{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9990771103736721,
  "eval_steps": 50,
  "global_step": 795,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012567007677656253,
      "grad_norm": 18.75091794627999,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 0.7624,
      "step": 1
    },
    {
      "epoch": 0.0025134015355312506,
      "grad_norm": 17.52654411272103,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.7516,
      "step": 2
    },
    {
      "epoch": 0.003770102303296876,
      "grad_norm": 16.514255723157607,
      "learning_rate": 7.5e-07,
      "loss": 0.7638,
      "step": 3
    },
    {
      "epoch": 0.005026803071062501,
      "grad_norm": 15.863246140843936,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.7628,
      "step": 4
    },
    {
      "epoch": 0.006283503838828127,
      "grad_norm": 16.009485294186245,
      "learning_rate": 1.25e-06,
      "loss": 0.6841,
      "step": 5
    },
    {
      "epoch": 0.007540204606593752,
      "grad_norm": 12.359798457900594,
      "learning_rate": 1.5e-06,
      "loss": 0.6439,
      "step": 6
    },
    {
      "epoch": 0.008796905374359378,
      "grad_norm": 7.382396803359724,
      "learning_rate": 1.75e-06,
      "loss": 0.6556,
      "step": 7
    },
    {
      "epoch": 0.010053606142125002,
      "grad_norm": 9.902433893820467,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.5683,
      "step": 8
    },
    {
      "epoch": 0.011310306909890627,
      "grad_norm": 5.336530839540533,
      "learning_rate": 2.25e-06,
      "loss": 0.5813,
      "step": 9
    },
    {
      "epoch": 0.012567007677656254,
      "grad_norm": 4.96442690704384,
      "learning_rate": 2.5e-06,
      "loss": 0.5555,
      "step": 10
    },
    {
      "epoch": 0.013823708445421879,
      "grad_norm": 4.049027389723904,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.5449,
      "step": 11
    },
    {
      "epoch": 0.015080409213187504,
      "grad_norm": 2.9876344466981175,
      "learning_rate": 3e-06,
      "loss": 0.5739,
      "step": 12
    },
    {
      "epoch": 0.01633710998095313,
      "grad_norm": 3.5573781991080535,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.5489,
      "step": 13
    },
    {
      "epoch": 0.017593810748718755,
      "grad_norm": 2.8413983357245605,
      "learning_rate": 3.5e-06,
      "loss": 0.5336,
      "step": 14
    },
    {
      "epoch": 0.01885051151648438,
      "grad_norm": 3.025149469387222,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.6036,
      "step": 15
    },
    {
      "epoch": 0.020107212284250005,
      "grad_norm": 3.220040516331875,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.5046,
      "step": 16
    },
    {
      "epoch": 0.02136391305201563,
      "grad_norm": 2.783851178663962,
      "learning_rate": 4.25e-06,
      "loss": 0.5365,
      "step": 17
    },
    {
      "epoch": 0.022620613819781255,
      "grad_norm": 2.897929267846762,
      "learning_rate": 4.5e-06,
      "loss": 0.5198,
      "step": 18
    },
    {
      "epoch": 0.02387731458754688,
      "grad_norm": 2.506735216769208,
      "learning_rate": 4.75e-06,
      "loss": 0.5094,
      "step": 19
    },
    {
      "epoch": 0.025134015355312508,
      "grad_norm": 2.565147056156479,
      "learning_rate": 5e-06,
      "loss": 0.5352,
      "step": 20
    },
    {
      "epoch": 0.026390716123078133,
      "grad_norm": 2.516902243933518,
      "learning_rate": 5.2500000000000006e-06,
      "loss": 0.5026,
      "step": 21
    },
    {
      "epoch": 0.027647416890843757,
      "grad_norm": 2.7534715241704832,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.5186,
      "step": 22
    },
    {
      "epoch": 0.028904117658609382,
      "grad_norm": 2.9905067284933606,
      "learning_rate": 5.75e-06,
      "loss": 0.5913,
      "step": 23
    },
    {
      "epoch": 0.030160818426375007,
      "grad_norm": 2.3261883764698608,
      "learning_rate": 6e-06,
      "loss": 0.5275,
      "step": 24
    },
    {
      "epoch": 0.03141751919414063,
      "grad_norm": 2.2175719666441704,
      "learning_rate": 6.25e-06,
      "loss": 0.4986,
      "step": 25
    },
    {
      "epoch": 0.03267421996190626,
      "grad_norm": 2.499813549718401,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 0.5014,
      "step": 26
    },
    {
      "epoch": 0.03393092072967188,
      "grad_norm": 2.217010030707422,
      "learning_rate": 6.750000000000001e-06,
      "loss": 0.5205,
      "step": 27
    },
    {
      "epoch": 0.03518762149743751,
      "grad_norm": 2.30544152290609,
      "learning_rate": 7e-06,
      "loss": 0.5144,
      "step": 28
    },
    {
      "epoch": 0.03644432226520313,
      "grad_norm": 2.322128869370069,
      "learning_rate": 7.25e-06,
      "loss": 0.583,
      "step": 29
    },
    {
      "epoch": 0.03770102303296876,
      "grad_norm": 2.326781634174622,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.4918,
      "step": 30
    },
    {
      "epoch": 0.03895772380073438,
      "grad_norm": 2.4674314043738943,
      "learning_rate": 7.75e-06,
      "loss": 0.5194,
      "step": 31
    },
    {
      "epoch": 0.04021442456850001,
      "grad_norm": 2.1812796298312707,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.5206,
      "step": 32
    },
    {
      "epoch": 0.04147112533626564,
      "grad_norm": 2.1549349105457836,
      "learning_rate": 8.25e-06,
      "loss": 0.5916,
      "step": 33
    },
    {
      "epoch": 0.04272782610403126,
      "grad_norm": 2.199454313573332,
      "learning_rate": 8.5e-06,
      "loss": 0.5276,
      "step": 34
    },
    {
      "epoch": 0.04398452687179689,
      "grad_norm": 2.1700798684465537,
      "learning_rate": 8.750000000000001e-06,
      "loss": 0.5261,
      "step": 35
    },
    {
      "epoch": 0.04524122763956251,
      "grad_norm": 2.0007451576632858,
      "learning_rate": 9e-06,
      "loss": 0.528,
      "step": 36
    },
    {
      "epoch": 0.04649792840732814,
      "grad_norm": 2.1400416338070367,
      "learning_rate": 9.250000000000001e-06,
      "loss": 0.5444,
      "step": 37
    },
    {
      "epoch": 0.04775462917509376,
      "grad_norm": 2.403488357912535,
      "learning_rate": 9.5e-06,
      "loss": 0.5155,
      "step": 38
    },
    {
      "epoch": 0.04901132994285939,
      "grad_norm": 3.009219784165261,
      "learning_rate": 9.75e-06,
      "loss": 0.5153,
      "step": 39
    },
    {
      "epoch": 0.050268030710625015,
      "grad_norm": 2.142435686354672,
      "learning_rate": 1e-05,
      "loss": 0.493,
      "step": 40
    },
    {
      "epoch": 0.05152473147839064,
      "grad_norm": 2.239870156543961,
      "learning_rate": 1.025e-05,
      "loss": 0.5078,
      "step": 41
    },
    {
      "epoch": 0.052781432246156265,
      "grad_norm": 2.6345987571093086,
      "learning_rate": 1.0500000000000001e-05,
      "loss": 0.4873,
      "step": 42
    },
    {
      "epoch": 0.05403813301392189,
      "grad_norm": 1.9418390969701194,
      "learning_rate": 1.075e-05,
      "loss": 0.4965,
      "step": 43
    },
    {
      "epoch": 0.055294833781687515,
      "grad_norm": 2.6081247589601193,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.5281,
      "step": 44
    },
    {
      "epoch": 0.056551534549453136,
      "grad_norm": 2.0666878694041433,
      "learning_rate": 1.125e-05,
      "loss": 0.5448,
      "step": 45
    },
    {
      "epoch": 0.057808235317218765,
      "grad_norm": 2.404619928095954,
      "learning_rate": 1.15e-05,
      "loss": 0.4765,
      "step": 46
    },
    {
      "epoch": 0.059064936084984386,
      "grad_norm": 2.0576801046013724,
      "learning_rate": 1.1750000000000001e-05,
      "loss": 0.5118,
      "step": 47
    },
    {
      "epoch": 0.060321636852750014,
      "grad_norm": 2.3318752319695717,
      "learning_rate": 1.2e-05,
      "loss": 0.5178,
      "step": 48
    },
    {
      "epoch": 0.06157833762051564,
      "grad_norm": 2.1469466151657293,
      "learning_rate": 1.2250000000000001e-05,
      "loss": 0.5127,
      "step": 49
    },
    {
      "epoch": 0.06283503838828126,
      "grad_norm": 2.122786996441985,
      "learning_rate": 1.25e-05,
      "loss": 0.508,
      "step": 50
    },
    {
      "epoch": 0.06283503838828126,
      "eval_loss": NaN,
      "eval_runtime": 399.176,
      "eval_samples_per_second": 20.83,
      "eval_steps_per_second": 2.605,
      "step": 50
    },
    {
      "epoch": 0.06409173915604689,
      "grad_norm": 2.1375097174172617,
      "learning_rate": 1.275e-05,
      "loss": 0.5397,
      "step": 51
    },
    {
      "epoch": 0.06534843992381252,
      "grad_norm": 2.106065428482765,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.4904,
      "step": 52
    },
    {
      "epoch": 0.06660514069157814,
      "grad_norm": 2.0188566811543973,
      "learning_rate": 1.325e-05,
      "loss": 0.5276,
      "step": 53
    },
    {
      "epoch": 0.06786184145934376,
      "grad_norm": 2.243686294713883,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 0.604,
      "step": 54
    },
    {
      "epoch": 0.06911854222710939,
      "grad_norm": 2.195249183257568,
      "learning_rate": 1.375e-05,
      "loss": 0.4981,
      "step": 55
    },
    {
      "epoch": 0.07037524299487502,
      "grad_norm": 2.192582683330822,
      "learning_rate": 1.4e-05,
      "loss": 0.5028,
      "step": 56
    },
    {
      "epoch": 0.07163194376264065,
      "grad_norm": 2.0627327989918185,
      "learning_rate": 1.425e-05,
      "loss": 0.5125,
      "step": 57
    },
    {
      "epoch": 0.07288864453040626,
      "grad_norm": 1.872712329188738,
      "learning_rate": 1.45e-05,
      "loss": 0.508,
      "step": 58
    },
    {
      "epoch": 0.07414534529817189,
      "grad_norm": 2.2251336046889008,
      "learning_rate": 1.4750000000000003e-05,
      "loss": 0.5025,
      "step": 59
    },
    {
      "epoch": 0.07540204606593752,
      "grad_norm": 1.974200197833877,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.5279,
      "step": 60
    },
    {
      "epoch": 0.07665874683370315,
      "grad_norm": 1.938388866679753,
      "learning_rate": 1.525e-05,
      "loss": 0.5284,
      "step": 61
    },
    {
      "epoch": 0.07791544760146876,
      "grad_norm": 1.9081681403522774,
      "learning_rate": 1.55e-05,
      "loss": 0.587,
      "step": 62
    },
    {
      "epoch": 0.07917214836923439,
      "grad_norm": 1.86283059738371,
      "learning_rate": 1.575e-05,
      "loss": 0.4899,
      "step": 63
    },
    {
      "epoch": 0.08042884913700002,
      "grad_norm": 1.947746623023955,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.5527,
      "step": 64
    },
    {
      "epoch": 0.08168554990476565,
      "grad_norm": 1.9186877361719825,
      "learning_rate": 1.6250000000000002e-05,
      "loss": 0.4835,
      "step": 65
    },
    {
      "epoch": 0.08294225067253128,
      "grad_norm": 2.044575571724766,
      "learning_rate": 1.65e-05,
      "loss": 0.5214,
      "step": 66
    },
    {
      "epoch": 0.08419895144029689,
      "grad_norm": 2.1551282978146578,
      "learning_rate": 1.675e-05,
      "loss": 0.5338,
      "step": 67
    },
    {
      "epoch": 0.08545565220806252,
      "grad_norm": 1.9391411629335615,
      "learning_rate": 1.7e-05,
      "loss": 0.5632,
      "step": 68
    },
    {
      "epoch": 0.08671235297582815,
      "grad_norm": 1.8837181224290052,
      "learning_rate": 1.7250000000000003e-05,
      "loss": 0.6073,
      "step": 69
    },
    {
      "epoch": 0.08796905374359378,
      "grad_norm": 2.234034052091539,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 0.5692,
      "step": 70
    },
    {
      "epoch": 0.0892257545113594,
      "grad_norm": 1.8949651791435709,
      "learning_rate": 1.775e-05,
      "loss": 0.5247,
      "step": 71
    },
    {
      "epoch": 0.09048245527912502,
      "grad_norm": 1.7148270660492497,
      "learning_rate": 1.8e-05,
      "loss": 0.5223,
      "step": 72
    },
    {
      "epoch": 0.09173915604689065,
      "grad_norm": 1.9445592195454198,
      "learning_rate": 1.825e-05,
      "loss": 0.5089,
      "step": 73
    },
    {
      "epoch": 0.09299585681465627,
      "grad_norm": 1.8265253877418266,
      "learning_rate": 1.8500000000000002e-05,
      "loss": 0.5236,
      "step": 74
    },
    {
      "epoch": 0.0942525575824219,
      "grad_norm": 1.8233199917702092,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.5649,
      "step": 75
    },
    {
      "epoch": 0.09550925835018752,
      "grad_norm": 2.2269645461783405,
      "learning_rate": 1.9e-05,
      "loss": 0.5303,
      "step": 76
    },
    {
      "epoch": 0.09676595911795315,
      "grad_norm": 1.8067805055645487,
      "learning_rate": 1.925e-05,
      "loss": 0.5763,
      "step": 77
    },
    {
      "epoch": 0.09802265988571877,
      "grad_norm": 2.1573534367398364,
      "learning_rate": 1.95e-05,
      "loss": 0.5314,
      "step": 78
    },
    {
      "epoch": 0.0992793606534844,
      "grad_norm": 2.0382764916384546,
      "learning_rate": 1.9750000000000002e-05,
      "loss": 0.566,
      "step": 79
    },
    {
      "epoch": 0.10053606142125003,
      "grad_norm": 1.8481169886281565,
      "learning_rate": 2e-05,
      "loss": 0.519,
      "step": 80
    },
    {
      "epoch": 0.10179276218901565,
      "grad_norm": 2.0250286194462577,
      "learning_rate": 1.9999903471186634e-05,
      "loss": 0.5109,
      "step": 81
    },
    {
      "epoch": 0.10304946295678127,
      "grad_norm": 1.9865218436602592,
      "learning_rate": 1.9999613886610097e-05,
      "loss": 0.5131,
      "step": 82
    },
    {
      "epoch": 0.1043061637245469,
      "grad_norm": 2.146087026568179,
      "learning_rate": 1.9999131251861037e-05,
      "loss": 0.5479,
      "step": 83
    },
    {
      "epoch": 0.10556286449231253,
      "grad_norm": 1.883855000830492,
      "learning_rate": 1.999845557625709e-05,
      "loss": 0.5515,
      "step": 84
    },
    {
      "epoch": 0.10681956526007814,
      "grad_norm": 1.9686030378439734,
      "learning_rate": 1.9997586872842683e-05,
      "loss": 0.527,
      "step": 85
    },
    {
      "epoch": 0.10807626602784377,
      "grad_norm": 2.36575606473121,
      "learning_rate": 1.9996525158388804e-05,
      "loss": 0.5402,
      "step": 86
    },
    {
      "epoch": 0.1093329667956094,
      "grad_norm": 1.7575993387464999,
      "learning_rate": 1.999527045339266e-05,
      "loss": 0.5285,
      "step": 87
    },
    {
      "epoch": 0.11058966756337503,
      "grad_norm": 2.385054737158702,
      "learning_rate": 1.9993822782077282e-05,
      "loss": 0.5904,
      "step": 88
    },
    {
      "epoch": 0.11184636833114066,
      "grad_norm": 1.9263541895607634,
      "learning_rate": 1.999218217239108e-05,
      "loss": 0.5315,
      "step": 89
    },
    {
      "epoch": 0.11310306909890627,
      "grad_norm": 1.985590164700294,
      "learning_rate": 1.999034865600726e-05,
      "loss": 0.5356,
      "step": 90
    },
    {
      "epoch": 0.1143597698666719,
      "grad_norm": 1.8572569893256032,
      "learning_rate": 1.998832226832327e-05,
      "loss": 0.5492,
      "step": 91
    },
    {
      "epoch": 0.11561647063443753,
      "grad_norm": 2.0556913179235305,
      "learning_rate": 1.9986103048460056e-05,
      "loss": 0.5274,
      "step": 92
    },
    {
      "epoch": 0.11687317140220316,
      "grad_norm": 1.7389370827636832,
      "learning_rate": 1.9983691039261358e-05,
      "loss": 0.5498,
      "step": 93
    },
    {
      "epoch": 0.11812987216996877,
      "grad_norm": 1.8846320386596898,
      "learning_rate": 1.9981086287292853e-05,
      "loss": 0.6494,
      "step": 94
    },
    {
      "epoch": 0.1193865729377344,
      "grad_norm": 1.6471533089571895,
      "learning_rate": 1.997828884284126e-05,
      "loss": 0.5245,
      "step": 95
    },
    {
      "epoch": 0.12064327370550003,
      "grad_norm": 1.993702988982152,
      "learning_rate": 1.9975298759913382e-05,
      "loss": 0.5261,
      "step": 96
    },
    {
      "epoch": 0.12189997447326566,
      "grad_norm": 1.74703558113797,
      "learning_rate": 1.9972116096235047e-05,
      "loss": 0.5069,
      "step": 97
    },
    {
      "epoch": 0.12315667524103129,
      "grad_norm": 1.8912653823700982,
      "learning_rate": 1.996874091325001e-05,
      "loss": 0.5378,
      "step": 98
    },
    {
      "epoch": 0.1244133760087969,
      "grad_norm": 1.9270886670287957,
      "learning_rate": 1.9965173276118747e-05,
      "loss": 0.513,
      "step": 99
    },
    {
      "epoch": 0.12567007677656253,
      "grad_norm": 1.9246733227266641,
      "learning_rate": 1.9961413253717214e-05,
      "loss": 0.5371,
      "step": 100
    },
    {
      "epoch": 0.12567007677656253,
      "eval_loss": NaN,
      "eval_runtime": 385.6745,
      "eval_samples_per_second": 21.56,
      "eval_steps_per_second": 2.697,
      "step": 100
    },
    {
      "epoch": 0.12692677754432816,
      "grad_norm": 1.7630213216746193,
      "learning_rate": 1.9957460918635513e-05,
      "loss": 0.495,
      "step": 101
    },
    {
      "epoch": 0.12818347831209378,
      "grad_norm": 1.676584473649907,
      "learning_rate": 1.995331634717649e-05,
      "loss": 0.5571,
      "step": 102
    },
    {
      "epoch": 0.1294401790798594,
      "grad_norm": 1.7393851557554054,
      "learning_rate": 1.9948979619354253e-05,
      "loss": 0.5263,
      "step": 103
    },
    {
