{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.3692307692307693,
  "eval_steps": 500,
  "global_step": 360,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.324825406074524,
      "learning_rate": 0.0,
      "loss": 2.251,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.359919548034668,
      "learning_rate": 4e-05,
      "loss": 2.3496,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.1708112955093384,
      "learning_rate": 8e-05,
      "loss": 2.0811,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.3121654987335205,
      "learning_rate": 0.00012,
      "loss": 2.5163,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.736699104309082,
      "learning_rate": 0.00016,
      "loss": 2.2536,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.6031162738800049,
      "learning_rate": 0.0002,
      "loss": 1.9244,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.7248623371124268,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.981,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.186155080795288,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.4323,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.0301684141159058,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.1934,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.7665079236030579,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.0643,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.9783205986022949,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.3316,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.6272598505020142,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.1988,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.3676067292690277,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.9774,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.39943814277648926,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.9461,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.36930710077285767,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.0264,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.2694442868232727,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.9453,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.29302021861076355,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.0611,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.31116580963134766,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.839,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.29176589846611023,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.9196,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.3165068030357361,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.9196,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3522554636001587,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0832,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.34008151292800903,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.9705,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.2566126883029938,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.9122,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.29866355657577515,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.8918,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.2955140471458435,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.1007,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.33036312460899353,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9752,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.2844546139240265,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9755,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3072405457496643,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.0727,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.27163660526275635,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.9208,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3229711353778839,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.0546,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.23488745093345642,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.8587,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.21555615961551666,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.7837,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.23712514340877533,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9478,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.2658460736274719,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.034,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.2315426766872406,
      "learning_rate": 0.00018713968957871397,
      "loss": 1.0614,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.2795284688472748,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.936,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.23665310442447662,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.0365,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.29602324962615967,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.031,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.22743946313858032,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.8417,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3170803189277649,
      "learning_rate": 0.00018492239467849224,
      "loss": 1.0181,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.30657052993774414,
      "learning_rate": 0.0001844789356984479,
      "loss": 1.0949,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.2403457909822464,
      "learning_rate": 0.00018403547671840356,
      "loss": 1.0674,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.30654340982437134,
      "learning_rate": 0.0001835920177383592,
      "loss": 1.2225,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.2646230161190033,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.8863,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.19537745416164398,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.8136,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.2946692407131195,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.7739,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.25506192445755005,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.917,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.25431299209594727,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.8607,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.25379678606987,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.9536,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.3052731156349182,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.9212,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.29013338685035706,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.9172,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.26132503151893616,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.9132,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.25556033849716187,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.8975,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.24604447185993195,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.9775,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3651309311389923,
      "learning_rate": 0.00017827050997782707,
      "loss": 1.0722,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.29941031336784363,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.0118,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.22141927480697632,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.7191,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.24013017117977142,
      "learning_rate": 0.000176940133037694,
      "loss": 0.8956,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.22057652473449707,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.7262,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.2441413700580597,
      "learning_rate": 0.00017605321507760532,
      "loss": 1.0653,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.29345762729644775,
      "learning_rate": 0.000175609756097561,
      "loss": 1.045,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.2953290045261383,
      "learning_rate": 0.00017516629711751663,
