{
  "best_metric": 0.8386966586112976,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.10933442667760011,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005466721333880005,
      "grad_norm": 0.4661848545074463,
      "learning_rate": 2.333333333333333e-06,
      "loss": 0.7648,
      "step": 1
    },
    {
      "epoch": 0.0005466721333880005,
      "eval_loss": 1.3695563077926636,
      "eval_runtime": 94.695,
      "eval_samples_per_second": 32.536,
      "eval_steps_per_second": 8.142,
      "step": 1
    },
    {
      "epoch": 0.001093344266776001,
      "grad_norm": 0.411937952041626,
      "learning_rate": 4.666666666666666e-06,
      "loss": 0.7517,
      "step": 2
    },
    {
      "epoch": 0.0016400164001640015,
      "grad_norm": 0.539547324180603,
      "learning_rate": 7e-06,
      "loss": 0.9216,
      "step": 3
    },
    {
      "epoch": 0.002186688533552002,
      "grad_norm": 0.5318194627761841,
      "learning_rate": 9.333333333333333e-06,
      "loss": 0.8582,
      "step": 4
    },
    {
      "epoch": 0.0027333606669400026,
      "grad_norm": 0.5687560439109802,
      "learning_rate": 1.1666666666666665e-05,
      "loss": 0.9711,
      "step": 5
    },
    {
      "epoch": 0.003280032800328003,
      "grad_norm": 0.7335965633392334,
      "learning_rate": 1.4e-05,
      "loss": 0.9818,
      "step": 6
    },
    {
      "epoch": 0.003826704933716004,
      "grad_norm": 0.4608137309551239,
      "learning_rate": 1.633333333333333e-05,
      "loss": 0.8496,
      "step": 7
    },
    {
      "epoch": 0.004373377067104004,
      "grad_norm": 0.5464603900909424,
      "learning_rate": 1.8666666666666665e-05,
      "loss": 0.9922,
      "step": 8
    },
    {
      "epoch": 0.004920049200492005,
      "grad_norm": 0.557895839214325,
      "learning_rate": 2.1e-05,
      "loss": 1.0499,
      "step": 9
    },
    {
      "epoch": 0.005466721333880005,
      "grad_norm": 0.43142303824424744,
      "learning_rate": 2.333333333333333e-05,
      "loss": 0.9916,
      "step": 10
    },
    {
      "epoch": 0.006013393467268006,
      "grad_norm": 0.39260706305503845,
      "learning_rate": 2.5666666666666663e-05,
      "loss": 0.9236,
      "step": 11
    },
    {
      "epoch": 0.006560065600656006,
      "grad_norm": 0.40968865156173706,
      "learning_rate": 2.8e-05,
      "loss": 1.0978,
      "step": 12
    },
    {
      "epoch": 0.007106737734044007,
      "grad_norm": 0.4441259503364563,
      "learning_rate": 3.0333333333333333e-05,
      "loss": 1.0146,
      "step": 13
    },
    {
      "epoch": 0.007653409867432008,
      "grad_norm": 0.40066277980804443,
      "learning_rate": 3.266666666666666e-05,
      "loss": 0.916,
      "step": 14
    },
    {
      "epoch": 0.008200082000820008,
      "grad_norm": 0.4672339856624603,
      "learning_rate": 3.5e-05,
      "loss": 1.0468,
      "step": 15
    },
    {
      "epoch": 0.008746754134208008,
      "grad_norm": 0.48708584904670715,
      "learning_rate": 3.733333333333333e-05,
      "loss": 1.049,
      "step": 16
    },
    {
      "epoch": 0.00929342626759601,
      "grad_norm": 0.5237523913383484,
      "learning_rate": 3.9666666666666664e-05,
      "loss": 1.0419,
      "step": 17
    },
    {
      "epoch": 0.00984009840098401,
      "grad_norm": 0.5612183213233948,
      "learning_rate": 4.2e-05,
      "loss": 0.9977,
      "step": 18
    },
    {
      "epoch": 0.01038677053437201,
      "grad_norm": 0.5430253148078918,
      "learning_rate": 4.4333333333333324e-05,
      "loss": 1.146,
      "step": 19
    },
    {
      "epoch": 0.01093344266776001,
      "grad_norm": 0.5050835013389587,
      "learning_rate": 4.666666666666666e-05,
      "loss": 0.9679,
      "step": 20
    },
    {
      "epoch": 0.011480114801148012,
      "grad_norm": 0.4491889774799347,
      "learning_rate": 4.899999999999999e-05,
      "loss": 0.8918,
      "step": 21
    },
    {
      "epoch": 0.012026786934536012,
      "grad_norm": 0.46133682131767273,
      "learning_rate": 5.1333333333333325e-05,
      "loss": 0.891,
      "step": 22
    },
    {
      "epoch": 0.012573459067924012,
      "grad_norm": 0.5220205783843994,
      "learning_rate": 5.3666666666666666e-05,
      "loss": 0.9138,
      "step": 23
    },
    {
      "epoch": 0.013120131201312012,
      "grad_norm": 0.5471235513687134,
      "learning_rate": 5.6e-05,
      "loss": 1.0219,
      "step": 24
    },
    {
      "epoch": 0.013666803334700014,
