{
  "best_metric": 0.7370568513870239,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.3367003367003367,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016835016835016834,
      "grad_norm": 4.319352149963379,
      "learning_rate": 1e-05,
      "loss": 1.8327,
      "step": 1
    },
    {
      "epoch": 0.0016835016835016834,
      "eval_loss": 2.372297525405884,
      "eval_runtime": 17.2412,
      "eval_samples_per_second": 58.059,
      "eval_steps_per_second": 14.558,
      "step": 1
    },
    {
      "epoch": 0.003367003367003367,
      "grad_norm": 4.540854454040527,
      "learning_rate": 2e-05,
      "loss": 1.9518,
      "step": 2
    },
    {
      "epoch": 0.005050505050505051,
      "grad_norm": 4.712023735046387,
      "learning_rate": 3e-05,
      "loss": 1.9915,
      "step": 3
    },
    {
      "epoch": 0.006734006734006734,
      "grad_norm": 4.823323726654053,
      "learning_rate": 4e-05,
      "loss": 1.9523,
      "step": 4
    },
    {
      "epoch": 0.008417508417508417,
      "grad_norm": 4.232856750488281,
      "learning_rate": 5e-05,
      "loss": 1.7925,
      "step": 5
    },
    {
      "epoch": 0.010101010101010102,
      "grad_norm": 4.345725059509277,
      "learning_rate": 6e-05,
      "loss": 1.5668,
      "step": 6
    },
    {
      "epoch": 0.011784511784511785,
      "grad_norm": 5.355642318725586,
      "learning_rate": 7e-05,
      "loss": 1.465,
      "step": 7
    },
    {
      "epoch": 0.013468013468013467,
      "grad_norm": 4.013998508453369,
      "learning_rate": 8e-05,
      "loss": 1.3113,
      "step": 8
    },
    {
      "epoch": 0.015151515151515152,
      "grad_norm": 3.272343873977661,
      "learning_rate": 9e-05,
      "loss": 1.1731,
      "step": 9
    },
    {
      "epoch": 0.016835016835016835,
      "grad_norm": 3.523111581802368,
      "learning_rate": 0.0001,
      "loss": 1.2607,
      "step": 10
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 3.553222417831421,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.1841,
      "step": 11
    },
    {
      "epoch": 0.020202020202020204,
      "grad_norm": 2.7934727668762207,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.1874,
      "step": 12
    },
    {
      "epoch": 0.021885521885521887,
      "grad_norm": 2.705348253250122,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.1013,
      "step": 13
    },
    {
      "epoch": 0.02356902356902357,
      "grad_norm": 2.504117012023926,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.1668,
      "step": 14
    },
    {
      "epoch": 0.025252525252525252,
      "grad_norm": 2.309999942779541,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8765,
      "step": 15
    },
    {
      "epoch": 0.026936026936026935,
      "grad_norm": 2.465071439743042,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.066,
      "step": 16
    },
    {
      "epoch": 0.02861952861952862,
      "grad_norm": 2.1769981384277344,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9792,
      "step": 17
    },
    {
      "epoch": 0.030303030303030304,
      "grad_norm": 2.3015010356903076,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.9079,
      "step": 18
    },
    {
      "epoch": 0.03198653198653199,
      "grad_norm": 2.195624589920044,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.981,
      "step": 19
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 2.0270633697509766,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.0297,
      "step": 20
    },
    {
      "epoch": 0.03535353535353535,
      "grad_norm": 2.019474744796753,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.9251,
      "step": 21
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 1.9527926445007324,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.9565,
      "step": 22
    },
    {
      "epoch": 0.03872053872053872,
      "grad_norm": 2.0163164138793945,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.8976,
      "step": 23
    },
    {
      "epoch": 0.04040404040404041,
      "grad_norm": 1.986339807510376,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.8554,
      "step": 24
    },
    {
      "epoch": 0.04208754208754209,
      "grad_norm": 1.735572338104248,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.7782,
      "step": 25
    },
    {
      "epoch": 0.04377104377104377,
      "grad_norm": 1.9113609790802002,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.762,
      "step": 26
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 2.2292163372039795,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8647,
      "step": 27
    },
    {
      "epoch": 0.04713804713804714,
      "grad_norm": 2.1260342597961426,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.9383,
      "step": 28
    },
    {
      "epoch": 0.04882154882154882,
      "grad_norm": 2.054738998413086,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.9177,
      "step": 29
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 2.2084426879882812,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9378,
      "step": 30
    },
    {
      "epoch": 0.05218855218855219,
      "grad_norm": 1.9933043718338013,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.8784,
      "step": 31
    },
    {
      "epoch": 0.05387205387205387,
      "grad_norm": 2.025364637374878,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.9158,
      "step": 32
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 1.986376166343689,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8355,
