{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0725274725274727,
  "eval_steps": 500,
  "global_step": 315,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.6954374313354492,
      "learning_rate": 0.0,
      "loss": 2.8668,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.8240327835083008,
      "learning_rate": 4e-05,
      "loss": 2.5618,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.8686439990997314,
      "learning_rate": 8e-05,
      "loss": 3.0462,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 2.1201276779174805,
      "learning_rate": 0.00012,
      "loss": 3.0026,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.8257514238357544,
      "learning_rate": 0.00016,
      "loss": 2.6236,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 3.506345748901367,
      "learning_rate": 0.0002,
      "loss": 2.5651,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.69150710105896,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.8867,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.2807364463806152,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.2836,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.8597283363342285,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.3437,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.224591612815857,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.1484,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.0756514072418213,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.0571,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5450265407562256,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.1114,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5045146942138672,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.2447,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5302490592002869,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.9551,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5578133463859558,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.1672,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.4630785584449768,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.083,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.45596879720687866,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.9996,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.43671905994415283,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.2504,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.39970552921295166,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.9088,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.4318220615386963,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.9521,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3746018707752228,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0365,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.34836089611053467,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.072,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3661908805370331,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.0866,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3273928165435791,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.8607,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.32546013593673706,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.9655,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.2658108174800873,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.917,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.32198530435562134,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.1911,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.34959399700164795,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.0189,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.2920706272125244,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.8385,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3053075671195984,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.8186,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.3444528877735138,
      "learning_rate": 0.00018891352549889136,
      "loss": 1.0898,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.31521955132484436,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.8046,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.3406025767326355,
      "learning_rate": 0.00018802660753880268,
      "loss": 1.0474,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.35697925090789795,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.9019,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3648720681667328,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.9981,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.35189640522003174,
      "learning_rate": 0.00018669623059866964,
      "loss": 1.0958,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.32063135504722595,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.997,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.28678596019744873,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.8982,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.4540692865848541,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.9774,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3912484645843506,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.917,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.32867908477783203,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.7079,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.27686625719070435,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.9834,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.33547407388687134,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.9818,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.28583016991615295,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.824,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.352393239736557,
      "learning_rate": 0.00018270509977827052,
