{
  "best_metric": 0.19777049124240875,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.03274572941112263,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021830486274081756,
      "grad_norm": 190.99996948242188,
      "learning_rate": 1e-05,
      "loss": 7.3753,
      "step": 1
    },
    {
      "epoch": 0.00021830486274081756,
      "eval_loss": 2.728501796722412,
      "eval_runtime": 730.2555,
      "eval_samples_per_second": 10.565,
      "eval_steps_per_second": 2.642,
      "step": 1
    },
    {
      "epoch": 0.00043660972548163513,
      "grad_norm": 188.52349853515625,
      "learning_rate": 2e-05,
      "loss": 7.5658,
      "step": 2
    },
    {
      "epoch": 0.0006549145882224527,
      "grad_norm": 147.88009643554688,
      "learning_rate": 3e-05,
      "loss": 6.325,
      "step": 3
    },
    {
      "epoch": 0.0008732194509632703,
      "grad_norm": 56.96106719970703,
      "learning_rate": 4e-05,
      "loss": 4.1736,
      "step": 4
    },
    {
      "epoch": 0.0010915243137040878,
      "grad_norm": 51.80082702636719,
      "learning_rate": 5e-05,
      "loss": 3.8419,
      "step": 5
    },
    {
      "epoch": 0.0013098291764449053,
      "grad_norm": 41.39720916748047,
      "learning_rate": 6e-05,
      "loss": 2.9984,
      "step": 6
    },
    {
      "epoch": 0.0015281340391857228,
      "grad_norm": 32.141746520996094,
      "learning_rate": 7e-05,
      "loss": 2.4535,
      "step": 7
    },
    {
      "epoch": 0.0017464389019265405,
      "grad_norm": 34.04977798461914,
      "learning_rate": 8e-05,
      "loss": 2.2783,
      "step": 8
    },
    {
      "epoch": 0.0019647437646673578,
      "grad_norm": 23.786035537719727,
      "learning_rate": 9e-05,
      "loss": 2.4103,
      "step": 9
    },
    {
      "epoch": 0.0021830486274081757,
      "grad_norm": 23.26265525817871,
      "learning_rate": 0.0001,
      "loss": 1.9067,
      "step": 10
    },
    {
      "epoch": 0.002401353490148993,
      "grad_norm": 26.522775650024414,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.9491,
      "step": 11
    },
    {
      "epoch": 0.0026196583528898107,
      "grad_norm": 23.938302993774414,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.9849,
      "step": 12
    },
    {
      "epoch": 0.002837963215630628,
      "grad_norm": 20.957582473754883,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.7137,
      "step": 13
    },
    {
      "epoch": 0.0030562680783714456,
      "grad_norm": 22.476621627807617,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.8734,
      "step": 14
    },
    {
      "epoch": 0.003274572941112263,
      "grad_norm": 21.35898780822754,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.3322,
      "step": 15
    },
    {
      "epoch": 0.003492877803853081,
      "grad_norm": 27.492908477783203,
      "learning_rate": 9.975414512725057e-05,
      "loss": 2.1707,
      "step": 16
    },
    {
      "epoch": 0.0037111826665938985,
      "grad_norm": 19.75967025756836,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.3851,
      "step": 17
    },
    {
      "epoch": 0.0039294875293347156,
      "grad_norm": 16.00577735900879,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.5938,
      "step": 18
    },
    {
      "epoch": 0.0041477923920755335,
      "grad_norm": 20.51640510559082,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.4207,
      "step": 19
    },
    {
      "epoch": 0.004366097254816351,
      "grad_norm": 16.361709594726562,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.5419,
      "step": 20
    },
    {
      "epoch": 0.0045844021175571684,
      "grad_norm": 18.289527893066406,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.0772,
      "step": 21
    },
    {
      "epoch": 0.004802706980297986,
      "grad_norm": 22.397504806518555,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.783,
      "step": 22
    },
    {
      "epoch": 0.005021011843038803,
      "grad_norm": 18.129150390625,
      "learning_rate": 9.884934153917997e-05,
      "loss": 1.3098,
      "step": 23
    },
    {
      "epoch": 0.005239316705779621,
      "grad_norm": 19.402833938598633,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.2821,
      "step": 24
    },
    {
      "epoch": 0.005457621568520438,
