{
  "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": 1.6525499820709229,
      "learning_rate": 0.0,
      "loss": 2.4309,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 2.59049391746521,
      "learning_rate": 4e-05,
      "loss": 3.2935,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.4867584705352783,
      "learning_rate": 8e-05,
      "loss": 2.4426,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.8229094743728638,
      "learning_rate": 0.00012,
      "loss": 2.9208,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.2393176555633545,
      "learning_rate": 0.00016,
      "loss": 2.5664,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.6051244735717773,
      "learning_rate": 0.0002,
      "loss": 2.4695,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.1993753910064697,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.6291,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 2.116241693496704,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.3491,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.8124693632125854,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.3178,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.4746452569961548,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.3747,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.0956214666366577,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2291,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5584886074066162,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.2929,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.8778825402259827,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0355,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5020594596862793,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.1668,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.4985601305961609,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.1048,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.4597553312778473,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.0144,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.44980549812316895,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.128,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.33276212215423584,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.9434,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.46772485971450806,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.2302,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.3876091241836548,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.0448,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3786633610725403,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0449,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.4180683195590973,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.1112,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.4051693081855774,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.0586,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.30783703923225403,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.9412,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3420283794403076,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.9213,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.47376200556755066,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9635,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.3626822233200073,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.7696,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.46646377444267273,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.098,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.38763922452926636,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.1587,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3439793288707733,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.1153,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.30000773072242737,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.9554,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3823530972003937,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.8394,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.34664639830589294,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9849,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.3785923719406128,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.9833,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.2902650535106659,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.8436,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3445191979408264,
      "learning_rate": 0.00018669623059866964,
      "loss": 1.1307,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3029124438762665,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.9933,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.35134652256965637,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.0888,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3323468863964081,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.9426,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.30780231952667236,
      "learning_rate": 0.00018492239467849224,
      "loss": 1.0471,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.33622869849205017,
      "learning_rate": 0.0001844789356984479,
      "loss": 1.0502,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.27680298686027527,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.9102,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.30690091848373413,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.8996,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.25448524951934814,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.1005,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.34958240389823914,
      "learning_rate": 0.00018270509977827052,
      "loss": 1.0281,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.4468621015548706,
      "learning_rate": 0.00018226164079822616,
      "loss": 1.0252,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.31876784563064575,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.8992,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.34545132517814636,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.068,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.32640132308006287,
      "learning_rate": 0.00018093126385809312,
      "loss": 1.1285,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.3564831018447876,
      "learning_rate": 0.0001804878048780488,
      "loss": 1.2185,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.32339203357696533,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.0446,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.35078808665275574,
      "learning_rate": 0.00017960088691796008,
      "loss": 1.1539,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.2938004732131958,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.9885,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.3535275459289551,
      "learning_rate": 0.0001787139689578714,
      "loss": 1.2243,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.27938902378082275,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.8127,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.3669883906841278,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.1137,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.29758307337760925,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.8903,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.33421579003334045,
      "learning_rate": 0.000176940133037694,
      "loss": 0.9599,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.2770750820636749,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.8669,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.30138126015663147,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.9341,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.40909135341644287,
      "learning_rate": 0.000175609756097561,
      "loss": 0.9882,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3172509968280792,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.947,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3970111012458801,
      "learning_rate": 0.0001747228381374723,
      "loss": 1.0486,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.31454795598983765,
      "learning_rate": 0.00017427937915742792,
      "loss": 1.0186,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3479641079902649,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.9327,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3524766266345978,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.9507,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.2844376266002655,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.7746,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.3422749638557434,
      "learning_rate": 0.00017250554323725056,
      "loss": 1.0457,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.4011959135532379,
      "learning_rate": 0.00017206208425720623,
      "loss": 1.007,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.4012478291988373,
      "learning_rate": 0.00017161862527716187,
      "loss": 1.0548,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3155313730239868,
      "learning_rate": 0.00017117516629711752,
      "loss": 1.0115,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.42125996947288513,
      "learning_rate": 0.0001707317073170732,
      "loss": 1.0328,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.24873152375221252,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8636,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3159611225128174,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.8,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.33214104175567627,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.9654,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.347202867269516,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.9652,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.2956635653972626,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.8443,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.32437971234321594,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.7974,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.34554967284202576,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.8792,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.36469560861587524,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.866,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.344759076833725,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.8353,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.34023046493530273,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.02,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.333598256111145,
