{
  "best_metric": 1.4160813093185425,
  "best_model_checkpoint": "miner_id_24/checkpoint-1900",
  "epoch": 0.10406967190666594,
  "eval_steps": 100,
  "global_step": 1900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.4773511529824174e-05,
      "grad_norm": 0.9768730998039246,
      "learning_rate": 6.666666649834951e-06,
      "loss": 2.6066,
      "step": 1
    },
    {
      "epoch": 5.4773511529824174e-05,
      "eval_loss": 2.296978235244751,
      "eval_runtime": 45.7865,
      "eval_samples_per_second": 2.009,
      "eval_steps_per_second": 2.009,
      "step": 1
    },
    {
      "epoch": 0.00010954702305964835,
      "grad_norm": 3.5348165035247803,
      "learning_rate": 1.3333333299669903e-05,
      "loss": 2.2621,
      "step": 2
    },
    {
      "epoch": 0.00016432053458947254,
      "grad_norm": 0.821417510509491,
      "learning_rate": 1.9999999494757503e-05,
      "loss": 1.6219,
      "step": 3
    },
    {
      "epoch": 0.0002190940461192967,
      "grad_norm": 1.6492409706115723,
      "learning_rate": 2.6666666599339806e-05,
      "loss": 2.4681,
      "step": 4
    },
    {
      "epoch": 0.0002738675576491209,
      "grad_norm": 1.1491681337356567,
      "learning_rate": 3.333333370392211e-05,
      "loss": 2.459,
      "step": 5
    },
    {
      "epoch": 0.0003286410691789451,
      "grad_norm": 0.6358470916748047,
      "learning_rate": 3.9999998989515007e-05,
      "loss": 2.1835,
      "step": 6
    },
    {
      "epoch": 0.00038341458070876926,
      "grad_norm": 0.815460741519928,
      "learning_rate": 4.6666664275107905e-05,
      "loss": 2.5673,
      "step": 7
    },
    {
      "epoch": 0.0004381880922385934,
      "grad_norm": 2.9213340282440186,
      "learning_rate": 5.333333319867961e-05,
      "loss": 1.8313,
      "step": 8
    },
    {
      "epoch": 0.0004929616037684176,
      "grad_norm": 1.1703193187713623,
      "learning_rate": 6.000000212225132e-05,
      "loss": 1.9391,
      "step": 9
    },
    {
      "epoch": 0.0005477351152982418,
      "grad_norm": 0.812526285648346,
      "learning_rate": 6.666666740784422e-05,
      "loss": 3.092,
      "step": 10
    },
    {
      "epoch": 0.000602508626828066,
      "grad_norm": 1.7026020288467407,
      "learning_rate": 7.333333633141592e-05,
      "loss": 1.987,
      "step": 11
    },
    {
      "epoch": 0.0006572821383578902,
      "grad_norm": 2.2235491275787354,
      "learning_rate": 7.999999797903001e-05,
      "loss": 2.3579,
      "step": 12
    },
    {
      "epoch": 0.0007120556498877143,
      "grad_norm": 2.0740509033203125,
      "learning_rate": 8.666666690260172e-05,
      "loss": 1.9962,
      "step": 13
    },
    {
      "epoch": 0.0007668291614175385,
      "grad_norm": 1.1765992641448975,
      "learning_rate": 9.333332855021581e-05,
      "loss": 2.3411,
      "step": 14
    },
    {
      "epoch": 0.0008216026729473627,
      "grad_norm": 3.0403523445129395,
      "learning_rate": 9.999999747378752e-05,
      "loss": 2.004,
      "step": 15
    },
    {
      "epoch": 0.0008763761844771868,
      "grad_norm": 1.138260006904602,
      "learning_rate": 0.00010666666639735922,
      "loss": 2.2383,
      "step": 16
    },
    {
      "epoch": 0.000931149696007011,
      "grad_norm": 0.8550275564193726,
      "learning_rate": 0.00011333332804497331,
      "loss": 1.701,
      "step": 17
    },
    {
      "epoch": 0.0009859232075368353,
      "grad_norm": 3.592313289642334,
      "learning_rate": 0.00012000000424450263,
      "loss": 4.1003,
      "step": 18
    },
    {
      "epoch": 0.0010406967190666593,
      "grad_norm": 3.2478175163269043,
      "learning_rate": 0.00012666666589211673,
      "loss": 3.5006,
      "step": 19
    },
    {
      "epoch": 0.0010954702305964836,
      "grad_norm": 1.4223264455795288,
      "learning_rate": 0.00013333333481568843,
      "loss": 2.0294,
      "step": 20
    },
    {
      "epoch": 0.0011502437421263077,
      "grad_norm": 2.4346776008605957,
      "learning_rate": 0.0001399999891873449,
      "loss": 2.7581,
      "step": 21
    },
    {
      "epoch": 0.001205017253656132,
      "grad_norm": 1.796597957611084,
      "learning_rate": 0.00014666667266283184,
      "loss": 2.1086,
      "step": 22
    },
    {
      "epoch": 0.001259790765185956,
      "grad_norm": 6.398910999298096,
      "learning_rate": 0.00015333332703448832,
      "loss": 2.238,
      "step": 23
    },
    {
      "epoch": 0.0013145642767157803,
      "grad_norm": 0.6837334036827087,
      "learning_rate": 0.00015999999595806003,
      "loss": 0.9244,
      "step": 24
    },
    {
      "epoch": 0.0013693377882456044,
      "grad_norm": 1.8410735130310059,
      "learning_rate": 0.00016666666488163173,
      "loss": 1.6576,
      "step": 25
    },
    {
      "epoch": 0.0014241112997754287,
      "grad_norm": 6.760753631591797,
      "learning_rate": 0.00017333333380520344,
      "loss": 3.0678,
      "step": 26
    },
    {
      "epoch": 0.0014788848113052528,
      "grad_norm": 4.763922214508057,
      "learning_rate": 0.00017999998817685992,
      "loss": 3.2307,
      "step": 27
    },
    {
      "epoch": 0.001533658322835077,
      "grad_norm": 2.865272045135498,
      "learning_rate": 0.00018666665710043162,
      "loss": 2.0444,
      "step": 28
    },
    {
      "epoch": 0.0015884318343649011,
      "grad_norm": 4.132416725158691,
      "learning_rate": 0.00019333332602400333,
      "loss": 1.5826,
      "step": 29
    },
    {
      "epoch": 0.0016432053458947254,
      "grad_norm": 3.711785316467285,
      "learning_rate": 0.00019999999494757503,
      "loss": 1.5979,
      "step": 30
    },
    {
      "epoch": 0.0016979788574245495,
      "grad_norm": 7.421922206878662,
      "learning_rate": 0.00019999999494757503,
      "loss": 0.8549,
      "step": 31
    },
    {
      "epoch": 0.0017527523689543736,
      "grad_norm": 3.282616376876831,
      "learning_rate": 0.00019999999494757503,
      "loss": 1.9327,
      "step": 32
    },
    {
      "epoch": 0.0018075258804841979,
      "grad_norm": 7.0716047286987305,
      "learning_rate": 0.00019999999494757503,
      "loss": 1.5558,
      "step": 33
    },
    {
      "epoch": 0.001862299392014022,
      "grad_norm": 7.632896900177002,
      "learning_rate": 0.00019999999494757503,
      "loss": 2.8625,
      "step": 34
    },
    {
      "epoch": 0.0019170729035438462,
      "grad_norm": 4.289644718170166,
      "learning_rate": 0.00019999999494757503,
      "loss": 1.5348,
      "step": 35
    },
    {
      "epoch": 0.0019718464150736705,
      "grad_norm": 6.085939884185791,
      "learning_rate": 0.00019999999494757503,
      "loss": 1.8138,
      "step": 36
    },
    {
      "epoch": 0.0020266199266034944,
      "grad_norm": 4.090256214141846,
      "learning_rate": 0.0001999999803956598,
      "loss": 2.1474,
      "step": 37
    },
    {
      "epoch": 0.0020813934381333186,
      "grad_norm": 20.634706497192383,
      "learning_rate": 0.0001999999803956598,
      "loss": 4.4707,
      "step": 38
    },
    {
      "epoch": 0.002136166949663143,
      "grad_norm": 3.807300329208374,
      "learning_rate": 0.0001999999803956598,
      "loss": 1.2229,
      "step": 39
    },
    {
      "epoch": 0.0021909404611929672,
      "grad_norm": 2.3026716709136963,
      "learning_rate": 0.0001999999803956598,
      "loss": 1.6349,
      "step": 40
    },
    {
      "epoch": 0.002245713972722791,
      "grad_norm": 3.326026439666748,
      "learning_rate": 0.00019999996584374458,
      "loss": 2.4853,
      "step": 41
    },
    {
      "epoch": 0.0023004874842526154,
      "grad_norm": 5.645256996154785,
      "learning_rate": 0.00019999996584374458,
      "loss": 2.8029,
      "step": 42
    },
    {
      "epoch": 0.0023552609957824397,
      "grad_norm": 5.101483345031738,
      "learning_rate": 0.00019999996584374458,
      "loss": 2.1219,
      "step": 43
    },
    {
      "epoch": 0.002410034507312264,
      "grad_norm": 15.552334785461426,
      "learning_rate": 0.00019999996584374458,
      "loss": 2.4868,
      "step": 44
    },
    {
      "epoch": 0.002464808018842088,
      "grad_norm": 4.182264804840088,
      "learning_rate": 0.00019999996584374458,
      "loss": 1.7253,
      "step": 45
    },
    {
      "epoch": 0.002519581530371912,
      "grad_norm": 6.083288669586182,
      "learning_rate": 0.00019999995129182935,
      "loss": 2.7396,
      "step": 46
    },
    {
      "epoch": 0.0025743550419017364,
      "grad_norm": 4.40397310256958,
      "learning_rate": 0.00019999995129182935,
      "loss": 2.8195,
      "step": 47
    },
    {
      "epoch": 0.0026291285534315607,
      "grad_norm": 2.1146864891052246,
      "learning_rate": 0.00019999995129182935,
      "loss": 1.8644,
      "step": 48
    },
    {
      "epoch": 0.0026839020649613845,
      "grad_norm": 5.840154647827148,
      "learning_rate": 0.00019999993673991412,
      "loss": 3.4308,
      "step": 49
    },
    {
      "epoch": 0.002738675576491209,
      "grad_norm": 2.556663751602173,
      "learning_rate": 0.0001999999221879989,
      "loss": 1.8434,
      "step": 50
    },
    {
      "epoch": 0.002793449088021033,
      "grad_norm": 2.5221335887908936,
      "learning_rate": 0.0001999999221879989,
      "loss": 1.6593,
      "step": 51
    },
    {
      "epoch": 0.0028482225995508574,
      "grad_norm": 5.409939289093018,
      "learning_rate": 0.00019999990763608366,
      "loss": 1.291,
      "step": 52
    },
    {
      "epoch": 0.0029029961110806812,
      "grad_norm": 6.110541820526123,
      "learning_rate": 0.00019999990763608366,
      "loss": 1.8362,
      "step": 53
    },
    {
      "epoch": 0.0029577696226105055,
      "grad_norm": 3.036054849624634,
      "learning_rate": 0.00019999989308416843,
      "loss": 2.5228,
      "step": 54
    },
    {
      "epoch": 0.00301254313414033,
      "grad_norm": 1.70968759059906,
      "learning_rate": 0.00019999989308416843,
      "loss": 1.2433,
      "step": 55
    },
    {
      "epoch": 0.003067316645670154,
      "grad_norm": 2.375856876373291,
      "learning_rate": 0.00019999989308416843,
      "loss": 1.1941,
      "step": 56
    },
    {
      "epoch": 0.003122090157199978,
      "grad_norm": 5.67842960357666,
      "learning_rate": 0.0001999998785322532,
      "loss": 2.202,
      "step": 57
    },
    {
      "epoch": 0.0031768636687298023,
      "grad_norm": 2.5988142490386963,
      "learning_rate": 0.00019999986398033798,
      "loss": 1.9969,
      "step": 58
    },
    {
      "epoch": 0.0032316371802596265,
      "grad_norm": 2.14386248588562,
      "learning_rate": 0.00019999984942842275,
      "loss": 1.8093,
      "step": 59
    },
    {
      "epoch": 0.003286410691789451,
      "grad_norm": 6.440406799316406,
      "learning_rate": 0.00019999984942842275,
      "loss": 1.1994,
      "step": 60
    },
    {
      "epoch": 0.0033411842033192747,
      "grad_norm": 2.41021990776062,
      "learning_rate": 0.00019999983487650752,
      "loss": 1.6569,
      "step": 61
    },
    {
      "epoch": 0.003395957714849099,
      "grad_norm": 2.660693407058716,
      "learning_rate": 0.00019999983487650752,
      "loss": 1.473,
      "step": 62
    },
    {
      "epoch": 0.0034507312263789233,
      "grad_norm": 2.5611565113067627,
      "learning_rate": 0.0001999998203245923,
      "loss": 2.2089,
      "step": 63
    },
    {
      "epoch": 0.003505504737908747,
      "grad_norm": 3.8733954429626465,
      "learning_rate": 0.00019999980577267706,
      "loss": 2.3284,
      "step": 64
    },
    {
      "epoch": 0.0035602782494385714,
      "grad_norm": 9.533913612365723,
      "learning_rate": 0.00019999979122076184,
      "loss": 2.8818,
      "step": 65
    },
    {
      "epoch": 0.0036150517609683957,
      "grad_norm": 2.5346055030822754,
      "learning_rate": 0.0001999997766688466,
      "loss": 1.6175,
      "step": 66
    },
    {
      "epoch": 0.00366982527249822,
      "grad_norm": 2.3738250732421875,
      "learning_rate": 0.00019999976211693138,
      "loss": 1.8676,
      "step": 67
    },
    {
      "epoch": 0.003724598784028044,
      "grad_norm": 5.370700836181641,
      "learning_rate": 0.00019999976211693138,
      "loss": 1.5898,
      "step": 68
    },
    {
      "epoch": 0.003779372295557868,
      "grad_norm": 2.5777502059936523,
      "learning_rate": 0.00019999974756501615,
      "loss": 1.1626,
      "step": 69
    },
    {
      "epoch": 0.0038341458070876924,
      "grad_norm": 10.031082153320312,
      "learning_rate": 0.00019999973301310092,
      "loss": 1.9212,
      "step": 70
    },
    {
      "epoch": 0.0038889193186175167,
      "grad_norm": 3.7496495246887207,
      "learning_rate": 0.0001999997184611857,
      "loss": 1.2288,
      "step": 71
    },
    {
      "epoch": 0.003943692830147341,
      "grad_norm": 2.1219987869262695,
      "learning_rate": 0.00019999970390927047,
      "loss": 2.123,
      "step": 72
    },
    {
      "epoch": 0.003998466341677165,
      "grad_norm": 11.218868255615234,
      "learning_rate": 0.00019999968935735524,
      "loss": 3.452,
      "step": 73
    },
    {
      "epoch": 0.004053239853206989,
      "grad_norm": 3.715468645095825,
      "learning_rate": 0.00019999967480544,
      "loss": 0.3953,
      "step": 74
    },
    {
      "epoch": 0.0041080133647368134,
      "grad_norm": 4.391203880310059,
      "learning_rate": 0.00019999966025352478,
      "loss": 2.0177,
      "step": 75
    },
    {
      "epoch": 0.004162786876266637,
      "grad_norm": 2.273371696472168,
      "learning_rate": 0.00019999964570160955,
      "loss": 0.8277,
      "step": 76
    },
    {
      "epoch": 0.004217560387796462,
      "grad_norm": 5.312260627746582,
      "learning_rate": 0.00019999963114969432,
      "loss": 1.7209,
      "step": 77
    },
    {
      "epoch": 0.004272333899326286,
      "grad_norm": 21.646921157836914,
      "learning_rate": 0.0001999996165977791,
      "loss": 2.3728,
      "step": 78
    },
    {
      "epoch": 0.00432710741085611,
      "grad_norm": 4.745275497436523,
      "learning_rate": 0.00019999960204586387,
      "loss": 1.4758,
      "step": 79
    },
    {
      "epoch": 0.0043818809223859344,
      "grad_norm": 5.046701431274414,
      "learning_rate": 0.0001999995729420334,
      "loss": 1.8066,
      "step": 80
    },
    {
      "epoch": 0.004436654433915758,
      "grad_norm": 4.840040683746338,
      "learning_rate": 0.0001999995729420334,
      "loss": 2.5664,
      "step": 81
    },
    {
      "epoch": 0.004491427945445582,
      "grad_norm": 8.423829078674316,
      "learning_rate": 0.00019999955839011818,
      "loss": 4.6944,
      "step": 82
    },
    {
      "epoch": 0.004546201456975407,
      "grad_norm": 3.6969454288482666,
      "learning_rate": 0.00019999952928628772,
      "loss": 1.9163,
      "step": 83
    },
    {
      "epoch": 0.004600974968505231,
      "grad_norm": 8.3900785446167,
      "learning_rate": 0.0001999995147343725,
      "loss": 1.2402,
      "step": 84
    },
    {
      "epoch": 0.0046557484800350555,
      "grad_norm": 7.6708269119262695,
      "learning_rate": 0.00019999950018245727,
      "loss": 1.3891,
      "step": 85
    },
    {
      "epoch": 0.004710521991564879,
      "grad_norm": 4.737713813781738,
      "learning_rate": 0.00019999948563054204,
      "loss": 2.5931,
      "step": 86
    },
    {
      "epoch": 0.004765295503094703,
      "grad_norm": 9.408939361572266,
      "learning_rate": 0.00019999945652671158,
      "loss": 2.3207,
      "step": 87
    },
    {
      "epoch": 0.004820069014624528,
      "grad_norm": 4.382488250732422,
      "learning_rate": 0.00019999944197479635,
      "loss": 2.2336,
      "step": 88
    },
    {
      "epoch": 0.004874842526154352,
      "grad_norm": 4.295185089111328,
      "learning_rate": 0.00019999942742288113,
      "loss": 1.5363,
      "step": 89
    },
    {
      "epoch": 0.004929616037684176,
      "grad_norm": 5.823575019836426,
      "learning_rate": 0.00019999939831905067,
      "loss": 1.7304,
      "step": 90
    },
    {
      "epoch": 0.004984389549214,
      "grad_norm": 9.16861343383789,
      "learning_rate": 0.00019999938376713544,
      "loss": 3.1967,
      "step": 91
    },
    {
      "epoch": 0.005039163060743824,
      "grad_norm": 6.002506256103516,
      "learning_rate": 0.0001999993692152202,
      "loss": 2.3385,
      "step": 92
    },
    {
      "epoch": 0.005093936572273648,
      "grad_norm": 9.674535751342773,
      "learning_rate": 0.00019999934011138976,
      "loss": 3.4634,
      "step": 93
    },
    {
      "epoch": 0.005148710083803473,
      "grad_norm": 5.63020133972168,
      "learning_rate": 0.0001999993110075593,
      "loss": 1.0089,
      "step": 94
    },
    {
      "epoch": 0.005203483595333297,
      "grad_norm": 14.6937894821167,
      "learning_rate": 0.00019999929645564407,
      "loss": 1.7225,
      "step": 95
    },
    {
      "epoch": 0.005258257106863121,
      "grad_norm": 8.6484956741333,
      "learning_rate": 0.00019999928190372884,
      "loss": 2.2635,
      "step": 96
    },
    {
      "epoch": 0.005313030618392945,
      "grad_norm": 2.430532217025757,
      "learning_rate": 0.00019999925279989839,
      "loss": 1.943,
      "step": 97
    },
    {
      "epoch": 0.005367804129922769,
      "grad_norm": 11.094538688659668,
      "learning_rate": 0.00019999923824798316,
      "loss": 3.1786,
      "step": 98
    },
    {
      "epoch": 0.005422577641452594,
      "grad_norm": 8.20773696899414,
      "learning_rate": 0.0001999992091441527,
      "loss": 3.7003,
      "step": 99
    },
    {
      "epoch": 0.005477351152982418,
      "grad_norm": 8.1862211227417,
      "learning_rate": 0.00019999918004032224,
      "loss": 1.7666,
      "step": 100
    },
    {
      "epoch": 0.005477351152982418,
      "eval_loss": 1.8293787240982056,
      "eval_runtime": 45.7958,
      "eval_samples_per_second": 2.009,
      "eval_steps_per_second": 2.009,
      "step": 100
    },
    {
      "epoch": 0.0055321246645122415,
      "grad_norm": 2.077155590057373,
      "learning_rate": 0.00019999916548840702,
      "loss": 0.894,
      "step": 101
    },
    {
      "epoch": 0.005586898176042066,
      "grad_norm": 3.6075992584228516,
      "learning_rate": 0.00019999913638457656,
      "loss": 2.0699,
      "step": 102
    },
    {
      "epoch": 0.00564167168757189,
      "grad_norm": 5.622782230377197,
      "learning_rate": 0.0001999991072807461,
      "loss": 3.0741,
      "step": 103
    },
    {
      "epoch": 0.005696445199101715,
      "grad_norm": 2.650892972946167,
      "learning_rate": 0.00019999909272883087,
      "loss": 1.9957,
      "step": 104
    },
    {
      "epoch": 0.005751218710631539,
      "grad_norm": 2.38722562789917,
      "learning_rate": 0.00019999906362500042,
      "loss": 1.3942,
      "step": 105
    },
    {
      "epoch": 0.0058059922221613625,
      "grad_norm": 3.8706064224243164,
      "learning_rate": 0.00019999903452116996,
      "loss": 0.9571,
      "step": 106
    },
    {
      "epoch": 0.005860765733691187,
      "grad_norm": 5.672741889953613,
      "learning_rate": 0.00019999901996925473,
      "loss": 2.3593,
      "step": 107
    },
    {
      "epoch": 0.005915539245221011,
      "grad_norm": 2.481201410293579,
      "learning_rate": 0.00019999899086542428,
      "loss": 1.7938,
      "step": 108
    },
    {
      "epoch": 0.005970312756750835,
      "grad_norm": 5.1551032066345215,
      "learning_rate": 0.00019999897631350905,
      "loss": 1.4613,
      "step": 109
    },
    {
      "epoch": 0.00602508626828066,
      "grad_norm": 5.946004867553711,
      "learning_rate": 0.0001999989472096786,
      "loss": 2.8604,
      "step": 110
    },
    {
      "epoch": 0.0060798597798104835,
      "grad_norm": 3.6556293964385986,
      "learning_rate": 0.0001999989035539329,
      "loss": 2.7064,
      "step": 111
    },
    {
      "epoch": 0.006134633291340308,
      "grad_norm": 2.124431848526001,
      "learning_rate": 0.00019999888900201768,
      "loss": 1.3621,
      "step": 112
    },
    {
      "epoch": 0.006189406802870132,
      "grad_norm": 6.623743057250977,
      "learning_rate": 0.00019999885989818722,
      "loss": 3.0968,
      "step": 113
    },
    {
      "epoch": 0.006244180314399956,
      "grad_norm": 7.896109104156494,
      "learning_rate": 0.000199998845346272,
      "loss": 2.4904,
      "step": 114
    },
    {
      "epoch": 0.006298953825929781,
      "grad_norm": 3.254516363143921,
      "learning_rate": 0.0001999988016905263,
      "loss": 1.4879,
      "step": 115
    },
    {
      "epoch": 0.0063537273374596045,
      "grad_norm": 4.302073955535889,
      "learning_rate": 0.00019999877258669585,
      "loss": 2.2566,
      "step": 116
    },
    {
      "epoch": 0.006408500848989428,
      "grad_norm": 3.8796324729919434,
      "learning_rate": 0.0001999987434828654,
      "loss": 1.5976,
      "step": 117
    },
    {
      "epoch": 0.006463274360519253,
      "grad_norm": 2.339210271835327,
      "learning_rate": 0.00019999871437903494,
      "loss": 1.4285,
      "step": 118
    },
    {
      "epoch": 0.006518047872049077,
      "grad_norm": 2.80706787109375,
      "learning_rate": 0.0001999986998271197,
      "loss": 1.5288,
      "step": 119
    },
    {
      "epoch": 0.006572821383578902,
      "grad_norm": 3.1644108295440674,
      "learning_rate": 0.00019999865617137402,
      "loss": 1.6015,
      "step": 120
    },
    {
      "epoch": 0.0066275948951087255,
      "grad_norm": 2.360415458679199,
      "learning_rate": 0.0001999986416194588,
      "loss": 1.9964,
      "step": 121
    },
    {
      "epoch": 0.006682368406638549,
      "grad_norm": 2.0627126693725586,
      "learning_rate": 0.0001999985979637131,
      "loss": 1.4581,
      "step": 122
    },
    {
      "epoch": 0.006737141918168374,
      "grad_norm": 6.038996696472168,
      "learning_rate": 0.00019999858341179788,
      "loss": 2.0242,
      "step": 123
    },
    {
      "epoch": 0.006791915429698198,
      "grad_norm": 5.647372245788574,
      "learning_rate": 0.0001999985397560522,
      "loss": 3.1284,
      "step": 124
    },
    {
      "epoch": 0.006846688941228022,
      "grad_norm": 2.55873441696167,
      "learning_rate": 0.00019999851065222174,
      "loss": 1.3799,
      "step": 125
    },
    {
      "epoch": 0.0069014624527578465,
      "grad_norm": 3.399287700653076,
      "learning_rate": 0.00019999848154839128,
      "loss": 1.2626,
      "step": 126
    },
    {
      "epoch": 0.00695623596428767,
      "grad_norm": 3.4777650833129883,
      "learning_rate": 0.00019999845244456083,
      "loss": 1.823,
      "step": 127
    },
    {
      "epoch": 0.007011009475817494,
      "grad_norm": 2.231151819229126,
      "learning_rate": 0.00019999840878881514,
      "loss": 0.519,
      "step": 128
    },
    {
      "epoch": 0.007065782987347319,
      "grad_norm": 1.4420349597930908,
      "learning_rate": 0.00019999837968498468,
      "loss": 0.9166,
      "step": 129
    },
    {
      "epoch": 0.007120556498877143,
      "grad_norm": 7.306528568267822,
      "learning_rate": 0.00019999835058115423,
      "loss": 2.7134,
      "step": 130
    },
    {
      "epoch": 0.0071753300104069676,
      "grad_norm": 3.8706390857696533,
      "learning_rate": 0.00019999830692540854,
      "loss": 0.8782,
      "step": 131
    },
    {
      "epoch": 0.007230103521936791,
      "grad_norm": 2.33634877204895,
      "learning_rate": 0.00019999827782157809,
      "loss": 1.8408,
      "step": 132
    },
    {
      "epoch": 0.007284877033466615,
      "grad_norm": 2.4954023361206055,
      "learning_rate": 0.00019999824871774763,
      "loss": 1.7269,
      "step": 133
    },
    {
      "epoch": 0.00733965054499644,
      "grad_norm": 3.6082170009613037,
      "learning_rate": 0.00019999821961391717,
      "loss": 1.4462,
      "step": 134
    },
    {
      "epoch": 0.007394424056526264,
      "grad_norm": 1.7699745893478394,
      "learning_rate": 0.0001999981759581715,
      "loss": 1.0929,
      "step": 135
    },
    {
      "epoch": 0.007449197568056088,
      "grad_norm": 5.153398513793945,
      "learning_rate": 0.00019999814685434103,
      "loss": 2.4886,
      "step": 136
    },
    {
      "epoch": 0.007503971079585912,
      "grad_norm": 2.282461166381836,
      "learning_rate": 0.00019999811775051057,
      "loss": 1.6376,
      "step": 137
    },
    {
      "epoch": 0.007558744591115736,
      "grad_norm": 3.7063608169555664,
      "learning_rate": 0.0001999980740947649,
      "loss": 1.3274,
      "step": 138
    },
    {
      "epoch": 0.007613518102645561,
      "grad_norm": 5.959068298339844,
      "learning_rate": 0.00019999804499093443,
      "loss": 2.0164,
      "step": 139
    },
    {
      "epoch": 0.007668291614175385,
      "grad_norm": 3.709977388381958,
      "learning_rate": 0.00019999800133518875,
      "loss": 1.9344,
      "step": 140
    },
    {
      "epoch": 0.007723065125705209,
      "grad_norm": 3.034954309463501,
      "learning_rate": 0.0001999979722313583,
      "loss": 1.894,
      "step": 141
    },
    {
      "epoch": 0.007777838637235033,
      "grad_norm": 3.3923349380493164,
      "learning_rate": 0.0001999979285756126,
      "loss": 2.2652,
      "step": 142
    },
    {
      "epoch": 0.007832612148764857,
      "grad_norm": 4.926137924194336,
      "learning_rate": 0.00019999789947178215,
      "loss": 2.4808,
      "step": 143
    },
    {
      "epoch": 0.007887385660294682,
      "grad_norm": 3.900794267654419,
      "learning_rate": 0.00019999785581603646,
      "loss": 2.6266,
      "step": 144
    },
    {
      "epoch": 0.007942159171824505,
      "grad_norm": 5.045756816864014,
      "learning_rate": 0.00019999781216029078,
      "loss": 2.4982,
      "step": 145
    },
    {
      "epoch": 0.00799693268335433,
      "grad_norm": 2.6197421550750732,
      "learning_rate": 0.00019999778305646032,
      "loss": 1.743,
      "step": 146
    },
    {
      "epoch": 0.008051706194884154,
      "grad_norm": 8.259982109069824,
      "learning_rate": 0.00019999773940071464,
      "loss": 2.7157,
      "step": 147
    },
    {
      "epoch": 0.008106479706413977,
      "grad_norm": 4.401483058929443,
      "learning_rate": 0.00019999771029688418,
      "loss": 3.0378,
      "step": 148
    },
    {
      "epoch": 0.008161253217943802,
      "grad_norm": 5.386708736419678,
      "learning_rate": 0.00019999765208922327,
      "loss": 2.1189,
      "step": 149
    },
    {
      "epoch": 0.008216026729473627,
      "grad_norm": 3.547675371170044,
      "learning_rate": 0.0001999976229853928,
      "loss": 1.3589,
      "step": 150
    },
    {
      "epoch": 0.008270800241003452,
      "grad_norm": 8.1455717086792,
      "learning_rate": 0.00019999759388156235,
      "loss": 1.7577,
      "step": 151
    },
    {
      "epoch": 0.008325573752533275,
      "grad_norm": 2.950439214706421,
      "learning_rate": 0.00019999753567390144,
      "loss": 1.1439,
      "step": 152
    },
    {
      "epoch": 0.0083803472640631,
      "grad_norm": 4.826971530914307,
      "learning_rate": 0.00019999750657007098,
      "loss": 1.0709,
      "step": 153
    },
    {
      "epoch": 0.008435120775592924,
      "grad_norm": 2.994509220123291,
      "learning_rate": 0.0001999974629143253,
      "loss": 1.6984,
      "step": 154
    },
    {
      "epoch": 0.008489894287122747,
      "grad_norm": 4.315898418426514,
      "learning_rate": 0.0001999974192585796,
      "loss": 1.763,
      "step": 155
    },
    {
      "epoch": 0.008544667798652572,
      "grad_norm": 3.527961492538452,
      "learning_rate": 0.00019999739015474916,
      "loss": 2.0056,
      "step": 156
    },
    {
      "epoch": 0.008599441310182396,
      "grad_norm": 5.413950443267822,
      "learning_rate": 0.00019999733194708824,
      "loss": 1.86,
      "step": 157
    },
    {
      "epoch": 0.00865421482171222,
      "grad_norm": 4.090121746063232,
      "learning_rate": 0.00019999730284325778,
      "loss": 2.0702,
      "step": 158
    },
    {
      "epoch": 0.008708988333242044,
      "grad_norm": 4.397725582122803,
      "learning_rate": 0.0001999972591875121,
      "loss": 3.0286,
      "step": 159
    },
    {
      "epoch": 0.008763761844771869,
      "grad_norm": 2.2897942066192627,
      "learning_rate": 0.00019999721553176641,
      "loss": 1.7597,
      "step": 160
    },
    {
      "epoch": 0.008818535356301692,
      "grad_norm": 2.368964910507202,
      "learning_rate": 0.00019999717187602073,
      "loss": 1.9825,
      "step": 161
    },
    {
      "epoch": 0.008873308867831517,
      "grad_norm": 7.571446418762207,
      "learning_rate": 0.00019999712822027504,
      "loss": 0.5782,
      "step": 162
    },
    {
      "epoch": 0.008928082379361341,
      "grad_norm": 1.1192164421081543,
      "learning_rate": 0.00019999708456452936,
      "loss": 1.3156,
      "step": 163
    },
    {
      "epoch": 0.008982855890891164,
      "grad_norm": 4.243453025817871,
      "learning_rate": 0.00019999704090878367,
      "loss": 0.7961,
      "step": 164
    },
    {
      "epoch": 0.009037629402420989,
      "grad_norm": 4.362403392791748,
      "learning_rate": 0.000199996997253038,
      "loss": 1.522,
      "step": 165
    },
    {
      "epoch": 0.009092402913950814,
      "grad_norm": 5.393119812011719,
      "learning_rate": 0.00019999693904537708,
      "loss": 2.156,
      "step": 166
    },
    {
      "epoch": 0.009147176425480637,
      "grad_norm": 1.979138970375061,
      "learning_rate": 0.00019999690994154662,
      "loss": 1.6939,
      "step": 167
    },
    {
      "epoch": 0.009201949937010461,
      "grad_norm": 6.118706226348877,
      "learning_rate": 0.00019999686628580093,
      "loss": 0.6832,
      "step": 168
    },
    {
      "epoch": 0.009256723448540286,
      "grad_norm": 8.015562057495117,
      "learning_rate": 0.00019999680807814002,
      "loss": 1.9663,
      "step": 169
    },
    {
      "epoch": 0.009311496960070111,
      "grad_norm": 2.658768653869629,
      "learning_rate": 0.00019999676442239434,
      "loss": 1.6543,
      "step": 170
    },
    {
      "epoch": 0.009366270471599934,
      "grad_norm": 2.9721367359161377,
      "learning_rate": 0.00019999672076664865,
      "loss": 0.7938,
      "step": 171
    },
    {
      "epoch": 0.009421043983129759,
      "grad_norm": 1.78675377368927,
      "learning_rate": 0.00019999666255898774,
      "loss": 1.6325,
      "step": 172
    },
    {
      "epoch": 0.009475817494659583,
      "grad_norm": 3.0815670490264893,
      "learning_rate": 0.00019999663345515728,
      "loss": 1.103,
      "step": 173
    },
    {
      "epoch": 0.009530591006189406,
      "grad_norm": 7.398219585418701,
      "learning_rate": 0.0001999965897994116,
      "loss": 2.7651,
      "step": 174
    },
    {
      "epoch": 0.009585364517719231,
      "grad_norm": 3.0404858589172363,
      "learning_rate": 0.00019999653159175068,
      "loss": 1.4954,
      "step": 175
    },
    {
      "epoch": 0.009640138029249056,
      "grad_norm": 4.336193084716797,
      "learning_rate": 0.000199996487936005,
      "loss": 2.0237,
      "step": 176
    },
    {
      "epoch": 0.009694911540778879,
      "grad_norm": 5.85668420791626,
      "learning_rate": 0.00019999642972834408,
      "loss": 2.1141,
      "step": 177
    },
    {
      "epoch": 0.009749685052308703,
      "grad_norm": 5.596229076385498,
      "learning_rate": 0.0001999963860725984,
      "loss": 0.9041,
      "step": 178
    },
    {
      "epoch": 0.009804458563838528,
      "grad_norm": 4.257452964782715,
      "learning_rate": 0.0001999963424168527,
      "loss": 0.9398,
      "step": 179
    },
    {
      "epoch": 0.009859232075368351,
      "grad_norm": 2.9462697505950928,
      "learning_rate": 0.0001999962842091918,
      "loss": 1.7364,
      "step": 180
    },
    {
      "epoch": 0.009914005586898176,
      "grad_norm": 5.250387668609619,
      "learning_rate": 0.00019999624055344611,
      "loss": 1.499,
      "step": 181
    },
    {
      "epoch": 0.009968779098428,
      "grad_norm": 8.451971054077148,
      "learning_rate": 0.00019999619689770043,
      "loss": 1.8761,
      "step": 182
    },
    {
      "epoch": 0.010023552609957824,
      "grad_norm": 8.262434005737305,
      "learning_rate": 0.00019999613869003952,
      "loss": 1.8783,
      "step": 183
    },
    {
      "epoch": 0.010078326121487648,
      "grad_norm": 2.62361478805542,
      "learning_rate": 0.0001999960804823786,
      "loss": 2.0308,
      "step": 184
    },
    {
      "epoch": 0.010133099633017473,
      "grad_norm": 2.678157329559326,
      "learning_rate": 0.00019999603682663292,
      "loss": 1.7922,
      "step": 185
    },
    {
      "epoch": 0.010187873144547296,
      "grad_norm": 1.3991825580596924,
      "learning_rate": 0.00019999599317088723,
      "loss": 1.5624,
      "step": 186
    },
    {
      "epoch": 0.01024264665607712,
      "grad_norm": 3.4970903396606445,
      "learning_rate": 0.00019999593496322632,
      "loss": 1.5973,
      "step": 187
    },
    {
      "epoch": 0.010297420167606946,
      "grad_norm": 2.0385215282440186,
      "learning_rate": 0.0001999958767555654,
      "loss": 1.3873,
      "step": 188
    },
    {
      "epoch": 0.01035219367913677,
      "grad_norm": 1.7962379455566406,
      "learning_rate": 0.00019999583309981972,
      "loss": 1.374,
      "step": 189
    },
    {
      "epoch": 0.010406967190666593,
      "grad_norm": 15.657769203186035,
      "learning_rate": 0.0001999957748921588,
      "loss": 8.388,
      "step": 190
    },
    {
      "epoch": 0.010461740702196418,
      "grad_norm": 4.045455455780029,
      "learning_rate": 0.00019999573123641312,
      "loss": 1.8906,
      "step": 191
    },
    {
      "epoch": 0.010516514213726243,
      "grad_norm": 2.667015552520752,
      "learning_rate": 0.0001999956730287522,
      "loss": 1.9753,
      "step": 192
    },
    {
      "epoch": 0.010571287725256066,
      "grad_norm": 2.920349359512329,
      "learning_rate": 0.0001999956148210913,
      "loss": 1.5602,
      "step": 193
    },
    {
      "epoch": 0.01062606123678589,
      "grad_norm": 4.383006572723389,
      "learning_rate": 0.00019999555661343038,
      "loss": 1.0355,
      "step": 194
    },
    {
      "epoch": 0.010680834748315715,
      "grad_norm": 2.048870801925659,
      "learning_rate": 0.0001999955129576847,
      "loss": 1.4326,
      "step": 195
    },
    {
      "epoch": 0.010735608259845538,
      "grad_norm": 22.607383728027344,
      "learning_rate": 0.00019999545475002378,
      "loss": 3.2812,
      "step": 196
    },
    {
      "epoch": 0.010790381771375363,
      "grad_norm": 2.358532190322876,
      "learning_rate": 0.0001999954110942781,
      "loss": 1.0922,
      "step": 197
    },
    {
      "epoch": 0.010845155282905188,
      "grad_norm": 4.793381214141846,
      "learning_rate": 0.00019999535288661718,
      "loss": 1.2193,
      "step": 198
    },
    {
      "epoch": 0.01089992879443501,
      "grad_norm": 3.632520914077759,
      "learning_rate": 0.00019999528012704104,
      "loss": 0.4353,
      "step": 199
    },
    {
      "epoch": 0.010954702305964835,
      "grad_norm": 2.862818956375122,
      "learning_rate": 0.00019999523647129536,
      "loss": 1.692,
      "step": 200
    },
    {
      "epoch": 0.010954702305964835,
      "eval_loss": 1.7723915576934814,
      "eval_runtime": 45.8228,
      "eval_samples_per_second": 2.008,
      "eval_steps_per_second": 2.008,
      "step": 200
    },
    {
      "epoch": 0.01100947581749466,
      "grad_norm": 2.6479239463806152,
      "learning_rate": 0.00019999517826363444,
      "loss": 1.3174,
      "step": 201
    },
    {
      "epoch": 0.011064249329024483,
      "grad_norm": 2.361941337585449,
      "learning_rate": 0.00019999512005597353,
      "loss": 1.5188,
      "step": 202
    },
    {
      "epoch": 0.011119022840554308,
      "grad_norm": 3.734485387802124,
      "learning_rate": 0.00019999507640022784,
      "loss": 1.9329,
      "step": 203
    },
    {
      "epoch": 0.011173796352084132,
      "grad_norm": 7.022838592529297,
      "learning_rate": 0.00019999501819256693,
      "loss": 2.2512,
      "step": 204
    },
    {
      "epoch": 0.011228569863613957,
      "grad_norm": 2.7253191471099854,
      "learning_rate": 0.0001999949454329908,
      "loss": 1.4294,
      "step": 205
    },
    {
      "epoch": 0.01128334337514378,
      "grad_norm": 3.644829750061035,
      "learning_rate": 0.00019999488722532988,
      "loss": 2.242,
      "step": 206
    },
    {
      "epoch": 0.011338116886673605,
      "grad_norm": 2.077529191970825,
      "learning_rate": 0.00019999482901766896,
      "loss": 1.2122,
      "step": 207
    },
    {
      "epoch": 0.01139289039820343,
      "grad_norm": 5.241451263427734,
      "learning_rate": 0.00019999477081000805,
      "loss": 2.0771,
      "step": 208
    },
    {
      "epoch": 0.011447663909733253,
      "grad_norm": 3.66778302192688,
      "learning_rate": 0.00019999471260234714,
      "loss": 1.9674,
      "step": 209
    },
    {
      "epoch": 0.011502437421263077,
      "grad_norm": 4.329482555389404,
      "learning_rate": 0.00019999465439468622,
      "loss": 1.6913,
      "step": 210
    },
    {
      "epoch": 0.011557210932792902,
      "grad_norm": 7.484829425811768,
      "learning_rate": 0.0001999945961870253,
      "loss": 1.7285,
      "step": 211
    },
    {
      "epoch": 0.011611984444322725,
      "grad_norm": 2.4847424030303955,
      "learning_rate": 0.0001999945379793644,
      "loss": 1.275,
      "step": 212
    },
    {
      "epoch": 0.01166675795585255,
      "grad_norm": 5.409372329711914,
      "learning_rate": 0.00019999447977170348,
      "loss": 1.8171,
      "step": 213
    },
    {
      "epoch": 0.011721531467382374,
      "grad_norm": 5.956262111663818,
      "learning_rate": 0.00019999442156404257,
      "loss": 1.7955,
      "step": 214
    },
    {
      "epoch": 0.011776304978912197,
      "grad_norm": 3.3556270599365234,
      "learning_rate": 0.00019999436335638165,
      "loss": 0.5915,
      "step": 215
    },
    {
      "epoch": 0.011831078490442022,
      "grad_norm": 2.1117236614227295,
      "learning_rate": 0.0001999942905968055,
      "loss": 2.0659,
      "step": 216
    },
    {
      "epoch": 0.011885852001971847,
      "grad_norm": 5.51160192489624,
      "learning_rate": 0.0001999942323891446,
      "loss": 3.2644,
      "step": 217
    },
    {
      "epoch": 0.01194062551350167,
      "grad_norm": 6.6730475425720215,
      "learning_rate": 0.00019999417418148369,
      "loss": 1.3294,
      "step": 218
    },
    {
      "epoch": 0.011995399025031495,
      "grad_norm": 2.2005457878112793,
      "learning_rate": 0.00019999411597382277,
      "loss": 1.1713,
      "step": 219
    },
    {
      "epoch": 0.01205017253656132,
      "grad_norm": 6.574706077575684,
      "learning_rate": 0.00019999404321424663,
      "loss": 2.0781,
      "step": 220
    },
    {
      "epoch": 0.012104946048091142,
      "grad_norm": 2.7223944664001465,
      "learning_rate": 0.00019999398500658572,
      "loss": 1.6209,
      "step": 221
    },
    {
      "epoch": 0.012159719559620967,
      "grad_norm": 3.601489305496216,
      "learning_rate": 0.0001999939267989248,
      "loss": 1.3192,
      "step": 222
    },
    {
      "epoch": 0.012214493071150792,
      "grad_norm": 1.914157748222351,
      "learning_rate": 0.00019999385403934866,
      "loss": 1.2931,
      "step": 223
    },
    {
      "epoch": 0.012269266582680616,
      "grad_norm": 8.133283615112305,
      "learning_rate": 0.00019999379583168775,
      "loss": 1.3791,
      "step": 224
    },
    {
      "epoch": 0.01232404009421044,
      "grad_norm": 2.6674044132232666,
      "learning_rate": 0.00019999373762402683,
      "loss": 1.5053,
      "step": 225
    },
    {
      "epoch": 0.012378813605740264,
      "grad_norm": 3.6785225868225098,
      "learning_rate": 0.0001999936648644507,
      "loss": 2.5412,
      "step": 226
    },
    {
      "epoch": 0.012433587117270089,
      "grad_norm": 2.3415210247039795,
      "learning_rate": 0.00019999360665678978,
      "loss": 1.8772,
      "step": 227
    },
    {
      "epoch": 0.012488360628799912,
      "grad_norm": 4.787502765655518,
      "learning_rate": 0.00019999353389721364,
      "loss": 1.2514,
      "step": 228
    },
    {
      "epoch": 0.012543134140329737,
      "grad_norm": 4.088205337524414,
      "learning_rate": 0.00019999347568955272,
      "loss": 2.587,
      "step": 229
    },
    {
      "epoch": 0.012597907651859561,
      "grad_norm": 3.8138277530670166,
      "learning_rate": 0.00019999340292997658,
      "loss": 1.8076,
      "step": 230
    },
    {
      "epoch": 0.012652681163389384,
      "grad_norm": 2.029222249984741,
      "learning_rate": 0.00019999334472231567,
      "loss": 1.7759,
      "step": 231
    },
    {
      "epoch": 0.012707454674919209,
      "grad_norm": 5.074730396270752,
      "learning_rate": 0.00019999327196273953,
      "loss": 1.9354,
      "step": 232
    },
    {
      "epoch": 0.012762228186449034,
      "grad_norm": 4.961703300476074,
      "learning_rate": 0.00019999321375507861,
      "loss": 2.1503,
      "step": 233
    },
    {
      "epoch": 0.012817001697978857,
      "grad_norm": 3.4551916122436523,
      "learning_rate": 0.00019999314099550247,
      "loss": 1.6486,
      "step": 234
    },
    {
      "epoch": 0.012871775209508681,
      "grad_norm": 3.713121175765991,
      "learning_rate": 0.00019999306823592633,
      "loss": 1.2335,
      "step": 235
    },
    {
      "epoch": 0.012926548721038506,
      "grad_norm": 7.003305435180664,
      "learning_rate": 0.00019999301002826542,
      "loss": 1.2471,
      "step": 236
    },
    {
      "epoch": 0.01298132223256833,
