{
  "best_metric": 0.6018400192260742,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.081276033729554,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00040638016864777,
      "grad_norm": 0.5703067779541016,
      "learning_rate": 1e-05,
      "loss": 0.3887,
      "step": 1
    },
    {
      "epoch": 0.00040638016864777,
      "eval_loss": 0.7825747132301331,
      "eval_runtime": 322.1111,
      "eval_samples_per_second": 12.868,
      "eval_steps_per_second": 3.219,
      "step": 1
    },
    {
      "epoch": 0.00081276033729554,
      "grad_norm": 0.6955717206001282,
      "learning_rate": 2e-05,
      "loss": 0.47,
      "step": 2
    },
    {
      "epoch": 0.0012191405059433099,
      "grad_norm": 0.7730527520179749,
      "learning_rate": 3e-05,
      "loss": 0.493,
      "step": 3
    },
    {
      "epoch": 0.00162552067459108,
      "grad_norm": 0.7028549313545227,
      "learning_rate": 4e-05,
      "loss": 0.4688,
      "step": 4
    },
    {
      "epoch": 0.00203190084323885,
      "grad_norm": 0.6494016647338867,
      "learning_rate": 5e-05,
      "loss": 0.5487,
      "step": 5
    },
    {
      "epoch": 0.0024382810118866198,
      "grad_norm": 0.4941878914833069,
      "learning_rate": 6e-05,
      "loss": 0.5306,
      "step": 6
    },
    {
      "epoch": 0.00284466118053439,
      "grad_norm": 0.44481906294822693,
      "learning_rate": 7e-05,
      "loss": 0.5372,
      "step": 7
    },
    {
      "epoch": 0.00325104134918216,
      "grad_norm": 0.6145043969154358,
      "learning_rate": 8e-05,
      "loss": 0.5759,
      "step": 8
    },
    {
      "epoch": 0.00365742151782993,
      "grad_norm": 0.6012505292892456,
      "learning_rate": 9e-05,
      "loss": 0.5722,
      "step": 9
    },
    {
      "epoch": 0.0040638016864777,
      "grad_norm": 0.428402841091156,
      "learning_rate": 0.0001,
      "loss": 0.5588,
      "step": 10
    },
    {
      "epoch": 0.00447018185512547,
      "grad_norm": 0.392630010843277,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.5603,
      "step": 11
    },
    {
      "epoch": 0.0048765620237732395,
      "grad_norm": 0.3763248920440674,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.5635,
      "step": 12
    },
    {
      "epoch": 0.00528294219242101,
      "grad_norm": 0.35733386874198914,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.5815,
      "step": 13
    },
    {
      "epoch": 0.00568932236106878,
      "grad_norm": 0.3512309789657593,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.585,
      "step": 14
    },
    {
      "epoch": 0.00609570252971655,
      "grad_norm": 0.40847259759902954,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.615,
      "step": 15
    },
    {
      "epoch": 0.00650208269836432,
      "grad_norm": 0.385098397731781,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.5674,
      "step": 16
    },
    {
      "epoch": 0.0069084628670120895,
      "grad_norm": 0.39880988001823425,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.6339,
      "step": 17
    },
    {
      "epoch": 0.00731484303565986,
      "grad_norm": 0.3675394058227539,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.6237,
      "step": 18
    },
    {
      "epoch": 0.00772122320430763,
      "grad_norm": 0.3523612916469574,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.5812,
      "step": 19
    },
    {
      "epoch": 0.0081276033729554,
      "grad_norm": 0.3897835314273834,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6298,
      "step": 20
    },
    {
      "epoch": 0.00853398354160317,
      "grad_norm": 0.3928382396697998,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.621,
      "step": 21
    },
    {
      "epoch": 0.00894036371025094,
      "grad_norm": 0.37205857038497925,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.5966,
      "step": 22
    },
    {
      "epoch": 0.00934674387889871,
      "grad_norm": 0.3798677325248718,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6377,
      "step": 23
    },
    {
      "epoch": 0.009753124047546479,
      "grad_norm": 0.3851011097431183,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.6194,
      "step": 24
    },
    {
      "epoch": 0.01015950421619425,
      "grad_norm": 0.44204574823379517,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.6703,
      "step": 25
    },
    {
      "epoch": 0.01056588438484202,
      "grad_norm": 0.40027621388435364,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.695,
      "step": 26
    },
    {
      "epoch": 0.01097226455348979,
      "grad_norm": 0.40019628405570984,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.6774,
      "step": 27
    },
    {
      "epoch": 0.01137864472213756,
      "grad_norm": 0.39973655343055725,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6296,
      "step": 28
    },
    {
