{
  "best_metric": 0.8381313681602478,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.7797270955165692,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003898635477582846,
      "grad_norm": 4.90963077545166,
      "learning_rate": 1e-05,
      "loss": 1.6507,
      "step": 1
    },
    {
      "epoch": 0.003898635477582846,
      "eval_loss": 2.4988527297973633,
      "eval_runtime": 19.1872,
      "eval_samples_per_second": 22.515,
      "eval_steps_per_second": 5.629,
      "step": 1
    },
    {
      "epoch": 0.007797270955165692,
      "grad_norm": 6.177927017211914,
      "learning_rate": 2e-05,
      "loss": 1.5088,
      "step": 2
    },
    {
      "epoch": 0.011695906432748537,
      "grad_norm": 6.14262056350708,
      "learning_rate": 3e-05,
      "loss": 1.6325,
      "step": 3
    },
    {
      "epoch": 0.015594541910331383,
      "grad_norm": 4.573946952819824,
      "learning_rate": 4e-05,
      "loss": 1.3979,
      "step": 4
    },
    {
      "epoch": 0.01949317738791423,
      "grad_norm": 3.1987500190734863,
      "learning_rate": 5e-05,
      "loss": 1.1356,
      "step": 5
    },
    {
      "epoch": 0.023391812865497075,
      "grad_norm": 3.196948528289795,
      "learning_rate": 6e-05,
      "loss": 1.1399,
      "step": 6
    },
    {
      "epoch": 0.02729044834307992,
      "grad_norm": 2.340547561645508,
      "learning_rate": 7e-05,
      "loss": 1.0067,
      "step": 7
    },
    {
      "epoch": 0.031189083820662766,
      "grad_norm": 1.8619967699050903,
      "learning_rate": 8e-05,
      "loss": 0.9345,
      "step": 8
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 1.89539635181427,
      "learning_rate": 9e-05,
      "loss": 0.9866,
      "step": 9
    },
    {
      "epoch": 0.03898635477582846,
      "grad_norm": 1.9467284679412842,
      "learning_rate": 0.0001,
      "loss": 1.1453,
      "step": 10
    },
    {
      "epoch": 0.042884990253411304,
      "grad_norm": 1.6094034910202026,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.9341,
      "step": 11
    },
    {
      "epoch": 0.04678362573099415,
      "grad_norm": 1.5425618886947632,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.0645,
      "step": 12
    },
    {
      "epoch": 0.050682261208576995,
      "grad_norm": 1.3987034559249878,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9663,
      "step": 13
    },
    {
      "epoch": 0.05458089668615984,
      "grad_norm": 1.562097430229187,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.9752,
      "step": 14
    },
    {
      "epoch": 0.05847953216374269,
      "grad_norm": 1.5005643367767334,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.1453,
      "step": 15
    },
    {
      "epoch": 0.06237816764132553,
      "grad_norm": 1.5458860397338867,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.0051,
      "step": 16
    },
    {
      "epoch": 0.06627680311890838,
      "grad_norm": 1.4813910722732544,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.0084,
      "step": 17
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 1.7048490047454834,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.1536,
      "step": 18
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 1.5201245546340942,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.0227,
      "step": 19
    },
    {
      "epoch": 0.07797270955165692,
      "grad_norm": 1.6540536880493164,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.0257,
      "step": 20
    },
    {
      "epoch": 0.08187134502923976,
      "grad_norm": 1.7732887268066406,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.0373,
      "step": 21
    },
    {
      "epoch": 0.08576998050682261,
      "grad_norm": 1.7157306671142578,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.1416,
      "step": 22
    },
    {
      "epoch": 0.08966861598440545,
      "grad_norm": 1.8828952312469482,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.2096,
      "step": 23
    },
    {
      "epoch": 0.0935672514619883,
      "grad_norm": 2.749904155731201,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.1399,
      "step": 24
    },
    {
      "epoch": 0.09746588693957114,
      "grad_norm": 1.5427305698394775,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.9655,
      "step": 25
    },
    {
      "epoch": 0.10136452241715399,
      "grad_norm": 1.8717269897460938,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.2355,
      "step": 26
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 1.6260595321655273,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.9651,
      "step": 27
    },
    {
      "epoch": 0.10916179337231968,
      "grad_norm": 1.7931687831878662,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.1854,
      "step": 28
