{
  "best_metric": 1.429347276687622,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.11825572801182557,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005912786400591279,
      "grad_norm": 0.9726289510726929,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.4873,
      "step": 1
    },
    {
      "epoch": 0.0005912786400591279,
      "eval_loss": 1.8040848970413208,
      "eval_runtime": 237.2932,
      "eval_samples_per_second": 12.006,
      "eval_steps_per_second": 6.005,
      "step": 1
    },
    {
      "epoch": 0.0011825572801182557,
      "grad_norm": 0.9772027134895325,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.2319,
      "step": 2
    },
    {
      "epoch": 0.0017738359201773836,
      "grad_norm": 1.1119064092636108,
      "learning_rate": 1e-05,
      "loss": 1.1924,
      "step": 3
    },
    {
      "epoch": 0.0023651145602365115,
      "grad_norm": 1.0203392505645752,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.0968,
      "step": 4
    },
    {
      "epoch": 0.0029563932002956393,
      "grad_norm": 1.0077756643295288,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.28,
      "step": 5
    },
    {
      "epoch": 0.003547671840354767,
      "grad_norm": 1.048666000366211,
      "learning_rate": 2e-05,
      "loss": 1.2347,
      "step": 6
    },
    {
      "epoch": 0.004138950480413895,
      "grad_norm": 1.0571691989898682,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 1.3182,
      "step": 7
    },
    {
      "epoch": 0.004730229120473023,
      "grad_norm": 0.7537508606910706,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.9406,
      "step": 8
    },
    {
      "epoch": 0.005321507760532151,
      "grad_norm": 0.8735187649726868,
      "learning_rate": 3e-05,
      "loss": 1.2131,
      "step": 9
    },
    {
      "epoch": 0.005912786400591279,
      "grad_norm": 0.7849937081336975,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.1487,
      "step": 10
    },
    {
      "epoch": 0.0065040650406504065,
      "grad_norm": 0.6883115768432617,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 1.0974,
      "step": 11
    },
    {
      "epoch": 0.007095343680709534,
      "grad_norm": 0.7022745013237,
      "learning_rate": 4e-05,
      "loss": 1.1683,
      "step": 12
    },
    {
      "epoch": 0.007686622320768662,
      "grad_norm": 0.7865653038024902,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 1.1794,
      "step": 13
    },
    {
      "epoch": 0.00827790096082779,
      "grad_norm": 0.8761787414550781,
      "learning_rate": 4.666666666666667e-05,
      "loss": 1.2902,
      "step": 14
    },
    {
      "epoch": 0.008869179600886918,
      "grad_norm": 0.8201810717582703,
      "learning_rate": 5e-05,
      "loss": 1.2349,
      "step": 15
    },
    {
      "epoch": 0.009460458240946046,
      "grad_norm": 0.7110611796379089,
      "learning_rate": 5.333333333333333e-05,
      "loss": 1.2526,
      "step": 16
    },
    {
      "epoch": 0.010051736881005174,
      "grad_norm": 0.634364902973175,
      "learning_rate": 5.666666666666667e-05,
      "loss": 1.2653,
      "step": 17
    },
    {
      "epoch": 0.010643015521064302,
      "grad_norm": 0.7168411612510681,
      "learning_rate": 6e-05,
      "loss": 1.2168,
      "step": 18
    },
    {
      "epoch": 0.01123429416112343,
      "grad_norm": 0.6394386291503906,
      "learning_rate": 6.333333333333333e-05,
      "loss": 1.28,
      "step": 19
    },
    {
      "epoch": 0.011825572801182557,
      "grad_norm": 0.6675559878349304,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.3341,
      "step": 20
    },
    {
      "epoch": 0.012416851441241685,
      "grad_norm": 0.7060176134109497,
      "learning_rate": 7e-05,
      "loss": 1.3246,
      "step": 21
    },
    {
      "epoch": 0.013008130081300813,
      "grad_norm": 0.8127558827400208,
      "learning_rate": 7.333333333333333e-05,
      "loss": 1.4198,
      "step": 22
    },
    {
      "epoch": 0.01359940872135994,
      "grad_norm": 0.7225644588470459,
      "learning_rate": 7.666666666666667e-05,
      "loss": 1.2954,
      "step": 23
    },
    {
      "epoch": 0.014190687361419069,
      "grad_norm": 0.6734681725502014,
      "learning_rate": 8e-05,
      "loss": 1.2682,
      "step": 24
    },
    {
      "epoch": 0.014781966001478197,
      "grad_norm": 0.815269947052002,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.5616,
      "step": 25
    },
