{
  "best_metric": 0.06431274861097336,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.05739292632183084,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028696463160915415,
      "grad_norm": 3.0429611206054688,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.639,
      "step": 1
    },
    {
      "epoch": 0.00028696463160915415,
      "eval_loss": 0.25444304943084717,
      "eval_runtime": 837.7662,
      "eval_samples_per_second": 7.006,
      "eval_steps_per_second": 3.503,
      "step": 1
    },
    {
      "epoch": 0.0005739292632183083,
      "grad_norm": 3.583061695098877,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.609,
      "step": 2
    },
    {
      "epoch": 0.0008608938948274625,
      "grad_norm": 2.7970328330993652,
      "learning_rate": 1e-05,
      "loss": 0.5934,
      "step": 3
    },
    {
      "epoch": 0.0011478585264366166,
      "grad_norm": 2.2916595935821533,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.5524,
      "step": 4
    },
    {
      "epoch": 0.001434823158045771,
      "grad_norm": 1.9195245504379272,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5608,
      "step": 5
    },
    {
      "epoch": 0.001721787789654925,
      "grad_norm": 1.781160593032837,
      "learning_rate": 2e-05,
      "loss": 0.5506,
      "step": 6
    },
    {
      "epoch": 0.002008752421264079,
      "grad_norm": 1.811500906944275,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.4814,
      "step": 7
    },
    {
      "epoch": 0.002295717052873233,
      "grad_norm": 1.500028133392334,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.4626,
      "step": 8
    },
    {
      "epoch": 0.0025826816844823877,
      "grad_norm": 1.9022938013076782,
      "learning_rate": 3e-05,
      "loss": 0.3973,
      "step": 9
    },
    {
      "epoch": 0.002869646316091542,
      "grad_norm": 1.2072649002075195,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.3819,
      "step": 10
    },
    {
      "epoch": 0.003156610947700696,
      "grad_norm": 1.5055830478668213,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 0.3815,
      "step": 11
    },
    {
      "epoch": 0.00344357557930985,
      "grad_norm": 1.6541370153427124,
      "learning_rate": 4e-05,
      "loss": 0.3644,
      "step": 12
    },
    {
      "epoch": 0.003730540210919004,
      "grad_norm": 1.8192777633666992,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.3275,
      "step": 13
    },
    {
      "epoch": 0.004017504842528158,
      "grad_norm": 1.3344385623931885,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.358,
      "step": 14
    },
    {
      "epoch": 0.004304469474137313,
      "grad_norm": 1.3325713872909546,
      "learning_rate": 5e-05,
      "loss": 0.3851,
      "step": 15
    },
    {
      "epoch": 0.004591434105746466,
      "grad_norm": 2.9268879890441895,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.4138,
      "step": 16
    },
    {
      "epoch": 0.004878398737355621,
      "grad_norm": 2.1012864112854004,
      "learning_rate": 5.666666666666667e-05,
      "loss": 0.3568,
      "step": 17
    },
    {
      "epoch": 0.0051653633689647755,
      "grad_norm": 1.307517647743225,
      "learning_rate": 6e-05,
      "loss": 0.3255,
      "step": 18
    },
    {
      "epoch": 0.005452328000573929,
      "grad_norm": 1.5392760038375854,
      "learning_rate": 6.333333333333333e-05,
      "loss": 0.2982,
      "step": 19
    },
    {
      "epoch": 0.005739292632183084,
      "grad_norm": 1.484470248222351,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.3148,
      "step": 20
    },
    {
      "epoch": 0.006026257263792237,
      "grad_norm": 1.5804404020309448,
      "learning_rate": 7e-05,
      "loss": 0.3173,
      "step": 21
    },
    {
      "epoch": 0.006313221895401392,
      "grad_norm": 1.0478932857513428,
      "learning_rate": 7.333333333333333e-05,
      "loss": 0.3367,
      "step": 22
    },
    {
      "epoch": 0.0066001865270105455,
      "grad_norm": 0.9721614718437195,
      "learning_rate": 7.666666666666667e-05,
      "loss": 0.3155,
      "step": 23
    },
    {
      "epoch": 0.0068871511586197,
      "grad_norm": 0.9773309230804443,
      "learning_rate": 8e-05,
      "loss": 0.3211,
      "step": 24
    },
    {
      "epoch": 0.007174115790228855,
      "grad_norm": 1.0934327840805054,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.2692,
      "step": 25
    },
    {