      "grad_norm": 30.574670791625977,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.3678,
      "step": 25
    },
    {
      "epoch": 0.005675926431261256,
      "grad_norm": 26.911649703979492,
      "learning_rate": 9.826044551386744e-05,
      "loss": 1.4161,
      "step": 26
    },
    {
      "epoch": 0.005894231294002074,
      "grad_norm": 14.460214614868164,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.4996,
      "step": 27
    },
    {
      "epoch": 0.006112536156742891,
      "grad_norm": 23.522342681884766,
      "learning_rate": 9.780178907671789e-05,
      "loss": 1.0764,
      "step": 28
    },
    {
      "epoch": 0.006330841019483709,
      "grad_norm": 24.953136444091797,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.5446,
      "step": 29
    },
    {
      "epoch": 0.006549145882224526,
      "grad_norm": 23.39252471923828,
      "learning_rate": 9.729086208503174e-05,
      "loss": 1.725,
      "step": 30
    },
    {
      "epoch": 0.006767450744965344,
      "grad_norm": 35.23050308227539,
      "learning_rate": 9.701596950580806e-05,
      "loss": 1.2337,
      "step": 31
    },
    {
      "epoch": 0.006985755607706162,
      "grad_norm": 23.742778778076172,
      "learning_rate": 9.672822322997305e-05,
      "loss": 1.161,
      "step": 32
    },
    {
      "epoch": 0.007204060470446979,
      "grad_norm": 18.19499397277832,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7297,
      "step": 33
    },
    {
      "epoch": 0.007422365333187797,
      "grad_norm": 24.505098342895508,
      "learning_rate": 9.611448774886924e-05,
      "loss": 1.2868,
      "step": 34
    },
    {
      "epoch": 0.007640670195928614,
      "grad_norm": 24.310970306396484,
      "learning_rate": 9.578866633275288e-05,
      "loss": 1.2301,
      "step": 35
    },
    {
      "epoch": 0.007858975058669431,
      "grad_norm": 17.73895263671875,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.3757,
      "step": 36
    },
    {
      "epoch": 0.00807727992141025,
      "grad_norm": 18.120927810668945,
      "learning_rate": 9.509956150664796e-05,
      "loss": 1.1695,
      "step": 37
    },
    {
      "epoch": 0.008295584784151067,
      "grad_norm": 19.693620681762695,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.835,
      "step": 38
    },
    {
      "epoch": 0.008513889646891884,
      "grad_norm": 16.011274337768555,
      "learning_rate": 9.43611409721806e-05,
      "loss": 1.9548,
      "step": 39
    },
    {
      "epoch": 0.008732194509632703,
      "grad_norm": 18.945898056030273,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.9979,
      "step": 40
    },
    {
      "epoch": 0.00895049937237352,
      "grad_norm": 14.817151069641113,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.5393,
      "step": 41
    },
    {
      "epoch": 0.009168804235114337,
      "grad_norm": 17.74724578857422,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.2671,
      "step": 42
    },
    {
      "epoch": 0.009387109097855154,
      "grad_norm": 23.253944396972656,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.5293,
      "step": 43
    },
    {
      "epoch": 0.009605413960595973,
      "grad_norm": 17.558008193969727,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.7826,
      "step": 44
    },
    {
      "epoch": 0.00982371882333679,
      "grad_norm": 17.273805618286133,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8188,
      "step": 45
    },
    {
      "epoch": 0.010042023686077607,
      "grad_norm": 29.831523895263672,
      "learning_rate": 9.140044155740101e-05,
      "loss": 2.2406,
      "step": 46
    },
    {
      "epoch": 0.010260328548818426,
      "grad_norm": 37.47415542602539,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.6603,
      "step": 47
    },
    {
      "epoch": 0.010478633411559243,
      "grad_norm": 21.16242218017578,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.3838,
      "step": 48
    },
    {
      "epoch": 0.01069693827430006,
      "grad_norm": 32.22922134399414,
      "learning_rate": 8.995939984474624e-05,
      "loss": 2.6782,
      "step": 49
    },
    {
      "epoch": 0.010915243137040877,
      "grad_norm": 39.75159454345703,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.8772,
      "step": 50
    },
    {
      "epoch": 0.010915243137040877,