    {
      "epoch": 0.015373244641537324,
      "grad_norm": 0.7292295098304749,
      "learning_rate": 8.666666666666667e-05,
      "loss": 1.5186,
      "step": 26
    },
    {
      "epoch": 0.015964523281596452,
      "grad_norm": 0.7140643000602722,
      "learning_rate": 9e-05,
      "loss": 1.3804,
      "step": 27
    },
    {
      "epoch": 0.01655580192165558,
      "grad_norm": 0.7823128700256348,
      "learning_rate": 9.333333333333334e-05,
      "loss": 1.4618,
      "step": 28
    },
    {
      "epoch": 0.017147080561714708,
      "grad_norm": 0.7901281118392944,
      "learning_rate": 9.666666666666667e-05,
      "loss": 1.431,
      "step": 29
    },
    {
      "epoch": 0.017738359201773836,
      "grad_norm": 0.8098665475845337,
      "learning_rate": 0.0001,
      "loss": 1.4555,
      "step": 30
    },
    {
      "epoch": 0.018329637841832964,
      "grad_norm": 0.7486283779144287,
      "learning_rate": 9.999146252290264e-05,
      "loss": 1.4853,
      "step": 31
    },
    {
      "epoch": 0.01892091648189209,
      "grad_norm": 0.8610166907310486,
      "learning_rate": 9.996585300715116e-05,
      "loss": 1.606,
      "step": 32
    },
    {
      "epoch": 0.01951219512195122,
      "grad_norm": 0.7736566066741943,
      "learning_rate": 9.99231801983717e-05,
      "loss": 1.3497,
      "step": 33
    },
    {
      "epoch": 0.020103473762010347,
      "grad_norm": 0.8386912941932678,
      "learning_rate": 9.986345866928941e-05,
      "loss": 1.4455,
      "step": 34
    },
    {
      "epoch": 0.020694752402069475,
      "grad_norm": 0.9145824909210205,
      "learning_rate": 9.978670881475172e-05,
      "loss": 1.7299,
      "step": 35
    },
    {
      "epoch": 0.021286031042128603,
      "grad_norm": 0.9461202025413513,
      "learning_rate": 9.96929568447637e-05,
      "loss": 1.6947,
      "step": 36
    },
    {
      "epoch": 0.02187730968218773,
      "grad_norm": 0.9634538888931274,
      "learning_rate": 9.958223477553714e-05,
      "loss": 1.86,
      "step": 37
    },
    {
      "epoch": 0.02246858832224686,
      "grad_norm": 0.9322118759155273,
      "learning_rate": 9.94545804185573e-05,
      "loss": 1.8198,
      "step": 38
    },
    {
      "epoch": 0.023059866962305987,
      "grad_norm": 0.9747868180274963,
      "learning_rate": 9.931003736767013e-05,
      "loss": 1.9704,
      "step": 39
    },
    {
      "epoch": 0.023651145602365115,
      "grad_norm": 0.9679445624351501,
      "learning_rate": 9.91486549841951e-05,
      "loss": 1.9984,
      "step": 40
    },
    {
      "epoch": 0.024242424242424242,
      "grad_norm": 1.168147087097168,
      "learning_rate": 9.89704883800683e-05,
      "loss": 1.7387,
      "step": 41
    },
    {
      "epoch": 0.02483370288248337,
      "grad_norm": 0.9986356496810913,
      "learning_rate": 9.877559839902184e-05,
      "loss": 1.8842,
      "step": 42
    },
    {
      "epoch": 0.025424981522542498,
      "grad_norm": 1.2003281116485596,
      "learning_rate": 9.85640515958057e-05,
      "loss": 1.9681,
      "step": 43
    },
    {
      "epoch": 0.026016260162601626,
      "grad_norm": 1.135547399520874,
      "learning_rate": 9.833592021345937e-05,
      "loss": 2.0643,
      "step": 44
    },
    {
      "epoch": 0.026607538802660754,
      "grad_norm": 1.413825511932373,
      "learning_rate": 9.809128215864097e-05,
      "loss": 2.184,
      "step": 45
    },
    {
      "epoch": 0.02719881744271988,
      "grad_norm": 1.2450569868087769,
      "learning_rate": 9.783022097502204e-05,
      "loss": 1.9967,
      "step": 46
    },
    {
      "epoch": 0.02779009608277901,
      "grad_norm": 1.3000105619430542,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.0032,
      "step": 47
    },
    {
      "epoch": 0.028381374722838137,
      "grad_norm": 1.388758659362793,
      "learning_rate": 9.725919140804099e-05,
      "loss": 2.1693,
      "step": 48
    },
    {
      "epoch": 0.028972653362897265,
      "grad_norm": 1.5098059177398682,
      "learning_rate": 9.694941803075283e-05,
      "loss": 2.0612,
      "step": 49
    },
    {
      "epoch": 0.029563932002956393,
      "grad_norm": 1.8700934648513794,
      "learning_rate": 9.662361147021779e-05,
      "loss": 1.9784,
      "step": 50
    },
    {
      "epoch": 0.029563932002956393,
      "eval_loss": 1.555537223815918,
      "eval_runtime": 238.9307,
      "eval_samples_per_second": 11.924,
      "eval_steps_per_second": 5.964,
