{
  "best_metric": 0.1497827023267746,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.8465608465608465,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004232804232804233,
      "grad_norm": 1.6714744567871094,
      "learning_rate": 1e-05,
      "loss": 3.1431,
      "step": 1
    },
    {
      "epoch": 0.004232804232804233,
      "eval_loss": 2.0089242458343506,
      "eval_runtime": 40.629,
      "eval_samples_per_second": 9.796,
      "eval_steps_per_second": 2.461,
      "step": 1
    },
    {
      "epoch": 0.008465608465608466,
      "grad_norm": 1.7588242292404175,
      "learning_rate": 2e-05,
      "loss": 3.4984,
      "step": 2
    },
    {
      "epoch": 0.012698412698412698,
      "grad_norm": 1.8874233961105347,
      "learning_rate": 3e-05,
      "loss": 3.1283,
      "step": 3
    },
    {
      "epoch": 0.016931216931216932,
      "grad_norm": 2.019477128982544,
      "learning_rate": 4e-05,
      "loss": 3.5263,
      "step": 4
    },
    {
      "epoch": 0.021164021164021163,
      "grad_norm": 1.963308334350586,
      "learning_rate": 5e-05,
      "loss": 3.2971,
      "step": 5
    },
    {
      "epoch": 0.025396825396825397,
      "grad_norm": 2.2798237800598145,
      "learning_rate": 6e-05,
      "loss": 3.9252,
      "step": 6
    },
    {
      "epoch": 0.02962962962962963,
      "grad_norm": 2.887723207473755,
      "learning_rate": 7e-05,
      "loss": 4.4977,
      "step": 7
    },
    {
      "epoch": 0.033862433862433865,
      "grad_norm": 2.67097806930542,
      "learning_rate": 8e-05,
      "loss": 3.4662,
      "step": 8
    },
    {
      "epoch": 0.0380952380952381,
      "grad_norm": 2.4605140686035156,
      "learning_rate": 9e-05,
      "loss": 2.9318,
      "step": 9
    },
    {
      "epoch": 0.042328042328042326,
      "grad_norm": 3.042994976043701,
      "learning_rate": 0.0001,
      "loss": 3.3773,
      "step": 10
    },
    {
      "epoch": 0.04656084656084656,
      "grad_norm": 2.580188035964966,
      "learning_rate": 9.999316524962345e-05,
      "loss": 2.7983,
      "step": 11
    },
    {
      "epoch": 0.050793650793650794,
      "grad_norm": 5.903667449951172,
      "learning_rate": 9.997266286704631e-05,
      "loss": 2.5527,
      "step": 12
    },
    {
      "epoch": 0.05502645502645503,
      "grad_norm": 6.125539779663086,
      "learning_rate": 9.993849845741524e-05,
      "loss": 2.1661,
      "step": 13
    },
    {
      "epoch": 0.05925925925925926,
      "grad_norm": 4.070702075958252,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.6598,
      "step": 14
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 2.248438596725464,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.1783,
      "step": 15
    },
    {
      "epoch": 0.06772486772486773,
      "grad_norm": 4.684490203857422,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.8716,
      "step": 16
    },
    {
      "epoch": 0.07195767195767196,
      "grad_norm": 3.82509708404541,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.424,
      "step": 17
    },
    {
      "epoch": 0.0761904761904762,
      "grad_norm": 4.508487224578857,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.7454,
      "step": 18
    },
    {
      "epoch": 0.08042328042328042,
      "grad_norm": 4.8689069747924805,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.5126,
      "step": 19
    },
    {
      "epoch": 0.08465608465608465,
      "grad_norm": 2.6785712242126465,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.2421,
      "step": 20
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 2.843942880630493,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.0082,
      "step": 21
    },
    {
      "epoch": 0.09312169312169312,
      "grad_norm": 3.262895345687866,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.2524,
      "step": 22
    },
    {
      "epoch": 0.09735449735449736,
      "grad_norm": 3.5198256969451904,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.0015,
      "step": 23
    },
    {
      "epoch": 0.10158730158730159,
      "grad_norm": 3.245711088180542,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.1404,
      "step": 24
    },
    {
      "epoch": 0.10582010582010581,
      "grad_norm": 2.175269603729248,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.0217,
      "step": 25
    },
    {
      "epoch": 0.11005291005291006,
      "grad_norm": 3.2844924926757812,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.9201,
      "step": 26
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 2.053403377532959,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.7076,
      "step": 27
    },
    {
      "epoch": 0.11851851851851852,
      "grad_norm": 2.659097671508789,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.8202,
      "step": 28
    },
    {
      "epoch": 0.12275132275132275,
      "grad_norm": 4.577873706817627,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3237,
      "step": 29
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 4.847832202911377,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.1849,
      "step": 30
    },
    {
      "epoch": 0.1312169312169312,
      "grad_norm": 2.996955394744873,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.6685,
      "step": 31
    },
    {
      "epoch": 0.13544973544973546,
      "grad_norm": 3.0688812732696533,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7403,
      "step": 32
    },
    {
      "epoch": 0.13968253968253969,
      "grad_norm": 3.3211264610290527,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7307,