      "epoch": 0.007461080421838008,
      "grad_norm": 0.8688898086547852,
      "learning_rate": 8.666666666666667e-05,
      "loss": 0.232,
      "step": 26
    },
    {
      "epoch": 0.007748045053447163,
      "grad_norm": 0.663547694683075,
      "learning_rate": 9e-05,
      "loss": 0.2225,
      "step": 27
    },
    {
      "epoch": 0.008035009685056316,
      "grad_norm": 0.9233863949775696,
      "learning_rate": 9.333333333333334e-05,
      "loss": 0.3036,
      "step": 28
    },
    {
      "epoch": 0.008321974316665471,
      "grad_norm": 1.5700796842575073,
      "learning_rate": 9.666666666666667e-05,
      "loss": 0.341,
      "step": 29
    },
    {
      "epoch": 0.008608938948274625,
      "grad_norm": 1.5582494735717773,
      "learning_rate": 0.0001,
      "loss": 0.3164,
      "step": 30
    },
    {
      "epoch": 0.00889590357988378,
      "grad_norm": 0.8336695432662964,
      "learning_rate": 9.999146252290264e-05,
      "loss": 0.2672,
      "step": 31
    },
    {
      "epoch": 0.009182868211492933,
      "grad_norm": 0.6727259159088135,
      "learning_rate": 9.996585300715116e-05,
      "loss": 0.2732,
      "step": 32
    },
    {
      "epoch": 0.009469832843102087,
      "grad_norm": 1.473003625869751,
      "learning_rate": 9.99231801983717e-05,
      "loss": 0.2974,
      "step": 33
    },
    {
      "epoch": 0.009756797474711242,
      "grad_norm": 0.6282394528388977,
      "learning_rate": 9.986345866928941e-05,
      "loss": 0.2313,
      "step": 34
    },
    {
      "epoch": 0.010043762106320396,
      "grad_norm": 0.4663063585758209,
      "learning_rate": 9.978670881475172e-05,
      "loss": 0.2191,
      "step": 35
    },
    {
      "epoch": 0.010330726737929551,
      "grad_norm": 1.9066166877746582,
      "learning_rate": 9.96929568447637e-05,
      "loss": 0.2749,
      "step": 36
    },
    {
      "epoch": 0.010617691369538704,
      "grad_norm": 1.0014101266860962,
      "learning_rate": 9.958223477553714e-05,
      "loss": 0.3103,
      "step": 37
    },
    {
      "epoch": 0.010904656001147858,
      "grad_norm": 0.8885980248451233,
      "learning_rate": 9.94545804185573e-05,
      "loss": 0.309,
      "step": 38
    },
    {
      "epoch": 0.011191620632757013,
      "grad_norm": 1.0599013566970825,
      "learning_rate": 9.931003736767013e-05,
      "loss": 0.3253,
      "step": 39
    },
    {
      "epoch": 0.011478585264366167,
      "grad_norm": 1.466591715812683,
      "learning_rate": 9.91486549841951e-05,
      "loss": 0.3137,
      "step": 40
    },
    {
      "epoch": 0.011765549895975322,
      "grad_norm": 1.4529075622558594,
      "learning_rate": 9.89704883800683e-05,
      "loss": 0.3301,
      "step": 41
    },
    {
      "epoch": 0.012052514527584475,
      "grad_norm": 0.7103596329689026,
      "learning_rate": 9.877559839902184e-05,
      "loss": 0.2657,
      "step": 42
    },
    {
      "epoch": 0.01233947915919363,
      "grad_norm": 0.9101693034172058,
      "learning_rate": 9.85640515958057e-05,
      "loss": 0.2966,
      "step": 43
    },
    {
      "epoch": 0.012626443790802784,
      "grad_norm": 1.1335175037384033,
      "learning_rate": 9.833592021345937e-05,
      "loss": 0.3217,
      "step": 44
    },
    {
      "epoch": 0.012913408422411938,
      "grad_norm": 0.7104204893112183,
      "learning_rate": 9.809128215864097e-05,
      "loss": 0.3061,
      "step": 45
    },
    {
      "epoch": 0.013200373054021091,
      "grad_norm": 0.853221595287323,
      "learning_rate": 9.783022097502204e-05,
      "loss": 0.2695,
      "step": 46
    },
    {
      "epoch": 0.013487337685630246,
      "grad_norm": 0.7009562253952026,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2505,
      "step": 47
    },
    {
      "epoch": 0.0137743023172394,
      "grad_norm": 0.6309565305709839,
      "learning_rate": 9.725919140804099e-05,
      "loss": 0.1364,
      "step": 48
    },
    {
      "epoch": 0.014061266948848555,
      "grad_norm": 1.174967646598816,
      "learning_rate": 9.694941803075283e-05,
      "loss": 0.1507,
      "step": 49
    },
    {
      "epoch": 0.01434823158045771,
      "grad_norm": 0.9244698882102966,
      "learning_rate": 9.662361147021779e-05,
      "loss": 0.2557,
      "step": 50
    },
    {
      "epoch": 0.01434823158045771,
      "eval_loss": 0.07957611978054047,
      "eval_runtime": 843.3163,
      "eval_samples_per_second": 6.959,
      "eval_steps_per_second": 3.48,
      "step": 50
