{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.8637362637362638,
  "eval_steps": 500,
  "global_step": 435,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 0.8077017664909363,
      "learning_rate": 0.0,
      "loss": 0.9887,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 0.7523753643035889,
      "learning_rate": 4e-05,
      "loss": 0.9009,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.765389084815979,
      "learning_rate": 8e-05,
      "loss": 0.9624,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 0.8093127608299255,
      "learning_rate": 0.00012,
      "loss": 0.9637,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.9327186346054077,
      "learning_rate": 0.00016,
      "loss": 0.9527,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.5091996192932129,
      "learning_rate": 0.0002,
      "loss": 0.7905,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.6602445840835571,
      "learning_rate": 0.00019955654101995565,
      "loss": 0.8583,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.5978100895881653,
      "learning_rate": 0.00019911308203991133,
      "loss": 0.8993,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.5891162753105164,
      "learning_rate": 0.00019866962305986697,
      "loss": 0.8058,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.4584941565990448,
      "learning_rate": 0.00019822616407982261,
      "loss": 0.8163,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.47484591603279114,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.8463,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.351951539516449,
      "learning_rate": 0.00019733924611973393,
      "loss": 0.7677,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.2790893614292145,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.7058,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.20740701258182526,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.7831,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.224847674369812,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.6561,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.27322402596473694,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.8321,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.22497926652431488,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.6968,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.28976911306381226,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.7469,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.2779470980167389,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.6422,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.2726289927959442,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.6917,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.32078272104263306,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.727,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3546641170978546,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.7902,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3228413760662079,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.6833,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.2988794147968292,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.671,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.2913096249103546,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.711,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.28192418813705444,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.7053,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.28685078024864197,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.7591,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.29851487278938293,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.8045,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.23794184625148773,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.6879,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.23139610886573792,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.707,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.24261024594306946,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.6653,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.2187165468931198,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.6428,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.26563167572021484,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.6604,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.2721128463745117,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.671,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.23759715259075165,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.6776,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.2488459199666977,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.6945,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.23577633500099182,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.7494,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.24760209023952484,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.7127,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.2727614939212799,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.6169,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.23416593670845032,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.6454,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.28653931617736816,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.7644,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.30816516280174255,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.7383,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.2630719542503357,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.685,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.24640275537967682,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.7253,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.2474466860294342,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.6784,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.2202293425798416,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.6593,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.2550554871559143,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.6976,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.25797396898269653,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.664,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.34011200070381165,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.734,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.24847422540187836,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.7315,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.21630249917507172,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.6585,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.27460163831710815,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.6613,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.24249251186847687,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.7606,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.27401289343833923,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.6403,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.23189976811408997,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.6579,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.2888374626636505,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.7065,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.22406132519245148,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.6882,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.20498928427696228,
      "learning_rate": 0.000176940133037694,
