{
  "best_metric": 1.2692981958389282,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.018789928598271326,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018789928598271326,
      "grad_norm": 8.089397430419922,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 4.6183,
      "step": 1
    },
    {
      "epoch": 0.00018789928598271326,
      "eval_loss": 2.3376758098602295,
      "eval_runtime": 822.7797,
      "eval_samples_per_second": 10.895,
      "eval_steps_per_second": 5.447,
      "step": 1
    },
    {
      "epoch": 0.0003757985719654265,
      "grad_norm": 9.32201862335205,
      "learning_rate": 6.666666666666667e-06,
      "loss": 4.6686,
      "step": 2
    },
    {
      "epoch": 0.0005636978579481398,
      "grad_norm": 8.962303161621094,
      "learning_rate": 1e-05,
      "loss": 4.6015,
      "step": 3
    },
    {
      "epoch": 0.000751597143930853,
      "grad_norm": 6.618922710418701,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 4.42,
      "step": 4
    },
    {
      "epoch": 0.0009394964299135663,
      "grad_norm": 5.780028343200684,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 3.8984,
      "step": 5
    },
    {
      "epoch": 0.0011273957158962795,
      "grad_norm": 5.112532138824463,
      "learning_rate": 2e-05,
      "loss": 3.9961,
      "step": 6
    },
    {
      "epoch": 0.0013152950018789928,
      "grad_norm": 4.7758402824401855,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 4.0382,
      "step": 7
    },
    {
      "epoch": 0.001503194287861706,
      "grad_norm": 4.002161026000977,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 6.447,
      "step": 8
    },
    {
      "epoch": 0.0016910935738444193,
      "grad_norm": 3.693472146987915,
      "learning_rate": 3e-05,
      "loss": 6.4715,
      "step": 9
    },
    {
      "epoch": 0.0018789928598271326,
      "grad_norm": 4.906447410583496,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 4.8352,
      "step": 10
    },
    {
      "epoch": 0.002066892145809846,
      "grad_norm": 4.642434597015381,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 5.1161,
      "step": 11
    },
    {
      "epoch": 0.002254791431792559,
      "grad_norm": 4.053666591644287,
      "learning_rate": 4e-05,
      "loss": 5.2271,
      "step": 12
    },
    {
      "epoch": 0.0024426907177752723,
      "grad_norm": 4.311800479888916,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 5.7124,
      "step": 13
    },
    {
      "epoch": 0.0026305900037579856,
      "grad_norm": 3.9106714725494385,
      "learning_rate": 4.666666666666667e-05,
      "loss": 4.7916,
      "step": 14
    },
    {
      "epoch": 0.002818489289740699,
      "grad_norm": 3.9047529697418213,
      "learning_rate": 5e-05,
      "loss": 4.9605,
      "step": 15
    },
    {
      "epoch": 0.003006388575723412,
      "grad_norm": 6.001646041870117,
      "learning_rate": 5.333333333333333e-05,
      "loss": 5.2707,
      "step": 16
    },
    {
      "epoch": 0.0031942878617061254,
      "grad_norm": 4.10309362411499,
      "learning_rate": 5.666666666666667e-05,
      "loss": 5.8945,
      "step": 17
    },
    {
      "epoch": 0.0033821871476888386,
      "grad_norm": 3.8678953647613525,
      "learning_rate": 6e-05,
      "loss": 5.1987,
      "step": 18
    },
    {
      "epoch": 0.003570086433671552,
      "grad_norm": 3.8875012397766113,
      "learning_rate": 6.333333333333333e-05,
      "loss": 4.8459,
      "step": 19
    },
    {
      "epoch": 0.003757985719654265,
      "grad_norm": 3.875514507293701,