      "epoch": 0.13069687984762504,
      "grad_norm": 1.5715249917558214,
      "learning_rate": 1.994445081889264e-05,
      "loss": 0.586,
      "step": 104
    },
    {
      "epoch": 0.13195358061539067,
      "grad_norm": 1.7638743676149398,
      "learning_rate": 1.99397300332236e-05,
      "loss": 0.5371,
      "step": 105
    },
    {
      "epoch": 0.13321028138315627,
      "grad_norm": 1.7333353036478043,
      "learning_rate": 1.99348173534855e-05,
      "loss": 0.5144,
      "step": 106
    },
    {
      "epoch": 0.1344669821509219,
      "grad_norm": 1.6032418727100688,
      "learning_rate": 1.9929712874521375e-05,
      "loss": 0.5037,
      "step": 107
    },
    {
      "epoch": 0.13572368291868753,
      "grad_norm": 1.6332164064062114,
      "learning_rate": 1.9924416694877077e-05,
      "loss": 0.5427,
      "step": 108
    },
    {
      "epoch": 0.13698038368645316,
      "grad_norm": 1.509888795711472,
      "learning_rate": 1.9918928916799395e-05,
      "loss": 0.5748,
      "step": 109
    },
    {
      "epoch": 0.13823708445421878,
      "grad_norm": 1.7081555607417591,
      "learning_rate": 1.9913249646234072e-05,
      "loss": 0.5201,
      "step": 110
    },
    {
      "epoch": 0.1394937852219844,
      "grad_norm": 1.5103689076557207,
      "learning_rate": 1.9907378992823755e-05,
      "loss": 0.5313,
      "step": 111
    },
    {
      "epoch": 0.14075048598975004,
      "grad_norm": 1.6174363391736,
      "learning_rate": 1.990131706990589e-05,
      "loss": 0.5414,
      "step": 112
    },
    {
      "epoch": 0.14200718675751567,
      "grad_norm": 1.5406431804458636,
      "learning_rate": 1.9895063994510512e-05,
      "loss": 0.5183,
      "step": 113
    },
    {
      "epoch": 0.1432638875252813,
      "grad_norm": 1.5953704972891425,
      "learning_rate": 1.9888619887358024e-05,
      "loss": 0.5036,
      "step": 114
    },
    {
      "epoch": 0.1445205882930469,
      "grad_norm": 1.6126627995125455,
      "learning_rate": 1.988198487285682e-05,
      "loss": 0.5268,
      "step": 115
    },
    {
      "epoch": 0.14577728906081253,
      "grad_norm": 1.5872606292238929,
      "learning_rate": 1.9875159079100917e-05,
      "loss": 0.5404,
      "step": 116
    },
    {
      "epoch": 0.14703398982857815,
      "grad_norm": 1.4997817516498149,
      "learning_rate": 1.9868142637867474e-05,
      "loss": 0.4942,
      "step": 117
    },
    {
      "epoch": 0.14829069059634378,
      "grad_norm": 1.5577686391641898,
      "learning_rate": 1.9860935684614235e-05,
      "loss": 0.6059,
      "step": 118
    },
    {
      "epoch": 0.1495473913641094,
      "grad_norm": 1.562098718613041,
      "learning_rate": 1.9853538358476933e-05,
      "loss": 0.5772,
      "step": 119
    },
    {
      "epoch": 0.15080409213187504,
      "grad_norm": 1.4588688366756248,
      "learning_rate": 1.9845950802266584e-05,
      "loss": 0.5652,
      "step": 120
    },
    {
      "epoch": 0.15206079289964067,
      "grad_norm": 1.4789008945019497,
      "learning_rate": 1.983817316246676e-05,
      "loss": 0.5258,
      "step": 121
    },
    {
      "epoch": 0.1533174936674063,
      "grad_norm": 1.6321791739327218,
      "learning_rate": 1.9830205589230713e-05,
      "loss": 0.5833,
      "step": 122
    },
    {
      "epoch": 0.15457419443517192,
      "grad_norm": 1.4311215238919617,
      "learning_rate": 1.9822048236378536e-05,
      "loss": 0.5357,
      "step": 123
    },
    {
      "epoch": 0.15583089520293752,
      "grad_norm": 1.4711622354911698,
      "learning_rate": 1.9813701261394136e-05,
      "loss": 0.5412,
      "step": 124
    },
    {
      "epoch": 0.15708759597070315,
      "grad_norm": 1.561014461052019,
      "learning_rate": 1.980516482542224e-05,
      "loss": 0.5579,
      "step": 125
    },
    {
      "epoch": 0.15834429673846878,
      "grad_norm": 1.5602653545497562,
      "learning_rate": 1.9796439093265245e-05,
      "loss": 0.5243,
      "step": 126
    },
    {
      "epoch": 0.1596009975062344,
      "grad_norm": 1.533314694761247,
      "learning_rate": 1.9787524233380076e-05,
      "loss": 0.525,
      "step": 127
    },
    {
      "epoch": 0.16085769827400004,
      "grad_norm": 1.557676346471582,
      "learning_rate": 1.9778420417874894e-05,
      "loss": 0.5242,
      "step": 128
    },
    {
      "epoch": 0.16211439904176567,
      "grad_norm": 1.5308931674522483,
      "learning_rate": 1.9769127822505805e-05,
      "loss": 0.6101,
      "step": 129
    },
    {
      "epoch": 0.1633710998095313,
      "grad_norm": 1.588409977024727,
      "learning_rate": 1.9759646626673445e-05,
      "loss": 0.5748,
      "step": 130
    },
    {
      "epoch": 0.16462780057729692,
      "grad_norm": 1.5825263108270393,
      "learning_rate": 1.9749977013419536e-05,
      "loss": 0.5317,
      "step": 131
    },
    {
      "epoch": 0.16588450134506255,
      "grad_norm": 1.3805626708260326,
      "learning_rate": 1.9740119169423337e-05,
      "loss": 0.5818,
      "step": 132
    },
    {
      "epoch": 0.16714120211282815,
      "grad_norm": 18.459816671434435,
      "learning_rate": 1.973007328499804e-05,
      "loss": 0.5388,
      "step": 133
    },
    {
      "epoch": 0.16839790288059378,
      "grad_norm": 1.8855793357632873,
      "learning_rate": 1.9719839554087108e-05,
      "loss": 0.623,
      "step": 134
    },
    {
      "epoch": 0.1696546036483594,
      "grad_norm": 1.542977480320436,
      "learning_rate": 1.9709418174260523e-05,
      "loss": 0.5248,
      "step": 135
    },
    {
      "epoch": 0.17091130441612504,
      "grad_norm": 1.6917497316960342,
      "learning_rate": 1.9698809346710965e-05,
      "loss": 0.5624,
      "step": 136
    },
    {
      "epoch": 0.17216800518389067,
      "grad_norm": 1.6100252189793525,
      "learning_rate": 1.9688013276249947e-05,
      "loss": 0.553,
      "step": 137
    },
    {
      "epoch": 0.1734247059516563,
      "grad_norm": 1.5825712812861108,
      "learning_rate": 1.9677030171303842e-05,
      "loss": 0.5645,
      "step": 138
    },
    {
      "epoch": 0.17468140671942192,
      "grad_norm": 1.6638750857270868,
      "learning_rate": 1.966586024390986e-05,
      "loss": 0.5349,
      "step": 139
    },
    {
      "epoch": 0.17593810748718755,
      "grad_norm": 1.5448265769685363,
      "learning_rate": 1.9654503709711984e-05,
      "loss": 0.534,
      "step": 140
    },
    {
      "epoch": 0.17719480825495318,
      "grad_norm": 1.605020502262543,
      "learning_rate": 1.964296078795675e-05,
      "loss": 0.5553,
      "step": 141
    },
    {
      "epoch": 0.1784515090227188,
      "grad_norm": 1.527407593624494,
      "learning_rate": 1.9631231701489083e-05,
      "loss": 0.5298,
      "step": 142
    },
    {
      "epoch": 0.1797082097904844,
      "grad_norm": 1.5204305071770103,
      "learning_rate": 1.9619316676747928e-05,
      "loss": 0.5212,
      "step": 143
    },
    {
      "epoch": 0.18096491055825004,
      "grad_norm": 1.5980803059820479,
      "learning_rate": 1.9607215943761933e-05,
      "loss": 0.5611,
      "step": 144
    },
    {
      "epoch": 0.18222161132601566,
      "grad_norm": 2.3142581133230986,
      "learning_rate": 1.9594929736144978e-05,
      "loss": 0.536,
      "step": 145
    },
    {
      "epoch": 0.1834783120937813,
      "grad_norm": 1.5920429437394876,
      "learning_rate": 1.9582458291091664e-05,
      "loss": 0.5363,
      "step": 146
    },
    {
      "epoch": 0.18473501286154692,
      "grad_norm": 1.4799465577039153,
      "learning_rate": 1.9569801849372757e-05,
      "loss": 0.5093,
      "step": 147
    },
    {
      "epoch": 0.18599171362931255,
      "grad_norm": 1.5040620797412507,
      "learning_rate": 1.9556960655330512e-05,
      "loss": 0.5755,
      "step": 148
    },
    {
      "epoch": 0.18724841439707818,
      "grad_norm": 1.5753521873652412,
      "learning_rate": 1.954393495687398e-05,
      "loss": 0.5408,
      "step": 149
    },
    {
      "epoch": 0.1885051151648438,
      "grad_norm": 1.436217689781534,
      "learning_rate": 1.9530725005474195e-05,
      "loss": 0.5908,
      "step": 150
    },
    {
      "epoch": 0.1885051151648438,
      "eval_loss": NaN,
      "eval_runtime": 389.6633,
      "eval_samples_per_second": 21.339,
      "eval_steps_per_second": 2.669,
      "step": 150
    },
    {
      "epoch": 0.18976181593260943,
      "grad_norm": 1.4915607993777378,
      "learning_rate": 1.9517331056159353e-05,
      "loss": 0.5643,
      "step": 151
    },
    {
      "epoch": 0.19101851670037504,
      "grad_norm": 1.3658845196609777,
      "learning_rate": 1.9503753367509855e-05,
      "loss": 0.5409,
      "step": 152
    },
    {
      "epoch": 0.19227521746814066,
      "grad_norm": 1.6396983118066124,
      "learning_rate": 1.9489992201653337e-05,
      "loss": 0.5318,
      "step": 153
    },
    {
      "epoch": 0.1935319182359063,
      "grad_norm": 1.4530656863997269,
      "learning_rate": 1.9476047824259602e-05,
      "loss": 0.5288,
      "step": 154
    },
    {
      "epoch": 0.19478861900367192,
      "grad_norm": 1.8323995061487757,
      "learning_rate": 1.946192050453549e-05,
      "loss": 0.5207,
      "step": 155
    },
    {
      "epoch": 0.19604531977143755,
      "grad_norm": 1.4963171570508917,
      "learning_rate": 1.944761051521968e-05,
      "loss": 0.5341,
      "step": 156
    },
    {
      "epoch": 0.19730202053920318,
      "grad_norm": 1.4571814574677353,
      "learning_rate": 1.9433118132577432e-05,
      "loss": 0.5147,
      "step": 157
    },
    {
      "epoch": 0.1985587213069688,
      "grad_norm": 1.46930107978953,
      "learning_rate": 1.941844363639525e-05,
      "loss": 0.5533,
      "step": 158
    },
    {
      "epoch": 0.19981542207473443,
      "grad_norm": 1.4876593945156182,
      "learning_rate": 1.9403587309975467e-05,
      "loss": 0.5524,
      "step": 159
    },
    {
      "epoch": 0.20107212284250006,
      "grad_norm": 1.5458825520839694,
      "learning_rate": 1.93885494401308e-05,
      "loss": 0.5147,
      "step": 160
    },
    {
      "epoch": 0.20232882361026566,
      "grad_norm": 1.4541059075079896,
      "learning_rate": 1.9373330317178797e-05,
      "loss": 0.6548,
      "step": 161
    },
    {
      "epoch": 0.2035855243780313,
      "grad_norm": 1.4441733330016775,
      "learning_rate": 1.9357930234936228e-05,
      "loss": 0.5307,
      "step": 162
    },
    {
      "epoch": 0.20484222514579692,
      "grad_norm": 1.3924614428073763,
      "learning_rate": 1.9342349490713427e-05,
      "loss": 0.4934,
      "step": 163
    },
    {
      "epoch": 0.20609892591356255,
      "grad_norm": 1.4163101626594428,
      "learning_rate": 1.932658838530855e-05,
      "loss": 0.5248,
      "step": 164
    },
    {
      "epoch": 0.20735562668132818,
      "grad_norm": 1.4434173531044028,
      "learning_rate": 1.9310647223001752e-05,
      "loss": 0.5606,
      "step": 165
    },
    {
      "epoch": 0.2086123274490938,
      "grad_norm": 1.4428551480982263,
      "learning_rate": 1.929452631154933e-05,
      "loss": 0.531,
      "step": 166
    },
    {
      "epoch": 0.20986902821685943,
      "grad_norm": 1.423851316496012,
      "learning_rate": 1.9278225962177776e-05,
      "loss": 0.5223,
      "step": 167
    },
    {
      "epoch": 0.21112572898462506,
      "grad_norm": 1.492507341069709,
      "learning_rate": 1.9261746489577767e-05,
      "loss": 0.6371,
      "step": 168
    },
    {
      "epoch": 0.2123824297523907,
      "grad_norm": 1.448145384070868,
      "learning_rate": 1.9245088211898086e-05,
      "loss": 0.5101,
      "step": 169
    },
    {
      "epoch": 0.2136391305201563,
      "grad_norm": 1.384046704220895,
      "learning_rate": 1.9228251450739495e-05,
      "loss": 0.5975,
      "step": 170
    },
    {
      "epoch": 0.21489583128792192,
      "grad_norm": 1.3991515824529313,
      "learning_rate": 1.92112365311485e-05,
      "loss": 0.5913,
      "step": 171
    },
    {
      "epoch": 0.21615253205568755,
      "grad_norm": 1.3857833501335572,
      "learning_rate": 1.919404378161111e-05,
      "loss": 0.5224,
      "step": 172
    },
    {
      "epoch": 0.21740923282345317,
      "grad_norm": 1.3507684127877164,
      "learning_rate": 1.9176673534046465e-05,
      "loss": 0.5393,
      "step": 173
    },
    {
      "epoch": 0.2186659335912188,
      "grad_norm": 1.4477184992508454,
      "learning_rate": 1.9159126123800437e-05,
      "loss": 0.5426,
      "step": 174
    },
    {
      "epoch": 0.21992263435898443,
      "grad_norm": 1.2834792398929344,
      "learning_rate": 1.9141401889639167e-05,
      "loss": 0.5497,
      "step": 175
    },
    {
      "epoch": 0.22117933512675006,
      "grad_norm": 1.3623159756756789,
      "learning_rate": 1.9123501173742514e-05,
      "loss": 0.5103,
      "step": 176
    },
    {
      "epoch": 0.2224360358945157,
      "grad_norm": 1.4467854185777025,
      "learning_rate": 1.910542432169745e-05,
      "loss": 0.5348,
      "step": 177
    },
    {
      "epoch": 0.22369273666228132,
      "grad_norm": 1.3284354351981553,
      "learning_rate": 1.908717168249139e-05,
      "loss": 0.528,
      "step": 178
    },
    {
      "epoch": 0.22494943743004692,
      "grad_norm": 1.397962009852414,
      "learning_rate": 1.9068743608505454e-05,
      "loss": 0.5727,
      "step": 179
    },
    {
      "epoch": 0.22620613819781255,
      "grad_norm": 1.427342226625829,
      "learning_rate": 1.905014045550767e-05,
      "loss": 0.5328,
      "step": 180
    },
    {
      "epoch": 0.22746283896557817,
      "grad_norm": 1.287239450182925,
      "learning_rate": 1.903136258264609e-05,
      "loss": 0.5404,
      "step": 181
    },
    {
      "epoch": 0.2287195397333438,
      "grad_norm": 1.3231711055343047,
      "learning_rate": 1.9012410352441866e-05,
      "loss": 0.5387,
      "step": 182
    },
    {
      "epoch": 0.22997624050110943,
      "grad_norm": 1.380871461116662,
      "learning_rate": 1.899328413078227e-05,
      "loss": 0.5245,
      "step": 183
    },
    {
      "epoch": 0.23123294126887506,
      "grad_norm": 1.3476601420913,
      "learning_rate": 1.8973984286913584e-05,
      "loss": 0.5639,
      "step": 184
    },
    {
      "epoch": 0.2324896420366407,
      "grad_norm": 1.3713222215493124,
      "learning_rate": 1.8954511193434024e-05,
      "loss": 0.533,
      "step": 185
    },
    {
      "epoch": 0.23374634280440632,
      "grad_norm": 1.301173886904826,
      "learning_rate": 1.8934865226286507e-05,
      "loss": 0.5302,
      "step": 186
    },
    {
      "epoch": 0.23500304357217194,
      "grad_norm": 1.250844193542083,
      "learning_rate": 1.891504676475141e-05,
      "loss": 0.5678,
      "step": 187
    },
    {
      "epoch": 0.23625974433993754,
      "grad_norm": 1.3624917616288885,
      "learning_rate": 1.8895056191439252e-05,
      "loss": 0.5478,
      "step": 188
    },
    {
      "epoch": 0.23751644510770317,
      "grad_norm": 1.316550725145833,
      "learning_rate": 1.8874893892283296e-05,
      "loss": 0.5371,
      "step": 189
    },
    {
      "epoch": 0.2387731458754688,
      "grad_norm": 1.4024386573064895,
      "learning_rate": 1.8854560256532098e-05,
      "loss": 0.5223,
      "step": 190
    },
    {
      "epoch": 0.24002984664323443,
      "grad_norm": 1.2545561250193908,
      "learning_rate": 1.8834055676742018e-05,
      "loss": 0.5312,
      "step": 191
    },
    {
      "epoch": 0.24128654741100006,
      "grad_norm": 1.3191673233181607,
      "learning_rate": 1.8813380548769594e-05,
      "loss": 0.5449,
      "step": 192
    },
    {
      "epoch": 0.24254324817876569,
      "grad_norm": 1.351413784775738,
      "learning_rate": 1.8792535271763944e-05,
      "loss": 0.5338,
      "step": 193
    },
    {
      "epoch": 0.24379994894653131,
      "grad_norm": 1.241988064092758,
      "learning_rate": 1.8771520248159044e-05,
      "loss": 0.537,
      "step": 194
    },
    {
      "epoch": 0.24505664971429694,
      "grad_norm": 1.2555364071859036,
      "learning_rate": 1.8750335883665948e-05,
      "loss": 0.5831,
      "step": 195
    },
    {
      "epoch": 0.24631335048206257,
      "grad_norm": 1.2648163083865465,
      "learning_rate": 1.8728982587264965e-05,
      "loss": 0.5553,
      "step": 196
    },
    {
      "epoch": 0.2475700512498282,
      "grad_norm": 1.3009972836834804,
      "learning_rate": 1.8707460771197773e-05,
      "loss": 0.5213,
      "step": 197
    },
    {
      "epoch": 0.2488267520175938,
      "grad_norm": 1.308271909393604,
      "learning_rate": 1.8685770850959444e-05,
      "loss": 0.5781,
      "step": 198
    },
    {
      "epoch": 0.25008345278535943,
      "grad_norm": 1.2985339297627132,
      "learning_rate": 1.8663913245290433e-05,
      "loss": 0.5319,
      "step": 199
    },
    {
      "epoch": 0.25134015355312506,
      "grad_norm": 1.2451217830797545,
      "learning_rate": 1.8641888376168483e-05,
      "loss": 0.5608,
      "step": 200
    },
    {
      "epoch": 0.25134015355312506,
      "eval_loss": NaN,
      "eval_runtime": 381.9917,
      "eval_samples_per_second": 21.767,
      "eval_steps_per_second": 2.723,
      "step": 200
    },
    {
      "epoch": 0.2525968543208907,
      "grad_norm": 1.4207395274648773,
      "learning_rate": 1.8619696668800494e-05,
      "loss": 0.5194,
      "step": 201
    },
    {
      "epoch": 0.2538535550886563,
      "grad_norm": 1.2969288642452035,
