{
  "best_metric": 11.5,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.4035087719298245,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007017543859649123,
      "grad_norm": 0.00021037270198576152,
      "learning_rate": 1e-05,
      "loss": 46.0,
      "step": 1
    },
    {
      "epoch": 0.007017543859649123,
      "eval_loss": 11.5,
      "eval_runtime": 1.1015,
      "eval_samples_per_second": 217.889,
      "eval_steps_per_second": 54.472,
      "step": 1
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 7.683919830014929e-05,
      "learning_rate": 2e-05,
      "loss": 46.0,
      "step": 2
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 0.00011457066284492612,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.028070175438596492,
      "grad_norm": 0.00013803814363200217,
      "learning_rate": 4e-05,
      "loss": 46.0,
      "step": 4
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 5.097964822198264e-05,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 5
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 9.476527338847518e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.04912280701754386,
      "grad_norm": 0.00010046480019809678,
      "learning_rate": 7e-05,
      "loss": 46.0,
      "step": 7
    },
    {
      "epoch": 0.056140350877192984,
      "grad_norm": 0.0001933151506818831,
      "learning_rate": 8e-05,
      "loss": 46.0,
      "step": 8
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 8.163167512975633e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 0.00011006933345925063,
      "learning_rate": 0.0001,
      "loss": 46.0,
      "step": 10
    },
    {
      "epoch": 0.07719298245614035,
      "grad_norm": 0.00010468786786077544,
      "learning_rate": 9.999316524962345e-05,
      "loss": 46.0,
      "step": 11
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 0.00020174520614091307,
      "learning_rate": 9.997266286704631e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.0912280701754386,
      "grad_norm": 0.00022835728304926306,
      "learning_rate": 9.993849845741524e-05,
      "loss": 46.0,
      "step": 13
    },
    {
      "epoch": 0.09824561403508772,
      "grad_norm": 0.0002736512979026884,
      "learning_rate": 9.989068136093873e-05,
      "loss": 46.0,
      "step": 14
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 8.854314364725724e-05,
      "learning_rate": 9.98292246503335e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.11228070175438597,
      "grad_norm": 7.895521412137896e-05,
      "learning_rate": 9.975414512725057e-05,
      "loss": 46.0,
      "step": 16
    },
    {
      "epoch": 0.11929824561403508,
      "grad_norm": 0.00010392226977273822,
      "learning_rate": 9.966546331768191e-05,
      "loss": 46.0,
      "step": 17
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 0.00014997807738836855,
      "learning_rate": 9.956320346634876e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.00015150054241530597,
      "learning_rate": 9.944739353007344e-05,
      "loss": 46.0,
      "step": 19
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 0.00018257946067024022,
      "learning_rate": 9.931806517013612e-05,
      "loss": 46.0,
      "step": 20
    },
    {
      "epoch": 0.14736842105263157,
      "grad_norm": 0.00021177575399633497,
      "learning_rate": 9.917525374361912e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.1543859649122807,
      "grad_norm": 0.00013557009515352547,
      "learning_rate": 9.901899829374047e-05,
      "loss": 46.0,
      "step": 22
    },
    {
      "epoch": 0.16140350877192983,
      "grad_norm": 0.0001964844122994691,
      "learning_rate": 9.884934153917997e-05,
      "loss": 46.0,
      "step": 23
    },
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 0.0002958090044558048,
      "learning_rate": 9.86663298624003e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 9.043505997397006e-05,
      "learning_rate": 9.847001329696653e-05,
      "loss": 46.0,
      "step": 25
    },
    {
      "epoch": 0.1824561403508772,
      "grad_norm": 0.00019477946625556797,
      "learning_rate": 9.826044551386744e-05,
      "loss": 46.0,
      "step": 26
    },
    {
      "epoch": 0.18947368421052632,
      "grad_norm": 0.0002486860321369022,