      "grad_norm": 2.446171998977661,
      "learning_rate": 0.00019999293726868927,
      "loss": 1.6452,
      "step": 237
    },
    {
      "epoch": 0.013036095744098154,
      "grad_norm": 6.034176349639893,
      "learning_rate": 0.00019999286450911313,
      "loss": 1.2343,
      "step": 238
    },
    {
      "epoch": 0.013090869255627979,
      "grad_norm": 5.170461177825928,
      "learning_rate": 0.00019999280630145222,
      "loss": 1.6076,
      "step": 239
    },
    {
      "epoch": 0.013145642767157803,
      "grad_norm": 2.170388698577881,
      "learning_rate": 0.00019999273354187608,
      "loss": 1.1359,
      "step": 240
    },
    {
      "epoch": 0.013200416278687626,
      "grad_norm": 1.9967479705810547,
      "learning_rate": 0.00019999266078229994,
      "loss": 1.2804,
      "step": 241
    },
    {
      "epoch": 0.013255189790217451,
      "grad_norm": 2.297745704650879,
      "learning_rate": 0.0001999925880227238,
      "loss": 0.9847,
      "step": 242
    },
    {
      "epoch": 0.013309963301747276,
      "grad_norm": 10.358915328979492,
      "learning_rate": 0.00019999251526314765,
      "loss": 2.2011,
      "step": 243
    },
    {
      "epoch": 0.013364736813277099,
      "grad_norm": 2.76355242729187,
      "learning_rate": 0.0001999924425035715,
      "loss": 1.5864,
      "step": 244
    },
    {
      "epoch": 0.013419510324806923,
      "grad_norm": 2.426405429840088,
      "learning_rate": 0.0001999923842959106,
      "loss": 1.4766,
      "step": 245
    },
    {
      "epoch": 0.013474283836336748,
      "grad_norm": 1.7413564920425415,
      "learning_rate": 0.00019999231153633446,
      "loss": 0.4673,
      "step": 246
    },
    {
      "epoch": 0.013529057347866571,
      "grad_norm": 3.01285719871521,
      "learning_rate": 0.0001999922387767583,
      "loss": 1.926,
      "step": 247
    },
    {
      "epoch": 0.013583830859396396,
      "grad_norm": 2.7426364421844482,
      "learning_rate": 0.00019999216601718217,
      "loss": 1.0913,
      "step": 248
    },
    {
      "epoch": 0.01363860437092622,
      "grad_norm": 11.577319145202637,
      "learning_rate": 0.00019999209325760603,
      "loss": 2.9807,
      "step": 249
    },
    {
      "epoch": 0.013693377882456044,
      "grad_norm": 6.44500732421875,
      "learning_rate": 0.0001999920204980299,
      "loss": 0.9453,
      "step": 250
    },
    {
      "epoch": 0.013748151393985868,
      "grad_norm": 2.300079107284546,
      "learning_rate": 0.00019999194773845375,
      "loss": 1.4995,
      "step": 251
    },
    {
      "epoch": 0.013802924905515693,
      "grad_norm": 1.0096324682235718,
      "learning_rate": 0.0001999918749788776,
      "loss": 1.0031,
      "step": 252
    },
    {
      "epoch": 0.013857698417045516,
      "grad_norm": 3.1160483360290527,
      "learning_rate": 0.00019999180221930146,
      "loss": 0.9832,
      "step": 253
    },
    {
      "epoch": 0.01391247192857534,
      "grad_norm": 2.124481678009033,
      "learning_rate": 0.00019999172945972532,
      "loss": 1.5455,
      "step": 254
    },
    {
      "epoch": 0.013967245440105166,
      "grad_norm": 2.8532865047454834,
      "learning_rate": 0.00019999165670014918,
      "loss": 1.8523,
      "step": 255
    },
    {
      "epoch": 0.014022018951634989,
      "grad_norm": 6.256829261779785,
      "learning_rate": 0.00019999158394057304,
      "loss": 1.8563,
      "step": 256
    },
    {
      "epoch": 0.014076792463164813,
      "grad_norm": 6.112888813018799,
      "learning_rate": 0.0001999915111809969,
      "loss": 1.6723,
      "step": 257
    },
    {
      "epoch": 0.014131565974694638,
      "grad_norm": 12.402007102966309,
      "learning_rate": 0.00019999143842142075,
      "loss": 1.8908,
      "step": 258
    },
    {
      "epoch": 0.014186339486224463,
      "grad_norm": 3.635824680328369,
      "learning_rate": 0.0001999913656618446,
      "loss": 1.8974,
      "step": 259
    },
    {
      "epoch": 0.014241112997754286,
      "grad_norm": 5.2535600662231445,
      "learning_rate": 0.00019999127835035324,
      "loss": 1.578,
      "step": 260
    },
    {
      "epoch": 0.01429588650928411,
      "grad_norm": 3.182847261428833,
      "learning_rate": 0.0001999912055907771,
      "loss": 1.3392,
      "step": 261
    },
    {
      "epoch": 0.014350660020813935,
      "grad_norm": 2.927551031112671,
      "learning_rate": 0.00019999113283120096,
      "loss": 1.1099,
      "step": 262
    },
    {
      "epoch": 0.014405433532343758,
      "grad_norm": 3.513979196548462,
      "learning_rate": 0.00019999106007162482,
      "loss": 2.3135,
      "step": 263
    },
    {
      "epoch": 0.014460207043873583,
      "grad_norm": 4.018962860107422,
      "learning_rate": 0.00019999098731204867,
      "loss": 2.8762,
      "step": 264
    },
    {
      "epoch": 0.014514980555403408,
      "grad_norm": 3.1075074672698975,
      "learning_rate": 0.0001999909000005573,
      "loss": 1.0861,
      "step": 265
    },
    {
      "epoch": 0.01456975406693323,
      "grad_norm": 3.164689064025879,
      "learning_rate": 0.00019999082724098116,
      "loss": 1.7109,
      "step": 266
    },
    {
      "epoch": 0.014624527578463055,
      "grad_norm": 3.062580108642578,
      "learning_rate": 0.0001999907399294898,
      "loss": 1.9063,
      "step": 267
    },
    {
      "epoch": 0.01467930108999288,
      "grad_norm": 2.5741569995880127,
      "learning_rate": 0.00019999066716991365,
      "loss": 1.0126,
      "step": 268
    },
    {
      "epoch": 0.014734074601522703,
      "grad_norm": 1.6732112169265747,
      "learning_rate": 0.0001999905944103375,
      "loss": 1.3186,
      "step": 269
    },
    {
      "epoch": 0.014788848113052528,
      "grad_norm": 4.041171073913574,
      "learning_rate": 0.00019999050709884614,
      "loss": 1.5264,
      "step": 270
    },
    {
      "epoch": 0.014843621624582352,
      "grad_norm": 5.263913154602051,
      "learning_rate": 0.00019999043433927,
      "loss": 1.8575,
      "step": 271
    },
    {
      "epoch": 0.014898395136112175,
      "grad_norm": 6.201498985290527,
      "learning_rate": 0.00019999034702777863,
      "loss": 1.9033,
      "step": 272
    },
    {
      "epoch": 0.014953168647642,
      "grad_norm": 2.128628730773926,
      "learning_rate": 0.00019999027426820248,
      "loss": 1.5478,
      "step": 273
    },
    {
      "epoch": 0.015007942159171825,
      "grad_norm": 2.085555076599121,
      "learning_rate": 0.00019999020150862634,
      "loss": 1.1487,
      "step": 274
    },
    {
      "epoch": 0.015062715670701648,
      "grad_norm": 2.0912060737609863,
      "learning_rate": 0.00019999011419713497,
      "loss": 1.3025,
      "step": 275
    },
    {
      "epoch": 0.015117489182231473,
      "grad_norm": 4.089863300323486,
      "learning_rate": 0.0001999900268856436,
      "loss": 1.3725,
      "step": 276
    },
    {
      "epoch": 0.015172262693761297,
      "grad_norm": 3.475039005279541,
      "learning_rate": 0.00019998993957415223,
      "loss": 1.8748,
      "step": 277
    },
    {
      "epoch": 0.015227036205291122,
      "grad_norm": 2.629746913909912,
      "learning_rate": 0.0001999898668145761,
      "loss": 1.2002,
      "step": 278
    },
    {
      "epoch": 0.015281809716820945,
      "grad_norm": 4.122725009918213,
      "learning_rate": 0.00019998979405499995,
      "loss": 2.0507,
      "step": 279
    },
    {
      "epoch": 0.01533658322835077,
      "grad_norm": 1.904913067817688,
      "learning_rate": 0.00019998970674350858,
      "loss": 1.3102,
      "step": 280
    },
    {
      "epoch": 0.015391356739880594,
      "grad_norm": 1.5456165075302124,
      "learning_rate": 0.0001999896194320172,
      "loss": 0.9051,
      "step": 281
    },
    {
      "epoch": 0.015446130251410417,
      "grad_norm": 2.505502462387085,
      "learning_rate": 0.00019998954667244107,
      "loss": 0.2162,
      "step": 282
    },
    {
      "epoch": 0.015500903762940242,
      "grad_norm": 2.4814047813415527,
      "learning_rate": 0.0001999894593609497,
      "loss": 2.2721,
      "step": 283
    },
    {
      "epoch": 0.015555677274470067,
      "grad_norm": 2.8680660724639893,
      "learning_rate": 0.00019998937204945832,
      "loss": 1.6248,
      "step": 284
    },
    {
      "epoch": 0.01561045078599989,
      "grad_norm": 1.7132946252822876,
      "learning_rate": 0.00019998928473796695,
      "loss": 0.9827,
      "step": 285
    },
    {
      "epoch": 0.015665224297529715,
      "grad_norm": 2.348878860473633,
      "learning_rate": 0.0001999892119783908,
      "loss": 1.1002,
      "step": 286
    },
    {
      "epoch": 0.015719997809059538,
      "grad_norm": 4.16648006439209,
      "learning_rate": 0.00019998912466689944,
      "loss": 1.1093,
      "step": 287
    },
    {
      "epoch": 0.015774771320589364,
      "grad_norm": 3.7905845642089844,
      "learning_rate": 0.00019998902280349284,
      "loss": 1.8792,
      "step": 288
    },
    {
      "epoch": 0.015829544832119187,
      "grad_norm": 2.3154585361480713,
      "learning_rate": 0.0001999889500439167,
      "loss": 1.8163,
      "step": 289
    },
    {
      "epoch": 0.01588431834364901,
      "grad_norm": 1.986282467842102,
      "learning_rate": 0.00019998886273242533,
      "loss": 1.4405,
      "step": 290
    },
    {
      "epoch": 0.015939091855178836,
      "grad_norm": 2.0427939891815186,
      "learning_rate": 0.00019998877542093396,
      "loss": 1.813,
      "step": 291
    },
    {
      "epoch": 0.01599386536670866,
      "grad_norm": 4.37157678604126,
      "learning_rate": 0.0001999886881094426,
      "loss": 1.6863,
      "step": 292
    },
    {
      "epoch": 0.016048638878238482,
      "grad_norm": 2.6430723667144775,
      "learning_rate": 0.00019998860079795122,
      "loss": 1.8036,
      "step": 293
    },
    {
      "epoch": 0.01610341238976831,
      "grad_norm": 3.4160568714141846,
      "learning_rate": 0.00019998851348645985,
      "loss": 2.0427,
      "step": 294
    },
    {
      "epoch": 0.016158185901298132,
      "grad_norm": 2.1437175273895264,
      "learning_rate": 0.00019998842617496848,
      "loss": 1.6231,
      "step": 295
    },
    {
      "epoch": 0.016212959412827955,
      "grad_norm": 4.011427402496338,
      "learning_rate": 0.00019998835341539234,
      "loss": 1.7282,
      "step": 296
    },
    {
      "epoch": 0.01626773292435778,
      "grad_norm": 0.9240309000015259,
      "learning_rate": 0.00019998825155198574,
      "loss": 0.9516,
      "step": 297
    },
    {
      "epoch": 0.016322506435887604,
      "grad_norm": 3.4479479789733887,
      "learning_rate": 0.00019998816424049437,
      "loss": 1.1484,
      "step": 298
    },
    {
      "epoch": 0.016377279947417427,
      "grad_norm": 6.742218971252441,
      "learning_rate": 0.000199988076929003,
      "loss": 2.2983,
      "step": 299
    },
    {
      "epoch": 0.016432053458947254,
      "grad_norm": 2.109532594680786,
      "learning_rate": 0.00019998798961751163,
      "loss": 1.2159,
      "step": 300
    },
    {
      "epoch": 0.016432053458947254,
      "eval_loss": 1.6724214553833008,
      "eval_runtime": 45.8078,
      "eval_samples_per_second": 2.008,
      "eval_steps_per_second": 2.008,
      "step": 300
    },
    {
      "epoch": 0.016486826970477077,
      "grad_norm": 1.9522716999053955,
      "learning_rate": 0.00019998790230602026,
      "loss": 1.4299,
      "step": 301
    },
    {
      "epoch": 0.016541600482006903,
      "grad_norm": 2.3339600563049316,
      "learning_rate": 0.0001999878149945289,
      "loss": 1.9106,
      "step": 302
    },
    {
      "epoch": 0.016596373993536726,
      "grad_norm": 6.451596260070801,
      "learning_rate": 0.0001999877131311223,
      "loss": 0.7215,
      "step": 303
    },
    {
      "epoch": 0.01665114750506655,
      "grad_norm": 2.005361318588257,
      "learning_rate": 0.00019998762581963092,
      "loss": 1.5036,
      "step": 304
    },
    {
      "epoch": 0.016705921016596376,
      "grad_norm": 1.861480951309204,
      "learning_rate": 0.00019998753850813955,
      "loss": 1.0752,
      "step": 305
    },
    {
      "epoch": 0.0167606945281262,
      "grad_norm": 2.486722707748413,
      "learning_rate": 0.00019998745119664818,
      "loss": 1.4207,
      "step": 306
    },
    {
      "epoch": 0.01681546803965602,
      "grad_norm": 4.579799652099609,
      "learning_rate": 0.0001999873638851568,
      "loss": 1.7362,
      "step": 307
    },
    {
      "epoch": 0.016870241551185848,
      "grad_norm": 7.78305721282959,
      "learning_rate": 0.0001999872620217502,
      "loss": 2.6027,
      "step": 308
    },
    {
      "epoch": 0.01692501506271567,
      "grad_norm": 2.7974135875701904,
      "learning_rate": 0.00019998717471025884,
      "loss": 1.4097,
      "step": 309
    },
    {
      "epoch": 0.016979788574245494,
      "grad_norm": 2.8497776985168457,
      "learning_rate": 0.00019998708739876747,
      "loss": 1.4822,
      "step": 310
    },
    {
      "epoch": 0.01703456208577532,
      "grad_norm": 3.4799299240112305,
      "learning_rate": 0.00019998698553536087,
      "loss": 1.842,
      "step": 311
    },
    {
      "epoch": 0.017089335597305143,
      "grad_norm": 7.858489513397217,
      "learning_rate": 0.0001999868982238695,
      "loss": 2.1818,
      "step": 312
    },
    {
      "epoch": 0.017144109108834966,
      "grad_norm": 4.679003715515137,
      "learning_rate": 0.00019998681091237813,
      "loss": 1.621,
      "step": 313
    },
    {
      "epoch": 0.017198882620364793,
      "grad_norm": 3.0637378692626953,
      "learning_rate": 0.00019998670904897153,
      "loss": 1.7758,
      "step": 314
    },
    {
      "epoch": 0.017253656131894616,
      "grad_norm": 2.90982985496521,
      "learning_rate": 0.00019998662173748016,
      "loss": 1.6474,
      "step": 315
    },
    {
      "epoch": 0.01730842964342444,
      "grad_norm": 3.1720833778381348,
      "learning_rate": 0.00019998651987407357,
      "loss": 1.5214,
      "step": 316
    },
    {
      "epoch": 0.017363203154954265,
      "grad_norm": 2.877821683883667,
      "learning_rate": 0.0001999864325625822,
      "loss": 1.0111,
      "step": 317
    },
    {
      "epoch": 0.01741797666648409,
      "grad_norm": 7.447439670562744,
      "learning_rate": 0.0001999863306991756,
      "loss": 1.3673,
      "step": 318
    },
    {
      "epoch": 0.01747275017801391,
      "grad_norm": 3.1247761249542236,
      "learning_rate": 0.00019998624338768423,
      "loss": 2.3662,
      "step": 319
    },
    {
      "epoch": 0.017527523689543738,
      "grad_norm": 3.590869665145874,
      "learning_rate": 0.00019998614152427763,
      "loss": 1.0538,
      "step": 320
    },
    {
      "epoch": 0.01758229720107356,
      "grad_norm": 2.684602975845337,
      "learning_rate": 0.00019998605421278626,
      "loss": 1.5909,
      "step": 321
    },
    {
      "epoch": 0.017637070712603384,
      "grad_norm": 2.8864200115203857,
      "learning_rate": 0.00019998595234937966,
      "loss": 1.5928,
      "step": 322
    },
    {
      "epoch": 0.01769184422413321,
      "grad_norm": 5.757589340209961,
      "learning_rate": 0.00019998585048597306,
      "loss": 1.6649,
      "step": 323
    },
    {
      "epoch": 0.017746617735663033,
      "grad_norm": 2.546389102935791,
      "learning_rate": 0.0001999857631744817,
      "loss": 1.7719,
      "step": 324
    },
    {
      "epoch": 0.017801391247192856,
      "grad_norm": 5.650021553039551,
      "learning_rate": 0.0001999856613110751,
      "loss": 2.498,
      "step": 325
    },
    {
      "epoch": 0.017856164758722683,
      "grad_norm": 2.9920921325683594,
      "learning_rate": 0.00019998557399958372,
      "loss": 1.3675,
      "step": 326
    },
    {
      "epoch": 0.017910938270252506,
      "grad_norm": 7.897839546203613,
      "learning_rate": 0.0001999854575842619,
      "loss": 0.8179,
      "step": 327
    },
    {
      "epoch": 0.01796571178178233,
      "grad_norm": 6.1676859855651855,
      "learning_rate": 0.00019998537027277052,
      "loss": 1.3136,
      "step": 328
    },
    {
      "epoch": 0.018020485293312155,
      "grad_norm": 3.422642707824707,
      "learning_rate": 0.00019998526840936393,
      "loss": 1.9066,
      "step": 329
    },
    {
      "epoch": 0.018075258804841978,
      "grad_norm": 4.648807525634766,
      "learning_rate": 0.00019998518109787256,
      "loss": 2.0298,
      "step": 330
    },
    {
      "epoch": 0.0181300323163718,
      "grad_norm": 4.958664417266846,
      "learning_rate": 0.00019998506468255073,
      "loss": 2.3633,
      "step": 331
    },
    {
      "epoch": 0.018184805827901628,
      "grad_norm": 4.302834510803223,
      "learning_rate": 0.00019998497737105936,
      "loss": 1.9108,
      "step": 332
    },
    {
      "epoch": 0.01823957933943145,
      "grad_norm": 6.7737507820129395,
      "learning_rate": 0.00019998487550765276,
      "loss": 1.9946,
      "step": 333
    },
    {
      "epoch": 0.018294352850961274,
      "grad_norm": 7.634446144104004,
      "learning_rate": 0.00019998477364424616,
      "loss": 1.1412,
      "step": 334
    },
    {
      "epoch": 0.0183491263624911,
      "grad_norm": 4.122168064117432,
      "learning_rate": 0.00019998467178083956,
      "loss": 1.4122,
      "step": 335
    },
    {
      "epoch": 0.018403899874020923,
      "grad_norm": 5.0762410163879395,
      "learning_rate": 0.0001999845844693482,
      "loss": 1.9072,
      "step": 336
    },
    {
      "epoch": 0.018458673385550746,
      "grad_norm": 6.307768821716309,
      "learning_rate": 0.00019998446805402637,
      "loss": 1.2732,
      "step": 337
    },
    {
      "epoch": 0.018513446897080572,
      "grad_norm": 3.5309252738952637,
      "learning_rate": 0.000199984380742535,
      "loss": 1.7296,
      "step": 338
    },
    {
      "epoch": 0.018568220408610395,
      "grad_norm": 13.933138847351074,
      "learning_rate": 0.00019998426432721317,
      "loss": 2.7839,
      "step": 339
    },
    {
      "epoch": 0.018622993920140222,
      "grad_norm": 3.400097608566284,
      "learning_rate": 0.00019998416246380657,
      "loss": 1.4113,
      "step": 340
    },
    {
      "epoch": 0.018677767431670045,
      "grad_norm": 3.065422773361206,
      "learning_rate": 0.0001999840751523152,
      "loss": 1.9106,
      "step": 341
    },
    {
      "epoch": 0.018732540943199868,
      "grad_norm": 5.911104679107666,
      "learning_rate": 0.00019998395873699337,
      "loss": 2.0744,
      "step": 342
    },
    {
      "epoch": 0.018787314454729694,
      "grad_norm": 5.705029010772705,
      "learning_rate": 0.000199983871425502,
      "loss": 1.5506,
      "step": 343
    },
    {
      "epoch": 0.018842087966259517,
      "grad_norm": 10.861597061157227,
      "learning_rate": 0.00019998375501018018,
      "loss": 2.124,
      "step": 344
    },
    {
      "epoch": 0.01889686147778934,
      "grad_norm": 3.7650856971740723,
      "learning_rate": 0.00019998365314677358,
      "loss": 1.5479,
      "step": 345
    },
    {
      "epoch": 0.018951634989319167,
      "grad_norm": 6.920382022857666,
      "learning_rate": 0.00019998355128336698,
      "loss": 1.5195,
      "step": 346
    },
    {
      "epoch": 0.01900640850084899,
      "grad_norm": 3.1243700981140137,
      "learning_rate": 0.00019998344941996038,
      "loss": 1.7276,
      "step": 347
    },
    {
      "epoch": 0.019061182012378813,
      "grad_norm": 3.8070809841156006,
      "learning_rate": 0.00019998334755655378,
      "loss": 2.2149,
      "step": 348
    },
    {
      "epoch": 0.01911595552390864,
      "grad_norm": 9.481094360351562,
      "learning_rate": 0.00019998323114123195,
      "loss": 2.374,
      "step": 349
    },
    {
      "epoch": 0.019170729035438462,
      "grad_norm": 4.047249794006348,
      "learning_rate": 0.00019998312927782536,
      "loss": 2.8157,
      "step": 350
    },
    {
      "epoch": 0.019225502546968285,
      "grad_norm": 2.769554615020752,
      "learning_rate": 0.00019998302741441876,
      "loss": 1.2197,
      "step": 351
    },
    {
      "epoch": 0.01928027605849811,
      "grad_norm": 3.782444715499878,
      "learning_rate": 0.00019998292555101216,
      "loss": 2.297,
      "step": 352
    },
    {
      "epoch": 0.019335049570027935,
      "grad_norm": 6.582858085632324,
      "learning_rate": 0.00019998282368760556,
      "loss": 1.8441,
      "step": 353
    },
    {
      "epoch": 0.019389823081557758,
      "grad_norm": 2.3139607906341553,
      "learning_rate": 0.00019998270727228373,
      "loss": 1.6753,
      "step": 354
    },
    {
      "epoch": 0.019444596593087584,
      "grad_norm": 2.8104615211486816,
      "learning_rate": 0.00019998260540887713,
      "loss": 1.0394,
      "step": 355
    },
    {
      "epoch": 0.019499370104617407,
      "grad_norm": 2.188955783843994,
      "learning_rate": 0.0001999824889935553,
      "loss": 1.3045,
      "step": 356
    },
    {
      "epoch": 0.01955414361614723,
      "grad_norm": 1.9037485122680664,
      "learning_rate": 0.0001999823871301487,
      "loss": 1.6061,
      "step": 357
    },
    {
      "epoch": 0.019608917127677056,
      "grad_norm": 2.7938170433044434,
      "learning_rate": 0.0001999822852667421,
      "loss": 1.2819,
      "step": 358
    },
    {
      "epoch": 0.01966369063920688,
      "grad_norm": 3.296421766281128,
      "learning_rate": 0.00019998216885142028,
      "loss": 1.6281,
      "step": 359
    },
    {
      "epoch": 0.019718464150736702,
      "grad_norm": 5.736504554748535,
      "learning_rate": 0.00019998206698801368,
      "loss": 1.3733,
      "step": 360
    },
    {
      "epoch": 0.01977323766226653,
      "grad_norm": 3.637608528137207,
      "learning_rate": 0.00019998196512460709,
      "loss": 1.5263,
      "step": 361
    },
    {
      "epoch": 0.019828011173796352,
      "grad_norm": 11.763082504272461,
      "learning_rate": 0.00019998183415737003,
      "loss": 2.8593,
      "step": 362
    },
    {
      "epoch": 0.019882784685326175,
      "grad_norm": 1.2855253219604492,
      "learning_rate": 0.00019998173229396343,
      "loss": 0.8822,
      "step": 363
    },
    {
      "epoch": 0.019937558196856,
      "grad_norm": 2.2582623958587646,
      "learning_rate": 0.00019998163043055683,
      "loss": 1.5389,
      "step": 364
    },
    {
      "epoch": 0.019992331708385824,
      "grad_norm": 3.773824453353882,
      "learning_rate": 0.000199981514015235,
      "loss": 2.7939,
      "step": 365
    },
    {
      "epoch": 0.020047105219915647,
      "grad_norm": 4.323941230773926,
      "learning_rate": 0.00019998139759991318,
      "loss": 2.9804,
      "step": 366
    },
    {
      "epoch": 0.020101878731445474,
      "grad_norm": 14.04068374633789,
      "learning_rate": 0.00019998129573650658,
      "loss": 2.5594,
      "step": 367
    },
    {
      "epoch": 0.020156652242975297,
      "grad_norm": 6.746912956237793,
      "learning_rate": 0.00019998117932118475,
      "loss": 1.1945,
      "step": 368
    },
    {
      "epoch": 0.02021142575450512,
      "grad_norm": 3.6870174407958984,
      "learning_rate": 0.00019998106290586293,
      "loss": 1.6209,
      "step": 369
    },
    {
      "epoch": 0.020266199266034946,
      "grad_norm": 3.7550156116485596,
      "learning_rate": 0.00019998096104245633,
      "loss": 2.0315,
      "step": 370
    },
    {
      "epoch": 0.02032097277756477,
      "grad_norm": 1.7662843465805054,
      "learning_rate": 0.0001999808446271345,
      "loss": 1.2604,
      "step": 371
    },
    {
      "epoch": 0.020375746289094592,
      "grad_norm": 1.261892318725586,
      "learning_rate": 0.00019998072821181267,
      "loss": 0.9062,
      "step": 372
    },
    {
      "epoch": 0.02043051980062442,
      "grad_norm": 3.737919807434082,
      "learning_rate": 0.00019998062634840608,
      "loss": 1.1183,
      "step": 373
    },
    {
      "epoch": 0.02048529331215424,
      "grad_norm": 2.105478286743164,
      "learning_rate": 0.00019998050993308425,
      "loss": 1.2761,
      "step": 374
    },
    {
      "epoch": 0.020540066823684068,
      "grad_norm": 2.292257308959961,
      "learning_rate": 0.00019998039351776242,
      "loss": 1.9789,
      "step": 375
    },
    {
      "epoch": 0.02059484033521389,
      "grad_norm": 5.653337001800537,
      "learning_rate": 0.0001999802771024406,
      "loss": 1.8839,
      "step": 376
    },
    {
      "epoch": 0.020649613846743714,
      "grad_norm": 2.098447799682617,
      "learning_rate": 0.000199980175239034,
      "loss": 1.0714,
      "step": 377
    },
    {
      "epoch": 0.02070438735827354,
      "grad_norm": 2.362586736679077,
      "learning_rate": 0.00019998004427179694,
      "loss": 1.9089,
      "step": 378
    },
    {
      "epoch": 0.020759160869803363,
      "grad_norm": 1.7979459762573242,
      "learning_rate": 0.00019997992785647511,
      "loss": 0.8479,
      "step": 379
    },
    {
      "epoch": 0.020813934381333186,
      "grad_norm": 5.7349958419799805,
      "learning_rate": 0.00019997982599306852,
      "loss": 1.3777,
      "step": 380
    },
    {
      "epoch": 0.020868707892863013,
      "grad_norm": 2.8502285480499268,
      "learning_rate": 0.0001999797095777467,
      "loss": 1.4992,
      "step": 381
    },
    {
      "epoch": 0.020923481404392836,
      "grad_norm": 3.9419901371002197,
      "learning_rate": 0.00019997959316242486,
      "loss": 2.3285,
      "step": 382
    },
    {
      "epoch": 0.02097825491592266,
      "grad_norm": 4.350181579589844,
      "learning_rate": 0.00019997947674710304,
      "loss": 1.3246,
      "step": 383
    },
    {
      "epoch": 0.021033028427452485,
      "grad_norm": 10.539562225341797,
      "learning_rate": 0.0001999793603317812,
      "loss": 1.6758,
      "step": 384
    },
    {
      "epoch": 0.02108780193898231,
      "grad_norm": 3.001288414001465,
      "learning_rate": 0.00019997924391645938,
      "loss": 1.6323,
      "step": 385
    },
    {
      "epoch": 0.02114257545051213,
      "grad_norm": 6.38343620300293,
      "learning_rate": 0.00019997912750113755,
      "loss": 2.8408,
      "step": 386
    },
    {
      "epoch": 0.021197348962041958,
      "grad_norm": 2.3264219760894775,
      "learning_rate": 0.0001999789965339005,
      "loss": 1.5258,
      "step": 387
    },
    {
      "epoch": 0.02125212247357178,
      "grad_norm": 2.016171932220459,
      "learning_rate": 0.0001999788946704939,
      "loss": 1.7213,
      "step": 388
    },
    {
      "epoch": 0.021306895985101604,
      "grad_norm": 1.610205054283142,
      "learning_rate": 0.00019997877825517207,
      "loss": 1.298,
      "step": 389
    },
    {
      "epoch": 0.02136166949663143,
      "grad_norm": 12.843563079833984,
      "learning_rate": 0.00019997866183985025,
      "loss": 2.0047,
      "step": 390
    },
    {
      "epoch": 0.021416443008161253,
      "grad_norm": 7.350549221038818,
      "learning_rate": 0.0001999785308726132,
      "loss": 2.825,
      "step": 391
    },
    {
      "epoch": 0.021471216519691076,
      "grad_norm": 5.073253154754639,
      "learning_rate": 0.00019997841445729136,
      "loss": 1.7124,
      "step": 392
    },
    {
      "epoch": 0.021525990031220903,
      "grad_norm": 4.183217525482178,
      "learning_rate": 0.00019997829804196954,
      "loss": 2.2989,
      "step": 393
    },
    {
      "epoch": 0.021580763542750726,
      "grad_norm": 13.708772659301758,
      "learning_rate": 0.0001999781816266477,
      "loss": 2.6242,
      "step": 394
    },
    {
      "epoch": 0.02163553705428055,
      "grad_norm": 5.762530326843262,
      "learning_rate": 0.00019997806521132588,
      "loss": 1.9874,
      "step": 395
    },
    {
      "epoch": 0.021690310565810375,
      "grad_norm": 2.6158292293548584,
      "learning_rate": 0.00019997793424408883,
      "loss": 1.454,
      "step": 396
    },
    {
      "epoch": 0.021745084077340198,
      "grad_norm": 1.6630626916885376,
      "learning_rate": 0.00019997780327685177,
      "loss": 0.9438,
      "step": 397
    },
    {
      "epoch": 0.02179985758887002,
      "grad_norm": 4.25056791305542,
      "learning_rate": 0.00019997768686152995,
      "loss": 2.2075,
      "step": 398
    },
    {
      "epoch": 0.021854631100399848,
      "grad_norm": 14.837138175964355,
      "learning_rate": 0.00019997757044620812,
      "loss": 2.0991,
      "step": 399
    },
    {
      "epoch": 0.02190940461192967,
      "grad_norm": 1.7295869588851929,
      "learning_rate": 0.0001999774540308863,
      "loss": 1.109,
      "step": 400
    },
    {
      "epoch": 0.02190940461192967,
      "eval_loss": 1.599177360534668,
      "eval_runtime": 45.8225,
      "eval_samples_per_second": 2.008,
      "eval_steps_per_second": 2.008,
      "step": 400
    },
    {
      "epoch": 0.021964178123459493,
      "grad_norm": 5.130411148071289,
      "learning_rate": 0.00019997733761556447,
      "loss": 1.7871,
      "step": 401
    },
    {
      "epoch": 0.02201895163498932,
      "grad_norm": 4.680836200714111,
      "learning_rate": 0.0001999772066483274,
      "loss": 2.5319,
      "step": 402
    },
    {
      "epoch": 0.022073725146519143,
      "grad_norm": 1.6801224946975708,
      "learning_rate": 0.00019997707568109035,
      "loss": 1.2908,
      "step": 403
    },
    {
      "epoch": 0.022128498658048966,
      "grad_norm": 4.2358198165893555,
      "learning_rate": 0.00019997695926576853,
      "loss": 1.5157,
      "step": 404
    },
    {
      "epoch": 0.022183272169578792,
      "grad_norm": 31.605363845825195,
      "learning_rate": 0.00019997682829853147,
      "loss": 5.0143,
      "step": 405
    },
    {
      "epoch": 0.022238045681108615,
      "grad_norm": 5.570003509521484,
      "learning_rate": 0.00019997671188320965,
      "loss": 1.754,
      "step": 406
    },
    {
      "epoch": 0.02229281919263844,
      "grad_norm": 5.697838306427002,
      "learning_rate": 0.00019997659546788782,
      "loss": 1.8064,
      "step": 407
    },
    {
      "epoch": 0.022347592704168265,
      "grad_norm": 2.7525737285614014,
      "learning_rate": 0.00019997646450065076,
      "loss": 1.214,
      "step": 408
    },
    {
      "epoch": 0.022402366215698088,
      "grad_norm": 18.19300079345703,
      "learning_rate": 0.00019997634808532894,
      "loss": 3.0383,
      "step": 409
    },
    {
      "epoch": 0.022457139727227914,
      "grad_norm": 7.2815399169921875,
      "learning_rate": 0.00019997621711809188,
      "loss": 2.2317,
      "step": 410
    },
    {
      "epoch": 0.022511913238757737,
      "grad_norm": 2.944873094558716,
      "learning_rate": 0.00019997610070277005,
      "loss": 2.2014,
      "step": 411
    },
    {
      "epoch": 0.02256668675028756,
      "grad_norm": 7.1419758796691895,
      "learning_rate": 0.00019997595518361777,
      "loss": 3.06,
      "step": 412
    },
    {
      "epoch": 0.022621460261817387,
      "grad_norm": 3.3824477195739746,
      "learning_rate": 0.00019997583876829594,
      "loss": 1.1332,
      "step": 413
    },
    {
      "epoch": 0.02267623377334721,
      "grad_norm": 3.033876895904541,
      "learning_rate": 0.0001999757078010589,
      "loss": 1.354,
      "step": 414
    },
    {
      "epoch": 0.022731007284877033,
      "grad_norm": 4.576082229614258,
      "learning_rate": 0.00019997557683382183,
      "loss": 2.5575,
      "step": 415
    },
    {
      "epoch": 0.02278578079640686,
      "grad_norm": 3.208787679672241,
      "learning_rate": 0.0001999754604185,
      "loss": 1.451,
      "step": 416
    },
    {
      "epoch": 0.022840554307936682,
      "grad_norm": 5.048257827758789,
      "learning_rate": 0.00019997532945126295,
      "loss": 1.3908,
      "step": 417
    },
    {
      "epoch": 0.022895327819466505,
      "grad_norm": 2.659308910369873,
      "learning_rate": 0.0001999751984840259,
      "loss": 1.6026,
      "step": 418
    },
    {
      "epoch": 0.02295010133099633,
      "grad_norm": 5.103361129760742,
      "learning_rate": 0.00019997508206870407,
      "loss": 1.0738,
      "step": 419
    },
    {
      "epoch": 0.023004874842526155,
      "grad_norm": 3.2900636196136475,
      "learning_rate": 0.000199974951101467,
      "loss": 1.6284,
      "step": 420
    },
    {
      "epoch": 0.023059648354055978,
      "grad_norm": 8.646068572998047,
      "learning_rate": 0.00019997482013422996,
      "loss": 1.8317,
      "step": 421
    },
    {
      "epoch": 0.023114421865585804,
      "grad_norm": 6.553443908691406,
      "learning_rate": 0.0001999746891669929,
      "loss": 2.6101,
      "step": 422
    },
    {
      "epoch": 0.023169195377115627,
      "grad_norm": 4.250142574310303,
      "learning_rate": 0.00019997455819975585,
      "loss": 1.6124,
      "step": 423
    },
    {
      "epoch": 0.02322396888864545,
      "grad_norm": 6.2050275802612305,
      "learning_rate": 0.00019997444178443402,
      "loss": 1.4548,
      "step": 424
    },
    {
      "epoch": 0.023278742400175276,
      "grad_norm": 6.343344211578369,
      "learning_rate": 0.00019997431081719697,
      "loss": 1.5823,
      "step": 425
    },
    {
      "epoch": 0.0233335159117051,
      "grad_norm": 2.1498122215270996,
      "learning_rate": 0.0001999741798499599,
      "loss": 1.5639,
      "step": 426
    },
    {
      "epoch": 0.023388289423234922,
      "grad_norm": 2.9880738258361816,
      "learning_rate": 0.00019997404888272285,
      "loss": 1.2812,
      "step": 427
    },
    {
      "epoch": 0.02344306293476475,
      "grad_norm": 2.086683511734009,
      "learning_rate": 0.0001999739179154858,
      "loss": 1.5889,
      "step": 428
    },
    {
      "epoch": 0.023497836446294572,
      "grad_norm": 3.1044375896453857,
      "learning_rate": 0.00019997378694824874,
      "loss": 1.808,
      "step": 429
    },
    {
      "epoch": 0.023552609957824395,
      "grad_norm": 1.4911607503890991,
      "learning_rate": 0.0001999736559810117,
      "loss": 1.2584,
      "step": 430
    },
    {
      "epoch": 0.02360738346935422,
      "grad_norm": 2.582908868789673,
      "learning_rate": 0.00019997352501377463,
      "loss": 1.3861,
      "step": 431
    },
    {
      "epoch": 0.023662156980884044,
      "grad_norm": 3.1264243125915527,
      "learning_rate": 0.00019997339404653758,
      "loss": 1.5949,
      "step": 432
    },
    {
      "epoch": 0.023716930492413867,
      "grad_norm": 11.121711730957031,
      "learning_rate": 0.00019997326307930052,
      "loss": 2.7972,
      "step": 433
    },
    {
      "epoch": 0.023771704003943694,
      "grad_norm": 19.708160400390625,
      "learning_rate": 0.00019997311756014824,
      "loss": 3.1718,
      "step": 434
    },
    {
      "epoch": 0.023826477515473517,
      "grad_norm": 2.2796785831451416,
      "learning_rate": 0.00019997298659291118,
      "loss": 1.3047,
      "step": 435
    },
    {
      "epoch": 0.02388125102700334,
      "grad_norm": 3.9746243953704834,
      "learning_rate": 0.00019997285562567413,
      "loss": 1.4947,
      "step": 436
    },
    {
      "epoch": 0.023936024538533166,
      "grad_norm": 1.464916706085205,
      "learning_rate": 0.00019997272465843707,
      "loss": 1.0372,
      "step": 437
    },
    {
      "epoch": 0.02399079805006299,
      "grad_norm": 5.597276210784912,
      "learning_rate": 0.0001999725791392848,
      "loss": 1.675,
      "step": 438
    },
    {
      "epoch": 0.024045571561592812,
      "grad_norm": 2.312849998474121,
      "learning_rate": 0.00019997244817204773,
      "loss": 1.6031,
      "step": 439
    },
    {
      "epoch": 0.02410034507312264,
      "grad_norm": 4.762145042419434,
      "learning_rate": 0.00019997231720481068,
      "loss": 1.745,
      "step": 440
    },
    {
      "epoch": 0.02415511858465246,
      "grad_norm": 5.301693916320801,
      "learning_rate": 0.00019997218623757362,
      "loss": 1.8204,
      "step": 441
    },
    {
      "epoch": 0.024209892096182285,
      "grad_norm": 5.354303359985352,
      "learning_rate": 0.00019997204071842134,
      "loss": 2.728,
      "step": 442
    },
    {
      "epoch": 0.02426466560771211,
      "grad_norm": 6.050148963928223,
      "learning_rate": 0.00019997190975118428,
      "loss": 2.0223,
      "step": 443
    },
    {
      "epoch": 0.024319439119241934,
      "grad_norm": 3.561933755874634,
      "learning_rate": 0.000199971764232032,
      "loss": 1.7845,
      "step": 444
    },
    {
      "epoch": 0.02437421263077176,
      "grad_norm": 4.620594501495361,
      "learning_rate": 0.00019997163326479495,
      "loss": 1.7166,
      "step": 445
    },
    {
      "epoch": 0.024428986142301583,
      "grad_norm": 2.180711507797241,
      "learning_rate": 0.00019997148774564266,
      "loss": 1.3496,
      "step": 446
    },
    {
      "epoch": 0.024483759653831406,
      "grad_norm": 2.9577245712280273,
      "learning_rate": 0.0001999713567784056,
      "loss": 1.7357,
      "step": 447
    },
    {
      "epoch": 0.024538533165361233,
      "grad_norm": 3.1220734119415283,
      "learning_rate": 0.00019997121125925332,
      "loss": 1.185,
      "step": 448
    },
    {
      "epoch": 0.024593306676891056,
      "grad_norm": 3.8561742305755615,
      "learning_rate": 0.00019997108029201627,
      "loss": 1.8569,
      "step": 449
    },
    {
      "epoch": 0.02464808018842088,
      "grad_norm": 2.649073600769043,
      "learning_rate": 0.0001999709493247792,
      "loss": 2.0329,
      "step": 450
    },
    {
      "epoch": 0.024702853699950705,
      "grad_norm": 3.2313873767852783,
      "learning_rate": 0.00019997081835754216,
      "loss": 1.3475,
      "step": 451
    },
    {
      "epoch": 0.02475762721148053,
      "grad_norm": 4.513105869293213,
      "learning_rate": 0.00019997067283838987,
      "loss": 1.7759,
      "step": 452
    },
    {
      "epoch": 0.02481240072301035,
      "grad_norm": 2.4460456371307373,
      "learning_rate": 0.0001999705273192376,
      "loss": 1.5273,
      "step": 453
    },
    {
      "epoch": 0.024867174234540178,
      "grad_norm": 8.538464546203613,
      "learning_rate": 0.00019997039635200053,
      "loss": 1.5746,
      "step": 454
    },
    {
      "epoch": 0.02492194774607,
      "grad_norm": 4.571901798248291,
      "learning_rate": 0.00019997025083284825,
      "loss": 1.8844,
      "step": 455
    },
    {
      "epoch": 0.024976721257599824,
      "grad_norm": 2.7902510166168213,
      "learning_rate": 0.00019997010531369597,
      "loss": 1.1205,
      "step": 456
    },
    {
      "epoch": 0.02503149476912965,
      "grad_norm": 4.074983596801758,
      "learning_rate": 0.00019996995979454368,
      "loss": 2.1886,
      "step": 457
    },
    {
      "epoch": 0.025086268280659473,
      "grad_norm": 1.9580203294754028,
      "learning_rate": 0.00019996982882730663,
      "loss": 0.5724,
      "step": 458
    },
    {
      "epoch": 0.025141041792189296,
      "grad_norm": 2.327698230743408,
      "learning_rate": 0.00019996969786006957,
      "loss": 1.871,
      "step": 459
    },
    {
      "epoch": 0.025195815303719123,
      "grad_norm": 4.517700672149658,
      "learning_rate": 0.0001999695523409173,
      "loss": 0.8499,
      "step": 460
    },
    {
      "epoch": 0.025250588815248946,
      "grad_norm": 5.545160293579102,
      "learning_rate": 0.000199969406821765,
      "loss": 1.9977,
      "step": 461
    },
    {
      "epoch": 0.02530536232677877,
      "grad_norm": 2.6670126914978027,
      "learning_rate": 0.00019996926130261272,
      "loss": 2.0204,
      "step": 462
    },
    {
      "epoch": 0.025360135838308595,
      "grad_norm": 7.4760026931762695,
      "learning_rate": 0.00019996911578346044,
      "loss": 2.351,
      "step": 463
    },
    {
      "epoch": 0.025414909349838418,
      "grad_norm": 4.095712661743164,
      "learning_rate": 0.00019996897026430815,
      "loss": 1.3999,
      "step": 464
    },
    {
      "epoch": 0.02546968286136824,
      "grad_norm": 7.59335470199585,
      "learning_rate": 0.0001999688392970711,
      "loss": 4.9274,
      "step": 465
    },
    {
      "epoch": 0.025524456372898068,
      "grad_norm": 4.121271133422852,
      "learning_rate": 0.00019996869377791882,
      "loss": 2.0696,
      "step": 466
    },
    {
      "epoch": 0.02557922988442789,
      "grad_norm": 5.125986099243164,
      "learning_rate": 0.00019996854825876653,
      "loss": 1.1427,
      "step": 467
    },
    {
      "epoch": 0.025634003395957713,
      "grad_norm": 2.4887499809265137,
      "learning_rate": 0.00019996840273961425,
      "loss": 1.8513,
      "step": 468
    },
    {
      "epoch": 0.02568877690748754,
      "grad_norm": 2.1701221466064453,
      "learning_rate": 0.00019996825722046196,
      "loss": 1.3725,
      "step": 469
    },
    {
      "epoch": 0.025743550419017363,
      "grad_norm": 4.924761772155762,
      "learning_rate": 0.00019996811170130968,
      "loss": 1.4494,
      "step": 470
    },
    {
      "epoch": 0.025798323930547186,
      "grad_norm": 3.85150146484375,
      "learning_rate": 0.0001999679661821574,
      "loss": 1.5057,
      "step": 471
    },
    {
      "epoch": 0.025853097442077012,
      "grad_norm": 1.895165205001831,
      "learning_rate": 0.00019996782066300511,
      "loss": 1.3757,
      "step": 472
    },
    {
      "epoch": 0.025907870953606835,
      "grad_norm": 2.167163133621216,
      "learning_rate": 0.00019996767514385283,
      "loss": 1.6916,
      "step": 473
    },
    {
      "epoch": 0.02596264446513666,
      "grad_norm": 2.4372665882110596,
      "learning_rate": 0.00019996752962470055,
      "loss": 1.3162,
      "step": 474
    },
    {
      "epoch": 0.026017417976666485,
      "grad_norm": 3.7717442512512207,
