{
  "best_metric": 0.5702857375144958,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 2.857142857142857,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014285714285714285,
      "grad_norm": 2.519127607345581,
      "learning_rate": 1e-05,
      "loss": 2.985,
      "step": 1
    },
    {
      "epoch": 0.014285714285714285,
      "eval_loss": 3.75492525100708,
      "eval_runtime": 11.3908,
      "eval_samples_per_second": 10.359,
      "eval_steps_per_second": 2.634,
      "step": 1
    },
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 3.209221124649048,
      "learning_rate": 2e-05,
      "loss": 3.6962,
      "step": 2
    },
    {
      "epoch": 0.04285714285714286,
      "grad_norm": 3.748162269592285,
      "learning_rate": 3e-05,
      "loss": 3.9344,
      "step": 3
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 4.119169235229492,
      "learning_rate": 4e-05,
      "loss": 4.3858,
      "step": 4
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 5.879914283752441,
      "learning_rate": 5e-05,
      "loss": 5.2543,
      "step": 5
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 7.298717975616455,
      "learning_rate": 6e-05,
      "loss": 5.9522,
      "step": 6
    },
    {
      "epoch": 0.1,
      "grad_norm": 6.251786708831787,
      "learning_rate": 7e-05,
      "loss": 2.5727,
      "step": 7
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 3.9049463272094727,
      "learning_rate": 8e-05,
      "loss": 2.0242,
      "step": 8
    },
    {
      "epoch": 0.12857142857142856,
      "grad_norm": 3.813844919204712,
      "learning_rate": 9e-05,
      "loss": 1.5286,
      "step": 9
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 7.440138339996338,
      "learning_rate": 0.0001,
      "loss": 1.9084,
      "step": 10
    },
    {
      "epoch": 0.15714285714285714,
      "grad_norm": 4.414340496063232,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.1659,
      "step": 11
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 3.153130292892456,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.3703,
      "step": 12
    },
    {
      "epoch": 0.18571428571428572,
      "grad_norm": 3.876814603805542,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.8993,
      "step": 13
    },
    {
      "epoch": 0.2,
      "grad_norm": 2.7842297554016113,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.099,
      "step": 14
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 3.0498592853546143,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.3144,
      "step": 15
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 5.432994842529297,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.4012,
      "step": 16
    },
    {
      "epoch": 0.24285714285714285,
      "grad_norm": 7.054082870483398,
      "learning_rate": 9.966546331768191e-05,
      "loss": 2.764,
      "step": 17
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 3.130740165710449,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.6397,
      "step": 18
    },
    {
      "epoch": 0.2714285714285714,
      "grad_norm": 3.236175298690796,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.6477,
      "step": 19
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 3.804147243499756,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.7096,
      "step": 20
    },
    {
      "epoch": 0.3,
      "grad_norm": 3.9267539978027344,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.3708,
      "step": 21
    },
    {
      "epoch": 0.3142857142857143,
      "grad_norm": 3.7682619094848633,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.0546,
      "step": 22
    },
    {
      "epoch": 0.32857142857142857,
      "grad_norm": 3.176764488220215,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.999,
      "step": 23
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 12.539762496948242,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.5707,
      "step": 24
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 9.397242546081543,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.2526,
      "step": 25
    },
    {
      "epoch": 0.37142857142857144,
      "grad_norm": 5.560171127319336,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.9198,
      "step": 26
    },
    {
      "epoch": 0.38571428571428573,
      "grad_norm": 2.5559253692626953,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.9474,
      "step": 27
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.4075191020965576,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.5628,
      "step": 28
    },
    {
      "epoch": 0.4142857142857143,
      "grad_norm": 2.5436270236968994,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7871,
      "step": 29
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.7659904956817627,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.6873,
      "step": 30
    },
    {
      "epoch": 0.44285714285714284,
      "grad_norm": 2.1641976833343506,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8944,
      "step": 31
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 2.05495285987854,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.9246,
      "step": 32
    },
    {
      "epoch": 0.4714285714285714,
      "grad_norm": 2.315678596496582,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.9817,
      "step": 33
    },
    {
      "epoch": 0.4857142857142857,