    },
    {
      "epoch": 0.11306042884990253,
      "grad_norm": 1.480766773223877,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.886,
      "step": 29
    },
    {
      "epoch": 0.11695906432748537,
      "grad_norm": 1.5593950748443604,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9215,
      "step": 30
    },
    {
      "epoch": 0.12085769980506822,
      "grad_norm": 1.5582053661346436,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.0217,
      "step": 31
    },
    {
      "epoch": 0.12475633528265107,
      "grad_norm": 1.6883318424224854,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.0148,
      "step": 32
    },
    {
      "epoch": 0.1286549707602339,
      "grad_norm": 1.5681369304656982,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8947,
      "step": 33
    },
    {
      "epoch": 0.13255360623781676,
      "grad_norm": 1.6557368040084839,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.9614,
      "step": 34
    },
    {
      "epoch": 0.1364522417153996,
      "grad_norm": 1.9279215335845947,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.0485,
      "step": 35
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 1.7705576419830322,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.9417,
      "step": 36
    },
    {
      "epoch": 0.1442495126705653,
      "grad_norm": 2.0263447761535645,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.0199,
      "step": 37
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.711944580078125,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8542,
      "step": 38
    },
    {
      "epoch": 0.15204678362573099,
      "grad_norm": 1.5743972063064575,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.8234,
      "step": 39
    },
    {
      "epoch": 0.15594541910331383,
      "grad_norm": 1.870926856994629,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.9552,
      "step": 40
    },
    {
      "epoch": 0.15984405458089668,
      "grad_norm": 1.7767713069915771,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7834,
      "step": 41
    },
    {
      "epoch": 0.16374269005847952,
      "grad_norm": 1.9706684350967407,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9514,
      "step": 42
    },
    {
      "epoch": 0.16764132553606237,
      "grad_norm": 1.9393295049667358,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.734,
      "step": 43
    },
    {
      "epoch": 0.17153996101364521,
      "grad_norm": 1.9289604425430298,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.8515,
      "step": 44
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 2.444415330886841,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.9716,
      "step": 45
    },
    {
      "epoch": 0.1793372319688109,
      "grad_norm": 2.3726983070373535,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.9559,
      "step": 46
    },
    {
      "epoch": 0.18323586744639375,
      "grad_norm": 2.310903549194336,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.9794,
      "step": 47
    },
    {
      "epoch": 0.1871345029239766,
      "grad_norm": 2.8057477474212646,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.0433,
      "step": 48
    },
    {
      "epoch": 0.19103313840155944,
      "grad_norm": 4.125555038452148,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.2519,
      "step": 49
    },
    {
      "epoch": 0.1949317738791423,
      "grad_norm": 3.5546317100524902,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.1267,
      "step": 50
    },
    {
      "epoch": 0.1949317738791423,
      "eval_loss": 1.1245676279067993,
      "eval_runtime": 19.2201,
      "eval_samples_per_second": 22.476,
      "eval_steps_per_second": 5.619,
      "step": 50
    },
    {
      "epoch": 0.19883040935672514,
      "grad_norm": 3.8160557746887207,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.4157,
      "step": 51
    },
    {
      "epoch": 0.20272904483430798,
      "grad_norm": 2.509950637817383,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.0091,
      "step": 52
    },
    {
      "epoch": 0.20662768031189083,
      "grad_norm": 1.5624240636825562,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.0101,
      "step": 53
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 1.0679713487625122,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.8846,
      "step": 54
    },
    {
      "epoch": 0.21442495126705652,
      "grad_norm": 1.3471870422363281,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.8174,
      "step": 55
    },
    {
      "epoch": 0.21832358674463936,
      "grad_norm": 1.1532950401306152,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.8976,
      "step": 56
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.104249358177185,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.8191,