      "step": 33
    },
    {
      "epoch": 0.1439153439153439,
      "grad_norm": 4.159071445465088,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.0391,
      "step": 34
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 4.019430637359619,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.9554,
      "step": 35
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 6.0396013259887695,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.5647,
      "step": 36
    },
    {
      "epoch": 0.15661375661375662,
      "grad_norm": 3.8017523288726807,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.9664,
      "step": 37
    },
    {
      "epoch": 0.16084656084656085,
      "grad_norm": 3.132852792739868,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8059,
      "step": 38
    },
    {
      "epoch": 0.16507936507936508,
      "grad_norm": 2.5289409160614014,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7292,
      "step": 39
    },
    {
      "epoch": 0.1693121693121693,
      "grad_norm": 2.2652974128723145,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.6037,
      "step": 40
    },
    {
      "epoch": 0.17354497354497356,
      "grad_norm": 3.1899678707122803,
      "learning_rate": 9.357421218136386e-05,
      "loss": 1.0462,
      "step": 41
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 2.732605218887329,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.6194,
      "step": 42
    },
    {
      "epoch": 0.182010582010582,
      "grad_norm": 2.596256971359253,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7684,
      "step": 43
    },
    {
      "epoch": 0.18624338624338624,
      "grad_norm": 2.5796756744384766,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.5619,
      "step": 44
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 4.140925884246826,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.83,
      "step": 45
    },
    {
      "epoch": 0.19470899470899472,
      "grad_norm": 3.873262405395508,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.1124,
      "step": 46
    },
    {
      "epoch": 0.19894179894179895,
      "grad_norm": 3.1621084213256836,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.6438,
      "step": 47
    },
    {
      "epoch": 0.20317460317460317,
      "grad_norm": 4.241144180297852,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.0761,
      "step": 48
    },
    {
      "epoch": 0.2074074074074074,
      "grad_norm": 5.300878047943115,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.1735,
      "step": 49
    },
    {
      "epoch": 0.21164021164021163,
      "grad_norm": 5.850068092346191,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.3391,
      "step": 50
    },
    {
      "epoch": 0.21164021164021163,
      "eval_loss": 0.28510138392448425,
      "eval_runtime": 41.0861,
      "eval_samples_per_second": 9.687,
      "eval_steps_per_second": 2.434,
      "step": 50
    },
    {
      "epoch": 0.21587301587301588,
      "grad_norm": 8.396745681762695,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.3575,
      "step": 51
    },
    {
      "epoch": 0.2201058201058201,
      "grad_norm": 4.838835716247559,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.1254,
      "step": 52
    },
    {
      "epoch": 0.22433862433862434,
      "grad_norm": 2.195279598236084,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.6839,
      "step": 53
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 2.4905669689178467,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.6647,
      "step": 54
    },
    {
      "epoch": 0.2328042328042328,
      "grad_norm": 2.541898727416992,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.6525,
      "step": 55
    },
    {
      "epoch": 0.23703703703703705,
      "grad_norm": 2.7231433391571045,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7526,
      "step": 56
    },
    {
      "epoch": 0.24126984126984127,
      "grad_norm": 4.360929012298584,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.2631,
      "step": 57
    },
    {
      "epoch": 0.2455026455026455,
      "grad_norm": 4.290722370147705,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.1508,
      "step": 58
    },
    {
      "epoch": 0.24973544973544973,
      "grad_norm": 2.3104233741760254,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.7923,
      "step": 59
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 2.016592502593994,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.5964,
      "step": 60
    },
    {
      "epoch": 0.2582010582010582,
      "grad_norm": 1.6593921184539795,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.6714,
      "step": 61
    },
    {
      "epoch": 0.2624338624338624,
      "grad_norm": 3.42293119430542,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.616,
      "step": 62
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 2.126283645629883,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.927,
      "step": 63
    },
    {
      "epoch": 0.2708994708994709,
      "grad_norm": 2.27679181098938,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.8001,
      "step": 64
    },
    {
      "epoch": 0.2751322751322751,
      "grad_norm": 1.9078603982925415,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7786,
      "step": 65
    },
    {
      "epoch": 0.27936507936507937,
      "grad_norm": 1.7316244840621948,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.5738,
      "step": 66
    },
    {
