{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6081081081081081,
  "eval_steps": 30,
  "global_step": 180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0033783783783783786,
      "grad_norm": 1.4937225174709319,
      "learning_rate": 2.5e-06,
      "loss": 2.1185,
      "step": 1
    },
    {
      "epoch": 0.0033783783783783786,
      "eval_loss": 2.0952866077423096,
      "eval_runtime": 187.5733,
      "eval_samples_per_second": 0.267,
      "eval_steps_per_second": 0.069,
      "step": 1
    },
    {
      "epoch": 0.006756756756756757,
      "grad_norm": 1.442277502174201,
      "learning_rate": 5e-06,
      "loss": 2.1679,
      "step": 2
    },
    {
      "epoch": 0.010135135135135136,
      "grad_norm": 1.4361264107689526,
      "learning_rate": 7.5e-06,
      "loss": 2.1475,
      "step": 3
    },
    {
      "epoch": 0.013513513513513514,
      "grad_norm": 1.5925067561400204,
      "learning_rate": 1e-05,
      "loss": 2.1111,
      "step": 4
    },
    {
      "epoch": 0.016891891891891893,
      "grad_norm": 1.5729343116389016,
      "learning_rate": 1.25e-05,
      "loss": 2.1772,
      "step": 5
    },
    {
      "epoch": 0.02027027027027027,
      "grad_norm": 0.77386625695677,
      "learning_rate": 1.5e-05,
      "loss": 2.1445,
      "step": 6
    },
    {
      "epoch": 0.02364864864864865,
      "grad_norm": 0.9687092422157498,
      "learning_rate": 1.75e-05,
      "loss": 2.0929,
      "step": 7
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 0.5745308246234537,
      "learning_rate": 2e-05,
      "loss": 2.1085,
      "step": 8
    },
    {
      "epoch": 0.030405405405405407,
      "grad_norm": 0.7880273258575979,
      "learning_rate": 2.25e-05,
      "loss": 2.1717,
      "step": 9
    },
    {
      "epoch": 0.033783783783783786,
      "grad_norm": 0.5987395071382063,
      "learning_rate": 2.5e-05,
      "loss": 2.074,
      "step": 10
    },
    {
      "epoch": 0.037162162162162164,
      "grad_norm": 0.8312307017045393,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 2.2338,
      "step": 11
    },
    {
      "epoch": 0.04054054054054054,
      "grad_norm": 0.7733440491356615,
      "learning_rate": 3e-05,
      "loss": 2.2148,
      "step": 12
    },
    {
      "epoch": 0.04391891891891892,
      "grad_norm": 0.7510878886656168,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 2.243,
      "step": 13
    },
    {
      "epoch": 0.0472972972972973,
      "grad_norm": 0.6210806018904155,
      "learning_rate": 3.5e-05,
      "loss": 1.9863,
      "step": 14
    },
    {
      "epoch": 0.05067567567567568,
      "grad_norm": 1.018373738736693,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 2.0294,
      "step": 15
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 0.771759792529477,
      "learning_rate": 4e-05,
      "loss": 2.0353,
      "step": 16
    },
    {
      "epoch": 0.057432432432432436,
      "grad_norm": 0.5625682320002908,
      "learning_rate": 4.25e-05,
      "loss": 2.0775,
      "step": 17
    },
    {
      "epoch": 0.060810810810810814,
      "grad_norm": 0.5157565411105806,
      "learning_rate": 4.5e-05,
      "loss": 2.1791,
      "step": 18
    },
    {
      "epoch": 0.06418918918918919,
      "grad_norm": 0.8173537204599863,
      "learning_rate": 4.75e-05,
      "loss": 2.0549,
      "step": 19
    },
    {
      "epoch": 0.06756756756756757,
      "grad_norm": 2.5851976259061664,
      "learning_rate": 5e-05,
      "loss": 2.0757,
      "step": 20
    },
    {
      "epoch": 0.07094594594594594,
      "grad_norm": 0.5130578194248145,
      "learning_rate": 4.999854243002125e-05,
      "loss": 2.2505,
      "step": 21
    },
    {
      "epoch": 0.07432432432432433,
      "grad_norm": 0.5786770218696188,
      "learning_rate": 4.999416990893036e-05,
      "loss": 2.2533,
      "step": 22
    },
    {
      "epoch": 0.0777027027027027,
      "grad_norm": 0.8219446198677083,
      "learning_rate": 4.998688300323891e-05,
      "loss": 2.1092,
      "step": 23
