{
  "best_metric": 0.3864835798740387,
  "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": 1.1189391613006592,
      "learning_rate": 1e-05,
      "loss": 0.7853,
      "step": 1
    },
    {
      "epoch": 0.004629629629629629,
      "eval_loss": 1.228265643119812,
      "eval_runtime": 10.7547,
      "eval_samples_per_second": 33.846,
      "eval_steps_per_second": 8.461,
      "step": 1
    },
    {
      "epoch": 0.009259259259259259,
      "grad_norm": 1.278108835220337,
      "learning_rate": 2e-05,
      "loss": 0.8937,
      "step": 2
    },
    {
      "epoch": 0.013888888888888888,
      "grad_norm": 1.2460616827011108,
      "learning_rate": 3e-05,
      "loss": 0.8594,
      "step": 3
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 1.1683036088943481,
      "learning_rate": 4e-05,
      "loss": 0.8173,
      "step": 4
    },
    {
      "epoch": 0.023148148148148147,
      "grad_norm": 0.9271842837333679,
      "learning_rate": 5e-05,
      "loss": 0.7674,
      "step": 5
    },
    {
      "epoch": 0.027777777777777776,
      "grad_norm": 0.9821398258209229,
      "learning_rate": 6e-05,
      "loss": 0.6899,
      "step": 6
    },
    {
      "epoch": 0.032407407407407406,
      "grad_norm": 0.8240920305252075,
      "learning_rate": 7e-05,
      "loss": 0.6314,
      "step": 7
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 0.7650155425071716,
      "learning_rate": 8e-05,
      "loss": 0.5987,
      "step": 8
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 0.8365386128425598,
      "learning_rate": 9e-05,
      "loss": 0.5258,
      "step": 9
    },
    {
      "epoch": 0.046296296296296294,
      "grad_norm": 0.6722853779792786,
      "learning_rate": 0.0001,
      "loss": 0.5495,
      "step": 10
    },
    {
      "epoch": 0.05092592592592592,
      "grad_norm": 0.7667433619499207,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.4895,
      "step": 11
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 0.7887847423553467,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.5203,
      "step": 12
    },
    {
      "epoch": 0.06018518518518518,
      "grad_norm": 0.7217102646827698,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.5065,
      "step": 13
    },
    {
      "epoch": 0.06481481481481481,
      "grad_norm": 0.554767906665802,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.4226,
      "step": 14
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 0.4702896773815155,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.4611,
      "step": 15
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.46863293647766113,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.4735,
      "step": 16
    },
    {
      "epoch": 0.0787037037037037,
      "grad_norm": 0.4609469473361969,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.4109,
      "step": 17
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.5020431280136108,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.5005,
      "step": 18
    },
    {
      "epoch": 0.08796296296296297,
      "grad_norm": 0.41165754199028015,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.4021,
      "step": 19
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 0.43588876724243164,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.4268,
      "step": 20
    },
    {
      "epoch": 0.09722222222222222,
      "grad_norm": 0.41449710726737976,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.4877,
      "step": 21
    },
    {
      "epoch": 0.10185185185185185,
      "grad_norm": 0.4562777280807495,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.452,
      "step": 22
    },
    {
      "epoch": 0.10648148148148148,
      "grad_norm": 0.48189520835876465,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.4408,
      "step": 23
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.4281782805919647,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.4469,
      "step": 24
    },
    {
      "epoch": 0.11574074074074074,
      "grad_norm": 0.41198083758354187,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4151,
      "step": 25
    },
    {
      "epoch": 0.12037037037037036,
      "grad_norm": 0.39334577322006226,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.3618,
      "step": 26
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.3958817720413208,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.4334,
      "step": 27
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 0.47193270921707153,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4169,
      "step": 28
    },
    {
      "epoch": 0.13425925925925927,
      "grad_norm": 0.45587804913520813,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.4541,
      "step": 29
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 0.4567444622516632,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.4202,
      "step": 30
    },
    {
      "epoch": 0.14351851851851852,
      "grad_norm": 0.42318323254585266,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.4131,
      "step": 31
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.4647253751754761,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.416,
      "step": 32
    },
    {
      "epoch": 0.1527777777777778,
      "grad_norm": 0.4837891459465027,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.4482,
      "step": 33
    },
    {
      "epoch": 0.1574074074074074,
      "grad_norm": 0.39502987265586853,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.3376,
