{
  "best_metric": 5.3569310694001615e-05,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.8800880088008801,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0044004400440044,
      "grad_norm": 0.124293252825737,
      "learning_rate": 1e-05,
      "loss": 0.0426,
      "step": 1
    },
    {
      "epoch": 0.0044004400440044,
      "eval_loss": 0.4005989134311676,
      "eval_runtime": 26.9175,
      "eval_samples_per_second": 14.229,
      "eval_steps_per_second": 3.566,
      "step": 1
    },
    {
      "epoch": 0.0088008800880088,
      "grad_norm": 0.16282618045806885,
      "learning_rate": 2e-05,
      "loss": 0.062,
      "step": 2
    },
    {
      "epoch": 0.013201320132013201,
      "grad_norm": 0.21799585223197937,
      "learning_rate": 3e-05,
      "loss": 0.0727,
      "step": 3
    },
    {
      "epoch": 0.0176017601760176,
      "grad_norm": 0.21013480424880981,
      "learning_rate": 4e-05,
      "loss": 0.0685,
      "step": 4
    },
    {
      "epoch": 0.022002200220022004,
      "grad_norm": 0.20355410873889923,
      "learning_rate": 5e-05,
      "loss": 0.0581,
      "step": 5
    },
    {
      "epoch": 0.026402640264026403,
      "grad_norm": 0.17260350286960602,
      "learning_rate": 6e-05,
      "loss": 0.0502,
      "step": 6
    },
    {
      "epoch": 0.030803080308030802,
      "grad_norm": 0.13334129750728607,
      "learning_rate": 7e-05,
      "loss": 0.0366,
      "step": 7
    },
    {
      "epoch": 0.0352035203520352,
      "grad_norm": 0.18650147318840027,
      "learning_rate": 8e-05,
      "loss": 0.0244,
      "step": 8
    },
    {
      "epoch": 0.039603960396039604,
      "grad_norm": 0.07796633988618851,
      "learning_rate": 9e-05,
      "loss": 0.0059,
      "step": 9
    },
    {
      "epoch": 0.04400440044004401,
      "grad_norm": 0.054084423929452896,
      "learning_rate": 0.0001,
      "loss": 0.0044,
      "step": 10
    },
    {
      "epoch": 0.0484048404840484,
      "grad_norm": 0.009877416305243969,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.0003,
      "step": 11
    },
    {
      "epoch": 0.052805280528052806,
      "grad_norm": 0.0258188396692276,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.0007,
      "step": 12
    },
    {
      "epoch": 0.05720572057205721,
      "grad_norm": 0.002410753397271037,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.0001,
      "step": 13
    },
    {
      "epoch": 0.061606160616061605,
      "grad_norm": 0.021880745887756348,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.0004,
      "step": 14
    },
    {
      "epoch": 0.066006600660066,
      "grad_norm": 0.02978755719959736,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.0006,
      "step": 15
    },
    {
      "epoch": 0.0704070407040704,
      "grad_norm": 0.14782631397247314,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.0012,
      "step": 16
    },
    {
      "epoch": 0.0748074807480748,
      "grad_norm": 0.1662040501832962,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.0048,
      "step": 17
    },
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 0.036936525255441666,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.0007,
      "step": 18
    },
    {
      "epoch": 0.08360836083608361,
      "grad_norm": 0.02265871688723564,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.0004,
      "step": 19
    },
    {
      "epoch": 0.08800880088008801,
      "grad_norm": 1.1831775903701782,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.0142,
      "step": 20
    },
    {
      "epoch": 0.0924092409240924,
      "grad_norm": 0.03350690007209778,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.0003,
      "step": 21
    },
    {
      "epoch": 0.0968096809680968,
      "grad_norm": 0.6453636288642883,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.0033,
      "step": 22
    },
    {
      "epoch": 0.10121012101210121,
      "grad_norm": 0.11069868505001068,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.0013,
      "step": 23
    },
    {
      "epoch": 0.10561056105610561,
      "grad_norm": 0.43788349628448486,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.005,
      "step": 24
    },
    {
      "epoch": 0.11001100110011001,
      "grad_norm": 0.42596757411956787,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.0049,
      "step": 25
    },
    {
      "epoch": 0.11441144114411442,
      "grad_norm": 0.1743294596672058,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.0017,
      "step": 26
    },
    {
      "epoch": 0.1188118811881188,
      "grad_norm": 0.0388183556497097,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.0005,
      "step": 27
    },
    {
      "epoch": 0.12321232123212321,
      "grad_norm": 0.016508113592863083,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.0002,
      "step": 28
    },
    {
      "epoch": 0.1276127612761276,
      "grad_norm": 0.041783303022384644,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0004,
      "step": 29
    },
    {
      "epoch": 0.132013201320132,
      "grad_norm": 0.015788815915584564,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0003,
      "step": 30
    },
    {
      "epoch": 0.13641364136413642,
      "grad_norm": 0.004324780311435461,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.0001,
      "step": 31
    },
    {
      "epoch": 0.1408140814081408,
      "grad_norm": 0.010136484168469906,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.0002,
