{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.778021978021978,
  "eval_steps": 500,
  "global_step": 270,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.2240082025527954,
      "learning_rate": 0.0,
      "loss": 3.2004,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.1817413568496704,
      "learning_rate": 4e-05,
      "loss": 2.9195,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.089200496673584,
      "learning_rate": 8e-05,
      "loss": 2.9322,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.23591947555542,
      "learning_rate": 0.00012,
      "loss": 2.493,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.2914438247680664,
      "learning_rate": 0.00016,
      "loss": 2.6719,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.425159215927124,
      "learning_rate": 0.0002,
      "loss": 2.0729,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 1.8763092756271362,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.063,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.2933986186981201,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.4339,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.5251818895339966,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.5351,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.9210705161094666,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.1847,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.8823724389076233,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.9696,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.8065115809440613,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.0103,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.8599637150764465,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.7631,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.7091007232666016,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.774,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5932487845420837,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.7102,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5805957317352295,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.8034,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.5351698398590088,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.7074,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.5085647106170654,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.7856,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.4852818250656128,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.6869,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.4774964451789856,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.5578,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.4320865273475647,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.6558,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.5121509432792664,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.7886,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.43891361355781555,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.6733,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.4488874077796936,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.6966,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.42902886867523193,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.75,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.42811888456344604,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.5749,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.38084888458251953,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.6558,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.39865079522132874,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.6655,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.29908454418182373,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.5844,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.38320380449295044,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.6285,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.44202783703804016,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.7849,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.34681448340415955,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.5957,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.3555922210216522,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.6433,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.7906959056854248,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.7658,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.4097070097923279,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.7638,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.36098968982696533,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.5424,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3689538836479187,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.6799,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.3969242572784424,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.5619,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.41041359305381775,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.7333,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.33059433102607727,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.5086,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.428994745016098,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.526,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3604447841644287,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.575,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.3401334881782532,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.5467,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.41614830493927,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.5289,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.4010107219219208,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.5476,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.31574419140815735,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.4687,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.42631375789642334,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.7165,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.45691990852355957,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.6254,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.34974104166030884,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.7309,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.4650188684463501,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.679,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.3808349668979645,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.7072,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.39578449726104736,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.6168,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.4203926920890808,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.5618,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.3733426332473755,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.5847,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3396105468273163,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.4976,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.3268498182296753,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.4698,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.34606558084487915,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.5485,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.3481427729129791,
      "learning_rate": 0.000176940133037694,
      "loss": 0.537,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.4629095792770386,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.5555,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.462342768907547,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.6044,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.43930208683013916,
      "learning_rate": 0.000175609756097561,
      "loss": 0.6379,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.4079689383506775,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.495,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.5146216154098511,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.645,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.3735997676849365,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.6333,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.462772011756897,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.5522,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.46557778120040894,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.4982,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.422385036945343,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.498,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.3375857174396515,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.6013,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.29001280665397644,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.5406,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.4896228015422821,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.5926,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3039141297340393,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.5804,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.3966655731201172,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.6625,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.4385382831096649,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.5815,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.40156519412994385,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.6006,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.37846580147743225,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.5044,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.3760215938091278,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.501,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.4516732394695282,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.4967,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.3656870126724243,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.5011,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.31711170077323914,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.4302,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.40144112706184387,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.5364,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.37173205614089966,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.4019,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.352626234292984,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.592,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3332176208496094,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.4131,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3604816198348999,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.5192,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.3146759271621704,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.4339,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.35468390583992004,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.4299,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.4313686788082123,
      "learning_rate": 0.000164079822616408,
      "loss": 0.5436,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.3751888871192932,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.493,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.39044705033302307,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.6177,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.3849164843559265,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.4894,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.40703052282333374,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.545,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.367977112531662,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.452,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.5252164006233215,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.4366,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.4373919665813446,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.5665,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.3770761489868164,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.4594,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.6411177515983582,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.5672,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.5393151640892029,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.5241,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.3491095006465912,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.6669,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.4589627981185913,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.5866,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.41086679697036743,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.5123,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.5647931098937988,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.6576,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.36647412180900574,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.5656,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.3683735728263855,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.5391,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.4131142497062683,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.5337,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.3431665599346161,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.4085,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.4302043914794922,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.5011,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.3393073081970215,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.3961,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.45697256922721863,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.4796,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.4157907962799072,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.5821,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.507879912853241,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.6692,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.3931836485862732,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.4588,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.427739679813385,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.4788,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.37858736515045166,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.5924,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.4577133059501648,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.5587,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.40195730328559875,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.6127,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.4415499269962311,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.6255,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.5513373017311096,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.653,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.6036509871482849,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.6635,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.3825967311859131,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.4513,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.48890331387519836,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.5639,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.40356022119522095,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.5302,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.42591437697410583,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.496,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.35469311475753784,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.4106,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.4026336967945099,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.5897,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.4216915965080261,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.4037,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.3963623642921448,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.5404,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.43660643696784973,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.4459,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.48640280961990356,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.6062,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.3660179078578949,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.6173,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.3584440052509308,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.484,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.32160452008247375,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.4685,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.3843126595020294,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.4972,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.44002872705459595,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.5735,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.38660556077957153,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.4691,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.37619107961654663,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.5755,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.44009754061698914,