      "loss": 1.0294,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.26082924008369446,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.7238,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.27766555547714233,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.6959,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.36140140891075134,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.9503,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.3121930956840515,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.9366,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.35253670811653137,
      "learning_rate": 0.0001804878048780488,
      "loss": 1.1623,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.2716571092605591,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.9414,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.30994951725006104,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.9096,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.31247520446777344,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.8017,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.28188270330429077,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.7927,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3326320946216583,
      "learning_rate": 0.00017827050997782707,
      "loss": 1.116,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.32496708631515503,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.9588,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2965904176235199,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.7861,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.28513047099113464,
      "learning_rate": 0.000176940133037694,
      "loss": 0.9813,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.3087981343269348,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.9828,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.2550174593925476,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.7715,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.30323970317840576,
      "learning_rate": 0.000175609756097561,
      "loss": 0.7541,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.33333873748779297,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.83,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.4127664566040039,
      "learning_rate": 0.0001747228381374723,
      "loss": 1.0672,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.31748759746551514,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.8194,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.34332820773124695,
      "learning_rate": 0.0001738359201773836,
      "loss": 1.0114,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.30672529339790344,
      "learning_rate": 0.00017339246119733924,
      "loss": 1.0645,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.40536418557167053,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.9311,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.34949374198913574,
      "learning_rate": 0.00017250554323725056,
      "loss": 1.0504,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.2618216872215271,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.8031,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.28889700770378113,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.7552,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.33343473076820374,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.9207,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.27106234431266785,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.7919,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.32367196679115295,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8798,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.2873658239841461,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.8827,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.34274572134017944,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.9862,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.2695680260658264,
      "learning_rate": 0.00016895787139689582,
      "loss": 1.0274,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.3303172290325165,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.9043,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.3585675060749054,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.9913,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.30480650067329407,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.7677,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.39837783575057983,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.8506,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.31981536746025085,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.9267,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.27938956022262573,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.9014,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3646959960460663,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.9302,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3169518709182739,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.8155,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.21440419554710388,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.7536,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.2928217351436615,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.7949,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.36313536763191223,
      "learning_rate": 0.000164079822616408,
      "loss": 1.2098,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.42078697681427,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.9803,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.35949447751045227,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.7935,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.337721049785614,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.854,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.3007311224937439,
      "learning_rate": 0.0001623059866962306,
      "loss": 1.0034,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.3104252219200134,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.8135,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.3317263722419739,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.8386,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.2832105755805969,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.7435,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.3323349952697754,
