{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 231,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 3.7534801519593604,
      "learning_rate": 8.333333333333333e-07,
      "loss": 1.4653,
      "step": 1
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 3.7280354025925315,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 1.4506,
      "step": 2
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 3.5932332342570357,
      "learning_rate": 2.5e-06,
      "loss": 1.4357,
      "step": 3
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 3.0154735438586653,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.4393,
      "step": 4
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 2.013171058733714,
      "learning_rate": 4.166666666666667e-06,
      "loss": 1.4166,
      "step": 5
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 3.8256853010163394,
      "learning_rate": 5e-06,
      "loss": 1.371,
      "step": 6
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 3.598730580451478,
      "learning_rate": 5.833333333333334e-06,
      "loss": 1.3857,
      "step": 7
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 3.3412845505760607,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.376,
      "step": 8
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 2.9232898010326602,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.3148,
      "step": 9
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 1.8840862505972766,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.273,
      "step": 10
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.392155364549258,
      "learning_rate": 9.166666666666666e-06,
      "loss": 1.273,
      "step": 11
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 1.8296739180191237,
      "learning_rate": 1e-05,
      "loss": 1.268,
      "step": 12
    },
    {
      "epoch": 0.3939393939393939,
      "grad_norm": 1.7210931776898732,
      "learning_rate": 1.0833333333333334e-05,
      "loss": 1.2441,
      "step": 13
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 1.6440952005671419,
      "learning_rate": 1.1666666666666668e-05,
      "loss": 1.2842,
      "step": 14
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 1.3129392501749428,
      "learning_rate": 1.25e-05,
      "loss": 1.1896,
      "step": 15
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 1.2437943533442561,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 1.1817,
      "step": 16
    },
    {
      "epoch": 0.5151515151515151,
      "grad_norm": 1.6970895963146584,
      "learning_rate": 1.416666666666667e-05,
      "loss": 1.1676,
      "step": 17
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 1.4036369489768061,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.2177,
      "step": 18
    },
    {
      "epoch": 0.5757575757575758,
      "grad_norm": 1.2485425864748194,
      "learning_rate": 1.5833333333333333e-05,
      "loss": 1.2119,
      "step": 19
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.7621345658061873,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.189,
      "step": 20
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 1.095009224436933,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 1.1704,
      "step": 21
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.535866920691866,
      "learning_rate": 1.8333333333333333e-05,
      "loss": 1.2007,
      "step": 22
    },
    {
      "epoch": 0.696969696969697,
      "grad_norm": 1.3676985370581474,
      "learning_rate": 1.916666666666667e-05,
      "loss": 1.226,
      "step": 23
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 1.3598557410740304,
      "learning_rate": 2e-05,
      "loss": 1.1348,
      "step": 24
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 1.3324658719395368,
      "learning_rate": 1.999884834944106e-05,
      "loss": 1.1591,
      "step": 25
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 1.2615631380454355,
      "learning_rate": 1.9995393663024054e-05,
      "loss": 1.1753,
      "step": 26
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 1.0241029740978715,
      "learning_rate": 1.9989636736467278e-05,
      "loss": 1.1406,
      "step": 27
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 1.3626314910300852,
      "learning_rate": 1.9981578895764272e-05,
      "loss": 1.143,
      "step": 28
    },
    {
      "epoch": 0.8787878787878788,
      "grad_norm": 1.2966710472786716,
      "learning_rate": 1.9971221996878395e-05,
      "loss": 1.1353,
      "step": 29
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 1.0450748303364155,
      "learning_rate": 1.9958568425315316e-05,
      "loss": 1.1482,
      "step": 30
    },
    {
      "epoch": 0.9393939393939394,
      "grad_norm": 1.0253321834429778,
      "learning_rate": 1.9943621095573588e-05,
      "loss": 1.1704,
      "step": 31