      "step": 33
    },
    {
      "epoch": 0.05723905723905724,
      "grad_norm": 1.9484467506408691,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.9356,
      "step": 34
    },
    {
      "epoch": 0.058922558922558925,
      "grad_norm": 1.6905690431594849,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8482,
      "step": 35
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 1.9445687532424927,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.892,
      "step": 36
    },
    {
      "epoch": 0.06228956228956229,
      "grad_norm": 1.8993502855300903,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.835,
      "step": 37
    },
    {
      "epoch": 0.06397306397306397,
      "grad_norm": 1.8194026947021484,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8822,
      "step": 38
    },
    {
      "epoch": 0.06565656565656566,
      "grad_norm": 1.958947777748108,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.8508,
      "step": 39
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 1.8258440494537354,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.824,
      "step": 40
    },
    {
      "epoch": 0.06902356902356903,
      "grad_norm": 2.006749391555786,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.9773,
      "step": 41
    },
    {
      "epoch": 0.0707070707070707,
      "grad_norm": 1.9754902124404907,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7579,
      "step": 42
    },
    {
      "epoch": 0.0723905723905724,
      "grad_norm": 1.9275133609771729,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8001,
      "step": 43
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 2.120222330093384,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.8203,
      "step": 44
    },
    {
      "epoch": 0.07575757575757576,
      "grad_norm": 1.976261019706726,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.816,
      "step": 45
    },
    {
      "epoch": 0.07744107744107744,
      "grad_norm": 1.8439478874206543,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.8419,
      "step": 46
    },
    {
      "epoch": 0.07912457912457913,
      "grad_norm": 1.9471632242202759,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7938,
      "step": 47
    },
    {
      "epoch": 0.08080808080808081,
      "grad_norm": 1.7120723724365234,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.751,
      "step": 48
    },
    {
      "epoch": 0.08249158249158249,
      "grad_norm": 1.830754280090332,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.7963,
      "step": 49
    },
    {
      "epoch": 0.08417508417508418,
      "grad_norm": 2.427234411239624,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.8423,
      "step": 50
    },
    {
      "epoch": 0.08417508417508418,
      "eval_loss": 0.9269463419914246,
      "eval_runtime": 17.2522,
      "eval_samples_per_second": 58.021,
      "eval_steps_per_second": 14.549,
      "step": 50
    },
    {
      "epoch": 0.08585858585858586,
      "grad_norm": 3.4819653034210205,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.2178,
      "step": 51
    },
    {
      "epoch": 0.08754208754208755,
      "grad_norm": 3.1172475814819336,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.0994,
      "step": 52
    },
    {
      "epoch": 0.08922558922558922,
      "grad_norm": 2.456912040710449,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.1342,
      "step": 53
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 1.9707106351852417,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.9668,
      "step": 54
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 1.8037205934524536,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.9851,
      "step": 55
    },
    {
      "epoch": 0.09427609427609428,
      "grad_norm": 1.8836532831192017,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.8874,
      "step": 56
    },
    {
      "epoch": 0.09595959595959595,
      "grad_norm": 1.9802582263946533,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.9077,
      "step": 57
    },
    {
      "epoch": 0.09764309764309764,
      "grad_norm": 2.1473500728607178,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.8493,
      "step": 58
    },
    {
      "epoch": 0.09932659932659933,
      "grad_norm": 2.0039942264556885,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.9097,
      "step": 59
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 1.6674935817718506,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8319,
      "step": 60
    },
    {
      "epoch": 0.1026936026936027,
      "grad_norm": 1.6484204530715942,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.9454,
      "step": 61
    },
    {
      "epoch": 0.10437710437710437,
      "grad_norm": 1.7139694690704346,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8934,
      "step": 62
    },
    {
      "epoch": 0.10606060606060606,
      "grad_norm": 1.4551633596420288,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.7733,
      "step": 63
    },
    {
      "epoch": 0.10774410774410774,
      "grad_norm": 1.5291248559951782,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.8588,
      "step": 64
    },
    {
      "epoch": 0.10942760942760943,
      "grad_norm": 1.6962776184082031,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.8191,
      "step": 65
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 1.4618008136749268,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.8829,
      "step": 66
    },
    {
      "epoch": 0.1127946127946128,
