{
  "best_metric": 0.6043992638587952,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.10933442667760011,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005466721333880005,
      "grad_norm": 1.5685559511184692,
      "learning_rate": 1e-05,
      "loss": 0.6201,
      "step": 1
    },
    {
      "epoch": 0.0005466721333880005,
      "eval_loss": 1.2423924207687378,
      "eval_runtime": 317.3681,
      "eval_samples_per_second": 9.708,
      "eval_steps_per_second": 2.429,
      "step": 1
    },
    {
      "epoch": 0.001093344266776001,
      "grad_norm": 1.7842057943344116,
      "learning_rate": 2e-05,
      "loss": 0.7283,
      "step": 2
    },
    {
      "epoch": 0.0016400164001640015,
      "grad_norm": 0.8638198971748352,
      "learning_rate": 3e-05,
      "loss": 0.7406,
      "step": 3
    },
    {
      "epoch": 0.002186688533552002,
      "grad_norm": 1.0290772914886475,
      "learning_rate": 4e-05,
      "loss": 0.7696,
      "step": 4
    },
    {
      "epoch": 0.0027333606669400026,
      "grad_norm": 0.8170171976089478,
      "learning_rate": 5e-05,
      "loss": 0.7364,
      "step": 5
    },
    {
      "epoch": 0.003280032800328003,
      "grad_norm": 0.41177359223365784,
      "learning_rate": 6e-05,
      "loss": 0.752,
      "step": 6
    },
    {
      "epoch": 0.003826704933716004,
      "grad_norm": 0.3283713757991791,
      "learning_rate": 7e-05,
      "loss": 0.7753,
      "step": 7
    },
    {
      "epoch": 0.004373377067104004,
      "grad_norm": 0.289739727973938,
      "learning_rate": 8e-05,
      "loss": 0.7008,
      "step": 8
    },
    {
      "epoch": 0.004920049200492005,
      "grad_norm": 0.559328556060791,
      "learning_rate": 9e-05,
      "loss": 0.7024,
      "step": 9
    },
    {
      "epoch": 0.005466721333880005,
      "grad_norm": 0.3776341676712036,
      "learning_rate": 0.0001,
      "loss": 0.6434,
      "step": 10
    },
    {
      "epoch": 0.006013393467268006,
      "grad_norm": 0.4670841097831726,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.6869,
      "step": 11
    },
    {
      "epoch": 0.006560065600656006,
      "grad_norm": 0.393575519323349,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.705,
      "step": 12
    },
    {
      "epoch": 0.007106737734044007,
      "grad_norm": 0.3016532063484192,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.6966,
      "step": 13
    },
    {
      "epoch": 0.007653409867432008,
      "grad_norm": 0.3321461081504822,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.6701,
      "step": 14
    },
    {
      "epoch": 0.008200082000820008,
      "grad_norm": 0.2765994369983673,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.6431,
      "step": 15
    },
    {
      "epoch": 0.008746754134208008,
      "grad_norm": 0.3029332756996155,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.6934,
      "step": 16
    },
    {
      "epoch": 0.00929342626759601,
      "grad_norm": 0.2704845666885376,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.6768,
      "step": 17
    },
    {
      "epoch": 0.00984009840098401,
      "grad_norm": 0.29650449752807617,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.7132,
      "step": 18
    },
    {
      "epoch": 0.01038677053437201,
      "grad_norm": 0.36541548371315,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.6589,
      "step": 19
    },
    {
      "epoch": 0.01093344266776001,
      "grad_norm": 0.3385908603668213,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6724,
      "step": 20
    },
    {
      "epoch": 0.011480114801148012,
      "grad_norm": 0.27720966935157776,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.6729,
      "step": 21
    },
    {
      "epoch": 0.012026786934536012,
      "grad_norm": 0.24973812699317932,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.7068,
      "step": 22
    },
    {
      "epoch": 0.012573459067924012,
      "grad_norm": 0.27048227190971375,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6707,
      "step": 23
    },
    {
      "epoch": 0.013120131201312012,
      "grad_norm": 0.28500187397003174,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.647,
      "step": 24
    },
    {
      "epoch": 0.013666803334700014,
      "grad_norm": 0.27583548426628113,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.5803,
      "step": 25
    },
    {
      "epoch": 0.014213475468088014,
      "grad_norm": 0.3138293921947479,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.7286,
      "step": 26
    },
    {
      "epoch": 0.014760147601476014,
      "grad_norm": 0.32263466715812683,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.6329,
      "step": 27
    },
    {
      "epoch": 0.015306819734864016,
      "grad_norm": 0.32008203864097595,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6561,
      "step": 28
