{
  "best_metric": 0.06836096197366714,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.3484848484848486,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006734006734006734,
      "grad_norm": 6.07405948638916,
      "learning_rate": 1e-05,
      "loss": 2.8675,
      "step": 1
    },
    {
      "epoch": 0.006734006734006734,
      "eval_loss": 4.463713645935059,
      "eval_runtime": 18.5834,
      "eval_samples_per_second": 13.453,
      "eval_steps_per_second": 3.39,
      "step": 1
    },
    {
      "epoch": 0.013468013468013467,
      "grad_norm": 5.357595443725586,
      "learning_rate": 2e-05,
      "loss": 2.8226,
      "step": 2
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 6.693935871124268,
      "learning_rate": 3e-05,
      "loss": 3.0659,
      "step": 3
    },
    {
      "epoch": 0.026936026936026935,
      "grad_norm": 8.008469581604004,
      "learning_rate": 4e-05,
      "loss": 3.6189,
      "step": 4
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 7.128346920013428,
      "learning_rate": 5e-05,
      "loss": 2.9142,
      "step": 5
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 10.227160453796387,
      "learning_rate": 6e-05,
      "loss": 3.0143,
      "step": 6
    },
    {
      "epoch": 0.04713804713804714,
      "grad_norm": 9.440218925476074,
      "learning_rate": 7e-05,
      "loss": 2.2017,
      "step": 7
    },
    {
      "epoch": 0.05387205387205387,
      "grad_norm": 8.69577407836914,
      "learning_rate": 8e-05,
      "loss": 1.271,
      "step": 8
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 5.280088424682617,
      "learning_rate": 9e-05,
      "loss": 0.5759,
      "step": 9
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 5.407863140106201,
      "learning_rate": 0.0001,
      "loss": 1.0077,
      "step": 10
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 8.638448715209961,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.8908,
      "step": 11
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 4.7006731033325195,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.4552,
      "step": 12
    },
    {
      "epoch": 0.08754208754208755,
      "grad_norm": 10.99746322631836,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.3914,
      "step": 13
    },
    {
      "epoch": 0.09427609427609428,
      "grad_norm": 31.76006507873535,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.7439,
      "step": 14
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 47.447818756103516,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.3914,
      "step": 15
    },
    {
      "epoch": 0.10774410774410774,
      "grad_norm": 14.401652336120605,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.1671,
      "step": 16
    },
    {
      "epoch": 0.11447811447811448,
      "grad_norm": 10.397513389587402,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.3987,
      "step": 17
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 20.854961395263672,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.1551,
      "step": 18
    },
    {
      "epoch": 0.12794612794612795,
      "grad_norm": 22.479373931884766,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.499,
      "step": 19
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 14.431221961975098,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.5327,
      "step": 20
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 6.367738723754883,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.727,
      "step": 21
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 13.41352367401123,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.9818,
      "step": 22
    },
    {
      "epoch": 0.15488215488215487,
      "grad_norm": 15.608229637145996,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.6623,
      "step": 23
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 7.56013822555542,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.5318,
      "step": 24
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 8.449981689453125,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.0854,
      "step": 25
    },
    {
      "epoch": 0.1750841750841751,
      "grad_norm": 19.131107330322266,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.6134,
      "step": 26
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 30.024925231933594,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.5722,
      "step": 27
    },
    {
      "epoch": 0.18855218855218855,
      "grad_norm": 16.029897689819336,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.2676,
      "step": 28
    },
    {
      "epoch": 0.19528619528619529,
      "grad_norm": 18.885520935058594,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9975,
      "step": 29
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 13.079731941223145,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.6918,
      "step": 30
    },
    {
      "epoch": 0.20875420875420875,
      "grad_norm": 12.65259838104248,
      "learning_rate": 9.701596950580806e-05,
      "loss": 2.0133,
      "step": 31
    },
    {
      "epoch": 0.21548821548821548,
      "grad_norm": 7.153381824493408,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.2373,
      "step": 32
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 6.592780113220215,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7422,
      "step": 33
    },
    {
      "epoch": 0.22895622895622897,