      "grad_norm": 0.5401260852813721,
      "learning_rate": 5.833333333333333e-05,
      "loss": 0.9114,
      "step": 25
    },
    {
      "epoch": 0.014213475468088014,
      "grad_norm": 0.5504897236824036,
      "learning_rate": 6.0666666666666666e-05,
      "loss": 0.9869,
      "step": 26
    },
    {
      "epoch": 0.014760147601476014,
      "grad_norm": 0.6574556827545166,
      "learning_rate": 6.3e-05,
      "loss": 0.9166,
      "step": 27
    },
    {
      "epoch": 0.015306819734864016,
      "grad_norm": 0.6381729245185852,
      "learning_rate": 6.533333333333333e-05,
      "loss": 1.0102,
      "step": 28
    },
    {
      "epoch": 0.015853491868252016,
      "grad_norm": 0.6967756748199463,
      "learning_rate": 6.766666666666667e-05,
      "loss": 0.9655,
      "step": 29
    },
    {
      "epoch": 0.016400164001640016,
      "grad_norm": 0.7127764225006104,
      "learning_rate": 7e-05,
      "loss": 1.0242,
      "step": 30
    },
    {
      "epoch": 0.016946836135028016,
      "grad_norm": 0.6833203434944153,
      "learning_rate": 6.999402376603183e-05,
      "loss": 0.9315,
      "step": 31
    },
    {
      "epoch": 0.017493508268416016,
      "grad_norm": 0.8914316296577454,
      "learning_rate": 6.99760971050058e-05,
      "loss": 1.0732,
      "step": 32
    },
    {
      "epoch": 0.018040180401804017,
      "grad_norm": 1.0326182842254639,
      "learning_rate": 6.994622613886018e-05,
      "loss": 1.0459,
      "step": 33
    },
    {
      "epoch": 0.01858685253519202,
      "grad_norm": 0.8010824918746948,
      "learning_rate": 6.990442106850258e-05,
      "loss": 0.986,
      "step": 34
    },
    {
      "epoch": 0.01913352466858002,
      "grad_norm": 0.9589248895645142,
      "learning_rate": 6.98506961703262e-05,
      "loss": 0.9221,
      "step": 35
    },
    {
      "epoch": 0.01968019680196802,
      "grad_norm": 0.7887236475944519,
      "learning_rate": 6.978506979133457e-05,
      "loss": 1.0374,
      "step": 36
    },
    {
      "epoch": 0.02022686893535602,
      "grad_norm": 0.8019972443580627,
      "learning_rate": 6.9707564342876e-05,
      "loss": 0.8858,
      "step": 37
    },
    {
      "epoch": 0.02077354106874402,
      "grad_norm": 0.8885377049446106,
      "learning_rate": 6.96182062929901e-05,
      "loss": 1.0831,
      "step": 38
    },
    {
      "epoch": 0.02132021320213202,
      "grad_norm": 0.9791058301925659,
      "learning_rate": 6.951702615736908e-05,
      "loss": 1.0472,
      "step": 39
    },
    {
      "epoch": 0.02186688533552002,
      "grad_norm": 1.0434457063674927,
      "learning_rate": 6.940405848893656e-05,
      "loss": 0.9667,
      "step": 40
    },
    {
      "epoch": 0.022413557468908024,
      "grad_norm": 1.0951871871948242,
      "learning_rate": 6.92793418660478e-05,
      "loss": 1.1452,
      "step": 41
    },
    {
      "epoch": 0.022960229602296024,
      "grad_norm": 1.0019595623016357,
      "learning_rate": 6.914291887931528e-05,
      "loss": 0.8607,
      "step": 42
    },
    {
      "epoch": 0.023506901735684024,
      "grad_norm": 1.2730623483657837,
      "learning_rate": 6.899483611706398e-05,
      "loss": 1.0172,
      "step": 43
    },
    {
      "epoch": 0.024053573869072024,
      "grad_norm": 1.064156413078308,
      "learning_rate": 6.883514414942155e-05,
      "loss": 0.9434,
      "step": 44
    },
    {
      "epoch": 0.024600246002460024,
      "grad_norm": 1.1558951139450073,
      "learning_rate": 6.866389751104867e-05,
      "loss": 0.9083,
      "step": 45
    },
    {
      "epoch": 0.025146918135848025,
      "grad_norm": 1.3744535446166992,
      "learning_rate": 6.848115468251542e-05,
      "loss": 0.8842,
      "step": 46
    },
    {
      "epoch": 0.025693590269236025,
      "grad_norm": 1.5875253677368164,
      "learning_rate": 6.828697807033038e-05,
      "loss": 1.0323,
      "step": 47
    },
    {
      "epoch": 0.026240262402624025,
      "grad_norm": 1.4661047458648682,
      "learning_rate": 6.808143398562868e-05,
      "loss": 0.8986,
      "step": 48
    },
    {
      "epoch": 0.026786934536012028,
      "grad_norm": 1.6527341604232788,
      "learning_rate": 6.786459262152698e-05,
      "loss": 1.0423,
      "step": 49
    },
    {
      "epoch": 0.02733360666940003,
      "grad_norm": 4.2761406898498535,
      "learning_rate": 6.763652802915244e-05,
      "loss": 1.1307,
      "step": 50
    },
    {
      "epoch": 0.02733360666940003,
      "eval_loss": 0.9474524855613708,