      "grad_norm": 1.4861972332000732,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8924,
      "step": 67
    },
    {
      "epoch": 0.11447811447811448,
      "grad_norm": 1.5194450616836548,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.7037,
      "step": 68
    },
    {
      "epoch": 0.11616161616161616,
      "grad_norm": 1.535462737083435,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.777,
      "step": 69
    },
    {
      "epoch": 0.11784511784511785,
      "grad_norm": 1.6160717010498047,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.8378,
      "step": 70
    },
    {
      "epoch": 0.11952861952861953,
      "grad_norm": 1.5254099369049072,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7481,
      "step": 71
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 1.5566266775131226,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.7738,
      "step": 72
    },
    {
      "epoch": 0.12289562289562289,
      "grad_norm": 1.5855193138122559,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.8142,
      "step": 73
    },
    {
      "epoch": 0.12457912457912458,
      "grad_norm": 1.7887102365493774,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.903,
      "step": 74
    },
    {
      "epoch": 0.12626262626262627,
      "grad_norm": 1.4805766344070435,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7097,
      "step": 75
    },
    {
      "epoch": 0.12794612794612795,
      "grad_norm": 1.7022184133529663,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.8855,
      "step": 76
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 1.6215180158615112,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7803,
      "step": 77
    },
    {
      "epoch": 0.13131313131313133,
      "grad_norm": 1.7519510984420776,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.9047,
      "step": 78
    },
    {
      "epoch": 0.132996632996633,
      "grad_norm": 1.607469081878662,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7434,
      "step": 79
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 1.6657859086990356,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7741,
      "step": 80
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 1.5035887956619263,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.6932,
      "step": 81
    },
    {
      "epoch": 0.13804713804713806,
      "grad_norm": 1.4654340744018555,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7465,
      "step": 82
    },
    {
      "epoch": 0.13973063973063973,
      "grad_norm": 1.6217503547668457,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.8216,
      "step": 83
    },
    {
      "epoch": 0.1414141414141414,
      "grad_norm": 1.5641340017318726,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7657,
      "step": 84
    },
    {
      "epoch": 0.14309764309764308,
      "grad_norm": 1.5489754676818848,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7206,
      "step": 85
    },
    {
      "epoch": 0.1447811447811448,
      "grad_norm": 1.7311922311782837,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7656,
      "step": 86
    },
    {
      "epoch": 0.14646464646464646,
      "grad_norm": 1.5707072019577026,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6038,
      "step": 87
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 1.7641593217849731,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6605,
      "step": 88
    },
    {
      "epoch": 0.14983164983164984,
      "grad_norm": 1.5499985218048096,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6845,
      "step": 89
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 1.7486380338668823,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.8173,
      "step": 90
    },
    {
      "epoch": 0.1531986531986532,
      "grad_norm": 1.6857919692993164,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.8042,
      "step": 91
    },
    {
      "epoch": 0.15488215488215487,
      "grad_norm": 1.6147234439849854,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7976,
      "step": 92
    },
    {
      "epoch": 0.15656565656565657,
      "grad_norm": 1.5985932350158691,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.71,
      "step": 93
    },
    {
      "epoch": 0.15824915824915825,
      "grad_norm": 1.7648745775222778,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.7224,
      "step": 94
    },
    {
      "epoch": 0.15993265993265993,
      "grad_norm": 2.0295968055725098,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7475,
      "step": 95
    },
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 1.7528477907180786,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7503,
      "step": 96
    },
    {
      "epoch": 0.1632996632996633,
      "grad_norm": 1.7403875589370728,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6849,
      "step": 97
    },
    {
      "epoch": 0.16498316498316498,
      "grad_norm": 1.7989548444747925,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.7173,
      "step": 98
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 1.6930757761001587,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.7075,
      "step": 99
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 2.128187656402588,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8447,
      "step": 100
    },
    {
      "epoch": 0.16835016835016836,
      "eval_loss": 0.8251528143882751,
      "eval_runtime": 17.2663,
      "eval_samples_per_second": 57.974,
      "eval_steps_per_second": 14.537,
