{
  "best_metric": 0.10878434032201767,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.1297016861219196,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012970168612191958,
      "grad_norm": 43.15007019042969,
      "learning_rate": 1e-06,
      "loss": 24.5956,
      "step": 1
    },
    {
      "epoch": 0.0012970168612191958,
      "eval_loss": 11.099210739135742,
      "eval_runtime": 43.2298,
      "eval_samples_per_second": 7.518,
      "eval_steps_per_second": 1.897,
      "step": 1
    },
    {
      "epoch": 0.0025940337224383916,
      "grad_norm": 34.01232147216797,
      "learning_rate": 2e-06,
      "loss": 21.4527,
      "step": 2
    },
    {
      "epoch": 0.0038910505836575876,
      "grad_norm": 43.92300796508789,
      "learning_rate": 3e-06,
      "loss": 21.7764,
      "step": 3
    },
    {
      "epoch": 0.005188067444876783,
      "grad_norm": 36.848297119140625,
      "learning_rate": 4e-06,
      "loss": 22.2293,
      "step": 4
    },
    {
      "epoch": 0.00648508430609598,
      "grad_norm": 34.78293991088867,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 21.3363,
      "step": 5
    },
    {
      "epoch": 0.007782101167315175,
      "grad_norm": 43.606285095214844,
      "learning_rate": 6e-06,
      "loss": 21.3269,
      "step": 6
    },
    {
      "epoch": 0.009079118028534372,
      "grad_norm": 35.7335319519043,
      "learning_rate": 7e-06,
      "loss": 18.8252,
      "step": 7
    },
    {
      "epoch": 0.010376134889753566,
      "grad_norm": 39.83949661254883,
      "learning_rate": 8e-06,
      "loss": 20.006,
      "step": 8
    },
    {
      "epoch": 0.011673151750972763,
      "grad_norm": 32.874061584472656,
      "learning_rate": 9e-06,
      "loss": 19.244,
      "step": 9
    },
    {
      "epoch": 0.01297016861219196,
      "grad_norm": 35.38383102416992,
      "learning_rate": 9.999999999999999e-06,
      "loss": 21.033,
      "step": 10
    },
    {
      "epoch": 0.014267185473411154,
      "grad_norm": 42.5994987487793,
      "learning_rate": 1.1e-05,
      "loss": 19.4729,
      "step": 11
    },
    {
      "epoch": 0.01556420233463035,
      "grad_norm": 32.3964958190918,
      "learning_rate": 1.2e-05,
      "loss": 19.9392,
      "step": 12
    },
    {
      "epoch": 0.016861219195849545,
      "grad_norm": 34.603797912597656,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 18.9286,
      "step": 13
    },
    {
      "epoch": 0.018158236057068743,
      "grad_norm": 22.889278411865234,
      "learning_rate": 1.4e-05,
      "loss": 19.2667,
      "step": 14
    },
    {
      "epoch": 0.019455252918287938,
      "grad_norm": 20.571109771728516,
      "learning_rate": 1.5e-05,
      "loss": 17.9724,
      "step": 15
    },
    {
      "epoch": 0.020752269779507133,
      "grad_norm": 24.65373992919922,
      "learning_rate": 1.6e-05,
      "loss": 18.7244,
      "step": 16
    },
    {
      "epoch": 0.02204928664072633,
      "grad_norm": 20.301925659179688,
      "learning_rate": 1.7e-05,
      "loss": 15.1692,
      "step": 17
    },
    {
      "epoch": 0.023346303501945526,
      "grad_norm": 20.82584571838379,
      "learning_rate": 1.8e-05,
      "loss": 15.8121,
      "step": 18
    },
    {
      "epoch": 0.02464332036316472,
      "grad_norm": 20.620403289794922,
      "learning_rate": 1.9e-05,
      "loss": 14.7579,
      "step": 19
    },
    {
      "epoch": 0.02594033722438392,
      "grad_norm": 38.9058952331543,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 13.4066,
      "step": 20