      "eval_runtime": 94.8645,
      "eval_samples_per_second": 32.478,
      "eval_steps_per_second": 8.127,
      "step": 50
    },
    {
      "epoch": 0.02788027880278803,
      "grad_norm": 0.9167900681495667,
      "learning_rate": 6.739731809235446e-05,
      "loss": 0.7292,
      "step": 51
    },
    {
      "epoch": 0.02842695093617603,
      "grad_norm": 1.0346499681472778,
      "learning_rate": 6.71470445011073e-05,
      "loss": 0.7878,
      "step": 52
    },
    {
      "epoch": 0.02897362306956403,
      "grad_norm": 0.9062778949737549,
      "learning_rate": 6.688579272361309e-05,
      "loss": 0.8643,
      "step": 53
    },
    {
      "epoch": 0.02952029520295203,
      "grad_norm": 0.6097351908683777,
      "learning_rate": 6.66136519771145e-05,
      "loss": 0.8222,
      "step": 54
    },
    {
      "epoch": 0.03006696733634003,
      "grad_norm": 0.5191702246665955,
      "learning_rate": 6.633071519742718e-05,
      "loss": 0.9669,
      "step": 55
    },
    {
      "epoch": 0.030613639469728032,
      "grad_norm": 0.37056273221969604,
      "learning_rate": 6.603707900720217e-05,
      "loss": 0.8109,
      "step": 56
    },
    {
      "epoch": 0.031160311603116032,
      "grad_norm": 0.3645178973674774,
      "learning_rate": 6.573284368292943e-05,
      "loss": 0.921,
      "step": 57
    },
    {
      "epoch": 0.03170698373650403,
      "grad_norm": 0.35407713055610657,
      "learning_rate": 6.541811312069348e-05,
      "loss": 0.8393,
      "step": 58
    },
    {
      "epoch": 0.03225365586989203,
      "grad_norm": 0.30585721135139465,
      "learning_rate": 6.509299480069303e-05,
      "loss": 0.8196,
      "step": 59
    },
    {
      "epoch": 0.03280032800328003,
      "grad_norm": 0.31569743156433105,
      "learning_rate": 6.47575997505365e-05,
      "loss": 0.9089,
      "step": 60
    },
    {
      "epoch": 0.03334700013666803,
      "grad_norm": 0.31442388892173767,
      "learning_rate": 6.441204250732624e-05,
      "loss": 0.7743,
      "step": 61
    },
    {
      "epoch": 0.03389367227005603,
      "grad_norm": 0.3461879789829254,
      "learning_rate": 6.405644107854427e-05,
      "loss": 0.8485,
      "step": 62
    },
    {
      "epoch": 0.03444034440344403,
      "grad_norm": 0.346314400434494,
      "learning_rate": 6.369091690175273e-05,
      "loss": 0.7661,
      "step": 63
    },
    {
      "epoch": 0.03498701653683203,
      "grad_norm": 0.3185812532901764,
      "learning_rate": 6.331559480312315e-05,
      "loss": 0.8583,
      "step": 64
    },
    {
      "epoch": 0.03553368867022003,
      "grad_norm": 0.3503943979740143,
      "learning_rate": 6.293060295480838e-05,
      "loss": 0.8725,
      "step": 65
    },
    {
      "epoch": 0.03608036080360803,
      "grad_norm": 0.3459616005420685,
      "learning_rate": 6.25360728311719e-05,
      "loss": 0.8382,
      "step": 66
    },
    {
      "epoch": 0.03662703293699603,
      "grad_norm": 0.38812822103500366,
      "learning_rate": 6.213213916388954e-05,
      "loss": 0.9174,
      "step": 67
    },
    {
      "epoch": 0.03717370507038404,
      "grad_norm": 0.37094104290008545,
      "learning_rate": 6.171893989593859e-05,
      "loss": 0.881,
      "step": 68
    },
    {
      "epoch": 0.03772037720377204,
      "grad_norm": 0.5786832571029663,
      "learning_rate": 6.129661613449057e-05,
      "loss": 0.9016,
      "step": 69
    },
    {
      "epoch": 0.03826704933716004,
      "grad_norm": 0.6645287871360779,
      "learning_rate": 6.086531210272306e-05,
      "loss": 0.965,
      "step": 70
    },
    {
      "epoch": 0.03881372147054804,
      "grad_norm": 0.43764594197273254,
      "learning_rate": 6.042517509056784e-05,
      "loss": 0.9049,
      "step": 71
    },
    {
      "epoch": 0.03936039360393604,
      "grad_norm": 0.34731465578079224,
      "learning_rate": 5.997635540441133e-05,
      "loss": 0.8948,
      "step": 72
    },
    {
      "epoch": 0.03990706573732404,
      "grad_norm": 0.40091952681541443,
      "learning_rate": 5.9519006315765176e-05,
      "loss": 0.8426,
      "step": 73
    },
    {
      "epoch": 0.04045373787071204,
      "grad_norm": 0.3977827727794647,
      "learning_rate": 5.9053284008924185e-05,
      "loss": 0.8352,
      "step": 74
    },
    {
      "epoch": 0.04100041000410004,
      "grad_norm": 0.4238167107105255,
      "learning_rate": 5.85793475276295e-05,
      "loss": 0.8615,
      "step": 75
    },
    {