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 0.7123342305131811,
      "learning_rate": 4.997668265705137e-05,
      "loss": 2.3369,
      "step": 24
    },
    {
      "epoch": 0.08445945945945946,
      "grad_norm": 0.44584577341815756,
      "learning_rate": 4.9963570191942696e-05,
      "loss": 2.0125,
      "step": 25
    },
    {
      "epoch": 0.08783783783783784,
      "grad_norm": 0.5308641065159894,
      "learning_rate": 4.994754730678713e-05,
      "loss": 2.0653,
      "step": 26
    },
    {
      "epoch": 0.09121621621621621,
      "grad_norm": 0.4833891468070717,
      "learning_rate": 4.992861607753817e-05,
      "loss": 2.0177,
      "step": 27
    },
    {
      "epoch": 0.0945945945945946,
      "grad_norm": 0.4487741255853019,
      "learning_rate": 4.9906778956959454e-05,
      "loss": 1.9773,
      "step": 28
    },
    {
      "epoch": 0.09797297297297297,
      "grad_norm": 0.7070413556606907,
      "learning_rate": 4.988203877430713e-05,
      "loss": 2.0163,
      "step": 29
    },
    {
      "epoch": 0.10135135135135136,
      "grad_norm": 0.6433406570980086,
      "learning_rate": 4.985439873496321e-05,
      "loss": 2.055,
      "step": 30
    },
    {
      "epoch": 0.10135135135135136,
      "eval_loss": 2.022883653640747,
      "eval_runtime": 194.2976,
      "eval_samples_per_second": 0.257,
      "eval_steps_per_second": 0.067,
      "step": 30
    },
    {
      "epoch": 0.10472972972972973,
      "grad_norm": 1.9573381693992367,
      "learning_rate": 4.982386242002024e-05,
      "loss": 2.3371,
      "step": 31
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 1.6578265269127788,
      "learning_rate": 4.979043378581744e-05,
      "loss": 2.1288,
      "step": 32
    },
    {
      "epoch": 0.11148648648648649,
      "grad_norm": 0.5544836623908992,
      "learning_rate": 4.975411716342802e-05,
      "loss": 2.1887,
      "step": 33
    },
    {
      "epoch": 0.11486486486486487,
      "grad_norm": 0.5455040506142,
      "learning_rate": 4.971491725809807e-05,
      "loss": 2.1214,
      "step": 34
    },
    {
      "epoch": 0.11824324324324324,
      "grad_norm": 0.5065209751020103,
      "learning_rate": 4.967283914863693e-05,
      "loss": 2.1692,
      "step": 35
    },
    {
      "epoch": 0.12162162162162163,
      "grad_norm": 0.6453232517165945,
      "learning_rate": 4.96278882867592e-05,
      "loss": 2.0598,
      "step": 36
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.1731862208697716,
      "learning_rate": 4.9580070496378364e-05,
      "loss": 2.2156,
      "step": 37
    },
    {
      "epoch": 0.12837837837837837,
      "grad_norm": 0.7667101172051888,
      "learning_rate": 4.952939197285227e-05,
      "loss": 2.1392,
      "step": 38
    },
    {
      "epoch": 0.13175675675675674,
      "grad_norm": 0.41781856442196297,
      "learning_rate": 4.947585928218041e-05,
      "loss": 2.1534,
      "step": 39
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 0.5945736341225079,
      "learning_rate": 4.9419479360153286e-05,
      "loss": 1.9795,
      "step": 40
    },
    {
      "epoch": 0.13851351351351351,
      "grad_norm": 0.6467707595603454,
      "learning_rate": 4.936025951145368e-05,
      "loss": 2.0017,
      "step": 41
    },
    {
      "epoch": 0.14189189189189189,
      "grad_norm": 0.5109600024808127,
      "learning_rate": 4.929820740871039e-05,
      "loss": 2.2144,
      "step": 42
    },
    {
      "epoch": 0.14527027027027026,
      "grad_norm": 1.0548277894819795,
      "learning_rate": 4.9233331091504034e-05,
      "loss": 2.0657,
      "step": 43
    },
    {
      "epoch": 0.14864864864864866,
      "grad_norm": 0.6580975841596574,
      "learning_rate": 4.916563896532549e-05,
      "loss": 2.1431,
      "step": 44
    },
    {
      "epoch": 0.15202702702702703,
      "grad_norm": 0.3988619886160755,
      "learning_rate": 4.9095139800486824e-05,
      "loss": 2.0123,
      "step": 45
    },
    {
      "epoch": 0.1554054054054054,
      "grad_norm": 0.5209858406284475,
      "learning_rate": 4.9021842730985036e-05,