    },
    {
      "epoch": 0.027237354085603113,
      "grad_norm": 24.992218017578125,
      "learning_rate": 2.1e-05,
      "loss": 12.6445,
      "step": 21
    },
    {
      "epoch": 0.028534370946822308,
      "grad_norm": 29.613855361938477,
      "learning_rate": 2.2e-05,
      "loss": 11.2814,
      "step": 22
    },
    {
      "epoch": 0.029831387808041506,
      "grad_norm": 24.93452262878418,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 9.3331,
      "step": 23
    },
    {
      "epoch": 0.0311284046692607,
      "grad_norm": 27.680971145629883,
      "learning_rate": 2.4e-05,
      "loss": 8.6512,
      "step": 24
    },
    {
      "epoch": 0.0324254215304799,
      "grad_norm": 29.876705169677734,
      "learning_rate": 2.5e-05,
      "loss": 7.8155,
      "step": 25
    },
    {
      "epoch": 0.03372243839169909,
      "grad_norm": 35.160499572753906,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 5.7938,
      "step": 26
    },
    {
      "epoch": 0.03501945525291829,
      "grad_norm": 27.901893615722656,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 4.1644,
      "step": 27
    },
    {
      "epoch": 0.03631647211413749,
      "grad_norm": 26.058135986328125,
      "learning_rate": 2.8e-05,
      "loss": 3.4339,
      "step": 28
    },
    {
      "epoch": 0.03761348897535668,
      "grad_norm": 21.99599838256836,
      "learning_rate": 2.9e-05,
      "loss": 2.2824,
      "step": 29
    },
    {
      "epoch": 0.038910505836575876,
      "grad_norm": 25.322467803955078,
      "learning_rate": 3e-05,
      "loss": 1.5445,
      "step": 30
    },
    {
      "epoch": 0.040207522697795074,
      "grad_norm": 16.150192260742188,
      "learning_rate": 2.9984895998119723e-05,
      "loss": 1.1335,
      "step": 31
    },
    {
      "epoch": 0.041504539559014265,
      "grad_norm": 23.29557228088379,
      "learning_rate": 2.993961440992859e-05,
      "loss": 2.223,
      "step": 32
    },
    {
      "epoch": 0.042801556420233464,
      "grad_norm": 11.53945541381836,
      "learning_rate": 2.9864246426519023e-05,
      "loss": 0.357,
      "step": 33
    },
    {
      "epoch": 0.04409857328145266,
      "grad_norm": 16.441926956176758,
      "learning_rate": 2.9758943828979444e-05,
      "loss": 0.4553,
      "step": 34
    },
    {
      "epoch": 0.04539559014267185,
      "grad_norm": 13.965824127197266,
      "learning_rate": 2.9623918682727355e-05,
      "loss": 0.8248,
      "step": 35
    },
    {
      "epoch": 0.04669260700389105,
      "grad_norm": 21.11853790283203,
      "learning_rate": 2.9459442910437798e-05,
      "loss": 1.1816,
      "step": 36
    },
    {
      "epoch": 0.04798962386511025,
      "grad_norm": 21.567947387695312,
      "learning_rate": 2.9265847744427305e-05,
      "loss": 2.031,
      "step": 37
    },
    {
      "epoch": 0.04928664072632944,
      "grad_norm": 18.425945281982422,
      "learning_rate": 2.904352305959606e-05,
      "loss": 0.9298,
      "step": 38
    },
    {
      "epoch": 0.05058365758754864,
      "grad_norm": 7.7157511711120605,
      "learning_rate": 2.8792916588271762e-05,
      "loss": 0.4712,
      "step": 39
    },
    {
      "epoch": 0.05188067444876784,
      "grad_norm": 40.98714065551758,
      "learning_rate": 2.8514533018536286e-05,
      "loss": 1.8018,
      "step": 40
    },
    {
      "epoch": 0.05317769130998703,
      "grad_norm": 36.11446762084961,
      "learning_rate": 2.820893297785107e-05,
      "loss": 1.6269,
      "step": 41
    },
    {