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 1.1597022794746223,
      "learning_rate": 1.9926383450473344e-05,
      "loss": 1.1227,
      "step": 32
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9818517160172446,
      "learning_rate": 1.9906859460363307e-05,
      "loss": 1.1181,
      "step": 33
    },
    {
      "epoch": 1.0303030303030303,
      "grad_norm": 1.2203351707581194,
      "learning_rate": 1.9885053622206305e-05,
      "loss": 1.1038,
      "step": 34
    },
    {
      "epoch": 1.0606060606060606,
      "grad_norm": 0.8164521351807881,
      "learning_rate": 1.986097095854347e-05,
      "loss": 1.1224,
      "step": 35
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 1.0332875375836503,
      "learning_rate": 1.9834617016337424e-05,
      "loss": 1.0862,
      "step": 36
    },
    {
      "epoch": 1.121212121212121,
      "grad_norm": 1.1444300521111264,
      "learning_rate": 1.9805997865694616e-05,
      "loss": 1.1256,
      "step": 37
    },
    {
      "epoch": 1.1515151515151516,
      "grad_norm": 1.0516200340358717,
      "learning_rate": 1.9775120098467212e-05,
      "loss": 1.0576,
      "step": 38
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 1.0619889836423235,
      "learning_rate": 1.9741990826734793e-05,
      "loss": 1.0839,
      "step": 39
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 0.7339593543024099,
      "learning_rate": 1.970661768116622e-05,
      "loss": 1.0922,
      "step": 40
    },
    {
      "epoch": 1.2424242424242424,
      "grad_norm": 0.7449027025719063,
      "learning_rate": 1.9669008809262064e-05,
      "loss": 1.0906,
      "step": 41
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 0.7878491686848133,
      "learning_rate": 1.9629172873477995e-05,
      "loss": 1.0525,
      "step": 42
    },
    {
      "epoch": 1.303030303030303,
      "grad_norm": 0.8253942516053946,
      "learning_rate": 1.9587119049229558e-05,
      "loss": 1.1174,
      "step": 43
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.837890811618985,
      "learning_rate": 1.954285702277879e-05,
      "loss": 1.0749,
      "step": 44
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.803417169311157,
      "learning_rate": 1.9496396989003195e-05,
      "loss": 1.0412,
      "step": 45
    },
    {
      "epoch": 1.393939393939394,
      "grad_norm": 0.7241352107388317,
      "learning_rate": 1.944774964904754e-05,
      "loss": 1.0468,
      "step": 46
    },
    {
      "epoch": 1.4242424242424243,
      "grad_norm": 0.6967732978695761,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 1.0741,
      "step": 47
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.8011299281904884,
      "learning_rate": 1.9343938371606714e-05,
      "loss": 1.0601,
      "step": 48
    },
    {
      "epoch": 1.4848484848484849,
      "grad_norm": 1.030205010857351,
      "learning_rate": 1.9288798344984673e-05,
      "loss": 1.0525,
      "step": 49
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 1.360503951653952,
      "learning_rate": 1.9231518828401458e-05,
      "loss": 1.0088,
      "step": 50
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 0.8273495047388694,
      "learning_rate": 1.917211301505453e-05,
      "loss": 1.0604,
      "step": 51
    },
    {
      "epoch": 1.5757575757575757,
      "grad_norm": 0.739961928668185,
      "learning_rate": 1.911059458789152e-05,
      "loss": 1.0258,
      "step": 52
    },
    {
      "epoch": 1.606060606060606,
      "grad_norm": 0.8137123285238224,
      "learning_rate": 1.9046977716458627e-05,
      "loss": 1.0711,
      "step": 53
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.752395472391603,
      "learning_rate": 1.8981277053636963e-05,
      "loss": 1.0706,
      "step": 54
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.7195979175801954,
      "learning_rate": 1.891350773226754e-05,
      "loss": 1.0282,
      "step": 55
    },
    {
      "epoch": 1.696969696969697,
      "grad_norm": 0.8569717777088246,
      "learning_rate": 1.8843685361665724e-05,
      "loss": 1.0789,
      "step": 56
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 0.9225329838257503,
      "learning_rate": 1.8771826024025944e-05,
      "loss": 1.0095,
      "step": 57
    },
    {
      "epoch": 1.7575757575757576,
      "grad_norm": 0.8347374278004095,
      "learning_rate": 1.8697946270717468e-05,
      "loss": 1.0852,
      "step": 58
    },
    {
      "epoch": 1.7878787878787878,
      "grad_norm": 0.7056208620119615,
      "learning_rate": 1.8622063118472135e-05,
      "loss": 1.0375,
      "step": 59
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.633739244615503,
      "learning_rate": 1.8544194045464888e-05,
      "loss": 1.0488,
      "step": 60
    },
    {
      "epoch": 1.8484848484848486,
      "grad_norm": 0.9603071854776339,
      "learning_rate": 1.8464356987288012e-05,
