{
  "best_metric": 10.352631568908691,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.25,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00625,
      "grad_norm": 0.06334076076745987,
      "learning_rate": 1e-05,
      "loss": 10.38,
      "step": 1
    },
    {
      "epoch": 0.00625,
      "eval_loss": 10.378706932067871,
      "eval_runtime": 0.5968,
      "eval_samples_per_second": 452.408,
      "eval_steps_per_second": 113.94,
      "step": 1
    },
    {
      "epoch": 0.0125,
      "grad_norm": 0.03656429797410965,
      "learning_rate": 2e-05,
      "loss": 10.38,
      "step": 2
    },
    {
      "epoch": 0.01875,
      "grad_norm": 0.03441770374774933,
      "learning_rate": 3e-05,
      "loss": 10.3812,
      "step": 3
    },
    {
      "epoch": 0.025,
      "grad_norm": 0.03471704572439194,
      "learning_rate": 4e-05,
      "loss": 10.3795,
      "step": 4
    },
    {
      "epoch": 0.03125,
      "grad_norm": 0.03330289572477341,
      "learning_rate": 5e-05,
      "loss": 10.3802,
      "step": 5
    },
    {
      "epoch": 0.0375,
      "grad_norm": 0.03487839922308922,
      "learning_rate": 6e-05,
      "loss": 10.3796,
      "step": 6
    },
    {
      "epoch": 0.04375,
      "grad_norm": 0.03472553938627243,
      "learning_rate": 7e-05,
      "loss": 10.3799,
      "step": 7
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.03558014705777168,
      "learning_rate": 8e-05,
      "loss": 10.3811,
      "step": 8
    },
    {
      "epoch": 0.05625,
      "grad_norm": 0.03530484810471535,
      "learning_rate": 9e-05,
      "loss": 10.3802,
      "step": 9
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.04263327270746231,
      "learning_rate": 0.0001,
      "loss": 10.3786,
      "step": 10
    },
    {
      "epoch": 0.06875,
      "grad_norm": 0.03410453721880913,
      "learning_rate": 9.999316524962345e-05,
      "loss": 10.3774,
      "step": 11
    },
    {
      "epoch": 0.075,
      "grad_norm": 0.0450933501124382,
      "learning_rate": 9.997266286704631e-05,
      "loss": 10.3788,
      "step": 12
    },
    {
      "epoch": 0.08125,
      "grad_norm": 0.03739609569311142,
      "learning_rate": 9.993849845741524e-05,
      "loss": 10.3801,
      "step": 13
    },
    {
      "epoch": 0.0875,
      "grad_norm": 0.045744042843580246,
      "learning_rate": 9.989068136093873e-05,
      "loss": 10.3782,
      "step": 14
    },
    {
      "epoch": 0.09375,
      "grad_norm": 0.0383274219930172,
      "learning_rate": 9.98292246503335e-05,
      "loss": 10.378,
      "step": 15
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.05043305829167366,
      "learning_rate": 9.975414512725057e-05,
      "loss": 10.3787,
      "step": 16
    },
    {
      "epoch": 0.10625,
      "grad_norm": 0.04675762727856636,
      "learning_rate": 9.966546331768191e-05,
      "loss": 10.3773,
      "step": 17
    },
    {
      "epoch": 0.1125,
      "grad_norm": 0.04881301522254944,
      "learning_rate": 9.956320346634876e-05,
      "loss": 10.3758,
      "step": 18
    },
    {
      "epoch": 0.11875,
      "grad_norm": 0.06490051746368408,
      "learning_rate": 9.944739353007344e-05,
      "loss": 10.375,
      "step": 19
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.06786436587572098,
      "learning_rate": 9.931806517013612e-05,
      "loss": 10.3752,
      "step": 20
    },
    {
      "epoch": 0.13125,
      "grad_norm": 0.06405546516180038,
      "learning_rate": 9.917525374361912e-05,
      "loss": 10.376,
      "step": 21
    },
    {
      "epoch": 0.1375,
      "grad_norm": 0.06183639168739319,
      "learning_rate": 9.901899829374047e-05,
      "loss": 10.375,
      "step": 22
    },
    {
      "epoch": 0.14375,
      "grad_norm": 0.07523166388273239,
      "learning_rate": 9.884934153917997e-05,
      "loss": 10.3731,
      "step": 23
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.10190968960523605,
      "learning_rate": 9.86663298624003e-05,
      "loss": 10.3734,
      "step": 24
    },
    {
      "epoch": 0.15625,
      "grad_norm": 0.08188779652118683,
      "learning_rate": 9.847001329696653e-05,