      "epoch": 0.04154708213748804,
      "grad_norm": 0.46092405915260315,
      "learning_rate": 5.809735872075529e-05,
      "loss": 0.8255,
      "step": 76
    },
    {
      "epoch": 0.04209375427087604,
      "grad_norm": 0.4420395791530609,
      "learning_rate": 5.760748218703755e-05,
      "loss": 0.7647,
      "step": 77
    },
    {
      "epoch": 0.04264042640426404,
      "grad_norm": 0.4960534870624542,
      "learning_rate": 5.710988521886378e-05,
      "loss": 0.909,
      "step": 78
    },
    {
      "epoch": 0.04318709853765204,
      "grad_norm": 0.49868643283843994,
      "learning_rate": 5.660473774514275e-05,
      "loss": 0.7568,
      "step": 79
    },
    {
      "epoch": 0.04373377067104004,
      "grad_norm": 0.5315876603126526,
      "learning_rate": 5.6092212273273975e-05,
      "loss": 0.8924,
      "step": 80
    },
    {
      "epoch": 0.04428044280442804,
      "grad_norm": 0.5740758776664734,
      "learning_rate": 5.557248383023655e-05,
      "loss": 0.8379,
      "step": 81
    },
    {
      "epoch": 0.04482711493781605,
      "grad_norm": 0.613091766834259,
      "learning_rate": 5.5045729902817676e-05,
      "loss": 0.9659,
      "step": 82
    },
    {
      "epoch": 0.04537378707120405,
      "grad_norm": 0.6900278329849243,
      "learning_rate": 5.4512130377000987e-05,
      "loss": 0.9506,
      "step": 83
    },
    {
      "epoch": 0.04592045920459205,
      "grad_norm": 0.6675617694854736,
      "learning_rate": 5.397186747653573e-05,
      "loss": 0.9986,
      "step": 84
    },
    {
      "epoch": 0.04646713133798005,
      "grad_norm": 0.6233535408973694,
      "learning_rate": 5.342512570070745e-05,
      "loss": 0.9033,
      "step": 85
    },
    {
      "epoch": 0.04701380347136805,
      "grad_norm": 0.659621000289917,
      "learning_rate": 5.287209176133174e-05,
      "loss": 0.9068,
      "step": 86
    },
    {
      "epoch": 0.04756047560475605,
      "grad_norm": 0.759048342704773,
      "learning_rate": 5.231295451899226e-05,
      "loss": 0.9384,
      "step": 87
    },
    {
      "epoch": 0.04810714773814405,
      "grad_norm": 0.8321371078491211,
      "learning_rate": 5.174790491854502e-05,
      "loss": 1.0077,
      "step": 88
    },
    {
      "epoch": 0.04865381987153205,
      "grad_norm": 0.7181084156036377,
      "learning_rate": 5.117713592391096e-05,
      "loss": 1.0386,
      "step": 89
    },
    {
      "epoch": 0.04920049200492005,
      "grad_norm": 0.8390389084815979,
      "learning_rate": 5.060084245217884e-05,
      "loss": 1.0526,
      "step": 90
    },
    {
      "epoch": 0.04974716413830805,
      "grad_norm": 0.7568452954292297,
      "learning_rate": 5.0019221307041306e-05,
      "loss": 0.9571,
      "step": 91
    },
    {
      "epoch": 0.05029383627169605,
      "grad_norm": 1.033366322517395,
      "learning_rate": 4.943247111158662e-05,
      "loss": 0.9084,
      "step": 92
    },
    {
      "epoch": 0.05084050840508405,
      "grad_norm": 0.9008201360702515,
      "learning_rate": 4.884079224046898e-05,
      "loss": 0.8388,
      "step": 93
    },
    {
      "epoch": 0.05138718053847205,
      "grad_norm": 0.8567910194396973,
      "learning_rate": 4.824438675148086e-05,
      "loss": 0.9807,
      "step": 94
    },
    {
      "epoch": 0.05193385267186005,
      "grad_norm": 1.0424281358718872,
      "learning_rate": 4.764345831655036e-05,
      "loss": 1.0143,
      "step": 95
    },
    {
      "epoch": 0.05248052480524805,
      "grad_norm": 1.1355541944503784,
      "learning_rate": 4.703821215218748e-05,
      "loss": 0.9176,
      "step": 96
    },
    {
      "epoch": 0.053027196938636056,
      "grad_norm": 1.2170919179916382,
      "learning_rate": 4.642885494940291e-05,
      "loss": 0.8303,
      "step": 97
    },
    {
      "epoch": 0.053573869072024057,
      "grad_norm": 1.626427173614502,
      "learning_rate": 4.581559480312316e-05,
      "loss": 0.8297,
      "step": 98
    },
    {
      "epoch": 0.05412054120541206,
      "grad_norm": 1.3740547895431519,
      "learning_rate": 4.519864114112636e-05,
      "loss": 0.7661,
      "step": 99
    },
    {
      "epoch": 0.05466721333880006,
      "grad_norm": 2.6349620819091797,
      "learning_rate": 4.45782046525229e-05,
      "loss": 1.0357,
      "step": 100
    },
    {
      "epoch": 0.05466721333880006,
      "eval_loss": 0.8693193197250366,
      "eval_runtime": 94.6807,
      "eval_samples_per_second": 32.541,
      "eval_steps_per_second": 8.143,