      "loss": 2.2487,
      "step": 46
    },
    {
      "epoch": 0.15878378378378377,
      "grad_norm": 0.5433634333987769,
      "learning_rate": 4.894575725331862e-05,
      "loss": 2.1736,
      "step": 47
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 0.5109855249570185,
      "learning_rate": 4.886689322525719e-05,
      "loss": 2.0823,
      "step": 48
    },
    {
      "epoch": 0.16554054054054054,
      "grad_norm": 0.6194335580813743,
      "learning_rate": 4.878526086456426e-05,
      "loss": 2.1036,
      "step": 49
    },
    {
      "epoch": 0.16891891891891891,
      "grad_norm": 1.0780413583147488,
      "learning_rate": 4.8700870747673466e-05,
      "loss": 2.0302,
      "step": 50
    },
    {
      "epoch": 0.17229729729729729,
      "grad_norm": 0.580340495769622,
      "learning_rate": 4.8613733808318204e-05,
      "loss": 2.1776,
      "step": 51
    },
    {
      "epoch": 0.17567567567567569,
      "grad_norm": 0.8129429382764808,
      "learning_rate": 4.85238613361151e-05,
      "loss": 2.0965,
      "step": 52
    },
    {
      "epoch": 0.17905405405405406,
      "grad_norm": 0.7779782864994534,
      "learning_rate": 4.8431264975101245e-05,
      "loss": 2.1582,
      "step": 53
    },
    {
      "epoch": 0.18243243243243243,
      "grad_norm": 0.8528745581545691,
      "learning_rate": 4.8335956722225616e-05,
      "loss": 2.1511,
      "step": 54
    },
    {
      "epoch": 0.1858108108108108,
      "grad_norm": 0.49188324413548323,
      "learning_rate": 4.823794892579471e-05,
      "loss": 2.1583,
      "step": 55
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 0.724195478643155,
      "learning_rate": 4.8137254283872696e-05,
      "loss": 1.9438,
      "step": 56
    },
    {
      "epoch": 0.19256756756756757,
      "grad_norm": 0.8754624301347438,
      "learning_rate": 4.803388584263618e-05,
      "loss": 2.1349,
      "step": 57
    },
    {
      "epoch": 0.19594594594594594,
      "grad_norm": 0.4870044791836658,
      "learning_rate": 4.7927856994684e-05,
      "loss": 2.0239,
      "step": 58
    },
    {
      "epoch": 0.19932432432432431,
      "grad_norm": 0.5041896039366629,
      "learning_rate": 4.781918147730199e-05,
      "loss": 2.0841,
      "step": 59
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 0.4874068239264915,
      "learning_rate": 4.7707873370683163e-05,
      "loss": 2.1407,
      "step": 60
    },
    {
      "epoch": 0.20270270270270271,
      "eval_loss": 2.015751838684082,
      "eval_runtime": 196.268,
      "eval_samples_per_second": 0.255,
      "eval_steps_per_second": 0.066,
      "step": 60
    },
    {
      "epoch": 0.20608108108108109,
      "grad_norm": 0.5424018707478311,
      "learning_rate": 4.75939470961035e-05,
      "loss": 2.186,
      "step": 61
    },
    {
      "epoch": 0.20945945945945946,
      "grad_norm": 0.5115180976703219,
      "learning_rate": 4.747741741405344e-05,
      "loss": 2.2014,
      "step": 62
    },
    {
      "epoch": 0.21283783783783783,
      "grad_norm": 0.5058558197015601,
      "learning_rate": 4.735829942232555e-05,
      "loss": 2.0927,
      "step": 63
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.8021043767946636,
      "learning_rate": 4.7236608554058375e-05,
      "loss": 2.1884,
      "step": 64
    },
    {
      "epoch": 0.2195945945945946,
      "grad_norm": 0.5293842363703689,
      "learning_rate": 4.711236057573691e-05,
      "loss": 2.0714,
      "step": 65
    },
    {
      "epoch": 0.22297297297297297,
      "grad_norm": 0.48722486629288786,
      "learning_rate": 4.6985571585149876e-05,
      "loss": 2.0562,
      "step": 66
    },
    {
      "epoch": 0.22635135135135134,
      "grad_norm": 0.4279248526312935,
      "learning_rate": 4.685625800930406e-05,
      "loss": 2.0847,
      "step": 67
    },
    {
      "epoch": 0.22972972972972974,
      "grad_norm": 0.5130161800768928,
      "learning_rate": 4.6724436602296e-05,
      "loss": 2.0617,
      "step": 68
    },
    {
      "epoch": 0.23310810810810811,
