{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.023545108503708355,
  "eval_steps": 38,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015696739002472236,
      "grad_norm": 12.95445442199707,
      "learning_rate": 4e-05,
      "loss": 3.7815,
      "step": 1
    },
    {
      "epoch": 0.00015696739002472236,
      "eval_loss": 0.7498059868812561,
      "eval_runtime": 821.0788,
      "eval_samples_per_second": 3.268,
      "eval_steps_per_second": 1.634,
      "step": 1
    },
    {
      "epoch": 0.0003139347800494447,
      "grad_norm": 14.029548645019531,
      "learning_rate": 8e-05,
      "loss": 3.2859,
      "step": 2
    },
    {
      "epoch": 0.0004709021700741671,
      "grad_norm": 6.270756244659424,
      "learning_rate": 0.00012,
      "loss": 2.9561,
      "step": 3
    },
    {
      "epoch": 0.0006278695600988894,
      "grad_norm": 14.352215766906738,
      "learning_rate": 0.00016,
      "loss": 4.7327,
      "step": 4
    },
    {
      "epoch": 0.0007848369501236119,
      "grad_norm": 10.848075866699219,
      "learning_rate": 0.0002,
      "loss": 2.3772,
      "step": 5
    },
    {
      "epoch": 0.0009418043401483342,
      "grad_norm": 11.940299987792969,
      "learning_rate": 0.00024,
      "loss": 2.1429,
      "step": 6
    },
    {
      "epoch": 0.0010987717301730565,
      "grad_norm": 9.965449333190918,
      "learning_rate": 0.00028,
      "loss": 2.3103,
      "step": 7
    },
    {
      "epoch": 0.0012557391201977789,
      "grad_norm": 14.837979316711426,
      "learning_rate": 0.00032,
      "loss": 2.7905,
      "step": 8
    },
    {
      "epoch": 0.0014127065102225013,
      "grad_norm": 11.992790222167969,
      "learning_rate": 0.00036,
      "loss": 2.418,
      "step": 9
    },
    {
      "epoch": 0.0015696739002472237,
      "grad_norm": 16.958616256713867,
      "learning_rate": 0.0004,
      "loss": 3.5232,
      "step": 10
    },
    {
      "epoch": 0.001726641290271946,
      "grad_norm": 6.701943874359131,
      "learning_rate": 0.0003999496469885013,
      "loss": 2.2088,
      "step": 11
    },
    {
      "epoch": 0.0018836086802966683,
      "grad_norm": 5.240756511688232,
      "learning_rate": 0.00039979861330826294,
      "loss": 1.9175,
      "step": 12
    },
    {
      "epoch": 0.0020405760703213907,
      "grad_norm": 11.867003440856934,
      "learning_rate": 0.0003995469750092912,
      "loss": 2.6973,
      "step": 13
    },
    {
      "epoch": 0.002197543460346113,
      "grad_norm": 11.783756256103516,
      "learning_rate": 0.00039919485879904784,
      "loss": 3.5406,
      "step": 14
    },
    {
      "epoch": 0.0023545108503708356,
      "grad_norm": 10.173484802246094,
      "learning_rate": 0.00039874244197864856,
      "loss": 2.6159,
      "step": 15
    },
    {
      "epoch": 0.0025114782403955578,
      "grad_norm": 6.714694499969482,
      "learning_rate": 0.00039818995235358696,
      "loss": 1.4429,
      "step": 16
    },
    {
      "epoch": 0.00266844563042028,
      "grad_norm": 11.201931953430176,
      "learning_rate": 0.00039753766811902755,
      "loss": 2.7839,
      "step": 17
    },
    {
      "epoch": 0.0028254130204450026,
      "grad_norm": 7.3074951171875,
      "learning_rate": 0.0003967859177197259,
      "loss": 1.5164,
      "step": 18
    },
    {
      "epoch": 0.002982380410469725,