      "epoch": 0.011785024890785329,
      "grad_norm": 0.4191434681415558,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6229,
      "step": 29
    },
    {
      "epoch": 0.0121914050594331,
      "grad_norm": 0.42103180289268494,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.6193,
      "step": 30
    },
    {
      "epoch": 0.01259778522808087,
      "grad_norm": 0.41863998770713806,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.6392,
      "step": 31
    },
    {
      "epoch": 0.01300416539672864,
      "grad_norm": 0.45318982005119324,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.6681,
      "step": 32
    },
    {
      "epoch": 0.01341054556537641,
      "grad_norm": 0.46077102422714233,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.6999,
      "step": 33
    },
    {
      "epoch": 0.013816925734024179,
      "grad_norm": 0.4924982488155365,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.5957,
      "step": 34
    },
    {
      "epoch": 0.01422330590267195,
      "grad_norm": 0.5045682191848755,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.688,
      "step": 35
    },
    {
      "epoch": 0.01462968607131972,
      "grad_norm": 0.5184033513069153,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.6779,
      "step": 36
    },
    {
      "epoch": 0.01503606623996749,
      "grad_norm": 0.5416311025619507,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.6813,
      "step": 37
    },
    {
      "epoch": 0.01544244640861526,
      "grad_norm": 0.5728555917739868,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7191,
      "step": 38
    },
    {
      "epoch": 0.01584882657726303,
      "grad_norm": 0.5730562210083008,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.6899,
      "step": 39
    },
    {
      "epoch": 0.0162552067459108,
      "grad_norm": 0.6756515502929688,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7062,
      "step": 40
    },
    {
      "epoch": 0.01666158691455857,
      "grad_norm": 0.6657019853591919,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.6889,
      "step": 41
    },
    {
      "epoch": 0.01706796708320634,
      "grad_norm": 0.8455941677093506,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7749,
      "step": 42
    },
    {
      "epoch": 0.017474347251854108,
      "grad_norm": 0.787888765335083,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8057,
      "step": 43
    },
    {
      "epoch": 0.01788072742050188,
      "grad_norm": 0.7980632781982422,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7538,
      "step": 44
    },
    {
      "epoch": 0.01828710758914965,
      "grad_norm": 0.7574694156646729,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.6432,
      "step": 45
    },
    {
      "epoch": 0.01869348775779742,
      "grad_norm": 0.8679765462875366,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.6301,
      "step": 46
    },
    {
      "epoch": 0.01909986792644519,
      "grad_norm": 1.1122722625732422,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.6445,
      "step": 47
    },
    {
      "epoch": 0.019506248095092958,
      "grad_norm": 1.2623975276947021,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.6442,
      "step": 48
    },
    {
      "epoch": 0.01991262826374073,
      "grad_norm": 1.4207667112350464,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.7484,
      "step": 49
    },
    {
      "epoch": 0.0203190084323885,
      "grad_norm": 1.7285435199737549,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.6858,
      "step": 50
    },
    {
      "epoch": 0.0203190084323885,
      "eval_loss": 0.6686556339263916,
      "eval_runtime": 324.4967,
      "eval_samples_per_second": 12.774,
      "eval_steps_per_second": 3.196,
      "step": 50
    },
    {
      "epoch": 0.02072538860103627,
      "grad_norm": 0.2862623929977417,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.3778,
      "step": 51
    },
    {
      "epoch": 0.02113176876968404,
      "grad_norm": 0.3473515212535858,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.437,
      "step": 52
    },
    {
      "epoch": 0.021538148938331808,
      "grad_norm": 0.32383036613464355,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.433,
      "step": 53
    },
    {
      "epoch": 0.02194452910697958,
      "grad_norm": 0.32732561230659485,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.4885,
      "step": 54
    },
    {
      "epoch": 0.02235090927562735,
      "grad_norm": 0.2704610228538513,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.4361,
      "step": 55
    },
    {
      "epoch": 0.02275728944427512,
      "grad_norm": 0.2536717653274536,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.4283,
      "step": 56
    },
    {
      "epoch": 0.02316366961292289,