      "loss": 1.0812,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.2912586033344269,
      "learning_rate": 0.0001747228381374723,
      "loss": 1.0766,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.23332780599594116,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.8158,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.2499706894159317,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.8437,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.27131178975105286,
      "learning_rate": 0.00017339246119733924,
      "loss": 1.0566,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.24329422414302826,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.9095,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.22750143706798553,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.7947,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.2624737620353699,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.9386,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.2711818516254425,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.9837,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.27666857838630676,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.8833,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.3417559266090393,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.9458,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.22324572503566742,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8771,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.2463648021221161,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.9063,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.26554247736930847,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.7789,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.2468937337398529,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.8174,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.25815922021865845,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.9862,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.31987327337265015,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.9373,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.2607921361923218,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.868,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.256076455116272,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.964,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.30199241638183594,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.9589,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.25212472677230835,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.7611,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.28898489475250244,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.8258,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.2534230947494507,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.9872,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.34786713123321533,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.8787,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.246382936835289,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.9206,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.24042193591594696,
      "learning_rate": 0.000164079822616408,
      "loss": 0.8852,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.2742517590522766,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.0141,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.35837244987487793,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.8341,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.34418734908103943,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.983,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.22571487724781036,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.922,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.2469213604927063,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.8723,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.25319820642471313,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.8899,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.26773932576179504,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.9122,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.319469153881073,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.9063,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.3045397102832794,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.9796,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.2373318076133728,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.7972,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.2942262589931488,
      "learning_rate": 0.00015920177383592018,
      "loss": 1.0482,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.2682504951953888,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.9848,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.2669702470302582,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.9132,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.3225294351577759,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.8952,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.26344791054725647,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.7989,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.24924379587173462,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.8447,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.2464321106672287,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.9466,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.23833177983760834,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.7899,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.2665916085243225,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.9145,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.347912073135376,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.9713,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.2539026141166687,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.9148,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.2564728558063507,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.9329,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.3068060874938965,
      "learning_rate": 0.00015388026607538802,
      "loss": 1.0892,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.2893538773059845,
      "learning_rate": 0.0001534368070953437,
      "loss": 1.1,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.2652214467525482,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.895,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.2822696566581726,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.9642,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.2733194828033447,
      "learning_rate": 0.00015210643015521066,
      "loss": 1.0426,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3380885720252991,
      "learning_rate": 0.0001516629711751663,
      "loss": 1.0605,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.30380016565322876,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.8828,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.2769828736782074,
      "learning_rate": 0.00015077605321507762,
      "loss": 1.0097,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.2908085882663727,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.9055,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.3042433261871338,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.9883,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.26983577013015747,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.872,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.2748490869998932,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.9954,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.22607482969760895,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.8797,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.2863655090332031,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.986,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.2706533968448639,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.8819,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.27256569266319275,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.814,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.28774821758270264,