      "loss": 1.0381,
      "step": 61
    },
    {
      "epoch": 1.878787878787879,
      "grad_norm": 1.313352604898714,
      "learning_rate": 1.8382570332820045e-05,
      "loss": 1.0452,
      "step": 62
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 0.6953628804372607,
      "learning_rate": 1.8298852919990254e-05,
      "loss": 1.0504,
      "step": 63
    },
    {
      "epoch": 1.9393939393939394,
      "grad_norm": 0.9890364492503796,
      "learning_rate": 1.821322403143969e-05,
      "loss": 1.0912,
      "step": 64
    },
    {
      "epoch": 1.9696969696969697,
      "grad_norm": 1.0546358199194728,
      "learning_rate": 1.812570339007983e-05,
      "loss": 1.0467,
      "step": 65
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9107247102190045,
      "learning_rate": 1.8036311154549783e-05,
      "loss": 1.0572,
      "step": 66
    },
    {
      "epoch": 2.0303030303030303,
      "grad_norm": 1.3313691563894987,
      "learning_rate": 1.7945067914573147e-05,
      "loss": 1.0101,
      "step": 67
    },
    {
      "epoch": 2.0606060606060606,
      "grad_norm": 0.8157507572511916,
      "learning_rate": 1.7851994686215592e-05,
      "loss": 1.0077,
      "step": 68
    },
    {
      "epoch": 2.090909090909091,
      "grad_norm": 1.7614606198798635,
      "learning_rate": 1.77571129070442e-05,
      "loss": 0.9905,
      "step": 69
    },
    {
      "epoch": 2.121212121212121,
      "grad_norm": 1.0028456150188514,
      "learning_rate": 1.766044443118978e-05,
      "loss": 0.9417,
      "step": 70
    },
    {
      "epoch": 2.1515151515151514,
      "grad_norm": 1.1688264116388754,
      "learning_rate": 1.7562011524313187e-05,
      "loss": 1.0185,
      "step": 71
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 1.0978225448452226,
      "learning_rate": 1.7461836858476858e-05,
      "loss": 0.9874,
      "step": 72
    },
    {
      "epoch": 2.212121212121212,
      "grad_norm": 0.9769785456244791,
      "learning_rate": 1.7359943506922775e-05,
      "loss": 0.975,
      "step": 73
    },
    {
      "epoch": 2.242424242424242,
      "grad_norm": 0.8903933383299362,
      "learning_rate": 1.725635493875799e-05,
      "loss": 0.9613,
      "step": 74
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 0.8917713530223099,
      "learning_rate": 1.7151095013548996e-05,
      "loss": 0.966,
      "step": 75
    },
    {
      "epoch": 2.303030303030303,
      "grad_norm": 1.1156632285783152,
      "learning_rate": 1.7044187975826126e-05,
      "loss": 0.9915,
      "step": 76
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 1.0239381971186403,
      "learning_rate": 1.693565844949933e-05,
      "loss": 0.9652,
      "step": 77
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 0.9934135933686126,
      "learning_rate": 1.6825531432186545e-05,
      "loss": 0.9438,
      "step": 78
    },
    {
      "epoch": 2.393939393939394,
      "grad_norm": 0.740253946637632,
      "learning_rate": 1.671383228945597e-05,
      "loss": 0.9774,
      "step": 79
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 0.7810207175331545,
      "learning_rate": 1.6600586748983642e-05,
      "loss": 0.9898,
      "step": 80
    },
    {
      "epoch": 2.4545454545454546,
      "grad_norm": 0.7087847965812841,
      "learning_rate": 1.648582089462756e-05,
      "loss": 0.9643,
      "step": 81
    },
    {
      "epoch": 2.484848484848485,
      "grad_norm": 0.8877841074351782,
      "learning_rate": 1.6369561160419783e-05,
      "loss": 0.9474,
      "step": 82
    },
    {
      "epoch": 2.515151515151515,
      "grad_norm": 0.9995781065101929,
      "learning_rate": 1.625183432447789e-05,
      "loss": 0.9831,
      "step": 83
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 0.7357590902785535,
      "learning_rate": 1.6132667502837164e-05,
      "loss": 0.9423,
      "step": 84
    },
    {
      "epoch": 2.5757575757575757,
      "grad_norm": 0.5927012422452901,
      "learning_rate": 1.6012088143204953e-05,
      "loss": 0.9717,
      "step": 85
    },
    {
      "epoch": 2.606060606060606,
      "grad_norm": 0.7725169251679959,
      "learning_rate": 1.589012401863864e-05,
      "loss": 0.969,
      "step": 86
    },
    {
      "epoch": 2.6363636363636362,
      "grad_norm": 0.8390116446417146,
      "learning_rate": 1.5766803221148676e-05,
      "loss": 0.9753,
      "step": 87
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.6955660637034465,
      "learning_rate": 1.5642154155228124e-05,
      "loss": 0.9813,
      "step": 88
    },
    {
      "epoch": 2.6969696969696972,
      "grad_norm": 0.652317970033698,
      "learning_rate": 1.5516205531310272e-05,
      "loss": 0.986,
      "step": 89
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 0.9163768562042793,
      "learning_rate": 1.538898635915576e-05,
      "loss": 0.9788,
      "step": 90
    },
    {