      "epoch": 0.054474708171206226,
      "grad_norm": 40.24372482299805,
      "learning_rate": 2.7876731904027994e-05,
      "loss": 1.417,
      "step": 42
    },
    {
      "epoch": 0.055771725032425425,
      "grad_norm": 37.61830520629883,
      "learning_rate": 2.7518598805819542e-05,
      "loss": 0.8011,
      "step": 43
    },
    {
      "epoch": 0.057068741893644616,
      "grad_norm": 7.277573108673096,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 0.1595,
      "step": 44
    },
    {
      "epoch": 0.058365758754863814,
      "grad_norm": 7.73269510269165,
      "learning_rate": 2.672747223702045e-05,
      "loss": 0.2451,
      "step": 45
    },
    {
      "epoch": 0.05966277561608301,
      "grad_norm": 5.931721210479736,
      "learning_rate": 2.6296071990054167e-05,
      "loss": 0.086,
      "step": 46
    },
    {
      "epoch": 0.0609597924773022,
      "grad_norm": 18.46846580505371,
      "learning_rate": 2.5841922957410875e-05,
      "loss": 0.8838,
      "step": 47
    },
    {
      "epoch": 0.0622568093385214,
      "grad_norm": 20.60508155822754,
      "learning_rate": 2.5365939734802973e-05,
      "loss": 2.3646,
      "step": 48
    },
    {
      "epoch": 0.06355382619974059,
      "grad_norm": 12.769781112670898,
      "learning_rate": 2.4869080889095693e-05,
      "loss": 1.2122,
      "step": 49
    },
    {
      "epoch": 0.0648508430609598,
      "grad_norm": 19.520858764648438,
      "learning_rate": 2.4352347027881003e-05,
      "loss": 1.8933,
      "step": 50
    },
    {
      "epoch": 0.0648508430609598,
      "eval_loss": 0.5612907409667969,
      "eval_runtime": 44.2478,
      "eval_samples_per_second": 7.345,
      "eval_steps_per_second": 1.853,
      "step": 50
    },
    {
      "epoch": 0.06614785992217899,
      "grad_norm": 20.423954010009766,
      "learning_rate": 2.3816778784387097e-05,
      "loss": 2.997,
      "step": 51
    },
    {
      "epoch": 0.06744487678339818,
      "grad_norm": 17.79172134399414,
      "learning_rate": 2.3263454721781537e-05,
      "loss": 1.577,
      "step": 52
    },
    {
      "epoch": 0.06874189364461739,
      "grad_norm": 6.911210060119629,
      "learning_rate": 2.2693489161088592e-05,
      "loss": 0.398,
      "step": 53
    },
    {
      "epoch": 0.07003891050583658,
      "grad_norm": 12.149227142333984,
      "learning_rate": 2.210802993709498e-05,
      "loss": 0.9617,
      "step": 54
    },
    {
      "epoch": 0.07133592736705577,
      "grad_norm": 8.559869766235352,
      "learning_rate": 2.1508256086763372e-05,
      "loss": 0.432,
      "step": 55
    },
    {
      "epoch": 0.07263294422827497,
      "grad_norm": 5.802802562713623,
      "learning_rate": 2.0895375474808857e-05,
      "loss": 0.3059,
      "step": 56
    },
    {
      "epoch": 0.07392996108949416,
      "grad_norm": 5.68005895614624,
      "learning_rate": 2.0270622361220143e-05,
      "loss": 0.2853,
      "step": 57
    },
    {
      "epoch": 0.07522697795071336,
      "grad_norm": 2.1309173107147217,
      "learning_rate": 1.963525491562421e-05,
      "loss": 0.1154,
      "step": 58
    },
    {
      "epoch": 0.07652399481193256,
      "grad_norm": 12.48730182647705,
      "learning_rate": 1.8990552683500128e-05,
      "loss": 0.3949,
      "step": 59
    },
    {
      "epoch": 0.07782101167315175,
      "grad_norm": 13.918665885925293,
      "learning_rate": 1.8337814009344716e-05,
      "loss": 0.5255,
      "step": 60
    },
    {
      "epoch": 0.07911802853437094,
      "grad_norm": 10.23596477508545,
