{
  "best_metric": 0.8675870895385742,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.9259259259259259,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004629629629629629,
      "grad_norm": 17.85034942626953,
      "learning_rate": 1e-05,
      "loss": 5.119,
      "step": 1
    },
    {
      "epoch": 0.004629629629629629,
      "eval_loss": 1.331807017326355,
      "eval_runtime": 2.2021,
      "eval_samples_per_second": 165.298,
      "eval_steps_per_second": 41.324,
      "step": 1
    },
    {
      "epoch": 0.009259259259259259,
      "grad_norm": 23.258453369140625,
      "learning_rate": 2e-05,
      "loss": 4.727,
      "step": 2
    },
    {
      "epoch": 0.013888888888888888,
      "grad_norm": 15.921564102172852,
      "learning_rate": 3e-05,
      "loss": 5.1946,
      "step": 3
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 14.084012031555176,
      "learning_rate": 4e-05,
      "loss": 5.1429,
      "step": 4
    },
    {
      "epoch": 0.023148148148148147,
      "grad_norm": 11.529329299926758,
      "learning_rate": 5e-05,
      "loss": 4.6813,
      "step": 5
    },
    {
      "epoch": 0.027777777777777776,
      "grad_norm": 13.520435333251953,
      "learning_rate": 6e-05,
      "loss": 4.5275,
      "step": 6
    },
    {
      "epoch": 0.032407407407407406,
      "grad_norm": 10.294478416442871,
      "learning_rate": 7e-05,
      "loss": 4.1649,
      "step": 7
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 12.807920455932617,
      "learning_rate": 8e-05,
      "loss": 4.7356,
      "step": 8
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 11.908681869506836,
      "learning_rate": 9e-05,
      "loss": 5.0737,
      "step": 9
    },
    {
      "epoch": 0.046296296296296294,
      "grad_norm": 10.713079452514648,
      "learning_rate": 0.0001,
      "loss": 4.7638,
      "step": 10
    },
    {
      "epoch": 0.05092592592592592,
      "grad_norm": 11.653141021728516,
      "learning_rate": 9.999316524962345e-05,
      "loss": 4.2081,
      "step": 11
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 10.416969299316406,
      "learning_rate": 9.997266286704631e-05,
      "loss": 4.1728,
      "step": 12
    },
    {
      "epoch": 0.06018518518518518,
      "grad_norm": 8.240694046020508,
      "learning_rate": 9.993849845741524e-05,
      "loss": 4.4884,
      "step": 13
    },
    {
      "epoch": 0.06481481481481481,
      "grad_norm": 6.751835823059082,
      "learning_rate": 9.989068136093873e-05,
      "loss": 3.556,
      "step": 14
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 9.583756446838379,
      "learning_rate": 9.98292246503335e-05,
      "loss": 4.7617,
      "step": 15
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 6.77708101272583,
      "learning_rate": 9.975414512725057e-05,
      "loss": 3.917,
      "step": 16
    },
    {
      "epoch": 0.0787037037037037,
      "grad_norm": 8.212162971496582,
      "learning_rate": 9.966546331768191e-05,
      "loss": 4.7593,
      "step": 17
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 7.024133682250977,
      "learning_rate": 9.956320346634876e-05,
      "loss": 4.5034,
      "step": 18
    },
    {
      "epoch": 0.08796296296296297,
      "grad_norm": 10.87393856048584,
      "learning_rate": 9.944739353007344e-05,
      "loss": 4.4721,
      "step": 19
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 9.538769721984863,
      "learning_rate": 9.931806517013612e-05,
      "loss": 4.3214,
      "step": 20
    },
    {
      "epoch": 0.09722222222222222,
      "grad_norm": 7.0022993087768555,
      "learning_rate": 9.917525374361912e-05,
      "loss": 4.1592,
      "step": 21
    },
    {
      "epoch": 0.10185185185185185,
      "grad_norm": 7.79717493057251,
      "learning_rate": 9.901899829374047e-05,
      "loss": 3.4414,
      "step": 22
    },
    {
      "epoch": 0.10648148148148148,
      "grad_norm": 6.814549922943115,
      "learning_rate": 9.884934153917997e-05,
      "loss": 3.5808,
      "step": 23
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 8.230525970458984,
      "learning_rate": 9.86663298624003e-05,
      "loss": 4.316,
      "step": 24
    },
    {
      "epoch": 0.11574074074074074,
      "grad_norm": 7.780643939971924,
