{
  "best_metric": 0.07214683294296265,
  "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": 6.132140636444092,
      "learning_rate": 1e-05,
      "loss": 2.8675,
      "step": 1
    },
    {
      "epoch": 0.006734006734006734,
      "eval_loss": 4.463713645935059,
      "eval_runtime": 18.5443,
      "eval_samples_per_second": 13.481,
      "eval_steps_per_second": 3.397,
      "step": 1
    },
    {
      "epoch": 0.013468013468013467,
      "grad_norm": 5.409855842590332,
      "learning_rate": 2e-05,
      "loss": 2.8226,
      "step": 2
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 6.761349201202393,
      "learning_rate": 3e-05,
      "loss": 3.0622,
      "step": 3
    },
    {
      "epoch": 0.026936026936026935,
      "grad_norm": 8.050304412841797,
      "learning_rate": 4e-05,
      "loss": 3.6173,
      "step": 4
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 7.167492866516113,
      "learning_rate": 5e-05,
      "loss": 2.9141,
      "step": 5
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 10.310314178466797,
      "learning_rate": 6e-05,
      "loss": 3.014,
      "step": 6
    },
    {
      "epoch": 0.04713804713804714,
      "grad_norm": 9.393827438354492,
      "learning_rate": 7e-05,
      "loss": 2.1968,
      "step": 7
    },
    {
      "epoch": 0.05387205387205387,
      "grad_norm": 8.703909873962402,
      "learning_rate": 8e-05,
      "loss": 1.2678,
      "step": 8
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 5.206347465515137,
      "learning_rate": 9e-05,
      "loss": 0.5729,
      "step": 9
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 5.4500250816345215,
      "learning_rate": 0.0001,
      "loss": 1.0102,
      "step": 10
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 8.799238204956055,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.8976,
      "step": 11
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 4.803284168243408,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.4592,
      "step": 12
    },
    {
      "epoch": 0.08754208754208755,
      "grad_norm": 11.390392303466797,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.4095,
      "step": 13
    },
    {
      "epoch": 0.09427609427609428,
      "grad_norm": 30.048377990722656,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.7348,
      "step": 14
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 45.86519241333008,
      "learning_rate": 9.98292246503335e-05,
      "loss": 2.3048,
      "step": 15
    },
    {
      "epoch": 0.10774410774410774,
      "grad_norm": 14.224701881408691,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.125,
      "step": 16
    },
    {
      "epoch": 0.11447811447811448,
      "grad_norm": 9.508378982543945,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.3909,
      "step": 17
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 19.514083862304688,
      "learning_rate": 9.956320346634876e-05,
      "loss": 2.1024,
      "step": 18
    },
    {
      "epoch": 0.12794612794612795,
      "grad_norm": 21.436721801757812,
      "learning_rate": 9.944739353007344e-05,
      "loss": 2.413,
      "step": 19
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 13.761083602905273,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.4748,
      "step": 20
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 6.313822269439697,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7081,
      "step": 21
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 12.715644836425781,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.9751,
      "step": 22
    },
    {
      "epoch": 0.15488215488215487,
      "grad_norm": 15.10627269744873,
      "learning_rate": 9.884934153917997e-05,
      "loss": 2.6651,
      "step": 23
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 6.592527866363525,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.505,
      "step": 24
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 6.924004554748535,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.0411,
      "step": 25
    },
    {
      "epoch": 0.1750841750841751,
      "grad_norm": 18.89887809753418,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.6264,
      "step": 26
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 31.06809425354004,
      "learning_rate": 9.803768380684242e-05,
      "loss": 2.6526,
      "step": 27
    },
    {
      "epoch": 0.18855218855218855,
      "grad_norm": 16.651866912841797,
      "learning_rate": 9.780178907671789e-05,
      "loss": 2.31,
      "step": 28
    },
    {
      "epoch": 0.19528619528619529,
      "grad_norm": 20.13156509399414,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9759,
      "step": 29
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 14.252116203308105,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.6914,
      "step": 30
    },
    {
      "epoch": 0.20875420875420875,
      "grad_norm": 13.092583656311035,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.9892,
      "step": 31
    },
    {
      "epoch": 0.21548821548821548,
      "grad_norm": 7.790039539337158,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.2098,
      "step": 32
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 6.479490756988525,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.6916,
      "step": 33
    },
    {
      "epoch": 0.22895622895622897,
      "grad_norm": 4.446484088897705,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.477,
