{
  "best_metric": 10.333786964416504,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.11312217194570136,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005656108597285068,
      "grad_norm": 0.062021128833293915,
      "learning_rate": 1.0100000000000002e-05,
      "loss": 10.38,
      "step": 1
    },
    {
      "epoch": 0.0005656108597285068,
      "eval_loss": 10.380452156066895,
      "eval_runtime": 8.0865,
      "eval_samples_per_second": 2945.633,
      "eval_steps_per_second": 92.128,
      "step": 1
    },
    {
      "epoch": 0.0011312217194570137,
      "grad_norm": 0.053750570863485336,
      "learning_rate": 2.0200000000000003e-05,
      "loss": 10.3795,
      "step": 2
    },
    {
      "epoch": 0.0016968325791855204,
      "grad_norm": 0.05637124180793762,
      "learning_rate": 3.0299999999999998e-05,
      "loss": 10.3798,
      "step": 3
    },
    {
      "epoch": 0.0022624434389140274,
      "grad_norm": 0.05955745279788971,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 10.3783,
      "step": 4
    },
    {
      "epoch": 0.002828054298642534,
      "grad_norm": 0.05484645813703537,
      "learning_rate": 5.05e-05,
      "loss": 10.3809,
      "step": 5
    },
    {
      "epoch": 0.003393665158371041,
      "grad_norm": 0.0704905167222023,
      "learning_rate": 6.0599999999999996e-05,
      "loss": 10.3812,
      "step": 6
    },
    {
      "epoch": 0.003959276018099547,
      "grad_norm": 0.06389003992080688,
      "learning_rate": 7.07e-05,
      "loss": 10.3791,
      "step": 7
    },
    {
      "epoch": 0.004524886877828055,
      "grad_norm": 0.05992201343178749,
      "learning_rate": 8.080000000000001e-05,
      "loss": 10.3783,
      "step": 8
    },
    {
      "epoch": 0.005090497737556561,
      "grad_norm": 0.06138139218091965,
      "learning_rate": 9.09e-05,
      "loss": 10.3794,
      "step": 9
    },
    {
      "epoch": 0.005656108597285068,
      "grad_norm": 0.06030235439538956,
      "learning_rate": 0.000101,
      "loss": 10.3799,
      "step": 10
    },
    {
      "epoch": 0.006221719457013574,
      "grad_norm": 0.06504027545452118,
      "learning_rate": 0.00010046842105263158,
      "loss": 10.3793,
      "step": 11
    },
    {
      "epoch": 0.006787330316742082,
      "grad_norm": 0.0788484662771225,
      "learning_rate": 9.993684210526315e-05,
      "loss": 10.3778,
      "step": 12
    },
    {
      "epoch": 0.007352941176470588,
      "grad_norm": 0.06486255675554276,
      "learning_rate": 9.940526315789473e-05,
      "loss": 10.377,
      "step": 13
    },
    {
      "epoch": 0.007918552036199095,
      "grad_norm": 0.07012791931629181,
      "learning_rate": 9.887368421052632e-05,
      "loss": 10.3765,
      "step": 14
    },
    {
      "epoch": 0.008484162895927601,
      "grad_norm": 0.07867205142974854,
      "learning_rate": 9.83421052631579e-05,
      "loss": 10.3772,
      "step": 15
    },
    {
      "epoch": 0.00904977375565611,
      "grad_norm": 0.07887768745422363,
      "learning_rate": 9.781052631578948e-05,
      "loss": 10.3753,
      "step": 16
    },
    {
      "epoch": 0.009615384615384616,
      "grad_norm": 0.08439292013645172,
      "learning_rate": 9.727894736842106e-05,
      "loss": 10.3755,
      "step": 17
    },
    {
      "epoch": 0.010180995475113122,
      "grad_norm": 0.09982705861330032,
      "learning_rate": 9.674736842105263e-05,
      "loss": 10.3748,
      "step": 18
    },
    {
      "epoch": 0.010746606334841629,
      "grad_norm": 0.0821399837732315,
      "learning_rate": 9.621578947368421e-05,
      "loss": 10.3751,
      "step": 19
    },
    {
      "epoch": 0.011312217194570135,
      "grad_norm": 0.10993044823408127,
      "learning_rate": 9.568421052631578e-05,
      "loss": 10.3726,
      "step": 20
    },
    {
      "epoch": 0.011877828054298642,
      "grad_norm": 0.09375250339508057,
      "learning_rate": 9.515263157894737e-05,
      "loss": 10.3728,
      "step": 21
    },
    {
      "epoch": 0.012443438914027148,
      "grad_norm": 0.10467270761728287,
      "learning_rate": 9.462105263157895e-05,
      "loss": 10.3732,
      "step": 22
    },
    {
      "epoch": 0.013009049773755657,
      "grad_norm": 0.11246021836996078,
      "learning_rate": 9.408947368421054e-05,
      "loss": 10.3718,
      "step": 23
    },
    {
      "epoch": 0.013574660633484163,
      "grad_norm": 0.1300632804632187,
      "learning_rate": 9.355789473684211e-05,
      "loss": 10.3706,
      "step": 24
    },
    {
      "epoch": 0.01414027149321267,