      "grad_norm": 4.040820598602295,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.4954,
      "step": 34
    },
    {
      "epoch": 0.2356902356902357,
      "grad_norm": 10.684036254882812,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.6209,
      "step": 35
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 42.659934997558594,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.7747,
      "step": 36
    },
    {
      "epoch": 0.24915824915824916,
      "grad_norm": 34.38843536376953,
      "learning_rate": 9.509956150664796e-05,
      "loss": 3.6641,
      "step": 37
    },
    {
      "epoch": 0.2558922558922559,
      "grad_norm": 27.4233341217041,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.3805,
      "step": 38
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 20.68123435974121,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.7897,
      "step": 39
    },
    {
      "epoch": 0.26936026936026936,
      "grad_norm": 27.30316925048828,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.7781,
      "step": 40
    },
    {
      "epoch": 0.2760942760942761,
      "grad_norm": 21.985980987548828,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.2172,
      "step": 41
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 17.444570541381836,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9672,
      "step": 42
    },
    {
      "epoch": 0.2895622895622896,
      "grad_norm": 15.064393043518066,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.0241,
      "step": 43
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 6.0796990394592285,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.439,
      "step": 44
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 2.4602503776550293,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.0886,
      "step": 45
    },
    {
      "epoch": 0.30976430976430974,
      "grad_norm": 0.6047365069389343,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.0202,
      "step": 46
    },
    {
      "epoch": 0.3164983164983165,
      "grad_norm": 0.3158435821533203,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0061,
      "step": 47
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 2.975714683532715,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2098,
      "step": 48
    },
    {
      "epoch": 0.32996632996632996,
      "grad_norm": 3.283388376235962,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.2562,
      "step": 49
    },
    {
      "epoch": 0.3367003367003367,
      "grad_norm": 2.497776746749878,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.2065,
      "step": 50
    },
    {
      "epoch": 0.3367003367003367,
      "eval_loss": 0.8457704782485962,
      "eval_runtime": 18.9108,
      "eval_samples_per_second": 13.22,
      "eval_steps_per_second": 3.331,
      "step": 50
    },
    {
      "epoch": 0.3434343434343434,
      "grad_norm": 5.373112678527832,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.2834,
      "step": 51
    },
    {
      "epoch": 0.3501683501683502,
      "grad_norm": 5.381284713745117,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.4121,
      "step": 52
    },
    {
      "epoch": 0.3569023569023569,
      "grad_norm": 18.220869064331055,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.8005,
      "step": 53
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 14.743596076965332,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.7095,
      "step": 54
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 10.073766708374023,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.3236,
      "step": 55
    },
    {
      "epoch": 0.3771043771043771,
      "grad_norm": 6.281829833984375,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.028,
      "step": 56
    },
    {
      "epoch": 0.3838383838383838,
      "grad_norm": 7.684318542480469,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7977,
      "step": 57
    },
    {
      "epoch": 0.39057239057239057,
      "grad_norm": 5.156148433685303,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.3209,
      "step": 58
    },
    {
      "epoch": 0.39730639730639733,
      "grad_norm": 2.0325448513031006,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.1417,
      "step": 59
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 1.1448686122894287,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0491,
      "step": 60
    },
    {
      "epoch": 0.4107744107744108,
      "grad_norm": 25.814224243164062,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.9241,
      "step": 61
    },
    {
      "epoch": 0.4175084175084175,
      "grad_norm": 12.02128791809082,
      "learning_rate": 8.262928807620843e-05,
      "loss": 1.2726,
      "step": 62
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 7.019981384277344,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7207,
      "step": 63
    },
    {
      "epoch": 0.43097643097643096,
      "grad_norm": 24.718162536621094,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.9373,
      "step": 64
    },
    {
      "epoch": 0.4377104377104377,
      "grad_norm": 10.742963790893555,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.4919,
      "step": 65
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 9.399407386779785,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.9248,
      "step": 66
    },
    {
      "epoch": 0.4511784511784512,
      "grad_norm": 11.707751274108887,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7539,
      "step": 67
