000000000002,
      "loss": 1.954,
      "step": 39
    },
    {
      "epoch": 0.02611818478615736,
      "grad_norm": 3.1160991191864014,
      "learning_rate": 0.00016,
      "loss": 2.2944,
      "step": 40
    },
    {
      "epoch": 0.026771139405811297,
      "grad_norm": 2.9257686138153076,
      "learning_rate": 0.000164,
      "loss": 2.1756,
      "step": 41
    },
    {
      "epoch": 0.02742409402546523,
      "grad_norm": 3.0116686820983887,
      "learning_rate": 0.000168,
      "loss": 2.2031,
      "step": 42
    },
    {
      "epoch": 0.028077048645119163,
      "grad_norm": 3.1789779663085938,
      "learning_rate": 0.000172,
      "loss": 1.71,
      "step": 43
    },
    {
      "epoch": 0.0287300032647731,
      "grad_norm": 3.2652573585510254,
      "learning_rate": 0.00017600000000000002,
      "loss": 2.108,
      "step": 44
    },
    {
      "epoch": 0.029382957884427033,
      "grad_norm": 3.3591766357421875,
      "learning_rate": 0.00018,
      "loss": 2.252,
      "step": 45
    },
    {
      "epoch": 0.030035912504080966,
      "grad_norm": 4.020256519317627,
      "learning_rate": 0.00018400000000000003,
      "loss": 2.0209,
      "step": 46
    },
    {
      "epoch": 0.0306888671237349,
      "grad_norm": 3.1844100952148438,
      "learning_rate": 0.000188,
      "loss": 1.7205,
      "step": 47
    },
    {
      "epoch": 0.031341821743388835,
      "grad_norm": 4.041150093078613,
      "learning_rate": 0.000192,
      "loss": 2.0322,
      "step": 48
    },
    {
      "epoch": 0.031994776363042765,
      "grad_norm": 3.976959228515625,
      "learning_rate": 0.000196,
      "loss": 1.5729,
      "step": 49
    },
    {
      "epoch": 0.0326477309826967,
      "grad_norm": 3.8643813133239746,
      "learning_rate": 0.0002,
      "loss": 1.3921,
      "step": 50
    },
    {
      "epoch": 0.03330068560235064,
      "grad_norm": 4.523630142211914,
      "learning_rate": 0.0001999922905547776,
      "loss": 2.0141,
      "step": 51
    },
    {
      "epoch": 0.03395364022200457,
      "grad_norm": 3.308136463165283,
      "learning_rate": 0.0001999691634078213,
      "loss": 1.6375,
      "step": 52
    },
    {
      "epoch": 0.034606594841658504,
      "grad_norm": 3.70528244972229,
      "learning_rate": 0.00019993062212508053,
      "loss": 2.1218,
      "step": 53
    },
    {
      "epoch": 0.03525954946131244,
      "grad_norm": 3.909076690673828,
      "learning_rate": 0.0001998766726491935,
      "loss": 1.7935,
      "step": 54
    },
    {
      "epoch": 0.03591250408096637,
      "grad_norm": 3.2719497680664062,
      "learning_rate": 0.00019980732329857076,
      "loss": 1.4998,
      "step": 55
    },
    {
      "epoch": 0.03656545870062031,
      "grad_norm": 4.357359886169434,
      "learning_rate": 0.0001997225847661127,
      "loss": 1.7119,
      "step": 56
    },
    {
      "epoch": 0.03721841332027424,
      "grad_norm": 3.111414909362793,
      "learning_rate": 0.00019962247011756081,
      "loss": 1.3332,
      "step": 57
    },
    {
      "epoch": 0.03787136793992817,
      "grad_norm": 3.3698601722717285,
      "learning_rate": 0.00019950699478948309,
      "loss": 1.3576,
      "step": 58
    },
    {
      "epoch": 0.03852432255958211,
      "grad_norm": 4.0696024894714355,
      "learning_rate": 0.00019937617658689384,
      "loss": 1.2196,
      "step": 59
    },
    {
      "epoch": 0.039177277179236046,
      "grad_norm": 3.984119176864624,
      "learning_rate": 0.00019923003568050844,
      "loss": 1.4652,
      "step": 60
    },
    {
      "epoch": 0.039830231798889976,
      "grad_norm": 3.909024238586426,
      "learning_rate": 0.00019906859460363307,
      "loss": 1.2951,
      "step": 61
    },
    {
      "epoch": 0.04048318641854391,
      "grad_norm": 3.550440788269043,
      "learning_rate": 0.0001988918782486906,
      "loss": 1.4699,
      "step": 62
    },
    {
      "epoch": 0.04113614103819784,
      "grad_norm": 3.341071367263794,
      "learning_rate": 0.0001986999138633821,
      "loss": 2.1781,
      "step": 63
    },
    {
      "epoch": 0.04178909565785178,
      "grad_norm": 2.938025951385498,
      "learning_rate": 0.00019849273104648592,
      "loss": 1.7088,
      "step": 64
    },
    {
      "epoch": 0.042442050277505715,
      "grad_norm": 2.956080913543701,
      "learning_rate": 0.00019827036174329353,
      "loss": 2.0676,
      "step": 65
    },
    {
      "epoch": 0.043095004897159644,
      "grad_norm": 2.349592924118042,
      "learning_rate": 0.00019803284024068427,
      "loss": 1.7783,
      "step": 66
    },
    {
      "epoch": 0.04374795951681358,
      "grad_norm": 2.7854583263397217,
      "learning_rate": 0.0001977802031618383,
      "loss": 2.222,
      "step": 67
    },
    {
      "epoch": 0.04440091413646752,
      "grad_norm": 3.6111695766448975,
      "learning_rate": 0.00019751248946059014,
      "loss": 2.0701,
      "step": 68
    },
    {
      "epoch": 0.04505386875612145,
      "grad_norm": 3.226724863052368,
      "learning_rate": 0.00019722974041542203,
      "loss": 2.2502,
      "step": 69
    },
    {
      "epoch": 0.045706823375775384,
      "grad_norm": 3.4755945205688477,
      "learning_rate": 0.0001969319996230995,
      "loss": 2.0837,
      "step": 70
    },
    {
      "epoch": 0.04635977799542932,
      "grad_norm": 3.1673951148986816,
      "learning_rate": 0.0001966193129919491,
      "loss": 1.8692,
      "step": 71
    },
    {
      "epoch": 0.04701273261508325,
      "grad_norm": 3.5966238975524902,
      "learning_rate": 0.00019629172873477995,
      "loss": 2.0036,
      "step": 72
    },
    {
      "epoch": 0.047665687234737186,
      "grad_norm": 4.344339370727539,
      "learning_rate": 0.00019594929736144976,
      "loss": 1.963,
      "step": 73
    },