      "learning_rate": 0.00016585365853658536,
      "loss": 1.0249,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3101555109024048,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.9582,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.33129116892814636,
      "learning_rate": 0.00016496674057649667,
      "loss": 1.1624,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.30904698371887207,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.9186,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3824373483657837,
      "learning_rate": 0.000164079822616408,
      "loss": 1.0527,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.32758963108062744,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.1586,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.39826932549476624,
      "learning_rate": 0.0001631929046563193,
      "loss": 1.2648,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.3101160526275635,
      "learning_rate": 0.00016274944567627495,
      "loss": 1.0503,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.5018938183784485,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.8718,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.314115434885025,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.9757,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.3091287314891815,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.9042,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.3007432520389557,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.9866,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.33295589685440063,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.8291,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.3381161689758301,
      "learning_rate": 0.00016008869179600887,
      "loss": 1.0308,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.3053942024707794,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.7676,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.32999739050865173,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.7638,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.4934881627559662,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.9291,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.36715981364250183,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.9131,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.3625679314136505,
      "learning_rate": 0.00015787139689578714,
      "loss": 1.0562,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.36306384205818176,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.9225,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.2506583333015442,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.7906,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.34501585364341736,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.866,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.3541669547557831,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.936,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.3231780230998993,
      "learning_rate": 0.00015565410199556542,
      "loss": 1.009,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.30839109420776367,
      "learning_rate": 0.00015521064301552106,
      "loss": 1.192,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.2860703468322754,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.8922,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.3583816885948181,
      "learning_rate": 0.00015432372505543238,
      "loss": 1.0708,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.33360984921455383,
      "learning_rate": 0.00015388026607538802,
      "loss": 1.0233,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.34765884280204773,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.913,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.326040655374527,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.8333,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.3660181760787964,
      "learning_rate": 0.00015254988913525498,
      "loss": 1.0709,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.37662452459335327,
      "learning_rate": 0.00015210643015521066,
      "loss": 1.1435,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3499009907245636,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.9603,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.25945529341697693,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.9645,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.34172216057777405,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.9783,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.2964763045310974,
      "learning_rate": 0.0001503325942350333,
      "loss": 1.0131,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.280081570148468,
      "learning_rate": 0.0001498891352549889,
      "loss": 1.0352,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.4915473461151123,
      "learning_rate": 0.00014944567627494458,
      "loss": 1.1019,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.3027263581752777,
      "learning_rate": 0.00014900221729490022,
      "loss": 1.0324,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.31653857231140137,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.9722,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.3870300054550171,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.9521,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.31218865513801575,
      "learning_rate": 0.0001476718403547672,
      "loss": 1.0037,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.3220807909965515,
      "learning_rate": 0.00014722838137472282,
      "loss": 1.089,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.2677379548549652,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.7959,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.33389076590538025,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.8544,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.3093551695346832,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.9041,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.2977532148361206,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.9339,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.2609766125679016,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.8509,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.328764408826828,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.9613,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.34873923659324646,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.8578,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.3248665928840637,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.9369,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.33797210454940796,
      "learning_rate": 0.00014323725055432373,
      "loss": 1.0622,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.3088889420032501,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.9253,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.3533850908279419,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.9182,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.40451779961586,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.8442,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.33084341883659363,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.824,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.31345072388648987,
      "learning_rate": 0.000141019955654102,
      "loss": 0.9001,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.3291054666042328,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.9342,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.3141261339187622,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.897,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.31741398572921753,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.9915,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.3589644432067871,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.8985,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.36022889614105225,
      "learning_rate": 0.00013880266075388026,
      "loss": 1.023,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.37724706530570984,
      "learning_rate": 0.00013835920177383593,
      "loss": 1.0334,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.3073366582393646,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.9127,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.3582838177680969,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.9063,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.32595396041870117,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.7566,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.3323315680027008,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.8991,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.31097739934921265,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.8336,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.28176063299179077,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.8019,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5535985827445984,
      "learning_rate": 0.0001352549889135255,
      "loss": 1.0361,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.29516372084617615,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.91,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.3543173670768738,
      "learning_rate": 0.0001343680709534368,
      "loss": 1.0058,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.38949835300445557,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.7881,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.3360844552516937,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.7793,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.32752725481987,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.9641,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.3531540036201477,
      "learning_rate": 0.00013259423503325944,