      "step": 50
    },
    {
      "epoch": 0.03015521064301552,
      "grad_norm": 1.1767340898513794,
      "learning_rate": 9.628188298907782e-05,
      "loss": 1.5257,
      "step": 51
    },
    {
      "epoch": 0.03074648928307465,
      "grad_norm": 0.8743080496788025,
      "learning_rate": 9.592434928729616e-05,
      "loss": 1.1786,
      "step": 52
    },
    {
      "epoch": 0.03133776792313378,
      "grad_norm": 0.7236108779907227,
      "learning_rate": 9.555113246230442e-05,
      "loss": 1.1467,
      "step": 53
    },
    {
      "epoch": 0.031929046563192905,
      "grad_norm": 0.5204956531524658,
      "learning_rate": 9.516235996730645e-05,
      "loss": 0.9421,
      "step": 54
    },
    {
      "epoch": 0.032520325203252036,
      "grad_norm": 0.4584566056728363,
      "learning_rate": 9.475816456775313e-05,
      "loss": 1.1128,
      "step": 55
    },
    {
      "epoch": 0.03311160384331116,
      "grad_norm": 0.4526122510433197,
      "learning_rate": 9.43386842960031e-05,
      "loss": 1.0164,
      "step": 56
    },
    {
      "epoch": 0.03370288248337029,
      "grad_norm": 0.4665258228778839,
      "learning_rate": 9.39040624041849e-05,
      "loss": 1.0138,
      "step": 57
    },
    {
      "epoch": 0.034294161123429416,
      "grad_norm": 0.465076744556427,
      "learning_rate": 9.345444731527642e-05,
      "loss": 1.0276,
      "step": 58
    },
    {
      "epoch": 0.03488543976348855,
      "grad_norm": 0.527400553226471,
      "learning_rate": 9.298999257241863e-05,
      "loss": 1.1934,
      "step": 59
    },
    {
      "epoch": 0.03547671840354767,
      "grad_norm": 0.49932149052619934,
      "learning_rate": 9.251085678648072e-05,
      "loss": 1.1936,
      "step": 60
    },
    {
      "epoch": 0.0360679970436068,
      "grad_norm": 0.4894202947616577,
      "learning_rate": 9.201720358189464e-05,
      "loss": 1.294,
      "step": 61
    },
    {
      "epoch": 0.03665927568366593,
      "grad_norm": 0.49566730856895447,
      "learning_rate": 9.150920154077754e-05,
      "loss": 1.1933,
      "step": 62
    },
    {
      "epoch": 0.03725055432372506,
      "grad_norm": 0.5004077553749084,
      "learning_rate": 9.098702414536107e-05,
      "loss": 0.9939,
      "step": 63
    },
    {
      "epoch": 0.03784183296378418,
      "grad_norm": 0.537868320941925,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.196,
      "step": 64
    },
    {
      "epoch": 0.038433111603843315,
      "grad_norm": 0.49859926104545593,
      "learning_rate": 8.9900861364012e-05,
      "loss": 1.2272,
      "step": 65
    },
    {
      "epoch": 0.03902439024390244,
      "grad_norm": 0.5565657019615173,
      "learning_rate": 8.933724690167417e-05,
      "loss": 1.0484,
      "step": 66
    },
    {
      "epoch": 0.03961566888396157,
      "grad_norm": 0.49499908089637756,
      "learning_rate": 8.876019880555649e-05,
      "loss": 1.2345,
      "step": 67
    },
    {
      "epoch": 0.040206947524020695,
      "grad_norm": 0.5242329835891724,
      "learning_rate": 8.816991413705516e-05,
      "loss": 1.3664,
      "step": 68
    },
    {
      "epoch": 0.040798226164079826,
      "grad_norm": 0.5149632692337036,
      "learning_rate": 8.756659447784368e-05,
      "loss": 1.2817,
      "step": 69
    },
    {
      "epoch": 0.04138950480413895,
      "grad_norm": 0.51432204246521,
      "learning_rate": 8.695044586103296e-05,
      "loss": 1.2525,
      "step": 70
    },
    {
      "epoch": 0.04198078344419808,
      "grad_norm": 0.5460650324821472,
      "learning_rate": 8.632167870081121e-05,
      "loss": 1.2673,
      "step": 71
    },
    {
      "epoch": 0.042572062084257206,
      "grad_norm": 0.6104385256767273,
      "learning_rate": 8.568050772058762e-05,
      "loss": 1.3757,
      "step": 72
    },
    {
      "epoch": 0.04316334072431634,
      "grad_norm": 0.5687586069107056,
      "learning_rate": 8.502715187966455e-05,
      "loss": 1.2904,
      "step": 73
    },
    {
      "epoch": 0.04375461936437546,
      "grad_norm": 0.5552237629890442,
      "learning_rate": 8.436183429846313e-05,
      "loss": 1.2907,
      "step": 74
    },
    {
      "epoch": 0.04434589800443459,
      "grad_norm": 0.5990892648696899,
      "learning_rate": 8.368478218232787e-05,
      "loss": 1.3684,
      "step": 75
    },
    {
      "epoch": 0.04493717664449372,
      "grad_norm": 0.6610813140869141,
      "learning_rate": 8.299622674393614e-05,