    {
      "epoch": 0.04831864185439112,
      "grad_norm": 3.6855549812316895,
      "learning_rate": 0.00019559207167107684,
      "loss": 1.5932,
      "step": 74
    },
    {
      "epoch": 0.04897159647404505,
      "grad_norm": 3.7931909561157227,
      "learning_rate": 0.000195220106743899,
      "loss": 1.272,
      "step": 75
    },
    {
      "epoch": 0.04962455109369899,
      "grad_norm": 3.422001361846924,
      "learning_rate": 0.00019483345993278093,
      "loss": 1.8281,
      "step": 76
    },
    {
      "epoch": 0.04962455109369899,
      "eval_loss": NaN,
      "eval_runtime": 704.1079,
      "eval_samples_per_second": 3.664,
      "eval_steps_per_second": 0.916,
      "step": 76
    },
    {
      "epoch": 0.05027750571335292,
      "grad_norm": 3.9176759719848633,
      "learning_rate": 0.0001944321908543708,
      "loss": 1.9556,
      "step": 77
    },
    {
      "epoch": 0.050930460333006855,
      "grad_norm": 3.578507423400879,
      "learning_rate": 0.00019401636137990816,
      "loss": 2.025,
      "step": 78
    },
    {
      "epoch": 0.05158341495266079,
      "grad_norm": 3.641873598098755,
      "learning_rate": 0.00019358603562568416,
      "loss": 1.667,
      "step": 79
    },
    {
      "epoch": 0.05223636957231472,
      "grad_norm": 4.218084335327148,
      "learning_rate": 0.0001931412799431554,
      "loss": 1.797,
      "step": 80
    },
    {
      "epoch": 0.05288932419196866,
      "grad_norm": 3.496741533279419,
      "learning_rate": 0.0001926821629087133,
      "loss": 1.5076,
      "step": 81
    },
    {
      "epoch": 0.053542278811622594,
      "grad_norm": 5.606319427490234,
      "learning_rate": 0.00019220875531311045,
      "loss": 1.5796,
      "step": 82
    },
    {
      "epoch": 0.054195233431276524,
      "grad_norm": 3.143007516860962,
      "learning_rate": 0.00019172113015054532,
      "loss": 1.4222,
      "step": 83
    },
    {
      "epoch": 0.05484818805093046,
      "grad_norm": 3.359457015991211,
      "learning_rate": 0.00019121936260740752,
      "loss": 0.9389,
      "step": 84
    },
    {
      "epoch": 0.0555011426705844,
      "grad_norm": 3.911376476287842,
      "learning_rate": 0.00019070353005068484,
      "loss": 1.8963,
      "step": 85
    },
    {
      "epoch": 0.056154097290238326,
      "grad_norm": 3.542954444885254,
      "learning_rate": 0.00019017371201603407,
      "loss": 1.4677,
      "step": 86
    },
    {
      "epoch": 0.05680705190989226,
      "grad_norm": 3.1694722175598145,
      "learning_rate": 0.00018962999019551754,
      "loss": 1.4803,
      "step": 87
    },
    {
      "epoch": 0.0574600065295462,
      "grad_norm": 2.960282564163208,
      "learning_rate": 0.00018907244842500704,
      "loss": 1.8923,
      "step": 88
    },
    {
      "epoch": 0.05811296114920013,
      "grad_norm": 2.6101479530334473,
      "learning_rate": 0.00018850117267125738,
      "loss": 1.9243,
      "step": 89
    },
    {
      "epoch": 0.058765915768854066,
      "grad_norm": 3.0619993209838867,
      "learning_rate": 0.00018791625101865117,
      "loss": 2.1384,
      "step": 90
    },
    {
      "epoch": 0.059418870388507995,
      "grad_norm": 2.6776371002197266,
      "learning_rate": 0.0001873177736556172,
      "loss": 1.7285,
      "step": 91
    },
    {
      "epoch": 0.06007182500816193,
      "grad_norm": 3.687798023223877,
      "learning_rate": 0.00018670583286072443,
      "loss": 1.8332,
      "step": 92
    },
    {
      "epoch": 0.06072477962781587,
      "grad_norm": 2.632847547531128,
      "learning_rate": 0.0001860805229884536,
      "loss": 1.8342,
      "step": 93
    },
    {
      "epoch": 0.0613777342474698,
      "grad_norm": 3.5173568725585938,
      "learning_rate": 0.00018544194045464886,
      "loss": 2.004,
      "step": 94
    },
    {
      "epoch": 0.062030688867123734,
      "grad_norm": 3.2944045066833496,
      "learning_rate": 0.0001847901837216515,
      "loss": 1.8861,
      "step": 95
    },
    {
      "epoch": 0.06268364348677767,
      "grad_norm": 3.5300235748291016,
      "learning_rate": 0.00018412535328311814,
      "loss": 1.7608,
      "step": 96
    },
    {
      "epoch": 0.06333659810643161,
      "grad_norm": 3.253826856613159,
      "learning_rate": 0.0001834475516485257,
      "loss": 1.9151,
      "step": 97
    },
    {
      "epoch": 0.06398955272608553,
      "grad_norm": 3.243023633956909,
      "learning_rate": 0.00018275688332736577,
      "loss": 1.5671,
      "step": 98
    },
    {
      "epoch": 0.06464250734573947,
      "grad_norm": 3.3818089962005615,
      "learning_rate": 0.00018205345481302998,
      "loss": 1.4077,
      "step": 99
    },
    {
      "epoch": 0.0652954619653934,
      "grad_norm": 3.632511615753174,
      "learning_rate": 0.00018133737456639044,
      "loss": 1.0454,
      "step": 100
    },
    {
      "epoch": 0.06594841658504734,
      "grad_norm": 3.6621978282928467,
      "learning_rate": 0.0001806087529990758,
      "loss": 2.0844,
      "step": 101
    },
    {
      "epoch": 0.06660137120470128,
      "grad_norm": 5.99480676651001,
      "learning_rate": 0.0001798677024564473,
      "loss": 1.8015,
      "step": 102
    },
    {
      "epoch": 0.06725432582435521,
      "grad_norm": 3.063887357711792,
      "learning_rate": 0.00017911433720027624,
      "loss": 1.7182,
      "step": 103
    },
    {
      "epoch": 0.06790728044400914,
      "grad_norm": 3.2303333282470703,
      "learning_rate": 0.00017834877339112612,
      "loss": 1.6701,
      "step": 104
    },
    {
      "epoch": 0.06856023506366307,
      "grad_norm": 7.370791435241699,
      "learning_rate": 0.000177571129070442,
      "loss": 1.6819,
      "step": 105
    },
    {
      "epoch": 0.06921318968331701,
      "grad_norm": 3.4059948921203613,