      "step": 100
    },
    {
      "epoch": 0.05521388547218806,
      "grad_norm": 0.44926929473876953,
      "learning_rate": 4.3954497215805244e-05,
      "loss": 0.63,
      "step": 101
    },
    {
      "epoch": 0.05576055760557606,
      "grad_norm": 0.34577685594558716,
      "learning_rate": 4.332773182649165e-05,
      "loss": 0.6255,
      "step": 102
    },
    {
      "epoch": 0.05630722973896406,
      "grad_norm": 0.37551775574684143,
      "learning_rate": 4.2698122524388405e-05,
      "loss": 0.8668,
      "step": 103
    },
    {
      "epoch": 0.05685390187235206,
      "grad_norm": 0.3831069767475128,
      "learning_rate": 4.206588432049535e-05,
      "loss": 0.7327,
      "step": 104
    },
    {
      "epoch": 0.05740057400574006,
      "grad_norm": 0.368376761674881,
      "learning_rate": 4.143123312357996e-05,
      "loss": 0.7613,
      "step": 105
    },
    {
      "epoch": 0.05794724613912806,
      "grad_norm": 0.2958766222000122,
      "learning_rate": 4.079438566644454e-05,
      "loss": 0.8557,
      "step": 106
    },
    {
      "epoch": 0.05849391827251606,
      "grad_norm": 0.2869422137737274,
      "learning_rate": 4.015555943191231e-05,
      "loss": 0.8202,
      "step": 107
    },
    {
      "epoch": 0.05904059040590406,
      "grad_norm": 0.2743949890136719,
      "learning_rate": 3.9514972578557114e-05,
      "loss": 0.824,
      "step": 108
    },
    {
      "epoch": 0.05958726253929206,
      "grad_norm": 0.2857745289802551,
      "learning_rate": 3.8872843866202525e-05,
      "loss": 0.8618,
      "step": 109
    },
    {
      "epoch": 0.06013393467268006,
      "grad_norm": 0.2635364532470703,
      "learning_rate": 3.8229392581215565e-05,
      "loss": 0.7633,
      "step": 110
    },
    {
      "epoch": 0.06068060680606806,
      "grad_norm": 0.27216577529907227,
      "learning_rate": 3.7584838461620587e-05,
      "loss": 0.8427,
      "step": 111
    },
    {
      "epoch": 0.061227278939456065,
      "grad_norm": 0.28717127442359924,
      "learning_rate": 3.693940162205895e-05,
      "loss": 0.7745,
      "step": 112
    },
    {
      "epoch": 0.061773951072844065,
      "grad_norm": 0.2799830138683319,
      "learning_rate": 3.629330247862007e-05,
      "loss": 0.7972,
      "step": 113
    },
    {
      "epoch": 0.062320623206232065,
      "grad_norm": 0.3147888779640198,
      "learning_rate": 3.564676167356954e-05,
      "loss": 0.8222,
      "step": 114
    },
    {
      "epoch": 0.06286729533962006,
      "grad_norm": 0.30850040912628174,
      "learning_rate": 3.5e-05,
      "loss": 0.8039,
      "step": 115
    },
    {
      "epoch": 0.06341396747300806,
      "grad_norm": 0.3144112229347229,
      "learning_rate": 3.435323832643046e-05,
      "loss": 0.7823,
      "step": 116
    },
    {
      "epoch": 0.06396063960639606,
      "grad_norm": 0.3839268088340759,
      "learning_rate": 3.370669752137993e-05,
      "loss": 0.9132,
      "step": 117
    },
    {
      "epoch": 0.06450731173978407,
      "grad_norm": 0.37383535504341125,
      "learning_rate": 3.306059837794105e-05,
      "loss": 0.8359,
      "step": 118
    },
    {
      "epoch": 0.06505398387317206,
      "grad_norm": 0.42678016424179077,
      "learning_rate": 3.241516153837941e-05,
      "loss": 0.9635,
      "step": 119
    },
    {
      "epoch": 0.06560065600656007,
      "grad_norm": 0.478986918926239,
      "learning_rate": 3.177060741878443e-05,
      "loss": 0.8426,
      "step": 120
    },
    {
      "epoch": 0.06614732813994807,
      "grad_norm": 0.33792608976364136,
      "learning_rate": 3.1127156133797475e-05,
      "loss": 0.7594,
      "step": 121
    },
    {
      "epoch": 0.06669400027333607,
      "grad_norm": 0.401961088180542,
      "learning_rate": 3.048502742144289e-05,
      "loss": 0.9038,
      "step": 122
    },
    {
      "epoch": 0.06724067240672407,
      "grad_norm": 0.3711259067058563,
      "learning_rate": 2.984444056808768e-05,
      "loss": 0.8834,
      "step": 123
    },
    {
      "epoch": 0.06778734454011207,
      "grad_norm": 0.4284830689430237,
      "learning_rate": 2.9205614333555444e-05,
      "loss": 0.8564,
      "step": 124
    },
    {
      "epoch": 0.06833401667350007,
      "grad_norm": 0.4255787134170532,
      "learning_rate": 2.856876687642003e-05,
      "loss": 0.7818,
      "step": 125
    },
    {
      "epoch": 0.06888068880688807,
      "grad_norm": 0.4699144959449768,