      "learning_rate": 0.0001467849223946785,
      "loss": 1.0045,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.2880246341228485,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.8148,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.22975188493728638,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.7255,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.3559398651123047,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.0426,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.26260390877723694,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.7974,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.29924553632736206,
      "learning_rate": 0.00014456762749445675,
      "loss": 1.0016,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.2867199182510376,
      "learning_rate": 0.00014412416851441242,
      "loss": 1.0256,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.24110491573810577,
      "learning_rate": 0.00014368070953436806,
      "loss": 1.0062,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.3398730754852295,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.8798,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.3224598467350006,
      "learning_rate": 0.00014279379157427938,
      "loss": 1.0336,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.3525543808937073,
      "learning_rate": 0.00014235033259423505,
      "loss": 1.0595,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.3223823010921478,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.8172,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.2496713548898697,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.7775,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.24472974240779877,
      "learning_rate": 0.000141019955654102,
      "loss": 0.7616,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.23788590729236603,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.843,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.22866271436214447,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.8686,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.2880803346633911,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.8133,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.3186396658420563,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.8266,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.3100837767124176,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.9989,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.3032197058200836,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.7964,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.26381272077560425,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.7951,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.29895642399787903,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.9122,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.3034965395927429,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.9875,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.29225099086761475,
      "learning_rate": 0.00013658536585365856,
      "loss": 1.0497,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.27091482281684875,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.9453,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.30645209550857544,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.9241,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.33493053913116455,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.865,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.3289957642555237,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.8489,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.29001396894454956,
      "learning_rate": 0.0001343680709534368,
      "loss": 1.0196,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.26686790585517883,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.7279,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.24405522644519806,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.9722,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.3259618878364563,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.9367,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.3824666440486908,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.7387,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.2564922273159027,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.8994,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.3223087191581726,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.8789,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.27202287316322327,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.7464,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.3067648708820343,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.8302,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.2566090524196625,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.7577,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.30753663182258606,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.9198,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.32335028052330017,
      "learning_rate": 0.000129490022172949,
      "loss": 0.9276,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.3700528144836426,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.8151,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.26127123832702637,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.7975,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.3368043005466461,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.8798,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.33629676699638367,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.8675,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.25021353363990784,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.7169,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.35793545842170715,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.934,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.3116871118545532,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.8393,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.29269301891326904,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.6943,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.3115348815917969,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.6748,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.25913795828819275,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.7767,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.3764997720718384,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.841,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.2573704719543457,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.9767,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.347034752368927,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.9443,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.35626864433288574,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.7724,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.30096229910850525,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.8064,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.33854082226753235,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.8912,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.2561153173446655,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.8006,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.35288384556770325,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.7788,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.32962197065353394,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.8105,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.330152690410614,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.8561,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.3713672161102295,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.9064,