      "grad_norm": 0.7460272297512813,
      "learning_rate": 4.659012444314128e-05,
      "loss": 2.1029,
      "step": 69
    },
    {
      "epoch": 0.23648648648648649,
      "grad_norm": 0.4943699960691202,
      "learning_rate": 4.645333893356176e-05,
      "loss": 1.9948,
      "step": 70
    },
    {
      "epoch": 0.23986486486486486,
      "grad_norm": 0.6350670407835639,
      "learning_rate": 4.6314097795731e-05,
      "loss": 2.0935,
      "step": 71
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 0.542940777570525,
      "learning_rate": 4.6172419069978065e-05,
      "loss": 2.0267,
      "step": 72
    },
    {
      "epoch": 0.24662162162162163,
      "grad_norm": 0.4567422527911003,
      "learning_rate": 4.602832111245029e-05,
      "loss": 1.9971,
      "step": 73
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.4699317313725709,
      "learning_rate": 4.5881822592734946e-05,
      "loss": 2.1758,
      "step": 74
    },
    {
      "epoch": 0.2533783783783784,
      "grad_norm": 0.6913326755097541,
      "learning_rate": 4.573294249144041e-05,
      "loss": 2.1574,
      "step": 75
    },
    {
      "epoch": 0.25675675675675674,
      "grad_norm": 0.4362574963180428,
      "learning_rate": 4.5581700097737015e-05,
      "loss": 2.0498,
      "step": 76
    },
    {
      "epoch": 0.26013513513513514,
      "grad_norm": 0.6932798791839507,
      "learning_rate": 4.542811500685785e-05,
      "loss": 2.0777,
      "step": 77
    },
    {
      "epoch": 0.2635135135135135,
      "grad_norm": 0.4469936094893796,
      "learning_rate": 4.527220711756007e-05,
      "loss": 2.1046,
      "step": 78
    },
    {
      "epoch": 0.2668918918918919,
      "grad_norm": 0.5112163825070385,
      "learning_rate": 4.511399662954667e-05,
      "loss": 2.0955,
      "step": 79
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 0.4272672573543929,
      "learning_rate": 4.4953504040849445e-05,
      "loss": 2.1927,
      "step": 80
    },
    {
      "epoch": 0.27364864864864863,
      "grad_norm": 0.4203647309881028,
      "learning_rate": 4.479075014517321e-05,
      "loss": 2.0421,
      "step": 81
    },
    {
      "epoch": 0.27702702702702703,
      "grad_norm": 0.5896256230009808,
      "learning_rate": 4.462575602920171e-05,
      "loss": 2.109,
      "step": 82
    },
    {
      "epoch": 0.28040540540540543,
      "grad_norm": 0.7482696034746834,
      "learning_rate": 4.445854306986563e-05,
      "loss": 2.0851,
      "step": 83
    },
    {
      "epoch": 0.28378378378378377,
      "grad_norm": 0.508289422303338,
      "learning_rate": 4.428913293157293e-05,
      "loss": 2.1759,
      "step": 84
    },
    {
      "epoch": 0.28716216216216217,
      "grad_norm": 0.4749189097462539,
      "learning_rate": 4.411754756340198e-05,
      "loss": 2.0721,
      "step": 85
    },
    {
      "epoch": 0.2905405405405405,
      "grad_norm": 0.493594282927666,
      "learning_rate": 4.3943809196257794e-05,
      "loss": 2.0351,
      "step": 86
    },
    {
      "epoch": 0.2939189189189189,
      "grad_norm": 0.4836545743981663,
      "learning_rate": 4.376794033999177e-05,
      "loss": 2.0896,
      "step": 87
    },
    {
      "epoch": 0.2972972972972973,
      "grad_norm": 0.47767898533003106,
      "learning_rate": 4.358996378048524e-05,
      "loss": 2.083,
      "step": 88
    },
    {
      "epoch": 0.30067567567567566,
      "grad_norm": 0.4390064059005752,
      "learning_rate": 4.340990257669732e-05,
      "loss": 2.0627,
      "step": 89
    },
    {
      "epoch": 0.30405405405405406,
      "grad_norm": 0.4601711355647231,
      "learning_rate": 4.3227780057677345e-05,
      "loss": 2.0997,
      "step": 90
    },
    {
      "epoch": 0.30405405405405406,
      "eval_loss": 2.011120080947876,
      "eval_runtime": 190.8365,
      "eval_samples_per_second": 0.262,
      "eval_steps_per_second": 0.068,
      "step": 90
    },
    {
      "epoch": 0.30743243243243246,
      "grad_norm": 0.5654017461216198,
      "learning_rate": 4.304361981954231e-05,