    },
    {
      "epoch": 0.45791245791245794,
      "grad_norm": 7.641355991363525,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.5246,
      "step": 68
    },
    {
      "epoch": 0.46464646464646464,
      "grad_norm": 4.6552605628967285,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.3858,
      "step": 69
    },
    {
      "epoch": 0.4713804713804714,
      "grad_norm": 4.222383975982666,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.2244,
      "step": 70
    },
    {
      "epoch": 0.4781144781144781,
      "grad_norm": 1.4126560688018799,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.098,
      "step": 71
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 10.674031257629395,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.5692,
      "step": 72
    },
    {
      "epoch": 0.49158249158249157,
      "grad_norm": 13.465852737426758,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.1135,
      "step": 73
    },
    {
      "epoch": 0.4983164983164983,
      "grad_norm": 19.84742546081543,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.91,
      "step": 74
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 7.916626453399658,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.0617,
      "step": 75
    },
    {
      "epoch": 0.5117845117845118,
      "grad_norm": 5.618990898132324,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.7292,
      "step": 76
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 11.931623458862305,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.1185,
      "step": 77
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 10.379307746887207,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.8425,
      "step": 78
    },
    {
      "epoch": 0.531986531986532,
      "grad_norm": 7.273519992828369,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7785,
      "step": 79
    },
    {
      "epoch": 0.5387205387205387,
      "grad_norm": 19.81070327758789,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.9766,
      "step": 80
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 12.640477180480957,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.8389,
      "step": 81
    },
    {
      "epoch": 0.5521885521885522,
      "grad_norm": 6.227380752563477,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3501,
      "step": 82
    },
    {
      "epoch": 0.5589225589225589,
      "grad_norm": 4.514026165008545,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.1479,
      "step": 83
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 5.958155632019043,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.3406,
      "step": 84
    },
    {
      "epoch": 0.5723905723905723,
      "grad_norm": 4.188724994659424,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.3617,
      "step": 85
    },
    {
      "epoch": 0.5791245791245792,
      "grad_norm": 2.480914831161499,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2277,
      "step": 86
    },
    {
      "epoch": 0.5858585858585859,
      "grad_norm": 2.2869393825531006,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.1159,
      "step": 87
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 4.936868190765381,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.3539,
      "step": 88
    },
    {
      "epoch": 0.5993265993265994,
      "grad_norm": 8.723807334899902,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.5773,
      "step": 89
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 5.4641828536987305,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.2134,
      "step": 90
    },
    {
      "epoch": 0.6127946127946128,
      "grad_norm": 1.001682162284851,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.0464,
      "step": 91
    },
    {
      "epoch": 0.6195286195286195,
      "grad_norm": 4.068861961364746,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.4054,
      "step": 92
    },
    {
      "epoch": 0.6262626262626263,
      "grad_norm": 4.326088905334473,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.4375,
      "step": 93
    },
    {
      "epoch": 0.632996632996633,
      "grad_norm": 2.2480709552764893,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0747,
      "step": 94
    },
    {
      "epoch": 0.6397306397306397,
      "grad_norm": 1.390701174736023,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.0962,
      "step": 95
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 4.089734077453613,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.3238,
      "step": 96
    },
    {
      "epoch": 0.6531986531986532,
      "grad_norm": 7.0590996742248535,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7572,
      "step": 97
    },
    {
      "epoch": 0.6599326599326599,
      "grad_norm": 4.033264636993408,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.4239,
      "step": 98
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 4.695234775543213,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.4603,
      "step": 99
    },
    {
      "epoch": 0.6734006734006734,
      "grad_norm": 10.34823989868164,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.9534,
      "step": 100
    },
    {
      "epoch": 0.6734006734006734,
      "eval_loss": 0.513434886932373,
      "eval_runtime": 18.954,
      "eval_samples_per_second": 13.19,
      "eval_steps_per_second": 3.324,
      "step": 100
    },
    {
      "epoch": 0.6801346801346801,