      "grad_norm": 8.446715354919434,
      "learning_rate": 0.00039593507968464716,
      "loss": 2.2741,
      "step": 19
    },
    {
      "epoch": 0.0031393478004944474,
      "grad_norm": 5.973799705505371,
      "learning_rate": 0.0003949855824363647,
      "loss": 1.5339,
      "step": 20
    },
    {
      "epoch": 0.0032963151905191696,
      "grad_norm": 6.163540363311768,
      "learning_rate": 0.0003939379040753374,
      "loss": 1.755,
      "step": 21
    },
    {
      "epoch": 0.003453282580543892,
      "grad_norm": 7.136409759521484,
      "learning_rate": 0.00039279257213917066,
      "loss": 2.1914,
      "step": 22
    },
    {
      "epoch": 0.0036102499705686145,
      "grad_norm": 7.554473400115967,
      "learning_rate": 0.0003915501633369861,
      "loss": 2.1009,
      "step": 23
    },
    {
      "epoch": 0.0037672173605933367,
      "grad_norm": 37.26305389404297,
      "learning_rate": 0.00039021130325903074,
      "loss": 4.9365,
      "step": 24
    },
    {
      "epoch": 0.003924184750618059,
      "grad_norm": 10.216833114624023,
      "learning_rate": 0.00038877666606167355,
      "loss": 1.8749,
      "step": 25
    },
    {
      "epoch": 0.0040811521406427815,
      "grad_norm": 11.548598289489746,
      "learning_rate": 0.00038724697412794747,
      "loss": 2.5951,
      "step": 26
    },
    {
      "epoch": 0.004238119530667504,
      "grad_norm": 10.462121963500977,
      "learning_rate": 0.0003856229977038078,
      "loss": 2.2098,
      "step": 27
    },
    {
      "epoch": 0.004395086920692226,
      "grad_norm": 9.643802642822266,
      "learning_rate": 0.0003839055545102902,
      "loss": 1.9106,
      "step": 28
    },
    {
      "epoch": 0.0045520543107169485,
      "grad_norm": 9.896982192993164,
      "learning_rate": 0.00038209550933176323,
      "loss": 2.4819,
      "step": 29
    },
    {
      "epoch": 0.004709021700741671,
      "grad_norm": 15.647576332092285,
      "learning_rate": 0.0003801937735804838,
      "loss": 3.3157,
      "step": 30
    },
    {
      "epoch": 0.004865989090766393,
      "grad_norm": 7.6956634521484375,
      "learning_rate": 0.0003782013048376736,
      "loss": 2.4637,
      "step": 31
    },
    {
      "epoch": 0.0050229564807911155,
      "grad_norm": 7.653892993927002,
      "learning_rate": 0.0003761191063713476,
      "loss": 1.8644,
      "step": 32
    },
    {
      "epoch": 0.005179923870815838,
      "grad_norm": 20.444591522216797,
      "learning_rate": 0.0003739482266311391,
      "loss": 2.7017,
      "step": 33
    },
    {
      "epoch": 0.00533689126084056,
      "grad_norm": 7.471802711486816,
      "learning_rate": 0.00037168975872037323,
      "loss": 2.9944,
      "step": 34
    },
    {
      "epoch": 0.005493858650865283,
      "grad_norm": 6.789485454559326,
      "learning_rate": 0.00036934483984565685,
      "loss": 1.5157,
      "step": 35
    },
    {
      "epoch": 0.005650826040890005,
      "grad_norm": 6.496057510375977,
      "learning_rate": 0.00036691465074426054,
      "loss": 2.2969,
      "step": 36
    },
    {
      "epoch": 0.005807793430914728,
      "grad_norm": 7.474277496337891,
      "learning_rate": 0.00036440041508958203,
      "loss": 1.8918,
      "step": 37
    },
    {
      "epoch": 0.00596476082093945,
      "grad_norm": 12.531452178955078,
      "learning_rate": 0.0003618033988749895,
      "loss": 2.7539,