      "learning_rate": 6.666666666666667e-05,
      "loss": 4.5654,
      "step": 20
    },
    {
      "epoch": 0.003945885005636978,
      "grad_norm": 4.3774943351745605,
      "learning_rate": 7e-05,
      "loss": 5.0304,
      "step": 21
    },
    {
      "epoch": 0.004133784291619692,
      "grad_norm": 9.754307746887207,
      "learning_rate": 7.333333333333333e-05,
      "loss": 5.6285,
      "step": 22
    },
    {
      "epoch": 0.004321683577602405,
      "grad_norm": 5.715425968170166,
      "learning_rate": 7.666666666666667e-05,
      "loss": 6.7236,
      "step": 23
    },
    {
      "epoch": 0.004509582863585118,
      "grad_norm": 6.149569034576416,
      "learning_rate": 8e-05,
      "loss": 6.1906,
      "step": 24
    },
    {
      "epoch": 0.004697482149567831,
      "grad_norm": 5.921987056732178,
      "learning_rate": 8.333333333333334e-05,
      "loss": 6.3798,
      "step": 25
    },
    {
      "epoch": 0.004885381435550545,
      "grad_norm": 6.240573883056641,
      "learning_rate": 8.666666666666667e-05,
      "loss": 6.1837,
      "step": 26
    },
    {
      "epoch": 0.005073280721533258,
      "grad_norm": 5.769016265869141,
      "learning_rate": 9e-05,
      "loss": 6.4518,
      "step": 27
    },
    {
      "epoch": 0.005261180007515971,
      "grad_norm": 5.863321781158447,
      "learning_rate": 9.333333333333334e-05,
      "loss": 6.2235,
      "step": 28
    },
    {
      "epoch": 0.0054490792934986845,
      "grad_norm": 6.841501712799072,
      "learning_rate": 9.666666666666667e-05,
      "loss": 5.9651,
      "step": 29
    },
    {
      "epoch": 0.005636978579481398,
      "grad_norm": 5.785431385040283,
      "learning_rate": 0.0001,
      "loss": 5.9554,
      "step": 30
    },
    {
      "epoch": 0.005824877865464111,
      "grad_norm": 5.980314254760742,
      "learning_rate": 9.994965332706573e-05,
      "loss": 5.6978,
      "step": 31
    },
    {
      "epoch": 0.006012777151446824,
      "grad_norm": 6.056541442871094,
      "learning_rate": 9.979871469976196e-05,
      "loss": 5.2931,
      "step": 32
    },
    {
      "epoch": 0.0062006764374295375,
      "grad_norm": 5.904792308807373,
      "learning_rate": 9.954748808839674e-05,
      "loss": 5.5411,
      "step": 33
    },
    {
      "epoch": 0.006388575723412251,
      "grad_norm": 5.62144136428833,
      "learning_rate": 9.919647942993148e-05,
      "loss": 4.1701,
      "step": 34
    },
    {
      "epoch": 0.006576475009394964,
      "grad_norm": 6.057515621185303,
      "learning_rate": 9.874639560909117e-05,
      "loss": 4.739,
      "step": 35
    },
    {
      "epoch": 0.006764374295377677,
      "grad_norm": 7.6517558097839355,
      "learning_rate": 9.819814303479267e-05,
      "loss": 5.8531,
      "step": 36
    },
    {
      "epoch": 0.0069522735813603905,
      "grad_norm": 5.870713710784912,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.2783,
      "step": 37
    },
    {
      "epoch": 0.007140172867343104,
      "grad_norm": 6.46204137802124,
      "learning_rate": 9.681174353198687e-05,
      "loss": 4.375,
      "step": 38
    },
    {
      "epoch": 0.007328072153325817,
      "grad_norm": 7.084475994110107,
      "learning_rate": 9.597638862757255e-05,
      "loss": 4.1746,
      "step": 39
    },
    {
      "epoch": 0.00751597143930853,
      "grad_norm": 6.561005115509033,
      "learning_rate": 9.504844339512095e-05,
      "loss": 5.4644,
      "step": 40
    },
    {
      "epoch": 0.0077038707252912435,
      "grad_norm": 7.431431770324707,
      "learning_rate": 9.40297765928369e-05,
