{
  "best_metric": 0.6829315423965454,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.09754907938056334,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00048774539690281675,
      "grad_norm": 0.42755216360092163,
      "learning_rate": 1e-05,
      "loss": 0.8209,
      "step": 1
    },
    {
      "epoch": 0.00048774539690281675,
      "eval_loss": 1.4778821468353271,
      "eval_runtime": 249.3288,
      "eval_samples_per_second": 13.849,
      "eval_steps_per_second": 3.465,
      "step": 1
    },
    {
      "epoch": 0.0009754907938056335,
      "grad_norm": 0.4249762296676636,
      "learning_rate": 2e-05,
      "loss": 0.8839,
      "step": 2
    },
    {
      "epoch": 0.0014632361907084503,
      "grad_norm": 0.46692362427711487,
      "learning_rate": 3e-05,
      "loss": 0.8946,
      "step": 3
    },
    {
      "epoch": 0.001950981587611267,
      "grad_norm": 0.42918190360069275,
      "learning_rate": 4e-05,
      "loss": 0.891,
      "step": 4
    },
    {
      "epoch": 0.0024387269845140835,
      "grad_norm": 0.4296896755695343,
      "learning_rate": 5e-05,
      "loss": 0.8432,
      "step": 5
    },
    {
      "epoch": 0.0029264723814169005,
      "grad_norm": 0.5116732716560364,
      "learning_rate": 6e-05,
      "loss": 0.8429,
      "step": 6
    },
    {
      "epoch": 0.003414217778319717,
      "grad_norm": 0.54510098695755,
      "learning_rate": 7e-05,
      "loss": 0.8155,
      "step": 7
    },
    {
      "epoch": 0.003901963175222534,
      "grad_norm": 0.497958242893219,
      "learning_rate": 8e-05,
      "loss": 0.9446,
      "step": 8
    },
    {
      "epoch": 0.0043897085721253505,
      "grad_norm": 0.5095407366752625,
      "learning_rate": 9e-05,
      "loss": 0.7652,
      "step": 9
    },
    {
      "epoch": 0.004877453969028167,
      "grad_norm": 0.6286997199058533,
      "learning_rate": 0.0001,
      "loss": 0.8051,
      "step": 10
    },
    {
      "epoch": 0.005365199365930984,
      "grad_norm": 0.551766037940979,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.84,
      "step": 11
    },
    {
      "epoch": 0.005852944762833801,
      "grad_norm": 0.48569273948669434,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.7634,
      "step": 12
    },
    {
      "epoch": 0.0063406901597366176,
      "grad_norm": 0.5907832980155945,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.8695,
      "step": 13
    },
    {
      "epoch": 0.006828435556639434,
      "grad_norm": 0.5869553089141846,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.7659,
      "step": 14
    },
    {
      "epoch": 0.007316180953542251,
      "grad_norm": 0.5571699142456055,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.7572,
      "step": 15
    },
    {
      "epoch": 0.007803926350445068,
      "grad_norm": 0.682612419128418,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7622,
      "step": 16
    },
    {
      "epoch": 0.008291671747347884,
      "grad_norm": 0.6647069454193115,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8033,
      "step": 17
    },
    {
      "epoch": 0.008779417144250701,
      "grad_norm": 0.7218847870826721,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.749,
      "step": 18
    },
    {
      "epoch": 0.009267162541153518,
      "grad_norm": 0.6879798173904419,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.6535,
      "step": 19
    },
    {
      "epoch": 0.009754907938056334,
      "grad_norm": 0.6669095158576965,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6185,
      "step": 20
    },
    {
      "epoch": 0.010242653334959152,
      "grad_norm": 0.7336055040359497,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7455,
      "step": 21
    },
    {
      "epoch": 0.010730398731861967,
      "grad_norm": 0.7467696070671082,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.6521,
      "step": 22
    },
    {
      "epoch": 0.011218144128764785,
      "grad_norm": 0.7632023096084595,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7245,
      "step": 23
    },
    {
      "epoch": 0.011705889525667602,
      "grad_norm": 0.8390482068061829,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7136,
      "step": 24
    },
    {
      "epoch": 0.012193634922570418,
      "grad_norm": 0.8675934076309204,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.6735,
      "step": 25
    },
    {
      "epoch": 0.012681380319473235,
      "grad_norm": 0.9683317542076111,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7933,
      "step": 26
    },
    {
      "epoch": 0.013169125716376053,
      "grad_norm": 1.026005744934082,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8079,
      "step": 27
    },
    {
      "epoch": 0.013656871113278868,
      "grad_norm": 1.0004651546478271,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.7579,