      "step": 32
    },
    {
      "epoch": 0.14521452145214522,
      "grad_norm": 0.000882372260093689,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.1496149614961496,
      "grad_norm": 0.0007833244744688272,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.0,
      "step": 34
    },
    {
      "epoch": 0.15401540154015403,
      "grad_norm": 0.000685386941768229,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 0.0007669946062378585,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.1628162816281628,
      "grad_norm": 0.0013068517437204719,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.0,
      "step": 37
    },
    {
      "epoch": 0.16721672167216722,
      "grad_norm": 0.0012661711079999804,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.1716171617161716,
      "grad_norm": 0.0012077712453901768,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.17601760176017603,
      "grad_norm": 0.0011527056340128183,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.0001,
      "step": 40
    },
    {
      "epoch": 0.18041804180418042,
      "grad_norm": 0.001161446562036872,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.0,
      "step": 41
    },
    {
      "epoch": 0.1848184818481848,
      "grad_norm": 0.0030522786546498537,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.0001,
      "step": 42
    },
    {
      "epoch": 0.18921892189218922,
      "grad_norm": 0.14969733357429504,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.0017,
      "step": 43
    },
    {
      "epoch": 0.1936193619361936,
      "grad_norm": 0.004970098379999399,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.0002,
      "step": 44
    },
    {
      "epoch": 0.19801980198019803,
      "grad_norm": 0.009716896340250969,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0003,
      "step": 45
    },
    {
      "epoch": 0.20242024202420242,
      "grad_norm": 0.03123481199145317,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.0004,
      "step": 46
    },
    {
      "epoch": 0.2068206820682068,
      "grad_norm": 0.0060460539534688,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0001,
      "step": 47
    },
    {
      "epoch": 0.21122112211221122,
      "grad_norm": 0.012646622024476528,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0002,
      "step": 48
    },
    {
      "epoch": 0.2156215621562156,
      "grad_norm": 0.00430687703192234,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.0001,
      "step": 49
    },
    {
      "epoch": 0.22002200220022003,
      "grad_norm": 0.02385520562529564,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.0002,
      "step": 50
    },
    {
      "epoch": 0.22002200220022003,
      "eval_loss": 0.0004325860645622015,
      "eval_runtime": 27.3877,
      "eval_samples_per_second": 13.984,
      "eval_steps_per_second": 3.505,
      "step": 50
    },
    {
      "epoch": 0.22442244224422442,
      "grad_norm": 0.06392838805913925,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.0017,
      "step": 51
    },
    {
      "epoch": 0.22882288228822883,
      "grad_norm": 0.11681962013244629,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0021,
      "step": 52
    },
    {
      "epoch": 0.23322332233223322,
      "grad_norm": 0.05899782478809357,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.0005,
      "step": 53
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 0.055354826152324677,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.0005,
      "step": 54
    },
    {
      "epoch": 0.24202420242024203,
      "grad_norm": 0.004946995060890913,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.0001,
      "step": 55
    },
    {
      "epoch": 0.24642464246424642,
      "grad_norm": 0.023520469665527344,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0002,
      "step": 56
    },
    {
      "epoch": 0.2508250825082508,
      "grad_norm": 0.0017183292657136917,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.2552255225522552,
      "grad_norm": 0.034859199076890945,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.0002,
      "step": 58
    },
    {
      "epoch": 0.25962596259625964,
      "grad_norm": 0.0012458146084100008,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.0,
      "step": 59
    },
    {
      "epoch": 0.264026402640264,
      "grad_norm": 0.121714748442173,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0016,
      "step": 60
    },
    {
      "epoch": 0.2684268426842684,
      "grad_norm": 0.00027960087754763663,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.0,
      "step": 61
    },
    {
      "epoch": 0.27282728272827284,
      "grad_norm": 0.0002494723885320127,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.0,
      "step": 62
    },
    {
      "epoch": 0.27722772277227725,
      "grad_norm": 0.0016496744938194752,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.2816281628162816,
      "grad_norm": 0.0001633824867894873,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.0,
      "step": 64
    },
    {
      "epoch": 0.28602860286028603,
      "grad_norm": 0.003394791390746832,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.0,
      "step": 65
    },
    {
      "epoch": 0.29042904290429045,
      "grad_norm": 0.0007833955460228026,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.2948294829482948,