      "learning_rate": 1.85973385516143e-05,
      "loss": 0.5303,
      "step": 202
    },
    {
      "epoch": 0.25511025585642194,
      "grad_norm": 1.244817385015466,
      "learning_rate": 1.8574814456250406e-05,
      "loss": 0.5519,
      "step": 203
    },
    {
      "epoch": 0.25636695662418757,
      "grad_norm": 1.2786899670392922,
      "learning_rate": 1.855212481755365e-05,
      "loss": 0.5314,
      "step": 204
    },
    {
      "epoch": 0.2576236573919532,
      "grad_norm": 1.6119075958517899,
      "learning_rate": 1.852927007356481e-05,
      "loss": 0.5153,
      "step": 205
    },
    {
      "epoch": 0.2588803581597188,
      "grad_norm": 1.3027579835871468,
      "learning_rate": 1.8506250665512156e-05,
      "loss": 0.5317,
      "step": 206
    },
    {
      "epoch": 0.26013705892748445,
      "grad_norm": 1.4097127031945536,
      "learning_rate": 1.848306703780291e-05,
      "loss": 0.5432,
      "step": 207
    },
    {
      "epoch": 0.2613937596952501,
      "grad_norm": 1.2253893934005955,
      "learning_rate": 1.8459719638014693e-05,
      "loss": 0.5144,
      "step": 208
    },
    {
      "epoch": 0.2626504604630157,
      "grad_norm": 1.3490881789862665,
      "learning_rate": 1.843620891688686e-05,
      "loss": 0.5227,
      "step": 209
    },
    {
      "epoch": 0.26390716123078134,
      "grad_norm": 1.2692047638329742,
      "learning_rate": 1.8412535328311813e-05,
      "loss": 0.5172,
      "step": 210
    },
    {
      "epoch": 0.2651638619985469,
      "grad_norm": 1.3001969775108575,
      "learning_rate": 1.8388699329326237e-05,
      "loss": 0.5013,
      "step": 211
    },
    {
      "epoch": 0.26642056276631254,
      "grad_norm": 1.2460584486023816,
      "learning_rate": 1.8364701380102267e-05,
      "loss": 0.5097,
      "step": 212
    },
    {
      "epoch": 0.26767726353407817,
      "grad_norm": 1.2575445422859304,
      "learning_rate": 1.8340541943938623e-05,
      "loss": 0.5253,
      "step": 213
    },
    {
      "epoch": 0.2689339643018438,
      "grad_norm": 1.247709368946671,
      "learning_rate": 1.831622148725164e-05,
      "loss": 0.5195,
      "step": 214
    },
    {
      "epoch": 0.2701906650696094,
      "grad_norm": 1.331986681061102,
      "learning_rate": 1.8291740479566286e-05,
      "loss": 0.517,
      "step": 215
    },
    {
      "epoch": 0.27144736583737505,
      "grad_norm": 1.2798935292338272,
      "learning_rate": 1.8267099393507083e-05,
      "loss": 0.5774,
      "step": 216
    },
    {
      "epoch": 0.2727040666051407,
      "grad_norm": 1.2305947859868307,
      "learning_rate": 1.8242298704788988e-05,
      "loss": 0.5285,
      "step": 217
    },
    {
      "epoch": 0.2739607673729063,
      "grad_norm": 1.2890582922664517,
      "learning_rate": 1.821733889220822e-05,
      "loss": 0.5111,
      "step": 218
    },
    {
      "epoch": 0.27521746814067194,
      "grad_norm": 1.2655404616013888,
      "learning_rate": 1.819222043763299e-05,
      "loss": 0.549,
      "step": 219
    },
    {
      "epoch": 0.27647416890843757,
      "grad_norm": 1.3037267105348513,
      "learning_rate": 1.816694382599422e-05,
      "loss": 0.535,
      "step": 220
    },
    {
      "epoch": 0.2777308696762032,
      "grad_norm": 1.2775883338383642,
      "learning_rate": 1.814150954527618e-05,
      "loss": 0.518,
      "step": 221
    },
    {
      "epoch": 0.2789875704439688,
      "grad_norm": 1.3182350382629517,
      "learning_rate": 1.8115918086507054e-05,
      "loss": 0.5879,
      "step": 222
    },
    {
      "epoch": 0.28024427121173445,
      "grad_norm": 1.2837663456694282,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.5575,
      "step": 223
    },
    {
      "epoch": 0.2815009719795001,
      "grad_norm": 1.3410051389307014,
      "learning_rate": 1.8064265614090976e-05,
      "loss": 0.5776,
      "step": 224
    },
    {
      "epoch": 0.2827576727472657,
      "grad_norm": 1.3538997044655456,
      "learning_rate": 1.8038205597634392e-05,
      "loss": 0.5315,
      "step": 225
    },
    {
      "epoch": 0.28401437351503134,
      "grad_norm": 1.2837659278037532,
      "learning_rate": 1.801199039748822e-05,
      "loss": 0.5341,
      "step": 226
    },
    {
      "epoch": 0.28527107428279697,
      "grad_norm": 1.3959368719539762,
      "learning_rate": 1.7985620519756897e-05,
      "loss": 0.53,
      "step": 227
    },
    {
      "epoch": 0.2865277750505626,
      "grad_norm": 1.277924618484306,
      "learning_rate": 1.7959096473531016e-05,
      "loss": 0.5131,
      "step": 228
    },
    {
      "epoch": 0.2877844758183282,
      "grad_norm": 1.360578070388895,
      "learning_rate": 1.7932418770877523e-05,
      "loss": 0.5146,
      "step": 229
    },
    {
      "epoch": 0.2890411765860938,
      "grad_norm": 1.2558461807056212,
      "learning_rate": 1.7905587926829815e-05,
      "loss": 0.567,
      "step": 230
    },
    {
      "epoch": 0.2902978773538594,
      "grad_norm": 1.2185312710624743,
      "learning_rate": 1.7878604459377795e-05,
      "loss": 0.5259,
      "step": 231
    },
    {
      "epoch": 0.29155457812162505,
      "grad_norm": 1.1707487670839811,
      "learning_rate": 1.7851468889457883e-05,
      "loss": 0.5384,
      "step": 232
    },
    {
      "epoch": 0.2928112788893907,
      "grad_norm": 1.2419851366188785,
      "learning_rate": 1.7824181740942958e-05,
      "loss": 0.526,
      "step": 233
    },
    {
      "epoch": 0.2940679796571563,
      "grad_norm": 1.2190078071425596,
      "learning_rate": 1.7796743540632226e-05,
      "loss": 0.5228,
      "step": 234
    },
    {
      "epoch": 0.29532468042492194,
      "grad_norm": 1.2620408913566545,
      "learning_rate": 1.776915481824107e-05,
      "loss": 0.5362,
      "step": 235
    },
    {
      "epoch": 0.29658138119268757,
      "grad_norm": 1.2019501932459877,
      "learning_rate": 1.7741416106390828e-05,
      "loss": 0.5403,
      "step": 236
    },
    {
      "epoch": 0.2978380819604532,
      "grad_norm": 1.2349476994702815,
      "learning_rate": 1.7713527940598473e-05,
      "loss": 0.5346,
      "step": 237
    },
    {
      "epoch": 0.2990947827282188,
      "grad_norm": 1.228835848024245,
      "learning_rate": 1.7685490859266324e-05,
      "loss": 0.5357,
      "step": 238
    },
    {
      "epoch": 0.30035148349598445,
      "grad_norm": 1.1433816285308742,
      "learning_rate": 1.7657305403671618e-05,
      "loss": 0.5237,
      "step": 239
    },
    {
      "epoch": 0.3016081842637501,
      "grad_norm": 1.1830531733373626,
      "learning_rate": 1.762897211795607e-05,
      "loss": 0.5048,
      "step": 240
    },
    {
      "epoch": 0.3028648850315157,
      "grad_norm": 1.3012741117414692,
      "learning_rate": 1.760049154911537e-05,
      "loss": 0.5325,
      "step": 241
    },
    {
      "epoch": 0.30412158579928134,
      "grad_norm": 1.3019810089595567,
      "learning_rate": 1.7571864246988623e-05,
      "loss": 0.5311,
      "step": 242
    },
    {
      "epoch": 0.30537828656704696,
      "grad_norm": 1.2381762150161675,
      "learning_rate": 1.7543090764247726e-05,
      "loss": 0.5256,
      "step": 243
    },
    {
      "epoch": 0.3066349873348126,
      "grad_norm": 1.189237177245814,
      "learning_rate": 1.751417165638671e-05,
      "loss": 0.533,
      "step": 244
    },
    {
      "epoch": 0.3078916881025782,
      "grad_norm": 1.1392996416893437,
      "learning_rate": 1.7485107481711014e-05,
      "loss": 0.5116,
      "step": 245
    },
    {
      "epoch": 0.30914838887034385,
      "grad_norm": 1.2392857084749362,
      "learning_rate": 1.7455898801326685e-05,
      "loss": 0.5324,
      "step": 246
    },
    {
      "epoch": 0.3104050896381095,
      "grad_norm": 1.2004003016053595,
      "learning_rate": 1.742654617912958e-05,
      "loss": 0.5445,
      "step": 247
    },
    {
      "epoch": 0.31166179040587505,
      "grad_norm": 1.202284432596933,
      "learning_rate": 1.7397050181794463e-05,
      "loss": 0.5455,
      "step": 248
    },
    {
      "epoch": 0.3129184911736407,
      "grad_norm": 1.2367358266165964,
      "learning_rate": 1.736741137876405e-05,
      "loss": 0.5263,
      "step": 249
    },
    {
      "epoch": 0.3141751919414063,
      "grad_norm": 1.2263686883476443,
      "learning_rate": 1.733763034223804e-05,
      "loss": 0.5318,
      "step": 250
    },
    {
      "epoch": 0.3141751919414063,
      "eval_loss": NaN,
      "eval_runtime": 393.3082,
      "eval_samples_per_second": 21.141,
      "eval_steps_per_second": 2.644,
      "step": 250
    },
    {
      "epoch": 0.31543189270917193,
      "grad_norm": 1.839889882151207,
      "learning_rate": 1.730770764716206e-05,
      "loss": 0.4856,
      "step": 251
    },
    {
      "epoch": 0.31668859347693756,
      "grad_norm": 1.2987969186805615,
      "learning_rate": 1.7277643871216558e-05,
      "loss": 0.5393,
      "step": 252
    },
    {
      "epoch": 0.3179452942447032,
      "grad_norm": 1.4429089329852214,
      "learning_rate": 1.724743959480565e-05,
      "loss": 0.5473,
      "step": 253
    },
    {
      "epoch": 0.3192019950124688,
      "grad_norm": 2.3182483058377357,
      "learning_rate": 1.721709540104594e-05,
      "loss": 0.5719,
      "step": 254
    },
    {
      "epoch": 0.32045869578023445,
      "grad_norm": 1.2943046560287874,
      "learning_rate": 1.7186611875755227e-05,
      "loss": 0.5421,
      "step": 255
    },
    {
      "epoch": 0.3217153965480001,
      "grad_norm": 1.3312637937305758,
      "learning_rate": 1.715598960744121e-05,
      "loss": 0.5756,
      "step": 256
    },
    {
      "epoch": 0.3229720973157657,
      "grad_norm": 1.203432712589985,
      "learning_rate": 1.712522918729014e-05,
      "loss": 0.5876,
      "step": 257
    },
    {
      "epoch": 0.32422879808353133,
      "grad_norm": 1.248392549739193,
      "learning_rate": 1.7094331209155394e-05,
      "loss": 0.5375,
      "step": 258
    },
    {
      "epoch": 0.32548549885129696,
      "grad_norm": 1.3256545033784541,
      "learning_rate": 1.7063296269545988e-05,
      "loss": 0.5067,
      "step": 259
    },
    {
      "epoch": 0.3267421996190626,
      "grad_norm": 1.1874224988844255,
      "learning_rate": 1.7032124967615112e-05,
      "loss": 0.5281,
      "step": 260
    },
    {
      "epoch": 0.3279989003868282,
      "grad_norm": 1.36231925710455,
      "learning_rate": 1.7000817905148523e-05,
      "loss": 0.546,
      "step": 261
    },
    {
      "epoch": 0.32925560115459385,
      "grad_norm": 1.2674188969413769,
      "learning_rate": 1.696937568655294e-05,
      "loss": 0.5139,
      "step": 262
    },
    {
      "epoch": 0.3305123019223595,
      "grad_norm": 1.2676550984339194,
      "learning_rate": 1.6937798918844363e-05,
      "loss": 0.5033,
      "step": 263
    },
    {
      "epoch": 0.3317690026901251,
      "grad_norm": 1.2627941544296886,
      "learning_rate": 1.6906088211636387e-05,
      "loss": 0.5323,
      "step": 264
    },
    {
      "epoch": 0.33302570345789073,
      "grad_norm": 1.1828449763849782,
      "learning_rate": 1.6874244177128395e-05,
      "loss": 0.4978,
      "step": 265
    },
    {
      "epoch": 0.3342824042256563,
      "grad_norm": 1.2113446935401968,
      "learning_rate": 1.6842267430093762e-05,
      "loss": 0.5336,
      "step": 266
    },
    {
      "epoch": 0.33553910499342193,
      "grad_norm": 1.1871927265354432,
      "learning_rate": 1.6810158587867973e-05,
      "loss": 0.4963,
      "step": 267
    },
    {
      "epoch": 0.33679580576118756,
      "grad_norm": 1.21086248350049,
      "learning_rate": 1.6777918270336718e-05,
      "loss": 0.5204,
      "step": 268
    },
    {
      "epoch": 0.3380525065289532,
      "grad_norm": 1.2862931993679727,
      "learning_rate": 1.6745547099923917e-05,
      "loss": 0.5306,
      "step": 269
    },
    {
      "epoch": 0.3393092072967188,
      "grad_norm": 1.2086868536312418,
      "learning_rate": 1.6713045701579705e-05,
      "loss": 0.4775,
      "step": 270
    },
    {
      "epoch": 0.34056590806448445,
      "grad_norm": 1.246734645659461,
      "learning_rate": 1.6680414702768358e-05,
      "loss": 0.5003,
      "step": 271
    },
    {
      "epoch": 0.3418226088322501,
      "grad_norm": 1.1307518995270345,
      "learning_rate": 1.66476547334562e-05,
      "loss": 0.5618,
      "step": 272
    },
    {
      "epoch": 0.3430793096000157,
      "grad_norm": 1.2461483743109123,
      "learning_rate": 1.661476642609943e-05,
      "loss": 0.5154,
      "step": 273
    },
    {
      "epoch": 0.34433601036778133,
      "grad_norm": 1.2318638718720292,
      "learning_rate": 1.658175041563189e-05,
      "loss": 0.5255,
      "step": 274
    },
    {
      "epoch": 0.34559271113554696,
      "grad_norm": 1.2614769482466344,
      "learning_rate": 1.6548607339452853e-05,
      "loss": 0.4903,
      "step": 275
    },
    {
      "epoch": 0.3468494119033126,
      "grad_norm": 1.218403889343406,
      "learning_rate": 1.6515337837414677e-05,
      "loss": 0.5374,
      "step": 276
    },
    {
      "epoch": 0.3481061126710782,
      "grad_norm": 1.309250396407954,
      "learning_rate": 1.6481942551810476e-05,
      "loss": 0.5207,
      "step": 277
    },
    {
      "epoch": 0.34936281343884384,
      "grad_norm": 1.1711784327085948,
      "learning_rate": 1.6448422127361707e-05,
      "loss": 0.531,
      "step": 278
    },
    {
      "epoch": 0.3506195142066095,
      "grad_norm": 1.1878422695605408,
      "learning_rate": 1.641477721120573e-05,
      "loss": 0.54,
      "step": 279
    },
    {
      "epoch": 0.3518762149743751,
      "grad_norm": 1.161149033672964,
      "learning_rate": 1.638100845288331e-05,
      "loss": 0.5078,
      "step": 280
    },
    {
      "epoch": 0.35313291574214073,
      "grad_norm": 1.1916167026440183,
      "learning_rate": 1.6347116504326082e-05,
      "loss": 0.5246,
      "step": 281
    },
    {
      "epoch": 0.35438961650990636,
      "grad_norm": 1.1648314835473719,
      "learning_rate": 1.631310201984396e-05,
      "loss": 0.5111,
      "step": 282
    },
    {
      "epoch": 0.355646317277672,
      "grad_norm": 1.2652965637545066,
      "learning_rate": 1.627896565611251e-05,
      "loss": 0.5376,
      "step": 283
    },
    {
      "epoch": 0.3569030180454376,
      "grad_norm": 1.0925768418862014,
      "learning_rate": 1.6244708072160267e-05,
      "loss": 0.5158,
      "step": 284
    },
    {
      "epoch": 0.3581597188132032,
      "grad_norm": 1.237142044854975,
      "learning_rate": 1.6210329929356017e-05,
      "loss": 0.4975,
      "step": 285
    },
    {
      "epoch": 0.3594164195809688,
      "grad_norm": 1.314890455752597,
      "learning_rate": 1.6175831891396034e-05,
      "loss": 0.5504,
      "step": 286
    },
    {
      "epoch": 0.36067312034873444,
      "grad_norm": 1.2189337274031111,
      "learning_rate": 1.614121462429124e-05,
      "loss": 0.55,
      "step": 287
    },
    {
      "epoch": 0.3619298211165001,
      "grad_norm": 1.1195814719052748,
      "learning_rate": 1.6106478796354382e-05,
      "loss": 0.5159,
      "step": 288
    },
    {
      "epoch": 0.3631865218842657,
      "grad_norm": 1.2263611549293467,
      "learning_rate": 1.6071625078187113e-05,
      "loss": 0.5478,
      "step": 289
    },
    {
      "epoch": 0.36444322265203133,
      "grad_norm": 1.150066595637109,
      "learning_rate": 1.6036654142667043e-05,
      "loss": 0.5503,
      "step": 290
    },
    {
      "epoch": 0.36569992341979696,
      "grad_norm": 1.1156487171205896,
      "learning_rate": 1.600156666493475e-05,
      "loss": 0.5218,
      "step": 291
    },
    {
      "epoch": 0.3669566241875626,
      "grad_norm": 1.132115800963164,
      "learning_rate": 1.596636332238076e-05,
      "loss": 0.4936,
      "step": 292
    },
    {
      "epoch": 0.3682133249553282,
      "grad_norm": 1.1553749691225366,
      "learning_rate": 1.593104479463244e-05,
      "loss": 0.5209,
      "step": 293
    },
    {
      "epoch": 0.36947002572309384,
      "grad_norm": 1.1883358272581606,
      "learning_rate": 1.5895611763540914e-05,
      "loss": 0.4964,
      "step": 294
    },
    {
      "epoch": 0.37072672649085947,
      "grad_norm": 1.1558054507595528,
      "learning_rate": 1.5860064913167863e-05,
      "loss": 0.5063,
      "step": 295
    },
    {
      "epoch": 0.3719834272586251,
      "grad_norm": 1.2438113556876693,
      "learning_rate": 1.5824404929772347e-05,
      "loss": 0.507,
      "step": 296
    },
    {
      "epoch": 0.3732401280263907,
      "grad_norm": 1.1179995486577579,
      "learning_rate": 1.5788632501797545e-05,
      "loss": 0.4902,
      "step": 297
    },
    {
      "epoch": 0.37449682879415636,
      "grad_norm": 1.1092026267657866,
      "learning_rate": 1.575274831985746e-05,
      "loss": 0.512,
      "step": 298
    },
    {
      "epoch": 0.375753529561922,
      "grad_norm": 1.154632467938108,
      "learning_rate": 1.5716753076723594e-05,
      "loss": 0.5245,
      "step": 299
    },
    {
      "epoch": 0.3770102303296876,
      "grad_norm": 1.189993649393655,
      "learning_rate": 1.568064746731156e-05,
      "loss": 0.5191,
      "step": 300
    },
    {
      "epoch": 0.3770102303296876,
      "eval_loss": NaN,
      "eval_runtime": 390.9329,
      "eval_samples_per_second": 21.27,
      "eval_steps_per_second": 2.66,
      "step": 300
    },
    {