      "loss": 0.6585,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.23647762835025787,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.6065,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.26996946334838867,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.6717,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.27953213453292847,
      "learning_rate": 0.000175609756097561,
      "loss": 0.7811,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.24994726479053497,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.7874,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.24634505808353424,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.7353,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.23995284736156464,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.7199,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.23969849944114685,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.6682,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.24753603339195251,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.6345,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.25502079725265503,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.7209,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.24455444514751434,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.7349,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.28426915407180786,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.691,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.2716725170612335,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.7302,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.24627460539340973,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.6846,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.2583073377609253,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.668,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.2567511200904846,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.7579,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.26131707429885864,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.7136,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.23471911251544952,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.6961,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.2195940464735031,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.646,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.23043136298656464,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.7342,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.24426446855068207,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.7003,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.24054990708827972,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.6873,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.22914347052574158,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.6545,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.26548057794570923,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.6716,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.26090720295906067,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.7119,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.19147682189941406,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.64,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.21883703768253326,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.7559,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.2173861861228943,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.6988,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.2113824486732483,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.7929,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.25258970260620117,
      "learning_rate": 0.000164079822616408,
      "loss": 0.6593,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.2212488353252411,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.7345,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.2389560341835022,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.6899,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.2408762276172638,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.6782,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.26670125126838684,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.6974,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.25152724981307983,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.7145,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.26121988892555237,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.717,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.24530276656150818,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.7213,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.2343507707118988,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.6385,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.20087078213691711,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.6815,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.2694112956523895,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.7067,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.21269765496253967,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.7219,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.22413238883018494,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.6669,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.21722529828548431,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.6692,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.2504139542579651,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.6418,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.23298482596874237,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.6893,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.21787787973880768,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.6851,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.21027401089668274,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.6954,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.25054827332496643,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.6924,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.22826993465423584,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.7403,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.2577382028102875,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.6611,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.21939462423324585,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.642,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.20012962818145752,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.6408,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.22713278234004974,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.682,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.23737652599811554,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.7028,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.2669889032840729,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.6578,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.24940653145313263,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.7106,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.23241238296031952,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.7195,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.21564380824565887,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.6742,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.2113444060087204,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.6895,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.2382802665233612,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.8483,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.2202911078929901,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.7001,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.20593562722