      "step": 57
    },
    {
      "epoch": 0.22612085769980506,
      "grad_norm": 0.9159103631973267,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.8686,
      "step": 58
    },
    {
      "epoch": 0.2300194931773879,
      "grad_norm": 0.9362701773643494,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.7816,
      "step": 59
    },
    {
      "epoch": 0.23391812865497075,
      "grad_norm": 1.00645112991333,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.9014,
      "step": 60
    },
    {
      "epoch": 0.2378167641325536,
      "grad_norm": 1.0416297912597656,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.8775,
      "step": 61
    },
    {
      "epoch": 0.24171539961013644,
      "grad_norm": 0.9825323820114136,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.7537,
      "step": 62
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 0.9186838865280151,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7195,
      "step": 63
    },
    {
      "epoch": 0.24951267056530213,
      "grad_norm": 0.9931292533874512,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.8496,
      "step": 64
    },
    {
      "epoch": 0.253411306042885,
      "grad_norm": 1.144757866859436,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.0131,
      "step": 65
    },
    {
      "epoch": 0.2573099415204678,
      "grad_norm": 1.1379342079162598,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.9548,
      "step": 66
    },
    {
      "epoch": 0.26120857699805067,
      "grad_norm": 1.1928482055664062,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.9502,
      "step": 67
    },
    {
      "epoch": 0.2651072124756335,
      "grad_norm": 1.1090162992477417,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.0886,
      "step": 68
    },
    {
      "epoch": 0.26900584795321636,
      "grad_norm": 1.1548633575439453,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.0118,
      "step": 69
    },
    {
      "epoch": 0.2729044834307992,
      "grad_norm": 1.2537670135498047,
      "learning_rate": 7.734740790612136e-05,
      "loss": 1.058,
      "step": 70
    },
    {
      "epoch": 0.27680311890838205,
      "grad_norm": 1.2101843357086182,
      "learning_rate": 7.66515864363997e-05,
      "loss": 1.0915,
      "step": 71
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 1.147745132446289,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.0505,
      "step": 72
    },
    {
      "epoch": 0.28460038986354774,
      "grad_norm": 1.2283207178115845,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.9304,
      "step": 73
    },
    {
      "epoch": 0.2884990253411306,
      "grad_norm": 1.2400833368301392,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.9748,
      "step": 74
    },
    {
      "epoch": 0.29239766081871343,
      "grad_norm": 1.0907278060913086,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7978,
      "step": 75
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 1.0984690189361572,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.8842,
      "step": 76
    },
    {
      "epoch": 0.3001949317738791,
      "grad_norm": 1.291126012802124,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.9813,
      "step": 77
    },
    {
      "epoch": 0.30409356725146197,
      "grad_norm": 1.2157424688339233,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.8265,
      "step": 78
    },
    {
      "epoch": 0.3079922027290448,
      "grad_norm": 1.2085779905319214,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.824,
      "step": 79
    },
    {
      "epoch": 0.31189083820662766,
      "grad_norm": 1.2817813158035278,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.8366,
      "step": 80
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 1.3367719650268555,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.8464,
      "step": 81
    },
    {
      "epoch": 0.31968810916179335,
      "grad_norm": 1.5635021924972534,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.811,
      "step": 82
    },
    {
      "epoch": 0.3235867446393762,
      "grad_norm": 1.2968013286590576,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.8215,
      "step": 83
    },
    {
      "epoch": 0.32748538011695905,
      "grad_norm": 1.475118637084961,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.9895,
      "step": 84
    },
    {
      "epoch": 0.3313840155945419,
      "grad_norm": 1.7100423574447632,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.8798,
      "step": 85
    },
    {
      "epoch": 0.33528265107212474,
      "grad_norm": 1.5012485980987549,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8908,
      "step": 86
    },
    {