      "epoch": 0.28359788359788357,
      "grad_norm": 2.466203451156616,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8297,
      "step": 67
    },
    {
      "epoch": 0.2878306878306878,
      "grad_norm": 5.6646857261657715,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.9338,
      "step": 68
    },
    {
      "epoch": 0.2920634920634921,
      "grad_norm": 2.967580556869507,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.7797,
      "step": 69
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 2.2649996280670166,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.8364,
      "step": 70
    },
    {
      "epoch": 0.30052910052910053,
      "grad_norm": 2.2311346530914307,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7768,
      "step": 71
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": 1.7841646671295166,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.679,
      "step": 72
    },
    {
      "epoch": 0.308994708994709,
      "grad_norm": 1.596014380455017,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.505,
      "step": 73
    },
    {
      "epoch": 0.31322751322751324,
      "grad_norm": 1.7665396928787231,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.4276,
      "step": 74
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 1.6678146123886108,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.5239,
      "step": 75
    },
    {
      "epoch": 0.3216931216931217,
      "grad_norm": 1.899565577507019,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.5342,
      "step": 76
    },
    {
      "epoch": 0.32592592592592595,
      "grad_norm": 1.4789760112762451,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.303,
      "step": 77
    },
    {
      "epoch": 0.33015873015873015,
      "grad_norm": 3.2063186168670654,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.7548,
      "step": 78
    },
    {
      "epoch": 0.3343915343915344,
      "grad_norm": 2.527874708175659,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.5949,
      "step": 79
    },
    {
      "epoch": 0.3386243386243386,
      "grad_norm": 2.182678461074829,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.4594,
      "step": 80
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 4.4873576164245605,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.2856,
      "step": 81
    },
    {
      "epoch": 0.3470899470899471,
      "grad_norm": 1.7451472282409668,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.4107,
      "step": 82
    },
    {
      "epoch": 0.3513227513227513,
      "grad_norm": 3.1027092933654785,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.7229,
      "step": 83
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 3.0617892742156982,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7879,
      "step": 84
    },
    {
      "epoch": 0.35978835978835977,
      "grad_norm": 2.025111436843872,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.4687,
      "step": 85
    },
    {
      "epoch": 0.364021164021164,
      "grad_norm": 2.529101848602295,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.8121,
      "step": 86
    },
    {
      "epoch": 0.3682539682539683,
      "grad_norm": 2.5290567874908447,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.8566,
      "step": 87
    },
    {
      "epoch": 0.3724867724867725,
      "grad_norm": 2.221857786178589,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6362,
      "step": 88
    },
    {
      "epoch": 0.37671957671957673,
      "grad_norm": 1.564263105392456,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.5029,
      "step": 89
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.461040735244751,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5951,
      "step": 90
    },
    {
      "epoch": 0.3851851851851852,
      "grad_norm": 2.8098888397216797,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.8597,
      "step": 91
    },
    {
      "epoch": 0.38941798941798944,
      "grad_norm": 1.710269808769226,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.3263,
      "step": 92
    },
    {
      "epoch": 0.39365079365079364,
      "grad_norm": 2.327526807785034,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.5541,
      "step": 93
    },
    {
      "epoch": 0.3978835978835979,
      "grad_norm": 3.009798526763916,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.584,
      "step": 94
    },
    {
      "epoch": 0.4021164021164021,
      "grad_norm": 3.270240545272827,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.4716,
      "step": 95
    },
    {
      "epoch": 0.40634920634920635,
      "grad_norm": 2.6876206398010254,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5108,
      "step": 96
    },
    {
      "epoch": 0.4105820105820106,
      "grad_norm": 2.992650032043457,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.4605,
      "step": 97
    },
    {
      "epoch": 0.4148148148148148,
      "grad_norm": 2.9727976322174072,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.803,
      "step": 98
    },
    {
      "epoch": 0.41904761904761906,
      "grad_norm": 3.2047364711761475,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.5982,
      "step": 99
    },
    {
      "epoch": 0.42328042328042326,
      "grad_norm": 4.053775787353516,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.6948,
      "step": 100
    },
    {
      "epoch": 0.42328042328042326,
      "eval_loss": 0.1990184634923935,
      "eval_runtime": 41.1149,
      "eval_samples_per_second": 9.68,