      "step": 28
    },
    {
      "epoch": 0.014144616510181686,
      "grad_norm": 0.9923139214515686,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6652,
      "step": 29
    },
    {
      "epoch": 0.014632361907084501,
      "grad_norm": 1.1677155494689941,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7852,
      "step": 30
    },
    {
      "epoch": 0.015120107303987319,
      "grad_norm": 1.1109479665756226,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.7314,
      "step": 31
    },
    {
      "epoch": 0.015607852700890136,
      "grad_norm": 1.178887963294983,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.6344,
      "step": 32
    },
    {
      "epoch": 0.016095598097792953,
      "grad_norm": 1.1039280891418457,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8052,
      "step": 33
    },
    {
      "epoch": 0.016583343494695767,
      "grad_norm": 0.9677231907844543,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6957,
      "step": 34
    },
    {
      "epoch": 0.017071088891598585,
      "grad_norm": 1.3303396701812744,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7921,
      "step": 35
    },
    {
      "epoch": 0.017558834288501402,
      "grad_norm": 1.3315911293029785,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8033,
      "step": 36
    },
    {
      "epoch": 0.01804657968540422,
      "grad_norm": 1.4298336505889893,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8131,
      "step": 37
    },
    {
      "epoch": 0.018534325082307037,
      "grad_norm": 1.2538775205612183,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7601,
      "step": 38
    },
    {
      "epoch": 0.01902207047920985,
      "grad_norm": 1.2895811796188354,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7014,
      "step": 39
    },
    {
      "epoch": 0.01950981587611267,
      "grad_norm": 1.301110863685608,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7467,
      "step": 40
    },
    {
      "epoch": 0.019997561273015486,
      "grad_norm": 1.4002180099487305,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7049,
      "step": 41
    },
    {
      "epoch": 0.020485306669918303,
      "grad_norm": 1.42429518699646,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.6995,
      "step": 42
    },
    {
      "epoch": 0.02097305206682112,
      "grad_norm": 1.5314632654190063,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.6996,
      "step": 43
    },
    {
      "epoch": 0.021460797463723934,
      "grad_norm": 1.3588933944702148,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.6915,
      "step": 44
    },
    {
      "epoch": 0.021948542860626752,
      "grad_norm": 1.8157392740249634,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7544,
      "step": 45
    },
    {
      "epoch": 0.02243628825752957,
      "grad_norm": 1.422425389289856,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.665,
      "step": 46
    },
    {
      "epoch": 0.022924033654432387,
      "grad_norm": 1.61789870262146,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7163,
      "step": 47
    },
    {
      "epoch": 0.023411779051335204,
      "grad_norm": 1.9989192485809326,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8351,
      "step": 48
    },
    {
      "epoch": 0.02389952444823802,
      "grad_norm": 1.481856346130371,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.4612,
      "step": 49
    },
    {
      "epoch": 0.024387269845140835,
      "grad_norm": 5.016469478607178,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.2368,
      "step": 50
    },
    {
      "epoch": 0.024387269845140835,
      "eval_loss": 0.7829228043556213,
      "eval_runtime": 251.0575,
      "eval_samples_per_second": 13.754,
      "eval_steps_per_second": 3.441,
      "step": 50
    },
    {
      "epoch": 0.024875015242043653,
      "grad_norm": 0.5631384253501892,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.8365,
      "step": 51
    },
    {
      "epoch": 0.02536276063894647,
      "grad_norm": 0.4840724766254425,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.8109,
      "step": 52
    },
    {
      "epoch": 0.025850506035849288,
      "grad_norm": 0.42858225107192993,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.8418,
      "step": 53
    },
    {
      "epoch": 0.026338251432752105,
      "grad_norm": 0.3773359954357147,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.7861,
      "step": 54
    },
    {
      "epoch": 0.02682599682965492,
      "grad_norm": 0.35703587532043457,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.7623,
      "step": 55
    },
    {
      "epoch": 0.027313742226557736,
      "grad_norm": 0.388830304145813,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7697,
      "step": 56
    },
    {
      "epoch": 0.027801487623460554,