      "epoch": 0.37826693109745324,
      "grad_norm": 1.1500530686780315,
      "learning_rate": 1.5644432188667695e-05,
      "loss": 0.5288,
      "step": 301
    },
    {
      "epoch": 0.37952363186521887,
      "grad_norm": 1.1878804551065247,
      "learning_rate": 1.5608107939955565e-05,
      "loss": 0.5231,
      "step": 302
    },
    {
      "epoch": 0.38078033263298444,
      "grad_norm": 1.1168332905551357,
      "learning_rate": 1.5571675422442504e-05,
      "loss": 0.5387,
      "step": 303
    },
    {
      "epoch": 0.38203703340075007,
      "grad_norm": 1.1448743390588387,
      "learning_rate": 1.5535135339486044e-05,
      "loss": 0.5214,
      "step": 304
    },
    {
      "epoch": 0.3832937341685157,
      "grad_norm": 1.1699623266496315,
      "learning_rate": 1.549848839652035e-05,
      "loss": 0.5466,
      "step": 305
    },
    {
      "epoch": 0.3845504349362813,
      "grad_norm": 1.1274856023440132,
      "learning_rate": 1.5461735301042615e-05,
      "loss": 0.5534,
      "step": 306
    },
    {
      "epoch": 0.38580713570404696,
      "grad_norm": 1.1200748824733626,
      "learning_rate": 1.542487676259937e-05,
      "loss": 0.5213,
      "step": 307
    },
    {
      "epoch": 0.3870638364718126,
      "grad_norm": 1.1177676101897944,
      "learning_rate": 1.5387913492772816e-05,
      "loss": 0.5261,
      "step": 308
    },
    {
      "epoch": 0.3883205372395782,
      "grad_norm": 1.0956645557598703,
      "learning_rate": 1.5350846205167065e-05,
      "loss": 0.5007,
      "step": 309
    },
    {
      "epoch": 0.38957723800734384,
      "grad_norm": 1.170185855384506,
      "learning_rate": 1.5313675615394373e-05,
      "loss": 0.5221,
      "step": 310
    },
    {
      "epoch": 0.39083393877510947,
      "grad_norm": 1.1889108508498927,
      "learning_rate": 1.527640244106133e-05,
      "loss": 0.5385,
      "step": 311
    },
    {
      "epoch": 0.3920906395428751,
      "grad_norm": 1.1415465303312236,
      "learning_rate": 1.5239027401754987e-05,
      "loss": 0.5112,
      "step": 312
    },
    {
      "epoch": 0.3933473403106407,
      "grad_norm": 1.2013200373878787,
      "learning_rate": 1.5201551219028988e-05,
      "loss": 0.4914,
      "step": 313
    },
    {
      "epoch": 0.39460404107840635,
      "grad_norm": 1.1988351313938457,
      "learning_rate": 1.5163974616389621e-05,
      "loss": 0.4947,
      "step": 314
    },
    {
      "epoch": 0.395860741846172,
      "grad_norm": 1.089460298631534,
      "learning_rate": 1.5126298319281859e-05,
      "loss": 0.5458,
      "step": 315
    },
    {
      "epoch": 0.3971174426139376,
      "grad_norm": 1.1216780572022857,
      "learning_rate": 1.508852305507535e-05,
      "loss": 0.529,
      "step": 316
    },
    {
      "epoch": 0.39837414338170324,
      "grad_norm": 1.1750196353813835,
      "learning_rate": 1.5050649553050383e-05,
      "loss": 0.5343,
      "step": 317
    },
    {
      "epoch": 0.39963084414946887,
      "grad_norm": 1.1613435161044152,
      "learning_rate": 1.5012678544383797e-05,
      "loss": 0.4809,
      "step": 318
    },
    {
      "epoch": 0.4008875449172345,
      "grad_norm": 1.0838357359556312,
      "learning_rate": 1.4974610762134875e-05,
      "loss": 0.5397,
      "step": 319
    },
    {
      "epoch": 0.4021442456850001,
      "grad_norm": 1.1334411455279323,
      "learning_rate": 1.4936446941231186e-05,
      "loss": 0.5023,
      "step": 320
    },
    {
      "epoch": 0.4034009464527657,
      "grad_norm": 1.084067016750503,
      "learning_rate": 1.4898187818454401e-05,
      "loss": 0.507,
      "step": 321
    },
    {
      "epoch": 0.4046576472205313,
      "grad_norm": 1.1436033686465177,
      "learning_rate": 1.485983413242606e-05,
      "loss": 0.4803,
      "step": 322
    },
    {
      "epoch": 0.40591434798829695,
      "grad_norm": 1.1381556287788788,
      "learning_rate": 1.4821386623593332e-05,
      "loss": 0.5212,
      "step": 323
    },
    {
      "epoch": 0.4071710487560626,
      "grad_norm": 1.2083085101416968,
      "learning_rate": 1.4782846034214689e-05,
      "loss": 0.6227,
      "step": 324
    },
    {
      "epoch": 0.4084277495238282,
      "grad_norm": 1.1218491511435251,
      "learning_rate": 1.4744213108345605e-05,
      "loss": 0.5064,
      "step": 325
    },
    {
      "epoch": 0.40968445029159384,
      "grad_norm": 1.222423494749568,
      "learning_rate": 1.4705488591824182e-05,
      "loss": 0.5404,
      "step": 326
    },
    {
      "epoch": 0.41094115105935947,
      "grad_norm": 1.3200013736515412,
      "learning_rate": 1.4666673232256738e-05,
      "loss": 0.5236,
      "step": 327
    },
    {
      "epoch": 0.4121978518271251,
      "grad_norm": 1.174130976702849,
      "learning_rate": 1.4627767779003402e-05,
      "loss": 0.5109,
      "step": 328
    },
    {
      "epoch": 0.4134545525948907,
      "grad_norm": 1.1121745715846247,
      "learning_rate": 1.4588772983163612e-05,
      "loss": 0.5187,
      "step": 329
    },
    {
      "epoch": 0.41471125336265635,
      "grad_norm": 1.1211595150469165,
      "learning_rate": 1.4549689597561652e-05,
      "loss": 0.5195,
      "step": 330
    },
    {
      "epoch": 0.415967954130422,
      "grad_norm": 1.0882830091956517,
      "learning_rate": 1.4510518376732081e-05,
      "loss": 0.5197,
      "step": 331
    },
    {
      "epoch": 0.4172246548981876,
      "grad_norm": 1.103233638957626,
      "learning_rate": 1.4471260076905198e-05,
      "loss": 0.5025,
      "step": 332
    },
    {
      "epoch": 0.41848135566595324,
      "grad_norm": 1.073960984254828,
      "learning_rate": 1.4431915455992416e-05,
      "loss": 0.5093,
      "step": 333
    },
    {
      "epoch": 0.41973805643371886,
      "grad_norm": 1.0782782404257423,
      "learning_rate": 1.4392485273571652e-05,
      "loss": 0.4834,
      "step": 334
    },
    {
      "epoch": 0.4209947572014845,
      "grad_norm": 1.1812719353147918,
      "learning_rate": 1.435297029087265e-05,
      "loss": 0.5096,
      "step": 335
    },
    {
      "epoch": 0.4222514579692501,
      "grad_norm": 1.0945216590303213,
      "learning_rate": 1.431337127076229e-05,
      "loss": 0.4992,
      "step": 336
    },
    {
      "epoch": 0.42350815873701575,
      "grad_norm": 1.124754349061893,
      "learning_rate": 1.4273688977729852e-05,
      "loss": 0.5806,
      "step": 337
    },
    {
      "epoch": 0.4247648595047814,
      "grad_norm": 1.182469605262903,
      "learning_rate": 1.4233924177872269e-05,
      "loss": 0.5119,
      "step": 338
    },
    {
      "epoch": 0.426021560272547,
      "grad_norm": 1.095989659016963,
      "learning_rate": 1.4194077638879333e-05,
      "loss": 0.5369,
      "step": 339
    },
    {
      "epoch": 0.4272782610403126,
      "grad_norm": 1.1287938362303405,
      "learning_rate": 1.4154150130018867e-05,
      "loss": 0.4763,
      "step": 340
    },
    {
      "epoch": 0.4285349618080782,
      "grad_norm": 1.1391290234474063,
      "learning_rate": 1.4114142422121879e-05,
      "loss": 0.5052,
      "step": 341
    },
    {
      "epoch": 0.42979166257584384,
      "grad_norm": 1.0672829625786657,
      "learning_rate": 1.4074055287567685e-05,
      "loss": 0.539,
      "step": 342
    },
    {
      "epoch": 0.43104836334360946,
      "grad_norm": 1.1130997359221613,
      "learning_rate": 1.4033889500268991e-05,
      "loss": 0.5033,
      "step": 343
    },
    {
      "epoch": 0.4323050641113751,
      "grad_norm": 1.11023882693686,
      "learning_rate": 1.3993645835656955e-05,
      "loss": 0.4961,
      "step": 344
    },
    {
      "epoch": 0.4335617648791407,
      "grad_norm": 1.129690617178472,
      "learning_rate": 1.3953325070666215e-05,
      "loss": 0.5302,
      "step": 345
    },
    {
      "epoch": 0.43481846564690635,
      "grad_norm": 1.1112927798263614,
      "learning_rate": 1.3912927983719888e-05,
      "loss": 0.5032,
      "step": 346
    },
    {
      "epoch": 0.436075166414672,
      "grad_norm": 1.1287505890600753,
      "learning_rate": 1.3872455354714552e-05,
      "loss": 0.5287,
      "step": 347
    },
    {
      "epoch": 0.4373318671824376,
      "grad_norm": 1.1474684694732853,
      "learning_rate": 1.3831907965005173e-05,
      "loss": 0.503,
      "step": 348
    },
    {
      "epoch": 0.43858856795020323,
      "grad_norm": 1.1271461572724835,
      "learning_rate": 1.3791286597390035e-05,
      "loss": 0.52,
      "step": 349
    },
    {
      "epoch": 0.43984526871796886,
      "grad_norm": 1.0112579946119413,
      "learning_rate": 1.375059203609562e-05,
      "loss": 0.512,
      "step": 350
    },
    {
      "epoch": 0.43984526871796886,
      "eval_loss": NaN,
      "eval_runtime": 386.8898,
      "eval_samples_per_second": 21.492,
      "eval_steps_per_second": 2.688,
      "step": 350
    },
    {
      "epoch": 0.4411019694857345,
      "grad_norm": 1.1391998689599176,
      "learning_rate": 1.370982506676147e-05,
      "loss": 0.5153,
      "step": 351
    },
    {
      "epoch": 0.4423586702535001,
      "grad_norm": 1.1522319157530978,
      "learning_rate": 1.3668986476425024e-05,
      "loss": 0.5223,
      "step": 352
    },
    {
      "epoch": 0.44361537102126575,
      "grad_norm": 1.056841423994722,
      "learning_rate": 1.362807705350641e-05,
      "loss": 0.5459,
      "step": 353
    },
    {
      "epoch": 0.4448720717890314,
      "grad_norm": 1.1383935709291246,
      "learning_rate": 1.3587097587793243e-05,
      "loss": 0.5449,
      "step": 354
    },
    {
      "epoch": 0.446128772556797,
      "grad_norm": 1.106248398688068,
      "learning_rate": 1.3546048870425356e-05,
      "loss": 0.4944,
      "step": 355
    },
    {
      "epoch": 0.44738547332456263,
      "grad_norm": 1.067289329127628,
      "learning_rate": 1.3504931693879553e-05,
      "loss": 0.5538,
      "step": 356
    },
    {
      "epoch": 0.44864217409232826,
      "grad_norm": 1.0795347423113244,
      "learning_rate": 1.3463746851954275e-05,
      "loss": 0.5306,
      "step": 357
    },
    {
      "epoch": 0.44989887486009383,
      "grad_norm": 1.1163481113252645,
      "learning_rate": 1.342249513975432e-05,
      "loss": 0.5146,
      "step": 358
    },
    {
      "epoch": 0.45115557562785946,
      "grad_norm": 1.1760911501443567,
      "learning_rate": 1.3381177353675441e-05,
      "loss": 0.5239,
      "step": 359
    },
    {
      "epoch": 0.4524122763956251,
      "grad_norm": 1.1510645603762788,
      "learning_rate": 1.3339794291389015e-05,
      "loss": 0.4986,
      "step": 360
    },
    {
      "epoch": 0.4536689771633907,
      "grad_norm": 1.0505550098423375,
      "learning_rate": 1.3298346751826624e-05,
      "loss": 0.4932,
      "step": 361
    },
    {
      "epoch": 0.45492567793115635,
      "grad_norm": 1.110458489656852,
      "learning_rate": 1.3256835535164622e-05,
      "loss": 0.499,
      "step": 362
    },
    {
      "epoch": 0.456182378698922,
      "grad_norm": 1.0429297164870697,
      "learning_rate": 1.3215261442808718e-05,
      "loss": 0.5519,
      "step": 363
    },
    {
      "epoch": 0.4574390794666876,
      "grad_norm": 1.1025779859161235,
      "learning_rate": 1.3173625277378464e-05,
      "loss": 0.498,
      "step": 364
    },
    {
      "epoch": 0.45869578023445323,
      "grad_norm": 1.0866619959147732,
      "learning_rate": 1.3131927842691793e-05,
      "loss": 0.4939,
      "step": 365
    },
    {
      "epoch": 0.45995248100221886,
      "grad_norm": 1.0657930951927579,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 0.4984,
      "step": 366
    },
    {
      "epoch": 0.4612091817699845,
      "grad_norm": 1.0589212846976253,
      "learning_rate": 1.3048352386719605e-05,
      "loss": 0.4943,
      "step": 367
    },
    {
      "epoch": 0.4624658825377501,
      "grad_norm": 1.0942767373527489,
      "learning_rate": 1.3006475978922013e-05,
      "loss": 0.5145,
      "step": 368
    },
    {
      "epoch": 0.46372258330551575,
      "grad_norm": 1.123925914892006,
      "learning_rate": 1.2964541528812689e-05,
      "loss": 0.5212,
      "step": 369
    },
    {
      "epoch": 0.4649792840732814,
      "grad_norm": 1.1029621728132757,
      "learning_rate": 1.2922549845968174e-05,
      "loss": 0.5008,
      "step": 370
    },
    {
      "epoch": 0.466235984841047,
      "grad_norm": 1.1066345430120166,
      "learning_rate": 1.2880501741069931e-05,
      "loss": 0.5099,
      "step": 371
    },
    {
      "epoch": 0.46749268560881263,
      "grad_norm": 1.1178828922894442,
      "learning_rate": 1.2838398025888695e-05,
      "loss": 0.5174,
      "step": 372
    },
    {
      "epoch": 0.46874938637657826,
      "grad_norm": 1.0618894730289437,
      "learning_rate": 1.2796239513268796e-05,
      "loss": 0.5266,
      "step": 373
    },
    {
      "epoch": 0.4700060871443439,
      "grad_norm": 1.1442577048190856,
      "learning_rate": 1.275402701711248e-05,
      "loss": 0.5406,
      "step": 374
    },
    {
      "epoch": 0.4712627879121095,
      "grad_norm": 1.5555245911074627,
      "learning_rate": 1.2711761352364172e-05,
      "loss": 0.526,
      "step": 375
    },
    {
      "epoch": 0.4725194886798751,
      "grad_norm": 3.2281540462224814,
      "learning_rate": 1.2669443334994768e-05,
      "loss": 0.5058,
      "step": 376
    },
    {
      "epoch": 0.4737761894476407,
      "grad_norm": 1.230186696498868,
      "learning_rate": 1.262707378198587e-05,
      "loss": 0.5189,
      "step": 377
    },
    {
      "epoch": 0.47503289021540634,
      "grad_norm": 1.1067717727956337,
      "learning_rate": 1.2584653511314012e-05,
      "loss": 0.5499,
      "step": 378
    },
    {
      "epoch": 0.476289590983172,
      "grad_norm": 1.2096032452146201,
      "learning_rate": 1.2542183341934873e-05,
      "loss": 0.4961,
      "step": 379
    },
    {
      "epoch": 0.4775462917509376,
      "grad_norm": 1.1760777197898722,
      "learning_rate": 1.2499664093767458e-05,
      "loss": 0.5352,
      "step": 380
    },
    {
      "epoch": 0.47880299251870323,
      "grad_norm": 1.1829467616609262,
      "learning_rate": 1.245709658767829e-05,
      "loss": 0.5039,
      "step": 381
    },
    {
      "epoch": 0.48005969328646886,
      "grad_norm": 1.093348347620876,
      "learning_rate": 1.241448164546553e-05,
      "loss": 0.5063,
      "step": 382
    },
    {
      "epoch": 0.4813163940542345,
      "grad_norm": 1.0813316534886166,
      "learning_rate": 1.2371820089843145e-05,
      "loss": 0.504,
      "step": 383
    },
    {
      "epoch": 0.4825730948220001,
      "grad_norm": 1.0559642834186367,
      "learning_rate": 1.2329112744425e-05,
      "loss": 0.4968,
      "step": 384
    },
    {
      "epoch": 0.48382979558976574,
      "grad_norm": 1.1119456528103215,
      "learning_rate": 1.2286360433708976e-05,
      "loss": 0.5623,
      "step": 385
    },
    {
      "epoch": 0.48508649635753137,
      "grad_norm": 1.143973204715742,
      "learning_rate": 1.2243563983061029e-05,
      "loss": 0.4909,
      "step": 386
    },
    {
      "epoch": 0.486343197125297,
      "grad_norm": 1.0989207521976259,
      "learning_rate": 1.2200724218699284e-05,
      "loss": 0.5342,
      "step": 387
    },
    {
      "epoch": 0.48759989789306263,
      "grad_norm": 1.097054041408541,
      "learning_rate": 1.2157841967678064e-05,
      "loss": 0.4762,
      "step": 388
    },
    {
      "epoch": 0.48885659866082826,
      "grad_norm": 1.0459339979949123,
      "learning_rate": 1.2114918057871928e-05,
      "loss": 0.4651,
      "step": 389
    },
    {
      "epoch": 0.4901132994285939,
      "grad_norm": 1.0847962784136453,
      "learning_rate": 1.2071953317959692e-05,
      "loss": 0.5305,
      "step": 390
    },
    {
      "epoch": 0.4913700001963595,
      "grad_norm": 1.1246107275670814,
      "learning_rate": 1.202894857740843e-05,
      "loss": 0.524,
      "step": 391
    },
    {
      "epoch": 0.49262670096412514,
      "grad_norm": 1.0117888555208185,
      "learning_rate": 1.1985904666457455e-05,
      "loss": 0.4387,
      "step": 392
    },
    {
      "epoch": 0.49388340173189077,
      "grad_norm": 1.072130705469674,
      "learning_rate": 1.19428224161023e-05,
      "loss": 0.4996,
      "step": 393
    },
    {
      "epoch": 0.4951401024996564,
      "grad_norm": 1.0949029023305772,
      "learning_rate": 1.1899702658078663e-05,
      "loss": 0.5001,
      "step": 394
    },
    {
      "epoch": 0.49639680326742197,
      "grad_norm": 1.0307577287604857,
      "learning_rate": 1.1856546224846354e-05,
      "loss": 0.5561,
      "step": 395
    },
    {
      "epoch": 0.4976535040351876,
      "grad_norm": 1.0754967872326906,
      "learning_rate": 1.181335394957324e-05,
      "loss": 0.4659,
      "step": 396
    },
    {
      "epoch": 0.4989102048029532,
      "grad_norm": 1.078728824641922,
      "learning_rate": 1.1770126666119133e-05,
      "loss": 0.5014,
      "step": 397
    },
    {
      "epoch": 0.5001669055707189,
      "grad_norm": 1.0499497992004496,
      "learning_rate": 1.1726865209019709e-05,
      "loss": 0.4716,
      "step": 398
    },
    {
      "epoch": 0.5014236063384845,
      "grad_norm": 1.0777776407348791,
      "learning_rate": 1.1683570413470384e-05,
      "loss": 0.4928,
      "step": 399
    },
    {
      "epoch": 0.5026803071062501,
      "grad_norm": 1.0574879518909284,
      "learning_rate": 1.1640243115310219e-05,
      "loss": 0.4814,