      "step": 38
    },
    {
      "epoch": 0.00596476082093945,
      "eval_loss": 0.6094685196876526,
      "eval_runtime": 820.3189,
      "eval_samples_per_second": 3.271,
      "eval_steps_per_second": 1.636,
      "step": 38
    },
    {
      "epoch": 0.006121728210964172,
      "grad_norm": 11.514887809753418,
      "learning_rate": 0.00035912490977635625,
      "loss": 3.1396,
      "step": 39
    },
    {
      "epoch": 0.006278695600988895,
      "grad_norm": 9.372078895568848,
      "learning_rate": 0.000356366296493606,
      "loss": 2.4996,
      "step": 40
    },
    {
      "epoch": 0.006435662991013617,
      "grad_norm": 12.012513160705566,
      "learning_rate": 0.0003535289480716022,
      "loss": 2.7457,
      "step": 41
    },
    {
      "epoch": 0.006592630381038339,
      "grad_norm": 9.123496055603027,
      "learning_rate": 0.00035061429320072223,
      "loss": 2.8422,
      "step": 42
    },
    {
      "epoch": 0.006749597771063062,
      "grad_norm": 6.817448139190674,
      "learning_rate": 0.00034762379949746815,
      "loss": 2.2889,
      "step": 43
    },
    {
      "epoch": 0.006906565161087784,
      "grad_norm": 5.610447883605957,
      "learning_rate": 0.0003445589727654783,
      "loss": 1.5969,
      "step": 44
    },
    {
      "epoch": 0.007063532551112506,
      "grad_norm": 7.098076343536377,
      "learning_rate": 0.0003414213562373095,
      "loss": 2.2073,
      "step": 45
    },
    {
      "epoch": 0.007220499941137229,
      "grad_norm": 9.250218391418457,
      "learning_rate": 0.00033821252979737297,
      "loss": 2.2856,
      "step": 46
    },
    {
      "epoch": 0.007377467331161951,
      "grad_norm": 6.528243064880371,
      "learning_rate": 0.0003349341091864149,
      "loss": 1.8539,
      "step": 47
    },
    {
      "epoch": 0.007534434721186673,
      "grad_norm": 11.957141876220703,
      "learning_rate": 0.00033158774518794254,
      "loss": 3.4304,
      "step": 48
    },
    {
      "epoch": 0.007691402111211396,
      "grad_norm": 5.783234596252441,
      "learning_rate": 0.0003281751227970048,
      "loss": 1.9596,
      "step": 49
    },
    {
      "epoch": 0.007848369501236118,
      "grad_norm": 15.507065773010254,
      "learning_rate": 0.00032469796037174674,
      "loss": 3.9566,
      "step": 50
    },
    {
      "epoch": 0.008005336891260841,
      "grad_norm": 7.186437606811523,
      "learning_rate": 0.000321158008768164,
      "loss": 1.9811,
      "step": 51
    },
    {
      "epoch": 0.008162304281285563,
      "grad_norm": 7.9519124031066895,
      "learning_rate": 0.00031755705045849464,
      "loss": 2.5435,
      "step": 52
    },
    {
      "epoch": 0.008319271671310285,
      "grad_norm": 11.823431968688965,
      "learning_rate": 0.0003138968986336904,
      "loss": 2.5919,
      "step": 53
    },
    {
      "epoch": 0.008476239061335008,
      "grad_norm": 5.554260730743408,
      "learning_rate": 0.0003101793962904205,
      "loss": 1.4945,
      "step": 54
    },
    {
      "epoch": 0.00863320645135973,
      "grad_norm": 7.568012237548828,
      "learning_rate": 0.00030640641530306733,
      "loss": 2.155,
      "step": 55
    },
    {
      "epoch": 0.008790173841384452,
      "grad_norm": 31.618026733398438,
      "learning_rate": 0.00030257985548118126,
      "loss": 2.7959,
      "step": 56
    },
    {