      "grad_norm": 0.000947092950809747,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0,
      "step": 67
    },
    {
      "epoch": 0.2992299229922992,
      "grad_norm": 0.0001762367901392281,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.0,
      "step": 68
    },
    {
      "epoch": 0.30363036303630364,
      "grad_norm": 0.0015382329002022743,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.30803080308030806,
      "grad_norm": 0.07792892307043076,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.0003,
      "step": 70
    },
    {
      "epoch": 0.3124312431243124,
      "grad_norm": 0.0010983330430462956,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.0,
      "step": 71
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 0.0004244677838869393,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.32123212321232125,
      "grad_norm": 0.0009605819941498339,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.0,
      "step": 73
    },
    {
      "epoch": 0.3256325632563256,
      "grad_norm": 8.180613076547161e-05,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.0,
      "step": 74
    },
    {
      "epoch": 0.33003300330033003,
      "grad_norm": 0.0002515311643946916,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.33443344334433445,
      "grad_norm": 0.0002276443556183949,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.0,
      "step": 76
    },
    {
      "epoch": 0.3388338833883388,
      "grad_norm": 9.419534762855619e-05,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.0,
      "step": 77
    },
    {
      "epoch": 0.3432343234323432,
      "grad_norm": 0.00022496163728646934,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.34763476347634764,
      "grad_norm": 0.0003317221417091787,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.0,
      "step": 79
    },
    {
      "epoch": 0.35203520352035206,
      "grad_norm": 0.00034522838541306555,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0,
      "step": 80
    },
    {
      "epoch": 0.3564356435643564,
      "grad_norm": 0.002015438862144947,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.36083608360836084,
      "grad_norm": 0.00035753045813180506,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0,
      "step": 82
    },
    {
      "epoch": 0.36523652365236525,
      "grad_norm": 0.00015272438758984208,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.0,
      "step": 83
    },
    {
      "epoch": 0.3696369636963696,
      "grad_norm": 0.00011201669258298352,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.37403740374037403,
      "grad_norm": 0.0010279722046107054,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.0,
      "step": 85
    },
    {
      "epoch": 0.37843784378437845,
      "grad_norm": 0.0002681734040379524,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 86
    },
    {
      "epoch": 0.38283828382838286,
      "grad_norm": 9.819068509386852e-05,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.3872387238723872,
      "grad_norm": 0.001013385597616434,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.0,
      "step": 88
    },
    {
      "epoch": 0.39163916391639164,
      "grad_norm": 0.0005750965210609138,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.0,
      "step": 89
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 9.149555990006775e-05,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.4004400440044004,
      "grad_norm": 0.0007983499090187252,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.0,
      "step": 91
    },
    {
      "epoch": 0.40484048404840484,
      "grad_norm": 0.002837753389030695,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.0,
      "step": 92
    },
    {
      "epoch": 0.40924092409240925,
      "grad_norm": 0.00023237118148244917,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.0,
      "step": 93
    },
    {
      "epoch": 0.4136413641364136,
      "grad_norm": 0.0034211031161248684,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0001,
      "step": 94
    },
    {
      "epoch": 0.41804180418041803,
      "grad_norm": 0.003545045154169202,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0,
      "step": 95
    },
    {
      "epoch": 0.42244224422442245,
      "grad_norm": 0.0012118261074647307,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.42684268426842686,
      "grad_norm": 0.0002147269988199696,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.0,
      "step": 97
    },
    {
      "epoch": 0.4312431243124312,
      "grad_norm": 0.0006729561137035489,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.0,
      "step": 98
    },
    {
      "epoch": 0.43564356435643564,
      "grad_norm": 0.001695933286100626,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.0,
      "step": 99
    },
    {
      "epoch": 0.44004400440044006,
      "grad_norm": 0.0009355765650980175,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 0.44004400440044006,
      "eval_loss": 0.00010409079550299793,
      "eval_runtime": 27.4113,
      "eval_samples_per_second": 13.972,
      "eval_steps_per_second": 3.502,
      "step": 100
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.009364509955048561,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.0001,
      "step": 101
    },
    {
      "epoch": 0.44884488448844884,
      "grad_norm": 0.007904025726020336,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.0,