      "step": 400
    },
    {
      "epoch": 0.5026803071062501,
      "eval_loss": NaN,
      "eval_runtime": 389.4493,
      "eval_samples_per_second": 21.351,
      "eval_steps_per_second": 2.67,
      "step": 400
    },
    {
      "epoch": 0.5039370078740157,
      "grad_norm": 1.0747572780095613,
      "learning_rate": 1.1596884151005743e-05,
      "loss": 0.5086,
      "step": 401
    },
    {
      "epoch": 0.5051937086417814,
      "grad_norm": 1.104818199875437,
      "learning_rate": 1.155349435763483e-05,
      "loss": 0.5385,
      "step": 402
    },
    {
      "epoch": 0.506450409409547,
      "grad_norm": 1.0738096255710292,
      "learning_rate": 1.1510074572870533e-05,
      "loss": 0.4624,
      "step": 403
    },
    {
      "epoch": 0.5077071101773126,
      "grad_norm": 1.0669378834870606,
      "learning_rate": 1.1466625634964911e-05,
      "loss": 0.5015,
      "step": 404
    },
    {
      "epoch": 0.5089638109450783,
      "grad_norm": 1.0058479382503636,
      "learning_rate": 1.1423148382732854e-05,
      "loss": 0.4808,
      "step": 405
    },
    {
      "epoch": 0.5102205117128439,
      "grad_norm": 1.0558622246582776,
      "learning_rate": 1.1379643655535869e-05,
      "loss": 0.4676,
      "step": 406
    },
    {
      "epoch": 0.5114772124806095,
      "grad_norm": 1.0593950117803592,
      "learning_rate": 1.1336112293265896e-05,
      "loss": 0.5675,
      "step": 407
    },
    {
      "epoch": 0.5127339132483751,
      "grad_norm": 1.0819776501101257,
      "learning_rate": 1.1292555136329082e-05,
      "loss": 0.523,
      "step": 408
    },
    {
      "epoch": 0.5139906140161408,
      "grad_norm": 1.1503702106834164,
      "learning_rate": 1.1248973025629567e-05,
      "loss": 0.573,
      "step": 409
    },
    {
      "epoch": 0.5152473147839064,
      "grad_norm": 1.1896682820272197,
      "learning_rate": 1.1205366802553231e-05,
      "loss": 0.5443,
      "step": 410
    },
    {
      "epoch": 0.516504015551672,
      "grad_norm": 1.051710377423096,
      "learning_rate": 1.1161737308951473e-05,
      "loss": 0.5213,
      "step": 411
    },
    {
      "epoch": 0.5177607163194377,
      "grad_norm": 1.0876393327574223,
      "learning_rate": 1.111808538712494e-05,
      "loss": 0.4783,
      "step": 412
    },
    {
      "epoch": 0.5190174170872033,
      "grad_norm": 1.1011922768783085,
      "learning_rate": 1.1074411879807271e-05,
      "loss": 0.5381,
      "step": 413
    },
    {
      "epoch": 0.5202741178549689,
      "grad_norm": 1.0360462896838518,
      "learning_rate": 1.1030717630148839e-05,
      "loss": 0.4827,
      "step": 414
    },
    {
      "epoch": 0.5215308186227345,
      "grad_norm": 1.0634457362167398,
      "learning_rate": 1.0987003481700456e-05,
      "loss": 0.468,
      "step": 415
    },
    {
      "epoch": 0.5227875193905002,
      "grad_norm": 1.063398934605818,
      "learning_rate": 1.0943270278397097e-05,
      "loss": 0.5022,
      "step": 416
    },
    {
      "epoch": 0.5240442201582658,
      "grad_norm": 1.1236585460615724,
      "learning_rate": 1.0899518864541607e-05,
      "loss": 0.4927,
      "step": 417
    },
    {
      "epoch": 0.5253009209260314,
      "grad_norm": 1.1131356127327812,
      "learning_rate": 1.08557500847884e-05,
      "loss": 0.482,
      "step": 418
    },
    {
      "epoch": 0.526557621693797,
      "grad_norm": 1.074020533914174,
      "learning_rate": 1.0811964784127145e-05,
      "loss": 0.4989,
      "step": 419
    },
    {
      "epoch": 0.5278143224615627,
      "grad_norm": 1.10409363319172,
      "learning_rate": 1.076816380786647e-05,
      "loss": 0.5241,
      "step": 420
    },
    {
      "epoch": 0.5290710232293283,
      "grad_norm": 1.122732579577094,
      "learning_rate": 1.0724348001617626e-05,
      "loss": 0.5156,
      "step": 421
    },
    {
      "epoch": 0.5303277239970938,
      "grad_norm": 1.0617618240477706,
      "learning_rate": 1.0680518211278169e-05,
      "loss": 0.48,
      "step": 422
    },
    {
      "epoch": 0.5315844247648595,
      "grad_norm": 1.0479305127381242,
      "learning_rate": 1.063667528301563e-05,
      "loss": 0.4979,
      "step": 423
    },
    {
      "epoch": 0.5328411255326251,
      "grad_norm": 0.9841907268191958,
      "learning_rate": 1.0592820063251177e-05,
      "loss": 0.4794,
      "step": 424
    },
    {
      "epoch": 0.5340978263003907,
      "grad_norm": 1.0319821042091273,
      "learning_rate": 1.0548953398643276e-05,
      "loss": 0.5059,
      "step": 425
    },
    {
      "epoch": 0.5353545270681563,
      "grad_norm": 1.0138228640258524,
      "learning_rate": 1.0505076136071342e-05,
      "loss": 0.4951,
      "step": 426
    },
    {
      "epoch": 0.536611227835922,
      "grad_norm": 1.1594538762080069,
      "learning_rate": 1.0461189122619394e-05,
      "loss": 0.4968,
      "step": 427
    },
    {
      "epoch": 0.5378679286036876,
      "grad_norm": 1.007644935103111,
      "learning_rate": 1.0417293205559694e-05,
      "loss": 0.5192,
      "step": 428
    },
    {
      "epoch": 0.5391246293714532,
      "grad_norm": 1.0681339563091352,
      "learning_rate": 1.0373389232336404e-05,
      "loss": 0.516,
      "step": 429
    },
    {
      "epoch": 0.5403813301392189,
      "grad_norm": 1.0071232530991345,
      "learning_rate": 1.0329478050549208e-05,
      "loss": 0.4812,
      "step": 430
    },
    {
      "epoch": 0.5416380309069845,
      "grad_norm": 1.0658183171395332,
      "learning_rate": 1.0285560507936962e-05,
      "loss": 0.4668,
      "step": 431
    },
    {
      "epoch": 0.5428947316747501,
      "grad_norm": 0.97242755575935,
      "learning_rate": 1.0241637452361323e-05,
      "loss": 0.5024,
      "step": 432
    },
    {
      "epoch": 0.5441514324425157,
      "grad_norm": 1.1113207771581286,
      "learning_rate": 1.0197709731790375e-05,
      "loss": 0.4847,
      "step": 433
    },
    {
      "epoch": 0.5454081332102814,
      "grad_norm": 1.0305552020476478,
      "learning_rate": 1.0153778194282269e-05,
      "loss": 0.5019,
      "step": 434
    },
    {
      "epoch": 0.546664833978047,
      "grad_norm": 1.0370594881922448,
      "learning_rate": 1.0109843687968837e-05,
      "loss": 0.4958,
      "step": 435
    },
    {
      "epoch": 0.5479215347458126,
      "grad_norm": 1.01930158227936,
      "learning_rate": 1.0065907061039234e-05,
      "loss": 0.5096,
      "step": 436
    },
    {
      "epoch": 0.5491782355135783,
      "grad_norm": 0.9871603297074679,
      "learning_rate": 1.0021969161723555e-05,
      "loss": 0.4685,
      "step": 437
    },
    {
      "epoch": 0.5504349362813439,
      "grad_norm": 1.0920379317965205,
      "learning_rate": 9.97803083827645e-06,
      "loss": 0.4644,
      "step": 438
    },
    {
      "epoch": 0.5516916370491095,
      "grad_norm": 1.054600973465295,
      "learning_rate": 9.934092938960769e-06,
      "loss": 0.4893,
      "step": 439
    },
    {
      "epoch": 0.5529483378168751,
      "grad_norm": 1.0201582460505152,
      "learning_rate": 9.890156312031165e-06,
      "loss": 0.4955,
      "step": 440
    },
    {
      "epoch": 0.5542050385846408,
      "grad_norm": 0.9716441699106971,
      "learning_rate": 9.846221805717734e-06,
      "loss": 0.495,
      "step": 441
    },
    {
      "epoch": 0.5554617393524064,
      "grad_norm": 1.082312481961198,
      "learning_rate": 9.802290268209627e-06,
      "loss": 0.5257,
      "step": 442
    },
    {
      "epoch": 0.556718440120172,
      "grad_norm": 1.0097621423303396,
      "learning_rate": 9.75836254763868e-06,
      "loss": 0.5063,
      "step": 443
    },
    {
      "epoch": 0.5579751408879376,
      "grad_norm": 1.0275627453990908,
      "learning_rate": 9.71443949206304e-06,
      "loss": 0.5461,
      "step": 444
    },
    {
      "epoch": 0.5592318416557033,
      "grad_norm": 0.990883428276697,
      "learning_rate": 9.670521949450793e-06,
      "loss": 0.4691,
      "step": 445
    },
    {
      "epoch": 0.5604885424234689,
      "grad_norm": 1.3593079122891867,
      "learning_rate": 9.6266107676636e-06,
      "loss": 0.4809,
      "step": 446
    },
    {
      "epoch": 0.5617452431912345,
      "grad_norm": 1.0402512025062964,
      "learning_rate": 9.58270679444031e-06,
      "loss": 0.5249,
      "step": 447
    },
    {
      "epoch": 0.5630019439590002,
      "grad_norm": 1.0374899415597172,
      "learning_rate": 9.538810877380611e-06,
      "loss": 0.4911,
      "step": 448
    },
    {
      "epoch": 0.5642586447267658,
      "grad_norm": 1.0181963135605545,
      "learning_rate": 9.49492386392866e-06,
      "loss": 0.5074,
      "step": 449
    },
    {
      "epoch": 0.5655153454945314,
      "grad_norm": 1.2455466094666068,
      "learning_rate": 9.451046601356725e-06,
      "loss": 0.5031,
      "step": 450
    },
    {
      "epoch": 0.5655153454945314,
      "eval_loss": NaN,
      "eval_runtime": 390.362,
      "eval_samples_per_second": 21.301,
      "eval_steps_per_second": 2.664,
      "step": 450
    },
    {
      "epoch": 0.566772046262297,
      "grad_norm": 1.087941249032518,
      "learning_rate": 9.407179936748827e-06,
      "loss": 0.4838,
      "step": 451
    },
    {
      "epoch": 0.5680287470300627,
      "grad_norm": 1.0487351474005773,
      "learning_rate": 9.363324716984375e-06,
      "loss": 0.6147,
      "step": 452
    },
    {
      "epoch": 0.5692854477978283,
      "grad_norm": 1.0006830147884598,
      "learning_rate": 9.319481788721833e-06,
      "loss": 0.4864,
      "step": 453
    },
    {
      "epoch": 0.5705421485655939,
      "grad_norm": 1.0804045530543167,
      "learning_rate": 9.275651998382377e-06,
      "loss": 0.465,
      "step": 454
    },
    {
      "epoch": 0.5717988493333596,
      "grad_norm": 1.0428355842758288,
      "learning_rate": 9.231836192133532e-06,
      "loss": 0.4821,
      "step": 455
    },
    {
      "epoch": 0.5730555501011252,
      "grad_norm": 1.0610803769161647,
      "learning_rate": 9.188035215872858e-06,
      "loss": 0.4867,
      "step": 456
    },
    {
      "epoch": 0.5743122508688908,
      "grad_norm": 1.0520660600408804,
      "learning_rate": 9.144249915211605e-06,
      "loss": 0.5214,
      "step": 457
    },
    {
      "epoch": 0.5755689516366564,
      "grad_norm": 1.0373635995203723,
      "learning_rate": 9.100481135458393e-06,
      "loss": 0.4943,
      "step": 458
    },
    {
      "epoch": 0.576825652404422,
      "grad_norm": 1.3517258385540856,
      "learning_rate": 9.056729721602904e-06,
      "loss": 0.6224,
      "step": 459
    },
    {
      "epoch": 0.5780823531721876,
      "grad_norm": 1.0301066331386723,
      "learning_rate": 9.012996518299547e-06,
      "loss": 0.5092,
      "step": 460
    },
    {
      "epoch": 0.5793390539399532,
      "grad_norm": 1.0099912645887554,
      "learning_rate": 8.969282369851163e-06,
      "loss": 0.4901,
      "step": 461
    },
    {
      "epoch": 0.5805957547077188,
      "grad_norm": 1.0482057682006019,
      "learning_rate": 8.92558812019273e-06,
      "loss": 0.4793,
      "step": 462
    },
    {
      "epoch": 0.5818524554754845,
      "grad_norm": 1.0475419610115655,
      "learning_rate": 8.881914612875062e-06,
      "loss": 0.48,
      "step": 463
    },
    {
      "epoch": 0.5831091562432501,
      "grad_norm": 1.0523184837700892,
      "learning_rate": 8.838262691048529e-06,
      "loss": 0.4852,
      "step": 464
    },
    {
      "epoch": 0.5843658570110157,
      "grad_norm": 1.3520200098351463,
      "learning_rate": 8.79463319744677e-06,
      "loss": 0.4807,
      "step": 465
    },
    {
      "epoch": 0.5856225577787814,
      "grad_norm": 1.070883661168547,
      "learning_rate": 8.751026974370438e-06,
      "loss": 0.5023,
      "step": 466
    },
    {
      "epoch": 0.586879258546547,
      "grad_norm": 1.064553688268609,
      "learning_rate": 8.70744486367092e-06,
      "loss": 0.4924,
      "step": 467
    },
    {
      "epoch": 0.5881359593143126,
      "grad_norm": 1.0759932963506342,
      "learning_rate": 8.66388770673411e-06,
      "loss": 0.4971,
      "step": 468
    },
    {
      "epoch": 0.5893926600820782,
      "grad_norm": 0.9719685034220976,
      "learning_rate": 8.620356344464135e-06,
      "loss": 0.4932,
      "step": 469
    },
    {
      "epoch": 0.5906493608498439,
      "grad_norm": 1.0215732980684333,
      "learning_rate": 8.576851617267151e-06,
      "loss": 0.4901,
      "step": 470
    },
    {
      "epoch": 0.5919060616176095,
      "grad_norm": 1.0057794928079793,
      "learning_rate": 8.533374365035089e-06,
      "loss": 0.4755,
      "step": 471
    },
    {
      "epoch": 0.5931627623853751,
      "grad_norm": 1.0731603783900507,
      "learning_rate": 8.489925427129469e-06,
      "loss": 0.5194,
      "step": 472
    },
    {
      "epoch": 0.5944194631531408,
      "grad_norm": 1.0413553281269248,
      "learning_rate": 8.446505642365174e-06,
      "loss": 0.4651,
      "step": 473
    },
    {
      "epoch": 0.5956761639209064,
      "grad_norm": 1.0439372619946545,
      "learning_rate": 8.40311584899426e-06,
      "loss": 0.5009,
      "step": 474
    },
    {
      "epoch": 0.596932864688672,
      "grad_norm": 1.079306190387013,
      "learning_rate": 8.359756884689785e-06,
      "loss": 0.4643,
      "step": 475
    },
    {
      "epoch": 0.5981895654564376,
      "grad_norm": 0.9998675795140389,
      "learning_rate": 8.316429586529616e-06,
      "loss": 0.4811,
      "step": 476
    },
    {
      "epoch": 0.5994462662242033,
      "grad_norm": 0.9612157155286085,
      "learning_rate": 8.273134790980295e-06,
      "loss": 0.4732,
      "step": 477
    },
    {
      "epoch": 0.6007029669919689,
      "grad_norm": 1.0216579545060833,
      "learning_rate": 8.22987333388087e-06,
      "loss": 0.4878,
      "step": 478
    },
    {
      "epoch": 0.6019596677597345,
      "grad_norm": 1.035592271636439,
      "learning_rate": 8.186646050426763e-06,
      "loss": 0.4763,
      "step": 479
    },
    {
      "epoch": 0.6032163685275002,
      "grad_norm": 0.9266009986946163,
      "learning_rate": 8.143453775153646e-06,
      "loss": 0.4962,
      "step": 480
    },
    {
      "epoch": 0.6044730692952658,
      "grad_norm": 1.0063210029903829,
      "learning_rate": 8.100297341921342e-06,
      "loss": 0.5457,
      "step": 481
    },
    {
      "epoch": 0.6057297700630314,
      "grad_norm": 1.0212142908210302,
      "learning_rate": 8.057177583897704e-06,
      "loss": 0.4623,
      "step": 482
    },
    {
      "epoch": 0.606986470830797,
      "grad_norm": 1.0319718233335433,
      "learning_rate": 8.014095333542548e-06,
      "loss": 0.5095,
      "step": 483
    },
    {
      "epoch": 0.6082431715985627,
      "grad_norm": 0.9974523217893733,
      "learning_rate": 7.971051422591571e-06,
      "loss": 0.5192,
      "step": 484
    },
    {
      "epoch": 0.6094998723663283,
      "grad_norm": 0.9326473530788999,
      "learning_rate": 7.928046682040311e-06,
      "loss": 0.4574,
      "step": 485
    },
    {
      "epoch": 0.6107565731340939,
      "grad_norm": 0.9393968466161859,
      "learning_rate": 7.885081942128074e-06,
      "loss": 0.5029,
      "step": 486
    },
    {
      "epoch": 0.6120132739018596,
      "grad_norm": 0.9680572001368599,
      "learning_rate": 7.84215803232194e-06,
      "loss": 0.514,
      "step": 487
    },
    {
      "epoch": 0.6132699746696252,
      "grad_norm": 1.0704719257655635,
      "learning_rate": 7.79927578130072e-06,
      "loss": 0.4928,
      "step": 488
    },
    {
      "epoch": 0.6145266754373908,
      "grad_norm": 1.0200776137947951,
      "learning_rate": 7.756436016938973e-06,
      "loss": 0.4869,
      "step": 489
    },
    {
      "epoch": 0.6157833762051564,
      "grad_norm": 0.9387956884468813,
      "learning_rate": 7.713639566291028e-06,
      "loss": 0.4799,
      "step": 490
    },
    {
      "epoch": 0.6170400769729221,
      "grad_norm": 0.9312805823610483,
      "learning_rate": 7.670887255575003e-06,
      "loss": 0.4931,
      "step": 491
    },
    {
      "epoch": 0.6182967777406877,
      "grad_norm": 0.9295388110852509,
      "learning_rate": 7.628179910156859e-06,
      "loss": 0.5234,
      "step": 492
    },
    {
      "epoch": 0.6195534785084533,
      "grad_norm": 0.9969654532505003,
      "learning_rate": 7.585518354534473e-06,
      "loss": 0.5349,
      "step": 493
    },
    {
      "epoch": 0.620810179276219,
      "grad_norm": 0.969918008367211,
      "learning_rate": 7.542903412321714e-06,
      "loss": 0.4843,
      "step": 494
    },
    {
      "epoch": 0.6220668800439845,
      "grad_norm": 0.9449769047029168,
      "learning_rate": 7.500335906232544e-06,
      "loss": 0.4639,
      "step": 495
    },
    {
      "epoch": 0.6233235808117501,
      "grad_norm": 1.033777318960197,
      "learning_rate": 7.4578166580651335e-06,
      "loss": 0.504,
      "step": 496
    },
    {
      "epoch": 0.6245802815795157,
      "grad_norm": 0.9914352689303235,
      "learning_rate": 7.4153464886859925e-06,
      "loss": 0.4981,
      "step": 497
    },
    {
      "epoch": 0.6258369823472814,
      "grad_norm": 1.056953990111743,
      "learning_rate": 7.372926218014131e-06,
      "loss": 0.516,
      "step": 498
    },
    {
      "epoch": 0.627093683115047,
      "grad_norm": 0.9687789789603087,
      "learning_rate": 7.330556665005235e-06,
      "loss": 0.4599,
      "step": 499
    },