      "loss": 10.3744,
      "step": 25
    },
    {
      "epoch": 0.1625,
      "grad_norm": 0.09415493160486221,
      "learning_rate": 9.826044551386744e-05,
      "loss": 10.3744,
      "step": 26
    },
    {
      "epoch": 0.16875,
      "grad_norm": 0.09845616668462753,
      "learning_rate": 9.803768380684242e-05,
      "loss": 10.3698,
      "step": 27
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.1411401480436325,
      "learning_rate": 9.780178907671789e-05,
      "loss": 10.3683,
      "step": 28
    },
    {
      "epoch": 0.18125,
      "grad_norm": 0.12798817455768585,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3729,
      "step": 29
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.15741682052612305,
      "learning_rate": 9.729086208503174e-05,
      "loss": 10.3671,
      "step": 30
    },
    {
      "epoch": 0.19375,
      "grad_norm": 0.16327780485153198,
      "learning_rate": 9.701596950580806e-05,
      "loss": 10.3688,
      "step": 31
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.17126795649528503,
      "learning_rate": 9.672822322997305e-05,
      "loss": 10.3619,
      "step": 32
    },
    {
      "epoch": 0.20625,
      "grad_norm": 0.18012569844722748,
      "learning_rate": 9.642770192448536e-05,
      "loss": 10.3682,
      "step": 33
    },
    {
      "epoch": 0.2125,
      "grad_norm": 0.18857280910015106,
      "learning_rate": 9.611448774886924e-05,
      "loss": 10.3591,
      "step": 34
    },
    {
      "epoch": 0.21875,
      "grad_norm": 0.16803322732448578,
      "learning_rate": 9.578866633275288e-05,
      "loss": 10.3585,
      "step": 35
    },
    {
      "epoch": 0.225,
      "grad_norm": 0.20192867517471313,
      "learning_rate": 9.545032675245813e-05,
      "loss": 10.361,
      "step": 36
    },
    {
      "epoch": 0.23125,
      "grad_norm": 0.17020496726036072,
      "learning_rate": 9.509956150664796e-05,
      "loss": 10.3641,
      "step": 37
    },
    {
      "epoch": 0.2375,
      "grad_norm": 0.21077771484851837,
      "learning_rate": 9.473646649103818e-05,
      "loss": 10.3628,
      "step": 38
    },
    {
      "epoch": 0.24375,
      "grad_norm": 0.18458126485347748,
      "learning_rate": 9.43611409721806e-05,
      "loss": 10.3486,
      "step": 39
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.23663665354251862,
      "learning_rate": 9.397368756032445e-05,
      "loss": 10.3477,
      "step": 40
    },
    {
      "epoch": 0.25625,
      "grad_norm": 0.11249205470085144,
      "learning_rate": 9.357421218136386e-05,
      "loss": 10.3677,
      "step": 41
    },
    {
      "epoch": 0.2625,
      "grad_norm": 0.12037327140569687,
      "learning_rate": 9.316282404787871e-05,
      "loss": 10.366,
      "step": 42
    },
    {
      "epoch": 0.26875,
      "grad_norm": 0.12676556408405304,
      "learning_rate": 9.273963562927695e-05,
      "loss": 10.365,
      "step": 43
    },
    {
      "epoch": 0.275,
      "grad_norm": 0.12306234240531921,
      "learning_rate": 9.230476262104677e-05,
      "loss": 10.3606,
      "step": 44
    },
    {
      "epoch": 0.28125,
      "grad_norm": 0.12216205894947052,
      "learning_rate": 9.185832391312644e-05,
      "loss": 10.3598,
      "step": 45
    },
    {
      "epoch": 0.2875,
      "grad_norm": 0.1008618175983429,
      "learning_rate": 9.140044155740101e-05,
      "loss": 10.3648,
      "step": 46
    },
    {
      "epoch": 0.29375,
      "grad_norm": 0.10435564070940018,
      "learning_rate": 9.093124073433463e-05,
      "loss": 10.3642,
      "step": 47
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.10676997900009155,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3594,
      "step": 48
    },
    {
      "epoch": 0.30625,
      "grad_norm": 0.09724239259958267,
      "learning_rate": 8.995939984474624e-05,
      "loss": 10.3605,
      "step": 49
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.10994001477956772,
      "learning_rate": 8.945702546981969e-05,
      "loss": 10.3597,
      "step": 50
    },
    {
      "epoch": 0.3125,
      "eval_loss": 10.35695743560791,