      "eval_steps_per_second": 2.432,
      "step": 100
    },
    {
      "epoch": 0.4275132275132275,
      "grad_norm": 3.709782123565674,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.7057,
      "step": 101
    },
    {
      "epoch": 0.43174603174603177,
      "grad_norm": 3.146618604660034,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.7502,
      "step": 102
    },
    {
      "epoch": 0.43597883597883597,
      "grad_norm": 3.61533522605896,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.69,
      "step": 103
    },
    {
      "epoch": 0.4402116402116402,
      "grad_norm": 2.936035394668579,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.569,
      "step": 104
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.1050968170166016,
      "learning_rate": 5e-05,
      "loss": 0.5472,
      "step": 105
    },
    {
      "epoch": 0.4486772486772487,
      "grad_norm": 1.8016530275344849,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.4647,
      "step": 106
    },
    {
      "epoch": 0.45291005291005293,
      "grad_norm": 2.0102932453155518,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.4983,
      "step": 107
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 2.467546224594116,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.6294,
      "step": 108
    },
    {
      "epoch": 0.4613756613756614,
      "grad_norm": 2.855675220489502,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.5709,
      "step": 109
    },
    {
      "epoch": 0.4656084656084656,
      "grad_norm": 2.4019744396209717,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.5041,
      "step": 110
    },
    {
      "epoch": 0.46984126984126984,
      "grad_norm": 2.463066577911377,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.6505,
      "step": 111
    },
    {
      "epoch": 0.4740740740740741,
      "grad_norm": 2.4147982597351074,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.624,
      "step": 112
    },
    {
      "epoch": 0.4783068783068783,
      "grad_norm": 2.0820560455322266,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.4698,
      "step": 113
    },
    {
      "epoch": 0.48253968253968255,
      "grad_norm": 2.389864683151245,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.5939,
      "step": 114
    },
    {
      "epoch": 0.48677248677248675,
      "grad_norm": 2.3950488567352295,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.5771,
      "step": 115
    },
    {
      "epoch": 0.491005291005291,
      "grad_norm": 2.0432913303375244,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.5298,
      "step": 116
    },
    {
      "epoch": 0.49523809523809526,
      "grad_norm": 1.8616389036178589,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.3899,
      "step": 117
    },
    {
      "epoch": 0.49947089947089945,
      "grad_norm": 2.788710117340088,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.6409,
      "step": 118
    },
    {
      "epoch": 0.5037037037037037,
      "grad_norm": 1.6810587644577026,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.4127,
      "step": 119
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 2.332592248916626,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7031,
      "step": 120
    },
    {
      "epoch": 0.5121693121693122,
      "grad_norm": 2.248194456100464,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.4465,
      "step": 121
    },
    {
      "epoch": 0.5164021164021164,
      "grad_norm": 1.7367057800292969,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.4071,
      "step": 122
    },
    {
      "epoch": 0.5206349206349207,
      "grad_norm": 2.0206806659698486,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.6206,
      "step": 123
    },
    {
      "epoch": 0.5248677248677248,
      "grad_norm": 2.396857976913452,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.5027,
      "step": 124
    },
    {
      "epoch": 0.5291005291005291,
      "grad_norm": 2.2567622661590576,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4398,
      "step": 125
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 2.5292673110961914,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.5829,
      "step": 126
    },
    {
      "epoch": 0.5375661375661376,
      "grad_norm": 2.5528736114501953,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.4593,
      "step": 127
    },
    {
      "epoch": 0.5417989417989418,
      "grad_norm": 4.135124683380127,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.8111,
      "step": 128
    },
    {
      "epoch": 0.546031746031746,
      "grad_norm": 1.8155592679977417,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.4043,
      "step": 129
    },
    {
      "epoch": 0.5502645502645502,
      "grad_norm": 2.1554229259490967,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.5827,
      "step": 130
    },
    {
      "epoch": 0.5544973544973545,
      "grad_norm": 1.8356127738952637,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6062,
      "step": 131
    },
    {
      "epoch": 0.5587301587301587,
      "grad_norm": 1.523517370223999,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.3939,
      "step": 132
    },
    {
      "epoch": 0.562962962962963,
      "grad_norm": 2.9438838958740234,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.5291,
      "step": 133
    },
    {
      "epoch": 0.5671957671957671,
      "grad_norm": 2.588531732559204,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.6309,
      "step": 134
