{
  "best_metric": 10.353894233703613,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.047702337414533315,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003180155827635554,
      "grad_norm": 0.04820059984922409,
      "learning_rate": 1e-05,
      "loss": 10.3792,
      "step": 1
    },
    {
      "epoch": 0.0003180155827635554,
      "eval_loss": 10.377628326416016,
      "eval_runtime": 13.0677,
      "eval_samples_per_second": 405.275,
      "eval_steps_per_second": 101.319,
      "step": 1
    },
    {
      "epoch": 0.0006360311655271108,
      "grad_norm": 0.04332883656024933,
      "learning_rate": 2e-05,
      "loss": 10.3785,
      "step": 2
    },
    {
      "epoch": 0.0009540467482906663,
      "grad_norm": 0.036125682294368744,
      "learning_rate": 3e-05,
      "loss": 10.38,
      "step": 3
    },
    {
      "epoch": 0.0012720623310542216,
      "grad_norm": 0.03849286213517189,
      "learning_rate": 4e-05,
      "loss": 10.3802,
      "step": 4
    },
    {
      "epoch": 0.0015900779138177772,
      "grad_norm": 0.03251954913139343,
      "learning_rate": 5e-05,
      "loss": 10.3798,
      "step": 5
    },
    {
      "epoch": 0.0019080934965813325,
      "grad_norm": 0.027257749810814857,
      "learning_rate": 6e-05,
      "loss": 10.3793,
      "step": 6
    },
    {
      "epoch": 0.002226109079344888,
      "grad_norm": 0.028928343206644058,
      "learning_rate": 7e-05,
      "loss": 10.3795,
      "step": 7
    },
    {
      "epoch": 0.002544124662108443,
      "grad_norm": 0.023493245244026184,
      "learning_rate": 8e-05,
      "loss": 10.3798,
      "step": 8
    },
    {
      "epoch": 0.0028621402448719985,
      "grad_norm": 0.029313910752534866,
      "learning_rate": 9e-05,
      "loss": 10.3804,
      "step": 9
    },
    {
      "epoch": 0.0031801558276355543,
      "grad_norm": 0.02993670664727688,
      "learning_rate": 0.0001,
      "loss": 10.3797,
      "step": 10
    },
    {
      "epoch": 0.0034981714103991097,
      "grad_norm": 0.030695907771587372,
      "learning_rate": 9.999316524962345e-05,
      "loss": 10.3795,
      "step": 11
    },
    {
      "epoch": 0.003816186993162665,
      "grad_norm": 0.030389390885829926,
      "learning_rate": 9.997266286704631e-05,
      "loss": 10.3801,
      "step": 12
    },
    {
      "epoch": 0.004134202575926221,
      "grad_norm": 0.03839806467294693,
      "learning_rate": 9.993849845741524e-05,
      "loss": 10.3798,
      "step": 13
    },
    {
      "epoch": 0.004452218158689776,
      "grad_norm": 0.03743355721235275,
      "learning_rate": 9.989068136093873e-05,
      "loss": 10.3789,
      "step": 14
    },
    {
      "epoch": 0.0047702337414533315,
      "grad_norm": 0.04195557162165642,
      "learning_rate": 9.98292246503335e-05,
      "loss": 10.379,
      "step": 15
    },
    {
      "epoch": 0.005088249324216886,
      "grad_norm": 0.04913628101348877,
      "learning_rate": 9.975414512725057e-05,
      "loss": 10.3789,
      "step": 16
    },
    {
      "epoch": 0.005406264906980442,
      "grad_norm": 0.043840620666742325,
      "learning_rate": 9.966546331768191e-05,
      "loss": 10.3793,
      "step": 17
    },
    {
      "epoch": 0.005724280489743997,
      "grad_norm": 0.04655149579048157,
      "learning_rate": 9.956320346634876e-05,
      "loss": 10.3796,
      "step": 18
    },
    {
      "epoch": 0.006042296072507553,
      "grad_norm": 0.044875383377075195,
      "learning_rate": 9.944739353007344e-05,
      "loss": 10.3781,
      "step": 19
    },
    {
      "epoch": 0.006360311655271109,
      "grad_norm": 0.05200745165348053,
      "learning_rate": 9.931806517013612e-05,
      "loss": 10.3761,
      "step": 20
    },
    {
      "epoch": 0.0066783272380346636,
      "grad_norm": 0.04136663302779198,
      "learning_rate": 9.917525374361912e-05,