      "grad_norm": 3.041677951812744,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.2417,
      "step": 34
    },
    {
      "epoch": 0.5,
      "grad_norm": 2.6964292526245117,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.9742,
      "step": 35
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 2.627190351486206,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.1788,
      "step": 36
    },
    {
      "epoch": 0.5285714285714286,
      "grad_norm": 2.3803153038024902,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.0276,
      "step": 37
    },
    {
      "epoch": 0.5428571428571428,
      "grad_norm": 3.7245514392852783,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.2044,
      "step": 38
    },
    {
      "epoch": 0.5571428571428572,
      "grad_norm": 4.564674377441406,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.9224,
      "step": 39
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 3.461322784423828,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7295,
      "step": 40
    },
    {
      "epoch": 0.5857142857142857,
      "grad_norm": 1.652644157409668,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7221,
      "step": 41
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.437732458114624,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7285,
      "step": 42
    },
    {
      "epoch": 0.6142857142857143,
      "grad_norm": 2.756502628326416,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8202,
      "step": 43
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 2.347248077392578,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.8247,
      "step": 44
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 2.27787709236145,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8575,
      "step": 45
    },
    {
      "epoch": 0.6571428571428571,
      "grad_norm": 1.786317229270935,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.6708,
      "step": 46
    },
    {
      "epoch": 0.6714285714285714,
      "grad_norm": 2.69231915473938,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.0209,
      "step": 47
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 1.9469243288040161,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.823,
      "step": 48
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.8390750885009766,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6969,
      "step": 49
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.7473998069763184,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.6906,
      "step": 50
    },
    {
      "epoch": 0.7142857142857143,
      "eval_loss": 0.7170376777648926,
      "eval_runtime": 11.606,
      "eval_samples_per_second": 10.167,
      "eval_steps_per_second": 2.585,
      "step": 50
    },
    {
      "epoch": 0.7285714285714285,
      "grad_norm": 2.934380292892456,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.3184,
      "step": 51
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 2.639586925506592,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.1347,
      "step": 52
    },
    {
      "epoch": 0.7571428571428571,
      "grad_norm": 1.953918218612671,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.7801,
      "step": 53
    },
    {
      "epoch": 0.7714285714285715,
      "grad_norm": 1.699932336807251,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.8282,
      "step": 54
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 2.004262685775757,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.9015,
      "step": 55
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.690697193145752,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.6823,
      "step": 56
    },
    {
      "epoch": 0.8142857142857143,
      "grad_norm": 3.4753313064575195,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.5769,
      "step": 57
    },
    {
      "epoch": 0.8285714285714286,
      "grad_norm": 2.999044895172119,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.6295,
      "step": 58
    },
    {
      "epoch": 0.8428571428571429,
      "grad_norm": 2.3511900901794434,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.6905,
      "step": 59
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 2.1141486167907715,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.603,
      "step": 60
    },
    {
      "epoch": 0.8714285714285714,
      "grad_norm": 1.5743640661239624,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6214,
      "step": 61
    },
    {
      "epoch": 0.8857142857142857,
      "grad_norm": 1.8264353275299072,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.4951,
      "step": 62
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.8982853889465332,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.707,
      "step": 63
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 1.6748406887054443,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.6687,
      "step": 64
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 1.6021674871444702,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.6786,
      "step": 65
    },
    {
      "epoch": 0.9428571428571428,
      "grad_norm": 1.7680158615112305,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.5064,
      "step": 66
    },
    {
      "epoch": 0.9571428571428572,
      "grad_norm": 2.2200098037719727,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.5501,
      "step": 67
    },
    {