    },
    {
      "epoch": 0.014635196212066862,
      "grad_norm": 1.385195016860962,
      "learning_rate": 9.628188298907782e-05,
      "loss": 0.3523,
      "step": 51
    },
    {
      "epoch": 0.014922160843676016,
      "grad_norm": 0.8282255530357361,
      "learning_rate": 9.592434928729616e-05,
      "loss": 0.317,
      "step": 52
    },
    {
      "epoch": 0.015209125475285171,
      "grad_norm": 0.8197574615478516,
      "learning_rate": 9.555113246230442e-05,
      "loss": 0.3337,
      "step": 53
    },
    {
      "epoch": 0.015496090106894326,
      "grad_norm": 0.556509256362915,
      "learning_rate": 9.516235996730645e-05,
      "loss": 0.291,
      "step": 54
    },
    {
      "epoch": 0.01578305473850348,
      "grad_norm": 0.5262755751609802,
      "learning_rate": 9.475816456775313e-05,
      "loss": 0.3254,
      "step": 55
    },
    {
      "epoch": 0.016070019370112633,
      "grad_norm": 0.4416431188583374,
      "learning_rate": 9.43386842960031e-05,
      "loss": 0.3296,
      "step": 56
    },
    {
      "epoch": 0.016356984001721787,
      "grad_norm": 0.4305843710899353,
      "learning_rate": 9.39040624041849e-05,
      "loss": 0.284,
      "step": 57
    },
    {
      "epoch": 0.016643948633330942,
      "grad_norm": 0.3605152368545532,
      "learning_rate": 9.345444731527642e-05,
      "loss": 0.2945,
      "step": 58
    },
    {
      "epoch": 0.016930913264940096,
      "grad_norm": 0.3456534147262573,
      "learning_rate": 9.298999257241863e-05,
      "loss": 0.3118,
      "step": 59
    },
    {
      "epoch": 0.01721787789654925,
      "grad_norm": 0.6163169741630554,
      "learning_rate": 9.251085678648072e-05,
      "loss": 0.3324,
      "step": 60
    },
    {
      "epoch": 0.017504842528158406,
      "grad_norm": 0.6102662086486816,
      "learning_rate": 9.201720358189464e-05,
      "loss": 0.2856,
      "step": 61
    },
    {
      "epoch": 0.01779180715976756,
      "grad_norm": 0.36927440762519836,
      "learning_rate": 9.150920154077754e-05,
      "loss": 0.3296,
      "step": 62
    },
    {
      "epoch": 0.01807877179137671,
      "grad_norm": 0.38277602195739746,
      "learning_rate": 9.098702414536107e-05,
      "loss": 0.3145,
      "step": 63
    },
    {
      "epoch": 0.018365736422985866,
      "grad_norm": 0.21570929884910583,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.2956,
      "step": 64
    },
    {
      "epoch": 0.01865270105459502,
      "grad_norm": 0.3367782235145569,
      "learning_rate": 8.9900861364012e-05,
      "loss": 0.3012,
      "step": 65
    },
    {
      "epoch": 0.018939665686204175,
      "grad_norm": 0.29729658365249634,
      "learning_rate": 8.933724690167417e-05,
      "loss": 0.2627,
      "step": 66
    },
    {
      "epoch": 0.01922663031781333,
      "grad_norm": 0.28526386618614197,
      "learning_rate": 8.876019880555649e-05,
      "loss": 0.2558,
      "step": 67
    },
    {
      "epoch": 0.019513594949422484,
      "grad_norm": 0.35815444588661194,
      "learning_rate": 8.816991413705516e-05,
      "loss": 0.2597,
      "step": 68
    },
    {
      "epoch": 0.01980055958103164,
      "grad_norm": 0.26656872034072876,
      "learning_rate": 8.756659447784368e-05,
      "loss": 0.2538,
      "step": 69
    },
    {
      "epoch": 0.020087524212640793,
      "grad_norm": 0.2528567910194397,
      "learning_rate": 8.695044586103296e-05,
      "loss": 0.2784,
      "step": 70
    },
    {
      "epoch": 0.020374488844249947,
      "grad_norm": 0.4498709738254547,
      "learning_rate": 8.632167870081121e-05,
      "loss": 0.299,
      "step": 71
    },
    {
      "epoch": 0.020661453475859102,
      "grad_norm": 0.80962073802948,
      "learning_rate": 8.568050772058762e-05,
      "loss": 0.2407,
      "step": 72
    },
    {
      "epoch": 0.020948418107468253,
      "grad_norm": 0.32711413502693176,
      "learning_rate": 8.502715187966455e-05,
      "loss": 0.2614,
      "step": 73
    },
    {
      "epoch": 0.021235382739077407,
      "grad_norm": 0.6672317981719971,
      "learning_rate": 8.436183429846313e-05,
      "loss": 0.3,
      "step": 74
    },
    {
      "epoch": 0.021522347370686562,
      "grad_norm": 0.40455496311187744,
      "learning_rate": 8.368478218232787e-05,
      "loss": 0.259,
      "step": 75
    },
    {
      "epoch": 0.021809312002295717,
      "grad_norm": 0.6652066707611084,
      "learning_rate": 8.299622674393614e-05,