      "step": 100
    },
    {
      "epoch": 0.17003367003367004,
      "grad_norm": 2.0755367279052734,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.9672,
      "step": 101
    },
    {
      "epoch": 0.1717171717171717,
      "grad_norm": 2.0217695236206055,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.9535,
      "step": 102
    },
    {
      "epoch": 0.1734006734006734,
      "grad_norm": 1.9532135725021362,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.9503,
      "step": 103
    },
    {
      "epoch": 0.1750841750841751,
      "grad_norm": 1.8931111097335815,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.8849,
      "step": 104
    },
    {
      "epoch": 0.17676767676767677,
      "grad_norm": 1.6922742128372192,
      "learning_rate": 5e-05,
      "loss": 0.8469,
      "step": 105
    },
    {
      "epoch": 0.17845117845117844,
      "grad_norm": 1.7153887748718262,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.8565,
      "step": 106
    },
    {
      "epoch": 0.18013468013468015,
      "grad_norm": 1.6420055627822876,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.8784,
      "step": 107
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 1.5930083990097046,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.8256,
      "step": 108
    },
    {
      "epoch": 0.1835016835016835,
      "grad_norm": 1.415897011756897,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.8017,
      "step": 109
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.426174283027649,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8197,
      "step": 110
    },
    {
      "epoch": 0.18686868686868688,
      "grad_norm": 1.4900239706039429,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.7042,
      "step": 111
    },
    {
      "epoch": 0.18855218855218855,
      "grad_norm": 1.5487056970596313,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8758,
      "step": 112
    },
    {
      "epoch": 0.19023569023569023,
      "grad_norm": 1.4241440296173096,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.7972,
      "step": 113
    },
    {
      "epoch": 0.1919191919191919,
      "grad_norm": 1.5170420408248901,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.8287,
      "step": 114
    },
    {
      "epoch": 0.1936026936026936,
      "grad_norm": 1.4301002025604248,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.7282,
      "step": 115
    },
    {
      "epoch": 0.19528619528619529,
      "grad_norm": 1.4963473081588745,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.7553,
      "step": 116
    },
    {
      "epoch": 0.19696969696969696,
      "grad_norm": 1.3359309434890747,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.697,
      "step": 117
    },
    {
      "epoch": 0.19865319865319866,
      "grad_norm": 1.4342330694198608,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.7276,
      "step": 118
    },
    {
      "epoch": 0.20033670033670034,
      "grad_norm": 1.4613280296325684,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.6979,
      "step": 119
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 1.3762140274047852,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6833,
      "step": 120
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 1.4406741857528687,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7792,
      "step": 121
    },
    {
      "epoch": 0.2053872053872054,
      "grad_norm": 1.4419723749160767,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.7243,
      "step": 122
    },
    {
      "epoch": 0.20707070707070707,
      "grad_norm": 1.439305067062378,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.7154,
      "step": 123
    },
    {
      "epoch": 0.20875420875420875,
      "grad_norm": 1.4699344635009766,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7628,
      "step": 124
    },
    {
      "epoch": 0.21043771043771045,
      "grad_norm": 1.4562989473342896,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7785,
      "step": 125
    },
    {
      "epoch": 0.21212121212121213,
      "grad_norm": 1.3667465448379517,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.6523,
      "step": 126
    },
    {
      "epoch": 0.2138047138047138,
      "grad_norm": 1.4240037202835083,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7409,
      "step": 127
    },
    {
      "epoch": 0.21548821548821548,
      "grad_norm": 1.5213513374328613,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7481,
      "step": 128
    },
    {
      "epoch": 0.21717171717171718,
      "grad_norm": 1.4982272386550903,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.7974,
      "step": 129
    },
    {
      "epoch": 0.21885521885521886,
      "grad_norm": 1.4482314586639404,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6998,
      "step": 130
    },
    {
      "epoch": 0.22053872053872053,
      "grad_norm": 1.4862515926361084,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6552,
      "step": 131
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.431307315826416,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.6858,
      "step": 132
    },
    {
      "epoch": 0.2239057239057239,
      "grad_norm": 1.466747760772705,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.6499,
      "step": 133
    },
    {
      "epoch": 0.2255892255892256,
      "grad_norm": 1.5380254983901978,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.788,
      "step": 134