      "grad_norm": 0.16326434910297394,
      "learning_rate": 9.302631578947369e-05,
      "loss": 10.3704,
      "step": 25
    },
    {
      "epoch": 0.014705882352941176,
      "grad_norm": 0.13459563255310059,
      "learning_rate": 9.249473684210526e-05,
      "loss": 10.3687,
      "step": 26
    },
    {
      "epoch": 0.015271493212669683,
      "grad_norm": 0.12868914008140564,
      "learning_rate": 9.196315789473685e-05,
      "loss": 10.3698,
      "step": 27
    },
    {
      "epoch": 0.01583710407239819,
      "grad_norm": 0.14536577463150024,
      "learning_rate": 9.143157894736843e-05,
      "loss": 10.3672,
      "step": 28
    },
    {
      "epoch": 0.016402714932126698,
      "grad_norm": 0.14456918835639954,
      "learning_rate": 9.09e-05,
      "loss": 10.3665,
      "step": 29
    },
    {
      "epoch": 0.016968325791855202,
      "grad_norm": 0.15334004163742065,
      "learning_rate": 9.036842105263158e-05,
      "loss": 10.3661,
      "step": 30
    },
    {
      "epoch": 0.01753393665158371,
      "grad_norm": 0.18508021533489227,
      "learning_rate": 8.983684210526316e-05,
      "loss": 10.3633,
      "step": 31
    },
    {
      "epoch": 0.01809954751131222,
      "grad_norm": 0.15807212889194489,
      "learning_rate": 8.930526315789474e-05,
      "loss": 10.3645,
      "step": 32
    },
    {
      "epoch": 0.018665158371040724,
      "grad_norm": 0.15088380873203278,
      "learning_rate": 8.877368421052632e-05,
      "loss": 10.3629,
      "step": 33
    },
    {
      "epoch": 0.019230769230769232,
      "grad_norm": 0.1459580808877945,
      "learning_rate": 8.82421052631579e-05,
      "loss": 10.3616,
      "step": 34
    },
    {
      "epoch": 0.019796380090497737,
      "grad_norm": 0.14841324090957642,
      "learning_rate": 8.771052631578948e-05,
      "loss": 10.3609,
      "step": 35
    },
    {
      "epoch": 0.020361990950226245,
      "grad_norm": 0.15354986488819122,
      "learning_rate": 8.717894736842105e-05,
      "loss": 10.3602,
      "step": 36
    },
    {
      "epoch": 0.02092760180995475,
      "grad_norm": 0.17225728929042816,
      "learning_rate": 8.664736842105263e-05,
      "loss": 10.3598,
      "step": 37
    },
    {
      "epoch": 0.021493212669683258,
      "grad_norm": 0.1513800323009491,
      "learning_rate": 8.61157894736842e-05,
      "loss": 10.3605,
      "step": 38
    },
    {
      "epoch": 0.022058823529411766,
      "grad_norm": 0.14970330893993378,
      "learning_rate": 8.55842105263158e-05,
      "loss": 10.3568,
      "step": 39
    },
    {
      "epoch": 0.02262443438914027,
      "grad_norm": 0.14152267575263977,
      "learning_rate": 8.505263157894737e-05,
      "loss": 10.3571,
      "step": 40
    },
    {
      "epoch": 0.02319004524886878,
      "grad_norm": 0.11801969259977341,
      "learning_rate": 8.452105263157896e-05,
      "loss": 10.3565,
      "step": 41
    },
    {
      "epoch": 0.023755656108597284,
      "grad_norm": 0.13193698227405548,
      "learning_rate": 8.398947368421053e-05,
      "loss": 10.3548,
      "step": 42
    },
    {
      "epoch": 0.024321266968325792,
      "grad_norm": 0.12654702365398407,
      "learning_rate": 8.345789473684211e-05,
      "loss": 10.3526,
      "step": 43
    },
    {
      "epoch": 0.024886877828054297,
      "grad_norm": 0.12153801321983337,
      "learning_rate": 8.292631578947368e-05,
      "loss": 10.3572,
      "step": 44
    },
    {
      "epoch": 0.025452488687782805,
      "grad_norm": 0.11495444178581238,
      "learning_rate": 8.239473684210526e-05,
      "loss": 10.3546,
      "step": 45
    },
    {
      "epoch": 0.026018099547511313,
      "grad_norm": 0.09821103513240814,
      "learning_rate": 8.186315789473683e-05,
      "loss": 10.3542,
      "step": 46
    },
    {
      "epoch": 0.026583710407239818,
      "grad_norm": 0.09399436414241791,
      "learning_rate": 8.133157894736842e-05,
      "loss": 10.3539,
      "step": 47
    },
    {
      "epoch": 0.027149321266968326,
      "grad_norm": 0.10562458634376526,
      "learning_rate": 8.080000000000001e-05,
      "loss": 10.3534,
      "step": 48
    },
    {
      "epoch": 0.02771493212669683,
      "grad_norm": 0.10220655053853989,
      "learning_rate": 8.026842105263159e-05,
      "loss": 10.3517,
      "step": 49
    },
    {
      "epoch": 0.02828054298642534,
      "grad_norm": 0.13333728909492493,
      "learning_rate": 7.973684210526316e-05,
      "loss": 10.3467,
      "step": 50
    },
    {