      "grad_norm": 0.4029677212238312,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.8793,
      "step": 57
    },
    {
      "epoch": 0.02828923302036337,
      "grad_norm": 0.4202454388141632,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.7603,
      "step": 58
    },
    {
      "epoch": 0.02877697841726619,
      "grad_norm": 0.4346356689929962,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.7832,
      "step": 59
    },
    {
      "epoch": 0.029264723814169002,
      "grad_norm": 0.4237990081310272,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.7074,
      "step": 60
    },
    {
      "epoch": 0.02975246921107182,
      "grad_norm": 0.4588177502155304,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6918,
      "step": 61
    },
    {
      "epoch": 0.030240214607974637,
      "grad_norm": 0.48189812898635864,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8579,
      "step": 62
    },
    {
      "epoch": 0.030727960004877455,
      "grad_norm": 0.4455983638763428,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.5964,
      "step": 63
    },
    {
      "epoch": 0.031215705401780272,
      "grad_norm": 0.45201095938682556,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.7495,
      "step": 64
    },
    {
      "epoch": 0.031703450798683086,
      "grad_norm": 0.5913598537445068,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7466,
      "step": 65
    },
    {
      "epoch": 0.03219119619558591,
      "grad_norm": 0.558763861656189,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.6726,
      "step": 66
    },
    {
      "epoch": 0.03267894159248872,
      "grad_norm": 0.5548415184020996,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6972,
      "step": 67
    },
    {
      "epoch": 0.033166686989391535,
      "grad_norm": 0.5588158369064331,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7348,
      "step": 68
    },
    {
      "epoch": 0.033654432386294356,
      "grad_norm": 0.565741240978241,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.6659,
      "step": 69
    },
    {
      "epoch": 0.03414217778319717,
      "grad_norm": 0.557705819606781,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.5816,
      "step": 70
    },
    {
      "epoch": 0.03462992318009999,
      "grad_norm": 0.6664299368858337,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.6496,
      "step": 71
    },
    {
      "epoch": 0.035117668577002804,
      "grad_norm": 0.6529439687728882,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.6415,
      "step": 72
    },
    {
      "epoch": 0.03560541397390562,
      "grad_norm": 0.6623764634132385,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.5984,
      "step": 73
    },
    {
      "epoch": 0.03609315937080844,
      "grad_norm": 0.7059494256973267,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.631,
      "step": 74
    },
    {
      "epoch": 0.03658090476771125,
      "grad_norm": 0.7974410653114319,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7556,
      "step": 75
    },
    {
      "epoch": 0.037068650164614074,
      "grad_norm": 0.8475507497787476,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6946,
      "step": 76
    },
    {
      "epoch": 0.03755639556151689,
      "grad_norm": 0.9229975342750549,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6986,
      "step": 77
    },
    {
      "epoch": 0.0380441409584197,
      "grad_norm": 1.0926481485366821,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.8234,
      "step": 78
    },
    {
      "epoch": 0.03853188635532252,
      "grad_norm": 1.0317264795303345,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7751,
      "step": 79
    },
    {
      "epoch": 0.03901963175222534,
      "grad_norm": 1.0278832912445068,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.5828,
      "step": 80
    },
    {
      "epoch": 0.03950737714912816,
      "grad_norm": 1.0799914598464966,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.7043,
      "step": 81
    },
    {
      "epoch": 0.03999512254603097,
      "grad_norm": 1.2069917917251587,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7712,
      "step": 82
    },
    {
      "epoch": 0.040482867942933785,
      "grad_norm": 1.0386675596237183,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6799,
      "step": 83
    },
    {
      "epoch": 0.040970613339836606,
      "grad_norm": 1.0302294492721558,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.6263,
      "step": 84
    },
    {
      "epoch": 0.04145835873673942,
      "grad_norm": 1.1998454332351685,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.753,
      "step": 85
    },
    {
      "epoch": 0.04194610413364224,
      "grad_norm": 1.2848238945007324,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8633,
      "step": 86
    },