      "loss": 1.5621,
      "step": 76
    },
    {
      "epoch": 0.04552845528455285,
      "grad_norm": 0.6220623850822449,
      "learning_rate": 8.229640312433937e-05,
      "loss": 1.4063,
      "step": 77
    },
    {
      "epoch": 0.04611973392461197,
      "grad_norm": 0.692918598651886,
      "learning_rate": 8.158555031266254e-05,
      "loss": 1.4554,
      "step": 78
    },
    {
      "epoch": 0.046711012564671105,
      "grad_norm": 0.6769721508026123,
      "learning_rate": 8.086391106448965e-05,
      "loss": 1.5272,
      "step": 79
    },
    {
      "epoch": 0.04730229120473023,
      "grad_norm": 0.704415500164032,
      "learning_rate": 8.013173181896283e-05,
      "loss": 1.5395,
      "step": 80
    },
    {
      "epoch": 0.04789356984478936,
      "grad_norm": 0.6997012495994568,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.6002,
      "step": 81
    },
    {
      "epoch": 0.048484848484848485,
      "grad_norm": 0.7182490825653076,
      "learning_rate": 7.863675700402526e-05,
      "loss": 1.6381,
      "step": 82
    },
    {
      "epoch": 0.049076127124907616,
      "grad_norm": 0.7177379727363586,
      "learning_rate": 7.787447196714427e-05,
      "loss": 1.6261,
      "step": 83
    },
    {
      "epoch": 0.04966740576496674,
      "grad_norm": 0.8007391095161438,
      "learning_rate": 7.710266782362247e-05,
      "loss": 1.657,
      "step": 84
    },
    {
      "epoch": 0.05025868440502587,
      "grad_norm": 0.7926273941993713,
      "learning_rate": 7.63216081438678e-05,
      "loss": 1.6578,
      "step": 85
    },
    {
      "epoch": 0.050849963045084996,
      "grad_norm": 0.8020119667053223,
      "learning_rate": 7.553155965904535e-05,
      "loss": 1.6819,
      "step": 86
    },
    {
      "epoch": 0.05144124168514413,
      "grad_norm": 0.8183744549751282,
      "learning_rate": 7.473279216998895e-05,
      "loss": 1.7629,
      "step": 87
    },
    {
      "epoch": 0.05203252032520325,
      "grad_norm": 0.9529420733451843,
      "learning_rate": 7.392557845506432e-05,
      "loss": 1.7812,
      "step": 88
    },
    {
      "epoch": 0.05262379896526238,
      "grad_norm": 0.9576981663703918,
      "learning_rate": 7.311019417701566e-05,
      "loss": 1.8943,
      "step": 89
    },
    {
      "epoch": 0.05321507760532151,
      "grad_norm": 0.9187182784080505,
      "learning_rate": 7.228691778882693e-05,
      "loss": 1.8159,
      "step": 90
    },
    {
      "epoch": 0.05380635624538064,
      "grad_norm": 0.8962719440460205,
      "learning_rate": 7.145603043863045e-05,
      "loss": 1.7825,
      "step": 91
    },
    {
      "epoch": 0.05439763488543976,
      "grad_norm": 1.0772016048431396,
      "learning_rate": 7.061781587369519e-05,
      "loss": 2.2153,
      "step": 92
    },
    {
      "epoch": 0.054988913525498895,
      "grad_norm": 0.9609599709510803,
      "learning_rate": 6.977256034352712e-05,
      "loss": 1.8156,
      "step": 93
    },
    {
      "epoch": 0.05558019216555802,
      "grad_norm": 0.9851707816123962,
      "learning_rate": 6.892055250211552e-05,
      "loss": 1.8342,
      "step": 94
    },
    {
      "epoch": 0.05617147080561715,
      "grad_norm": 1.048850178718567,
      "learning_rate": 6.806208330935766e-05,
      "loss": 2.1506,
      "step": 95
    },
    {
      "epoch": 0.056762749445676275,
      "grad_norm": 1.2707563638687134,
      "learning_rate": 6.719744593169641e-05,
      "loss": 2.2091,
      "step": 96
    },
    {
      "epoch": 0.057354028085735406,
      "grad_norm": 1.1597068309783936,
      "learning_rate": 6.632693564200416e-05,
      "loss": 1.9979,
      "step": 97
    },
    {
      "epoch": 0.05794530672579453,
      "grad_norm": 1.3379724025726318,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.2064,
      "step": 98
    },
    {
      "epoch": 0.05853658536585366,
      "grad_norm": 1.2999430894851685,
      "learning_rate": 6.456948734446624e-05,
      "loss": 2.262,
      "step": 99
    },
    {
      "epoch": 0.059127864005912786,
      "grad_norm": 1.5316917896270752,
      "learning_rate": 6.368314950360415e-05,
      "loss": 2.2301,
      "step": 100
    },
    {
      "epoch": 0.059127864005912786,
      "eval_loss": 1.5102187395095825,
      "eval_runtime": 238.8457,
      "eval_samples_per_second": 11.928,
      "eval_steps_per_second": 5.966,
      "step": 100
    },
    {
      "epoch": 0.05971914264597192,