      "learning_rate": 0.00019996738410554826,
      "loss": 1.2756,
      "step": 475
    },
    {
      "epoch": 0.026072191488196308,
      "grad_norm": 15.147383689880371,
      "learning_rate": 0.00019996723858639598,
      "loss": 2.2377,
      "step": 476
    },
    {
      "epoch": 0.02612696499972613,
      "grad_norm": 3.109168529510498,
      "learning_rate": 0.0001999670930672437,
      "loss": 1.5867,
      "step": 477
    },
    {
      "epoch": 0.026181738511255957,
      "grad_norm": 2.832362651824951,
      "learning_rate": 0.0001999669475480914,
      "loss": 0.9354,
      "step": 478
    },
    {
      "epoch": 0.02623651202278578,
      "grad_norm": 3.7794301509857178,
      "learning_rate": 0.00019996680202893913,
      "loss": 1.3813,
      "step": 479
    },
    {
      "epoch": 0.026291285534315607,
      "grad_norm": 2.71999454498291,
      "learning_rate": 0.00019996665650978684,
      "loss": 1.6529,
      "step": 480
    },
    {
      "epoch": 0.02634605904584543,
      "grad_norm": 8.999110221862793,
      "learning_rate": 0.00019996649643871933,
      "loss": 2.9247,
      "step": 481
    },
    {
      "epoch": 0.026400832557375253,
      "grad_norm": 3.0944626331329346,
      "learning_rate": 0.00019996635091956705,
      "loss": 0.9985,
      "step": 482
    },
    {
      "epoch": 0.02645560606890508,
      "grad_norm": 7.079189300537109,
      "learning_rate": 0.00019996620540041476,
      "loss": 2.2132,
      "step": 483
    },
    {
      "epoch": 0.026510379580434902,
      "grad_norm": 1.8117257356643677,
      "learning_rate": 0.00019996605988126248,
      "loss": 1.2071,
      "step": 484
    },
    {
      "epoch": 0.026565153091964725,
      "grad_norm": 4.151696681976318,
      "learning_rate": 0.00019996589981019497,
      "loss": 2.2908,
      "step": 485
    },
    {
      "epoch": 0.02661992660349455,
      "grad_norm": 1.9948385953903198,
      "learning_rate": 0.00019996575429104269,
      "loss": 0.9615,
      "step": 486
    },
    {
      "epoch": 0.026674700115024375,
      "grad_norm": 2.8528406620025635,
      "learning_rate": 0.0001999656087718904,
      "loss": 1.5477,
      "step": 487
    },
    {
      "epoch": 0.026729473626554198,
      "grad_norm": 2.9781887531280518,
      "learning_rate": 0.0001999654487008229,
      "loss": 2.2522,
      "step": 488
    },
    {
      "epoch": 0.026784247138084024,
      "grad_norm": 2.4434621334075928,
      "learning_rate": 0.0001999653031816706,
      "loss": 1.3765,
      "step": 489
    },
    {
      "epoch": 0.026839020649613847,
      "grad_norm": 6.457531929016113,
      "learning_rate": 0.0001999651431106031,
      "loss": 0.7342,
      "step": 490
    },
    {
      "epoch": 0.02689379416114367,
      "grad_norm": 2.587033987045288,
      "learning_rate": 0.0001999649975914508,
      "loss": 1.7555,
      "step": 491
    },
    {
      "epoch": 0.026948567672673496,
      "grad_norm": 1.2588802576065063,
      "learning_rate": 0.00019996485207229853,
      "loss": 0.9505,
      "step": 492
    },
    {
      "epoch": 0.02700334118420332,
      "grad_norm": 3.2792539596557617,
      "learning_rate": 0.00019996469200123101,
      "loss": 2.0816,
      "step": 493
    },
    {
      "epoch": 0.027058114695733142,
      "grad_norm": 5.901131629943848,
      "learning_rate": 0.00019996454648207873,
      "loss": 1.6268,
      "step": 494
    },
    {
      "epoch": 0.02711288820726297,
      "grad_norm": 18.265899658203125,
      "learning_rate": 0.00019996438641101122,
      "loss": 4.0273,
      "step": 495
    },
    {
      "epoch": 0.027167661718792792,
      "grad_norm": 1.4512457847595215,
      "learning_rate": 0.0001999642263399437,
      "loss": 0.8252,
      "step": 496
    },
    {
      "epoch": 0.027222435230322615,
      "grad_norm": 1.871789813041687,
      "learning_rate": 0.00019996408082079142,
      "loss": 1.3755,
      "step": 497
    },
    {
      "epoch": 0.02727720874185244,
      "grad_norm": 17.486318588256836,
      "learning_rate": 0.0001999639207497239,
      "loss": 2.5441,
      "step": 498
    },
    {
      "epoch": 0.027331982253382264,
      "grad_norm": 2.023953676223755,
      "learning_rate": 0.00019996377523057163,
      "loss": 1.9946,
      "step": 499
    },
    {
      "epoch": 0.027386755764912087,
      "grad_norm": 2.858928680419922,
      "learning_rate": 0.00019996362971141934,
      "loss": 1.7774,
      "step": 500
    },
    {
      "epoch": 0.027386755764912087,
      "eval_loss": 1.567700982093811,
      "eval_runtime": 45.8268,
      "eval_samples_per_second": 2.008,
      "eval_steps_per_second": 2.008,
      "step": 500
    },
    {
      "epoch": 0.027441529276441914,
      "grad_norm": 5.591996192932129,
      "learning_rate": 0.00019996346964035183,
      "loss": 0.7195,
      "step": 501
    },
    {
      "epoch": 0.027496302787971737,
      "grad_norm": 3.0231382846832275,
      "learning_rate": 0.00019996330956928432,
      "loss": 1.3438,
      "step": 502
    },
    {
      "epoch": 0.02755107629950156,
      "grad_norm": 2.664381265640259,
      "learning_rate": 0.0001999631494982168,
      "loss": 1.2406,
      "step": 503
    },
    {
      "epoch": 0.027605849811031386,
      "grad_norm": 2.313901662826538,
      "learning_rate": 0.0001999629894271493,
      "loss": 0.9682,
      "step": 504
    },
    {
      "epoch": 0.02766062332256121,
      "grad_norm": 3.898216724395752,
      "learning_rate": 0.000199962843907997,
      "loss": 1.2749,
      "step": 505
    },
    {
      "epoch": 0.027715396834091032,
      "grad_norm": 20.45926284790039,
      "learning_rate": 0.0001999626838369295,
      "loss": 1.4861,
      "step": 506
    },
    {
      "epoch": 0.02777017034562086,
      "grad_norm": 2.3453691005706787,
      "learning_rate": 0.000199962523765862,
      "loss": 1.2669,
      "step": 507
    },
    {
      "epoch": 0.02782494385715068,
      "grad_norm": 1.965760588645935,
      "learning_rate": 0.0001999623782467097,
      "loss": 1.1255,
      "step": 508
    },
    {
      "epoch": 0.027879717368680505,
      "grad_norm": 2.973541021347046,
      "learning_rate": 0.0001999622181756422,
      "loss": 1.7273,
      "step": 509
    },
    {
      "epoch": 0.02793449088021033,
      "grad_norm": 3.2710390090942383,
      "learning_rate": 0.00019996204355265945,
      "loss": 1.3289,
      "step": 510
    },
    {
      "epoch": 0.027989264391740154,
      "grad_norm": 4.714122295379639,
      "learning_rate": 0.00019996189803350717,
      "loss": 1.8075,
      "step": 511
    },
    {
      "epoch": 0.028044037903269977,
      "grad_norm": 2.9777207374572754,
      "learning_rate": 0.00019996173796243966,
      "loss": 1.1221,
      "step": 512
    },
    {
      "epoch": 0.028098811414799803,
      "grad_norm": 8.469680786132812,
      "learning_rate": 0.00019996157789137214,
      "loss": 1.7417,
      "step": 513
    },
    {
      "epoch": 0.028153584926329626,
      "grad_norm": 6.78841495513916,
      "learning_rate": 0.00019996141782030463,
      "loss": 1.3509,
      "step": 514
    },
    {
      "epoch": 0.02820835843785945,
      "grad_norm": 4.236387729644775,
      "learning_rate": 0.00019996125774923712,
      "loss": 0.4208,
      "step": 515
    },
    {
      "epoch": 0.028263131949389276,
      "grad_norm": 6.488805770874023,
      "learning_rate": 0.0001999610976781696,
      "loss": 4.0552,
      "step": 516
    },
    {
      "epoch": 0.0283179054609191,
      "grad_norm": 5.682816028594971,
      "learning_rate": 0.0001999609376071021,
      "loss": 2.8401,
      "step": 517
    },
    {
      "epoch": 0.028372678972448925,
      "grad_norm": 25.428808212280273,
      "learning_rate": 0.00019996077753603458,
      "loss": 5.3619,
      "step": 518
    },
    {
      "epoch": 0.02842745248397875,
      "grad_norm": 29.87771987915039,
      "learning_rate": 0.00019996061746496707,
      "loss": 4.4843,
      "step": 519
    },
    {
      "epoch": 0.02848222599550857,
      "grad_norm": 6.237757682800293,
      "learning_rate": 0.00019996045739389956,
      "loss": 1.0533,
      "step": 520
    },
    {
      "epoch": 0.028536999507038398,
      "grad_norm": 2.37473464012146,
      "learning_rate": 0.00019996029732283205,
      "loss": 1.6877,
      "step": 521
    },
    {
      "epoch": 0.02859177301856822,
      "grad_norm": 3.3657302856445312,
      "learning_rate": 0.00019996013725176454,
      "loss": 1.431,
      "step": 522
    },
    {
      "epoch": 0.028646546530098044,
      "grad_norm": 3.6105141639709473,
      "learning_rate": 0.00019995997718069702,
      "loss": 2.1649,
      "step": 523
    },
    {
      "epoch": 0.02870132004162787,
      "grad_norm": 3.0149009227752686,
      "learning_rate": 0.00019995980255771428,
      "loss": 1.1798,
      "step": 524
    },
    {
      "epoch": 0.028756093553157693,
      "grad_norm": 2.6965456008911133,
      "learning_rate": 0.00019995964248664677,
      "loss": 1.9068,
      "step": 525
    },
    {
      "epoch": 0.028810867064687516,
      "grad_norm": 9.398114204406738,
      "learning_rate": 0.00019995948241557926,
      "loss": 1.775,
      "step": 526
    },
    {
      "epoch": 0.028865640576217343,
      "grad_norm": 3.6122689247131348,
      "learning_rate": 0.00019995932234451175,
      "loss": 2.3912,
      "step": 527
    },
    {
      "epoch": 0.028920414087747166,
      "grad_norm": 2.512441396713257,
      "learning_rate": 0.000199959147721529,
      "loss": 1.3796,
      "step": 528
    },
    {
      "epoch": 0.02897518759927699,
      "grad_norm": 2.0033202171325684,
      "learning_rate": 0.0001999589876504615,
      "loss": 1.4893,
      "step": 529
    },
    {
      "epoch": 0.029029961110806815,
      "grad_norm": 2.9270594120025635,
      "learning_rate": 0.00019995882757939398,
      "loss": 1.2749,
      "step": 530
    },
    {
      "epoch": 0.029084734622336638,
      "grad_norm": 3.672581911087036,
      "learning_rate": 0.00019995866750832647,
      "loss": 1.5981,
      "step": 531
    },
    {
      "epoch": 0.02913950813386646,
      "grad_norm": 3.097888708114624,
      "learning_rate": 0.00019995849288534373,
      "loss": 1.601,
      "step": 532
    },
    {
      "epoch": 0.029194281645396288,
      "grad_norm": 3.9518885612487793,
      "learning_rate": 0.00019995833281427622,
      "loss": 1.586,
      "step": 533
    },
    {
      "epoch": 0.02924905515692611,
      "grad_norm": 2.094583749771118,
      "learning_rate": 0.00019995815819129348,
      "loss": 1.656,
      "step": 534
    },
    {
      "epoch": 0.029303828668455933,
      "grad_norm": 7.83223819732666,
      "learning_rate": 0.00019995799812022597,
      "loss": 2.035,
      "step": 535
    },
    {
      "epoch": 0.02935860217998576,
      "grad_norm": 6.811017990112305,
      "learning_rate": 0.00019995782349724323,
      "loss": 2.0981,
      "step": 536
    },
    {
      "epoch": 0.029413375691515583,
      "grad_norm": 4.653653144836426,
      "learning_rate": 0.0001999576634261757,
      "loss": 1.2298,
      "step": 537
    },
    {
      "epoch": 0.029468149203045406,
      "grad_norm": 3.592209815979004,
      "learning_rate": 0.0001999575033551082,
      "loss": 1.8392,
      "step": 538
    },
    {
      "epoch": 0.029522922714575232,
      "grad_norm": 2.3463337421417236,
      "learning_rate": 0.00019995732873212546,
      "loss": 1.8096,
      "step": 539
    },
    {
      "epoch": 0.029577696226105055,
      "grad_norm": 2.5547144412994385,
      "learning_rate": 0.00019995716866105795,
      "loss": 1.5092,
      "step": 540
    },
    {
      "epoch": 0.02963246973763488,
      "grad_norm": 2.406036853790283,
      "learning_rate": 0.0001999569940380752,
      "loss": 1.6569,
      "step": 541
    },
    {
      "epoch": 0.029687243249164705,
      "grad_norm": 3.773861885070801,
      "learning_rate": 0.0001999568339670077,
      "loss": 1.4448,
      "step": 542
    },
    {
      "epoch": 0.029742016760694528,
      "grad_norm": 6.554800987243652,
      "learning_rate": 0.00019995665934402496,
      "loss": 2.2434,
      "step": 543
    },
    {
      "epoch": 0.02979679027222435,
      "grad_norm": 9.627795219421387,
      "learning_rate": 0.00019995649927295744,
      "loss": 1.3558,
      "step": 544
    },
    {
      "epoch": 0.029851563783754177,
      "grad_norm": 10.564467430114746,
      "learning_rate": 0.00019995631009805948,
      "loss": 1.9541,
      "step": 545
    },
    {
      "epoch": 0.029906337295284,
      "grad_norm": 3.133584499359131,
      "learning_rate": 0.00019995615002699196,
      "loss": 1.8843,
      "step": 546
    },
    {
      "epoch": 0.029961110806813823,
      "grad_norm": 2.480484962463379,
      "learning_rate": 0.00019995598995592445,
      "loss": 1.3508,
      "step": 547
    },
    {
      "epoch": 0.03001588431834365,
      "grad_norm": 7.362759113311768,
      "learning_rate": 0.0001999558153329417,
      "loss": 0.7921,
      "step": 548
    },
    {
      "epoch": 0.030070657829873473,
      "grad_norm": 3.544055223464966,
      "learning_rate": 0.00019995564070995897,
      "loss": 1.9903,
      "step": 549
    },
    {
      "epoch": 0.030125431341403296,
      "grad_norm": 19.644033432006836,
      "learning_rate": 0.00019995546608697623,
      "loss": 4.0918,
      "step": 550
    },
    {
      "epoch": 0.030180204852933122,
      "grad_norm": 2.9573874473571777,
      "learning_rate": 0.0001999552914639935,
      "loss": 1.5407,
      "step": 551
    },
    {
      "epoch": 0.030234978364462945,
      "grad_norm": 2.97021222114563,
      "learning_rate": 0.00019995513139292598,
      "loss": 1.4817,
      "step": 552
    },
    {
      "epoch": 0.03028975187599277,
      "grad_norm": 5.000908374786377,
      "learning_rate": 0.00019995495676994324,
      "loss": 2.9172,
      "step": 553
    },
    {
      "epoch": 0.030344525387522595,
      "grad_norm": 8.964093208312988,
      "learning_rate": 0.0001999547821469605,
      "loss": 2.3129,
      "step": 554
    },
    {
      "epoch": 0.030399298899052418,
      "grad_norm": 2.0946078300476074,
      "learning_rate": 0.00019995460752397776,
      "loss": 1.2831,
      "step": 555
    },
    {
      "epoch": 0.030454072410582244,
      "grad_norm": 2.5984015464782715,
      "learning_rate": 0.00019995443290099502,
      "loss": 1.6279,
      "step": 556
    },
    {
      "epoch": 0.030508845922112067,
      "grad_norm": 3.8878087997436523,
      "learning_rate": 0.0001999542728299275,
      "loss": 0.8293,
      "step": 557
    },
    {
      "epoch": 0.03056361943364189,
      "grad_norm": 2.8146889209747314,
      "learning_rate": 0.00019995408365502954,
      "loss": 2.0527,
      "step": 558
    },
    {
      "epoch": 0.030618392945171716,
      "grad_norm": 6.011548042297363,
      "learning_rate": 0.0001999539090320468,
      "loss": 2.2556,
      "step": 559
    },
    {
      "epoch": 0.03067316645670154,
      "grad_norm": 4.749360084533691,
      "learning_rate": 0.00019995374896097928,
      "loss": 3.4949,
      "step": 560
    },
    {
      "epoch": 0.030727939968231362,
      "grad_norm": 10.707727432250977,
      "learning_rate": 0.00019995355978608131,
      "loss": 2.4373,
      "step": 561
    },
    {
      "epoch": 0.03078271347976119,
      "grad_norm": 2.321373462677002,
      "learning_rate": 0.00019995338516309857,
      "loss": 1.6621,
      "step": 562
    },
    {
      "epoch": 0.030837486991291012,
      "grad_norm": 4.383183479309082,
      "learning_rate": 0.00019995321054011583,
      "loss": 1.9736,
      "step": 563
    },
    {
      "epoch": 0.030892260502820835,
      "grad_norm": 2.163784980773926,
      "learning_rate": 0.0001999530359171331,
      "loss": 1.392,
      "step": 564
    },
    {
      "epoch": 0.03094703401435066,
      "grad_norm": 4.460881233215332,
      "learning_rate": 0.00019995286129415035,
      "loss": 1.723,
      "step": 565
    },
    {
      "epoch": 0.031001807525880484,
      "grad_norm": 5.057430267333984,
      "learning_rate": 0.0001999526866711676,
      "loss": 1.8147,
      "step": 566
    },
    {
      "epoch": 0.031056581037410307,
      "grad_norm": 10.324482917785645,
      "learning_rate": 0.00019995251204818487,
      "loss": 2.0627,
      "step": 567
    },
    {
      "epoch": 0.031111354548940134,
      "grad_norm": 11.905305862426758,
      "learning_rate": 0.00019995233742520213,
      "loss": 3.0103,
      "step": 568
    },
    {
      "epoch": 0.031166128060469957,
      "grad_norm": 2.468735456466675,
      "learning_rate": 0.0001999521628022194,
      "loss": 1.763,
      "step": 569
    },
    {
      "epoch": 0.03122090157199978,
      "grad_norm": 4.717224597930908,
      "learning_rate": 0.00019995197362732142,
      "loss": 1.7256,
      "step": 570
    },
    {
      "epoch": 0.0312756750835296,
      "grad_norm": 1.9846495389938354,
      "learning_rate": 0.00019995179900433868,
      "loss": 1.0687,
      "step": 571
    },
    {
      "epoch": 0.03133044859505943,
      "grad_norm": 2.5977163314819336,
      "learning_rate": 0.00019995162438135594,
      "loss": 1.5659,
      "step": 572
    },
    {
      "epoch": 0.031385222106589256,
      "grad_norm": 2.5467684268951416,
      "learning_rate": 0.00019995143520645797,
      "loss": 2.1309,
      "step": 573
    },
    {
      "epoch": 0.031439995618119075,
      "grad_norm": 2.3087234497070312,
      "learning_rate": 0.00019995126058347523,
      "loss": 0.9664,
      "step": 574
    },
    {
      "epoch": 0.0314947691296489,
      "grad_norm": 2.7367124557495117,
      "learning_rate": 0.0001999510859604925,
      "loss": 1.1646,
      "step": 575
    },
    {
      "epoch": 0.03154954264117873,
      "grad_norm": 2.5174684524536133,
      "learning_rate": 0.00019995091133750975,
      "loss": 1.7587,
      "step": 576
    },
    {
      "epoch": 0.03160431615270855,
      "grad_norm": 6.583778381347656,
      "learning_rate": 0.00019995072216261178,
      "loss": 2.7998,
      "step": 577
    },
    {
      "epoch": 0.031659089664238374,
      "grad_norm": 5.452660083770752,
      "learning_rate": 0.00019995054753962904,
      "loss": 0.8055,
      "step": 578
    },
    {
      "epoch": 0.0317138631757682,
      "grad_norm": 1.5658069849014282,
      "learning_rate": 0.0001999503729166463,
      "loss": 0.9979,
      "step": 579
    },
    {
      "epoch": 0.03176863668729802,
      "grad_norm": 5.004964828491211,
      "learning_rate": 0.00019995018374174833,
      "loss": 1.6093,
      "step": 580
    },
    {
      "epoch": 0.031823410198827846,
      "grad_norm": 2.3882203102111816,
      "learning_rate": 0.00019994999456685036,
      "loss": 1.7115,
      "step": 581
    },
    {
      "epoch": 0.03187818371035767,
      "grad_norm": 7.815603256225586,
      "learning_rate": 0.00019994981994386762,
      "loss": 2.4137,
      "step": 582
    },
    {
      "epoch": 0.03193295722188749,
      "grad_norm": 3.3125486373901367,
      "learning_rate": 0.00019994964532088488,
      "loss": 1.3005,
      "step": 583
    },
    {
      "epoch": 0.03198773073341732,
      "grad_norm": 2.119232654571533,
      "learning_rate": 0.00019994945614598691,
      "loss": 1.1696,
      "step": 584
    },
    {
      "epoch": 0.032042504244947145,
      "grad_norm": 16.076013565063477,
      "learning_rate": 0.00019994926697108895,
      "loss": 1.9417,
      "step": 585
    },
    {
      "epoch": 0.032097277756476965,
      "grad_norm": 1.6582173109054565,
      "learning_rate": 0.0001999490923481062,
      "loss": 0.8813,
      "step": 586
    },
    {
      "epoch": 0.03215205126800679,
      "grad_norm": 3.1527390480041504,
      "learning_rate": 0.00019994890317320824,
      "loss": 1.5572,
      "step": 587
    },
    {
      "epoch": 0.03220682477953662,
      "grad_norm": 4.367067813873291,
      "learning_rate": 0.0001999487285502255,
      "loss": 2.3801,
      "step": 588
    },
    {
      "epoch": 0.03226159829106644,
      "grad_norm": 2.154573440551758,
      "learning_rate": 0.00019994853937532753,
      "loss": 1.6123,
      "step": 589
    },
    {
      "epoch": 0.032316371802596264,
      "grad_norm": 13.966064453125,
      "learning_rate": 0.00019994835020042956,
      "loss": 1.8096,
      "step": 590
    },
    {
      "epoch": 0.03237114531412609,
      "grad_norm": 5.635392189025879,
      "learning_rate": 0.00019994817557744682,
      "loss": 1.462,
      "step": 591
    },
    {
      "epoch": 0.03242591882565591,
      "grad_norm": 2.6879231929779053,
      "learning_rate": 0.00019994798640254885,
      "loss": 1.572,
      "step": 592
    },
    {
      "epoch": 0.032480692337185736,
      "grad_norm": 2.8692896366119385,
      "learning_rate": 0.0001999478117795661,
      "loss": 1.2353,
      "step": 593
    },
    {
      "epoch": 0.03253546584871556,
      "grad_norm": 2.470681667327881,
      "learning_rate": 0.0001999476080527529,
      "loss": 1.3468,
      "step": 594
    },
    {
      "epoch": 0.03259023936024538,
      "grad_norm": 6.809054851531982,
      "learning_rate": 0.00019994741887785494,
      "loss": 2.0087,
      "step": 595
    },
    {
      "epoch": 0.03264501287177521,
      "grad_norm": 2.3193209171295166,
      "learning_rate": 0.0001999472442548722,
      "loss": 1.2876,
      "step": 596
    },
    {
      "epoch": 0.032699786383305035,
      "grad_norm": 5.817577362060547,
      "learning_rate": 0.00019994705507997423,
      "loss": 0.8163,
      "step": 597
    },
    {
      "epoch": 0.032754559894834855,
      "grad_norm": 3.5115158557891846,
      "learning_rate": 0.0001999468804569915,
      "loss": 2.1381,
      "step": 598
    },
    {
      "epoch": 0.03280933340636468,
      "grad_norm": 3.434645175933838,
      "learning_rate": 0.00019994669128209352,
      "loss": 2.0175,
      "step": 599
    },
    {
      "epoch": 0.03286410691789451,
      "grad_norm": 2.6568996906280518,
      "learning_rate": 0.00019994648755528033,
      "loss": 0.9696,
      "step": 600
    },
    {
      "epoch": 0.03286410691789451,
      "eval_loss": 1.545455813407898,
      "eval_runtime": 45.8967,
      "eval_samples_per_second": 2.005,
      "eval_steps_per_second": 2.005,
      "step": 600
    },
    {
      "epoch": 0.03291888042942433,
      "grad_norm": 5.9341721534729,
      "learning_rate": 0.00019994629838038236,
      "loss": 1.6347,
      "step": 601
    },
    {
      "epoch": 0.032973653940954153,
      "grad_norm": 3.8457694053649902,
      "learning_rate": 0.00019994612375739962,
      "loss": 2.5334,
      "step": 602
    },
    {
      "epoch": 0.03302842745248398,
      "grad_norm": 6.015210151672363,
      "learning_rate": 0.00019994593458250165,
      "loss": 0.9482,
      "step": 603
    },
    {
      "epoch": 0.033083200964013806,
      "grad_norm": 3.220912218093872,
      "learning_rate": 0.00019994574540760368,
      "loss": 0.5155,
      "step": 604
    },
    {
      "epoch": 0.033137974475543626,
      "grad_norm": 2.4226861000061035,
      "learning_rate": 0.0001999455562327057,
      "loss": 1.8799,
      "step": 605
    },
    {
      "epoch": 0.03319274798707345,
      "grad_norm": 2.6042206287384033,
      "learning_rate": 0.00019994536705780774,
      "loss": 1.4343,
      "step": 606
    },
    {
      "epoch": 0.03324752149860328,
      "grad_norm": 5.761486530303955,
      "learning_rate": 0.00019994516333099455,
      "loss": 1.3923,
      "step": 607
    },
    {
      "epoch": 0.0333022950101331,
      "grad_norm": 10.515082359313965,
      "learning_rate": 0.00019994497415609658,
      "loss": 1.4593,
      "step": 608
    },
    {
      "epoch": 0.033357068521662925,
      "grad_norm": 2.43754506111145,
      "learning_rate": 0.0001999447849811986,
      "loss": 1.6423,
      "step": 609
    },
    {
      "epoch": 0.03341184203319275,
      "grad_norm": 2.6760287284851074,
      "learning_rate": 0.00019994459580630064,
      "loss": 1.1096,
      "step": 610
    },
    {
      "epoch": 0.03346661554472257,
      "grad_norm": 4.430553913116455,
      "learning_rate": 0.00019994440663140267,
      "loss": 0.5048,
      "step": 611
    },
    {
      "epoch": 0.0335213890562524,
      "grad_norm": 4.079591274261475,
      "learning_rate": 0.0001999442174565047,
      "loss": 1.4062,
      "step": 612
    },
    {
      "epoch": 0.033576162567782224,
      "grad_norm": 3.0218091011047363,
      "learning_rate": 0.00019994402828160673,
      "loss": 1.25,
      "step": 613
    },
    {
      "epoch": 0.03363093607931204,
      "grad_norm": 4.72252893447876,
      "learning_rate": 0.00019994383910670877,
      "loss": 1.5048,
      "step": 614
    },
    {
      "epoch": 0.03368570959084187,
      "grad_norm": 3.159303903579712,
      "learning_rate": 0.0001999436499318108,
      "loss": 1.5677,
      "step": 615
    },
    {
      "epoch": 0.033740483102371696,
      "grad_norm": 4.434576034545898,
      "learning_rate": 0.00019994346075691283,
      "loss": 0.8751,
      "step": 616
    },
    {
      "epoch": 0.033795256613901516,
      "grad_norm": 5.189826965332031,
      "learning_rate": 0.00019994325703009963,
      "loss": 1.3905,
      "step": 617
    },
    {
      "epoch": 0.03385003012543134,
      "grad_norm": 4.713236331939697,
      "learning_rate": 0.00019994306785520166,
      "loss": 2.2673,
      "step": 618
    },
    {
      "epoch": 0.03390480363696117,
      "grad_norm": 2.387118339538574,
      "learning_rate": 0.00019994286412838846,
      "loss": 1.2302,
      "step": 619
    },
    {
      "epoch": 0.03395957714849099,
      "grad_norm": 5.3190789222717285,
      "learning_rate": 0.0001999426749534905,
      "loss": 1.5604,
      "step": 620
    },
    {
      "epoch": 0.034014350660020815,
      "grad_norm": 5.085553169250488,
      "learning_rate": 0.0001999424712266773,
      "loss": 0.9437,
      "step": 621
    },
    {
      "epoch": 0.03406912417155064,
      "grad_norm": 2.232142210006714,
      "learning_rate": 0.00019994228205177933,
      "loss": 1.0496,
      "step": 622
    },
    {
      "epoch": 0.03412389768308046,
      "grad_norm": 22.68629264831543,
      "learning_rate": 0.00019994209287688136,
      "loss": 2.1767,
      "step": 623
    },
    {
      "epoch": 0.03417867119461029,
      "grad_norm": 3.6032323837280273,
      "learning_rate": 0.00019994188915006816,
      "loss": 1.8542,
      "step": 624
    },
    {
      "epoch": 0.03423344470614011,
      "grad_norm": 5.180454730987549,
      "learning_rate": 0.0001999416999751702,
      "loss": 0.72,
      "step": 625
    },
    {
      "epoch": 0.03428821821766993,
      "grad_norm": 4.474588871002197,
      "learning_rate": 0.000199941496248357,
      "loss": 1.5323,
      "step": 626
    },
    {
      "epoch": 0.03434299172919976,
      "grad_norm": 3.7035841941833496,
      "learning_rate": 0.00019994130707345903,
      "loss": 1.4235,
      "step": 627
    },
    {
      "epoch": 0.034397765240729586,
      "grad_norm": 4.612367153167725,
      "learning_rate": 0.00019994110334664583,
      "loss": 2.0198,
      "step": 628
    },
    {
      "epoch": 0.034452538752259405,
      "grad_norm": 2.349138021469116,
      "learning_rate": 0.00019994091417174786,
      "loss": 1.7092,
      "step": 629
    },
    {
      "epoch": 0.03450731226378923,
      "grad_norm": 3.2345616817474365,
      "learning_rate": 0.00019994071044493467,
      "loss": 2.2887,
      "step": 630
    },
    {
      "epoch": 0.03456208577531906,
      "grad_norm": 6.781264781951904,
      "learning_rate": 0.0001999405212700367,
      "loss": 1.1305,
      "step": 631
    },
    {
      "epoch": 0.03461685928684888,
      "grad_norm": 3.049609899520874,
      "learning_rate": 0.0001999403175432235,
      "loss": 1.7413,
      "step": 632
    },
    {
      "epoch": 0.034671632798378704,
      "grad_norm": 1.2743079662322998,
      "learning_rate": 0.0001999401138164103,
      "loss": 0.6093,
      "step": 633
    },
    {
      "epoch": 0.03472640630990853,
      "grad_norm": 8.135610580444336,
      "learning_rate": 0.00019993992464151233,
      "loss": 1.4096,
      "step": 634
    },
    {
      "epoch": 0.03478117982143835,
      "grad_norm": 19.706254959106445,
      "learning_rate": 0.00019993972091469914,
      "loss": 3.6421,
      "step": 635
    },
    {
      "epoch": 0.03483595333296818,
      "grad_norm": 2.986678123474121,
      "learning_rate": 0.00019993951718788594,
      "loss": 1.1301,
      "step": 636
    },
    {
      "epoch": 0.034890726844498,
      "grad_norm": 3.0149621963500977,
      "learning_rate": 0.00019993932801298797,
      "loss": 0.4025,
      "step": 637
    },
    {
      "epoch": 0.03494550035602782,
      "grad_norm": 6.655350685119629,
      "learning_rate": 0.00019993912428617477,
      "loss": 1.3878,
      "step": 638
    },
    {
      "epoch": 0.03500027386755765,
      "grad_norm": 5.655645847320557,
      "learning_rate": 0.00019993892055936158,
      "loss": 1.6963,
      "step": 639
    },
    {
      "epoch": 0.035055047379087476,
      "grad_norm": 5.7464165687561035,
      "learning_rate": 0.00019993871683254838,
      "loss": 2.8941,
      "step": 640
    },
    {
      "epoch": 0.035109820890617295,
      "grad_norm": 5.960227012634277,
      "learning_rate": 0.00019993851310573518,
      "loss": 2.0158,
      "step": 641
    },
    {
      "epoch": 0.03516459440214712,
      "grad_norm": 2.4028258323669434,
      "learning_rate": 0.00019993830937892199,
      "loss": 1.6664,
      "step": 642
    },
    {
      "epoch": 0.03521936791367695,
      "grad_norm": 4.973051071166992,
      "learning_rate": 0.00019993812020402402,
      "loss": 2.3957,
      "step": 643
    },
    {
      "epoch": 0.03527414142520677,
      "grad_norm": 1.8895233869552612,
      "learning_rate": 0.00019993791647721082,
      "loss": 0.8845,
      "step": 644
    },
    {
      "epoch": 0.035328914936736594,
      "grad_norm": 2.392570734024048,
      "learning_rate": 0.00019993771275039762,
      "loss": 1.0444,
      "step": 645
    },
    {
      "epoch": 0.03538368844826642,
      "grad_norm": 5.3235087394714355,
      "learning_rate": 0.00019993752357549965,
      "loss": 1.8209,
      "step": 646
    },
    {
      "epoch": 0.03543846195979624,
      "grad_norm": 12.341041564941406,
      "learning_rate": 0.00019993731984868646,
      "loss": 1.2923,
      "step": 647
    },
    {
      "epoch": 0.035493235471326066,
      "grad_norm": 6.640406131744385,
      "learning_rate": 0.00019993710156995803,
      "loss": 1.7946,
      "step": 648
    },
    {
      "epoch": 0.03554800898285589,
      "grad_norm": 2.4953668117523193,
      "learning_rate": 0.00019993689784314483,
      "loss": 0.8693,
      "step": 649
    },
    {
      "epoch": 0.03560278249438571,
      "grad_norm": 7.280468463897705,
      "learning_rate": 0.00019993669411633164,
      "loss": 1.648,
      "step": 650
    },
    {
      "epoch": 0.03565755600591554,
      "grad_norm": 3.4213411808013916,
      "learning_rate": 0.00019993649038951844,
      "loss": 1.9201,
      "step": 651
    },
    {
      "epoch": 0.035712329517445365,
      "grad_norm": 2.3556482791900635,
      "learning_rate": 0.00019993628666270524,
      "loss": 0.9742,
      "step": 652
    },
    {
      "epoch": 0.035767103028975185,
      "grad_norm": 3.275639772415161,
      "learning_rate": 0.00019993608293589205,
      "loss": 1.419,
      "step": 653
    },
    {
      "epoch": 0.03582187654050501,
      "grad_norm": 9.817517280578613,
      "learning_rate": 0.00019993587920907885,
      "loss": 2.2447,
      "step": 654
    },
    {
      "epoch": 0.03587665005203484,
      "grad_norm": 2.9262707233428955,
      "learning_rate": 0.00019993567548226565,
      "loss": 1.8769,
      "step": 655
    },
    {
      "epoch": 0.03593142356356466,
      "grad_norm": 4.825551509857178,
      "learning_rate": 0.00019993547175545245,
      "loss": 1.862,
      "step": 656
    },
    {
      "epoch": 0.035986197075094484,
      "grad_norm": 9.008596420288086,
      "learning_rate": 0.00019993526802863926,
      "loss": 1.7659,
      "step": 657
    },
    {
      "epoch": 0.03604097058662431,
      "grad_norm": 1.9753257036209106,
      "learning_rate": 0.00019993504974991083,
      "loss": 1.2985,
      "step": 658
    },
    {
      "epoch": 0.03609574409815413,
      "grad_norm": 2.676898717880249,
      "learning_rate": 0.00019993484602309763,
      "loss": 0.1234,
      "step": 659
    },
    {
      "epoch": 0.036150517609683956,
      "grad_norm": 3.5156960487365723,
      "learning_rate": 0.00019993464229628444,
      "loss": 1.1234,
      "step": 660
    },
    {
      "epoch": 0.03620529112121378,
      "grad_norm": 3.7204461097717285,
      "learning_rate": 0.000199934424017556,
      "loss": 1.6869,
      "step": 661
    },
    {
      "epoch": 0.0362600646327436,
      "grad_norm": 5.203382968902588,
      "learning_rate": 0.00019993422029074281,
      "loss": 2.2017,
      "step": 662
    },
    {
      "epoch": 0.03631483814427343,
      "grad_norm": 23.429712295532227,
      "learning_rate": 0.00019993401656392962,
      "loss": 4.7062,
      "step": 663
    },
    {
      "epoch": 0.036369611655803255,
      "grad_norm": 7.3945746421813965,
      "learning_rate": 0.00019993381283711642,
      "loss": 3.1709,
      "step": 664
    },
    {
      "epoch": 0.036424385167333075,
      "grad_norm": 6.19509744644165,
      "learning_rate": 0.000199933594558388,
      "loss": 1.7133,
      "step": 665
    },
    {
      "epoch": 0.0364791586788629,
      "grad_norm": 3.4542794227600098,
      "learning_rate": 0.0001999333908315748,
      "loss": 2.2842,
      "step": 666
    },
    {
      "epoch": 0.03653393219039273,
      "grad_norm": 4.722288131713867,
      "learning_rate": 0.00019993317255284637,
      "loss": 1.6513,
      "step": 667
    },
    {
      "epoch": 0.03658870570192255,
      "grad_norm": 3.3203587532043457,
      "learning_rate": 0.00019993296882603317,
      "loss": 1.7348,
      "step": 668
    },
    {
      "epoch": 0.03664347921345237,
      "grad_norm": 2.1591796875,
      "learning_rate": 0.00019993276509921998,
      "loss": 1.5938,
      "step": 669
    },
    {
      "epoch": 0.0366982527249822,
      "grad_norm": 3.1169159412384033,
      "learning_rate": 0.00019993254682049155,
      "loss": 1.4142,
      "step": 670
    },
    {
      "epoch": 0.03675302623651202,
      "grad_norm": 3.938988447189331,
      "learning_rate": 0.00019993234309367836,
      "loss": 1.1194,
      "step": 671
    },
    {
      "epoch": 0.036807799748041846,
      "grad_norm": 2.0717759132385254,
      "learning_rate": 0.00019993212481494993,
      "loss": 1.38,
      "step": 672
    },
    {
      "epoch": 0.03686257325957167,
      "grad_norm": 2.7971839904785156,
      "learning_rate": 0.00019993192108813673,
      "loss": 1.17,
      "step": 673
    },
    {
      "epoch": 0.03691734677110149,
      "grad_norm": 2.7915003299713135,
      "learning_rate": 0.0001999317028094083,
      "loss": 1.6271,
      "step": 674
    },
    {
      "epoch": 0.03697212028263132,
      "grad_norm": 4.79559326171875,
      "learning_rate": 0.00019993148453067988,
      "loss": 1.5778,
      "step": 675
    },
    {
      "epoch": 0.037026893794161145,
      "grad_norm": 15.365832328796387,
      "learning_rate": 0.00019993128080386668,
      "loss": 4.3285,
      "step": 676
    },
    {
      "epoch": 0.03708166730569097,
      "grad_norm": 2.399919271469116,
      "learning_rate": 0.00019993106252513826,
      "loss": 1.5544,
      "step": 677
    },
    {
      "epoch": 0.03713644081722079,
      "grad_norm": 9.011710166931152,
      "learning_rate": 0.00019993085879832506,
      "loss": 2.3918,
      "step": 678
    },
    {
      "epoch": 0.03719121432875062,
      "grad_norm": 7.81559419631958,
      "learning_rate": 0.00019993064051959664,
      "loss": 1.2881,
      "step": 679
    },
    {
      "epoch": 0.037245987840280444,
      "grad_norm": 1.9700508117675781,
      "learning_rate": 0.0001999304222408682,
      "loss": 1.366,
      "step": 680
    },
    {
      "epoch": 0.03730076135181026,
      "grad_norm": 4.863327503204346,
      "learning_rate": 0.00019993020396213979,
      "loss": 1.6234,
      "step": 681
    },
    {
      "epoch": 0.03735553486334009,
      "grad_norm": 2.391315460205078,
      "learning_rate": 0.0001999300002353266,
      "loss": 1.5791,
      "step": 682
    },
    {
      "epoch": 0.037410308374869916,
      "grad_norm": 7.926125526428223,
      "learning_rate": 0.00019992978195659816,
      "loss": 1.0332,
      "step": 683
    },
    {
      "epoch": 0.037465081886399736,
      "grad_norm": 1.685792088508606,
      "learning_rate": 0.00019992956367786974,
      "loss": 1.2011,
      "step": 684
    },
    {
      "epoch": 0.03751985539792956,
      "grad_norm": 6.302787780761719,
      "learning_rate": 0.0001999293453991413,
      "loss": 1.5192,
      "step": 685
    },
    {
      "epoch": 0.03757462890945939,
      "grad_norm": 5.445502281188965,
      "learning_rate": 0.00019992914167232811,
      "loss": 1.0135,
      "step": 686
    },
    {
      "epoch": 0.03762940242098921,
      "grad_norm": 2.5961945056915283,
      "learning_rate": 0.0001999289233935997,
      "loss": 1.6335,
      "step": 687
    },
    {
      "epoch": 0.037684175932519035,
      "grad_norm": 2.0894582271575928,
      "learning_rate": 0.00019992870511487126,
      "loss": 1.1112,
      "step": 688
    },
    {
      "epoch": 0.03773894944404886,
      "grad_norm": 3.320329427719116,
      "learning_rate": 0.00019992848683614284,
      "loss": 1.9097,
      "step": 689
    },
    {
      "epoch": 0.03779372295557868,
      "grad_norm": 1.579961895942688,
      "learning_rate": 0.0001999282685574144,
      "loss": 0.9695,
      "step": 690
    },
    {
      "epoch": 0.03784849646710851,
      "grad_norm": 2.100783348083496,
      "learning_rate": 0.000199928050278686,
      "loss": 0.9917,
      "step": 691
    },
    {
      "epoch": 0.03790326997863833,
      "grad_norm": 6.3961944580078125,
      "learning_rate": 0.00019992783199995756,
      "loss": 1.5669,
      "step": 692
    },
    {
      "epoch": 0.03795804349016815,
      "grad_norm": 2.288487434387207,
      "learning_rate": 0.00019992761372122914,
      "loss": 1.3267,
      "step": 693
    },
    {
      "epoch": 0.03801281700169798,
      "grad_norm": 3.8638393878936768,
      "learning_rate": 0.0001999273954425007,
      "loss": 2.346,
      "step": 694
    },
    {
      "epoch": 0.038067590513227806,
      "grad_norm": 2.9057981967926025,
      "learning_rate": 0.00019992717716377228,
      "loss": 1.3032,
      "step": 695
    },
    {
      "epoch": 0.038122364024757625,
      "grad_norm": 2.4089808464050293,
      "learning_rate": 0.00019992695888504386,
      "loss": 0.8255,
      "step": 696
    },
    {
      "epoch": 0.03817713753628745,
      "grad_norm": 7.989795207977295,
      "learning_rate": 0.00019992674060631543,
      "loss": 3.2339,
      "step": 697
    },
    {
      "epoch": 0.03823191104781728,
      "grad_norm": 4.2920684814453125,
      "learning_rate": 0.00019992650777567178,
      "loss": 0.507,
      "step": 698
    },
    {
      "epoch": 0.0382866845593471,
      "grad_norm": 2.477735757827759,
      "learning_rate": 0.00019992630404885858,
      "loss": 1.7634,
      "step": 699
    },
    {
      "epoch": 0.038341458070876924,
      "grad_norm": 17.7137393951416,
      "learning_rate": 0.00019992607121821493,
      "loss": 2.4803,
      "step": 700
    },
    {
      "epoch": 0.038341458070876924,
      "eval_loss": 1.5383886098861694,
      "eval_runtime": 45.803,
      "eval_samples_per_second": 2.009,
      "eval_steps_per_second": 2.009,
      "step": 700
    },
    {
      "epoch": 0.03839623158240675,
      "grad_norm": 2.426609754562378,
      "learning_rate": 0.0001999258529394865,
      "loss": 1.5496,
      "step": 701
    },
    {
      "epoch": 0.03845100509393657,
      "grad_norm": 7.199146270751953,
      "learning_rate": 0.00019992563466075808,
      "loss": 1.9441,
      "step": 702
    },
    {
      "epoch": 0.0385057786054664,
      "grad_norm": 2.841669797897339,
      "learning_rate": 0.00019992541638202965,
      "loss": 1.6856,
      "step": 703
    },
    {
      "epoch": 0.03856055211699622,
      "grad_norm": 6.010741233825684,
      "learning_rate": 0.00019992519810330123,
      "loss": 2.1933,
      "step": 704
    },
    {
      "epoch": 0.03861532562852604,
      "grad_norm": 5.864816188812256,
      "learning_rate": 0.0001999249798245728,
      "loss": 1.2413,
      "step": 705
    },
    {
      "epoch": 0.03867009914005587,
      "grad_norm": 2.310821294784546,
      "learning_rate": 0.00019992474699392915,
      "loss": 1.379,
      "step": 706
    },
    {
      "epoch": 0.038724872651585696,
      "grad_norm": 5.2942891120910645,
      "learning_rate": 0.00019992452871520072,
      "loss": 1.247,
      "step": 707
    },
    {
      "epoch": 0.038779646163115515,
      "grad_norm": 2.907808303833008,
      "learning_rate": 0.0001999243104364723,
      "loss": 1.3219,
      "step": 708
    },
    {
      "epoch": 0.03883441967464534,
      "grad_norm": 4.096454620361328,
      "learning_rate": 0.00019992407760582864,
      "loss": 1.7025,
      "step": 709
    },
    {
      "epoch": 0.03888919318617517,
      "grad_norm": 5.378364086151123,
      "learning_rate": 0.00019992385932710022,
      "loss": 1.5096,
      "step": 710
    },
    {
      "epoch": 0.03894396669770499,
      "grad_norm": 5.325686454772949,
      "learning_rate": 0.00019992362649645656,
      "loss": 1.6724,
      "step": 711
    },
    {
      "epoch": 0.038998740209234814,
      "grad_norm": 4.951519966125488,
      "learning_rate": 0.00019992340821772814,
      "loss": 1.4662,
      "step": 712
    },
    {
      "epoch": 0.03905351372076464,