      "epoch": 0.3391812865497076,
      "grad_norm": 1.6295896768569946,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.9206,
      "step": 87
    },
    {
      "epoch": 0.34307992202729043,
      "grad_norm": 1.6735135316848755,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.9472,
      "step": 88
    },
    {
      "epoch": 0.3469785575048733,
      "grad_norm": 1.7130054235458374,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.0369,
      "step": 89
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 1.6237515211105347,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.902,
      "step": 90
    },
    {
      "epoch": 0.35477582846003897,
      "grad_norm": 1.4516394138336182,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.8535,
      "step": 91
    },
    {
      "epoch": 0.3586744639376218,
      "grad_norm": 1.6372218132019043,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.865,
      "step": 92
    },
    {
      "epoch": 0.36257309941520466,
      "grad_norm": 1.4809690713882446,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.805,
      "step": 93
    },
    {
      "epoch": 0.3664717348927875,
      "grad_norm": 1.3445452451705933,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.7176,
      "step": 94
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.3368396759033203,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6981,
      "step": 95
    },
    {
      "epoch": 0.3742690058479532,
      "grad_norm": 1.6319324970245361,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.8374,
      "step": 96
    },
    {
      "epoch": 0.37816764132553604,
      "grad_norm": 1.7608789205551147,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.9572,
      "step": 97
    },
    {
      "epoch": 0.3820662768031189,
      "grad_norm": 1.650806188583374,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.7664,
      "step": 98
    },
    {
      "epoch": 0.38596491228070173,
      "grad_norm": 2.386909008026123,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.0769,
      "step": 99
    },
    {
      "epoch": 0.3898635477582846,
      "grad_norm": 2.659219741821289,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.1377,
      "step": 100
    },
    {
      "epoch": 0.3898635477582846,
      "eval_loss": 0.96268630027771,
      "eval_runtime": 19.2345,
      "eval_samples_per_second": 22.46,
      "eval_steps_per_second": 5.615,
      "step": 100
    },
    {
      "epoch": 0.3937621832358674,
      "grad_norm": 2.57578706741333,
      "learning_rate": 5.330452921628497e-05,
      "loss": 1.1375,
      "step": 101
    },
    {
      "epoch": 0.39766081871345027,
      "grad_norm": 1.840401291847229,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.0448,
      "step": 102
    },
    {
      "epoch": 0.4015594541910331,
      "grad_norm": 1.357450008392334,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.7451,
      "step": 103
    },
    {
      "epoch": 0.40545808966861596,
      "grad_norm": 1.1181912422180176,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.8256,
      "step": 104
    },
    {
      "epoch": 0.4093567251461988,
      "grad_norm": 1.0798479318618774,
      "learning_rate": 5e-05,
      "loss": 0.8896,
      "step": 105
    },
    {
      "epoch": 0.41325536062378165,
      "grad_norm": 0.9752025604248047,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.8598,
      "step": 106
    },
    {
      "epoch": 0.4171539961013645,
      "grad_norm": 0.8327402472496033,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.7254,
      "step": 107
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.9912234544754028,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.7752,
      "step": 108
    },
    {
      "epoch": 0.4249512670565302,
      "grad_norm": 0.8864346742630005,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.6974,
      "step": 109
    },
    {
      "epoch": 0.42884990253411304,
      "grad_norm": 0.840218186378479,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.767,
      "step": 110
    },
    {
      "epoch": 0.4327485380116959,
      "grad_norm": 0.889740526676178,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.8652,
      "step": 111
    },
    {
      "epoch": 0.43664717348927873,
      "grad_norm": 0.9511635303497314,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.7903,
      "step": 112
    },
    {
      "epoch": 0.4405458089668616,
      "grad_norm": 0.8167177438735962,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.7002,
      "step": 113
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.9066333174705505,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.7985,
      "step": 114
    },
    {
      "epoch": 0.44834307992202727,