      "grad_norm": 0.6291592717170715,
      "learning_rate": 6.279213887972179e-05,
      "loss": 1.2329,
      "step": 101
    },
    {
      "epoch": 0.06031042128603104,
      "grad_norm": 0.6495620012283325,
      "learning_rate": 6.189675975213094e-05,
      "loss": 1.1084,
      "step": 102
    },
    {
      "epoch": 0.06090169992609017,
      "grad_norm": 0.6183136701583862,
      "learning_rate": 6.099731789198344e-05,
      "loss": 1.1053,
      "step": 103
    },
    {
      "epoch": 0.0614929785661493,
      "grad_norm": 0.49170196056365967,
      "learning_rate": 6.009412045785051e-05,
      "loss": 1.1741,
      "step": 104
    },
    {
      "epoch": 0.06208425720620843,
      "grad_norm": 0.4875796139240265,
      "learning_rate": 5.918747589082853e-05,
      "loss": 1.1359,
      "step": 105
    },
    {
      "epoch": 0.06267553584626756,
      "grad_norm": 0.42337316274642944,
      "learning_rate": 5.82776938092065e-05,
      "loss": 0.9936,
      "step": 106
    },
    {
      "epoch": 0.06326681448632668,
      "grad_norm": 0.4198471009731293,
      "learning_rate": 5.736508490273188e-05,
      "loss": 1.0373,
      "step": 107
    },
    {
      "epoch": 0.06385809312638581,
      "grad_norm": 0.3972650468349457,
      "learning_rate": 5.644996082651017e-05,
      "loss": 1.0443,
      "step": 108
    },
    {
      "epoch": 0.06444937176644494,
      "grad_norm": 0.4315491318702698,
      "learning_rate": 5.553263409457504e-05,
      "loss": 1.0413,
      "step": 109
    },
    {
      "epoch": 0.06504065040650407,
      "grad_norm": 0.4730534553527832,
      "learning_rate": 5.4613417973165106e-05,
      "loss": 1.1193,
      "step": 110
    },
    {
      "epoch": 0.06563192904656319,
      "grad_norm": 0.497887521982193,
      "learning_rate": 5.3692626373743706e-05,
      "loss": 1.2155,
      "step": 111
    },
    {
      "epoch": 0.06622320768662232,
      "grad_norm": 0.44312167167663574,
      "learning_rate": 5.27705737457985e-05,
      "loss": 1.1505,
      "step": 112
    },
    {
      "epoch": 0.06681448632668145,
      "grad_norm": 0.44145482778549194,
      "learning_rate": 5.184757496945726e-05,
      "loss": 0.9454,
      "step": 113
    },
    {
      "epoch": 0.06740576496674058,
      "grad_norm": 0.43695953488349915,
      "learning_rate": 5.092394524795649e-05,
      "loss": 1.1793,
      "step": 114
    },
    {
      "epoch": 0.0679970436067997,
      "grad_norm": 0.44189295172691345,
      "learning_rate": 5e-05,
      "loss": 1.1351,
      "step": 115
    },
    {
      "epoch": 0.06858832224685883,
      "grad_norm": 0.47619709372520447,
      "learning_rate": 4.907605475204352e-05,
      "loss": 1.0839,
      "step": 116
    },
    {
      "epoch": 0.06917960088691796,
      "grad_norm": 0.46892696619033813,
      "learning_rate": 4.8152425030542766e-05,
      "loss": 1.1188,
      "step": 117
    },
    {
      "epoch": 0.0697708795269771,
      "grad_norm": 0.4708046317100525,
      "learning_rate": 4.72294262542015e-05,
      "loss": 1.2853,
      "step": 118
    },
    {
      "epoch": 0.07036215816703621,
      "grad_norm": 0.4775142967700958,
      "learning_rate": 4.6307373626256306e-05,
      "loss": 1.2427,
      "step": 119
    },
    {
      "epoch": 0.07095343680709534,
      "grad_norm": 0.4797629117965698,
      "learning_rate": 4.5386582026834906e-05,
      "loss": 1.2563,
      "step": 120
    },
    {
      "epoch": 0.07154471544715447,
      "grad_norm": 0.5305618047714233,
      "learning_rate": 4.446736590542497e-05,
      "loss": 1.2615,
      "step": 121
    },
    {
      "epoch": 0.0721359940872136,
      "grad_norm": 0.5574907660484314,
      "learning_rate": 4.3550039173489845e-05,
      "loss": 1.395,
      "step": 122
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 0.5033929944038391,
      "learning_rate": 4.2634915097268115e-05,
      "loss": 1.1613,
      "step": 123
    },
    {
      "epoch": 0.07331855136733186,
      "grad_norm": 0.5360080003738403,
      "learning_rate": 4.1722306190793495e-05,
      "loss": 1.4785,
      "step": 124
    },
    {
      "epoch": 0.07390983000739099,
      "grad_norm": 0.5265625715255737,
      "learning_rate": 4.0812524109171476e-05,
      "loss": 1.2515,
      "step": 125
    },
    {
      "epoch": 0.07450110864745012,
      "grad_norm": 0.6063189506530762,
      "learning_rate": 3.99058795421495e-05,
      "loss": 1.5267,
      "step": 126
    },
    {
      "epoch": 0.07509238728750924,