      "learning_rate": 1.767835342197955e-05,
      "loss": 0.4977,
      "step": 61
    },
    {
      "epoch": 0.08041504539559015,
      "grad_norm": 6.709722518920898,
      "learning_rate": 1.7013498987264832e-05,
      "loss": 0.1514,
      "step": 62
    },
    {
      "epoch": 0.08171206225680934,
      "grad_norm": 5.081240177154541,
      "learning_rate": 1.6344589633551502e-05,
      "loss": 0.165,
      "step": 63
    },
    {
      "epoch": 0.08300907911802853,
      "grad_norm": 26.20868492126465,
      "learning_rate": 1.5672972455257726e-05,
      "loss": 1.1272,
      "step": 64
    },
    {
      "epoch": 0.08430609597924774,
      "grad_norm": 22.001665115356445,
      "learning_rate": 1.5e-05,
      "loss": 0.71,
      "step": 65
    },
    {
      "epoch": 0.08560311284046693,
      "grad_norm": 8.501405715942383,
      "learning_rate": 1.4327027544742281e-05,
      "loss": 0.2905,
      "step": 66
    },
    {
      "epoch": 0.08690012970168612,
      "grad_norm": 7.549007892608643,
      "learning_rate": 1.36554103664485e-05,
      "loss": 0.2497,
      "step": 67
    },
    {
      "epoch": 0.08819714656290532,
      "grad_norm": 16.637163162231445,
      "learning_rate": 1.2986501012735174e-05,
      "loss": 0.3425,
      "step": 68
    },
    {
      "epoch": 0.08949416342412451,
      "grad_norm": 45.87193298339844,
      "learning_rate": 1.2321646578020452e-05,
      "loss": 0.4744,
      "step": 69
    },
    {
      "epoch": 0.0907911802853437,
      "grad_norm": 11.191590309143066,
      "learning_rate": 1.1662185990655285e-05,
      "loss": 0.3808,
      "step": 70
    },
    {
      "epoch": 0.09208819714656291,
      "grad_norm": 11.546527862548828,
      "learning_rate": 1.1009447316499875e-05,
      "loss": 0.5787,
      "step": 71
    },
    {
      "epoch": 0.0933852140077821,
      "grad_norm": 4.363774299621582,
      "learning_rate": 1.036474508437579e-05,
      "loss": 0.0979,
      "step": 72
    },
    {
      "epoch": 0.0946822308690013,
      "grad_norm": 27.667964935302734,
      "learning_rate": 9.729377638779859e-06,
      "loss": 0.1371,
      "step": 73
    },
    {
      "epoch": 0.0959792477302205,
      "grad_norm": 6.752371788024902,
      "learning_rate": 9.104624525191147e-06,
      "loss": 0.1615,
      "step": 74
    },
    {
      "epoch": 0.09727626459143969,
      "grad_norm": 5.200261116027832,
      "learning_rate": 8.491743913236629e-06,
      "loss": 0.1498,
      "step": 75
    },
    {
      "epoch": 0.09857328145265888,
      "grad_norm": 11.683087348937988,
      "learning_rate": 7.89197006290502e-06,
      "loss": 0.1882,
      "step": 76
    },
    {
      "epoch": 0.09987029831387809,
      "grad_norm": 10.970105171203613,
      "learning_rate": 7.30651083891141e-06,
      "loss": 0.3211,
      "step": 77
    },
    {
      "epoch": 0.10116731517509728,
      "grad_norm": 9.882152557373047,
      "learning_rate": 6.736545278218464e-06,
      "loss": 0.2548,
      "step": 78
    },
    {
      "epoch": 0.10246433203631647,
      "grad_norm": 7.567006587982178,
      "learning_rate": 6.1832212156129045e-06,
      "loss": 0.2546,
      "step": 79
    },
    {
      "epoch": 0.10376134889753567,
      "grad_norm": 8.493035316467285,
      "learning_rate": 5.647652972118998e-06,
      "loss": 0.2932,
      "step": 80
    },
    {
      "epoch": 0.10505836575875487,
      "grad_norm": 5.506453990936279,
      "learning_rate": 5.130919110904311e-06,
      "loss": 0.1486,
      "step": 81
    },
    {