      "epoch": 0.02828054298642534,
      "eval_loss": 10.350386619567871,
      "eval_runtime": 8.1717,
      "eval_samples_per_second": 2914.943,
      "eval_steps_per_second": 91.168,
      "step": 50
    },
    {
      "epoch": 0.028846153846153848,
      "grad_norm": 0.12691977620124817,
      "learning_rate": 7.920526315789474e-05,
      "loss": 10.3513,
      "step": 51
    },
    {
      "epoch": 0.029411764705882353,
      "grad_norm": 0.08717770874500275,
      "learning_rate": 7.867368421052631e-05,
      "loss": 10.3522,
      "step": 52
    },
    {
      "epoch": 0.02997737556561086,
      "grad_norm": 0.06944411247968674,
      "learning_rate": 7.814210526315789e-05,
      "loss": 10.3525,
      "step": 53
    },
    {
      "epoch": 0.030542986425339366,
      "grad_norm": 0.07963120192289352,
      "learning_rate": 7.761052631578946e-05,
      "loss": 10.3511,
      "step": 54
    },
    {
      "epoch": 0.031108597285067874,
      "grad_norm": 0.0897977203130722,
      "learning_rate": 7.707894736842105e-05,
      "loss": 10.3484,
      "step": 55
    },
    {
      "epoch": 0.03167420814479638,
      "grad_norm": 0.08346674591302872,
      "learning_rate": 7.654736842105264e-05,
      "loss": 10.3466,
      "step": 56
    },
    {
      "epoch": 0.03223981900452489,
      "grad_norm": 0.11057797819375992,
      "learning_rate": 7.601578947368422e-05,
      "loss": 10.3507,
      "step": 57
    },
    {
      "epoch": 0.032805429864253395,
      "grad_norm": 0.07332270592451096,
      "learning_rate": 7.548421052631579e-05,
      "loss": 10.3516,
      "step": 58
    },
    {
      "epoch": 0.0333710407239819,
      "grad_norm": 0.05284840986132622,
      "learning_rate": 7.495263157894737e-05,
      "loss": 10.3498,
      "step": 59
    },
    {
      "epoch": 0.033936651583710405,
      "grad_norm": 0.06752610951662064,
      "learning_rate": 7.442105263157894e-05,
      "loss": 10.3497,
      "step": 60
    },
    {
      "epoch": 0.034502262443438916,
      "grad_norm": 0.06512323766946793,
      "learning_rate": 7.388947368421053e-05,
      "loss": 10.3478,
      "step": 61
    },
    {
      "epoch": 0.03506787330316742,
      "grad_norm": 0.0671728327870369,
      "learning_rate": 7.335789473684211e-05,
      "loss": 10.3461,
      "step": 62
    },
    {
      "epoch": 0.035633484162895926,
      "grad_norm": 0.07600655406713486,
      "learning_rate": 7.282631578947368e-05,
      "loss": 10.3527,
      "step": 63
    },
    {
      "epoch": 0.03619909502262444,
      "grad_norm": 0.0868535041809082,
      "learning_rate": 7.229473684210527e-05,
      "loss": 10.3483,
      "step": 64
    },
    {
      "epoch": 0.03676470588235294,
      "grad_norm": 0.05451541021466255,
      "learning_rate": 7.176315789473685e-05,
      "loss": 10.347,
      "step": 65
    },
    {
      "epoch": 0.03733031674208145,
      "grad_norm": 0.0499880388379097,
      "learning_rate": 7.123157894736842e-05,
      "loss": 10.348,
      "step": 66
    },
    {
      "epoch": 0.03789592760180995,
      "grad_norm": 0.056676704436540604,
      "learning_rate": 7.07e-05,
      "loss": 10.3474,
      "step": 67
    },
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 0.06582105159759521,
      "learning_rate": 7.016842105263159e-05,
      "loss": 10.3454,
      "step": 68
    },
    {
      "epoch": 0.03902714932126697,
      "grad_norm": 0.07939665019512177,
      "learning_rate": 6.963684210526316e-05,
      "loss": 10.3508,
      "step": 69
    },
    {
      "epoch": 0.03959276018099547,
      "grad_norm": 0.07071398943662643,
      "learning_rate": 6.910526315789474e-05,
      "loss": 10.3478,
      "step": 70
    },
    {
      "epoch": 0.040158371040723985,
      "grad_norm": 0.05655914917588234,
      "learning_rate": 6.857368421052631e-05,
      "loss": 10.3488,
      "step": 71
    },
    {
      "epoch": 0.04072398190045249,
      "grad_norm": 0.04718935862183571,
      "learning_rate": 6.80421052631579e-05,
      "loss": 10.3471,
      "step": 72
    },
    {
      "epoch": 0.041289592760180995,
      "grad_norm": 0.05402664840221405,
      "learning_rate": 6.751052631578948e-05,
      "loss": 10.3492,
      "step": 73
    },
    {
      "epoch": 0.0418552036199095,
      "grad_norm": 0.06643565744161606,
      "learning_rate": 6.697894736842105e-05,
      "loss": 10.3456,
      "step": 74
    },
    {
      "epoch": 0.04242081447963801,
      "grad_norm": 0.07058984041213989,
      "learning_rate": 6.644736842105264e-05,
      "loss": 10.3428,
      "step": 75