      "grad_norm": 0.6113285422325134,
      "learning_rate": 3.9002682108016585e-05,
      "loss": 1.3004,
      "step": 127
    },
    {
      "epoch": 0.07568366592756837,
      "grad_norm": 0.6226088404655457,
      "learning_rate": 3.8103240247869075e-05,
      "loss": 1.4766,
      "step": 128
    },
    {
      "epoch": 0.0762749445676275,
      "grad_norm": 0.6256705522537231,
      "learning_rate": 3.720786112027822e-05,
      "loss": 1.4295,
      "step": 129
    },
    {
      "epoch": 0.07686622320768663,
      "grad_norm": 0.6089186072349548,
      "learning_rate": 3.631685049639586e-05,
      "loss": 1.3509,
      "step": 130
    },
    {
      "epoch": 0.07745750184774575,
      "grad_norm": 0.6548407077789307,
      "learning_rate": 3.543051265553377e-05,
      "loss": 1.6872,
      "step": 131
    },
    {
      "epoch": 0.07804878048780488,
      "grad_norm": 0.7260014414787292,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.7412,
      "step": 132
    },
    {
      "epoch": 0.07864005912786401,
      "grad_norm": 0.7247932553291321,
      "learning_rate": 3.367306435799584e-05,
      "loss": 1.6406,
      "step": 133
    },
    {
      "epoch": 0.07923133776792314,
      "grad_norm": 0.7475252747535706,
      "learning_rate": 3.2802554068303596e-05,
      "loss": 1.7114,
      "step": 134
    },
    {
      "epoch": 0.07982261640798226,
      "grad_norm": 0.8387429714202881,
      "learning_rate": 3.1937916690642356e-05,
      "loss": 1.738,
      "step": 135
    },
    {
      "epoch": 0.08041389504804139,
      "grad_norm": 0.8532408475875854,
      "learning_rate": 3.107944749788449e-05,
      "loss": 1.9453,
      "step": 136
    },
    {
      "epoch": 0.08100517368810052,
      "grad_norm": 0.7722581624984741,
      "learning_rate": 3.0227439656472877e-05,
      "loss": 1.6583,
      "step": 137
    },
    {
      "epoch": 0.08159645232815965,
      "grad_norm": 0.7713450193405151,
      "learning_rate": 2.9382184126304834e-05,
      "loss": 1.7002,
      "step": 138
    },
    {
      "epoch": 0.08218773096821877,
      "grad_norm": 0.8988615870475769,
      "learning_rate": 2.8543969561369556e-05,
      "loss": 1.9302,
      "step": 139
    },
    {
      "epoch": 0.0827790096082779,
      "grad_norm": 1.005490779876709,
      "learning_rate": 2.771308221117309e-05,
      "loss": 2.0785,
      "step": 140
    },
    {
      "epoch": 0.08337028824833703,
      "grad_norm": 0.9457467198371887,
      "learning_rate": 2.688980582298435e-05,
      "loss": 1.8597,
      "step": 141
    },
    {
      "epoch": 0.08396156688839616,
      "grad_norm": 1.0314273834228516,
      "learning_rate": 2.607442154493568e-05,
      "loss": 2.0085,
      "step": 142
    },
    {
      "epoch": 0.08455284552845528,
      "grad_norm": 0.9571870565414429,
      "learning_rate": 2.5267207830011068e-05,
      "loss": 1.9062,
      "step": 143
    },
    {
      "epoch": 0.08514412416851441,
      "grad_norm": 1.1800788640975952,
      "learning_rate": 2.446844034095466e-05,
      "loss": 1.9822,
      "step": 144
    },
    {
      "epoch": 0.08573540280857354,
      "grad_norm": 1.0346328020095825,
      "learning_rate": 2.3678391856132204e-05,
      "loss": 1.9708,
      "step": 145
    },
    {
      "epoch": 0.08632668144863268,
      "grad_norm": 1.2094911336898804,
      "learning_rate": 2.2897332176377528e-05,
      "loss": 2.021,
      "step": 146
    },
    {
      "epoch": 0.08691796008869179,
      "grad_norm": 1.429420828819275,
      "learning_rate": 2.2125528032855724e-05,
      "loss": 2.3484,
      "step": 147
    },
    {
      "epoch": 0.08750923872875092,
      "grad_norm": 1.514777660369873,
      "learning_rate": 2.136324299597474e-05,
      "loss": 2.3654,
      "step": 148
    },
    {
      "epoch": 0.08810051736881006,
      "grad_norm": 1.3983551263809204,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.1405,
      "step": 149
    },
    {
      "epoch": 0.08869179600886919,
      "grad_norm": 1.4536499977111816,
      "learning_rate": 1.9868268181037185e-05,
      "loss": 2.1021,
      "step": 150
    },
    {
      "epoch": 0.08869179600886919,
      "eval_loss": 1.445052146911621,
      "eval_runtime": 238.6227,
      "eval_samples_per_second": 11.939,
      "eval_steps_per_second": 5.972,
      "step": 150
    },
    {
      "epoch": 0.0892830746489283,
      "grad_norm": 0.37140536308288574,
      "learning_rate": 1.9136088935510362e-05,