      "eval_runtime": 0.5964,
      "eval_samples_per_second": 452.751,
      "eval_steps_per_second": 114.026,
      "step": 50
    },
    {
      "epoch": 0.31875,
      "grad_norm": 0.09128973633050919,
      "learning_rate": 8.894386393810563e-05,
      "loss": 10.3572,
      "step": 51
    },
    {
      "epoch": 0.325,
      "grad_norm": 0.08918166905641556,
      "learning_rate": 8.842005554284296e-05,
      "loss": 10.3555,
      "step": 52
    },
    {
      "epoch": 0.33125,
      "grad_norm": 0.07096360623836517,
      "learning_rate": 8.788574348801675e-05,
      "loss": 10.3597,
      "step": 53
    },
    {
      "epoch": 0.3375,
      "grad_norm": 0.08530693501234055,
      "learning_rate": 8.73410738492077e-05,
      "loss": 10.3588,
      "step": 54
    },
    {
      "epoch": 0.34375,
      "grad_norm": 0.055037908256053925,
      "learning_rate": 8.678619553365659e-05,
      "loss": 10.3567,
      "step": 55
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.07192099094390869,
      "learning_rate": 8.622126023955446e-05,
      "loss": 10.3554,
      "step": 56
    },
    {
      "epoch": 0.35625,
      "grad_norm": 0.06012772023677826,
      "learning_rate": 8.564642241456986e-05,
      "loss": 10.3519,
      "step": 57
    },
    {
      "epoch": 0.3625,
      "grad_norm": 0.06842062622308731,
      "learning_rate": 8.506183921362443e-05,
      "loss": 10.3551,
      "step": 58
    },
    {
      "epoch": 0.36875,
      "grad_norm": 0.06274768710136414,
      "learning_rate": 8.44676704559283e-05,
      "loss": 10.3526,
      "step": 59
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.07295379787683487,
      "learning_rate": 8.386407858128706e-05,
      "loss": 10.3526,
      "step": 60
    },
    {
      "epoch": 0.38125,
      "grad_norm": 0.04899614676833153,
      "learning_rate": 8.32512286056924e-05,
      "loss": 10.3517,
      "step": 61
    },
    {
      "epoch": 0.3875,
      "grad_norm": 0.060171786695718765,
      "learning_rate": 8.262928807620843e-05,
      "loss": 10.3527,
      "step": 62
    },
    {
      "epoch": 0.39375,
      "grad_norm": 0.06014130264520645,
      "learning_rate": 8.199842702516583e-05,
      "loss": 10.3545,
      "step": 63
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.04926243796944618,
      "learning_rate": 8.135881792367686e-05,
      "loss": 10.3531,
      "step": 64
    },
    {
      "epoch": 0.40625,
      "grad_norm": 0.0463285855948925,
      "learning_rate": 8.07106356344834e-05,
      "loss": 10.3545,
      "step": 65
    },
    {
      "epoch": 0.4125,
      "grad_norm": 0.05200220271945,
      "learning_rate": 8.005405736415126e-05,
      "loss": 10.3563,
      "step": 66
    },
    {
      "epoch": 0.41875,
      "grad_norm": 0.04179251194000244,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.35,
      "step": 67
    },
    {
      "epoch": 0.425,
      "grad_norm": 0.061032552272081375,
      "learning_rate": 7.871643313414718e-05,
      "loss": 10.3513,
      "step": 68
    },
    {
      "epoch": 0.43125,
      "grad_norm": 0.06431969255208969,
      "learning_rate": 7.803575286758364e-05,
      "loss": 10.35,
      "step": 69
    },
    {
      "epoch": 0.4375,
      "grad_norm": 0.07795145362615585,
      "learning_rate": 7.734740790612136e-05,
      "loss": 10.3524,
      "step": 70
    },
    {
      "epoch": 0.44375,
      "grad_norm": 0.11047030985355377,
      "learning_rate": 7.66515864363997e-05,
      "loss": 10.3532,
      "step": 71
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.07937394082546234,
      "learning_rate": 7.594847868906076e-05,
      "loss": 10.3505,
      "step": 72
    },
    {
      "epoch": 0.45625,
      "grad_norm": 0.0515572652220726,
      "learning_rate": 7.52382768867422e-05,
      "loss": 10.3514,
      "step": 73
    },
    {
      "epoch": 0.4625,
      "grad_norm": 0.09167144447565079,
      "learning_rate": 7.452117519152542e-05,
      "loss": 10.3519,
      "step": 74
    },
    {
      "epoch": 0.46875,
      "grad_norm": 0.10241222381591797,
      "learning_rate": 7.379736965185368e-05,
      "loss": 10.3526,