      "grad_norm": 0.9710180163383484,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.8682,
      "step": 115
    },
    {
      "epoch": 0.4522417153996101,
      "grad_norm": 1.026107668876648,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.9463,
      "step": 116
    },
    {
      "epoch": 0.45614035087719296,
      "grad_norm": 1.144396424293518,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.9756,
      "step": 117
    },
    {
      "epoch": 0.4600389863547758,
      "grad_norm": 0.9720786213874817,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7923,
      "step": 118
    },
    {
      "epoch": 0.46393762183235865,
      "grad_norm": 0.8938807845115662,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.8101,
      "step": 119
    },
    {
      "epoch": 0.4678362573099415,
      "grad_norm": 1.144248127937317,
      "learning_rate": 3.772572564296005e-05,
      "loss": 1.0173,
      "step": 120
    },
    {
      "epoch": 0.47173489278752434,
      "grad_norm": 0.9937459826469421,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.8223,
      "step": 121
    },
    {
      "epoch": 0.4756335282651072,
      "grad_norm": 0.9959102272987366,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.8625,
      "step": 122
    },
    {
      "epoch": 0.47953216374269003,
      "grad_norm": 1.0088458061218262,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.8588,
      "step": 123
    },
    {
      "epoch": 0.4834307992202729,
      "grad_norm": 1.1958123445510864,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.9693,
      "step": 124
    },
    {
      "epoch": 0.4873294346978557,
      "grad_norm": 1.2331714630126953,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.9571,
      "step": 125
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": 1.2077465057373047,
      "learning_rate": 3.298534127791785e-05,
      "loss": 1.0563,
      "step": 126
    },
    {
      "epoch": 0.4951267056530214,
      "grad_norm": 1.073055386543274,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.8451,
      "step": 127
    },
    {
      "epoch": 0.49902534113060426,
      "grad_norm": 1.2219706773757935,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.9929,
      "step": 128
    },
    {
      "epoch": 0.5029239766081871,
      "grad_norm": 1.2187883853912354,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.8952,
      "step": 129
    },
    {
      "epoch": 0.50682261208577,
      "grad_norm": 1.0449047088623047,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.788,
      "step": 130
    },
    {
      "epoch": 0.5107212475633528,
      "grad_norm": 1.2690509557724,
      "learning_rate": 2.916090697523549e-05,
      "loss": 1.0085,
      "step": 131
    },
    {
      "epoch": 0.5146198830409356,
      "grad_norm": 1.0717588663101196,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.7838,
      "step": 132
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 1.0692975521087646,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7223,
      "step": 133
    },
    {
      "epoch": 0.5224171539961013,
      "grad_norm": 1.176875352859497,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7841,
      "step": 134
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 1.1164765357971191,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7474,
      "step": 135
    },
    {
      "epoch": 0.530214424951267,
      "grad_norm": 1.1768156290054321,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7283,
      "step": 136
    },
    {
      "epoch": 0.5341130604288499,
      "grad_norm": 1.33505117893219,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.8782,
      "step": 137
    },
    {
      "epoch": 0.5380116959064327,
      "grad_norm": 1.3603265285491943,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.8582,
      "step": 138
    },
    {
      "epoch": 0.5419103313840156,
      "grad_norm": 1.2987911701202393,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.8193,
      "step": 139
    },
    {
      "epoch": 0.5458089668615984,
      "grad_norm": 1.4902960062026978,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.9436,
      "step": 140
    },
    {
      "epoch": 0.5497076023391813,
      "grad_norm": 1.3773430585861206,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7515,
      "step": 141
    },
    {
      "epoch": 0.5536062378167641,
      "grad_norm": 1.4242339134216309,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.8044,
      "step": 142
    },
    {
      "epoch": 0.557504873294347,
      "grad_norm": 1.589614987373352,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8548,
      "step": 143
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 1.4356437921524048,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.8482,
      "step": 144
    },