      "loss": 2.2149,
      "step": 91
    },
    {
      "epoch": 0.3108108108108108,
      "grad_norm": 0.5064873219371222,
      "learning_rate": 4.285744572241972e-05,
      "loss": 2.1093,
      "step": 92
    },
    {
      "epoch": 0.3141891891891892,
      "grad_norm": 0.46470652155232134,
      "learning_rate": 4.266928188735621e-05,
      "loss": 2.1098,
      "step": 93
    },
    {
      "epoch": 0.31756756756756754,
      "grad_norm": 0.4413493288478021,
      "learning_rate": 4.247915269319241e-05,
      "loss": 2.1431,
      "step": 94
    },
    {
      "epoch": 0.32094594594594594,
      "grad_norm": 1.0020586721524896,
      "learning_rate": 4.2287082773404386e-05,
      "loss": 2.0877,
      "step": 95
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 0.4848089444845991,
      "learning_rate": 4.209309701291201e-05,
      "loss": 2.1175,
      "step": 96
    },
    {
      "epoch": 0.3277027027027027,
      "grad_norm": 0.5555159336979827,
      "learning_rate": 4.189722054485492e-05,
      "loss": 2.1563,
      "step": 97
    },
    {
      "epoch": 0.3310810810810811,
      "grad_norm": 0.3802895433591588,
      "learning_rate": 4.169947874733619e-05,
      "loss": 2.0732,
      "step": 98
    },
    {
      "epoch": 0.3344594594594595,
      "grad_norm": 0.7320601930371831,
      "learning_rate": 4.149989724013425e-05,
      "loss": 2.1452,
      "step": 99
    },
    {
      "epoch": 0.33783783783783783,
      "grad_norm": 0.8602357197050848,
      "learning_rate": 4.1298501881383624e-05,
      "loss": 2.1766,
      "step": 100
    },
    {
      "epoch": 0.34121621621621623,
      "grad_norm": 0.5831812051877154,
      "learning_rate": 4.109531876422463e-05,
      "loss": 2.1593,
      "step": 101
    },
    {
      "epoch": 0.34459459459459457,
      "grad_norm": 0.7665489432929005,
      "learning_rate": 4.089037421342277e-05,
      "loss": 2.0295,
      "step": 102
    },
    {
      "epoch": 0.34797297297297297,
      "grad_norm": 0.45337471468141477,
      "learning_rate": 4.0683694781958e-05,
      "loss": 2.1087,
      "step": 103
    },
    {
      "epoch": 0.35135135135135137,
      "grad_norm": 0.4591955107711257,
      "learning_rate": 4.047530724758451e-05,
      "loss": 2.0354,
      "step": 104
    },
    {
      "epoch": 0.3547297297297297,
      "grad_norm": 0.7505711753697653,
      "learning_rate": 4.026523860936132e-05,
      "loss": 2.0258,
      "step": 105
    },
    {
      "epoch": 0.3581081081081081,
      "grad_norm": 0.589397231315979,
      "learning_rate": 4.005351608415426e-05,
      "loss": 2.0051,
      "step": 106
    },
    {
      "epoch": 0.3614864864864865,
      "grad_norm": 0.6872824203092515,
      "learning_rate": 3.9840167103109675e-05,
      "loss": 1.9355,
      "step": 107
    },
    {
      "epoch": 0.36486486486486486,
      "grad_norm": 0.45802674220232215,
      "learning_rate": 3.9625219308100455e-05,
      "loss": 2.0836,
      "step": 108
    },
    {
      "epoch": 0.36824324324324326,
      "grad_norm": 0.5524787455898191,
      "learning_rate": 3.940870054814462e-05,
      "loss": 2.0474,
      "step": 109
    },
    {
      "epoch": 0.3716216216216216,
      "grad_norm": 0.38416177227514725,
      "learning_rate": 3.919063887579726e-05,
      "loss": 2.0985,
      "step": 110
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.45960539321926364,
      "learning_rate": 3.897106254351587e-05,
      "loss": 2.0129,
      "step": 111
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 0.37861955022931376,
      "learning_rate": 3.875e-05,
      "loss": 2.1427,
      "step": 112
    },
    {
      "epoch": 0.38175675675675674,
      "grad_norm": 0.581523763120522,
      "learning_rate": 3.852747988650539e-05,
      "loss": 2.0318,
      "step": 113
    },
    {
      "epoch": 0.38513513513513514,
      "grad_norm": 0.3504600135974039,
      "learning_rate": 3.83035310331331e-05,
      "loss": 2.033,
      "step": 114
    },
    {
      "epoch": 0.3885135135135135,
      "grad_norm": 0.4242352094167052,