      "grad_norm": 0.285106897354126,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.4773,
      "step": 57
    },
    {
      "epoch": 0.023570049781570658,
      "grad_norm": 0.2967824637889862,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.5429,
      "step": 58
    },
    {
      "epoch": 0.02397642995021843,
      "grad_norm": 0.3114878833293915,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.5618,
      "step": 59
    },
    {
      "epoch": 0.0243828101188662,
      "grad_norm": 0.30405136942863464,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.5474,
      "step": 60
    },
    {
      "epoch": 0.02478919028751397,
      "grad_norm": 0.29424792528152466,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.5328,
      "step": 61
    },
    {
      "epoch": 0.02519557045616174,
      "grad_norm": 0.3119474947452545,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.5363,
      "step": 62
    },
    {
      "epoch": 0.025601950624809508,
      "grad_norm": 0.31077051162719727,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.5284,
      "step": 63
    },
    {
      "epoch": 0.02600833079345728,
      "grad_norm": 0.30840662121772766,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.5821,
      "step": 64
    },
    {
      "epoch": 0.02641471096210505,
      "grad_norm": 0.3145436644554138,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.5766,
      "step": 65
    },
    {
      "epoch": 0.02682109113075282,
      "grad_norm": 0.307223379611969,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.5749,
      "step": 66
    },
    {
      "epoch": 0.02722747129940059,
      "grad_norm": 0.3212253451347351,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.5985,
      "step": 67
    },
    {
      "epoch": 0.027633851468048358,
      "grad_norm": 0.33554473519325256,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.6247,
      "step": 68
    },
    {
      "epoch": 0.02804023163669613,
      "grad_norm": 0.3112795352935791,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.5757,
      "step": 69
    },
    {
      "epoch": 0.0284466118053439,
      "grad_norm": 0.3420306444168091,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.6472,
      "step": 70
    },
    {
      "epoch": 0.02885299197399167,
      "grad_norm": 0.35244178771972656,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.6519,
      "step": 71
    },
    {
      "epoch": 0.02925937214263944,
      "grad_norm": 0.3327883780002594,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5784,
      "step": 72
    },
    {
      "epoch": 0.029665752311287208,
      "grad_norm": 0.3330589830875397,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.5819,
      "step": 73
    },
    {
      "epoch": 0.03007213247993498,
      "grad_norm": 0.3763622045516968,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.6554,
      "step": 74
    },
    {
      "epoch": 0.03047851264858275,
      "grad_norm": 0.346807599067688,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.5837,
      "step": 75
    },
    {
      "epoch": 0.03088489281723052,
      "grad_norm": 0.37593328952789307,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7105,
      "step": 76
    },
    {
      "epoch": 0.03129127298587829,
      "grad_norm": 0.3915523588657379,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6501,
      "step": 77
    },
    {
      "epoch": 0.03169765315452606,
      "grad_norm": 0.3732468783855438,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.6974,
      "step": 78
    },
    {
      "epoch": 0.03210403332317383,
      "grad_norm": 0.3714943826198578,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6553,
      "step": 79
    },
    {
      "epoch": 0.0325104134918216,
      "grad_norm": 0.37029245495796204,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.5918,
      "step": 80
    },
    {
      "epoch": 0.032916793660469366,
      "grad_norm": 0.3933842182159424,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.6413,
      "step": 81
    },
    {
      "epoch": 0.03332317382911714,
      "grad_norm": 0.42775794863700867,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7058,
      "step": 82
    },
    {
      "epoch": 0.03372955399776491,
      "grad_norm": 0.45325636863708496,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6744,
      "step": 83
    },
    {
      "epoch": 0.03413593416641268,
      "grad_norm": 0.476238876581192,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.6628,
      "step": 84
    },
    {
      "epoch": 0.03454231433506045,
      "grad_norm": 0.442513644695282,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.6799,
      "step": 85
    },
    {
      "epoch": 0.034948694503708216,
      "grad_norm": 0.46050167083740234,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.6397,
      "step": 86
    },
    {