    },
    {
      "epoch": 0.042986425339366516,
      "grad_norm": 0.09027786552906036,
      "learning_rate": 6.591578947368422e-05,
      "loss": 10.3491,
      "step": 76
    },
    {
      "epoch": 0.04355203619909502,
      "grad_norm": 0.047901950776576996,
      "learning_rate": 6.538421052631579e-05,
      "loss": 10.349,
      "step": 77
    },
    {
      "epoch": 0.04411764705882353,
      "grad_norm": 0.04141535609960556,
      "learning_rate": 6.485263157894737e-05,
      "loss": 10.3488,
      "step": 78
    },
    {
      "epoch": 0.04468325791855204,
      "grad_norm": 0.04282054677605629,
      "learning_rate": 6.432105263157894e-05,
      "loss": 10.3473,
      "step": 79
    },
    {
      "epoch": 0.04524886877828054,
      "grad_norm": 0.05405720695853233,
      "learning_rate": 6.378947368421053e-05,
      "loss": 10.3454,
      "step": 80
    },
    {
      "epoch": 0.04581447963800905,
      "grad_norm": 0.06005045026540756,
      "learning_rate": 6.32578947368421e-05,
      "loss": 10.3433,
      "step": 81
    },
    {
      "epoch": 0.04638009049773756,
      "grad_norm": 0.10236992686986923,
      "learning_rate": 6.27263157894737e-05,
      "loss": 10.35,
      "step": 82
    },
    {
      "epoch": 0.04694570135746606,
      "grad_norm": 0.07769302278757095,
      "learning_rate": 6.219473684210527e-05,
      "loss": 10.3463,
      "step": 83
    },
    {
      "epoch": 0.04751131221719457,
      "grad_norm": 0.03876901790499687,
      "learning_rate": 6.166315789473685e-05,
      "loss": 10.3472,
      "step": 84
    },
    {
      "epoch": 0.04807692307692308,
      "grad_norm": 0.03502112627029419,
      "learning_rate": 6.113157894736842e-05,
      "loss": 10.3474,
      "step": 85
    },
    {
      "epoch": 0.048642533936651584,
      "grad_norm": 0.06084531545639038,
      "learning_rate": 6.0599999999999996e-05,
      "loss": 10.3461,
      "step": 86
    },
    {
      "epoch": 0.04920814479638009,
      "grad_norm": 0.07850203663110733,
      "learning_rate": 6.006842105263158e-05,
      "loss": 10.3443,
      "step": 87
    },
    {
      "epoch": 0.049773755656108594,
      "grad_norm": 0.09611647576093674,
      "learning_rate": 5.953684210526315e-05,
      "loss": 10.3509,
      "step": 88
    },
    {
      "epoch": 0.050339366515837106,
      "grad_norm": 0.07283317297697067,
      "learning_rate": 5.900526315789474e-05,
      "loss": 10.3477,
      "step": 89
    },
    {
      "epoch": 0.05090497737556561,
      "grad_norm": 0.04070362076163292,
      "learning_rate": 5.847368421052632e-05,
      "loss": 10.3477,
      "step": 90
    },
    {
      "epoch": 0.051470588235294115,
      "grad_norm": 0.04328368604183197,
      "learning_rate": 5.79421052631579e-05,
      "loss": 10.3458,
      "step": 91
    },
    {
      "epoch": 0.05203619909502263,
      "grad_norm": 0.048710327595472336,
      "learning_rate": 5.7410526315789475e-05,
      "loss": 10.3459,
      "step": 92
    },
    {
      "epoch": 0.05260180995475113,
      "grad_norm": 0.07019612193107605,
      "learning_rate": 5.687894736842105e-05,
      "loss": 10.3449,
      "step": 93
    },
    {
      "epoch": 0.053167420814479636,
      "grad_norm": 0.07387306541204453,
      "learning_rate": 5.6347368421052625e-05,
      "loss": 10.3485,
      "step": 94
    },
    {
      "epoch": 0.05373303167420815,
      "grad_norm": 0.08147264271974564,
      "learning_rate": 5.5815789473684214e-05,
      "loss": 10.347,
      "step": 95
    },
    {
      "epoch": 0.05429864253393665,
      "grad_norm": 0.06585867702960968,
      "learning_rate": 5.5284210526315796e-05,
      "loss": 10.3463,
      "step": 96
    },
    {
      "epoch": 0.05486425339366516,
      "grad_norm": 0.046585794538259506,
      "learning_rate": 5.475263157894737e-05,
      "loss": 10.3451,
      "step": 97
    },
    {
      "epoch": 0.05542986425339366,
      "grad_norm": 0.05905357748270035,
      "learning_rate": 5.422105263157895e-05,
      "loss": 10.3458,
      "step": 98
    },
    {
      "epoch": 0.055995475113122174,
      "grad_norm": 0.06317008286714554,
      "learning_rate": 5.368947368421053e-05,
      "loss": 10.3458,
      "step": 99
    },
    {
      "epoch": 0.05656108597285068,
      "grad_norm": 0.08555221557617188,
      "learning_rate": 5.3157894736842104e-05,
      "loss": 10.3401,
      "step": 100
    },
    {
      "epoch": 0.05656108597285068,
      "eval_loss": 10.344589233398438,
      "eval_runtime": 8.2091,
      "eval_samples_per_second": 2901.663,