      "loss": 0.2683,
      "step": 76
    },
    {
      "epoch": 0.02209627663390487,
      "grad_norm": 0.5522506833076477,
      "learning_rate": 8.229640312433937e-05,
      "loss": 0.2418,
      "step": 77
    },
    {
      "epoch": 0.022383241265514026,
      "grad_norm": 0.5324224829673767,
      "learning_rate": 8.158555031266254e-05,
      "loss": 0.2535,
      "step": 78
    },
    {
      "epoch": 0.02267020589712318,
      "grad_norm": 0.5191222429275513,
      "learning_rate": 8.086391106448965e-05,
      "loss": 0.3081,
      "step": 79
    },
    {
      "epoch": 0.022957170528732335,
      "grad_norm": 0.4188215434551239,
      "learning_rate": 8.013173181896283e-05,
      "loss": 0.3202,
      "step": 80
    },
    {
      "epoch": 0.02324413516034149,
      "grad_norm": 0.5270218253135681,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.278,
      "step": 81
    },
    {
      "epoch": 0.023531099791950644,
      "grad_norm": 0.9171215891838074,
      "learning_rate": 7.863675700402526e-05,
      "loss": 0.2802,
      "step": 82
    },
    {
      "epoch": 0.023818064423559795,
      "grad_norm": 0.4189884662628174,
      "learning_rate": 7.787447196714427e-05,
      "loss": 0.2681,
      "step": 83
    },
    {
      "epoch": 0.02410502905516895,
      "grad_norm": 0.9392601251602173,
      "learning_rate": 7.710266782362247e-05,
      "loss": 0.2689,
      "step": 84
    },
    {
      "epoch": 0.024391993686778104,
      "grad_norm": 0.8024010062217712,
      "learning_rate": 7.63216081438678e-05,
      "loss": 0.1928,
      "step": 85
    },
    {
      "epoch": 0.02467895831838726,
      "grad_norm": 0.774445652961731,
      "learning_rate": 7.553155965904535e-05,
      "loss": 0.3051,
      "step": 86
    },
    {
      "epoch": 0.024965922949996413,
      "grad_norm": 0.732581615447998,
      "learning_rate": 7.473279216998895e-05,
      "loss": 0.2474,
      "step": 87
    },
    {
      "epoch": 0.025252887581605567,
      "grad_norm": 0.43084821105003357,
      "learning_rate": 7.392557845506432e-05,
      "loss": 0.2828,
      "step": 88
    },
    {
      "epoch": 0.025539852213214722,
      "grad_norm": 0.40919262170791626,
      "learning_rate": 7.311019417701566e-05,
      "loss": 0.2772,
      "step": 89
    },
    {
      "epoch": 0.025826816844823876,
      "grad_norm": 0.41505667567253113,
      "learning_rate": 7.228691778882693e-05,
      "loss": 0.2427,
      "step": 90
    },
    {
      "epoch": 0.02611378147643303,
      "grad_norm": 0.34625786542892456,
      "learning_rate": 7.145603043863045e-05,
      "loss": 0.2526,
      "step": 91
    },
    {
      "epoch": 0.026400746108042182,
      "grad_norm": 0.44996926188468933,
      "learning_rate": 7.061781587369519e-05,
      "loss": 0.259,
      "step": 92
    },
    {
      "epoch": 0.026687710739651337,
      "grad_norm": 0.491010844707489,
      "learning_rate": 6.977256034352712e-05,
      "loss": 0.2211,
      "step": 93
    },
    {
      "epoch": 0.02697467537126049,
      "grad_norm": 0.7121477723121643,
      "learning_rate": 6.892055250211552e-05,
      "loss": 0.3465,
      "step": 94
    },
    {
      "epoch": 0.027261640002869646,
      "grad_norm": 0.7240779399871826,
      "learning_rate": 6.806208330935766e-05,
      "loss": 0.2903,
      "step": 95
    },
    {
      "epoch": 0.0275486046344788,
      "grad_norm": 1.1428096294403076,
      "learning_rate": 6.719744593169641e-05,
      "loss": 0.2585,
      "step": 96
    },
    {
      "epoch": 0.027835569266087955,
      "grad_norm": 0.932219922542572,
      "learning_rate": 6.632693564200416e-05,
      "loss": 0.2002,
      "step": 97
    },
    {
      "epoch": 0.02812253389769711,
      "grad_norm": 0.6620375514030457,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1406,
      "step": 98
    },
    {
      "epoch": 0.028409498529306264,
      "grad_norm": 1.5361576080322266,
      "learning_rate": 6.456948734446624e-05,
      "loss": 0.1937,
      "step": 99
    },
    {
      "epoch": 0.02869646316091542,
      "grad_norm": 1.8901885747909546,
      "learning_rate": 6.368314950360415e-05,
      "loss": 0.2269,
      "step": 100
    },
    {
      "epoch": 0.02869646316091542,
      "eval_loss": 0.07314909249544144,
      "eval_runtime": 842.9095,
      "eval_samples_per_second": 6.963,
      "eval_steps_per_second": 3.482,
      "step": 100
    },
    {
      "epoch": 0.028983427792524573,
      "grad_norm": 0.6289970874786377,