      "learning_rate": 0.00016053215077605322,
      "loss": 1.0087,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.3414359390735626,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.85,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.30590707063674927,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.8116,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.2879641354084015,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.8213,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.3349141776561737,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.7937,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.38549837470054626,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.9843,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.41241493821144104,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.9697,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.3053611218929291,
      "learning_rate": 0.0001574279379157428,
      "loss": 1.03,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.280692994594574,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.9026,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.41260674595832825,
      "learning_rate": 0.0001565410199556541,
      "loss": 1.0454,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.3307574987411499,
      "learning_rate": 0.00015609756097560978,
      "loss": 1.2087,
      "step": 105
    },
    {
      "epoch": 0.6989010989010989,
      "grad_norm": 0.3261273205280304,
      "learning_rate": 0.00015565410199556542,
      "loss": 1.1587,
      "step": 106
    },
    {
      "epoch": 0.7054945054945055,
      "grad_norm": 0.31398382782936096,
      "learning_rate": 0.00015521064301552106,
      "loss": 1.0175,
      "step": 107
    },
    {
      "epoch": 0.7120879120879121,
      "grad_norm": 0.2939504086971283,
      "learning_rate": 0.0001547671840354767,
      "loss": 0.9852,
      "step": 108
    },
    {
      "epoch": 0.7186813186813187,
      "grad_norm": 0.311310738325119,
      "learning_rate": 0.00015432372505543238,
      "loss": 0.9863,
      "step": 109
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.3005566895008087,
      "learning_rate": 0.00015388026607538802,
      "loss": 0.7199,
      "step": 110
    },
    {
      "epoch": 0.7318681318681318,
      "grad_norm": 0.3201131224632263,
      "learning_rate": 0.0001534368070953437,
      "loss": 0.9781,
      "step": 111
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.32149285078048706,
      "learning_rate": 0.00015299334811529934,
      "loss": 1.1968,
      "step": 112
    },
    {
      "epoch": 0.7450549450549451,
      "grad_norm": 0.20881633460521698,
      "learning_rate": 0.00015254988913525498,
      "loss": 0.6594,
      "step": 113
    },
    {
      "epoch": 0.7516483516483516,
      "grad_norm": 0.27455934882164,
      "learning_rate": 0.00015210643015521066,
      "loss": 0.9927,
      "step": 114
    },
    {
      "epoch": 0.7582417582417582,
      "grad_norm": 0.3547341525554657,
      "learning_rate": 0.0001516629711751663,
      "loss": 0.9064,
      "step": 115
    },
    {
      "epoch": 0.7648351648351648,
      "grad_norm": 0.29746896028518677,
      "learning_rate": 0.00015121951219512197,
      "loss": 0.7962,
      "step": 116
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 0.3209431767463684,
      "learning_rate": 0.00015077605321507762,
      "loss": 0.9651,
      "step": 117
    },
    {
      "epoch": 0.778021978021978,
      "grad_norm": 0.3097621500492096,
      "learning_rate": 0.0001503325942350333,
      "loss": 0.7405,
      "step": 118
    },
    {
      "epoch": 0.7846153846153846,
      "grad_norm": 0.36424967646598816,
      "learning_rate": 0.0001498891352549889,
      "loss": 0.9138,
      "step": 119
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.41704678535461426,
      "learning_rate": 0.00014944567627494458,
      "loss": 0.8959,
      "step": 120
    },
    {
      "epoch": 0.7978021978021979,
      "grad_norm": 0.9710575342178345,
      "learning_rate": 0.00014900221729490022,
      "loss": 0.9368,
      "step": 121
    },
    {
      "epoch": 0.8043956043956044,
      "grad_norm": 0.38822558522224426,
      "learning_rate": 0.0001485587583148559,
      "loss": 0.9681,
      "step": 122
    },
    {
      "epoch": 0.810989010989011,
      "grad_norm": 0.3288450837135315,
      "learning_rate": 0.00014811529933481154,
      "loss": 0.8019,
      "step": 123
    },
    {
      "epoch": 0.8175824175824176,
      "grad_norm": 0.35870131850242615,
      "learning_rate": 0.0001476718403547672,
      "loss": 0.7741,
      "step": 124
    },
    {
      "epoch": 0.8241758241758241,
      "grad_norm": 0.31660914421081543,
      "learning_rate": 0.00014722838137472282,
      "loss": 0.9909,
      "step": 125
    },
    {
      "epoch": 0.8307692307692308,
      "grad_norm": 0.3862468898296356,
      "learning_rate": 0.0001467849223946785,
      "loss": 0.8362,
      "step": 126
    },
    {
      "epoch": 0.8373626373626374,
      "grad_norm": 0.42162254452705383,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.948,
      "step": 127
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.34994199872016907,
      "learning_rate": 0.0001458980044345898,
      "loss": 1.1064,
      "step": 128
    },
    {
      "epoch": 0.8505494505494505,
      "grad_norm": 0.3114795386791229,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.097,
      "step": 129
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.2868303656578064,
      "learning_rate": 0.00014501108647450113,
      "loss": 0.7247,
      "step": 130
    },
    {
      "epoch": 0.8637362637362638,
      "grad_norm": 0.32066768407821655,
      "learning_rate": 0.00014456762749445675,
      "loss": 0.9474,
      "step": 131
    },
    {
      "epoch": 0.8703296703296703,
      "grad_norm": 0.2781572639942169,
      "learning_rate": 0.00014412416851441242,
      "loss": 0.7625,
      "step": 132
    },
    {
      "epoch": 0.8769230769230769,
      "grad_norm": 0.34843742847442627,
      "learning_rate": 0.00014368070953436806,
      "loss": 0.898,