    {
      "epoch": 0.5653021442495126,
      "grad_norm": 1.3600770235061646,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6998,
      "step": 145
    },
    {
      "epoch": 0.5692007797270955,
      "grad_norm": 1.4260246753692627,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.683,
      "step": 146
    },
    {
      "epoch": 0.5730994152046783,
      "grad_norm": 1.6639034748077393,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.8587,
      "step": 147
    },
    {
      "epoch": 0.5769980506822612,
      "grad_norm": 1.7599772214889526,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.8492,
      "step": 148
    },
    {
      "epoch": 0.580896686159844,
      "grad_norm": 2.006871461868286,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.1456,
      "step": 149
    },
    {
      "epoch": 0.5847953216374269,
      "grad_norm": 2.1173348426818848,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.0789,
      "step": 150
    },
    {
      "epoch": 0.5847953216374269,
      "eval_loss": 0.8595620393753052,
      "eval_runtime": 19.2515,
      "eval_samples_per_second": 22.44,
      "eval_steps_per_second": 5.61,
      "step": 150
    },
    {
      "epoch": 0.5886939571150097,
      "grad_norm": 1.3765146732330322,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.9562,
      "step": 151
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 1.0930370092391968,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.8387,
      "step": 152
    },
    {
      "epoch": 0.5964912280701754,
      "grad_norm": 1.1251763105392456,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.853,
      "step": 153
    },
    {
      "epoch": 0.6003898635477583,
      "grad_norm": 0.9944729208946228,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.846,
      "step": 154
    },
    {
      "epoch": 0.6042884990253411,
      "grad_norm": 1.0956628322601318,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.7911,
      "step": 155
    },
    {
      "epoch": 0.6081871345029239,
      "grad_norm": 1.2850069999694824,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.8239,
      "step": 156
    },
    {
      "epoch": 0.6120857699805068,
      "grad_norm": 0.8358404040336609,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.7112,
      "step": 157
    },
    {
      "epoch": 0.6159844054580896,
      "grad_norm": 0.8287035226821899,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.681,
      "step": 158
    },
    {
      "epoch": 0.6198830409356725,
      "grad_norm": 0.8843977451324463,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.7649,
      "step": 159
    },
    {
      "epoch": 0.6237816764132553,
      "grad_norm": 0.9642041325569153,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7682,
      "step": 160
    },
    {
      "epoch": 0.6276803118908382,
      "grad_norm": 0.8703583478927612,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7294,
      "step": 161
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.8379156589508057,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7701,
      "step": 162
    },
    {
      "epoch": 0.6354775828460039,
      "grad_norm": 0.876076877117157,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.7334,
      "step": 163
    },
    {
      "epoch": 0.6393762183235867,
      "grad_norm": 1.1558319330215454,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.9088,
      "step": 164
    },
    {
      "epoch": 0.6432748538011696,
      "grad_norm": 0.8530052900314331,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.713,
      "step": 165
    },
    {
      "epoch": 0.6471734892787524,
      "grad_norm": 1.1041018962860107,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.9476,
      "step": 166
    },
    {
      "epoch": 0.6510721247563352,
      "grad_norm": 0.9333986639976501,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.7771,
      "step": 167
    },
    {
      "epoch": 0.6549707602339181,
      "grad_norm": 1.054619312286377,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.9292,
      "step": 168
    },
    {
      "epoch": 0.6588693957115009,
      "grad_norm": 1.0360103845596313,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.8571,
      "step": 169
    },
    {
      "epoch": 0.6627680311890838,
      "grad_norm": 1.012162685394287,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.812,
      "step": 170
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.1223911046981812,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.9188,
      "step": 171
    },
    {
      "epoch": 0.6705653021442495,
      "grad_norm": 1.0251071453094482,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.9477,
      "step": 172
    },
    {
      "epoch": 0.6744639376218323,