    {
      "epoch": 0.042433849530545055,
      "grad_norm": 1.159552812576294,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.7037,
      "step": 87
    },
    {
      "epoch": 0.04292159492744787,
      "grad_norm": 1.185767650604248,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6602,
      "step": 88
    },
    {
      "epoch": 0.04340934032435069,
      "grad_norm": 1.153672456741333,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.722,
      "step": 89
    },
    {
      "epoch": 0.043897085721253504,
      "grad_norm": 1.3746973276138306,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7243,
      "step": 90
    },
    {
      "epoch": 0.044384831118156325,
      "grad_norm": 1.162945032119751,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6855,
      "step": 91
    },
    {
      "epoch": 0.04487257651505914,
      "grad_norm": 1.436776876449585,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7705,
      "step": 92
    },
    {
      "epoch": 0.04536032191196195,
      "grad_norm": 1.14664626121521,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.6167,
      "step": 93
    },
    {
      "epoch": 0.04584806730886477,
      "grad_norm": 1.2447847127914429,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6369,
      "step": 94
    },
    {
      "epoch": 0.04633581270576759,
      "grad_norm": 1.4392436742782593,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6753,
      "step": 95
    },
    {
      "epoch": 0.04682355810267041,
      "grad_norm": 1.3012615442276,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5964,
      "step": 96
    },
    {
      "epoch": 0.04731130349957322,
      "grad_norm": 1.672782063484192,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7482,
      "step": 97
    },
    {
      "epoch": 0.04779904889647604,
      "grad_norm": 1.9180303812026978,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.7675,
      "step": 98
    },
    {
      "epoch": 0.04828679429337886,
      "grad_norm": 2.4247143268585205,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.9774,
      "step": 99
    },
    {
      "epoch": 0.04877453969028167,
      "grad_norm": 1.9715301990509033,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.6453,
      "step": 100
    },
    {
      "epoch": 0.04877453969028167,
      "eval_loss": 0.7220537066459656,
      "eval_runtime": 252.6341,
      "eval_samples_per_second": 13.668,
      "eval_steps_per_second": 3.42,
      "step": 100
    },
    {
      "epoch": 0.04926228508718449,
      "grad_norm": 0.4161648750305176,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.886,
      "step": 101
    },
    {
      "epoch": 0.049750030484087306,
      "grad_norm": 0.35051146149635315,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.7691,
      "step": 102
    },
    {
      "epoch": 0.050237775880990126,
      "grad_norm": 0.3567993640899658,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.7322,
      "step": 103
    },
    {
      "epoch": 0.05072552127789294,
      "grad_norm": 0.37923744320869446,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.7983,
      "step": 104
    },
    {
      "epoch": 0.051213266674795754,
      "grad_norm": 0.36066076159477234,
      "learning_rate": 5e-05,
      "loss": 0.7976,
      "step": 105
    },
    {
      "epoch": 0.051701012071698575,
      "grad_norm": 0.38446488976478577,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.751,
      "step": 106
    },
    {
      "epoch": 0.05218875746860139,
      "grad_norm": 0.3728892505168915,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.8109,
      "step": 107
    },
    {
      "epoch": 0.05267650286550421,
      "grad_norm": 0.4253670275211334,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.8112,
      "step": 108
    },
    {
      "epoch": 0.053164248262407024,
      "grad_norm": 0.4034174382686615,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.6981,
      "step": 109
    },
    {
      "epoch": 0.05365199365930984,
      "grad_norm": 0.4255368709564209,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.7126,
      "step": 110
    },
    {
      "epoch": 0.05413973905621266,
      "grad_norm": 0.44515857100486755,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.727,
      "step": 111
    },
    {
      "epoch": 0.05462748445311547,
      "grad_norm": 0.4727829694747925,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.759,
      "step": 112
    },
    {
      "epoch": 0.055115229850018294,
      "grad_norm": 0.4589659869670868,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.6898,
      "step": 113
    },
    {
      "epoch": 0.05560297524692111,
      "grad_norm": 0.498053640127182,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.6972,
      "step": 114
    },
    {
      "epoch": 0.05609072064382392,