      "learning_rate": 9.847001329696653e-05,
      "loss": 3.9929,
      "step": 25
    },
    {
      "epoch": 0.12037037037037036,
      "grad_norm": 5.998938083648682,
      "learning_rate": 9.826044551386744e-05,
      "loss": 4.3758,
      "step": 26
    },
    {
      "epoch": 0.125,
      "grad_norm": 5.587447166442871,
      "learning_rate": 9.803768380684242e-05,
      "loss": 3.2193,
      "step": 27
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 6.207060813903809,
      "learning_rate": 9.780178907671789e-05,
      "loss": 4.2283,
      "step": 28
    },
    {
      "epoch": 0.13425925925925927,
      "grad_norm": 5.888337135314941,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.2497,
      "step": 29
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 5.476317405700684,
      "learning_rate": 9.729086208503174e-05,
      "loss": 3.8746,
      "step": 30
    },
    {
      "epoch": 0.14351851851851852,
      "grad_norm": 5.5299201011657715,
      "learning_rate": 9.701596950580806e-05,
      "loss": 3.3871,
      "step": 31
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 5.175489902496338,
      "learning_rate": 9.672822322997305e-05,
      "loss": 4.1937,
      "step": 32
    },
    {
      "epoch": 0.1527777777777778,
      "grad_norm": 5.811768054962158,
      "learning_rate": 9.642770192448536e-05,
      "loss": 4.1615,
      "step": 33
    },
    {
      "epoch": 0.1574074074074074,
      "grad_norm": 6.40473747253418,
      "learning_rate": 9.611448774886924e-05,
      "loss": 4.0811,
      "step": 34
    },
    {
      "epoch": 0.16203703703703703,
      "grad_norm": 5.893089771270752,
      "learning_rate": 9.578866633275288e-05,
      "loss": 3.7876,
      "step": 35
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 7.377657890319824,
      "learning_rate": 9.545032675245813e-05,
      "loss": 4.5545,
      "step": 36
    },
    {
      "epoch": 0.1712962962962963,
      "grad_norm": 5.871709823608398,
      "learning_rate": 9.509956150664796e-05,
      "loss": 3.6182,
      "step": 37
    },
    {
      "epoch": 0.17592592592592593,
      "grad_norm": 6.56091833114624,
      "learning_rate": 9.473646649103818e-05,
      "loss": 3.6333,
      "step": 38
    },
    {
      "epoch": 0.18055555555555555,
      "grad_norm": 6.150292873382568,
      "learning_rate": 9.43611409721806e-05,
      "loss": 3.531,
      "step": 39
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 6.087308883666992,
      "learning_rate": 9.397368756032445e-05,
      "loss": 3.8467,
      "step": 40
    },
    {
      "epoch": 0.18981481481481483,
      "grad_norm": 5.346468448638916,
      "learning_rate": 9.357421218136386e-05,
      "loss": 3.3521,
      "step": 41
    },
    {
      "epoch": 0.19444444444444445,
      "grad_norm": 6.701805114746094,
      "learning_rate": 9.316282404787871e-05,
      "loss": 4.5454,
      "step": 42
    },
    {
      "epoch": 0.19907407407407407,
      "grad_norm": 5.57968282699585,
      "learning_rate": 9.273963562927695e-05,
      "loss": 3.7131,
      "step": 43
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 6.712480545043945,
      "learning_rate": 9.230476262104677e-05,
      "loss": 3.5673,
      "step": 44
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 5.590303421020508,
      "learning_rate": 9.185832391312644e-05,
      "loss": 3.8381,
      "step": 45
    },
    {
      "epoch": 0.21296296296296297,
      "grad_norm": 5.819985866546631,
      "learning_rate": 9.140044155740101e-05,
      "loss": 3.5446,
      "step": 46
    },
    {
      "epoch": 0.2175925925925926,
      "grad_norm": 6.234548568725586,
      "learning_rate": 9.093124073433463e-05,
      "loss": 4.0436,
      "step": 47
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 5.958637237548828,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.4125,
      "step": 48
    },
    {
      "epoch": 0.22685185185185186,
      "grad_norm": 4.7884745597839355,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.6823,
      "step": 49
    },
    {
      "epoch": 0.23148148148148148,
      "grad_norm": 6.987212181091309,
      "learning_rate": 8.945702546981969e-05,
      "loss": 3.6642,
      "step": 50
    },
    {
      "epoch": 0.23148148148148148,
      "eval_loss": 0.9653534889221191,