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.3681902289390564,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.7937,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.3448575735092163,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.8962,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.3634438216686249,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.8184,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.3251909911632538,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.7097,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.36121052503585815,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.8797,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.38897934556007385,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.794,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.3509772717952728,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.9007,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.4110635817050934,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.7548,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.4391213059425354,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.9656,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.34741657972335815,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.8888,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.38059529662132263,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.7633,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.35730400681495667,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.8325,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.3571794927120209,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.8876,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.34386131167411804,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.7503,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.37305471301078796,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.8298,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.43587958812713623,
      "learning_rate": 0.00011308203991130821,
      "loss": 1.0244,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.42374899983406067,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.8814,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.4243118166923523,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.9307,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.3978307247161865,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.9259,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.39943623542785645,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.7532,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.41764727234840393,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.8222,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.43645957112312317,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.7125,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.3851727843284607,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.8622,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.37473347783088684,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.8233,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.3378634452819824,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.6141,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.4252351224422455,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.9509,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.37427589297294617,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.7176,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.332575261592865,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.9179,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.4058108627796173,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.9031,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.3690628409385681,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.6857,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.4522566497325897,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.811,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.4308803379535675,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.8971,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.47627875208854675,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.9088,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.38658806681632996,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.7868,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.3888651430606842,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.7831,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.38331109285354614,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.7802,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.3810722231864929,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.6881,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.4020719528198242,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.8184,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.42692068219184875,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.94,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.38645777106285095,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.8733,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.3883891701698303,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.8317,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.4348927140235901,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.8848,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.43304821848869324,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.9528,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.46210238337516785,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.8779,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.3665306270122528,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.7622,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.414601594209671,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.8313,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.3844327926635742,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.7779,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.36982735991477966,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.7441,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.41227850317955017,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.762,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.41558489203453064,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.8883,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.3549192249774933,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.7584,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.4222319424152374,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.7647,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.40838804841041565,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.7624,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.45156601071357727,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.8658,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.4446638226509094,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.8659,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.41718968749046326,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.7126,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.42325103282928467,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.8823,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.38767120242118835,
      "learning_rate": 9.445676274944568e-05,
      "loss": 0.8492,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.45927509665489197,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.8427,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.45483723282814026,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.9172,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.5018066763877869,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.944,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.4168771505355835,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.8637,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.45594704151153564,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.8242,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.4496884047985077,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.902,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.47609734535217285,