      "step": 133
    },
    {
      "epoch": 0.8835164835164835,
      "grad_norm": 0.4077232778072357,
      "learning_rate": 0.00014323725055432373,
      "loss": 0.9139,
      "step": 134
    },
    {
      "epoch": 0.8901098901098901,
      "grad_norm": 0.3193439841270447,
      "learning_rate": 0.00014279379157427938,
      "loss": 0.835,
      "step": 135
    },
    {
      "epoch": 0.8967032967032967,
      "grad_norm": 0.3766500949859619,
      "learning_rate": 0.00014235033259423505,
      "loss": 1.033,
      "step": 136
    },
    {
      "epoch": 0.9032967032967033,
      "grad_norm": 0.3754067122936249,
      "learning_rate": 0.0001419068736141907,
      "loss": 0.9025,
      "step": 137
    },
    {
      "epoch": 0.9098901098901099,
      "grad_norm": 0.35820555686950684,
      "learning_rate": 0.00014146341463414634,
      "loss": 0.979,
      "step": 138
    },
    {
      "epoch": 0.9164835164835164,
      "grad_norm": 0.26612144708633423,
      "learning_rate": 0.000141019955654102,
      "loss": 0.8198,
      "step": 139
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.31570959091186523,
      "learning_rate": 0.00014057649667405765,
      "loss": 0.9311,
      "step": 140
    },
    {
      "epoch": 0.9296703296703297,
      "grad_norm": 0.3997712731361389,
      "learning_rate": 0.00014013303769401332,
      "loss": 1.0036,
      "step": 141
    },
    {
      "epoch": 0.9362637362637363,
      "grad_norm": 0.28671470284461975,
      "learning_rate": 0.00013968957871396897,
      "loss": 0.7956,
      "step": 142
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 0.2961069345474243,
      "learning_rate": 0.00013924611973392464,
      "loss": 0.9616,
      "step": 143
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.4304637908935547,
      "learning_rate": 0.00013880266075388026,
      "loss": 0.9982,
      "step": 144
    },
    {
      "epoch": 0.9560439560439561,
      "grad_norm": 0.26339417695999146,
      "learning_rate": 0.00013835920177383593,
      "loss": 0.9484,
      "step": 145
    },
    {
      "epoch": 0.9626373626373627,
      "grad_norm": 0.32710322737693787,
      "learning_rate": 0.00013791574279379157,
      "loss": 0.9314,
      "step": 146
    },
    {
      "epoch": 0.9692307692307692,
      "grad_norm": 0.3484141528606415,
      "learning_rate": 0.00013747228381374724,
      "loss": 0.7562,
      "step": 147
    },
    {
      "epoch": 0.9758241758241758,
      "grad_norm": 0.3400699496269226,
      "learning_rate": 0.0001370288248337029,
      "loss": 1.0014,
      "step": 148
    },
    {
      "epoch": 0.9824175824175824,
      "grad_norm": 0.3703884482383728,
      "learning_rate": 0.00013658536585365856,
      "loss": 0.9358,
      "step": 149
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.3845970034599304,
      "learning_rate": 0.00013614190687361418,
      "loss": 1.0897,
      "step": 150
    },
    {
      "epoch": 0.9956043956043956,
      "grad_norm": 0.3006916642189026,
      "learning_rate": 0.00013569844789356985,
      "loss": 0.9231,
      "step": 151
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5204401016235352,
      "learning_rate": 0.0001352549889135255,
      "loss": 0.9319,
      "step": 152
    },
    {
      "epoch": 1.0065934065934066,
      "grad_norm": 0.34535032510757446,
      "learning_rate": 0.00013481152993348116,
      "loss": 0.7057,
      "step": 153
    },
    {
      "epoch": 1.0131868131868131,
      "grad_norm": 0.3064813017845154,
      "learning_rate": 0.0001343680709534368,
      "loss": 0.9414,
      "step": 154
    },
    {
      "epoch": 1.0197802197802197,
      "grad_norm": 0.30574846267700195,
      "learning_rate": 0.00013392461197339248,
      "loss": 0.9608,
      "step": 155
    },
    {
      "epoch": 1.0263736263736263,
      "grad_norm": 0.32127997279167175,
      "learning_rate": 0.00013348115299334812,
      "loss": 0.9406,
      "step": 156
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.31777361035346985,
      "learning_rate": 0.00013303769401330377,
      "loss": 0.9024,
      "step": 157
    },
    {
      "epoch": 1.0395604395604396,
      "grad_norm": 0.3551713824272156,
      "learning_rate": 0.00013259423503325944,
      "loss": 0.9009,
      "step": 158
    },
    {
      "epoch": 1.0461538461538462,
      "grad_norm": 0.36708202958106995,
      "learning_rate": 0.00013215077605321509,
      "loss": 0.6567,
      "step": 159
    },
    {
      "epoch": 1.0527472527472528,
      "grad_norm": 0.2715701758861542,
      "learning_rate": 0.00013170731707317076,
      "loss": 0.5907,
      "step": 160
    },
    {
      "epoch": 1.0593406593406594,
      "grad_norm": 0.33414098620414734,
      "learning_rate": 0.0001312638580931264,
      "loss": 0.7598,
      "step": 161
    },
    {
      "epoch": 1.065934065934066,
      "grad_norm": 0.4587686359882355,
      "learning_rate": 0.00013082039911308205,
      "loss": 0.9269,
      "step": 162
    },
    {
      "epoch": 1.0725274725274725,
      "grad_norm": 0.3041750490665436,
      "learning_rate": 0.0001303769401330377,
      "loss": 0.7888,
      "step": 163
    },
    {
      "epoch": 1.079120879120879,
      "grad_norm": 0.338975191116333,
      "learning_rate": 0.00012993348115299336,
      "loss": 0.8071,
      "step": 164
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.3622402250766754,
      "learning_rate": 0.000129490022172949,
      "loss": 1.2186,
      "step": 165
    },
    {
      "epoch": 1.0923076923076924,
      "grad_norm": 0.4060513377189636,
      "learning_rate": 0.00012904656319290468,
      "loss": 0.8133,
      "step": 166
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.2938317358493805,
      "learning_rate": 0.00012860310421286032,
      "loss": 0.8516,
      "step": 167
    },
    {
      "epoch": 1.1054945054945056,
      "grad_norm": 0.38381171226501465,
      "learning_rate": 0.00012815964523281597,
      "loss": 0.6775,
      "step": 168
    },
    {
      "epoch": 1.1120879120879121,
      "grad_norm": 0.4568723738193512,
      "learning_rate": 0.0001277161862527716,
      "loss": 0.8801,
      "step": 169
    },
    {
      "epoch": 1.1186813186813187,