      "learning_rate": 3.807818245509429e-05,
      "loss": 2.034,
      "step": 115
    },
    {
      "epoch": 0.3918918918918919,
      "grad_norm": 0.4250673616692747,
      "learning_rate": 3.785146334895093e-05,
      "loss": 2.1702,
      "step": 116
    },
    {
      "epoch": 0.3952702702702703,
      "grad_norm": 3.2751318573643617,
      "learning_rate": 3.762340308883302e-05,
      "loss": 2.1026,
      "step": 117
    },
    {
      "epoch": 0.39864864864864863,
      "grad_norm": 0.48584128738743915,
      "learning_rate": 3.739403122263288e-05,
      "loss": 2.22,
      "step": 118
    },
    {
      "epoch": 0.40202702702702703,
      "grad_norm": 0.4187766943285619,
      "learning_rate": 3.716337746817685e-05,
      "loss": 2.1541,
      "step": 119
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 0.5051183151449187,
      "learning_rate": 3.6931471709374946e-05,
      "loss": 2.1113,
      "step": 120
    },
    {
      "epoch": 0.40540540540540543,
      "eval_loss": 2.009887218475342,
      "eval_runtime": 193.8883,
      "eval_samples_per_second": 0.258,
      "eval_steps_per_second": 0.067,
      "step": 120
    },
    {
      "epoch": 0.40878378378378377,
      "grad_norm": 0.40423483975901836,
      "learning_rate": 3.669834399234913e-05,
      "loss": 2.0209,
      "step": 121
    },
    {
      "epoch": 0.41216216216216217,
      "grad_norm": 0.3825955755250103,
      "learning_rate": 3.646402452154043e-05,
      "loss": 2.074,
      "step": 122
    },
    {
      "epoch": 0.4155405405405405,
      "grad_norm": 1.4013949742645142,
      "learning_rate": 3.622854365579561e-05,
      "loss": 2.1807,
      "step": 123
    },
    {
      "epoch": 0.4189189189189189,
      "grad_norm": 0.43240866134882766,
      "learning_rate": 3.5991931904433824e-05,
      "loss": 1.9988,
      "step": 124
    },
    {
      "epoch": 0.4222972972972973,
      "grad_norm": 0.4777714379483413,
      "learning_rate": 3.575421992329377e-05,
      "loss": 2.0801,
      "step": 125
    },
    {
      "epoch": 0.42567567567567566,
      "grad_norm": 0.49357523405169307,
      "learning_rate": 3.551543851076188e-05,
      "loss": 2.0035,
      "step": 126
    },
    {
      "epoch": 0.42905405405405406,
      "grad_norm": 0.3447821776586979,
      "learning_rate": 3.5275618603782006e-05,
      "loss": 2.0435,
      "step": 127
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.3718901049854852,
      "learning_rate": 3.503479127384719e-05,
      "loss": 1.8828,
      "step": 128
    },
    {
      "epoch": 0.4358108108108108,
      "grad_norm": 0.3888324394883177,
      "learning_rate": 3.479298772297398e-05,
      "loss": 2.1094,
      "step": 129
    },
    {
      "epoch": 0.4391891891891892,
      "grad_norm": 0.5267690929558577,
      "learning_rate": 3.4550239279659854e-05,
      "loss": 2.1593,
      "step": 130
    },
    {
      "epoch": 0.44256756756756754,
      "grad_norm": 0.4636315581971976,
      "learning_rate": 3.4306577394824207e-05,
      "loss": 2.1605,
      "step": 131
    },
    {
      "epoch": 0.44594594594594594,
      "grad_norm": 0.3968487601273563,
      "learning_rate": 3.406203363773356e-05,
      "loss": 2.0023,
      "step": 132
    },
    {
      "epoch": 0.44932432432432434,
      "grad_norm": 0.392460435962094,
      "learning_rate": 3.381663969191137e-05,
      "loss": 2.1517,
      "step": 133
    },
    {
      "epoch": 0.4527027027027027,
      "grad_norm": 0.4031589419917055,
      "learning_rate": 3.3570427351033046e-05,
      "loss": 2.0701,
      "step": 134
    },
    {
      "epoch": 0.4560810810810811,
      "grad_norm": 0.4253231691696294,
      "learning_rate": 3.332342851480672e-05,
      "loss": 2.0944,
      "step": 135
    },
    {
      "epoch": 0.4594594594594595,
      "grad_norm": 1.089550042036897,
      "learning_rate": 3.307567518484025e-05,
      "loss": 2.1879,
      "step": 136
    },
    {
      "epoch": 0.46283783783783783,
      "grad_norm": 0.5433174961880026,
      "learning_rate": 3.282719946049505e-05,