      "learning_rate": 9.803768380684242e-05,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.19649122807017544,
      "grad_norm": 0.00022384659678209573,
      "learning_rate": 9.780178907671789e-05,
      "loss": 46.0,
      "step": 28
    },
    {
      "epoch": 0.20350877192982456,
      "grad_norm": 0.000436764006735757,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 29
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.0004282392328605056,
      "learning_rate": 9.729086208503174e-05,
      "loss": 46.0,
      "step": 30
    },
    {
      "epoch": 0.21754385964912282,
      "grad_norm": 0.00023486613645218313,
      "learning_rate": 9.701596950580806e-05,
      "loss": 46.0,
      "step": 31
    },
    {
      "epoch": 0.22456140350877193,
      "grad_norm": 0.00027485619648359716,
      "learning_rate": 9.672822322997305e-05,
      "loss": 46.0,
      "step": 32
    },
    {
      "epoch": 0.23157894736842105,
      "grad_norm": 0.00046266603749245405,
      "learning_rate": 9.642770192448536e-05,
      "loss": 46.0,
      "step": 33
    },
    {
      "epoch": 0.23859649122807017,
      "grad_norm": 0.00023902856628410518,
      "learning_rate": 9.611448774886924e-05,
      "loss": 46.0,
      "step": 34
    },
    {
      "epoch": 0.24561403508771928,
      "grad_norm": 0.00033735958277247846,
      "learning_rate": 9.578866633275288e-05,
      "loss": 46.0,
      "step": 35
    },
    {
      "epoch": 0.25263157894736843,
      "grad_norm": 0.00020371965365484357,
      "learning_rate": 9.545032675245813e-05,
      "loss": 46.0,
      "step": 36
    },
    {
      "epoch": 0.2596491228070175,
      "grad_norm": 0.00015130790416151285,
      "learning_rate": 9.509956150664796e-05,
      "loss": 46.0,
      "step": 37
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.00022740459826309234,
      "learning_rate": 9.473646649103818e-05,
      "loss": 46.0,
      "step": 38
    },
    {
      "epoch": 0.2736842105263158,
      "grad_norm": 0.0002811090962495655,
      "learning_rate": 9.43611409721806e-05,
      "loss": 46.0,
      "step": 39
    },
    {
      "epoch": 0.2807017543859649,
      "grad_norm": 0.00019960838835686445,
      "learning_rate": 9.397368756032445e-05,
      "loss": 46.0,
      "step": 40
    },
    {
      "epoch": 0.28771929824561404,
      "grad_norm": 0.00014518367242999375,
      "learning_rate": 9.357421218136386e-05,
      "loss": 46.0,
      "step": 41
    },
    {
      "epoch": 0.29473684210526313,
      "grad_norm": 0.00045839257654733956,
      "learning_rate": 9.316282404787871e-05,
      "loss": 46.0,
      "step": 42
    },
    {
      "epoch": 0.3017543859649123,
      "grad_norm": 0.000284804729744792,
      "learning_rate": 9.273963562927695e-05,
      "loss": 46.0,
      "step": 43
    },
    {
      "epoch": 0.3087719298245614,
      "grad_norm": 0.00019825409981422126,
      "learning_rate": 9.230476262104677e-05,
      "loss": 46.0,
      "step": 44
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 0.000379782693926245,
      "learning_rate": 9.185832391312644e-05,
      "loss": 46.0,
      "step": 45
    },
    {
      "epoch": 0.32280701754385965,
      "grad_norm": 0.00019821675959974527,
      "learning_rate": 9.140044155740101e-05,
      "loss": 46.0,
      "step": 46
    },
    {
      "epoch": 0.3298245614035088,
      "grad_norm": 0.000726365833543241,
      "learning_rate": 9.093124073433463e-05,
      "loss": 46.0,
      "step": 47
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 0.0005751466378569603,
      "learning_rate": 9.045084971874738e-05,
      "loss": 46.0,
      "step": 48
    },
    {
      "epoch": 0.34385964912280703,
      "grad_norm": 0.0006562319467775524,
      "learning_rate": 8.995939984474624e-05,
      "loss": 46.0,
      "step": 49
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 0.00047178444219753146,
      "learning_rate": 8.945702546981969e-05,
      "loss": 46.0,
      "step": 50
    },
    {
      "epoch": 0.3508771929824561,
      "eval_loss": 11.5,
      "eval_runtime": 1.0967,
      "eval_samples_per_second": 218.836,
      "eval_steps_per_second": 54.709,
      "step": 50
    },
    {
      "epoch": 0.35789473684210527,
      "grad_norm": 0.00014034660125616938,
      "learning_rate": 8.894386393810563e-05,
      "loss": 46.0,