      "grad_norm": 0.435303658246994,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.9645,
      "step": 170
    },
    {
      "epoch": 1.1252747252747253,
      "grad_norm": 0.317023903131485,
      "learning_rate": 0.00012682926829268293,
      "loss": 0.6754,
      "step": 171
    },
    {
      "epoch": 1.1318681318681318,
      "grad_norm": 0.343130499124527,
      "learning_rate": 0.0001263858093126386,
      "loss": 0.8705,
      "step": 172
    },
    {
      "epoch": 1.1384615384615384,
      "grad_norm": 0.38000965118408203,
      "learning_rate": 0.00012594235033259424,
      "loss": 0.7875,
      "step": 173
    },
    {
      "epoch": 1.145054945054945,
      "grad_norm": 0.47831991314888,
      "learning_rate": 0.00012549889135254989,
      "loss": 0.7921,
      "step": 174
    },
    {
      "epoch": 1.1516483516483516,
      "grad_norm": 0.5294928550720215,
      "learning_rate": 0.00012505543237250553,
      "loss": 1.0668,
      "step": 175
    },
    {
      "epoch": 1.1582417582417581,
      "grad_norm": 0.4222194254398346,
      "learning_rate": 0.0001246119733924612,
      "loss": 0.8373,
      "step": 176
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.3982214331626892,
      "learning_rate": 0.00012416851441241685,
      "loss": 0.7711,
      "step": 177
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 0.40821346640586853,
      "learning_rate": 0.00012372505543237252,
      "loss": 0.773,
      "step": 178
    },
    {
      "epoch": 1.178021978021978,
      "grad_norm": 0.35746657848358154,
      "learning_rate": 0.00012328159645232816,
      "loss": 0.7166,
      "step": 179
    },
    {
      "epoch": 1.1846153846153846,
      "grad_norm": 0.4423096477985382,
      "learning_rate": 0.0001228381374722838,
      "loss": 0.7889,
      "step": 180
    },
    {
      "epoch": 1.1912087912087912,
      "grad_norm": 0.40855491161346436,
      "learning_rate": 0.00012239467849223948,
      "loss": 0.8963,
      "step": 181
    },
    {
      "epoch": 1.1978021978021978,
      "grad_norm": 0.3888983428478241,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.9323,
      "step": 182
    },
    {
      "epoch": 1.2043956043956043,
      "grad_norm": 0.4350970685482025,
      "learning_rate": 0.00012150776053215078,
      "loss": 0.9372,
      "step": 183
    },
    {
      "epoch": 1.210989010989011,
      "grad_norm": 0.5111949443817139,
      "learning_rate": 0.00012106430155210644,
      "loss": 0.808,
      "step": 184
    },
    {
      "epoch": 1.2175824175824177,
      "grad_norm": 0.4017014503479004,
      "learning_rate": 0.0001206208425720621,
      "loss": 0.9143,
      "step": 185
    },
    {
      "epoch": 1.2241758241758243,
      "grad_norm": 0.4676794707775116,
      "learning_rate": 0.00012017738359201774,
      "loss": 0.9045,
      "step": 186
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.4239216446876526,
      "learning_rate": 0.0001197339246119734,
      "loss": 0.7217,
      "step": 187
    },
    {
      "epoch": 1.2373626373626374,
      "grad_norm": 0.464688777923584,
      "learning_rate": 0.00011929046563192906,
      "loss": 0.926,
      "step": 188
    },
    {
      "epoch": 1.243956043956044,
      "grad_norm": 0.39492112398147583,
      "learning_rate": 0.00011884700665188471,
      "loss": 0.6492,
      "step": 189
    },
    {
      "epoch": 1.2505494505494505,
      "grad_norm": 0.47923383116722107,
      "learning_rate": 0.00011840354767184036,
      "loss": 0.8464,
      "step": 190
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.44110584259033203,
      "learning_rate": 0.00011796008869179602,
      "loss": 0.8642,
      "step": 191
    },
    {
      "epoch": 1.2637362637362637,
      "grad_norm": 0.4045514464378357,
      "learning_rate": 0.00011751662971175166,
      "loss": 0.8109,
      "step": 192
    },
    {
      "epoch": 1.2703296703296703,
      "grad_norm": 0.3923543691635132,
      "learning_rate": 0.00011707317073170732,
      "loss": 0.7604,
      "step": 193
    },
    {
      "epoch": 1.2769230769230768,
      "grad_norm": 0.4686066210269928,
      "learning_rate": 0.00011662971175166298,
      "loss": 1.0255,
      "step": 194
    },
    {
      "epoch": 1.2835164835164834,
      "grad_norm": 0.4381221532821655,
      "learning_rate": 0.00011618625277161863,
      "loss": 0.8676,
      "step": 195
    },
    {
      "epoch": 1.2901098901098902,
      "grad_norm": 0.4110540449619293,
      "learning_rate": 0.00011574279379157429,
      "loss": 0.6166,
      "step": 196
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.49437323212623596,
      "learning_rate": 0.00011529933481152995,
      "loss": 0.9385,
      "step": 197
    },
    {
      "epoch": 1.3032967032967033,
      "grad_norm": 0.45208626985549927,
      "learning_rate": 0.00011485587583148558,
      "loss": 0.8375,
      "step": 198
    },
    {
      "epoch": 1.30989010989011,
      "grad_norm": 0.37106406688690186,
      "learning_rate": 0.00011441241685144124,
      "loss": 0.7563,
      "step": 199
    },
    {
      "epoch": 1.3164835164835165,
      "grad_norm": 0.370037704706192,
      "learning_rate": 0.0001139689578713969,
      "loss": 0.8622,
      "step": 200
    },
    {
      "epoch": 1.323076923076923,
      "grad_norm": 0.48143476247787476,
      "learning_rate": 0.00011352549889135255,
      "loss": 0.7221,
      "step": 201
    },
    {
      "epoch": 1.3296703296703296,
      "grad_norm": 0.4213281273841858,
      "learning_rate": 0.00011308203991130821,
      "loss": 0.7247,
      "step": 202
    },
    {
      "epoch": 1.3362637362637364,
      "grad_norm": 0.4462879002094269,
      "learning_rate": 0.00011263858093126387,
      "loss": 0.7985,
      "step": 203
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 0.46097874641418457,
      "learning_rate": 0.00011219512195121953,
      "loss": 0.8601,
      "step": 204
    },
    {
      "epoch": 1.3494505494505495,
      "grad_norm": 0.4965132176876068,
      "learning_rate": 0.00011175166297117516,
      "loss": 0.8169,
      "step": 205
    },
    {
      "epoch": 1.3560439560439561,
      "grad_norm": 0.39928263425827026,
      "learning_rate": 0.00011130820399113082,
      "loss": 0.9583,