      "eval_runtime": 2.2045,
      "eval_samples_per_second": 165.12,
      "eval_steps_per_second": 41.28,
      "step": 50
    },
    {
      "epoch": 0.2361111111111111,
      "grad_norm": 21.279102325439453,
      "learning_rate": 8.894386393810563e-05,
      "loss": 4.3028,
      "step": 51
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 17.004270553588867,
      "learning_rate": 8.842005554284296e-05,
      "loss": 3.9888,
      "step": 52
    },
    {
      "epoch": 0.24537037037037038,
      "grad_norm": 7.366148471832275,
      "learning_rate": 8.788574348801675e-05,
      "loss": 3.4765,
      "step": 53
    },
    {
      "epoch": 0.25,
      "grad_norm": 6.349573135375977,
      "learning_rate": 8.73410738492077e-05,
      "loss": 3.7577,
      "step": 54
    },
    {
      "epoch": 0.25462962962962965,
      "grad_norm": 7.052974700927734,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.4683,
      "step": 55
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 7.836319446563721,
      "learning_rate": 8.622126023955446e-05,
      "loss": 3.9603,
      "step": 56
    },
    {
      "epoch": 0.2638888888888889,
      "grad_norm": 6.91050386428833,
      "learning_rate": 8.564642241456986e-05,
      "loss": 3.5036,
      "step": 57
    },
    {
      "epoch": 0.26851851851851855,
      "grad_norm": 5.882349967956543,
      "learning_rate": 8.506183921362443e-05,
      "loss": 3.4007,
      "step": 58
    },
    {
      "epoch": 0.27314814814814814,
      "grad_norm": 5.551027774810791,
      "learning_rate": 8.44676704559283e-05,
      "loss": 3.8384,
      "step": 59
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 5.197802543640137,
      "learning_rate": 8.386407858128706e-05,
      "loss": 2.9505,
      "step": 60
    },
    {
      "epoch": 0.2824074074074074,
      "grad_norm": 5.7865891456604,
      "learning_rate": 8.32512286056924e-05,
      "loss": 3.8189,
      "step": 61
    },
    {
      "epoch": 0.28703703703703703,
      "grad_norm": 6.744373798370361,
      "learning_rate": 8.262928807620843e-05,
      "loss": 3.4227,
      "step": 62
    },
    {
      "epoch": 0.2916666666666667,
      "grad_norm": 5.771090030670166,
      "learning_rate": 8.199842702516583e-05,
      "loss": 3.3638,
      "step": 63
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 5.358920097351074,
      "learning_rate": 8.135881792367686e-05,
      "loss": 3.8057,
      "step": 64
    },
    {
      "epoch": 0.30092592592592593,
      "grad_norm": 5.056331634521484,
      "learning_rate": 8.07106356344834e-05,
      "loss": 3.712,
      "step": 65
    },
    {
      "epoch": 0.3055555555555556,
      "grad_norm": 6.427181720733643,
      "learning_rate": 8.005405736415126e-05,
      "loss": 3.6894,
      "step": 66
    },
    {
      "epoch": 0.3101851851851852,
      "grad_norm": 6.271670341491699,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.9568,
      "step": 67
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 5.762444972991943,
      "learning_rate": 7.871643313414718e-05,
      "loss": 3.2159,
      "step": 68
    },
    {
      "epoch": 0.3194444444444444,
      "grad_norm": 5.460045337677002,
      "learning_rate": 7.803575286758364e-05,
      "loss": 3.9406,
      "step": 69
    },
    {
      "epoch": 0.32407407407407407,
      "grad_norm": 5.539421081542969,
      "learning_rate": 7.734740790612136e-05,
      "loss": 3.6225,
      "step": 70
    },
    {
      "epoch": 0.3287037037037037,
      "grad_norm": 4.93095588684082,
      "learning_rate": 7.66515864363997e-05,
      "loss": 3.3258,
      "step": 71
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 5.033069133758545,
      "learning_rate": 7.594847868906076e-05,
      "loss": 3.728,
      "step": 72
    },
    {
      "epoch": 0.33796296296296297,
      "grad_norm": 6.113219738006592,
      "learning_rate": 7.52382768867422e-05,
      "loss": 3.5339,
      "step": 73
    },
    {
      "epoch": 0.3425925925925926,
      "grad_norm": 5.191130638122559,
      "learning_rate": 7.452117519152542e-05,
      "loss": 3.4594,
      "step": 74
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 5.532462120056152,
      "learning_rate": 7.379736965185368e-05,
      "loss": 3.6219,
      "step": 75
    },
    {