      "learning_rate": 2.7934115679504645e-05,
      "loss": 0.8755,
      "step": 126
    },
    {
      "epoch": 0.06942736094027607,
      "grad_norm": 0.4922056198120117,
      "learning_rate": 2.7301877475611606e-05,
      "loss": 0.908,
      "step": 127
    },
    {
      "epoch": 0.06997403307366407,
      "grad_norm": 0.47387874126434326,
      "learning_rate": 2.667226817350835e-05,
      "loss": 0.9525,
      "step": 128
    },
    {
      "epoch": 0.07052070520705207,
      "grad_norm": 0.47072669863700867,
      "learning_rate": 2.604550278419475e-05,
      "loss": 0.8472,
      "step": 129
    },
    {
      "epoch": 0.07106737734044007,
      "grad_norm": 0.595217764377594,
      "learning_rate": 2.54217953474771e-05,
      "loss": 0.8562,
      "step": 130
    },
    {
      "epoch": 0.07161404947382807,
      "grad_norm": 0.585902214050293,
      "learning_rate": 2.4801358858873636e-05,
      "loss": 0.8419,
      "step": 131
    },
    {
      "epoch": 0.07216072160721607,
      "grad_norm": 0.6359130144119263,
      "learning_rate": 2.4184405196876842e-05,
      "loss": 0.8576,
      "step": 132
    },
    {
      "epoch": 0.07270739374060407,
      "grad_norm": 0.532152533531189,
      "learning_rate": 2.3571145050597088e-05,
      "loss": 0.8793,
      "step": 133
    },
    {
      "epoch": 0.07325406587399207,
      "grad_norm": 0.6238685250282288,
      "learning_rate": 2.296178784781251e-05,
      "loss": 0.8179,
      "step": 134
    },
    {
      "epoch": 0.07380073800738007,
      "grad_norm": 0.7119914889335632,
      "learning_rate": 2.2356541683449646e-05,
      "loss": 0.9274,
      "step": 135
    },
    {
      "epoch": 0.07434741014076808,
      "grad_norm": 0.7729023694992065,
      "learning_rate": 2.175561324851914e-05,
      "loss": 1.088,
      "step": 136
    },
    {
      "epoch": 0.07489408227415607,
      "grad_norm": 0.7109841108322144,
      "learning_rate": 2.1159207759531013e-05,
      "loss": 0.9875,
      "step": 137
    },
    {
      "epoch": 0.07544075440754408,
      "grad_norm": 0.6977630257606506,
      "learning_rate": 2.0567528888413382e-05,
      "loss": 0.8897,
      "step": 138
    },
    {
      "epoch": 0.07598742654093207,
      "grad_norm": 0.7141391038894653,
      "learning_rate": 1.9980778692958684e-05,
      "loss": 0.9585,
      "step": 139
    },
    {
      "epoch": 0.07653409867432008,
      "grad_norm": 0.7913526296615601,
      "learning_rate": 1.9399157547821162e-05,
      "loss": 0.8552,
      "step": 140
    },
    {
      "epoch": 0.07708077080770807,
      "grad_norm": 0.9253504276275635,
      "learning_rate": 1.882286407608904e-05,
      "loss": 0.88,
      "step": 141
    },
    {
      "epoch": 0.07762744294109608,
      "grad_norm": 1.1985421180725098,
      "learning_rate": 1.825209508145497e-05,
      "loss": 0.9832,
      "step": 142
    },
    {
      "epoch": 0.07817411507448407,
      "grad_norm": 0.9133749008178711,
      "learning_rate": 1.7687045481007746e-05,
      "loss": 0.8496,
      "step": 143
    },
    {
      "epoch": 0.07872078720787208,
      "grad_norm": 1.0693060159683228,
      "learning_rate": 1.712790823866826e-05,
      "loss": 0.9679,
      "step": 144
    },
    {
      "epoch": 0.07926745934126007,
      "grad_norm": 1.4201616048812866,
      "learning_rate": 1.657487429929254e-05,
      "loss": 0.9618,
      "step": 145
    },
    {
      "epoch": 0.07981413147464808,
      "grad_norm": 1.446235179901123,
      "learning_rate": 1.602813252346427e-05,
      "loss": 0.9855,
      "step": 146
    },
    {
      "epoch": 0.08036080360803607,
      "grad_norm": 1.2012956142425537,
      "learning_rate": 1.5487869622999004e-05,
      "loss": 0.8761,
      "step": 147
    },
    {
      "epoch": 0.08090747574142408,
      "grad_norm": 1.4860199689865112,
      "learning_rate": 1.4954270097182317e-05,
      "loss": 0.8868,
      "step": 148
    },
    {
      "epoch": 0.08145414787481207,
      "grad_norm": 1.4566800594329834,
      "learning_rate": 1.4427516169763444e-05,
      "loss": 0.8158,
      "step": 149
    },
    {
      "epoch": 0.08200082000820008,
      "grad_norm": 2.238769769668579,
      "learning_rate": 1.3907787726726029e-05,
      "loss": 0.9074,
      "step": 150
    },
    {
      "epoch": 0.08200082000820008,
      "eval_loss": 0.8439501523971558,
      "eval_runtime": 94.8117,
      "eval_samples_per_second": 32.496,
      "eval_steps_per_second": 8.132,
      "step": 150
    },
    {