      "step": 206
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.5035346746444702,
      "learning_rate": 0.00011086474501108647,
      "loss": 0.9851,
      "step": 207
    },
    {
      "epoch": 1.3692307692307693,
      "grad_norm": 0.5127368569374084,
      "learning_rate": 0.00011042128603104213,
      "loss": 0.8507,
      "step": 208
    },
    {
      "epoch": 1.3758241758241758,
      "grad_norm": 0.39642006158828735,
      "learning_rate": 0.00010997782705099779,
      "loss": 0.716,
      "step": 209
    },
    {
      "epoch": 1.3824175824175824,
      "grad_norm": 0.47569793462753296,
      "learning_rate": 0.00010953436807095345,
      "loss": 0.7786,
      "step": 210
    },
    {
      "epoch": 1.389010989010989,
      "grad_norm": 0.647522509098053,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.8166,
      "step": 211
    },
    {
      "epoch": 1.3956043956043955,
      "grad_norm": 0.5686987638473511,
      "learning_rate": 0.00010864745011086475,
      "loss": 0.8687,
      "step": 212
    },
    {
      "epoch": 1.402197802197802,
      "grad_norm": 0.4099014401435852,
      "learning_rate": 0.00010820399113082041,
      "loss": 0.7439,
      "step": 213
    },
    {
      "epoch": 1.4087912087912087,
      "grad_norm": 0.5358811020851135,
      "learning_rate": 0.00010776053215077607,
      "loss": 0.7286,
      "step": 214
    },
    {
      "epoch": 1.4153846153846155,
      "grad_norm": 0.39305442571640015,
      "learning_rate": 0.00010731707317073172,
      "loss": 0.6529,
      "step": 215
    },
    {
      "epoch": 1.421978021978022,
      "grad_norm": 0.5362666845321655,
      "learning_rate": 0.00010687361419068738,
      "loss": 0.7931,
      "step": 216
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.5605432987213135,
      "learning_rate": 0.00010643015521064301,
      "loss": 0.7819,
      "step": 217
    },
    {
      "epoch": 1.4351648351648352,
      "grad_norm": 0.40266886353492737,
      "learning_rate": 0.00010598669623059867,
      "loss": 0.7869,
      "step": 218
    },
    {
      "epoch": 1.4417582417582417,
      "grad_norm": 0.5134586095809937,
      "learning_rate": 0.00010554323725055433,
      "loss": 0.7585,
      "step": 219
    },
    {
      "epoch": 1.4483516483516483,
      "grad_norm": 0.4238825738430023,
      "learning_rate": 0.00010509977827050999,
      "loss": 0.6799,
      "step": 220
    },
    {
      "epoch": 1.4549450549450549,
      "grad_norm": 0.6013477444648743,
      "learning_rate": 0.00010465631929046564,
      "loss": 0.9191,
      "step": 221
    },
    {
      "epoch": 1.4615384615384617,
      "grad_norm": 0.4416446089744568,
      "learning_rate": 0.0001042128603104213,
      "loss": 0.9287,
      "step": 222
    },
    {
      "epoch": 1.4681318681318682,
      "grad_norm": 0.457163006067276,
      "learning_rate": 0.00010376940133037693,
      "loss": 0.777,
      "step": 223
    },
    {
      "epoch": 1.4747252747252748,
      "grad_norm": 0.4844575524330139,
      "learning_rate": 0.00010332594235033259,
      "loss": 0.7849,
      "step": 224
    },
    {
      "epoch": 1.4813186813186814,
      "grad_norm": 0.4775691628456116,
      "learning_rate": 0.00010288248337028825,
      "loss": 0.851,
      "step": 225
    },
    {
      "epoch": 1.487912087912088,
      "grad_norm": 0.4356340169906616,
      "learning_rate": 0.0001024390243902439,
      "loss": 0.7115,
      "step": 226
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.44481128454208374,
      "learning_rate": 0.00010199556541019956,
      "loss": 0.7819,
      "step": 227
    },
    {
      "epoch": 1.501098901098901,
      "grad_norm": 0.4558474123477936,
      "learning_rate": 0.00010155210643015522,
      "loss": 0.8979,
      "step": 228
    },
    {
      "epoch": 1.5076923076923077,
      "grad_norm": 0.4950856864452362,
      "learning_rate": 0.00010110864745011087,
      "loss": 0.7285,
      "step": 229
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 0.5578146576881409,
      "learning_rate": 0.00010066518847006652,
      "loss": 0.9181,
      "step": 230
    },
    {
      "epoch": 1.5208791208791208,
      "grad_norm": 0.49424436688423157,
      "learning_rate": 0.00010022172949002218,
      "loss": 0.6759,
      "step": 231
    },
    {
      "epoch": 1.5274725274725274,
      "grad_norm": 0.491445392370224,
      "learning_rate": 9.977827050997783e-05,
      "loss": 0.8547,
      "step": 232
    },
    {
      "epoch": 1.534065934065934,
      "grad_norm": 0.494456946849823,
      "learning_rate": 9.933481152993348e-05,
      "loss": 0.8263,
      "step": 233
    },
    {
      "epoch": 1.5406593406593405,
      "grad_norm": 0.42617034912109375,
      "learning_rate": 9.889135254988914e-05,
      "loss": 0.5556,
      "step": 234
    },
    {
      "epoch": 1.5472527472527473,
      "grad_norm": 0.5140032172203064,
      "learning_rate": 9.84478935698448e-05,
      "loss": 0.8583,
      "step": 235
    },
    {
      "epoch": 1.5538461538461539,
      "grad_norm": 0.579046368598938,
      "learning_rate": 9.800443458980046e-05,
      "loss": 0.9627,
      "step": 236
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.48717352747917175,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.8486,
      "step": 237
    },
    {
      "epoch": 1.567032967032967,
      "grad_norm": 0.5456934571266174,
      "learning_rate": 9.711751662971176e-05,
      "loss": 0.9161,
      "step": 238
    },
    {
      "epoch": 1.5736263736263736,
      "grad_norm": 0.4280259907245636,
      "learning_rate": 9.667405764966742e-05,
      "loss": 0.7307,
      "step": 239
    },
    {
      "epoch": 1.5802197802197804,
      "grad_norm": 0.4907631278038025,
      "learning_rate": 9.623059866962306e-05,
      "loss": 0.8357,
      "step": 240
    },
    {
      "epoch": 1.586813186813187,
      "grad_norm": 0.5201488733291626,
      "learning_rate": 9.578713968957872e-05,
      "loss": 0.7085,
      "step": 241
    },
    {
      "epoch": 1.5934065934065935,
      "grad_norm": 0.48537105321884155,
      "learning_rate": 9.534368070953438e-05,
      "loss": 0.7675,
      "step": 242
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.44829583168029785,