      "epoch": 0.008947141231409175,
      "grad_norm": 11.720658302307129,
      "learning_rate": 0.0002987016436128694,
      "loss": 3.1511,
      "step": 57
    },
    {
      "epoch": 0.009104108621433897,
      "grad_norm": 9.653231620788574,
      "learning_rate": 0.0002947737324945997,
      "loss": 2.2899,
      "step": 58
    },
    {
      "epoch": 0.009261076011458619,
      "grad_norm": 8.848836898803711,
      "learning_rate": 0.00029079809994790937,
      "loss": 1.7292,
      "step": 59
    },
    {
      "epoch": 0.009418043401483342,
      "grad_norm": 7.872807025909424,
      "learning_rate": 0.00028677674782351165,
      "loss": 2.3457,
      "step": 60
    },
    {
      "epoch": 0.009575010791508064,
      "grad_norm": 7.429281711578369,
      "learning_rate": 0.00028271170099330415,
      "loss": 1.9487,
      "step": 61
    },
    {
      "epoch": 0.009731978181532786,
      "grad_norm": 12.662517547607422,
      "learning_rate": 0.00027860500633078477,
      "loss": 2.1071,
      "step": 62
    },
    {
      "epoch": 0.00988894557155751,
      "grad_norm": 7.445736885070801,
      "learning_rate": 0.00027445873168038907,
      "loss": 2.6263,
      "step": 63
    },
    {
      "epoch": 0.010045912961582231,
      "grad_norm": 8.707975387573242,
      "learning_rate": 0.0002702749648162686,
      "loss": 2.4687,
      "step": 64
    },
    {
      "epoch": 0.010202880351606953,
      "grad_norm": 7.881085395812988,
      "learning_rate": 0.00026605581239103347,
      "loss": 2.033,
      "step": 65
    },
    {
      "epoch": 0.010359847741631676,
      "grad_norm": 10.121798515319824,
      "learning_rate": 0.00026180339887498953,
      "loss": 1.9015,
      "step": 66
    },
    {
      "epoch": 0.010516815131656398,
      "grad_norm": 21.383502960205078,
      "learning_rate": 0.00025751986548640346,
      "loss": 2.6845,
      "step": 67
    },
    {
      "epoch": 0.01067378252168112,
      "grad_norm": 13.87905216217041,
      "learning_rate": 0.00025320736911333503,
      "loss": 2.0689,
      "step": 68
    },
    {
      "epoch": 0.010830749911705843,
      "grad_norm": 20.752147674560547,
      "learning_rate": 0.0002488680812275788,
      "loss": 2.3047,
      "step": 69
    },
    {
      "epoch": 0.010987717301730565,
      "grad_norm": 8.677228927612305,
      "learning_rate": 0.0002445041867912629,
      "loss": 2.2145,
      "step": 70
    },
    {
      "epoch": 0.011144684691755289,
      "grad_norm": 16.90841293334961,
      "learning_rate": 0.00024011788315665458,
      "loss": 2.6634,
      "step": 71
    },
    {
      "epoch": 0.01130165208178001,
      "grad_norm": 58.644561767578125,
      "learning_rate": 0.00023571137895972733,
      "loss": 3.7571,
      "step": 72
    },
    {
      "epoch": 0.011458619471804732,
      "grad_norm": 9.913825035095215,
      "learning_rate": 0.0002312868930080462,
      "loss": 2.2174,
      "step": 73
    },
    {
      "epoch": 0.011615586861829456,
      "grad_norm": 7.47474479675293,
      "learning_rate": 0.0002268466531635311,
      "loss": 1.7509,
      "step": 74
    },
    {
      "epoch": 0.011772554251854177,
      "grad_norm": 8.850740432739258,
      "learning_rate": 0.00022239289522066157,
      "loss": 1.9296,
      "step": 75
    },
    {
      "epoch": 0.0119295216418789,
      "grad_norm": 6.602862358093262,