      "learning_rate": 6.279213887972179e-05,
      "loss": 0.2776,
      "step": 101
    },
    {
      "epoch": 0.029270392424133724,
      "grad_norm": 0.4327123761177063,
      "learning_rate": 6.189675975213094e-05,
      "loss": 0.2454,
      "step": 102
    },
    {
      "epoch": 0.02955735705574288,
      "grad_norm": 0.31198781728744507,
      "learning_rate": 6.099731789198344e-05,
      "loss": 0.3004,
      "step": 103
    },
    {
      "epoch": 0.029844321687352033,
      "grad_norm": 0.24795642495155334,
      "learning_rate": 6.009412045785051e-05,
      "loss": 0.2992,
      "step": 104
    },
    {
      "epoch": 0.030131286318961188,
      "grad_norm": 0.2529444396495819,
      "learning_rate": 5.918747589082853e-05,
      "loss": 0.3179,
      "step": 105
    },
    {
      "epoch": 0.030418250950570342,
      "grad_norm": 0.2385726273059845,
      "learning_rate": 5.82776938092065e-05,
      "loss": 0.2885,
      "step": 106
    },
    {
      "epoch": 0.030705215582179497,
      "grad_norm": 0.3763389587402344,
      "learning_rate": 5.736508490273188e-05,
      "loss": 0.2945,
      "step": 107
    },
    {
      "epoch": 0.03099218021378865,
      "grad_norm": 0.3574504852294922,
      "learning_rate": 5.644996082651017e-05,
      "loss": 0.3193,
      "step": 108
    },
    {
      "epoch": 0.0312791448453978,
      "grad_norm": 0.2397194802761078,
      "learning_rate": 5.553263409457504e-05,
      "loss": 0.3078,
      "step": 109
    },
    {
      "epoch": 0.03156610947700696,
      "grad_norm": 0.2164476364850998,
      "learning_rate": 5.4613417973165106e-05,
      "loss": 0.2868,
      "step": 110
    },
    {
      "epoch": 0.03185307410861611,
      "grad_norm": 0.3787127435207367,
      "learning_rate": 5.3692626373743706e-05,
      "loss": 0.2738,
      "step": 111
    },
    {
      "epoch": 0.032140038740225266,
      "grad_norm": 0.24689379334449768,
      "learning_rate": 5.27705737457985e-05,
      "loss": 0.283,
      "step": 112
    },
    {
      "epoch": 0.03242700337183442,
      "grad_norm": 0.26295608282089233,
      "learning_rate": 5.184757496945726e-05,
      "loss": 0.283,
      "step": 113
    },
    {
      "epoch": 0.032713968003443575,
      "grad_norm": 0.1907181441783905,
      "learning_rate": 5.092394524795649e-05,
      "loss": 0.2788,
      "step": 114
    },
    {
      "epoch": 0.03300093263505273,
      "grad_norm": 0.20249591767787933,
      "learning_rate": 5e-05,
      "loss": 0.2666,
      "step": 115
    },
    {
      "epoch": 0.033287897266661884,
      "grad_norm": 0.280271053314209,
      "learning_rate": 4.907605475204352e-05,
      "loss": 0.2414,
      "step": 116
    },
    {
      "epoch": 0.03357486189827104,
      "grad_norm": 0.25560441613197327,
      "learning_rate": 4.8152425030542766e-05,
      "loss": 0.2671,
      "step": 117
    },
    {
      "epoch": 0.03386182652988019,
      "grad_norm": 0.22025573253631592,
      "learning_rate": 4.72294262542015e-05,
      "loss": 0.2634,
      "step": 118
    },
    {
      "epoch": 0.03414879116148935,
      "grad_norm": 0.22071503102779388,
      "learning_rate": 4.6307373626256306e-05,
      "loss": 0.2807,
      "step": 119
    },
    {
      "epoch": 0.0344357557930985,
      "grad_norm": 0.2339547574520111,
      "learning_rate": 4.5386582026834906e-05,
      "loss": 0.3041,
      "step": 120
    },
    {
      "epoch": 0.034722720424707657,
      "grad_norm": 0.24428895115852356,
      "learning_rate": 4.446736590542497e-05,
      "loss": 0.2918,
      "step": 121
    },
    {
      "epoch": 0.03500968505631681,
      "grad_norm": 0.2549816966056824,
      "learning_rate": 4.3550039173489845e-05,
      "loss": 0.2667,
      "step": 122
    },
    {
      "epoch": 0.035296649687925966,
      "grad_norm": 0.29650628566741943,
      "learning_rate": 4.2634915097268115e-05,
      "loss": 0.2566,
      "step": 123
    },
    {
      "epoch": 0.03558361431953512,
      "grad_norm": 0.24224285781383514,
      "learning_rate": 4.1722306190793495e-05,
      "loss": 0.2607,
      "step": 124
    },
    {
      "epoch": 0.035870578951144275,
      "grad_norm": 0.35612723231315613,
      "learning_rate": 4.0812524109171476e-05,
      "loss": 0.2404,
      "step": 125
    },
    {
      "epoch": 0.03615754358275342,
      "grad_norm": 0.3032487630844116,
      "learning_rate": 3.99058795421495e-05,
      "loss": 0.2661,
      "step": 126
    },
    {