    },
    {
      "epoch": 0.015853491868252016,
      "grad_norm": 0.3512203097343445,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7223,
      "step": 29
    },
    {
      "epoch": 0.016400164001640016,
      "grad_norm": 0.3767859637737274,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.6481,
      "step": 30
    },
    {
      "epoch": 0.016946836135028016,
      "grad_norm": 0.3525494337081909,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.6341,
      "step": 31
    },
    {
      "epoch": 0.017493508268416016,
      "grad_norm": 0.46691110730171204,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7674,
      "step": 32
    },
    {
      "epoch": 0.018040180401804017,
      "grad_norm": 0.41331732273101807,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.6584,
      "step": 33
    },
    {
      "epoch": 0.01858685253519202,
      "grad_norm": 0.5147906541824341,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.7344,
      "step": 34
    },
    {
      "epoch": 0.01913352466858002,
      "grad_norm": 0.5044989585876465,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7817,
      "step": 35
    },
    {
      "epoch": 0.01968019680196802,
      "grad_norm": 0.511785626411438,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.6783,
      "step": 36
    },
    {
      "epoch": 0.02022686893535602,
      "grad_norm": 0.5214494466781616,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.7073,
      "step": 37
    },
    {
      "epoch": 0.02077354106874402,
      "grad_norm": 0.6733724474906921,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7379,
      "step": 38
    },
    {
      "epoch": 0.02132021320213202,
      "grad_norm": 0.5296518206596375,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.623,
      "step": 39
    },
    {
      "epoch": 0.02186688533552002,
      "grad_norm": 0.5682909488677979,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7561,
      "step": 40
    },
    {
      "epoch": 0.022413557468908024,
      "grad_norm": 0.6005738377571106,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.7669,
      "step": 41
    },
    {
      "epoch": 0.022960229602296024,
      "grad_norm": 0.6031546592712402,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.7992,
      "step": 42
    },
    {
      "epoch": 0.023506901735684024,
      "grad_norm": 0.5350504517555237,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7114,
      "step": 43
    },
    {
      "epoch": 0.024053573869072024,
      "grad_norm": 0.5931272506713867,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.69,
      "step": 44
    },
    {
      "epoch": 0.024600246002460024,
      "grad_norm": 0.704857349395752,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.689,
      "step": 45
    },
    {
      "epoch": 0.025146918135848025,
      "grad_norm": 0.6874116659164429,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.8132,
      "step": 46
    },
    {
      "epoch": 0.025693590269236025,
      "grad_norm": 0.8350479006767273,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.6316,
      "step": 47
    },
    {
      "epoch": 0.026240262402624025,
      "grad_norm": 1.0941030979156494,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7244,
      "step": 48
    },
    {
      "epoch": 0.026786934536012028,
      "grad_norm": 0.9311143159866333,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6847,
      "step": 49
    },
    {
      "epoch": 0.02733360666940003,
      "grad_norm": 0.9431465864181519,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.576,
      "step": 50
    },
    {
      "epoch": 0.02733360666940003,
      "eval_loss": 0.6646648049354553,
      "eval_runtime": 318.7933,
      "eval_samples_per_second": 9.665,
      "eval_steps_per_second": 2.418,
      "step": 50
    },
    {
      "epoch": 0.02788027880278803,
      "grad_norm": 0.33106833696365356,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.4668,
      "step": 51
    },
    {
      "epoch": 0.02842695093617603,
      "grad_norm": 0.32308751344680786,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.5081,
      "step": 52
    },
    {
      "epoch": 0.02897362306956403,
      "grad_norm": 0.2541446089744568,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.5991,
      "step": 53
    },
    {
      "epoch": 0.02952029520295203,
      "grad_norm": 0.18958967924118042,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.5753,
      "step": 54
    },
    {
      "epoch": 0.03006696733634003,
      "grad_norm": 0.2008042186498642,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.5626,
      "step": 55
    },
    {
      "epoch": 0.030613639469728032,
      "grad_norm": 0.19314073026180267,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.554,
      "step": 56
    },
    {
      "epoch": 0.031160311603116032,