      "epoch": 0.10635538261997406,
      "grad_norm": 0.8174970149993896,
      "learning_rate": 4.6340602651970304e-06,
      "loss": 0.017,
      "step": 82
    },
    {
      "epoch": 0.10765239948119326,
      "grad_norm": 3.514220714569092,
      "learning_rate": 4.158077042589129e-06,
      "loss": 0.0581,
      "step": 83
    },
    {
      "epoch": 0.10894941634241245,
      "grad_norm": 0.8819956183433533,
      "learning_rate": 3.7039280099458373e-06,
      "loss": 0.0219,
      "step": 84
    },
    {
      "epoch": 0.11024643320363164,
      "grad_norm": 17.65021514892578,
      "learning_rate": 3.272527762979553e-06,
      "loss": 1.1424,
      "step": 85
    },
    {
      "epoch": 0.11154345006485085,
      "grad_norm": 2.7677478790283203,
      "learning_rate": 2.86474508437579e-06,
      "loss": 0.0682,
      "step": 86
    },
    {
      "epoch": 0.11284046692607004,
      "grad_norm": 9.2994966506958,
      "learning_rate": 2.4814011941804603e-06,
      "loss": 0.3074,
      "step": 87
    },
    {
      "epoch": 0.11413748378728923,
      "grad_norm": 5.88765811920166,
      "learning_rate": 2.1232680959720085e-06,
      "loss": 0.2075,
      "step": 88
    },
    {
      "epoch": 0.11543450064850844,
      "grad_norm": 8.574594497680664,
      "learning_rate": 1.79106702214893e-06,
      "loss": 0.247,
      "step": 89
    },
    {
      "epoch": 0.11673151750972763,
      "grad_norm": 3.277462959289551,
      "learning_rate": 1.4854669814637145e-06,
      "loss": 0.0624,
      "step": 90
    },
    {
      "epoch": 0.11802853437094682,
      "grad_norm": 12.124244689941406,
      "learning_rate": 1.2070834117282414e-06,
      "loss": 0.3679,
      "step": 91
    },
    {
      "epoch": 0.11932555123216602,
      "grad_norm": 2.1732170581817627,
      "learning_rate": 9.56476940403942e-07,
      "loss": 0.0485,
      "step": 92
    },
    {
      "epoch": 0.12062256809338522,
      "grad_norm": 4.28770112991333,
      "learning_rate": 7.341522555726971e-07,
      "loss": 0.1238,
      "step": 93
    },
    {
      "epoch": 0.1219195849546044,
      "grad_norm": 2.6389272212982178,
      "learning_rate": 5.405570895622014e-07,
      "loss": 0.0633,
      "step": 94
    },
    {
      "epoch": 0.12321660181582361,
      "grad_norm": 7.191143989562988,
      "learning_rate": 3.760813172726457e-07,
      "loss": 0.1797,
      "step": 95
    },
    {
      "epoch": 0.1245136186770428,
      "grad_norm": 10.877296447753906,
      "learning_rate": 2.41056171020555e-07,
      "loss": 0.2109,
      "step": 96
    },
    {
      "epoch": 0.125810635538262,
      "grad_norm": 21.885887145996094,
      "learning_rate": 1.357535734809795e-07,
      "loss": 0.8667,
      "step": 97
    },
    {
      "epoch": 0.12710765239948119,
      "grad_norm": 1.5145925283432007,
      "learning_rate": 6.038559007141397e-08,
      "loss": 0.0464,
      "step": 98
    },
    {
      "epoch": 0.12840466926070038,
      "grad_norm": 22.95406723022461,
      "learning_rate": 1.510400188028116e-08,
      "loss": 0.2276,
      "step": 99
    },
    {
      "epoch": 0.1297016861219196,
      "grad_norm": 10.279451370239258,
      "learning_rate": 0.0,
      "loss": 0.1799,
      "step": 100
    },
    {
      "epoch": 0.1297016861219196,
      "eval_loss": 0.10878434032201767,
      "eval_runtime": 44.3192,
      "eval_samples_per_second": 7.333,
      "eval_steps_per_second": 1.85,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": 3.32627164790784e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}