{
  "best_metric": 2.4749317169189453,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 1.0530934620447565,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014041246160596753,
      "grad_norm": 0.8327537775039673,
      "learning_rate": 2e-05,
      "loss": 1.9615,
      "step": 1
    },
    {
      "epoch": 0.014041246160596753,
      "eval_loss": 3.3978569507598877,
      "eval_runtime": 0.5068,
      "eval_samples_per_second": 98.667,
      "eval_steps_per_second": 25.654,
      "step": 1
    },
    {
      "epoch": 0.028082492321193506,
      "grad_norm": 1.332243800163269,
      "learning_rate": 4e-05,
      "loss": 1.824,
      "step": 2
    },
    {
      "epoch": 0.04212373848179026,
      "grad_norm": 1.4095451831817627,
      "learning_rate": 6e-05,
      "loss": 2.211,
      "step": 3
    },
    {
      "epoch": 0.05616498464238701,
      "grad_norm": 2.0809977054595947,
      "learning_rate": 8e-05,
      "loss": 2.3834,
      "step": 4
    },
    {
      "epoch": 0.07020623080298377,
      "grad_norm": 2.163429021835327,
      "learning_rate": 0.0001,
      "loss": 2.7688,
      "step": 5
    },
    {
      "epoch": 0.08424747696358052,
      "grad_norm": 2.884552001953125,
      "learning_rate": 9.997539658034168e-05,
      "loss": 2.8267,
      "step": 6
    },
    {
      "epoch": 0.09828872312417727,
      "grad_norm": 3.912673234939575,
      "learning_rate": 9.990161322484486e-05,
      "loss": 3.3231,
      "step": 7
    },
    {
      "epoch": 0.11232996928477403,
      "grad_norm": 5.349924564361572,
      "learning_rate": 9.977873061452552e-05,
      "loss": 3.5412,
      "step": 8
    },
    {
      "epoch": 0.12637121544537078,
      "grad_norm": 6.738022327423096,
      "learning_rate": 9.96068831197139e-05,
      "loss": 3.6021,
      "step": 9
    },
    {
      "epoch": 0.14041246160596754,
      "grad_norm": 8.926319122314453,
      "learning_rate": 9.938625865312251e-05,
      "loss": 3.5968,
      "step": 10
    },
    {
      "epoch": 0.15445370776656428,
      "grad_norm": 8.15119743347168,
      "learning_rate": 9.911709846436641e-05,
      "loss": 3.9218,
      "step": 11
    },
    {
      "epoch": 0.16849495392716105,
      "grad_norm": 12.402828216552734,
      "learning_rate": 9.879969687616027e-05,
      "loss": 4.5223,
      "step": 12
    },
    {
      "epoch": 0.18253620008775778,
      "grad_norm": 2.7531869411468506,
      "learning_rate": 9.84344009624807e-05,
      "loss": 2.1757,
      "step": 13
    },
    {
      "epoch": 0.19657744624835455,
      "grad_norm": 5.453584671020508,
      "learning_rate": 9.80216101690461e-05,
      "loss": 1.8657,
      "step": 14
    },
    {
      "epoch": 0.21061869240895129,
      "grad_norm": 6.201056003570557,
      "learning_rate": 9.756177587652856e-05,
      "loss": 2.0874,
      "step": 15
    },
    {
      "epoch": 0.22465993856954805,
      "grad_norm": 6.548382759094238,
      "learning_rate": 9.705540090697575e-05,
      "loss": 2.5228,
      "step": 16
    },
    {
      "epoch": 0.2387011847301448,
      "grad_norm": 4.07675313949585,
      "learning_rate": 9.650303897398232e-05,
      "loss": 2.5761,
      "step": 17
    },
    {
      "epoch": 0.25274243089074155,
      "grad_norm": 2.8793468475341797,
      "learning_rate": 9.590529407721231e-05,
      "loss": 2.6513,
      "step": 18
    },
    {
      "epoch": 0.2667836770513383,
      "grad_norm": 5.506067276000977,
      "learning_rate": 9.526281984193436e-05,
      "loss": 3.0722,
      "step": 19
    },
    {
      "epoch": 0.2808249232119351,
      "grad_norm": 10.677892684936523,
      "learning_rate": 9.4576318804292e-05,
      "loss": 3.2006,
      "step": 20
    },
    {
      "epoch": 0.2948661693725318,
      "grad_norm": 9.370729446411133,
      "learning_rate": 9.384654164309083e-05,
      "loss": 3.1187,
      "step": 21
    },
    {
      "epoch": 0.30890741553312856,
      "grad_norm": 7.775137901306152,
      "learning_rate": 9.30742863589421e-05,
      "loss": 3.2763,
      "step": 22
    },
    {
      "epoch": 0.3229486616937253,
      "grad_norm": 6.3419623374938965,
      "learning_rate": 9.226039740166091e-05,
      "loss": 3.7332,
      "step": 23
    },
    {
      "epoch": 0.3369899078543221,
      "grad_norm": 8.918274879455566,
      "learning_rate": 9.140576474687264e-05,
      "loss": 3.8572,
      "step": 24
    },
    {
      "epoch": 0.3510311540149188,
      "grad_norm": 15.176338195800781,
      "learning_rate": 9.051132292283771e-05,
      "loss": 5.0712,