      "epoch": 0.03535507467235599,
      "grad_norm": 0.466876357793808,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6257,
      "step": 87
    },
    {
      "epoch": 0.03576145484100376,
      "grad_norm": 0.5117881298065186,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7653,
      "step": 88
    },
    {
      "epoch": 0.03616783500965153,
      "grad_norm": 0.5123875737190247,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6894,
      "step": 89
    },
    {
      "epoch": 0.0365742151782993,
      "grad_norm": 0.5730488300323486,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7029,
      "step": 90
    },
    {
      "epoch": 0.036980595346947066,
      "grad_norm": 0.5926147699356079,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7447,
      "step": 91
    },
    {
      "epoch": 0.03738697551559484,
      "grad_norm": 0.6123211979866028,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.6966,
      "step": 92
    },
    {
      "epoch": 0.03779335568424261,
      "grad_norm": 0.6656809449195862,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7384,
      "step": 93
    },
    {
      "epoch": 0.03819973585289038,
      "grad_norm": 0.717059314250946,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6863,
      "step": 94
    },
    {
      "epoch": 0.03860611602153815,
      "grad_norm": 0.8445681929588318,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6915,
      "step": 95
    },
    {
      "epoch": 0.039012496190185916,
      "grad_norm": 1.0902982950210571,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7754,
      "step": 96
    },
    {
      "epoch": 0.03941887635883369,
      "grad_norm": 1.0230746269226074,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6997,
      "step": 97
    },
    {
      "epoch": 0.03982525652748146,
      "grad_norm": 1.252565622329712,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6817,
      "step": 98
    },
    {
      "epoch": 0.04023163669612923,
      "grad_norm": 1.4270718097686768,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.8816,
      "step": 99
    },
    {
      "epoch": 0.040638016864777,
      "grad_norm": 1.4159191846847534,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.4889,
      "step": 100
    },
    {
      "epoch": 0.040638016864777,
      "eval_loss": 0.6537060737609863,
      "eval_runtime": 324.3271,
      "eval_samples_per_second": 12.78,
      "eval_steps_per_second": 3.197,
      "step": 100
    },
    {
      "epoch": 0.041044397033424766,
      "grad_norm": 0.29153937101364136,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.4053,
      "step": 101
    },
    {
      "epoch": 0.04145077720207254,
      "grad_norm": 0.3360256254673004,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.463,
      "step": 102
    },
    {
      "epoch": 0.04185715737072031,
      "grad_norm": 0.3049038350582123,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.4448,
      "step": 103
    },
    {
      "epoch": 0.04226353753936808,
      "grad_norm": 0.29683127999305725,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.4503,
      "step": 104
    },
    {
      "epoch": 0.04266991770801585,
      "grad_norm": 0.2814784348011017,
      "learning_rate": 5e-05,
      "loss": 0.4805,
      "step": 105
    },
    {
      "epoch": 0.043076297876663616,
      "grad_norm": 0.276571124792099,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.4791,
      "step": 106
    },
    {
      "epoch": 0.04348267804531139,
      "grad_norm": 0.2771744430065155,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.5268,
      "step": 107
    },
    {
      "epoch": 0.04388905821395916,
      "grad_norm": 0.28336915373802185,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.5273,
      "step": 108
    },
    {
      "epoch": 0.04429543838260693,
      "grad_norm": 0.2806955575942993,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.5325,
      "step": 109
    },
    {
      "epoch": 0.0447018185512547,
      "grad_norm": 0.26702681183815,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.5084,
      "step": 110
    },
    {
      "epoch": 0.045108198719902466,
      "grad_norm": 0.28449276089668274,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.5073,
      "step": 111
    },
    {
      "epoch": 0.04551457888855024,
      "grad_norm": 0.2979961335659027,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.578,
      "step": 112
    },
    {
      "epoch": 0.04592095905719801,
      "grad_norm": 0.29456135630607605,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.5686,
      "step": 113
    },
    {
      "epoch": 0.04632733922584578,
      "grad_norm": 0.28308016061782837,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.5609,
      "step": 114
    },
    {
      "epoch": 0.04673371939449355,
      "grad_norm": 0.3001972734928131,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.5683,