      "step": 102
    },
    {
      "epoch": 0.45324532453245325,
      "grad_norm": 0.04869995638728142,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.0001,
      "step": 103
    },
    {
      "epoch": 0.45764576457645767,
      "grad_norm": 0.011372685432434082,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.0002,
      "step": 104
    },
    {
      "epoch": 0.46204620462046203,
      "grad_norm": 0.019802408292889595,
      "learning_rate": 5e-05,
      "loss": 0.0002,
      "step": 105
    },
    {
      "epoch": 0.46644664466446645,
      "grad_norm": 0.005836585070937872,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.0,
      "step": 106
    },
    {
      "epoch": 0.47084708470847086,
      "grad_norm": 0.0077280886471271515,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.0001,
      "step": 107
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 0.02475179359316826,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.0001,
      "step": 108
    },
    {
      "epoch": 0.47964796479647964,
      "grad_norm": 0.012859947048127651,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.0001,
      "step": 109
    },
    {
      "epoch": 0.48404840484048406,
      "grad_norm": 0.0004646368615794927,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.0,
      "step": 110
    },
    {
      "epoch": 0.4884488448844885,
      "grad_norm": 0.00020194578974042088,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.0,
      "step": 111
    },
    {
      "epoch": 0.49284928492849284,
      "grad_norm": 0.00016206988948397338,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.0,
      "step": 112
    },
    {
      "epoch": 0.49724972497249725,
      "grad_norm": 0.00033520840224809945,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.0,
      "step": 113
    },
    {
      "epoch": 0.5016501650165016,
      "grad_norm": 0.00021148104860913008,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.0,
      "step": 114
    },
    {
      "epoch": 0.506050605060506,
      "grad_norm": 0.0035717824939638376,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.0,
      "step": 115
    },
    {
      "epoch": 0.5104510451045104,
      "grad_norm": 0.0006776192458346486,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.0,
      "step": 116
    },
    {
      "epoch": 0.5148514851485149,
      "grad_norm": 0.00022907224774826318,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.0,
      "step": 117
    },
    {
      "epoch": 0.5192519251925193,
      "grad_norm": 0.00020309958199504763,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.0,
      "step": 118
    },
    {
      "epoch": 0.5236523652365237,
      "grad_norm": 0.00039795140037313104,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.0,
      "step": 119
    },
    {
      "epoch": 0.528052805280528,
      "grad_norm": 0.08950094133615494,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0016,
      "step": 120
    },
    {
      "epoch": 0.5324532453245324,
      "grad_norm": 0.0001389589160680771,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.0,
      "step": 121
    },
    {
      "epoch": 0.5368536853685368,
      "grad_norm": 0.006973727140575647,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.0001,
      "step": 122
    },
    {
      "epoch": 0.5412541254125413,
      "grad_norm": 7.795386773068458e-05,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.0,
      "step": 123
    },
    {
      "epoch": 0.5456545654565457,
      "grad_norm": 0.000972930749412626,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0,
      "step": 124
    },
    {
      "epoch": 0.5500550055005501,
      "grad_norm": 0.0004302636662032455,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.0,
      "step": 125
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 0.00022756092948839068,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.0,
      "step": 126
    },
    {
      "epoch": 0.5588558855885588,
      "grad_norm": 0.00010001434566220269,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.0,
      "step": 127
    },
    {
      "epoch": 0.5632563256325632,
      "grad_norm": 7.633665518369526e-05,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.0,
      "step": 128
    },
    {
      "epoch": 0.5676567656765676,
      "grad_norm": 9.883515303954482e-05,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.0,
      "step": 129
    },
    {
      "epoch": 0.5720572057205721,
      "grad_norm": 0.0007232616189867258,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 0.5764576457645765,
      "grad_norm": 0.0002906982263084501,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.0,
      "step": 131
    },
    {
      "epoch": 0.5808580858085809,
      "grad_norm": 7.372764230240136e-05,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.0,
      "step": 132
    },
    {
      "epoch": 0.5852585258525853,
      "grad_norm": 0.0002904881548602134,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.0,
      "step": 133
    },
    {
      "epoch": 0.5896589658965896,
      "grad_norm": 0.0007073272718116641,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.0,
      "step": 134
    },
    {
      "epoch": 0.594059405940594,
      "grad_norm": 0.0002736274036578834,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.0,
      "step": 135
    },
    {
      "epoch": 0.5984598459845984,
      "grad_norm": 0.004230921156704426,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.0,