206116,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.6996,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.20558840036392212,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.7296,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.21931356191635132,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.6656,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.2617608606815338,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.6548,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.2506304979324341,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.7402,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.28052857518196106,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.5783,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.2687359154224396,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.6872,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.25916817784309387,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.676,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.269065260887146,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.6371,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.23729294538497925,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.6965,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.23053863644599915,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.6534,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.23717789351940155,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.6844,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.21095876395702362,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.7731,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.21727360785007477,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.6502,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.22151313722133636,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.6978,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.21052038669586182,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.6175,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.21093420684337616,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.6499,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.225594162940979,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.7145,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.22462083399295807,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.7183,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.22764378786087036,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.6572,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.22606384754180908,
      "learning_rate": 0.000141019955654102,
      "loss": 0.6062,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.22973784804344177,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.7111,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.2363857477903366,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.6886,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.24516572058200836,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.6531,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.24978530406951904,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.6228,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.24957957863807678,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.7004,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.21780256927013397,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.7102,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.23822268843650818,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.6118,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.20289704203605652,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.6886,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.2438238263130188,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.7397,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.22133423388004303,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.6404,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.2018754631280899,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.6337,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.22072115540504456,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.6772,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.28079548478126526,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.6397,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.232382133603096,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.6071,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.2601761817932129,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.6103,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.2203921377658844,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.6495,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.23914580047130585,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.6648,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.2667677104473114,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.6814,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.23313704133033752,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.6058,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.2429087907075882,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.6381,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.26997268199920654,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.6817,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.2587141990661621,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.6236,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.23588891327381134,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.621,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.23202061653137207,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.6736,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.21766787767410278,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.6128,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.2406807541847229,
      "learning_rate": 0.000129490022172949,
      "loss": 0.6389,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.24828147888183594,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.7085,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.23612111806869507,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.6507,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.2180779129266739,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.5768,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.24062983691692352,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.6616,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.26763615012168884,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.7021,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.23063182830810547,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.7328,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.28771325945854187,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.6431,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.2550864815711975,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.7015,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.22699037194252014,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.7124,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.2582772374153137,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.6555,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.23609748482704163,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.6692,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.23890641331672668,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.6579,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.2444433867931366,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.5809,