      "grad_norm": 0.5529409646987915,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.7435,
      "step": 115
    },
    {
      "epoch": 0.05657846604072674,
      "grad_norm": 0.502553403377533,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.6511,
      "step": 116
    },
    {
      "epoch": 0.057066211437629556,
      "grad_norm": 0.5404387712478638,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.6481,
      "step": 117
    },
    {
      "epoch": 0.05755395683453238,
      "grad_norm": 0.5820646286010742,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.6155,
      "step": 118
    },
    {
      "epoch": 0.05804170223143519,
      "grad_norm": 0.5800485014915466,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.6183,
      "step": 119
    },
    {
      "epoch": 0.058529447628338005,
      "grad_norm": 0.6577337384223938,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6044,
      "step": 120
    },
    {
      "epoch": 0.059017193025240826,
      "grad_norm": 0.6654838919639587,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.6515,
      "step": 121
    },
    {
      "epoch": 0.05950493842214364,
      "grad_norm": 0.7200480103492737,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6409,
      "step": 122
    },
    {
      "epoch": 0.05999268381904646,
      "grad_norm": 0.6738976240158081,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.5441,
      "step": 123
    },
    {
      "epoch": 0.060480429215949275,
      "grad_norm": 0.7650407552719116,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6873,
      "step": 124
    },
    {
      "epoch": 0.06096817461285209,
      "grad_norm": 0.7669803500175476,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.6336,
      "step": 125
    },
    {
      "epoch": 0.06145592000975491,
      "grad_norm": 0.7825415730476379,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.6059,
      "step": 126
    },
    {
      "epoch": 0.06194366540665772,
      "grad_norm": 0.8878684043884277,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.6077,
      "step": 127
    },
    {
      "epoch": 0.062431410803560544,
      "grad_norm": 0.8407205939292908,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.631,
      "step": 128
    },
    {
      "epoch": 0.06291915620046336,
      "grad_norm": 0.8824788331985474,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.5548,
      "step": 129
    },
    {
      "epoch": 0.06340690159736617,
      "grad_norm": 0.938753604888916,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.5976,
      "step": 130
    },
    {
      "epoch": 0.06389464699426899,
      "grad_norm": 1.011763334274292,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6762,
      "step": 131
    },
    {
      "epoch": 0.06438239239117181,
      "grad_norm": 0.979924201965332,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.6759,
      "step": 132
    },
    {
      "epoch": 0.06487013778807463,
      "grad_norm": 0.9880190491676331,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.6734,
      "step": 133
    },
    {
      "epoch": 0.06535788318497744,
      "grad_norm": 0.9890837669372559,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.6368,
      "step": 134
    },
    {
      "epoch": 0.06584562858188026,
      "grad_norm": 0.99824059009552,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.586,
      "step": 135
    },
    {
      "epoch": 0.06633337397878307,
      "grad_norm": 0.8986355662345886,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.5416,
      "step": 136
    },
    {
      "epoch": 0.0668211193756859,
      "grad_norm": 1.206850528717041,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.6797,
      "step": 137
    },
    {
      "epoch": 0.06730886477258871,
      "grad_norm": 1.0518172979354858,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.6248,
      "step": 138
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 1.2634769678115845,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.6241,
      "step": 139
    },
    {
      "epoch": 0.06828435556639434,
      "grad_norm": 1.0548444986343384,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.5556,
      "step": 140
    },
    {
      "epoch": 0.06877210096329715,
      "grad_norm": 1.184350609779358,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.5882,
      "step": 141
    },
    {
      "epoch": 0.06925984636019998,
      "grad_norm": 1.2766765356063843,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.7174,
      "step": 142
    },
    {
      "epoch": 0.0697475917571028,
      "grad_norm": 1.2047975063323975,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6027,
      "step": 143
    },
    {
      "epoch": 0.07023533715400561,
      "grad_norm": 1.2198841571807861,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.5523,
      "step": 144
    },
    {