      "learning_rate": 0.00021792786178068672,
      "loss": 2.5602,
      "step": 76
    },
    {
      "epoch": 0.0119295216418789,
      "eval_loss": 0.5898057818412781,
      "eval_runtime": 820.7489,
      "eval_samples_per_second": 3.269,
      "eval_steps_per_second": 1.635,
      "step": 76
    },
    {
      "epoch": 0.012086489031903623,
      "grad_norm": 6.227441787719727,
      "learning_rate": 0.00021345380112240797,
      "loss": 1.5853,
      "step": 77
    },
    {
      "epoch": 0.012243456421928344,
      "grad_norm": 6.998437881469727,
      "learning_rate": 0.00020897296607010301,
      "loss": 2.4302,
      "step": 78
    },
    {
      "epoch": 0.012400423811953066,
      "grad_norm": 7.076618671417236,
      "learning_rate": 0.00020448761285916104,
      "loss": 2.2843,
      "step": 79
    },
    {
      "epoch": 0.01255739120197779,
      "grad_norm": 7.667428016662598,
      "learning_rate": 0.0002,
      "loss": 2.4866,
      "step": 80
    },
    {
      "epoch": 0.012714358592002512,
      "grad_norm": 8.555462837219238,
      "learning_rate": 0.00019551238714083903,
      "loss": 2.2074,
      "step": 81
    },
    {
      "epoch": 0.012871325982027233,
      "grad_norm": 13.07919979095459,
      "learning_rate": 0.00019102703392989709,
      "loss": 2.0399,
      "step": 82
    },
    {
      "epoch": 0.013028293372051957,
      "grad_norm": 7.338263034820557,
      "learning_rate": 0.00018654619887759207,
      "loss": 2.3211,
      "step": 83
    },
    {
      "epoch": 0.013185260762076679,
      "grad_norm": 15.829663276672363,
      "learning_rate": 0.00018207213821931333,
      "loss": 2.6278,
      "step": 84
    },
    {
      "epoch": 0.0133422281521014,
      "grad_norm": 24.069778442382812,
      "learning_rate": 0.00017760710477933845,
      "loss": 2.8608,
      "step": 85
    },
    {
      "epoch": 0.013499195542126124,
      "grad_norm": 10.94772720336914,
      "learning_rate": 0.00017315334683646897,
      "loss": 2.7356,
      "step": 86
    },
    {
      "epoch": 0.013656162932150846,
      "grad_norm": 11.706610679626465,
      "learning_rate": 0.00016871310699195379,
      "loss": 2.2746,
      "step": 87
    },
    {
      "epoch": 0.013813130322175567,
      "grad_norm": 6.187313556671143,
      "learning_rate": 0.00016428862104027268,
      "loss": 1.8093,
      "step": 88
    },
    {
      "epoch": 0.01397009771220029,
      "grad_norm": 21.33131980895996,
      "learning_rate": 0.00015988211684334546,
      "loss": 3.0504,
      "step": 89
    },
    {
      "epoch": 0.014127065102225013,
      "grad_norm": 5.162511825561523,
      "learning_rate": 0.00015549581320873715,
      "loss": 1.5756,
      "step": 90
    },
    {
      "epoch": 0.014284032492249734,
      "grad_norm": 7.791429042816162,
      "learning_rate": 0.00015113191877242117,
      "loss": 1.8701,
      "step": 91
    },
    {
      "epoch": 0.014440999882274458,
      "grad_norm": 10.379227638244629,
      "learning_rate": 0.00014679263088666499,
      "loss": 2.3252,
      "step": 92
    },
    {
      "epoch": 0.01459796727229918,
      "grad_norm": 10.369537353515625,
      "learning_rate": 0.00014248013451359656,
      "loss": 2.2013,
      "step": 93
    },
    {
      "epoch": 0.014754934662323901,
      "grad_norm": 7.18357515335083,
      "learning_rate": 0.00013819660112501054,
      "loss": 1.4809,
      "step": 94