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.2541671693325043,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.6248,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.2675187885761261,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.6446,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.24710074067115784,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.6958,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.26115259528160095,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.6072,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.2584088146686554,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.7139,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.2508622705936432,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.6891,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.23005181550979614,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.7362,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.25642529129981995,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.7115,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.24418359994888306,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.6847,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.27225470542907715,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.6467,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.2445187270641327,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.6837,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.2522325813770294,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.5973,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.29015442728996277,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.6485,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.2669098973274231,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.6932,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.2966671884059906,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.6226,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.26699814200401306,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.6323,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.26266252994537354,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.6605,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.3513379693031311,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.6668,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.29028186202049255,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.6953,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.24698711931705475,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.5995,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.2789497971534729,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.6409,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.22779995203018188,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.5886,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.3301622271537781,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.6616,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.2717677354812622,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.6985,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.26959317922592163,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.5898,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.2560386061668396,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.6726,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.2860150635242462,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.6676,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.25546208024024963,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.6749,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.36086368560791016,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.659,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.30359092354774475,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.5703,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.2877999246120453,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.6937,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.28343451023101807,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.662,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.2527635991573334,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.6158,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.2869073450565338,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.7508,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.29274916648864746,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.666,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.25595784187316895,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.6352,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.2592969238758087,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.6579,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.2994536757469177,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.6113,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.23978127539157867,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.6176,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.26289495825767517,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.659,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.2562961280345917,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.6343,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.26053619384765625,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.678,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.26842328906059265,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.6837,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.2875808775424957,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.6814,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.28536874055862427,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.6662,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.2610325217247009,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.6408,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.25660914182662964,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.6614,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.26448601484298706,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.768,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.27543431520462036,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.7033,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.23746508359909058,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.677,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.2522618770599365,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.6911,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.24367687106132507,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.6403,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.23886358737945557,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.6631,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.251811146736145,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.5988,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.25968319177627563,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.6179,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.271772563457489,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.6335,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.27321547269821167,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.6595,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.27290716767311096,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.6939,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.27754583954811096,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.7261,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.26694318652153015,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.7057,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.2594609558582306,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.7151,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.2762211263179779,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.6451,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.26050442457199097,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.6568,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.26617348194122314,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.6881,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.26192399859428406,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.6431,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.2613207697868347,