      "learning_rate": 0.00017678152414234968,
      "loss": 1.3683,
      "step": 106
    },
    {
      "epoch": 0.06986614430297095,
      "grad_norm": 4.130568504333496,
      "learning_rate": 0.000175980080355168,
      "loss": 1.6074,
      "step": 107
    },
    {
      "epoch": 0.07051909892262488,
      "grad_norm": 4.288647651672363,
      "learning_rate": 0.00017516692128263648,
      "loss": 1.2521,
      "step": 108
    },
    {
      "epoch": 0.07117205354227882,
      "grad_norm": 3.245211362838745,
      "learning_rate": 0.00017434217230486164,
      "loss": 1.3333,
      "step": 109
    },
    {
      "epoch": 0.07182500816193274,
      "grad_norm": 3.7068018913269043,
      "learning_rate": 0.00017350596058898483,
      "loss": 1.287,
      "step": 110
    },
    {
      "epoch": 0.07247796278158668,
      "grad_norm": 3.418928623199463,
      "learning_rate": 0.0001726584150695744,
      "loss": 1.3896,
      "step": 111
    },
    {
      "epoch": 0.07313091740124061,
      "grad_norm": 3.3947291374206543,
      "learning_rate": 0.00017179966642874543,
      "loss": 1.7948,
      "step": 112
    },
    {
      "epoch": 0.07378387202089455,
      "grad_norm": 2.770167589187622,
      "learning_rate": 0.0001709298470760101,
      "loss": 1.8008,
      "step": 113
    },
    {
      "epoch": 0.07443682664054849,
      "grad_norm": 2.841723918914795,
      "learning_rate": 0.00017004909112786144,
      "loss": 1.7773,
      "step": 114
    },
    {
      "epoch": 0.07508978126020241,
      "grad_norm": 3.010446071624756,
      "learning_rate": 0.00016915753438709417,
      "loss": 1.9485,
      "step": 115
    },
    {
      "epoch": 0.07574273587985635,
      "grad_norm": 2.804893970489502,
      "learning_rate": 0.00016825531432186543,
      "loss": 1.8283,
      "step": 116
    },
    {
      "epoch": 0.07639569049951028,
      "grad_norm": 2.607825517654419,
      "learning_rate": 0.00016734257004449862,
      "loss": 1.5881,
      "step": 117
    },
    {
      "epoch": 0.07704864511916422,
      "grad_norm": 3.1926357746124268,
      "learning_rate": 0.00016641944229003395,
      "loss": 1.9909,
      "step": 118
    },
    {
      "epoch": 0.07770159973881816,
      "grad_norm": 2.6762239933013916,
      "learning_rate": 0.00016548607339452853,
      "loss": 1.7493,
      "step": 119
    },
    {
      "epoch": 0.07835455435847209,
      "grad_norm": 2.9282002449035645,
      "learning_rate": 0.00016454260727310978,
      "loss": 1.6987,
      "step": 120
    },
    {
      "epoch": 0.07900750897812601,
      "grad_norm": 3.6605136394500732,
      "learning_rate": 0.00016358918939778536,
      "loss": 2.1916,
      "step": 121
    },
    {
      "epoch": 0.07966046359777995,
      "grad_norm": 3.031012535095215,
      "learning_rate": 0.00016262596677501297,
      "loss": 1.9056,
      "step": 122
    },
    {
      "epoch": 0.08031341821743389,
      "grad_norm": 3.2578601837158203,
      "learning_rate": 0.0001616530879230335,
      "loss": 1.5707,
      "step": 123
    },
    {
      "epoch": 0.08096637283708782,
      "grad_norm": 3.2448766231536865,
      "learning_rate": 0.00016067070284897137,
      "loss": 1.43,
      "step": 124
    },
    {
      "epoch": 0.08161932745674176,
      "grad_norm": 3.2631771564483643,
      "learning_rate": 0.00015967896302570485,
      "loss": 1.0851,
      "step": 125
    },
    {
      "epoch": 0.08227228207639568,
      "grad_norm": 3.316664457321167,
      "learning_rate": 0.0001586780213685108,
      "loss": 1.9519,
      "step": 126
    },
    {
      "epoch": 0.08292523669604962,
      "grad_norm": 2.7955403327941895,
      "learning_rate": 0.00015766803221148673,
      "loss": 1.6003,
      "step": 127
    },
    {
      "epoch": 0.08357819131570356,
      "grad_norm": 3.2884178161621094,
      "learning_rate": 0.0001566491512837543,
      "loss": 1.7108,
      "step": 128
    },
    {
      "epoch": 0.0842311459353575,
      "grad_norm": 3.472278356552124,
      "learning_rate": 0.00015562153568544752,
      "loss": 1.8399,
      "step": 129
    },
    {
      "epoch": 0.08488410055501143,
      "grad_norm": 2.900644302368164,
      "learning_rate": 0.00015458534386348966,
      "loss": 1.6259,
      "step": 130
    },
    {
      "epoch": 0.08553705517466537,
      "grad_norm": 3.018883228302002,
      "learning_rate": 0.0001535407355871626,
      "loss": 1.5246,
      "step": 131
    },
    {
      "epoch": 0.08619000979431929,
      "grad_norm": 3.375364303588867,
      "learning_rate": 0.00015248787192347196,
      "loss": 1.6209,
      "step": 132
    },
    {
      "epoch": 0.08684296441397323,
      "grad_norm": 2.9012420177459717,
      "learning_rate": 0.00015142691521231267,
      "loss": 1.2602,
      "step": 133
    },
    {
      "epoch": 0.08749591903362716,
      "grad_norm": 4.421230316162109,
      "learning_rate": 0.00015035802904143762,
      "loss": 1.5445,
      "step": 134
    },
    {
      "epoch": 0.0881488736532811,
      "grad_norm": 3.3842790126800537,
      "learning_rate": 0.00014928137822123452,
      "loss": 1.2163,
      "step": 135
    },
    {
      "epoch": 0.08880182827293504,
      "grad_norm": 3.1379024982452393,
      "learning_rate": 0.0001481971287593138,
      "loss": 1.6229,
      "step": 136
    },
    {
      "epoch": 0.08945478289258897,
      "grad_norm": 3.0401148796081543,
      "learning_rate": 0.00014710544783491208,
      "loss": 2.1325,
      "step": 137
    },
    {
      "epoch": 0.0901077375122429,
      "grad_norm": 3.1100378036499023,
      "learning_rate": 0.00014600650377311522,
      "loss": 1.8436,
      "step": 138
    },
    {
      "epoch": 0.09076069213189683,
      "grad_norm": 2.646742105484009,
      "learning_rate": 0.00014490046601890405,
      "loss": 2.0225,