      "step": 115
    },
    {
      "epoch": 0.047140099563141316,
      "grad_norm": 0.3108060359954834,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.6219,
      "step": 116
    },
    {
      "epoch": 0.04754647973178909,
      "grad_norm": 0.34362515807151794,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.6131,
      "step": 117
    },
    {
      "epoch": 0.04795285990043686,
      "grad_norm": 0.3093394339084625,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.5979,
      "step": 118
    },
    {
      "epoch": 0.04835924006908463,
      "grad_norm": 0.31067323684692383,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.5956,
      "step": 119
    },
    {
      "epoch": 0.0487656202377324,
      "grad_norm": 0.3171115815639496,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.5799,
      "step": 120
    },
    {
      "epoch": 0.049172000406380166,
      "grad_norm": 0.3306173086166382,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.6741,
      "step": 121
    },
    {
      "epoch": 0.04957838057502794,
      "grad_norm": 0.34329941868782043,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6716,
      "step": 122
    },
    {
      "epoch": 0.04998476074367571,
      "grad_norm": 0.3293571174144745,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.648,
      "step": 123
    },
    {
      "epoch": 0.05039114091232348,
      "grad_norm": 0.3370497226715088,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6112,
      "step": 124
    },
    {
      "epoch": 0.05079752108097125,
      "grad_norm": 0.31460097432136536,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.6038,
      "step": 125
    },
    {
      "epoch": 0.051203901249619016,
      "grad_norm": 0.3532765209674835,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.7412,
      "step": 126
    },
    {
      "epoch": 0.05161028141826679,
      "grad_norm": 0.36661919951438904,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7394,
      "step": 127
    },
    {
      "epoch": 0.05201666158691456,
      "grad_norm": 0.35972923040390015,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7378,
      "step": 128
    },
    {
      "epoch": 0.05242304175556233,
      "grad_norm": 0.3590826392173767,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.6347,
      "step": 129
    },
    {
      "epoch": 0.0528294219242101,
      "grad_norm": 0.36343610286712646,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6365,
      "step": 130
    },
    {
      "epoch": 0.053235802092857866,
      "grad_norm": 0.4085390567779541,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6899,
      "step": 131
    },
    {
      "epoch": 0.05364218226150564,
      "grad_norm": 0.4001818597316742,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.5884,
      "step": 132
    },
    {
      "epoch": 0.05404856243015341,
      "grad_norm": 0.3833065927028656,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.5881,
      "step": 133
    },
    {
      "epoch": 0.05445494259880118,
      "grad_norm": 0.41603603959083557,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.6404,
      "step": 134
    },
    {
      "epoch": 0.05486132276744895,
      "grad_norm": 0.4442412257194519,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.6538,
      "step": 135
    },
    {
      "epoch": 0.055267702936096716,
      "grad_norm": 0.4578719139099121,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.6446,
      "step": 136
    },
    {
      "epoch": 0.05567408310474449,
      "grad_norm": 0.45253047347068787,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.6825,
      "step": 137
    },
    {
      "epoch": 0.05608046327339226,
      "grad_norm": 0.45945021510124207,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.6229,
      "step": 138
    },
    {
      "epoch": 0.05648684344204003,
      "grad_norm": 0.47304898500442505,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.7037,
      "step": 139
    },
    {
      "epoch": 0.0568932236106878,
      "grad_norm": 0.46290355920791626,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.6147,
      "step": 140
    },
    {
      "epoch": 0.057299603779335566,
      "grad_norm": 0.533750057220459,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7219,
      "step": 141
    },
    {
      "epoch": 0.05770598394798334,
      "grad_norm": 0.5705858469009399,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.7157,
      "step": 142
    },
    {
      "epoch": 0.05811236411663111,
      "grad_norm": 0.6732305288314819,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7586,
      "step": 143
    },
    {
      "epoch": 0.05851874428527888,
      "grad_norm": 0.5787506699562073,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.6348,
      "step": 144
    },
    {
