{
  "best_metric": 0.12753550708293915,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 1.7204301075268817,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017204301075268817,
      "grad_norm": 4.601269245147705,
      "learning_rate": 2e-05,
      "loss": 0.4272,
      "step": 1
    },
    {
      "epoch": 0.017204301075268817,
      "eval_loss": 1.4783204793930054,
      "eval_runtime": 5.1438,
      "eval_samples_per_second": 76.208,
      "eval_steps_per_second": 9.526,
      "step": 1
    },
    {
      "epoch": 0.034408602150537634,
      "grad_norm": 7.236650466918945,
      "learning_rate": 4e-05,
      "loss": 0.6626,
      "step": 2
    },
    {
      "epoch": 0.05161290322580645,
      "grad_norm": 7.9963555335998535,
      "learning_rate": 6e-05,
      "loss": 0.6886,
      "step": 3
    },
    {
      "epoch": 0.06881720430107527,
      "grad_norm": 4.405614376068115,
      "learning_rate": 8e-05,
      "loss": 0.4014,
      "step": 4
    },
    {
      "epoch": 0.08602150537634409,
      "grad_norm": 3.2208263874053955,
      "learning_rate": 0.0001,
      "loss": 0.3021,
      "step": 5
    },
    {
      "epoch": 0.1032258064516129,
      "grad_norm": 1.8561677932739258,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.2245,
      "step": 6
    },
    {
      "epoch": 0.12043010752688173,
      "grad_norm": 1.6137471199035645,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.2223,
      "step": 7
    },
    {
      "epoch": 0.13763440860215054,
      "grad_norm": 0.9222277998924255,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.1546,
      "step": 8
    },
    {
      "epoch": 0.15483870967741936,
      "grad_norm": 0.9431182146072388,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.1754,
      "step": 9
    },
    {
      "epoch": 0.17204301075268819,
      "grad_norm": 0.7953192591667175,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.1822,
      "step": 10
    },
    {
      "epoch": 0.18924731182795698,
      "grad_norm": 0.9455572366714478,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.2185,
      "step": 11
    },
    {
      "epoch": 0.2064516129032258,
      "grad_norm": 0.8408288359642029,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.2108,
      "step": 12
    },
    {
      "epoch": 0.22365591397849463,
      "grad_norm": 0.35438165068626404,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.0773,
      "step": 13
    },
    {
      "epoch": 0.24086021505376345,
      "grad_norm": 0.42859965562820435,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.0717,
      "step": 14
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 0.36290422081947327,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.0868,
      "step": 15
    },
    {
      "epoch": 0.2752688172043011,
      "grad_norm": 0.5616369247436523,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.1069,
      "step": 16
    },
    {
      "epoch": 0.2924731182795699,
      "grad_norm": 0.47484615445137024,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.0989,
      "step": 17
    },
    {
      "epoch": 0.3096774193548387,
      "grad_norm": 0.4143848121166229,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.11,
      "step": 18
    },
    {
      "epoch": 0.32688172043010755,
      "grad_norm": 0.49859318137168884,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.114,
      "step": 19
    },
    {
      "epoch": 0.34408602150537637,
      "grad_norm": 0.5608797073364258,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.1247,
      "step": 20
    },
    {
      "epoch": 0.36129032258064514,
      "grad_norm": 0.5681672096252441,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.1305,
      "step": 21
    },
    {
      "epoch": 0.37849462365591396,
      "grad_norm": 0.5968943238258362,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.1441,
      "step": 22
    },
    {
      "epoch": 0.3956989247311828,
      "grad_norm": 0.5786952376365662,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.135,
      "step": 23
    },
    {
      "epoch": 0.4129032258064516,
      "grad_norm": 0.7746197581291199,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.1746,
      "step": 24
    },
    {
      "epoch": 0.43010752688172044,
      "grad_norm": 0.9171465039253235,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.2272,
      "step": 25
    },
    {
      "epoch": 0.43010752688172044,
      "eval_loss": 0.1376180797815323,
      "eval_runtime": 5.1567,
      "eval_samples_per_second": 76.018,
      "eval_steps_per_second": 9.502,
      "step": 25
    },
    {
      "epoch": 0.44731182795698926,
      "grad_norm": 0.16825996339321136,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.0449,
      "step": 26
    },
    {
      "epoch": 0.4645161290322581,
      "grad_norm": 0.2606010437011719,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.0656,
      "step": 27
    },
    {
      "epoch": 0.4817204301075269,
      "grad_norm": 0.3626805245876312,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.0898,
      "step": 28
    },
    {
      "epoch": 0.4989247311827957,
      "grad_norm": 0.3628605008125305,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.0909,
      "step": 29
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 0.34184515476226807,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.0935,
      "step": 30
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.4369655251502991,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.1039,
      "step": 31
    },
    {
      "epoch": 0.5505376344086022,
      "grad_norm": 0.4320714473724365,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.1077,
      "step": 32
    },
    {
      "epoch": 0.567741935483871,
      "grad_norm": 0.4757688045501709,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.1194,