      "learning_rate": 9.445676274944568e-05,
      "loss": 0.5665,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.2585696578025818,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.5734,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.2603786885738373,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.5693,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.2711561322212219,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.6292,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.2895728349685669,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.7013,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.2778817117214203,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.7185,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.2786506712436676,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.6739,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.27488216757774353,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.6122,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.2739354074001312,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.6778,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.27722060680389404,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.6219,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.2824021577835083,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.7032,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.2531246840953827,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.6656,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.2856135368347168,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.7059,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.2852787375450134,
      "learning_rate": 8.869179600886919e-05,
      "loss": 0.6254,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.2868466377258301,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.7288,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.2495230734348297,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.6524,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.33029741048812866,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.7068,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.2786446511745453,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.6147,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.2919760048389435,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.6464,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.27557429671287537,
      "learning_rate": 8.603104212860311e-05,
      "loss": 0.6482,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.28281936049461365,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.6747,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.28582388162612915,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.6247,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.28495752811431885,
      "learning_rate": 8.470066518847007e-05,
      "loss": 0.6663,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.285674512386322,
      "learning_rate": 8.425720620842572e-05,
      "loss": 0.6572,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.25451236963272095,
      "learning_rate": 8.381374722838138e-05,
      "loss": 0.5202,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.2509683072566986,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.6553,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.2887680232524872,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.6364,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.2715301513671875,
      "learning_rate": 8.248337028824834e-05,
      "loss": 0.6218,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.2742822766304016,
      "learning_rate": 8.2039911308204e-05,
      "loss": 0.6377,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.27390575408935547,
      "learning_rate": 8.159645232815965e-05,
      "loss": 0.6109,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.2751968204975128,
      "learning_rate": 8.11529933481153e-05,
      "loss": 0.6375,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.2989785075187683,
      "learning_rate": 8.070953436807095e-05,
      "loss": 0.596,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.29874324798583984,
      "learning_rate": 8.026607538802661e-05,
      "loss": 0.6711,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.2511677145957947,
      "learning_rate": 7.982261640798227e-05,
      "loss": 0.5981,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.28917020559310913,
      "learning_rate": 7.937915742793793e-05,
      "loss": 0.62,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.2855004668235779,
      "learning_rate": 7.893569844789357e-05,
      "loss": 0.6715,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.2739986777305603,
      "learning_rate": 7.849223946784923e-05,
      "loss": 0.6147,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.27280476689338684,
      "learning_rate": 7.804878048780489e-05,
      "loss": 0.6289,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.28312546014785767,
      "learning_rate": 7.760532150776053e-05,
      "loss": 0.6134,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.3064590096473694,
      "learning_rate": 7.716186252771619e-05,
      "loss": 0.644,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.3090949058532715,
      "learning_rate": 7.671840354767185e-05,
      "loss": 0.675,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.251126766204834,
      "learning_rate": 7.627494456762749e-05,
      "loss": 0.6514,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.2694707214832306,
      "learning_rate": 7.583148558758315e-05,
      "loss": 0.7176,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.32085904479026794,
      "learning_rate": 7.538802660753881e-05,
      "loss": 0.6407,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.28608202934265137,
      "learning_rate": 7.494456762749445e-05,
      "loss": 0.6476,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.3048093020915985,
      "learning_rate": 7.450110864745011e-05,
      "loss": 0.6926,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.29552730917930603,
      "learning_rate": 7.405764966740577e-05,
      "loss": 0.6092,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.3000955283641815,
      "learning_rate": 7.361419068736141e-05,
      "loss": 0.7191,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.29062774777412415,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.6191,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.2899002730846405,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.6394,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.3069395422935486,
      "learning_rate": 7.228381374722837e-05,
      "loss": 0.5736,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.27552661299705505,
      "learning_rate": 7.184035476718403e-05,
      "loss": 0.6246,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.29063814878463745,
      "learning_rate": 7.139689578713969e-05,