      "epoch": 2.757575757575758,
      "grad_norm": 0.9755867476029597,
      "learning_rate": 1.526052594117071e-05,
      "loss": 0.9963,
      "step": 91
    },
    {
      "epoch": 2.787878787878788,
      "grad_norm": 0.7979637900804633,
      "learning_rate": 1.513085386565758e-05,
      "loss": 0.8987,
      "step": 92
    },
    {
      "epoch": 2.8181818181818183,
      "grad_norm": 0.6047746764213806,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.9562,
      "step": 93
    },
    {
      "epoch": 2.8484848484848486,
      "grad_norm": 0.7004229678113894,
      "learning_rate": 1.4867994483783485e-05,
      "loss": 0.9574,
      "step": 94
    },
    {
      "epoch": 2.878787878787879,
      "grad_norm": 0.6634250338162349,
      "learning_rate": 1.4734867721853341e-05,
      "loss": 0.9354,
      "step": 95
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.6098329273475578,
      "learning_rate": 1.4600650377311523e-05,
      "loss": 1.0021,
      "step": 96
    },
    {
      "epoch": 2.9393939393939394,
      "grad_norm": 0.6634799890984943,
      "learning_rate": 1.4465373364454001e-05,
      "loss": 0.9903,
      "step": 97
    },
    {
      "epoch": 2.9696969696969697,
      "grad_norm": 0.648335744657684,
      "learning_rate": 1.4329067841650274e-05,
      "loss": 0.9815,
      "step": 98
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.6123865941264336,
      "learning_rate": 1.4191765204166643e-05,
      "loss": 0.9748,
      "step": 99
    },
    {
      "epoch": 3.0303030303030303,
      "grad_norm": 0.8870057580728834,
      "learning_rate": 1.4053497076934948e-05,
      "loss": 0.8943,
      "step": 100
    },
    {
      "epoch": 3.0606060606060606,
      "grad_norm": 1.043019776302281,
      "learning_rate": 1.3914295307268396e-05,
      "loss": 0.8922,
      "step": 101
    },
    {
      "epoch": 3.090909090909091,
      "grad_norm": 1.0097389292377588,
      "learning_rate": 1.3774191957526144e-05,
      "loss": 0.9181,
      "step": 102
    },
    {
      "epoch": 3.121212121212121,
      "grad_norm": 0.8023572741366075,
      "learning_rate": 1.3633219297728415e-05,
      "loss": 0.9023,
      "step": 103
    },
    {
      "epoch": 3.1515151515151514,
      "grad_norm": 0.8599823129094757,
      "learning_rate": 1.3491409798123687e-05,
      "loss": 0.8463,
      "step": 104
    },
    {
      "epoch": 3.1818181818181817,
      "grad_norm": 0.846226263288226,
      "learning_rate": 1.3348796121709862e-05,
      "loss": 0.8943,
      "step": 105
    },
    {
      "epoch": 3.212121212121212,
      "grad_norm": 0.8068651832312013,
      "learning_rate": 1.3205411116710973e-05,
      "loss": 0.8591,
      "step": 106
    },
    {
      "epoch": 3.242424242424242,
      "grad_norm": 0.8794302717245362,
      "learning_rate": 1.3061287809011243e-05,
      "loss": 0.9567,
      "step": 107
    },
    {
      "epoch": 3.2727272727272725,
      "grad_norm": 0.6929729360758241,
      "learning_rate": 1.291645939454825e-05,
      "loss": 0.8667,
      "step": 108
    },
    {
      "epoch": 3.303030303030303,
      "grad_norm": 0.6862022565486124,
      "learning_rate": 1.277095923166689e-05,
      "loss": 0.9159,
      "step": 109
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.8566772965263243,
      "learning_rate": 1.2624820833435939e-05,
      "loss": 0.8782,
      "step": 110
    },
    {
      "epoch": 3.3636363636363638,
      "grad_norm": 0.7676560041774851,
      "learning_rate": 1.2478077859929e-05,
      "loss": 0.8965,
      "step": 111
    },
    {
      "epoch": 3.393939393939394,
      "grad_norm": 0.6603140157942726,
      "learning_rate": 1.2330764110471567e-05,
      "loss": 0.92,
      "step": 112
    },
    {
      "epoch": 3.4242424242424243,
      "grad_norm": 0.717749175888083,
      "learning_rate": 1.2182913515856016e-05,
      "loss": 0.9075,
      "step": 113
    },
    {
      "epoch": 3.4545454545454546,
      "grad_norm": 0.6260887806285697,
      "learning_rate": 1.2034560130526341e-05,
      "loss": 0.9495,
      "step": 114
    },
    {
      "epoch": 3.484848484848485,
      "grad_norm": 0.6724764325790348,
      "learning_rate": 1.1885738124734359e-05,
      "loss": 0.8674,
      "step": 115
    },
    {
      "epoch": 3.515151515151515,
      "grad_norm": 0.7434536747516892,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.8698,
      "step": 116
    },
    {
      "epoch": 3.5454545454545454,
      "grad_norm": 0.7425472412968097,
      "learning_rate": 1.1586825464562515e-05,
      "loss": 0.8984,
      "step": 117
    },
    {
      "epoch": 3.5757575757575757,
      "grad_norm": 0.6048226747843541,
      "learning_rate": 1.1436803658769082e-05,
      "loss": 0.8799,
      "step": 118
    },
    {
      "epoch": 3.606060606060606,
      "grad_norm": 0.5857051892436379,
      "learning_rate": 1.1286450913828313e-05,
      "loss": 0.8818,