      "step": 51
    },
    {
      "epoch": 0.3649122807017544,
      "grad_norm": 0.00021817724336870015,
      "learning_rate": 8.842005554284296e-05,
      "loss": 46.0,
      "step": 52
    },
    {
      "epoch": 0.3719298245614035,
      "grad_norm": 0.0003717761137522757,
      "learning_rate": 8.788574348801675e-05,
      "loss": 46.0,
      "step": 53
    },
    {
      "epoch": 0.37894736842105264,
      "grad_norm": 0.0003482745960354805,
      "learning_rate": 8.73410738492077e-05,
      "loss": 46.0,
      "step": 54
    },
    {
      "epoch": 0.38596491228070173,
      "grad_norm": 0.000325809873174876,
      "learning_rate": 8.678619553365659e-05,
      "loss": 46.0,
      "step": 55
    },
    {
      "epoch": 0.3929824561403509,
      "grad_norm": 0.0007256643148139119,
      "learning_rate": 8.622126023955446e-05,
      "loss": 46.0,
      "step": 56
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.0004237841349095106,
      "learning_rate": 8.564642241456986e-05,
      "loss": 46.0,
      "step": 57
    },
    {
      "epoch": 0.4070175438596491,
      "grad_norm": 0.0002420614182483405,
      "learning_rate": 8.506183921362443e-05,
      "loss": 46.0,
      "step": 58
    },
    {
      "epoch": 0.41403508771929826,
      "grad_norm": 0.000972063688095659,
      "learning_rate": 8.44676704559283e-05,
      "loss": 46.0,
      "step": 59
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.00014191176160238683,
      "learning_rate": 8.386407858128706e-05,
      "loss": 46.0,
      "step": 60
    },
    {
      "epoch": 0.4280701754385965,
      "grad_norm": 0.0002644241030793637,
      "learning_rate": 8.32512286056924e-05,
      "loss": 46.0,
      "step": 61
    },
    {
      "epoch": 0.43508771929824563,
      "grad_norm": 0.0003872114175464958,
      "learning_rate": 8.262928807620843e-05,
      "loss": 46.0,
      "step": 62
    },
    {
      "epoch": 0.4421052631578947,
      "grad_norm": 0.0003983385977335274,
      "learning_rate": 8.199842702516583e-05,
      "loss": 46.0,
      "step": 63
    },
    {
      "epoch": 0.44912280701754387,
      "grad_norm": 0.0006656920304521918,
      "learning_rate": 8.135881792367686e-05,
      "loss": 46.0,
      "step": 64
    },
    {
      "epoch": 0.45614035087719296,
      "grad_norm": 0.0012674872996285558,
      "learning_rate": 8.07106356344834e-05,
      "loss": 46.0,
      "step": 65
    },
    {
      "epoch": 0.4631578947368421,
      "grad_norm": 0.0007862824713811278,
      "learning_rate": 8.005405736415126e-05,
      "loss": 46.0,
      "step": 66
    },
    {
      "epoch": 0.47017543859649125,
      "grad_norm": 0.0006588378455489874,
      "learning_rate": 7.938926261462366e-05,
      "loss": 46.0,
      "step": 67
    },
    {
      "epoch": 0.47719298245614034,
      "grad_norm": 0.0007850521942600608,
      "learning_rate": 7.871643313414718e-05,
      "loss": 46.0,
      "step": 68
    },
    {
      "epoch": 0.4842105263157895,
      "grad_norm": 0.0008522047428414226,
      "learning_rate": 7.803575286758364e-05,
      "loss": 46.0,
      "step": 69
    },
    {
      "epoch": 0.49122807017543857,
      "grad_norm": 0.000569663243368268,
      "learning_rate": 7.734740790612136e-05,
      "loss": 46.0,
      "step": 70
    },
    {
      "epoch": 0.4982456140350877,
      "grad_norm": 0.0005156466504558921,
      "learning_rate": 7.66515864363997e-05,
      "loss": 46.0,
      "step": 71
    },
    {
      "epoch": 0.5052631578947369,
      "grad_norm": 0.0005122990696690977,
      "learning_rate": 7.594847868906076e-05,
      "loss": 46.0,
      "step": 72
    },
    {
      "epoch": 0.512280701754386,
      "grad_norm": 0.0005598064744845033,
      "learning_rate": 7.52382768867422e-05,
      "loss": 46.0,
      "step": 73
    },
    {
      "epoch": 0.519298245614035,
      "grad_norm": 0.000518511573318392,
      "learning_rate": 7.452117519152542e-05,
      "loss": 46.0,
      "step": 74
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.0004727860796265304,
      "learning_rate": 7.379736965185368e-05,
      "loss": 46.0,
      "step": 75
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.00039679394103586674,
      "learning_rate": 7.30670581489344e-05,
      "loss": 46.0,
      "step": 76
    },
    {
      "epoch": 0.5403508771929825,