      "step": 75
    },
    {
      "epoch": 0.475,
      "grad_norm": 0.08735226839780807,
      "learning_rate": 7.30670581489344e-05,
      "loss": 10.3501,
      "step": 76
    },
    {
      "epoch": 0.48125,
      "grad_norm": 0.10863838344812393,
      "learning_rate": 7.233044034264034e-05,
      "loss": 10.3471,
      "step": 77
    },
    {
      "epoch": 0.4875,
      "grad_norm": 0.11681757122278214,
      "learning_rate": 7.158771761692464e-05,
      "loss": 10.3487,
      "step": 78
    },
    {
      "epoch": 0.49375,
      "grad_norm": 0.138514906167984,
      "learning_rate": 7.083909302476453e-05,
      "loss": 10.3468,
      "step": 79
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.16592583060264587,
      "learning_rate": 7.008477123264848e-05,
      "loss": 10.3464,
      "step": 80
    },
    {
      "epoch": 0.50625,
      "grad_norm": 0.09019774943590164,
      "learning_rate": 6.932495846462261e-05,
      "loss": 10.3602,
      "step": 81
    },
    {
      "epoch": 0.5125,
      "grad_norm": 0.06759248673915863,
      "learning_rate": 6.855986244591104e-05,
      "loss": 10.3591,
      "step": 82
    },
    {
      "epoch": 0.51875,
      "grad_norm": 0.06121740862727165,
      "learning_rate": 6.778969234612584e-05,
      "loss": 10.3535,
      "step": 83
    },
    {
      "epoch": 0.525,
      "grad_norm": 0.057054176926612854,
      "learning_rate": 6.701465872208216e-05,
      "loss": 10.3553,
      "step": 84
    },
    {
      "epoch": 0.53125,
      "grad_norm": 0.05265101417899132,
      "learning_rate": 6.623497346023418e-05,
      "loss": 10.3555,
      "step": 85
    },
    {
      "epoch": 0.5375,
      "grad_norm": 0.06349074095487595,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3554,
      "step": 86
    },
    {
      "epoch": 0.54375,
      "grad_norm": 0.05550549924373627,
      "learning_rate": 6.466250186922325e-05,
      "loss": 10.3555,
      "step": 87
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.061292193830013275,
      "learning_rate": 6.387014543809223e-05,
      "loss": 10.3547,
      "step": 88
    },
    {
      "epoch": 0.55625,
      "grad_norm": 0.052093759179115295,
      "learning_rate": 6.307399704769099e-05,
      "loss": 10.3522,
      "step": 89
    },
    {
      "epoch": 0.5625,
      "grad_norm": 0.06096919998526573,
      "learning_rate": 6.227427435703997e-05,
      "loss": 10.3551,
      "step": 90
    },
    {
      "epoch": 0.56875,
      "grad_norm": 0.06460977345705032,
      "learning_rate": 6.147119600233758e-05,
      "loss": 10.3542,
      "step": 91
    },
    {
      "epoch": 0.575,
      "grad_norm": 0.055585552006959915,
      "learning_rate": 6.066498153718735e-05,
      "loss": 10.3559,
      "step": 92
    },
    {
      "epoch": 0.58125,
      "grad_norm": 0.04695078730583191,
      "learning_rate": 5.985585137257401e-05,
      "loss": 10.3527,
      "step": 93
    },
    {
      "epoch": 0.5875,
      "grad_norm": 0.04420129954814911,
      "learning_rate": 5.90440267166055e-05,
      "loss": 10.3578,
      "step": 94
    },
    {
      "epoch": 0.59375,
      "grad_norm": 0.04916565492749214,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 10.3543,
      "step": 95
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.041832007467746735,
      "learning_rate": 5.74131823855921e-05,
      "loss": 10.3524,
      "step": 96
    },
    {
      "epoch": 0.60625,
      "grad_norm": 0.04612992703914642,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 10.3526,
      "step": 97
    },
    {
      "epoch": 0.6125,
      "grad_norm": 0.046181656420230865,
      "learning_rate": 5.577423184847932e-05,
      "loss": 10.3546,
      "step": 98
    },
    {
      "epoch": 0.61875,
      "grad_norm": 0.04212898015975952,
      "learning_rate": 5.495227651252315e-05,
      "loss": 10.3557,
      "step": 99
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.041884634643793106,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 10.3522,
      "step": 100
    },
    {
      "epoch": 0.625,
      "eval_loss": 10.353293418884277,
      "eval_runtime": 0.5866,