      "epoch": 0.07072308255090842,
      "grad_norm": 1.6669135093688965,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.67,
      "step": 145
    },
    {
      "epoch": 0.07121082794781124,
      "grad_norm": 1.6680443286895752,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.6166,
      "step": 146
    },
    {
      "epoch": 0.07169857334471406,
      "grad_norm": 1.3673017024993896,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.5009,
      "step": 147
    },
    {
      "epoch": 0.07218631874161688,
      "grad_norm": 2.1820733547210693,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.7683,
      "step": 148
    },
    {
      "epoch": 0.07267406413851969,
      "grad_norm": 2.975788116455078,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5585,
      "step": 149
    },
    {
      "epoch": 0.0731618095354225,
      "grad_norm": 3.086648941040039,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.5239,
      "step": 150
    },
    {
      "epoch": 0.0731618095354225,
      "eval_loss": 0.6829315423965454,
      "eval_runtime": 251.633,
      "eval_samples_per_second": 13.722,
      "eval_steps_per_second": 3.434,
      "step": 150
    },
    {
      "epoch": 0.07364955493232532,
      "grad_norm": 0.2489556521177292,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.8439,
      "step": 151
    },
    {
      "epoch": 0.07413730032922815,
      "grad_norm": 0.2686026096343994,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.7862,
      "step": 152
    },
    {
      "epoch": 0.07462504572613096,
      "grad_norm": 0.29824158549308777,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.7672,
      "step": 153
    },
    {
      "epoch": 0.07511279112303378,
      "grad_norm": 0.30238965153694153,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.7349,
      "step": 154
    },
    {
      "epoch": 0.07560053651993659,
      "grad_norm": 0.34403547644615173,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7646,
      "step": 155
    },
    {
      "epoch": 0.0760882819168394,
      "grad_norm": 0.3634992241859436,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.7325,
      "step": 156
    },
    {
      "epoch": 0.07657602731374223,
      "grad_norm": 0.3693501949310303,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.7153,
      "step": 157
    },
    {
      "epoch": 0.07706377271064505,
      "grad_norm": 0.3857001066207886,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.7527,
      "step": 158
    },
    {
      "epoch": 0.07755151810754786,
      "grad_norm": 0.40264785289764404,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.7009,
      "step": 159
    },
    {
      "epoch": 0.07803926350445067,
      "grad_norm": 0.4148149788379669,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7876,
      "step": 160
    },
    {
      "epoch": 0.07852700890135349,
      "grad_norm": 0.39454057812690735,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.6545,
      "step": 161
    },
    {
      "epoch": 0.07901475429825632,
      "grad_norm": 0.47955575585365295,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7919,
      "step": 162
    },
    {
      "epoch": 0.07950249969515913,
      "grad_norm": 0.4430481791496277,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.6919,
      "step": 163
    },
    {
      "epoch": 0.07999024509206194,
      "grad_norm": 0.47135019302368164,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.6977,
      "step": 164
    },
    {
      "epoch": 0.08047799048896476,
      "grad_norm": 0.5089796185493469,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.7501,
      "step": 165
    },
    {
      "epoch": 0.08096573588586757,
      "grad_norm": 0.7076864242553711,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.8075,
      "step": 166
    },
    {
      "epoch": 0.0814534812827704,
      "grad_norm": 0.5751909613609314,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.7103,
      "step": 167
    },
    {
      "epoch": 0.08194122667967321,
      "grad_norm": 0.5947926640510559,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.7587,
      "step": 168
    },
    {
      "epoch": 0.08242897207657603,
      "grad_norm": 0.5765040516853333,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.6549,
      "step": 169
    },
    {
      "epoch": 0.08291671747347884,
      "grad_norm": 0.6634975075721741,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.7082,
      "step": 170
    },
    {
      "epoch": 0.08340446287038165,
      "grad_norm": 0.6290510892868042,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.6165,
      "step": 171
    },
    {
      "epoch": 0.08389220826728448,
      "grad_norm": 0.706638514995575,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.7422,
      "step": 172
    },
    {
      "epoch": 0.0843799536641873,