      "grad_norm": 1.0444908142089844,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.8948,
      "step": 173
    },
    {
      "epoch": 0.6783625730994152,
      "grad_norm": 1.0306769609451294,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.8377,
      "step": 174
    },
    {
      "epoch": 0.682261208576998,
      "grad_norm": 1.2064474821090698,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 1.0077,
      "step": 175
    },
    {
      "epoch": 0.6861598440545809,
      "grad_norm": 1.0620136260986328,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.8925,
      "step": 176
    },
    {
      "epoch": 0.6900584795321637,
      "grad_norm": 1.111035943031311,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.8747,
      "step": 177
    },
    {
      "epoch": 0.6939571150097466,
      "grad_norm": 1.121589183807373,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7912,
      "step": 178
    },
    {
      "epoch": 0.6978557504873294,
      "grad_norm": 1.3358514308929443,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.8525,
      "step": 179
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 1.1037346124649048,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.8062,
      "step": 180
    },
    {
      "epoch": 0.7056530214424951,
      "grad_norm": 1.4299840927124023,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.8202,
      "step": 181
    },
    {
      "epoch": 0.7095516569200779,
      "grad_norm": 1.1731818914413452,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.8998,
      "step": 182
    },
    {
      "epoch": 0.7134502923976608,
      "grad_norm": 1.220818281173706,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.9044,
      "step": 183
    },
    {
      "epoch": 0.7173489278752436,
      "grad_norm": 1.0840685367584229,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.806,
      "step": 184
    },
    {
      "epoch": 0.7212475633528265,
      "grad_norm": 0.9430334568023682,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.6598,
      "step": 185
    },
    {
      "epoch": 0.7251461988304093,
      "grad_norm": 1.277156949043274,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.8684,
      "step": 186
    },
    {
      "epoch": 0.7290448343079922,
      "grad_norm": 1.352520227432251,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.8438,
      "step": 187
    },
    {
      "epoch": 0.732943469785575,
      "grad_norm": 1.3346585035324097,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.7865,
      "step": 188
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 1.2239853143692017,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.8224,
      "step": 189
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 1.2965459823608398,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.7801,
      "step": 190
    },
    {
      "epoch": 0.7446393762183235,
      "grad_norm": 1.331040620803833,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.8555,
      "step": 191
    },
    {
      "epoch": 0.7485380116959064,
      "grad_norm": 1.328275442123413,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.8474,
      "step": 192
    },
    {
      "epoch": 0.7524366471734892,
      "grad_norm": 1.2639459371566772,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.75,
      "step": 193
    },
    {
      "epoch": 0.7563352826510721,
      "grad_norm": 1.2733054161071777,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.7322,
      "step": 194
    },
    {
      "epoch": 0.7602339181286549,
      "grad_norm": 1.4358400106430054,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.7163,
      "step": 195
    },
    {
      "epoch": 0.7641325536062378,
      "grad_norm": 1.4011861085891724,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.7988,
      "step": 196
    },
    {
      "epoch": 0.7680311890838206,
      "grad_norm": 1.679960012435913,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.9068,
      "step": 197
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": 1.5878187417984009,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.7644,
      "step": 198
    },
    {
      "epoch": 0.7758284600389863,
      "grad_norm": 2.4619383811950684,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.0626,
      "step": 199
    },
    {
      "epoch": 0.7797270955165692,
      "grad_norm": 2.3302814960479736,
      "learning_rate": 0.0,
      "loss": 0.9743,
      "step": 200
    },
    {
      "epoch": 0.7797270955165692,
      "eval_loss": 0.8381313681602478,
      "eval_runtime": 19.2397,
      "eval_samples_per_second": 22.454,
      "eval_steps_per_second": 5.613,
      "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": 8.28736052133888e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}