      "step": 119
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 0.637356411543135,
      "learning_rate": 1.113580186050475e-05,
      "loss": 0.9064,
      "step": 120
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 0.6064428910342201,
      "learning_rate": 1.0984891197811686e-05,
      "loss": 0.9302,
      "step": 121
    },
    {
      "epoch": 3.6969696969696972,
      "grad_norm": 0.5537669259101815,
      "learning_rate": 1.0833753685018935e-05,
      "loss": 0.8941,
      "step": 122
    },
    {
      "epoch": 3.7272727272727275,
      "grad_norm": 0.5743073173865274,
      "learning_rate": 1.0682424133646712e-05,
      "loss": 0.8766,
      "step": 123
    },
    {
      "epoch": 3.757575757575758,
      "grad_norm": 0.5728259261566023,
      "learning_rate": 1.0530937399447496e-05,
      "loss": 0.8918,
      "step": 124
    },
    {
      "epoch": 3.787878787878788,
      "grad_norm": 0.6098156545365195,
      "learning_rate": 1.0379328374377715e-05,
      "loss": 0.8625,
      "step": 125
    },
    {
      "epoch": 3.8181818181818183,
      "grad_norm": 0.5539061790372378,
      "learning_rate": 1.0227631978561057e-05,
      "loss": 0.9148,
      "step": 126
    },
    {
      "epoch": 3.8484848484848486,
      "grad_norm": 0.5666613692531657,
      "learning_rate": 1.0075883152245334e-05,
      "loss": 0.9084,
      "step": 127
    },
    {
      "epoch": 3.878787878787879,
      "grad_norm": 0.6105631729061529,
      "learning_rate": 9.92411684775467e-06,
      "loss": 0.8947,
      "step": 128
    },
    {
      "epoch": 3.909090909090909,
      "grad_norm": 0.5237994282193307,
      "learning_rate": 9.772368021438943e-06,
      "loss": 0.8764,
      "step": 129
    },
    {
      "epoch": 3.9393939393939394,
      "grad_norm": 0.5641506972742417,
      "learning_rate": 9.620671625622287e-06,
      "loss": 0.8969,
      "step": 130
    },
    {
      "epoch": 3.9696969696969697,
      "grad_norm": 0.5516688413694879,
      "learning_rate": 9.469062600552509e-06,
      "loss": 0.8959,
      "step": 131
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5365834406563174,
      "learning_rate": 9.317575866353293e-06,
      "loss": 0.892,
      "step": 132
    },
    {
      "epoch": 4.03030303030303,
      "grad_norm": 1.0007085148840356,
      "learning_rate": 9.166246314981066e-06,
      "loss": 0.8288,
      "step": 133
    },
    {
      "epoch": 4.0606060606060606,
      "grad_norm": 1.0505705841587225,
      "learning_rate": 9.015108802188314e-06,
      "loss": 0.8344,
      "step": 134
    },
    {
      "epoch": 4.090909090909091,
      "grad_norm": 1.0790528239025274,
      "learning_rate": 8.86419813949525e-06,
      "loss": 0.7931,
      "step": 135
    },
    {
      "epoch": 4.121212121212121,
      "grad_norm": 1.0504428771897605,
      "learning_rate": 8.71354908617169e-06,
      "loss": 0.8533,
      "step": 136
    },
    {
      "epoch": 4.151515151515151,
      "grad_norm": 1.0176472157915408,
      "learning_rate": 8.56319634123092e-06,
      "loss": 0.8465,
      "step": 137
    },
    {
      "epoch": 4.181818181818182,
      "grad_norm": 0.8515876419617665,
      "learning_rate": 8.413174535437486e-06,
      "loss": 0.8032,
      "step": 138
    },
    {
      "epoch": 4.212121212121212,
      "grad_norm": 0.8111743244978168,
      "learning_rate": 8.263518223330698e-06,
      "loss": 0.8263,
      "step": 139
    },
    {
      "epoch": 4.242424242424242,
      "grad_norm": 0.7402905926853802,
      "learning_rate": 8.114261875265643e-06,
      "loss": 0.8496,
      "step": 140
    },
    {
      "epoch": 4.2727272727272725,
      "grad_norm": 0.8107517723295261,
      "learning_rate": 7.965439869473664e-06,
      "loss": 0.8236,
      "step": 141
    },
    {
      "epoch": 4.303030303030303,
      "grad_norm": 0.6985764871276913,
      "learning_rate": 7.817086484143987e-06,
      "loss": 0.827,
      "step": 142
    },
    {
      "epoch": 4.333333333333333,
      "grad_norm": 0.747658317788757,
      "learning_rate": 7.669235889528436e-06,
      "loss": 0.8383,
      "step": 143
    },
    {
      "epoch": 4.363636363636363,
      "grad_norm": 0.6866276940990358,
      "learning_rate": 7.521922140071003e-06,
      "loss": 0.7865,
      "step": 144
    },
    {
      "epoch": 4.393939393939394,
      "grad_norm": 0.6969331589908039,
      "learning_rate": 7.375179166564062e-06,
      "loss": 0.8331,
      "step": 145
    },
    {
      "epoch": 4.424242424242424,
      "grad_norm": 0.6694564106121556,
      "learning_rate": 7.2290407683331154e-06,
      "loss": 0.8041,
      "step": 146
    },
    {
      "epoch": 4.454545454545454,
      "grad_norm": 0.6401945837489893,
      "learning_rate": 7.0835406054517505e-06,
      "loss": 0.8349,
      "step": 147
    },
    {
      "epoch": 4.484848484848484,
      "grad_norm": 0.5826877721012064,