      "epoch": 0.08254749214158809,
      "grad_norm": 0.21387195587158203,
      "learning_rate": 1.339526225485725e-05,
      "loss": 0.5987,
      "step": 151
    },
    {
      "epoch": 0.08309416427497608,
      "grad_norm": 0.21969622373580933,
      "learning_rate": 1.2890114781136224e-05,
      "loss": 0.701,
      "step": 152
    },
    {
      "epoch": 0.08364083640836409,
      "grad_norm": 0.23904825747013092,
      "learning_rate": 1.239251781296245e-05,
      "loss": 0.7627,
      "step": 153
    },
    {
      "epoch": 0.08418750854175208,
      "grad_norm": 0.25487756729125977,
      "learning_rate": 1.1902641279244715e-05,
      "loss": 0.7506,
      "step": 154
    },
    {
      "epoch": 0.08473418067514009,
      "grad_norm": 0.2533106207847595,
      "learning_rate": 1.1420652472370497e-05,
      "loss": 0.7238,
      "step": 155
    },
    {
      "epoch": 0.08528085280852808,
      "grad_norm": 0.2788962423801422,
      "learning_rate": 1.0946715991075805e-05,
      "loss": 0.8004,
      "step": 156
    },
    {
      "epoch": 0.08582752494191609,
      "grad_norm": 0.2542433738708496,
      "learning_rate": 1.0480993684234815e-05,
      "loss": 0.7999,
      "step": 157
    },
    {
      "epoch": 0.08637419707530408,
      "grad_norm": 0.2701437175273895,
      "learning_rate": 1.0023644595588671e-05,
      "loss": 0.7623,
      "step": 158
    },
    {
      "epoch": 0.08692086920869209,
      "grad_norm": 0.2716737389564514,
      "learning_rate": 9.57482490943216e-06,
      "loss": 0.8127,
      "step": 159
    },
    {
      "epoch": 0.08746754134208008,
      "grad_norm": 0.28511807322502136,
      "learning_rate": 9.134687897276934e-06,
      "loss": 0.8619,
      "step": 160
    },
    {
      "epoch": 0.08801421347546809,
      "grad_norm": 0.32100751996040344,
      "learning_rate": 8.703383865509432e-06,
      "loss": 0.8368,
      "step": 161
    },
    {
      "epoch": 0.08856088560885608,
      "grad_norm": 0.27488431334495544,
      "learning_rate": 8.281060104061394e-06,
      "loss": 0.7795,
      "step": 162
    },
    {
      "epoch": 0.08910755774224409,
      "grad_norm": 0.2900071442127228,
      "learning_rate": 7.867860836110453e-06,
      "loss": 0.8229,
      "step": 163
    },
    {
      "epoch": 0.0896542298756321,
      "grad_norm": 0.3044150471687317,
      "learning_rate": 7.463927168828087e-06,
      "loss": 0.8705,
      "step": 164
    },
    {
      "epoch": 0.09020090200902009,
      "grad_norm": 0.34009850025177,
      "learning_rate": 7.069397045191617e-06,
      "loss": 0.9019,
      "step": 165
    },
    {
      "epoch": 0.0907475741424081,
      "grad_norm": 0.33406728506088257,
      "learning_rate": 6.684405196876842e-06,
      "loss": 0.7769,
      "step": 166
    },
    {
      "epoch": 0.09129424627579609,
      "grad_norm": 0.35519149899482727,
      "learning_rate": 6.309083098247264e-06,
      "loss": 0.8062,
      "step": 167
    },
    {
      "epoch": 0.0918409184091841,
      "grad_norm": 0.33212265372276306,
      "learning_rate": 5.943558921455733e-06,
      "loss": 0.7822,
      "step": 168
    },
    {
      "epoch": 0.09238759054257209,
      "grad_norm": 0.3488451838493347,
      "learning_rate": 5.587957492673759e-06,
      "loss": 0.7944,
      "step": 169
    },
    {
      "epoch": 0.0929342626759601,
      "grad_norm": 0.4000808298587799,
      "learning_rate": 5.2424002494635095e-06,
      "loss": 0.823,
      "step": 170
    },
    {
      "epoch": 0.09348093480934809,
      "grad_norm": 0.37309879064559937,
      "learning_rate": 4.9070051993069636e-06,
      "loss": 0.8506,
      "step": 171
    },
    {
      "epoch": 0.0940276069427361,
      "grad_norm": 0.3660164773464203,
      "learning_rate": 4.581886879306507e-06,
      "loss": 0.8042,
      "step": 172
    },
    {
      "epoch": 0.09457427907612409,
      "grad_norm": 0.389154851436615,
      "learning_rate": 4.2671563170705725e-06,
      "loss": 0.9166,
      "step": 173
    },
    {
      "epoch": 0.0951209512095121,
      "grad_norm": 0.3975100815296173,
      "learning_rate": 3.962920992797834e-06,
      "loss": 0.7654,
      "step": 174
    },
    {
      "epoch": 0.09566762334290009,
      "grad_norm": 0.4443868100643158,
      "learning_rate": 3.6692848025728216e-06,
      "loss": 0.8351,
      "step": 175
    },
    {
      "epoch": 0.0962142954762881,
      "grad_norm": 0.4617209732532501,
      "learning_rate": 3.38634802288549e-06,
      "loss": 0.8746,