      "epoch": 0.35185185185185186,
      "grad_norm": 5.176677703857422,
      "learning_rate": 7.30670581489344e-05,
      "loss": 3.331,
      "step": 76
    },
    {
      "epoch": 0.35648148148148145,
      "grad_norm": 5.5989670753479,
      "learning_rate": 7.233044034264034e-05,
      "loss": 3.472,
      "step": 77
    },
    {
      "epoch": 0.3611111111111111,
      "grad_norm": 5.910463333129883,
      "learning_rate": 7.158771761692464e-05,
      "loss": 3.4703,
      "step": 78
    },
    {
      "epoch": 0.36574074074074076,
      "grad_norm": 5.001678943634033,
      "learning_rate": 7.083909302476453e-05,
      "loss": 3.8668,
      "step": 79
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 6.036172389984131,
      "learning_rate": 7.008477123264848e-05,
      "loss": 4.5376,
      "step": 80
    },
    {
      "epoch": 0.375,
      "grad_norm": 5.105536460876465,
      "learning_rate": 6.932495846462261e-05,
      "loss": 3.7697,
      "step": 81
    },
    {
      "epoch": 0.37962962962962965,
      "grad_norm": 5.185485363006592,
      "learning_rate": 6.855986244591104e-05,
      "loss": 3.3149,
      "step": 82
    },
    {
      "epoch": 0.38425925925925924,
      "grad_norm": 5.382936477661133,
      "learning_rate": 6.778969234612584e-05,
      "loss": 3.7265,
      "step": 83
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 6.7064056396484375,
      "learning_rate": 6.701465872208216e-05,
      "loss": 4.0798,
      "step": 84
    },
    {
      "epoch": 0.39351851851851855,
      "grad_norm": 5.775436878204346,
      "learning_rate": 6.623497346023418e-05,
      "loss": 3.427,
      "step": 85
    },
    {
      "epoch": 0.39814814814814814,
      "grad_norm": 6.115148067474365,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.5284,
      "step": 86
    },
    {
      "epoch": 0.4027777777777778,
      "grad_norm": 4.93687105178833,
      "learning_rate": 6.466250186922325e-05,
      "loss": 3.3446,
      "step": 87
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 5.204934597015381,
      "learning_rate": 6.387014543809223e-05,
      "loss": 3.5982,
      "step": 88
    },
    {
      "epoch": 0.41203703703703703,
      "grad_norm": 5.958828449249268,
      "learning_rate": 6.307399704769099e-05,
      "loss": 3.3625,
      "step": 89
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 5.508089065551758,
      "learning_rate": 6.227427435703997e-05,
      "loss": 3.6133,
      "step": 90
    },
    {
      "epoch": 0.4212962962962963,
      "grad_norm": 6.385080337524414,
      "learning_rate": 6.147119600233758e-05,
      "loss": 3.9251,
      "step": 91
    },
    {
      "epoch": 0.42592592592592593,
      "grad_norm": 4.458702564239502,
      "learning_rate": 6.066498153718735e-05,
      "loss": 2.8038,
      "step": 92
    },
    {
      "epoch": 0.4305555555555556,
      "grad_norm": 5.644857883453369,
      "learning_rate": 5.985585137257401e-05,
      "loss": 3.3902,
      "step": 93
    },
    {
      "epoch": 0.4351851851851852,
      "grad_norm": 5.60584020614624,
      "learning_rate": 5.90440267166055e-05,
      "loss": 3.4215,
      "step": 94
    },
    {
      "epoch": 0.4398148148148148,
      "grad_norm": 5.254773139953613,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 3.5091,
      "step": 95
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 5.908911228179932,
      "learning_rate": 5.74131823855921e-05,
      "loss": 3.8167,
      "step": 96
    },
    {
      "epoch": 0.44907407407407407,
      "grad_norm": 5.07248592376709,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 3.7275,
      "step": 97
    },
    {
      "epoch": 0.4537037037037037,
      "grad_norm": 5.707670211791992,
      "learning_rate": 5.577423184847932e-05,
      "loss": 3.4284,
      "step": 98
    },
    {
      "epoch": 0.4583333333333333,
      "grad_norm": 7.595188140869141,
      "learning_rate": 5.495227651252315e-05,
      "loss": 4.0493,
      "step": 99
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 7.258778095245361,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 4.4078,
      "step": 100
    },
    {
      "epoch": 0.46296296296296297,
      "eval_loss": 0.9506180286407471,
      "eval_runtime": 2.2048,
      "eval_samples_per_second": 165.096,