      "grad_norm": 2.802297592163086,
      "learning_rate": 0.0001999231899389997,
      "loss": 0.7626,
      "step": 713
    },
    {
      "epoch": 0.03910828723229446,
      "grad_norm": 7.528237819671631,
      "learning_rate": 0.00019992295710835606,
      "loss": 2.7406,
      "step": 714
    },
    {
      "epoch": 0.039163060743824286,
      "grad_norm": 28.17909049987793,
      "learning_rate": 0.00019992273882962763,
      "loss": 4.0146,
      "step": 715
    },
    {
      "epoch": 0.03921783425535411,
      "grad_norm": 2.132882595062256,
      "learning_rate": 0.00019992250599898398,
      "loss": 1.3904,
      "step": 716
    },
    {
      "epoch": 0.03927260776688393,
      "grad_norm": 6.554956436157227,
      "learning_rate": 0.00019992228772025555,
      "loss": 1.3525,
      "step": 717
    },
    {
      "epoch": 0.03932738127841376,
      "grad_norm": 5.276966571807861,
      "learning_rate": 0.0001999220548896119,
      "loss": 0.8738,
      "step": 718
    },
    {
      "epoch": 0.039382154789943585,
      "grad_norm": 6.0127763748168945,
      "learning_rate": 0.00019992183661088347,
      "loss": 1.9509,
      "step": 719
    },
    {
      "epoch": 0.039436928301473405,
      "grad_norm": 3.205453634262085,
      "learning_rate": 0.00019992160378023982,
      "loss": 1.55,
      "step": 720
    },
    {
      "epoch": 0.03949170181300323,
      "grad_norm": 2.9228837490081787,
      "learning_rate": 0.00019992137094959617,
      "loss": 0.9511,
      "step": 721
    },
    {
      "epoch": 0.03954647532453306,
      "grad_norm": 5.482321739196777,
      "learning_rate": 0.00019992115267086774,
      "loss": 1.2131,
      "step": 722
    },
    {
      "epoch": 0.03960124883606288,
      "grad_norm": 2.8969435691833496,
      "learning_rate": 0.00019992090528830886,
      "loss": 0.8703,
      "step": 723
    },
    {
      "epoch": 0.039656022347592704,
      "grad_norm": 12.20158863067627,
      "learning_rate": 0.00019992068700958043,
      "loss": 2.2383,
      "step": 724
    },
    {
      "epoch": 0.03971079585912253,
      "grad_norm": 2.5308172702789307,
      "learning_rate": 0.00019992045417893678,
      "loss": 1.7975,
      "step": 725
    },
    {
      "epoch": 0.03976556937065235,
      "grad_norm": 2.828237533569336,
      "learning_rate": 0.00019992023590020835,
      "loss": 1.8182,
      "step": 726
    },
    {
      "epoch": 0.039820342882182176,
      "grad_norm": 2.5133886337280273,
      "learning_rate": 0.0001999200030695647,
      "loss": 1.5254,
      "step": 727
    },
    {
      "epoch": 0.039875116393712,
      "grad_norm": 2.807950258255005,
      "learning_rate": 0.00019991977023892105,
      "loss": 1.7576,
      "step": 728
    },
    {
      "epoch": 0.03992988990524182,
      "grad_norm": 5.899503707885742,
      "learning_rate": 0.0001999195374082774,
      "loss": 2.5011,
      "step": 729
    },
    {
      "epoch": 0.03998466341677165,
      "grad_norm": 2.7652580738067627,
      "learning_rate": 0.00019991931912954897,
      "loss": 1.1785,
      "step": 730
    },
    {
      "epoch": 0.040039436928301475,
      "grad_norm": 13.434412956237793,
      "learning_rate": 0.00019991907174699008,
      "loss": 2.4315,
      "step": 731
    },
    {
      "epoch": 0.040094210439831295,
      "grad_norm": 2.3617937564849854,
      "learning_rate": 0.00019991885346826166,
      "loss": 1.2925,
      "step": 732
    },
    {
      "epoch": 0.04014898395136112,
      "grad_norm": 2.886478900909424,
      "learning_rate": 0.000199918620637618,
      "loss": 1.2974,
      "step": 733
    },
    {
      "epoch": 0.04020375746289095,
      "grad_norm": 1.9317086935043335,
      "learning_rate": 0.00019991838780697435,
      "loss": 1.0724,
      "step": 734
    },
    {
      "epoch": 0.04025853097442077,
      "grad_norm": 2.804575204849243,
      "learning_rate": 0.0001999181549763307,
      "loss": 1.7677,
      "step": 735
    },
    {
      "epoch": 0.04031330448595059,
      "grad_norm": 4.496385097503662,
      "learning_rate": 0.00019991792214568704,
      "loss": 2.0637,
      "step": 736
    },
    {
      "epoch": 0.04036807799748042,
      "grad_norm": 8.435135841369629,
      "learning_rate": 0.0001999176893150434,
      "loss": 1.7521,
      "step": 737
    },
    {
      "epoch": 0.04042285150901024,
      "grad_norm": 2.9613468647003174,
      "learning_rate": 0.00019991745648439974,
      "loss": 1.4962,
      "step": 738
    },
    {
      "epoch": 0.040477625020540066,
      "grad_norm": 4.763615608215332,
      "learning_rate": 0.00019991722365375608,
      "loss": 2.1036,
      "step": 739
    },
    {
      "epoch": 0.04053239853206989,
      "grad_norm": 3.7914624214172363,
      "learning_rate": 0.00019991699082311243,
      "loss": 1.7363,
      "step": 740
    },
    {
      "epoch": 0.04058717204359971,
      "grad_norm": 3.071640968322754,
      "learning_rate": 0.00019991675799246877,
      "loss": 1.8911,
      "step": 741
    },
    {
      "epoch": 0.04064194555512954,
      "grad_norm": 1.7824753522872925,
      "learning_rate": 0.00019991652516182512,
      "loss": 0.86,
      "step": 742
    },
    {
      "epoch": 0.040696719066659365,
      "grad_norm": 3.295123815536499,
      "learning_rate": 0.00019991629233118147,
      "loss": 1.7853,
      "step": 743
    },
    {
      "epoch": 0.040751492578189184,
      "grad_norm": 2.3705248832702637,
      "learning_rate": 0.00019991604494862258,
      "loss": 1.4052,
      "step": 744
    },
    {
      "epoch": 0.04080626608971901,
      "grad_norm": 3.615321636199951,
      "learning_rate": 0.00019991582666989416,
      "loss": 1.6131,
      "step": 745
    },
    {
      "epoch": 0.04086103960124884,
      "grad_norm": 2.4579885005950928,
      "learning_rate": 0.00019991557928733528,
      "loss": 1.0758,
      "step": 746
    },
    {
      "epoch": 0.040915813112778664,
      "grad_norm": 2.2303617000579834,
      "learning_rate": 0.00019991534645669162,
      "loss": 1.3348,
      "step": 747
    },
    {
      "epoch": 0.04097058662430848,
      "grad_norm": 2.5846755504608154,
      "learning_rate": 0.00019991509907413274,
      "loss": 1.1839,
      "step": 748
    },
    {
      "epoch": 0.04102536013583831,
      "grad_norm": 3.072831630706787,
      "learning_rate": 0.0001999148662434891,
      "loss": 1.3771,
      "step": 749
    },
    {
      "epoch": 0.041080133647368136,
      "grad_norm": 5.604996681213379,
      "learning_rate": 0.00019991464796476066,
      "loss": 2.2407,
      "step": 750
    },
    {
      "epoch": 0.041134907158897956,
      "grad_norm": 5.320943355560303,
      "learning_rate": 0.00019991440058220178,
      "loss": 3.1362,
      "step": 751
    },
    {
      "epoch": 0.04118968067042778,
      "grad_norm": 6.932474613189697,
      "learning_rate": 0.00019991416775155813,
      "loss": 2.7975,
      "step": 752
    },
    {
      "epoch": 0.04124445418195761,
      "grad_norm": 5.458995819091797,
      "learning_rate": 0.00019991392036899924,
      "loss": 2.8255,
      "step": 753
    },
    {
      "epoch": 0.04129922769348743,
      "grad_norm": 4.136767387390137,
      "learning_rate": 0.0001999136875383556,
      "loss": 1.5934,
      "step": 754
    },
    {
      "epoch": 0.041354001205017255,
      "grad_norm": 3.1819519996643066,
      "learning_rate": 0.00019991345470771194,
      "loss": 1.9382,
      "step": 755
    },
    {
      "epoch": 0.04140877471654708,
      "grad_norm": 4.666064262390137,
      "learning_rate": 0.00019991320732515305,
      "loss": 1.8055,
      "step": 756
    },
    {
      "epoch": 0.0414635482280769,
      "grad_norm": 1.8068761825561523,
      "learning_rate": 0.0001999129744945094,
      "loss": 1.1226,
      "step": 757
    },
    {
      "epoch": 0.04151832173960673,
      "grad_norm": 7.238759994506836,
      "learning_rate": 0.00019991272711195052,
      "loss": 1.4538,
      "step": 758
    },
    {
      "epoch": 0.04157309525113655,
      "grad_norm": 1.9586671590805054,
      "learning_rate": 0.00019991247972939163,
      "loss": 1.145,
      "step": 759
    },
    {
      "epoch": 0.04162786876266637,
      "grad_norm": 2.4283549785614014,
      "learning_rate": 0.00019991224689874798,
      "loss": 1.5714,
      "step": 760
    },
    {
      "epoch": 0.0416826422741962,
      "grad_norm": 2.9736433029174805,
      "learning_rate": 0.0001999119995161891,
      "loss": 1.5477,
      "step": 761
    },
    {
      "epoch": 0.041737415785726026,
      "grad_norm": 5.909196853637695,
      "learning_rate": 0.00019991176668554544,
      "loss": 1.7703,
      "step": 762
    },
    {
      "epoch": 0.041792189297255845,
      "grad_norm": 4.073479175567627,
      "learning_rate": 0.0001999115338549018,
      "loss": 2.0348,
      "step": 763
    },
    {
      "epoch": 0.04184696280878567,
      "grad_norm": 3.431818962097168,
      "learning_rate": 0.0001999112864723429,
      "loss": 1.8012,
      "step": 764
    },
    {
      "epoch": 0.0419017363203155,
      "grad_norm": 23.87184715270996,
      "learning_rate": 0.00019991103908978403,
      "loss": 2.2954,
      "step": 765
    },
    {
      "epoch": 0.04195650983184532,
      "grad_norm": 6.128746509552002,
      "learning_rate": 0.00019991080625914037,
      "loss": 0.854,
      "step": 766
    },
    {
      "epoch": 0.042011283343375144,
      "grad_norm": 4.787575721740723,
      "learning_rate": 0.0001999105588765815,
      "loss": 2.5957,
      "step": 767
    },
    {
      "epoch": 0.04206605685490497,
      "grad_norm": 26.95694923400879,
      "learning_rate": 0.0001999103114940226,
      "loss": 4.5234,
      "step": 768
    },
    {
      "epoch": 0.04212083036643479,
      "grad_norm": 3.125880718231201,
      "learning_rate": 0.00019991007866337895,
      "loss": 1.4568,
      "step": 769
    },
    {
      "epoch": 0.04217560387796462,
      "grad_norm": 2.4120023250579834,
      "learning_rate": 0.00019990983128082007,
      "loss": 1.054,
      "step": 770
    },
    {
      "epoch": 0.04223037738949444,
      "grad_norm": 2.3234496116638184,
      "learning_rate": 0.0001999095838982612,
      "loss": 1.5045,
      "step": 771
    },
    {
      "epoch": 0.04228515090102426,
      "grad_norm": 3.073195695877075,
      "learning_rate": 0.0001999093365157023,
      "loss": 0.6096,
      "step": 772
    },
    {
      "epoch": 0.04233992441255409,
      "grad_norm": 2.1723878383636475,
      "learning_rate": 0.00019990910368505865,
      "loss": 1.8067,
      "step": 773
    },
    {
      "epoch": 0.042394697924083916,
      "grad_norm": 6.666521072387695,
      "learning_rate": 0.00019990884175058454,
      "loss": 1.4498,
      "step": 774
    },
    {
      "epoch": 0.042449471435613735,
      "grad_norm": 3.237586259841919,
      "learning_rate": 0.0001999086089199409,
      "loss": 1.8426,
      "step": 775
    },
    {
      "epoch": 0.04250424494714356,
      "grad_norm": 2.01762318611145,
      "learning_rate": 0.000199908361537382,
      "loss": 1.2749,
      "step": 776
    },
    {
      "epoch": 0.04255901845867339,
      "grad_norm": 6.003203392028809,
      "learning_rate": 0.00019990811415482312,
      "loss": 3.0663,
      "step": 777
    },
    {
      "epoch": 0.04261379197020321,
      "grad_norm": 4.959639072418213,
      "learning_rate": 0.00019990786677226424,
      "loss": 2.434,
      "step": 778
    },
    {
      "epoch": 0.042668565481733034,
      "grad_norm": 5.995190143585205,
      "learning_rate": 0.00019990761938970536,
      "loss": 2.0121,
      "step": 779
    },
    {
      "epoch": 0.04272333899326286,
      "grad_norm": 2.567612409591675,
      "learning_rate": 0.0001999073865590617,
      "loss": 1.668,
      "step": 780
    },
    {
      "epoch": 0.04277811250479268,
      "grad_norm": 26.090251922607422,
      "learning_rate": 0.0001999071246245876,
      "loss": 3.181,
      "step": 781
    },
    {
      "epoch": 0.042832886016322506,
      "grad_norm": 2.011209487915039,
      "learning_rate": 0.0001999068772420287,
      "loss": 1.3108,
      "step": 782
    },
    {
      "epoch": 0.04288765952785233,
      "grad_norm": 4.16195821762085,
      "learning_rate": 0.00019990662985946983,
      "loss": 1.712,
      "step": 783
    },
    {
      "epoch": 0.04294243303938215,
      "grad_norm": 7.45143461227417,
      "learning_rate": 0.00019990638247691095,
      "loss": 2.0569,
      "step": 784
    },
    {
      "epoch": 0.04299720655091198,
      "grad_norm": 6.768797397613525,
      "learning_rate": 0.00019990613509435207,
      "loss": 1.3159,
      "step": 785
    },
    {
      "epoch": 0.043051980062441805,
      "grad_norm": 2.942767858505249,
      "learning_rate": 0.00019990588771179318,
      "loss": 1.7175,
      "step": 786
    },
    {
      "epoch": 0.043106753573971625,
      "grad_norm": 2.8617501258850098,
      "learning_rate": 0.0001999056403292343,
      "loss": 1.5159,
      "step": 787
    },
    {
      "epoch": 0.04316152708550145,
      "grad_norm": 2.0887410640716553,
      "learning_rate": 0.00019990539294667542,
      "loss": 1.4672,
      "step": 788
    },
    {
      "epoch": 0.04321630059703128,
      "grad_norm": 3.948923349380493,
      "learning_rate": 0.00019990514556411654,
      "loss": 1.5657,
      "step": 789
    },
    {
      "epoch": 0.0432710741085611,
      "grad_norm": 2.1342947483062744,
      "learning_rate": 0.00019990488362964243,
      "loss": 1.4763,
      "step": 790
    },
    {
      "epoch": 0.043325847620090924,
      "grad_norm": 2.8393874168395996,
      "learning_rate": 0.00019990463624708354,
      "loss": 1.7042,
      "step": 791
    },
    {
      "epoch": 0.04338062113162075,
      "grad_norm": 2.8560547828674316,
      "learning_rate": 0.00019990438886452466,
      "loss": 1.5841,
      "step": 792
    },
    {
      "epoch": 0.04343539464315057,
      "grad_norm": 3.9475908279418945,
      "learning_rate": 0.00019990414148196578,
      "loss": 1.2508,
      "step": 793
    },
    {
      "epoch": 0.043490168154680396,
      "grad_norm": 3.7046589851379395,
      "learning_rate": 0.0001999038940994069,
      "loss": 1.7096,
      "step": 794
    },
    {
      "epoch": 0.04354494166621022,
      "grad_norm": 5.436389446258545,
      "learning_rate": 0.0001999036321649328,
      "loss": 0.9829,
      "step": 795
    },
    {
      "epoch": 0.04359971517774004,
      "grad_norm": 3.943171977996826,
      "learning_rate": 0.0001999033847823739,
      "loss": 0.9963,
      "step": 796
    },
    {
      "epoch": 0.04365448868926987,
      "grad_norm": 2.0854833126068115,
      "learning_rate": 0.0001999031228478998,
      "loss": 1.5932,
      "step": 797
    },
    {
      "epoch": 0.043709262200799695,
      "grad_norm": 3.595808506011963,
      "learning_rate": 0.0001999028754653409,
      "loss": 1.2991,
      "step": 798
    },
    {
      "epoch": 0.043764035712329515,
      "grad_norm": 7.151854515075684,
      "learning_rate": 0.00019990262808278203,
      "loss": 2.0197,
      "step": 799
    },
    {
      "epoch": 0.04381880922385934,
      "grad_norm": 5.620245933532715,
      "learning_rate": 0.00019990238070022315,
      "loss": 1.645,
      "step": 800
    },
    {
      "epoch": 0.04381880922385934,
      "eval_loss": 1.5223790407180786,
      "eval_runtime": 45.7963,
      "eval_samples_per_second": 2.009,
      "eval_steps_per_second": 2.009,
      "step": 800
    },
    {
      "epoch": 0.04387358273538917,
      "grad_norm": 2.881911277770996,
      "learning_rate": 0.00019990211876574904,
      "loss": 1.3091,
      "step": 801
    },
    {
      "epoch": 0.04392835624691899,
      "grad_norm": 19.980520248413086,
      "learning_rate": 0.00019990185683127493,
      "loss": 2.7798,
      "step": 802
    },
    {
      "epoch": 0.04398312975844881,
      "grad_norm": 2.100637674331665,
      "learning_rate": 0.00019990160944871604,
      "loss": 1.1725,
      "step": 803
    },
    {
      "epoch": 0.04403790326997864,
      "grad_norm": 3.3756346702575684,
      "learning_rate": 0.00019990134751424193,
      "loss": 1.6722,
      "step": 804
    },
    {
      "epoch": 0.04409267678150846,
      "grad_norm": 5.341908931732178,
      "learning_rate": 0.00019990110013168305,
      "loss": 1.6811,
      "step": 805
    },
    {
      "epoch": 0.044147450293038286,
      "grad_norm": 2.4228878021240234,
      "learning_rate": 0.00019990085274912417,
      "loss": 1.3853,
      "step": 806
    },
    {
      "epoch": 0.04420222380456811,
      "grad_norm": 2.839414596557617,
      "learning_rate": 0.00019990059081465006,
      "loss": 1.8256,
      "step": 807
    },
    {
      "epoch": 0.04425699731609793,
      "grad_norm": 2.5532171726226807,
      "learning_rate": 0.00019990032888017595,
      "loss": 1.4176,
      "step": 808
    },
    {
      "epoch": 0.04431177082762776,
      "grad_norm": 6.836004257202148,
      "learning_rate": 0.00019990006694570184,
      "loss": 1.4669,
      "step": 809
    },
    {
      "epoch": 0.044366544339157585,
      "grad_norm": 6.076110363006592,
      "learning_rate": 0.00019989981956314296,
      "loss": 1.5265,
      "step": 810
    },
    {
      "epoch": 0.044421317850687404,
      "grad_norm": 4.344412803649902,
      "learning_rate": 0.00019989955762866884,
      "loss": 1.982,
      "step": 811
    },
    {
      "epoch": 0.04447609136221723,
      "grad_norm": 3.505463123321533,
      "learning_rate": 0.00019989931024610996,
      "loss": 1.448,
      "step": 812
    },
    {
      "epoch": 0.04453086487374706,
      "grad_norm": 4.983546257019043,
      "learning_rate": 0.00019989904831163585,
      "loss": 0.755,
      "step": 813
    },
    {
      "epoch": 0.04458563838527688,
      "grad_norm": 2.158612012863159,
      "learning_rate": 0.00019989878637716174,
      "loss": 1.324,
      "step": 814
    },
    {
      "epoch": 0.0446404118968067,
      "grad_norm": 2.8137784004211426,
      "learning_rate": 0.00019989853899460286,
      "loss": 0.7969,
      "step": 815
    },
    {
      "epoch": 0.04469518540833653,
      "grad_norm": 4.856146335601807,
      "learning_rate": 0.00019989827706012875,
      "loss": 1.8819,
      "step": 816
    },
    {
      "epoch": 0.044749958919866356,
      "grad_norm": 5.219011306762695,
      "learning_rate": 0.00019989801512565464,
      "loss": 1.8336,
      "step": 817
    },
    {
      "epoch": 0.044804732431396176,
      "grad_norm": 1.9362643957138062,
      "learning_rate": 0.00019989775319118053,
      "loss": 0.7581,
      "step": 818
    },
    {
      "epoch": 0.044859505942926,
      "grad_norm": 3.125628709793091,
      "learning_rate": 0.00019989750580862164,
      "loss": 1.3014,
      "step": 819
    },
    {
      "epoch": 0.04491427945445583,
      "grad_norm": 2.1531171798706055,
      "learning_rate": 0.0001998972293222323,
      "loss": 1.5964,
      "step": 820
    },
    {
      "epoch": 0.04496905296598565,
      "grad_norm": 1.79838228225708,
      "learning_rate": 0.0001998969673877582,
      "loss": 0.8523,
      "step": 821
    },
    {
      "epoch": 0.045023826477515475,
      "grad_norm": 17.19166374206543,
      "learning_rate": 0.00019989670545328408,
      "loss": 4.1484,
      "step": 822
    },
    {
      "epoch": 0.0450785999890453,
      "grad_norm": 3.7939414978027344,
      "learning_rate": 0.00019989644351880997,
      "loss": 0.9818,
      "step": 823
    },
    {
      "epoch": 0.04513337350057512,
      "grad_norm": 7.0855937004089355,
      "learning_rate": 0.00019989618158433586,
      "loss": 1.4815,
      "step": 824
    },
    {
      "epoch": 0.04518814701210495,
      "grad_norm": 3.2853240966796875,
      "learning_rate": 0.00019989591964986175,
      "loss": 1.4265,
      "step": 825
    },
    {
      "epoch": 0.04524292052363477,
      "grad_norm": 4.521949768066406,
      "learning_rate": 0.00019989565771538764,
      "loss": 2.5335,
      "step": 826
    },
    {
      "epoch": 0.04529769403516459,
      "grad_norm": 2.6979081630706787,
      "learning_rate": 0.00019989539578091353,
      "loss": 1.1061,
      "step": 827
    },
    {
      "epoch": 0.04535246754669442,
      "grad_norm": 4.191196441650391,
      "learning_rate": 0.00019989513384643942,
      "loss": 1.9117,
      "step": 828
    },
    {
      "epoch": 0.045407241058224246,
      "grad_norm": 4.036169528961182,
      "learning_rate": 0.0001998948719119653,
      "loss": 1.4741,
      "step": 829
    },
    {
      "epoch": 0.045462014569754065,
      "grad_norm": 7.5417680740356445,
      "learning_rate": 0.0001998946099774912,
      "loss": 3.271,
      "step": 830
    },
    {
      "epoch": 0.04551678808128389,
      "grad_norm": 8.979975700378418,
      "learning_rate": 0.0001998943480430171,
      "loss": 2.0002,
      "step": 831
    },
    {
      "epoch": 0.04557156159281372,
      "grad_norm": 4.824958801269531,
      "learning_rate": 0.00019989408610854298,
      "loss": 2.4304,
      "step": 832
    },
    {
      "epoch": 0.04562633510434354,
      "grad_norm": 8.319833755493164,
      "learning_rate": 0.00019989382417406887,
      "loss": 1.1293,
      "step": 833
    },
    {
      "epoch": 0.045681108615873364,
      "grad_norm": 2.590785503387451,
      "learning_rate": 0.00019989356223959476,
      "loss": 1.6703,
      "step": 834
    },
    {
      "epoch": 0.04573588212740319,
      "grad_norm": 2.9310731887817383,
      "learning_rate": 0.00019989328575320542,
      "loss": 1.1609,
      "step": 835
    },
    {
      "epoch": 0.04579065563893301,
      "grad_norm": 2.959238052368164,
      "learning_rate": 0.0001998930238187313,
      "loss": 1.5473,
      "step": 836
    },
    {
      "epoch": 0.04584542915046284,
      "grad_norm": 4.477295398712158,
      "learning_rate": 0.0001998927618842572,
      "loss": 1.8152,
      "step": 837
    },
    {
      "epoch": 0.04590020266199266,
      "grad_norm": 1.9720697402954102,
      "learning_rate": 0.0001998924999497831,
      "loss": 1.3062,
      "step": 838
    },
    {
      "epoch": 0.04595497617352248,
      "grad_norm": 2.3523526191711426,
      "learning_rate": 0.00019989222346339375,
      "loss": 1.6815,
      "step": 839
    },
    {
      "epoch": 0.04600974968505231,
      "grad_norm": 3.904212713241577,
      "learning_rate": 0.00019989196152891964,
      "loss": 0.4859,
      "step": 840
    },
    {
      "epoch": 0.046064523196582136,
      "grad_norm": 2.9702157974243164,
      "learning_rate": 0.00019989169959444553,
      "loss": 1.1396,
      "step": 841
    },
    {
      "epoch": 0.046119296708111955,
      "grad_norm": 5.488214015960693,
      "learning_rate": 0.00019989143765997142,
      "loss": 2.9286,
      "step": 842
    },
    {
      "epoch": 0.04617407021964178,
      "grad_norm": 4.33150053024292,
      "learning_rate": 0.0001998911757254973,
      "loss": 1.2329,
      "step": 843
    },
    {
      "epoch": 0.04622884373117161,
      "grad_norm": 2.924995183944702,
      "learning_rate": 0.00019989089923910797,
      "loss": 1.6893,
      "step": 844
    },
    {
      "epoch": 0.04628361724270143,
      "grad_norm": 2.3616514205932617,
      "learning_rate": 0.00019989063730463386,
      "loss": 1.3287,
      "step": 845
    },
    {
      "epoch": 0.046338390754231254,
      "grad_norm": 10.80899715423584,
      "learning_rate": 0.00019989036081824452,
      "loss": 2.4968,
      "step": 846
    },
    {
      "epoch": 0.04639316426576108,
      "grad_norm": 2.3218982219696045,
      "learning_rate": 0.0001998900988837704,
      "loss": 1.2017,
      "step": 847
    },
    {
      "epoch": 0.0464479377772909,
      "grad_norm": 3.2090072631835938,
      "learning_rate": 0.00019988982239738107,
      "loss": 1.1744,
      "step": 848
    },
    {
      "epoch": 0.046502711288820726,
      "grad_norm": 8.053661346435547,
      "learning_rate": 0.00019988954591099173,
      "loss": 1.7894,
      "step": 849
    },
    {
      "epoch": 0.04655748480035055,
      "grad_norm": 2.5731208324432373,
      "learning_rate": 0.00019988928397651762,
      "loss": 1.6167,
      "step": 850
    },
    {
      "epoch": 0.04661225831188037,
      "grad_norm": 2.367985486984253,
      "learning_rate": 0.00019988900749012828,
      "loss": 1.3716,
      "step": 851
    },
    {
      "epoch": 0.0466670318234102,
      "grad_norm": 3.9112253189086914,
      "learning_rate": 0.00019988874555565417,
      "loss": 0.4074,
      "step": 852
    },
    {
      "epoch": 0.046721805334940025,
      "grad_norm": 3.3098368644714355,
      "learning_rate": 0.00019988846906926483,
      "loss": 1.5081,
      "step": 853
    },
    {
      "epoch": 0.046776578846469845,
      "grad_norm": 3.036428451538086,
      "learning_rate": 0.00019988820713479072,
      "loss": 1.6575,
      "step": 854
    },
    {
      "epoch": 0.04683135235799967,
      "grad_norm": 18.394636154174805,
      "learning_rate": 0.00019988793064840138,
      "loss": 2.1641,
      "step": 855
    },
    {
      "epoch": 0.0468861258695295,
      "grad_norm": 2.849440336227417,
      "learning_rate": 0.00019988765416201204,
      "loss": 1.3375,
      "step": 856
    },
    {
      "epoch": 0.04694089938105932,
      "grad_norm": 6.109793186187744,
      "learning_rate": 0.00019988739222753793,
      "loss": 1.7391,
      "step": 857
    },
    {
      "epoch": 0.046995672892589144,
      "grad_norm": 3.8669593334198,
      "learning_rate": 0.0001998871157411486,
      "loss": 0.6934,
      "step": 858
    },
    {
      "epoch": 0.04705044640411897,
      "grad_norm": 5.794949531555176,
      "learning_rate": 0.00019988683925475925,
      "loss": 2.4485,
      "step": 859
    },
    {
      "epoch": 0.04710521991564879,
      "grad_norm": 4.190285682678223,
      "learning_rate": 0.0001998865627683699,
      "loss": 1.4703,
      "step": 860
    },
    {
      "epoch": 0.047159993427178616,
      "grad_norm": 4.122284889221191,
      "learning_rate": 0.00019988628628198057,
      "loss": 1.7271,
      "step": 861
    },
    {
      "epoch": 0.04721476693870844,
      "grad_norm": 2.71099591255188,
      "learning_rate": 0.00019988602434750646,
      "loss": 1.2421,
      "step": 862
    },
    {
      "epoch": 0.04726954045023826,
      "grad_norm": 2.5013809204101562,
      "learning_rate": 0.00019988574786111712,
      "loss": 1.3689,
      "step": 863
    },
    {
      "epoch": 0.04732431396176809,
      "grad_norm": 2.2138819694519043,
      "learning_rate": 0.00019988547137472779,
      "loss": 1.3296,
      "step": 864
    },
    {
      "epoch": 0.047379087473297915,
      "grad_norm": 6.625699043273926,
      "learning_rate": 0.00019988519488833845,
      "loss": 1.7345,
      "step": 865
    },
    {
      "epoch": 0.047433860984827735,
      "grad_norm": 5.073902130126953,
      "learning_rate": 0.0001998849184019491,
      "loss": 0.7873,
      "step": 866
    },
    {
      "epoch": 0.04748863449635756,
      "grad_norm": 2.514251470565796,
      "learning_rate": 0.00019988464191555977,
      "loss": 1.5594,
      "step": 867
    },
    {
      "epoch": 0.04754340800788739,
      "grad_norm": 4.05952787399292,
      "learning_rate": 0.00019988437998108566,
      "loss": 2.0164,
      "step": 868
    },
    {
      "epoch": 0.04759818151941721,
      "grad_norm": 6.746005535125732,
      "learning_rate": 0.00019988410349469632,
      "loss": 0.6855,
      "step": 869
    },
    {
      "epoch": 0.04765295503094703,
      "grad_norm": 2.1179358959198,
      "learning_rate": 0.00019988381245639175,
      "loss": 1.1086,
      "step": 870
    },
    {
      "epoch": 0.04770772854247686,
      "grad_norm": 9.643244743347168,
      "learning_rate": 0.0001998835359700024,
      "loss": 1.6732,
      "step": 871
    },
    {
      "epoch": 0.04776250205400668,
      "grad_norm": 5.071493625640869,
      "learning_rate": 0.00019988325948361307,
      "loss": 1.6702,
      "step": 872
    },
    {
      "epoch": 0.047817275565536506,
      "grad_norm": 3.539566993713379,
      "learning_rate": 0.00019988299754913896,
      "loss": 1.0968,
      "step": 873
    },
    {
      "epoch": 0.04787204907706633,
      "grad_norm": 5.023833751678467,
      "learning_rate": 0.0001998827065108344,
      "loss": 1.7122,
      "step": 874
    },
    {
      "epoch": 0.04792682258859615,
      "grad_norm": 3.3158161640167236,
      "learning_rate": 0.00019988243002444506,
      "loss": 1.4016,
      "step": 875
    },
    {
      "epoch": 0.04798159610012598,
      "grad_norm": 2.7828142642974854,
      "learning_rate": 0.00019988215353805572,
      "loss": 1.4596,
      "step": 876
    },
    {
      "epoch": 0.048036369611655805,
      "grad_norm": 2.747831106185913,
      "learning_rate": 0.00019988187705166638,
      "loss": 1.5123,
      "step": 877
    },
    {
      "epoch": 0.048091143123185624,
      "grad_norm": 4.536540508270264,
      "learning_rate": 0.00019988160056527704,
      "loss": 2.16,
      "step": 878
    },
    {
      "epoch": 0.04814591663471545,
      "grad_norm": 4.6713409423828125,
      "learning_rate": 0.00019988130952697247,
      "loss": 1.4124,
      "step": 879
    },
    {
      "epoch": 0.04820069014624528,
      "grad_norm": 7.708503246307373,
      "learning_rate": 0.00019988103304058313,
      "loss": 2.1105,
      "step": 880
    },
    {
      "epoch": 0.0482554636577751,
      "grad_norm": 3.5326731204986572,
      "learning_rate": 0.0001998807565541938,
      "loss": 0.7135,
      "step": 881
    },
    {
      "epoch": 0.04831023716930492,
      "grad_norm": 2.760098457336426,
      "learning_rate": 0.00019988048006780446,
      "loss": 1.5075,
      "step": 882
    },
    {
      "epoch": 0.04836501068083475,
      "grad_norm": 2.1063220500946045,
      "learning_rate": 0.0001998801890294999,
      "loss": 1.3162,
      "step": 883
    },
    {
      "epoch": 0.04841978419236457,
      "grad_norm": 4.5819091796875,
      "learning_rate": 0.00019987991254311055,
      "loss": 1.8532,
      "step": 884
    },
    {
      "epoch": 0.048474557703894396,
      "grad_norm": 4.830545425415039,
      "learning_rate": 0.0001998796360567212,
      "loss": 1.4878,
      "step": 885
    },
    {
      "epoch": 0.04852933121542422,
      "grad_norm": 3.136568546295166,
      "learning_rate": 0.00019987935957033187,
      "loss": 1.3367,
      "step": 886
    },
    {
      "epoch": 0.04858410472695404,
      "grad_norm": 4.153894424438477,
      "learning_rate": 0.0001998790685320273,
      "loss": 0.8104,
      "step": 887
    },
    {
      "epoch": 0.04863887823848387,
      "grad_norm": 8.66752815246582,
      "learning_rate": 0.00019987877749372274,
      "loss": 2.4269,
      "step": 888
    },
    {
      "epoch": 0.048693651750013695,
      "grad_norm": 3.9201767444610596,
      "learning_rate": 0.00019987851555924863,
      "loss": 1.3197,
      "step": 889
    },
    {
      "epoch": 0.04874842526154352,
      "grad_norm": 12.566381454467773,
      "learning_rate": 0.00019987822452094406,
      "loss": 3.139,
      "step": 890
    },
    {
      "epoch": 0.04880319877307334,
      "grad_norm": 5.035951137542725,
      "learning_rate": 0.0001998779334826395,
      "loss": 0.7635,
      "step": 891
    },
    {
      "epoch": 0.04885797228460317,
      "grad_norm": 8.520139694213867,
      "learning_rate": 0.00019987765699625015,
      "loss": 2.2123,
      "step": 892
    },
    {
      "epoch": 0.04891274579613299,
      "grad_norm": 3.627441883087158,
      "learning_rate": 0.00019987738050986081,
      "loss": 1.1802,
      "step": 893
    },
    {
      "epoch": 0.04896751930766281,
      "grad_norm": 2.428539276123047,
      "learning_rate": 0.00019987708947155625,
      "loss": 0.7227,
      "step": 894
    },
    {
      "epoch": 0.04902229281919264,
      "grad_norm": 3.2855470180511475,
      "learning_rate": 0.00019987679843325168,
      "loss": 1.3774,
      "step": 895
    },
    {
      "epoch": 0.049077066330722466,
      "grad_norm": 2.169501781463623,
      "learning_rate": 0.00019987652194686234,
      "loss": 1.6416,
      "step": 896
    },
    {
      "epoch": 0.049131839842252285,
      "grad_norm": 4.948390007019043,
      "learning_rate": 0.00019987623090855777,
      "loss": 1.2127,
      "step": 897
    },
    {
      "epoch": 0.04918661335378211,
      "grad_norm": 10.759867668151855,
      "learning_rate": 0.0001998759398702532,
      "loss": 2.2877,
      "step": 898
    },
    {
      "epoch": 0.04924138686531194,
      "grad_norm": 1.948150873184204,
      "learning_rate": 0.00019987566338386387,
      "loss": 1.1571,
      "step": 899
    },
    {
      "epoch": 0.04929616037684176,
      "grad_norm": 6.397727966308594,
      "learning_rate": 0.0001998753723455593,
      "loss": 1.4191,
      "step": 900
    },
    {
      "epoch": 0.04929616037684176,
      "eval_loss": 1.5006483793258667,
      "eval_runtime": 45.8094,
      "eval_samples_per_second": 2.008,
      "eval_steps_per_second": 2.008,
      "step": 900
    },
    {
      "epoch": 0.049350933888371584,
      "grad_norm": 2.131800413131714,
      "learning_rate": 0.00019987508130725473,
      "loss": 1.6017,
      "step": 901
    },
    {
      "epoch": 0.04940570739990141,
      "grad_norm": 2.794480562210083,
      "learning_rate": 0.0001998748048208654,
      "loss": 1.7215,
      "step": 902
    },
    {
      "epoch": 0.04946048091143123,
      "grad_norm": 4.604470729827881,
      "learning_rate": 0.00019987451378256083,
      "loss": 2.1056,
      "step": 903
    },
    {
      "epoch": 0.04951525442296106,
      "grad_norm": 5.471393585205078,
      "learning_rate": 0.00019987422274425626,
      "loss": 1.7783,
      "step": 904
    },
    {
      "epoch": 0.04957002793449088,
      "grad_norm": 3.9499096870422363,
      "learning_rate": 0.00019987394625786692,
      "loss": 1.4015,
      "step": 905
    },
    {
      "epoch": 0.0496248014460207,
      "grad_norm": 4.5135369300842285,
      "learning_rate": 0.00019987364066764712,
      "loss": 1.7104,
      "step": 906
    },
    {
      "epoch": 0.04967957495755053,
      "grad_norm": 2.662191867828369,
      "learning_rate": 0.00019987336418125778,
      "loss": 1.7559,
      "step": 907
    },
    {
      "epoch": 0.049734348469080356,
      "grad_norm": 6.606955528259277,
      "learning_rate": 0.00019987307314295322,
      "loss": 2.2062,
      "step": 908
    },
    {
      "epoch": 0.049789121980610175,
      "grad_norm": 2.5226712226867676,
      "learning_rate": 0.00019987278210464865,
      "loss": 1.3267,
      "step": 909
    },
    {
      "epoch": 0.04984389549214,
      "grad_norm": 4.274563789367676,
      "learning_rate": 0.00019987249106634408,
      "loss": 1.2643,
      "step": 910
    },
    {
      "epoch": 0.04989866900366983,
      "grad_norm": 2.5601933002471924,
      "learning_rate": 0.00019987220002803952,
      "loss": 1.3287,
      "step": 911
    },
    {
      "epoch": 0.04995344251519965,
      "grad_norm": 3.0377278327941895,
      "learning_rate": 0.00019987192354165018,
      "loss": 1.6967,
      "step": 912
    },
    {
      "epoch": 0.050008216026729474,
      "grad_norm": 3.887397050857544,
      "learning_rate": 0.00019987161795143038,
      "loss": 1.3629,
      "step": 913
    },
    {
      "epoch": 0.0500629895382593,
      "grad_norm": 4.616495609283447,
      "learning_rate": 0.0001998713269131258,
      "loss": 2.2397,
      "step": 914
    },
    {
      "epoch": 0.05011776304978912,
      "grad_norm": 2.990123987197876,
      "learning_rate": 0.00019987103587482125,
      "loss": 0.8201,
      "step": 915
    },
    {
      "epoch": 0.050172536561318946,
      "grad_norm": 4.317672252655029,
      "learning_rate": 0.00019987074483651668,
      "loss": 1.015,
      "step": 916
    },
    {
      "epoch": 0.05022731007284877,
      "grad_norm": 6.333430767059326,
      "learning_rate": 0.00019987046835012734,
      "loss": 1.2311,
      "step": 917
    },
    {
      "epoch": 0.05028208358437859,
      "grad_norm": 2.6125752925872803,
      "learning_rate": 0.00019987016275990754,
      "loss": 1.2349,
      "step": 918
    },
    {
      "epoch": 0.05033685709590842,
      "grad_norm": 11.224117279052734,
      "learning_rate": 0.00019986987172160298,
      "loss": 1.9129,
      "step": 919
    },
    {
      "epoch": 0.050391630607438245,
      "grad_norm": 4.756463527679443,
      "learning_rate": 0.0001998695806832984,
      "loss": 1.4372,
      "step": 920
    },
    {
      "epoch": 0.050446404118968065,
      "grad_norm": 2.320573329925537,
      "learning_rate": 0.0001998692750930786,
      "loss": 1.6657,
      "step": 921
    },
    {
      "epoch": 0.05050117763049789,
      "grad_norm": 6.417954921722412,
      "learning_rate": 0.00019986899860668927,
      "loss": 1.5258,
      "step": 922
    },
    {
      "epoch": 0.05055595114202772,
      "grad_norm": 2.524817705154419,
      "learning_rate": 0.00019986869301646948,
      "loss": 1.3985,
      "step": 923
    },
    {
      "epoch": 0.05061072465355754,
      "grad_norm": 14.284415245056152,
      "learning_rate": 0.0001998684019781649,
      "loss": 2.8207,
      "step": 924
    },
    {
      "epoch": 0.050665498165087364,
      "grad_norm": 2.3908703327178955,
      "learning_rate": 0.00019986811093986034,
      "loss": 1.1871,
      "step": 925
    },
    {
      "epoch": 0.05072027167661719,
      "grad_norm": 2.883953332901001,
      "learning_rate": 0.00019986781990155578,
      "loss": 1.4919,
      "step": 926
    },
    {
      "epoch": 0.05077504518814701,
      "grad_norm": 8.701272010803223,
      "learning_rate": 0.00019986751431133598,
      "loss": 2.6059,
      "step": 927
    },
    {
      "epoch": 0.050829818699676836,
      "grad_norm": 8.932642936706543,
      "learning_rate": 0.00019986722327303141,
      "loss": 2.3144,
      "step": 928
    },
    {
      "epoch": 0.05088459221120666,
      "grad_norm": 2.858231782913208,
      "learning_rate": 0.00019986693223472685,
      "loss": 2.1098,
      "step": 929
    },
    {
      "epoch": 0.05093936572273648,
      "grad_norm": 3.3616323471069336,
      "learning_rate": 0.00019986664119642228,
      "loss": 1.6003,
      "step": 930
    },
    {
      "epoch": 0.05099413923426631,
      "grad_norm": 1.5610297918319702,
      "learning_rate": 0.00019986633560620248,
      "loss": 0.5579,
      "step": 931
    },
    {
      "epoch": 0.051048912745796135,
      "grad_norm": 1.9361895322799683,
      "learning_rate": 0.00019986604456789792,
      "loss": 0.921,
      "step": 932
    },
    {
      "epoch": 0.051103686257325955,
      "grad_norm": 1.858687400817871,
      "learning_rate": 0.00019986573897767812,
      "loss": 1.1535,
      "step": 933
    },
    {
      "epoch": 0.05115845976885578,
      "grad_norm": 2.0991852283477783,
      "learning_rate": 0.00019986544793937355,
      "loss": 1.2481,
      "step": 934
    },
    {
      "epoch": 0.05121323328038561,
      "grad_norm": 4.071154594421387,
      "learning_rate": 0.00019986514234915376,
      "loss": 0.9916,
      "step": 935
    },
    {
      "epoch": 0.05126800679191543,
      "grad_norm": 9.929917335510254,
      "learning_rate": 0.0001998648513108492,
      "loss": 2.4775,
      "step": 936
    },
    {
      "epoch": 0.05132278030344525,
      "grad_norm": 4.365743160247803,
      "learning_rate": 0.0001998645457206294,
      "loss": 0.8725,
      "step": 937
    },
    {
      "epoch": 0.05137755381497508,
      "grad_norm": 4.574920654296875,
      "learning_rate": 0.00019986425468232483,
      "loss": 1.8031,
      "step": 938
    },
    {
      "epoch": 0.0514323273265049,
      "grad_norm": 1.7376959323883057,
      "learning_rate": 0.00019986394909210503,
      "loss": 0.5866,
      "step": 939
    },
    {
      "epoch": 0.051487100838034726,
      "grad_norm": 2.413264036178589,
      "learning_rate": 0.00019986365805380046,
      "loss": 1.5339,
      "step": 940
    },
    {
      "epoch": 0.05154187434956455,
      "grad_norm": 4.839515686035156,
      "learning_rate": 0.00019986335246358067,
      "loss": 1.4348,
      "step": 941
    },
    {
      "epoch": 0.05159664786109437,
      "grad_norm": 3.33718204498291,
      "learning_rate": 0.0001998630614252761,
      "loss": 1.654,
      "step": 942
    },
    {
      "epoch": 0.0516514213726242,
      "grad_norm": 2.2684295177459717,
      "learning_rate": 0.0001998627558350563,
      "loss": 1.4905,
      "step": 943
    },
    {
      "epoch": 0.051706194884154025,
      "grad_norm": 4.460848808288574,
      "learning_rate": 0.0001998624502448365,
      "loss": 1.4463,
      "step": 944
    },
    {
      "epoch": 0.051760968395683844,
      "grad_norm": 2.6271071434020996,
      "learning_rate": 0.00019986215920653194,
      "loss": 1.0749,
      "step": 945
    },
    {
      "epoch": 0.05181574190721367,
      "grad_norm": 2.2784299850463867,
      "learning_rate": 0.00019986185361631215,
      "loss": 1.0147,
      "step": 946
    },
    {
      "epoch": 0.0518705154187435,
      "grad_norm": 3.7914721965789795,
      "learning_rate": 0.00019986154802609235,
      "loss": 1.679,
      "step": 947
    },
    {
      "epoch": 0.05192528893027332,
      "grad_norm": 2.5824697017669678,
      "learning_rate": 0.00019986124243587255,
      "loss": 1.2238,
      "step": 948
    },
    {
      "epoch": 0.05198006244180314,
      "grad_norm": 4.0160231590271,
      "learning_rate": 0.000199860951397568,
      "loss": 1.4138,
      "step": 949
    },
    {
      "epoch": 0.05203483595333297,
      "grad_norm": 5.599263668060303,
      "learning_rate": 0.0001998606458073482,
      "loss": 1.3471,
      "step": 950
    },
    {
      "epoch": 0.05208960946486279,
      "grad_norm": 2.5158355236053467,
      "learning_rate": 0.0001998603402171284,
      "loss": 0.9691,
      "step": 951
    },
    {
      "epoch": 0.052144382976392616,