      "step": 34
    },
    {
      "epoch": 0.16203703703703703,
      "grad_norm": 0.451773464679718,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.4395,
      "step": 35
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.45852717757225037,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.3956,
      "step": 36
    },
    {
      "epoch": 0.1712962962962963,
      "grad_norm": 0.46326276659965515,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.4746,
      "step": 37
    },
    {
      "epoch": 0.17592592592592593,
      "grad_norm": 0.40284261107444763,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.3842,
      "step": 38
    },
    {
      "epoch": 0.18055555555555555,
      "grad_norm": 0.46737217903137207,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.4238,
      "step": 39
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 0.4369564354419708,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.4137,
      "step": 40
    },
    {
      "epoch": 0.18981481481481483,
      "grad_norm": 0.4337729811668396,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.3598,
      "step": 41
    },
    {
      "epoch": 0.19444444444444445,
      "grad_norm": 0.4859578013420105,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.442,
      "step": 42
    },
    {
      "epoch": 0.19907407407407407,
      "grad_norm": 0.5021910667419434,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.4359,
      "step": 43
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 0.5430487394332886,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.467,
      "step": 44
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 0.44179415702819824,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.3657,
      "step": 45
    },
    {
      "epoch": 0.21296296296296297,
      "grad_norm": 0.465890496969223,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.3806,
      "step": 46
    },
    {
      "epoch": 0.2175925925925926,
      "grad_norm": 0.43715235590934753,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.3066,
      "step": 47
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.5051515102386475,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.353,
      "step": 48
    },
    {
      "epoch": 0.22685185185185186,
      "grad_norm": 0.49336570501327515,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.3661,
      "step": 49
    },
    {
      "epoch": 0.23148148148148148,
      "grad_norm": 0.5129603743553162,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.2802,
      "step": 50
    },
    {
      "epoch": 0.23148148148148148,
      "eval_loss": 0.42239895462989807,
      "eval_runtime": 10.7627,
      "eval_samples_per_second": 33.821,
      "eval_steps_per_second": 8.455,
      "step": 50
    },
    {
      "epoch": 0.2361111111111111,
      "grad_norm": 0.40209445357322693,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.4523,
      "step": 51
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 0.4091344475746155,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.4224,
      "step": 52
    },
    {
      "epoch": 0.24537037037037038,
      "grad_norm": 0.3767826557159424,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.4367,
      "step": 53
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.3493788540363312,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.4086,
      "step": 54
    },
    {
      "epoch": 0.25462962962962965,
      "grad_norm": 0.34255748987197876,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.4065,
      "step": 55
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 0.35259774327278137,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.4426,
      "step": 56
    },
    {
      "epoch": 0.2638888888888889,
      "grad_norm": 0.3914964497089386,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.4464,
      "step": 57
    },
    {
      "epoch": 0.26851851851851855,
      "grad_norm": 0.32041871547698975,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.4074,
      "step": 58
    },
    {
      "epoch": 0.27314814814814814,
      "grad_norm": 0.379145085811615,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.4209,
      "step": 59
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 0.328153133392334,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.4203,
      "step": 60
    },
    {
      "epoch": 0.2824074074074074,
      "grad_norm": 0.3137761652469635,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.3422,
      "step": 61
    },
    {
      "epoch": 0.28703703703703703,
      "grad_norm": 0.375429630279541,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.4358,
      "step": 62
    },
    {
      "epoch": 0.2916666666666667,
      "grad_norm": 0.3554491102695465,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.4222,
      "step": 63
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.3191734552383423,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.3777,
      "step": 64
    },
    {
      "epoch": 0.30092592592592593,
      "grad_norm": 0.33554840087890625,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.4333,
      "step": 65
    },
    {
      "epoch": 0.3055555555555556,
      "grad_norm": 0.37704455852508545,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.4059,
      "step": 66
    },
    {
      "epoch": 0.3101851851851852,
      "grad_norm": 0.336211621761322,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.4061,
      "step": 67