      "epoch": 0.9714285714285714,
      "grad_norm": 3.1830990314483643,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7414,
      "step": 68
    },
    {
      "epoch": 0.9857142857142858,
      "grad_norm": 1.3926595449447632,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.6525,
      "step": 69
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.7112162113189697,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.5554,
      "step": 70
    },
    {
      "epoch": 1.0142857142857142,
      "grad_norm": 1.6711753606796265,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7621,
      "step": 71
    },
    {
      "epoch": 1.0285714285714285,
      "grad_norm": 1.2971895933151245,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5844,
      "step": 72
    },
    {
      "epoch": 1.042857142857143,
      "grad_norm": 1.1436983346939087,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.655,
      "step": 73
    },
    {
      "epoch": 1.0571428571428572,
      "grad_norm": 1.364099383354187,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.5002,
      "step": 74
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": 1.8819807767868042,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.5487,
      "step": 75
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 2.837761163711548,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.5375,
      "step": 76
    },
    {
      "epoch": 1.1,
      "grad_norm": 1.5943292379379272,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.597,
      "step": 77
    },
    {
      "epoch": 1.1142857142857143,
      "grad_norm": 1.2622092962265015,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.4901,
      "step": 78
    },
    {
      "epoch": 1.1285714285714286,
      "grad_norm": 1.1407673358917236,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.3664,
      "step": 79
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 1.1375619173049927,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.4146,
      "step": 80
    },
    {
      "epoch": 1.157142857142857,
      "grad_norm": 1.943062663078308,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.3615,
      "step": 81
    },
    {
      "epoch": 1.1714285714285715,
      "grad_norm": 1.3213945627212524,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.2736,
      "step": 82
    },
    {
      "epoch": 1.1857142857142857,
      "grad_norm": 1.1036525964736938,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.2924,
      "step": 83
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.7500133514404297,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.4516,
      "step": 84
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": 1.616390585899353,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.2837,
      "step": 85
    },
    {
      "epoch": 1.2285714285714286,
      "grad_norm": 1.2593103647232056,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3234,
      "step": 86
    },
    {
      "epoch": 1.2428571428571429,
      "grad_norm": 4.43123197555542,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.8322,
      "step": 87
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 1.5008331537246704,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7254,
      "step": 88
    },
    {
      "epoch": 1.2714285714285714,
      "grad_norm": 1.5865715742111206,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6037,
      "step": 89
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 1.4093844890594482,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.3552,
      "step": 90
    },
    {
      "epoch": 1.3,
      "grad_norm": 1.5126615762710571,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.4734,
      "step": 91
    },
    {
      "epoch": 1.3142857142857143,
      "grad_norm": 2.392476797103882,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.5126,
      "step": 92
    },
    {
      "epoch": 1.3285714285714285,
      "grad_norm": 3.056910276412964,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4428,
      "step": 93
    },
    {
      "epoch": 1.342857142857143,
      "grad_norm": 1.5416685342788696,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.4955,
      "step": 94
    },
    {
      "epoch": 1.3571428571428572,
      "grad_norm": 1.495749831199646,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.3283,
      "step": 95
    },
    {
      "epoch": 1.3714285714285714,
      "grad_norm": 1.6940240859985352,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.3397,
      "step": 96
    },
    {
      "epoch": 1.3857142857142857,
      "grad_norm": 1.7251911163330078,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.3825,
      "step": 97
    },
    {
      "epoch": 1.4,
      "grad_norm": 1.6736160516738892,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.4352,
      "step": 98
    },
    {
      "epoch": 1.4142857142857144,
      "grad_norm": 1.4652953147888184,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.4346,
      "step": 99
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 1.5905109643936157,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.2946,
      "step": 100
    },
    {
      "epoch": 1.4285714285714286,
      "eval_loss": 0.5829328298568726,
      "eval_runtime": 11.8793,
      "eval_samples_per_second": 9.933,
      "eval_steps_per_second": 2.525,
      "step": 100
    },
    {
      "epoch": 1.4428571428571428,