      "grad_norm": 3.270940065383911,
      "learning_rate": 0.0001998600346269086,
      "loss": 1.3099,
      "step": 952
    },
    {
      "epoch": 0.05219915648792244,
      "grad_norm": 12.151966094970703,
      "learning_rate": 0.0001998597290366888,
      "loss": 3.0777,
      "step": 953
    },
    {
      "epoch": 0.05225392999945226,
      "grad_norm": 3.3343751430511475,
      "learning_rate": 0.000199859423446469,
      "loss": 0.2009,
      "step": 954
    },
    {
      "epoch": 0.05230870351098209,
      "grad_norm": 9.700345039367676,
      "learning_rate": 0.00019985913240816444,
      "loss": 1.1205,
      "step": 955
    },
    {
      "epoch": 0.052363477022511914,
      "grad_norm": 28.946340560913086,
      "learning_rate": 0.00019985881226602942,
      "loss": 3.5973,
      "step": 956
    },
    {
      "epoch": 0.052418250534041734,
      "grad_norm": 2.88745379447937,
      "learning_rate": 0.00019985852122772485,
      "loss": 1.3123,
      "step": 957
    },
    {
      "epoch": 0.05247302404557156,
      "grad_norm": 3.6593916416168213,
      "learning_rate": 0.00019985820108558983,
      "loss": 2.065,
      "step": 958
    },
    {
      "epoch": 0.05252779755710139,
      "grad_norm": 4.106207370758057,
      "learning_rate": 0.00019985789549537003,
      "loss": 1.8051,
      "step": 959
    },
    {
      "epoch": 0.05258257106863121,
      "grad_norm": 2.5467519760131836,
      "learning_rate": 0.00019985760445706546,
      "loss": 1.7369,
      "step": 960
    },
    {
      "epoch": 0.05263734458016103,
      "grad_norm": 6.04910135269165,
      "learning_rate": 0.00019985728431493044,
      "loss": 2.0872,
      "step": 961
    },
    {
      "epoch": 0.05269211809169086,
      "grad_norm": 7.665516376495361,
      "learning_rate": 0.00019985697872471064,
      "loss": 1.4299,
      "step": 962
    },
    {
      "epoch": 0.052746891603220686,
      "grad_norm": 2.4331014156341553,
      "learning_rate": 0.00019985668768640608,
      "loss": 0.6773,
      "step": 963
    },
    {
      "epoch": 0.052801665114750505,
      "grad_norm": 1.9538524150848389,
      "learning_rate": 0.00019985636754427105,
      "loss": 0.8632,
      "step": 964
    },
    {
      "epoch": 0.05285643862628033,
      "grad_norm": 2.6075265407562256,
      "learning_rate": 0.00019985606195405126,
      "loss": 1.2962,
      "step": 965
    },
    {
      "epoch": 0.05291121213781016,
      "grad_norm": 4.136146068572998,
      "learning_rate": 0.00019985575636383146,
      "loss": 1.4223,
      "step": 966
    },
    {
      "epoch": 0.05296598564933998,
      "grad_norm": 4.488940238952637,
      "learning_rate": 0.00019985543622169644,
      "loss": 1.8164,
      "step": 967
    },
    {
      "epoch": 0.053020759160869804,
      "grad_norm": 6.7578654289245605,
      "learning_rate": 0.00019985513063147664,
      "loss": 2.1701,
      "step": 968
    },
    {
      "epoch": 0.05307553267239963,
      "grad_norm": 4.949543476104736,
      "learning_rate": 0.00019985482504125684,
      "loss": 1.6733,
      "step": 969
    },
    {
      "epoch": 0.05313030618392945,
      "grad_norm": 2.4448459148406982,
      "learning_rate": 0.00019985450489912182,
      "loss": 1.649,
      "step": 970
    },
    {
      "epoch": 0.05318507969545928,
      "grad_norm": 2.0036685466766357,
      "learning_rate": 0.00019985421386081725,
      "loss": 0.7528,
      "step": 971
    },
    {
      "epoch": 0.0532398532069891,
      "grad_norm": 5.791175842285156,
      "learning_rate": 0.00019985390827059746,
      "loss": 1.7695,
      "step": 972
    },
    {
      "epoch": 0.05329462671851892,
      "grad_norm": 12.601698875427246,
      "learning_rate": 0.00019985358812846243,
      "loss": 2.9538,
      "step": 973
    },
    {
      "epoch": 0.05334940023004875,
      "grad_norm": 2.6858718395233154,
      "learning_rate": 0.0001998532679863274,
      "loss": 1.4144,
      "step": 974
    },
    {
      "epoch": 0.053404173741578576,
      "grad_norm": 2.6022539138793945,
      "learning_rate": 0.00019985296239610761,
      "loss": 1.2935,
      "step": 975
    },
    {
      "epoch": 0.053458947253108395,
      "grad_norm": 3.142796277999878,
      "learning_rate": 0.00019985265680588782,
      "loss": 1.7231,
      "step": 976
    },
    {
      "epoch": 0.05351372076463822,
      "grad_norm": 3.7918834686279297,
      "learning_rate": 0.0001998523366637528,
      "loss": 1.2474,
      "step": 977
    },
    {
      "epoch": 0.05356849427616805,
      "grad_norm": 2.0797007083892822,
      "learning_rate": 0.000199852031073533,
      "loss": 1.1566,
      "step": 978
    },
    {
      "epoch": 0.05362326778769787,
      "grad_norm": 3.4803242683410645,
      "learning_rate": 0.0001998517254833132,
      "loss": 1.7622,
      "step": 979
    },
    {
      "epoch": 0.053678041299227694,
      "grad_norm": 2.8092517852783203,
      "learning_rate": 0.00019985140534117818,
      "loss": 1.0689,
      "step": 980
    },
    {
      "epoch": 0.05373281481075752,
      "grad_norm": 2.2382652759552,
      "learning_rate": 0.00019985108519904315,
      "loss": 1.4057,
      "step": 981
    },
    {
      "epoch": 0.05378758832228734,
      "grad_norm": 7.932769298553467,
      "learning_rate": 0.00019985077960882336,
      "loss": 1.7337,
      "step": 982
    },
    {
      "epoch": 0.053842361833817166,
      "grad_norm": 8.121310234069824,
      "learning_rate": 0.00019985047401860356,
      "loss": 2.6,
      "step": 983
    },
    {
      "epoch": 0.05389713534534699,
      "grad_norm": 1.8821570873260498,
      "learning_rate": 0.00019985015387646854,
      "loss": 1.2218,
      "step": 984
    },
    {
      "epoch": 0.05395190885687681,
      "grad_norm": 2.67069149017334,
      "learning_rate": 0.00019984983373433352,
      "loss": 1.5537,
      "step": 985
    },
    {
      "epoch": 0.05400668236840664,
      "grad_norm": 4.353715896606445,
      "learning_rate": 0.00019984952814411372,
      "loss": 1.7398,
      "step": 986
    },
    {
      "epoch": 0.054061455879936465,
      "grad_norm": 1.154428243637085,
      "learning_rate": 0.0001998492080019787,
      "loss": 0.6542,
      "step": 987
    },
    {
      "epoch": 0.054116229391466285,
      "grad_norm": 4.610752105712891,
      "learning_rate": 0.0001998489024117589,
      "loss": 0.6904,
      "step": 988
    },
    {
      "epoch": 0.05417100290299611,
      "grad_norm": 4.157879829406738,
      "learning_rate": 0.00019984858226962388,
      "loss": 1.3718,
      "step": 989
    },
    {
      "epoch": 0.05422577641452594,
      "grad_norm": 20.927051544189453,
      "learning_rate": 0.00019984826212748885,
      "loss": 2.194,
      "step": 990
    },
    {
      "epoch": 0.05428054992605576,
      "grad_norm": 2.307434558868408,
      "learning_rate": 0.00019984794198535383,
      "loss": 1.6496,
      "step": 991
    },
    {
      "epoch": 0.054335323437585584,
      "grad_norm": 12.324235916137695,
      "learning_rate": 0.00019984763639513403,
      "loss": 1.6814,
      "step": 992
    },
    {
      "epoch": 0.05439009694911541,
      "grad_norm": 3.631117820739746,
      "learning_rate": 0.000199847316252999,
      "loss": 1.6312,
      "step": 993
    },
    {
      "epoch": 0.05444487046064523,
      "grad_norm": 12.558242797851562,
      "learning_rate": 0.00019984699611086398,
      "loss": 2.614,
      "step": 994
    },
    {
      "epoch": 0.054499643972175056,
      "grad_norm": 14.503931045532227,
      "learning_rate": 0.00019984667596872896,
      "loss": 3.928,
      "step": 995
    },
    {
      "epoch": 0.05455441748370488,
      "grad_norm": 4.537035942077637,
      "learning_rate": 0.00019984635582659394,
      "loss": 1.8025,
      "step": 996
    },
    {
      "epoch": 0.0546091909952347,
      "grad_norm": 3.605970859527588,
      "learning_rate": 0.00019984605023637414,
      "loss": 1.4318,
      "step": 997
    },
    {
      "epoch": 0.05466396450676453,
      "grad_norm": 2.8804948329925537,
      "learning_rate": 0.00019984573009423912,
      "loss": 1.3297,
      "step": 998
    },
    {
      "epoch": 0.054718738018294355,
      "grad_norm": 2.049692392349243,
      "learning_rate": 0.0001998454099521041,
      "loss": 1.1237,
      "step": 999
    },
    {
      "epoch": 0.054773511529824175,
      "grad_norm": 15.16750717163086,
      "learning_rate": 0.00019984507525805384,
      "loss": 1.7863,
      "step": 1000
    },
    {
      "epoch": 0.054773511529824175,
      "eval_loss": 1.50754714012146,
      "eval_runtime": 45.8273,
      "eval_samples_per_second": 2.008,
      "eval_steps_per_second": 2.008,
      "step": 1000
    },
    {
      "epoch": 0.054828285041354,
      "grad_norm": 6.057952404022217,
      "learning_rate": 0.00019984476966783404,
      "loss": 1.5828,
      "step": 1001
    },
    {
      "epoch": 0.05488305855288383,
      "grad_norm": 2.4424664974212646,
      "learning_rate": 0.00019984444952569902,
      "loss": 1.1082,
      "step": 1002
    },
    {
      "epoch": 0.05493783206441365,
      "grad_norm": 4.2152791023254395,
      "learning_rate": 0.000199844129383564,
      "loss": 1.7865,
      "step": 1003
    },
    {
      "epoch": 0.05499260557594347,
      "grad_norm": 6.5025506019592285,
      "learning_rate": 0.00019984380924142897,
      "loss": 0.9316,
      "step": 1004
    },
    {
      "epoch": 0.0550473790874733,
      "grad_norm": 4.0381879806518555,
      "learning_rate": 0.00019984348909929395,
      "loss": 1.3837,
      "step": 1005
    },
    {
      "epoch": 0.05510215259900312,
      "grad_norm": 4.296844005584717,
      "learning_rate": 0.00019984316895715892,
      "loss": 1.9026,
      "step": 1006
    },
    {
      "epoch": 0.055156926110532946,
      "grad_norm": 6.233590602874756,
      "learning_rate": 0.00019984283426310867,
      "loss": 2.0083,
      "step": 1007
    },
    {
      "epoch": 0.05521169962206277,
      "grad_norm": 2.338534355163574,
      "learning_rate": 0.00019984251412097365,
      "loss": 1.3708,
      "step": 1008
    },
    {
      "epoch": 0.05526647313359259,
      "grad_norm": 5.56455135345459,
      "learning_rate": 0.00019984219397883862,
      "loss": 1.5802,
      "step": 1009
    },
    {
      "epoch": 0.05532124664512242,
      "grad_norm": 14.208150863647461,
      "learning_rate": 0.0001998418738367036,
      "loss": 2.619,
      "step": 1010
    },
    {
      "epoch": 0.055376020156652245,
      "grad_norm": 3.4477884769439697,
      "learning_rate": 0.00019984155369456857,
      "loss": 1.4577,
      "step": 1011
    },
    {
      "epoch": 0.055430793668182064,
      "grad_norm": 2.3739163875579834,
      "learning_rate": 0.00019984123355243355,
      "loss": 1.6322,
      "step": 1012
    },
    {
      "epoch": 0.05548556717971189,
      "grad_norm": 8.73753547668457,
      "learning_rate": 0.00019984091341029853,
      "loss": 2.0648,
      "step": 1013
    },
    {
      "epoch": 0.05554034069124172,
      "grad_norm": 2.5227692127227783,
      "learning_rate": 0.0001998405932681635,
      "loss": 1.2335,
      "step": 1014
    },
    {
      "epoch": 0.05559511420277154,
      "grad_norm": 12.725528717041016,
      "learning_rate": 0.00019984025857411325,
      "loss": 3.3305,
      "step": 1015
    },
    {
      "epoch": 0.05564988771430136,
      "grad_norm": 5.5739426612854,
      "learning_rate": 0.00019983993843197823,
      "loss": 2.5046,
      "step": 1016
    },
    {
      "epoch": 0.05570466122583119,
      "grad_norm": 2.0886402130126953,
      "learning_rate": 0.00019983960373792797,
      "loss": 1.1264,
      "step": 1017
    },
    {
      "epoch": 0.05575943473736101,
      "grad_norm": 2.967329263687134,
      "learning_rate": 0.00019983928359579295,
      "loss": 1.4639,
      "step": 1018
    },
    {
      "epoch": 0.055814208248890836,
      "grad_norm": 2.317265033721924,
      "learning_rate": 0.0001998389489017427,
      "loss": 1.1928,
      "step": 1019
    },
    {
      "epoch": 0.05586898176042066,
      "grad_norm": 2.659088611602783,
      "learning_rate": 0.00019983862875960767,
      "loss": 1.4388,
      "step": 1020
    },
    {
      "epoch": 0.05592375527195048,
      "grad_norm": 4.855034828186035,
      "learning_rate": 0.00019983830861747265,
      "loss": 0.7371,
      "step": 1021
    },
    {
      "epoch": 0.05597852878348031,
      "grad_norm": 10.280354499816895,
      "learning_rate": 0.0001998379739234224,
      "loss": 0.8986,
      "step": 1022
    },
    {
      "epoch": 0.056033302295010134,
      "grad_norm": 7.4663615226745605,
      "learning_rate": 0.00019983765378128737,
      "loss": 1.462,
      "step": 1023
    },
    {
      "epoch": 0.056088075806539954,
      "grad_norm": 2.1958210468292236,
      "learning_rate": 0.00019983733363915235,
      "loss": 1.2072,
      "step": 1024
    },
    {
      "epoch": 0.05614284931806978,
      "grad_norm": 2.709280014038086,
      "learning_rate": 0.0001998369989451021,
      "loss": 1.2969,
      "step": 1025
    },
    {
      "epoch": 0.05619762282959961,
      "grad_norm": 5.367567539215088,
      "learning_rate": 0.00019983667880296707,
      "loss": 1.8719,
      "step": 1026
    },
    {
      "epoch": 0.056252396341129426,
      "grad_norm": 4.484698295593262,
      "learning_rate": 0.00019983634410891682,
      "loss": 1.5193,
      "step": 1027
    },
    {
      "epoch": 0.05630716985265925,
      "grad_norm": 1.928802728652954,
      "learning_rate": 0.00019983600941486657,
      "loss": 1.2096,
      "step": 1028
    },
    {
      "epoch": 0.05636194336418908,
      "grad_norm": 14.023823738098145,
      "learning_rate": 0.00019983568927273154,
      "loss": 1.6306,
      "step": 1029
    },
    {
      "epoch": 0.0564167168757189,
      "grad_norm": 8.033287048339844,
      "learning_rate": 0.0001998353545786813,
      "loss": 1.052,
      "step": 1030
    },
    {
      "epoch": 0.056471490387248725,
      "grad_norm": 2.328517436981201,
      "learning_rate": 0.00019983503443654627,
      "loss": 1.1459,
      "step": 1031
    },
    {
      "epoch": 0.05652626389877855,
      "grad_norm": 2.798537254333496,
      "learning_rate": 0.00019983469974249601,
      "loss": 1.1225,
      "step": 1032
    },
    {
      "epoch": 0.05658103741030838,
      "grad_norm": 2.868821859359741,
      "learning_rate": 0.00019983436504844576,
      "loss": 0.8836,
      "step": 1033
    },
    {
      "epoch": 0.0566358109218382,
      "grad_norm": 5.071940898895264,
      "learning_rate": 0.00019983404490631074,
      "loss": 1.7391,
      "step": 1034
    },
    {
      "epoch": 0.056690584433368024,
      "grad_norm": 6.081525802612305,
      "learning_rate": 0.00019983371021226048,
      "loss": 1.4132,
      "step": 1035
    },
    {
      "epoch": 0.05674535794489785,
      "grad_norm": 3.724945545196533,
      "learning_rate": 0.00019983337551821023,
      "loss": 1.6587,
      "step": 1036
    },
    {
      "epoch": 0.05680013145642767,
      "grad_norm": 2.096641778945923,
      "learning_rate": 0.00019983304082415998,
      "loss": 1.0837,
      "step": 1037
    },
    {
      "epoch": 0.0568549049679575,
      "grad_norm": 7.895615577697754,
      "learning_rate": 0.00019983272068202496,
      "loss": 1.9307,
      "step": 1038
    },
    {
      "epoch": 0.05690967847948732,
      "grad_norm": 2.304128646850586,
      "learning_rate": 0.0001998323859879747,
      "loss": 1.1451,
      "step": 1039
    },
    {
      "epoch": 0.05696445199101714,
      "grad_norm": 5.975157260894775,
      "learning_rate": 0.00019983205129392445,
      "loss": 1.1969,
      "step": 1040
    },
    {
      "epoch": 0.05701922550254697,
      "grad_norm": 3.0364627838134766,
      "learning_rate": 0.0001998317165998742,
      "loss": 1.089,
      "step": 1041
    },
    {
      "epoch": 0.057073999014076796,
      "grad_norm": 5.812072277069092,
      "learning_rate": 0.00019983138190582395,
      "loss": 0.3362,
      "step": 1042
    },
    {
      "epoch": 0.057128772525606615,
      "grad_norm": 20.8416690826416,
      "learning_rate": 0.0001998310472117737,
      "loss": 0.8185,
      "step": 1043
    },
    {
      "epoch": 0.05718354603713644,
      "grad_norm": 2.9029128551483154,
      "learning_rate": 0.00019983071251772344,
      "loss": 1.3177,
      "step": 1044
    },
    {
      "epoch": 0.05723831954866627,
      "grad_norm": 4.9826340675354,
      "learning_rate": 0.0001998303778236732,
      "loss": 2.3799,
      "step": 1045
    },
    {
      "epoch": 0.05729309306019609,
      "grad_norm": 5.792742729187012,
      "learning_rate": 0.00019983004312962294,
      "loss": 1.253,
      "step": 1046
    },
    {
      "epoch": 0.057347866571725914,
      "grad_norm": 4.3030266761779785,
      "learning_rate": 0.0001998297229874879,
      "loss": 2.2743,
      "step": 1047
    },
    {
      "epoch": 0.05740264008325574,
      "grad_norm": 11.025445938110352,
      "learning_rate": 0.00019982938829343766,
      "loss": 2.4423,
      "step": 1048
    },
    {
      "epoch": 0.05745741359478556,
      "grad_norm": 2.573404312133789,
      "learning_rate": 0.0001998290535993874,
      "loss": 1.2443,
      "step": 1049
    },
    {
      "epoch": 0.057512187106315386,
      "grad_norm": 3.6165921688079834,
      "learning_rate": 0.00019982871890533715,
      "loss": 1.6126,
      "step": 1050
    },
    {
      "epoch": 0.05756696061784521,
      "grad_norm": 2.256446599960327,
      "learning_rate": 0.00019982836965937167,
      "loss": 1.5294,
      "step": 1051
    },
    {
      "epoch": 0.05762173412937503,
      "grad_norm": 3.548931121826172,
      "learning_rate": 0.00019982803496532142,
      "loss": 1.589,
      "step": 1052
    },
    {
      "epoch": 0.05767650764090486,
      "grad_norm": 3.829618215560913,
      "learning_rate": 0.00019982770027127117,
      "loss": 1.6239,
      "step": 1053
    },
    {
      "epoch": 0.057731281152434685,
      "grad_norm": 3.378479480743408,
      "learning_rate": 0.00019982736557722092,
      "loss": 1.54,
      "step": 1054
    },
    {
      "epoch": 0.057786054663964505,
      "grad_norm": 1.7971792221069336,
      "learning_rate": 0.00019982701633125544,
      "loss": 0.91,
      "step": 1055
    },
    {
      "epoch": 0.05784082817549433,
      "grad_norm": 4.726898193359375,
      "learning_rate": 0.00019982668163720518,
      "loss": 2.5046,
      "step": 1056
    },
    {
      "epoch": 0.05789560168702416,
      "grad_norm": 2.072960138320923,
      "learning_rate": 0.00019982636149507016,
      "loss": 1.4772,
      "step": 1057
    },
    {
      "epoch": 0.05795037519855398,
      "grad_norm": 6.953313827514648,
      "learning_rate": 0.00019982601224910468,
      "loss": 1.2613,
      "step": 1058
    },
    {
      "epoch": 0.058005148710083804,
      "grad_norm": 11.830960273742676,
      "learning_rate": 0.00019982567755505443,
      "loss": 1.8428,
      "step": 1059
    },
    {
      "epoch": 0.05805992222161363,
      "grad_norm": 2.8075973987579346,
      "learning_rate": 0.00019982532830908895,
      "loss": 1.2229,
      "step": 1060
    },
    {
      "epoch": 0.05811469573314345,
      "grad_norm": 2.2096714973449707,
      "learning_rate": 0.0001998249936150387,
      "loss": 1.5319,
      "step": 1061
    },
    {
      "epoch": 0.058169469244673276,
      "grad_norm": 2.2569868564605713,
      "learning_rate": 0.00019982465892098844,
      "loss": 1.4618,
      "step": 1062
    },
    {
      "epoch": 0.0582242427562031,
      "grad_norm": 2.1697661876678467,
      "learning_rate": 0.00019982430967502296,
      "loss": 1.5143,
      "step": 1063
    },
    {
      "epoch": 0.05827901626773292,
      "grad_norm": 6.6876444816589355,
      "learning_rate": 0.00019982398953288794,
      "loss": 2.5463,
      "step": 1064
    },
    {
      "epoch": 0.05833378977926275,
      "grad_norm": 2.179957866668701,
      "learning_rate": 0.00019982364028692245,
      "loss": 1.0902,
      "step": 1065
    },
    {
      "epoch": 0.058388563290792575,
      "grad_norm": 7.136172771453857,
      "learning_rate": 0.00019982329104095697,
      "loss": 1.9274,
      "step": 1066
    },
    {
      "epoch": 0.058443336802322395,
      "grad_norm": 3.299555778503418,
      "learning_rate": 0.00019982295634690672,
      "loss": 1.6291,
      "step": 1067
    },
    {
      "epoch": 0.05849811031385222,
      "grad_norm": 3.5460476875305176,
      "learning_rate": 0.00019982260710094124,
      "loss": 1.5373,
      "step": 1068
    },
    {
      "epoch": 0.05855288382538205,
      "grad_norm": 12.865274429321289,
      "learning_rate": 0.000199822272406891,
      "loss": 2.9226,
      "step": 1069
    },
    {
      "epoch": 0.05860765733691187,
      "grad_norm": 13.994370460510254,
      "learning_rate": 0.00019982193771284074,
      "loss": 2.6397,
      "step": 1070
    },
    {
      "epoch": 0.05866243084844169,
      "grad_norm": 7.348345756530762,
      "learning_rate": 0.00019982158846687526,
      "loss": 1.7681,
      "step": 1071
    },
    {
      "epoch": 0.05871720435997152,
      "grad_norm": 22.327877044677734,
      "learning_rate": 0.00019982123922090977,
      "loss": 2.9567,
      "step": 1072
    },
    {
      "epoch": 0.05877197787150134,
      "grad_norm": 4.138152599334717,
      "learning_rate": 0.0001998208899749443,
      "loss": 0.9501,
      "step": 1073
    },
    {
      "epoch": 0.058826751383031166,
      "grad_norm": 7.54646635055542,
      "learning_rate": 0.00019982055528089404,
      "loss": 1.5559,
      "step": 1074
    },
    {
      "epoch": 0.05888152489456099,
      "grad_norm": 2.309318780899048,
      "learning_rate": 0.0001998202205868438,
      "loss": 1.274,
      "step": 1075
    },
    {
      "epoch": 0.05893629840609081,
      "grad_norm": 1.763060212135315,
      "learning_rate": 0.0001998198713408783,
      "loss": 0.9636,
      "step": 1076
    },
    {
      "epoch": 0.05899107191762064,
      "grad_norm": 17.8609561920166,
      "learning_rate": 0.00019981952209491283,
      "loss": 4.0527,
      "step": 1077
    },
    {
      "epoch": 0.059045845429150465,
      "grad_norm": 10.457375526428223,
      "learning_rate": 0.00019981917284894735,
      "loss": 2.3965,
      "step": 1078
    },
    {
      "epoch": 0.059100618940680284,
      "grad_norm": 3.8090882301330566,
      "learning_rate": 0.0001998188381548971,
      "loss": 1.4764,
      "step": 1079
    },
    {
      "epoch": 0.05915539245221011,
      "grad_norm": 4.318417072296143,
      "learning_rate": 0.0001998184889089316,
      "loss": 1.285,
      "step": 1080
    },
    {
      "epoch": 0.05921016596373994,
      "grad_norm": 7.628039836883545,
      "learning_rate": 0.00019981813966296613,
      "loss": 1.8734,
      "step": 1081
    },
    {
      "epoch": 0.05926493947526976,
      "grad_norm": 1.9067680835723877,
      "learning_rate": 0.00019981779041700065,
      "loss": 1.0592,
      "step": 1082
    },
    {
      "epoch": 0.05931971298679958,
      "grad_norm": 8.714491844177246,
      "learning_rate": 0.0001998174557229504,
      "loss": 2.3855,
      "step": 1083
    },
    {
      "epoch": 0.05937448649832941,
      "grad_norm": 3.3732969760894775,
      "learning_rate": 0.00019981710647698492,
      "loss": 0.9729,
      "step": 1084
    },
    {
      "epoch": 0.05942926000985923,
      "grad_norm": 6.312155246734619,
      "learning_rate": 0.00019981675723101944,
      "loss": 1.6444,
      "step": 1085
    },
    {
      "epoch": 0.059484033521389056,
      "grad_norm": 6.341533184051514,
      "learning_rate": 0.00019981640798505396,
      "loss": 1.6529,
      "step": 1086
    },
    {
      "epoch": 0.05953880703291888,
      "grad_norm": 3.2617979049682617,
      "learning_rate": 0.0001998160732910037,
      "loss": 1.3271,
      "step": 1087
    },
    {
      "epoch": 0.0595935805444487,
      "grad_norm": 5.378675937652588,
      "learning_rate": 0.000199815709493123,
      "loss": 1.4622,
      "step": 1088
    },
    {
      "epoch": 0.05964835405597853,
      "grad_norm": 3.869901180267334,
      "learning_rate": 0.00019981536024715751,
      "loss": 1.9104,
      "step": 1089
    },
    {
      "epoch": 0.059703127567508354,
      "grad_norm": 1.9948838949203491,
      "learning_rate": 0.00019981501100119203,
      "loss": 1.2343,
      "step": 1090
    },
    {
      "epoch": 0.059757901079038174,
      "grad_norm": 2.6390066146850586,
      "learning_rate": 0.00019981467630714178,
      "loss": 1.634,
      "step": 1091
    },
    {
      "epoch": 0.059812674590568,
      "grad_norm": 2.3948960304260254,
      "learning_rate": 0.00019981431250926107,
      "loss": 1.2006,
      "step": 1092
    },
    {
      "epoch": 0.05986744810209783,
      "grad_norm": 3.9241766929626465,
      "learning_rate": 0.0001998139632632956,
      "loss": 1.3022,
      "step": 1093
    },
    {
      "epoch": 0.059922221613627646,
      "grad_norm": 5.441091537475586,
      "learning_rate": 0.00019981362856924534,
      "loss": 1.3599,
      "step": 1094
    },
    {
      "epoch": 0.05997699512515747,
      "grad_norm": 6.214454650878906,
      "learning_rate": 0.00019981326477136463,
      "loss": 1.5521,
      "step": 1095
    },
    {
      "epoch": 0.0600317686366873,
      "grad_norm": 2.3404040336608887,
      "learning_rate": 0.00019981291552539915,
      "loss": 1.3477,
      "step": 1096
    },
    {
      "epoch": 0.06008654214821712,
      "grad_norm": 3.586533784866333,
      "learning_rate": 0.00019981256627943367,
      "loss": 1.2985,
      "step": 1097
    },
    {
      "epoch": 0.060141315659746945,
      "grad_norm": 3.3817882537841797,
      "learning_rate": 0.0001998122170334682,
      "loss": 1.5957,
      "step": 1098
    },
    {
      "epoch": 0.06019608917127677,
      "grad_norm": 2.279287576675415,
      "learning_rate": 0.00019981185323558748,
      "loss": 1.6202,
      "step": 1099
    },
    {
      "epoch": 0.06025086268280659,
      "grad_norm": 2.1332809925079346,
      "learning_rate": 0.00019981151854153723,
      "loss": 0.8685,
      "step": 1100
    },
    {
      "epoch": 0.06025086268280659,
      "eval_loss": 1.4863735437393188,
      "eval_runtime": 45.8142,
      "eval_samples_per_second": 2.008,
      "eval_steps_per_second": 2.008,
      "step": 1100
    },
    {
      "epoch": 0.06030563619433642,
      "grad_norm": 8.752928733825684,
      "learning_rate": 0.00019981115474365652,
      "loss": 3.0831,
      "step": 1101
    },
    {
      "epoch": 0.060360409705866244,
      "grad_norm": 3.3090109825134277,
      "learning_rate": 0.00019981080549769104,
      "loss": 1.4573,
      "step": 1102
    },
    {
      "epoch": 0.06041518321739607,
      "grad_norm": 21.9459228515625,
      "learning_rate": 0.00019981045625172555,
      "loss": 2.0192,
      "step": 1103
    },
    {
      "epoch": 0.06046995672892589,
      "grad_norm": 5.797779083251953,
      "learning_rate": 0.00019981009245384485,
      "loss": 0.3987,
      "step": 1104
    },
    {
      "epoch": 0.06052473024045572,
      "grad_norm": 3.1804001331329346,
      "learning_rate": 0.00019980974320787936,
      "loss": 1.2499,
      "step": 1105
    },
    {
      "epoch": 0.06057950375198554,
      "grad_norm": 3.1431047916412354,
      "learning_rate": 0.00019980939396191388,
      "loss": 1.2929,
      "step": 1106
    },
    {
      "epoch": 0.06063427726351536,
      "grad_norm": 8.74044418334961,
      "learning_rate": 0.00019980903016403317,
      "loss": 2.2115,
      "step": 1107
    },
    {
      "epoch": 0.06068905077504519,
      "grad_norm": 2.0406887531280518,
      "learning_rate": 0.0001998086809180677,
      "loss": 1.4434,
      "step": 1108
    },
    {
      "epoch": 0.060743824286575016,
      "grad_norm": 4.017370223999023,
      "learning_rate": 0.0001998083316721022,
      "loss": 1.7565,
      "step": 1109
    },
    {
      "epoch": 0.060798597798104835,
      "grad_norm": 5.879277229309082,
      "learning_rate": 0.0001998079678742215,
      "loss": 1.99,
      "step": 1110
    },
    {
      "epoch": 0.06085337130963466,
      "grad_norm": 3.0660295486450195,
      "learning_rate": 0.00019980761862825602,
      "loss": 1.7901,
      "step": 1111
    },
    {
      "epoch": 0.06090814482116449,
      "grad_norm": 2.8627610206604004,
      "learning_rate": 0.00019980725483037531,
      "loss": 1.3463,
      "step": 1112
    },
    {
      "epoch": 0.06096291833269431,
      "grad_norm": 4.535649299621582,
      "learning_rate": 0.00019980690558440983,
      "loss": 1.5925,
      "step": 1113
    },
    {
      "epoch": 0.061017691844224134,
      "grad_norm": 5.431495666503906,
      "learning_rate": 0.00019980654178652912,
      "loss": 1.3497,
      "step": 1114
    },
    {
      "epoch": 0.06107246535575396,
      "grad_norm": 2.0391674041748047,
      "learning_rate": 0.00019980619254056364,
      "loss": 0.7998,
      "step": 1115
    },
    {
      "epoch": 0.06112723886728378,
      "grad_norm": 2.9166617393493652,
      "learning_rate": 0.00019980584329459816,
      "loss": 1.8041,
      "step": 1116
    },
    {
      "epoch": 0.061182012378813606,
      "grad_norm": 3.7426161766052246,
      "learning_rate": 0.00019980547949671745,
      "loss": 2.1341,
      "step": 1117
    },
    {
      "epoch": 0.06123678589034343,
      "grad_norm": 2.187473773956299,
      "learning_rate": 0.00019980513025075197,
      "loss": 1.3458,
      "step": 1118
    },
    {
      "epoch": 0.06129155940187325,
      "grad_norm": 2.1662425994873047,
      "learning_rate": 0.00019980475190095603,
      "loss": 1.174,
      "step": 1119
    },
    {
      "epoch": 0.06134633291340308,
      "grad_norm": 2.885622024536133,
      "learning_rate": 0.00019980440265499055,
      "loss": 1.5111,
      "step": 1120
    },
    {
      "epoch": 0.061401106424932905,
      "grad_norm": 7.2540283203125,
      "learning_rate": 0.00019980403885710984,
      "loss": 2.1178,
      "step": 1121
    },
    {
      "epoch": 0.061455879936462725,
      "grad_norm": 6.56860876083374,
      "learning_rate": 0.00019980367505922914,
      "loss": 1.1062,
      "step": 1122
    },
    {
      "epoch": 0.06151065344799255,
      "grad_norm": 1.8632149696350098,
      "learning_rate": 0.00019980332581326365,
      "loss": 1.0614,
      "step": 1123
    },
    {
      "epoch": 0.06156542695952238,
      "grad_norm": 2.513143301010132,
      "learning_rate": 0.00019980296201538295,
      "loss": 1.1389,
      "step": 1124
    },
    {
      "epoch": 0.0616202004710522,
      "grad_norm": 3.877453327178955,
      "learning_rate": 0.00019980261276941746,
      "loss": 1.051,
      "step": 1125
    },
    {
      "epoch": 0.061674973982582024,
      "grad_norm": 9.525901794433594,
      "learning_rate": 0.00019980223441962153,
      "loss": 2.1792,
      "step": 1126
    },
    {
      "epoch": 0.06172974749411185,
      "grad_norm": 2.432573080062866,
      "learning_rate": 0.00019980188517365605,
      "loss": 1.1862,
      "step": 1127
    },
    {
      "epoch": 0.06178452100564167,
      "grad_norm": 5.380393981933594,
      "learning_rate": 0.00019980152137577534,
      "loss": 2.4991,
      "step": 1128
    },
    {
      "epoch": 0.061839294517171496,
      "grad_norm": 7.468969345092773,
      "learning_rate": 0.00019980115757789463,
      "loss": 0.8427,
      "step": 1129
    },
    {
      "epoch": 0.06189406802870132,
      "grad_norm": 2.469639301300049,
      "learning_rate": 0.00019980079378001392,
      "loss": 0.6919,
      "step": 1130
    },
    {
      "epoch": 0.06194884154023114,
      "grad_norm": 4.167551517486572,
      "learning_rate": 0.00019980044453404844,
      "loss": 0.866,
      "step": 1131
    },
    {
      "epoch": 0.06200361505176097,
      "grad_norm": 2.212693214416504,
      "learning_rate": 0.0001998000661842525,
      "loss": 1.0168,
      "step": 1132
    },
    {
      "epoch": 0.062058388563290795,
      "grad_norm": 7.185072422027588,
      "learning_rate": 0.00019979971693828702,
      "loss": 2.2904,
      "step": 1133
    },
    {
      "epoch": 0.062113162074820615,
      "grad_norm": 6.48591947555542,
      "learning_rate": 0.00019979933858849108,
      "loss": 1.9442,
      "step": 1134
    },
    {
      "epoch": 0.06216793558635044,
      "grad_norm": 7.906517505645752,
      "learning_rate": 0.0001997989893425256,
      "loss": 2.5297,
      "step": 1135
    },
    {
      "epoch": 0.06222270909788027,
      "grad_norm": 7.137140274047852,
      "learning_rate": 0.00019979861099272966,
      "loss": 2.2493,
      "step": 1136
    },
    {
      "epoch": 0.06227748260941009,
      "grad_norm": 2.1521875858306885,
      "learning_rate": 0.00019979826174676418,
      "loss": 0.8962,
      "step": 1137
    },
    {
      "epoch": 0.06233225612093991,
      "grad_norm": 2.339639902114868,
      "learning_rate": 0.00019979788339696825,
      "loss": 1.3497,
      "step": 1138
    },
    {
      "epoch": 0.06238702963246974,
      "grad_norm": 2.931731939315796,
      "learning_rate": 0.00019979753415100276,
      "loss": 0.6507,
      "step": 1139
    },
    {
      "epoch": 0.06244180314399956,
      "grad_norm": 2.221656560897827,
      "learning_rate": 0.00019979715580120683,
      "loss": 1.2574,
      "step": 1140
    },
    {
      "epoch": 0.062496576655529386,
      "grad_norm": 9.083978652954102,
      "learning_rate": 0.00019979679200332612,
      "loss": 1.5441,
      "step": 1141
    },
    {
      "epoch": 0.0625513501670592,
      "grad_norm": 5.485233306884766,
      "learning_rate": 0.0001997964282054454,
      "loss": 2.1849,
      "step": 1142
    },
    {
      "epoch": 0.06260612367858903,
      "grad_norm": 2.058213472366333,
      "learning_rate": 0.0001997960644075647,
      "loss": 0.6561,
      "step": 1143
    },
    {
      "epoch": 0.06266089719011886,
      "grad_norm": 6.9010419845581055,
      "learning_rate": 0.000199795700609684,
      "loss": 0.8908,
      "step": 1144
    },
    {
      "epoch": 0.06271567070164868,
      "grad_norm": 4.846176624298096,
      "learning_rate": 0.00019979532225988805,
      "loss": 1.1273,
      "step": 1145
    },
    {
      "epoch": 0.06277044421317851,
      "grad_norm": 5.268280982971191,
      "learning_rate": 0.00019979497301392257,
      "loss": 1.7133,
      "step": 1146
    },
    {
      "epoch": 0.06282521772470834,
      "grad_norm": 2.44862961769104,
      "learning_rate": 0.00019979459466412663,
      "loss": 1.4566,
      "step": 1147
    },
    {
      "epoch": 0.06287999123623815,
      "grad_norm": 2.53865385055542,
      "learning_rate": 0.00019979423086624593,
      "loss": 1.9001,
      "step": 1148
    },
    {
      "epoch": 0.06293476474776798,
      "grad_norm": 6.052866458892822,
      "learning_rate": 0.00019979385251645,
      "loss": 1.4644,
      "step": 1149
    },
    {
      "epoch": 0.0629895382592978,
      "grad_norm": 5.064899444580078,
      "learning_rate": 0.00019979348871856928,
      "loss": 1.2749,
      "step": 1150
    },
    {
      "epoch": 0.06304431177082763,
      "grad_norm": 1.9326177835464478,
      "learning_rate": 0.00019979312492068857,
      "loss": 0.9774,
      "step": 1151
    },
    {
      "epoch": 0.06309908528235746,
      "grad_norm": 2.4752068519592285,
      "learning_rate": 0.00019979274657089263,
      "loss": 1.4884,
      "step": 1152
    },
    {
      "epoch": 0.06315385879388728,
      "grad_norm": 3.7896640300750732,
      "learning_rate": 0.00019979238277301192,
      "loss": 2.3436,
      "step": 1153
    },
    {
      "epoch": 0.0632086323054171,
      "grad_norm": 3.2744686603546143,
      "learning_rate": 0.00019979200442321599,
      "loss": 1.2199,
      "step": 1154
    },
    {
      "epoch": 0.06326340581694692,
      "grad_norm": 2.3828980922698975,
      "learning_rate": 0.00019979164062533528,
      "loss": 1.4222,
      "step": 1155
    },
    {
      "epoch": 0.06331817932847675,
      "grad_norm": 3.0140702724456787,
      "learning_rate": 0.00019979127682745457,
      "loss": 1.4793,
      "step": 1156
    },
    {
      "epoch": 0.06337295284000657,
      "grad_norm": 2.054949998855591,
      "learning_rate": 0.00019979089847765863,
      "loss": 0.9143,
      "step": 1157
    },
    {
      "epoch": 0.0634277263515364,
      "grad_norm": 8.348918914794922,
      "learning_rate": 0.00019979053467977792,
      "loss": 3.2446,
      "step": 1158
    },
    {
      "epoch": 0.06348249986306623,
      "grad_norm": 2.871290683746338,
      "learning_rate": 0.00019979015632998198,
      "loss": 1.3535,
      "step": 1159
    },
    {
      "epoch": 0.06353727337459604,
      "grad_norm": 1.9848271608352661,
      "learning_rate": 0.00019978977798018605,
      "loss": 1.0958,
      "step": 1160
    },
    {
      "epoch": 0.06359204688612587,
      "grad_norm": 3.289140224456787,
      "learning_rate": 0.00019978941418230534,
      "loss": 1.4417,
      "step": 1161
    },
    {
      "epoch": 0.06364682039765569,
      "grad_norm": 4.446439266204834,
      "learning_rate": 0.0001997890358325094,
      "loss": 1.546,
      "step": 1162
    },
    {
      "epoch": 0.06370159390918552,
      "grad_norm": 6.054690837860107,
      "learning_rate": 0.0001997886720346287,
      "loss": 2.0148,
      "step": 1163
    },
    {
      "epoch": 0.06375636742071535,
      "grad_norm": 3.162100315093994,
      "learning_rate": 0.00019978829368483275,
      "loss": 1.4528,
      "step": 1164
    },
    {
      "epoch": 0.06381114093224517,
      "grad_norm": 1.7437341213226318,
      "learning_rate": 0.00019978791533503681,
      "loss": 0.51,
      "step": 1165
    },
    {
      "epoch": 0.06386591444377498,
      "grad_norm": 2.4370553493499756,
      "learning_rate": 0.0001997875515371561,
      "loss": 1.4193,
      "step": 1166
    },
    {
      "epoch": 0.06392068795530481,
      "grad_norm": 2.244701385498047,
      "learning_rate": 0.00019978717318736017,
      "loss": 1.4757,
      "step": 1167
    },
    {
      "epoch": 0.06397546146683464,
      "grad_norm": 4.300213813781738,
      "learning_rate": 0.00019978679483756423,
      "loss": 1.2403,
      "step": 1168
    },
    {
      "epoch": 0.06403023497836446,
      "grad_norm": 2.539480447769165,
      "learning_rate": 0.00019978643103968352,
      "loss": 1.0064,
      "step": 1169
    },
    {
      "epoch": 0.06408500848989429,
      "grad_norm": 9.921064376831055,
      "learning_rate": 0.00019978605268988758,
      "loss": 1.9335,
      "step": 1170
    },
    {
      "epoch": 0.06413978200142412,
      "grad_norm": 7.157392501831055,
      "learning_rate": 0.00019978567434009165,
      "loss": 1.4738,
      "step": 1171
    },
    {
      "epoch": 0.06419455551295393,
      "grad_norm": 2.458874225616455,
      "learning_rate": 0.0001997852959902957,
      "loss": 1.0384,
      "step": 1172
    },
    {
      "epoch": 0.06424932902448376,
      "grad_norm": 5.845635414123535,
      "learning_rate": 0.000199784932192415,
      "loss": 2.5508,
      "step": 1173
    },
    {
      "epoch": 0.06430410253601358,
      "grad_norm": 4.502786159515381,
      "learning_rate": 0.00019978455384261906,
      "loss": 1.7904,
      "step": 1174
    },
    {
      "epoch": 0.06435887604754341,
      "grad_norm": 4.454898357391357,
      "learning_rate": 0.0001997841609409079,
      "loss": 2.5441,
      "step": 1175
    },
    {
      "epoch": 0.06441364955907324,
      "grad_norm": 4.294528007507324,
      "learning_rate": 0.00019978379714302719,
      "loss": 1.3738,
      "step": 1176
    },
    {
      "epoch": 0.06446842307060306,
      "grad_norm": 2.744102716445923,
      "learning_rate": 0.00019978341879323125,
      "loss": 1.6042,
      "step": 1177
    },
    {
      "epoch": 0.06452319658213287,
      "grad_norm": 4.023571014404297,
      "learning_rate": 0.0001997830404434353,
      "loss": 1.2708,
      "step": 1178
    },
    {
      "epoch": 0.0645779700936627,
      "grad_norm": 2.673332452774048,
      "learning_rate": 0.00019978266209363937,
      "loss": 0.3013,
      "step": 1179
    },
    {
      "epoch": 0.06463274360519253,
      "grad_norm": 1.7212387323379517,
      "learning_rate": 0.00019978228374384344,
      "loss": 0.599,
      "step": 1180
    },
    {
      "epoch": 0.06468751711672235,
      "grad_norm": 3.538599967956543,
      "learning_rate": 0.0001997819053940475,
      "loss": 1.5255,
      "step": 1181
    },
    {
      "epoch": 0.06474229062825218,
      "grad_norm": 4.789577007293701,
      "learning_rate": 0.00019978152704425156,
      "loss": 1.297,
      "step": 1182
    },
    {
      "epoch": 0.064797064139782,
      "grad_norm": 2.9896745681762695,
      "learning_rate": 0.00019978114869445562,
      "loss": 1.4283,
      "step": 1183
    },
    {
      "epoch": 0.06485183765131182,
      "grad_norm": 3.2040305137634277,
      "learning_rate": 0.00019978077034465969,
      "loss": 1.479,
      "step": 1184
    },
    {
      "epoch": 0.06490661116284165,
      "grad_norm": 2.456704616546631,
      "learning_rate": 0.00019978039199486375,
      "loss": 1.0456,
      "step": 1185
    },
    {
      "epoch": 0.06496138467437147,
      "grad_norm": 2.061770439147949,
      "learning_rate": 0.00019977999909315258,
      "loss": 1.0816,
      "step": 1186
    },
    {
      "epoch": 0.0650161581859013,
      "grad_norm": 4.780132293701172,
      "learning_rate": 0.00019977962074335665,
      "loss": 1.6963,
      "step": 1187
    },
    {
      "epoch": 0.06507093169743113,
      "grad_norm": 5.542447566986084,
      "learning_rate": 0.0001997792423935607,
      "loss": 2.3317,
      "step": 1188
    },
    {
      "epoch": 0.06512570520896095,
      "grad_norm": 2.1674885749816895,
      "learning_rate": 0.00019977886404376477,
      "loss": 1.1872,
      "step": 1189
    },
    {
      "epoch": 0.06518047872049076,