    {
      "epoch": 0.6283503838828126,
      "grad_norm": 1.0066721178900888,
      "learning_rate": 7.2882386476358304e-06,
      "loss": 0.4614,
      "step": 500
    },
    {
      "epoch": 0.6283503838828126,
      "eval_loss": NaN,
      "eval_runtime": 384.2451,
      "eval_samples_per_second": 21.64,
      "eval_steps_per_second": 2.707,
      "step": 500
    },
    {
      "epoch": 0.6296070846505782,
      "grad_norm": 1.0360193648866638,
      "learning_rate": 7.2459729828875256e-06,
      "loss": 0.4916,
      "step": 501
    },
    {
      "epoch": 0.6308637854183439,
      "grad_norm": 0.9139912569370758,
      "learning_rate": 7.203760486731204e-06,
      "loss": 0.4688,
      "step": 502
    },
    {
      "epoch": 0.6321204861861095,
      "grad_norm": 1.0077884286770724,
      "learning_rate": 7.161601974111308e-06,
      "loss": 0.4936,
      "step": 503
    },
    {
      "epoch": 0.6333771869538751,
      "grad_norm": 0.9993486667429677,
      "learning_rate": 7.119498258930073e-06,
      "loss": 0.5179,
      "step": 504
    },
    {
      "epoch": 0.6346338877216408,
      "grad_norm": 0.9964058480599178,
      "learning_rate": 7.0774501540318305e-06,
      "loss": 0.4745,
      "step": 505
    },
    {
      "epoch": 0.6358905884894064,
      "grad_norm": 0.9646168801150186,
      "learning_rate": 7.035458471187312e-06,
      "loss": 0.4865,
      "step": 506
    },
    {
      "epoch": 0.637147289257172,
      "grad_norm": 0.9977812292191052,
      "learning_rate": 6.993524021077989e-06,
      "loss": 0.5161,
      "step": 507
    },
    {
      "epoch": 0.6384039900249376,
      "grad_norm": 0.9788000489126177,
      "learning_rate": 6.951647613280397e-06,
      "loss": 0.5361,
      "step": 508
    },
    {
      "epoch": 0.6396606907927033,
      "grad_norm": 0.9186321053151645,
      "learning_rate": 6.909830056250527e-06,
      "loss": 0.4871,
      "step": 509
    },
    {
      "epoch": 0.6409173915604689,
      "grad_norm": 1.0035904562057332,
      "learning_rate": 6.868072157308213e-06,
      "loss": 0.5202,
      "step": 510
    },
    {
      "epoch": 0.6421740923282345,
      "grad_norm": 0.9810776358670968,
      "learning_rate": 6.826374722621536e-06,
      "loss": 0.4599,
      "step": 511
    },
    {
      "epoch": 0.6434307930960002,
      "grad_norm": 0.9283679926638487,
      "learning_rate": 6.784738557191284e-06,
      "loss": 0.4628,
      "step": 512
    },
    {
      "epoch": 0.6446874938637658,
      "grad_norm": 0.9994992253986084,
      "learning_rate": 6.7431644648353785e-06,
      "loss": 0.4674,
      "step": 513
    },
    {
      "epoch": 0.6459441946315314,
      "grad_norm": 0.9106352041140137,
      "learning_rate": 6.701653248173382e-06,
      "loss": 0.4625,
      "step": 514
    },
    {
      "epoch": 0.647200895399297,
      "grad_norm": 0.9500901417881573,
      "learning_rate": 6.660205708610987e-06,
      "loss": 0.4797,
      "step": 515
    },
    {
      "epoch": 0.6484575961670627,
      "grad_norm": 0.9472535122755693,
      "learning_rate": 6.618822646324563e-06,
      "loss": 0.4669,
      "step": 516
    },
    {
      "epoch": 0.6497142969348283,
      "grad_norm": 0.9589653557097556,
      "learning_rate": 6.577504860245684e-06,
      "loss": 0.5408,
      "step": 517
    },
    {
      "epoch": 0.6509709977025939,
      "grad_norm": 0.96979303506713,
      "learning_rate": 6.536253148045726e-06,
      "loss": 0.4897,
      "step": 518
    },
    {
      "epoch": 0.6522276984703596,
      "grad_norm": 0.9496625953614718,
      "learning_rate": 6.495068306120452e-06,
      "loss": 0.4896,
      "step": 519
    },
    {
      "epoch": 0.6534843992381252,
      "grad_norm": 0.9999476061446844,
      "learning_rate": 6.453951129574644e-06,
      "loss": 0.5023,
      "step": 520
    },
    {
      "epoch": 0.6547411000058908,
      "grad_norm": 0.9223335871200387,
      "learning_rate": 6.41290241220676e-06,
      "loss": 0.5464,
      "step": 521
    },
    {
      "epoch": 0.6559978007736564,
      "grad_norm": 1.0030864529913075,
      "learning_rate": 6.3719229464935915e-06,
      "loss": 0.4778,
      "step": 522
    },
    {
      "epoch": 0.6572545015414221,
      "grad_norm": 0.9309808406108107,
      "learning_rate": 6.331013523574978e-06,
      "loss": 0.5015,
      "step": 523
    },
    {
      "epoch": 0.6585112023091877,
      "grad_norm": 1.1823052168866466,
      "learning_rate": 6.290174933238531e-06,
      "loss": 0.4782,
      "step": 524
    },
    {
      "epoch": 0.6597679030769533,
      "grad_norm": 0.9878321294333653,
      "learning_rate": 6.249407963904381e-06,
      "loss": 0.5033,
      "step": 525
    },
    {
      "epoch": 0.661024603844719,
      "grad_norm": 0.9465968966854122,
      "learning_rate": 6.208713402609968e-06,
      "loss": 0.4765,
      "step": 526
    },
    {
      "epoch": 0.6622813046124846,
      "grad_norm": 1.042662157579056,
      "learning_rate": 6.168092034994832e-06,
      "loss": 0.4847,
      "step": 527
    },
    {
      "epoch": 0.6635380053802502,
      "grad_norm": 0.9634576640584912,
      "learning_rate": 6.127544645285448e-06,
      "loss": 0.4634,
      "step": 528
    },
    {
      "epoch": 0.6647947061480158,
      "grad_norm": 0.9603382195784586,
      "learning_rate": 6.087072016280111e-06,
      "loss": 0.4902,
      "step": 529
    },
    {
      "epoch": 0.6660514069157815,
      "grad_norm": 0.9598750622234282,
      "learning_rate": 6.046674929333787e-06,
      "loss": 0.4806,
      "step": 530
    },
    {
      "epoch": 0.6673081076835471,
      "grad_norm": 0.9029178527016823,
      "learning_rate": 6.006354164343047e-06,
      "loss": 0.4577,
      "step": 531
    },
    {
      "epoch": 0.6685648084513126,
      "grad_norm": 0.9306648630657135,
      "learning_rate": 5.96611049973101e-06,
      "loss": 0.578,
      "step": 532
    },
    {
      "epoch": 0.6698215092190782,
      "grad_norm": 0.9745393471796585,
      "learning_rate": 5.925944712432317e-06,
      "loss": 0.4582,
      "step": 533
    },
    {
      "epoch": 0.6710782099868439,
      "grad_norm": 0.9854308021827322,
      "learning_rate": 5.885857577878122e-06,
      "loss": 0.4728,
      "step": 534
    },
    {
      "epoch": 0.6723349107546095,
      "grad_norm": 0.9505828662992784,
      "learning_rate": 5.845849869981137e-06,
      "loss": 0.4732,
      "step": 535
    },
    {
      "epoch": 0.6735916115223751,
      "grad_norm": 0.971008498361879,
      "learning_rate": 5.8059223611206716e-06,
      "loss": 0.4782,
      "step": 536
    },
    {
      "epoch": 0.6748483122901408,
      "grad_norm": 1.0199269663151482,
      "learning_rate": 5.766075822127735e-06,
      "loss": 0.4664,
      "step": 537
    },
    {
      "epoch": 0.6761050130579064,
      "grad_norm": 0.9414292961876951,
      "learning_rate": 5.726311022270152e-06,
      "loss": 0.4869,
      "step": 538
    },
    {
      "epoch": 0.677361713825672,
      "grad_norm": 0.9637472122488508,
      "learning_rate": 5.686628729237713e-06,
      "loss": 0.4853,
      "step": 539
    },
    {
      "epoch": 0.6786184145934376,
      "grad_norm": 1.004859916641192,
      "learning_rate": 5.647029709127355e-06,
      "loss": 0.4755,
      "step": 540
    },
    {
      "epoch": 0.6798751153612033,
      "grad_norm": 1.0313280249469097,
      "learning_rate": 5.6075147264283526e-06,
      "loss": 0.4728,
      "step": 541
    },
    {
      "epoch": 0.6811318161289689,
      "grad_norm": 0.9536505641573378,
      "learning_rate": 5.5680845440075885e-06,
      "loss": 0.473,
      "step": 542
    },
    {
      "epoch": 0.6823885168967345,
      "grad_norm": 0.9540350587248954,
      "learning_rate": 5.528739923094806e-06,
      "loss": 0.4657,
      "step": 543
    },
    {
      "epoch": 0.6836452176645001,
      "grad_norm": 0.9072196968401911,
      "learning_rate": 5.4894816232679195e-06,
      "loss": 0.4543,
      "step": 544
    },
    {
      "epoch": 0.6849019184322658,
      "grad_norm": 0.9814435512849559,
      "learning_rate": 5.450310402438353e-06,
      "loss": 0.4897,
      "step": 545
    },
    {
      "epoch": 0.6861586192000314,
      "grad_norm": 0.9601361725013989,
      "learning_rate": 5.4112270168363854e-06,
      "loss": 0.4749,
      "step": 546
    },
    {
      "epoch": 0.687415319967797,
      "grad_norm": 0.9663745304412944,
      "learning_rate": 5.3722322209966024e-06,
      "loss": 0.4848,
      "step": 547
    },
    {
      "epoch": 0.6886720207355627,
      "grad_norm": 1.0061563886612799,
      "learning_rate": 5.333326767743263e-06,
      "loss": 0.4673,
      "step": 548
    },
    {
      "epoch": 0.6899287215033283,
      "grad_norm": 0.9439604050992346,
      "learning_rate": 5.294511408175825e-06,
      "loss": 0.4853,
      "step": 549
    },
    {
      "epoch": 0.6911854222710939,
      "grad_norm": 0.962910340515467,
      "learning_rate": 5.2557868916543996e-06,
      "loss": 0.4791,
      "step": 550
    },
    {
      "epoch": 0.6911854222710939,
      "eval_loss": NaN,
      "eval_runtime": 395.5216,
      "eval_samples_per_second": 21.023,
      "eval_steps_per_second": 2.629,
      "step": 550
    },
    {
      "epoch": 0.6924421230388595,
      "grad_norm": 0.9707818718943069,
      "learning_rate": 5.217153965785315e-06,
      "loss": 0.5109,
      "step": 551
    },
    {
      "epoch": 0.6936988238066252,
      "grad_norm": 0.9595264837099737,
      "learning_rate": 5.178613376406672e-06,
      "loss": 0.4675,
      "step": 552
    },
    {
      "epoch": 0.6949555245743908,
      "grad_norm": 0.9611450529414026,
      "learning_rate": 5.14016586757394e-06,
      "loss": 0.4814,
      "step": 553
    },
    {
      "epoch": 0.6962122253421564,
      "grad_norm": 1.0045400911821167,
      "learning_rate": 5.1018121815456045e-06,
      "loss": 0.5006,
      "step": 554
    },
    {
      "epoch": 0.6974689261099221,
      "grad_norm": 0.964170058570595,
      "learning_rate": 5.063553058768814e-06,
      "loss": 0.4615,
      "step": 555
    },
    {
      "epoch": 0.6987256268776877,
      "grad_norm": 0.974630657567601,
      "learning_rate": 5.025389237865128e-06,
      "loss": 0.6329,
      "step": 556
    },
    {
      "epoch": 0.6999823276454533,
      "grad_norm": 0.9940742215685975,
      "learning_rate": 4.987321455616206e-06,
      "loss": 0.4603,
      "step": 557
    },
    {
      "epoch": 0.701239028413219,
      "grad_norm": 0.8894890015293643,
      "learning_rate": 4.9493504469496235e-06,
      "loss": 0.4553,
      "step": 558
    },
    {
      "epoch": 0.7024957291809846,
      "grad_norm": 0.9992618220443336,
      "learning_rate": 4.911476944924651e-06,
      "loss": 0.4864,
      "step": 559
    },
    {
      "epoch": 0.7037524299487502,
      "grad_norm": 0.9141872027503535,
      "learning_rate": 4.873701680718146e-06,
      "loss": 0.5114,
      "step": 560
    },
    {
      "epoch": 0.7050091307165158,
      "grad_norm": 0.9326203191415026,
      "learning_rate": 4.836025383610382e-06,
      "loss": 0.4764,
      "step": 561
    },
    {
      "epoch": 0.7062658314842815,
      "grad_norm": 0.925599543126751,
      "learning_rate": 4.798448780971013e-06,
      "loss": 0.4841,
      "step": 562
    },
    {
      "epoch": 0.7075225322520471,
      "grad_norm": 0.9315828509380828,
      "learning_rate": 4.7609725982450176e-06,
      "loss": 0.4739,
      "step": 563
    },
    {
      "epoch": 0.7087792330198127,
      "grad_norm": 0.934793953759224,
      "learning_rate": 4.7235975589386715e-06,
      "loss": 0.4464,
      "step": 564
    },
    {
      "epoch": 0.7100359337875783,
      "grad_norm": 0.9341913967846289,
      "learning_rate": 4.686324384605629e-06,
      "loss": 0.4559,
      "step": 565
    },
    {
      "epoch": 0.711292634555344,
      "grad_norm": 0.9828397495391764,
      "learning_rate": 4.649153794832939e-06,
      "loss": 0.5193,
      "step": 566
    },
    {
      "epoch": 0.7125493353231096,
      "grad_norm": 0.9608848681418946,
      "learning_rate": 4.612086507227186e-06,
      "loss": 0.4675,
      "step": 567
    },
    {
      "epoch": 0.7138060360908752,
      "grad_norm": 0.9250968302486778,
      "learning_rate": 4.5751232374006304e-06,
      "loss": 0.4469,
      "step": 568
    },
    {
      "epoch": 0.7150627368586407,
      "grad_norm": 0.8931095869951399,
      "learning_rate": 4.538264698957387e-06,
      "loss": 0.4384,
      "step": 569
    },
    {
      "epoch": 0.7163194376264064,
      "grad_norm": 0.8957255025032255,
      "learning_rate": 4.501511603479653e-06,
      "loss": 0.4595,
      "step": 570
    },
    {
      "epoch": 0.717576138394172,
      "grad_norm": 0.9797783050556119,
      "learning_rate": 4.4648646605139605e-06,
      "loss": 0.4803,
      "step": 571
    },
    {
      "epoch": 0.7188328391619376,
      "grad_norm": 1.0477043965745412,
      "learning_rate": 4.428324577557501e-06,
      "loss": 0.5001,
      "step": 572
    },
    {
      "epoch": 0.7200895399297033,
      "grad_norm": 0.9402442503704912,
      "learning_rate": 4.391892060044435e-06,
      "loss": 0.5285,
      "step": 573
    },
    {
      "epoch": 0.7213462406974689,
      "grad_norm": 0.895533404301798,
      "learning_rate": 4.355567811332311e-06,
      "loss": 0.4249,
      "step": 574
    },
    {
      "epoch": 0.7226029414652345,
      "grad_norm": 0.9375812495309651,
      "learning_rate": 4.319352532688444e-06,
      "loss": 0.4864,
      "step": 575
    },
    {
      "epoch": 0.7238596422330001,
      "grad_norm": 0.9535540256167436,
      "learning_rate": 4.283246923276411e-06,
      "loss": 0.451,
      "step": 576
    },
    {
      "epoch": 0.7251163430007658,
      "grad_norm": 0.9843964347322175,
      "learning_rate": 4.247251680142542e-06,
      "loss": 0.4934,
      "step": 577
    },
    {
      "epoch": 0.7263730437685314,
      "grad_norm": 0.902113121251565,
      "learning_rate": 4.211367498202456e-06,
      "loss": 0.4859,
      "step": 578
    },
    {
      "epoch": 0.727629744536297,
      "grad_norm": 0.9071019213314944,
      "learning_rate": 4.175595070227655e-06,
      "loss": 0.463,
      "step": 579
    },
    {
      "epoch": 0.7288864453040627,
      "grad_norm": 0.9445861043217729,
      "learning_rate": 4.13993508683214e-06,
      "loss": 0.4639,
      "step": 580
    },
    {
      "epoch": 0.7301431460718283,
      "grad_norm": 0.9529191091817809,
      "learning_rate": 4.1043882364590895e-06,
      "loss": 0.458,
      "step": 581
    },
    {
      "epoch": 0.7313998468395939,
      "grad_norm": 0.943614064462381,
      "learning_rate": 4.068955205367559e-06,
      "loss": 0.4501,
      "step": 582
    },
    {
      "epoch": 0.7326565476073595,
      "grad_norm": 0.9501101229235286,
      "learning_rate": 4.033636677619242e-06,
      "loss": 0.4507,
      "step": 583
    },
    {
      "epoch": 0.7339132483751252,
      "grad_norm": 0.9696808926218615,
      "learning_rate": 3.998433335065251e-06,
      "loss": 0.5016,
      "step": 584
    },
    {
      "epoch": 0.7351699491428908,
      "grad_norm": 0.8737082824243725,
      "learning_rate": 3.96334585733296e-06,
      "loss": 0.418,
      "step": 585
    },
    {
      "epoch": 0.7364266499106564,
      "grad_norm": 0.9176906083149247,
      "learning_rate": 3.9283749218128885e-06,
      "loss": 0.479,
      "step": 586
    },
    {
      "epoch": 0.7376833506784221,
      "grad_norm": 0.9192555275886508,
      "learning_rate": 3.893521203645618e-06,
      "loss": 0.49,
      "step": 587
    },
    {
      "epoch": 0.7389400514461877,
      "grad_norm": 0.9259761814325044,
      "learning_rate": 3.858785375708764e-06,
      "loss": 0.4658,
      "step": 588
    },
    {
      "epoch": 0.7401967522139533,
      "grad_norm": 0.8762077783379093,
      "learning_rate": 3.824168108603971e-06,
      "loss": 0.4825,
      "step": 589
    },
    {
      "epoch": 0.7414534529817189,
      "grad_norm": 0.9928947391135122,
      "learning_rate": 3.7896700706439826e-06,
      "loss": 0.5519,
      "step": 590
    },
    {
      "epoch": 0.7427101537494846,
      "grad_norm": 0.9049374842785678,
      "learning_rate": 3.7552919278397335e-06,
      "loss": 0.4518,
      "step": 591
    },
    {
      "epoch": 0.7439668545172502,
      "grad_norm": 0.8936620428913575,
      "learning_rate": 3.7210343438874917e-06,
      "loss": 0.4341,
      "step": 592
    },
    {
      "epoch": 0.7452235552850158,
      "grad_norm": 0.9409320634262343,
      "learning_rate": 3.6868979801560443e-06,
      "loss": 0.4719,
      "step": 593
    },
    {
      "epoch": 0.7464802560527815,
      "grad_norm": 0.9851785740451936,
      "learning_rate": 3.6528834956739224e-06,
      "loss": 0.429,
      "step": 594
    },
    {
      "epoch": 0.7477369568205471,
      "grad_norm": 0.9952385017039359,
      "learning_rate": 3.6189915471166927e-06,
      "loss": 0.474,
      "step": 595
    },
    {
      "epoch": 0.7489936575883127,
      "grad_norm": 0.9175118141037356,
      "learning_rate": 3.5852227887942713e-06,
      "loss": 0.4453,
      "step": 596
    },
    {
      "epoch": 0.7502503583560783,
      "grad_norm": 0.8948744735918709,
      "learning_rate": 3.5515778726382967e-06,
      "loss": 0.491,
      "step": 597
    },
    {
      "epoch": 0.751507059123844,
      "grad_norm": 0.9493043335059733,
      "learning_rate": 3.518057448189527e-06,
      "loss": 0.4812,
      "step": 598
    },
    {