      "step": 139
    },
    {
      "epoch": 0.09141364675155077,
      "grad_norm": 2.7213666439056396,
      "learning_rate": 0.00014378750511102826,
      "loss": 1.9278,
      "step": 140
    },
    {
      "epoch": 0.0920666013712047,
      "grad_norm": 2.6186165809631348,
      "learning_rate": 0.00014266779265571087,
      "loss": 2.1003,
      "step": 141
    },
    {
      "epoch": 0.09271955599085864,
      "grad_norm": 2.469266653060913,
      "learning_rate": 0.00014154150130018866,
      "loss": 2.1259,
      "step": 142
    },
    {
      "epoch": 0.09337251061051256,
      "grad_norm": 2.95566725730896,
      "learning_rate": 0.00014040880470609187,
      "loss": 2.0982,
      "step": 143
    },
    {
      "epoch": 0.0940254652301665,
      "grad_norm": 3.408046007156372,
      "learning_rate": 0.00013926987752266735,
      "loss": 2.1553,
      "step": 144
    },
    {
      "epoch": 0.09467841984982044,
      "grad_norm": 2.5797595977783203,
      "learning_rate": 0.00013812489535984981,
      "loss": 1.9652,
      "step": 145
    },
    {
      "epoch": 0.09533137446947437,
      "grad_norm": 3.9302403926849365,
      "learning_rate": 0.00013697403476118454,
      "loss": 1.916,
      "step": 146
    },
    {
      "epoch": 0.09598432908912831,
      "grad_norm": 3.0103251934051514,
      "learning_rate": 0.0001358174731766064,
      "loss": 1.5778,
      "step": 147
    },
    {
      "epoch": 0.09663728370878225,
      "grad_norm": 3.0252418518066406,
      "learning_rate": 0.00013465538893507907,
      "loss": 1.862,
      "step": 148
    },
    {
      "epoch": 0.09729023832843617,
      "grad_norm": 3.1504366397857666,
      "learning_rate": 0.00013348796121709862,
      "loss": 1.7159,
      "step": 149
    },
    {
      "epoch": 0.0979431929480901,
      "grad_norm": 2.718940019607544,
      "learning_rate": 0.00013231537002706594,
      "loss": 1.1477,
      "step": 150
    },
    {
      "epoch": 0.09859614756774404,
      "grad_norm": 3.6509456634521484,
      "learning_rate": 0.0001311377961655319,
      "loss": 1.6706,
      "step": 151
    },
    {
      "epoch": 0.09924910218739798,
      "grad_norm": 3.2815134525299072,
      "learning_rate": 0.00012995542120132017,
      "loss": 1.4804,
      "step": 152
    },
    {
      "epoch": 0.09924910218739798,
      "eval_loss": NaN,
      "eval_runtime": 699.3675,
      "eval_samples_per_second": 3.689,
      "eval_steps_per_second": 0.922,
      "step": 152
    },
    {
      "epoch": 0.09990205680705191,
      "grad_norm": 2.6223411560058594,
      "learning_rate": 0.00012876842744353112,
      "loss": 1.4696,
      "step": 153
    },
    {
      "epoch": 0.10055501142670584,
      "grad_norm": 3.07543683052063,
      "learning_rate": 0.00012757699791343186,
      "loss": 1.4233,
      "step": 154
    },
    {
      "epoch": 0.10120796604635977,
      "grad_norm": 3.1689348220825195,
      "learning_rate": 0.0001263813163162364,
      "loss": 1.6883,
      "step": 155
    },
    {
      "epoch": 0.10186092066601371,
      "grad_norm": 3.1390719413757324,
      "learning_rate": 0.00012518156701278019,
      "loss": 1.9252,
      "step": 156
    },
    {
      "epoch": 0.10251387528566765,
      "grad_norm": 2.6922318935394287,
      "learning_rate": 0.00012397793499109404,
      "loss": 1.4566,
      "step": 157
    },
    {
      "epoch": 0.10316682990532158,
      "grad_norm": 2.970062255859375,
      "learning_rate": 0.00012277060583788064,
      "loss": 1.4658,
      "step": 158
    },
    {
      "epoch": 0.10381978452497552,
      "grad_norm": 3.3430395126342773,
      "learning_rate": 0.00012155976570989949,
      "loss": 1.1341,
      "step": 159
    },
    {
      "epoch": 0.10447273914462944,
      "grad_norm": 3.108964204788208,
      "learning_rate": 0.0001203456013052634,
      "loss": 1.4,
      "step": 160
    },
    {
      "epoch": 0.10512569376428338,
      "grad_norm": 2.5076346397399902,
      "learning_rate": 0.00011912829983465168,
      "loss": 1.2977,
      "step": 161
    },
    {
      "epoch": 0.10577864838393732,
      "grad_norm": 2.782015085220337,
      "learning_rate": 0.00011790804899244452,
      "loss": 1.5569,
      "step": 162
    },
    {
      "epoch": 0.10643160300359125,
      "grad_norm": 2.4178273677825928,
      "learning_rate": 0.00011668503692778239,
      "loss": 1.588,
      "step": 163
    },
    {
      "epoch": 0.10708455762324519,
      "grad_norm": 2.7303292751312256,
      "learning_rate": 0.0001154594522155557,
      "loss": 1.9145,
      "step": 164
    },
    {
      "epoch": 0.10773751224289912,
      "grad_norm": 2.631848096847534,
      "learning_rate": 0.00011423148382732853,
      "loss": 1.9198,
      "step": 165
    },
    {
      "epoch": 0.10839046686255305,
      "grad_norm": 2.4288294315338135,
      "learning_rate": 0.00011300132110220134,
      "loss": 1.9154,
      "step": 166
    },
    {
      "epoch": 0.10904342148220698,
      "grad_norm": 2.742737293243408,
      "learning_rate": 0.00011176915371761702,
      "loss": 1.8217,
      "step": 167
    },
    {
      "epoch": 0.10969637610186092,
      "grad_norm": 2.437319278717041,
      "learning_rate": 0.00011053517166011471,
      "loss": 1.7938,
      "step": 168
    },
    {
      "epoch": 0.11034933072151486,
      "grad_norm": 2.4741907119750977,
      "learning_rate": 0.00010929956519603594,
      "loss": 1.7694,
      "step": 169
    },
    {
      "epoch": 0.1110022853411688,
      "grad_norm": 3.3339791297912598,
      "learning_rate": 0.0001080625248421878,
      "loss": 1.9348,
      "step": 170
    },
    {
      "epoch": 0.11165523996082272,
      "grad_norm": 3.3256616592407227,
      "learning_rate": 0.0001068242413364671,
      "loss": 1.8868,
      "step": 171
    },
    {
      "epoch": 0.11230819458047665,