      "grad_norm": 4.084795951843262,
      "learning_rate": 0.00019977848569396883,
      "loss": 1.2224,
      "step": 1190
    },
    {
      "epoch": 0.06523525223202059,
      "grad_norm": 2.1873438358306885,
      "learning_rate": 0.00019977809279225767,
      "loss": 1.4331,
      "step": 1191
    },
    {
      "epoch": 0.06529002574355042,
      "grad_norm": 5.108521938323975,
      "learning_rate": 0.00019977771444246173,
      "loss": 2.0731,
      "step": 1192
    },
    {
      "epoch": 0.06534479925508024,
      "grad_norm": 1.8123177289962769,
      "learning_rate": 0.0001997773360926658,
      "loss": 1.004,
      "step": 1193
    },
    {
      "epoch": 0.06539957276661007,
      "grad_norm": 5.401280879974365,
      "learning_rate": 0.00019977695774286985,
      "loss": 1.7383,
      "step": 1194
    },
    {
      "epoch": 0.0654543462781399,
      "grad_norm": 5.669796466827393,
      "learning_rate": 0.00019977657939307392,
      "loss": 2.2807,
      "step": 1195
    },
    {
      "epoch": 0.06550911978966971,
      "grad_norm": 23.46455955505371,
      "learning_rate": 0.00019977618649136275,
      "loss": 3.5181,
      "step": 1196
    },
    {
      "epoch": 0.06556389330119954,
      "grad_norm": 3.6794917583465576,
      "learning_rate": 0.00019977579358965158,
      "loss": 1.8464,
      "step": 1197
    },
    {
      "epoch": 0.06561866681272936,
      "grad_norm": 7.816056728363037,
      "learning_rate": 0.00019977541523985565,
      "loss": 1.82,
      "step": 1198
    },
    {
      "epoch": 0.06567344032425919,
      "grad_norm": 2.0452187061309814,
      "learning_rate": 0.0001997750368900597,
      "loss": 1.289,
      "step": 1199
    },
    {
      "epoch": 0.06572821383578901,
      "grad_norm": 2.3604800701141357,
      "learning_rate": 0.00019977464398834854,
      "loss": 1.0054,
      "step": 1200
    },
    {
      "epoch": 0.06572821383578901,
      "eval_loss": 1.4765090942382812,
      "eval_runtime": 45.8328,
      "eval_samples_per_second": 2.007,
      "eval_steps_per_second": 2.007,
      "step": 1200
    },
    {
      "epoch": 0.06578298734731884,
      "grad_norm": 2.2575297355651855,
      "learning_rate": 0.0001997742656385526,
      "loss": 1.1114,
      "step": 1201
    },
    {
      "epoch": 0.06583776085884865,
      "grad_norm": 4.688625812530518,
      "learning_rate": 0.00019977387273684144,
      "loss": 1.9371,
      "step": 1202
    },
    {
      "epoch": 0.06589253437037848,
      "grad_norm": 2.1282520294189453,
      "learning_rate": 0.00019977347983513027,
      "loss": 1.1906,
      "step": 1203
    },
    {
      "epoch": 0.06594730788190831,
      "grad_norm": 6.909064292907715,
      "learning_rate": 0.00019977310148533434,
      "loss": 1.5714,
      "step": 1204
    },
    {
      "epoch": 0.06600208139343813,
      "grad_norm": 18.800827026367188,
      "learning_rate": 0.0001997727231355384,
      "loss": 2.5105,
      "step": 1205
    },
    {
      "epoch": 0.06605685490496796,
      "grad_norm": 2.5906498432159424,
      "learning_rate": 0.00019977233023382723,
      "loss": 1.4241,
      "step": 1206
    },
    {
      "epoch": 0.06611162841649779,
      "grad_norm": 2.5188355445861816,
      "learning_rate": 0.0001997719518840313,
      "loss": 1.1973,
      "step": 1207
    },
    {
      "epoch": 0.06616640192802761,
      "grad_norm": 6.373004913330078,
      "learning_rate": 0.00019977155898232013,
      "loss": 2.0867,
      "step": 1208
    },
    {
      "epoch": 0.06622117543955743,
      "grad_norm": 5.097718238830566,
      "learning_rate": 0.00019977116608060896,
      "loss": 2.3039,
      "step": 1209
    },
    {
      "epoch": 0.06627594895108725,
      "grad_norm": 2.375654935836792,
      "learning_rate": 0.0001997707731788978,
      "loss": 1.1001,
      "step": 1210
    },
    {
      "epoch": 0.06633072246261708,
      "grad_norm": 2.5638909339904785,
      "learning_rate": 0.00019977038027718663,
      "loss": 1.0557,
      "step": 1211
    },
    {
      "epoch": 0.0663854959741469,
      "grad_norm": 2.4466943740844727,
      "learning_rate": 0.0001997700019273907,
      "loss": 0.4433,
      "step": 1212
    },
    {
      "epoch": 0.06644026948567673,
      "grad_norm": 2.8810417652130127,
      "learning_rate": 0.00019976960902567953,
      "loss": 1.7305,
      "step": 1213
    },
    {
      "epoch": 0.06649504299720656,
      "grad_norm": 2.9721312522888184,
      "learning_rate": 0.0001997692306758836,
      "loss": 1.5294,
      "step": 1214
    },
    {
      "epoch": 0.06654981650873637,
      "grad_norm": 3.940325975418091,
      "learning_rate": 0.00019976883777417243,
      "loss": 0.8505,
      "step": 1215
    },
    {
      "epoch": 0.0666045900202662,
      "grad_norm": 2.489117383956909,
      "learning_rate": 0.00019976844487246126,
      "loss": 1.9058,
      "step": 1216
    },
    {
      "epoch": 0.06665936353179602,
      "grad_norm": 3.3022713661193848,
      "learning_rate": 0.0001997680519707501,
      "loss": 1.0509,
      "step": 1217
    },
    {
      "epoch": 0.06671413704332585,
      "grad_norm": 7.344937801361084,
      "learning_rate": 0.00019976767362095416,
      "loss": 1.9963,
      "step": 1218
    },
    {
      "epoch": 0.06676891055485568,
      "grad_norm": 3.678572416305542,
      "learning_rate": 0.000199767280719243,
      "loss": 2.2767,
      "step": 1219
    },
    {
      "epoch": 0.0668236840663855,
      "grad_norm": 8.050299644470215,
      "learning_rate": 0.00019976688781753182,
      "loss": 3.0594,
      "step": 1220
    },
    {
      "epoch": 0.06687845757791532,
      "grad_norm": 1.2844557762145996,
      "learning_rate": 0.00019976649491582066,
      "loss": 0.833,
      "step": 1221
    },
    {
      "epoch": 0.06693323108944514,
      "grad_norm": 2.1064515113830566,
      "learning_rate": 0.00019976608746219426,
      "loss": 1.0227,
      "step": 1222
    },
    {
      "epoch": 0.06698800460097497,
      "grad_norm": 6.388916492462158,
      "learning_rate": 0.0001997656945604831,
      "loss": 0.7637,
      "step": 1223
    },
    {
      "epoch": 0.0670427781125048,
      "grad_norm": 4.9967803955078125,
      "learning_rate": 0.00019976530165877193,
      "loss": 1.2579,
      "step": 1224
    },
    {
      "epoch": 0.06709755162403462,
      "grad_norm": 3.899395704269409,
      "learning_rate": 0.00019976490875706077,
      "loss": 1.4406,
      "step": 1225
    },
    {
      "epoch": 0.06715232513556445,
      "grad_norm": 4.0837016105651855,
      "learning_rate": 0.0001997645158553496,
      "loss": 1.4285,
      "step": 1226
    },
    {
      "epoch": 0.06720709864709426,
      "grad_norm": 7.718870639801025,
      "learning_rate": 0.00019976412295363843,
      "loss": 2.3068,
      "step": 1227
    },
    {
      "epoch": 0.06726187215862409,
      "grad_norm": 2.3293964862823486,
      "learning_rate": 0.00019976373005192727,
      "loss": 1.1356,
      "step": 1228
    },
    {
      "epoch": 0.06731664567015391,
      "grad_norm": 9.258869171142578,
      "learning_rate": 0.0001997633371502161,
      "loss": 2.4199,
      "step": 1229
    },
    {
      "epoch": 0.06737141918168374,
      "grad_norm": 3.4575424194335938,
      "learning_rate": 0.00019976294424850494,
      "loss": 1.9954,
      "step": 1230
    },
    {
      "epoch": 0.06742619269321357,
      "grad_norm": 6.342923164367676,
      "learning_rate": 0.00019976255134679377,
      "loss": 2.932,
      "step": 1231
    },
    {
      "epoch": 0.06748096620474339,
      "grad_norm": 3.1610772609710693,
      "learning_rate": 0.0001997621584450826,
      "loss": 1.8102,
      "step": 1232
    },
    {
      "epoch": 0.0675357397162732,
      "grad_norm": 27.523195266723633,
      "learning_rate": 0.00019976176554337144,
      "loss": 3.0156,
      "step": 1233
    },
    {
      "epoch": 0.06759051322780303,
      "grad_norm": 2.064033031463623,
      "learning_rate": 0.00019976135808974504,
      "loss": 1.4366,
      "step": 1234
    },
    {
      "epoch": 0.06764528673933286,
      "grad_norm": 2.2271857261657715,
      "learning_rate": 0.00019976096518803388,
      "loss": 1.3011,
      "step": 1235
    },
    {
      "epoch": 0.06770006025086268,
      "grad_norm": 2.1836483478546143,
      "learning_rate": 0.0001997605722863227,
      "loss": 1.0433,
      "step": 1236
    },
    {
      "epoch": 0.06775483376239251,
      "grad_norm": 2.613513231277466,
      "learning_rate": 0.00019976016483269632,
      "loss": 0.6954,
      "step": 1237
    },
    {
      "epoch": 0.06780960727392234,
      "grad_norm": 5.104151725769043,
      "learning_rate": 0.00019975977193098515,
      "loss": 0.9726,
      "step": 1238
    },
    {
      "epoch": 0.06786438078545215,
      "grad_norm": 1.815178394317627,
      "learning_rate": 0.000199759379029274,
      "loss": 1.0727,
      "step": 1239
    },
    {
      "epoch": 0.06791915429698198,
      "grad_norm": 3.831669569015503,
      "learning_rate": 0.0001997589715756476,
      "loss": 1.8255,
      "step": 1240
    },
    {
      "epoch": 0.0679739278085118,
      "grad_norm": 2.753141164779663,
      "learning_rate": 0.00019975857867393643,
      "loss": 1.7884,
      "step": 1241
    },
    {
      "epoch": 0.06802870132004163,
      "grad_norm": 20.623218536376953,
      "learning_rate": 0.00019975818577222526,
      "loss": 5.2377,
      "step": 1242
    },
    {
      "epoch": 0.06808347483157146,
      "grad_norm": 13.143376350402832,
      "learning_rate": 0.00019975777831859887,
      "loss": 1.057,
      "step": 1243
    },
    {
      "epoch": 0.06813824834310128,
      "grad_norm": 4.989915370941162,
      "learning_rate": 0.0001997573854168877,
      "loss": 1.2751,
      "step": 1244
    },
    {
      "epoch": 0.0681930218546311,
      "grad_norm": 2.171431303024292,
      "learning_rate": 0.00019975699251517653,
      "loss": 1.2015,
      "step": 1245
    },
    {
      "epoch": 0.06824779536616092,
      "grad_norm": 13.053240776062012,
      "learning_rate": 0.00019975658506155014,
      "loss": 2.6071,
      "step": 1246
    },
    {
      "epoch": 0.06830256887769075,
      "grad_norm": 2.5270655155181885,
      "learning_rate": 0.00019975619215983897,
      "loss": 1.6387,
      "step": 1247
    },
    {
      "epoch": 0.06835734238922057,
      "grad_norm": 2.1556050777435303,
      "learning_rate": 0.00019975578470621258,
      "loss": 0.2103,
      "step": 1248
    },
    {
      "epoch": 0.0684121159007504,
      "grad_norm": 2.9698598384857178,
      "learning_rate": 0.00019975539180450141,
      "loss": 1.4523,
      "step": 1249
    },
    {
      "epoch": 0.06846688941228023,
      "grad_norm": 4.0287370681762695,
      "learning_rate": 0.00019975498435087502,
      "loss": 0.9453,
      "step": 1250
    },
    {
      "epoch": 0.06852166292381004,
      "grad_norm": 5.590306758880615,
      "learning_rate": 0.00019975457689724863,
      "loss": 1.6463,
      "step": 1251
    },
    {
      "epoch": 0.06857643643533987,
      "grad_norm": 2.1702816486358643,
      "learning_rate": 0.00019975418399553746,
      "loss": 1.1673,
      "step": 1252
    },
    {
      "epoch": 0.06863120994686969,
      "grad_norm": 7.676632404327393,
      "learning_rate": 0.00019975377654191107,
      "loss": 1.1208,
      "step": 1253
    },
    {
      "epoch": 0.06868598345839952,
      "grad_norm": 5.123149394989014,
      "learning_rate": 0.00019975336908828467,
      "loss": 1.7596,
      "step": 1254
    },
    {
      "epoch": 0.06874075696992935,
      "grad_norm": 3.166086435317993,
      "learning_rate": 0.0001997529761865735,
      "loss": 1.8017,
      "step": 1255
    },
    {
      "epoch": 0.06879553048145917,
      "grad_norm": 2.189197540283203,
      "learning_rate": 0.0001997525687329471,
      "loss": 1.0234,
      "step": 1256
    },
    {
      "epoch": 0.06885030399298898,
      "grad_norm": 2.455179214477539,
      "learning_rate": 0.00019975217583123595,
      "loss": 1.2955,
      "step": 1257
    },
    {
      "epoch": 0.06890507750451881,
      "grad_norm": 3.2137863636016846,
      "learning_rate": 0.00019975176837760955,
      "loss": 1.6603,
      "step": 1258
    },
    {
      "epoch": 0.06895985101604864,
      "grad_norm": 2.2944509983062744,
      "learning_rate": 0.00019975136092398316,
      "loss": 1.6804,
      "step": 1259
    },
    {
      "epoch": 0.06901462452757846,
      "grad_norm": 3.4039549827575684,
      "learning_rate": 0.00019975095347035676,
      "loss": 1.3547,
      "step": 1260
    },
    {
      "epoch": 0.06906939803910829,
      "grad_norm": 2.642883777618408,
      "learning_rate": 0.00019975054601673037,
      "loss": 1.6463,
      "step": 1261
    },
    {
      "epoch": 0.06912417155063812,
      "grad_norm": 1.949738621711731,
      "learning_rate": 0.00019975013856310397,
      "loss": 0.9294,
      "step": 1262
    },
    {
      "epoch": 0.06917894506216793,
      "grad_norm": 4.529524803161621,
      "learning_rate": 0.0001997497456613928,
      "loss": 1.5894,
      "step": 1263
    },
    {
      "epoch": 0.06923371857369776,
      "grad_norm": 1.8887587785720825,
      "learning_rate": 0.00019974933820776641,
      "loss": 1.049,
      "step": 1264
    },
    {
      "epoch": 0.06928849208522758,
      "grad_norm": 2.4835293292999268,
      "learning_rate": 0.00019974893075414002,
      "loss": 1.4716,
      "step": 1265
    },
    {
      "epoch": 0.06934326559675741,
      "grad_norm": 5.5841803550720215,
      "learning_rate": 0.00019974852330051363,
      "loss": 0.7601,
      "step": 1266
    },
    {
      "epoch": 0.06939803910828723,
      "grad_norm": 4.702973365783691,
      "learning_rate": 0.000199748101294972,
      "loss": 0.9172,
      "step": 1267
    },
    {
      "epoch": 0.06945281261981706,
      "grad_norm": 4.7085161209106445,
      "learning_rate": 0.0001997476938413456,
      "loss": 1.4569,
      "step": 1268
    },
    {
      "epoch": 0.06950758613134687,
      "grad_norm": 13.339258193969727,
      "learning_rate": 0.00019974730093963444,
      "loss": 1.6687,
      "step": 1269
    },
    {
      "epoch": 0.0695623596428767,
      "grad_norm": 4.346837043762207,
      "learning_rate": 0.00019974689348600805,
      "loss": 1.1901,
      "step": 1270
    },
    {
      "epoch": 0.06961713315440653,
      "grad_norm": 5.981629848480225,
      "learning_rate": 0.00019974648603238165,
      "loss": 2.658,
      "step": 1271
    },
    {
      "epoch": 0.06967190666593635,
      "grad_norm": 2.0462963581085205,
      "learning_rate": 0.00019974606402684003,
      "loss": 0.6666,
      "step": 1272
    },
    {
      "epoch": 0.06972668017746618,
      "grad_norm": 3.678997039794922,
      "learning_rate": 0.00019974565657321364,
      "loss": 1.7808,
      "step": 1273
    },
    {
      "epoch": 0.069781453688996,
      "grad_norm": 2.894195079803467,
      "learning_rate": 0.00019974526367150247,
      "loss": 1.4692,
      "step": 1274
    },
    {
      "epoch": 0.06983622720052582,
      "grad_norm": 3.5003316402435303,
      "learning_rate": 0.00019974484166596085,
      "loss": 1.4932,
      "step": 1275
    },
    {
      "epoch": 0.06989100071205565,
      "grad_norm": 3.0594656467437744,
      "learning_rate": 0.00019974443421233445,
      "loss": 1.4527,
      "step": 1276
    },
    {
      "epoch": 0.06994577422358547,
      "grad_norm": 9.041293144226074,
      "learning_rate": 0.00019974402675870806,
      "loss": 1.6029,
      "step": 1277
    },
    {
      "epoch": 0.0700005477351153,
      "grad_norm": 3.9026949405670166,
      "learning_rate": 0.00019974360475316644,
      "loss": 1.1943,
      "step": 1278
    },
    {
      "epoch": 0.07005532124664512,
      "grad_norm": 4.603769779205322,
      "learning_rate": 0.00019974321185145527,
      "loss": 1.4323,
      "step": 1279
    },
    {
      "epoch": 0.07011009475817495,
      "grad_norm": 3.3320729732513428,
      "learning_rate": 0.00019974278984591365,
      "loss": 1.4102,
      "step": 1280
    },
    {
      "epoch": 0.07016486826970478,
      "grad_norm": 2.2230122089385986,
      "learning_rate": 0.00019974238239228725,
      "loss": 0.8014,
      "step": 1281
    },
    {
      "epoch": 0.07021964178123459,
      "grad_norm": 4.487499713897705,
      "learning_rate": 0.00019974196038674563,
      "loss": 1.7109,
      "step": 1282
    },
    {
      "epoch": 0.07027441529276442,
      "grad_norm": 3.0846621990203857,
      "learning_rate": 0.00019974156748503447,
      "loss": 0.5291,
      "step": 1283
    },
    {
      "epoch": 0.07032918880429424,
      "grad_norm": 7.102634429931641,
      "learning_rate": 0.00019974114547949284,
      "loss": 2.5127,
      "step": 1284
    },
    {
      "epoch": 0.07038396231582407,
      "grad_norm": 3.468806028366089,
      "learning_rate": 0.00019974072347395122,
      "loss": 1.6471,
      "step": 1285
    },
    {
      "epoch": 0.0704387358273539,
      "grad_norm": 2.332357406616211,
      "learning_rate": 0.00019974031602032483,
      "loss": 1.3848,
      "step": 1286
    },
    {
      "epoch": 0.07049350933888372,
      "grad_norm": 2.7777457237243652,
      "learning_rate": 0.00019973990856669843,
      "loss": 1.7371,
      "step": 1287
    },
    {
      "epoch": 0.07054828285041354,
      "grad_norm": 2.6255273818969727,
      "learning_rate": 0.0001997394865611568,
      "loss": 1.3085,
      "step": 1288
    },
    {
      "epoch": 0.07060305636194336,
      "grad_norm": 3.5507466793060303,
      "learning_rate": 0.0001997390645556152,
      "loss": 1.7743,
      "step": 1289
    },
    {
      "epoch": 0.07065782987347319,
      "grad_norm": 3.9390788078308105,
      "learning_rate": 0.0001997386571019888,
      "loss": 1.6855,
      "step": 1290
    },
    {
      "epoch": 0.07071260338500301,
      "grad_norm": 2.493420362472534,
      "learning_rate": 0.0001997382496483624,
      "loss": 1.1921,
      "step": 1291
    },
    {
      "epoch": 0.07076737689653284,
      "grad_norm": 1.562272310256958,
      "learning_rate": 0.00019973782764282078,
      "loss": 0.7508,
      "step": 1292
    },
    {
      "epoch": 0.07082215040806267,
      "grad_norm": 3.4311883449554443,
      "learning_rate": 0.00019973740563727915,
      "loss": 0.7677,
      "step": 1293
    },
    {
      "epoch": 0.07087692391959248,
      "grad_norm": 2.096798896789551,
      "learning_rate": 0.00019973699818365276,
      "loss": 1.2034,
      "step": 1294
    },
    {
      "epoch": 0.0709316974311223,
      "grad_norm": 2.8316807746887207,
      "learning_rate": 0.00019973657617811114,
      "loss": 1.6018,
      "step": 1295
    },
    {
      "epoch": 0.07098647094265213,
      "grad_norm": 16.543968200683594,
      "learning_rate": 0.00019973616872448474,
      "loss": 1.5669,
      "step": 1296
    },
    {
      "epoch": 0.07104124445418196,
      "grad_norm": 5.107069492340088,
      "learning_rate": 0.00019973576127085835,
      "loss": 0.9824,
      "step": 1297
    },
    {
      "epoch": 0.07109601796571179,
      "grad_norm": 6.832019805908203,
      "learning_rate": 0.00019973533926531672,
      "loss": 2.3075,
      "step": 1298
    },
    {
      "epoch": 0.07115079147724161,
      "grad_norm": 2.377495050430298,
      "learning_rate": 0.0001997349172597751,
      "loss": 0.4571,
      "step": 1299
    },
    {
      "epoch": 0.07120556498877142,
      "grad_norm": 3.4131312370300293,
      "learning_rate": 0.0001997345098061487,
      "loss": 1.5311,
      "step": 1300
    },
    {
      "epoch": 0.07120556498877142,
      "eval_loss": 1.459395408630371,
      "eval_runtime": 45.7966,
      "eval_samples_per_second": 2.009,
      "eval_steps_per_second": 2.009,
      "step": 1300
    },
    {
      "epoch": 0.07126033850030125,
      "grad_norm": 3.64912486076355,
      "learning_rate": 0.00019973407324869186,
      "loss": 0.9624,
      "step": 1301
    },
    {
      "epoch": 0.07131511201183108,
      "grad_norm": 2.8525466918945312,
      "learning_rate": 0.00019973365124315023,
      "loss": 1.0188,
      "step": 1302
    },
    {
      "epoch": 0.0713698855233609,
      "grad_norm": 4.298676013946533,
      "learning_rate": 0.00019973324378952384,
      "loss": 1.648,
      "step": 1303
    },
    {
      "epoch": 0.07142465903489073,
      "grad_norm": 7.254672050476074,
      "learning_rate": 0.00019973282178398222,
      "loss": 1.8187,
      "step": 1304
    },
    {
      "epoch": 0.07147943254642056,
      "grad_norm": 6.393044948577881,
      "learning_rate": 0.0001997323997784406,
      "loss": 2.6024,
      "step": 1305
    },
    {
      "epoch": 0.07153420605795037,
      "grad_norm": 2.0393075942993164,
      "learning_rate": 0.0001997319923248142,
      "loss": 0.352,
      "step": 1306
    },
    {
      "epoch": 0.0715889795694802,
      "grad_norm": 12.329167366027832,
      "learning_rate": 0.00019973155576735735,
      "loss": 2.8644,
      "step": 1307
    },
    {
      "epoch": 0.07164375308101002,
      "grad_norm": 5.829715728759766,
      "learning_rate": 0.00019973114831373096,
      "loss": 1.9641,
      "step": 1308
    },
    {
      "epoch": 0.07169852659253985,
      "grad_norm": 8.062182426452637,
      "learning_rate": 0.00019973072630818933,
      "loss": 2.11,
      "step": 1309
    },
    {
      "epoch": 0.07175330010406968,
      "grad_norm": 8.244647026062012,
      "learning_rate": 0.0001997303043026477,
      "loss": 3.8867,
      "step": 1310
    },
    {
      "epoch": 0.0718080736155995,
      "grad_norm": 2.445629835128784,
      "learning_rate": 0.0001997298822971061,
      "loss": 1.4501,
      "step": 1311
    },
    {
      "epoch": 0.07186284712712931,
      "grad_norm": 2.556750535964966,
      "learning_rate": 0.00019972946029156446,
      "loss": 1.9805,
      "step": 1312
    },
    {
      "epoch": 0.07191762063865914,
      "grad_norm": 2.213388442993164,
      "learning_rate": 0.00019972903828602284,
      "loss": 1.3389,
      "step": 1313
    },
    {
      "epoch": 0.07197239415018897,
      "grad_norm": 2.952786922454834,
      "learning_rate": 0.00019972861628048122,
      "loss": 1.4066,
      "step": 1314
    },
    {
      "epoch": 0.0720271676617188,
      "grad_norm": 7.1004486083984375,
      "learning_rate": 0.0001997281942749396,
      "loss": 1.1918,
      "step": 1315
    },
    {
      "epoch": 0.07208194117324862,
      "grad_norm": 2.521646738052368,
      "learning_rate": 0.00019972777226939797,
      "loss": 1.5779,
      "step": 1316
    },
    {
      "epoch": 0.07213671468477845,
      "grad_norm": 3.4332518577575684,
      "learning_rate": 0.00019972735026385635,
      "loss": 1.6124,
      "step": 1317
    },
    {
      "epoch": 0.07219148819630826,
      "grad_norm": 2.055553436279297,
      "learning_rate": 0.00019972692825831473,
      "loss": 1.0485,
      "step": 1318
    },
    {
      "epoch": 0.07224626170783809,
      "grad_norm": 2.366363286972046,
      "learning_rate": 0.00019972649170085788,
      "loss": 1.281,
      "step": 1319
    },
    {
      "epoch": 0.07230103521936791,
      "grad_norm": 2.749699115753174,
      "learning_rate": 0.00019972606969531626,
      "loss": 1.0664,
      "step": 1320
    },
    {
      "epoch": 0.07235580873089774,
      "grad_norm": 1.1750961542129517,
      "learning_rate": 0.00019972564768977463,
      "loss": 0.7534,
      "step": 1321
    },
    {
      "epoch": 0.07241058224242757,
      "grad_norm": 6.893893718719482,
      "learning_rate": 0.000199725225684233,
      "loss": 1.8496,
      "step": 1322
    },
    {
      "epoch": 0.07246535575395739,
      "grad_norm": 2.633424997329712,
      "learning_rate": 0.0001997248036786914,
      "loss": 1.5854,
      "step": 1323
    },
    {
      "epoch": 0.0725201292654872,
      "grad_norm": 4.54069185256958,
      "learning_rate": 0.00019972436712123454,
      "loss": 1.9474,
      "step": 1324
    },
    {
      "epoch": 0.07257490277701703,
      "grad_norm": 5.529918670654297,
      "learning_rate": 0.0001997239451156929,
      "loss": 1.2875,
      "step": 1325
    },
    {
      "epoch": 0.07262967628854686,
      "grad_norm": 3.7261126041412354,
      "learning_rate": 0.0001997235231101513,
      "loss": 1.0508,
      "step": 1326
    },
    {
      "epoch": 0.07268444980007668,
      "grad_norm": 2.423260450363159,
      "learning_rate": 0.00019972310110460967,
      "loss": 1.3947,
      "step": 1327
    },
    {
      "epoch": 0.07273922331160651,
      "grad_norm": 5.715540409088135,
      "learning_rate": 0.00019972266454715282,
      "loss": 1.3463,
      "step": 1328
    },
    {
      "epoch": 0.07279399682313634,
      "grad_norm": 2.0795533657073975,
      "learning_rate": 0.0001997222425416112,
      "loss": 0.9892,
      "step": 1329
    },
    {
      "epoch": 0.07284877033466615,
      "grad_norm": 3.5038645267486572,
      "learning_rate": 0.00019972180598415434,
      "loss": 0.3981,
      "step": 1330
    },
    {
      "epoch": 0.07290354384619598,
      "grad_norm": 2.457761764526367,
      "learning_rate": 0.00019972138397861272,
      "loss": 0.8074,
      "step": 1331
    },
    {
      "epoch": 0.0729583173577258,
      "grad_norm": 2.1619420051574707,
      "learning_rate": 0.0001997209619730711,
      "loss": 1.2293,
      "step": 1332
    },
    {
      "epoch": 0.07301309086925563,
      "grad_norm": 1.08673894405365,
      "learning_rate": 0.00019972052541561425,
      "loss": 0.6418,
      "step": 1333
    },
    {
      "epoch": 0.07306786438078545,
      "grad_norm": 3.940671682357788,
      "learning_rate": 0.00019972010341007262,
      "loss": 1.2594,
      "step": 1334
    },
    {
      "epoch": 0.07312263789231528,
      "grad_norm": 5.109888076782227,
      "learning_rate": 0.000199719681404531,
      "loss": 1.0922,
      "step": 1335
    },
    {
      "epoch": 0.0731774114038451,
      "grad_norm": 1.9406392574310303,
      "learning_rate": 0.00019971924484707415,
      "loss": 1.0079,
      "step": 1336
    },
    {
      "epoch": 0.07323218491537492,
      "grad_norm": 9.918652534484863,
      "learning_rate": 0.00019971882284153253,
      "loss": 1.8914,
      "step": 1337
    },
    {
      "epoch": 0.07328695842690475,
      "grad_norm": 3.4552762508392334,
      "learning_rate": 0.00019971837173216045,
      "loss": 1.4941,
      "step": 1338
    },
    {
      "epoch": 0.07334173193843457,
      "grad_norm": 6.838827133178711,
      "learning_rate": 0.00019971794972661883,
      "loss": 2.0995,
      "step": 1339
    },
    {
      "epoch": 0.0733965054499644,
      "grad_norm": 11.89675521850586,
      "learning_rate": 0.00019971751316916198,
      "loss": 0.8273,
      "step": 1340
    },
    {
      "epoch": 0.07345127896149423,
      "grad_norm": 3.4899277687072754,
      "learning_rate": 0.00019971709116362035,
      "loss": 1.5056,
      "step": 1341
    },
    {
      "epoch": 0.07350605247302404,
      "grad_norm": 2.987988233566284,
      "learning_rate": 0.0001997166546061635,
      "loss": 1.3964,
      "step": 1342
    },
    {
      "epoch": 0.07356082598455387,
      "grad_norm": 2.6275718212127686,
      "learning_rate": 0.00019971623260062188,
      "loss": 1.1333,
      "step": 1343
    },
    {
      "epoch": 0.07361559949608369,
      "grad_norm": 7.408626556396484,
      "learning_rate": 0.0001997157814912498,
      "loss": 1.0796,
      "step": 1344
    },
    {
      "epoch": 0.07367037300761352,
      "grad_norm": 5.459932327270508,
      "learning_rate": 0.00019971535948570818,
      "loss": 1.3646,
      "step": 1345
    },
    {
      "epoch": 0.07372514651914334,
      "grad_norm": 7.099188804626465,
      "learning_rate": 0.00019971492292825133,
      "loss": 3.1107,
      "step": 1346
    },
    {
      "epoch": 0.07377992003067317,
      "grad_norm": 12.144237518310547,
      "learning_rate": 0.00019971448637079448,
      "loss": 2.1004,
      "step": 1347
    },
    {
      "epoch": 0.07383469354220298,
      "grad_norm": 1.8617298603057861,
      "learning_rate": 0.00019971406436525285,
      "loss": 0.8432,
      "step": 1348
    },
    {
      "epoch": 0.07388946705373281,
      "grad_norm": 2.5120038986206055,
      "learning_rate": 0.000199713627807796,
      "loss": 1.3939,
      "step": 1349
    },
    {
      "epoch": 0.07394424056526264,
      "grad_norm": 2.7750964164733887,
      "learning_rate": 0.00019971319125033915,
      "loss": 1.0774,
      "step": 1350
    },
    {
      "epoch": 0.07399901407679246,
      "grad_norm": 7.792165756225586,
      "learning_rate": 0.0001997127546928823,
      "loss": 2.1514,
      "step": 1351
    },
    {
      "epoch": 0.07405378758832229,
      "grad_norm": 2.678107261657715,
      "learning_rate": 0.00019971231813542545,
      "loss": 1.3419,
      "step": 1352
    },
    {
      "epoch": 0.07410856109985212,
      "grad_norm": 4.875060081481934,
      "learning_rate": 0.00019971189612988383,
      "loss": 1.257,
      "step": 1353
    },
    {
      "epoch": 0.07416333461138194,
      "grad_norm": 3.7907209396362305,
      "learning_rate": 0.00019971144502051175,
      "loss": 1.6065,
      "step": 1354
    },
    {
      "epoch": 0.07421810812291176,
      "grad_norm": 2.639202833175659,
      "learning_rate": 0.00019971102301497012,
      "loss": 1.3683,
      "step": 1355
    },
    {
      "epoch": 0.07427288163444158,
      "grad_norm": 13.316210746765137,
      "learning_rate": 0.00019971057190559804,
      "loss": 3.7714,
      "step": 1356
    },
    {
      "epoch": 0.07432765514597141,
      "grad_norm": 8.403239250183105,
      "learning_rate": 0.0001997101353481412,
      "loss": 2.0415,
      "step": 1357
    },
    {
      "epoch": 0.07438242865750123,
      "grad_norm": 1.3934814929962158,
      "learning_rate": 0.00019970971334259957,
      "loss": 0.7938,
      "step": 1358
    },
    {
      "epoch": 0.07443720216903106,
      "grad_norm": 3.599116325378418,
      "learning_rate": 0.0001997092622332275,
      "loss": 1.9304,
      "step": 1359
    },
    {
      "epoch": 0.07449197568056089,
      "grad_norm": 3.190457344055176,
      "learning_rate": 0.00019970882567577064,
      "loss": 1.6242,
      "step": 1360
    },
    {
      "epoch": 0.0745467491920907,
      "grad_norm": 2.3421385288238525,
      "learning_rate": 0.00019970840367022902,
      "loss": 1.1676,
      "step": 1361
    },
    {
      "epoch": 0.07460152270362053,
      "grad_norm": 3.0451178550720215,
      "learning_rate": 0.00019970795256085694,
      "loss": 1.2988,
      "step": 1362
    },
    {
      "epoch": 0.07465629621515035,
      "grad_norm": 1.7495276927947998,
      "learning_rate": 0.0001997075160034001,
      "loss": 0.8313,
      "step": 1363
    },
    {
      "epoch": 0.07471106972668018,
      "grad_norm": 7.3457865715026855,
      "learning_rate": 0.00019970707944594324,
      "loss": 2.2794,
      "step": 1364
    },
    {
      "epoch": 0.07476584323821,
      "grad_norm": 8.784904479980469,
      "learning_rate": 0.00019970664288848639,
      "loss": 0.8609,
      "step": 1365
    },
    {
      "epoch": 0.07482061674973983,
      "grad_norm": 8.261711120605469,
      "learning_rate": 0.00019970620633102953,
      "loss": 2.1192,
      "step": 1366
    },
    {
      "epoch": 0.07487539026126964,
      "grad_norm": 2.4588255882263184,
      "learning_rate": 0.00019970576977357268,
      "loss": 1.7409,
      "step": 1367
    },
    {
      "epoch": 0.07493016377279947,
      "grad_norm": 2.647510290145874,
      "learning_rate": 0.0001997053186642006,
      "loss": 1.1309,
      "step": 1368
    },
    {
      "epoch": 0.0749849372843293,
      "grad_norm": 4.713809967041016,
      "learning_rate": 0.00019970488210674375,
      "loss": 1.4397,
      "step": 1369
    },
    {
      "epoch": 0.07503971079585912,
      "grad_norm": 2.665269613265991,
      "learning_rate": 0.0001997044455492869,
      "loss": 1.3242,
      "step": 1370
    },
    {
      "epoch": 0.07509448430738895,
      "grad_norm": 4.076387882232666,
      "learning_rate": 0.00019970399443991482,
      "loss": 1.5392,
      "step": 1371
    },
    {
      "epoch": 0.07514925781891878,
      "grad_norm": 1.9091569185256958,
      "learning_rate": 0.00019970355788245797,
      "loss": 1.2195,
      "step": 1372
    },
    {
      "epoch": 0.07520403133044859,
      "grad_norm": 2.2873106002807617,
      "learning_rate": 0.00019970312132500112,
      "loss": 0.8205,
      "step": 1373
    },
    {
      "epoch": 0.07525880484197842,
      "grad_norm": 4.111666679382324,
      "learning_rate": 0.00019970267021562904,
      "loss": 0.4306,
      "step": 1374
    },
    {
      "epoch": 0.07531357835350824,
      "grad_norm": 10.324019432067871,
      "learning_rate": 0.0001997022336581722,
      "loss": 2.3714,
      "step": 1375
    },
    {
      "epoch": 0.07536835186503807,
      "grad_norm": 5.931121349334717,
      "learning_rate": 0.00019970179710071534,
      "loss": 1.9876,
      "step": 1376
    },
    {
      "epoch": 0.0754231253765679,
      "grad_norm": 2.2839603424072266,
      "learning_rate": 0.00019970134599134326,
      "loss": 1.3146,
      "step": 1377
    },
    {
      "epoch": 0.07547789888809772,
      "grad_norm": 5.223237037658691,
      "learning_rate": 0.00019970089488197118,
      "loss": 2.388,
      "step": 1378
    },
    {
      "epoch": 0.07553267239962753,
      "grad_norm": 3.1868598461151123,
      "learning_rate": 0.00019970045832451433,
      "loss": 1.5868,
      "step": 1379
    },
    {
      "epoch": 0.07558744591115736,
      "grad_norm": 14.203368186950684,
      "learning_rate": 0.00019970002176705748,
      "loss": 3.6402,
      "step": 1380
    },
    {
      "epoch": 0.07564221942268719,
      "grad_norm": 2.201968193054199,
      "learning_rate": 0.0001996995706576854,
      "loss": 0.9403,
      "step": 1381
    },
    {
      "epoch": 0.07569699293421701,
      "grad_norm": 10.802267074584961,
      "learning_rate": 0.00019969911954831332,
      "loss": 0.8877,
      "step": 1382
    },
    {
      "epoch": 0.07575176644574684,
      "grad_norm": 2.601930856704712,
      "learning_rate": 0.00019969868299085647,
      "loss": 1.346,
      "step": 1383
    },
    {
      "epoch": 0.07580653995727667,
      "grad_norm": 2.515486001968384,
      "learning_rate": 0.0001996982318814844,
      "loss": 1.5706,
      "step": 1384
    },
    {
      "epoch": 0.07586131346880648,
      "grad_norm": 2.307457208633423,
      "learning_rate": 0.0001996977807721123,
      "loss": 1.3073,
      "step": 1385
    },
    {
      "epoch": 0.0759160869803363,
      "grad_norm": 4.8957014083862305,
      "learning_rate": 0.00019969734421465546,
      "loss": 0.9373,
      "step": 1386
    },
    {
      "epoch": 0.07597086049186613,
      "grad_norm": 2.586819648742676,
      "learning_rate": 0.00019969689310528338,
      "loss": 1.1469,
      "step": 1387
    },
    {
      "epoch": 0.07602563400339596,
      "grad_norm": 2.8200254440307617,
      "learning_rate": 0.00019969645654782653,
      "loss": 0.8777,
      "step": 1388
    },
    {
      "epoch": 0.07608040751492579,
      "grad_norm": 6.714654922485352,
      "learning_rate": 0.00019969600543845445,
      "loss": 1.3261,
      "step": 1389
    },
    {
      "epoch": 0.07613518102645561,
      "grad_norm": 13.426777839660645,
      "learning_rate": 0.00019969555432908237,
      "loss": 4.1562,
      "step": 1390
    },
    {
      "epoch": 0.07618995453798542,
      "grad_norm": 4.611935615539551,
      "learning_rate": 0.0001996951032197103,
      "loss": 1.3565,
      "step": 1391
    },
    {
      "epoch": 0.07624472804951525,
      "grad_norm": 7.063266754150391,
      "learning_rate": 0.00019969466666225344,
      "loss": 1.4492,
      "step": 1392
    },
    {
      "epoch": 0.07629950156104508,
      "grad_norm": 9.437365531921387,
      "learning_rate": 0.00019969421555288136,
      "loss": 2.2908,
      "step": 1393
    },
    {
      "epoch": 0.0763542750725749,
      "grad_norm": 3.3332529067993164,
      "learning_rate": 0.00019969376444350928,
      "loss": 1.7321,
      "step": 1394
    },
    {
      "epoch": 0.07640904858410473,
      "grad_norm": 3.3247127532958984,
      "learning_rate": 0.0001996933133341372,
      "loss": 1.0544,
      "step": 1395
    },
    {
      "epoch": 0.07646382209563456,
      "grad_norm": 2.4913370609283447,
      "learning_rate": 0.00019969286222476512,
      "loss": 1.3001,
      "step": 1396
    },
    {
      "epoch": 0.07651859560716437,
      "grad_norm": 6.313663005828857,
      "learning_rate": 0.00019969241111539304,
      "loss": 2.185,
      "step": 1397
    },
    {
      "epoch": 0.0765733691186942,
      "grad_norm": 7.651676177978516,
      "learning_rate": 0.0001996919745579362,
      "loss": 2.797,
      "step": 1398
    },
    {
      "epoch": 0.07662814263022402,
      "grad_norm": 7.065035343170166,
      "learning_rate": 0.0001996915234485641,
      "loss": 2.5792,
      "step": 1399
    },
    {
      "epoch": 0.07668291614175385,
      "grad_norm": 2.3807780742645264,
      "learning_rate": 0.0001996910577872768,
      "loss": 1.436,
      "step": 1400
    },
    {
      "epoch": 0.07668291614175385,
      "eval_loss": 1.4525727033615112,
      "eval_runtime": 45.8053,
      "eval_samples_per_second": 2.009,
      "eval_steps_per_second": 2.009,
      "step": 1400
    },
    {
      "epoch": 0.07673768965328367,
      "grad_norm": 9.077579498291016,
      "learning_rate": 0.00019969060667790473,
      "loss": 2.4923,
      "step": 1401
    },
    {
      "epoch": 0.0767924631648135,
      "grad_norm": 3.8380625247955322,
      "learning_rate": 0.00019969015556853265,
      "loss": 1.4181,
      "step": 1402
    },
    {
      "epoch": 0.07684723667634331,
      "grad_norm": 2.3056206703186035,
      "learning_rate": 0.00019968970445916057,
      "loss": 1.5407,
      "step": 1403
    },
    {
      "epoch": 0.07690201018787314,
      "grad_norm": 1.9002110958099365,
      "learning_rate": 0.00019968926790170372,
      "loss": 0.957,
      "step": 1404
    },
    {
      "epoch": 0.07695678369940297,
      "grad_norm": 5.634620189666748,
      "learning_rate": 0.00019968881679233164,
      "loss": 1.3134,
      "step": 1405
    },
    {
      "epoch": 0.0770115572109328,
      "grad_norm": 11.967138290405273,
      "learning_rate": 0.00019968835113104433,
      "loss": 2.6731,
      "step": 1406
    },
    {
      "epoch": 0.07706633072246262,
      "grad_norm": 2.0894951820373535,
      "learning_rate": 0.00019968790002167225,
      "loss": 0.7808,
      "step": 1407
    },
    {
      "epoch": 0.07712110423399245,
      "grad_norm": 18.491823196411133,
      "learning_rate": 0.00019968744891230017,
      "loss": 2.8688,
      "step": 1408
    },
    {
      "epoch": 0.07717587774552226,
      "grad_norm": 9.050490379333496,
      "learning_rate": 0.0001996869978029281,
      "loss": 2.2145,
      "step": 1409
    },
    {
      "epoch": 0.07723065125705209,
      "grad_norm": 6.675502777099609,
      "learning_rate": 0.00019968653214164078,
      "loss": 2.0829,
      "step": 1410
    },
    {
      "epoch": 0.07728542476858191,
      "grad_norm": 7.930744647979736,
      "learning_rate": 0.0001996860810322687,
      "loss": 2.5591,
      "step": 1411
    },
    {
      "epoch": 0.07734019828011174,
      "grad_norm": 4.81467342376709,
      "learning_rate": 0.00019968562992289662,
      "loss": 0.3347,
      "step": 1412
    },
    {
      "epoch": 0.07739497179164156,
      "grad_norm": 2.0812339782714844,
      "learning_rate": 0.00019968517881352454,
      "loss": 1.1117,
      "step": 1413
    },
    {
      "epoch": 0.07744974530317139,
      "grad_norm": 3.3654088973999023,
      "learning_rate": 0.00019968472770415246,
      "loss": 0.9469,
      "step": 1414
    },
    {
      "epoch": 0.0775045188147012,
      "grad_norm": 2.1594812870025635,
      "learning_rate": 0.00019968426204286516,
      "loss": 1.4124,
      "step": 1415
    },
    {
      "epoch": 0.07755929232623103,
      "grad_norm": 3.639871835708618,
      "learning_rate": 0.00019968381093349308,
      "loss": 1.2511,
      "step": 1416
    },
    {
      "epoch": 0.07761406583776086,
      "grad_norm": 4.981328964233398,
      "learning_rate": 0.00019968334527220577,
      "loss": 1.1628,
      "step": 1417
    },
    {
      "epoch": 0.07766883934929068,
      "grad_norm": 4.922358989715576,
      "learning_rate": 0.0001996828941628337,
      "loss": 1.9897,
      "step": 1418
    },
    {
      "epoch": 0.07772361286082051,
      "grad_norm": 2.469970464706421,
      "learning_rate": 0.0001996824430534616,
      "loss": 1.4061,
      "step": 1419
    },
    {
      "epoch": 0.07777838637235034,
      "grad_norm": 3.9825384616851807,
      "learning_rate": 0.0001996819773921743,
      "loss": 1.1992,
      "step": 1420
    },
    {
      "epoch": 0.07783315988388016,
      "grad_norm": 2.309727430343628,
      "learning_rate": 0.00019968152628280222,
      "loss": 0.934,
      "step": 1421
    },
    {
      "epoch": 0.07788793339540998,
      "grad_norm": 3.8918237686157227,
      "learning_rate": 0.00019968106062151492,
      "loss": 2.3531,
      "step": 1422
    },
    {
      "epoch": 0.0779427069069398,
      "grad_norm": 3.5171124935150146,
      "learning_rate": 0.00019968060951214284,
      "loss": 1.4548,
      "step": 1423
    },
    {
      "epoch": 0.07799748041846963,
      "grad_norm": 3.621835231781006,
      "learning_rate": 0.00019968015840277076,
      "loss": 0.6247,
      "step": 1424
    },
    {
      "epoch": 0.07805225392999945,
      "grad_norm": 2.8866190910339355,
      "learning_rate": 0.00019967969274148345,
      "loss": 1.1846,
      "step": 1425
    },
    {
      "epoch": 0.07810702744152928,
      "grad_norm": 4.434223651885986,
      "learning_rate": 0.00019967924163211137,
      "loss": 1.1794,
      "step": 1426
    },