      "step": 33
    },
    {
      "epoch": 0.5849462365591398,
      "grad_norm": 0.48429444432258606,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.1216,
      "step": 34
    },
    {
      "epoch": 0.6021505376344086,
      "grad_norm": 0.5377363562583923,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.142,
      "step": 35
    },
    {
      "epoch": 0.6193548387096774,
      "grad_norm": 0.5409618616104126,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.1612,
      "step": 36
    },
    {
      "epoch": 0.6365591397849463,
      "grad_norm": 0.7560884356498718,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.198,
      "step": 37
    },
    {
      "epoch": 0.6537634408602151,
      "grad_norm": 0.25169119238853455,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.0631,
      "step": 38
    },
    {
      "epoch": 0.6709677419354839,
      "grad_norm": 0.2085525542497635,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.0531,
      "step": 39
    },
    {
      "epoch": 0.6881720430107527,
      "grad_norm": 0.2509376108646393,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.0688,
      "step": 40
    },
    {
      "epoch": 0.7053763440860215,
      "grad_norm": 0.27264726161956787,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.0792,
      "step": 41
    },
    {
      "epoch": 0.7225806451612903,
      "grad_norm": 0.2584315240383148,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.0824,
      "step": 42
    },
    {
      "epoch": 0.7397849462365591,
      "grad_norm": 0.34367600083351135,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0932,
      "step": 43
    },
    {
      "epoch": 0.7569892473118279,
      "grad_norm": 0.3771838843822479,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.1051,
      "step": 44
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 0.3859615921974182,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.1106,
      "step": 45
    },
    {
      "epoch": 0.7913978494623656,
      "grad_norm": 0.4388357698917389,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.1173,
      "step": 46
    },
    {
      "epoch": 0.8086021505376344,
      "grad_norm": 0.5637166500091553,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.131,
      "step": 47
    },
    {
      "epoch": 0.8258064516129032,
      "grad_norm": 0.47906917333602905,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.1548,
      "step": 48
    },
    {
      "epoch": 0.843010752688172,
      "grad_norm": 0.5929440855979919,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.1613,
      "step": 49
    },
    {
      "epoch": 0.8602150537634409,
      "grad_norm": 0.918541431427002,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.2385,
      "step": 50
    },
    {
      "epoch": 0.8602150537634409,
      "eval_loss": 0.13366764783859253,
      "eval_runtime": 5.1579,
      "eval_samples_per_second": 76.0,
      "eval_steps_per_second": 9.5,
      "step": 50
    },
    {
      "epoch": 0.8774193548387097,
      "grad_norm": 0.1686541885137558,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.0467,
      "step": 51
    },
    {
      "epoch": 0.8946236559139785,
      "grad_norm": 0.23044119775295258,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.0716,
      "step": 52
    },
    {
      "epoch": 0.9118279569892473,
      "grad_norm": 0.28096097707748413,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.0885,
      "step": 53
    },
    {
      "epoch": 0.9290322580645162,
      "grad_norm": 0.36806416511535645,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.1005,
      "step": 54
    },
    {
      "epoch": 0.946236559139785,
      "grad_norm": 0.3925113081932068,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.1102,
      "step": 55
    },
    {
      "epoch": 0.9634408602150538,
      "grad_norm": 0.4250904321670532,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.1243,
      "step": 56
    },
    {
      "epoch": 0.9806451612903225,
      "grad_norm": 0.47191616892814636,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.1558,
      "step": 57
    },
    {
      "epoch": 0.9978494623655914,
      "grad_norm": 0.6524373292922974,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.1878,
      "step": 58
    },
    {
      "epoch": 1.0150537634408603,
      "grad_norm": 1.1412904262542725,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.1142,
      "step": 59
    },
    {
      "epoch": 1.032258064516129,
      "grad_norm": 0.17924538254737854,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.0528,
      "step": 60
    },
    {
      "epoch": 1.049462365591398,
      "grad_norm": 0.2397976964712143,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.0629,
      "step": 61
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.23171919584274292,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0708,
      "step": 62
    },
    {
      "epoch": 1.0838709677419356,
      "grad_norm": 0.26210978627204895,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.0732,
      "step": 63
    },
    {
      "epoch": 1.1010752688172043,
      "grad_norm": 0.2662266790866852,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.0717,
      "step": 64
    },
    {
      "epoch": 1.118279569892473,
      "grad_norm": 0.33063340187072754,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.0796,
      "step": 65
    },
    {
      "epoch": 1.135483870967742,
      "grad_norm": 0.32689982652664185,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.0801,
      "step": 66
    },
    {
      "epoch": 1.1526881720430107,
      "grad_norm": 0.32011306285858154,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.0885,
      "step": 67
    },
    {
      "epoch": 1.1698924731182796,