      "epoch": 0.03644450821436258,
      "grad_norm": 0.33981555700302124,
      "learning_rate": 3.9002682108016585e-05,
      "loss": 0.2189,
      "step": 127
    },
    {
      "epoch": 0.03673147284597173,
      "grad_norm": 0.33926525712013245,
      "learning_rate": 3.8103240247869075e-05,
      "loss": 0.2906,
      "step": 128
    },
    {
      "epoch": 0.037018437477580886,
      "grad_norm": 0.3139205574989319,
      "learning_rate": 3.720786112027822e-05,
      "loss": 0.2836,
      "step": 129
    },
    {
      "epoch": 0.03730540210919004,
      "grad_norm": 0.4507588744163513,
      "learning_rate": 3.631685049639586e-05,
      "loss": 0.296,
      "step": 130
    },
    {
      "epoch": 0.037592366740799195,
      "grad_norm": 0.328153520822525,
      "learning_rate": 3.543051265553377e-05,
      "loss": 0.2721,
      "step": 131
    },
    {
      "epoch": 0.03787933137240835,
      "grad_norm": 0.5082656145095825,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2613,
      "step": 132
    },
    {
      "epoch": 0.038166296004017504,
      "grad_norm": 0.4505540132522583,
      "learning_rate": 3.367306435799584e-05,
      "loss": 0.2407,
      "step": 133
    },
    {
      "epoch": 0.03845326063562666,
      "grad_norm": 0.4038177728652954,
      "learning_rate": 3.2802554068303596e-05,
      "loss": 0.215,
      "step": 134
    },
    {
      "epoch": 0.03874022526723581,
      "grad_norm": 0.3410555124282837,
      "learning_rate": 3.1937916690642356e-05,
      "loss": 0.2292,
      "step": 135
    },
    {
      "epoch": 0.03902718989884497,
      "grad_norm": 0.4864601790904999,
      "learning_rate": 3.107944749788449e-05,
      "loss": 0.2465,
      "step": 136
    },
    {
      "epoch": 0.03931415453045412,
      "grad_norm": 0.6895772218704224,
      "learning_rate": 3.0227439656472877e-05,
      "loss": 0.2501,
      "step": 137
    },
    {
      "epoch": 0.03960111916206328,
      "grad_norm": 0.4328419864177704,
      "learning_rate": 2.9382184126304834e-05,
      "loss": 0.2526,
      "step": 138
    },
    {
      "epoch": 0.03988808379367243,
      "grad_norm": 0.47423994541168213,
      "learning_rate": 2.8543969561369556e-05,
      "loss": 0.242,
      "step": 139
    },
    {
      "epoch": 0.040175048425281586,
      "grad_norm": 0.39731431007385254,
      "learning_rate": 2.771308221117309e-05,
      "loss": 0.1844,
      "step": 140
    },
    {
      "epoch": 0.04046201305689074,
      "grad_norm": 0.5587954521179199,
      "learning_rate": 2.688980582298435e-05,
      "loss": 0.2735,
      "step": 141
    },
    {
      "epoch": 0.040748977688499895,
      "grad_norm": 0.47387251257896423,
      "learning_rate": 2.607442154493568e-05,
      "loss": 0.2045,
      "step": 142
    },
    {
      "epoch": 0.04103594232010905,
      "grad_norm": 0.5877320766448975,
      "learning_rate": 2.5267207830011068e-05,
      "loss": 0.2564,
      "step": 143
    },
    {
      "epoch": 0.041322906951718204,
      "grad_norm": 0.5738049149513245,
      "learning_rate": 2.446844034095466e-05,
      "loss": 0.3058,
      "step": 144
    },
    {
      "epoch": 0.04160987158332736,
      "grad_norm": 0.5666738152503967,
      "learning_rate": 2.3678391856132204e-05,
      "loss": 0.2889,
      "step": 145
    },
    {
      "epoch": 0.041896836214936506,
      "grad_norm": 0.6741418838500977,
      "learning_rate": 2.2897332176377528e-05,
      "loss": 0.2702,
      "step": 146
    },
    {
      "epoch": 0.04218380084654566,
      "grad_norm": 0.5714048743247986,
      "learning_rate": 2.2125528032855724e-05,
      "loss": 0.1961,
      "step": 147
    },
    {
      "epoch": 0.042470765478154815,
      "grad_norm": 1.3949394226074219,
      "learning_rate": 2.136324299597474e-05,
      "loss": 0.1444,
      "step": 148
    },
    {
      "epoch": 0.04275773010976397,
      "grad_norm": 0.38774827122688293,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1532,
      "step": 149
    },
    {
      "epoch": 0.043044694741373124,
      "grad_norm": 0.7958654165267944,
      "learning_rate": 1.9868268181037185e-05,
      "loss": 0.2234,
      "step": 150
    },
    {
      "epoch": 0.043044694741373124,
      "eval_loss": 0.06637585908174515,
      "eval_runtime": 842.6363,
      "eval_samples_per_second": 6.965,
      "eval_steps_per_second": 3.483,
      "step": 150
    },
    {
      "epoch": 0.04333165937298228,
      "grad_norm": 0.4346352219581604,