      "step": 34
    },
    {
      "epoch": 0.2356902356902357,
      "grad_norm": 10.597960472106934,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.6131,
      "step": 35
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 42.959205627441406,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.8986,
      "step": 36
    },
    {
      "epoch": 0.24915824915824916,
      "grad_norm": 34.18956756591797,
      "learning_rate": 9.509956150664796e-05,
      "loss": 3.8282,
      "step": 37
    },
    {
      "epoch": 0.2558922558922559,
      "grad_norm": 21.341564178466797,
      "learning_rate": 9.473646649103818e-05,
      "loss": 2.1605,
      "step": 38
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 19.44099998474121,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.6106,
      "step": 39
    },
    {
      "epoch": 0.26936026936026936,
      "grad_norm": 30.0230770111084,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.6303,
      "step": 40
    },
    {
      "epoch": 0.2760942760942761,
      "grad_norm": 19.14362907409668,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.0537,
      "step": 41
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 14.005041122436523,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8299,
      "step": 42
    },
    {
      "epoch": 0.2895622895622896,
      "grad_norm": 13.796131134033203,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7807,
      "step": 43
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 6.612885475158691,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.4645,
      "step": 44
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 3.7716755867004395,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.1261,
      "step": 45
    },
    {
      "epoch": 0.30976430976430974,
      "grad_norm": 1.0441535711288452,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.0327,
      "step": 46
    },
    {
      "epoch": 0.3164983164983165,
      "grad_norm": 0.5548287034034729,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.0089,
      "step": 47
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 5.096100330352783,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.286,
      "step": 48
    },
    {
      "epoch": 0.32996632996632996,
      "grad_norm": 5.335595607757568,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.3464,
      "step": 49
    },
    {
      "epoch": 0.3367003367003367,
      "grad_norm": 2.8638017177581787,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.2527,
      "step": 50
    },
    {
      "epoch": 0.3367003367003367,
      "eval_loss": 0.8852588534355164,
      "eval_runtime": 18.9343,
      "eval_samples_per_second": 13.204,
      "eval_steps_per_second": 3.327,
      "step": 50
    },
    {
      "epoch": 0.3434343434343434,
      "grad_norm": 5.724818706512451,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.3375,
      "step": 51
    },
    {
      "epoch": 0.3501683501683502,
      "grad_norm": 4.980798721313477,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.4263,
      "step": 52
    },
    {
      "epoch": 0.3569023569023569,
      "grad_norm": 28.462345123291016,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.709,
      "step": 53
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 17.771528244018555,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.293,
      "step": 54
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 5.521881103515625,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.1737,
      "step": 55
    },
    {
      "epoch": 0.3771043771043771,
      "grad_norm": 1.8116981983184814,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.013,
      "step": 56
    },
    {
      "epoch": 0.3838383838383838,
      "grad_norm": 8.941155433654785,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.9256,
      "step": 57
    },
    {
      "epoch": 0.39057239057239057,
      "grad_norm": 8.81081485748291,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.8113,
      "step": 58
    },
    {
      "epoch": 0.39730639730639733,
      "grad_norm": 2.942723035812378,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.2816,
      "step": 59
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 1.7295087575912476,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0975,
      "step": 60
    },
    {
      "epoch": 0.4107744107744108,
      "grad_norm": 23.97713851928711,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.4711,
      "step": 61
    },
    {
      "epoch": 0.4175084175084175,
      "grad_norm": 10.074360847473145,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8893,
      "step": 62
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 5.834024906158447,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.4531,
      "step": 63
    },
    {
      "epoch": 0.43097643097643096,
      "grad_norm": 16.764280319213867,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.8713,
      "step": 64
    },
    {
      "epoch": 0.4377104377104377,
      "grad_norm": 8.934554100036621,
      "learning_rate": 8.07106356344834e-05,
      "loss": 1.2704,
      "step": 65
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 9.550911903381348,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.8986,
      "step": 66
    },
    {
      "epoch": 0.4511784511784512,
      "grad_norm": 11.754020690917969,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.7684,
      "step": 67
    },
    {
      "epoch": 0.45791245791245794,