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 0.3658120036125183,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.4335,
      "step": 68
    },
    {
      "epoch": 0.3194444444444444,
      "grad_norm": 0.373349130153656,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3967,
      "step": 69
    },
    {
      "epoch": 0.32407407407407407,
      "grad_norm": 0.394365519285202,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.3665,
      "step": 70
    },
    {
      "epoch": 0.3287037037037037,
      "grad_norm": 0.3931962251663208,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.3883,
      "step": 71
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.3999130427837372,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.4245,
      "step": 72
    },
    {
      "epoch": 0.33796296296296297,
      "grad_norm": 0.4101896286010742,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.4217,
      "step": 73
    },
    {
      "epoch": 0.3425925925925926,
      "grad_norm": 0.37626171112060547,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.4004,
      "step": 74
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 0.4204075336456299,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.4293,
      "step": 75
    },
    {
      "epoch": 0.35185185185185186,
      "grad_norm": 0.39619171619415283,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.4069,
      "step": 76
    },
    {
      "epoch": 0.35648148148148145,
      "grad_norm": 0.41514161229133606,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.4446,
      "step": 77
    },
    {
      "epoch": 0.3611111111111111,
      "grad_norm": 0.3830327093601227,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.4099,
      "step": 78
    },
    {
      "epoch": 0.36574074074074076,
      "grad_norm": 0.3962486982345581,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.4251,
      "step": 79
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.419023722410202,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.39,
      "step": 80
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.424437940120697,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.3957,
      "step": 81
    },
    {
      "epoch": 0.37962962962962965,
      "grad_norm": 0.3462282419204712,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3117,
      "step": 82
    },
    {
      "epoch": 0.38425925925925924,
      "grad_norm": 0.42621999979019165,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.3887,
      "step": 83
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.40100347995758057,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.37,
      "step": 84
    },
    {
      "epoch": 0.39351851851851855,
      "grad_norm": 0.38728412985801697,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.3692,
      "step": 85
    },
    {
      "epoch": 0.39814814814814814,
      "grad_norm": 0.42241188883781433,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3328,
      "step": 86
    },
    {
      "epoch": 0.4027777777777778,
      "grad_norm": 0.3989827632904053,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.3833,
      "step": 87
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 0.43125689029693604,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.4123,
      "step": 88
    },
    {
      "epoch": 0.41203703703703703,
      "grad_norm": 0.45634379982948303,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.3681,
      "step": 89
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 0.45389023423194885,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.3932,
      "step": 90
    },
    {
      "epoch": 0.4212962962962963,
      "grad_norm": 0.42966943979263306,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.4025,
      "step": 91
    },
    {
      "epoch": 0.42592592592592593,
      "grad_norm": 0.39621248841285706,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.3723,
      "step": 92
    },
    {
      "epoch": 0.4305555555555556,
      "grad_norm": 0.4600270986557007,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4512,
      "step": 93
    },
    {
      "epoch": 0.4351851851851852,
      "grad_norm": 0.43024617433547974,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.3879,
      "step": 94
    },
    {
      "epoch": 0.4398148148148148,
      "grad_norm": 0.44412851333618164,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.3725,
      "step": 95
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.4359656870365143,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.3604,
      "step": 96
    },
    {
      "epoch": 0.44907407407407407,
      "grad_norm": 0.4809565544128418,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.3975,
      "step": 97
    },
    {
      "epoch": 0.4537037037037037,
      "grad_norm": 0.3862070143222809,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.2766,
      "step": 98
    },
    {
      "epoch": 0.4583333333333333,
      "grad_norm": 0.3667670786380768,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.2766,
      "step": 99
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 0.39991167187690735,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.2755,
      "step": 100
    },
    {
      "epoch": 0.46296296296296297,
      "eval_loss": 0.40024784207344055,
      "eval_runtime": 10.7502,
      "eval_samples_per_second": 33.86,
      "eval_steps_per_second": 8.465,
      "step": 100
    },
    {
      "epoch": 0.4675925925925926,