      "learning_rate": 1.9136088935510362e-05,
      "loss": 0.3313,
      "step": 151
    },
    {
      "epoch": 0.04361862400459143,
      "grad_norm": 0.311940461397171,
      "learning_rate": 1.8414449687337464e-05,
      "loss": 0.3227,
      "step": 152
    },
    {
      "epoch": 0.04390558863620059,
      "grad_norm": 0.28699979186058044,
      "learning_rate": 1.7703596875660645e-05,
      "loss": 0.3044,
      "step": 153
    },
    {
      "epoch": 0.04419255326780974,
      "grad_norm": 0.23011769354343414,
      "learning_rate": 1.700377325606388e-05,
      "loss": 0.2725,
      "step": 154
    },
    {
      "epoch": 0.0444795178994189,
      "grad_norm": 0.4881756901741028,
      "learning_rate": 1.631521781767214e-05,
      "loss": 0.3155,
      "step": 155
    },
    {
      "epoch": 0.04476648253102805,
      "grad_norm": 0.24843592941761017,
      "learning_rate": 1.5638165701536868e-05,
      "loss": 0.2792,
      "step": 156
    },
    {
      "epoch": 0.045053447162637206,
      "grad_norm": 0.23546892404556274,
      "learning_rate": 1.4972848120335453e-05,
      "loss": 0.2864,
      "step": 157
    },
    {
      "epoch": 0.04534041179424636,
      "grad_norm": 0.25201475620269775,
      "learning_rate": 1.4319492279412388e-05,
      "loss": 0.294,
      "step": 158
    },
    {
      "epoch": 0.045627376425855515,
      "grad_norm": 0.22863058745861053,
      "learning_rate": 1.3678321299188801e-05,
      "loss": 0.3157,
      "step": 159
    },
    {
      "epoch": 0.04591434105746467,
      "grad_norm": 0.3571547567844391,
      "learning_rate": 1.3049554138967051e-05,
      "loss": 0.2947,
      "step": 160
    },
    {
      "epoch": 0.046201305689073824,
      "grad_norm": 0.232662171125412,
      "learning_rate": 1.2433405522156332e-05,
      "loss": 0.2722,
      "step": 161
    },
    {
      "epoch": 0.04648827032068298,
      "grad_norm": 0.19611531496047974,
      "learning_rate": 1.183008586294485e-05,
      "loss": 0.2696,
      "step": 162
    },
    {
      "epoch": 0.04677523495229213,
      "grad_norm": 0.22698666155338287,
      "learning_rate": 1.1239801194443506e-05,
      "loss": 0.2843,
      "step": 163
    },
    {
      "epoch": 0.04706219958390129,
      "grad_norm": 0.22291672229766846,
      "learning_rate": 1.066275309832584e-05,
      "loss": 0.3031,
      "step": 164
    },
    {
      "epoch": 0.047349164215510435,
      "grad_norm": 0.21244947612285614,
      "learning_rate": 1.0099138635988026e-05,
      "loss": 0.2722,
      "step": 165
    },
    {
      "epoch": 0.04763612884711959,
      "grad_norm": 0.21219472587108612,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2478,
      "step": 166
    },
    {
      "epoch": 0.047923093478728744,
      "grad_norm": 0.20624606311321259,
      "learning_rate": 9.012975854638949e-06,
      "loss": 0.2502,
      "step": 167
    },
    {
      "epoch": 0.0482100581103379,
      "grad_norm": 0.21474754810333252,
      "learning_rate": 8.490798459222476e-06,
      "loss": 0.2662,
      "step": 168
    },
    {
      "epoch": 0.04849702274194705,
      "grad_norm": 0.24078983068466187,
      "learning_rate": 7.982796418105371e-06,
      "loss": 0.2888,
      "step": 169
    },
    {
      "epoch": 0.04878398737355621,
      "grad_norm": 0.24138078093528748,
      "learning_rate": 7.489143213519301e-06,
      "loss": 0.2411,
      "step": 170
    },
    {
      "epoch": 0.04907095200516536,
      "grad_norm": 0.24836519360542297,
      "learning_rate": 7.010007427581378e-06,
      "loss": 0.267,
      "step": 171
    },
    {
      "epoch": 0.04935791663677452,
      "grad_norm": 0.30620038509368896,
      "learning_rate": 6.5455526847235825e-06,
      "loss": 0.2755,
      "step": 172
    },
    {
      "epoch": 0.04964488126838367,
      "grad_norm": 0.29814326763153076,
      "learning_rate": 6.0959375958151045e-06,
      "loss": 0.2645,
      "step": 173
    },
    {
      "epoch": 0.049931845899992826,
      "grad_norm": 0.2532620429992676,
      "learning_rate": 5.6613157039969055e-06,
      "loss": 0.288,
      "step": 174
    },
    {
      "epoch": 0.05021881053160198,
      "grad_norm": 0.34292635321617126,
      "learning_rate": 5.241835432246889e-06,
      "loss": 0.2637,
      "step": 175
    },
    {
      "epoch": 0.050505775163211135,
      "grad_norm": 0.2579328715801239,
      "learning_rate": 4.837640032693558e-06,
      "loss": 0.2841,
      "step": 176
    },
    {