      "epoch": 0.05892512445392665,
      "grad_norm": 0.6227779388427734,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7038,
      "step": 145
    },
    {
      "epoch": 0.059331504622574416,
      "grad_norm": 0.776470959186554,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.7175,
      "step": 146
    },
    {
      "epoch": 0.05973788479122219,
      "grad_norm": 0.9819381237030029,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.7219,
      "step": 147
    },
    {
      "epoch": 0.06014426495986996,
      "grad_norm": 1.0406544208526611,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.7688,
      "step": 148
    },
    {
      "epoch": 0.06055064512851773,
      "grad_norm": 1.3075764179229736,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.8421,
      "step": 149
    },
    {
      "epoch": 0.0609570252971655,
      "grad_norm": 1.3507052659988403,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.586,
      "step": 150
    },
    {
      "epoch": 0.0609570252971655,
      "eval_loss": 0.601864218711853,
      "eval_runtime": 324.7775,
      "eval_samples_per_second": 12.763,
      "eval_steps_per_second": 3.193,
      "step": 150
    },
    {
      "epoch": 0.061363405465813266,
      "grad_norm": 0.16718070209026337,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.3547,
      "step": 151
    },
    {
      "epoch": 0.06176978563446104,
      "grad_norm": 0.196420356631279,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.3913,
      "step": 152
    },
    {
      "epoch": 0.06217616580310881,
      "grad_norm": 0.20742806792259216,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.4179,
      "step": 153
    },
    {
      "epoch": 0.06258254597175658,
      "grad_norm": 0.21235616505146027,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.4586,
      "step": 154
    },
    {
      "epoch": 0.06298892614040434,
      "grad_norm": 0.22335867583751678,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.4576,
      "step": 155
    },
    {
      "epoch": 0.06339530630905212,
      "grad_norm": 0.2386017143726349,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.4881,
      "step": 156
    },
    {
      "epoch": 0.06380168647769989,
      "grad_norm": 0.24453483521938324,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.5078,
      "step": 157
    },
    {
      "epoch": 0.06420806664634766,
      "grad_norm": 0.25477778911590576,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.5025,
      "step": 158
    },
    {
      "epoch": 0.06461444681499542,
      "grad_norm": 0.24356292188167572,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.4688,
      "step": 159
    },
    {
      "epoch": 0.0650208269836432,
      "grad_norm": 0.2839551270008087,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.5986,
      "step": 160
    },
    {
      "epoch": 0.06542720715229097,
      "grad_norm": 0.26258715987205505,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.5427,
      "step": 161
    },
    {
      "epoch": 0.06583358732093873,
      "grad_norm": 0.26351988315582275,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.5026,
      "step": 162
    },
    {
      "epoch": 0.06623996748958651,
      "grad_norm": 0.2849787473678589,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.5898,
      "step": 163
    },
    {
      "epoch": 0.06664634765823428,
      "grad_norm": 0.3135576844215393,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.5598,
      "step": 164
    },
    {
      "epoch": 0.06705272782688204,
      "grad_norm": 0.28335967659950256,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.5478,
      "step": 165
    },
    {
      "epoch": 0.06745910799552982,
      "grad_norm": 0.28295546770095825,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.5602,
      "step": 166
    },
    {
      "epoch": 0.06786548816417759,
      "grad_norm": 0.2867031693458557,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.5669,
      "step": 167
    },
    {
      "epoch": 0.06827186833282536,
      "grad_norm": 0.2970832288265228,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.5658,
      "step": 168
    },
    {
      "epoch": 0.06867824850147312,
      "grad_norm": 0.301959753036499,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.5396,
      "step": 169
    },
    {
      "epoch": 0.0690846286701209,
      "grad_norm": 0.3034633696079254,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.5869,
      "step": 170
    },
    {
      "epoch": 0.06949100883876867,
      "grad_norm": 0.3122958838939667,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.5953,
      "step": 171
    },
    {
      "epoch": 0.06989738900741643,
      "grad_norm": 0.29792520403862,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.5543,
      "step": 172
    },
    {
      "epoch": 0.07030376917606421,