      "loss": 10.3793,
      "step": 21
    },
    {
      "epoch": 0.006996342820798219,
      "grad_norm": 0.054821502417325974,
      "learning_rate": 9.901899829374047e-05,
      "loss": 10.3771,
      "step": 22
    },
    {
      "epoch": 0.007314358403561774,
      "grad_norm": 0.06425836682319641,
      "learning_rate": 9.884934153917997e-05,
      "loss": 10.3778,
      "step": 23
    },
    {
      "epoch": 0.00763237398632533,
      "grad_norm": 0.0892687663435936,
      "learning_rate": 9.86663298624003e-05,
      "loss": 10.3767,
      "step": 24
    },
    {
      "epoch": 0.007950389569088886,
      "grad_norm": 0.08915107697248459,
      "learning_rate": 9.847001329696653e-05,
      "loss": 10.3758,
      "step": 25
    },
    {
      "epoch": 0.008268405151852442,
      "grad_norm": 0.10310197621583939,
      "learning_rate": 9.826044551386744e-05,
      "loss": 10.3759,
      "step": 26
    },
    {
      "epoch": 0.008586420734615996,
      "grad_norm": 0.1294308304786682,
      "learning_rate": 9.803768380684242e-05,
      "loss": 10.373,
      "step": 27
    },
    {
      "epoch": 0.008904436317379551,
      "grad_norm": 0.1510711908340454,
      "learning_rate": 9.780178907671789e-05,
      "loss": 10.372,
      "step": 28
    },
    {
      "epoch": 0.009222451900143107,
      "grad_norm": 0.14311803877353668,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3683,
      "step": 29
    },
    {
      "epoch": 0.009540467482906663,
      "grad_norm": 0.11588717252016068,
      "learning_rate": 9.729086208503174e-05,
      "loss": 10.3722,
      "step": 30
    },
    {
      "epoch": 0.009858483065670217,
      "grad_norm": 0.13991692662239075,
      "learning_rate": 9.701596950580806e-05,
      "loss": 10.3698,
      "step": 31
    },
    {
      "epoch": 0.010176498648433773,
      "grad_norm": 0.12399426847696304,
      "learning_rate": 9.672822322997305e-05,
      "loss": 10.3682,
      "step": 32
    },
    {
      "epoch": 0.010494514231197329,
      "grad_norm": 0.12669697403907776,
      "learning_rate": 9.642770192448536e-05,
      "loss": 10.368,
      "step": 33
    },
    {
      "epoch": 0.010812529813960884,
      "grad_norm": 0.09879854321479797,
      "learning_rate": 9.611448774886924e-05,
      "loss": 10.3674,
      "step": 34
    },
    {
      "epoch": 0.01113054539672444,
      "grad_norm": 0.1339942067861557,
      "learning_rate": 9.578866633275288e-05,
      "loss": 10.3704,
      "step": 35
    },
    {
      "epoch": 0.011448560979487994,
      "grad_norm": 0.11396101117134094,
      "learning_rate": 9.545032675245813e-05,
      "loss": 10.3679,
      "step": 36
    },
    {
      "epoch": 0.01176657656225155,
      "grad_norm": 0.10969138890504837,
      "learning_rate": 9.509956150664796e-05,
      "loss": 10.362,
      "step": 37
    },
    {
      "epoch": 0.012084592145015106,
      "grad_norm": 0.1854265183210373,
      "learning_rate": 9.473646649103818e-05,
      "loss": 10.373,
      "step": 38
    },
    {
      "epoch": 0.012402607727778662,
      "grad_norm": 0.16093304753303528,
      "learning_rate": 9.43611409721806e-05,
      "loss": 10.3641,
      "step": 39
    },
    {
      "epoch": 0.012720623310542217,
      "grad_norm": 0.19819724559783936,
      "learning_rate": 9.397368756032445e-05,
      "loss": 10.37,
      "step": 40
    },
    {
      "epoch": 0.013038638893305771,
      "grad_norm": 0.22287717461585999,
      "learning_rate": 9.357421218136386e-05,
      "loss": 10.3613,
      "step": 41
    },
    {
      "epoch": 0.013356654476069327,
      "grad_norm": 0.21624359488487244,
      "learning_rate": 9.316282404787871e-05,
      "loss": 10.3678,
      "step": 42
    },
    {
      "epoch": 0.013674670058832883,
      "grad_norm": 0.1837552934885025,
      "learning_rate": 9.273963562927695e-05,
      "loss": 10.3703,