      "learning_rate": 9.135254988913526e-05,
      "loss": 1.0602,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.48761263489723206,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.7969,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.4995609223842621,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.7768,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.4266788959503174,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.7431,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.46587082743644714,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.8572,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.43794238567352295,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.8825,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.4323650896549225,
      "learning_rate": 8.869179600886919e-05,
      "loss": 0.8197,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.46451079845428467,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.9467,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.4118233323097229,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.9988,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.40218403935432434,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.9392,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.38731884956359863,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.7047,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.40897777676582336,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.7802,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.48364004492759705,
      "learning_rate": 8.603104212860311e-05,
      "loss": 0.8799,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.424683541059494,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.774,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.48241427540779114,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.858,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.4118233323097229,
      "learning_rate": 8.470066518847007e-05,
      "loss": 0.7979,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.431448757648468,
      "learning_rate": 8.425720620842572e-05,
      "loss": 0.8298,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.4889299273490906,
      "learning_rate": 8.381374722838138e-05,
      "loss": 0.8561,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.48912811279296875,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.7374,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.4408136308193207,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.8412,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.4046259820461273,
      "learning_rate": 8.248337028824834e-05,
      "loss": 0.7937,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.42287692427635193,
      "learning_rate": 8.2039911308204e-05,
      "loss": 0.8691,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.43346673250198364,
      "learning_rate": 8.159645232815965e-05,
      "loss": 0.7976,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.49521756172180176,
      "learning_rate": 8.11529933481153e-05,
      "loss": 0.8298,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.39719605445861816,
      "learning_rate": 8.070953436807095e-05,
      "loss": 0.8324,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.49136704206466675,
      "learning_rate": 8.026607538802661e-05,
      "loss": 0.9118,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.4690055549144745,
      "learning_rate": 7.982261640798227e-05,
      "loss": 0.8499,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.4954068064689636,
      "learning_rate": 7.937915742793793e-05,
      "loss": 0.8546,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.41638466715812683,
      "learning_rate": 7.893569844789357e-05,
      "loss": 0.8325,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.4888455271720886,
      "learning_rate": 7.849223946784923e-05,
      "loss": 0.8135,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.45901060104370117,
      "learning_rate": 7.804878048780489e-05,
      "loss": 0.7222,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.51753830909729,
      "learning_rate": 7.760532150776053e-05,
      "loss": 0.8365,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.49692103266716003,
      "learning_rate": 7.716186252771619e-05,
      "loss": 0.8654,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.43567755818367004,
      "learning_rate": 7.671840354767185e-05,
      "loss": 0.636,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.4655487835407257,
      "learning_rate": 7.627494456762749e-05,
      "loss": 0.8019,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.3646799921989441,
      "learning_rate": 7.583148558758315e-05,
      "loss": 0.6031,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.570026695728302,
      "learning_rate": 7.538802660753881e-05,
      "loss": 0.8259,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.4995371699333191,
      "learning_rate": 7.494456762749445e-05,
      "loss": 0.8976,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.4851059019565582,
      "learning_rate": 7.450110864745011e-05,
      "loss": 1.0404,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.5429724454879761,
      "learning_rate": 7.405764966740577e-05,
      "loss": 0.7501,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.3919091522693634,
      "learning_rate": 7.361419068736141e-05,
      "loss": 0.7617,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.5101870894432068,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.8821,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.5217682719230652,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.9254,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.37043899297714233,
      "learning_rate": 7.228381374722837e-05,
      "loss": 0.6348,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.4874213635921478,
      "learning_rate": 7.184035476718403e-05,
      "loss": 0.8839,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.4524523615837097,
      "learning_rate": 7.139689578713969e-05,
      "loss": 0.7836,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.4415155053138733,
      "learning_rate": 7.095343680709535e-05,
      "loss": 0.7287,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.4180910289287567,
      "learning_rate": 7.0509977827051e-05,
      "loss": 0.7229,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.43942537903785706,
      "learning_rate": 7.006651884700666e-05,
      "loss": 0.9758,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.45411768555641174,
      "learning_rate": 6.962305986696232e-05,
      "loss": 0.8657,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.5299389362335205,
      "learning_rate": 6.917960088691796e-05,
      "loss": 0.8721,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.4943889081478119,
      "learning_rate": 6.873614190687362e-05,
      "loss": 1.0215,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.4276939928531647,
      "learning_rate": 6.829268292682928e-05,
      "loss": 0.6959,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7421116232872009,
      "learning_rate": 6.784922394678492e-05,
      "loss": 0.9246,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.48450785875320435,
      "learning_rate": 6.740576496674058e-05,
      "loss": 0.8824,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.433089017868042,
      "learning_rate": 6.696230598669624e-05,
      "loss": 0.7267,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.5188565850257874,
      "learning_rate": 6.651884700665188e-05,
      "loss": 0.8052,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.4306478798389435,
      "learning_rate": 6.607538802660754e-05,
      "loss": 0.7429,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.4956829845905304,
      "learning_rate": 6.56319290465632e-05,