      "grad_norm": 2.873408317565918,
      "learning_rate": 0.00010558490560845107,
      "loss": 1.7327,
      "step": 172
    },
    {
      "epoch": 0.11296114920013059,
      "grad_norm": 2.9288012981414795,
      "learning_rate": 0.00010434470874995781,
      "loss": 1.9178,
      "step": 173
    },
    {
      "epoch": 0.11361410381978453,
      "grad_norm": 3.4907095432281494,
      "learning_rate": 0.00010310384198558225,
      "loss": 1.5658,
      "step": 174
    },
    {
      "epoch": 0.11426705843943846,
      "grad_norm": 2.5337088108062744,
      "learning_rate": 0.00010186249664321139,
      "loss": 0.9634,
      "step": 175
    },
    {
      "epoch": 0.1149200130590924,
      "grad_norm": 3.862973690032959,
      "learning_rate": 0.00010062086412452352,
      "loss": 1.7911,
      "step": 176
    },
    {
      "epoch": 0.11557296767874632,
      "grad_norm": 3.585923194885254,
      "learning_rate": 9.93791358754765e-05,
      "loss": 1.9018,
      "step": 177
    },
    {
      "epoch": 0.11622592229840026,
      "grad_norm": 2.8271729946136475,
      "learning_rate": 9.813750335678866e-05,
      "loss": 1.5603,
      "step": 178
    },
    {
      "epoch": 0.1168788769180542,
      "grad_norm": 2.844407796859741,
      "learning_rate": 9.689615801441774e-05,
      "loss": 1.4833,
      "step": 179
    },
    {
      "epoch": 0.11753183153770813,
      "grad_norm": 3.0475728511810303,
      "learning_rate": 9.56552912500422e-05,
      "loss": 1.4969,
      "step": 180
    },
    {
      "epoch": 0.11818478615736207,
      "grad_norm": 3.360382318496704,
      "learning_rate": 9.441509439154895e-05,
      "loss": 1.7167,
      "step": 181
    },
    {
      "epoch": 0.11883774077701599,
      "grad_norm": 2.9843080043792725,
      "learning_rate": 9.317575866353292e-05,
      "loss": 1.4516,
      "step": 182
    },
    {
      "epoch": 0.11949069539666993,
      "grad_norm": 3.0425808429718018,
      "learning_rate": 9.193747515781224e-05,
      "loss": 1.2171,
      "step": 183
    },
    {
      "epoch": 0.12014365001632386,
      "grad_norm": 3.03841495513916,
      "learning_rate": 9.070043480396404e-05,
      "loss": 1.2647,
      "step": 184
    },
    {
      "epoch": 0.1207966046359778,
      "grad_norm": 2.7172021865844727,
      "learning_rate": 8.94648283398853e-05,
      "loss": 1.0993,
      "step": 185
    },
    {
      "epoch": 0.12144955925563174,
      "grad_norm": 3.215526580810547,
      "learning_rate": 8.823084628238298e-05,
      "loss": 1.2345,
      "step": 186
    },
    {
      "epoch": 0.12210251387528567,
      "grad_norm": 2.8291847705841064,
      "learning_rate": 8.699867889779868e-05,
      "loss": 1.7698,
      "step": 187
    },
    {
      "epoch": 0.1227554684949396,
      "grad_norm": 2.8613245487213135,
      "learning_rate": 8.57685161726715e-05,
      "loss": 1.9141,
      "step": 188
    },
    {
      "epoch": 0.12340842311459353,
      "grad_norm": 2.358774185180664,
      "learning_rate": 8.454054778444431e-05,
      "loss": 1.7095,
      "step": 189
    },
    {
      "epoch": 0.12406137773424747,
      "grad_norm": 2.2548892498016357,
      "learning_rate": 8.331496307221762e-05,
      "loss": 1.7769,
      "step": 190
    },
    {
      "epoch": 0.1247143323539014,
      "grad_norm": 2.9085566997528076,
      "learning_rate": 8.209195100755551e-05,
      "loss": 1.9351,
      "step": 191
    },
    {
      "epoch": 0.12536728697355534,
      "grad_norm": 2.9980623722076416,
      "learning_rate": 8.087170016534835e-05,
      "loss": 2.0055,
      "step": 192
    },
    {
      "epoch": 0.12602024159320926,
      "grad_norm": 2.8316338062286377,
      "learning_rate": 7.965439869473664e-05,
      "loss": 1.8518,
      "step": 193
    },
    {
      "epoch": 0.12667319621286321,
      "grad_norm": 2.983452081680298,
      "learning_rate": 7.84402342901005e-05,
      "loss": 1.996,
      "step": 194
    },
    {
      "epoch": 0.12732615083251714,
      "grad_norm": 2.925206184387207,
      "learning_rate": 7.722939416211937e-05,
      "loss": 1.9398,
      "step": 195
    },
    {
      "epoch": 0.12797910545217106,
      "grad_norm": 2.671654462814331,
      "learning_rate": 7.6022065008906e-05,
      "loss": 1.7095,
      "step": 196
    },
    {
      "epoch": 0.128632060071825,
      "grad_norm": 3.020463705062866,
      "learning_rate": 7.481843298721982e-05,
      "loss": 1.82,
      "step": 197
    },
    {
      "epoch": 0.12928501469147893,
      "grad_norm": 2.837937593460083,
      "learning_rate": 7.361868368376364e-05,
      "loss": 1.5275,
      "step": 198
    },
    {
      "epoch": 0.12993796931113288,
      "grad_norm": 3.599421739578247,
      "learning_rate": 7.242300208656814e-05,
      "loss": 1.2762,
      "step": 199
    },
    {
      "epoch": 0.1305909239307868,
      "grad_norm": 3.3294129371643066,
      "learning_rate": 7.123157255646888e-05,
      "loss": 1.0834,
      "step": 200
    },
    {
      "epoch": 0.13124387855044076,
      "grad_norm": 3.3265252113342285,
      "learning_rate": 7.004457879867986e-05,
      "loss": 1.8808,
      "step": 201
    },
    {
      "epoch": 0.13189683317009468,
      "grad_norm": 3.3643386363983154,
      "learning_rate": 6.886220383446814e-05,
      "loss": 1.5511,
      "step": 202
    },
    {
      "epoch": 0.1325497877897486,
      "grad_norm": 2.6517298221588135,
      "learning_rate": 6.768462997293413e-05,
      "loss": 1.5762,
      "step": 203
    },
    {
      "epoch": 0.13320274240940255,
      "grad_norm": 3.111353874206543,
      "learning_rate": 6.651203878290139e-05,
      "loss": 1.4893,
      "step": 204
    },
    {
      "epoch": 0.13385569702905648,
      "grad_norm": 2.823064088821411,
      "learning_rate": 6.534461106492093e-05,