      "step": 43
    },
    {
      "epoch": 0.013992685641596439,
      "grad_norm": 0.19557404518127441,
      "learning_rate": 9.230476262104677e-05,
      "loss": 10.3679,
      "step": 44
    },
    {
      "epoch": 0.014310701224359994,
      "grad_norm": 0.20213252305984497,
      "learning_rate": 9.185832391312644e-05,
      "loss": 10.3695,
      "step": 45
    },
    {
      "epoch": 0.014628716807123548,
      "grad_norm": 0.27823758125305176,
      "learning_rate": 9.140044155740101e-05,
      "loss": 10.3584,
      "step": 46
    },
    {
      "epoch": 0.014946732389887104,
      "grad_norm": 0.2914884686470032,
      "learning_rate": 9.093124073433463e-05,
      "loss": 10.3635,
      "step": 47
    },
    {
      "epoch": 0.01526474797265066,
      "grad_norm": 0.29478126764297485,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.3615,
      "step": 48
    },
    {
      "epoch": 0.015582763555414216,
      "grad_norm": 0.3077702522277832,
      "learning_rate": 8.995939984474624e-05,
      "loss": 10.3596,
      "step": 49
    },
    {
      "epoch": 0.01590077913817777,
      "grad_norm": 0.26585403084754944,
      "learning_rate": 8.945702546981969e-05,
      "loss": 10.3563,
      "step": 50
    },
    {
      "epoch": 0.01590077913817777,
      "eval_loss": 10.362837791442871,
      "eval_runtime": 13.1213,
      "eval_samples_per_second": 403.619,
      "eval_steps_per_second": 100.905,
      "step": 50
    },
    {
      "epoch": 0.016218794720941326,
      "grad_norm": 0.17760102450847626,
      "learning_rate": 8.894386393810563e-05,
      "loss": 10.365,
      "step": 51
    },
    {
      "epoch": 0.016536810303704883,
      "grad_norm": 0.1078275740146637,
      "learning_rate": 8.842005554284296e-05,
      "loss": 10.3663,
      "step": 52
    },
    {
      "epoch": 0.016854825886468437,
      "grad_norm": 0.10713940113782883,
      "learning_rate": 8.788574348801675e-05,
      "loss": 10.3665,
      "step": 53
    },
    {
      "epoch": 0.01717284146923199,
      "grad_norm": 0.09926675260066986,
      "learning_rate": 8.73410738492077e-05,
      "loss": 10.3666,
      "step": 54
    },
    {
      "epoch": 0.01749085705199555,
      "grad_norm": 0.12043500691652298,
      "learning_rate": 8.678619553365659e-05,
      "loss": 10.3653,
      "step": 55
    },
    {
      "epoch": 0.017808872634759103,
      "grad_norm": 0.09669925272464752,
      "learning_rate": 8.622126023955446e-05,
      "loss": 10.3683,
      "step": 56
    },
    {
      "epoch": 0.01812688821752266,
      "grad_norm": 0.09334994852542877,
      "learning_rate": 8.564642241456986e-05,
      "loss": 10.368,
      "step": 57
    },
    {
      "epoch": 0.018444903800286214,
      "grad_norm": 0.08862730115652084,
      "learning_rate": 8.506183921362443e-05,
      "loss": 10.366,
      "step": 58
    },
    {
      "epoch": 0.01876291938304977,
      "grad_norm": 0.09216415882110596,
      "learning_rate": 8.44676704559283e-05,
      "loss": 10.3655,
      "step": 59
    },
    {
      "epoch": 0.019080934965813326,
      "grad_norm": 0.08441773056983948,
      "learning_rate": 8.386407858128706e-05,
      "loss": 10.3659,
      "step": 60
    },
    {
      "epoch": 0.01939895054857688,
      "grad_norm": 0.09132162481546402,
      "learning_rate": 8.32512286056924e-05,
      "loss": 10.3649,
      "step": 61
    },
    {
      "epoch": 0.019716966131340434,
      "grad_norm": 0.08384277671575546,
      "learning_rate": 8.262928807620843e-05,
      "loss": 10.3652,
      "step": 62
    },
    {
      "epoch": 0.02003498171410399,
      "grad_norm": 0.0875183492898941,
      "learning_rate": 8.199842702516583e-05,
      "loss": 10.3632,
      "step": 63
    },
    {
      "epoch": 0.020352997296867546,
      "grad_norm": 0.08083841949701309,
      "learning_rate": 8.135881792367686e-05,