      "grad_norm": 8.972500801086426,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.5583,
      "step": 68
    },
    {
      "epoch": 0.46464646464646464,
      "grad_norm": 6.071847915649414,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.4309,
      "step": 69
    },
    {
      "epoch": 0.4713804713804714,
      "grad_norm": 3.369199275970459,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.258,
      "step": 70
    },
    {
      "epoch": 0.4781144781144781,
      "grad_norm": 1.7296655178070068,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.1155,
      "step": 71
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 7.046713352203369,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.4025,
      "step": 72
    },
    {
      "epoch": 0.49158249158249157,
      "grad_norm": 16.670406341552734,
      "learning_rate": 7.52382768867422e-05,
      "loss": 1.2353,
      "step": 73
    },
    {
      "epoch": 0.4983164983164983,
      "grad_norm": 24.142732620239258,
      "learning_rate": 7.452117519152542e-05,
      "loss": 2.5904,
      "step": 74
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 5.877018451690674,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.774,
      "step": 75
    },
    {
      "epoch": 0.5117845117845118,
      "grad_norm": 4.660501480102539,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.5673,
      "step": 76
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 13.45825481414795,
      "learning_rate": 7.233044034264034e-05,
      "loss": 1.029,
      "step": 77
    },
    {
      "epoch": 0.5252525252525253,
      "grad_norm": 8.603231430053711,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.7161,
      "step": 78
    },
    {
      "epoch": 0.531986531986532,
      "grad_norm": 8.911141395568848,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6858,
      "step": 79
    },
    {
      "epoch": 0.5387205387205387,
      "grad_norm": 15.536916732788086,
      "learning_rate": 7.008477123264848e-05,
      "loss": 1.223,
      "step": 80
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 9.194901466369629,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.6348,
      "step": 81
    },
    {
      "epoch": 0.5521885521885522,
      "grad_norm": 7.485960960388184,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.3077,
      "step": 82
    },
    {
      "epoch": 0.5589225589225589,
      "grad_norm": 3.7320680618286133,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.0908,
      "step": 83
    },
    {
      "epoch": 0.5656565656565656,
      "grad_norm": 2.5001211166381836,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.1943,
      "step": 84
    },
    {
      "epoch": 0.5723905723905723,
      "grad_norm": 2.3888344764709473,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.172,
      "step": 85
    },
    {
      "epoch": 0.5791245791245792,
      "grad_norm": 1.0888677835464478,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.083,
      "step": 86
    },
    {
      "epoch": 0.5858585858585859,
      "grad_norm": 1.3575490713119507,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.0512,
      "step": 87
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 5.783532619476318,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.3206,
      "step": 88
    },
    {
      "epoch": 0.5993265993265994,
      "grad_norm": 9.555509567260742,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.64,
      "step": 89
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 5.8819756507873535,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.2869,
      "step": 90
    },
    {
      "epoch": 0.6127946127946128,
      "grad_norm": 1.8873581886291504,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.1831,
      "step": 91
    },
    {
      "epoch": 0.6195286195286195,
      "grad_norm": 4.715531826019287,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.2994,
      "step": 92
    },
    {
      "epoch": 0.6262626262626263,
      "grad_norm": 4.312103748321533,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.3225,
      "step": 93
    },
    {
      "epoch": 0.632996632996633,
      "grad_norm": 1.6485530138015747,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.0689,
      "step": 94
    },
    {
      "epoch": 0.6397306397306397,
      "grad_norm": 1.439943790435791,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.093,
      "step": 95
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 14.435766220092773,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.375,
      "step": 96
    },
    {
      "epoch": 0.6531986531986532,
      "grad_norm": 10.324198722839355,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.8422,
      "step": 97
    },
    {
      "epoch": 0.6599326599326599,
      "grad_norm": 4.5507731437683105,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.3404,
      "step": 98
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 4.188119888305664,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.3387,
      "step": 99
    },
    {
      "epoch": 0.6734006734006734,
      "grad_norm": 15.163769721984863,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.3711,
      "step": 100
    },
    {
      "epoch": 0.6734006734006734,
      "eval_loss": 0.5619240403175354,
      "eval_runtime": 18.8806,
      "eval_samples_per_second": 13.241,
      "eval_steps_per_second": 3.337,
      "step": 100
    },
    {
      "epoch": 0.6801346801346801,