      "epoch": 0.05079273979482029,
      "grad_norm": 0.21610936522483826,
      "learning_rate": 4.448867537695578e-06,
      "loss": 0.1728,
      "step": 177
    },
    {
      "epoch": 0.051079704426429444,
      "grad_norm": 0.3203733563423157,
      "learning_rate": 4.075650712703849e-06,
      "loss": 0.2958,
      "step": 178
    },
    {
      "epoch": 0.0513666690580386,
      "grad_norm": 0.24726489186286926,
      "learning_rate": 3.71811701092219e-06,
      "loss": 0.264,
      "step": 179
    },
    {
      "epoch": 0.05165363368964775,
      "grad_norm": 0.33239224553108215,
      "learning_rate": 3.376388529782215e-06,
      "loss": 0.2687,
      "step": 180
    },
    {
      "epoch": 0.05194059832125691,
      "grad_norm": 0.32938748598098755,
      "learning_rate": 3.0505819692471792e-06,
      "loss": 0.2599,
      "step": 181
    },
    {
      "epoch": 0.05222756295286606,
      "grad_norm": 0.37538081407546997,
      "learning_rate": 2.7408085919590264e-06,
      "loss": 0.2361,
      "step": 182
    },
    {
      "epoch": 0.05251452758447522,
      "grad_norm": 0.4944473206996918,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2265,
      "step": 183
    },
    {
      "epoch": 0.052801492216084364,
      "grad_norm": 0.587113618850708,
      "learning_rate": 2.1697790249779636e-06,
      "loss": 0.2091,
      "step": 184
    },
    {
      "epoch": 0.05308845684769352,
      "grad_norm": 0.8430886268615723,
      "learning_rate": 1.908717841359048e-06,
      "loss": 0.236,
      "step": 185
    },
    {
      "epoch": 0.05337542147930267,
      "grad_norm": 0.3732443153858185,
      "learning_rate": 1.6640797865406288e-06,
      "loss": 0.2492,
      "step": 186
    },
    {
      "epoch": 0.05366238611091183,
      "grad_norm": 0.3992467522621155,
      "learning_rate": 1.4359484041943038e-06,
      "loss": 0.2193,
      "step": 187
    },
    {
      "epoch": 0.05394935074252098,
      "grad_norm": 0.3827664852142334,
      "learning_rate": 1.2244016009781701e-06,
      "loss": 0.2682,
      "step": 188
    },
    {
      "epoch": 0.05423631537413014,
      "grad_norm": 0.6000558733940125,
      "learning_rate": 1.0295116199317057e-06,
      "loss": 0.3061,
      "step": 189
    },
    {
      "epoch": 0.05452328000573929,
      "grad_norm": 0.580310583114624,
      "learning_rate": 8.513450158049108e-07,
      "loss": 0.2275,
      "step": 190
    },
    {
      "epoch": 0.054810244637348446,
      "grad_norm": 0.4089508652687073,
      "learning_rate": 6.899626323298713e-07,
      "loss": 0.1949,
      "step": 191
    },
    {
      "epoch": 0.0550972092689576,
      "grad_norm": 0.49917787313461304,
      "learning_rate": 5.454195814427021e-07,
      "loss": 0.2221,
      "step": 192
    },
    {
      "epoch": 0.055384173900566755,
      "grad_norm": 0.5836434960365295,
      "learning_rate": 4.177652244628627e-07,
      "loss": 0.2155,
      "step": 193
    },
    {
      "epoch": 0.05567113853217591,
      "grad_norm": 0.6123931407928467,
      "learning_rate": 3.0704315523631953e-07,
      "loss": 0.2799,
      "step": 194
    },
    {
      "epoch": 0.055958103163785064,
      "grad_norm": 0.6153947114944458,
      "learning_rate": 2.1329118524827662e-07,
      "loss": 0.2804,
      "step": 195
    },
    {
      "epoch": 0.05624506779539422,
      "grad_norm": 0.5668597221374512,
      "learning_rate": 1.3654133071059893e-07,
      "loss": 0.2232,
      "step": 196
    },
    {
      "epoch": 0.05653203242700337,
      "grad_norm": 0.7655932903289795,
      "learning_rate": 7.681980162830282e-08,
      "loss": 0.201,
      "step": 197
    },
    {
      "epoch": 0.05681899705861253,
      "grad_norm": 0.6260830760002136,
      "learning_rate": 3.4146992848854695e-08,
      "loss": 0.1257,
      "step": 198
    },
    {
      "epoch": 0.05710596169022168,
      "grad_norm": 0.8820661306381226,
      "learning_rate": 8.537477097364522e-09,
      "loss": 0.2271,
      "step": 199
    },
    {
      "epoch": 0.05739292632183084,
      "grad_norm": 1.5282742977142334,
      "learning_rate": 0.0,
      "loss": 0.2199,
      "step": 200
    },
    {
      "epoch": 0.05739292632183084,
      "eval_loss": 0.06431274861097336,
      "eval_runtime": 843.744,
      "eval_samples_per_second": 6.956,
      "eval_steps_per_second": 3.479,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.1301336362673766e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}