      "grad_norm": 9.730579376220703,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.826,
      "step": 101
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 6.5242695808410645,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5181,
      "step": 102
    },
    {
      "epoch": 0.6936026936026936,
      "grad_norm": 8.60515308380127,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.6654,
      "step": 103
    },
    {
      "epoch": 0.7003367003367004,
      "grad_norm": 5.914134979248047,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.3439,
      "step": 104
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 6.541567802429199,
      "learning_rate": 5e-05,
      "loss": 0.2631,
      "step": 105
    },
    {
      "epoch": 0.7138047138047138,
      "grad_norm": 8.315234184265137,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.443,
      "step": 106
    },
    {
      "epoch": 0.7205387205387206,
      "grad_norm": 4.798381805419922,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.2272,
      "step": 107
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 2.8570470809936523,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.151,
      "step": 108
    },
    {
      "epoch": 0.734006734006734,
      "grad_norm": 3.9313015937805176,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.1467,
      "step": 109
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 8.422281265258789,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.3285,
      "step": 110
    },
    {
      "epoch": 0.7474747474747475,
      "grad_norm": 14.415046691894531,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9541,
      "step": 111
    },
    {
      "epoch": 0.7542087542087542,
      "grad_norm": 4.40872859954834,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.2606,
      "step": 112
    },
    {
      "epoch": 0.7609427609427609,
      "grad_norm": 3.593428134918213,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.2185,
      "step": 113
    },
    {
      "epoch": 0.7676767676767676,
      "grad_norm": 5.342737197875977,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.2744,
      "step": 114
    },
    {
      "epoch": 0.7744107744107744,
      "grad_norm": 9.533066749572754,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.8088,
      "step": 115
    },
    {
      "epoch": 0.7811447811447811,
      "grad_norm": 6.748232841491699,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.1951,
      "step": 116
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 4.205438613891602,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.6739,
      "step": 117
    },
    {
      "epoch": 0.7946127946127947,
      "grad_norm": 9.197023391723633,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.9677,
      "step": 118
    },
    {
      "epoch": 0.8013468013468014,
      "grad_norm": 6.26127290725708,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.3475,
      "step": 119
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 8.797593116760254,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.1827,
      "step": 120
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 1.0028709173202515,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.0185,
      "step": 121
    },
    {
      "epoch": 0.8215488215488216,
      "grad_norm": 5.19990348815918,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.2898,
      "step": 122
    },
    {
      "epoch": 0.8282828282828283,
      "grad_norm": 7.094882965087891,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.2851,
      "step": 123
    },
    {
      "epoch": 0.835016835016835,
      "grad_norm": 2.8967487812042236,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1538,
      "step": 124
    },
    {
      "epoch": 0.8417508417508418,
      "grad_norm": 4.530605316162109,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.107,
      "step": 125
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 8.84570598602295,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.2952,
      "step": 126
    },
    {
      "epoch": 0.8552188552188552,
      "grad_norm": 31.858335494995117,
      "learning_rate": 3.221030765387417e-05,
      "loss": 1.2982,
      "step": 127
    },
    {
      "epoch": 0.8619528619528619,
      "grad_norm": 14.406533241271973,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.8527,
      "step": 128
    },
    {
      "epoch": 0.8686868686868687,
      "grad_norm": 15.123346328735352,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.2729,
      "step": 129
    },
    {
      "epoch": 0.8754208754208754,
      "grad_norm": 6.778622627258301,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.1981,
      "step": 130
    },
    {
      "epoch": 0.8821548821548821,
      "grad_norm": 5.562117099761963,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.2807,
      "step": 131
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.8718782663345337,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.1479,
      "step": 132
    },
    {
      "epoch": 0.8956228956228957,
      "grad_norm": 1.972672462463379,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.1604,
      "step": 133
    },
    {
      "epoch": 0.9023569023569024,
      "grad_norm": 6.924598217010498,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.4563,
      "step": 134
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 7.300309181213379,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.4307,
      "step": 135
    },
    {
      "epoch": 0.9158249158249159,
