{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.3824175824175824,
  "eval_steps": 500,
  "global_step": 210,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 2.0722603797912598,
      "learning_rate": 0.0,
      "loss": 3.2131,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.6677350997924805,
      "learning_rate": 4e-05,
      "loss": 2.5554,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.6039100885391235,
      "learning_rate": 8e-05,
      "loss": 2.6951,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.6277270317077637,
      "learning_rate": 0.00012,
      "loss": 2.9003,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.0207111835479736,
      "learning_rate": 0.00016,
      "loss": 2.6989,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.6012003421783447,
      "learning_rate": 0.0002,
      "loss": 2.2728,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.338730812072754,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.7083,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 2.3853142261505127,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.5367,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.1683852672576904,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2907,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.9153192639350891,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.16,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.4894245862960815,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.5419,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.8791560530662537,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.323,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5337121486663818,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.1458,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5149000883102417,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0808,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.4778643846511841,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.088,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.47255033254623413,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.0745,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.43144354224205017,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.2685,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.38666868209838867,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.0754,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.38462671637535095,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.9311,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.35871055722236633,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.95,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.43639278411865234,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.9915,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3904358446598053,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.0229,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3931411802768707,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.897,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3906334340572357,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.0983,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3786067068576813,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.0237,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.36092478036880493,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9729,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.27863427996635437,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9565,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.30928313732147217,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.0746,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3250511586666107,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.9843,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.30846866965293884,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.0582,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.3773055672645569,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.9213,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3716050386428833,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.9804,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.3420291244983673,
      "learning_rate": 0.00018802660753880268,
      "loss": 1.0815,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.2763300836086273,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.902,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3937534689903259,
      "learning_rate": 0.00018713968957871397,
      "loss": 1.1645,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.27199873328208923,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.8738,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.2848569452762604,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.0149,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.31365159153938293,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.9087,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.24746054410934448,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.9948,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.23962347209453583,
      "learning_rate": 0.00018492239467849224,
      "loss": 1.1008,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.28994685411453247,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.915,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.30804207921028137,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.8168,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.397780179977417,
      "learning_rate": 0.0001835920177383592,
      "loss": 1.0102,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.28575780987739563,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.0709,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.2701430022716522,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.9748,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.34878647327423096,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.9461,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.29195308685302734,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.9907,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.32355818152427673,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.0469,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.3442789614200592,
      "learning_rate": 0.00018093126385809312,
      "loss": 1.017,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.3519359827041626,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.9013,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.26735949516296387,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.0039,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.27275341749191284,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.8377,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3131617307662964,
      "learning_rate": 0.00017915742793791575,
      "loss": 1.079,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.3103640675544739,
      "learning_rate": 0.0001787139689578714,
      "loss": 1.1037,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3662891089916229,
      "learning_rate": 0.00017827050997782707,
      "loss": 1.2238,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.31076231598854065,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.0621,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.364701509475708,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.8895,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.3279484212398529,
      "learning_rate": 0.000176940133037694,
      "loss": 0.8092,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.4195176959037781,
      "learning_rate": 0.00017649667405764967,
      "loss": 1.0942,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.35336142778396606,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.9458,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.2668030560016632,
      "learning_rate": 0.000175609756097561,
      "loss": 0.7203,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.2878060042858124,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.8954,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.28040236234664917,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.847,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.38638436794281006,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.9154,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3532263934612274,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.967,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.24510745704174042,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.9775,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.2761436402797699,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.9424,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.2630966901779175,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.9213,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.2421293705701828,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.903,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3474556505680084,
      "learning_rate": 0.00017161862527716187,
      "loss": 1.0754,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.25004228949546814,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.9385,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.3480256199836731,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.8971,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.35953742265701294,
      "learning_rate": 0.00017028824833702883,
      "loss": 1.0076,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.2506542503833771,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.771,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.29169702529907227,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.7205,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.26952701807022095,
      "learning_rate": 0.00016895787139689582,
      "loss": 1.0331,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.3254987895488739,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.9197,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.2873916029930115,
      "learning_rate": 0.0001680709534368071,
      "loss": 1.0837,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.3419133424758911,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.8816,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.29397767782211304,
      "learning_rate": 0.00016718403547671842,
      "loss": 1.0683,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.2623101472854614,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.8472,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.44186830520629883,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.2116,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.4125562906265259,
      "learning_rate": 0.00016585365853658536,
      "loss": 1.0062,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3349130153656006,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.8995,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.34971699118614197,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.8694,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3700663447380066,
      "learning_rate": 0.00016452328159645234,
      "loss": 1.0927,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.28516340255737305,
      "learning_rate": 0.000164079822616408,
      "loss": 0.8334,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.27797970175743103,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.8108,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3791492283344269,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.8473,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.34083792567253113,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.9353,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.28273823857307434,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.8956,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.3167821764945984,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.8953,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.26616188883781433,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.8261,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.237916499376297,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.8914,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.32362309098243713,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.9295,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.2910405099391937,
      "learning_rate": 0.00016008869179600887,
      "loss": 1.047,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.279320627450943,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.9465,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.36068761348724365,
      "learning_rate": 0.00015920177383592018,
      "loss": 1.0782,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.38116326928138733,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.8893,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.28538259863853455,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.8015,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.3541967272758484,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.8434,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.34469982981681824,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.8324,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.4213978946208954,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.9444,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.3815469741821289,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.8776,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.35397177934646606,
      "learning_rate": 0.00015609756097560978,
      "loss": 1.1552,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.2684699594974518,