      "grad_norm": 0.30746522545814514,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.4775,
      "step": 101
    },
    {
      "epoch": 0.4722222222222222,
      "grad_norm": 0.34196579456329346,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.4477,
      "step": 102
    },
    {
      "epoch": 0.47685185185185186,
      "grad_norm": 0.30922290682792664,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.4251,
      "step": 103
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 0.29165372252464294,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.3926,
      "step": 104
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 0.34693506360054016,
      "learning_rate": 5e-05,
      "loss": 0.4515,
      "step": 105
    },
    {
      "epoch": 0.49074074074074076,
      "grad_norm": 0.31552499532699585,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.4214,
      "step": 106
    },
    {
      "epoch": 0.49537037037037035,
      "grad_norm": 0.3281204402446747,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.4189,
      "step": 107
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.34436365962028503,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.4657,
      "step": 108
    },
    {
      "epoch": 0.5046296296296297,
      "grad_norm": 0.29861369729042053,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.3512,
      "step": 109
    },
    {
      "epoch": 0.5092592592592593,
      "grad_norm": 0.32682478427886963,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.3616,
      "step": 110
    },
    {
      "epoch": 0.5138888888888888,
      "grad_norm": 0.33883967995643616,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.3507,
      "step": 111
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.3338402211666107,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.4334,
      "step": 112
    },
    {
      "epoch": 0.5231481481481481,
      "grad_norm": 0.3603358864784241,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.3933,
      "step": 113
    },
    {
      "epoch": 0.5277777777777778,
      "grad_norm": 0.3439207077026367,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.4529,
      "step": 114
    },
    {
      "epoch": 0.5324074074074074,
      "grad_norm": 0.3596857786178589,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.4377,
      "step": 115
    },
    {
      "epoch": 0.5370370370370371,
      "grad_norm": 0.36623266339302063,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.4115,
      "step": 116
    },
    {
      "epoch": 0.5416666666666666,
      "grad_norm": 0.36478391289711,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.4317,
      "step": 117
    },
    {
      "epoch": 0.5462962962962963,
      "grad_norm": 0.3736148178577423,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.3784,
      "step": 118
    },
    {
      "epoch": 0.5509259259259259,
      "grad_norm": 0.40371760725975037,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.4028,
      "step": 119
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.37624305486679077,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.4507,
      "step": 120
    },
    {
      "epoch": 0.5601851851851852,
      "grad_norm": 0.3506893217563629,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.3588,
      "step": 121
    },
    {
      "epoch": 0.5648148148148148,
      "grad_norm": 0.3704533576965332,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.4267,
      "step": 122
    },
    {
      "epoch": 0.5694444444444444,
      "grad_norm": 0.3138867914676666,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.3257,
      "step": 123
    },
    {
      "epoch": 0.5740740740740741,
      "grad_norm": 0.3370218873023987,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.3786,
      "step": 124
    },
    {
      "epoch": 0.5787037037037037,
      "grad_norm": 0.39725756645202637,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4441,
      "step": 125
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 0.35435202717781067,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.3789,
      "step": 126
    },
    {
      "epoch": 0.5879629629629629,
      "grad_norm": 0.40256500244140625,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.4926,
      "step": 127
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.40021616220474243,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.4216,
      "step": 128
    },
    {
      "epoch": 0.5972222222222222,
      "grad_norm": 0.4228295683860779,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.4428,
      "step": 129
    },
    {
      "epoch": 0.6018518518518519,
      "grad_norm": 0.44069305062294006,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.4221,
      "step": 130
    },
    {
      "epoch": 0.6064814814814815,
      "grad_norm": 0.3829668462276459,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3845,
      "step": 131
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 0.3732275664806366,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.3565,
      "step": 132
    },
    {
      "epoch": 0.6157407407407407,
      "grad_norm": 0.3742140829563141,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.346,
      "step": 133
    },
    {
      "epoch": 0.6203703703703703,
      "grad_norm": 0.37690073251724243,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.3446,
      "step": 134
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.5322168469429016,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.4334,