      "loss": 10.3637,
      "step": 64
    },
    {
      "epoch": 0.020671012879631103,
      "grad_norm": 0.08265729993581772,
      "learning_rate": 8.07106356344834e-05,
      "loss": 10.3624,
      "step": 65
    },
    {
      "epoch": 0.020989028462394657,
      "grad_norm": 0.0666433721780777,
      "learning_rate": 8.005405736415126e-05,
      "loss": 10.3622,
      "step": 66
    },
    {
      "epoch": 0.02130704404515821,
      "grad_norm": 0.07333511114120483,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3613,
      "step": 67
    },
    {
      "epoch": 0.02162505962792177,
      "grad_norm": 0.06806871294975281,
      "learning_rate": 7.871643313414718e-05,
      "loss": 10.3627,
      "step": 68
    },
    {
      "epoch": 0.021943075210685323,
      "grad_norm": 0.07555898278951645,
      "learning_rate": 7.803575286758364e-05,
      "loss": 10.361,
      "step": 69
    },
    {
      "epoch": 0.02226109079344888,
      "grad_norm": 0.06851986795663834,
      "learning_rate": 7.734740790612136e-05,
      "loss": 10.3595,
      "step": 70
    },
    {
      "epoch": 0.022579106376212434,
      "grad_norm": 0.06847857683897018,
      "learning_rate": 7.66515864363997e-05,
      "loss": 10.3558,
      "step": 71
    },
    {
      "epoch": 0.02289712195897599,
      "grad_norm": 0.06496783345937729,
      "learning_rate": 7.594847868906076e-05,
      "loss": 10.3584,
      "step": 72
    },
    {
      "epoch": 0.023215137541739546,
      "grad_norm": 0.08555959910154343,
      "learning_rate": 7.52382768867422e-05,
      "loss": 10.3605,
      "step": 73
    },
    {
      "epoch": 0.0235331531245031,
      "grad_norm": 0.08276556432247162,
      "learning_rate": 7.452117519152542e-05,
      "loss": 10.3607,
      "step": 74
    },
    {
      "epoch": 0.023851168707266657,
      "grad_norm": 0.13021576404571533,
      "learning_rate": 7.379736965185368e-05,
      "loss": 10.3557,
      "step": 75
    },
    {
      "epoch": 0.02416918429003021,
      "grad_norm": 0.11780581623315811,
      "learning_rate": 7.30670581489344e-05,
      "loss": 10.358,
      "step": 76
    },
    {
      "epoch": 0.024487199872793766,
      "grad_norm": 0.16075696051120758,
      "learning_rate": 7.233044034264034e-05,
      "loss": 10.3509,
      "step": 77
    },
    {
      "epoch": 0.024805215455557323,
      "grad_norm": 0.12129935622215271,
      "learning_rate": 7.158771761692464e-05,
      "loss": 10.3527,
      "step": 78
    },
    {
      "epoch": 0.025123231038320877,
      "grad_norm": 0.1384841650724411,
      "learning_rate": 7.083909302476453e-05,
      "loss": 10.3525,
      "step": 79
    },
    {
      "epoch": 0.025441246621084435,
      "grad_norm": 0.13928252458572388,
      "learning_rate": 7.008477123264848e-05,
      "loss": 10.349,
      "step": 80
    },
    {
      "epoch": 0.02575926220384799,
      "grad_norm": 0.1140902191400528,
      "learning_rate": 6.932495846462261e-05,
      "loss": 10.353,
      "step": 81
    },
    {
      "epoch": 0.026077277786611543,
      "grad_norm": 0.11462803930044174,
      "learning_rate": 6.855986244591104e-05,
      "loss": 10.3527,
      "step": 82
    },
    {
      "epoch": 0.0263952933693751,
      "grad_norm": 0.10285041481256485,
      "learning_rate": 6.778969234612584e-05,
      "loss": 10.3583,
      "step": 83
    },
    {
      "epoch": 0.026713308952138654,
      "grad_norm": 0.17103056609630585,
      "learning_rate": 6.701465872208216e-05,
      "loss": 10.3572,
      "step": 84
    },
    {
      "epoch": 0.027031324534902212,
      "grad_norm": 0.14897240698337555,
      "learning_rate": 6.623497346023418e-05,
      "loss": 10.3583,
      "step": 85
    },
    {
      "epoch": 0.027349340117665766,
      "grad_norm": 0.0864802896976471,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3538,
      "step": 86