      "loss": 1.2319,
      "step": 151
    },
    {
      "epoch": 0.08987435328898744,
      "grad_norm": 0.437547504901886,
      "learning_rate": 1.8414449687337464e-05,
      "loss": 1.2127,
      "step": 152
    },
    {
      "epoch": 0.09046563192904657,
      "grad_norm": 0.4470095634460449,
      "learning_rate": 1.7703596875660645e-05,
      "loss": 1.101,
      "step": 153
    },
    {
      "epoch": 0.0910569105691057,
      "grad_norm": 0.43900978565216064,
      "learning_rate": 1.700377325606388e-05,
      "loss": 1.0225,
      "step": 154
    },
    {
      "epoch": 0.09164818920916482,
      "grad_norm": 0.4545993208885193,
      "learning_rate": 1.631521781767214e-05,
      "loss": 1.0986,
      "step": 155
    },
    {
      "epoch": 0.09223946784922395,
      "grad_norm": 0.48182153701782227,
      "learning_rate": 1.5638165701536868e-05,
      "loss": 1.1413,
      "step": 156
    },
    {
      "epoch": 0.09283074648928308,
      "grad_norm": 0.4654633402824402,
      "learning_rate": 1.4972848120335453e-05,
      "loss": 1.104,
      "step": 157
    },
    {
      "epoch": 0.09342202512934221,
      "grad_norm": 0.4657576382160187,
      "learning_rate": 1.4319492279412388e-05,
      "loss": 1.0422,
      "step": 158
    },
    {
      "epoch": 0.09401330376940133,
      "grad_norm": 0.4549095630645752,
      "learning_rate": 1.3678321299188801e-05,
      "loss": 1.0239,
      "step": 159
    },
    {
      "epoch": 0.09460458240946046,
      "grad_norm": 0.45037001371383667,
      "learning_rate": 1.3049554138967051e-05,
      "loss": 0.974,
      "step": 160
    },
    {
      "epoch": 0.09519586104951959,
      "grad_norm": 0.47302672266960144,
      "learning_rate": 1.2433405522156332e-05,
      "loss": 1.026,
      "step": 161
    },
    {
      "epoch": 0.09578713968957872,
      "grad_norm": 0.42686906456947327,
      "learning_rate": 1.183008586294485e-05,
      "loss": 1.1564,
      "step": 162
    },
    {
      "epoch": 0.09637841832963784,
      "grad_norm": 0.4490116834640503,
      "learning_rate": 1.1239801194443506e-05,
      "loss": 1.1345,
      "step": 163
    },
    {
      "epoch": 0.09696969696969697,
      "grad_norm": 0.4287410080432892,
      "learning_rate": 1.066275309832584e-05,
      "loss": 1.1877,
      "step": 164
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.43853017687797546,
      "learning_rate": 1.0099138635988026e-05,
      "loss": 1.1694,
      "step": 165
    },
    {
      "epoch": 0.09815225424981523,
      "grad_norm": 0.5354306101799011,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.1783,
      "step": 166
    },
    {
      "epoch": 0.09874353288987435,
      "grad_norm": 0.4395792484283447,
      "learning_rate": 9.012975854638949e-06,
      "loss": 1.0381,
      "step": 167
    },
    {
      "epoch": 0.09933481152993348,
      "grad_norm": 0.4514259696006775,
      "learning_rate": 8.490798459222476e-06,
      "loss": 0.9664,
      "step": 168
    },
    {
      "epoch": 0.09992609016999261,
      "grad_norm": 0.47987860441207886,
      "learning_rate": 7.982796418105371e-06,
      "loss": 1.1756,
      "step": 169
    },
    {
      "epoch": 0.10051736881005174,
      "grad_norm": 0.47819146513938904,
      "learning_rate": 7.489143213519301e-06,
      "loss": 1.057,
      "step": 170
    },
    {
      "epoch": 0.10110864745011086,
      "grad_norm": 0.466268926858902,
      "learning_rate": 7.010007427581378e-06,
      "loss": 1.0946,
      "step": 171
    },
    {
      "epoch": 0.10169992609016999,
      "grad_norm": 0.5092021226882935,
      "learning_rate": 6.5455526847235825e-06,
      "loss": 1.2211,
      "step": 172
    },
    {
      "epoch": 0.10229120473022912,
      "grad_norm": 0.4685361683368683,
      "learning_rate": 6.0959375958151045e-06,
      "loss": 1.0345,
      "step": 173
    },
    {
      "epoch": 0.10288248337028826,
      "grad_norm": 0.5377731323242188,
      "learning_rate": 5.6613157039969055e-06,
      "loss": 1.3137,
      "step": 174
    },
    {
      "epoch": 0.10347376201034737,
      "grad_norm": 0.5368238687515259,
      "learning_rate": 5.241835432246889e-06,
      "loss": 1.1479,
      "step": 175
    },
    {
      "epoch": 0.1040650406504065,
      "grad_norm": 0.6069375276565552,
      "learning_rate": 4.837640032693558e-06,
      "loss": 1.4047,
      "step": 176
    },
    {
      "epoch": 0.10465631929046564,
      "grad_norm": 0.5899990797042847,