      "learning_rate": 9.490022172949002e-05,
      "loss": 0.7647,
      "step": 243
    },
    {
      "epoch": 1.6065934065934067,
      "grad_norm": 0.44917064905166626,
      "learning_rate": 9.445676274944568e-05,
      "loss": 0.7813,
      "step": 244
    },
    {
      "epoch": 1.6131868131868132,
      "grad_norm": 0.5269826054573059,
      "learning_rate": 9.401330376940134e-05,
      "loss": 0.7184,
      "step": 245
    },
    {
      "epoch": 1.6197802197802198,
      "grad_norm": 0.4876798093318939,
      "learning_rate": 9.356984478935698e-05,
      "loss": 0.78,
      "step": 246
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.40217915177345276,
      "learning_rate": 9.312638580931264e-05,
      "loss": 0.797,
      "step": 247
    },
    {
      "epoch": 1.632967032967033,
      "grad_norm": 0.5015186667442322,
      "learning_rate": 9.26829268292683e-05,
      "loss": 0.7284,
      "step": 248
    },
    {
      "epoch": 1.6395604395604395,
      "grad_norm": 0.48553842306137085,
      "learning_rate": 9.223946784922394e-05,
      "loss": 0.745,
      "step": 249
    },
    {
      "epoch": 1.646153846153846,
      "grad_norm": 0.5199882984161377,
      "learning_rate": 9.17960088691796e-05,
      "loss": 0.9387,
      "step": 250
    },
    {
      "epoch": 1.6527472527472526,
      "grad_norm": 0.502065896987915,
      "learning_rate": 9.135254988913526e-05,
      "loss": 0.8418,
      "step": 251
    },
    {
      "epoch": 1.6593406593406592,
      "grad_norm": 0.42118778824806213,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.7361,
      "step": 252
    },
    {
      "epoch": 1.6659340659340658,
      "grad_norm": 0.5904996991157532,
      "learning_rate": 9.046563192904656e-05,
      "loss": 0.7712,
      "step": 253
    },
    {
      "epoch": 1.6725274725274726,
      "grad_norm": 0.4708808660507202,
      "learning_rate": 9.002217294900222e-05,
      "loss": 0.8115,
      "step": 254
    },
    {
      "epoch": 1.6791208791208792,
      "grad_norm": 0.49758708477020264,
      "learning_rate": 8.957871396895788e-05,
      "loss": 0.6859,
      "step": 255
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 0.5870069861412048,
      "learning_rate": 8.913525498891354e-05,
      "loss": 0.9235,
      "step": 256
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.6316494345664978,
      "learning_rate": 8.869179600886919e-05,
      "loss": 1.1027,
      "step": 257
    },
    {
      "epoch": 1.6989010989010989,
      "grad_norm": 0.5093106627464294,
      "learning_rate": 8.824833702882484e-05,
      "loss": 1.2491,
      "step": 258
    },
    {
      "epoch": 1.7054945054945057,
      "grad_norm": 0.5510773658752441,
      "learning_rate": 8.78048780487805e-05,
      "loss": 0.6927,
      "step": 259
    },
    {
      "epoch": 1.7120879120879122,
      "grad_norm": 0.5143725872039795,
      "learning_rate": 8.736141906873615e-05,
      "loss": 0.8841,
      "step": 260
    },
    {
      "epoch": 1.7186813186813188,
      "grad_norm": 0.47042328119277954,
      "learning_rate": 8.69179600886918e-05,
      "loss": 0.6449,
      "step": 261
    },
    {
      "epoch": 1.7252747252747254,
      "grad_norm": 0.5914619565010071,
      "learning_rate": 8.647450110864746e-05,
      "loss": 0.7105,
      "step": 262
    },
    {
      "epoch": 1.731868131868132,
      "grad_norm": 0.5668938755989075,
      "learning_rate": 8.603104212860311e-05,
      "loss": 0.753,
      "step": 263
    },
    {
      "epoch": 1.7384615384615385,
      "grad_norm": 0.56303870677948,
      "learning_rate": 8.558758314855876e-05,
      "loss": 0.8215,
      "step": 264
    },
    {
      "epoch": 1.745054945054945,
      "grad_norm": 0.5173187851905823,
      "learning_rate": 8.514412416851442e-05,
      "loss": 0.7045,
      "step": 265
    },
    {
      "epoch": 1.7516483516483516,
      "grad_norm": 0.5191384553909302,
      "learning_rate": 8.470066518847007e-05,
      "loss": 0.6456,
      "step": 266
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.4634022116661072,
      "learning_rate": 8.425720620842572e-05,
      "loss": 0.7615,
      "step": 267
    },
    {
      "epoch": 1.7648351648351648,
      "grad_norm": 0.5479320883750916,
      "learning_rate": 8.381374722838138e-05,
      "loss": 0.6899,
      "step": 268
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.47928696870803833,
      "learning_rate": 8.337028824833703e-05,
      "loss": 0.6561,
      "step": 269
    },
    {
      "epoch": 1.778021978021978,
      "grad_norm": 0.5587106347084045,
      "learning_rate": 8.292682926829268e-05,
      "loss": 0.9368,
      "step": 270
    },
    {
      "epoch": 1.7846153846153845,
      "grad_norm": 0.637795627117157,
      "learning_rate": 8.248337028824834e-05,
      "loss": 0.8483,
      "step": 271
    },
    {
      "epoch": 1.791208791208791,
      "grad_norm": 0.5552746653556824,
      "learning_rate": 8.2039911308204e-05,
      "loss": 0.7908,
      "step": 272
    },
    {
      "epoch": 1.7978021978021979,
      "grad_norm": 0.5976499319076538,
      "learning_rate": 8.159645232815965e-05,
      "loss": 0.9098,
      "step": 273
    },
    {
      "epoch": 1.8043956043956044,
      "grad_norm": 0.46297407150268555,
      "learning_rate": 8.11529933481153e-05,
      "loss": 0.7524,
      "step": 274
    },
    {
      "epoch": 1.810989010989011,
      "grad_norm": 0.500605046749115,
      "learning_rate": 8.070953436807095e-05,
      "loss": 0.5731,
      "step": 275
    },
    {
      "epoch": 1.8175824175824176,
      "grad_norm": 0.5981438755989075,
      "learning_rate": 8.026607538802661e-05,
      "loss": 0.7453,
      "step": 276
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.5893169641494751,
      "learning_rate": 7.982261640798227e-05,
      "loss": 0.9285,
      "step": 277
    },
    {
      "epoch": 1.830769230769231,
      "grad_norm": 0.6469881534576416,
      "learning_rate": 7.937915742793793e-05,
      "loss": 0.8432,
      "step": 278
    },
    {
      "epoch": 1.8373626373626375,
      "grad_norm": 0.6168275475502014,
      "learning_rate": 7.893569844789357e-05,
      "loss": 1.0163,
      "step": 279
    },