    },
    {
      "epoch": 0.014911902052348625,
      "grad_norm": 7.497470855712891,
      "learning_rate": 0.00013394418760896666,
      "loss": 1.8012,
      "step": 95
    },
    {
      "epoch": 0.015068869442373347,
      "grad_norm": 8.430214881896973,
      "learning_rate": 0.00012972503518373144,
      "loss": 1.6045,
      "step": 96
    },
    {
      "epoch": 0.01522583683239807,
      "grad_norm": 7.286400318145752,
      "learning_rate": 0.00012554126831961098,
      "loss": 1.9472,
      "step": 97
    },
    {
      "epoch": 0.015382804222422792,
      "grad_norm": 6.470623970031738,
      "learning_rate": 0.0001213949936692153,
      "loss": 1.9869,
      "step": 98
    },
    {
      "epoch": 0.015539771612447514,
      "grad_norm": 13.478861808776855,
      "learning_rate": 0.00011728829900669591,
      "loss": 2.1083,
      "step": 99
    },
    {
      "epoch": 0.015696739002472235,
      "grad_norm": 6.1007585525512695,
      "learning_rate": 0.00011322325217648839,
      "loss": 1.8082,
      "step": 100
    },
    {
      "epoch": 0.015853706392496957,
      "grad_norm": 7.112922668457031,
      "learning_rate": 0.00010920190005209065,
      "loss": 1.9454,
      "step": 101
    },
    {
      "epoch": 0.016010673782521682,
      "grad_norm": 12.862048149108887,
      "learning_rate": 0.00010522626750540028,
      "loss": 2.4716,
      "step": 102
    },
    {
      "epoch": 0.016167641172546404,
      "grad_norm": 6.302742958068848,
      "learning_rate": 0.00010129835638713063,
      "loss": 1.688,
      "step": 103
    },
    {
      "epoch": 0.016324608562571126,
      "grad_norm": 11.294086456298828,
      "learning_rate": 9.74201445188188e-05,
      "loss": 2.2397,
      "step": 104
    },
    {
      "epoch": 0.016481575952595848,
      "grad_norm": 12.633040428161621,
      "learning_rate": 9.359358469693271e-05,
      "loss": 2.1285,
      "step": 105
    },
    {
      "epoch": 0.01663854334262057,
      "grad_norm": 6.535755157470703,
      "learning_rate": 8.982060370957952e-05,
      "loss": 1.8518,
      "step": 106
    },
    {
      "epoch": 0.01679551073264529,
      "grad_norm": 7.625582695007324,
      "learning_rate": 8.610310136630962e-05,
      "loss": 2.0861,
      "step": 107
    },
    {
      "epoch": 0.016952478122670016,
      "grad_norm": 6.302818775177002,
      "learning_rate": 8.24429495415054e-05,
      "loss": 1.6471,
      "step": 108
    },
    {
      "epoch": 0.017109445512694738,
      "grad_norm": 7.8976030349731445,
      "learning_rate": 7.884199123183605e-05,
      "loss": 1.7234,
      "step": 109
    },
    {
      "epoch": 0.01726641290271946,
      "grad_norm": 19.286394119262695,
      "learning_rate": 7.530203962825331e-05,
      "loss": 3.6885,
      "step": 110
    },
    {
      "epoch": 0.017423380292744182,
      "grad_norm": 7.020461082458496,
      "learning_rate": 7.182487720299517e-05,
      "loss": 1.7969,
      "step": 111
    },
    {
      "epoch": 0.017580347682768904,
      "grad_norm": 10.761330604553223,
      "learning_rate": 6.841225481205749e-05,
      "loss": 2.5873,
      "step": 112
    },
    {
      "epoch": 0.01773731507279363,
      "grad_norm": 6.884322166442871,
      "learning_rate": 6.506589081358514e-05,
      "loss": 1.5864,
      "step": 113
    },
    {
      "epoch": 0.01789428246281835,
      "grad_norm": 8.130167007446289,