    },
    {
      "epoch": 0.02766735570042932,
      "grad_norm": 0.1780140995979309,
      "learning_rate": 6.466250186922325e-05,
      "loss": 10.35,
      "step": 87
    },
    {
      "epoch": 0.027985371283192877,
      "grad_norm": 0.23262430727481842,
      "learning_rate": 6.387014543809223e-05,
      "loss": 10.3586,
      "step": 88
    },
    {
      "epoch": 0.02830338686595643,
      "grad_norm": 0.302450954914093,
      "learning_rate": 6.307399704769099e-05,
      "loss": 10.3646,
      "step": 89
    },
    {
      "epoch": 0.02862140244871999,
      "grad_norm": 0.27525296807289124,
      "learning_rate": 6.227427435703997e-05,
      "loss": 10.3568,
      "step": 90
    },
    {
      "epoch": 0.028939418031483543,
      "grad_norm": 0.3150113821029663,
      "learning_rate": 6.147119600233758e-05,
      "loss": 10.3609,
      "step": 91
    },
    {
      "epoch": 0.029257433614247097,
      "grad_norm": 0.33403944969177246,
      "learning_rate": 6.066498153718735e-05,
      "loss": 10.3552,
      "step": 92
    },
    {
      "epoch": 0.029575449197010655,
      "grad_norm": 0.2955075800418854,
      "learning_rate": 5.985585137257401e-05,
      "loss": 10.3603,
      "step": 93
    },
    {
      "epoch": 0.02989346477977421,
      "grad_norm": 0.307024210691452,
      "learning_rate": 5.90440267166055e-05,
      "loss": 10.3565,
      "step": 94
    },
    {
      "epoch": 0.030211480362537766,
      "grad_norm": 0.29273131489753723,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 10.355,
      "step": 95
    },
    {
      "epoch": 0.03052949594530132,
      "grad_norm": 0.3266304135322571,
      "learning_rate": 5.74131823855921e-05,
      "loss": 10.3545,
      "step": 96
    },
    {
      "epoch": 0.030847511528064874,
      "grad_norm": 0.28510549664497375,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 10.3519,
      "step": 97
    },
    {
      "epoch": 0.03116552711082843,
      "grad_norm": 0.354200154542923,
      "learning_rate": 5.577423184847932e-05,
      "loss": 10.3509,
      "step": 98
    },
    {
      "epoch": 0.031483542693591986,
      "grad_norm": 0.3255683183670044,
      "learning_rate": 5.495227651252315e-05,
      "loss": 10.3438,
      "step": 99
    },
    {
      "epoch": 0.03180155827635554,
      "grad_norm": 0.3521130084991455,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 10.3529,
      "step": 100
    },
    {
      "epoch": 0.03180155827635554,
      "eval_loss": 10.355113983154297,
      "eval_runtime": 12.9968,
      "eval_samples_per_second": 407.484,
      "eval_steps_per_second": 101.871,
      "step": 100
    },
    {
      "epoch": 0.032119573859119094,
      "grad_norm": 0.1210668757557869,
      "learning_rate": 5.330452921628497e-05,
      "loss": 10.3555,
      "step": 101
    },
    {
      "epoch": 0.03243758944188265,
      "grad_norm": 0.10243978351354599,
      "learning_rate": 5.247918773366112e-05,
      "loss": 10.3572,
      "step": 102
    },
    {
      "epoch": 0.03275560502464621,
      "grad_norm": 0.08623477071523666,
      "learning_rate": 5.165316846586541e-05,
      "loss": 10.361,
      "step": 103
    },
    {
      "epoch": 0.033073620607409766,
      "grad_norm": 0.07962904125452042,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 10.36,
      "step": 104
    },
    {
      "epoch": 0.03339163619017332,
      "grad_norm": 0.08876842260360718,
      "learning_rate": 5e-05,
      "loss": 10.362,
      "step": 105
    },
    {
      "epoch": 0.033709651772936874,
      "grad_norm": 0.07856586575508118,
      "learning_rate": 4.917330276168208e-05,
      "loss": 10.3627,
      "step": 106
    },
    {
      "epoch": 0.03402766735570043,
      "grad_norm": 0.07900390028953552,
      "learning_rate": 4.834683153413459e-05,
      "loss": 10.3613,
      "step": 107
    },
    {