      "loss": 0.7868,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.521989643573761,
      "learning_rate": 6.518847006651884e-05,
      "loss": 0.8111,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.4799935817718506,
      "learning_rate": 6.47450110864745e-05,
      "loss": 0.7435,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.5171540379524231,
      "learning_rate": 6.430155210643016e-05,
      "loss": 0.6865,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.4364722967147827,
      "learning_rate": 6.38580931263858e-05,
      "loss": 0.6161,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.42384469509124756,
      "learning_rate": 6.341463414634146e-05,
      "loss": 0.7752,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.5198624134063721,
      "learning_rate": 6.297117516629712e-05,
      "loss": 0.7297,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.4433218538761139,
      "learning_rate": 6.252771618625277e-05,
      "loss": 0.9849,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.44770097732543945,
      "learning_rate": 6.208425720620842e-05,
      "loss": 0.5787,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.41243961453437805,
      "learning_rate": 6.164079822616408e-05,
      "loss": 0.7621,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.5933434963226318,
      "learning_rate": 6.119733924611974e-05,
      "loss": 0.7334,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.48033902049064636,
      "learning_rate": 6.075388026607539e-05,
      "loss": 0.6241,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.5377805829048157,
      "learning_rate": 6.031042128603105e-05,
      "loss": 0.6079,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.6087806224822998,
      "learning_rate": 5.98669623059867e-05,
      "loss": 0.7791,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 0.481659859418869,
      "learning_rate": 5.942350332594236e-05,
      "loss": 0.7125,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.5312716364860535,
      "learning_rate": 5.898004434589801e-05,
      "loss": 0.7319,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 0.4442366361618042,
      "learning_rate": 5.853658536585366e-05,
      "loss": 0.6331,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 0.4814037084579468,
      "learning_rate": 5.809312638580932e-05,
      "loss": 0.742,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.5577096343040466,
      "learning_rate": 5.7649667405764975e-05,
      "loss": 0.8529,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.46902143955230713,
      "learning_rate": 5.720620842572062e-05,
      "loss": 0.783,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.492708295583725,
      "learning_rate": 5.676274944567628e-05,
      "loss": 0.6733,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.4918416440486908,
      "learning_rate": 5.6319290465631935e-05,
      "loss": 0.8169,
      "step": 330
    },
    {
      "epoch": 2.178021978021978,
      "grad_norm": 0.49124279618263245,
      "learning_rate": 5.587583148558758e-05,
      "loss": 0.6956,
      "step": 331
    },
    {
      "epoch": 2.184615384615385,
      "grad_norm": 0.4592980146408081,
      "learning_rate": 5.543237250554324e-05,
      "loss": 0.7058,
      "step": 332
    },
    {
      "epoch": 2.1912087912087914,
      "grad_norm": 0.5117436051368713,
      "learning_rate": 5.4988913525498895e-05,
      "loss": 0.7569,
      "step": 333
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.5655015110969543,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.6956,
      "step": 334
    },
    {
      "epoch": 2.2043956043956046,
      "grad_norm": 0.5430145859718323,
      "learning_rate": 5.4101995565410204e-05,
      "loss": 0.7412,
      "step": 335
    },
    {
      "epoch": 2.210989010989011,
      "grad_norm": 0.47221046686172485,
      "learning_rate": 5.365853658536586e-05,
      "loss": 0.6909,
      "step": 336
    },
    {
      "epoch": 2.2175824175824177,
      "grad_norm": 0.48648378252983093,
      "learning_rate": 5.3215077605321506e-05,
      "loss": 0.629,
      "step": 337
    },
    {
      "epoch": 2.2241758241758243,
      "grad_norm": 0.5526441931724548,
      "learning_rate": 5.2771618625277164e-05,
      "loss": 0.9545,
      "step": 338
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.4849708080291748,
      "learning_rate": 5.232815964523282e-05,
      "loss": 0.6377,
      "step": 339
    },
    {
      "epoch": 2.2373626373626374,
      "grad_norm": 0.6233583092689514,
      "learning_rate": 5.1884700665188466e-05,
      "loss": 0.672,
      "step": 340
    },
    {
      "epoch": 2.243956043956044,
      "grad_norm": 0.5312808156013489,
      "learning_rate": 5.1441241685144124e-05,
      "loss": 0.6369,
      "step": 341
    },
    {
      "epoch": 2.2505494505494505,
      "grad_norm": 0.5869351029396057,
      "learning_rate": 5.099778270509978e-05,
      "loss": 0.695,
      "step": 342
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 0.584661602973938,
      "learning_rate": 5.0554323725055433e-05,
      "loss": 0.6961,
      "step": 343
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 0.5198956727981567,
      "learning_rate": 5.011086474501109e-05,
      "loss": 0.7041,
      "step": 344
    },
    {
      "epoch": 2.2703296703296703,
      "grad_norm": 0.5206749439239502,
      "learning_rate": 4.966740576496674e-05,
      "loss": 0.5057,
      "step": 345
    },
    {
      "epoch": 2.276923076923077,
      "grad_norm": 0.5449419617652893,
      "learning_rate": 4.92239467849224e-05,
      "loss": 0.8387,
      "step": 346
    },
    {
      "epoch": 2.2835164835164834,
      "grad_norm": 0.580464780330658,
      "learning_rate": 4.878048780487805e-05,
      "loss": 0.7704,
      "step": 347
    },
    {
      "epoch": 2.29010989010989,
      "grad_norm": 0.5909473299980164,
      "learning_rate": 4.833702882483371e-05,
      "loss": 0.7464,
      "step": 348
    },
    {
      "epoch": 2.2967032967032965,
      "grad_norm": 0.6433005928993225,
      "learning_rate": 4.789356984478936e-05,
      "loss": 0.6783,
      "step": 349
    },
    {
      "epoch": 2.303296703296703,
      "grad_norm": 0.5280606746673584,
      "learning_rate": 4.745011086474501e-05,
      "loss": 0.6453,
      "step": 350
    },
    {
      "epoch": 2.3098901098901097,
      "grad_norm": 0.6551902890205383,
      "learning_rate": 4.700665188470067e-05,
      "loss": 0.7583,
      "step": 351
    },
    {
      "epoch": 2.3164835164835162,
      "grad_norm": 0.5302130579948425,
      "learning_rate": 4.656319290465632e-05,
      "loss": 0.7089,
      "step": 352
    },
    {
      "epoch": 2.3230769230769233,
      "grad_norm": 0.5599292516708374,
      "learning_rate": 4.611973392461197e-05,
      "loss": 0.5758,
      "step": 353
    },
    {
      "epoch": 2.32967032967033,
      "grad_norm": 0.4949183762073517,
      "learning_rate": 4.567627494456763e-05,
      "loss": 0.655,
      "step": 354
    },
    {
      "epoch": 2.3362637362637364,
      "grad_norm": 0.5712494850158691,
      "learning_rate": 4.523281596452328e-05,
      "loss": 0.7972,
      "step": 355
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 0.5453433990478516,
      "learning_rate": 4.478935698447894e-05,
      "loss": 0.6013,
      "step": 356
    },
    {
      "epoch": 2.3494505494505495,
      "grad_norm": 0.5077885389328003,
      "learning_rate": 4.4345898004434597e-05,
      "loss": 0.6505,
      "step": 357
    },
    {
      "epoch": 2.356043956043956,
      "grad_norm": 0.49416041374206543,
      "learning_rate": 4.390243902439025e-05,
      "loss": 0.5852,
      "step": 358
    },
    {
      "epoch": 2.3626373626373627,
      "grad_norm": 0.576293408870697,
      "learning_rate": 4.34589800443459e-05,
      "loss": 0.7791,
      "step": 359
    },
    {
      "epoch": 2.3692307692307693,
      "grad_norm": 0.5039152503013611,
      "learning_rate": 4.301552106430156e-05,
      "loss": 0.5598,
      "step": 360
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.706571976454963e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}