      "grad_norm": 0.0006741546094417572,
      "learning_rate": 7.233044034264034e-05,
      "loss": 46.0,
      "step": 77
    },
    {
      "epoch": 0.5473684210526316,
      "grad_norm": 0.0004969995352439582,
      "learning_rate": 7.158771761692464e-05,
      "loss": 46.0,
      "step": 78
    },
    {
      "epoch": 0.5543859649122806,
      "grad_norm": 0.0005535801756195724,
      "learning_rate": 7.083909302476453e-05,
      "loss": 46.0,
      "step": 79
    },
    {
      "epoch": 0.5614035087719298,
      "grad_norm": 0.0004933408345095813,
      "learning_rate": 7.008477123264848e-05,
      "loss": 46.0,
      "step": 80
    },
    {
      "epoch": 0.5684210526315789,
      "grad_norm": 0.0011863734107464552,
      "learning_rate": 6.932495846462261e-05,
      "loss": 46.0,
      "step": 81
    },
    {
      "epoch": 0.5754385964912281,
      "grad_norm": 0.0009312622132711112,
      "learning_rate": 6.855986244591104e-05,
      "loss": 46.0,
      "step": 82
    },
    {
      "epoch": 0.5824561403508772,
      "grad_norm": 0.0012627077521756291,
      "learning_rate": 6.778969234612584e-05,
      "loss": 46.0,
      "step": 83
    },
    {
      "epoch": 0.5894736842105263,
      "grad_norm": 0.0007373731350526214,
      "learning_rate": 6.701465872208216e-05,
      "loss": 46.0,
      "step": 84
    },
    {
      "epoch": 0.5964912280701754,
      "grad_norm": 0.0002393435570411384,
      "learning_rate": 6.623497346023418e-05,
      "loss": 46.0,
      "step": 85
    },
    {
      "epoch": 0.6035087719298246,
      "grad_norm": 0.0004504582902882248,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 86
    },
    {
      "epoch": 0.6105263157894737,
      "grad_norm": 0.0007006081286817789,
      "learning_rate": 6.466250186922325e-05,
      "loss": 46.0,
      "step": 87
    },
    {
      "epoch": 0.6175438596491228,
      "grad_norm": 0.0007447799434885383,
      "learning_rate": 6.387014543809223e-05,
      "loss": 46.0,
      "step": 88
    },
    {
      "epoch": 0.624561403508772,
      "grad_norm": 0.0005565911997109652,
      "learning_rate": 6.307399704769099e-05,
      "loss": 46.0,
      "step": 89
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 0.0009676662739366293,
      "learning_rate": 6.227427435703997e-05,
      "loss": 46.0,
      "step": 90
    },
    {
      "epoch": 0.6385964912280702,
      "grad_norm": 0.0009430677746422589,
      "learning_rate": 6.147119600233758e-05,
      "loss": 46.0,
      "step": 91
    },
    {
      "epoch": 0.6456140350877193,
      "grad_norm": 0.0011268252274021506,
      "learning_rate": 6.066498153718735e-05,
      "loss": 46.0,
      "step": 92
    },
    {
      "epoch": 0.6526315789473685,
      "grad_norm": 0.00033556646667420864,
      "learning_rate": 5.985585137257401e-05,
      "loss": 46.0,
      "step": 93
    },
    {
      "epoch": 0.6596491228070176,
      "grad_norm": 0.0017779561458155513,
      "learning_rate": 5.90440267166055e-05,
      "loss": 46.0,
      "step": 94
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.0004352672549430281,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 46.0,
      "step": 95
    },
    {
      "epoch": 0.6736842105263158,
      "grad_norm": 0.00041180604603141546,
      "learning_rate": 5.74131823855921e-05,
      "loss": 46.0,
      "step": 96
    },
    {
      "epoch": 0.6807017543859649,
      "grad_norm": 0.0005235227872617543,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 46.0,
      "step": 97
    },
    {
      "epoch": 0.6877192982456141,
      "grad_norm": 0.0007366855279542506,
      "learning_rate": 5.577423184847932e-05,
      "loss": 46.0,
      "step": 98
    },
    {
      "epoch": 0.6947368421052632,
      "grad_norm": 0.0016353314276784658,
      "learning_rate": 5.495227651252315e-05,
      "loss": 46.0,
      "step": 99
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.0016165327979251742,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 46.0,
      "step": 100
    },
    {
      "epoch": 0.7017543859649122,
      "eval_loss": 11.5,
      "eval_runtime": 1.0913,
      "eval_samples_per_second": 219.931,
      "eval_steps_per_second": 54.983,
      "step": 100
    },
    {
      "epoch": 0.7087719298245614,
      "grad_norm": 0.0013664454454556108,