      "learning_rate": 4.448867537695578e-06,
      "loss": 1.4995,
      "step": 177
    },
    {
      "epoch": 0.10524759793052477,
      "grad_norm": 0.5741286873817444,
      "learning_rate": 4.075650712703849e-06,
      "loss": 1.2832,
      "step": 178
    },
    {
      "epoch": 0.10583887657058388,
      "grad_norm": 0.6058112382888794,
      "learning_rate": 3.71811701092219e-06,
      "loss": 1.4864,
      "step": 179
    },
    {
      "epoch": 0.10643015521064302,
      "grad_norm": 0.6389828324317932,
      "learning_rate": 3.376388529782215e-06,
      "loss": 1.5509,
      "step": 180
    },
    {
      "epoch": 0.10702143385070215,
      "grad_norm": 0.7593545913696289,
      "learning_rate": 3.0505819692471792e-06,
      "loss": 1.6754,
      "step": 181
    },
    {
      "epoch": 0.10761271249076128,
      "grad_norm": 0.6956416368484497,
      "learning_rate": 2.7408085919590264e-06,
      "loss": 1.6197,
      "step": 182
    },
    {
      "epoch": 0.1082039911308204,
      "grad_norm": 0.7472082376480103,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.6558,
      "step": 183
    },
    {
      "epoch": 0.10879526977087953,
      "grad_norm": 0.7749246954917908,
      "learning_rate": 2.1697790249779636e-06,
      "loss": 1.8279,
      "step": 184
    },
    {
      "epoch": 0.10938654841093866,
      "grad_norm": 0.7523097991943359,
      "learning_rate": 1.908717841359048e-06,
      "loss": 1.455,
      "step": 185
    },
    {
      "epoch": 0.10997782705099779,
      "grad_norm": 0.7814156413078308,
      "learning_rate": 1.6640797865406288e-06,
      "loss": 1.634,
      "step": 186
    },
    {
      "epoch": 0.11056910569105691,
      "grad_norm": 0.8871944546699524,
      "learning_rate": 1.4359484041943038e-06,
      "loss": 1.7472,
      "step": 187
    },
    {
      "epoch": 0.11116038433111604,
      "grad_norm": 0.8749101161956787,
      "learning_rate": 1.2244016009781701e-06,
      "loss": 1.854,
      "step": 188
    },
    {
      "epoch": 0.11175166297117517,
      "grad_norm": 0.8801904916763306,
      "learning_rate": 1.0295116199317057e-06,
      "loss": 1.7069,
      "step": 189
    },
    {
      "epoch": 0.1123429416112343,
      "grad_norm": 0.9642406105995178,
      "learning_rate": 8.513450158049108e-07,
      "loss": 1.8409,
      "step": 190
    },
    {
      "epoch": 0.11293422025129342,
      "grad_norm": 0.9762085676193237,
      "learning_rate": 6.899626323298713e-07,
      "loss": 1.8907,
      "step": 191
    },
    {
      "epoch": 0.11352549889135255,
      "grad_norm": 1.0283136367797852,
      "learning_rate": 5.454195814427021e-07,
      "loss": 1.9047,
      "step": 192
    },
    {
      "epoch": 0.11411677753141168,
      "grad_norm": 1.4411962032318115,
      "learning_rate": 4.177652244628627e-07,
      "loss": 1.8633,
      "step": 193
    },
    {
      "epoch": 0.11470805617147081,
      "grad_norm": 1.2451083660125732,
      "learning_rate": 3.0704315523631953e-07,
      "loss": 2.1482,
      "step": 194
    },
    {
      "epoch": 0.11529933481152993,
      "grad_norm": 1.1835973262786865,
      "learning_rate": 2.1329118524827662e-07,
      "loss": 2.0185,
      "step": 195
    },
    {
      "epoch": 0.11589061345158906,
      "grad_norm": 1.338761329650879,
      "learning_rate": 1.3654133071059893e-07,
      "loss": 1.7139,
      "step": 196
    },
    {
      "epoch": 0.11648189209164819,
      "grad_norm": 1.2973557710647583,
      "learning_rate": 7.681980162830282e-08,
      "loss": 2.0788,
      "step": 197
    },
    {
      "epoch": 0.11707317073170732,
      "grad_norm": 1.4432735443115234,
      "learning_rate": 3.4146992848854695e-08,
      "loss": 2.0671,
      "step": 198
    },
    {
      "epoch": 0.11766444937176644,
      "grad_norm": 1.424852728843689,
      "learning_rate": 8.537477097364522e-09,
      "loss": 2.191,
      "step": 199
    },
    {
      "epoch": 0.11825572801182557,
      "grad_norm": 1.7964314222335815,
      "learning_rate": 0.0,
      "loss": 1.8229,
      "step": 200
    },
    {
      "epoch": 0.11825572801182557,
      "eval_loss": 1.429347276687622,
      "eval_runtime": 238.6143,
      "eval_samples_per_second": 11.94,
      "eval_steps_per_second": 5.972,
      "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": 5,
        "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": 3.051020832441631e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}