      "grad_norm": 8.087121963500977,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.7569,
      "step": 101
    },
    {
      "epoch": 0.6868686868686869,
      "grad_norm": 12.076722145080566,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.8047,
      "step": 102
    },
    {
      "epoch": 0.6936026936026936,
      "grad_norm": 8.97599983215332,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.8198,
      "step": 103
    },
    {
      "epoch": 0.7003367003367004,
      "grad_norm": 35.782737731933594,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.5785,
      "step": 104
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 15.844557762145996,
      "learning_rate": 5e-05,
      "loss": 0.4267,
      "step": 105
    },
    {
      "epoch": 0.7138047138047138,
      "grad_norm": 13.940736770629883,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.5837,
      "step": 106
    },
    {
      "epoch": 0.7205387205387206,
      "grad_norm": 5.945451259613037,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.2677,
      "step": 107
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 2.7215940952301025,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.139,
      "step": 108
    },
    {
      "epoch": 0.734006734006734,
      "grad_norm": 2.1255171298980713,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.0989,
      "step": 109
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 4.9710693359375,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.1341,
      "step": 110
    },
    {
      "epoch": 0.7474747474747475,
      "grad_norm": 11.609274864196777,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.7799,
      "step": 111
    },
    {
      "epoch": 0.7542087542087542,
      "grad_norm": 3.79223370552063,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.1633,
      "step": 112
    },
    {
      "epoch": 0.7609427609427609,
      "grad_norm": 3.499357223510742,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.1111,
      "step": 113
    },
    {
      "epoch": 0.7676767676767676,
      "grad_norm": 3.413067579269409,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.1545,
      "step": 114
    },
    {
      "epoch": 0.7744107744107744,
      "grad_norm": 10.537412643432617,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.7944,
      "step": 115
    },
    {
      "epoch": 0.7811447811447811,
      "grad_norm": 5.053773403167725,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.1848,
      "step": 116
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 4.23495626449585,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.7384,
      "step": 117
    },
    {
      "epoch": 0.7946127946127947,
      "grad_norm": 9.184639930725098,
      "learning_rate": 3.933501846281267e-05,
      "loss": 1.1083,
      "step": 118
    },
    {
      "epoch": 0.8013468013468014,
      "grad_norm": 6.5048065185546875,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.5947,
      "step": 119
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 8.406859397888184,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.406,
      "step": 120
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 5.897573471069336,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.2213,
      "step": 121
    },
    {
      "epoch": 0.8215488215488216,
      "grad_norm": 1.6548019647598267,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.0599,
      "step": 122
    },
    {
      "epoch": 0.8282828282828283,
      "grad_norm": 2.9896063804626465,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.0424,
      "step": 123
    },
    {
      "epoch": 0.835016835016835,
      "grad_norm": 1.8859374523162842,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.1116,
      "step": 124
    },
    {
      "epoch": 0.8417508417508418,
      "grad_norm": 6.257426738739014,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.3661,
      "step": 125
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 5.276463508605957,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.1323,
      "step": 126
    },
    {
      "epoch": 0.8552188552188552,
      "grad_norm": 10.643860816955566,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.3371,
      "step": 127
    },
    {
      "epoch": 0.8619528619528619,
      "grad_norm": 8.419933319091797,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.2085,
      "step": 128
    },
    {
      "epoch": 0.8686868686868687,
      "grad_norm": 2.6579275131225586,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.0612,
      "step": 129
    },
    {
      "epoch": 0.8754208754208754,
      "grad_norm": 4.184366703033447,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.0868,
      "step": 130
    },
    {
      "epoch": 0.8821548821548821,
      "grad_norm": 3.3686296939849854,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.2388,
      "step": 131
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 1.4770985841751099,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.1174,
      "step": 132
    },
    {
      "epoch": 0.8956228956228957,
      "grad_norm": 1.966707468032837,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.2126,
      "step": 133
    },
    {
      "epoch": 0.9023569023569024,
      "grad_norm": 7.5656938552856445,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.6449,
      "step": 134
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 10.4683256149292,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.5177,