      "learning_rate": 5.330452921628497e-05,
      "loss": 46.0,
      "step": 101
    },
    {
      "epoch": 0.7157894736842105,
      "grad_norm": 0.0009399710688740015,
      "learning_rate": 5.247918773366112e-05,
      "loss": 46.0,
      "step": 102
    },
    {
      "epoch": 0.7228070175438597,
      "grad_norm": 0.000733562046661973,
      "learning_rate": 5.165316846586541e-05,
      "loss": 46.0,
      "step": 103
    },
    {
      "epoch": 0.7298245614035088,
      "grad_norm": 0.0017672738758847117,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 46.0,
      "step": 104
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 0.0010585612617433071,
      "learning_rate": 5e-05,
      "loss": 46.0,
      "step": 105
    },
    {
      "epoch": 0.743859649122807,
      "grad_norm": 0.0009115262655541301,
      "learning_rate": 4.917330276168208e-05,
      "loss": 46.0,
      "step": 106
    },
    {
      "epoch": 0.7508771929824561,
      "grad_norm": 0.0009277253411710262,
      "learning_rate": 4.834683153413459e-05,
      "loss": 46.0,
      "step": 107
    },
    {
      "epoch": 0.7578947368421053,
      "grad_norm": 0.0007808133377693594,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 46.0,
      "step": 108
    },
    {
      "epoch": 0.7649122807017544,
      "grad_norm": 0.0008117774850688875,
      "learning_rate": 4.669547078371504e-05,
      "loss": 46.0,
      "step": 109
    },
    {
      "epoch": 0.7719298245614035,
      "grad_norm": 0.0006931498646736145,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 46.0,
      "step": 110
    },
    {
      "epoch": 0.7789473684210526,
      "grad_norm": 0.0004360481398180127,
      "learning_rate": 4.504772348747687e-05,
      "loss": 46.0,
      "step": 111
    },
    {
      "epoch": 0.7859649122807018,
      "grad_norm": 0.0014560624258592725,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 46.0,
      "step": 112
    },
    {
      "epoch": 0.7929824561403509,
      "grad_norm": 0.00099574017804116,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 46.0,
      "step": 113
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.0007977131172083318,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 46.0,
      "step": 114
    },
    {
      "epoch": 0.8070175438596491,
      "grad_norm": 0.0007895089220255613,
      "learning_rate": 4.17702704859633e-05,
      "loss": 46.0,
      "step": 115
    },
    {
      "epoch": 0.8140350877192982,
      "grad_norm": 0.002135565271601081,
      "learning_rate": 4.095597328339452e-05,
      "loss": 46.0,
      "step": 116
    },
    {
      "epoch": 0.8210526315789474,
      "grad_norm": 0.001417685067281127,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 46.0,
      "step": 117
    },
    {
      "epoch": 0.8280701754385965,
      "grad_norm": 0.0014917891239747405,
      "learning_rate": 3.933501846281267e-05,
      "loss": 46.0,
      "step": 118
    },
    {
      "epoch": 0.8350877192982457,
      "grad_norm": 0.0009410835918970406,
      "learning_rate": 3.852880399766243e-05,
      "loss": 46.0,
      "step": 119
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.00041942732059396803,
      "learning_rate": 3.772572564296005e-05,
      "loss": 46.0,
      "step": 120
    },
    {
      "epoch": 0.8491228070175438,
      "grad_norm": 0.0008162674494087696,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 46.0,
      "step": 121
    },
    {
      "epoch": 0.856140350877193,
      "grad_norm": 0.0010323190363124013,
      "learning_rate": 3.612985456190778e-05,
      "loss": 46.0,
      "step": 122
    },
    {
      "epoch": 0.8631578947368421,
      "grad_norm": 0.000985603081062436,
      "learning_rate": 3.533749813077677e-05,
      "loss": 46.0,
      "step": 123
    },
    {
      "epoch": 0.8701754385964913,
      "grad_norm": 0.0010289421770721674,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 46.0,
      "step": 124
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 0.001965671544894576,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 46.0,
      "step": 125
    },
    {
      "epoch": 0.8842105263157894,
      "grad_norm": 0.0017534955404698849,
      "learning_rate": 3.298534127791785e-05,
      "loss": 46.0,
      "step": 126
    },
    {
      "epoch": 0.8912280701754386,