      "eval_samples_per_second": 460.305,
      "eval_steps_per_second": 115.929,
      "step": 100
    },
    {
      "epoch": 0.63125,
      "grad_norm": 0.05230015888810158,
      "learning_rate": 5.330452921628497e-05,
      "loss": 10.3516,
      "step": 101
    },
    {
      "epoch": 0.6375,
      "grad_norm": 0.04612657055258751,
      "learning_rate": 5.247918773366112e-05,
      "loss": 10.3528,
      "step": 102
    },
    {
      "epoch": 0.64375,
      "grad_norm": 0.056883301585912704,
      "learning_rate": 5.165316846586541e-05,
      "loss": 10.3516,
      "step": 103
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.05764239281415939,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 10.3537,
      "step": 104
    },
    {
      "epoch": 0.65625,
      "grad_norm": 0.04739293083548546,
      "learning_rate": 5e-05,
      "loss": 10.3567,
      "step": 105
    },
    {
      "epoch": 0.6625,
      "grad_norm": 0.06546645611524582,
      "learning_rate": 4.917330276168208e-05,
      "loss": 10.354,
      "step": 106
    },
    {
      "epoch": 0.66875,
      "grad_norm": 0.06665387749671936,
      "learning_rate": 4.834683153413459e-05,
      "loss": 10.3502,
      "step": 107
    },
    {
      "epoch": 0.675,
      "grad_norm": 0.0501079186797142,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 10.3537,
      "step": 108
    },
    {
      "epoch": 0.68125,
      "grad_norm": 0.03402156010270119,
      "learning_rate": 4.669547078371504e-05,
      "loss": 10.352,
      "step": 109
    },
    {
      "epoch": 0.6875,
      "grad_norm": 0.07886616885662079,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 10.3506,
      "step": 110
    },
    {
      "epoch": 0.69375,
      "grad_norm": 0.05963629484176636,
      "learning_rate": 4.504772348747687e-05,
      "loss": 10.35,
      "step": 111
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.05740436911582947,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 10.356,
      "step": 112
    },
    {
      "epoch": 0.70625,
      "grad_norm": 0.05395352467894554,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 10.3465,
      "step": 113
    },
    {
      "epoch": 0.7125,
      "grad_norm": 0.07751931250095367,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 10.346,
      "step": 114
    },
    {
      "epoch": 0.71875,
      "grad_norm": 0.10028713196516037,
      "learning_rate": 4.17702704859633e-05,
      "loss": 10.3483,
      "step": 115
    },
    {
      "epoch": 0.725,
      "grad_norm": 0.10091164708137512,
      "learning_rate": 4.095597328339452e-05,
      "loss": 10.347,
      "step": 116
    },
    {
      "epoch": 0.73125,
      "grad_norm": 0.08433723449707031,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 10.3509,
      "step": 117
    },
    {
      "epoch": 0.7375,
      "grad_norm": 0.12076109647750854,
      "learning_rate": 3.933501846281267e-05,
      "loss": 10.3477,
      "step": 118
    },
    {
      "epoch": 0.74375,
      "grad_norm": 0.15531793236732483,
      "learning_rate": 3.852880399766243e-05,
      "loss": 10.3423,
      "step": 119
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.20764897763729095,
      "learning_rate": 3.772572564296005e-05,
      "loss": 10.353,
      "step": 120
    },
    {
      "epoch": 0.75625,
      "grad_norm": 0.09875545650720596,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 10.3586,
      "step": 121
    },
    {
      "epoch": 0.7625,
      "grad_norm": 0.05107598379254341,
      "learning_rate": 3.612985456190778e-05,
      "loss": 10.3564,
      "step": 122
    },
    {
      "epoch": 0.76875,
      "grad_norm": 0.06652845442295074,
      "learning_rate": 3.533749813077677e-05,
      "loss": 10.3555,
      "step": 123
    },
    {
      "epoch": 0.775,
      "grad_norm": 0.05082063749432564,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3564,
      "step": 124
    },
    {
      "epoch": 0.78125,
      "grad_norm": 0.056762728840112686,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 10.3549,
      "step": 125
    },
    {
      "epoch": 0.7875,