      "loss": 1.658,
      "step": 205
    },
    {
      "epoch": 0.13450865164871043,
      "grad_norm": 2.825458526611328,
      "learning_rate": 6.418252682339361e-05,
      "loss": 1.6023,
      "step": 206
    },
    {
      "epoch": 0.13516160626836435,
      "grad_norm": 2.8322906494140625,
      "learning_rate": 6.30259652388155e-05,
      "loss": 1.4659,
      "step": 207
    },
    {
      "epoch": 0.13581456088801827,
      "grad_norm": 2.5433881282806396,
      "learning_rate": 6.187510464015022e-05,
      "loss": 1.3384,
      "step": 208
    },
    {
      "epoch": 0.13646751550767222,
      "grad_norm": 3.240464925765991,
      "learning_rate": 6.0730122477332675e-05,
      "loss": 0.9005,
      "step": 209
    },
    {
      "epoch": 0.13712047012732614,
      "grad_norm": 3.5450103282928467,
      "learning_rate": 5.9591195293908174e-05,
      "loss": 1.3865,
      "step": 210
    },
    {
      "epoch": 0.1377734247469801,
      "grad_norm": 2.67393159866333,
      "learning_rate": 5.845849869981137e-05,
      "loss": 1.2309,
      "step": 211
    },
    {
      "epoch": 0.13842637936663402,
      "grad_norm": 3.3300986289978027,
      "learning_rate": 5.733220734428919e-05,
      "loss": 1.9498,
      "step": 212
    },
    {
      "epoch": 0.13907933398628794,
      "grad_norm": 2.3089957237243652,
      "learning_rate": 5.621249488897176e-05,
      "loss": 1.7914,
      "step": 213
    },
    {
      "epoch": 0.1397322886059419,
      "grad_norm": 2.3583531379699707,
      "learning_rate": 5.509953398109594e-05,
      "loss": 1.6828,
      "step": 214
    },
    {
      "epoch": 0.1403852432255958,
      "grad_norm": 2.0636346340179443,
      "learning_rate": 5.399349622688479e-05,
      "loss": 1.7596,
      "step": 215
    },
    {
      "epoch": 0.14103819784524976,
      "grad_norm": 2.3721492290496826,
      "learning_rate": 5.2894552165087916e-05,
      "loss": 1.8535,
      "step": 216
    },
    {
      "epoch": 0.14169115246490369,
      "grad_norm": 2.338106632232666,
      "learning_rate": 5.1802871240686234e-05,
      "loss": 1.8166,
      "step": 217
    },
    {
      "epoch": 0.14234410708455764,
      "grad_norm": 2.8886420726776123,
      "learning_rate": 5.0718621778765476e-05,
      "loss": 1.8643,
      "step": 218
    },
    {
      "epoch": 0.14299706170421156,
      "grad_norm": 2.71232533454895,
      "learning_rate": 4.9641970958562366e-05,
      "loss": 1.5456,
      "step": 219
    },
    {
      "epoch": 0.14365001632386548,
      "grad_norm": 3.262185573577881,
      "learning_rate": 4.8573084787687326e-05,
      "loss": 1.6296,
      "step": 220
    },
    {
      "epoch": 0.14430297094351943,
      "grad_norm": 2.6300837993621826,
      "learning_rate": 4.751212807652806e-05,
      "loss": 1.6135,
      "step": 221
    },
    {
      "epoch": 0.14495592556317335,
      "grad_norm": 3.008484363555908,
      "learning_rate": 4.6459264412837454e-05,
      "loss": 1.7263,
      "step": 222
    },
    {
      "epoch": 0.1456088801828273,
      "grad_norm": 2.9057788848876953,
      "learning_rate": 4.5414656136510334e-05,
      "loss": 1.2964,
      "step": 223
    },
    {
      "epoch": 0.14626183480248123,
      "grad_norm": 2.710711717605591,
      "learning_rate": 4.437846431455249e-05,
      "loss": 1.2502,
      "step": 224
    },
    {
      "epoch": 0.14691478942213515,
      "grad_norm": 2.6256871223449707,
      "learning_rate": 4.335084871624572e-05,
      "loss": 0.9017,
      "step": 225
    },
    {
      "epoch": 0.1475677440417891,
      "grad_norm": 3.905369997024536,
      "learning_rate": 4.2331967788513295e-05,
      "loss": 2.0128,
      "step": 226
    },
    {
      "epoch": 0.14822069866144302,
      "grad_norm": 3.0856714248657227,
      "learning_rate": 4.132197863148925e-05,
      "loss": 1.7455,
      "step": 227
    },
    {
      "epoch": 0.14887365328109697,
      "grad_norm": 3.04111385345459,
      "learning_rate": 4.0321036974295156e-05,
      "loss": 1.7097,
      "step": 228
    },
    {
      "epoch": 0.14887365328109697,
      "eval_loss": NaN,
      "eval_runtime": 702.6357,
      "eval_samples_per_second": 3.672,
      "eval_steps_per_second": 0.918,
      "step": 228
    },
    {
      "epoch": 0.1495266079007509,
      "grad_norm": 2.8979952335357666,
      "learning_rate": 3.932929715102863e-05,
      "loss": 1.4961,
      "step": 229
    },
    {
      "epoch": 0.15017956252040482,
      "grad_norm": 2.8216731548309326,
      "learning_rate": 3.834691207696649e-05,
      "loss": 1.5215,
      "step": 230
    },
    {
      "epoch": 0.15083251714005877,
      "grad_norm": 2.5655124187469482,
      "learning_rate": 3.7374033224987084e-05,
      "loss": 1.5517,
      "step": 231
    },
    {
      "epoch": 0.1514854717597127,
      "grad_norm": 2.572943687438965,
      "learning_rate": 3.6410810602214684e-05,
      "loss": 1.2292,
      "step": 232
    },
    {
      "epoch": 0.15213842637936664,
      "grad_norm": 2.6719319820404053,
      "learning_rate": 3.5457392726890236e-05,
      "loss": 1.1804,
      "step": 233
    },
    {
      "epoch": 0.15279138099902057,
      "grad_norm": 2.3251240253448486,
      "learning_rate": 3.45139266054715e-05,
      "loss": 0.9235,
      "step": 234
    },
    {
      "epoch": 0.15344433561867452,
      "grad_norm": 2.7189831733703613,
      "learning_rate": 3.3580557709966066e-05,
      "loss": 0.9769,
      "step": 235
    },
    {
      "epoch": 0.15409729023832844,
      "grad_norm": 2.5098495483398438,
      "learning_rate": 3.2657429955501394e-05,
      "loss": 1.1983,
      "step": 236
    },
    {
      "epoch": 0.15475024485798236,
      "grad_norm": 2.41629695892334,
      "learning_rate": 3.174468567813461e-05,
      "loss": 1.7956,
      "step": 237
    },
    {