      "step": 135
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 0.3963230848312378,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.3718,
      "step": 136
    },
    {
      "epoch": 0.6342592592592593,
      "grad_norm": 0.400230348110199,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.3901,
      "step": 137
    },
    {
      "epoch": 0.6388888888888888,
      "grad_norm": 0.41444745659828186,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.3338,
      "step": 138
    },
    {
      "epoch": 0.6435185185185185,
      "grad_norm": 0.42496174573898315,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.4041,
      "step": 139
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 0.3889719247817993,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.3063,
      "step": 140
    },
    {
      "epoch": 0.6527777777777778,
      "grad_norm": 0.44650936126708984,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.4234,
      "step": 141
    },
    {
      "epoch": 0.6574074074074074,
      "grad_norm": 0.47589290142059326,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.3728,
      "step": 142
    },
    {
      "epoch": 0.6620370370370371,
      "grad_norm": 0.46845608949661255,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.3744,
      "step": 143
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.47357580065727234,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.4294,
      "step": 144
    },
    {
      "epoch": 0.6712962962962963,
      "grad_norm": 0.46446308493614197,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.3562,
      "step": 145
    },
    {
      "epoch": 0.6759259259259259,
      "grad_norm": 0.45242002606391907,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.3819,
      "step": 146
    },
    {
      "epoch": 0.6805555555555556,
      "grad_norm": 0.4365499019622803,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.3152,
      "step": 147
    },
    {
      "epoch": 0.6851851851851852,
      "grad_norm": 0.43016213178634644,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.3432,
      "step": 148
    },
    {
      "epoch": 0.6898148148148148,
      "grad_norm": 0.4874362647533417,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.329,
      "step": 149
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 0.4464547038078308,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.2995,
      "step": 150
    },
    {
      "epoch": 0.6944444444444444,
      "eval_loss": 0.38847672939300537,
      "eval_runtime": 10.7562,
      "eval_samples_per_second": 33.841,
      "eval_steps_per_second": 8.46,
      "step": 150
    },
    {
      "epoch": 0.6990740740740741,
      "grad_norm": 0.2641311287879944,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.4131,
      "step": 151
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 0.26060259342193604,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.3462,
      "step": 152
    },
    {
      "epoch": 0.7083333333333334,
      "grad_norm": 0.295708030462265,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.362,
      "step": 153
    },
    {
      "epoch": 0.7129629629629629,
      "grad_norm": 0.2942788302898407,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.3843,
      "step": 154
    },
    {
      "epoch": 0.7175925925925926,
      "grad_norm": 0.32238656282424927,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.3806,
      "step": 155
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 0.32758787274360657,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.4272,
      "step": 156
    },
    {
      "epoch": 0.7268518518518519,
      "grad_norm": 0.3266538083553314,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.3941,
      "step": 157
    },
    {
      "epoch": 0.7314814814814815,
      "grad_norm": 0.31273770332336426,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.3879,
      "step": 158
    },
    {
      "epoch": 0.7361111111111112,
      "grad_norm": 0.31668028235435486,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.4172,
      "step": 159
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.35479333996772766,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.4188,
      "step": 160
    },
    {
      "epoch": 0.7453703703703703,
      "grad_norm": 0.3185420632362366,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.3702,
      "step": 161
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.32833749055862427,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.3905,
      "step": 162
    },
    {
      "epoch": 0.7546296296296297,
      "grad_norm": 0.35279256105422974,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.4106,
      "step": 163
    },
    {
      "epoch": 0.7592592592592593,
      "grad_norm": 0.3606630265712738,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.348,
      "step": 164
    },
    {
      "epoch": 0.7638888888888888,
      "grad_norm": 0.37146317958831787,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.4223,
      "step": 165
    },
    {
      "epoch": 0.7685185185185185,
      "grad_norm": 0.3507327139377594,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.3814,
      "step": 166
    },
    {
      "epoch": 0.7731481481481481,
      "grad_norm": 0.35058239102363586,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.4144,
      "step": 167
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.34822559356689453,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.3639,