      "grad_norm": 0.0554436519742012,
      "learning_rate": 3.298534127791785e-05,
      "loss": 10.3549,
      "step": 126
    },
    {
      "epoch": 0.79375,
      "grad_norm": 0.04685700684785843,
      "learning_rate": 3.221030765387417e-05,
      "loss": 10.3549,
      "step": 127
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.03904030844569206,
      "learning_rate": 3.144013755408895e-05,
      "loss": 10.3525,
      "step": 128
    },
    {
      "epoch": 0.80625,
      "grad_norm": 0.05914858356118202,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 10.3544,
      "step": 129
    },
    {
      "epoch": 0.8125,
      "grad_norm": 0.038961850106716156,
      "learning_rate": 2.991522876735154e-05,
      "loss": 10.3527,
      "step": 130
    },
    {
      "epoch": 0.81875,
      "grad_norm": 0.04432930424809456,
      "learning_rate": 2.916090697523549e-05,
      "loss": 10.3527,
      "step": 131
    },
    {
      "epoch": 0.825,
      "grad_norm": 0.05260743200778961,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 10.3527,
      "step": 132
    },
    {
      "epoch": 0.83125,
      "grad_norm": 0.03423444181680679,
      "learning_rate": 2.766955965735968e-05,
      "loss": 10.3526,
      "step": 133
    },
    {
      "epoch": 0.8375,
      "grad_norm": 0.057460539042949677,
      "learning_rate": 2.693294185106562e-05,
      "loss": 10.3521,
      "step": 134
    },
    {
      "epoch": 0.84375,
      "grad_norm": 0.04621444270014763,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 10.3543,
      "step": 135
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.04410833865404129,
      "learning_rate": 2.547882480847461e-05,
      "loss": 10.3504,
      "step": 136
    },
    {
      "epoch": 0.85625,
      "grad_norm": 0.039265792816877365,
      "learning_rate": 2.476172311325783e-05,
      "loss": 10.3529,
      "step": 137
    },
    {
      "epoch": 0.8625,
      "grad_norm": 0.0439460426568985,
      "learning_rate": 2.405152131093926e-05,
      "loss": 10.352,
      "step": 138
    },
    {
      "epoch": 0.86875,
      "grad_norm": 0.04639211297035217,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 10.3504,
      "step": 139
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.059402670711278915,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 10.3519,
      "step": 140
    },
    {
      "epoch": 0.88125,
      "grad_norm": 0.04731443524360657,
      "learning_rate": 2.196424713241637e-05,
      "loss": 10.3523,
      "step": 141
    },
    {
      "epoch": 0.8875,
      "grad_norm": 0.050451599061489105,
      "learning_rate": 2.128356686585282e-05,
      "loss": 10.3538,
      "step": 142
    },
    {
      "epoch": 0.89375,
      "grad_norm": 0.046937163919210434,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.351,
      "step": 143
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.05124863609671593,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 10.3531,
      "step": 144
    },
    {
      "epoch": 0.90625,
      "grad_norm": 0.05496614798903465,
      "learning_rate": 1.928936436551661e-05,
      "loss": 10.3523,
      "step": 145
    },
    {
      "epoch": 0.9125,
      "grad_norm": 0.052969757467508316,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 10.3488,
      "step": 146
    },
    {
      "epoch": 0.91875,
      "grad_norm": 0.05567191541194916,
      "learning_rate": 1.800157297483417e-05,
      "loss": 10.3501,
      "step": 147
    },
    {
      "epoch": 0.925,
      "grad_norm": 0.05831804499030113,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 10.352,
      "step": 148
    },
    {
      "epoch": 0.93125,
      "grad_norm": 0.04748042672872543,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 10.3514,
      "step": 149
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.04899962991476059,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 10.3541,
      "step": 150
    },
    {
      "epoch": 0.9375,
      "eval_loss": 10.352654457092285,
      "eval_runtime": 0.588,
      "eval_samples_per_second": 459.208,
      "eval_steps_per_second": 115.652,
      "step": 150