      "eval_loss": 0.39272409677505493,
      "eval_runtime": 733.727,
      "eval_samples_per_second": 10.515,
      "eval_steps_per_second": 2.629,
      "step": 50
    },
    {
      "epoch": 0.011133547999781696,
      "grad_norm": 45.654075622558594,
      "learning_rate": 8.894386393810563e-05,
      "loss": 2.172,
      "step": 51
    },
    {
      "epoch": 0.011351852862522513,
      "grad_norm": 17.691335678100586,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.8694,
      "step": 52
    },
    {
      "epoch": 0.01157015772526333,
      "grad_norm": 11.43874454498291,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.0365,
      "step": 53
    },
    {
      "epoch": 0.011788462588004148,
      "grad_norm": 9.334946632385254,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.8827,
      "step": 54
    },
    {
      "epoch": 0.012006767450744965,
      "grad_norm": 8.754205703735352,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.0497,
      "step": 55
    },
    {
      "epoch": 0.012225072313485782,
      "grad_norm": 10.076279640197754,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.9138,
      "step": 56
    },
    {
      "epoch": 0.012443377176226601,
      "grad_norm": 8.010160446166992,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.0704,
      "step": 57
    },
    {
      "epoch": 0.012661682038967418,
      "grad_norm": 11.856115341186523,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.3049,
      "step": 58
    },
    {
      "epoch": 0.012879986901708235,
      "grad_norm": 12.080299377441406,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.6587,
      "step": 59
    },
    {
      "epoch": 0.013098291764449052,
      "grad_norm": 10.92935562133789,
      "learning_rate": 8.386407858128706e-05,
      "loss": 1.1809,
      "step": 60
    },
    {
      "epoch": 0.013316596627189871,
      "grad_norm": 9.630249977111816,
      "learning_rate": 8.32512286056924e-05,
      "loss": 1.1388,
      "step": 61
    },
    {
      "epoch": 0.013534901489930688,
      "grad_norm": 9.779946327209473,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.9071,
      "step": 62
    },
    {
      "epoch": 0.013753206352671505,
      "grad_norm": 9.861835479736328,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.8605,
      "step": 63
    },
    {
      "epoch": 0.013971511215412324,
      "grad_norm": 10.891703605651855,
      "learning_rate": 8.135881792367686e-05,
      "loss": 1.3454,
      "step": 64
    },
    {
      "epoch": 0.014189816078153141,
      "grad_norm": 6.902316570281982,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.6042,
      "step": 65
    },
    {
      "epoch": 0.014408120940893958,
      "grad_norm": 13.346320152282715,
      "learning_rate": 8.005405736415126e-05,
      "loss": 1.1173,
      "step": 66
    },
    {
      "epoch": 0.014626425803634775,
      "grad_norm": 14.308423042297363,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.0399,
      "step": 67
    },
    {
      "epoch": 0.014844730666375594,
      "grad_norm": 15.66178035736084,
      "learning_rate": 7.871643313414718e-05,
      "loss": 1.2423,
      "step": 68
    },
    {
      "epoch": 0.015063035529116411,
      "grad_norm": 9.643138885498047,
      "learning_rate": 7.803575286758364e-05,
      "loss": 1.0394,
      "step": 69
    },
    {
      "epoch": 0.015281340391857228,
      "grad_norm": 11.629717826843262,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.8529,
      "step": 70
    },
    {
      "epoch": 0.015499645254598047,
      "grad_norm": 9.830907821655273,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.9022,
      "step": 71
    },
    {
      "epoch": 0.015717950117338862,
      "grad_norm": 11.573919296264648,
      "learning_rate": 7.594847868906076e-05,
      "loss": 1.0336,
      "step": 72
    },
    {
      "epoch": 0.01593625498007968,
      "grad_norm": 10.771193504333496,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.9029,
      "step": 73
    },
    {
      "epoch": 0.0161545598428205,
      "grad_norm": 11.649493217468262,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.9517,
      "step": 74
    },
    {
      "epoch": 0.016372864705561315,
      "grad_norm": 10.555853843688965,
      "learning_rate": 7.379736965185368e-05,
      "loss": 1.0837,