      "grad_norm": 1.271888256072998,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.2734,
      "step": 101
    },
    {
      "epoch": 1.457142857142857,
      "grad_norm": 1.3705953359603882,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.3089,
      "step": 102
    },
    {
      "epoch": 1.4714285714285715,
      "grad_norm": 1.5721899271011353,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.4384,
      "step": 103
    },
    {
      "epoch": 1.4857142857142858,
      "grad_norm": 1.970078468322754,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.3752,
      "step": 104
    },
    {
      "epoch": 1.5,
      "grad_norm": 2.0915732383728027,
      "learning_rate": 5e-05,
      "loss": 0.6654,
      "step": 105
    },
    {
      "epoch": 1.5142857142857142,
      "grad_norm": 1.9158036708831787,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.6562,
      "step": 106
    },
    {
      "epoch": 1.5285714285714285,
      "grad_norm": 1.5594099760055542,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.4566,
      "step": 107
    },
    {
      "epoch": 1.5428571428571427,
      "grad_norm": 1.6696677207946777,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.511,
      "step": 108
    },
    {
      "epoch": 1.5571428571428572,
      "grad_norm": 2.218414068222046,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.3976,
      "step": 109
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 3.043891429901123,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.3726,
      "step": 110
    },
    {
      "epoch": 1.5857142857142859,
      "grad_norm": 2.990520477294922,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.5719,
      "step": 111
    },
    {
      "epoch": 1.6,
      "grad_norm": 2.552881956100464,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.5422,
      "step": 112
    },
    {
      "epoch": 1.6142857142857143,
      "grad_norm": 2.0727553367614746,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.3478,
      "step": 113
    },
    {
      "epoch": 1.6285714285714286,
      "grad_norm": 1.421685814857483,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.4016,
      "step": 114
    },
    {
      "epoch": 1.6428571428571428,
      "grad_norm": 1.6200323104858398,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.3108,
      "step": 115
    },
    {
      "epoch": 1.657142857142857,
      "grad_norm": 2.0927650928497314,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.3697,
      "step": 116
    },
    {
      "epoch": 1.6714285714285713,
      "grad_norm": 1.0981261730194092,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.2639,
      "step": 117
    },
    {
      "epoch": 1.6857142857142857,
      "grad_norm": 1.4273452758789062,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.3527,
      "step": 118
    },
    {
      "epoch": 1.7,
      "grad_norm": 1.573671817779541,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.339,
      "step": 119
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 1.4407639503479004,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.3433,
      "step": 120
    },
    {
      "epoch": 1.7285714285714286,
      "grad_norm": 2.1770682334899902,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.5287,
      "step": 121
    },
    {
      "epoch": 1.7428571428571429,
      "grad_norm": 2.1485633850097656,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.6635,
      "step": 122
    },
    {
      "epoch": 1.7571428571428571,
      "grad_norm": 2.6578752994537354,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.5962,
      "step": 123
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 2.1222684383392334,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6959,
      "step": 124
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": 2.117124557495117,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.5813,
      "step": 125
    },
    {
      "epoch": 1.8,
      "grad_norm": 1.381250262260437,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.2472,
      "step": 126
    },
    {
      "epoch": 1.8142857142857143,
      "grad_norm": 1.7829511165618896,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.2902,
      "step": 127
    },
    {
      "epoch": 1.8285714285714287,
      "grad_norm": 1.755326509475708,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.3767,
      "step": 128
    },
    {
      "epoch": 1.842857142857143,
      "grad_norm": 1.901581048965454,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.4177,
      "step": 129
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 1.6575934886932373,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.3761,
      "step": 130
    },
    {
      "epoch": 1.8714285714285714,
      "grad_norm": 1.5894078016281128,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3215,
      "step": 131
    },
    {
      "epoch": 1.8857142857142857,
      "grad_norm": 1.1058553457260132,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.2198,
      "step": 132
    },
    {
      "epoch": 1.9,
      "grad_norm": 1.212573528289795,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.1486,
      "step": 133
    },
    {
      "epoch": 1.9142857142857141,
      "grad_norm": 1.2629961967468262,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.2768,
      "step": 134
    },
    {
      "epoch": 1.9285714285714286,
      "grad_norm": 1.2031630277633667,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.2506,
