{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5802197802197804,
  "eval_steps": 500,
  "global_step": 240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.02959144115448,
      "learning_rate": 0.0,
      "loss": 3.3348,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.0243064165115356,
      "learning_rate": 4e-05,
      "loss": 3.3843,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.9533873796463013,
      "learning_rate": 8e-05,
      "loss": 3.1602,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.3778162002563477,
      "learning_rate": 0.00012,
      "loss": 3.8548,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.5720551013946533,
      "learning_rate": 0.00016,
      "loss": 3.334,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.0702953338623047,
      "learning_rate": 0.0002,
      "loss": 3.2436,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 1.883508563041687,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.4118,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.8991221189498901,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.7996,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.943290114402771,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.7992,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.1848249435424805,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.3218,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.8290153741836548,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.1483,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.782597541809082,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.1466,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 1.070041537284851,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0435,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.7890101671218872,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.1189,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.6797720789909363,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.9294,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.6561483144760132,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.8717,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.6154541969299316,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.9475,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.6936250925064087,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.1112,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.4830031096935272,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.8719,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.4977757930755615,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.8456,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.4251507520675659,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.7946,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.5000141263008118,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.9003,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.5055630803108215,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.8483,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.5189692378044128,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.862,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.39381036162376404,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.73,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.4727248549461365,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9574,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.5471789836883545,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.8291,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.4908490777015686,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.7855,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.5352988243103027,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.8019,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.4222325384616852,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.7782,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.5250545740127563,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.827,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.5112847685813904,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.7717,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.45085787773132324,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.8548,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.5169785618782043,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.8469,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.4831181466579437,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.7138,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.4298362731933594,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.6416,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.4677696228027344,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.8296,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.4513629376888275,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.6803,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.4796628952026367,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.7778,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.4168303906917572,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.748,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3913823962211609,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.8508,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.46302542090415955,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.86,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.43823087215423584,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.7062,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.4874539375305176,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.7632,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.44593605399131775,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.8815,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.4195469915866852,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.7796,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.40345215797424316,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.6468,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.4226957857608795,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.6274,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.477471262216568,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.7629,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.39429357647895813,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.6709,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.4581214189529419,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.7036,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.4935621917247772,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.6878,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.45704221725463867,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.7126,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.4570856988430023,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.7569,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.4568769037723541,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.7162,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.4904540181159973,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.7308,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.4313798248767853,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.635,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.5561969876289368,
      "learning_rate": 0.000176940133037694,
      "loss": 0.7838,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.44863128662109375,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.6366,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.4197455048561096,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.7589,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.4661950170993805,
      "learning_rate": 0.000175609756097561,
      "loss": 0.725,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.46837183833122253,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.64,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.5886682868003845,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.5071,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.5030215978622437,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.692,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.5501147508621216,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.8112,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.4744016230106354,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.6571,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.4610467553138733,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.6737,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.495379239320755,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.7577,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.4832289516925812,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.6387,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.5150049924850464,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.8346,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.4854123294353485,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.6864,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.45552781224250793,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.6789,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.4643484652042389,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.6516,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.4445684254169464,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.6762,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.5563467741012573,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.7624,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.4668287932872772,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.5379,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.424448698759079,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.6594,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.47027847170829773,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.6288,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.4704686403274536,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.7025,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.5712776184082031,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.6923,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.5098185539245605,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.6952,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.5409852266311646,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.6023,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.6706210374832153,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.713,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.34992656111717224,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.7375,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.6524062156677246,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.739,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.5203568935394287,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.7482,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.6416592597961426,
      "learning_rate": 0.000164079822616408,
      "loss": 0.7033,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.4666348695755005,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.6811,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.6599462628364563,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.7908,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.551964521408081,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.6226,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.429592490196228,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.6602,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.5001062750816345,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.6884,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.4265173375606537,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.6613,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.4387926757335663,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.6829,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.5375656485557556,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.6584,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.511247992515564,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.6725,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.49439311027526855,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.7958,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.521442174911499,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.6591,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.5001063942909241,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.7915,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.741524338722229,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.6201,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.49745646119117737,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.915,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.5976807475090027,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.7476,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.47543030977249146,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.8067,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.5175777673721313,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.618,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.5875190496444702,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.6178,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.5990605354309082,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.8333,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.4318668246269226,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.6031,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.5853533148765564,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.7543,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.49782299995422363,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.5579,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.42551514506340027,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.5257,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.5900877118110657,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.7055,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.5216739773750305,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.6168,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.5634824633598328,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.7089,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.4747273623943329,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.7088,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.4328377842903137,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.6372,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.5172659158706665,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.7256,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.4680604934692383,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.6149,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.46906736493110657,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.6567,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.4467626214027405,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.6442,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.5085018873214722,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.5982,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