      "eval_steps_per_second": 90.753,
      "step": 100
    },
    {
      "epoch": 0.057126696832579184,
      "grad_norm": 0.09945505112409592,
      "learning_rate": 5.262631578947368e-05,
      "loss": 10.3451,
      "step": 101
    },
    {
      "epoch": 0.057692307692307696,
      "grad_norm": 0.04811963438987732,
      "learning_rate": 5.209473684210527e-05,
      "loss": 10.3452,
      "step": 102
    },
    {
      "epoch": 0.0582579185520362,
      "grad_norm": 0.043795328587293625,
      "learning_rate": 5.1563157894736844e-05,
      "loss": 10.3436,
      "step": 103
    },
    {
      "epoch": 0.058823529411764705,
      "grad_norm": 0.05168459936976433,
      "learning_rate": 5.1031578947368426e-05,
      "loss": 10.3442,
      "step": 104
    },
    {
      "epoch": 0.05938914027149321,
      "grad_norm": 0.06889228522777557,
      "learning_rate": 5.05e-05,
      "loss": 10.344,
      "step": 105
    },
    {
      "epoch": 0.05995475113122172,
      "grad_norm": 0.07568846642971039,
      "learning_rate": 4.9968421052631576e-05,
      "loss": 10.3411,
      "step": 106
    },
    {
      "epoch": 0.060520361990950226,
      "grad_norm": 0.09742461889982224,
      "learning_rate": 4.943684210526316e-05,
      "loss": 10.3466,
      "step": 107
    },
    {
      "epoch": 0.06108597285067873,
      "grad_norm": 0.08516088128089905,
      "learning_rate": 4.890526315789474e-05,
      "loss": 10.3427,
      "step": 108
    },
    {
      "epoch": 0.06165158371040724,
      "grad_norm": 0.05197165533900261,
      "learning_rate": 4.8373684210526316e-05,
      "loss": 10.3429,
      "step": 109
    },
    {
      "epoch": 0.06221719457013575,
      "grad_norm": 0.05537767708301544,
      "learning_rate": 4.784210526315789e-05,
      "loss": 10.3442,
      "step": 110
    },
    {
      "epoch": 0.06278280542986425,
      "grad_norm": 0.06518259644508362,
      "learning_rate": 4.731052631578947e-05,
      "loss": 10.3444,
      "step": 111
    },
    {
      "epoch": 0.06334841628959276,
      "grad_norm": 0.06740637868642807,
      "learning_rate": 4.6778947368421055e-05,
      "loss": 10.3408,
      "step": 112
    },
    {
      "epoch": 0.06391402714932126,
      "grad_norm": 0.09538576751947403,
      "learning_rate": 4.624736842105263e-05,
      "loss": 10.3463,
      "step": 113
    },
    {
      "epoch": 0.06447963800904978,
      "grad_norm": 0.08066005259752274,
      "learning_rate": 4.571578947368421e-05,
      "loss": 10.3457,
      "step": 114
    },
    {
      "epoch": 0.06504524886877829,
      "grad_norm": 0.06505700945854187,
      "learning_rate": 4.518421052631579e-05,
      "loss": 10.3432,
      "step": 115
    },
    {
      "epoch": 0.06561085972850679,
      "grad_norm": 0.05407899618148804,
      "learning_rate": 4.465263157894737e-05,
      "loss": 10.3417,
      "step": 116
    },
    {
      "epoch": 0.0661764705882353,
      "grad_norm": 0.06977938115596771,
      "learning_rate": 4.412105263157895e-05,
      "loss": 10.3432,
      "step": 117
    },
    {
      "epoch": 0.0667420814479638,
      "grad_norm": 0.07747713476419449,
      "learning_rate": 4.358947368421053e-05,
      "loss": 10.3408,
      "step": 118
    },
    {
      "epoch": 0.0673076923076923,
      "grad_norm": 0.09030125290155411,
      "learning_rate": 4.30578947368421e-05,
      "loss": 10.3474,
      "step": 119
    },
    {
      "epoch": 0.06787330316742081,
      "grad_norm": 0.08575378358364105,
      "learning_rate": 4.2526315789473685e-05,
      "loss": 10.3429,
      "step": 120
    },
    {
      "epoch": 0.06843891402714933,
      "grad_norm": 0.06714797765016556,
      "learning_rate": 4.199473684210527e-05,
      "loss": 10.3433,
      "step": 121
    },
    {
      "epoch": 0.06900452488687783,
      "grad_norm": 0.05677073448896408,
      "learning_rate": 4.146315789473684e-05,
      "loss": 10.3432,
      "step": 122
    },
    {
      "epoch": 0.06957013574660634,
      "grad_norm": 0.059628356248140335,
      "learning_rate": 4.093157894736842e-05,
      "loss": 10.3412,
      "step": 123
    },
    {
      "epoch": 0.07013574660633484,
      "grad_norm": 0.06992416828870773,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 10.3418,
      "step": 124
    },
    {
      "epoch": 0.07070135746606335,
      "grad_norm": 0.09124021232128143,
      "learning_rate": 3.986842105263158e-05,
      "loss": 10.3367,
      "step": 125
    },
    {
      "epoch": 0.07126696832579185,
      "grad_norm": 0.10908302664756775,