      "epoch": 0.03434568293846398,
      "grad_norm": 0.08123540133237839,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 10.361,
      "step": 108
    },
    {
      "epoch": 0.03466369852122754,
      "grad_norm": 0.05919745936989784,
      "learning_rate": 4.669547078371504e-05,
      "loss": 10.361,
      "step": 109
    },
    {
      "epoch": 0.0349817141039911,
      "grad_norm": 0.061544034630060196,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 10.3606,
      "step": 110
    },
    {
      "epoch": 0.03529972968675465,
      "grad_norm": 0.06435167044401169,
      "learning_rate": 4.504772348747687e-05,
      "loss": 10.3604,
      "step": 111
    },
    {
      "epoch": 0.035617745269518206,
      "grad_norm": 0.05723894387483597,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 10.3597,
      "step": 112
    },
    {
      "epoch": 0.03593576085228176,
      "grad_norm": 0.0653674304485321,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 10.3601,
      "step": 113
    },
    {
      "epoch": 0.03625377643504532,
      "grad_norm": 0.062474265694618225,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 10.3588,
      "step": 114
    },
    {
      "epoch": 0.03657179201780887,
      "grad_norm": 0.07225754112005234,
      "learning_rate": 4.17702704859633e-05,
      "loss": 10.3593,
      "step": 115
    },
    {
      "epoch": 0.03688980760057243,
      "grad_norm": 0.05321989208459854,
      "learning_rate": 4.095597328339452e-05,
      "loss": 10.3577,
      "step": 116
    },
    {
      "epoch": 0.037207823183335986,
      "grad_norm": 0.06724876165390015,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 10.3574,
      "step": 117
    },
    {
      "epoch": 0.03752583876609954,
      "grad_norm": 0.06534626334905624,
      "learning_rate": 3.933501846281267e-05,
      "loss": 10.3608,
      "step": 118
    },
    {
      "epoch": 0.037843854348863094,
      "grad_norm": 0.06102212518453598,
      "learning_rate": 3.852880399766243e-05,
      "loss": 10.3599,
      "step": 119
    },
    {
      "epoch": 0.03816186993162665,
      "grad_norm": 0.06173279881477356,
      "learning_rate": 3.772572564296005e-05,
      "loss": 10.3573,
      "step": 120
    },
    {
      "epoch": 0.0384798855143902,
      "grad_norm": 0.06524460017681122,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 10.3577,
      "step": 121
    },
    {
      "epoch": 0.03879790109715376,
      "grad_norm": 0.09015753865242004,
      "learning_rate": 3.612985456190778e-05,
      "loss": 10.3567,
      "step": 122
    },
    {
      "epoch": 0.03911591667991732,
      "grad_norm": 0.09596744179725647,
      "learning_rate": 3.533749813077677e-05,
      "loss": 10.3557,
      "step": 123
    },
    {
      "epoch": 0.03943393226268087,
      "grad_norm": 0.13267070055007935,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3518,
      "step": 124
    },
    {
      "epoch": 0.039751947845444426,
      "grad_norm": 0.16284127533435822,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 10.351,
      "step": 125
    },
    {
      "epoch": 0.04006996342820798,
      "grad_norm": 0.12936189770698547,
      "learning_rate": 3.298534127791785e-05,
      "loss": 10.3534,
      "step": 126
    },
    {
      "epoch": 0.04038797901097154,
      "grad_norm": 0.13996922969818115,
      "learning_rate": 3.221030765387417e-05,
      "loss": 10.3498,
      "step": 127
    },
    {
      "epoch": 0.04070599459373509,
      "grad_norm": 0.17427155375480652,
      "learning_rate": 3.144013755408895e-05,
      "loss": 10.3501,
      "step": 128
    },
    {
      "epoch": 0.04102401017649865,
      "grad_norm": 0.12143827974796295,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 10.3529,
      "step": 129
    },
    {
      "epoch": 0.041342025759262206,
      "grad_norm": 0.14232085645198822,