.48549792170524597,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.7073,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.5844902992248535,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.8029,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.5346658229827881,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.6362,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.4461691677570343,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.7739,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.42769137024879456,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.6618,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.48869189620018005,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.6939,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.5522583723068237,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.675,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.6224931478500366,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.7831,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.5227327942848206,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.6792,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.5302318930625916,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.6413,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.5150425434112549,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.8127,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.473909467458725,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.718,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.42604658007621765,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.6352,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.5411060452461243,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.6788,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.4210425019264221,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.6636,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.45586320757865906,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.6941,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.5273366570472717,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.7422,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.4869183897972107,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.5557,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.5795156359672546,
      "learning_rate": 0.000141019955654102,
      "loss": 0.5999,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.6669048070907593,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.6658,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.5720503330230713,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.7401,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.47832322120666504,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.6083,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.5493850708007812,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.782,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.5128207802772522,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.5707,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.6153551936149597,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.7508,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.4160095453262329,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.6013,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.5060651302337646,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.5902,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.4234674870967865,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.6782,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.4937916100025177,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.568,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.6047046184539795,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.6228,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.5233971476554871,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.686,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.558993399143219,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.6521,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.4167839586734772,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.617,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.4800107479095459,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.5473,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.43436679244041443,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.6902,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.43532222509384155,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.6205,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.49403300881385803,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.6399,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.4887068569660187,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.6795,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.515297532081604,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.6483,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.5023236870765686,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.6369,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.4966796338558197,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.5022,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.5202856659889221,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.5507,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.5792418718338013,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.4337,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.617599606513977,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.677,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.41561445593833923,
      "learning_rate": 0.000129490022172949,
      "loss": 0.4695,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.5432271361351013,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.5082,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.5408562421798706,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.4167,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.5078502893447876,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.4723,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.5127493143081665,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.5109,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.5111672878265381,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.6219,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.5197771191596985,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.5634,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.5449637770652771,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.5008,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.5015102028846741,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.8306,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.44224315881729126,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.4353,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.5046929717063904,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.4312,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.45239609479904175,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.6467,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.5794095396995544,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.682,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.5387376546859741,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.6275,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.5860198140144348,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.541,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.5118013620376587,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.5416,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.490705281496048,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.4202,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.5507169961929321,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.4776,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.512652575969696,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.4503,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.669562041759491,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.5664,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.6799061894416809,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.4445,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.5918152928352356,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.5561,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.5839580297470093,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.4046,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.5532559156417847,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.4096,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.6861527562141418,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.659,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.6460908651351929,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.5529,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.5881571769714355,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.4539,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.5775097608566284,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.5233,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.6747599244117737,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.4591,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.6361888647079468,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.6006,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.5714813470840454,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.4343,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.5569661259651184,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.5319,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.5805423259735107,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.4222,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.6298860311508179,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.6575,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.6842706799507141,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.5465,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.6930952668190002,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.497,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.6609947681427002,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.59,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.6691651344299316,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.4566,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.7421806454658508,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.5731,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.7516620755195618,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.6346,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.7663669586181641,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.5493,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.6477105021476746,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.4923,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.6064060926437378,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.6335,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.686930775642395,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.5859,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.8102238178253174,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.6217,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.7128576040267944,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.4252,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.6690284609794617,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.4973,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.6318286061286926,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.5524,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.5983303189277649,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.4948,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.7668845057487488,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.5259,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.7168291211128235,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.4258,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.6599907279014587,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.5844,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.7194671630859375,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.5531,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.6974961161613464,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.5365,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.7058278322219849,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.4317,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.7691466808319092,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.4768,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.7972515821456909,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.5635,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.6399233341217041,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.4378,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.6822931170463562,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.5346,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.867255449295044,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.6005,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.7509020566940308,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.6108,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.6790703535079956,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.4454,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.6685671210289001,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.456,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.726274847984314,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.417,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.7956055402755737,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.5426,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.7833002805709839,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.4566,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.8292689919471741,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.5194,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.7871679067611694,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.5485,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.7078747749328613,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.4337,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.8382088541984558,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.528,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.9261732697486877,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.6008,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.8290076851844788,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.5768,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.8013708591461182,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.4287,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.7182276844978333,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.4193,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.7458386421203613,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.58,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.8419430255889893,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.6475,
      "step": 240
    }
  ],
  "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": 9.514775793722573e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}