      "grad_norm": 0.0007502880180254579,
      "learning_rate": 3.221030765387417e-05,
      "loss": 46.0,
      "step": 127
    },
    {
      "epoch": 0.8982456140350877,
      "grad_norm": 0.0008839897927828133,
      "learning_rate": 3.144013755408895e-05,
      "loss": 46.0,
      "step": 128
    },
    {
      "epoch": 0.9052631578947369,
      "grad_norm": 0.0008427347638644278,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 46.0,
      "step": 129
    },
    {
      "epoch": 0.9122807017543859,
      "grad_norm": 0.000796147680375725,
      "learning_rate": 2.991522876735154e-05,
      "loss": 46.0,
      "step": 130
    },
    {
      "epoch": 0.9192982456140351,
      "grad_norm": 0.0007270945934578776,
      "learning_rate": 2.916090697523549e-05,
      "loss": 46.0,
      "step": 131
    },
    {
      "epoch": 0.9263157894736842,
      "grad_norm": 0.00118484057020396,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 46.0,
      "step": 132
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.0016901111230254173,
      "learning_rate": 2.766955965735968e-05,
      "loss": 46.0,
      "step": 133
    },
    {
      "epoch": 0.9403508771929825,
      "grad_norm": 0.0017339104088023305,
      "learning_rate": 2.693294185106562e-05,
      "loss": 46.0,
      "step": 134
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 0.002110598608851433,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 46.0,
      "step": 135
    },
    {
      "epoch": 0.9543859649122807,
      "grad_norm": 0.0010102142114192247,
      "learning_rate": 2.547882480847461e-05,
      "loss": 46.0,
      "step": 136
    },
    {
      "epoch": 0.9614035087719298,
      "grad_norm": 0.0015186286764219403,
      "learning_rate": 2.476172311325783e-05,
      "loss": 46.0,
      "step": 137
    },
    {
      "epoch": 0.968421052631579,
      "grad_norm": 0.0026635241229087114,
      "learning_rate": 2.405152131093926e-05,
      "loss": 46.0,
      "step": 138
    },
    {
      "epoch": 0.9754385964912281,
      "grad_norm": 0.0022020465694367886,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 46.0,
      "step": 139
    },
    {
      "epoch": 0.9824561403508771,
      "grad_norm": 0.0016581055242568254,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 46.0,
      "step": 140
    },
    {
      "epoch": 0.9894736842105263,
      "grad_norm": 0.00140385830309242,
      "learning_rate": 2.196424713241637e-05,
      "loss": 46.0,
      "step": 141
    },
    {
      "epoch": 0.9964912280701754,
      "grad_norm": 0.0010630880715325475,
      "learning_rate": 2.128356686585282e-05,
      "loss": 46.0,
      "step": 142
    },
    {
      "epoch": 1.0035087719298246,
      "grad_norm": 0.0014701597392559052,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 143
    },
    {
      "epoch": 1.0105263157894737,
      "grad_norm": 0.0012205225648358464,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 46.0,
      "step": 144
    },
    {
      "epoch": 1.0175438596491229,
      "grad_norm": 0.0011462218826636672,
      "learning_rate": 1.928936436551661e-05,
      "loss": 46.0,
      "step": 145
    },
    {
      "epoch": 1.024561403508772,
      "grad_norm": 0.0011577660916373134,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 46.0,
      "step": 146
    },
    {
      "epoch": 1.0315789473684212,
      "grad_norm": 0.0010796741116791964,
      "learning_rate": 1.800157297483417e-05,
      "loss": 46.0,
      "step": 147
    },
    {
      "epoch": 1.03859649122807,
      "grad_norm": 0.0008427020511589944,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 46.0,
      "step": 148
    },
    {
      "epoch": 1.0456140350877192,
      "grad_norm": 0.0006218829075805843,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 46.0,
      "step": 149
    },
    {
      "epoch": 1.0526315789473684,
      "grad_norm": 0.0017611413495615125,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 46.0,
      "step": 150
    },
    {
      "epoch": 1.0526315789473684,
      "eval_loss": 11.5,
      "eval_runtime": 1.0931,
      "eval_samples_per_second": 219.553,
      "eval_steps_per_second": 54.888,
      "step": 150
    },
    {
      "epoch": 1.0596491228070175,
      "grad_norm": 0.0007416158332489431,