      "learning_rate": 6.178747020262707e-05,
      "loss": 1.8232,
      "step": 114
    },
    {
      "epoch": 0.01789428246281835,
      "eval_loss": 0.5430928468704224,
      "eval_runtime": 820.8054,
      "eval_samples_per_second": 3.269,
      "eval_steps_per_second": 1.635,
      "step": 114
    },
    {
      "epoch": 0.018051249852843072,
      "grad_norm": 6.698558807373047,
      "learning_rate": 5.857864376269051e-05,
      "loss": 2.5849,
      "step": 115
    },
    {
      "epoch": 0.018208217242867794,
      "grad_norm": 10.639579772949219,
      "learning_rate": 5.544102723452171e-05,
      "loss": 2.6,
      "step": 116
    },
    {
      "epoch": 0.018365184632892516,
      "grad_norm": 8.183032989501953,
      "learning_rate": 5.237620050253189e-05,
      "loss": 2.6161,
      "step": 117
    },
    {
      "epoch": 0.018522152022917238,
      "grad_norm": 6.063802242279053,
      "learning_rate": 4.938570679927783e-05,
      "loss": 1.3668,
      "step": 118
    },
    {
      "epoch": 0.018679119412941963,
      "grad_norm": 5.778029441833496,
      "learning_rate": 4.647105192839778e-05,
      "loss": 1.6742,
      "step": 119
    },
    {
      "epoch": 0.018836086802966685,
      "grad_norm": 9.222543716430664,
      "learning_rate": 4.363370350639404e-05,
      "loss": 2.0035,
      "step": 120
    },
    {
      "epoch": 0.018993054192991406,
      "grad_norm": 10.651296615600586,
      "learning_rate": 4.087509022364382e-05,
      "loss": 2.5014,
      "step": 121
    },
    {
      "epoch": 0.019150021583016128,
      "grad_norm": 11.831440925598145,
      "learning_rate": 3.819660112501053e-05,
      "loss": 2.2869,
      "step": 122
    },
    {
      "epoch": 0.01930698897304085,
      "grad_norm": 7.712268829345703,
      "learning_rate": 3.5599584910418035e-05,
      "loss": 2.0851,
      "step": 123
    },
    {
      "epoch": 0.01946395636306557,
      "grad_norm": 9.053482055664062,
      "learning_rate": 3.3085349255739474e-05,
      "loss": 1.8142,
      "step": 124
    },
    {
      "epoch": 0.019620923753090297,
      "grad_norm": 8.176172256469727,
      "learning_rate": 3.0655160154343174e-05,
      "loss": 2.3284,
      "step": 125
    },
    {
      "epoch": 0.01977789114311502,
      "grad_norm": 18.283300399780273,
      "learning_rate": 2.831024127962678e-05,
      "loss": 1.9836,
      "step": 126
    },
    {
      "epoch": 0.01993485853313974,
      "grad_norm": 7.915673732757568,
      "learning_rate": 2.6051773368860934e-05,
      "loss": 2.3106,
      "step": 127
    },
    {
      "epoch": 0.020091825923164462,
      "grad_norm": 6.272395133972168,
      "learning_rate": 2.38808936286524e-05,
      "loss": 1.862,
      "step": 128
    },
    {
      "epoch": 0.020248793313189184,
      "grad_norm": 9.373351097106934,
      "learning_rate": 2.1798695162326442e-05,
      "loss": 2.0214,
      "step": 129
    },
    {
      "epoch": 0.020405760703213906,
      "grad_norm": 8.452390670776367,
      "learning_rate": 1.9806226419516192e-05,
      "loss": 1.8931,
      "step": 130
    },
    {
      "epoch": 0.02056272809323863,
      "grad_norm": 6.104604721069336,
      "learning_rate": 1.790449066823683e-05,
      "loss": 1.9672,
      "step": 131
    },
    {
      "epoch": 0.020719695483263353,
      "grad_norm": 5.282866477966309,
      "learning_rate": 1.6094445489709885e-05,