      "loss": 0.7182,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.2732408046722412,
      "learning_rate": 7.095343680709535e-05,
      "loss": 0.6423,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.277762770652771,
      "learning_rate": 7.0509977827051e-05,
      "loss": 0.6816,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.3000591993331909,
      "learning_rate": 7.006651884700666e-05,
      "loss": 0.6736,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.2699439823627472,
      "learning_rate": 6.962305986696232e-05,
      "loss": 0.638,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.25381380319595337,
      "learning_rate": 6.917960088691796e-05,
      "loss": 0.6313,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.28480035066604614,
      "learning_rate": 6.873614190687362e-05,
      "loss": 0.6281,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.2797883152961731,
      "learning_rate": 6.829268292682928e-05,
      "loss": 0.6772,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3453793525695801,
      "learning_rate": 6.784922394678492e-05,
      "loss": 0.7245,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.3016928434371948,
      "learning_rate": 6.740576496674058e-05,
      "loss": 0.6263,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.27183499932289124,
      "learning_rate": 6.696230598669624e-05,
      "loss": 0.7207,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.269970178604126,
      "learning_rate": 6.651884700665188e-05,
      "loss": 0.5173,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.26854339241981506,
      "learning_rate": 6.607538802660754e-05,
      "loss": 0.6031,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.30020958185195923,
      "learning_rate": 6.56319290465632e-05,
      "loss": 0.5817,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.28741002082824707,
      "learning_rate": 6.518847006651884e-05,
      "loss": 0.6387,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.28789424896240234,
      "learning_rate": 6.47450110864745e-05,
      "loss": 0.6019,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.30814558267593384,
      "learning_rate": 6.430155210643016e-05,
      "loss": 0.6069,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.3298947513103485,
      "learning_rate": 6.38580931263858e-05,
      "loss": 0.6867,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.2842944264411926,
      "learning_rate": 6.341463414634146e-05,
      "loss": 0.5808,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.2799879014492035,
      "learning_rate": 6.297117516629712e-05,
      "loss": 0.6129,
      "step": 315
    },
    {
      "epoch": 2.0791208791208793,
      "grad_norm": 0.29776474833488464,
      "learning_rate": 6.252771618625277e-05,
      "loss": 0.5993,
      "step": 316
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 0.29667073488235474,
      "learning_rate": 6.208425720620842e-05,
      "loss": 0.6367,
      "step": 317
    },
    {
      "epoch": 2.0923076923076924,
      "grad_norm": 0.2922004163265228,
      "learning_rate": 6.164079822616408e-05,
      "loss": 0.6126,
      "step": 318
    },
    {
      "epoch": 2.098901098901099,
      "grad_norm": 0.2987346947193146,
      "learning_rate": 6.119733924611974e-05,
      "loss": 0.6482,
      "step": 319
    },
    {
      "epoch": 2.1054945054945056,
      "grad_norm": 0.31420716643333435,
      "learning_rate": 6.075388026607539e-05,
      "loss": 0.6043,
      "step": 320
    },
    {
      "epoch": 2.112087912087912,
      "grad_norm": 0.3014363646507263,
      "learning_rate": 6.031042128603105e-05,
      "loss": 0.6075,
      "step": 321
    },
    {
      "epoch": 2.1186813186813187,
      "grad_norm": 0.30079519748687744,
      "learning_rate": 5.98669623059867e-05,
      "loss": 0.5847,
      "step": 322
    },
    {
      "epoch": 2.1252747252747253,
      "grad_norm": 0.31427085399627686,
      "learning_rate": 5.942350332594236e-05,
      "loss": 0.5911,
      "step": 323
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.30805203318595886,
      "learning_rate": 5.898004434589801e-05,
      "loss": 0.5823,
      "step": 324
    },
    {
      "epoch": 2.1384615384615384,
      "grad_norm": 0.30514025688171387,
      "learning_rate": 5.853658536585366e-05,
      "loss": 0.6091,
      "step": 325
    },
    {
      "epoch": 2.145054945054945,
      "grad_norm": 0.31725582480430603,
      "learning_rate": 5.809312638580932e-05,
      "loss": 0.6254,
      "step": 326
    },
    {
      "epoch": 2.1516483516483516,
      "grad_norm": 0.323509156703949,
      "learning_rate": 5.7649667405764975e-05,
      "loss": 0.6337,
      "step": 327
    },
    {
      "epoch": 2.158241758241758,
      "grad_norm": 0.3517661392688751,
      "learning_rate": 5.720620842572062e-05,
      "loss": 0.5774,
      "step": 328
    },
    {
      "epoch": 2.1648351648351647,
      "grad_norm": 0.3371114134788513,
      "learning_rate": 5.676274944567628e-05,
      "loss": 0.6218,
      "step": 329
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.3836360275745392,
      "learning_rate": 5.6319290465631935e-05,
      "loss": 0.6329,
      "step": 330
    },
    {
      "epoch": 2.178021978021978,
      "grad_norm": 0.3552844226360321,
      "learning_rate": 5.587583148558758e-05,
      "loss": 0.6157,
      "step": 331
    },
    {
      "epoch": 2.184615384615385,
      "grad_norm": 0.3251331150531769,
      "learning_rate": 5.543237250554324e-05,
      "loss": 0.5729,
      "step": 332
    },
    {
      "epoch": 2.1912087912087914,
      "grad_norm": 0.3578687012195587,
      "learning_rate": 5.4988913525498895e-05,
      "loss": 0.648,
      "step": 333
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.331082820892334,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.6301,
      "step": 334
    },
    {
      "epoch": 2.2043956043956046,
      "grad_norm": 0.35480448603630066,
      "learning_rate": 5.4101995565410204e-05,
      "loss": 0.6247,
      "step": 335
    },
    {
      "epoch": 2.210989010989011,
      "grad_norm": 0.33531099557876587,
      "learning_rate": 5.365853658536586e-05,
      "loss": 0.6074,
      "step": 336
    },
    {
      "epoch": 2.2175824175824177,
      "grad_norm": 0.344844788312912,
      "learning_rate": 5.3215077605321506e-05,
      "loss": 0.6069,
      "step": 337
    },
    {
      "epoch": 2.2241758241758243,
      "grad_norm": 0.32093575596809387,
      "learning_rate": 5.2771618625277164e-05,
      "loss": 0.5587,
      "step": 338
    },
    {
      "epoch": 2.230769230769231,
      "grad_norm": 0.33849260210990906,
      "learning_rate": 5.232815964523282e-05,
      "loss": 0.6661,
      "step": 339
    },
    {
      "epoch": 2.2373626373626374,
      "grad_norm": 0.35878679156303406,
      "learning_rate": 5.1884700665188466e-05,
      "loss": 0.665,
      "step": 340
    },
    {
      "epoch": 2.243956043956044,
      "grad_norm": 0.38353458046913147,
      "learning_rate": 5.1441241685144124e-05,
      "loss": 0.6147,
      "step": 341
    },
    {
      "epoch": 2.2505494505494505,
      "grad_norm": 0.3415125906467438,
      "learning_rate": 5.099778270509978e-05,
      "loss": 0.6062,
      "step": 342
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 0.3562762439250946,
      "learning_rate": 5.0554323725055433e-05,
      "loss": 0.6585,
      "step": 343
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 0.3795083463191986,
      "learning_rate": 5.011086474501109e-05,
      "loss": 0.5794,
      "step": 344
    },
    {
      "epoch": 2.2703296703296703,
      "grad_norm": 0.3509095311164856,
      "learning_rate": 4.966740576496674e-05,
      "loss": 0.5891,
      "step": 345
    },
    {