      "grad_norm": 0.20551298558712006,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.5911,
      "step": 57
    },
    {
      "epoch": 0.03170698373650403,
      "grad_norm": 0.1891486495733261,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.6136,
      "step": 58
    },
    {
      "epoch": 0.03225365586989203,
      "grad_norm": 0.20632842183113098,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.6129,
      "step": 59
    },
    {
      "epoch": 0.03280032800328003,
      "grad_norm": 0.19857889413833618,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.6119,
      "step": 60
    },
    {
      "epoch": 0.03334700013666803,
      "grad_norm": 0.20179690420627594,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.5975,
      "step": 61
    },
    {
      "epoch": 0.03389367227005603,
      "grad_norm": 0.20558011531829834,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.6465,
      "step": 62
    },
    {
      "epoch": 0.03444034440344403,
      "grad_norm": 0.21030567586421967,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.5983,
      "step": 63
    },
    {
      "epoch": 0.03498701653683203,
      "grad_norm": 0.2043226659297943,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.6027,
      "step": 64
    },
    {
      "epoch": 0.03553368867022003,
      "grad_norm": 0.2239697277545929,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.5923,
      "step": 65
    },
    {
      "epoch": 0.03608036080360803,
      "grad_norm": 0.2189861387014389,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.6086,
      "step": 66
    },
    {
      "epoch": 0.03662703293699603,
      "grad_norm": 0.22846335172653198,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6471,
      "step": 67
    },
    {
      "epoch": 0.03717370507038404,
      "grad_norm": 0.21626874804496765,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.62,
      "step": 68
    },
    {
      "epoch": 0.03772037720377204,
      "grad_norm": 0.22324147820472717,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.5188,
      "step": 69
    },
    {
      "epoch": 0.03826704933716004,
      "grad_norm": 0.27362608909606934,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.6001,
      "step": 70
    },
    {
      "epoch": 0.03881372147054804,
      "grad_norm": 0.22006013989448547,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.5981,
      "step": 71
    },
    {
      "epoch": 0.03936039360393604,
      "grad_norm": 0.24898923933506012,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.63,
      "step": 72
    },
    {
      "epoch": 0.03990706573732404,
      "grad_norm": 0.2335711270570755,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.6415,
      "step": 73
    },
    {
      "epoch": 0.04045373787071204,
      "grad_norm": 0.300645112991333,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7114,
      "step": 74
    },
    {
      "epoch": 0.04100041000410004,
      "grad_norm": 0.2474636733531952,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.6156,
      "step": 75
    },
    {
      "epoch": 0.04154708213748804,
      "grad_norm": 0.28472772240638733,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6095,
      "step": 76
    },
    {
      "epoch": 0.04209375427087604,
      "grad_norm": 0.29183119535446167,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7231,
      "step": 77
    },
    {
      "epoch": 0.04264042640426404,
      "grad_norm": 0.3172072768211365,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.6416,
      "step": 78
    },
    {
      "epoch": 0.04318709853765204,
      "grad_norm": 0.35702043771743774,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.66,
      "step": 79
    },
    {
      "epoch": 0.04373377067104004,
      "grad_norm": 0.364234060049057,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.6385,
      "step": 80
    },
    {
      "epoch": 0.04428044280442804,
      "grad_norm": 0.3625519871711731,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.5836,
      "step": 81
    },
    {
      "epoch": 0.04482711493781605,
      "grad_norm": 0.35129520297050476,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.641,
      "step": 82
    },
    {
      "epoch": 0.04537378707120405,
      "grad_norm": 0.36390334367752075,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.6112,
      "step": 83
    },
    {
      "epoch": 0.04592045920459205,
      "grad_norm": 0.47982674837112427,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.7028,
      "step": 84
    },
    {
      "epoch": 0.04646713133798005,
      "grad_norm": 0.40073323249816895,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.6443,
      "step": 85
    },
    {
      "epoch": 0.04701380347136805,
      "grad_norm": 0.4263547956943512,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.626,
      "step": 86
    },
    {