      "learning_rate": 0.00015565410199556542,
      "loss": 0.7798,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.25741079449653625,
      "learning_rate": 0.00015521064301552106,
      "loss": 0.8422,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.32127293944358826,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.8322,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.3340221643447876,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.9798,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.34005194902420044,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.8661,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.3739411532878876,
      "learning_rate": 0.0001534368070953437,
      "loss": 1.021,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.3668403625488281,
      "learning_rate": 0.00015299334811529934,
      "loss": 0.9958,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.3145362436771393,
      "learning_rate": 0.00015254988913525498,
      "loss": 1.0518,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.3513026535511017,
      "learning_rate": 0.00015210643015521066,
      "loss": 1.0291,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.34400007128715515,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.9739,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.3597501516342163,
      "learning_rate": 0.00015121951219512197,
      "loss": 1.2324,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.2896723449230194,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.8937,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.30057957768440247,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.8983,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.3905964195728302,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.7167,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.3202342092990875,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.8969,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.2450852394104004,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.9203,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.3147158622741699,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.7941,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.34787628054618835,
      "learning_rate": 0.00014811529933481154,
      "loss": 1.0058,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.3001445233821869,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.8574,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.3221536874771118,
      "learning_rate": 0.00014722838137472282,
      "loss": 1.1149,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.32140639424324036,
      "learning_rate": 0.0001467849223946785,
      "loss": 1.1972,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.30501997470855713,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.929,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.3393065333366394,
      "learning_rate": 0.0001458980044345898,
      "loss": 0.8179,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.3530517816543579,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.0044,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.29705455899238586,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.9902,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.3452480733394623,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.9743,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.2938392162322998,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.8866,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.30601850152015686,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.9861,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.28590455651283264,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.8338,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.2874011695384979,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.9952,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.3361506462097168,
      "learning_rate": 0.00014235033259423505,
      "loss": 1.0219,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.3574809730052948,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.8814,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.4311088025569916,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.9013,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.26233023405075073,
      "learning_rate": 0.000141019955654102,
      "loss": 0.8736,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.35940396785736084,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.9749,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.27149611711502075,
      "learning_rate": 0.00014013303769401332,
      "loss": 0.922,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.4147508442401886,
      "learning_rate": 0.00013968957871396897,
      "loss": 1.0781,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.295341432094574,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.9529,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.36334657669067383,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.8085,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.24359752237796783,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.7036,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.3110310733318329,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.7797,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.3413989841938019,
      "learning_rate": 0.00013747228381374724,
      "loss": 1.0027,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.2888753116130829,
      "learning_rate": 0.0001370288248337029,
      "loss": 0.8844,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.32249295711517334,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.8261,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.4273090660572052,
      "learning_rate": 0.00013614190687361418,
      "loss": 1.0066,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.28998544812202454,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.8485,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.4690309762954712,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.6486,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.3045438528060913,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.8676,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.3148064613342285,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.9665,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.32930025458335876,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.8087,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.2816562354564667,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.7944,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.3011133074760437,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.7996,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.3297262191772461,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.8268,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.3308207392692566,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.7508,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.3697322607040405,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.7181,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.3329128921031952,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.7619,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.36436977982521057,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.7969,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.33429184556007385,
      "learning_rate": 0.0001303769401330377,
      "loss": 1.0637,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.4259260892868042,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.968,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.3352951109409332,
      "learning_rate": 0.000129490022172949,
      "loss": 0.8191,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.4135381579399109,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.9858,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.3486995995044708,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.8626,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.37806546688079834,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.9596,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.3310850262641907,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.9345,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.3593229651451111,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.9171,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.38787880539894104,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.8608,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.35755735635757446,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.7518,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.45123910903930664,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.8825,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.3731641471385956,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.9151,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.4211123287677765,
      "learning_rate": 0.00012505543237250553,
      "loss": 0.9073,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.3269520103931427,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.7488,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.36462828516960144,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.8809,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.36362966895103455,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.8035,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.3671634793281555,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.9194,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.3457624018192291,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.7065,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.4401772618293762,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.9267,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.4606243371963501,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.836,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.3353036940097809,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.6218,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.4171563684940338,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.7914,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.3640008270740509,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.8632,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.43573465943336487,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.8191,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.3201373219490051,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.7808,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.403213769197464,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.9004,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.4063056707382202,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.9791,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.4900030195713043,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.8013,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.49652716517448425,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.9993,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.4425002634525299,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.8854,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.46226751804351807,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.9893,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.3779703378677368,
      "learning_rate": 0.00011662971175166298,
      "loss": 0.7875,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.4313388168811798,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.7672,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.36810222268104553,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.6342,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.37219274044036865,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.8084,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.4840892553329468,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.804,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.4374985694885254,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.8546,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.3962724208831787,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.7414,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.37382033467292786,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.8653,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.44277113676071167,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.8241,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.46842196583747864,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.7964,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.4144313931465149,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.7453,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.4482251703739166,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.9691,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.41152456402778625,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.7846,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.4497469961643219,
      "learning_rate": 0.00011086474501108647,
      "loss": 1.001,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.45057448744773865,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.8659,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.4924719035625458,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.9199,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.4531312584877014,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.9154,
      "step": 210
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.407565412043981e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}