    {
      "epoch": 0.07816180095305911,
      "grad_norm": 2.4676835536956787,
      "learning_rate": 0.00019967877597082406,
      "loss": 1.3145,
      "step": 1427
    },
    {
      "epoch": 0.07821657446458892,
      "grad_norm": 2.8481316566467285,
      "learning_rate": 0.00019967831030953676,
      "loss": 0.2393,
      "step": 1428
    },
    {
      "epoch": 0.07827134797611875,
      "grad_norm": 2.823312520980835,
      "learning_rate": 0.00019967785920016468,
      "loss": 0.9355,
      "step": 1429
    },
    {
      "epoch": 0.07832612148764857,
      "grad_norm": 4.501286506652832,
      "learning_rate": 0.00019967739353887737,
      "loss": 1.3263,
      "step": 1430
    },
    {
      "epoch": 0.0783808949991784,
      "grad_norm": 5.196568489074707,
      "learning_rate": 0.0001996769424295053,
      "loss": 1.75,
      "step": 1431
    },
    {
      "epoch": 0.07843566851070823,
      "grad_norm": 1.9867002964019775,
      "learning_rate": 0.00019967647676821798,
      "loss": 1.0372,
      "step": 1432
    },
    {
      "epoch": 0.07849044202223805,
      "grad_norm": 2.329399824142456,
      "learning_rate": 0.00019967601110693067,
      "loss": 1.2029,
      "step": 1433
    },
    {
      "epoch": 0.07854521553376786,
      "grad_norm": 10.428762435913086,
      "learning_rate": 0.00019967554544564337,
      "loss": 2.8858,
      "step": 1434
    },
    {
      "epoch": 0.07859998904529769,
      "grad_norm": 4.388474464416504,
      "learning_rate": 0.00019967509433627129,
      "loss": 1.5661,
      "step": 1435
    },
    {
      "epoch": 0.07865476255682752,
      "grad_norm": 1.9230912923812866,
      "learning_rate": 0.00019967462867498398,
      "loss": 0.9729,
      "step": 1436
    },
    {
      "epoch": 0.07870953606835734,
      "grad_norm": 2.4774575233459473,
      "learning_rate": 0.00019967416301369667,
      "loss": 1.2177,
      "step": 1437
    },
    {
      "epoch": 0.07876430957988717,
      "grad_norm": 2.211354970932007,
      "learning_rate": 0.00019967369735240936,
      "loss": 1.2408,
      "step": 1438
    },
    {
      "epoch": 0.078819083091417,
      "grad_norm": 3.0999834537506104,
      "learning_rate": 0.00019967323169112206,
      "loss": 1.5709,
      "step": 1439
    },
    {
      "epoch": 0.07887385660294681,
      "grad_norm": 2.4165666103363037,
      "learning_rate": 0.00019967276602983475,
      "loss": 1.2278,
      "step": 1440
    },
    {
      "epoch": 0.07892863011447664,
      "grad_norm": 23.898090362548828,
      "learning_rate": 0.00019967231492046267,
      "loss": 4.4609,
      "step": 1441
    },
    {
      "epoch": 0.07898340362600646,
      "grad_norm": 5.140242576599121,
      "learning_rate": 0.00019967184925917536,
      "loss": 1.4995,
      "step": 1442
    },
    {
      "epoch": 0.07903817713753629,
      "grad_norm": 4.646583080291748,
      "learning_rate": 0.00019967138359788805,
      "loss": 1.3869,
      "step": 1443
    },
    {
      "epoch": 0.07909295064906612,
      "grad_norm": 13.000452995300293,
      "learning_rate": 0.00019967091793660074,
      "loss": 1.0249,
      "step": 1444
    },
    {
      "epoch": 0.07914772416059594,
      "grad_norm": 18.49662971496582,
      "learning_rate": 0.00019967045227531344,
      "loss": 0.9563,
      "step": 1445
    },
    {
      "epoch": 0.07920249767212575,
      "grad_norm": 11.53803539276123,
      "learning_rate": 0.0001996699720621109,
      "loss": 2.6065,
      "step": 1446
    },
    {
      "epoch": 0.07925727118365558,
      "grad_norm": 2.710165023803711,
      "learning_rate": 0.0001996695064008236,
      "loss": 1.417,
      "step": 1447
    },
    {
      "epoch": 0.07931204469518541,
      "grad_norm": 7.959472179412842,
      "learning_rate": 0.00019966904073953629,
      "loss": 1.9872,
      "step": 1448
    },
    {
      "epoch": 0.07936681820671523,
      "grad_norm": 3.0780301094055176,
      "learning_rate": 0.00019966857507824898,
      "loss": 1.8723,
      "step": 1449
    },
    {
      "epoch": 0.07942159171824506,
      "grad_norm": 3.122063159942627,
      "learning_rate": 0.00019966810941696167,
      "loss": 1.0471,
      "step": 1450
    },
    {
      "epoch": 0.07947636522977489,
      "grad_norm": 5.577142238616943,
      "learning_rate": 0.0001996676583075896,
      "loss": 0.8737,
      "step": 1451
    },
    {
      "epoch": 0.0795311387413047,
      "grad_norm": 2.5648083686828613,
      "learning_rate": 0.00019966717809438705,
      "loss": 1.841,
      "step": 1452
    },
    {
      "epoch": 0.07958591225283453,
      "grad_norm": 13.036639213562012,
      "learning_rate": 0.00019966671243309975,
      "loss": 2.5821,
      "step": 1453
    },
    {
      "epoch": 0.07964068576436435,
      "grad_norm": 5.561155319213867,
      "learning_rate": 0.00019966624677181244,
      "loss": 2.4185,
      "step": 1454
    },
    {
      "epoch": 0.07969545927589418,
      "grad_norm": 4.362271308898926,
      "learning_rate": 0.00019966578111052513,
      "loss": 1.4128,
      "step": 1455
    },
    {
      "epoch": 0.079750232787424,
      "grad_norm": 2.4462544918060303,
      "learning_rate": 0.0001996653008973226,
      "loss": 1.4017,
      "step": 1456
    },
    {
      "epoch": 0.07980500629895383,
      "grad_norm": 3.0277044773101807,
      "learning_rate": 0.0001996648352360353,
      "loss": 1.2262,
      "step": 1457
    },
    {
      "epoch": 0.07985977981048364,
      "grad_norm": 2.587843179702759,
      "learning_rate": 0.00019966436957474798,
      "loss": 1.6021,
      "step": 1458
    },
    {
      "epoch": 0.07991455332201347,
      "grad_norm": 1.9765968322753906,
      "learning_rate": 0.00019966388936154544,
      "loss": 1.0098,
      "step": 1459
    },
    {
      "epoch": 0.0799693268335433,
      "grad_norm": 2.372321844100952,
      "learning_rate": 0.00019966343825217336,
      "loss": 1.5524,
      "step": 1460
    },
    {
      "epoch": 0.08002410034507312,
      "grad_norm": 3.6783149242401123,
      "learning_rate": 0.00019966295803897083,
      "loss": 0.9837,
      "step": 1461
    },
    {
      "epoch": 0.08007887385660295,
      "grad_norm": 5.807269096374512,
      "learning_rate": 0.00019966249237768352,
      "loss": 2.4054,
      "step": 1462
    },
    {
      "epoch": 0.08013364736813278,
      "grad_norm": 3.8301377296447754,
      "learning_rate": 0.00019966201216448098,
      "loss": 1.9325,
      "step": 1463
    },
    {
      "epoch": 0.08018842087966259,
      "grad_norm": 2.1701607704162598,
      "learning_rate": 0.00019966154650319368,
      "loss": 1.3704,
      "step": 1464
    },
    {
      "epoch": 0.08024319439119242,
      "grad_norm": 2.4040915966033936,
      "learning_rate": 0.00019966106628999114,
      "loss": 1.3143,
      "step": 1465
    },
    {
      "epoch": 0.08029796790272224,
      "grad_norm": 2.6740150451660156,
      "learning_rate": 0.00019966060062870383,
      "loss": 1.9036,
      "step": 1466
    },
    {
      "epoch": 0.08035274141425207,
      "grad_norm": 1.999948263168335,
      "learning_rate": 0.00019966013496741652,
      "loss": 1.0367,
      "step": 1467
    },
    {
      "epoch": 0.0804075149257819,
      "grad_norm": 3.7520833015441895,
      "learning_rate": 0.000199659654754214,
      "loss": 2.0978,
      "step": 1468
    },
    {
      "epoch": 0.08046228843731172,
      "grad_norm": 4.63543176651001,
      "learning_rate": 0.00019965917454101145,
      "loss": 1.5354,
      "step": 1469
    },
    {
      "epoch": 0.08051706194884153,
      "grad_norm": 5.335099697113037,
      "learning_rate": 0.00019965870887972414,
      "loss": 0.8611,
      "step": 1470
    },
    {
      "epoch": 0.08057183546037136,
      "grad_norm": 4.00559139251709,
      "learning_rate": 0.0001996582286665216,
      "loss": 1.3418,
      "step": 1471
    },
    {
      "epoch": 0.08062660897190119,
      "grad_norm": 3.0016591548919678,
      "learning_rate": 0.0001996577630052343,
      "loss": 1.2661,
      "step": 1472
    },
    {
      "epoch": 0.08068138248343101,
      "grad_norm": 4.118222713470459,
      "learning_rate": 0.00019965728279203176,
      "loss": 1.782,
      "step": 1473
    },
    {
      "epoch": 0.08073615599496084,
      "grad_norm": 11.117999076843262,
      "learning_rate": 0.00019965680257882923,
      "loss": 2.1877,
      "step": 1474
    },
    {
      "epoch": 0.08079092950649067,
      "grad_norm": 16.499534606933594,
      "learning_rate": 0.00019965633691754192,
      "loss": 1.6707,
      "step": 1475
    },
    {
      "epoch": 0.08084570301802048,
      "grad_norm": 7.0326104164123535,
      "learning_rate": 0.00019965585670433939,
      "loss": 2.0197,
      "step": 1476
    },
    {
      "epoch": 0.0809004765295503,
      "grad_norm": 3.946012258529663,
      "learning_rate": 0.00019965539104305208,
      "loss": 1.709,
      "step": 1477
    },
    {
      "epoch": 0.08095525004108013,
      "grad_norm": 1.8866736888885498,
      "learning_rate": 0.00019965491082984954,
      "loss": 0.8602,
      "step": 1478
    },
    {
      "epoch": 0.08101002355260996,
      "grad_norm": 1.8353054523468018,
      "learning_rate": 0.000199654430616647,
      "loss": 0.6678,
      "step": 1479
    },
    {
      "epoch": 0.08106479706413978,
      "grad_norm": 2.269958972930908,
      "learning_rate": 0.00019965395040344447,
      "loss": 1.1417,
      "step": 1480
    },
    {
      "epoch": 0.08111957057566961,
      "grad_norm": 6.572633266448975,
      "learning_rate": 0.00019965347019024193,
      "loss": 2.938,
      "step": 1481
    },
    {
      "epoch": 0.08117434408719942,
      "grad_norm": 2.709977149963379,
      "learning_rate": 0.00019965300452895463,
      "loss": 1.3618,
      "step": 1482
    },
    {
      "epoch": 0.08122911759872925,
      "grad_norm": 3.5330874919891357,
      "learning_rate": 0.0001996525243157521,
      "loss": 2.1012,
      "step": 1483
    },
    {
      "epoch": 0.08128389111025908,
      "grad_norm": 9.052667617797852,
      "learning_rate": 0.00019965204410254955,
      "loss": 2.6081,
      "step": 1484
    },
    {
      "epoch": 0.0813386646217889,
      "grad_norm": 2.9612131118774414,
      "learning_rate": 0.00019965156388934702,
      "loss": 1.4694,
      "step": 1485
    },
    {
      "epoch": 0.08139343813331873,
      "grad_norm": 2.409897565841675,
      "learning_rate": 0.00019965108367614448,
      "loss": 1.3398,
      "step": 1486
    },
    {
      "epoch": 0.08144821164484856,
      "grad_norm": 25.36638832092285,
      "learning_rate": 0.00019965060346294194,
      "loss": 5.4219,
      "step": 1487
    },
    {
      "epoch": 0.08150298515637837,
      "grad_norm": 3.5509581565856934,
      "learning_rate": 0.0001996501232497394,
      "loss": 0.9825,
      "step": 1488
    },
    {
      "epoch": 0.0815577586679082,
      "grad_norm": 2.419881582260132,
      "learning_rate": 0.0001996496575884521,
      "loss": 1.2551,
      "step": 1489
    },
    {
      "epoch": 0.08161253217943802,
      "grad_norm": 2.4005820751190186,
      "learning_rate": 0.00019964916282333434,
      "loss": 1.4931,
      "step": 1490
    },
    {
      "epoch": 0.08166730569096785,
      "grad_norm": 4.326116561889648,
      "learning_rate": 0.0001996486826101318,
      "loss": 1.357,
      "step": 1491
    },
    {
      "epoch": 0.08172207920249767,
      "grad_norm": 2.7888262271881104,
      "learning_rate": 0.00019964820239692926,
      "loss": 1.205,
      "step": 1492
    },
    {
      "epoch": 0.0817768527140275,
      "grad_norm": 8.663041114807129,
      "learning_rate": 0.00019964772218372673,
      "loss": 1.8428,
      "step": 1493
    },
    {
      "epoch": 0.08183162622555733,
      "grad_norm": 3.3990867137908936,
      "learning_rate": 0.0001996472419705242,
      "loss": 1.4949,
      "step": 1494
    },
    {
      "epoch": 0.08188639973708714,
      "grad_norm": 13.5848970413208,
      "learning_rate": 0.00019964676175732166,
      "loss": 2.6723,
      "step": 1495
    },
    {
      "epoch": 0.08194117324861697,
      "grad_norm": 3.253664255142212,
      "learning_rate": 0.00019964628154411912,
      "loss": 2.2548,
      "step": 1496
    },
    {
      "epoch": 0.08199594676014679,
      "grad_norm": 14.445476531982422,
      "learning_rate": 0.00019964580133091658,
      "loss": 2.1907,
      "step": 1497
    },
    {
      "epoch": 0.08205072027167662,
      "grad_norm": 2.473802328109741,
      "learning_rate": 0.00019964530656579882,
      "loss": 1.3988,
      "step": 1498
    },
    {
      "epoch": 0.08210549378320645,
      "grad_norm": 3.46917986869812,
      "learning_rate": 0.0001996448409045115,
      "loss": 1.3282,
      "step": 1499
    },
    {
      "epoch": 0.08216026729473627,
      "grad_norm": 3.1851043701171875,
      "learning_rate": 0.00019964434613939375,
      "loss": 2.0431,
      "step": 1500
    },
    {
      "epoch": 0.08216026729473627,
      "eval_loss": 1.4487701654434204,
      "eval_runtime": 45.7908,
      "eval_samples_per_second": 2.009,
      "eval_steps_per_second": 2.009,
      "step": 1500
    },
    {
      "epoch": 0.08221504080626608,
      "grad_norm": 2.644230365753174,
      "learning_rate": 0.00019964385137427598,
      "loss": 1.0201,
      "step": 1501
    },
    {
      "epoch": 0.08226981431779591,
      "grad_norm": 3.3109381198883057,
      "learning_rate": 0.00019964338571298867,
      "loss": 2.1633,
      "step": 1502
    },
    {
      "epoch": 0.08232458782932574,
      "grad_norm": 2.2769994735717773,
      "learning_rate": 0.0001996428909478709,
      "loss": 0.9587,
      "step": 1503
    },
    {
      "epoch": 0.08237936134085556,
      "grad_norm": 18.05397605895996,
      "learning_rate": 0.00019964241073466837,
      "loss": 5.8203,
      "step": 1504
    },
    {
      "epoch": 0.08243413485238539,
      "grad_norm": 4.970171928405762,
      "learning_rate": 0.00019964193052146584,
      "loss": 1.9049,
      "step": 1505
    },
    {
      "epoch": 0.08248890836391522,
      "grad_norm": 2.5732288360595703,
      "learning_rate": 0.00019964143575634807,
      "loss": 1.8356,
      "step": 1506
    },
    {
      "epoch": 0.08254368187544503,
      "grad_norm": 5.276823043823242,
      "learning_rate": 0.00019964095554314554,
      "loss": 1.7411,
      "step": 1507
    },
    {
      "epoch": 0.08259845538697486,
      "grad_norm": 2.517587661743164,
      "learning_rate": 0.000199640475329943,
      "loss": 1.3749,
      "step": 1508
    },
    {
      "epoch": 0.08265322889850468,
      "grad_norm": 2.749763250350952,
      "learning_rate": 0.00019963998056482524,
      "loss": 1.24,
      "step": 1509
    },
    {
      "epoch": 0.08270800241003451,
      "grad_norm": 3.0508553981781006,
      "learning_rate": 0.0001996395003516227,
      "loss": 1.2107,
      "step": 1510
    },
    {
      "epoch": 0.08276277592156434,
      "grad_norm": 2.6661288738250732,
      "learning_rate": 0.00019963900558650494,
      "loss": 0.4588,
      "step": 1511
    },
    {
      "epoch": 0.08281754943309416,
      "grad_norm": 2.103199005126953,
      "learning_rate": 0.00019963851082138717,
      "loss": 0.5174,
      "step": 1512
    },
    {
      "epoch": 0.08287232294462397,
      "grad_norm": 1.9838420152664185,
      "learning_rate": 0.00019963803060818464,
      "loss": 1.1079,
      "step": 1513
    },
    {
      "epoch": 0.0829270964561538,
      "grad_norm": 5.811516761779785,
      "learning_rate": 0.00019963753584306687,
      "loss": 1.802,
      "step": 1514
    },
    {
      "epoch": 0.08298186996768363,
      "grad_norm": 3.9923489093780518,
      "learning_rate": 0.00019963705562986434,
      "loss": 1.1584,
      "step": 1515
    },
    {
      "epoch": 0.08303664347921345,
      "grad_norm": 7.046119213104248,
      "learning_rate": 0.00019963656086474657,
      "loss": 2.3634,
      "step": 1516
    },
    {
      "epoch": 0.08309141699074328,
      "grad_norm": 3.1615540981292725,
      "learning_rate": 0.0001996360660996288,
      "loss": 1.7934,
      "step": 1517
    },
    {
      "epoch": 0.0831461905022731,
      "grad_norm": 5.487991809844971,
      "learning_rate": 0.00019963558588642627,
      "loss": 1.4922,
      "step": 1518
    },
    {
      "epoch": 0.08320096401380292,
      "grad_norm": 2.0903475284576416,
      "learning_rate": 0.0001996350911213085,
      "loss": 0.9912,
      "step": 1519
    },
    {
      "epoch": 0.08325573752533275,
      "grad_norm": 2.9480371475219727,
      "learning_rate": 0.00019963461090810597,
      "loss": 1.665,
      "step": 1520
    },
    {
      "epoch": 0.08331051103686257,
      "grad_norm": 4.065296173095703,
      "learning_rate": 0.0001996341161429882,
      "loss": 0.946,
      "step": 1521
    },
    {
      "epoch": 0.0833652845483924,
      "grad_norm": 2.4524824619293213,
      "learning_rate": 0.00019963363592978567,
      "loss": 1.484,
      "step": 1522
    },
    {
      "epoch": 0.08342005805992223,
      "grad_norm": 3.6152079105377197,
      "learning_rate": 0.0001996331411646679,
      "loss": 1.809,
      "step": 1523
    },
    {
      "epoch": 0.08347483157145205,
      "grad_norm": 9.343366622924805,
      "learning_rate": 0.00019963264639955014,
      "loss": 2.2557,
      "step": 1524
    },
    {
      "epoch": 0.08352960508298186,
      "grad_norm": 6.168064117431641,
      "learning_rate": 0.00019963215163443238,
      "loss": 0.5783,
      "step": 1525
    },
    {
      "epoch": 0.08358437859451169,
      "grad_norm": 6.170744895935059,
      "learning_rate": 0.0001996316568693146,
      "loss": 1.1468,
      "step": 1526
    },
    {
      "epoch": 0.08363915210604152,
      "grad_norm": 3.076389789581299,
      "learning_rate": 0.00019963117665611207,
      "loss": 1.6097,
      "step": 1527
    },
    {
      "epoch": 0.08369392561757134,
      "grad_norm": 2.5352582931518555,
      "learning_rate": 0.00019963066733907908,
      "loss": 1.2973,
      "step": 1528
    },
    {
      "epoch": 0.08374869912910117,
      "grad_norm": 8.637377738952637,
      "learning_rate": 0.00019963018712587655,
      "loss": 2.0319,
      "step": 1529
    },
    {
      "epoch": 0.083803472640631,
      "grad_norm": 8.284051895141602,
      "learning_rate": 0.00019962969236075878,
      "loss": 2.6702,
      "step": 1530
    },
    {
      "epoch": 0.08385824615216081,
      "grad_norm": 4.006243705749512,
      "learning_rate": 0.00019962919759564102,
      "loss": 1.2531,
      "step": 1531
    },
    {
      "epoch": 0.08391301966369064,
      "grad_norm": 2.430426597595215,
      "learning_rate": 0.00019962870283052325,
      "loss": 1.3688,
      "step": 1532
    },
    {
      "epoch": 0.08396779317522046,
      "grad_norm": 8.81794261932373,
      "learning_rate": 0.0001996282080654055,
      "loss": 1.0681,
      "step": 1533
    },
    {
      "epoch": 0.08402256668675029,
      "grad_norm": 2.254807710647583,
      "learning_rate": 0.00019962771330028772,
      "loss": 1.0833,
      "step": 1534
    },
    {
      "epoch": 0.08407734019828011,
      "grad_norm": 8.204705238342285,
      "learning_rate": 0.00019962721853516996,
      "loss": 1.0315,
      "step": 1535
    },
    {
      "epoch": 0.08413211370980994,
      "grad_norm": 12.457432746887207,
      "learning_rate": 0.0001996267237700522,
      "loss": 2.1372,
      "step": 1536
    },
    {
      "epoch": 0.08418688722133975,
      "grad_norm": 4.304850101470947,
      "learning_rate": 0.00019962622900493443,
      "loss": 1.3724,
      "step": 1537
    },
    {
      "epoch": 0.08424166073286958,
      "grad_norm": 3.3129217624664307,
      "learning_rate": 0.00019962573423981667,
      "loss": 1.1056,
      "step": 1538
    },
    {
      "epoch": 0.0842964342443994,
      "grad_norm": 5.002777099609375,
      "learning_rate": 0.0001996252394746989,
      "loss": 0.3937,
      "step": 1539
    },
    {
      "epoch": 0.08435120775592923,
      "grad_norm": 2.3212170600891113,
      "learning_rate": 0.0001996247301576659,
      "loss": 1.5739,
      "step": 1540
    },
    {
      "epoch": 0.08440598126745906,
      "grad_norm": 11.913793563842773,
      "learning_rate": 0.00019962424994446337,
      "loss": 2.255,
      "step": 1541
    },
    {
      "epoch": 0.08446075477898889,
      "grad_norm": 6.527188301086426,
      "learning_rate": 0.00019962374062743038,
      "loss": 1.5455,
      "step": 1542
    },
    {
      "epoch": 0.0845155282905187,
      "grad_norm": 7.627561569213867,
      "learning_rate": 0.00019962324586231261,
      "loss": 2.0006,
      "step": 1543
    },
    {
      "epoch": 0.08457030180204853,
      "grad_norm": 2.7838804721832275,
      "learning_rate": 0.00019962275109719485,
      "loss": 1.3878,
      "step": 1544
    },
    {
      "epoch": 0.08462507531357835,
      "grad_norm": 14.950521469116211,
      "learning_rate": 0.00019962225633207709,
      "loss": 1.5723,
      "step": 1545
    },
    {
      "epoch": 0.08467984882510818,
      "grad_norm": 6.019796371459961,
      "learning_rate": 0.00019962176156695932,
      "loss": 1.5813,
      "step": 1546
    },
    {
      "epoch": 0.084734622336638,
      "grad_norm": 2.5229287147521973,
      "learning_rate": 0.00019962125224992633,
      "loss": 0.5221,
      "step": 1547
    },
    {
      "epoch": 0.08478939584816783,
      "grad_norm": 5.166425704956055,
      "learning_rate": 0.00019962075748480856,
      "loss": 1.3138,
      "step": 1548
    },
    {
      "epoch": 0.08484416935969764,
      "grad_norm": 3.4543843269348145,
      "learning_rate": 0.00019962024816777557,
      "loss": 1.0796,
      "step": 1549
    },
    {
      "epoch": 0.08489894287122747,
      "grad_norm": 2.96730375289917,
      "learning_rate": 0.0001996197534026578,
      "loss": 1.4804,
      "step": 1550
    },
    {
      "epoch": 0.0849537163827573,
      "grad_norm": 4.246142864227295,
      "learning_rate": 0.00019961925863754004,
      "loss": 1.6327,
      "step": 1551
    },
    {
      "epoch": 0.08500848989428712,
      "grad_norm": 3.8429198265075684,
      "learning_rate": 0.00019961874932050705,
      "loss": 1.7124,
      "step": 1552
    },
    {
      "epoch": 0.08506326340581695,
      "grad_norm": 2.477874755859375,
      "learning_rate": 0.00019961825455538929,
      "loss": 0.7521,
      "step": 1553
    },
    {
      "epoch": 0.08511803691734678,
      "grad_norm": 2.3058462142944336,
      "learning_rate": 0.0001996177452383563,
      "loss": 1.172,
      "step": 1554
    },
    {
      "epoch": 0.08517281042887659,
      "grad_norm": 6.57858943939209,
      "learning_rate": 0.00019961725047323853,
      "loss": 2.2358,
      "step": 1555
    },
    {
      "epoch": 0.08522758394040642,
      "grad_norm": 2.197486162185669,
      "learning_rate": 0.00019961675570812076,
      "loss": 0.8065,
      "step": 1556
    },
    {
      "epoch": 0.08528235745193624,
      "grad_norm": 3.2342543601989746,
      "learning_rate": 0.00019961624639108777,
      "loss": 1.3541,
      "step": 1557
    },
    {
      "epoch": 0.08533713096346607,
      "grad_norm": 6.365350723266602,
      "learning_rate": 0.00019961575162597,
      "loss": 1.6865,
      "step": 1558
    },
    {
      "epoch": 0.0853919044749959,
      "grad_norm": 7.0232439041137695,
      "learning_rate": 0.000199615242308937,
      "loss": 2.3282,
      "step": 1559
    },
    {
      "epoch": 0.08544667798652572,
      "grad_norm": 6.357398986816406,
      "learning_rate": 0.00019961473299190402,
      "loss": 1.6822,
      "step": 1560
    },
    {
      "epoch": 0.08550145149805553,
      "grad_norm": 3.5684726238250732,
      "learning_rate": 0.00019961423822678626,
      "loss": 1.2976,
      "step": 1561
    },
    {
      "epoch": 0.08555622500958536,
      "grad_norm": 2.251303195953369,
      "learning_rate": 0.00019961372890975326,
      "loss": 1.1571,
      "step": 1562
    },
    {
      "epoch": 0.08561099852111519,
      "grad_norm": 3.625739097595215,
      "learning_rate": 0.0001996132341446355,
      "loss": 1.4705,
      "step": 1563
    },
    {
      "epoch": 0.08566577203264501,
      "grad_norm": 6.529778003692627,
      "learning_rate": 0.0001996127248276025,
      "loss": 1.3786,
      "step": 1564
    },
    {
      "epoch": 0.08572054554417484,
      "grad_norm": 3.294416666030884,
      "learning_rate": 0.0001996122155105695,
      "loss": 1.8424,
      "step": 1565
    },
    {
      "epoch": 0.08577531905570467,
      "grad_norm": 4.6975836753845215,
      "learning_rate": 0.00019961172074545175,
      "loss": 1.9397,
      "step": 1566
    },
    {
      "epoch": 0.08583009256723449,
      "grad_norm": 8.647466659545898,
      "learning_rate": 0.00019961121142841876,
      "loss": 1.4882,
      "step": 1567
    },
    {
      "epoch": 0.0858848660787643,
      "grad_norm": 1.885026454925537,
      "learning_rate": 0.00019961070211138576,
      "loss": 0.9346,
      "step": 1568
    },
    {
      "epoch": 0.08593963959029413,
      "grad_norm": 14.397427558898926,
      "learning_rate": 0.00019961019279435277,
      "loss": 2.2096,
      "step": 1569
    },
    {
      "epoch": 0.08599441310182396,
      "grad_norm": 2.729597330093384,
      "learning_rate": 0.000199609698029235,
      "loss": 0.8955,
      "step": 1570
    },
    {
      "epoch": 0.08604918661335378,
      "grad_norm": 2.551683187484741,
      "learning_rate": 0.00019960917416028678,
      "loss": 1.4264,
      "step": 1571
    },
    {
      "epoch": 0.08610396012488361,
      "grad_norm": 5.4264678955078125,
      "learning_rate": 0.00019960867939516902,
      "loss": 2.0086,
      "step": 1572
    },
    {
      "epoch": 0.08615873363641344,
      "grad_norm": 20.8983154296875,
      "learning_rate": 0.00019960817007813603,
      "loss": 2.843,
      "step": 1573
    },
    {
      "epoch": 0.08621350714794325,
      "grad_norm": 26.641448974609375,
      "learning_rate": 0.00019960766076110303,
      "loss": 4.8887,
      "step": 1574
    },
    {
      "epoch": 0.08626828065947308,
      "grad_norm": 4.779064655303955,
      "learning_rate": 0.00019960715144407004,
      "loss": 1.1539,
      "step": 1575
    },
    {
      "epoch": 0.0863230541710029,
      "grad_norm": 5.188298225402832,
      "learning_rate": 0.00019960664212703705,
      "loss": 2.0723,
      "step": 1576
    },
    {
      "epoch": 0.08637782768253273,
      "grad_norm": 2.4111762046813965,
      "learning_rate": 0.00019960613281000406,
      "loss": 1.3313,
      "step": 1577
    },
    {
      "epoch": 0.08643260119406256,
      "grad_norm": 3.055211067199707,
      "learning_rate": 0.00019960562349297106,
      "loss": 0.7347,
      "step": 1578
    },
    {
      "epoch": 0.08648737470559238,
      "grad_norm": 4.273102283477783,
      "learning_rate": 0.00019960511417593807,
      "loss": 1.8998,
      "step": 1579
    },
    {
      "epoch": 0.0865421482171222,
      "grad_norm": 16.386035919189453,
      "learning_rate": 0.0001996046194108203,
      "loss": 1.8626,
      "step": 1580
    },
    {
      "epoch": 0.08659692172865202,
      "grad_norm": 2.2933871746063232,
      "learning_rate": 0.00019960409554187208,
      "loss": 1.4067,
      "step": 1581
    },
    {
      "epoch": 0.08665169524018185,
      "grad_norm": 4.8411431312561035,
      "learning_rate": 0.0001996035862248391,
      "loss": 0.9777,
      "step": 1582
    },
    {
      "epoch": 0.08670646875171167,
      "grad_norm": 2.632385492324829,
      "learning_rate": 0.0001996030769078061,
      "loss": 2.0125,
      "step": 1583
    },
    {
      "epoch": 0.0867612422632415,
      "grad_norm": 7.2967424392700195,
      "learning_rate": 0.0001996025675907731,
      "loss": 1.9157,
      "step": 1584
    },
    {
      "epoch": 0.08681601577477133,
      "grad_norm": 7.005876064300537,
      "learning_rate": 0.00019960204372182488,
      "loss": 1.6911,
      "step": 1585
    },
    {
      "epoch": 0.08687078928630114,
      "grad_norm": 3.64652681350708,
      "learning_rate": 0.00019960154895670712,
      "loss": 0.7428,
      "step": 1586
    },
    {
      "epoch": 0.08692556279783097,
      "grad_norm": 3.6834051609039307,
      "learning_rate": 0.00019960103963967413,
      "loss": 1.8116,
      "step": 1587
    },
    {
      "epoch": 0.08698033630936079,
      "grad_norm": 2.0026519298553467,
      "learning_rate": 0.00019960053032264113,
      "loss": 1.3036,
      "step": 1588
    },
    {
      "epoch": 0.08703510982089062,
      "grad_norm": 3.325471878051758,
      "learning_rate": 0.0001996000064536929,
      "loss": 1.4191,
      "step": 1589
    },
    {
      "epoch": 0.08708988333242045,
      "grad_norm": 2.1651158332824707,
      "learning_rate": 0.00019959949713665992,
      "loss": 1.1829,
      "step": 1590
    },
    {
      "epoch": 0.08714465684395027,
      "grad_norm": 6.8586649894714355,
      "learning_rate": 0.00019959898781962693,
      "loss": 1.7971,
      "step": 1591
    },
    {
      "epoch": 0.08719943035548008,
      "grad_norm": 7.707522392272949,
      "learning_rate": 0.0001995984639506787,
      "loss": 1.3531,
      "step": 1592
    },
    {
      "epoch": 0.08725420386700991,
      "grad_norm": 7.583007335662842,
      "learning_rate": 0.0001995979546336457,
      "loss": 2.1687,
      "step": 1593
    },
    {
      "epoch": 0.08730897737853974,
      "grad_norm": 5.887197494506836,
      "learning_rate": 0.0001995974307646975,
      "loss": 1.3811,
      "step": 1594
    },
    {
      "epoch": 0.08736375089006956,
      "grad_norm": 4.864095211029053,
      "learning_rate": 0.0001995969214476645,
      "loss": 1.1953,
      "step": 1595
    },
    {
      "epoch": 0.08741852440159939,
      "grad_norm": 2.5976927280426025,
      "learning_rate": 0.0001995964121306315,
      "loss": 1.5991,
      "step": 1596
    },
    {
      "epoch": 0.08747329791312922,
      "grad_norm": 4.593461036682129,
      "learning_rate": 0.00019959590281359851,
      "loss": 1.3635,
      "step": 1597
    },
    {
      "epoch": 0.08752807142465903,
      "grad_norm": 3.9681715965270996,
      "learning_rate": 0.0001995953789446503,
      "loss": 1.2548,
      "step": 1598
    },
    {
      "epoch": 0.08758284493618886,
      "grad_norm": 2.8463826179504395,
      "learning_rate": 0.00019959485507570207,
      "loss": 1.5531,
      "step": 1599
    },
    {
      "epoch": 0.08763761844771868,
      "grad_norm": 9.914241790771484,
      "learning_rate": 0.00019959434575866908,
      "loss": 1.6568,
      "step": 1600
    },
    {
      "epoch": 0.08763761844771868,
      "eval_loss": 1.4340760707855225,
      "eval_runtime": 45.7731,
      "eval_samples_per_second": 2.01,
      "eval_steps_per_second": 2.01,
      "step": 1600
    },
    {
      "epoch": 0.08769239195924851,
      "grad_norm": 5.366902828216553,
      "learning_rate": 0.00019959382188972086,
      "loss": 1.7077,
      "step": 1601
    },
    {
      "epoch": 0.08774716547077833,
      "grad_norm": 3.1227846145629883,
      "learning_rate": 0.00019959331257268786,
      "loss": 0.6804,
      "step": 1602
    },
    {
      "epoch": 0.08780193898230816,
      "grad_norm": 2.122840404510498,
      "learning_rate": 0.00019959280325565487,
      "loss": 0.9901,
      "step": 1603
    },
    {
      "epoch": 0.08785671249383797,
      "grad_norm": 2.5407469272613525,
      "learning_rate": 0.00019959227938670665,
      "loss": 1.2803,
      "step": 1604
    },
    {
      "epoch": 0.0879114860053678,
      "grad_norm": 4.401165962219238,
      "learning_rate": 0.00019959175551775843,
      "loss": 1.2984,
      "step": 1605
    },
    {
      "epoch": 0.08796625951689763,
      "grad_norm": 7.368124008178711,
      "learning_rate": 0.0001995912316488102,
      "loss": 1.2305,
      "step": 1606
    },
    {
      "epoch": 0.08802103302842745,
      "grad_norm": 4.00018310546875,
      "learning_rate": 0.00019959072233177722,
      "loss": 1.2776,
      "step": 1607
    },
    {
      "epoch": 0.08807580653995728,
      "grad_norm": 3.637449026107788,
      "learning_rate": 0.000199590198462829,
      "loss": 1.0946,
      "step": 1608
    },
    {
      "epoch": 0.0881305800514871,
      "grad_norm": 17.352436065673828,
      "learning_rate": 0.000199589689145796,
      "loss": 2.4658,
      "step": 1609
    },
    {
      "epoch": 0.08818535356301692,
      "grad_norm": 4.499262809753418,
      "learning_rate": 0.00019958916527684778,
      "loss": 1.1501,
      "step": 1610
    },
    {
      "epoch": 0.08824012707454675,
      "grad_norm": 5.440906047821045,
      "learning_rate": 0.0001995886559598148,
      "loss": 2.0484,
      "step": 1611
    },
    {
      "epoch": 0.08829490058607657,
      "grad_norm": 2.9596195220947266,
      "learning_rate": 0.00019958813209086657,
      "loss": 1.5122,
      "step": 1612
    },
    {
      "epoch": 0.0883496740976064,
      "grad_norm": 4.285594463348389,
      "learning_rate": 0.00019958760822191834,
      "loss": 1.2588,
      "step": 1613
    },
    {
      "epoch": 0.08840444760913622,
      "grad_norm": 5.51903772354126,
      "learning_rate": 0.00019958708435297012,
      "loss": 1.0402,
      "step": 1614
    },
    {
      "epoch": 0.08845922112066605,
      "grad_norm": 2.569270610809326,
      "learning_rate": 0.0001995865604840219,
      "loss": 1.44,
      "step": 1615
    },
    {
      "epoch": 0.08851399463219586,
      "grad_norm": 7.142980098724365,
      "learning_rate": 0.00019958603661507368,
      "loss": 1.8552,
      "step": 1616
    },
    {
      "epoch": 0.08856876814372569,
      "grad_norm": 2.3455028533935547,
      "learning_rate": 0.00019958551274612546,
      "loss": 1.3489,
      "step": 1617
    },
    {
      "epoch": 0.08862354165525552,
      "grad_norm": 2.725896120071411,
      "learning_rate": 0.00019958500342909247,
      "loss": 0.7,
      "step": 1618
    },
    {
      "epoch": 0.08867831516678534,
      "grad_norm": 1.2618005275726318,
      "learning_rate": 0.00019958447956014425,
      "loss": 0.6799,
      "step": 1619
    },
    {
      "epoch": 0.08873308867831517,
      "grad_norm": 7.873151779174805,
      "learning_rate": 0.00019958395569119602,
      "loss": 1.8586,
      "step": 1620
    },
    {
      "epoch": 0.088787862189845,
      "grad_norm": 3.2256438732147217,
      "learning_rate": 0.0001995834318222478,
      "loss": 1.3345,
      "step": 1621
    },
    {
      "epoch": 0.08884263570137481,
      "grad_norm": 2.496401309967041,
      "learning_rate": 0.00019958290795329958,
      "loss": 1.6573,
      "step": 1622
    },
    {
      "epoch": 0.08889740921290464,
      "grad_norm": 2.2526159286499023,
      "learning_rate": 0.00019958238408435136,
      "loss": 1.0317,
      "step": 1623
    },
    {
      "epoch": 0.08895218272443446,
      "grad_norm": 5.444879055023193,
      "learning_rate": 0.00019958186021540314,
      "loss": 0.7277,
      "step": 1624
    },
    {
      "epoch": 0.08900695623596429,
      "grad_norm": 3.6625874042510986,
      "learning_rate": 0.00019958133634645492,
      "loss": 1.284,
      "step": 1625
    },
    {
      "epoch": 0.08906172974749411,
      "grad_norm": 2.2699735164642334,
      "learning_rate": 0.0001995808124775067,
      "loss": 1.3443,
      "step": 1626
    },
    {
      "epoch": 0.08911650325902394,
      "grad_norm": 4.333250999450684,
      "learning_rate": 0.00019958028860855848,
      "loss": 1.7153,
      "step": 1627
    },
    {
      "epoch": 0.08917127677055375,
      "grad_norm": 3.067652463912964,
      "learning_rate": 0.00019957976473961025,
      "loss": 1.5669,
      "step": 1628
    },
    {
      "epoch": 0.08922605028208358,
      "grad_norm": 2.9399352073669434,
      "learning_rate": 0.00019957924087066203,
      "loss": 1.1713,
      "step": 1629
    },
    {
      "epoch": 0.0892808237936134,
      "grad_norm": 3.4539082050323486,
      "learning_rate": 0.00019957870244979858,
      "loss": 1.7796,
      "step": 1630
    },
    {
      "epoch": 0.08933559730514323,
      "grad_norm": 3.2130351066589355,
      "learning_rate": 0.00019957817858085036,
      "loss": 1.4774,
      "step": 1631
    },
    {
      "epoch": 0.08939037081667306,
      "grad_norm": 2.6095948219299316,
      "learning_rate": 0.00019957765471190214,
      "loss": 1.3897,
      "step": 1632
    },
    {
      "epoch": 0.08944514432820289,
      "grad_norm": 6.259021282196045,
      "learning_rate": 0.00019957713084295392,
      "loss": 1.7241,
      "step": 1633
    },
    {
      "epoch": 0.08949991783973271,
      "grad_norm": 4.784141540527344,
      "learning_rate": 0.00019957659242209047,
      "loss": 1.1163,
      "step": 1634
    },
    {
      "epoch": 0.08955469135126252,
      "grad_norm": 7.56728458404541,
      "learning_rate": 0.00019957606855314225,
      "loss": 1.2942,
      "step": 1635
    },
    {
      "epoch": 0.08960946486279235,
      "grad_norm": 3.0181610584259033,
      "learning_rate": 0.00019957554468419403,
      "loss": 1.3902,
      "step": 1636
    },
    {
      "epoch": 0.08966423837432218,
      "grad_norm": 7.075383186340332,
      "learning_rate": 0.0001995750208152458,
      "loss": 1.6522,
      "step": 1637
    },
    {
      "epoch": 0.089719011885852,
      "grad_norm": 4.079206466674805,
      "learning_rate": 0.00019957448239438236,
      "loss": 0.4215,
      "step": 1638
    },
    {
      "epoch": 0.08977378539738183,
      "grad_norm": 7.782792091369629,
      "learning_rate": 0.00019957395852543414,
      "loss": 1.3374,
      "step": 1639
    },
    {
      "epoch": 0.08982855890891166,
      "grad_norm": 3.933861494064331,
      "learning_rate": 0.00019957343465648592,
      "loss": 1.2032,
      "step": 1640
    },
    {
      "epoch": 0.08988333242044147,
      "grad_norm": 9.589438438415527,
      "learning_rate": 0.0001995729107875377,
      "loss": 2.5558,
      "step": 1641
    },
    {
      "epoch": 0.0899381059319713,
      "grad_norm": 6.3403754234313965,
      "learning_rate": 0.00019957237236667424,
      "loss": 2.4346,
      "step": 1642
    },
    {
      "epoch": 0.08999287944350112,
      "grad_norm": 6.288458824157715,
      "learning_rate": 0.00019957184849772602,
      "loss": 1.2491,
      "step": 1643
    },
    {
      "epoch": 0.09004765295503095,
      "grad_norm": 2.5266575813293457,
      "learning_rate": 0.00019957131007686257,
      "loss": 1.0979,
      "step": 1644
    },
    {
      "epoch": 0.09010242646656078,
      "grad_norm": 3.0301926136016846,
      "learning_rate": 0.00019957078620791435,
      "loss": 0.628,
      "step": 1645
    },
    {
      "epoch": 0.0901571999780906,
      "grad_norm": 3.3828582763671875,
      "learning_rate": 0.0001995702477870509,
      "loss": 1.424,
      "step": 1646
    },
    {
      "epoch": 0.09021197348962041,
      "grad_norm": 2.031400203704834,
      "learning_rate": 0.00019956970936618745,
      "loss": 1.0983,
      "step": 1647
    },
    {
      "epoch": 0.09026674700115024,
      "grad_norm": 4.630466461181641,
      "learning_rate": 0.00019956918549723923,
      "loss": 1.2242,
      "step": 1648
    },
    {
      "epoch": 0.09032152051268007,
      "grad_norm": 7.430382251739502,
      "learning_rate": 0.00019956864707637578,
      "loss": 2.0,
      "step": 1649
    },
    {
      "epoch": 0.0903762940242099,
      "grad_norm": 2.8569140434265137,
      "learning_rate": 0.00019956810865551233,
      "loss": 0.8801,
      "step": 1650
    },
    {
      "epoch": 0.09043106753573972,
      "grad_norm": 5.034245014190674,
      "learning_rate": 0.0001995675847865641,
      "loss": 1.8236,
      "step": 1651
    },
    {
      "epoch": 0.09048584104726955,
      "grad_norm": 5.263605117797852,
      "learning_rate": 0.00019956704636570066,
      "loss": 1.3793,
      "step": 1652
    },
    {
      "epoch": 0.09054061455879936,
      "grad_norm": 5.179928302764893,
      "learning_rate": 0.0001995665079448372,
      "loss": 1.1276,
      "step": 1653
    },
    {
      "epoch": 0.09059538807032919,
      "grad_norm": 3.6077303886413574,
      "learning_rate": 0.000199565984075889,
      "loss": 1.3063,
      "step": 1654
    },
    {
      "epoch": 0.09065016158185901,
      "grad_norm": 3.229447364807129,
      "learning_rate": 0.00019956546020694077,
      "loss": 1.2795,
      "step": 1655
    },
    {
      "epoch": 0.09070493509338884,
      "grad_norm": 2.970724105834961,
      "learning_rate": 0.00019956492178607732,
      "loss": 1.6878,
      "step": 1656
    },
    {
      "epoch": 0.09075970860491867,
      "grad_norm": 6.656960487365723,
      "learning_rate": 0.00019956438336521387,
      "loss": 1.5603,
      "step": 1657
    },
    {
      "epoch": 0.09081448211644849,
      "grad_norm": 3.442094087600708,
      "learning_rate": 0.00019956384494435042,
      "loss": 0.9154,
      "step": 1658
    },
    {
      "epoch": 0.0908692556279783,
      "grad_norm": 8.969644546508789,
      "learning_rate": 0.00019956330652348697,
      "loss": 1.9593,
      "step": 1659
    },
    {
      "epoch": 0.09092402913950813,
      "grad_norm": 3.8026201725006104,
      "learning_rate": 0.00019956276810262352,
      "loss": 1.2455,
      "step": 1660
    },
    {
      "epoch": 0.09097880265103796,
      "grad_norm": 3.63321852684021,
      "learning_rate": 0.00019956222968176007,
      "loss": 1.9388,
      "step": 1661
    },
    {
      "epoch": 0.09103357616256778,
      "grad_norm": 2.566716432571411,
      "learning_rate": 0.00019956169126089662,
      "loss": 1.7642,
      "step": 1662
    },
    {
      "epoch": 0.09108834967409761,
      "grad_norm": 7.871973037719727,
      "learning_rate": 0.0001995611673919484,
      "loss": 3.7299,
      "step": 1663
    },
    {
      "epoch": 0.09114312318562744,
      "grad_norm": 4.749972820281982,
      "learning_rate": 0.00019956062897108495,
      "loss": 2.6936,
      "step": 1664
    },
    {
      "epoch": 0.09119789669715725,