      "loss": 4.7945,
      "step": 41
    },
    {
      "epoch": 0.007891770011273957,
      "grad_norm": 8.801129341125488,
      "learning_rate": 9.292243968009331e-05,
      "loss": 6.055,
      "step": 42
    },
    {
      "epoch": 0.00807966929725667,
      "grad_norm": 9.020700454711914,
      "learning_rate": 9.172866268606513e-05,
      "loss": 7.4741,
      "step": 43
    },
    {
      "epoch": 0.008267568583239383,
      "grad_norm": 8.685187339782715,
      "learning_rate": 9.045084971874738e-05,
      "loss": 6.0838,
      "step": 44
    },
    {
      "epoch": 0.008455467869222097,
      "grad_norm": 8.159883499145508,
      "learning_rate": 8.90915741234015e-05,
      "loss": 5.7845,
      "step": 45
    },
    {
      "epoch": 0.00864336715520481,
      "grad_norm": 8.369349479675293,
      "learning_rate": 8.765357330018056e-05,
      "loss": 5.8667,
      "step": 46
    },
    {
      "epoch": 0.008831266441187523,
      "grad_norm": 8.60290813446045,
      "learning_rate": 8.613974319136958e-05,
      "loss": 5.4422,
      "step": 47
    },
    {
      "epoch": 0.009019165727170236,
      "grad_norm": 9.08957290649414,
      "learning_rate": 8.455313244934324e-05,
      "loss": 5.5388,
      "step": 48
    },
    {
      "epoch": 0.00920706501315295,
      "grad_norm": 8.95803165435791,
      "learning_rate": 8.289693629698564e-05,
      "loss": 5.2326,
      "step": 49
    },
    {
      "epoch": 0.009394964299135663,
      "grad_norm": 7.402853965759277,
      "learning_rate": 8.117449009293668e-05,
      "loss": 4.5367,
      "step": 50
    },
    {
      "epoch": 0.009394964299135663,
      "eval_loss": 1.5429913997650146,
      "eval_runtime": 828.4457,
      "eval_samples_per_second": 10.82,
      "eval_steps_per_second": 5.41,
      "step": 50
    },
    {
      "epoch": 0.009582863585118376,
      "grad_norm": 12.12710189819336,
      "learning_rate": 7.938926261462366e-05,
      "loss": 4.1207,
      "step": 51
    },
    {
      "epoch": 0.00977076287110109,
      "grad_norm": 6.877650260925293,
      "learning_rate": 7.754484907260513e-05,
      "loss": 3.854,
      "step": 52
    },
    {
      "epoch": 0.009958662157083803,
      "grad_norm": 3.922449827194214,
      "learning_rate": 7.564496387029532e-05,
      "loss": 3.875,
      "step": 53
    },
    {
      "epoch": 0.010146561443066516,
      "grad_norm": 2.6158945560455322,
      "learning_rate": 7.369343312364993e-05,
      "loss": 3.8383,
      "step": 54
    },
    {
      "epoch": 0.01033446072904923,
      "grad_norm": 2.6309781074523926,
      "learning_rate": 7.169418695587791e-05,
      "loss": 3.3104,
      "step": 55
    },
    {
      "epoch": 0.010522360015031942,
      "grad_norm": 2.4806551933288574,
      "learning_rate": 6.965125158269619e-05,
      "loss": 3.6959,
      "step": 56
    },
    {
      "epoch": 0.010710259301014656,
      "grad_norm": 2.6647136211395264,
      "learning_rate": 6.756874120406714e-05,
      "loss": 4.4607,
      "step": 57
    },
    {
      "epoch": 0.010898158586997369,
      "grad_norm": 2.6696109771728516,
      "learning_rate": 6.545084971874738e-05,
      "loss": 5.5749,
      "step": 58
    },
    {
      "epoch": 0.011086057872980082,
      "grad_norm": 2.808939218521118,
      "learning_rate": 6.330184227833376e-05,
      "loss": 4.7221,
      "step": 59
    },
    {
      "epoch": 0.011273957158962795,
      "grad_norm": 2.9471914768218994,
      "learning_rate": 6.112604669781572e-05,
      "loss": 4.6405,
      "step": 60
    },
    {
