{
  "best_metric": 0.3863507807254791,
  "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": 1.1116503477096558,
      "learning_rate": 1e-05,
      "loss": 0.7853,
      "step": 1
    },
    {
      "epoch": 0.004629629629629629,
      "eval_loss": 1.228265643119812,
      "eval_runtime": 10.7636,
      "eval_samples_per_second": 33.818,
      "eval_steps_per_second": 8.454,
      "step": 1
    },
    {
      "epoch": 0.009259259259259259,
      "grad_norm": 1.269981026649475,
      "learning_rate": 2e-05,
      "loss": 0.8937,
      "step": 2
    },
    {
      "epoch": 0.013888888888888888,
      "grad_norm": 1.243467092514038,
      "learning_rate": 3e-05,
      "loss": 0.8599,
      "step": 3
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 1.1687246561050415,
      "learning_rate": 4e-05,
      "loss": 0.8177,
      "step": 4
    },
    {
      "epoch": 0.023148148148148147,
      "grad_norm": 0.9286789298057556,
      "learning_rate": 5e-05,
      "loss": 0.7678,
      "step": 5
    },
    {
      "epoch": 0.027777777777777776,
      "grad_norm": 0.9791531562805176,
      "learning_rate": 6e-05,
      "loss": 0.6908,
      "step": 6
    },
    {
      "epoch": 0.032407407407407406,
      "grad_norm": 0.8217535018920898,
      "learning_rate": 7e-05,
      "loss": 0.632,
      "step": 7
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 0.7658693194389343,
      "learning_rate": 8e-05,
      "loss": 0.5994,
      "step": 8
    },
    {
      "epoch": 0.041666666666666664,
      "grad_norm": 0.8283236026763916,
      "learning_rate": 9e-05,
      "loss": 0.5253,
      "step": 9
    },
    {
      "epoch": 0.046296296296296294,
      "grad_norm": 0.6653305292129517,
      "learning_rate": 0.0001,
      "loss": 0.5498,
      "step": 10
    },
    {
      "epoch": 0.05092592592592592,
      "grad_norm": 0.776948094367981,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.4912,
      "step": 11
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 0.7898920774459839,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.5208,
      "step": 12
    },
    {
      "epoch": 0.06018518518518518,
      "grad_norm": 0.6957536935806274,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.5063,
      "step": 13
    },
    {
      "epoch": 0.06481481481481481,
      "grad_norm": 0.5255388617515564,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.4221,
      "step": 14
    },
    {
      "epoch": 0.06944444444444445,
      "grad_norm": 0.4727154076099396,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.4621,
      "step": 15
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.46541333198547363,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.4741,
      "step": 16
    },
    {
      "epoch": 0.0787037037037037,
      "grad_norm": 0.46019768714904785,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.411,
      "step": 17
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.48117706179618835,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.4996,
      "step": 18
    },
    {
      "epoch": 0.08796296296296297,
      "grad_norm": 0.3986371159553528,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.403,
      "step": 19
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 0.4216457009315491,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.4267,
      "step": 20
    },
    {
      "epoch": 0.09722222222222222,
      "grad_norm": 0.4218006730079651,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.4882,
      "step": 21
    },
    {
      "epoch": 0.10185185185185185,
      "grad_norm": 0.4426274001598358,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.4515,
      "step": 22
    },
    {
      "epoch": 0.10648148148148148,
      "grad_norm": 0.48022329807281494,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.4407,
      "step": 23
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.4235152006149292,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.4444,
      "step": 24
    },
    {
      "epoch": 0.11574074074074074,
      "grad_norm": 0.39923521876335144,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4146,
      "step": 25
    },
    {
      "epoch": 0.12037037037037036,
      "grad_norm": 0.39281854033470154,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.3625,
      "step": 26
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.39478978514671326,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.4351,
      "step": 27
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 0.45827656984329224,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.4168,
      "step": 28
    },
    {
      "epoch": 0.13425925925925927,
      "grad_norm": 0.45175567269325256,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.4545,
      "step": 29
    },
    {
      "epoch": 0.1388888888888889,
      "grad_norm": 0.4498355984687805,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.4195,
      "step": 30
    },
    {
      "epoch": 0.14351851851851852,
      "grad_norm": 0.4225335717201233,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.4137,
      "step": 31
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.46917879581451416,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.4149,
      "step": 32
    },
    {
      "epoch": 0.1527777777777778,
      "grad_norm": 0.47430655360221863,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.4475,
      "step": 33
    },
    {
      "epoch": 0.1574074074074074,