      "grad_norm": 4.078336238861084,
      "learning_rate": 0.0001995600905502215,
      "loss": 1.4273,
      "step": 1665
    },
    {
      "epoch": 0.09125267020868708,
      "grad_norm": 3.5786890983581543,
      "learning_rate": 0.00019955955212935805,
      "loss": 1.5589,
      "step": 1666
    },
    {
      "epoch": 0.0913074437202169,
      "grad_norm": 4.337762832641602,
      "learning_rate": 0.0001995590137084946,
      "loss": 1.7134,
      "step": 1667
    },
    {
      "epoch": 0.09136221723174673,
      "grad_norm": 3.1509594917297363,
      "learning_rate": 0.00019955846073571593,
      "loss": 0.6404,
      "step": 1668
    },
    {
      "epoch": 0.09141699074327655,
      "grad_norm": 2.5405430793762207,
      "learning_rate": 0.0001995579368667677,
      "loss": 1.6504,
      "step": 1669
    },
    {
      "epoch": 0.09147176425480638,
      "grad_norm": 8.691856384277344,
      "learning_rate": 0.00019955739844590425,
      "loss": 1.8161,
      "step": 1670
    },
    {
      "epoch": 0.0915265377663362,
      "grad_norm": 3.038316488265991,
      "learning_rate": 0.0001995568600250408,
      "loss": 0.9657,
      "step": 1671
    },
    {
      "epoch": 0.09158131127786602,
      "grad_norm": 2.1997008323669434,
      "learning_rate": 0.00019955630705226213,
      "loss": 1.1157,
      "step": 1672
    },
    {
      "epoch": 0.09163608478939585,
      "grad_norm": 2.6481521129608154,
      "learning_rate": 0.00019955576863139868,
      "loss": 1.4962,
      "step": 1673
    },
    {
      "epoch": 0.09169085830092567,
      "grad_norm": 1.0748844146728516,
      "learning_rate": 0.00019955523021053523,
      "loss": 0.6835,
      "step": 1674
    },
    {
      "epoch": 0.0917456318124555,
      "grad_norm": 3.4543325901031494,
      "learning_rate": 0.00019955469178967178,
      "loss": 2.1548,
      "step": 1675
    },
    {
      "epoch": 0.09180040532398533,
      "grad_norm": 3.6799814701080322,
      "learning_rate": 0.00019955415336880833,
      "loss": 1.4191,
      "step": 1676
    },
    {
      "epoch": 0.09185517883551514,
      "grad_norm": 2.6445376873016357,
      "learning_rate": 0.00019955361494794488,
      "loss": 1.3654,
      "step": 1677
    },
    {
      "epoch": 0.09190995234704497,
      "grad_norm": 2.439629077911377,
      "learning_rate": 0.0001995530619751662,
      "loss": 1.5195,
      "step": 1678
    },
    {
      "epoch": 0.09196472585857479,
      "grad_norm": 2.235034942626953,
      "learning_rate": 0.00019955253810621798,
      "loss": 0.9295,
      "step": 1679
    },
    {
      "epoch": 0.09201949937010462,
      "grad_norm": 3.1850292682647705,
      "learning_rate": 0.0001995519851334393,
      "loss": 1.8507,
      "step": 1680
    },
    {
      "epoch": 0.09207427288163444,
      "grad_norm": 3.014841318130493,
      "learning_rate": 0.00019955144671257585,
      "loss": 0.9887,
      "step": 1681
    },
    {
      "epoch": 0.09212904639316427,
      "grad_norm": 2.501145839691162,
      "learning_rate": 0.00019955089373979717,
      "loss": 1.0976,
      "step": 1682
    },
    {
      "epoch": 0.09218381990469408,
      "grad_norm": 3.8537378311157227,
      "learning_rate": 0.00019955035531893373,
      "loss": 1.8243,
      "step": 1683
    },
    {
      "epoch": 0.09223859341622391,
      "grad_norm": 4.351325988769531,
      "learning_rate": 0.00019954981689807028,
      "loss": 1.3183,
      "step": 1684
    },
    {
      "epoch": 0.09229336692775374,
      "grad_norm": 1.8156189918518066,
      "learning_rate": 0.0001995492639252916,
      "loss": 0.8285,
      "step": 1685
    },
    {
      "epoch": 0.09234814043928356,
      "grad_norm": 5.1356329917907715,
      "learning_rate": 0.00019954872550442815,
      "loss": 1.6608,
      "step": 1686
    },
    {
      "epoch": 0.09240291395081339,
      "grad_norm": 2.1491870880126953,
      "learning_rate": 0.0001995481870835647,
      "loss": 0.9235,
      "step": 1687
    },
    {
      "epoch": 0.09245768746234322,
      "grad_norm": 7.064915180206299,
      "learning_rate": 0.00019954763411078602,
      "loss": 0.9916,
      "step": 1688
    },
    {
      "epoch": 0.09251246097387303,
      "grad_norm": 3.437438726425171,
      "learning_rate": 0.00019954708113800734,
      "loss": 0.6795,
      "step": 1689
    },
    {
      "epoch": 0.09256723448540286,
      "grad_norm": 5.699773788452148,
      "learning_rate": 0.0001995465427171439,
      "loss": 2.4879,
      "step": 1690
    },
    {
      "epoch": 0.09262200799693268,
      "grad_norm": 5.413378715515137,
      "learning_rate": 0.00019954600429628044,
      "loss": 1.6067,
      "step": 1691
    },
    {
      "epoch": 0.09267678150846251,
      "grad_norm": 3.0996882915496826,
      "learning_rate": 0.00019954545132350177,
      "loss": 1.038,
      "step": 1692
    },
    {
      "epoch": 0.09273155501999233,
      "grad_norm": 4.2636590003967285,
      "learning_rate": 0.0001995448983507231,
      "loss": 2.6147,
      "step": 1693
    },
    {
      "epoch": 0.09278632853152216,
      "grad_norm": 1.9887982606887817,
      "learning_rate": 0.00019954435992985964,
      "loss": 1.039,
      "step": 1694
    },
    {
      "epoch": 0.09284110204305197,
      "grad_norm": 2.6945536136627197,
      "learning_rate": 0.00019954380695708096,
      "loss": 1.7197,
      "step": 1695
    },
    {
      "epoch": 0.0928958755545818,
      "grad_norm": 5.358307838439941,
      "learning_rate": 0.00019954325398430228,
      "loss": 2.0935,
      "step": 1696
    },
    {
      "epoch": 0.09295064906611163,
      "grad_norm": 3.0616438388824463,
      "learning_rate": 0.0001995427010115236,
      "loss": 1.5183,
      "step": 1697
    },
    {
      "epoch": 0.09300542257764145,
      "grad_norm": 2.9555561542510986,
      "learning_rate": 0.00019954216259066015,
      "loss": 1.0742,
      "step": 1698
    },
    {
      "epoch": 0.09306019608917128,
      "grad_norm": 3.4128341674804688,
      "learning_rate": 0.00019954160961788148,
      "loss": 1.8553,
      "step": 1699
    },
    {
      "epoch": 0.0931149696007011,
      "grad_norm": 4.204677581787109,
      "learning_rate": 0.0001995410566451028,
      "loss": 1.3901,
      "step": 1700
    },
    {
      "epoch": 0.0931149696007011,
      "eval_loss": 1.4360973834991455,
      "eval_runtime": 45.7605,
      "eval_samples_per_second": 2.01,
      "eval_steps_per_second": 2.01,
      "step": 1700
    },
    {
      "epoch": 0.09316974311223092,
      "grad_norm": 2.093738317489624,
      "learning_rate": 0.00019954051822423935,
      "loss": 0.8378,
      "step": 1701
    },
    {
      "epoch": 0.09322451662376074,
      "grad_norm": 3.873685359954834,
      "learning_rate": 0.00019953996525146067,
      "loss": 1.5295,
      "step": 1702
    },
    {
      "epoch": 0.09327929013529057,
      "grad_norm": 3.745143175125122,
      "learning_rate": 0.000199539412278682,
      "loss": 1.3683,
      "step": 1703
    },
    {
      "epoch": 0.0933340636468204,
      "grad_norm": 15.979313850402832,
      "learning_rate": 0.00019953887385781854,
      "loss": 1.665,
      "step": 1704
    },
    {
      "epoch": 0.09338883715835022,
      "grad_norm": 7.592923641204834,
      "learning_rate": 0.00019953832088503987,
      "loss": 1.7577,
      "step": 1705
    },
    {
      "epoch": 0.09344361066988005,
      "grad_norm": 5.458607196807861,
      "learning_rate": 0.0001995377679122612,
      "loss": 1.4803,
      "step": 1706
    },
    {
      "epoch": 0.09349838418140988,
      "grad_norm": 2.4999823570251465,
      "learning_rate": 0.0001995372149394825,
      "loss": 1.7869,
      "step": 1707
    },
    {
      "epoch": 0.09355315769293969,
      "grad_norm": 2.4218177795410156,
      "learning_rate": 0.00019953666196670383,
      "loss": 1.3429,
      "step": 1708
    },
    {
      "epoch": 0.09360793120446952,
      "grad_norm": 2.142124891281128,
      "learning_rate": 0.00019953610899392515,
      "loss": 1.1452,
      "step": 1709
    },
    {
      "epoch": 0.09366270471599934,
      "grad_norm": 4.530423641204834,
      "learning_rate": 0.00019953555602114648,
      "loss": 0.6014,
      "step": 1710
    },
    {
      "epoch": 0.09371747822752917,
      "grad_norm": 2.2396562099456787,
      "learning_rate": 0.0001995350030483678,
      "loss": 1.3763,
      "step": 1711
    },
    {
      "epoch": 0.093772251739059,
      "grad_norm": 8.47006893157959,
      "learning_rate": 0.00019953445007558912,
      "loss": 2.1985,
      "step": 1712
    },
    {
      "epoch": 0.09382702525058882,
      "grad_norm": 16.272075653076172,
      "learning_rate": 0.00019953389710281044,
      "loss": 2.2964,
      "step": 1713
    },
    {
      "epoch": 0.09388179876211863,
      "grad_norm": 2.867579221725464,
      "learning_rate": 0.00019953334413003176,
      "loss": 1.7925,
      "step": 1714
    },
    {
      "epoch": 0.09393657227364846,
      "grad_norm": 2.2792773246765137,
      "learning_rate": 0.0001995327911572531,
      "loss": 1.2294,
      "step": 1715
    },
    {
      "epoch": 0.09399134578517829,
      "grad_norm": 3.3239622116088867,
      "learning_rate": 0.0001995322381844744,
      "loss": 2.2645,
      "step": 1716
    },
    {
      "epoch": 0.09404611929670811,
      "grad_norm": 6.84503698348999,
      "learning_rate": 0.00019953168521169573,
      "loss": 1.5343,
      "step": 1717
    },
    {
      "epoch": 0.09410089280823794,
      "grad_norm": 3.401970863342285,
      "learning_rate": 0.00019953113223891705,
      "loss": 0.9166,
      "step": 1718
    },
    {
      "epoch": 0.09415566631976777,
      "grad_norm": 2.7699713706970215,
      "learning_rate": 0.00019953057926613837,
      "loss": 1.6435,
      "step": 1719
    },
    {
      "epoch": 0.09421043983129758,
      "grad_norm": 4.692700386047363,
      "learning_rate": 0.00019953001174144447,
      "loss": 1.6416,
      "step": 1720
    },
    {
      "epoch": 0.0942652133428274,
      "grad_norm": 6.0493974685668945,
      "learning_rate": 0.0001995294587686658,
      "loss": 0.8079,
      "step": 1721
    },
    {
      "epoch": 0.09431998685435723,
      "grad_norm": 3.3965518474578857,
      "learning_rate": 0.0001995289057958871,
      "loss": 0.9784,
      "step": 1722
    },
    {
      "epoch": 0.09437476036588706,
      "grad_norm": 2.5575971603393555,
      "learning_rate": 0.0001995283382711932,
      "loss": 1.3142,
      "step": 1723
    },
    {
      "epoch": 0.09442953387741689,
      "grad_norm": 2.5071768760681152,
      "learning_rate": 0.00019952779985032976,
      "loss": 1.9478,
      "step": 1724
    },
    {
      "epoch": 0.09448430738894671,
      "grad_norm": 4.449032783508301,
      "learning_rate": 0.00019952723232563585,
      "loss": 1.6503,
      "step": 1725
    },
    {
      "epoch": 0.09453908090047652,
      "grad_norm": 5.065138339996338,
      "learning_rate": 0.00019952667935285717,
      "loss": 2.1451,
      "step": 1726
    },
    {
      "epoch": 0.09459385441200635,
      "grad_norm": 2.8541817665100098,
      "learning_rate": 0.00019952611182816327,
      "loss": 0.736,
      "step": 1727
    },
    {
      "epoch": 0.09464862792353618,
      "grad_norm": 2.47845721244812,
      "learning_rate": 0.0001995255588553846,
      "loss": 1.5384,
      "step": 1728
    },
    {
      "epoch": 0.094703401435066,
      "grad_norm": 9.68614387512207,
      "learning_rate": 0.0001995250058826059,
      "loss": 1.8912,
      "step": 1729
    },
    {
      "epoch": 0.09475817494659583,
      "grad_norm": 3.7445404529571533,
      "learning_rate": 0.000199524438357912,
      "loss": 1.8164,
      "step": 1730
    },
    {
      "epoch": 0.09481294845812566,
      "grad_norm": 3.669001579284668,
      "learning_rate": 0.00019952388538513333,
      "loss": 1.0819,
      "step": 1731
    },
    {
      "epoch": 0.09486772196965547,
      "grad_norm": 2.9337830543518066,
      "learning_rate": 0.00019952331786043942,
      "loss": 1.6034,
      "step": 1732
    },
    {
      "epoch": 0.0949224954811853,
      "grad_norm": 3.0850977897644043,
      "learning_rate": 0.00019952276488766074,
      "loss": 1.7686,
      "step": 1733
    },
    {
      "epoch": 0.09497726899271512,
      "grad_norm": 2.0788979530334473,
      "learning_rate": 0.00019952219736296684,
      "loss": 0.9199,
      "step": 1734
    },
    {
      "epoch": 0.09503204250424495,
      "grad_norm": 3.008871555328369,
      "learning_rate": 0.00019952164439018816,
      "loss": 1.5426,
      "step": 1735
    },
    {
      "epoch": 0.09508681601577477,
      "grad_norm": 4.750055313110352,
      "learning_rate": 0.00019952107686549425,
      "loss": 1.6043,
      "step": 1736
    },
    {
      "epoch": 0.0951415895273046,
      "grad_norm": 2.194444179534912,
      "learning_rate": 0.00019952052389271557,
      "loss": 0.9602,
      "step": 1737
    },
    {
      "epoch": 0.09519636303883441,
      "grad_norm": 3.4514377117156982,
      "learning_rate": 0.00019951995636802167,
      "loss": 1.202,
      "step": 1738
    },
    {
      "epoch": 0.09525113655036424,
      "grad_norm": 4.065868377685547,
      "learning_rate": 0.000199519403395243,
      "loss": 0.4163,
      "step": 1739
    },
    {
      "epoch": 0.09530591006189407,
      "grad_norm": 3.552816390991211,
      "learning_rate": 0.00019951883587054908,
      "loss": 0.6728,
      "step": 1740
    },
    {
      "epoch": 0.0953606835734239,
      "grad_norm": 2.4412248134613037,
      "learning_rate": 0.00019951826834585518,
      "loss": 0.9636,
      "step": 1741
    },
    {
      "epoch": 0.09541545708495372,
      "grad_norm": 1.1864272356033325,
      "learning_rate": 0.0001995177153730765,
      "loss": 0.7336,
      "step": 1742
    },
    {
      "epoch": 0.09547023059648355,
      "grad_norm": 3.3133068084716797,
      "learning_rate": 0.0001995171478483826,
      "loss": 1.1571,
      "step": 1743
    },
    {
      "epoch": 0.09552500410801336,
      "grad_norm": 4.142937660217285,
      "learning_rate": 0.00019951659487560391,
      "loss": 1.9706,
      "step": 1744
    },
    {
      "epoch": 0.09557977761954319,
      "grad_norm": 8.665338516235352,
      "learning_rate": 0.00019951601279899478,
      "loss": 0.6556,
      "step": 1745
    },
    {
      "epoch": 0.09563455113107301,
      "grad_norm": 5.229712963104248,
      "learning_rate": 0.0001995154598262161,
      "loss": 1.1388,
      "step": 1746
    },
    {
      "epoch": 0.09568932464260284,
      "grad_norm": 5.1271162033081055,
      "learning_rate": 0.0001995148923015222,
      "loss": 1.0896,
      "step": 1747
    },
    {
      "epoch": 0.09574409815413266,
      "grad_norm": 7.014554977416992,
      "learning_rate": 0.0001995143247768283,
      "loss": 1.2773,
      "step": 1748
    },
    {
      "epoch": 0.09579887166566249,
      "grad_norm": 5.28106164932251,
      "learning_rate": 0.00019951375725213438,
      "loss": 1.7505,
      "step": 1749
    },
    {
      "epoch": 0.0958536451771923,
      "grad_norm": 8.524224281311035,
      "learning_rate": 0.00019951318972744048,
      "loss": 1.8971,
      "step": 1750
    },
    {
      "epoch": 0.09590841868872213,
      "grad_norm": 2.8733017444610596,
      "learning_rate": 0.0001995126367546618,
      "loss": 0.9363,
      "step": 1751
    },
    {
      "epoch": 0.09596319220025196,
      "grad_norm": 8.174698829650879,
      "learning_rate": 0.0001995120692299679,
      "loss": 1.2486,
      "step": 1752
    },
    {
      "epoch": 0.09601796571178178,
      "grad_norm": 3.1510748863220215,
      "learning_rate": 0.00019951150170527399,
      "loss": 1.8346,
      "step": 1753
    },
    {
      "epoch": 0.09607273922331161,
      "grad_norm": 5.399638652801514,
      "learning_rate": 0.00019951093418058008,
      "loss": 1.0717,
      "step": 1754
    },
    {
      "epoch": 0.09612751273484144,
      "grad_norm": 8.204363822937012,
      "learning_rate": 0.00019951036665588617,
      "loss": 2.5344,
      "step": 1755
    },
    {
      "epoch": 0.09618228624637125,
      "grad_norm": 9.668304443359375,
      "learning_rate": 0.00019950979913119227,
      "loss": 2.0912,
      "step": 1756
    },
    {
      "epoch": 0.09623705975790108,
      "grad_norm": 3.4727652072906494,
      "learning_rate": 0.00019950923160649836,
      "loss": 1.9356,
      "step": 1757
    },
    {
      "epoch": 0.0962918332694309,
      "grad_norm": 7.371083736419678,
      "learning_rate": 0.00019950866408180445,
      "loss": 1.344,
      "step": 1758
    },
    {
      "epoch": 0.09634660678096073,
      "grad_norm": 2.298321008682251,
      "learning_rate": 0.00019950809655711055,
      "loss": 0.8885,
      "step": 1759
    },
    {
      "epoch": 0.09640138029249055,
      "grad_norm": 2.5113284587860107,
      "learning_rate": 0.00019950752903241664,
      "loss": 1.591,
      "step": 1760
    },
    {
      "epoch": 0.09645615380402038,
      "grad_norm": 2.852226495742798,
      "learning_rate": 0.00019950696150772274,
      "loss": 0.9527,
      "step": 1761
    },
    {
      "epoch": 0.0965109273155502,
      "grad_norm": 3.186530351638794,
      "learning_rate": 0.0001995063794311136,
      "loss": 1.0311,
      "step": 1762
    },
    {
      "epoch": 0.09656570082708002,
      "grad_norm": 2.648871898651123,
      "learning_rate": 0.0001995058119064197,
      "loss": 1.1579,
      "step": 1763
    },
    {
      "epoch": 0.09662047433860985,
      "grad_norm": 4.486452579498291,
      "learning_rate": 0.00019950525893364102,
      "loss": 1.5712,
      "step": 1764
    },
    {
      "epoch": 0.09667524785013967,
      "grad_norm": 2.7985925674438477,
      "learning_rate": 0.00019950467685703188,
      "loss": 0.9926,
      "step": 1765
    },
    {
      "epoch": 0.0967300213616695,
      "grad_norm": 9.927842140197754,
      "learning_rate": 0.00019950410933233798,
      "loss": 3.3276,
      "step": 1766
    },
    {
      "epoch": 0.09678479487319933,
      "grad_norm": 3.2434985637664795,
      "learning_rate": 0.00019950354180764407,
      "loss": 1.0788,
      "step": 1767
    },
    {
      "epoch": 0.09683956838472914,
      "grad_norm": 3.0872771739959717,
      "learning_rate": 0.00019950295973103493,
      "loss": 1.0205,
      "step": 1768
    },
    {
      "epoch": 0.09689434189625896,
      "grad_norm": 2.5954806804656982,
      "learning_rate": 0.00019950239220634103,
      "loss": 0.2781,
      "step": 1769
    },
    {
      "epoch": 0.09694911540778879,
      "grad_norm": 2.164501905441284,
      "learning_rate": 0.00019950182468164712,
      "loss": 1.2394,
      "step": 1770
    },
    {
      "epoch": 0.09700388891931862,
      "grad_norm": 1.9297341108322144,
      "learning_rate": 0.000199501242605038,
      "loss": 1.1728,
      "step": 1771
    },
    {
      "epoch": 0.09705866243084844,
      "grad_norm": 3.7778513431549072,
      "learning_rate": 0.00019950067508034408,
      "loss": 0.9456,
      "step": 1772
    },
    {
      "epoch": 0.09711343594237827,
      "grad_norm": 9.403797149658203,
      "learning_rate": 0.00019950010755565017,
      "loss": 2.7684,
      "step": 1773
    },
    {
      "epoch": 0.09716820945390808,
      "grad_norm": 4.247941017150879,
      "learning_rate": 0.00019949952547904104,
      "loss": 1.0527,
      "step": 1774
    },
    {
      "epoch": 0.09722298296543791,
      "grad_norm": 3.1958489418029785,
      "learning_rate": 0.00019949895795434713,
      "loss": 1.427,
      "step": 1775
    },
    {
      "epoch": 0.09727775647696774,
      "grad_norm": 3.371579647064209,
      "learning_rate": 0.00019949839042965323,
      "loss": 1.1556,
      "step": 1776
    },
    {
      "epoch": 0.09733252998849756,
      "grad_norm": 3.3798880577087402,
      "learning_rate": 0.0001994978083530441,
      "loss": 1.3945,
      "step": 1777
    },
    {
      "epoch": 0.09738730350002739,
      "grad_norm": 2.414996385574341,
      "learning_rate": 0.00019949722627643496,
      "loss": 1.5379,
      "step": 1778
    },
    {
      "epoch": 0.09744207701155722,
      "grad_norm": 1.5653700828552246,
      "learning_rate": 0.00019949665875174105,
      "loss": 0.7863,
      "step": 1779
    },
    {
      "epoch": 0.09749685052308704,
      "grad_norm": 2.9738993644714355,
      "learning_rate": 0.00019949609122704715,
      "loss": 1.1626,
      "step": 1780
    },
    {
      "epoch": 0.09755162403461685,
      "grad_norm": 7.854586124420166,
      "learning_rate": 0.00019949549459852278,
      "loss": 1.3594,
      "step": 1781
    },
    {
      "epoch": 0.09760639754614668,
      "grad_norm": 2.3894333839416504,
      "learning_rate": 0.00019949492707382888,
      "loss": 1.1781,
      "step": 1782
    },
    {
      "epoch": 0.09766117105767651,
      "grad_norm": 3.33176851272583,
      "learning_rate": 0.00019949435954913497,
      "loss": 1.5442,
      "step": 1783
    },
    {
      "epoch": 0.09771594456920633,
      "grad_norm": 1.5332276821136475,
      "learning_rate": 0.00019949377747252584,
      "loss": 0.3197,
      "step": 1784
    },
    {
      "epoch": 0.09777071808073616,
      "grad_norm": 3.7499499320983887,
      "learning_rate": 0.0001994931953959167,
      "loss": 1.8758,
      "step": 1785
    },
    {
      "epoch": 0.09782549159226599,
      "grad_norm": 1.6528342962265015,
      "learning_rate": 0.0001994926278712228,
      "loss": 0.628,
      "step": 1786
    },
    {
      "epoch": 0.0978802651037958,
      "grad_norm": 11.0723295211792,
      "learning_rate": 0.00019949204579461366,
      "loss": 3.2053,
      "step": 1787
    },
    {
      "epoch": 0.09793503861532563,
      "grad_norm": 2.9138479232788086,
      "learning_rate": 0.00019949147826991975,
      "loss": 1.3303,
      "step": 1788
    },
    {
      "epoch": 0.09798981212685545,
      "grad_norm": 2.8633129596710205,
      "learning_rate": 0.0001994908816413954,
      "loss": 1.2231,
      "step": 1789
    },
    {
      "epoch": 0.09804458563838528,
      "grad_norm": 6.167202472686768,
      "learning_rate": 0.00019949031411670148,
      "loss": 1.1135,
      "step": 1790
    },
    {
      "epoch": 0.0980993591499151,
      "grad_norm": 2.066720724105835,
      "learning_rate": 0.00019948973204009235,
      "loss": 1.1756,
      "step": 1791
    },
    {
      "epoch": 0.09815413266144493,
      "grad_norm": 7.668239593505859,
      "learning_rate": 0.00019948916451539844,
      "loss": 1.4441,
      "step": 1792
    },
    {
      "epoch": 0.09820890617297474,
      "grad_norm": 2.545876979827881,
      "learning_rate": 0.0001994885824387893,
      "loss": 1.4338,
      "step": 1793
    },
    {
      "epoch": 0.09826367968450457,
      "grad_norm": 6.887261867523193,
      "learning_rate": 0.00019948798581026495,
      "loss": 2.3364,
      "step": 1794
    },
    {
      "epoch": 0.0983184531960344,
      "grad_norm": 2.963183879852295,
      "learning_rate": 0.00019948741828557104,
      "loss": 1.3663,
      "step": 1795
    },
    {
      "epoch": 0.09837322670756422,
      "grad_norm": 2.4916186332702637,
      "learning_rate": 0.0001994868362089619,
      "loss": 1.5044,
      "step": 1796
    },
    {
      "epoch": 0.09842800021909405,
      "grad_norm": 12.172907829284668,
      "learning_rate": 0.00019948625413235277,
      "loss": 2.82,
      "step": 1797
    },
    {
      "epoch": 0.09848277373062388,
      "grad_norm": 3.075561285018921,
      "learning_rate": 0.00019948567205574363,
      "loss": 1.5581,
      "step": 1798
    },
    {
      "epoch": 0.09853754724215369,
      "grad_norm": 3.3067069053649902,
      "learning_rate": 0.0001994850899791345,
      "loss": 1.7518,
      "step": 1799
    },
    {
      "epoch": 0.09859232075368352,
      "grad_norm": 5.215954780578613,
      "learning_rate": 0.00019948450790252537,
      "loss": 2.0323,
      "step": 1800
    },
    {
      "epoch": 0.09859232075368352,
      "eval_loss": 1.4282009601593018,
      "eval_runtime": 45.8051,
      "eval_samples_per_second": 2.009,
      "eval_steps_per_second": 2.009,
      "step": 1800
    },
    {
      "epoch": 0.09864709426521334,
      "grad_norm": 3.8546948432922363,
      "learning_rate": 0.00019948392582591623,
      "loss": 0.5203,
      "step": 1801
    },
    {
      "epoch": 0.09870186777674317,
      "grad_norm": 3.781024217605591,
      "learning_rate": 0.0001994833437493071,
      "loss": 1.6861,
      "step": 1802
    },
    {
      "epoch": 0.098756641288273,
      "grad_norm": 2.9869425296783447,
      "learning_rate": 0.00019948276167269796,
      "loss": 1.1671,
      "step": 1803
    },
    {
      "epoch": 0.09881141479980282,
      "grad_norm": 5.464297294616699,
      "learning_rate": 0.00019948217959608883,
      "loss": 1.8935,
      "step": 1804
    },
    {
      "epoch": 0.09886618831133263,
      "grad_norm": 6.277845859527588,
      "learning_rate": 0.00019948158296756446,
      "loss": 0.7775,
      "step": 1805
    },
    {
      "epoch": 0.09892096182286246,
      "grad_norm": 20.088220596313477,
      "learning_rate": 0.00019948100089095533,
      "loss": 3.1423,
      "step": 1806
    },
    {
      "epoch": 0.09897573533439229,
      "grad_norm": 12.158109664916992,
      "learning_rate": 0.0001994804188143462,
      "loss": 2.7274,
      "step": 1807
    },
    {
      "epoch": 0.09903050884592211,
      "grad_norm": 9.296465873718262,
      "learning_rate": 0.00019947983673773706,
      "loss": 2.8062,
      "step": 1808
    },
    {
      "epoch": 0.09908528235745194,
      "grad_norm": 3.023076057434082,
      "learning_rate": 0.00019947925466112792,
      "loss": 1.7602,
      "step": 1809
    },
    {
      "epoch": 0.09914005586898177,
      "grad_norm": 2.9368622303009033,
      "learning_rate": 0.0001994786725845188,
      "loss": 1.6559,
      "step": 1810
    },
    {
      "epoch": 0.09919482938051158,
      "grad_norm": 2.8509392738342285,
      "learning_rate": 0.00019947809050790966,
      "loss": 1.7867,
      "step": 1811
    },
    {
      "epoch": 0.0992496028920414,
      "grad_norm": 5.3155837059021,
      "learning_rate": 0.0001994774938793853,
      "loss": 2.0592,
      "step": 1812
    },
    {
      "epoch": 0.09930437640357123,
      "grad_norm": 7.001282215118408,
      "learning_rate": 0.00019947691180277616,
      "loss": 1.6101,
      "step": 1813
    },
    {
      "epoch": 0.09935914991510106,
      "grad_norm": 2.9061944484710693,
      "learning_rate": 0.00019947632972616702,
      "loss": 1.6325,
      "step": 1814
    },
    {
      "epoch": 0.09941392342663088,
      "grad_norm": 4.167232513427734,
      "learning_rate": 0.00019947573309764266,
      "loss": 1.5199,
      "step": 1815
    },
    {
      "epoch": 0.09946869693816071,
      "grad_norm": 3.4173386096954346,
      "learning_rate": 0.00019947515102103353,
      "loss": 1.1667,
      "step": 1816
    },
    {
      "epoch": 0.09952347044969052,
      "grad_norm": 7.581405162811279,
      "learning_rate": 0.0001994745689444244,
      "loss": 1.777,
      "step": 1817
    },
    {
      "epoch": 0.09957824396122035,
      "grad_norm": 2.3832995891571045,
      "learning_rate": 0.00019947398686781526,
      "loss": 0.9963,
      "step": 1818
    },
    {
      "epoch": 0.09963301747275018,
      "grad_norm": 3.554032802581787,
      "learning_rate": 0.0001994733902392909,
      "loss": 1.4269,
      "step": 1819
    },
    {
      "epoch": 0.09968779098428,
      "grad_norm": 2.9356231689453125,
      "learning_rate": 0.00019947280816268176,
      "loss": 1.0813,
      "step": 1820
    },
    {
      "epoch": 0.09974256449580983,
      "grad_norm": 5.936192989349365,
      "learning_rate": 0.00019947222608607262,
      "loss": 1.9394,
      "step": 1821
    },
    {
      "epoch": 0.09979733800733966,
      "grad_norm": 4.02824592590332,
      "learning_rate": 0.00019947162945754826,
      "loss": 1.4028,
      "step": 1822
    },
    {
      "epoch": 0.09985211151886947,
      "grad_norm": 7.492675304412842,
      "learning_rate": 0.0001994710328290239,
      "loss": 1.8142,
      "step": 1823
    },
    {
      "epoch": 0.0999068850303993,
      "grad_norm": 9.210909843444824,
      "learning_rate": 0.00019947043620049953,
      "loss": 2.185,
      "step": 1824
    },
    {
      "epoch": 0.09996165854192912,
      "grad_norm": 3.7197258472442627,
      "learning_rate": 0.0001994698541238904,
      "loss": 1.2431,
      "step": 1825
    },
    {
      "epoch": 0.10001643205345895,
      "grad_norm": 7.044360160827637,
      "learning_rate": 0.00019946925749536604,
      "loss": 1.7099,
      "step": 1826
    },
    {
      "epoch": 0.10007120556498877,
      "grad_norm": 2.761525869369507,
      "learning_rate": 0.0001994686754187569,
      "loss": 1.2355,
      "step": 1827
    },
    {
      "epoch": 0.1001259790765186,
      "grad_norm": 4.938474178314209,
      "learning_rate": 0.00019946807879023254,
      "loss": 1.4506,
      "step": 1828
    },
    {
      "epoch": 0.10018075258804841,
      "grad_norm": 6.595236778259277,
      "learning_rate": 0.0001994674967136234,
      "loss": 1.1941,
      "step": 1829
    },
    {
      "epoch": 0.10023552609957824,
      "grad_norm": 8.319955825805664,
      "learning_rate": 0.00019946690008509904,
      "loss": 1.6507,
      "step": 1830
    },
    {
      "epoch": 0.10029029961110807,
      "grad_norm": 13.318974494934082,
      "learning_rate": 0.00019946630345657468,
      "loss": 2.2487,
      "step": 1831
    },
    {
      "epoch": 0.10034507312263789,
      "grad_norm": 1.5066258907318115,
      "learning_rate": 0.00019946572137996554,
      "loss": 0.6026,
      "step": 1832
    },
    {
      "epoch": 0.10039984663416772,
      "grad_norm": 2.2993364334106445,
      "learning_rate": 0.00019946512475144118,
      "loss": 1.2659,
      "step": 1833
    },
    {
      "epoch": 0.10045462014569755,
      "grad_norm": 3.5633597373962402,
      "learning_rate": 0.00019946452812291682,
      "loss": 1.3637,
      "step": 1834
    },
    {
      "epoch": 0.10050939365722736,
      "grad_norm": 4.434072971343994,
      "learning_rate": 0.00019946393149439245,
      "loss": 1.8591,
      "step": 1835
    },
    {
      "epoch": 0.10056416716875718,
      "grad_norm": 4.084584712982178,
      "learning_rate": 0.00019946334941778332,
      "loss": 1.3568,
      "step": 1836
    },
    {
      "epoch": 0.10061894068028701,
      "grad_norm": 5.759298324584961,
      "learning_rate": 0.00019946275278925896,
      "loss": 1.2103,
      "step": 1837
    },
    {
      "epoch": 0.10067371419181684,
      "grad_norm": 15.634417533874512,
      "learning_rate": 0.0001994621561607346,
      "loss": 2.1667,
      "step": 1838
    },
    {
      "epoch": 0.10072848770334666,
      "grad_norm": 2.7730205059051514,
      "learning_rate": 0.00019946155953221023,
      "loss": 1.2137,
      "step": 1839
    },
    {
      "epoch": 0.10078326121487649,
      "grad_norm": 2.280982255935669,
      "learning_rate": 0.00019946096290368587,
      "loss": 1.4175,
      "step": 1840
    },
    {
      "epoch": 0.1008380347264063,
      "grad_norm": 6.145959377288818,
      "learning_rate": 0.0001994603662751615,
      "loss": 1.8612,
      "step": 1841
    },
    {
      "epoch": 0.10089280823793613,
      "grad_norm": 2.550093412399292,
      "learning_rate": 0.00019945976964663714,
      "loss": 1.1868,
      "step": 1842
    },
    {
      "epoch": 0.10094758174946596,
      "grad_norm": 2.951878786087036,
      "learning_rate": 0.00019945917301811278,
      "loss": 1.4326,
      "step": 1843
    },
    {
      "epoch": 0.10100235526099578,
      "grad_norm": 3.958461046218872,
      "learning_rate": 0.00019945857638958842,
      "loss": 1.6951,
      "step": 1844
    },
    {
      "epoch": 0.10105712877252561,
      "grad_norm": 2.450077772140503,
      "learning_rate": 0.00019945797976106405,
      "loss": 0.5035,
      "step": 1845
    },
    {
      "epoch": 0.10111190228405544,
      "grad_norm": 5.428252696990967,
      "learning_rate": 0.0001994573831325397,
      "loss": 1.5036,
      "step": 1846
    },
    {
      "epoch": 0.10116667579558525,
      "grad_norm": 6.934701442718506,
      "learning_rate": 0.00019945680105593055,
      "loss": 0.9149,
      "step": 1847
    },
    {
      "epoch": 0.10122144930711507,
      "grad_norm": 3.0453102588653564,
      "learning_rate": 0.0001994562044274062,
      "loss": 1.4526,
      "step": 1848
    },
    {
      "epoch": 0.1012762228186449,
      "grad_norm": 5.676654815673828,
      "learning_rate": 0.00019945560779888183,
      "loss": 1.2067,
      "step": 1849
    },
    {
      "epoch": 0.10133099633017473,
      "grad_norm": 4.689570903778076,
      "learning_rate": 0.00019945501117035747,
      "loss": 1.8942,
      "step": 1850
    },
    {
      "epoch": 0.10138576984170455,
      "grad_norm": 2.045813798904419,
      "learning_rate": 0.00019945439998991787,
      "loss": 1.1351,
      "step": 1851
    },
    {
      "epoch": 0.10144054335323438,
      "grad_norm": 23.710771560668945,
      "learning_rate": 0.0001994538033613935,
      "loss": 3.3836,
      "step": 1852
    },
    {
      "epoch": 0.1014953168647642,
      "grad_norm": 3.4462273120880127,
      "learning_rate": 0.00019945320673286915,
      "loss": 1.4525,
      "step": 1853
    },
    {
      "epoch": 0.10155009037629402,
      "grad_norm": 3.6417644023895264,
      "learning_rate": 0.00019945261010434479,
      "loss": 0.9514,
      "step": 1854
    },
    {
      "epoch": 0.10160486388782385,
      "grad_norm": 5.392815589904785,
      "learning_rate": 0.0001994519989239052,
      "loss": 1.8253,
      "step": 1855
    },
    {
      "epoch": 0.10165963739935367,
      "grad_norm": 2.7808806896209717,
      "learning_rate": 0.00019945140229538083,
      "loss": 1.0775,
      "step": 1856
    },
    {
      "epoch": 0.1017144109108835,
      "grad_norm": 6.551398277282715,
      "learning_rate": 0.00019945080566685647,
      "loss": 2.4638,
      "step": 1857
    },
    {
      "epoch": 0.10176918442241333,
      "grad_norm": 3.701451539993286,
      "learning_rate": 0.00019945019448641688,
      "loss": 1.7492,
      "step": 1858
    },
    {
      "epoch": 0.10182395793394315,
      "grad_norm": 6.419137001037598,
      "learning_rate": 0.00019944961240980774,
      "loss": 2.4334,
      "step": 1859
    },
    {
      "epoch": 0.10187873144547296,
      "grad_norm": 19.80063247680664,
      "learning_rate": 0.00019944900122936815,
      "loss": 1.8548,
      "step": 1860
    },
    {
      "epoch": 0.10193350495700279,
      "grad_norm": 3.8727643489837646,
      "learning_rate": 0.0001994484046008438,
      "loss": 1.9761,
      "step": 1861
    },
    {
      "epoch": 0.10198827846853262,
      "grad_norm": 8.819198608398438,
      "learning_rate": 0.0001994477934204042,
      "loss": 1.7611,
      "step": 1862
    },
    {
      "epoch": 0.10204305198006244,
      "grad_norm": 2.1019418239593506,
      "learning_rate": 0.00019944719679187983,
      "loss": 1.1403,
      "step": 1863
    },
    {
      "epoch": 0.10209782549159227,
      "grad_norm": 3.8152120113372803,
      "learning_rate": 0.00019944658561144024,
      "loss": 1.9315,
      "step": 1864
    },
    {
      "epoch": 0.1021525990031221,
      "grad_norm": 4.02876091003418,
      "learning_rate": 0.00019944598898291588,
      "loss": 1.6145,
      "step": 1865
    },
    {
      "epoch": 0.10220737251465191,
      "grad_norm": 3.521867275238037,
      "learning_rate": 0.00019944539235439152,
      "loss": 1.951,
      "step": 1866
    },
    {
      "epoch": 0.10226214602618174,
      "grad_norm": 3.1583070755004883,
      "learning_rate": 0.00019944478117395192,
      "loss": 1.1244,
      "step": 1867
    },
    {
      "epoch": 0.10231691953771156,
      "grad_norm": 2.827655792236328,
      "learning_rate": 0.00019944418454542756,
      "loss": 1.2546,
      "step": 1868
    },
    {
      "epoch": 0.10237169304924139,
      "grad_norm": 5.409700870513916,
      "learning_rate": 0.00019944357336498797,
      "loss": 1.6044,
      "step": 1869
    },
    {
      "epoch": 0.10242646656077121,
      "grad_norm": 6.389496803283691,
      "learning_rate": 0.00019944296218454838,
      "loss": 2.1491,
      "step": 1870
    },
    {
      "epoch": 0.10248124007230104,
      "grad_norm": 9.527792930603027,
      "learning_rate": 0.0001994423510041088,
      "loss": 2.2999,
      "step": 1871
    },
    {
      "epoch": 0.10253601358383085,
      "grad_norm": 3.9300289154052734,
      "learning_rate": 0.00019944176892749965,
      "loss": 1.8294,
      "step": 1872
    },
    {
      "epoch": 0.10259078709536068,
      "grad_norm": 2.085177183151245,
      "learning_rate": 0.00019944115774706006,
      "loss": 1.4306,
      "step": 1873
    },
    {
      "epoch": 0.1026455606068905,
      "grad_norm": 2.2292897701263428,
      "learning_rate": 0.00019944054656662047,
      "loss": 0.7711,
      "step": 1874
    },
    {
      "epoch": 0.10270033411842033,
      "grad_norm": 24.590848922729492,
      "learning_rate": 0.00019943993538618088,
      "loss": 2.7812,
      "step": 1875
    },
    {
      "epoch": 0.10275510762995016,
      "grad_norm": 7.477816581726074,
      "learning_rate": 0.00019943932420574129,
      "loss": 2.1254,
      "step": 1876
    },
    {
      "epoch": 0.10280988114147999,
      "grad_norm": 1.9157342910766602,
      "learning_rate": 0.00019943872757721692,
      "loss": 0.8909,
      "step": 1877
    },
    {
      "epoch": 0.1028646546530098,
      "grad_norm": 2.535543203353882,
      "learning_rate": 0.00019943811639677733,
      "loss": 1.7207,
      "step": 1878
    },
    {
      "epoch": 0.10291942816453963,
      "grad_norm": 3.701524257659912,
      "learning_rate": 0.00019943750521633774,
      "loss": 1.991,
      "step": 1879
    },
    {
      "epoch": 0.10297420167606945,
      "grad_norm": 10.9535551071167,
      "learning_rate": 0.00019943689403589815,
      "loss": 3.1444,
      "step": 1880
    },
    {
      "epoch": 0.10302897518759928,
      "grad_norm": 3.6761090755462646,
      "learning_rate": 0.00019943628285545856,
      "loss": 2.7595,
      "step": 1881
    },
    {
      "epoch": 0.1030837486991291,
      "grad_norm": 5.340241432189941,
      "learning_rate": 0.0001994356862269342,
      "loss": 1.0692,
      "step": 1882
    },
    {
      "epoch": 0.10313852221065893,
      "grad_norm": 2.0909578800201416,
      "learning_rate": 0.0001994350750464946,
      "loss": 1.4183,
      "step": 1883
    },
    {
      "epoch": 0.10319329572218874,
      "grad_norm": 4.1810455322265625,
      "learning_rate": 0.000199434463866055,
      "loss": 0.924,
      "step": 1884
    },
    {
      "epoch": 0.10324806923371857,
      "grad_norm": 18.529428482055664,
      "learning_rate": 0.00019943385268561542,
      "loss": 2.8434,
      "step": 1885
    },
    {
      "epoch": 0.1033028427452484,
      "grad_norm": 3.495797872543335,
      "learning_rate": 0.00019943325605709106,
      "loss": 1.5539,
      "step": 1886
    },
    {
      "epoch": 0.10335761625677822,
      "grad_norm": 3.0535025596618652,
      "learning_rate": 0.00019943264487665147,
      "loss": 0.9195,
      "step": 1887
    },
    {
      "epoch": 0.10341238976830805,
      "grad_norm": 2.238903284072876,
      "learning_rate": 0.00019943201914429665,
      "loss": 1.3202,
      "step": 1888
    },
    {
      "epoch": 0.10346716327983788,
      "grad_norm": 5.551600933074951,
      "learning_rate": 0.00019943140796385705,
      "loss": 2.2327,
      "step": 1889
    },
    {
      "epoch": 0.10352193679136769,
      "grad_norm": 2.4146406650543213,
      "learning_rate": 0.0001994308113353327,
      "loss": 1.1681,
      "step": 1890
    },
    {
      "epoch": 0.10357671030289752,
      "grad_norm": 2.234593152999878,
      "learning_rate": 0.0001994302001548931,
      "loss": 0.8746,
      "step": 1891
    },
    {
      "epoch": 0.10363148381442734,
      "grad_norm": 2.3647313117980957,
      "learning_rate": 0.00019942957442253828,
      "loss": 1.5359,
      "step": 1892
    },
    {
      "epoch": 0.10368625732595717,
      "grad_norm": 4.106690883636475,
      "learning_rate": 0.00019942897779401392,
      "loss": 1.4351,
      "step": 1893
    },
    {
      "epoch": 0.103741030837487,
      "grad_norm": 13.654232025146484,
      "learning_rate": 0.0001994283520616591,
      "loss": 1.1637,
      "step": 1894
    },
    {
      "epoch": 0.10379580434901682,
      "grad_norm": 2.655611038208008,
      "learning_rate": 0.0001994277408812195,
      "loss": 1.9033,
      "step": 1895
    },
    {
      "epoch": 0.10385057786054663,
      "grad_norm": 10.075474739074707,
      "learning_rate": 0.00019942712970077991,
      "loss": 3.376,
      "step": 1896
    },
    {
      "epoch": 0.10390535137207646,
      "grad_norm": 5.982178688049316,
      "learning_rate": 0.00019942651852034032,
      "loss": 1.7437,
      "step": 1897
    },
    {
      "epoch": 0.10396012488360629,
      "grad_norm": 4.259973049163818,
      "learning_rate": 0.00019942590733990073,
      "loss": 1.4645,
      "step": 1898
    },
    {
      "epoch": 0.10401489839513611,
      "grad_norm": 3.801454782485962,
      "learning_rate": 0.0001994252816075459,
      "loss": 1.6512,
      "step": 1899
    },
    {
      "epoch": 0.10406967190666594,
      "grad_norm": 2.5095059871673584,
      "learning_rate": 0.00019942468497902155,
      "loss": 1.6014,
      "step": 1900
    },
    {
      "epoch": 0.10406967190666594,
      "eval_loss": 1.4160813093185425,
      "eval_runtime": 45.8133,
      "eval_samples_per_second": 2.008,
      "eval_steps_per_second": 2.008,
      "step": 1900
    }
  ],
  "logging_steps": 1,
  "max_steps": 54771,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.502061563510784e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}