{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7912087912087912,
  "eval_steps": 500,
  "global_step": 120,
  "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
    }
  ],
  "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": 5.042719022513357e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}