    },
    {
      "epoch": 0.94375,
      "grad_norm": 0.06384117156267166,
      "learning_rate": 1.553232954407171e-05,
      "loss": 10.3474,
      "step": 151
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.06839928030967712,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 10.3536,
      "step": 152
    },
    {
      "epoch": 0.95625,
      "grad_norm": 0.07641822099685669,
      "learning_rate": 1.435357758543015e-05,
      "loss": 10.35,
      "step": 153
    },
    {
      "epoch": 0.9625,
      "grad_norm": 0.06236473470926285,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 10.3468,
      "step": 154
    },
    {
      "epoch": 0.96875,
      "grad_norm": 0.09652981907129288,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 10.3417,
      "step": 155
    },
    {
      "epoch": 0.975,
      "grad_norm": 0.08992639929056168,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 10.3471,
      "step": 156
    },
    {
      "epoch": 0.98125,
      "grad_norm": 0.08130533993244171,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 10.3487,
      "step": 157
    },
    {
      "epoch": 0.9875,
      "grad_norm": 0.12119293212890625,
      "learning_rate": 1.157994445715706e-05,
      "loss": 10.3414,
      "step": 158
    },
    {
      "epoch": 0.99375,
      "grad_norm": 0.14771638810634613,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 10.3473,
      "step": 159
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.21836015582084656,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 10.3452,
      "step": 160
    },
    {
      "epoch": 1.00625,
      "grad_norm": 0.07928885519504547,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 10.3586,
      "step": 161
    },
    {
      "epoch": 1.0125,
      "grad_norm": 0.058356594294309616,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3572,
      "step": 162
    },
    {
      "epoch": 1.01875,
      "grad_norm": 0.059847019612789154,
      "learning_rate": 9.068759265665384e-06,
      "loss": 10.3539,
      "step": 163
    },
    {
      "epoch": 1.025,
      "grad_norm": 0.04969866946339607,
      "learning_rate": 8.599558442598998e-06,
      "loss": 10.3546,
      "step": 164
    },
    {
      "epoch": 1.03125,
      "grad_norm": 0.05429890379309654,
      "learning_rate": 8.141676086873572e-06,
      "loss": 10.3534,
      "step": 165
    },
    {
      "epoch": 1.0375,
      "grad_norm": 0.05387968197464943,
      "learning_rate": 7.695237378953223e-06,
      "loss": 10.3549,
      "step": 166
    },
    {
      "epoch": 1.04375,
      "grad_norm": 0.057014212012290955,
      "learning_rate": 7.260364370723044e-06,
      "loss": 10.3534,
      "step": 167
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.04998062551021576,
      "learning_rate": 6.837175952121306e-06,
      "loss": 10.3535,
      "step": 168
    },
    {
      "epoch": 1.05625,
      "grad_norm": 0.05028769001364708,
      "learning_rate": 6.425787818636131e-06,
      "loss": 10.3533,
      "step": 169
    },
    {
      "epoch": 1.0625,
      "grad_norm": 0.04779903590679169,
      "learning_rate": 6.026312439675552e-06,
      "loss": 10.3506,
      "step": 170
    },
    {
      "epoch": 1.06875,
      "grad_norm": 0.03619011119008064,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 10.3515,
      "step": 171
    },
    {
      "epoch": 1.075,
      "grad_norm": 0.044742800295352936,
      "learning_rate": 5.263533508961827e-06,
      "loss": 10.3527,
      "step": 172
    },
    {
      "epoch": 1.08125,
      "grad_norm": 0.03877142071723938,
      "learning_rate": 4.900438493352055e-06,
      "loss": 10.3548,
      "step": 173
    },
    {
      "epoch": 1.0875,
      "grad_norm": 0.04972178116440773,
      "learning_rate": 4.549673247541875e-06,
      "loss": 10.356,
      "step": 174
    },
    {
      "epoch": 1.09375,
      "grad_norm": 0.0364697091281414,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 10.3527,
      "step": 175
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.05496422201395035,
      "learning_rate": 3.885512251130763e-06,
      "loss": 10.3537,