      "loss": 2.1532,
      "step": 132
    },
    {
      "epoch": 0.020876662873288074,
      "grad_norm": 8.8634672164917,
      "learning_rate": 1.4377002296192233e-05,
      "loss": 1.9147,
      "step": 133
    },
    {
      "epoch": 0.021033630263312796,
      "grad_norm": 29.37977409362793,
      "learning_rate": 1.275302587205256e-05,
      "loss": 3.5516,
      "step": 134
    },
    {
      "epoch": 0.021190597653337518,
      "grad_norm": 12.045405387878418,
      "learning_rate": 1.1223333938326485e-05,
      "loss": 2.0136,
      "step": 135
    },
    {
      "epoch": 0.02134756504336224,
      "grad_norm": 6.3739399909973145,
      "learning_rate": 9.788696740969295e-06,
      "loss": 1.7538,
      "step": 136
    },
    {
      "epoch": 0.021504532433386965,
      "grad_norm": 10.208410263061523,
      "learning_rate": 8.44983666301391e-06,
      "loss": 1.9149,
      "step": 137
    },
    {
      "epoch": 0.021661499823411687,
      "grad_norm": 6.10170841217041,
      "learning_rate": 7.2074278608293525e-06,
      "loss": 1.7403,
      "step": 138
    },
    {
      "epoch": 0.02181846721343641,
      "grad_norm": 11.614684104919434,
      "learning_rate": 6.062095924662625e-06,
      "loss": 2.1914,
      "step": 139
    },
    {
      "epoch": 0.02197543460346113,
      "grad_norm": 13.544835090637207,
      "learning_rate": 5.0144175636352765e-06,
      "loss": 2.4752,
      "step": 140
    },
    {
      "epoch": 0.022132401993485852,
      "grad_norm": 10.997184753417969,
      "learning_rate": 4.064920315352904e-06,
      "loss": 1.691,
      "step": 141
    },
    {
      "epoch": 0.022289369383510577,
      "grad_norm": 5.709866046905518,
      "learning_rate": 3.2140822802740668e-06,
      "loss": 1.5808,
      "step": 142
    },
    {
      "epoch": 0.0224463367735353,
      "grad_norm": 8.197881698608398,
      "learning_rate": 2.462331880972468e-06,
      "loss": 2.0699,
      "step": 143
    },
    {
      "epoch": 0.02260330416356002,
      "grad_norm": 9.883748054504395,
      "learning_rate": 1.81004764641306e-06,
      "loss": 2.9457,
      "step": 144
    },
    {
      "epoch": 0.022760271553584743,
      "grad_norm": 9.526391983032227,
      "learning_rate": 1.2575580213514792e-06,
      "loss": 2.7024,
      "step": 145
    },
    {
      "epoch": 0.022917238943609464,
      "grad_norm": 6.334656715393066,
      "learning_rate": 8.051412009521864e-07,
      "loss": 2.2296,
      "step": 146
    },
    {
      "epoch": 0.023074206333634186,
      "grad_norm": 6.532505989074707,
      "learning_rate": 4.530249907087836e-07,
      "loss": 2.0629,
      "step": 147
    },
    {
      "epoch": 0.02323117372365891,
      "grad_norm": 6.112399578094482,
      "learning_rate": 2.0138669173708213e-07,
      "loss": 1.8538,
      "step": 148
    },
    {
      "epoch": 0.023388141113683633,
      "grad_norm": 6.967254161834717,
      "learning_rate": 5.035301149869387e-08,
      "loss": 1.9779,
      "step": 149
    },
    {
      "epoch": 0.023545108503708355,
      "grad_norm": 6.000161647796631,
      "learning_rate": 0.0,
      "loss": 1.649,
      "step": 150
    }
  ],
  "logging_steps": 1,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 38,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.333035535623782e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}