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 1.5833460092544556,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7462,
      "step": 135
    },
    {
      "epoch": 0.22895622895622897,
      "grad_norm": 1.5846306085586548,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7795,
      "step": 136
    },
    {
      "epoch": 0.23063973063973064,
      "grad_norm": 1.4377760887145996,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.6324,
      "step": 137
    },
    {
      "epoch": 0.23232323232323232,
      "grad_norm": 1.5191439390182495,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.6281,
      "step": 138
    },
    {
      "epoch": 0.234006734006734,
      "grad_norm": 1.4722684621810913,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.6257,
      "step": 139
    },
    {
      "epoch": 0.2356902356902357,
      "grad_norm": 1.5686328411102295,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.6873,
      "step": 140
    },
    {
      "epoch": 0.23737373737373738,
      "grad_norm": 1.4807740449905396,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.5796,
      "step": 141
    },
    {
      "epoch": 0.23905723905723905,
      "grad_norm": 1.4003280401229858,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.6285,
      "step": 142
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 1.5255802869796753,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7166,
      "step": 143
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 1.6983699798583984,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.732,
      "step": 144
    },
    {
      "epoch": 0.2441077441077441,
      "grad_norm": 1.538061261177063,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6466,
      "step": 145
    },
    {
      "epoch": 0.24579124579124578,
      "grad_norm": 1.6083265542984009,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.668,
      "step": 146
    },
    {
      "epoch": 0.2474747474747475,
      "grad_norm": 1.7365162372589111,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.6049,
      "step": 147
    },
    {
      "epoch": 0.24915824915824916,
      "grad_norm": 1.8119126558303833,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.6753,
      "step": 148
    },
    {
      "epoch": 0.25084175084175087,
      "grad_norm": 1.7427568435668945,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5982,
      "step": 149
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 2.1858670711517334,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.6981,
      "step": 150
    },
    {
      "epoch": 0.25252525252525254,
      "eval_loss": 0.762880802154541,
      "eval_runtime": 17.251,
      "eval_samples_per_second": 58.026,
      "eval_steps_per_second": 14.55,
      "step": 150
    },
    {
      "epoch": 0.2542087542087542,
      "grad_norm": 1.7905802726745605,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.9552,
      "step": 151
    },
    {
      "epoch": 0.2558922558922559,
      "grad_norm": 1.7423441410064697,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.8458,
      "step": 152
    },
    {
      "epoch": 0.25757575757575757,
      "grad_norm": 1.6511619091033936,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.7862,
      "step": 153
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 1.7994682788848877,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.8944,
      "step": 154
    },
    {
      "epoch": 0.2609427609427609,
      "grad_norm": 1.6717253923416138,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.9051,
      "step": 155
    },
    {
      "epoch": 0.26262626262626265,
      "grad_norm": 1.7721930742263794,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.7626,
      "step": 156
    },
    {
      "epoch": 0.26430976430976433,
      "grad_norm": 1.6830980777740479,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.8222,
      "step": 157
    },
    {
      "epoch": 0.265993265993266,
      "grad_norm": 1.5053858757019043,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.734,
      "step": 158
    },
    {
      "epoch": 0.2676767676767677,
      "grad_norm": 1.5103014707565308,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.7761,
      "step": 159
    },
    {
      "epoch": 0.26936026936026936,
      "grad_norm": 1.5218517780303955,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7607,
      "step": 160
    },
    {
      "epoch": 0.27104377104377103,
      "grad_norm": 1.4983371496200562,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.7144,
      "step": 161
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 1.4919451475143433,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.7573,
      "step": 162
    },
    {
      "epoch": 0.27441077441077444,
      "grad_norm": 1.4426158666610718,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.8044,
      "step": 163
    },
    {
      "epoch": 0.2760942760942761,
      "grad_norm": 1.4994579553604126,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.8339,
      "step": 164
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 1.4691531658172607,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.8057,
      "step": 165
    },
    {
      "epoch": 0.27946127946127947,
      "grad_norm": 1.4192619323730469,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.6637,
      "step": 166
    },
    {
      "epoch": 0.28114478114478114,
      "grad_norm": 1.4521950483322144,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.6674,
      "step": 167
    },
    {
      "epoch": 0.2828282828282828,