      "epoch": 0.011461856444945509,
      "grad_norm": 2.7732815742492676,
      "learning_rate": 5.8927844739931834e-05,
      "loss": 4.311,
      "step": 61
    },
    {
      "epoch": 0.011649755730928222,
      "grad_norm": 2.873124599456787,
      "learning_rate": 5.6711663290882776e-05,
      "loss": 4.8382,
      "step": 62
    },
    {
      "epoch": 0.011837655016910935,
      "grad_norm": 2.967327117919922,
      "learning_rate": 5.448196544517168e-05,
      "loss": 4.4859,
      "step": 63
    },
    {
      "epoch": 0.012025554302893648,
      "grad_norm": 3.0220985412597656,
      "learning_rate": 5.2243241517525754e-05,
      "loss": 4.8879,
      "step": 64
    },
    {
      "epoch": 0.012213453588876362,
      "grad_norm": 5.608536720275879,
      "learning_rate": 5e-05,
      "loss": 4.8269,
      "step": 65
    },
    {
      "epoch": 0.012401352874859075,
      "grad_norm": 2.988602876663208,
      "learning_rate": 4.775675848247427e-05,
      "loss": 5.6113,
      "step": 66
    },
    {
      "epoch": 0.012589252160841788,
      "grad_norm": 2.927661180496216,
      "learning_rate": 4.551803455482833e-05,
      "loss": 4.4028,
      "step": 67
    },
    {
      "epoch": 0.012777151446824501,
      "grad_norm": 2.921163320541382,
      "learning_rate": 4.328833670911724e-05,
      "loss": 4.3565,
      "step": 68
    },
    {
      "epoch": 0.012965050732807215,
      "grad_norm": 3.0370848178863525,
      "learning_rate": 4.107215526006817e-05,
      "loss": 4.7969,
      "step": 69
    },
    {
      "epoch": 0.013152950018789928,
      "grad_norm": 3.3245177268981934,
      "learning_rate": 3.887395330218429e-05,
      "loss": 5.602,
      "step": 70
    },
    {
      "epoch": 0.013340849304772641,
      "grad_norm": 3.5475261211395264,
      "learning_rate": 3.6698157721666246e-05,
      "loss": 4.6884,
      "step": 71
    },
    {
      "epoch": 0.013528748590755355,
      "grad_norm": 3.5381057262420654,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 5.7957,
      "step": 72
    },
    {
      "epoch": 0.013716647876738068,
      "grad_norm": 4.085561752319336,
      "learning_rate": 3.243125879593286e-05,
      "loss": 5.4665,
      "step": 73
    },
    {
      "epoch": 0.013904547162720781,
      "grad_norm": 4.82763671875,
      "learning_rate": 3.0348748417303823e-05,
      "loss": 5.9452,
      "step": 74
    },
    {
      "epoch": 0.014092446448703494,
      "grad_norm": 4.237555980682373,
      "learning_rate": 2.8305813044122097e-05,
      "loss": 5.4789,
      "step": 75
    },
    {
      "epoch": 0.014280345734686208,
      "grad_norm": 4.894902229309082,
      "learning_rate": 2.630656687635007e-05,
      "loss": 6.3016,
      "step": 76
    },
    {
      "epoch": 0.01446824502066892,
      "grad_norm": 4.798618316650391,
      "learning_rate": 2.43550361297047e-05,
      "loss": 5.9612,
      "step": 77
    },
    {
      "epoch": 0.014656144306651634,
      "grad_norm": 7.736368179321289,
      "learning_rate": 2.245515092739488e-05,
      "loss": 6.1193,
      "step": 78
    },
    {
      "epoch": 0.014844043592634347,
      "grad_norm": 5.555391788482666,
      "learning_rate": 2.061073738537635e-05,
      "loss": 6.2544,
      "step": 79
    },
    {
      "epoch": 0.01503194287861706,
      "grad_norm": 6.320089817047119,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 5.6853,
      "step": 80
    },
    {
      "epoch": 0.015219842164599774,
      "grad_norm": 5.559424877166748,
      "learning_rate": 1.7103063703014372e-05,
      "loss": 4.8867,
      "step": 81