      "step": 176
    },
    {
      "epoch": 0.09676096760967609,
      "grad_norm": 0.4271644651889801,
      "learning_rate": 3.1142072763869042e-06,
      "loss": 0.7862,
      "step": 177
    },
    {
      "epoch": 0.0973076397430641,
      "grad_norm": 0.5230273604393005,
      "learning_rate": 2.852955498892694e-06,
      "loss": 0.7907,
      "step": 178
    },
    {
      "epoch": 0.0978543118764521,
      "grad_norm": 0.49080246686935425,
      "learning_rate": 2.6026819076455325e-06,
      "loss": 0.8707,
      "step": 179
    },
    {
      "epoch": 0.0984009840098401,
      "grad_norm": 0.524896502494812,
      "learning_rate": 2.36347197084755e-06,
      "loss": 0.8869,
      "step": 180
    },
    {
      "epoch": 0.0989476561432281,
      "grad_norm": 0.5297053456306458,
      "learning_rate": 2.1354073784730253e-06,
      "loss": 0.855,
      "step": 181
    },
    {
      "epoch": 0.0994943282766161,
      "grad_norm": 0.6338819265365601,
      "learning_rate": 1.9185660143713184e-06,
      "loss": 1.0045,
      "step": 182
    },
    {
      "epoch": 0.1000410004100041,
      "grad_norm": 0.6989834308624268,
      "learning_rate": 1.7130219296696263e-06,
      "loss": 0.9497,
      "step": 183
    },
    {
      "epoch": 0.1005876725433921,
      "grad_norm": 0.602967381477356,
      "learning_rate": 1.5188453174845743e-06,
      "loss": 0.8483,
      "step": 184
    },
    {
      "epoch": 0.1011343446767801,
      "grad_norm": 0.7088273763656616,
      "learning_rate": 1.3361024889513333e-06,
      "loss": 0.846,
      "step": 185
    },
    {
      "epoch": 0.1016810168101681,
      "grad_norm": 0.7697593569755554,
      "learning_rate": 1.16485585057844e-06,
      "loss": 0.9718,
      "step": 186
    },
    {
      "epoch": 0.1022276889435561,
      "grad_norm": 0.6648566722869873,
      "learning_rate": 1.0051638829360127e-06,
      "loss": 0.9544,
      "step": 187
    },
    {
      "epoch": 0.1027743610769441,
      "grad_norm": 0.8641712069511414,
      "learning_rate": 8.570811206847189e-07,
      "loss": 0.9615,
      "step": 188
    },
    {
      "epoch": 0.1033210332103321,
      "grad_norm": 0.8209101557731628,
      "learning_rate": 7.206581339521939e-07,
      "loss": 0.9253,
      "step": 189
    },
    {
      "epoch": 0.1038677053437201,
      "grad_norm": 0.7885981202125549,
      "learning_rate": 5.959415110634375e-07,
      "loss": 0.9993,
      "step": 190
    },
    {
      "epoch": 0.1044143774771081,
      "grad_norm": 0.8673349022865295,
      "learning_rate": 4.829738426309099e-07,
      "loss": 0.8788,
      "step": 191
    },
    {
      "epoch": 0.1049610496104961,
      "grad_norm": 1.1715073585510254,
      "learning_rate": 3.817937070098914e-07,
      "loss": 0.9042,
      "step": 192
    },
    {
      "epoch": 0.1055077217438841,
      "grad_norm": 0.8940293192863464,
      "learning_rate": 2.9243565712400384e-07,
      "loss": 0.9155,
      "step": 193
    },
    {
      "epoch": 0.10605439387727211,
      "grad_norm": 1.1870354413986206,
      "learning_rate": 2.1493020866542365e-07,
      "loss": 0.7754,
      "step": 194
    },
    {
      "epoch": 0.1066010660106601,
      "grad_norm": 1.0665806531906128,
      "learning_rate": 1.4930382967379363e-07,
      "loss": 0.7945,
      "step": 195
    },
    {
      "epoch": 0.10714773814404811,
      "grad_norm": 1.1132820844650269,
      "learning_rate": 9.557893149741924e-08,
      "loss": 0.8022,
      "step": 196
    },
    {
      "epoch": 0.1076944102774361,
      "grad_norm": 1.1399116516113281,
      "learning_rate": 5.377386113981197e-08,
      "loss": 0.7458,
      "step": 197
    },
    {
      "epoch": 0.10824108241082411,
      "grad_norm": 1.4629731178283691,
      "learning_rate": 2.3902894994198286e-08,
      "loss": 0.8933,
      "step": 198
    },
    {
      "epoch": 0.1087877545442121,
      "grad_norm": 2.013901710510254,
      "learning_rate": 5.976233968155164e-09,
      "loss": 1.116,
      "step": 199
    },
    {
      "epoch": 0.10933442667760011,
      "grad_norm": 2.5633609294891357,
      "learning_rate": 0.0,
      "loss": 0.9893,
      "step": 200
    },
    {
      "epoch": 0.10933442667760011,
      "eval_loss": 0.8386966586112976,
      "eval_runtime": 94.776,
      "eval_samples_per_second": 32.508,
      "eval_steps_per_second": 8.135,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.813079334767821e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}