      "eval_steps_per_second": 41.274,
      "step": 100
    },
    {
      "epoch": 0.4675925925925926,
      "grad_norm": 16.511831283569336,
      "learning_rate": 5.330452921628497e-05,
      "loss": 4.1775,
      "step": 101
    },
    {
      "epoch": 0.4722222222222222,
      "grad_norm": 15.729872703552246,
      "learning_rate": 5.247918773366112e-05,
      "loss": 3.6591,
      "step": 102
    },
    {
      "epoch": 0.47685185185185186,
      "grad_norm": 13.131829261779785,
      "learning_rate": 5.165316846586541e-05,
      "loss": 4.0842,
      "step": 103
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 9.212827682495117,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 4.3572,
      "step": 104
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 7.942713260650635,
      "learning_rate": 5e-05,
      "loss": 4.5441,
      "step": 105
    },
    {
      "epoch": 0.49074074074074076,
      "grad_norm": 8.172318458557129,
      "learning_rate": 4.917330276168208e-05,
      "loss": 3.2651,
      "step": 106
    },
    {
      "epoch": 0.49537037037037035,
      "grad_norm": 6.004984378814697,
      "learning_rate": 4.834683153413459e-05,
      "loss": 3.3305,
      "step": 107
    },
    {
      "epoch": 0.5,
      "grad_norm": 6.3809099197387695,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 3.9816,
      "step": 108
    },
    {
      "epoch": 0.5046296296296297,
      "grad_norm": 7.3555521965026855,
      "learning_rate": 4.669547078371504e-05,
      "loss": 3.7786,
      "step": 109
    },
    {
      "epoch": 0.5092592592592593,
      "grad_norm": 6.51990270614624,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 3.9163,
      "step": 110
    },
    {
      "epoch": 0.5138888888888888,
      "grad_norm": 7.259381294250488,
      "learning_rate": 4.504772348747687e-05,
      "loss": 3.9092,
      "step": 111
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 5.540770053863525,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 3.2743,
      "step": 112
    },
    {
      "epoch": 0.5231481481481481,
      "grad_norm": 6.928374290466309,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 3.7641,
      "step": 113
    },
    {
      "epoch": 0.5277777777777778,
      "grad_norm": 5.83001184463501,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 3.6273,
      "step": 114
    },
    {
      "epoch": 0.5324074074074074,
      "grad_norm": 5.870872974395752,
      "learning_rate": 4.17702704859633e-05,
      "loss": 4.0163,
      "step": 115
    },
    {
      "epoch": 0.5370370370370371,
      "grad_norm": 4.91756534576416,
      "learning_rate": 4.095597328339452e-05,
      "loss": 3.7131,
      "step": 116
    },
    {
      "epoch": 0.5416666666666666,
      "grad_norm": 5.4933695793151855,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 3.3995,
      "step": 117
    },
    {
      "epoch": 0.5462962962962963,
      "grad_norm": 5.07306432723999,
      "learning_rate": 3.933501846281267e-05,
      "loss": 2.9209,
      "step": 118
    },
    {
      "epoch": 0.5509259259259259,
      "grad_norm": 5.808611869812012,
      "learning_rate": 3.852880399766243e-05,
      "loss": 3.6237,
      "step": 119
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 5.321529865264893,
      "learning_rate": 3.772572564296005e-05,
      "loss": 3.5946,
      "step": 120
    },
    {
      "epoch": 0.5601851851851852,
      "grad_norm": 6.00226354598999,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 3.8642,
      "step": 121
    },
    {
      "epoch": 0.5648148148148148,
      "grad_norm": 5.1574835777282715,
      "learning_rate": 3.612985456190778e-05,
      "loss": 2.9057,
      "step": 122
    },
    {
      "epoch": 0.5694444444444444,
      "grad_norm": 5.116312026977539,
      "learning_rate": 3.533749813077677e-05,
      "loss": 3.6405,
      "step": 123
    },
    {
      "epoch": 0.5740740740740741,
      "grad_norm": 5.007522106170654,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 3.4349,
      "step": 124
    },
    {
      "epoch": 0.5787037037037037,
      "grad_norm": 5.0423994064331055,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 3.6707,
      "step": 125
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 5.853762149810791,