      "epoch": 0.04756047560475605,
      "grad_norm": 0.4399144649505615,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6745,
      "step": 87
    },
    {
      "epoch": 0.04810714773814405,
      "grad_norm": 0.5968857407569885,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7285,
      "step": 88
    },
    {
      "epoch": 0.04865381987153205,
      "grad_norm": 0.6030961275100708,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.6013,
      "step": 89
    },
    {
      "epoch": 0.04920049200492005,
      "grad_norm": 0.5240572094917297,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5845,
      "step": 90
    },
    {
      "epoch": 0.04974716413830805,
      "grad_norm": 0.6258083581924438,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6952,
      "step": 91
    },
    {
      "epoch": 0.05029383627169605,
      "grad_norm": 0.5299344062805176,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.6829,
      "step": 92
    },
    {
      "epoch": 0.05084050840508405,
      "grad_norm": 0.6700068712234497,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7186,
      "step": 93
    },
    {
      "epoch": 0.05138718053847205,
      "grad_norm": 0.6080848574638367,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.697,
      "step": 94
    },
    {
      "epoch": 0.05193385267186005,
      "grad_norm": 0.6662163138389587,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.6736,
      "step": 95
    },
    {
      "epoch": 0.05248052480524805,
      "grad_norm": 0.7447817325592041,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7106,
      "step": 96
    },
    {
      "epoch": 0.053027196938636056,
      "grad_norm": 0.8476828336715698,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.6801,
      "step": 97
    },
    {
      "epoch": 0.053573869072024057,
      "grad_norm": 0.9032142162322998,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.5914,
      "step": 98
    },
    {
      "epoch": 0.05412054120541206,
      "grad_norm": 0.8118094801902771,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.7818,
      "step": 99
    },
    {
      "epoch": 0.05466721333880006,
      "grad_norm": 1.258407711982727,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.6371,
      "step": 100
    },
    {
      "epoch": 0.05466721333880006,
      "eval_loss": 0.6287000775337219,
      "eval_runtime": 318.2705,
      "eval_samples_per_second": 9.68,
      "eval_steps_per_second": 2.422,
      "step": 100
    },
    {
      "epoch": 0.05521388547218806,
      "grad_norm": 0.19034165143966675,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.4066,
      "step": 101
    },
    {
      "epoch": 0.05576055760557606,
      "grad_norm": 0.21388307213783264,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.5452,
      "step": 102
    },
    {
      "epoch": 0.05630722973896406,
      "grad_norm": 0.20722991228103638,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.5275,
      "step": 103
    },
    {
      "epoch": 0.05685390187235206,
      "grad_norm": 0.2075161188840866,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.5133,
      "step": 104
    },
    {
      "epoch": 0.05740057400574006,
      "grad_norm": 0.1850241869688034,
      "learning_rate": 5e-05,
      "loss": 0.5426,
      "step": 105
    },
    {
      "epoch": 0.05794724613912806,
      "grad_norm": 0.1928945928812027,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.5609,
      "step": 106
    },
    {
      "epoch": 0.05849391827251606,
      "grad_norm": 0.19245478510856628,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.5947,
      "step": 107
    },
    {
      "epoch": 0.05904059040590406,
      "grad_norm": 0.1945430338382721,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.6053,
      "step": 108
    },
    {
      "epoch": 0.05958726253929206,
      "grad_norm": 0.1807744801044464,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.5505,
      "step": 109
    },
    {
      "epoch": 0.06013393467268006,
      "grad_norm": 0.1963709145784378,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.5702,
      "step": 110
    },
    {
      "epoch": 0.06068060680606806,
      "grad_norm": 0.1867251843214035,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.6285,
      "step": 111
    },
    {
      "epoch": 0.061227278939456065,
      "grad_norm": 0.20253677666187286,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.592,
      "step": 112
    },
    {
      "epoch": 0.061773951072844065,
      "grad_norm": 0.19805753231048584,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.6037,
      "step": 113
    },
    {
      "epoch": 0.062320623206232065,
      "grad_norm": 0.22108222544193268,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.6076,
      "step": 114
    },
    {
      "epoch": 0.06286729533962006,