      "grad_norm": 0.3934857249259949,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.3383,
      "step": 34
    },
    {
      "epoch": 0.16203703703703703,
      "grad_norm": 0.4452110826969147,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.4392,
      "step": 35
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.46636447310447693,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.3946,
      "step": 36
    },
    {
      "epoch": 0.1712962962962963,
      "grad_norm": 0.47346222400665283,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.475,
      "step": 37
    },
    {
      "epoch": 0.17592592592592593,
      "grad_norm": 0.4050373435020447,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.3835,
      "step": 38
    },
    {
      "epoch": 0.18055555555555555,
      "grad_norm": 0.4660976827144623,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.4228,
      "step": 39
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 0.4406033456325531,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.415,
      "step": 40
    },
    {
      "epoch": 0.18981481481481483,
      "grad_norm": 0.4363653361797333,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.3598,
      "step": 41
    },
    {
      "epoch": 0.19444444444444445,
      "grad_norm": 0.4854587912559509,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.4426,
      "step": 42
    },
    {
      "epoch": 0.19907407407407407,
      "grad_norm": 0.4999794363975525,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.4363,
      "step": 43
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 0.5329166054725647,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.4684,
      "step": 44
    },
    {
      "epoch": 0.20833333333333334,
      "grad_norm": 0.44108039140701294,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.3653,
      "step": 45
    },
    {
      "epoch": 0.21296296296296297,
      "grad_norm": 0.48241159319877625,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.3816,
      "step": 46
    },
    {
      "epoch": 0.2175925925925926,
      "grad_norm": 0.4330708384513855,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.3062,
      "step": 47
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.4994361698627472,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.3543,
      "step": 48
    },
    {
      "epoch": 0.22685185185185186,
      "grad_norm": 0.5072311758995056,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.3651,
      "step": 49
    },
    {
      "epoch": 0.23148148148148148,
      "grad_norm": 0.5219935178756714,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.2811,
      "step": 50
    },
    {
      "epoch": 0.23148148148148148,
      "eval_loss": 0.4220910668373108,
      "eval_runtime": 10.7809,
      "eval_samples_per_second": 33.763,
      "eval_steps_per_second": 8.441,
      "step": 50
    },
    {
      "epoch": 0.2361111111111111,
      "grad_norm": 0.40513595938682556,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.4518,
      "step": 51
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 0.42868730425834656,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.4215,
      "step": 52
    },
    {
      "epoch": 0.24537037037037038,
      "grad_norm": 0.3781394362449646,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.4375,
      "step": 53
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.35364967584609985,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.4096,
      "step": 54
    },
    {
      "epoch": 0.25462962962962965,
      "grad_norm": 0.3423779606819153,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.4061,
      "step": 55
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 0.35195615887641907,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.4425,
      "step": 56
    },
    {
      "epoch": 0.2638888888888889,
      "grad_norm": 0.391480416059494,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.4465,
      "step": 57
    },
    {
      "epoch": 0.26851851851851855,
      "grad_norm": 0.31563639640808105,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.4086,
      "step": 58
    },
    {
      "epoch": 0.27314814814814814,
      "grad_norm": 0.38046443462371826,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.4205,
      "step": 59
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 0.3305398225784302,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.4202,
      "step": 60
    },
    {
      "epoch": 0.2824074074074074,
      "grad_norm": 0.312997430562973,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.3426,
      "step": 61
    },
    {
      "epoch": 0.28703703703703703,
      "grad_norm": 0.3744153380393982,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.436,
      "step": 62
    },
    {
      "epoch": 0.2916666666666667,
      "grad_norm": 0.35333868861198425,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.4221,
      "step": 63
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.3206513524055481,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.3775,
      "step": 64
    },
    {
      "epoch": 0.30092592592592593,
      "grad_norm": 0.3325778543949127,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.4343,
      "step": 65
    },
    {
      "epoch": 0.3055555555555556,
      "grad_norm": 0.3781082034111023,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.4059,
      "step": 66
    },
    {
      "epoch": 0.3101851851851852,
      "grad_norm": 0.3358839452266693,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.4053,