    {
      "epoch": 1.843956043956044,
      "grad_norm": 0.5998719930648804,
      "learning_rate": 7.849223946784923e-05,
      "loss": 0.8968,
      "step": 280
    },
    {
      "epoch": 1.8505494505494506,
      "grad_norm": 0.6153989434242249,
      "learning_rate": 7.804878048780489e-05,
      "loss": 0.7152,
      "step": 281
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.535092830657959,
      "learning_rate": 7.760532150776053e-05,
      "loss": 0.8648,
      "step": 282
    },
    {
      "epoch": 1.8637362637362638,
      "grad_norm": 0.4524797797203064,
      "learning_rate": 7.716186252771619e-05,
      "loss": 0.7664,
      "step": 283
    },
    {
      "epoch": 1.8703296703296703,
      "grad_norm": 0.5313891172409058,
      "learning_rate": 7.671840354767185e-05,
      "loss": 0.6354,
      "step": 284
    },
    {
      "epoch": 1.876923076923077,
      "grad_norm": 0.47400233149528503,
      "learning_rate": 7.627494456762749e-05,
      "loss": 0.5774,
      "step": 285
    },
    {
      "epoch": 1.8835164835164835,
      "grad_norm": 0.45615118741989136,
      "learning_rate": 7.583148558758315e-05,
      "loss": 0.9476,
      "step": 286
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.4720500111579895,
      "learning_rate": 7.538802660753881e-05,
      "loss": 0.7317,
      "step": 287
    },
    {
      "epoch": 1.8967032967032966,
      "grad_norm": 0.6102631092071533,
      "learning_rate": 7.494456762749445e-05,
      "loss": 0.8796,
      "step": 288
    },
    {
      "epoch": 1.9032967032967032,
      "grad_norm": 0.4916665256023407,
      "learning_rate": 7.450110864745011e-05,
      "loss": 0.8131,
      "step": 289
    },
    {
      "epoch": 1.9098901098901098,
      "grad_norm": 0.522645115852356,
      "learning_rate": 7.405764966740577e-05,
      "loss": 0.7223,
      "step": 290
    },
    {
      "epoch": 1.9164835164835163,
      "grad_norm": 0.4716815650463104,
      "learning_rate": 7.361419068736141e-05,
      "loss": 0.6585,
      "step": 291
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 0.48739391565322876,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.6986,
      "step": 292
    },
    {
      "epoch": 1.9296703296703297,
      "grad_norm": 0.6024096608161926,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.9534,
      "step": 293
    },
    {
      "epoch": 1.9362637362637363,
      "grad_norm": 0.5128664970397949,
      "learning_rate": 7.228381374722837e-05,
      "loss": 0.7733,
      "step": 294
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.5806596279144287,
      "learning_rate": 7.184035476718403e-05,
      "loss": 0.8125,
      "step": 295
    },
    {
      "epoch": 1.9494505494505494,
      "grad_norm": 0.5788159966468811,
      "learning_rate": 7.139689578713969e-05,
      "loss": 0.8607,
      "step": 296
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.5046370029449463,
      "learning_rate": 7.095343680709535e-05,
      "loss": 0.6603,
      "step": 297
    },
    {
      "epoch": 1.9626373626373628,
      "grad_norm": 0.5114449858665466,
      "learning_rate": 7.0509977827051e-05,
      "loss": 0.8205,
      "step": 298
    },
    {
      "epoch": 1.9692307692307693,
      "grad_norm": 0.6085333824157715,
      "learning_rate": 7.006651884700666e-05,
      "loss": 0.8441,
      "step": 299
    },
    {
      "epoch": 1.975824175824176,
      "grad_norm": 0.5628012418746948,
      "learning_rate": 6.962305986696232e-05,
      "loss": 0.7131,
      "step": 300
    },
    {
      "epoch": 1.9824175824175825,
      "grad_norm": 0.5451134443283081,
      "learning_rate": 6.917960088691796e-05,
      "loss": 0.9351,
      "step": 301
    },
    {
      "epoch": 1.989010989010989,
      "grad_norm": 0.5784966349601746,
      "learning_rate": 6.873614190687362e-05,
      "loss": 0.8826,
      "step": 302
    },
    {
      "epoch": 1.9956043956043956,
      "grad_norm": 0.5935767292976379,
      "learning_rate": 6.829268292682928e-05,
      "loss": 0.7644,
      "step": 303
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7064018845558167,
      "learning_rate": 6.784922394678492e-05,
      "loss": 0.8582,
      "step": 304
    },
    {
      "epoch": 2.0065934065934066,
      "grad_norm": 0.5176734924316406,
      "learning_rate": 6.740576496674058e-05,
      "loss": 0.871,
      "step": 305
    },
    {
      "epoch": 2.013186813186813,
      "grad_norm": 0.39148128032684326,
      "learning_rate": 6.696230598669624e-05,
      "loss": 0.6972,
      "step": 306
    },
    {
      "epoch": 2.0197802197802197,
      "grad_norm": 0.5755179524421692,
      "learning_rate": 6.651884700665188e-05,
      "loss": 0.7348,
      "step": 307
    },
    {
      "epoch": 2.0263736263736263,
      "grad_norm": 0.5623214840888977,
      "learning_rate": 6.607538802660754e-05,
      "loss": 0.6345,
      "step": 308
    },
    {
      "epoch": 2.032967032967033,
      "grad_norm": 0.55307936668396,
      "learning_rate": 6.56319290465632e-05,
      "loss": 0.6979,
      "step": 309
    },
    {
      "epoch": 2.0395604395604394,
      "grad_norm": 0.5802642703056335,
      "learning_rate": 6.518847006651884e-05,
      "loss": 0.7513,
      "step": 310
    },
    {
      "epoch": 2.046153846153846,
      "grad_norm": 0.5402441024780273,
      "learning_rate": 6.47450110864745e-05,
      "loss": 0.7021,
      "step": 311
    },
    {
      "epoch": 2.0527472527472526,
      "grad_norm": 0.6132050156593323,
      "learning_rate": 6.430155210643016e-05,
      "loss": 0.7383,
      "step": 312
    },
    {
      "epoch": 2.059340659340659,
      "grad_norm": 0.5783182382583618,
      "learning_rate": 6.38580931263858e-05,
      "loss": 0.8362,
      "step": 313
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.6269601583480835,
      "learning_rate": 6.341463414634146e-05,
      "loss": 0.8861,
      "step": 314
    },
    {
      "epoch": 2.0725274725274727,
      "grad_norm": 0.7019800543785095,
      "learning_rate": 6.297117516629712e-05,
      "loss": 0.6313,
      "step": 315
    }
  ],
  "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": 5.145012475158528e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}