      "step": 136
    },
    {
      "epoch": 0.6028602860286029,
      "grad_norm": 0.00011136902321595699,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.0,
      "step": 137
    },
    {
      "epoch": 0.6072607260726073,
      "grad_norm": 0.0003115125000476837,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.0,
      "step": 138
    },
    {
      "epoch": 0.6116611661166117,
      "grad_norm": 9.300404053647071e-05,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.0,
      "step": 139
    },
    {
      "epoch": 0.6160616061606161,
      "grad_norm": 9.342883276985958e-05,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.0,
      "step": 140
    },
    {
      "epoch": 0.6204620462046204,
      "grad_norm": 0.00012543365301098675,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.0,
      "step": 141
    },
    {
      "epoch": 0.6248624862486248,
      "grad_norm": 0.0002591195807326585,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.0,
      "step": 142
    },
    {
      "epoch": 0.6292629262926293,
      "grad_norm": 0.00020919264352414757,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 143
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 0.0010372920660302043,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0,
      "step": 144
    },
    {
      "epoch": 0.6380638063806381,
      "grad_norm": 0.0046968706883490086,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.0001,
      "step": 145
    },
    {
      "epoch": 0.6424642464246425,
      "grad_norm": 9.763091657077894e-05,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0,
      "step": 146
    },
    {
      "epoch": 0.6468646864686468,
      "grad_norm": 0.00041341569158248603,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0,
      "step": 147
    },
    {
      "epoch": 0.6512651265126512,
      "grad_norm": 0.0011587744811549783,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.0,
      "step": 148
    },
    {
      "epoch": 0.6556655665566556,
      "grad_norm": 0.00031451601535081863,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0,
      "step": 149
    },
    {
      "epoch": 0.6600660066006601,
      "grad_norm": 0.0003138885658700019,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0,
      "step": 150
    },
    {
      "epoch": 0.6600660066006601,
      "eval_loss": 5.3569310694001615e-05,
      "eval_runtime": 27.4117,
      "eval_samples_per_second": 13.972,
      "eval_steps_per_second": 3.502,
      "step": 150
    },
    {
      "epoch": 0.6644664466446645,
      "grad_norm": 0.006883980240672827,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.0015,
      "step": 151
    },
    {
      "epoch": 0.6688668866886689,
      "grad_norm": 0.0009321029647253454,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.0,
      "step": 152
    },
    {
      "epoch": 0.6732673267326733,
      "grad_norm": 0.018465682864189148,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.0003,
      "step": 153
    },
    {
      "epoch": 0.6776677667766776,
      "grad_norm": 0.008836818858981133,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.0001,
      "step": 154
    },
    {
      "epoch": 0.682068206820682,
      "grad_norm": 0.15176299214363098,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.0003,
      "step": 155
    },
    {
      "epoch": 0.6864686468646864,
      "grad_norm": 0.00036234338767826557,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.0,
      "step": 156
    },
    {
      "epoch": 0.6908690869086909,
      "grad_norm": 0.009254254400730133,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.0,
      "step": 157
    },
    {
      "epoch": 0.6952695269526953,
      "grad_norm": 0.0002747817779891193,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0,
      "step": 158
    },
    {
      "epoch": 0.6996699669966997,
      "grad_norm": 0.0006913605029694736,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.0,
      "step": 159
    },
    {
      "epoch": 0.7040704070407041,
      "grad_norm": 0.00010415512952022254,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0,
      "step": 160
    },
    {
      "epoch": 0.7084708470847084,
      "grad_norm": 0.005324000958353281,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.0,
      "step": 161
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 0.001175431301817298,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0,
      "step": 162
    },
    {
      "epoch": 0.7172717271727173,
      "grad_norm": 0.0012561972253024578,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.0,
      "step": 163
    },
    {
      "epoch": 0.7216721672167217,
      "grad_norm": 0.00022268269094638526,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.0,
      "step": 164
    },
    {
      "epoch": 0.7260726072607261,
      "grad_norm": 0.000508906610775739,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0,
      "step": 165
    },
    {
      "epoch": 0.7304730473047305,
      "grad_norm": 9.159876208286732e-05,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.0,
      "step": 166
    },
    {
      "epoch": 0.7348734873487349,
      "grad_norm": 8.172845264198259e-05,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.0,
      "step": 167
    },
    {
      "epoch": 0.7392739273927392,
      "grad_norm": 0.00010027219832409173,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0,