      "learning_rate": 3.933684210526316e-05,
      "loss": 10.3426,
      "step": 126
    },
    {
      "epoch": 0.07183257918552036,
      "grad_norm": 0.08162763714790344,
      "learning_rate": 3.880526315789473e-05,
      "loss": 10.3418,
      "step": 127
    },
    {
      "epoch": 0.07239819004524888,
      "grad_norm": 0.05531831085681915,
      "learning_rate": 3.827368421052632e-05,
      "loss": 10.3389,
      "step": 128
    },
    {
      "epoch": 0.07296380090497738,
      "grad_norm": 0.06366059929132462,
      "learning_rate": 3.7742105263157896e-05,
      "loss": 10.338,
      "step": 129
    },
    {
      "epoch": 0.07352941176470588,
      "grad_norm": 0.06867145001888275,
      "learning_rate": 3.721052631578947e-05,
      "loss": 10.3417,
      "step": 130
    },
    {
      "epoch": 0.07409502262443439,
      "grad_norm": 0.10291559994220734,
      "learning_rate": 3.6678947368421054e-05,
      "loss": 10.3357,
      "step": 131
    },
    {
      "epoch": 0.0746606334841629,
      "grad_norm": 0.09882048517465591,
      "learning_rate": 3.6147368421052636e-05,
      "loss": 10.3433,
      "step": 132
    },
    {
      "epoch": 0.0752262443438914,
      "grad_norm": 0.07626540958881378,
      "learning_rate": 3.561578947368421e-05,
      "loss": 10.3397,
      "step": 133
    },
    {
      "epoch": 0.0757918552036199,
      "grad_norm": 0.04596826434135437,
      "learning_rate": 3.508421052631579e-05,
      "loss": 10.3394,
      "step": 134
    },
    {
      "epoch": 0.07635746606334842,
      "grad_norm": 0.0479527972638607,
      "learning_rate": 3.455263157894737e-05,
      "loss": 10.3388,
      "step": 135
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.07407166063785553,
      "learning_rate": 3.402105263157895e-05,
      "loss": 10.34,
      "step": 136
    },
    {
      "epoch": 0.07748868778280543,
      "grad_norm": 0.09090636670589447,
      "learning_rate": 3.3489473684210526e-05,
      "loss": 10.3363,
      "step": 137
    },
    {
      "epoch": 0.07805429864253394,
      "grad_norm": 0.08997251093387604,
      "learning_rate": 3.295789473684211e-05,
      "loss": 10.3424,
      "step": 138
    },
    {
      "epoch": 0.07861990950226244,
      "grad_norm": 0.07923514395952225,
      "learning_rate": 3.242631578947368e-05,
      "loss": 10.3398,
      "step": 139
    },
    {
      "epoch": 0.07918552036199095,
      "grad_norm": 0.07008980959653854,
      "learning_rate": 3.1894736842105265e-05,
      "loss": 10.3375,
      "step": 140
    },
    {
      "epoch": 0.07975113122171945,
      "grad_norm": 0.049700357019901276,
      "learning_rate": 3.136315789473685e-05,
      "loss": 10.3388,
      "step": 141
    },
    {
      "epoch": 0.08031674208144797,
      "grad_norm": 0.06060990318655968,
      "learning_rate": 3.083157894736842e-05,
      "loss": 10.3363,
      "step": 142
    },
    {
      "epoch": 0.08088235294117647,
      "grad_norm": 0.08178900182247162,
      "learning_rate": 3.0299999999999998e-05,
      "loss": 10.3372,
      "step": 143
    },
    {
      "epoch": 0.08144796380090498,
      "grad_norm": 0.09628574550151825,
      "learning_rate": 2.9768421052631577e-05,
      "loss": 10.3433,
      "step": 144
    },
    {
      "epoch": 0.08201357466063348,
      "grad_norm": 0.08116014301776886,
      "learning_rate": 2.923684210526316e-05,
      "loss": 10.3396,
      "step": 145
    },
    {
      "epoch": 0.08257918552036199,
      "grad_norm": 0.05855511128902435,
      "learning_rate": 2.8705263157894737e-05,
      "loss": 10.3388,
      "step": 146
    },
    {
      "epoch": 0.0831447963800905,
      "grad_norm": 0.045891135931015015,
      "learning_rate": 2.8173684210526313e-05,
      "loss": 10.3368,
      "step": 147
    },
    {
      "epoch": 0.083710407239819,
      "grad_norm": 0.06934593617916107,
      "learning_rate": 2.7642105263157898e-05,
      "loss": 10.3369,
      "step": 148
    },
    {
      "epoch": 0.08427601809954752,
      "grad_norm": 0.07505083084106445,
      "learning_rate": 2.7110526315789473e-05,
      "loss": 10.3353,
      "step": 149
    },
    {
      "epoch": 0.08484162895927602,
      "grad_norm": 0.09443920105695724,
      "learning_rate": 2.6578947368421052e-05,
      "loss": 10.3336,
      "step": 150
    },
    {
      "epoch": 0.08484162895927602,
      "eval_loss": 10.336673736572266,
      "eval_runtime": 8.6605,
      "eval_samples_per_second": 2750.409,
      "eval_steps_per_second": 86.022,
      "step": 150
    },
    {
      "epoch": 0.08540723981900453,