      "step": 67
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 0.36629346013069153,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.4335,
      "step": 68
    },
    {
      "epoch": 0.3194444444444444,
      "grad_norm": 0.3664039969444275,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3958,
      "step": 69
    },
    {
      "epoch": 0.32407407407407407,
      "grad_norm": 0.39814943075180054,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.367,
      "step": 70
    },
    {
      "epoch": 0.3287037037037037,
      "grad_norm": 0.39790067076683044,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.3887,
      "step": 71
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.4013422429561615,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.4253,
      "step": 72
    },
    {
      "epoch": 0.33796296296296297,
      "grad_norm": 0.41339045763015747,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.4214,
      "step": 73
    },
    {
      "epoch": 0.3425925925925926,
      "grad_norm": 0.3853583335876465,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.4016,
      "step": 74
    },
    {
      "epoch": 0.3472222222222222,
      "grad_norm": 0.4177508056163788,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.4277,
      "step": 75
    },
    {
      "epoch": 0.35185185185185186,
      "grad_norm": 0.3948586881160736,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.408,
      "step": 76
    },
    {
      "epoch": 0.35648148148148145,
      "grad_norm": 0.38890504837036133,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.4446,
      "step": 77
    },
    {
      "epoch": 0.3611111111111111,
      "grad_norm": 0.38982126116752625,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.4105,
      "step": 78
    },
    {
      "epoch": 0.36574074074074076,
      "grad_norm": 0.4018224775791168,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.4262,
      "step": 79
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.4219288229942322,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.3909,
      "step": 80
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.4250439703464508,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.3956,
      "step": 81
    },
    {
      "epoch": 0.37962962962962965,
      "grad_norm": 0.3462982773780823,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3117,
      "step": 82
    },
    {
      "epoch": 0.38425925925925924,
      "grad_norm": 0.4220518171787262,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.3884,
      "step": 83
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.3963468670845032,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.3703,
      "step": 84
    },
    {
      "epoch": 0.39351851851851855,
      "grad_norm": 0.3883061707019806,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.3685,
      "step": 85
    },
    {
      "epoch": 0.39814814814814814,
      "grad_norm": 0.4225544333457947,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3344,
      "step": 86
    },
    {
      "epoch": 0.4027777777777778,
      "grad_norm": 0.39544677734375,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.3829,
      "step": 87
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 0.42198488116264343,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.4131,
      "step": 88
    },
    {
      "epoch": 0.41203703703703703,
      "grad_norm": 0.4477500915527344,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.3664,
      "step": 89
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 0.44047096371650696,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.3926,
      "step": 90
    },
    {
      "epoch": 0.4212962962962963,
      "grad_norm": 0.43650689721107483,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.4018,
      "step": 91
    },
    {
      "epoch": 0.42592592592592593,
      "grad_norm": 0.3988071084022522,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.3736,
      "step": 92
    },
    {
      "epoch": 0.4305555555555556,
      "grad_norm": 0.46088728308677673,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4514,
      "step": 93
    },
    {
      "epoch": 0.4351851851851852,
      "grad_norm": 0.4239994287490845,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.3864,
      "step": 94
    },
    {
      "epoch": 0.4398148148148148,
      "grad_norm": 0.44305211305618286,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.374,
      "step": 95
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.4329140782356262,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.3593,
      "step": 96
    },
    {
      "epoch": 0.44907407407407407,
      "grad_norm": 0.48329660296440125,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.3975,
      "step": 97
    },
    {
      "epoch": 0.4537037037037037,
      "grad_norm": 0.3880534768104553,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.2765,
      "step": 98
    },
    {
      "epoch": 0.4583333333333333,
      "grad_norm": 0.38081857562065125,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.2781,
      "step": 99
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 0.39689257740974426,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.2756,
      "step": 100
    },
    {
      "epoch": 0.46296296296296297,
      "eval_loss": 0.40054818987846375,
      "eval_runtime": 10.7735,
      "eval_samples_per_second": 33.787,
      "eval_steps_per_second": 8.447,
      "step": 100
    },