      "grad_norm": 1.4031963348388672,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.7377,
      "step": 168
    },
    {
      "epoch": 0.2845117845117845,
      "grad_norm": 1.496728777885437,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.7805,
      "step": 169
    },
    {
      "epoch": 0.28619528619528617,
      "grad_norm": 1.4464303255081177,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.7118,
      "step": 170
    },
    {
      "epoch": 0.2878787878787879,
      "grad_norm": 1.3609129190444946,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.6358,
      "step": 171
    },
    {
      "epoch": 0.2895622895622896,
      "grad_norm": 1.3781795501708984,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.7453,
      "step": 172
    },
    {
      "epoch": 0.29124579124579125,
      "grad_norm": 1.481461763381958,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.7722,
      "step": 173
    },
    {
      "epoch": 0.29292929292929293,
      "grad_norm": 1.6674716472625732,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.7086,
      "step": 174
    },
    {
      "epoch": 0.2946127946127946,
      "grad_norm": 1.4592093229293823,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.652,
      "step": 175
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 1.3736507892608643,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.6336,
      "step": 176
    },
    {
      "epoch": 0.29797979797979796,
      "grad_norm": 1.4343737363815308,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7196,
      "step": 177
    },
    {
      "epoch": 0.2996632996632997,
      "grad_norm": 1.4188438653945923,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7377,
      "step": 178
    },
    {
      "epoch": 0.30134680134680136,
      "grad_norm": 1.3953213691711426,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.6917,
      "step": 179
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 1.452767252922058,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.698,
      "step": 180
    },
    {
      "epoch": 0.3047138047138047,
      "grad_norm": 1.5965834856033325,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.621,
      "step": 181
    },
    {
      "epoch": 0.3063973063973064,
      "grad_norm": 1.459354281425476,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.6425,
      "step": 182
    },
    {
      "epoch": 0.30808080808080807,
      "grad_norm": 1.4931968450546265,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.7052,
      "step": 183
    },
    {
      "epoch": 0.30976430976430974,
      "grad_norm": 1.5617070198059082,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7951,
      "step": 184
    },
    {
      "epoch": 0.3114478114478115,
      "grad_norm": 1.60529363155365,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.6656,
      "step": 185
    },
    {
      "epoch": 0.31313131313131315,
      "grad_norm": 1.419008493423462,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.6919,
      "step": 186
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 1.604127287864685,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.7654,
      "step": 187
    },
    {
      "epoch": 0.3164983164983165,
      "grad_norm": 1.533624291419983,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.6289,
      "step": 188
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 1.596411943435669,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.7371,
      "step": 189
    },
    {
      "epoch": 0.31986531986531985,
      "grad_norm": 1.5748000144958496,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.7545,
      "step": 190
    },
    {
      "epoch": 0.32154882154882153,
      "grad_norm": 1.6616222858428955,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.6707,
      "step": 191
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 1.849848985671997,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.8708,
      "step": 192
    },
    {
      "epoch": 0.32491582491582494,
      "grad_norm": 1.6856423616409302,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.7734,
      "step": 193
    },
    {
      "epoch": 0.3265993265993266,
      "grad_norm": 1.731228232383728,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.7311,
      "step": 194
    },
    {
      "epoch": 0.3282828282828283,
      "grad_norm": 1.7076404094696045,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.6382,
      "step": 195
    },
    {
      "epoch": 0.32996632996632996,
      "grad_norm": 1.618672490119934,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.6231,
      "step": 196
    },
    {
      "epoch": 0.33164983164983164,
      "grad_norm": 1.684415578842163,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.6247,
      "step": 197
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.310145378112793,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.6567,
      "step": 198
    },
    {
      "epoch": 0.335016835016835,
      "grad_norm": 1.9177016019821167,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.7074,
      "step": 199
    },
    {
      "epoch": 0.3367003367003367,
      "grad_norm": 2.5717124938964844,
      "learning_rate": 0.0,
      "loss": 0.9441,
      "step": 200
    },
    {
      "epoch": 0.3367003367003367,
      "eval_loss": 0.7370568513870239,
      "eval_runtime": 17.2974,
      "eval_samples_per_second": 57.87,
      "eval_steps_per_second": 14.511,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.54569648635904e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}