      "learning_rate": 6.93871219098876e-06,
      "loss": 0.8273,
      "step": 148
    },
    {
      "epoch": 4.515151515151516,
      "grad_norm": 0.6743506335006482,
      "learning_rate": 6.79458888328903e-06,
      "loss": 0.8016,
      "step": 149
    },
    {
      "epoch": 4.545454545454545,
      "grad_norm": 0.6129743658390665,
      "learning_rate": 6.651203878290139e-06,
      "loss": 0.806,
      "step": 150
    },
    {
      "epoch": 4.575757575757576,
      "grad_norm": 0.6198055806276196,
      "learning_rate": 6.508590201876317e-06,
      "loss": 0.8029,
      "step": 151
    },
    {
      "epoch": 4.606060606060606,
      "grad_norm": 0.5366143520854241,
      "learning_rate": 6.366780702271589e-06,
      "loss": 0.7958,
      "step": 152
    },
    {
      "epoch": 4.636363636363637,
      "grad_norm": 0.6235444740229246,
      "learning_rate": 6.225808042473857e-06,
      "loss": 0.798,
      "step": 153
    },
    {
      "epoch": 4.666666666666667,
      "grad_norm": 0.5876484414463102,
      "learning_rate": 6.085704692731609e-06,
      "loss": 0.8163,
      "step": 154
    },
    {
      "epoch": 4.696969696969697,
      "grad_norm": 0.5750442183343925,
      "learning_rate": 5.946502923065054e-06,
      "loss": 0.8496,
      "step": 155
    },
    {
      "epoch": 4.7272727272727275,
      "grad_norm": 0.5460754757390077,
      "learning_rate": 5.8082347958333625e-06,
      "loss": 0.8636,
      "step": 156
    },
    {
      "epoch": 4.757575757575758,
      "grad_norm": 0.5807029402548276,
      "learning_rate": 5.670932158349732e-06,
      "loss": 0.8037,
      "step": 157
    },
    {
      "epoch": 4.787878787878788,
      "grad_norm": 0.526223502385406,
      "learning_rate": 5.534626635546e-06,
      "loss": 0.8265,
      "step": 158
    },
    {
      "epoch": 4.818181818181818,
      "grad_norm": 0.538758051506074,
      "learning_rate": 5.399349622688479e-06,
      "loss": 0.8259,
      "step": 159
    },
    {
      "epoch": 4.848484848484849,
      "grad_norm": 0.5117272882892506,
      "learning_rate": 5.2651322781466606e-06,
      "loss": 0.8454,
      "step": 160
    },
    {
      "epoch": 4.878787878787879,
      "grad_norm": 0.49607846008096673,
      "learning_rate": 5.132005516216512e-06,
      "loss": 0.8156,
      "step": 161
    },
    {
      "epoch": 4.909090909090909,
      "grad_norm": 0.5450147990534439,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.8446,
      "step": 162
    },
    {
      "epoch": 4.9393939393939394,
      "grad_norm": 0.49866480953344056,
      "learning_rate": 4.869146134342426e-06,
      "loss": 0.7934,
      "step": 163
    },
    {
      "epoch": 4.96969696969697,
      "grad_norm": 0.5070575647925789,
      "learning_rate": 4.739474058829288e-06,
      "loss": 0.7954,
      "step": 164
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.5283944255561349,
      "learning_rate": 4.611013640844245e-06,
      "loss": 0.8068,
      "step": 165
    },
    {
      "epoch": 5.03030303030303,
      "grad_norm": 1.107205965757332,
      "learning_rate": 4.483794468689728e-06,
      "loss": 0.7644,
      "step": 166
    },
    {
      "epoch": 5.0606060606060606,
      "grad_norm": 0.6689088324032454,
      "learning_rate": 4.357845844771881e-06,
      "loss": 0.7905,
      "step": 167
    },
    {
      "epoch": 5.090909090909091,
      "grad_norm": 1.269036804802727,
      "learning_rate": 4.2331967788513295e-06,
      "loss": 0.7536,
      "step": 168
    },
    {
      "epoch": 5.121212121212121,
      "grad_norm": 0.9543470305488272,
      "learning_rate": 4.109875981361363e-06,
      "loss": 0.7184,
      "step": 169
    },
    {
      "epoch": 5.151515151515151,
      "grad_norm": 1.16749705227223,
      "learning_rate": 3.987911856795047e-06,
      "loss": 0.7367,
      "step": 170
    },
    {
      "epoch": 5.181818181818182,
      "grad_norm": 0.840687639573645,
      "learning_rate": 3.867332497162836e-06,
      "loss": 0.7761,
      "step": 171
    },
    {
      "epoch": 5.212121212121212,
      "grad_norm": 0.8957863953464329,
      "learning_rate": 3.748165675522113e-06,
      "loss": 0.7624,
      "step": 172
    },
    {
      "epoch": 5.242424242424242,
      "grad_norm": 0.9622162931250663,
      "learning_rate": 3.630438839580217e-06,
      "loss": 0.7736,
      "step": 173
    },
    {
      "epoch": 5.2727272727272725,
      "grad_norm": 0.6167972178568236,
      "learning_rate": 3.5141791053724405e-06,
      "loss": 0.7906,
      "step": 174
    },
    {
      "epoch": 5.303030303030303,
      "grad_norm": 0.826789291507702,
      "learning_rate": 3.399413251016359e-06,
      "loss": 0.7527,
      "step": 175
    },
    {
      "epoch": 5.333333333333333,
      "grad_norm": 0.7317208354854027,
      "learning_rate": 3.2861677105440335e-06,
      "loss": 0.7636,
      "step": 176
    },
    {
      "epoch": 5.363636363636363,