      "epoch": 2.276923076923077,
      "grad_norm": 0.3474126160144806,
      "learning_rate": 4.92239467849224e-05,
      "loss": 0.5685,
      "step": 346
    },
    {
      "epoch": 2.2835164835164834,
      "grad_norm": 0.3418504595756531,
      "learning_rate": 4.878048780487805e-05,
      "loss": 0.5573,
      "step": 347
    },
    {
      "epoch": 2.29010989010989,
      "grad_norm": 0.38374704122543335,
      "learning_rate": 4.833702882483371e-05,
      "loss": 0.5345,
      "step": 348
    },
    {
      "epoch": 2.2967032967032965,
      "grad_norm": 0.3838048577308655,
      "learning_rate": 4.789356984478936e-05,
      "loss": 0.669,
      "step": 349
    },
    {
      "epoch": 2.303296703296703,
      "grad_norm": 0.3914019763469696,
      "learning_rate": 4.745011086474501e-05,
      "loss": 0.5836,
      "step": 350
    },
    {
      "epoch": 2.3098901098901097,
      "grad_norm": 0.35847949981689453,
      "learning_rate": 4.700665188470067e-05,
      "loss": 0.5819,
      "step": 351
    },
    {
      "epoch": 2.3164835164835162,
      "grad_norm": 0.37206998467445374,
      "learning_rate": 4.656319290465632e-05,
      "loss": 0.609,
      "step": 352
    },
    {
      "epoch": 2.3230769230769233,
      "grad_norm": 0.36886441707611084,
      "learning_rate": 4.611973392461197e-05,
      "loss": 0.5944,
      "step": 353
    },
    {
      "epoch": 2.32967032967033,
      "grad_norm": 0.34457334876060486,
      "learning_rate": 4.567627494456763e-05,
      "loss": 0.5911,
      "step": 354
    },
    {
      "epoch": 2.3362637362637364,
      "grad_norm": 0.34723272919654846,
      "learning_rate": 4.523281596452328e-05,
      "loss": 0.6414,
      "step": 355
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 0.38124364614486694,
      "learning_rate": 4.478935698447894e-05,
      "loss": 0.584,
      "step": 356
    },
    {
      "epoch": 2.3494505494505495,
      "grad_norm": 0.4017902612686157,
      "learning_rate": 4.4345898004434597e-05,
      "loss": 0.5929,
      "step": 357
    },
    {
      "epoch": 2.356043956043956,
      "grad_norm": 0.402834415435791,
      "learning_rate": 4.390243902439025e-05,
      "loss": 0.613,
      "step": 358
    },
    {
      "epoch": 2.3626373626373627,
      "grad_norm": 0.3912964165210724,
      "learning_rate": 4.34589800443459e-05,
      "loss": 0.5949,
      "step": 359
    },
    {
      "epoch": 2.3692307692307693,
      "grad_norm": 0.36788588762283325,
      "learning_rate": 4.301552106430156e-05,
      "loss": 0.6354,
      "step": 360
    },
    {
      "epoch": 2.375824175824176,
      "grad_norm": 0.40774407982826233,
      "learning_rate": 4.257206208425721e-05,
      "loss": 0.6792,
      "step": 361
    },
    {
      "epoch": 2.3824175824175824,
      "grad_norm": 0.3771168887615204,
      "learning_rate": 4.212860310421286e-05,
      "loss": 0.5933,
      "step": 362
    },
    {
      "epoch": 2.389010989010989,
      "grad_norm": 0.3673039972782135,
      "learning_rate": 4.168514412416852e-05,
      "loss": 0.5968,
      "step": 363
    },
    {
      "epoch": 2.3956043956043955,
      "grad_norm": 0.3940329849720001,
      "learning_rate": 4.124168514412417e-05,
      "loss": 0.5942,
      "step": 364
    },
    {
      "epoch": 2.402197802197802,
      "grad_norm": 0.3786124289035797,
      "learning_rate": 4.0798226164079826e-05,
      "loss": 0.7234,
      "step": 365
    },
    {
      "epoch": 2.4087912087912087,
      "grad_norm": 0.43362823128700256,
      "learning_rate": 4.035476718403548e-05,
      "loss": 0.6285,
      "step": 366
    },
    {
      "epoch": 2.4153846153846152,
      "grad_norm": 0.3915743827819824,
      "learning_rate": 3.9911308203991135e-05,
      "loss": 0.5821,
      "step": 367
    },
    {
      "epoch": 2.421978021978022,
      "grad_norm": 0.42584264278411865,
      "learning_rate": 3.9467849223946786e-05,
      "loss": 0.5934,
      "step": 368
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.44291138648986816,
      "learning_rate": 3.9024390243902444e-05,
      "loss": 0.5921,
      "step": 369
    },
    {
      "epoch": 2.4351648351648354,
      "grad_norm": 0.37372294068336487,
      "learning_rate": 3.8580931263858095e-05,
      "loss": 0.6044,
      "step": 370
    },
    {
      "epoch": 2.441758241758242,
      "grad_norm": 0.43186941742897034,
      "learning_rate": 3.8137472283813746e-05,
      "loss": 0.6622,
      "step": 371
    },
    {
      "epoch": 2.4483516483516485,
      "grad_norm": 0.4179324507713318,
      "learning_rate": 3.7694013303769404e-05,
      "loss": 0.6017,
      "step": 372
    },
    {
      "epoch": 2.454945054945055,
      "grad_norm": 0.39667195081710815,
      "learning_rate": 3.7250554323725055e-05,
      "loss": 0.5389,
      "step": 373
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.36382627487182617,
      "learning_rate": 3.6807095343680706e-05,
      "loss": 0.5609,
      "step": 374
    },
    {
      "epoch": 2.4681318681318682,
      "grad_norm": 0.4093233644962311,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.5548,
      "step": 375
    },
    {
      "epoch": 2.474725274725275,
      "grad_norm": 0.451909601688385,
      "learning_rate": 3.5920177383592015e-05,
      "loss": 0.6714,
      "step": 376
    },
    {
      "epoch": 2.4813186813186814,
      "grad_norm": 0.4452255964279175,
      "learning_rate": 3.547671840354767e-05,
      "loss": 0.6257,
      "step": 377
    },
    {
      "epoch": 2.487912087912088,
      "grad_norm": 0.4478726387023926,
      "learning_rate": 3.503325942350333e-05,
      "loss": 0.6663,
      "step": 378
    },
    {
      "epoch": 2.4945054945054945,
      "grad_norm": 0.3799694776535034,
      "learning_rate": 3.458980044345898e-05,
      "loss": 0.5937,
      "step": 379
    },
    {
      "epoch": 2.501098901098901,
      "grad_norm": 0.42000776529312134,
      "learning_rate": 3.414634146341464e-05,
      "loss": 0.6023,
      "step": 380
    },
    {
      "epoch": 2.5076923076923077,
      "grad_norm": 0.40969085693359375,
      "learning_rate": 3.370288248337029e-05,
      "loss": 0.5605,
      "step": 381
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 0.40965500473976135,
      "learning_rate": 3.325942350332594e-05,
      "loss": 0.5495,
      "step": 382
    },
    {
      "epoch": 2.520879120879121,
      "grad_norm": 0.42173510789871216,
      "learning_rate": 3.28159645232816e-05,
      "loss": 0.5852,
      "step": 383
    },
    {
      "epoch": 2.5274725274725274,
      "grad_norm": 0.4287414252758026,
      "learning_rate": 3.237250554323725e-05,
      "loss": 0.5482,
      "step": 384
    },
    {
      "epoch": 2.534065934065934,
      "grad_norm": 0.44657522439956665,
      "learning_rate": 3.19290465631929e-05,
      "loss": 0.669,
      "step": 385
    },
    {
      "epoch": 2.5406593406593405,
      "grad_norm": 0.41047608852386475,
      "learning_rate": 3.148558758314856e-05,
      "loss": 0.639,
      "step": 386
    },
    {
      "epoch": 2.547252747252747,
      "grad_norm": 0.4406319558620453,
      "learning_rate": 3.104212860310421e-05,
      "loss": 0.5938,
      "step": 387
    },
    {
      "epoch": 2.5538461538461537,
      "grad_norm": 0.3928898870944977,
      "learning_rate": 3.059866962305987e-05,
      "loss": 0.6008,
      "step": 388
    },
    {
      "epoch": 2.5604395604395602,
      "grad_norm": 0.363491028547287,
      "learning_rate": 3.0155210643015524e-05,
      "loss": 0.5019,
      "step": 389
    },
    {
      "epoch": 2.567032967032967,
      "grad_norm": 0.41302213072776794,
      "learning_rate": 2.971175166297118e-05,
      "loss": 0.5937,
      "step": 390
    },
    {
      "epoch": 2.5736263736263734,
      "grad_norm": 0.4231741726398468,