    },
    {
      "epoch": 0.015407741450582487,
      "grad_norm": 5.159763813018799,
      "learning_rate": 1.544686755065677e-05,
      "loss": 5.3778,
      "step": 82
    },
    {
      "epoch": 0.0155956407365652,
      "grad_norm": 5.190471649169922,
      "learning_rate": 1.3860256808630428e-05,
      "loss": 4.3495,
      "step": 83
    },
    {
      "epoch": 0.015783540022547914,
      "grad_norm": 5.162275314331055,
      "learning_rate": 1.2346426699819458e-05,
      "loss": 4.7606,
      "step": 84
    },
    {
      "epoch": 0.01597143930853063,
      "grad_norm": 5.0200347900390625,
      "learning_rate": 1.090842587659851e-05,
      "loss": 3.9641,
      "step": 85
    },
    {
      "epoch": 0.01615933859451334,
      "grad_norm": 4.721124172210693,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.9436,
      "step": 86
    },
    {
      "epoch": 0.016347237880496055,
      "grad_norm": 5.321893215179443,
      "learning_rate": 8.271337313934869e-06,
      "loss": 4.0494,
      "step": 87
    },
    {
      "epoch": 0.016535137166478767,
      "grad_norm": 5.561007022857666,
      "learning_rate": 7.077560319906695e-06,
      "loss": 4.481,
      "step": 88
    },
    {
      "epoch": 0.01672303645246148,
      "grad_norm": 6.137837886810303,
      "learning_rate": 5.9702234071631e-06,
      "loss": 4.0547,
      "step": 89
    },
    {
      "epoch": 0.016910935738444193,
      "grad_norm": 6.851164817810059,
      "learning_rate": 4.951556604879048e-06,
      "loss": 5.9195,
      "step": 90
    },
    {
      "epoch": 0.017098835024426908,
      "grad_norm": 6.387176036834717,
      "learning_rate": 4.023611372427471e-06,
      "loss": 6.3249,
      "step": 91
    },
    {
      "epoch": 0.01728673431040962,
      "grad_norm": 8.208516120910645,
      "learning_rate": 3.18825646801314e-06,
      "loss": 7.7682,
      "step": 92
    },
    {
      "epoch": 0.017474633596392335,
      "grad_norm": 8.880036354064941,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 7.4679,
      "step": 93
    },
    {
      "epoch": 0.017662532882375046,
      "grad_norm": 9.490116119384766,
      "learning_rate": 1.8018569652073381e-06,
      "loss": 6.5789,
      "step": 94
    },
    {
      "epoch": 0.01785043216835776,
      "grad_norm": 10.559647560119629,
      "learning_rate": 1.2536043909088191e-06,
      "loss": 7.196,
      "step": 95
    },
    {
      "epoch": 0.018038331454340473,
      "grad_norm": 10.684134483337402,
      "learning_rate": 8.035205700685167e-07,
      "loss": 5.8043,
      "step": 96
    },
    {
      "epoch": 0.018226230740323188,
      "grad_norm": 9.896649360656738,
      "learning_rate": 4.52511911603265e-07,
      "loss": 5.7818,
      "step": 97
    },
    {
      "epoch": 0.0184141300263059,
      "grad_norm": 10.521429061889648,
      "learning_rate": 2.012853002380466e-07,
      "loss": 5.4138,
      "step": 98
    },
    {
      "epoch": 0.018602029312288614,
      "grad_norm": 12.07073974609375,
      "learning_rate": 5.0346672934270534e-08,
      "loss": 5.933,
      "step": 99
    },
    {
      "epoch": 0.018789928598271326,
      "grad_norm": 15.48339557647705,
      "learning_rate": 0.0,
      "loss": 5.1382,
      "step": 100
    },
    {
      "epoch": 0.018789928598271326,
      "eval_loss": 1.2692981958389282,
      "eval_runtime": 828.1962,
      "eval_samples_per_second": 10.824,
      "eval_steps_per_second": 5.412,
      "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": 1.6778451655380173e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}