      "epoch": 0.1554031994776363,
      "grad_norm": 2.5007240772247314,
      "learning_rate": 3.0842465612905837e-05,
      "loss": 1.7452,
      "step": 238
    },
    {
      "epoch": 0.15605615409729023,
      "grad_norm": 1.9491175413131714,
      "learning_rate": 2.9950908872138584e-05,
      "loss": 1.3075,
      "step": 239
    },
    {
      "epoch": 0.15670910871694418,
      "grad_norm": 2.146371841430664,
      "learning_rate": 2.9070152923989946e-05,
      "loss": 1.7472,
      "step": 240
    },
    {
      "epoch": 0.1573620633365981,
      "grad_norm": 2.1137588024139404,
      "learning_rate": 2.82003335712546e-05,
      "loss": 1.8301,
      "step": 241
    },
    {
      "epoch": 0.15801501795625203,
      "grad_norm": 2.4170126914978027,
      "learning_rate": 2.7341584930425657e-05,
      "loss": 1.8519,
      "step": 242
    },
    {
      "epoch": 0.15866797257590598,
      "grad_norm": 2.6382076740264893,
      "learning_rate": 2.6494039411015193e-05,
      "loss": 2.012,
      "step": 243
    },
    {
      "epoch": 0.1593209271955599,
      "grad_norm": 2.1745855808258057,
      "learning_rate": 2.5657827695138372e-05,
      "loss": 1.7181,
      "step": 244
    },
    {
      "epoch": 0.15997388181521385,
      "grad_norm": 2.9943010807037354,
      "learning_rate": 2.4833078717363544e-05,
      "loss": 1.5537,
      "step": 245
    },
    {
      "epoch": 0.16062683643486778,
      "grad_norm": 3.608306407928467,
      "learning_rate": 2.4019919644832023e-05,
      "loss": 1.7291,
      "step": 246
    },
    {
      "epoch": 0.1612797910545217,
      "grad_norm": 2.9223315715789795,
      "learning_rate": 2.3218475857650346e-05,
      "loss": 1.7161,
      "step": 247
    },
    {
      "epoch": 0.16193274567417565,
      "grad_norm": 3.305222749710083,
      "learning_rate": 2.242887092955801e-05,
      "loss": 1.4356,
      "step": 248
    },
    {
      "epoch": 0.16258570029382957,
      "grad_norm": 2.8326313495635986,
      "learning_rate": 2.1651226608873877e-05,
      "loss": 1.3055,
      "step": 249
    },
    {
      "epoch": 0.16323865491348352,
      "grad_norm": 3.042375087738037,
      "learning_rate": 2.0885662799723804e-05,
      "loss": 0.8947,
      "step": 250
    },
    {
      "epoch": 0.16389160953313744,
      "grad_norm": 2.6567325592041016,
      "learning_rate": 2.0132297543552757e-05,
      "loss": 1.776,
      "step": 251
    },
    {
      "epoch": 0.16454456415279137,
      "grad_norm": 2.997938871383667,
      "learning_rate": 1.939124700092423e-05,
      "loss": 1.8796,
      "step": 252
    },
    {
      "epoch": 0.16519751877244532,
      "grad_norm": 2.9053895473480225,
      "learning_rate": 1.866262543360958e-05,
      "loss": 1.662,
      "step": 253
    },
    {
      "epoch": 0.16585047339209924,
      "grad_norm": 2.6591832637786865,
      "learning_rate": 1.7946545186970022e-05,
      "loss": 1.6189,
      "step": 254
    },
    {
      "epoch": 0.1665034280117532,
      "grad_norm": 2.9311482906341553,
      "learning_rate": 1.7243116672634262e-05,
      "loss": 1.5663,
      "step": 255
    },
    {
      "epoch": 0.1671563826314071,
      "grad_norm": 2.9493162631988525,
      "learning_rate": 1.6552448351474304e-05,
      "loss": 1.5125,
      "step": 256
    },
    {
      "epoch": 0.16780933725106106,
      "grad_norm": 2.19980525970459,
      "learning_rate": 1.587464671688187e-05,
      "loss": 1.171,
      "step": 257
    },
    {
      "epoch": 0.168462291870715,
      "grad_norm": 3.4264473915100098,
      "learning_rate": 1.520981627834851e-05,
      "loss": 1.0619,
      "step": 258
    },
    {
      "epoch": 0.1691152464903689,
      "grad_norm": 2.755953550338745,
      "learning_rate": 1.4558059545351143e-05,
      "loss": 1.3709,
      "step": 259
    },
    {
      "epoch": 0.16976820111002286,
      "grad_norm": 3.0671868324279785,
      "learning_rate": 1.3919477011546423e-05,
      "loss": 1.3373,
      "step": 260
    },
    {
      "epoch": 0.17042115572967678,
      "grad_norm": 2.703378200531006,
      "learning_rate": 1.3294167139275593e-05,
      "loss": 1.4812,
      "step": 261
    },
    {
      "epoch": 0.17107411034933073,
      "grad_norm": 2.7871146202087402,
      "learning_rate": 1.2682226344382796e-05,
      "loss": 1.5082,
      "step": 262
    },
    {
      "epoch": 0.17172706496898466,
      "grad_norm": 2.1928627490997314,
      "learning_rate": 1.208374898134883e-05,
      "loss": 1.7859,
      "step": 263
    },
    {
      "epoch": 0.17238001958863858,
      "grad_norm": 2.330217123031616,
      "learning_rate": 1.1498827328742623e-05,
      "loss": 1.9261,
      "step": 264
    },
    {
      "epoch": 0.17303297420829253,
      "grad_norm": 2.532562732696533,
      "learning_rate": 1.0927551574992967e-05,
      "loss": 1.744,
      "step": 265
    },
    {
      "epoch": 0.17368592882794645,
      "grad_norm": 2.453615188598633,
      "learning_rate": 1.0370009804482483e-05,
      "loss": 1.8084,
      "step": 266
    },
    {
      "epoch": 0.1743388834476004,
      "grad_norm": 2.09717059135437,
      "learning_rate": 9.82628798396592e-06,
      "loss": 1.7786,
      "step": 267
    },
    {
      "epoch": 0.17499183806725432,
      "grad_norm": 3.074509620666504,
      "learning_rate": 9.296469949315156e-06,
      "loss": 1.9725,
      "step": 268
    },
    {
      "epoch": 0.17564479268690825,
      "grad_norm": 2.6540865898132324,
      "learning_rate": 8.780637392592495e-06,
      "loss": 1.6455,
      "step": 269
    },
    {
      "epoch": 0.1762977473065622,
      "grad_norm": 3.0181193351745605,
      "learning_rate": 8.278869849454718e-06,
      "loss": 1.7383,
      "step": 270
    },
    {
      "epoch": 0.17695070192621612,
      "grad_norm": 3.034897565841675,
      "learning_rate": 7.791244686889588e-06,