      "step": 75
    },
    {
      "epoch": 0.016591169568302134,
      "grad_norm": 12.330526351928711,
      "learning_rate": 7.30670581489344e-05,
      "loss": 1.3982,
      "step": 76
    },
    {
      "epoch": 0.016809474431042953,
      "grad_norm": 8.561495780944824,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.5557,
      "step": 77
    },
    {
      "epoch": 0.017027779293783768,
      "grad_norm": 10.27099609375,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.9408,
      "step": 78
    },
    {
      "epoch": 0.017246084156524587,
      "grad_norm": 19.418272018432617,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6873,
      "step": 79
    },
    {
      "epoch": 0.017464389019265406,
      "grad_norm": 15.824254989624023,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.8229,
      "step": 80
    },
    {
      "epoch": 0.01768269388200622,
      "grad_norm": 16.62073516845703,
      "learning_rate": 6.932495846462261e-05,
      "loss": 1.2136,
      "step": 81
    },
    {
      "epoch": 0.01790099874474704,
      "grad_norm": 11.906272888183594,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.5912,
      "step": 82
    },
    {
      "epoch": 0.01811930360748786,
      "grad_norm": 9.35510540008545,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6718,
      "step": 83
    },
    {
      "epoch": 0.018337608470228674,
      "grad_norm": 18.38622283935547,
      "learning_rate": 6.701465872208216e-05,
      "loss": 1.6497,
      "step": 84
    },
    {
      "epoch": 0.018555913332969493,
      "grad_norm": 19.09699058532715,
      "learning_rate": 6.623497346023418e-05,
      "loss": 1.2194,
      "step": 85
    },
    {
      "epoch": 0.018774218195710308,
      "grad_norm": 13.23594856262207,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.7641,
      "step": 86
    },
    {
      "epoch": 0.018992523058451127,
      "grad_norm": 13.044976234436035,
      "learning_rate": 6.466250186922325e-05,
      "loss": 1.1724,
      "step": 87
    },
    {
      "epoch": 0.019210827921191945,
      "grad_norm": 17.994647979736328,
      "learning_rate": 6.387014543809223e-05,
      "loss": 1.4368,
      "step": 88
    },
    {
      "epoch": 0.01942913278393276,
      "grad_norm": 11.946012496948242,
      "learning_rate": 6.307399704769099e-05,
      "loss": 1.17,
      "step": 89
    },
    {
      "epoch": 0.01964743764667358,
      "grad_norm": 13.894006729125977,
      "learning_rate": 6.227427435703997e-05,
      "loss": 1.0433,
      "step": 90
    },
    {
      "epoch": 0.0198657425094144,
      "grad_norm": 10.097606658935547,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.7098,
      "step": 91
    },
    {
      "epoch": 0.020084047372155214,
      "grad_norm": 15.475691795349121,
      "learning_rate": 6.066498153718735e-05,
      "loss": 1.2925,
      "step": 92
    },
    {
      "epoch": 0.020302352234896032,
      "grad_norm": 15.94665241241455,
      "learning_rate": 5.985585137257401e-05,
      "loss": 1.0256,
      "step": 93
    },
    {
      "epoch": 0.02052065709763685,
      "grad_norm": 8.952512741088867,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.5552,
      "step": 94
    },
    {
      "epoch": 0.020738961960377666,
      "grad_norm": 14.608858108520508,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.9805,
      "step": 95
    },
    {
      "epoch": 0.020957266823118485,
      "grad_norm": 9.33961296081543,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.32,
      "step": 96
    },
    {
      "epoch": 0.021175571685859304,
      "grad_norm": 16.70509147644043,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.931,
      "step": 97
    },
    {
      "epoch": 0.02139387654860012,
      "grad_norm": 17.932279586791992,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.3505,
      "step": 98
    },
    {
      "epoch": 0.021612181411340938,
      "grad_norm": 25.598703384399414,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.713,
      "step": 99
    },
    {
      "epoch": 0.021830486274081753,
      "grad_norm": 32.65713119506836,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 2.8362,
      "step": 100
    },
    {
      "epoch": 0.021830486274081753,
      "eval_loss": 0.240097314119339,
      "eval_runtime": 734.0134,