      "step": 135
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 1.4574642181396484,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.309,
      "step": 136
    },
    {
      "epoch": 1.9571428571428573,
      "grad_norm": 1.7468329668045044,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.2791,
      "step": 137
    },
    {
      "epoch": 1.9714285714285715,
      "grad_norm": 2.3594560623168945,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.387,
      "step": 138
    },
    {
      "epoch": 1.9857142857142858,
      "grad_norm": 1.570247769355774,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.4993,
      "step": 139
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.6004133224487305,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.2532,
      "step": 140
    },
    {
      "epoch": 2.0142857142857142,
      "grad_norm": 1.1867337226867676,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.4305,
      "step": 141
    },
    {
      "epoch": 2.0285714285714285,
      "grad_norm": 1.166598916053772,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.3282,
      "step": 142
    },
    {
      "epoch": 2.0428571428571427,
      "grad_norm": 1.198882818222046,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2792,
      "step": 143
    },
    {
      "epoch": 2.057142857142857,
      "grad_norm": 1.2067052125930786,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.1992,
      "step": 144
    },
    {
      "epoch": 2.0714285714285716,
      "grad_norm": 0.8378006219863892,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.1208,
      "step": 145
    },
    {
      "epoch": 2.085714285714286,
      "grad_norm": 1.2983418703079224,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.197,
      "step": 146
    },
    {
      "epoch": 2.1,
      "grad_norm": 1.0510296821594238,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.2351,
      "step": 147
    },
    {
      "epoch": 2.1142857142857143,
      "grad_norm": 1.0158988237380981,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.1511,
      "step": 148
    },
    {
      "epoch": 2.1285714285714286,
      "grad_norm": 0.7991763353347778,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0982,
      "step": 149
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 1.238604187965393,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.1743,
      "step": 150
    },
    {
      "epoch": 2.142857142857143,
      "eval_loss": 0.5702857375144958,
      "eval_runtime": 12.1216,
      "eval_samples_per_second": 9.735,
      "eval_steps_per_second": 2.475,
      "step": 150
    },
    {
      "epoch": 2.157142857142857,
      "grad_norm": 1.1941012144088745,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.1452,
      "step": 151
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 1.109334945678711,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.1816,
      "step": 152
    },
    {
      "epoch": 2.185714285714286,
      "grad_norm": 2.1563236713409424,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.1634,
      "step": 153
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.8632590770721436,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.1013,
      "step": 154
    },
    {
      "epoch": 2.2142857142857144,
      "grad_norm": 1.1032346487045288,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.1238,
      "step": 155
    },
    {
      "epoch": 2.2285714285714286,
      "grad_norm": 0.9520765542984009,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.1144,
      "step": 156
    },
    {
      "epoch": 2.242857142857143,
      "grad_norm": 1.1301237344741821,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.1697,
      "step": 157
    },
    {
      "epoch": 2.257142857142857,
      "grad_norm": 1.370141625404358,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.3614,
      "step": 158
    },
    {
      "epoch": 2.2714285714285714,
      "grad_norm": 1.5145504474639893,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.3282,
      "step": 159
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 1.321903944015503,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.2861,
      "step": 160
    },
    {
      "epoch": 2.3,
      "grad_norm": 1.6712088584899902,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.3021,
      "step": 161
    },
    {
      "epoch": 2.314285714285714,
      "grad_norm": 1.4461297988891602,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2127,
      "step": 162
    },
    {
      "epoch": 2.3285714285714287,
      "grad_norm": 1.1821919679641724,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.171,
      "step": 163
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 1.4862414598464966,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.2028,
      "step": 164
    },
    {
      "epoch": 2.357142857142857,
      "grad_norm": 1.4551775455474854,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.2536,
      "step": 165
    },
    {
      "epoch": 2.3714285714285714,
      "grad_norm": 1.2563072443008423,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.1257,
      "step": 166
    },
    {
      "epoch": 2.3857142857142857,
      "grad_norm": 1.1403878927230835,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.1571,
      "step": 167
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.1456217765808105,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.1302,