      "loss": 1.7912,
      "step": 271
    },
    {
      "epoch": 0.17760365654587007,
      "grad_norm": 3.0905239582061768,
      "learning_rate": 7.317837091286706e-06,
      "loss": 1.5027,
      "step": 272
    },
    {
      "epoch": 0.178256611165524,
      "grad_norm": 3.1407511234283447,
      "learning_rate": 6.858720056844614e-06,
      "loss": 1.2953,
      "step": 273
    },
    {
      "epoch": 0.17890956578517794,
      "grad_norm": 2.7985000610351562,
      "learning_rate": 6.413964374315851e-06,
      "loss": 1.4958,
      "step": 274
    },
    {
      "epoch": 0.17956252040483187,
      "grad_norm": 2.70698881149292,
      "learning_rate": 5.983638620091858e-06,
      "loss": 1.1345,
      "step": 275
    },
    {
      "epoch": 0.1802154750244858,
      "grad_norm": 3.302675485610962,
      "learning_rate": 5.567809145629244e-06,
      "loss": 1.8954,
      "step": 276
    },
    {
      "epoch": 0.18086842964413974,
      "grad_norm": 2.7587976455688477,
      "learning_rate": 5.1665400672190725e-06,
      "loss": 1.6744,
      "step": 277
    },
    {
      "epoch": 0.18152138426379366,
      "grad_norm": 2.4605860710144043,
      "learning_rate": 4.7798932561009865e-06,
      "loss": 1.4846,
      "step": 278
    },
    {
      "epoch": 0.1821743388834476,
      "grad_norm": 3.0369081497192383,
      "learning_rate": 4.407928328923194e-06,
      "loss": 1.5561,
      "step": 279
    },
    {
      "epoch": 0.18282729350310153,
      "grad_norm": 2.6894164085388184,
      "learning_rate": 4.050702638550275e-06,
      "loss": 1.1031,
      "step": 280
    },
    {
      "epoch": 0.18348024812275546,
      "grad_norm": 2.849666118621826,
      "learning_rate": 3.7082712652200867e-06,
      "loss": 1.366,
      "step": 281
    },
    {
      "epoch": 0.1841332027424094,
      "grad_norm": 2.834463119506836,
      "learning_rate": 3.380687008050909e-06,
      "loss": 1.1118,
      "step": 282
    },
    {
      "epoch": 0.18478615736206333,
      "grad_norm": 2.5449914932250977,
      "learning_rate": 3.068000376900515e-06,
      "loss": 1.0414,
      "step": 283
    },
    {
      "epoch": 0.18543911198171728,
      "grad_norm": 2.6311261653900146,
      "learning_rate": 2.770259584577972e-06,
      "loss": 0.9975,
      "step": 284
    },
    {
      "epoch": 0.1860920666013712,
      "grad_norm": 2.644763946533203,
      "learning_rate": 2.4875105394098654e-06,
      "loss": 1.1698,
      "step": 285
    },
    {
      "epoch": 0.18674502122102513,
      "grad_norm": 2.4958488941192627,
      "learning_rate": 2.219796838161681e-06,
      "loss": 1.6067,
      "step": 286
    },
    {
      "epoch": 0.18739797584067908,
      "grad_norm": 2.388773202896118,
      "learning_rate": 1.967159759315751e-06,
      "loss": 1.9297,
      "step": 287
    },
    {
      "epoch": 0.188050930460333,
      "grad_norm": 2.2818784713745117,
      "learning_rate": 1.7296382567064672e-06,
      "loss": 1.7271,
      "step": 288
    },
    {
      "epoch": 0.18870388507998695,
      "grad_norm": 2.581960439682007,
      "learning_rate": 1.5072689535141072e-06,
      "loss": 1.7268,
      "step": 289
    },
    {
      "epoch": 0.18935683969964087,
      "grad_norm": 2.5180134773254395,
      "learning_rate": 1.3000861366179062e-06,
      "loss": 1.9191,
      "step": 290
    },
    {
      "epoch": 0.19000979431929482,
      "grad_norm": 2.125568151473999,
      "learning_rate": 1.1081217513094212e-06,
      "loss": 1.7848,
      "step": 291
    },
    {
      "epoch": 0.19066274893894875,
      "grad_norm": 2.7064099311828613,
      "learning_rate": 9.314053963669245e-07,
      "loss": 1.6782,
      "step": 292
    },
    {
      "epoch": 0.19131570355860267,
      "grad_norm": 2.437058448791504,
      "learning_rate": 7.699643194915784e-07,
      "loss": 1.8157,
      "step": 293
    },
    {
      "epoch": 0.19196865817825662,
      "grad_norm": 3.013352870941162,
      "learning_rate": 6.238234131061616e-07,
      "loss": 1.3813,
      "step": 294
    },
    {
      "epoch": 0.19262161279791054,
      "grad_norm": 2.7739081382751465,
      "learning_rate": 4.93005210516928e-07,
      "loss": 1.7656,
      "step": 295
    },
    {
      "epoch": 0.1932745674175645,
      "grad_norm": 3.043750286102295,
      "learning_rate": 3.775298824391982e-07,
      "loss": 1.5386,
      "step": 296
    },
    {
      "epoch": 0.1939275220372184,
      "grad_norm": 2.856957197189331,
      "learning_rate": 2.774152338873126e-07,
      "loss": 1.4946,
      "step": 297
    },
    {
      "epoch": 0.19458047665687234,
      "grad_norm": 2.9437901973724365,
      "learning_rate": 1.9267670142926187e-07,
      "loss": 1.3205,
      "step": 298
    },
    {
      "epoch": 0.1952334312765263,
      "grad_norm": 2.6561126708984375,
      "learning_rate": 1.2332735080651248e-07,
      "loss": 1.1922,
      "step": 299
    },
    {
      "epoch": 0.1958863858961802,
      "grad_norm": 2.5239169597625732,
      "learning_rate": 6.9377874919474e-08,
      "loss": 0.956,
      "step": 300
    },
    {
      "epoch": 0.19653934051583416,
      "grad_norm": 2.8316755294799805,
      "learning_rate": 3.0836592178717926e-08,
      "loss": 1.8631,
      "step": 301
    },
    {
      "epoch": 0.19719229513548808,
      "grad_norm": 2.5579283237457275,
      "learning_rate": 7.709445222403577e-09,
      "loss": 1.4522,
      "step": 302
    },
    {
      "epoch": 0.197845249755142,
      "grad_norm": 2.6677441596984863,
      "learning_rate": 0.0,
      "loss": 1.7175,
      "step": 303
    }
  ],
  "logging_steps": 1,
  "max_steps": 303,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 76,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.294759255217275e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}