      "grad_norm": 0.642446772035738,
      "learning_rate": 3.174468567813461e-06,
      "loss": 0.7305,
      "step": 177
    },
    {
      "epoch": 5.393939393939394,
      "grad_norm": 0.7284416191645582,
      "learning_rate": 3.0643415505006733e-06,
      "loss": 0.7348,
      "step": 178
    },
    {
      "epoch": 5.424242424242424,
      "grad_norm": 0.57803777430404,
      "learning_rate": 2.9558120241738786e-06,
      "loss": 0.736,
      "step": 179
    },
    {
      "epoch": 5.454545454545454,
      "grad_norm": 0.6118445719047273,
      "learning_rate": 2.8489049864510053e-06,
      "loss": 0.7682,
      "step": 180
    },
    {
      "epoch": 5.484848484848484,
      "grad_norm": 0.6249005218713161,
      "learning_rate": 2.7436450612420098e-06,
      "loss": 0.7369,
      "step": 181
    },
    {
      "epoch": 5.515151515151516,
      "grad_norm": 0.5654139353846552,
      "learning_rate": 2.640056493077231e-06,
      "loss": 0.7485,
      "step": 182
    },
    {
      "epoch": 5.545454545454545,
      "grad_norm": 0.5883561260909623,
      "learning_rate": 2.5381631415231455e-06,
      "loss": 0.7836,
      "step": 183
    },
    {
      "epoch": 5.575757575757576,
      "grad_norm": 0.6196867197558733,
      "learning_rate": 2.4379884756868167e-06,
      "loss": 0.7365,
      "step": 184
    },
    {
      "epoch": 5.606060606060606,
      "grad_norm": 0.5806556055602284,
      "learning_rate": 2.339555568810221e-06,
      "loss": 0.7919,
      "step": 185
    },
    {
      "epoch": 5.636363636363637,
      "grad_norm": 0.5491253477719896,
      "learning_rate": 2.2428870929558012e-06,
      "loss": 0.767,
      "step": 186
    },
    {
      "epoch": 5.666666666666667,
      "grad_norm": 0.5903532417352905,
      "learning_rate": 2.1480053137844115e-06,
      "loss": 0.766,
      "step": 187
    },
    {
      "epoch": 5.696969696969697,
      "grad_norm": 0.5095765500696539,
      "learning_rate": 2.054932085426856e-06,
      "loss": 0.8117,
      "step": 188
    },
    {
      "epoch": 5.7272727272727275,
      "grad_norm": 0.5139996546456344,
      "learning_rate": 1.963688845450218e-06,
      "loss": 0.7629,
      "step": 189
    },
    {
      "epoch": 5.757575757575758,
      "grad_norm": 0.511647923970949,
      "learning_rate": 1.8742966099201699e-06,
      "loss": 0.7715,
      "step": 190
    },
    {
      "epoch": 5.787878787878788,
      "grad_norm": 0.5246225499699126,
      "learning_rate": 1.7867759685603115e-06,
      "loss": 0.7672,
      "step": 191
    },
    {
      "epoch": 5.818181818181818,
      "grad_norm": 0.492921983199909,
      "learning_rate": 1.7011470800097496e-06,
      "loss": 0.7878,
      "step": 192
    },
    {
      "epoch": 5.848484848484849,
      "grad_norm": 0.5075012690699857,
      "learning_rate": 1.6174296671799571e-06,
      "loss": 0.7853,
      "step": 193
    },
    {
      "epoch": 5.878787878787879,
      "grad_norm": 0.4985332854344134,
      "learning_rate": 1.5356430127119915e-06,
      "loss": 0.7642,
      "step": 194
    },
    {
      "epoch": 5.909090909090909,
      "grad_norm": 0.522090632801161,
      "learning_rate": 1.4558059545351144e-06,
      "loss": 0.7463,
      "step": 195
    },
    {
      "epoch": 5.9393939393939394,
      "grad_norm": 0.45497911395088,
      "learning_rate": 1.3779368815278648e-06,
      "loss": 0.7499,
      "step": 196
    },
    {
      "epoch": 5.96969696969697,
      "grad_norm": 0.49667869280611776,
      "learning_rate": 1.302053729282533e-06,
      "loss": 0.732,
      "step": 197
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.47565921977270686,
      "learning_rate": 1.2281739759740575e-06,
      "loss": 0.7762,
      "step": 198
    },
    {
      "epoch": 6.03030303030303,
      "grad_norm": 0.8751233721998436,
      "learning_rate": 1.156314638334277e-06,
      "loss": 0.7405,
      "step": 199
    },
    {
      "epoch": 6.0606060606060606,
      "grad_norm": 0.6709493135419762,
      "learning_rate": 1.086492267732462e-06,
      "loss": 0.7503,
      "step": 200
    },
    {
      "epoch": 6.090909090909091,
      "grad_norm": 0.5685238381894403,
      "learning_rate": 1.01872294636304e-06,
      "loss": 0.7894,
      "step": 201
    },
    {
      "epoch": 6.121212121212121,
      "grad_norm": 0.5702523647122428,
      "learning_rate": 9.530222835413739e-07,
      "loss": 0.756,
      "step": 202
    },
    {
      "epoch": 6.151515151515151,
      "grad_norm": 0.7689907935969016,
      "learning_rate": 8.894054121084839e-07,
      "loss": 0.7125,
      "step": 203
    },
    {
      "epoch": 6.181818181818182,
      "grad_norm": 0.6818231860364762,
      "learning_rate": 8.278869849454718e-07,
      "loss": 0.7253,
      "step": 204
    },
    {
      "epoch": 6.212121212121212,
      "grad_norm": 0.5869654356498157,
      "learning_rate": 7.684811715985429e-07,