      "grad_norm": 0.2066812366247177,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.5932,
      "step": 115
    },
    {
      "epoch": 0.06341396747300806,
      "grad_norm": 0.22471247613430023,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.6044,
      "step": 116
    },
    {
      "epoch": 0.06396063960639606,
      "grad_norm": 0.21643920242786407,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.613,
      "step": 117
    },
    {
      "epoch": 0.06450731173978407,
      "grad_norm": 0.25059255957603455,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.62,
      "step": 118
    },
    {
      "epoch": 0.06505398387317206,
      "grad_norm": 0.2656647861003876,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.6234,
      "step": 119
    },
    {
      "epoch": 0.06560065600656007,
      "grad_norm": 0.2614147365093231,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.6128,
      "step": 120
    },
    {
      "epoch": 0.06614732813994807,
      "grad_norm": 0.2318594753742218,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.6268,
      "step": 121
    },
    {
      "epoch": 0.06669400027333607,
      "grad_norm": 0.23655599355697632,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.5969,
      "step": 122
    },
    {
      "epoch": 0.06724067240672407,
      "grad_norm": 0.26997312903404236,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.7177,
      "step": 123
    },
    {
      "epoch": 0.06778734454011207,
      "grad_norm": 0.23019258677959442,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.5786,
      "step": 124
    },
    {
      "epoch": 0.06833401667350007,
      "grad_norm": 0.24995802342891693,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.5704,
      "step": 125
    },
    {
      "epoch": 0.06888068880688807,
      "grad_norm": 0.2818213403224945,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.535,
      "step": 126
    },
    {
      "epoch": 0.06942736094027607,
      "grad_norm": 0.26154807209968567,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.5728,
      "step": 127
    },
    {
      "epoch": 0.06997403307366407,
      "grad_norm": 0.2667124569416046,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.5677,
      "step": 128
    },
    {
      "epoch": 0.07052070520705207,
      "grad_norm": 0.3307899832725525,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.654,
      "step": 129
    },
    {
      "epoch": 0.07106737734044007,
      "grad_norm": 0.3584456741809845,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.6197,
      "step": 130
    },
    {
      "epoch": 0.07161404947382807,
      "grad_norm": 0.3462895452976227,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6547,
      "step": 131
    },
    {
      "epoch": 0.07216072160721607,
      "grad_norm": 0.3121941387653351,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.6364,
      "step": 132
    },
    {
      "epoch": 0.07270739374060407,
      "grad_norm": 0.42693427205085754,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.634,
      "step": 133
    },
    {
      "epoch": 0.07325406587399207,
      "grad_norm": 0.37320294976234436,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.5838,
      "step": 134
    },
    {
      "epoch": 0.07380073800738007,
      "grad_norm": 0.4191465675830841,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7757,
      "step": 135
    },
    {
      "epoch": 0.07434741014076808,
      "grad_norm": 0.45593488216400146,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.7457,
      "step": 136
    },
    {
      "epoch": 0.07489408227415607,
      "grad_norm": 0.4598701298236847,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.7122,
      "step": 137
    },
    {
      "epoch": 0.07544075440754408,
      "grad_norm": 0.5200105309486389,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.6258,
      "step": 138
    },
    {
      "epoch": 0.07598742654093207,
      "grad_norm": 0.4483514726161957,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.6612,
      "step": 139
    },
    {
      "epoch": 0.07653409867432008,
      "grad_norm": 0.4841548502445221,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.5732,
      "step": 140
    },
    {
      "epoch": 0.07708077080770807,
      "grad_norm": 0.4909835457801819,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7197,
      "step": 141
    },
    {
      "epoch": 0.07762744294109608,
      "grad_norm": 0.5816509127616882,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.701,
      "step": 142
    },
    {
      "epoch": 0.07817411507448407,
      "grad_norm": 0.5213097929954529,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.6011,
      "step": 143
    },
    {
      "epoch": 0.07872078720787208,
      "grad_norm": 0.593346357345581,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.6995,
      "step": 144
    },