      "grad_norm": 0.10061606764793396,
      "learning_rate": 2.6047368421052634e-05,
      "loss": 10.3406,
      "step": 151
    },
    {
      "epoch": 0.08597285067873303,
      "grad_norm": 0.06028294190764427,
      "learning_rate": 2.5515789473684213e-05,
      "loss": 10.3384,
      "step": 152
    },
    {
      "epoch": 0.08653846153846154,
      "grad_norm": 0.0465410090982914,
      "learning_rate": 2.4984210526315788e-05,
      "loss": 10.3362,
      "step": 153
    },
    {
      "epoch": 0.08710407239819004,
      "grad_norm": 0.05667021870613098,
      "learning_rate": 2.445263157894737e-05,
      "loss": 10.3345,
      "step": 154
    },
    {
      "epoch": 0.08766968325791855,
      "grad_norm": 0.06780000030994415,
      "learning_rate": 2.3921052631578946e-05,
      "loss": 10.3364,
      "step": 155
    },
    {
      "epoch": 0.08823529411764706,
      "grad_norm": 0.09162377566099167,
      "learning_rate": 2.3389473684210528e-05,
      "loss": 10.3332,
      "step": 156
    },
    {
      "epoch": 0.08880090497737557,
      "grad_norm": 0.0900709331035614,
      "learning_rate": 2.2857894736842106e-05,
      "loss": 10.3398,
      "step": 157
    },
    {
      "epoch": 0.08936651583710407,
      "grad_norm": 0.06955718994140625,
      "learning_rate": 2.2326315789473685e-05,
      "loss": 10.338,
      "step": 158
    },
    {
      "epoch": 0.08993212669683258,
      "grad_norm": 0.0517783984541893,
      "learning_rate": 2.1794736842105264e-05,
      "loss": 10.3337,
      "step": 159
    },
    {
      "epoch": 0.09049773755656108,
      "grad_norm": 0.05297861248254776,
      "learning_rate": 2.1263157894736842e-05,
      "loss": 10.3348,
      "step": 160
    },
    {
      "epoch": 0.09106334841628959,
      "grad_norm": 0.08668467402458191,
      "learning_rate": 2.073157894736842e-05,
      "loss": 10.3373,
      "step": 161
    },
    {
      "epoch": 0.0916289592760181,
      "grad_norm": 0.08060705661773682,
      "learning_rate": 2.0200000000000003e-05,
      "loss": 10.3338,
      "step": 162
    },
    {
      "epoch": 0.09219457013574661,
      "grad_norm": 0.08586835861206055,
      "learning_rate": 1.966842105263158e-05,
      "loss": 10.3389,
      "step": 163
    },
    {
      "epoch": 0.09276018099547512,
      "grad_norm": 0.07375074923038483,
      "learning_rate": 1.913684210526316e-05,
      "loss": 10.3386,
      "step": 164
    },
    {
      "epoch": 0.09332579185520362,
      "grad_norm": 0.046294908970594406,
      "learning_rate": 1.8605263157894736e-05,
      "loss": 10.3356,
      "step": 165
    },
    {
      "epoch": 0.09389140271493213,
      "grad_norm": 0.04964763671159744,
      "learning_rate": 1.8073684210526318e-05,
      "loss": 10.3364,
      "step": 166
    },
    {
      "epoch": 0.09445701357466063,
      "grad_norm": 0.06984888017177582,
      "learning_rate": 1.7542105263157897e-05,
      "loss": 10.3365,
      "step": 167
    },
    {
      "epoch": 0.09502262443438914,
      "grad_norm": 0.07992294430732727,
      "learning_rate": 1.7010526315789475e-05,
      "loss": 10.3328,
      "step": 168
    },
    {
      "epoch": 0.09558823529411764,
      "grad_norm": 0.08656508475542068,
      "learning_rate": 1.6478947368421054e-05,
      "loss": 10.3398,
      "step": 169
    },
    {
      "epoch": 0.09615384615384616,
      "grad_norm": 0.07822012156248093,
      "learning_rate": 1.5947368421052633e-05,
      "loss": 10.3356,
      "step": 170
    },
    {
      "epoch": 0.09671945701357466,
      "grad_norm": 0.05577806010842323,
      "learning_rate": 1.541578947368421e-05,
      "loss": 10.3354,
      "step": 171
    },
    {
      "epoch": 0.09728506787330317,
      "grad_norm": 0.05001489445567131,
      "learning_rate": 1.4884210526315788e-05,
      "loss": 10.335,
      "step": 172
    },
    {
      "epoch": 0.09785067873303167,
      "grad_norm": 0.07180096209049225,
      "learning_rate": 1.4352631578947369e-05,
      "loss": 10.3366,
      "step": 173
    },
    {
      "epoch": 0.09841628959276018,
      "grad_norm": 0.08262878656387329,
      "learning_rate": 1.3821052631578949e-05,
      "loss": 10.3344,
      "step": 174
    },
    {
      "epoch": 0.09898190045248868,
      "grad_norm": 0.08866975456476212,
      "learning_rate": 1.3289473684210526e-05,
      "loss": 10.3304,
      "step": 175
    },
    {
      "epoch": 0.09954751131221719,
      "grad_norm": 0.08908353745937347,
      "learning_rate": 1.2757894736842106e-05,
      "loss": 10.3387,