      "learning_rate": 2.926829268292683e-05,
      "loss": 0.5883,
      "step": 391
    },
    {
      "epoch": 2.5802197802197804,
      "grad_norm": 0.39978164434432983,
      "learning_rate": 2.8824833702882487e-05,
      "loss": 0.521,
      "step": 392
    },
    {
      "epoch": 2.586813186813187,
      "grad_norm": 0.44265252351760864,
      "learning_rate": 2.838137472283814e-05,
      "loss": 0.5911,
      "step": 393
    },
    {
      "epoch": 2.5934065934065935,
      "grad_norm": 0.4575295150279999,
      "learning_rate": 2.793791574279379e-05,
      "loss": 0.6394,
      "step": 394
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.4084360599517822,
      "learning_rate": 2.7494456762749448e-05,
      "loss": 0.603,
      "step": 395
    },
    {
      "epoch": 2.6065934065934067,
      "grad_norm": 0.439318984746933,
      "learning_rate": 2.7050997782705102e-05,
      "loss": 0.6178,
      "step": 396
    },
    {
      "epoch": 2.6131868131868132,
      "grad_norm": 0.42168593406677246,
      "learning_rate": 2.6607538802660753e-05,
      "loss": 0.583,
      "step": 397
    },
    {
      "epoch": 2.61978021978022,
      "grad_norm": 0.42136847972869873,
      "learning_rate": 2.616407982261641e-05,
      "loss": 0.5854,
      "step": 398
    },
    {
      "epoch": 2.6263736263736264,
      "grad_norm": 0.39368385076522827,
      "learning_rate": 2.5720620842572062e-05,
      "loss": 0.5738,
      "step": 399
    },
    {
      "epoch": 2.632967032967033,
      "grad_norm": 0.44657933712005615,
      "learning_rate": 2.5277161862527717e-05,
      "loss": 0.5183,
      "step": 400
    },
    {
      "epoch": 2.6395604395604395,
      "grad_norm": 0.4116158187389374,
      "learning_rate": 2.483370288248337e-05,
      "loss": 0.545,
      "step": 401
    },
    {
      "epoch": 2.646153846153846,
      "grad_norm": 0.471483439207077,
      "learning_rate": 2.4390243902439026e-05,
      "loss": 0.6098,
      "step": 402
    },
    {
      "epoch": 2.6527472527472526,
      "grad_norm": 0.4349648952484131,
      "learning_rate": 2.394678492239468e-05,
      "loss": 0.6527,
      "step": 403
    },
    {
      "epoch": 2.659340659340659,
      "grad_norm": 0.39896857738494873,
      "learning_rate": 2.3503325942350335e-05,
      "loss": 0.614,
      "step": 404
    },
    {
      "epoch": 2.665934065934066,
      "grad_norm": 0.40988850593566895,
      "learning_rate": 2.3059866962305986e-05,
      "loss": 0.6554,
      "step": 405
    },
    {
      "epoch": 2.672527472527473,
      "grad_norm": 0.44231531023979187,
      "learning_rate": 2.261640798226164e-05,
      "loss": 0.6108,
      "step": 406
    },
    {
      "epoch": 2.6791208791208794,
      "grad_norm": 0.42809388041496277,
      "learning_rate": 2.2172949002217298e-05,
      "loss": 0.591,
      "step": 407
    },
    {
      "epoch": 2.685714285714286,
      "grad_norm": 0.40389585494995117,
      "learning_rate": 2.172949002217295e-05,
      "loss": 0.623,
      "step": 408
    },
    {
      "epoch": 2.6923076923076925,
      "grad_norm": 0.4272451400756836,
      "learning_rate": 2.1286031042128604e-05,
      "loss": 0.6169,
      "step": 409
    },
    {
      "epoch": 2.698901098901099,
      "grad_norm": 0.4311954975128174,
      "learning_rate": 2.084257206208426e-05,
      "loss": 0.6427,
      "step": 410
    },
    {
      "epoch": 2.7054945054945057,
      "grad_norm": 0.3911745548248291,
      "learning_rate": 2.0399113082039913e-05,
      "loss": 0.6045,
      "step": 411
    },
    {
      "epoch": 2.7120879120879122,
      "grad_norm": 0.3971542418003082,
      "learning_rate": 1.9955654101995567e-05,
      "loss": 0.651,
      "step": 412
    },
    {
      "epoch": 2.718681318681319,
      "grad_norm": 0.40163570642471313,
      "learning_rate": 1.9512195121951222e-05,
      "loss": 0.6377,
      "step": 413
    },
    {
      "epoch": 2.7252747252747254,
      "grad_norm": 0.41939297318458557,
      "learning_rate": 1.9068736141906873e-05,
      "loss": 0.6572,
      "step": 414
    },
    {
      "epoch": 2.731868131868132,
      "grad_norm": 0.40067601203918457,
      "learning_rate": 1.8625277161862528e-05,
      "loss": 0.6572,
      "step": 415
    },
    {
      "epoch": 2.7384615384615385,
      "grad_norm": 0.39213740825653076,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.5677,
      "step": 416
    },
    {
      "epoch": 2.745054945054945,
      "grad_norm": 0.4138976037502289,
      "learning_rate": 1.7738359201773837e-05,
      "loss": 0.6122,
      "step": 417
    },
    {
      "epoch": 2.7516483516483516,
      "grad_norm": 0.37361735105514526,
      "learning_rate": 1.729490022172949e-05,
      "loss": 0.5834,
      "step": 418
    },
    {
      "epoch": 2.758241758241758,
      "grad_norm": 0.45028218626976013,
      "learning_rate": 1.6851441241685146e-05,
      "loss": 0.611,
      "step": 419
    },
    {
      "epoch": 2.764835164835165,
      "grad_norm": 0.46391284465789795,
      "learning_rate": 1.64079822616408e-05,
      "loss": 0.6272,
      "step": 420
    },
    {
      "epoch": 2.7714285714285714,
      "grad_norm": 0.44817444682121277,
      "learning_rate": 1.596452328159645e-05,
      "loss": 0.636,
      "step": 421
    },
    {
      "epoch": 2.778021978021978,
      "grad_norm": 0.4548102617263794,
      "learning_rate": 1.5521064301552106e-05,
      "loss": 0.6471,
      "step": 422
    },
    {
      "epoch": 2.7846153846153845,
      "grad_norm": 0.4243184030056,
      "learning_rate": 1.5077605321507762e-05,
      "loss": 0.5987,
      "step": 423
    },
    {
      "epoch": 2.791208791208791,
      "grad_norm": 0.40378686785697937,
      "learning_rate": 1.4634146341463415e-05,
      "loss": 0.5556,
      "step": 424
    },
    {
      "epoch": 2.7978021978021976,
      "grad_norm": 0.46278807520866394,
      "learning_rate": 1.419068736141907e-05,
      "loss": 0.6067,
      "step": 425
    },
    {
      "epoch": 2.804395604395604,
      "grad_norm": 0.41471660137176514,
      "learning_rate": 1.3747228381374724e-05,
      "loss": 0.5817,
      "step": 426
    },
    {
      "epoch": 2.8109890109890108,
      "grad_norm": 0.4059871733188629,
      "learning_rate": 1.3303769401330377e-05,
      "loss": 0.528,
      "step": 427
    },
    {
      "epoch": 2.8175824175824173,
      "grad_norm": 0.45474469661712646,
      "learning_rate": 1.2860310421286031e-05,
      "loss": 0.6658,
      "step": 428
    },
    {
      "epoch": 2.824175824175824,
      "grad_norm": 0.4757836163043976,
      "learning_rate": 1.2416851441241686e-05,
      "loss": 0.6812,
      "step": 429
    },
    {
      "epoch": 2.830769230769231,
      "grad_norm": 0.42723771929740906,
      "learning_rate": 1.197339246119734e-05,
      "loss": 0.5488,
      "step": 430
    },
    {
      "epoch": 2.8373626373626375,
      "grad_norm": 0.41617435216903687,
      "learning_rate": 1.1529933481152993e-05,
      "loss": 0.5782,
      "step": 431
    },
    {
      "epoch": 2.843956043956044,
      "grad_norm": 0.41583624482154846,
      "learning_rate": 1.1086474501108649e-05,
      "loss": 0.6055,
      "step": 432
    },
    {
      "epoch": 2.8505494505494506,
      "grad_norm": 0.4336477816104889,
      "learning_rate": 1.0643015521064302e-05,
      "loss": 0.5542,
      "step": 433
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.42993390560150146,
      "learning_rate": 1.0199556541019956e-05,
      "loss": 0.6012,
      "step": 434
    },
    {
      "epoch": 2.8637362637362638,
      "grad_norm": 0.4529070258140564,
      "learning_rate": 9.756097560975611e-06,
      "loss": 0.595,
      "step": 435
    }
  ],
  "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": 2.0019807924221952e+17,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}