    {
      "epoch": 0.07926745934126007,
      "grad_norm": 0.6509579420089722,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.6902,
      "step": 145
    },
    {
      "epoch": 0.07981413147464808,
      "grad_norm": 0.6911070942878723,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.6726,
      "step": 146
    },
    {
      "epoch": 0.08036080360803607,
      "grad_norm": 0.7146452069282532,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.6411,
      "step": 147
    },
    {
      "epoch": 0.08090747574142408,
      "grad_norm": 0.8908387422561646,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.7009,
      "step": 148
    },
    {
      "epoch": 0.08145414787481207,
      "grad_norm": 0.7855592370033264,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.5792,
      "step": 149
    },
    {
      "epoch": 0.08200082000820008,
      "grad_norm": 0.8410571217536926,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.5918,
      "step": 150
    },
    {
      "epoch": 0.08200082000820008,
      "eval_loss": 0.607322096824646,
      "eval_runtime": 319.0592,
      "eval_samples_per_second": 9.657,
      "eval_steps_per_second": 2.416,
      "step": 150
    },
    {
      "epoch": 0.08254749214158809,
      "grad_norm": 0.12340952455997467,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.3729,
      "step": 151
    },
    {
      "epoch": 0.08309416427497608,
      "grad_norm": 0.14587201178073883,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.4657,
      "step": 152
    },
    {
      "epoch": 0.08364083640836409,
      "grad_norm": 0.14822916686534882,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.5115,
      "step": 153
    },
    {
      "epoch": 0.08418750854175208,
      "grad_norm": 0.1783442199230194,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.5835,
      "step": 154
    },
    {
      "epoch": 0.08473418067514009,
      "grad_norm": 0.16984927654266357,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.5514,
      "step": 155
    },
    {
      "epoch": 0.08528085280852808,
      "grad_norm": 0.17151455581188202,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.597,
      "step": 156
    },
    {
      "epoch": 0.08582752494191609,
      "grad_norm": 0.16910728812217712,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.5772,
      "step": 157
    },
    {
      "epoch": 0.08637419707530408,
      "grad_norm": 0.17516940832138062,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.567,
      "step": 158
    },
    {
      "epoch": 0.08692086920869209,
      "grad_norm": 0.18733669817447662,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.5565,
      "step": 159
    },
    {
      "epoch": 0.08746754134208008,
      "grad_norm": 0.18877604603767395,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.5908,
      "step": 160
    },
    {
      "epoch": 0.08801421347546809,
      "grad_norm": 0.18422381579875946,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.5614,
      "step": 161
    },
    {
      "epoch": 0.08856088560885608,
      "grad_norm": 0.19738604128360748,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.6375,
      "step": 162
    },
    {
      "epoch": 0.08910755774224409,
      "grad_norm": 0.20399752259254456,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.5726,
      "step": 163
    },
    {
      "epoch": 0.0896542298756321,
      "grad_norm": 0.20180173218250275,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.6027,
      "step": 164
    },
    {
      "epoch": 0.09020090200902009,
      "grad_norm": 0.207729309797287,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.5945,
      "step": 165
    },
    {
      "epoch": 0.0907475741424081,
      "grad_norm": 0.20664362609386444,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.5953,
      "step": 166
    },
    {
      "epoch": 0.09129424627579609,
      "grad_norm": 0.21931584179401398,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.6335,
      "step": 167
    },
    {
      "epoch": 0.0918409184091841,
      "grad_norm": 0.25631073117256165,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.6236,
      "step": 168
    },
    {
      "epoch": 0.09238759054257209,
      "grad_norm": 0.23474138975143433,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.5626,
      "step": 169
    },
    {
      "epoch": 0.0929342626759601,
      "grad_norm": 0.2910461127758026,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.7015,
      "step": 170
    },
    {
      "epoch": 0.09348093480934809,
      "grad_norm": 0.24991028010845184,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.5745,
      "step": 171
    },
    {
      "epoch": 0.0940276069427361,
      "grad_norm": 0.2374863177537918,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.6469,
      "step": 172
    },
    {
      "epoch": 0.09457427907612409,