      "loss": 0.7161,
      "step": 205
    },
    {
      "epoch": 6.242424242424242,
      "grad_norm": 0.5900428653556422,
      "learning_rate": 7.1120165501533e-07,
      "loss": 0.7646,
      "step": 206
    },
    {
      "epoch": 6.2727272727272725,
      "grad_norm": 0.586624607392676,
      "learning_rate": 6.560616283932897e-07,
      "loss": 0.7118,
      "step": 207
    },
    {
      "epoch": 6.303030303030303,
      "grad_norm": 0.5405544938434272,
      "learning_rate": 6.030737921409169e-07,
      "loss": 0.7006,
      "step": 208
    },
    {
      "epoch": 6.333333333333333,
      "grad_norm": 0.5574392942218139,
      "learning_rate": 5.522503509524591e-07,
      "loss": 0.7092,
      "step": 209
    },
    {
      "epoch": 6.363636363636363,
      "grad_norm": 0.48000107743256276,
      "learning_rate": 5.036030109968082e-07,
      "loss": 0.7192,
      "step": 210
    },
    {
      "epoch": 6.393939393939394,
      "grad_norm": 0.4914775806204615,
      "learning_rate": 4.5714297722121105e-07,
      "loss": 0.7487,
      "step": 211
    },
    {
      "epoch": 6.424242424242424,
      "grad_norm": 0.5013183529579176,
      "learning_rate": 4.128809507704445e-07,
      "loss": 0.7414,
      "step": 212
    },
    {
      "epoch": 6.454545454545454,
      "grad_norm": 0.5138364493756118,
      "learning_rate": 3.708271265220087e-07,
      "loss": 0.7341,
      "step": 213
    },
    {
      "epoch": 6.484848484848484,
      "grad_norm": 0.5099662338072006,
      "learning_rate": 3.309911907379393e-07,
      "loss": 0.7659,
      "step": 214
    },
    {
      "epoch": 6.515151515151516,
      "grad_norm": 0.5193526378643841,
      "learning_rate": 2.9338231883378365e-07,
      "loss": 0.7035,
      "step": 215
    },
    {
      "epoch": 6.545454545454545,
      "grad_norm": 0.5110392254369897,
      "learning_rate": 2.5800917326521013e-07,
      "loss": 0.7248,
      "step": 216
    },
    {
      "epoch": 6.575757575757576,
      "grad_norm": 0.44960656873587745,
      "learning_rate": 2.248799015327907e-07,
      "loss": 0.7299,
      "step": 217
    },
    {
      "epoch": 6.606060606060606,
      "grad_norm": 0.4317807441071986,
      "learning_rate": 1.9400213430538773e-07,
      "loss": 0.699,
      "step": 218
    },
    {
      "epoch": 6.636363636363637,
      "grad_norm": 0.44904572498244527,
      "learning_rate": 1.6538298366257975e-07,
      "loss": 0.7115,
      "step": 219
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.43024370705927745,
      "learning_rate": 1.3902904145653094e-07,
      "loss": 0.7266,
      "step": 220
    },
    {
      "epoch": 6.696969696969697,
      "grad_norm": 0.4371438929709028,
      "learning_rate": 1.1494637779369766e-07,
      "loss": 0.7299,
      "step": 221
    },
    {
      "epoch": 6.7272727272727275,
      "grad_norm": 0.4423008608942414,
      "learning_rate": 9.314053963669245e-08,
      "loss": 0.7441,
      "step": 222
    },
    {
      "epoch": 6.757575757575758,
      "grad_norm": 0.44987736057658106,
      "learning_rate": 7.361654952665608e-08,
      "loss": 0.7542,
      "step": 223
    },
    {
      "epoch": 6.787878787878788,
      "grad_norm": 0.4327741370940891,
      "learning_rate": 5.637890442641403e-08,
      "loss": 0.7327,
      "step": 224
    },
    {
      "epoch": 6.818181818181818,
      "grad_norm": 0.43929304443257705,
      "learning_rate": 4.143157468468717e-08,
      "loss": 0.7568,
      "step": 225
    },
    {
      "epoch": 6.848484848484849,
      "grad_norm": 0.42753635817867786,
      "learning_rate": 2.8778003121607834e-08,
      "loss": 0.7064,
      "step": 226
    },
    {
      "epoch": 6.878787878787879,
      "grad_norm": 0.4433338556506804,
      "learning_rate": 1.8421104235727406e-08,
      "loss": 0.7227,
      "step": 227
    },
    {
      "epoch": 6.909090909090909,
      "grad_norm": 0.438311797000866,
      "learning_rate": 1.0363263532724433e-08,
      "loss": 0.757,
      "step": 228
    },
    {
      "epoch": 6.9393939393939394,
      "grad_norm": 0.44045538713370924,
      "learning_rate": 4.606336975948589e-09,
      "loss": 0.7508,
      "step": 229
    },
    {
      "epoch": 6.96969696969697,
      "grad_norm": 0.4145322423815856,
      "learning_rate": 1.1516505589381777e-09,
      "loss": 0.7098,
      "step": 230
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.42610978207978184,
      "learning_rate": 0.0,
      "loss": 0.7233,
      "step": 231
    },
    {
      "epoch": 7.0,
      "step": 231,
      "total_flos": 8.483077647142748e+17,
      "train_loss": 0.9281180423575562,
      "train_runtime": 20881.4801,
      "train_samples_per_second": 1.059,
      "train_steps_per_second": 0.011
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 231,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 8.483077647142748e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}