      "step": 176
    },
    {
      "epoch": 0.1001131221719457,
      "grad_norm": 0.07283877581357956,
      "learning_rate": 1.2226315789473685e-05,
      "loss": 10.3373,
      "step": 177
    },
    {
      "epoch": 0.10067873303167421,
      "grad_norm": 0.04923555254936218,
      "learning_rate": 1.1694736842105264e-05,
      "loss": 10.3338,
      "step": 178
    },
    {
      "epoch": 0.10124434389140272,
      "grad_norm": 0.056405432522296906,
      "learning_rate": 1.1163157894736842e-05,
      "loss": 10.3338,
      "step": 179
    },
    {
      "epoch": 0.10180995475113122,
      "grad_norm": 0.08115344494581223,
      "learning_rate": 1.0631578947368421e-05,
      "loss": 10.3357,
      "step": 180
    },
    {
      "epoch": 0.10237556561085973,
      "grad_norm": 0.09056730568408966,
      "learning_rate": 1.0100000000000002e-05,
      "loss": 10.3305,
      "step": 181
    },
    {
      "epoch": 0.10294117647058823,
      "grad_norm": 0.0918162390589714,
      "learning_rate": 9.56842105263158e-06,
      "loss": 10.3387,
      "step": 182
    },
    {
      "epoch": 0.10350678733031674,
      "grad_norm": 0.06968989223241806,
      "learning_rate": 9.036842105263159e-06,
      "loss": 10.3346,
      "step": 183
    },
    {
      "epoch": 0.10407239819004525,
      "grad_norm": 0.04789090156555176,
      "learning_rate": 8.505263157894738e-06,
      "loss": 10.3325,
      "step": 184
    },
    {
      "epoch": 0.10463800904977376,
      "grad_norm": 0.05091318488121033,
      "learning_rate": 7.973684210526316e-06,
      "loss": 10.3329,
      "step": 185
    },
    {
      "epoch": 0.10520361990950226,
      "grad_norm": 0.0671328529715538,
      "learning_rate": 7.442105263157894e-06,
      "loss": 10.334,
      "step": 186
    },
    {
      "epoch": 0.10576923076923077,
      "grad_norm": 0.08944947272539139,
      "learning_rate": 6.9105263157894745e-06,
      "loss": 10.3309,
      "step": 187
    },
    {
      "epoch": 0.10633484162895927,
      "grad_norm": 0.09175018966197968,
      "learning_rate": 6.378947368421053e-06,
      "loss": 10.3368,
      "step": 188
    },
    {
      "epoch": 0.10690045248868778,
      "grad_norm": 0.07989748567342758,
      "learning_rate": 5.847368421052632e-06,
      "loss": 10.3345,
      "step": 189
    },
    {
      "epoch": 0.1074660633484163,
      "grad_norm": 0.05122963339090347,
      "learning_rate": 5.315789473684211e-06,
      "loss": 10.3373,
      "step": 190
    },
    {
      "epoch": 0.1080316742081448,
      "grad_norm": 0.04192551225423813,
      "learning_rate": 4.78421052631579e-06,
      "loss": 10.3345,
      "step": 191
    },
    {
      "epoch": 0.1085972850678733,
      "grad_norm": 0.06257504224777222,
      "learning_rate": 4.252631578947369e-06,
      "loss": 10.3357,
      "step": 192
    },
    {
      "epoch": 0.10916289592760181,
      "grad_norm": 0.07879539579153061,
      "learning_rate": 3.721052631578947e-06,
      "loss": 10.3345,
      "step": 193
    },
    {
      "epoch": 0.10972850678733032,
      "grad_norm": 0.09828386455774307,
      "learning_rate": 3.1894736842105266e-06,
      "loss": 10.3395,
      "step": 194
    },
    {
      "epoch": 0.11029411764705882,
      "grad_norm": 0.0789114385843277,
      "learning_rate": 2.6578947368421053e-06,
      "loss": 10.3362,
      "step": 195
    },
    {
      "epoch": 0.11085972850678733,
      "grad_norm": 0.05153012275695801,
      "learning_rate": 2.1263157894736844e-06,
      "loss": 10.3363,
      "step": 196
    },
    {
      "epoch": 0.11142533936651584,
      "grad_norm": 0.04866836592555046,
      "learning_rate": 1.5947368421052633e-06,
      "loss": 10.333,
      "step": 197
    },
    {
      "epoch": 0.11199095022624435,
      "grad_norm": 0.052815958857536316,
      "learning_rate": 1.0631578947368422e-06,
      "loss": 10.335,
      "step": 198
    },
    {
      "epoch": 0.11255656108597285,
      "grad_norm": 0.07986342906951904,
      "learning_rate": 5.315789473684211e-07,
      "loss": 10.3327,
      "step": 199
    },
    {
      "epoch": 0.11312217194570136,
      "grad_norm": 0.10749009251594543,
      "learning_rate": 0.0,
      "loss": 10.3305,
      "step": 200
    },
    {
      "epoch": 0.11312217194570136,
      "eval_loss": 10.333786964416504,
      "eval_runtime": 8.2124,
      "eval_samples_per_second": 2900.488,
      "eval_steps_per_second": 90.716,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 187990750789632.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}