      "grad_norm": 0.7100273370742798,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.6488,
      "step": 173
    },
    {
      "epoch": 0.08486769906109011,
      "grad_norm": 0.7350596785545349,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.6134,
      "step": 174
    },
    {
      "epoch": 0.08535544445799292,
      "grad_norm": 0.7528049349784851,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.6131,
      "step": 175
    },
    {
      "epoch": 0.08584318985489574,
      "grad_norm": 0.8489141464233398,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.6189,
      "step": 176
    },
    {
      "epoch": 0.08633093525179857,
      "grad_norm": 0.8818708062171936,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.6339,
      "step": 177
    },
    {
      "epoch": 0.08681868064870138,
      "grad_norm": 0.881334662437439,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.6839,
      "step": 178
    },
    {
      "epoch": 0.0873064260456042,
      "grad_norm": 0.8695350289344788,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.6886,
      "step": 179
    },
    {
      "epoch": 0.08779417144250701,
      "grad_norm": 0.8996140360832214,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.5852,
      "step": 180
    },
    {
      "epoch": 0.08828191683940982,
      "grad_norm": 0.9175009727478027,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6435,
      "step": 181
    },
    {
      "epoch": 0.08876966223631265,
      "grad_norm": 1.0094784498214722,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.7114,
      "step": 182
    },
    {
      "epoch": 0.08925740763321546,
      "grad_norm": 1.0606130361557007,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.7202,
      "step": 183
    },
    {
      "epoch": 0.08974515303011828,
      "grad_norm": 0.983785092830658,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.571,
      "step": 184
    },
    {
      "epoch": 0.09023289842702109,
      "grad_norm": 1.2475382089614868,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.7458,
      "step": 185
    },
    {
      "epoch": 0.0907206438239239,
      "grad_norm": 1.212286353111267,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.639,
      "step": 186
    },
    {
      "epoch": 0.09120838922082673,
      "grad_norm": 1.2203342914581299,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.6917,
      "step": 187
    },
    {
      "epoch": 0.09169613461772955,
      "grad_norm": 1.1570426225662231,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.7431,
      "step": 188
    },
    {
      "epoch": 0.09218388001463236,
      "grad_norm": 1.4021419286727905,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.8602,
      "step": 189
    },
    {
      "epoch": 0.09267162541153517,
      "grad_norm": 1.5850142240524292,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.7399,
      "step": 190
    },
    {
      "epoch": 0.09315937080843799,
      "grad_norm": 1.0403721332550049,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.5372,
      "step": 191
    },
    {
      "epoch": 0.09364711620534082,
      "grad_norm": 1.275734305381775,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.6592,
      "step": 192
    },
    {
      "epoch": 0.09413486160224363,
      "grad_norm": 1.2790805101394653,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.6199,
      "step": 193
    },
    {
      "epoch": 0.09462260699914644,
      "grad_norm": 1.175279140472412,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.573,
      "step": 194
    },
    {
      "epoch": 0.09511035239604926,
      "grad_norm": 1.4071108102798462,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.6917,
      "step": 195
    },
    {
      "epoch": 0.09559809779295209,
      "grad_norm": 1.5487494468688965,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.702,
      "step": 196
    },
    {
      "epoch": 0.0960858431898549,
      "grad_norm": 1.5550881624221802,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.7165,
      "step": 197
    },
    {
      "epoch": 0.09657358858675771,
      "grad_norm": 1.708490014076233,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.546,
      "step": 198
    },
    {
      "epoch": 0.09706133398366053,
      "grad_norm": 3.0243024826049805,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.0006,
      "step": 199
    },
    {
      "epoch": 0.09754907938056334,
      "grad_norm": 3.116490125656128,
      "learning_rate": 0.0,
      "loss": 0.697,
      "step": 200
    },
    {
      "epoch": 0.09754907938056334,
      "eval_loss": 0.6851520538330078,
      "eval_runtime": 252.1622,
      "eval_samples_per_second": 13.694,
      "eval_steps_per_second": 3.426,
      "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": 2.929090691806003e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}