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 2.6910924911499023,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7492,
      "step": 135
    },
    {
      "epoch": 0.5756613756613757,
      "grad_norm": 1.2879542112350464,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.2478,
      "step": 136
    },
    {
      "epoch": 0.5798941798941799,
      "grad_norm": 2.958266258239746,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.6849,
      "step": 137
    },
    {
      "epoch": 0.5841269841269842,
      "grad_norm": 2.645630359649658,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.6001,
      "step": 138
    },
    {
      "epoch": 0.5883597883597883,
      "grad_norm": 2.227250576019287,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.2719,
      "step": 139
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 3.5327680110931396,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.9031,
      "step": 140
    },
    {
      "epoch": 0.5968253968253968,
      "grad_norm": 2.8783230781555176,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.4759,
      "step": 141
    },
    {
      "epoch": 0.6010582010582011,
      "grad_norm": 2.1304266452789307,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.396,
      "step": 142
    },
    {
      "epoch": 0.6052910052910053,
      "grad_norm": 2.239182233810425,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.3765,
      "step": 143
    },
    {
      "epoch": 0.6095238095238096,
      "grad_norm": 2.1924729347229004,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.4428,
      "step": 144
    },
    {
      "epoch": 0.6137566137566137,
      "grad_norm": 3.0594825744628906,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6758,
      "step": 145
    },
    {
      "epoch": 0.617989417989418,
      "grad_norm": 2.562217950820923,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.5913,
      "step": 146
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 2.1563374996185303,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.5236,
      "step": 147
    },
    {
      "epoch": 0.6264550264550265,
      "grad_norm": 2.564004898071289,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5818,
      "step": 148
    },
    {
      "epoch": 0.6306878306878307,
      "grad_norm": 2.4984490871429443,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.6464,
      "step": 149
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 3.0725834369659424,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.4697,
      "step": 150
    },
    {
      "epoch": 0.6349206349206349,
      "eval_loss": 0.1561691015958786,
      "eval_runtime": 41.1207,
      "eval_samples_per_second": 9.679,
      "eval_steps_per_second": 2.432,
      "step": 150
    },
    {
      "epoch": 0.6391534391534391,
      "grad_norm": 1.970943808555603,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.4118,
      "step": 151
    },
    {
      "epoch": 0.6433862433862434,
      "grad_norm": 1.959216594696045,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.467,
      "step": 152
    },
    {
      "epoch": 0.6476190476190476,
      "grad_norm": 2.0195982456207275,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.5091,
      "step": 153
    },
    {
      "epoch": 0.6518518518518519,
      "grad_norm": 1.6715471744537354,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.2947,
      "step": 154
    },
    {
      "epoch": 0.656084656084656,
      "grad_norm": 2.0884463787078857,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.4799,
      "step": 155
    },
    {
      "epoch": 0.6603174603174603,
      "grad_norm": 1.8190643787384033,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.4612,
      "step": 156
    },
    {
      "epoch": 0.6645502645502646,
      "grad_norm": 2.2603588104248047,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.446,
      "step": 157
    },
    {
      "epoch": 0.6687830687830688,
      "grad_norm": 2.1522154808044434,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.5833,
      "step": 158
    },
    {
      "epoch": 0.6730158730158731,
      "grad_norm": 2.063936233520508,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.4798,
      "step": 159
    },
    {
      "epoch": 0.6772486772486772,
      "grad_norm": 1.4574905633926392,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.412,
      "step": 160
    },
    {
      "epoch": 0.6814814814814815,
      "grad_norm": 1.8604955673217773,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.5166,
      "step": 161
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 2.9001357555389404,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.5933,
      "step": 162
    },
    {
      "epoch": 0.68994708994709,
      "grad_norm": 1.585640788078308,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.4097,
      "step": 163
    },
    {
      "epoch": 0.6941798941798942,
      "grad_norm": 2.744859457015991,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.6607,
      "step": 164
    },
    {
      "epoch": 0.6984126984126984,
      "grad_norm": 2.249626636505127,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.4273,
      "step": 165
    },
    {
      "epoch": 0.7026455026455026,
      "grad_norm": 1.7049546241760254,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.3905,
      "step": 166
    },
    {
      "epoch": 0.7068783068783069,
      "grad_norm": 1.5164399147033691,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.383,
      "step": 167