      "grad_norm": 0.3238459527492523,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.607,
      "step": 173
    },
    {
      "epoch": 0.07071014934471198,
      "grad_norm": 0.3111880123615265,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.5687,
      "step": 174
    },
    {
      "epoch": 0.07111652951335974,
      "grad_norm": 0.3515706956386566,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.6497,
      "step": 175
    },
    {
      "epoch": 0.07152290968200752,
      "grad_norm": 0.3376741111278534,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.6586,
      "step": 176
    },
    {
      "epoch": 0.07192928985065529,
      "grad_norm": 0.368792325258255,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.6795,
      "step": 177
    },
    {
      "epoch": 0.07233567001930306,
      "grad_norm": 0.36353152990341187,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.6,
      "step": 178
    },
    {
      "epoch": 0.07274205018795082,
      "grad_norm": 0.40904077887535095,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.7258,
      "step": 179
    },
    {
      "epoch": 0.0731484303565986,
      "grad_norm": 0.3784622550010681,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6551,
      "step": 180
    },
    {
      "epoch": 0.07355481052524637,
      "grad_norm": 0.3995051980018616,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.608,
      "step": 181
    },
    {
      "epoch": 0.07396119069389413,
      "grad_norm": 0.37983453273773193,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.5462,
      "step": 182
    },
    {
      "epoch": 0.0743675708625419,
      "grad_norm": 0.4253169894218445,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.6193,
      "step": 183
    },
    {
      "epoch": 0.07477395103118968,
      "grad_norm": 0.4190753698348999,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.6613,
      "step": 184
    },
    {
      "epoch": 0.07518033119983744,
      "grad_norm": 0.4571462869644165,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.6729,
      "step": 185
    },
    {
      "epoch": 0.07558671136848522,
      "grad_norm": 0.45947661995887756,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.6268,
      "step": 186
    },
    {
      "epoch": 0.07599309153713299,
      "grad_norm": 0.4734838604927063,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.6556,
      "step": 187
    },
    {
      "epoch": 0.07639947170578076,
      "grad_norm": 0.46690595149993896,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6492,
      "step": 188
    },
    {
      "epoch": 0.07680585187442852,
      "grad_norm": 0.5277649164199829,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.6791,
      "step": 189
    },
    {
      "epoch": 0.0772122320430763,
      "grad_norm": 0.4808817207813263,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.6501,
      "step": 190
    },
    {
      "epoch": 0.07761861221172407,
      "grad_norm": 0.6094409823417664,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.774,
      "step": 191
    },
    {
      "epoch": 0.07802499238037183,
      "grad_norm": 0.5904640555381775,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.6561,
      "step": 192
    },
    {
      "epoch": 0.0784313725490196,
      "grad_norm": 0.6269820928573608,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.7267,
      "step": 193
    },
    {
      "epoch": 0.07883775271766738,
      "grad_norm": 0.6637465953826904,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.6865,
      "step": 194
    },
    {
      "epoch": 0.07924413288631514,
      "grad_norm": 0.7612296938896179,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.688,
      "step": 195
    },
    {
      "epoch": 0.07965051305496292,
      "grad_norm": 0.9234216213226318,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.8103,
      "step": 196
    },
    {
      "epoch": 0.08005689322361069,
      "grad_norm": 1.025644063949585,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.7367,
      "step": 197
    },
    {
      "epoch": 0.08046327339225846,
      "grad_norm": 1.365725040435791,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.7141,
      "step": 198
    },
    {
      "epoch": 0.08086965356090622,
      "grad_norm": 1.546324372291565,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.6137,
      "step": 199
    },
    {
      "epoch": 0.081276033729554,
      "grad_norm": 1.5818018913269043,
      "learning_rate": 0.0,
      "loss": 0.8947,
      "step": 200
    },
    {
      "epoch": 0.081276033729554,
      "eval_loss": 0.6018400192260742,
      "eval_runtime": 324.2175,
      "eval_samples_per_second": 12.785,
      "eval_steps_per_second": 3.198,
      "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": 3.103766688269599e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}