      "epoch": 0.7527637598916096,
      "grad_norm": 0.9526119414704524,
      "learning_rate": 3.4846621625853248e-06,
      "loss": 0.4758,
      "step": 599
    },
    {
      "epoch": 0.7540204606593752,
      "grad_norm": 0.9375798827152386,
      "learning_rate": 3.4513926605471504e-06,
      "loss": 0.4703,
      "step": 600
    },
    {
      "epoch": 0.7540204606593752,
      "eval_loss": NaN,
      "eval_runtime": 391.2661,
      "eval_samples_per_second": 21.252,
      "eval_steps_per_second": 2.658,
      "step": 600
    },
    {
      "epoch": 0.7552771614271409,
      "grad_norm": 0.9276644067982343,
      "learning_rate": 3.4182495843681117e-06,
      "loss": 0.461,
      "step": 601
    },
    {
      "epoch": 0.7565338621949065,
      "grad_norm": 0.9573184146956152,
      "learning_rate": 3.385233573900576e-06,
      "loss": 0.4812,
      "step": 602
    },
    {
      "epoch": 0.7577905629626721,
      "grad_norm": 0.9005304918861501,
      "learning_rate": 3.3523452665438004e-06,
      "loss": 0.4603,
      "step": 603
    },
    {
      "epoch": 0.7590472637304377,
      "grad_norm": 0.8844651813155415,
      "learning_rate": 3.3195852972316435e-06,
      "loss": 0.4783,
      "step": 604
    },
    {
      "epoch": 0.7603039644982033,
      "grad_norm": 0.9053279526971507,
      "learning_rate": 3.2869542984202974e-06,
      "loss": 0.5253,
      "step": 605
    },
    {
      "epoch": 0.7615606652659689,
      "grad_norm": 0.995160552063608,
      "learning_rate": 3.254452900076083e-06,
      "loss": 0.5082,
      "step": 606
    },
    {
      "epoch": 0.7628173660337345,
      "grad_norm": 0.9879909586608571,
      "learning_rate": 3.2220817296632845e-06,
      "loss": 0.4499,
      "step": 607
    },
    {
      "epoch": 0.7640740668015001,
      "grad_norm": 0.9345160999737937,
      "learning_rate": 3.1898414121320277e-06,
      "loss": 0.4915,
      "step": 608
    },
    {
      "epoch": 0.7653307675692658,
      "grad_norm": 0.9546540611891579,
      "learning_rate": 3.1577325699062424e-06,
      "loss": 0.4864,
      "step": 609
    },
    {
      "epoch": 0.7665874683370314,
      "grad_norm": 0.9216552084428411,
      "learning_rate": 3.125755822871607e-06,
      "loss": 0.5028,
      "step": 610
    },
    {
      "epoch": 0.767844169104797,
      "grad_norm": 0.921600882945863,
      "learning_rate": 3.093911788363617e-06,
      "loss": 0.4773,
      "step": 611
    },
    {
      "epoch": 0.7691008698725627,
      "grad_norm": 0.9429114879803641,
      "learning_rate": 3.062201081155637e-06,
      "loss": 0.4828,
      "step": 612
    },
    {
      "epoch": 0.7703575706403283,
      "grad_norm": 0.9468558457454733,
      "learning_rate": 3.0306243134470668e-06,
      "loss": 0.5299,
      "step": 613
    },
    {
      "epoch": 0.7716142714080939,
      "grad_norm": 0.8680737752062002,
      "learning_rate": 2.9991820948514795e-06,
      "loss": 0.4608,
      "step": 614
    },
    {
      "epoch": 0.7728709721758595,
      "grad_norm": 0.9257236575469265,
      "learning_rate": 2.9678750323848893e-06,
      "loss": 0.4786,
      "step": 615
    },
    {
      "epoch": 0.7741276729436252,
      "grad_norm": 0.9656830199257891,
      "learning_rate": 2.936703730454017e-06,
      "loss": 0.4358,
      "step": 616
    },
    {
      "epoch": 0.7753843737113908,
      "grad_norm": 0.9907979170488217,
      "learning_rate": 2.90566879084461e-06,
      "loss": 0.5215,
      "step": 617
    },
    {
      "epoch": 0.7766410744791564,
      "grad_norm": 0.8950799317069913,
      "learning_rate": 2.8747708127098593e-06,
      "loss": 0.4717,
      "step": 618
    },
    {
      "epoch": 0.777897775246922,
      "grad_norm": 0.9505878825468562,
      "learning_rate": 2.8440103925587904e-06,
      "loss": 0.4566,
      "step": 619
    },
    {
      "epoch": 0.7791544760146877,
      "grad_norm": 0.969358314749328,
      "learning_rate": 2.813388124244778e-06,
      "loss": 0.4492,
      "step": 620
    },
    {
      "epoch": 0.7804111767824533,
      "grad_norm": 0.9785261324929386,
      "learning_rate": 2.7829045989540594e-06,
      "loss": 0.4496,
      "step": 621
    },
    {
      "epoch": 0.7816678775502189,
      "grad_norm": 0.9531236242065506,
      "learning_rate": 2.7525604051943512e-06,
      "loss": 0.5504,
      "step": 622
    },
    {
      "epoch": 0.7829245783179846,
      "grad_norm": 0.9826298336215402,
      "learning_rate": 2.7223561287834467e-06,
      "loss": 0.4586,
      "step": 623
    },
    {
      "epoch": 0.7841812790857502,
      "grad_norm": 0.9317085993058872,
      "learning_rate": 2.692292352837942e-06,
      "loss": 0.4672,
      "step": 624
    },
    {
      "epoch": 0.7854379798535158,
      "grad_norm": 1.0787276642963513,
      "learning_rate": 2.662369657761963e-06,
      "loss": 0.4608,
      "step": 625
    },
    {
      "epoch": 0.7866946806212815,
      "grad_norm": 0.9372652077711696,
      "learning_rate": 2.6325886212359496e-06,
      "loss": 0.4377,
      "step": 626
    },
    {
      "epoch": 0.7879513813890471,
      "grad_norm": 0.9921327711014636,
      "learning_rate": 2.602949818205539e-06,
      "loss": 0.4584,
      "step": 627
    },
    {
      "epoch": 0.7892080821568127,
      "grad_norm": 0.947977203839485,
      "learning_rate": 2.5734538208704197e-06,
      "loss": 0.4787,
      "step": 628
    },
    {
      "epoch": 0.7904647829245783,
      "grad_norm": 0.8656699847159132,
      "learning_rate": 2.5441011986733165e-06,
      "loss": 0.4662,
      "step": 629
    },
    {
      "epoch": 0.791721483692344,
      "grad_norm": 0.8459597720147866,
      "learning_rate": 2.514892518288988e-06,
      "loss": 0.4475,
      "step": 630
    },
    {
      "epoch": 0.7929781844601096,
      "grad_norm": 0.9446896479383777,
      "learning_rate": 2.485828343613288e-06,
      "loss": 0.4766,
      "step": 631
    },
    {
      "epoch": 0.7942348852278752,
      "grad_norm": 0.9122011845063069,
      "learning_rate": 2.456909235752276e-06,
      "loss": 0.4502,
      "step": 632
    },
    {
      "epoch": 0.7954915859956408,
      "grad_norm": 0.9193582934450675,
      "learning_rate": 2.4281357530113804e-06,
      "loss": 0.4823,
      "step": 633
    },
    {
      "epoch": 0.7967482867634065,
      "grad_norm": 0.897269277270419,
      "learning_rate": 2.399508450884631e-06,
      "loss": 0.4513,
      "step": 634
    },
    {
      "epoch": 0.7980049875311721,
      "grad_norm": 0.9475888045070303,
      "learning_rate": 2.3710278820439313e-06,
      "loss": 0.5161,
      "step": 635
    },
    {
      "epoch": 0.7992616882989377,
      "grad_norm": 0.9443257123202231,
      "learning_rate": 2.3426945963283853e-06,
      "loss": 0.486,
      "step": 636
    },
    {
      "epoch": 0.8005183890667034,
      "grad_norm": 0.9502264882194557,
      "learning_rate": 2.3145091407336785e-06,
      "loss": 0.4578,
      "step": 637
    },
    {
      "epoch": 0.801775089834469,
      "grad_norm": 0.9187557661433506,
      "learning_rate": 2.2864720594015288e-06,
      "loss": 0.4871,
      "step": 638
    },
    {
      "epoch": 0.8030317906022346,
      "grad_norm": 0.8862615742754856,
      "learning_rate": 2.2585838936091753e-06,
      "loss": 0.4635,
      "step": 639
    },
    {
      "epoch": 0.8042884913700002,
      "grad_norm": 0.9044746570210405,
      "learning_rate": 2.230845181758928e-06,
      "loss": 0.4614,
      "step": 640
    },
    {
      "epoch": 0.8055451921377659,
      "grad_norm": 0.9371401414038523,
      "learning_rate": 2.2032564593677773e-06,
      "loss": 0.4718,
      "step": 641
    },
    {
      "epoch": 0.8068018929055314,
      "grad_norm": 1.0205326351085469,
      "learning_rate": 2.1758182590570454e-06,
      "loss": 0.4587,
      "step": 642
    },
    {
      "epoch": 0.808058593673297,
      "grad_norm": 0.9391567214691986,
      "learning_rate": 2.148531110542118e-06,
      "loss": 0.4583,
      "step": 643
    },
    {
      "epoch": 0.8093152944410626,
      "grad_norm": 0.9423357541683243,
      "learning_rate": 2.1213955406222076e-06,
      "loss": 0.4564,
      "step": 644
    },
    {
      "epoch": 0.8105719952088283,
      "grad_norm": 0.9170267994353932,
      "learning_rate": 2.09441207317019e-06,
      "loss": 0.4501,
      "step": 645
    },
    {
      "epoch": 0.8118286959765939,
      "grad_norm": 0.9670344205389225,
      "learning_rate": 2.0675812291224796e-06,
      "loss": 0.4827,
      "step": 646
    },
    {
      "epoch": 0.8130853967443595,
      "grad_norm": 0.9406467714039654,
      "learning_rate": 2.0409035264689857e-06,
      "loss": 0.4708,
      "step": 647
    },
    {
      "epoch": 0.8143420975121252,
      "grad_norm": 0.8958190576761381,
      "learning_rate": 2.014379480243105e-06,
      "loss": 0.4483,
      "step": 648
    },
    {
      "epoch": 0.8155987982798908,
      "grad_norm": 0.9488884622008084,
      "learning_rate": 1.988009602511779e-06,
      "loss": 0.4569,
      "step": 649
    },
    {
      "epoch": 0.8168554990476564,
      "grad_norm": 0.9215947064515085,
      "learning_rate": 1.961794402365611e-06,
      "loss": 0.5286,
      "step": 650
    },
    {
      "epoch": 0.8168554990476564,
      "eval_loss": NaN,
      "eval_runtime": 392.1209,
      "eval_samples_per_second": 21.205,
      "eval_steps_per_second": 2.652,
      "step": 650
    },
    {
      "epoch": 0.818112199815422,
      "grad_norm": 0.9209169808681984,
      "learning_rate": 1.935734385909028e-06,
      "loss": 0.4795,
      "step": 651
    },
    {
      "epoch": 0.8193689005831877,
      "grad_norm": 0.9076583048514367,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 0.4711,
      "step": 652
    },
    {
      "epoch": 0.8206256013509533,
      "grad_norm": 0.9912038417618557,
      "learning_rate": 1.8840819134929467e-06,
      "loss": 0.48,
      "step": 653
    },
    {
      "epoch": 0.8218823021187189,
      "grad_norm": 0.9324565329660811,
      "learning_rate": 1.8584904547238214e-06,
      "loss": 0.4387,
      "step": 654
    },
    {
      "epoch": 0.8231390028864846,
      "grad_norm": 0.8864965286423587,
      "learning_rate": 1.8330561740057839e-06,
      "loss": 0.4469,
      "step": 655
    },
    {
      "epoch": 0.8243957036542502,
      "grad_norm": 0.8720461851671827,
      "learning_rate": 1.8077795623670135e-06,
      "loss": 0.4531,
      "step": 656
    },
    {
      "epoch": 0.8256524044220158,
      "grad_norm": 0.8921315350992695,
      "learning_rate": 1.7826611077917843e-06,
      "loss": 0.4797,
      "step": 657
    },
    {
      "epoch": 0.8269091051897814,
      "grad_norm": 0.8844082344199783,
      "learning_rate": 1.757701295211014e-06,
      "loss": 0.4523,
      "step": 658
    },
    {
      "epoch": 0.8281658059575471,
      "grad_norm": 0.9020082915341568,
      "learning_rate": 1.7329006064929232e-06,
      "loss": 0.4772,
      "step": 659
    },
    {
      "epoch": 0.8294225067253127,
      "grad_norm": 0.9058399917219788,
      "learning_rate": 1.7082595204337183e-06,
      "loss": 0.5386,
      "step": 660
    },
    {
      "epoch": 0.8306792074930783,
      "grad_norm": 0.8817763873468203,
      "learning_rate": 1.683778512748362e-06,
      "loss": 0.4663,
      "step": 661
    },
    {
      "epoch": 0.831935908260844,
      "grad_norm": 0.9634025095210257,
      "learning_rate": 1.6594580560613782e-06,
      "loss": 0.4689,
      "step": 662
    },
    {
      "epoch": 0.8331926090286096,
      "grad_norm": 0.9633653565356368,
      "learning_rate": 1.6352986198977327e-06,
      "loss": 0.4667,
      "step": 663
    },
    {
      "epoch": 0.8344493097963752,
      "grad_norm": 0.9487086679856576,
      "learning_rate": 1.6113006706737667e-06,
      "loss": 0.5184,
      "step": 664
    },
    {
      "epoch": 0.8357060105641408,
      "grad_norm": 0.9325953615840198,
      "learning_rate": 1.587464671688187e-06,
      "loss": 0.456,
      "step": 665
    },
    {
      "epoch": 0.8369627113319065,
      "grad_norm": 1.009772295164291,
      "learning_rate": 1.563791083113142e-06,
      "loss": 0.4451,
      "step": 666
    },
    {
      "epoch": 0.8382194120996721,
      "grad_norm": 0.9419871710371429,
      "learning_rate": 1.540280361985308e-06,
      "loss": 0.5302,
      "step": 667
    },
    {
      "epoch": 0.8394761128674377,
      "grad_norm": 0.8754091668537753,
      "learning_rate": 1.5169329621970918e-06,
      "loss": 0.4655,
      "step": 668
    },
    {
      "epoch": 0.8407328136352034,
      "grad_norm": 0.8613931367520573,
      "learning_rate": 1.4937493344878474e-06,
      "loss": 0.63,
      "step": 669
    },
    {
      "epoch": 0.841989514402969,
      "grad_norm": 0.9312238100708667,
      "learning_rate": 1.4707299264351914e-06,
      "loss": 0.5655,
      "step": 670
    },
    {
      "epoch": 0.8432462151707346,
      "grad_norm": 0.9049299425860378,
      "learning_rate": 1.4478751824463543e-06,
      "loss": 0.4651,
      "step": 671
    },
    {
      "epoch": 0.8445029159385002,
      "grad_norm": 0.8788628461504958,
      "learning_rate": 1.4251855437495976e-06,
      "loss": 0.475,
      "step": 672
    },
    {
      "epoch": 0.8457596167062659,
      "grad_norm": 0.8951500164340301,
      "learning_rate": 1.4026614483857037e-06,
      "loss": 0.4673,
      "step": 673
    },
    {
      "epoch": 0.8470163174740315,
      "grad_norm": 0.9244238966775989,
      "learning_rate": 1.3803033311995072e-06,
      "loss": 0.4796,
      "step": 674
    },
    {
      "epoch": 0.8482730182417971,
      "grad_norm": 0.9749389580422814,
      "learning_rate": 1.3581116238315194e-06,
      "loss": 0.4735,
      "step": 675
    },
    {
      "epoch": 0.8495297190095628,
      "grad_norm": 0.936241513202334,
      "learning_rate": 1.336086754709569e-06,
      "loss": 0.4635,
      "step": 676
    },
    {
      "epoch": 0.8507864197773284,
      "grad_norm": 0.9584973374609863,
      "learning_rate": 1.3142291490405568e-06,
      "loss": 0.4638,
      "step": 677
    },
    {
      "epoch": 0.852043120545094,
      "grad_norm": 0.9235602347304942,
      "learning_rate": 1.2925392288022299e-06,
      "loss": 0.4699,
      "step": 678
    },
    {
      "epoch": 0.8532998213128595,
      "grad_norm": 0.8876268215636179,
      "learning_rate": 1.2710174127350362e-06,
      "loss": 0.4681,
      "step": 679
    },
    {
      "epoch": 0.8545565220806252,
      "grad_norm": 0.9354140918132684,
      "learning_rate": 1.2496641163340562e-06,
      "loss": 0.4699,
      "step": 680
    },
    {
      "epoch": 0.8558132228483908,
      "grad_norm": 0.9255534990449884,
      "learning_rate": 1.2284797518409575e-06,
      "loss": 0.4483,
      "step": 681
    },
    {
      "epoch": 0.8570699236161564,
      "grad_norm": 0.9733945197204105,
      "learning_rate": 1.2074647282360573e-06,
      "loss": 0.4697,
      "step": 682
    },
    {
      "epoch": 0.858326624383922,
      "grad_norm": 0.9031964521291095,
      "learning_rate": 1.1866194512304075e-06,
      "loss": 0.4631,
      "step": 683
    },
    {
      "epoch": 0.8595833251516877,
      "grad_norm": 0.8891842214060443,
      "learning_rate": 1.165944323257986e-06,
      "loss": 0.5275,
      "step": 684
    },
    {
      "epoch": 0.8608400259194533,
      "grad_norm": 0.9289352194308863,
      "learning_rate": 1.1454397434679022e-06,
      "loss": 0.4573,
      "step": 685
    },
    {
      "epoch": 0.8620967266872189,
      "grad_norm": 0.9246693948234718,
      "learning_rate": 1.125106107716708e-06,
      "loss": 0.4606,
      "step": 686
    },
    {
      "epoch": 0.8633534274549846,
      "grad_norm": 0.8763495664310694,
      "learning_rate": 1.10494380856075e-06,
      "loss": 0.4315,
      "step": 687
    },
    {
      "epoch": 0.8646101282227502,
      "grad_norm": 0.9677586559163779,
      "learning_rate": 1.0849532352485903e-06,
      "loss": 0.4771,
      "step": 688
    },
    {
      "epoch": 0.8658668289905158,
      "grad_norm": 0.8612887488120702,
      "learning_rate": 1.0651347737134965e-06,
      "loss": 0.4706,
      "step": 689
    },
    {
      "epoch": 0.8671235297582814,
      "grad_norm": 0.8842124304281852,
      "learning_rate": 1.0454888065659775e-06,
      "loss": 0.4548,
      "step": 690
    },
    {
      "epoch": 0.8683802305260471,
      "grad_norm": 0.9277463249641559,
      "learning_rate": 1.0260157130864178e-06,
      "loss": 0.4567,
      "step": 691
    },
    {
      "epoch": 0.8696369312938127,
      "grad_norm": 0.8437870865194692,
      "learning_rate": 1.0067158692177325e-06,
      "loss": 0.4597,
      "step": 692
    },
    {
      "epoch": 0.8708936320615783,
      "grad_norm": 0.8643510843583194,
      "learning_rate": 9.87589647558135e-07,
      "loss": 0.4256,
      "step": 693
    },
    {
      "epoch": 0.872150332829344,
      "grad_norm": 0.9295154059632877,
      "learning_rate": 9.686374173539147e-07,
      "loss": 0.4861,
      "step": 694
    },
    {
      "epoch": 0.8734070335971096,
      "grad_norm": 0.9448636463228528,
      "learning_rate": 9.49859544492332e-07,
      "loss": 0.4711,
      "step": 695
    },
    {
      "epoch": 0.8746637343648752,
      "grad_norm": 0.9093250850860881,
      "learning_rate": 9.312563914945461e-07,
      "loss": 0.4696,
      "step": 696
    },
    {
      "epoch": 0.8759204351326408,
      "grad_norm": 0.9002792388799274,
      "learning_rate": 9.128283175086106e-07,
      "loss": 0.4656,