      "step": 168
    },
    {
      "epoch": 0.7436743674367436,
      "grad_norm": 0.00027720481739379466,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.0,
      "step": 169
    },
    {
      "epoch": 0.7480748074807481,
      "grad_norm": 0.0016994699835777283,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0,
      "step": 170
    },
    {
      "epoch": 0.7524752475247525,
      "grad_norm": 0.0006918084109202027,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0,
      "step": 171
    },
    {
      "epoch": 0.7568756875687569,
      "grad_norm": 0.0001846846571424976,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.0,
      "step": 172
    },
    {
      "epoch": 0.7612761276127613,
      "grad_norm": 0.005455648526549339,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.0,
      "step": 173
    },
    {
      "epoch": 0.7656765676567657,
      "grad_norm": 7.301468576770276e-05,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0,
      "step": 174
    },
    {
      "epoch": 0.77007700770077,
      "grad_norm": 9.088708611670882e-05,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.0,
      "step": 175
    },
    {
      "epoch": 0.7744774477447744,
      "grad_norm": 8.755698945606127e-05,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.0,
      "step": 176
    },
    {
      "epoch": 0.7788778877887789,
      "grad_norm": 8.032718324102461e-05,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.0,
      "step": 177
    },
    {
      "epoch": 0.7832783278327833,
      "grad_norm": 0.00011616480333032086,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.0,
      "step": 178
    },
    {
      "epoch": 0.7876787678767877,
      "grad_norm": 0.0011928172316402197,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.0,
      "step": 179
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 0.00020878778013866395,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0,
      "step": 180
    },
    {
      "epoch": 0.7964796479647965,
      "grad_norm": 7.090213330229744e-05,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 181
    },
    {
      "epoch": 0.8008800880088008,
      "grad_norm": 9.082104224944487e-05,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.0,
      "step": 182
    },
    {
      "epoch": 0.8052805280528053,
      "grad_norm": 7.074158202158287e-05,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.0,
      "step": 183
    },
    {
      "epoch": 0.8096809680968097,
      "grad_norm": 8.598820568295196e-05,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0,
      "step": 184
    },
    {
      "epoch": 0.8140814081408141,
      "grad_norm": 9.918822615873069e-05,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.0,
      "step": 185
    },
    {
      "epoch": 0.8184818481848185,
      "grad_norm": 0.00048347472329623997,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.0,
      "step": 186
    },
    {
      "epoch": 0.8228822882288229,
      "grad_norm": 0.0001888483384391293,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0,
      "step": 187
    },
    {
      "epoch": 0.8272827282728272,
      "grad_norm": 0.0325004942715168,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.0002,
      "step": 188
    },
    {
      "epoch": 0.8316831683168316,
      "grad_norm": 7.351018575718626e-05,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0,
      "step": 189
    },
    {
      "epoch": 0.8360836083608361,
      "grad_norm": 0.00011750213161576539,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 0.8404840484048405,
      "grad_norm": 8.28156407806091e-05,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.0,
      "step": 191
    },
    {
      "epoch": 0.8448844884488449,
      "grad_norm": 0.00011592848022701219,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0,
      "step": 192
    },
    {
      "epoch": 0.8492849284928493,
      "grad_norm": 0.00044225406600162387,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.0,
      "step": 193
    },
    {
      "epoch": 0.8536853685368537,
      "grad_norm": 0.0008053010096773505,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0,
      "step": 194
    },
    {
      "epoch": 0.858085808580858,
      "grad_norm": 0.0003437885025050491,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0,
      "step": 195
    },
    {
      "epoch": 0.8624862486248625,
      "grad_norm": 0.004610290750861168,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0001,
      "step": 196
    },
    {
      "epoch": 0.8668866886688669,
      "grad_norm": 0.00027010825579054654,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0,
      "step": 197
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 5.7863253459800035e-05,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0,
      "step": 198
    },
    {
      "epoch": 0.8756875687568757,
      "grad_norm": 0.0002412236062809825,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.0,
      "step": 199
    },
    {
      "epoch": 0.8800880088008801,
      "grad_norm": 0.0010247145546600223,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 200
    },
    {
      "epoch": 0.8800880088008801,
      "eval_loss": 7.128708966774866e-05,
      "eval_runtime": 27.4052,
      "eval_samples_per_second": 13.975,
      "eval_steps_per_second": 3.503,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.690927703443374e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}