      "loss": 2.1142,
      "step": 137
    },
    {
      "epoch": 0.46621621621621623,
      "grad_norm": 0.47522024279968983,
      "learning_rate": 3.257803353472724e-05,
      "loss": 2.0765,
      "step": 138
    },
    {
      "epoch": 0.46959459459459457,
      "grad_norm": 0.6397031743657627,
      "learning_rate": 3.232820968991664e-05,
      "loss": 2.0565,
      "step": 139
    },
    {
      "epoch": 0.47297297297297297,
      "grad_norm": 0.8231847588094275,
      "learning_rate": 3.207776029368427e-05,
      "loss": 2.1382,
      "step": 140
    },
    {
      "epoch": 0.47635135135135137,
      "grad_norm": 0.4277815234715947,
      "learning_rate": 3.1826717794698635e-05,
      "loss": 2.1454,
      "step": 141
    },
    {
      "epoch": 0.4797297297297297,
      "grad_norm": 0.395176536808308,
      "learning_rate": 3.157511471847176e-05,
      "loss": 2.0293,
      "step": 142
    },
    {
      "epoch": 0.4831081081081081,
      "grad_norm": 0.42124877734068217,
      "learning_rate": 3.1322983663145e-05,
      "loss": 2.0417,
      "step": 143
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 0.6103856586396839,
      "learning_rate": 3.107035729526566e-05,
      "loss": 2.0703,
      "step": 144
    },
    {
      "epoch": 0.48986486486486486,
      "grad_norm": 0.40802626443551787,
      "learning_rate": 3.081726834555458e-05,
      "loss": 1.9202,
      "step": 145
    },
    {
      "epoch": 0.49324324324324326,
      "grad_norm": 0.4038507240265364,
      "learning_rate": 3.0563749604665556e-05,
      "loss": 2.1105,
      "step": 146
    },
    {
      "epoch": 0.4966216216216216,
      "grad_norm": 0.39745914058435033,
      "learning_rate": 3.0309833918936865e-05,
      "loss": 2.0854,
      "step": 147
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.39094920659893395,
      "learning_rate": 3.0055554186135688e-05,
      "loss": 2.1638,
      "step": 148
    },
    {
      "epoch": 0.5033783783783784,
      "grad_norm": 0.4684851166837971,
      "learning_rate": 2.980094335119577e-05,
      "loss": 2.0368,
      "step": 149
    },
    {
      "epoch": 0.5067567567567568,
      "grad_norm": 0.8309495298034889,
      "learning_rate": 2.9546034401949064e-05,
      "loss": 2.1695,
      "step": 150
    },
    {
      "epoch": 0.5067567567567568,
      "eval_loss": 2.0075740814208984,
      "eval_runtime": 193.1213,
      "eval_samples_per_second": 0.259,
      "eval_steps_per_second": 0.067,
      "step": 150
    },
    {
      "epoch": 0.5101351351351351,
      "grad_norm": 0.5583192813687627,
      "learning_rate": 2.9290860364851702e-05,
      "loss": 2.0582,
      "step": 151
    },
    {
      "epoch": 0.5135135135135135,
      "grad_norm": 0.42473795943255627,
      "learning_rate": 2.90354543007051e-05,
      "loss": 2.0871,
      "step": 152
    },
    {
      "epoch": 0.5168918918918919,
      "grad_norm": 0.4247509513157766,
      "learning_rate": 2.877984930037251e-05,
      "loss": 2.0964,
      "step": 153
    },
    {
      "epoch": 0.5202702702702703,
      "grad_norm": 0.8778087000903096,
      "learning_rate": 2.8524078480491684e-05,
      "loss": 2.0506,
      "step": 154
    },
    {
      "epoch": 0.5236486486486487,
      "grad_norm": 0.501109409670388,
      "learning_rate": 2.826817497918428e-05,
      "loss": 2.1435,
      "step": 155
    },
    {
      "epoch": 0.527027027027027,
      "grad_norm": 0.7730432872928119,
      "learning_rate": 2.8012171951762378e-05,
      "loss": 2.0909,
      "step": 156
    },
    {
      "epoch": 0.5304054054054054,
      "grad_norm": 0.4007388361090252,
      "learning_rate": 2.7756102566432845e-05,
      "loss": 2.1613,
      "step": 157
    },
    {
      "epoch": 0.5337837837837838,
      "grad_norm": 0.4121213099878934,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 2.2213,
      "step": 158
    },
    {
      "epoch": 0.5371621621621622,
      "grad_norm": 0.4237936256648311,
      "learning_rate": 2.7243897433567157e-05,
      "loss": 2.1795,
      "step": 159