      "loss": 1.0192,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.33559122681617737,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.8055,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.3770013153553009,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.8351,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.3123881220817566,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.7128,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.26182934641838074,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.7649,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.26431235671043396,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.7429,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.43121954798698425,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.8651,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.309425413608551,
      "learning_rate": 0.000129490022172949,
      "loss": 0.6285,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.3685239255428314,
      "learning_rate": 0.00012904656319290468,
      "loss": 1.0647,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.26674482226371765,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.7441,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.48278793692588806,
      "learning_rate": 0.00012815964523281597,
      "loss": 1.0298,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.3902539014816284,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.8763,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.43501222133636475,
      "learning_rate": 0.00012727272727272728,
      "loss": 1.0258,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.36463525891304016,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.9459,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.3361537456512451,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.8334,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.3888196349143982,
      "learning_rate": 0.00012594235033259424,
      "loss": 1.112,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.4237583875656128,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.8316,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.37899884581565857,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.8125,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.30603137612342834,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.79,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.38935360312461853,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.8449,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.46504923701286316,
      "learning_rate": 0.00012372505543237252,
      "loss": 1.1637,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.37974920868873596,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.7895,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.44517454504966736,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.8115,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.31400156021118164,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.8794,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.4058041274547577,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.837,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.3683865964412689,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.8219,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.3810867369174957,
      "learning_rate": 0.00012106430155210644,
      "loss": 1.0203,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.4762330651283264,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.926,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.4322555363178253,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.9294,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.3780699074268341,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.8904,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.44516417384147644,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.7837,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.4465552568435669,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.96,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.43639782071113586,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.8267,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.5585591197013855,
      "learning_rate": 0.00011796008869179602,
      "loss": 1.0051,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.4337552487850189,
      "learning_rate": 0.00011751662971175166,
      "loss": 1.0171,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.4324861764907837,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.8813,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.4322637915611267,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.8898,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.5295554995536804,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.9328,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.44548794627189636,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.7084,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.4655121862888336,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.925,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.465004563331604,
      "learning_rate": 0.00011485587583148558,
      "loss": 1.0436,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.4021751582622528,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.7306,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.3959920406341553,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.7864,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.4573391377925873,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.9226,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.5056650042533875,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.8219,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.4371558129787445,
      "learning_rate": 0.00011263858093126387,
      "loss": 1.0047,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.4842739999294281,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.7322,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.8172526955604553,
      "learning_rate": 0.00011175166297117516,
      "loss": 1.0128,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.44949787855148315,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.85,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.45186272263526917,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.6802,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.4584757089614868,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.8161,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.4862142503261566,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.8785,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.5115880370140076,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.8237,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.5136667490005493,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.894,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.4120652973651886,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.8051,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.5302851796150208,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.8395,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.38329094648361206,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.7402,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.4526435434818268,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.6514,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.46651050448417664,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.8064,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.4789561927318573,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.7965,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.504118800163269,
      "learning_rate": 0.00010598669623059867,
      "loss": 1.0565,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.5061677694320679,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.9476,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.4608421325683594,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.8965,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.3995113968849182,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.8571,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.3929450511932373,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.803,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.47698885202407837,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.9712,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.36496636271476746,
      "learning_rate": 0.00010332594235033259,
      "loss": 1.0349,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.543424129486084,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.8917,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.4975453019142151,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.9042,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.513408362865448,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.8378,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.5649193525314331,
      "learning_rate": 0.00010155210643015522,
      "loss": 1.0589,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.6057289838790894,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.997,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.5099395513534546,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.998,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.4942122995853424,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.8104,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.5093843340873718,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.7819,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.511997401714325,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.8423,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.5232946276664734,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.8661,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.5954769849777222,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.8877,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.44104084372520447,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.8592,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.5269781351089478,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.8698,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.6050085425376892,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.9756,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.4890908896923065,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.7871,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.5456884503364563,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.8255,
      "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": 3.884594306624717e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}