      "grad_norm": 0.40406063199043274,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.1112,
      "step": 68
    },
    {
      "epoch": 1.1870967741935483,
      "grad_norm": 0.3917810618877411,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.116,
      "step": 69
    },
    {
      "epoch": 1.2043010752688172,
      "grad_norm": 0.4483303427696228,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.1178,
      "step": 70
    },
    {
      "epoch": 1.221505376344086,
      "grad_norm": 0.23751965165138245,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.0572,
      "step": 71
    },
    {
      "epoch": 1.238709677419355,
      "grad_norm": 0.1653883159160614,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.0467,
      "step": 72
    },
    {
      "epoch": 1.2559139784946236,
      "grad_norm": 0.2108721137046814,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.059,
      "step": 73
    },
    {
      "epoch": 1.2731182795698925,
      "grad_norm": 0.2989300787448883,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.0675,
      "step": 74
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 0.24671778082847595,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.0677,
      "step": 75
    },
    {
      "epoch": 1.2903225806451613,
      "eval_loss": 0.1286679357290268,
      "eval_runtime": 5.1485,
      "eval_samples_per_second": 76.139,
      "eval_steps_per_second": 9.517,
      "step": 75
    },
    {
      "epoch": 1.3075268817204302,
      "grad_norm": 0.287640243768692,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.0692,
      "step": 76
    },
    {
      "epoch": 1.324731182795699,
      "grad_norm": 0.3015075922012329,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.0807,
      "step": 77
    },
    {
      "epoch": 1.3419354838709676,
      "grad_norm": 0.2982653081417084,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.0783,
      "step": 78
    },
    {
      "epoch": 1.3591397849462366,
      "grad_norm": 0.3233046233654022,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.0851,
      "step": 79
    },
    {
      "epoch": 1.3763440860215055,
      "grad_norm": 0.31660306453704834,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.0887,
      "step": 80
    },
    {
      "epoch": 1.3935483870967742,
      "grad_norm": 0.3477661609649658,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0887,
      "step": 81
    },
    {
      "epoch": 1.410752688172043,
      "grad_norm": 0.43353694677352905,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.1107,
      "step": 82
    },
    {
      "epoch": 1.4279569892473118,
      "grad_norm": 0.5698493719100952,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.1305,
      "step": 83
    },
    {
      "epoch": 1.4451612903225808,
      "grad_norm": 0.26135772466659546,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.0479,
      "step": 84
    },
    {
      "epoch": 1.4623655913978495,
      "grad_norm": 0.205588236451149,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.0516,
      "step": 85
    },
    {
      "epoch": 1.4795698924731182,
      "grad_norm": 0.24263671040534973,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.0628,
      "step": 86
    },
    {
      "epoch": 1.4967741935483871,
      "grad_norm": 0.26423949003219604,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.0681,
      "step": 87
    },
    {
      "epoch": 1.513978494623656,
      "grad_norm": 0.2682032287120819,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.0733,
      "step": 88
    },
    {
      "epoch": 1.5311827956989248,
      "grad_norm": 0.30018141865730286,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.077,
      "step": 89
    },
    {
      "epoch": 1.5483870967741935,
      "grad_norm": 0.34617161750793457,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.0858,
      "step": 90
    },
    {
      "epoch": 1.5655913978494622,
      "grad_norm": 0.3334634304046631,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.0799,
      "step": 91
    },
    {
      "epoch": 1.5827956989247312,
      "grad_norm": 0.35072311758995056,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.0855,
      "step": 92
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.3579203188419342,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.0947,
      "step": 93
    },
    {
      "epoch": 1.6172043010752688,
      "grad_norm": 0.4464438855648041,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.1047,
      "step": 94
    },
    {
      "epoch": 1.6344086021505375,
      "grad_norm": 0.4803522527217865,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.1119,
      "step": 95
    },
    {
      "epoch": 1.6516129032258065,
      "grad_norm": 0.2232884019613266,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.0485,
      "step": 96
    },
    {
      "epoch": 1.6688172043010754,
      "grad_norm": 0.1642189770936966,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.0433,
      "step": 97
    },
    {
      "epoch": 1.686021505376344,
      "grad_norm": 0.2120582014322281,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.0515,
      "step": 98
    },
    {
      "epoch": 1.7032258064516128,
      "grad_norm": 0.25639230012893677,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.0691,
      "step": 99
    },
    {
      "epoch": 1.7204301075268817,
      "grad_norm": 0.31680721044540405,
      "learning_rate": 0.0,
      "loss": 0.0791,
      "step": 100
    },
    {
      "epoch": 1.7204301075268817,
      "eval_loss": 0.12753550708293915,
      "eval_runtime": 5.1539,
      "eval_samples_per_second": 76.058,
      "eval_steps_per_second": 9.507,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 3.178927560327168e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}