      "eval_samples_per_second": 10.511,
      "eval_steps_per_second": 2.628,
      "step": 100
    },
    {
      "epoch": 0.022048791136822572,
      "grad_norm": 10.253203392028809,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.87,
      "step": 101
    },
    {
      "epoch": 0.02226709599956339,
      "grad_norm": 10.306340217590332,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.8731,
      "step": 102
    },
    {
      "epoch": 0.022485400862304206,
      "grad_norm": 8.861244201660156,
      "learning_rate": 5.165316846586541e-05,
      "loss": 1.086,
      "step": 103
    },
    {
      "epoch": 0.022703705725045025,
      "grad_norm": 8.404253959655762,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.771,
      "step": 104
    },
    {
      "epoch": 0.022922010587785844,
      "grad_norm": 9.372161865234375,
      "learning_rate": 5e-05,
      "loss": 1.0651,
      "step": 105
    },
    {
      "epoch": 0.02314031545052666,
      "grad_norm": 10.037277221679688,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.0783,
      "step": 106
    },
    {
      "epoch": 0.023358620313267478,
      "grad_norm": 7.36504602432251,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.5935,
      "step": 107
    },
    {
      "epoch": 0.023576925176008297,
      "grad_norm": 8.560314178466797,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.716,
      "step": 108
    },
    {
      "epoch": 0.023795230038749112,
      "grad_norm": 7.645807266235352,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.8563,
      "step": 109
    },
    {
      "epoch": 0.02401353490148993,
      "grad_norm": 8.726021766662598,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.7333,
      "step": 110
    },
    {
      "epoch": 0.02423183976423075,
      "grad_norm": 6.535979270935059,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.5818,
      "step": 111
    },
    {
      "epoch": 0.024450144626971565,
      "grad_norm": 7.491533279418945,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8409,
      "step": 112
    },
    {
      "epoch": 0.024668449489712384,
      "grad_norm": 6.81107234954834,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.7046,
      "step": 113
    },
    {
      "epoch": 0.024886754352453203,
      "grad_norm": 8.90746784210205,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.7056,
      "step": 114
    },
    {
      "epoch": 0.025105059215194018,
      "grad_norm": 7.0315399169921875,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.5721,
      "step": 115
    },
    {
      "epoch": 0.025323364077934837,
      "grad_norm": 9.318288803100586,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.9053,
      "step": 116
    },
    {
      "epoch": 0.025541668940675652,
      "grad_norm": 7.193863868713379,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.6038,
      "step": 117
    },
    {
      "epoch": 0.02575997380341647,
      "grad_norm": 9.514883041381836,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.5982,
      "step": 118
    },
    {
      "epoch": 0.02597827866615729,
      "grad_norm": 7.204457759857178,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.73,
      "step": 119
    },
    {
      "epoch": 0.026196583528898105,
      "grad_norm": 10.129067420959473,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.8851,
      "step": 120
    },
    {
      "epoch": 0.026414888391638924,
      "grad_norm": 9.055540084838867,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.9419,
      "step": 121
    },
    {
      "epoch": 0.026633193254379742,
      "grad_norm": 8.0108060836792,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.8642,
      "step": 122
    },
    {
      "epoch": 0.026851498117120558,
      "grad_norm": 10.199997901916504,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.5764,
      "step": 123
    },
    {
      "epoch": 0.027069802979861377,
      "grad_norm": 10.891366958618164,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.6852,
      "step": 124
    },
    {
      "epoch": 0.027288107842602195,
      "grad_norm": 8.032575607299805,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.6096,
      "step": 125
    },
    {
      "epoch": 0.02750641270534301,
      "grad_norm": 7.451718330383301,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.4478,