      "learning_rate": 2.991522876735154e-05,
      "loss": 10.353,
      "step": 130
    },
    {
      "epoch": 0.04166004134202576,
      "grad_norm": 0.12601225078105927,
      "learning_rate": 2.916090697523549e-05,
      "loss": 10.3548,
      "step": 131
    },
    {
      "epoch": 0.041978056924789314,
      "grad_norm": 0.09353561699390411,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 10.3571,
      "step": 132
    },
    {
      "epoch": 0.04229607250755287,
      "grad_norm": 0.1307641565799713,
      "learning_rate": 2.766955965735968e-05,
      "loss": 10.361,
      "step": 133
    },
    {
      "epoch": 0.04261408809031642,
      "grad_norm": 0.15996910631656647,
      "learning_rate": 2.693294185106562e-05,
      "loss": 10.3569,
      "step": 134
    },
    {
      "epoch": 0.04293210367307998,
      "grad_norm": 0.1374237984418869,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 10.3552,
      "step": 135
    },
    {
      "epoch": 0.04325011925584354,
      "grad_norm": 0.13959072530269623,
      "learning_rate": 2.547882480847461e-05,
      "loss": 10.3573,
      "step": 136
    },
    {
      "epoch": 0.043568134838607095,
      "grad_norm": 0.23289057612419128,
      "learning_rate": 2.476172311325783e-05,
      "loss": 10.3583,
      "step": 137
    },
    {
      "epoch": 0.043886150421370645,
      "grad_norm": 0.23729613423347473,
      "learning_rate": 2.405152131093926e-05,
      "loss": 10.3513,
      "step": 138
    },
    {
      "epoch": 0.0442041660041342,
      "grad_norm": 0.2607218325138092,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 10.3483,
      "step": 139
    },
    {
      "epoch": 0.04452218158689776,
      "grad_norm": 0.3193565011024475,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 10.3494,
      "step": 140
    },
    {
      "epoch": 0.04484019716966131,
      "grad_norm": 0.3596358299255371,
      "learning_rate": 2.196424713241637e-05,
      "loss": 10.3504,
      "step": 141
    },
    {
      "epoch": 0.04515821275242487,
      "grad_norm": 0.24508459866046906,
      "learning_rate": 2.128356686585282e-05,
      "loss": 10.346,
      "step": 142
    },
    {
      "epoch": 0.045476228335188426,
      "grad_norm": 0.23422080278396606,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3558,
      "step": 143
    },
    {
      "epoch": 0.04579424391795198,
      "grad_norm": 0.2796928882598877,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 10.3502,
      "step": 144
    },
    {
      "epoch": 0.046112259500715534,
      "grad_norm": 0.2530340850353241,
      "learning_rate": 1.928936436551661e-05,
      "loss": 10.3552,
      "step": 145
    },
    {
      "epoch": 0.04643027508347909,
      "grad_norm": 0.30220237374305725,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 10.3486,
      "step": 146
    },
    {
      "epoch": 0.04674829066624265,
      "grad_norm": 0.2826690077781677,
      "learning_rate": 1.800157297483417e-05,
      "loss": 10.3413,
      "step": 147
    },
    {
      "epoch": 0.0470663062490062,
      "grad_norm": 0.27635130286216736,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 10.3415,
      "step": 148
    },
    {
      "epoch": 0.04738432183176976,
      "grad_norm": 0.2700005769729614,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 10.3369,
      "step": 149
    },
    {
      "epoch": 0.047702337414533315,
      "grad_norm": 0.31102126836776733,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 10.3438,
      "step": 150
    },
    {
      "epoch": 0.047702337414533315,
      "eval_loss": 10.353894233703613,
      "eval_runtime": 13.176,
      "eval_samples_per_second": 401.944,
      "eval_steps_per_second": 100.486,
      "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": 19632916267008.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}