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 2.3326051235198975,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.5324,
      "step": 168
    },
    {
      "epoch": 0.7153439153439154,
      "grad_norm": 2.0321743488311768,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.3742,
      "step": 169
    },
    {
      "epoch": 0.7195767195767195,
      "grad_norm": 2.192164897918701,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.4655,
      "step": 170
    },
    {
      "epoch": 0.7238095238095238,
      "grad_norm": 2.9935622215270996,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.4511,
      "step": 171
    },
    {
      "epoch": 0.728042328042328,
      "grad_norm": 2.612241268157959,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.5728,
      "step": 172
    },
    {
      "epoch": 0.7322751322751323,
      "grad_norm": 1.821539044380188,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.4093,
      "step": 173
    },
    {
      "epoch": 0.7365079365079366,
      "grad_norm": 1.6107043027877808,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.3771,
      "step": 174
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 2.128167152404785,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.4155,
      "step": 175
    },
    {
      "epoch": 0.744973544973545,
      "grad_norm": 1.5665826797485352,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.2701,
      "step": 176
    },
    {
      "epoch": 0.7492063492063492,
      "grad_norm": 2.0039846897125244,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.5075,
      "step": 177
    },
    {
      "epoch": 0.7534391534391535,
      "grad_norm": 2.1679248809814453,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.4244,
      "step": 178
    },
    {
      "epoch": 0.7576719576719577,
      "grad_norm": 2.0314784049987793,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.449,
      "step": 179
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 1.7632853984832764,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.3688,
      "step": 180
    },
    {
      "epoch": 0.7661375661375661,
      "grad_norm": 3.102304458618164,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.5191,
      "step": 181
    },
    {
      "epoch": 0.7703703703703704,
      "grad_norm": 2.5443382263183594,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.6566,
      "step": 182
    },
    {
      "epoch": 0.7746031746031746,
      "grad_norm": 3.381953477859497,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.5674,
      "step": 183
    },
    {
      "epoch": 0.7788359788359789,
      "grad_norm": 2.928821563720703,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.5408,
      "step": 184
    },
    {
      "epoch": 0.783068783068783,
      "grad_norm": 1.8287091255187988,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.3305,
      "step": 185
    },
    {
      "epoch": 0.7873015873015873,
      "grad_norm": 2.482009172439575,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.527,
      "step": 186
    },
    {
      "epoch": 0.7915343915343915,
      "grad_norm": 2.223562717437744,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.5677,
      "step": 187
    },
    {
      "epoch": 0.7957671957671958,
      "grad_norm": 2.3504953384399414,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.5924,
      "step": 188
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.942935585975647,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.3415,
      "step": 189
    },
    {
      "epoch": 0.8042328042328042,
      "grad_norm": 2.790147066116333,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.6834,
      "step": 190
    },
    {
      "epoch": 0.8084656084656084,
      "grad_norm": 3.0216917991638184,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.592,
      "step": 191
    },
    {
      "epoch": 0.8126984126984127,
      "grad_norm": 2.5821573734283447,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.4523,
      "step": 192
    },
    {
      "epoch": 0.816931216931217,
      "grad_norm": 2.931043863296509,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.6767,
      "step": 193
    },
    {
      "epoch": 0.8211640211640212,
      "grad_norm": 2.09012770652771,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.4223,
      "step": 194
    },
    {
      "epoch": 0.8253968253968254,
      "grad_norm": 1.9773967266082764,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.3672,
      "step": 195
    },
    {
      "epoch": 0.8296296296296296,
      "grad_norm": 3.460179567337036,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.5537,
      "step": 196
    },
    {
      "epoch": 0.8338624338624339,
      "grad_norm": 3.3920695781707764,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.5335,
      "step": 197
    },
    {
      "epoch": 0.8380952380952381,
      "grad_norm": 3.919065237045288,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.7317,
      "step": 198
    },
    {
      "epoch": 0.8423280423280424,
      "grad_norm": 2.8624651432037354,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.4744,
      "step": 199
    },
    {
      "epoch": 0.8465608465608465,
      "grad_norm": 5.172921657562256,
      "learning_rate": 0.0,
      "loss": 0.9618,
      "step": 200
    },
    {
      "epoch": 0.8465608465608465,
      "eval_loss": 0.1497827023267746,
      "eval_runtime": 41.1185,
      "eval_samples_per_second": 9.679,
      "eval_steps_per_second": 2.432,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.09187566075904e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}