    {
      "epoch": 0.4675925925925926,
      "grad_norm": 0.30973020195961,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.4769,
      "step": 101
    },
    {
      "epoch": 0.4722222222222222,
      "grad_norm": 0.3454133868217468,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.4476,
      "step": 102
    },
    {
      "epoch": 0.47685185185185186,
      "grad_norm": 0.3141106963157654,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.4246,
      "step": 103
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 0.29273855686187744,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.3928,
      "step": 104
    },
    {
      "epoch": 0.4861111111111111,
      "grad_norm": 0.35139960050582886,
      "learning_rate": 5e-05,
      "loss": 0.4515,
      "step": 105
    },
    {
      "epoch": 0.49074074074074076,
      "grad_norm": 0.31835365295410156,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.4208,
      "step": 106
    },
    {
      "epoch": 0.49537037037037035,
      "grad_norm": 0.33383437991142273,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.4209,
      "step": 107
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.34722745418548584,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.4656,
      "step": 108
    },
    {
      "epoch": 0.5046296296296297,
      "grad_norm": 0.2982996702194214,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.3507,
      "step": 109
    },
    {
      "epoch": 0.5092592592592593,
      "grad_norm": 0.3275409936904907,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.3617,
      "step": 110
    },
    {
      "epoch": 0.5138888888888888,
      "grad_norm": 0.33099961280822754,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.3517,
      "step": 111
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.33550557494163513,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.4334,
      "step": 112
    },
    {
      "epoch": 0.5231481481481481,
      "grad_norm": 0.36219605803489685,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.394,
      "step": 113
    },
    {
      "epoch": 0.5277777777777778,
      "grad_norm": 0.3489916920661926,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.4535,
      "step": 114
    },
    {
      "epoch": 0.5324074074074074,
      "grad_norm": 0.35915425419807434,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.4384,
      "step": 115
    },
    {
      "epoch": 0.5370370370370371,
      "grad_norm": 0.3669782876968384,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.4106,
      "step": 116
    },
    {
      "epoch": 0.5416666666666666,
      "grad_norm": 0.36302924156188965,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.4328,
      "step": 117
    },
    {
      "epoch": 0.5462962962962963,
      "grad_norm": 0.36465269327163696,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.3772,
      "step": 118
    },
    {
      "epoch": 0.5509259259259259,
      "grad_norm": 0.40110573172569275,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.4015,
      "step": 119
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.37549349665641785,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.4517,
      "step": 120
    },
    {
      "epoch": 0.5601851851851852,
      "grad_norm": 0.34770068526268005,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.3598,
      "step": 121
    },
    {
      "epoch": 0.5648148148148148,
      "grad_norm": 0.37237435579299927,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.4272,
      "step": 122
    },
    {
      "epoch": 0.5694444444444444,
      "grad_norm": 0.31195151805877686,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.3269,
      "step": 123
    },
    {
      "epoch": 0.5740740740740741,
      "grad_norm": 0.33469128608703613,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.3795,
      "step": 124
    },
    {
      "epoch": 0.5787037037037037,
      "grad_norm": 0.39495936036109924,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4441,
      "step": 125
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 0.35597342252731323,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.379,
      "step": 126
    },
    {
      "epoch": 0.5879629629629629,
      "grad_norm": 0.4018954336643219,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.4938,
      "step": 127
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.3984406888484955,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.4209,
      "step": 128
    },
    {
      "epoch": 0.5972222222222222,
      "grad_norm": 0.4191405475139618,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.444,
      "step": 129
    },
    {
      "epoch": 0.6018518518518519,
      "grad_norm": 0.4371749460697174,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.4234,
      "step": 130
    },
    {
      "epoch": 0.6064814814814815,
      "grad_norm": 0.3813394010066986,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3846,
      "step": 131
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 0.36820274591445923,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.3551,
      "step": 132
    },
    {
      "epoch": 0.6157407407407407,
      "grad_norm": 0.37040993571281433,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.3445,
      "step": 133
    },
    {
      "epoch": 0.6203703703703703,
      "grad_norm": 0.3780434727668762,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.3451,
      "step": 134