      "step": 126
    },
    {
      "epoch": 0.02772471756808383,
      "grad_norm": 10.194560050964355,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.8905,
      "step": 127
    },
    {
      "epoch": 0.027943022430824648,
      "grad_norm": 8.42761516571045,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7367,
      "step": 128
    },
    {
      "epoch": 0.028161327293565463,
      "grad_norm": 11.376543045043945,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.74,
      "step": 129
    },
    {
      "epoch": 0.028379632156306282,
      "grad_norm": 7.129746437072754,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.673,
      "step": 130
    },
    {
      "epoch": 0.028597937019047098,
      "grad_norm": 10.327281951904297,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.628,
      "step": 131
    },
    {
      "epoch": 0.028816241881787916,
      "grad_norm": 8.760981559753418,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.5678,
      "step": 132
    },
    {
      "epoch": 0.029034546744528735,
      "grad_norm": 12.513045310974121,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.8919,
      "step": 133
    },
    {
      "epoch": 0.02925285160726955,
      "grad_norm": 9.480098724365234,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.5844,
      "step": 134
    },
    {
      "epoch": 0.02947115647001037,
      "grad_norm": 10.187668800354004,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7816,
      "step": 135
    },
    {
      "epoch": 0.029689461332751188,
      "grad_norm": 8.392868041992188,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.5015,
      "step": 136
    },
    {
      "epoch": 0.029907766195492003,
      "grad_norm": 10.995698928833008,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.8457,
      "step": 137
    },
    {
      "epoch": 0.030126071058232822,
      "grad_norm": 14.566420555114746,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.9466,
      "step": 138
    },
    {
      "epoch": 0.03034437592097364,
      "grad_norm": 9.185835838317871,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.7234,
      "step": 139
    },
    {
      "epoch": 0.030562680783714456,
      "grad_norm": 11.179950714111328,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.7318,
      "step": 140
    },
    {
      "epoch": 0.030780985646455275,
      "grad_norm": 11.267284393310547,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.5025,
      "step": 141
    },
    {
      "epoch": 0.030999290509196094,
      "grad_norm": 23.727296829223633,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.7454,
      "step": 142
    },
    {
      "epoch": 0.03121759537193691,
      "grad_norm": 12.585330963134766,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.5683,
      "step": 143
    },
    {
      "epoch": 0.031435900234677724,
      "grad_norm": 6.629660129547119,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.316,
      "step": 144
    },
    {
      "epoch": 0.03165420509741854,
      "grad_norm": 16.88101577758789,
      "learning_rate": 1.928936436551661e-05,
      "loss": 1.3632,
      "step": 145
    },
    {
      "epoch": 0.03187250996015936,
      "grad_norm": 12.397906303405762,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 1.5565,
      "step": 146
    },
    {
      "epoch": 0.03209081482290018,
      "grad_norm": 9.401056289672852,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.6269,
      "step": 147
    },
    {
      "epoch": 0.032309119685641,
      "grad_norm": 9.893758773803711,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.762,
      "step": 148
    },
    {
      "epoch": 0.03252742454838182,
      "grad_norm": 20.863826751708984,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.4386,
      "step": 149
    },
    {
      "epoch": 0.03274572941112263,
      "grad_norm": 26.667558670043945,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 2.2714,
      "step": 150
    },
    {
      "epoch": 0.03274572941112263,
      "eval_loss": 0.19777049124240875,
      "eval_runtime": 734.7085,
      "eval_samples_per_second": 10.501,
      "eval_steps_per_second": 2.626,
      "step": 150
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.146497013481472e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}