      "step": 135
    },
    {
      "epoch": 0.9158249158249159,
      "grad_norm": 6.794452667236328,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.2473,
      "step": 136
    },
    {
      "epoch": 0.9225589225589226,
      "grad_norm": 4.865663051605225,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.2372,
      "step": 137
    },
    {
      "epoch": 0.9292929292929293,
      "grad_norm": 8.516963005065918,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.1894,
      "step": 138
    },
    {
      "epoch": 0.936026936026936,
      "grad_norm": 3.9662816524505615,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.3476,
      "step": 139
    },
    {
      "epoch": 0.9427609427609428,
      "grad_norm": 4.168189525604248,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.5468,
      "step": 140
    },
    {
      "epoch": 0.9494949494949495,
      "grad_norm": 5.537124156951904,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.5953,
      "step": 141
    },
    {
      "epoch": 0.9562289562289562,
      "grad_norm": 2.2850406169891357,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.2842,
      "step": 142
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 8.232489585876465,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6115,
      "step": 143
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 5.771413326263428,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.5147,
      "step": 144
    },
    {
      "epoch": 0.9764309764309764,
      "grad_norm": 3.171339750289917,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.3043,
      "step": 145
    },
    {
      "epoch": 0.9831649831649831,
      "grad_norm": 0.9569962024688721,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.0661,
      "step": 146
    },
    {
      "epoch": 0.98989898989899,
      "grad_norm": 0.7393059134483337,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.0497,
      "step": 147
    },
    {
      "epoch": 0.9966329966329966,
      "grad_norm": 4.10557746887207,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.2912,
      "step": 148
    },
    {
      "epoch": 1.005050505050505,
      "grad_norm": 2.197056293487549,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.0544,
      "step": 149
    },
    {
      "epoch": 1.0117845117845117,
      "grad_norm": 1.4618589878082275,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0333,
      "step": 150
    },
    {
      "epoch": 1.0117845117845117,
      "eval_loss": 0.1168971136212349,
      "eval_runtime": 18.874,
      "eval_samples_per_second": 13.246,
      "eval_steps_per_second": 3.338,
      "step": 150
    },
    {
      "epoch": 1.0185185185185186,
      "grad_norm": 1.071506381034851,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.0247,
      "step": 151
    },
    {
      "epoch": 1.0252525252525253,
      "grad_norm": 0.7605236768722534,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.0326,
      "step": 152
    },
    {
      "epoch": 1.031986531986532,
      "grad_norm": 6.588735580444336,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.1684,
      "step": 153
    },
    {
      "epoch": 1.0387205387205387,
      "grad_norm": 1.7316008806228638,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.0558,
      "step": 154
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 0.3867989182472229,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.0048,
      "step": 155
    },
    {
      "epoch": 1.0521885521885521,
      "grad_norm": 0.18220150470733643,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.0037,
      "step": 156
    },
    {
      "epoch": 1.0589225589225588,
      "grad_norm": 0.08184109628200531,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.0019,
      "step": 157
    },
    {
      "epoch": 1.0656565656565657,
      "grad_norm": 0.06923987716436386,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.002,
      "step": 158
    },
    {
      "epoch": 1.0723905723905724,
      "grad_norm": 0.870018720626831,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.0148,
      "step": 159
    },
    {
      "epoch": 1.0791245791245792,
      "grad_norm": 0.47851553559303284,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0099,
      "step": 160
    },
    {
      "epoch": 1.0858585858585859,
      "grad_norm": 0.2693154811859131,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.0069,
      "step": 161
    },
    {
      "epoch": 1.0925925925925926,
      "grad_norm": 4.425756931304932,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2038,
      "step": 162
    },
    {
      "epoch": 1.0993265993265993,
      "grad_norm": 4.47274923324585,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.1408,
      "step": 163
    },
    {
      "epoch": 1.106060606060606,
      "grad_norm": 0.6402637362480164,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.0244,
      "step": 164
    },
    {
      "epoch": 1.112794612794613,
      "grad_norm": 0.36187899112701416,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.0123,
      "step": 165
    },
    {
      "epoch": 1.1195286195286196,
      "grad_norm": 0.2956305146217346,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.01,
      "step": 166
    },
    {
      "epoch": 1.1262626262626263,
      "grad_norm": 0.15192988514900208,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.0045,
      "step": 167
    },
    {
      "epoch": 1.132996632996633,
      "grad_norm": 0.21553927659988403,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0166,