      "learning_rate": 0.00014235033259423505,
      "loss": 0.5447,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.3828625977039337,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.4198,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.4074431359767914,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.6089,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.2811187207698822,
      "learning_rate": 0.000141019955654102,
      "loss": 0.3642,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.4300229251384735,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.4538,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.41287022829055786,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.7081,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.3987810015678406,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.4395,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.4244191348552704,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.6583,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.5414079427719116,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.5561,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.4416467249393463,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.4204,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.29231685400009155,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.3262,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.31047335267066956,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.5358,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.3559879958629608,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.5791,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.4861917495727539,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.6753,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.39049023389816284,
      "learning_rate": 0.00013614190687361418,
      "loss": 0.5406,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.4635537564754486,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.3998,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5928805470466614,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.3846,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.35755646228790283,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.3709,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.3304623067378998,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.3406,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.4952533543109894,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.4299,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.44481590390205383,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.4372,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.34838855266571045,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.3225,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.40465107560157776,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.3798,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.4660601019859314,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.4619,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.43197980523109436,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.5388,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.5366076827049255,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.3979,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.4347151219844818,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.3825,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.38231268525123596,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.3746,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.4806695878505707,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.4321,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.4538815915584564,
      "learning_rate": 0.000129490022172949,
      "loss": 0.4431,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.3633645474910736,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.3965,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.3847673237323761,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.4278,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.5384268760681152,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.4595,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.3891454041004181,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.5066,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.3688364624977112,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.3476,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.498908132314682,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.3188,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.433374285697937,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.3192,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.4463401436805725,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.3202,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.4598141014575958,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.3781,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.4908256232738495,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.4174,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.4844362437725067,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.448,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.5686154961585999,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.5205,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.3801136314868927,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.3984,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.5846949815750122,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.422,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.44249263405799866,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.3603,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.41781550645828247,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.4306,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.5094308257102966,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.3539,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.5700743198394775,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.5443,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.520265519618988,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.3795,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.5511739253997803,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.4298,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.49977126717567444,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.5757,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.4320775866508484,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.5091,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.4998200535774231,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.3356,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.5414028167724609,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.4753,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.5499384999275208,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.4106,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.5342494249343872,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.5852,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.40448567271232605,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.3139,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.4487594664096832,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.3855,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.425373375415802,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.3666,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.5899381637573242,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.5231,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.39368343353271484,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.4163,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.5183475017547607,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.3957,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.5001964569091797,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.3212,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.565925121307373,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.4514,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.6077309250831604,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.5162,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.643592119216919,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.4979,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.5134578943252563,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.4664,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.5517260432243347,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.3496,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.5587923526763916,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.4731,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.46299734711647034,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.4422,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.6137144565582275,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.4825,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.5699131488800049,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.3672,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.6000216603279114,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.3151,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.5146446228027344,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.3499,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.5556411147117615,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.3703,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.5227416157722473,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.2822,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.5939992070198059,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.4051,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.6168639063835144,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.3667,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.500918984413147,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.4312,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.5234825015068054,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.3467,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.6361038684844971,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.4627,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.6411811709403992,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.4584,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.5219542980194092,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.4416,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.5459028482437134,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.4354,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.6969254612922668,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.3885,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.5649939179420471,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.4249,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.6990719437599182,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.4471,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.6019245386123657,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.399,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.5318156480789185,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.3313,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.708998441696167,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.3996,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.5821573734283447,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.3827,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.5359853506088257,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.3401,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.6486450433731079,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.4699,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.5802281498908997,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.3142,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.6745710968971252,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.3987,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.6669487953186035,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.3844,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.6804341077804565,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.5281,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.7038126587867737,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.3805,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.6071642637252808,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.3635,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.6137164831161499,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.3256,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.6459644436836243,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.3649,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.6115922331809998,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.3435,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.7247678637504578,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.4684,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.8030369877815247,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.46,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.5810509324073792,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.4843,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.7242643237113953,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.4224,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.6585989594459534,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.4362,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.6632310748100281,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.3829,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.7755358815193176,
      "learning_rate": 9.445676274944568e-05,
      "loss": 0.4587,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.6400403380393982,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.4181,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.6548476219177246,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.4276,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.8124223351478577,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.4642,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.7536482810974121,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.3769,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.6488485336303711,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.4124,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.5742541551589966,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.4393,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.6772143840789795,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.4205,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.7344285845756531,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.3581,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.5853085517883301,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.3772,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.6975771188735962,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.3388,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.549437403678894,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.392,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.5996490716934204,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.3269,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.6664270758628845,
      "learning_rate": 8.869179600886919e-05,
      "loss": 0.452,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.7387408018112183,
      "learning_rate": 8.824833702882484e-05,
      "loss": 0.4921,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.6442356109619141,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.3694,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.7290146350860596,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.3967,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.5723556280136108,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.539,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.7876671552658081,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.3946,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.5634341239929199,
      "learning_rate": 8.603104212860311e-05,
      "loss": 0.3229,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.7009791135787964,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.3689,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.6112445592880249,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.3697,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.4994143545627594,
      "learning_rate": 8.470066518847007e-05,
      "loss": 0.4125,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.7590649724006653,
      "learning_rate": 8.425720620842572e-05,
      "loss": 0.3607,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.6371490955352783,
      "learning_rate": 8.381374722838138e-05,
      "loss": 0.4376,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.7184921503067017,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.3606,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.7507034540176392,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.4151,
      "step": 270
    }
  ],
  "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": 1.1474254305626112e+17,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}