      "step": 168
    },
    {
      "epoch": 0.7824074074074074,
      "grad_norm": 0.3555870056152344,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.4114,
      "step": 169
    },
    {
      "epoch": 0.7870370370370371,
      "grad_norm": 0.35749712586402893,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.4029,
      "step": 170
    },
    {
      "epoch": 0.7916666666666666,
      "grad_norm": 0.3469519317150116,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.3668,
      "step": 171
    },
    {
      "epoch": 0.7962962962962963,
      "grad_norm": 0.38634976744651794,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.4036,
      "step": 172
    },
    {
      "epoch": 0.8009259259259259,
      "grad_norm": 0.4181394577026367,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.4194,
      "step": 173
    },
    {
      "epoch": 0.8055555555555556,
      "grad_norm": 0.40631362795829773,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.4073,
      "step": 174
    },
    {
      "epoch": 0.8101851851851852,
      "grad_norm": 0.3554861545562744,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.3535,
      "step": 175
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 0.417157918214798,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.3859,
      "step": 176
    },
    {
      "epoch": 0.8194444444444444,
      "grad_norm": 0.3751615285873413,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.357,
      "step": 177
    },
    {
      "epoch": 0.8240740740740741,
      "grad_norm": 0.3940601646900177,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.3805,
      "step": 178
    },
    {
      "epoch": 0.8287037037037037,
      "grad_norm": 0.4035862982273102,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.4273,
      "step": 179
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.39286839962005615,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.3548,
      "step": 180
    },
    {
      "epoch": 0.8379629629629629,
      "grad_norm": 0.39956730604171753,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.3481,
      "step": 181
    },
    {
      "epoch": 0.8425925925925926,
      "grad_norm": 0.4352265000343323,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.3963,
      "step": 182
    },
    {
      "epoch": 0.8472222222222222,
      "grad_norm": 0.42244186997413635,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.384,
      "step": 183
    },
    {
      "epoch": 0.8518518518518519,
      "grad_norm": 0.45087119936943054,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.4777,
      "step": 184
    },
    {
      "epoch": 0.8564814814814815,
      "grad_norm": 0.43319055438041687,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.3658,
      "step": 185
    },
    {
      "epoch": 0.8611111111111112,
      "grad_norm": 0.44350719451904297,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.379,
      "step": 186
    },
    {
      "epoch": 0.8657407407407407,
      "grad_norm": 0.3942970931529999,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.3377,
      "step": 187
    },
    {
      "epoch": 0.8703703703703703,
      "grad_norm": 0.3938329815864563,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.3534,
      "step": 188
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.4132087230682373,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.3661,
      "step": 189
    },
    {
      "epoch": 0.8796296296296297,
      "grad_norm": 0.44239145517349243,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.3827,
      "step": 190
    },
    {
      "epoch": 0.8842592592592593,
      "grad_norm": 0.4252067506313324,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.37,
      "step": 191
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.46257272362709045,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.3886,
      "step": 192
    },
    {
      "epoch": 0.8935185185185185,
      "grad_norm": 0.46437880396842957,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.3616,
      "step": 193
    },
    {
      "epoch": 0.8981481481481481,
      "grad_norm": 0.43990594148635864,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.3436,
      "step": 194
    },
    {
      "epoch": 0.9027777777777778,
      "grad_norm": 0.4099377989768982,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.2959,
      "step": 195
    },
    {
      "epoch": 0.9074074074074074,
      "grad_norm": 0.45510467886924744,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.3574,
      "step": 196
    },
    {
      "epoch": 0.9120370370370371,
      "grad_norm": 0.39879852533340454,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.2324,
      "step": 197
    },
    {
      "epoch": 0.9166666666666666,
      "grad_norm": 0.5208811163902283,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.3478,
      "step": 198
    },
    {
      "epoch": 0.9212962962962963,
      "grad_norm": 0.48168128728866577,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.3056,
      "step": 199
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 0.515430212020874,
      "learning_rate": 0.0,
      "loss": 0.3144,
      "step": 200
    },
    {
      "epoch": 0.9259259259259259,
      "eval_loss": 0.3864835798740387,
      "eval_runtime": 10.7673,
      "eval_samples_per_second": 33.806,
      "eval_steps_per_second": 8.451,
      "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": 5.449698231975936e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}