      "step": 168
    },
    {
      "epoch": 1.1397306397306397,
      "grad_norm": 0.8247107267379761,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.0872,
      "step": 169
    },
    {
      "epoch": 1.1464646464646464,
      "grad_norm": 0.47152265906333923,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.053,
      "step": 170
    },
    {
      "epoch": 1.1531986531986531,
      "grad_norm": 0.5226501226425171,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.0408,
      "step": 171
    },
    {
      "epoch": 1.15993265993266,
      "grad_norm": 4.133157253265381,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.1229,
      "step": 172
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 3.255939483642578,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.3159,
      "step": 173
    },
    {
      "epoch": 1.1734006734006734,
      "grad_norm": 2.623201847076416,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.221,
      "step": 174
    },
    {
      "epoch": 1.1801346801346801,
      "grad_norm": 2.4918131828308105,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.2262,
      "step": 175
    },
    {
      "epoch": 1.1868686868686869,
      "grad_norm": 3.277465343475342,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.1624,
      "step": 176
    },
    {
      "epoch": 1.1936026936026936,
      "grad_norm": 1.840551495552063,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.2623,
      "step": 177
    },
    {
      "epoch": 1.2003367003367003,
      "grad_norm": 6.421799182891846,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.4778,
      "step": 178
    },
    {
      "epoch": 1.2070707070707072,
      "grad_norm": 1.7253897190093994,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.2026,
      "step": 179
    },
    {
      "epoch": 1.2138047138047139,
      "grad_norm": 1.2812747955322266,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.1483,
      "step": 180
    },
    {
      "epoch": 1.2205387205387206,
      "grad_norm": 1.8860992193222046,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.1351,
      "step": 181
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 1.5098795890808105,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.1161,
      "step": 182
    },
    {
      "epoch": 1.234006734006734,
      "grad_norm": 1.1958431005477905,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.0601,
      "step": 183
    },
    {
      "epoch": 1.2407407407407407,
      "grad_norm": 0.6514748930931091,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.035,
      "step": 184
    },
    {
      "epoch": 1.2474747474747474,
      "grad_norm": 2.3137927055358887,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.1517,
      "step": 185
    },
    {
      "epoch": 1.2542087542087543,
      "grad_norm": 2.2861926555633545,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.1285,
      "step": 186
    },
    {
      "epoch": 1.2609427609427608,
      "grad_norm": 0.43230536580085754,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.0067,
      "step": 187
    },
    {
      "epoch": 1.2676767676767677,
      "grad_norm": 0.13292136788368225,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.0031,
      "step": 188
    },
    {
      "epoch": 1.2744107744107744,
      "grad_norm": 0.2081347107887268,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.0048,
      "step": 189
    },
    {
      "epoch": 1.2811447811447811,
      "grad_norm": 0.1091417670249939,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.003,
      "step": 190
    },
    {
      "epoch": 1.2878787878787878,
      "grad_norm": 0.18841508030891418,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.0049,
      "step": 191
    },
    {
      "epoch": 1.2946127946127945,
      "grad_norm": 0.027866071090102196,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0005,
      "step": 192
    },
    {
      "epoch": 1.3013468013468015,
      "grad_norm": 0.028528451919555664,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.0006,
      "step": 193
    },
    {
      "epoch": 1.308080808080808,
      "grad_norm": 0.0292882788926363,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0005,
      "step": 194
    },
    {
      "epoch": 1.3148148148148149,
      "grad_norm": 0.030428724363446236,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.0006,
      "step": 195
    },
    {
      "epoch": 1.3215488215488216,
      "grad_norm": 0.05487258359789848,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0017,
      "step": 196
    },
    {
      "epoch": 1.3282828282828283,
      "grad_norm": 0.2630290985107422,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.0051,
      "step": 197
    },
    {
      "epoch": 1.335016835016835,
      "grad_norm": 1.5410749912261963,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0196,
      "step": 198
    },
    {
      "epoch": 1.3417508417508417,
      "grad_norm": 0.5335988402366638,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.0093,
      "step": 199
    },
    {
      "epoch": 1.3484848484848486,
      "grad_norm": 0.08413808047771454,
      "learning_rate": 0.0,
      "loss": 0.003,
      "step": 200
    },
    {
      "epoch": 1.3484848484848486,
      "eval_loss": 0.07214683294296265,
      "eval_runtime": 18.8704,
      "eval_samples_per_second": 13.248,
      "eval_steps_per_second": 3.339,
      "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
}