      "grad_norm": 0.23797538876533508,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.6005,
      "step": 173
    },
    {
      "epoch": 0.0951209512095121,
      "grad_norm": 0.24992460012435913,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.6003,
      "step": 174
    },
    {
      "epoch": 0.09566762334290009,
      "grad_norm": 0.32820799946784973,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.6312,
      "step": 175
    },
    {
      "epoch": 0.0962142954762881,
      "grad_norm": 0.2872135639190674,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.5741,
      "step": 176
    },
    {
      "epoch": 0.09676096760967609,
      "grad_norm": 0.33533141016960144,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.6534,
      "step": 177
    },
    {
      "epoch": 0.0973076397430641,
      "grad_norm": 0.2799094021320343,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.5454,
      "step": 178
    },
    {
      "epoch": 0.0978543118764521,
      "grad_norm": 0.2851297855377197,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.5844,
      "step": 179
    },
    {
      "epoch": 0.0984009840098401,
      "grad_norm": 0.3653263449668884,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6415,
      "step": 180
    },
    {
      "epoch": 0.0989476561432281,
      "grad_norm": 0.34195563197135925,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6724,
      "step": 181
    },
    {
      "epoch": 0.0994943282766161,
      "grad_norm": 0.3807370364665985,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.5891,
      "step": 182
    },
    {
      "epoch": 0.1000410004100041,
      "grad_norm": 0.38535618782043457,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.666,
      "step": 183
    },
    {
      "epoch": 0.1005876725433921,
      "grad_norm": 0.40077871084213257,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.6739,
      "step": 184
    },
    {
      "epoch": 0.1011343446767801,
      "grad_norm": 0.5923600792884827,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.7377,
      "step": 185
    },
    {
      "epoch": 0.1016810168101681,
      "grad_norm": 0.4727908670902252,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.697,
      "step": 186
    },
    {
      "epoch": 0.1022276889435561,
      "grad_norm": 0.5158572196960449,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.8061,
      "step": 187
    },
    {
      "epoch": 0.1027743610769441,
      "grad_norm": 0.4872152507305145,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.618,
      "step": 188
    },
    {
      "epoch": 0.1033210332103321,
      "grad_norm": 0.5072970390319824,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.6356,
      "step": 189
    },
    {
      "epoch": 0.1038677053437201,
      "grad_norm": 0.49133968353271484,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.6823,
      "step": 190
    },
    {
      "epoch": 0.1044143774771081,
      "grad_norm": 0.5545623898506165,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.6271,
      "step": 191
    },
    {
      "epoch": 0.1049610496104961,
      "grad_norm": 0.4876463711261749,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.6235,
      "step": 192
    },
    {
      "epoch": 0.1055077217438841,
      "grad_norm": 0.5758100748062134,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.6521,
      "step": 193
    },
    {
      "epoch": 0.10605439387727211,
      "grad_norm": 0.6422720551490784,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.5958,
      "step": 194
    },
    {
      "epoch": 0.1066010660106601,
      "grad_norm": 0.6343724131584167,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.6019,
      "step": 195
    },
    {
      "epoch": 0.10714773814404811,
      "grad_norm": 0.7225890755653381,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.6374,
      "step": 196
    },
    {
      "epoch": 0.1076944102774361,
      "grad_norm": 0.6141881346702576,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.5586,
      "step": 197
    },
    {
      "epoch": 0.10824108241082411,
      "grad_norm": 0.7632716298103333,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.6225,
      "step": 198
    },
    {
      "epoch": 0.1087877545442121,
      "grad_norm": 0.7372617721557617,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.5753,
      "step": 199
    },
    {
      "epoch": 0.10933442667760011,
      "grad_norm": 0.8108389377593994,
      "learning_rate": 0.0,
      "loss": 0.5894,
      "step": 200
    },
    {
      "epoch": 0.10933442667760011,
      "eval_loss": 0.6043992638587952,
      "eval_runtime": 318.8334,
      "eval_samples_per_second": 9.663,
      "eval_steps_per_second": 2.418,
      "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": 3.78160696786944e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}