      "learning_rate": 3.298534127791785e-05,
      "loss": 4.1479,
      "step": 126
    },
    {
      "epoch": 0.5879629629629629,
      "grad_norm": 5.229793548583984,
      "learning_rate": 3.221030765387417e-05,
      "loss": 3.6106,
      "step": 127
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 4.285995006561279,
      "learning_rate": 3.144013755408895e-05,
      "loss": 3.2211,
      "step": 128
    },
    {
      "epoch": 0.5972222222222222,
      "grad_norm": 4.707469463348389,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 3.2949,
      "step": 129
    },
    {
      "epoch": 0.6018518518518519,
      "grad_norm": 5.068636417388916,
      "learning_rate": 2.991522876735154e-05,
      "loss": 3.3685,
      "step": 130
    },
    {
      "epoch": 0.6064814814814815,
      "grad_norm": 5.562315464019775,
      "learning_rate": 2.916090697523549e-05,
      "loss": 3.4797,
      "step": 131
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 5.14057731628418,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 3.1759,
      "step": 132
    },
    {
      "epoch": 0.6157407407407407,
      "grad_norm": 4.153538703918457,
      "learning_rate": 2.766955965735968e-05,
      "loss": 3.2033,
      "step": 133
    },
    {
      "epoch": 0.6203703703703703,
      "grad_norm": 6.161820411682129,
      "learning_rate": 2.693294185106562e-05,
      "loss": 3.7485,
      "step": 134
    },
    {
      "epoch": 0.625,
      "grad_norm": 4.745534896850586,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 3.3132,
      "step": 135
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 5.426248073577881,
      "learning_rate": 2.547882480847461e-05,
      "loss": 3.9259,
      "step": 136
    },
    {
      "epoch": 0.6342592592592593,
      "grad_norm": 6.031970500946045,
      "learning_rate": 2.476172311325783e-05,
      "loss": 3.3059,
      "step": 137
    },
    {
      "epoch": 0.6388888888888888,
      "grad_norm": 4.629186630249023,
      "learning_rate": 2.405152131093926e-05,
      "loss": 2.9809,
      "step": 138
    },
    {
      "epoch": 0.6435185185185185,
      "grad_norm": 6.900302886962891,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 4.1208,
      "step": 139
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 4.886723518371582,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 2.9442,
      "step": 140
    },
    {
      "epoch": 0.6527777777777778,
      "grad_norm": 5.8405561447143555,
      "learning_rate": 2.196424713241637e-05,
      "loss": 4.2413,
      "step": 141
    },
    {
      "epoch": 0.6574074074074074,
      "grad_norm": 4.583191871643066,
      "learning_rate": 2.128356686585282e-05,
      "loss": 3.1129,
      "step": 142
    },
    {
      "epoch": 0.6620370370370371,
      "grad_norm": 4.938739776611328,
      "learning_rate": 2.061073738537635e-05,
      "loss": 3.7119,
      "step": 143
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 5.5398969650268555,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 3.5924,
      "step": 144
    },
    {
      "epoch": 0.6712962962962963,
      "grad_norm": 5.933006763458252,
      "learning_rate": 1.928936436551661e-05,
      "loss": 3.5283,
      "step": 145
    },
    {
      "epoch": 0.6759259259259259,
      "grad_norm": 5.262126445770264,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 3.545,
      "step": 146
    },
    {
      "epoch": 0.6805555555555556,
      "grad_norm": 5.654722213745117,
      "learning_rate": 1.800157297483417e-05,
      "loss": 2.961,
      "step": 147
    },
    {
      "epoch": 0.6851851851851852,
      "grad_norm": 5.659895896911621,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 2.992,
      "step": 148
    },
    {
      "epoch": 0.6898148148148148,
      "grad_norm": 5.529632091522217,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 2.9833,
      "step": 149
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 6.873269081115723,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 3.9868,
      "step": 150
    },
    {
      "epoch": 0.6944444444444444,
      "eval_loss": 0.9384932518005371,
      "eval_runtime": 2.1989,
      "eval_samples_per_second": 165.541,
      "eval_steps_per_second": 41.385,
      "step": 150
    },
    {
      "epoch": 0.6990740740740741,