      "grad_norm": 4.754110813140869,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.2378,
      "step": 136
    },
    {
      "epoch": 0.9225589225589226,
      "grad_norm": 4.436905860900879,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.2473,
      "step": 137
    },
    {
      "epoch": 0.9292929292929293,
      "grad_norm": 13.839972496032715,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.2927,
      "step": 138
    },
    {
      "epoch": 0.936026936026936,
      "grad_norm": 5.017172336578369,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.3389,
      "step": 139
    },
    {
      "epoch": 0.9427609427609428,
      "grad_norm": 8.623014450073242,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 1.0407,
      "step": 140
    },
    {
      "epoch": 0.9494949494949495,
      "grad_norm": 9.330912590026855,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.6932,
      "step": 141
    },
    {
      "epoch": 0.9562289562289562,
      "grad_norm": 2.4931304454803467,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.232,
      "step": 142
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 4.584961891174316,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2462,
      "step": 143
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 2.8860232830047607,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.1719,
      "step": 144
    },
    {
      "epoch": 0.9764309764309764,
      "grad_norm": 2.347853422164917,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.1454,
      "step": 145
    },
    {
      "epoch": 0.9831649831649831,
      "grad_norm": 3.1085243225097656,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.1037,
      "step": 146
    },
    {
      "epoch": 0.98989898989899,
      "grad_norm": 1.3002732992172241,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0651,
      "step": 147
    },
    {
      "epoch": 0.9966329966329966,
      "grad_norm": 8.017468452453613,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.3988,
      "step": 148
    },
    {
      "epoch": 1.005050505050505,
      "grad_norm": 2.016037940979004,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0869,
      "step": 149
    },
    {
      "epoch": 1.0117845117845117,
      "grad_norm": 3.81487774848938,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0933,
      "step": 150
    },
    {
      "epoch": 1.0117845117845117,
      "eval_loss": 0.14942903816699982,
      "eval_runtime": 19.0456,
      "eval_samples_per_second": 13.126,
      "eval_steps_per_second": 3.308,
      "step": 150
    },
    {
      "epoch": 1.0185185185185186,
      "grad_norm": 4.189632415771484,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.4209,
      "step": 151
    },
    {
      "epoch": 1.0252525252525253,
      "grad_norm": 2.9430246353149414,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.1492,
      "step": 152
    },
    {
      "epoch": 1.031986531986532,
      "grad_norm": 7.276577472686768,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.1485,
      "step": 153
    },
    {
      "epoch": 1.0387205387205387,
      "grad_norm": 1.741584062576294,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.0782,
      "step": 154
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 2.1479732990264893,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.0254,
      "step": 155
    },
    {
      "epoch": 1.0521885521885521,
      "grad_norm": 0.7260915637016296,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.006,
      "step": 156
    },
    {
      "epoch": 1.0589225589225588,
      "grad_norm": 0.05938274413347244,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.0008,
      "step": 157
    },
    {
      "epoch": 1.0656565656565657,
      "grad_norm": 0.03683267906308174,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0007,
      "step": 158
    },
    {
      "epoch": 1.0723905723905724,
      "grad_norm": 0.891275942325592,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.0135,
      "step": 159
    },
    {
      "epoch": 1.0791245791245792,
      "grad_norm": 0.41197118163108826,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0135,
      "step": 160
    },
    {
      "epoch": 1.0858585858585859,
      "grad_norm": 0.29838982224464417,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.0123,
      "step": 161
    },
    {
      "epoch": 1.0925925925925926,
      "grad_norm": 3.438004493713379,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.1435,
      "step": 162
    },
    {
      "epoch": 1.0993265993265993,
      "grad_norm": 3.2176132202148438,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.1184,
      "step": 163
    },
    {
      "epoch": 1.106060606060606,
      "grad_norm": 0.7900349497795105,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.0194,
      "step": 164
    },
    {
      "epoch": 1.112794612794613,
      "grad_norm": 1.3965411186218262,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0136,
      "step": 165
    },
    {
      "epoch": 1.1195286195286196,
      "grad_norm": 0.535775363445282,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.0056,
      "step": 166
    },
    {
      "epoch": 1.1262626262626263,
      "grad_norm": 0.24931006133556366,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.0055,
      "step": 167
    },
    {
      "epoch": 1.132996632996633,
      "grad_norm": 0.3719997704029083,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0183,
      "step": 168