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 0.41107097005560067,
      "learning_rate": 2.6987828048237624e-05,
      "loss": 2.0895,
      "step": 160
    },
    {
      "epoch": 0.543918918918919,
      "grad_norm": 0.4463337134292773,
      "learning_rate": 2.6731825020815725e-05,
      "loss": 2.046,
      "step": 161
    },
    {
      "epoch": 0.5472972972972973,
      "grad_norm": 0.5230967905508315,
      "learning_rate": 2.6475921519508325e-05,
      "loss": 2.0374,
      "step": 162
    },
    {
      "epoch": 0.5506756756756757,
      "grad_norm": 0.414839716539812,
      "learning_rate": 2.62201506996275e-05,
      "loss": 2.2485,
      "step": 163
    },
    {
      "epoch": 0.5540540540540541,
      "grad_norm": 0.38087462228816815,
      "learning_rate": 2.5964545699294906e-05,
      "loss": 2.0365,
      "step": 164
    },
    {
      "epoch": 0.5574324324324325,
      "grad_norm": 0.5305482547516058,
      "learning_rate": 2.570913963514831e-05,
      "loss": 2.0701,
      "step": 165
    },
    {
      "epoch": 0.5608108108108109,
      "grad_norm": 0.39988875104823635,
      "learning_rate": 2.5453965598050944e-05,
      "loss": 2.1985,
      "step": 166
    },
    {
      "epoch": 0.5641891891891891,
      "grad_norm": 0.6054380331009478,
      "learning_rate": 2.5199056648804233e-05,
      "loss": 2.1136,
      "step": 167
    },
    {
      "epoch": 0.5675675675675675,
      "grad_norm": 0.39275163056643564,
      "learning_rate": 2.4944445813864314e-05,
      "loss": 2.0735,
      "step": 168
    },
    {
      "epoch": 0.5709459459459459,
      "grad_norm": 0.7078296605563206,
      "learning_rate": 2.469016608106315e-05,
      "loss": 2.1578,
      "step": 169
    },
    {
      "epoch": 0.5743243243243243,
      "grad_norm": 0.439519908152304,
      "learning_rate": 2.443625039533446e-05,
      "loss": 2.0469,
      "step": 170
    },
    {
      "epoch": 0.5777027027027027,
      "grad_norm": 0.47171431683346926,
      "learning_rate": 2.4182731654445427e-05,
      "loss": 2.0609,
      "step": 171
    },
    {
      "epoch": 0.581081081081081,
      "grad_norm": 0.43725040423496425,
      "learning_rate": 2.3929642704734347e-05,
      "loss": 2.1686,
      "step": 172
    },
    {
      "epoch": 0.5844594594594594,
      "grad_norm": 0.5156240873689197,
      "learning_rate": 2.3677016336855002e-05,
      "loss": 2.111,
      "step": 173
    },
    {
      "epoch": 0.5878378378378378,
      "grad_norm": 0.478909789809296,
      "learning_rate": 2.3424885281528248e-05,
      "loss": 2.0993,
      "step": 174
    },
    {
      "epoch": 0.5912162162162162,
      "grad_norm": 0.8822684350527039,
      "learning_rate": 2.3173282205301367e-05,
      "loss": 2.091,
      "step": 175
    },
    {
      "epoch": 0.5945945945945946,
      "grad_norm": 0.5005747298379083,
      "learning_rate": 2.2922239706315745e-05,
      "loss": 2.0998,
      "step": 176
    },
    {
      "epoch": 0.597972972972973,
      "grad_norm": 0.38147794073978136,
      "learning_rate": 2.2671790310083364e-05,
      "loss": 2.0433,
      "step": 177
    },
    {
      "epoch": 0.6013513513513513,
      "grad_norm": 0.449696856682795,
      "learning_rate": 2.2421966465272765e-05,
      "loss": 1.9547,
      "step": 178
    },
    {
      "epoch": 0.6047297297297297,
      "grad_norm": 0.4046647546809551,
      "learning_rate": 2.217280053950495e-05,
      "loss": 2.0109,
      "step": 179
    },
    {
      "epoch": 0.6081081081081081,
      "grad_norm": 0.44319480569143777,
      "learning_rate": 2.1924324815159757e-05,
      "loss": 2.0782,
      "step": 180
    },
    {
      "epoch": 0.6081081081081081,
      "eval_loss": 2.006296157836914,
      "eval_runtime": 194.8007,
      "eval_samples_per_second": 0.257,
      "eval_steps_per_second": 0.067,
      "step": 180
    }
  ],
  "logging_steps": 1,
  "max_steps": 296,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 60,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 308899416637440.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}