      "grad_norm": 11.233521461486816,
      "learning_rate": 1.553232954407171e-05,
      "loss": 3.7344,
      "step": 151
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 12.824865341186523,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 3.3177,
      "step": 152
    },
    {
      "epoch": 0.7083333333333334,
      "grad_norm": 13.246438026428223,
      "learning_rate": 1.435357758543015e-05,
      "loss": 3.7146,
      "step": 153
    },
    {
      "epoch": 0.7129629629629629,
      "grad_norm": 14.45628833770752,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 3.8136,
      "step": 154
    },
    {
      "epoch": 0.7175925925925926,
      "grad_norm": 18.83707046508789,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 3.7177,
      "step": 155
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 16.416080474853516,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 3.9186,
      "step": 156
    },
    {
      "epoch": 0.7268518518518519,
      "grad_norm": 21.26527214050293,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 4.0919,
      "step": 157
    },
    {
      "epoch": 0.7314814814814815,
      "grad_norm": 20.47049331665039,
      "learning_rate": 1.157994445715706e-05,
      "loss": 4.348,
      "step": 158
    },
    {
      "epoch": 0.7361111111111112,
      "grad_norm": 18.2163028717041,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 4.3827,
      "step": 159
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 13.731039047241211,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 4.1914,
      "step": 160
    },
    {
      "epoch": 0.7453703703703703,
      "grad_norm": 14.296989440917969,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 3.6654,
      "step": 161
    },
    {
      "epoch": 0.75,
      "grad_norm": 11.092514038085938,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.6952,
      "step": 162
    },
    {
      "epoch": 0.7546296296296297,
      "grad_norm": 8.552708625793457,
      "learning_rate": 9.068759265665384e-06,
      "loss": 3.5106,
      "step": 163
    },
    {
      "epoch": 0.7592592592592593,
      "grad_norm": 7.353050231933594,
      "learning_rate": 8.599558442598998e-06,
      "loss": 3.6866,
      "step": 164
    },
    {
      "epoch": 0.7638888888888888,
      "grad_norm": 6.845998287200928,
      "learning_rate": 8.141676086873572e-06,
      "loss": 3.3867,
      "step": 165
    },
    {
      "epoch": 0.7685185185185185,
      "grad_norm": 6.550758361816406,
      "learning_rate": 7.695237378953223e-06,
      "loss": 3.9186,
      "step": 166
    },
    {
      "epoch": 0.7731481481481481,
      "grad_norm": 6.150266647338867,
      "learning_rate": 7.260364370723044e-06,
      "loss": 3.4168,
      "step": 167
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 5.203208923339844,
      "learning_rate": 6.837175952121306e-06,
      "loss": 4.0376,
      "step": 168
    },
    {
      "epoch": 0.7824074074074074,
      "grad_norm": 5.947827339172363,
      "learning_rate": 6.425787818636131e-06,
      "loss": 3.7845,
      "step": 169
    },
    {
      "epoch": 0.7870370370370371,
      "grad_norm": 4.697939872741699,
      "learning_rate": 6.026312439675552e-06,
      "loss": 3.229,
      "step": 170
    },
    {
      "epoch": 0.7916666666666666,
      "grad_norm": 5.036762714385986,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 3.2721,
      "step": 171
    },
    {
      "epoch": 0.7962962962962963,
      "grad_norm": 6.238568305969238,
      "learning_rate": 5.263533508961827e-06,
      "loss": 4.1159,
      "step": 172
    },
    {
      "epoch": 0.8009259259259259,
      "grad_norm": 5.424266815185547,
      "learning_rate": 4.900438493352055e-06,
      "loss": 3.2487,
      "step": 173
    },
    {
      "epoch": 0.8055555555555556,
      "grad_norm": 5.883419036865234,
      "learning_rate": 4.549673247541875e-06,
      "loss": 3.3904,
      "step": 174
    },
    {
      "epoch": 0.8101851851851852,
      "grad_norm": 5.531612873077393,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 3.8494,
      "step": 175
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 6.308720588684082,
      "learning_rate": 3.885512251130763e-06,
      "loss": 2.9733,
      "step": 176
    },