    },
    {
      "epoch": 1.1397306397306397,
      "grad_norm": 1.9222278594970703,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.0818,
      "step": 169
    },
    {
      "epoch": 1.1464646464646464,
      "grad_norm": 0.8664422035217285,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0447,
      "step": 170
    },
    {
      "epoch": 1.1531986531986531,
      "grad_norm": 0.6781785488128662,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0339,
      "step": 171
    },
    {
      "epoch": 1.15993265993266,
      "grad_norm": 1.8942959308624268,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.1028,
      "step": 172
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 2.715618371963501,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.2262,
      "step": 173
    },
    {
      "epoch": 1.1734006734006734,
      "grad_norm": 2.206360340118408,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.1674,
      "step": 174
    },
    {
      "epoch": 1.1801346801346801,
      "grad_norm": 2.8105151653289795,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.1941,
      "step": 175
    },
    {
      "epoch": 1.1868686868686869,
      "grad_norm": 2.0999600887298584,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.1441,
      "step": 176
    },
    {
      "epoch": 1.1936026936026936,
      "grad_norm": 3.539193630218506,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.2769,
      "step": 177
    },
    {
      "epoch": 1.2003367003367003,
      "grad_norm": 6.587567329406738,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.485,
      "step": 178
    },
    {
      "epoch": 1.2070707070707072,
      "grad_norm": 2.510993003845215,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.2315,
      "step": 179
    },
    {
      "epoch": 1.2138047138047139,
      "grad_norm": 1.8116987943649292,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.1603,
      "step": 180
    },
    {
      "epoch": 1.2205387205387206,
      "grad_norm": 2.0455965995788574,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.1027,
      "step": 181
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 1.821972131729126,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.097,
      "step": 182
    },
    {
      "epoch": 1.234006734006734,
      "grad_norm": 1.7761726379394531,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.082,
      "step": 183
    },
    {
      "epoch": 1.2407407407407407,
      "grad_norm": 0.9251540303230286,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0481,
      "step": 184
    },
    {
      "epoch": 1.2474747474747474,
      "grad_norm": 3.9761788845062256,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.1979,
      "step": 185
    },
    {
      "epoch": 1.2542087542087543,
      "grad_norm": 2.820085287094116,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.1408,
      "step": 186
    },
    {
      "epoch": 1.2609427609427608,
      "grad_norm": 0.3278276324272156,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0093,
      "step": 187
    },
    {
      "epoch": 1.2676767676767677,
      "grad_norm": 1.6053980588912964,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.035,
      "step": 188
    },
    {
      "epoch": 1.2744107744107744,
      "grad_norm": 0.6956444978713989,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.015,
      "step": 189
    },
    {
      "epoch": 1.2811447811447811,
      "grad_norm": 0.27054452896118164,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.0115,
      "step": 190
    },
    {
      "epoch": 1.2878787878787878,
      "grad_norm": 0.4340273439884186,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.0158,
      "step": 191
    },
    {
      "epoch": 1.2946127946127945,
      "grad_norm": 0.03331722691655159,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0005,
      "step": 192
    },
    {
      "epoch": 1.3013468013468015,
      "grad_norm": 0.03457731008529663,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.0006,
      "step": 193
    },
    {
      "epoch": 1.308080808080808,
      "grad_norm": 0.03270023688673973,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0005,
      "step": 194
    },
    {
      "epoch": 1.3148148148148149,
      "grad_norm": 0.033798910677433014,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0005,
      "step": 195
    },
    {
      "epoch": 1.3215488215488216,
      "grad_norm": 0.6633827686309814,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0126,
      "step": 196
    },
    {
      "epoch": 1.3282828282828283,
      "grad_norm": 0.4700707197189331,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0119,
      "step": 197
    },
    {
      "epoch": 1.335016835016835,
      "grad_norm": 0.2931622266769409,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0068,
      "step": 198
    },
    {
      "epoch": 1.3417508417508417,
      "grad_norm": 0.4666554033756256,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.0086,
      "step": 199
    },
    {
      "epoch": 1.3484848484848486,
      "grad_norm": 0.5312454700469971,
      "learning_rate": 0.0,
      "loss": 0.0062,
      "step": 200
    },
    {
      "epoch": 1.3484848484848486,
      "eval_loss": 0.06836096197366714,
      "eval_runtime": 18.98,
      "eval_samples_per_second": 13.172,
      "eval_steps_per_second": 3.319,
      "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.017027157491712e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}