      "learning_rate": 1.553232954407171e-05,
      "loss": 46.0,
      "step": 151
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.0008989135385490954,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 46.0,
      "step": 152
    },
    {
      "epoch": 1.0736842105263158,
      "grad_norm": 0.0009362389100715518,
      "learning_rate": 1.435357758543015e-05,
      "loss": 46.0,
      "step": 153
    },
    {
      "epoch": 1.080701754385965,
      "grad_norm": 0.0018296175403520465,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 46.0,
      "step": 154
    },
    {
      "epoch": 1.087719298245614,
      "grad_norm": 0.002097910502925515,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 46.0,
      "step": 155
    },
    {
      "epoch": 1.0947368421052632,
      "grad_norm": 0.002335738157853484,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 46.0,
      "step": 156
    },
    {
      "epoch": 1.1017543859649124,
      "grad_norm": 0.001017907401546836,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 46.0,
      "step": 157
    },
    {
      "epoch": 1.1087719298245613,
      "grad_norm": 0.0005228331428952515,
      "learning_rate": 1.157994445715706e-05,
      "loss": 46.0,
      "step": 158
    },
    {
      "epoch": 1.1157894736842104,
      "grad_norm": 0.0008692171541042626,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 46.0,
      "step": 159
    },
    {
      "epoch": 1.1228070175438596,
      "grad_norm": 0.0012681116349995136,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 46.0,
      "step": 160
    },
    {
      "epoch": 1.1298245614035087,
      "grad_norm": 0.0009408880723640323,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 46.0,
      "step": 161
    },
    {
      "epoch": 1.1368421052631579,
      "grad_norm": 0.0011926135048270226,
      "learning_rate": 9.549150281252633e-06,
      "loss": 46.0,
      "step": 162
    },
    {
      "epoch": 1.143859649122807,
      "grad_norm": 0.0022217656951397657,
      "learning_rate": 9.068759265665384e-06,
      "loss": 46.0,
      "step": 163
    },
    {
      "epoch": 1.1508771929824562,
      "grad_norm": 0.001954504521563649,
      "learning_rate": 8.599558442598998e-06,
      "loss": 46.0,
      "step": 164
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": 0.0007504344102926552,
      "learning_rate": 8.141676086873572e-06,
      "loss": 46.0,
      "step": 165
    },
    {
      "epoch": 1.1649122807017545,
      "grad_norm": 0.0010206371080130339,
      "learning_rate": 7.695237378953223e-06,
      "loss": 46.0,
      "step": 166
    },
    {
      "epoch": 1.1719298245614036,
      "grad_norm": 0.0026015599723905325,
      "learning_rate": 7.260364370723044e-06,
      "loss": 46.0,
      "step": 167
    },
    {
      "epoch": 1.1789473684210527,
      "grad_norm": 0.0006100122118368745,
      "learning_rate": 6.837175952121306e-06,
      "loss": 46.0,
      "step": 168
    },
    {
      "epoch": 1.1859649122807017,
      "grad_norm": 0.0009925615740939975,
      "learning_rate": 6.425787818636131e-06,
      "loss": 46.0,
      "step": 169
    },
    {
      "epoch": 1.1929824561403508,
      "grad_norm": 0.001434491598047316,
      "learning_rate": 6.026312439675552e-06,
      "loss": 46.0,
      "step": 170
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.0017484030686318874,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 46.0,
      "step": 171
    },
    {
      "epoch": 1.207017543859649,
      "grad_norm": 0.0021861016284674406,
      "learning_rate": 5.263533508961827e-06,
      "loss": 46.0,
      "step": 172
    },
    {
      "epoch": 1.2140350877192982,
      "grad_norm": 0.0030659919138997793,
      "learning_rate": 4.900438493352055e-06,
      "loss": 46.0,
      "step": 173
    },
    {
      "epoch": 1.2210526315789474,
      "grad_norm": 0.0020961263217031956,
      "learning_rate": 4.549673247541875e-06,
      "loss": 46.0,
      "step": 174
    },
    {
      "epoch": 1.2280701754385965,
      "grad_norm": 0.001527472399175167,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 46.0,
      "step": 175
    },
    {
      "epoch": 1.2350877192982457,
      "grad_norm": 0.0017812148435041308,
      "learning_rate": 3.885512251130763e-06,
      "loss": 46.0,
      "step": 176
    },
    {