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.48591867089271545,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.433,
      "step": 135
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 0.3953004479408264,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.3709,
      "step": 136
    },
    {
      "epoch": 0.6342592592592593,
      "grad_norm": 0.3976372480392456,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.3897,
      "step": 137
    },
    {
      "epoch": 0.6388888888888888,
      "grad_norm": 0.41118407249450684,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.3342,
      "step": 138
    },
    {
      "epoch": 0.6435185185185185,
      "grad_norm": 0.425074964761734,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.4051,
      "step": 139
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 0.38811710476875305,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.3067,
      "step": 140
    },
    {
      "epoch": 0.6527777777777778,
      "grad_norm": 0.446621298789978,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.4242,
      "step": 141
    },
    {
      "epoch": 0.6574074074074074,
      "grad_norm": 0.4710548222064972,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.3721,
      "step": 142
    },
    {
      "epoch": 0.6620370370370371,
      "grad_norm": 0.473621129989624,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.3758,
      "step": 143
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.4742882251739502,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.4299,
      "step": 144
    },
    {
      "epoch": 0.6712962962962963,
      "grad_norm": 0.4604876637458801,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.3554,
      "step": 145
    },
    {
      "epoch": 0.6759259259259259,
      "grad_norm": 0.453888863325119,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.3811,
      "step": 146
    },
    {
      "epoch": 0.6805555555555556,
      "grad_norm": 0.43823665380477905,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.3157,
      "step": 147
    },
    {
      "epoch": 0.6851851851851852,
      "grad_norm": 0.4286869764328003,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.3436,
      "step": 148
    },
    {
      "epoch": 0.6898148148148148,
      "grad_norm": 0.4839453399181366,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.3277,
      "step": 149
    },
    {
      "epoch": 0.6944444444444444,
      "grad_norm": 0.44581836462020874,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.3,
      "step": 150
    },
    {
      "epoch": 0.6944444444444444,
      "eval_loss": 0.38866910338401794,
      "eval_runtime": 10.7686,
      "eval_samples_per_second": 33.802,
      "eval_steps_per_second": 8.451,
      "step": 150
    },
    {
      "epoch": 0.6990740740740741,
      "grad_norm": 0.2628742754459381,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.4141,
      "step": 151
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 0.25840333104133606,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.3456,
      "step": 152
    },
    {
      "epoch": 0.7083333333333334,
      "grad_norm": 0.2910604774951935,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.3609,
      "step": 153
    },
    {
      "epoch": 0.7129629629629629,
      "grad_norm": 0.29353925585746765,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.3841,
      "step": 154
    },
    {
      "epoch": 0.7175925925925926,
      "grad_norm": 0.32555025815963745,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.3813,
      "step": 155
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 0.3234391212463379,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.4271,
      "step": 156
    },
    {
      "epoch": 0.7268518518518519,
      "grad_norm": 0.32888540625572205,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.3928,
      "step": 157
    },
    {
      "epoch": 0.7314814814814815,
      "grad_norm": 0.3135108947753906,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.3881,
      "step": 158
    },
    {
      "epoch": 0.7361111111111112,
      "grad_norm": 0.31699323654174805,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.4168,
      "step": 159
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.3495485782623291,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.4176,
      "step": 160
    },
    {
      "epoch": 0.7453703703703703,
      "grad_norm": 0.3227025866508484,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.3711,
      "step": 161
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.33153361082077026,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.3912,
      "step": 162
    },
    {
      "epoch": 0.7546296296296297,
      "grad_norm": 0.35312163829803467,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.4107,
      "step": 163
    },
    {
      "epoch": 0.7592592592592593,
      "grad_norm": 0.3576184809207916,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.3481,
      "step": 164
    },
    {
      "epoch": 0.7638888888888888,
      "grad_norm": 0.3672941029071808,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.4223,
      "step": 165
    },
    {
      "epoch": 0.7685185185185185,
      "grad_norm": 0.35891035199165344,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.383,
      "step": 166
    },
    {
      "epoch": 0.7731481481481481,
      "grad_norm": 0.3527448773384094,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.4143,
      "step": 167