      "step": 697
    },
    {
      "epoch": 0.8771771359004065,
      "grad_norm": 0.8559481875479032,
      "learning_rate": 8.945756783025528e-07,
      "loss": 0.4335,
      "step": 698
    },
    {
      "epoch": 0.8784338366681721,
      "grad_norm": 0.8796349450465737,
      "learning_rate": 8.76498826257488e-07,
      "loss": 0.4561,
      "step": 699
    },
    {
      "epoch": 0.8796905374359377,
      "grad_norm": 0.8726954083378391,
      "learning_rate": 8.585981103608343e-07,
      "loss": 0.4993,
      "step": 700
    },
    {
      "epoch": 0.8796905374359377,
      "eval_loss": NaN,
      "eval_runtime": 391.2376,
      "eval_samples_per_second": 21.253,
      "eval_steps_per_second": 2.658,
      "step": 700
    },
    {
      "epoch": 0.8809472382037034,
      "grad_norm": 1.4368360063954035,
      "learning_rate": 8.40873876199565e-07,
      "loss": 0.4788,
      "step": 701
    },
    {
      "epoch": 0.882203938971469,
      "grad_norm": 0.9404327931258755,
      "learning_rate": 8.233264659535367e-07,
      "loss": 0.4502,
      "step": 702
    },
    {
      "epoch": 0.8834606397392346,
      "grad_norm": 0.8946470160723485,
      "learning_rate": 8.059562183888903e-07,
      "loss": 0.4608,
      "step": 703
    },
    {
      "epoch": 0.8847173405070002,
      "grad_norm": 0.9041054772329139,
      "learning_rate": 7.887634688515e-07,
      "loss": 0.4506,
      "step": 704
    },
    {
      "epoch": 0.8859740412747659,
      "grad_norm": 0.8915805709724289,
      "learning_rate": 7.71748549260507e-07,
      "loss": 0.4424,
      "step": 705
    },
    {
      "epoch": 0.8872307420425315,
      "grad_norm": 0.9307904793059376,
      "learning_rate": 7.549117881019141e-07,
      "loss": 0.4603,
      "step": 706
    },
    {
      "epoch": 0.8884874428102971,
      "grad_norm": 0.9166282118331757,
      "learning_rate": 7.382535104222366e-07,
      "loss": 0.4669,
      "step": 707
    },
    {
      "epoch": 0.8897441435780628,
      "grad_norm": 0.9726682302204435,
      "learning_rate": 7.21774037822226e-07,
      "loss": 0.4575,
      "step": 708
    },
    {
      "epoch": 0.8910008443458284,
      "grad_norm": 0.9024738036393012,
      "learning_rate": 7.054736884506718e-07,
      "loss": 0.4584,
      "step": 709
    },
    {
      "epoch": 0.892257545113594,
      "grad_norm": 0.9450717020332904,
      "learning_rate": 6.8935277699825e-07,
      "loss": 0.4478,
      "step": 710
    },
    {
      "epoch": 0.8935142458813596,
      "grad_norm": 0.8734170696346301,
      "learning_rate": 6.734116146914516e-07,
      "loss": 0.4811,
      "step": 711
    },
    {
      "epoch": 0.8947709466491253,
      "grad_norm": 0.9009909790129396,
      "learning_rate": 6.576505092865748e-07,
      "loss": 0.4695,
      "step": 712
    },
    {
      "epoch": 0.8960276474168909,
      "grad_norm": 0.9465203253593445,
      "learning_rate": 6.420697650637753e-07,
      "loss": 0.4469,
      "step": 713
    },
    {
      "epoch": 0.8972843481846565,
      "grad_norm": 0.9084056997490763,
      "learning_rate": 6.266696828212071e-07,
      "loss": 0.4467,
      "step": 714
    },
    {
      "epoch": 0.898541048952422,
      "grad_norm": 0.9510351940546182,
      "learning_rate": 6.114505598692011e-07,
      "loss": 0.4538,
      "step": 715
    },
    {
      "epoch": 0.8997977497201877,
      "grad_norm": 0.8690165913406015,
      "learning_rate": 5.964126900245359e-07,
      "loss": 0.4542,
      "step": 716
    },
    {
      "epoch": 0.9010544504879533,
      "grad_norm": 0.8525566457571607,
      "learning_rate": 5.815563636047539e-07,
      "loss": 0.4526,
      "step": 717
    },
    {
      "epoch": 0.9023111512557189,
      "grad_norm": 0.9287838751774835,
      "learning_rate": 5.668818674225684e-07,
      "loss": 0.4444,
      "step": 718
    },
    {
      "epoch": 0.9035678520234846,
      "grad_norm": 0.960597993996023,
      "learning_rate": 5.523894847803235e-07,
      "loss": 0.4688,
      "step": 719
    },
    {
      "epoch": 0.9048245527912502,
      "grad_norm": 0.8867015416832417,
      "learning_rate": 5.380794954645141e-07,
      "loss": 0.4369,
      "step": 720
    },
    {
      "epoch": 0.9060812535590158,
      "grad_norm": 0.9250364567041895,
      "learning_rate": 5.23952175740402e-07,
      "loss": 0.4728,
      "step": 721
    },
    {
      "epoch": 0.9073379543267814,
      "grad_norm": 0.8538358598265039,
      "learning_rate": 5.100077983466667e-07,
      "loss": 0.454,
      "step": 722
    },
    {
      "epoch": 0.9085946550945471,
      "grad_norm": 0.8588765866461067,
      "learning_rate": 4.962466324901483e-07,
      "loss": 0.4488,
      "step": 723
    },
    {
      "epoch": 0.9098513558623127,
      "grad_norm": 0.8879641890521957,
      "learning_rate": 4.826689438406495e-07,
      "loss": 0.4538,
      "step": 724
    },
    {
      "epoch": 0.9111080566300783,
      "grad_norm": 0.868954790800622,
      "learning_rate": 4.6927499452580574e-07,
      "loss": 0.4258,
      "step": 725
    },
    {
      "epoch": 0.912364757397844,
      "grad_norm": 0.869194697723244,
      "learning_rate": 4.5606504312602384e-07,
      "loss": 0.4428,
      "step": 726
    },
    {
      "epoch": 0.9136214581656096,
      "grad_norm": 0.9689587398952784,
      "learning_rate": 4.4303934466948804e-07,
      "loss": 0.4461,
      "step": 727
    },
    {
      "epoch": 0.9148781589333752,
      "grad_norm": 0.9714671146836645,
      "learning_rate": 4.3019815062724567e-07,
      "loss": 0.4523,
      "step": 728
    },
    {
      "epoch": 0.9161348597011408,
      "grad_norm": 0.9098783404381591,
      "learning_rate": 4.1754170890833777e-07,
      "loss": 0.5114,
      "step": 729
    },
    {
      "epoch": 0.9173915604689065,
      "grad_norm": 0.903763846717378,
      "learning_rate": 4.0507026385502747e-07,
      "loss": 0.4558,
      "step": 730
    },
    {
      "epoch": 0.9186482612366721,
      "grad_norm": 0.8589002511680877,
      "learning_rate": 3.9278405623806914e-07,
      "loss": 0.4463,
      "step": 731
    },
    {
      "epoch": 0.9199049620044377,
      "grad_norm": 0.9149570489401863,
      "learning_rate": 3.806833232520746e-07,
      "loss": 0.4665,
      "step": 732
    },
    {
      "epoch": 0.9211616627722033,
      "grad_norm": 0.857139001990913,
      "learning_rate": 3.687682985109209e-07,
      "loss": 0.4847,
      "step": 733
    },
    {
      "epoch": 0.922418363539969,
      "grad_norm": 0.9093058792535011,
      "learning_rate": 3.5703921204324863e-07,
      "loss": 0.5461,
      "step": 734
    },
    {
      "epoch": 0.9236750643077346,
      "grad_norm": 0.8979631581554675,
      "learning_rate": 3.454962902880199e-07,
      "loss": 0.4589,
      "step": 735
    },
    {
      "epoch": 0.9249317650755002,
      "grad_norm": 0.8828698198732804,
      "learning_rate": 3.3413975609013713e-07,
      "loss": 0.4622,
      "step": 736
    },
    {
      "epoch": 0.9261884658432659,
      "grad_norm": 0.8945978464715129,
      "learning_rate": 3.2296982869616134e-07,
      "loss": 0.4247,
      "step": 737
    },
    {
      "epoch": 0.9274451666110315,
      "grad_norm": 0.8897356645887511,
      "learning_rate": 3.1198672375005403e-07,
      "loss": 0.465,
      "step": 738
    },
    {
      "epoch": 0.9287018673787971,
      "grad_norm": 0.8698017477642928,
      "learning_rate": 3.0119065328903517e-07,
      "loss": 0.4426,
      "step": 739
    },
    {
      "epoch": 0.9299585681465627,
      "grad_norm": 0.8856161042535935,
      "learning_rate": 2.905818257394799e-07,
      "loss": 0.4489,
      "step": 740
    },
    {
      "epoch": 0.9312152689143284,
      "grad_norm": 0.8551132648021337,
      "learning_rate": 2.801604459128926e-07,
      "loss": 0.4546,
      "step": 741
    },
    {
      "epoch": 0.932471969682094,
      "grad_norm": 0.8755685457795177,
      "learning_rate": 2.6992671500196134e-07,
      "loss": 0.4767,
      "step": 742
    },
    {
      "epoch": 0.9337286704498596,
      "grad_norm": 1.0076154176090533,
      "learning_rate": 2.5988083057666534e-07,
      "loss": 0.5176,
      "step": 743
    },
    {
      "epoch": 0.9349853712176253,
      "grad_norm": 0.8773948389601972,
      "learning_rate": 2.5002298658046484e-07,
      "loss": 0.4665,
      "step": 744
    },
    {
      "epoch": 0.9362420719853909,
      "grad_norm": 0.949607330031333,
      "learning_rate": 2.4035337332655504e-07,
      "loss": 0.4865,
      "step": 745
    },
    {
      "epoch": 0.9374987727531565,
      "grad_norm": 0.8727367626946688,
      "learning_rate": 2.308721774941991e-07,
      "loss": 0.4755,
      "step": 746
    },
    {
      "epoch": 0.9387554735209221,
      "grad_norm": 0.950145974990549,
      "learning_rate": 2.2157958212510877e-07,
      "loss": 0.4658,
      "step": 747
    },
    {
      "epoch": 0.9400121742886878,
      "grad_norm": 0.8949527330544057,
      "learning_rate": 2.124757666199273e-07,
      "loss": 0.4715,
      "step": 748
    },
    {
      "epoch": 0.9412688750564534,
      "grad_norm": 0.857039311943978,
      "learning_rate": 2.035609067347566e-07,
      "loss": 0.4846,
      "step": 749
    },
    {
      "epoch": 0.942525575824219,
      "grad_norm": 0.9246764854504824,
      "learning_rate": 1.9483517457776436e-07,
      "loss": 0.5387,
      "step": 750
    },
    {
      "epoch": 0.942525575824219,
      "eval_loss": NaN,
      "eval_runtime": 392.0537,
      "eval_samples_per_second": 21.209,
      "eval_steps_per_second": 2.653,
      "step": 750
    },
    {
      "epoch": 0.9437822765919847,
      "grad_norm": 0.9246699749677241,
      "learning_rate": 1.8629873860586567e-07,
      "loss": 0.4915,
      "step": 751
    },
    {
      "epoch": 0.9450389773597502,
      "grad_norm": 0.9273150008131176,
      "learning_rate": 1.7795176362146783e-07,
      "loss": 0.4394,
      "step": 752
    },
    {
      "epoch": 0.9462956781275158,
      "grad_norm": 0.8721007270250941,
      "learning_rate": 1.6979441076928837e-07,
      "loss": 0.5125,
      "step": 753
    },
    {
      "epoch": 0.9475523788952814,
      "grad_norm": 0.8233991769635042,
      "learning_rate": 1.6182683753324435e-07,
      "loss": 0.4622,
      "step": 754
    },
    {
      "epoch": 0.9488090796630471,
      "grad_norm": 0.88887926972337,
      "learning_rate": 1.5404919773341576e-07,
      "loss": 0.46,
      "step": 755
    },
    {
      "epoch": 0.9500657804308127,
      "grad_norm": 0.9151783514520999,
      "learning_rate": 1.464616415230702e-07,
      "loss": 0.4769,
      "step": 756
    },
    {
      "epoch": 0.9513224811985783,
      "grad_norm": 0.9233338402724911,
      "learning_rate": 1.3906431538576626e-07,
      "loss": 0.4511,
      "step": 757
    },
    {
      "epoch": 0.952579181966344,
      "grad_norm": 0.876720746013767,
      "learning_rate": 1.3185736213252808e-07,
      "loss": 0.4623,
      "step": 758
    },
    {
      "epoch": 0.9538358827341096,
      "grad_norm": 0.8808110259800377,
      "learning_rate": 1.2484092089908307e-07,
      "loss": 0.455,
      "step": 759
    },
    {
      "epoch": 0.9550925835018752,
      "grad_norm": 0.9127364361814908,
      "learning_rate": 1.1801512714318286e-07,
      "loss": 0.4659,
      "step": 760
    },
    {
      "epoch": 0.9563492842696408,
      "grad_norm": 0.9250866501406244,
      "learning_rate": 1.113801126419789e-07,
      "loss": 0.4097,
      "step": 761
    },
    {
      "epoch": 0.9576059850374065,
      "grad_norm": 0.9039383706969123,
      "learning_rate": 1.0493600548948879e-07,
      "loss": 0.4372,
      "step": 762
    },
    {
      "epoch": 0.9588626858051721,
      "grad_norm": 0.9023237019743435,
      "learning_rate": 9.8682930094115e-08,
      "loss": 0.4524,
      "step": 763
    },
    {
      "epoch": 0.9601193865729377,
      "grad_norm": 0.9011103800480463,
      "learning_rate": 9.262100717624678e-08,
      "loss": 0.4342,
      "step": 764
    },
    {
      "epoch": 0.9613760873407033,
      "grad_norm": 0.9408044434789575,
      "learning_rate": 8.675035376593088e-08,
      "loss": 0.4699,
      "step": 765
    },
    {
      "epoch": 0.962632788108469,
      "grad_norm": 0.8157071127061982,
      "learning_rate": 8.107108320060675e-08,
      "loss": 0.4388,
      "step": 766
    },
    {
      "epoch": 0.9638894888762346,
      "grad_norm": 0.9614204495709833,
      "learning_rate": 7.558330512292378e-08,
      "loss": 0.5011,
      "step": 767
    },
    {
      "epoch": 0.9651461896440002,
      "grad_norm": 0.9164749653087414,
      "learning_rate": 7.028712547862526e-08,
      "loss": 0.4922,
      "step": 768
    },
    {
      "epoch": 0.9664028904117659,
      "grad_norm": 0.8941273006248021,
      "learning_rate": 6.51826465144978e-08,
      "loss": 0.5093,
      "step": 769
    },
    {
      "epoch": 0.9676595911795315,
      "grad_norm": 0.9345588962411722,
      "learning_rate": 6.026996677640062e-08,
      "loss": 0.4654,
      "step": 770
    },
    {
      "epoch": 0.9689162919472971,
      "grad_norm": 0.8714785559856224,
      "learning_rate": 5.5549181107362734e-08,
      "loss": 0.4459,
      "step": 771
    },
    {
      "epoch": 0.9701729927150627,
      "grad_norm": 0.8661748110904719,
      "learning_rate": 5.102038064575099e-08,
      "loss": 0.426,
      "step": 772
    },
    {
      "epoch": 0.9714296934828284,
      "grad_norm": 0.8998862817234337,
      "learning_rate": 4.6683652823513725e-08,
      "loss": 0.4808,
      "step": 773
    },
    {
      "epoch": 0.972686394250594,
      "grad_norm": 0.9253080744252631,
      "learning_rate": 4.253908136448881e-08,
      "loss": 0.4777,
      "step": 774
    },
    {
      "epoch": 0.9739430950183596,
      "grad_norm": 0.8884730525355212,
      "learning_rate": 3.858674628278825e-08,
      "loss": 0.4445,
      "step": 775
    },
    {
      "epoch": 0.9751997957861253,
      "grad_norm": 0.8920492529443076,
      "learning_rate": 3.482672388125719e-08,
      "loss": 0.5067,
      "step": 776
    },
    {
      "epoch": 0.9764564965538909,
      "grad_norm": 0.913098536113785,
      "learning_rate": 3.125908674999289e-08,
      "loss": 0.4704,
      "step": 777
    },
    {
      "epoch": 0.9777131973216565,
      "grad_norm": 0.8585074814418806,
      "learning_rate": 2.7883903764953647e-08,
      "loss": 0.4383,
      "step": 778
    },
    {
      "epoch": 0.9789698980894221,
      "grad_norm": 0.8563259132871073,
      "learning_rate": 2.470124008661978e-08,
      "loss": 0.486,
      "step": 779
    },
    {
      "epoch": 0.9802265988571878,
      "grad_norm": 1.0110036318343043,
      "learning_rate": 2.171115715874139e-08,
      "loss": 0.4784,
      "step": 780
    },
    {
      "epoch": 0.9814832996249534,
      "grad_norm": 0.9352424779414596,
      "learning_rate": 1.8913712707149255e-08,
      "loss": 0.4732,
      "step": 781
    },
    {
      "epoch": 0.982740000392719,
      "grad_norm": 0.904141538390942,
      "learning_rate": 1.630896073864352e-08,
      "loss": 0.483,
      "step": 782
    },
    {
      "epoch": 0.9839967011604847,
      "grad_norm": 0.8991415167948376,
      "learning_rate": 1.3896951539945635e-08,
      "loss": 0.467,
      "step": 783
    },
    {
      "epoch": 0.9852534019282503,
      "grad_norm": 0.8724840641479233,
      "learning_rate": 1.1677731676733584e-08,
      "loss": 0.4614,
      "step": 784
    },
    {
      "epoch": 0.9865101026960159,
      "grad_norm": 0.8862179253481299,
      "learning_rate": 9.651343992740369e-09,
      "loss": 0.4452,
      "step": 785
    },
    {
      "epoch": 0.9877668034637815,
      "grad_norm": 0.877231477260857,
      "learning_rate": 7.817827608924689e-09,
      "loss": 0.4913,
      "step": 786
    },
    {
      "epoch": 0.9890235042315472,
      "grad_norm": 0.9256633248853225,
      "learning_rate": 6.1772179227181926e-09,
      "loss": 0.4854,
      "step": 787
    },
    {
      "epoch": 0.9902802049993128,
      "grad_norm": 0.8460307202589556,
      "learning_rate": 4.7295466073427055e-09,
      "loss": 0.4562,
      "step": 788
    },
    {
      "epoch": 0.9915369057670783,
      "grad_norm": 0.9076188371683147,
      "learning_rate": 3.474841611197377e-09,
      "loss": 0.4736,
      "step": 789
    },
    {
      "epoch": 0.9927936065348439,
      "grad_norm": 0.8533095890208698,
      "learning_rate": 2.4131271573191172e-09,
      "loss": 0.452,
      "step": 790
    },
    {
      "epoch": 0.9940503073026096,
      "grad_norm": 0.8331866413387022,
      "learning_rate": 1.5444237429140806e-09,
      "loss": 0.4387,
      "step": 791
    },
    {
      "epoch": 0.9953070080703752,
      "grad_norm": 0.8888758833913929,
      "learning_rate": 8.687481389657582e-10,
      "loss": 0.4634,
      "step": 792
    },
    {
      "epoch": 0.9965637088381408,
      "grad_norm": 0.9295696536473508,
      "learning_rate": 3.861133899063507e-10,
      "loss": 0.4674,
      "step": 793
    },
    {
      "epoch": 0.9978204096059065,
      "grad_norm": 0.9051031551266895,
      "learning_rate": 9.652881336696951e-11,
      "loss": 0.4903,
      "step": 794
    },
    {
      "epoch": 0.9990771103736721,
      "grad_norm": 0.9088993808171332,
      "learning_rate": 0.0,
      "loss": 0.4562,
      "step": 795
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 795,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1331628437667840.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}