      "step": 168
    },
    {
      "epoch": 2.414285714285714,
      "grad_norm": 0.8845107555389404,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.0685,
      "step": 169
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.9619492292404175,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.1286,
      "step": 170
    },
    {
      "epoch": 2.442857142857143,
      "grad_norm": 1.2658023834228516,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.1488,
      "step": 171
    },
    {
      "epoch": 2.4571428571428573,
      "grad_norm": 0.9267793297767639,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.1032,
      "step": 172
    },
    {
      "epoch": 2.4714285714285715,
      "grad_norm": 0.7833018898963928,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.1033,
      "step": 173
    },
    {
      "epoch": 2.4857142857142858,
      "grad_norm": 1.8847062587738037,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.267,
      "step": 174
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.602597713470459,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.4773,
      "step": 175
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 1.2742280960083008,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.2388,
      "step": 176
    },
    {
      "epoch": 2.5285714285714285,
      "grad_norm": 1.4369244575500488,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.2101,
      "step": 177
    },
    {
      "epoch": 2.5428571428571427,
      "grad_norm": 1.5318524837493896,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.2578,
      "step": 178
    },
    {
      "epoch": 2.557142857142857,
      "grad_norm": 1.0596178770065308,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.1125,
      "step": 179
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.9206764101982117,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0764,
      "step": 180
    },
    {
      "epoch": 2.585714285714286,
      "grad_norm": 1.5647659301757812,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2418,
      "step": 181
    },
    {
      "epoch": 2.6,
      "grad_norm": 1.2543052434921265,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.1787,
      "step": 182
    },
    {
      "epoch": 2.6142857142857143,
      "grad_norm": 1.5105377435684204,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.1719,
      "step": 183
    },
    {
      "epoch": 2.6285714285714286,
      "grad_norm": 1.047243595123291,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0807,
      "step": 184
    },
    {
      "epoch": 2.642857142857143,
      "grad_norm": 1.3366680145263672,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.094,
      "step": 185
    },
    {
      "epoch": 2.657142857142857,
      "grad_norm": 1.3723382949829102,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.1605,
      "step": 186
    },
    {
      "epoch": 2.6714285714285713,
      "grad_norm": 1.1282715797424316,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0923,
      "step": 187
    },
    {
      "epoch": 2.685714285714286,
      "grad_norm": 1.4394956827163696,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.1583,
      "step": 188
    },
    {
      "epoch": 2.7,
      "grad_norm": 1.0634617805480957,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0887,
      "step": 189
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.7819549441337585,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.0814,
      "step": 190
    },
    {
      "epoch": 2.7285714285714286,
      "grad_norm": 1.9579026699066162,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.2219,
      "step": 191
    },
    {
      "epoch": 2.742857142857143,
      "grad_norm": 1.5076329708099365,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.3629,
      "step": 192
    },
    {
      "epoch": 2.757142857142857,
      "grad_norm": 1.2045427560806274,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.2177,
      "step": 193
    },
    {
      "epoch": 2.7714285714285714,
      "grad_norm": 1.2471433877944946,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.2475,
      "step": 194
    },
    {
      "epoch": 2.7857142857142856,
      "grad_norm": 1.3904614448547363,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.243,
      "step": 195
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.3182437419891357,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.1965,
      "step": 196
    },
    {
      "epoch": 2.814285714285714,
      "grad_norm": 1.5571266412734985,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.1518,
      "step": 197
    },
    {
      "epoch": 2.8285714285714287,
      "grad_norm": 1.4020003080368042,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.2513,
      "step": 198
    },
    {
      "epoch": 2.842857142857143,
      "grad_norm": 0.9706946611404419,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.1057,
      "step": 199
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.8867482542991638,
      "learning_rate": 0.0,
      "loss": 0.0712,
      "step": 200
    },
    {
      "epoch": 2.857142857142857,
      "eval_loss": 0.6212335228919983,
      "eval_runtime": 11.8615,
      "eval_samples_per_second": 9.948,
      "eval_steps_per_second": 2.529,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3.9261901324025856e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}