      "step": 176
    },
    {
      "epoch": 1.10625,
      "grad_norm": 0.047787848860025406,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 10.3537,
      "step": 177
    },
    {
      "epoch": 1.1125,
      "grad_norm": 0.051353756338357925,
      "learning_rate": 3.271776770026963e-06,
      "loss": 10.3531,
      "step": 178
    },
    {
      "epoch": 1.11875,
      "grad_norm": 0.053095653653144836,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 10.3513,
      "step": 179
    },
    {
      "epoch": 1.125,
      "grad_norm": 0.03344526141881943,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 10.3472,
      "step": 180
    },
    {
      "epoch": 1.13125,
      "grad_norm": 0.04324382543563843,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 10.3524,
      "step": 181
    },
    {
      "epoch": 1.1375,
      "grad_norm": 0.041307445615530014,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 10.3543,
      "step": 182
    },
    {
      "epoch": 1.14375,
      "grad_norm": 0.038289766758680344,
      "learning_rate": 1.962316193157593e-06,
      "loss": 10.3512,
      "step": 183
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.03312395513057709,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 10.351,
      "step": 184
    },
    {
      "epoch": 1.15625,
      "grad_norm": 0.0453076995909214,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 10.3525,
      "step": 185
    },
    {
      "epoch": 1.1625,
      "grad_norm": 0.04328174889087677,
      "learning_rate": 1.333670137599713e-06,
      "loss": 10.3531,
      "step": 186
    },
    {
      "epoch": 1.16875,
      "grad_norm": 0.04594443365931511,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 10.3519,
      "step": 187
    },
    {
      "epoch": 1.175,
      "grad_norm": 0.05437992885708809,
      "learning_rate": 9.810017062595322e-07,
      "loss": 10.3502,
      "step": 188
    },
    {
      "epoch": 1.18125,
      "grad_norm": 0.07186569273471832,
      "learning_rate": 8.247462563808817e-07,
      "loss": 10.3505,
      "step": 189
    },
    {
      "epoch": 1.1875,
      "grad_norm": 0.06211891770362854,
      "learning_rate": 6.819348298638839e-07,
      "loss": 10.3516,
      "step": 190
    },
    {
      "epoch": 1.19375,
      "grad_norm": 0.06346860527992249,
      "learning_rate": 5.526064699265753e-07,
      "loss": 10.3516,
      "step": 191
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.0640961304306984,
      "learning_rate": 4.367965336512403e-07,
      "loss": 10.3487,
      "step": 192
    },
    {
      "epoch": 1.20625,
      "grad_norm": 0.06364618241786957,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 10.3497,
      "step": 193
    },
    {
      "epoch": 1.2125,
      "grad_norm": 0.0918857604265213,
      "learning_rate": 2.458548727494292e-07,
      "loss": 10.3469,
      "step": 194
    },
    {
      "epoch": 1.21875,
      "grad_norm": 0.0839105099439621,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 10.3453,
      "step": 195
    },
    {
      "epoch": 1.225,
      "grad_norm": 0.09951995313167572,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 10.3474,
      "step": 196
    },
    {
      "epoch": 1.23125,
      "grad_norm": 0.07501597702503204,
      "learning_rate": 6.150154258476315e-08,
      "loss": 10.3499,
      "step": 197
    },
    {
      "epoch": 1.2375,
      "grad_norm": 0.11409381777048111,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 10.3454,
      "step": 198
    },
    {
      "epoch": 1.24375,
      "grad_norm": 0.15242773294448853,
      "learning_rate": 6.834750376549792e-09,
      "loss": 10.3484,
      "step": 199
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.21588319540023804,
      "learning_rate": 0.0,
      "loss": 10.339,
      "step": 200
    },
    {
      "epoch": 1.25,
      "eval_loss": 10.352631568908691,
      "eval_runtime": 0.6001,
      "eval_samples_per_second": 449.929,
      "eval_steps_per_second": 113.315,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 22561121107968.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}