    {
      "epoch": 0.8194444444444444,
      "grad_norm": 5.815715789794922,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 3.6319,
      "step": 177
    },
    {
      "epoch": 0.8240740740740741,
      "grad_norm": 6.776818752288818,
      "learning_rate": 3.271776770026963e-06,
      "loss": 3.7741,
      "step": 178
    },
    {
      "epoch": 0.8287037037037037,
      "grad_norm": 6.265354156494141,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 3.5251,
      "step": 179
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 5.8386030197143555,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 3.1307,
      "step": 180
    },
    {
      "epoch": 0.8379629629629629,
      "grad_norm": 5.972423076629639,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 3.0085,
      "step": 181
    },
    {
      "epoch": 0.8425925925925926,
      "grad_norm": 5.969120979309082,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 3.2039,
      "step": 182
    },
    {
      "epoch": 0.8472222222222222,
      "grad_norm": 6.234097957611084,
      "learning_rate": 1.962316193157593e-06,
      "loss": 3.3387,
      "step": 183
    },
    {
      "epoch": 0.8518518518518519,
      "grad_norm": 6.793857097625732,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 3.8919,
      "step": 184
    },
    {
      "epoch": 0.8564814814814815,
      "grad_norm": 5.666411399841309,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 3.2418,
      "step": 185
    },
    {
      "epoch": 0.8611111111111112,
      "grad_norm": 6.4262189865112305,
      "learning_rate": 1.333670137599713e-06,
      "loss": 3.4585,
      "step": 186
    },
    {
      "epoch": 0.8657407407407407,
      "grad_norm": 7.735586643218994,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 3.4223,
      "step": 187
    },
    {
      "epoch": 0.8703703703703703,
      "grad_norm": 7.73878288269043,
      "learning_rate": 9.810017062595322e-07,
      "loss": 3.2928,
      "step": 188
    },
    {
      "epoch": 0.875,
      "grad_norm": 8.772385597229004,
      "learning_rate": 8.247462563808817e-07,
      "loss": 4.3576,
      "step": 189
    },
    {
      "epoch": 0.8796296296296297,
      "grad_norm": 7.09291410446167,
      "learning_rate": 6.819348298638839e-07,
      "loss": 3.9895,
      "step": 190
    },
    {
      "epoch": 0.8842592592592593,
      "grad_norm": 7.7089457511901855,
      "learning_rate": 5.526064699265753e-07,
      "loss": 3.5064,
      "step": 191
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 6.583120346069336,
      "learning_rate": 4.367965336512403e-07,
      "loss": 3.2973,
      "step": 192
    },
    {
      "epoch": 0.8935185185185185,
      "grad_norm": 6.568912029266357,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 3.2589,
      "step": 193
    },
    {
      "epoch": 0.8981481481481481,
      "grad_norm": 7.783357620239258,
      "learning_rate": 2.458548727494292e-07,
      "loss": 3.6919,
      "step": 194
    },
    {
      "epoch": 0.9027777777777778,
      "grad_norm": 6.62523078918457,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 3.0181,
      "step": 195
    },
    {
      "epoch": 0.9074074074074074,
      "grad_norm": 7.197375774383545,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 3.2298,
      "step": 196
    },
    {
      "epoch": 0.9120370370370371,
      "grad_norm": 8.587085723876953,
      "learning_rate": 6.150154258476315e-08,
      "loss": 3.3353,
      "step": 197
    },
    {
      "epoch": 0.9166666666666666,
      "grad_norm": 8.449831008911133,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 3.1665,
      "step": 198
    },
    {
      "epoch": 0.9212962962962963,
      "grad_norm": 8.491254806518555,
      "learning_rate": 6.834750376549792e-09,
      "loss": 3.1809,
      "step": 199
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 9.122477531433105,
      "learning_rate": 0.0,
      "loss": 3.438,
      "step": 200
    },
    {
      "epoch": 0.9259259259259259,
      "eval_loss": 0.8675870895385742,
      "eval_runtime": 2.1973,
      "eval_samples_per_second": 165.656,
      "eval_steps_per_second": 41.414,
      "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": 3762008830771200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}