      "epoch": 1.2421052631578948,
      "grad_norm": 0.002013670513406396,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 46.0,
      "step": 177
    },
    {
      "epoch": 1.2491228070175437,
      "grad_norm": 0.0019801114685833454,
      "learning_rate": 3.271776770026963e-06,
      "loss": 46.0,
      "step": 178
    },
    {
      "epoch": 1.256140350877193,
      "grad_norm": 0.0009696230990812182,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 46.0,
      "step": 179
    },
    {
      "epoch": 1.263157894736842,
      "grad_norm": 0.0014637240674346685,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 46.0,
      "step": 180
    },
    {
      "epoch": 1.2701754385964912,
      "grad_norm": 0.0012320652604103088,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 46.0,
      "step": 181
    },
    {
      "epoch": 1.2771929824561403,
      "grad_norm": 0.0012087133945897222,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 46.0,
      "step": 182
    },
    {
      "epoch": 1.2842105263157895,
      "grad_norm": 0.0008970301132649183,
      "learning_rate": 1.962316193157593e-06,
      "loss": 46.0,
      "step": 183
    },
    {
      "epoch": 1.2912280701754386,
      "grad_norm": 0.0011605366598814726,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 46.0,
      "step": 184
    },
    {
      "epoch": 1.2982456140350878,
      "grad_norm": 0.0019775989931076765,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 46.0,
      "step": 185
    },
    {
      "epoch": 1.305263157894737,
      "grad_norm": 0.0012035091640427709,
      "learning_rate": 1.333670137599713e-06,
      "loss": 46.0,
      "step": 186
    },
    {
      "epoch": 1.312280701754386,
      "grad_norm": 0.001222224673256278,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 46.0,
      "step": 187
    },
    {
      "epoch": 1.3192982456140352,
      "grad_norm": 0.001736512640491128,
      "learning_rate": 9.810017062595322e-07,
      "loss": 46.0,
      "step": 188
    },
    {
      "epoch": 1.3263157894736843,
      "grad_norm": 0.002514014719054103,
      "learning_rate": 8.247462563808817e-07,
      "loss": 46.0,
      "step": 189
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.0021599014289677143,
      "learning_rate": 6.819348298638839e-07,
      "loss": 46.0,
      "step": 190
    },
    {
      "epoch": 1.3403508771929824,
      "grad_norm": 0.0014105592854321003,
      "learning_rate": 5.526064699265753e-07,
      "loss": 46.0,
      "step": 191
    },
    {
      "epoch": 1.3473684210526315,
      "grad_norm": 0.0005556212272495031,
      "learning_rate": 4.367965336512403e-07,
      "loss": 46.0,
      "step": 192
    },
    {
      "epoch": 1.3543859649122807,
      "grad_norm": 0.00064079713774845,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 46.0,
      "step": 193
    },
    {
      "epoch": 1.3614035087719298,
      "grad_norm": 0.0009812917560338974,
      "learning_rate": 2.458548727494292e-07,
      "loss": 46.0,
      "step": 194
    },
    {
      "epoch": 1.368421052631579,
      "grad_norm": 0.000798189954366535,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 46.0,
      "step": 195
    },
    {
      "epoch": 1.3754385964912281,
      "grad_norm": 0.0016942584188655019,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 46.0,
      "step": 196
    },
    {
      "epoch": 1.3824561403508773,
      "grad_norm": 0.0020428404677659273,
      "learning_rate": 6.150154258476315e-08,
      "loss": 46.0,
      "step": 197
    },
    {
      "epoch": 1.3894736842105262,
      "grad_norm": 0.0023198421113193035,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 46.0,
      "step": 198
    },
    {
      "epoch": 1.3964912280701753,
      "grad_norm": 0.0008498338866047561,
      "learning_rate": 6.834750376549792e-09,
      "loss": 46.0,
      "step": 199
    },
    {
      "epoch": 1.4035087719298245,
      "grad_norm": 0.0008746436797082424,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 200
    },
    {
      "epoch": 1.4035087719298245,
      "eval_loss": 11.5,
      "eval_runtime": 1.091,
      "eval_samples_per_second": 219.974,
      "eval_steps_per_second": 54.994,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 32158462771200.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}