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.3474094569683075,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.3634,
      "step": 168
    },
    {
      "epoch": 0.7824074074074074,
      "grad_norm": 0.35586419701576233,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.4117,
      "step": 169
    },
    {
      "epoch": 0.7870370370370371,
      "grad_norm": 0.3546221852302551,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.4027,
      "step": 170
    },
    {
      "epoch": 0.7916666666666666,
      "grad_norm": 0.347076416015625,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.3666,
      "step": 171
    },
    {
      "epoch": 0.7962962962962963,
      "grad_norm": 0.3904898166656494,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.4038,
      "step": 172
    },
    {
      "epoch": 0.8009259259259259,
      "grad_norm": 0.4171590507030487,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.4201,
      "step": 173
    },
    {
      "epoch": 0.8055555555555556,
      "grad_norm": 0.4123407006263733,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.4073,
      "step": 174
    },
    {
      "epoch": 0.8101851851851852,
      "grad_norm": 0.35650119185447693,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.3539,
      "step": 175
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 0.41362160444259644,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.3837,
      "step": 176
    },
    {
      "epoch": 0.8194444444444444,
      "grad_norm": 0.37842804193496704,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.3584,
      "step": 177
    },
    {
      "epoch": 0.8240740740740741,
      "grad_norm": 0.3910290598869324,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.3799,
      "step": 178
    },
    {
      "epoch": 0.8287037037037037,
      "grad_norm": 0.4038618803024292,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.427,
      "step": 179
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.3881385624408722,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.355,
      "step": 180
    },
    {
      "epoch": 0.8379629629629629,
      "grad_norm": 0.39390072226524353,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.3481,
      "step": 181
    },
    {
      "epoch": 0.8425925925925926,
      "grad_norm": 0.43367618322372437,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.397,
      "step": 182
    },
    {
      "epoch": 0.8472222222222222,
      "grad_norm": 0.42360448837280273,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.3826,
      "step": 183
    },
    {
      "epoch": 0.8518518518518519,
      "grad_norm": 0.45958757400512695,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.4798,
      "step": 184
    },
    {
      "epoch": 0.8564814814814815,
      "grad_norm": 0.43078696727752686,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.365,
      "step": 185
    },
    {
      "epoch": 0.8611111111111112,
      "grad_norm": 0.44293901324272156,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.3785,
      "step": 186
    },
    {
      "epoch": 0.8657407407407407,
      "grad_norm": 0.3917204439640045,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.3381,
      "step": 187
    },
    {
      "epoch": 0.8703703703703703,
      "grad_norm": 0.39390504360198975,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.3531,
      "step": 188
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.41439419984817505,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.3664,
      "step": 189
    },
    {
      "epoch": 0.8796296296296297,
      "grad_norm": 0.45025309920310974,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.3821,
      "step": 190
    },
    {
      "epoch": 0.8842592592592593,
      "grad_norm": 0.42373785376548767,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.3691,
      "step": 191
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.457111120223999,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.3889,
      "step": 192
    },
    {
      "epoch": 0.8935185185185185,
      "grad_norm": 0.4667859971523285,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.3626,
      "step": 193
    },
    {
      "epoch": 0.8981481481481481,
      "grad_norm": 0.4421243965625763,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.3445,
      "step": 194
    },
    {
      "epoch": 0.9027777777777778,
      "grad_norm": 0.4120250344276428,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.2968,
      "step": 195
    },
    {
      "epoch": 0.9074074074074074,
      "grad_norm": 0.45083436369895935,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.3572,
      "step": 196
    },
    {
      "epoch": 0.9120370370370371,
      "grad_norm": 0.39258265495300293,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.2324,
      "step": 197
    },
    {
      "epoch": 0.9166666666666666,
      "grad_norm": 0.5152950286865234,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.3479,
      "step": 198
    },
    {
      "epoch": 0.9212962962962963,
      "grad_norm": 0.47318968176841736,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.3031,
      "step": 199
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 0.5102648138999939,
      "learning_rate": 0.0,
      "loss": 0.3144,
      "step": 200
    },
    {
      "epoch": 0.9259259259259259,
      "eval_loss": 0.3863507807254791,
      "eval_runtime": 10.7812,
      "eval_samples_per_second": 33.762,
      "eval_steps_per_second": 8.441,
      "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
}