      "step": 25
    },
    {
      "epoch": 0.3510311540149188,
      "eval_loss": 2.6227145195007324,
      "eval_runtime": 0.5047,
      "eval_samples_per_second": 99.066,
      "eval_steps_per_second": 25.757,
      "step": 25
    },
    {
      "epoch": 0.36507240017551557,
      "grad_norm": 0.5822151303291321,
      "learning_rate": 8.957804998855866e-05,
      "loss": 2.2137,
      "step": 26
    },
    {
      "epoch": 0.37911364633611233,
      "grad_norm": 0.612755298614502,
      "learning_rate": 8.860696646428693e-05,
      "loss": 1.8046,
      "step": 27
    },
    {
      "epoch": 0.3931548924967091,
      "grad_norm": 0.6512185335159302,
      "learning_rate": 8.759913421559902e-05,
      "loss": 2.0374,
      "step": 28
    },
    {
      "epoch": 0.40719613865730586,
      "grad_norm": 0.9296779036521912,
      "learning_rate": 8.655565529226198e-05,
      "loss": 2.2375,
      "step": 29
    },
    {
      "epoch": 0.42123738481790257,
      "grad_norm": 1.1704964637756348,
      "learning_rate": 8.547767072315835e-05,
      "loss": 2.4913,
      "step": 30
    },
    {
      "epoch": 0.43527863097849934,
      "grad_norm": 1.2606786489486694,
      "learning_rate": 8.436635926858759e-05,
      "loss": 2.6343,
      "step": 31
    },
    {
      "epoch": 0.4493198771390961,
      "grad_norm": 1.8587498664855957,
      "learning_rate": 8.322293613130917e-05,
      "loss": 3.0057,
      "step": 32
    },
    {
      "epoch": 0.46336112329969287,
      "grad_norm": 1.7915164232254028,
      "learning_rate": 8.204865162773613e-05,
      "loss": 3.0309,
      "step": 33
    },
    {
      "epoch": 0.4774023694602896,
      "grad_norm": 2.1659657955169678,
      "learning_rate": 8.084478982073247e-05,
      "loss": 3.1982,
      "step": 34
    },
    {
      "epoch": 0.49144361562088634,
      "grad_norm": 2.6619133949279785,
      "learning_rate": 7.961266711550922e-05,
      "loss": 3.3039,
      "step": 35
    },
    {
      "epoch": 0.5054848617814831,
      "grad_norm": 3.697298288345337,
      "learning_rate": 7.835363082015468e-05,
      "loss": 3.6746,
      "step": 36
    },
    {
      "epoch": 0.5195261079420799,
      "grad_norm": 5.550060749053955,
      "learning_rate": 7.706905767237288e-05,
      "loss": 3.8725,
      "step": 37
    },
    {
      "epoch": 0.5335673541026766,
      "grad_norm": 0.6753820180892944,
      "learning_rate": 7.576035233404096e-05,
      "loss": 2.2385,
      "step": 38
    },
    {
      "epoch": 0.5476086002632734,
      "grad_norm": 1.0300302505493164,
      "learning_rate": 7.442894585523218e-05,
      "loss": 1.7155,
      "step": 39
    },
    {
      "epoch": 0.5616498464238702,
      "grad_norm": 1.5170297622680664,
      "learning_rate": 7.307629410938363e-05,
      "loss": 1.858,
      "step": 40
    },
    {
      "epoch": 0.5756910925844668,
      "grad_norm": 2.700623035430908,
      "learning_rate": 7.170387620131993e-05,
      "loss": 2.2176,
      "step": 41
    },
    {
      "epoch": 0.5897323387450636,
      "grad_norm": 3.4165198802948,
      "learning_rate": 7.031319284987394e-05,
      "loss": 2.4351,
      "step": 42
    },
    {
      "epoch": 0.6037735849056604,
      "grad_norm": 2.0354185104370117,
      "learning_rate": 6.890576474687263e-05,
      "loss": 2.4769,
      "step": 43
    },
    {
      "epoch": 0.6178148310662571,
      "grad_norm": 1.5906285047531128,
      "learning_rate": 6.7483130894283e-05,
      "loss": 2.8552,
      "step": 44
    },
    {
      "epoch": 0.6318560772268539,
      "grad_norm": 1.8608163595199585,
      "learning_rate": 6.604684692133597e-05,
      "loss": 2.8639,
      "step": 45
    },
    {
      "epoch": 0.6458973233874507,
      "grad_norm": 2.8141560554504395,
      "learning_rate": 6.459848338346861e-05,
      "loss": 2.8932,
      "step": 46
    },
    {
      "epoch": 0.6599385695480474,
      "grad_norm": 4.370851993560791,
      "learning_rate": 6.313962404494496e-05,
      "loss": 3.1846,
      "step": 47
    },
    {
      "epoch": 0.6739798157086442,
      "grad_norm": 4.608976364135742,
      "learning_rate": 6.167186414703289e-05,
      "loss": 3.3674,
      "step": 48
    },
    {
      "epoch": 0.688021061869241,
      "grad_norm": 6.83935022354126,
      "learning_rate": 6.019680866363139e-05,
      "loss": 3.7393,
      "step": 49
    },
    {
      "epoch": 0.7020623080298376,
      "grad_norm": 11.380165100097656,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 4.2031,
      "step": 50
    },
    {
      "epoch": 0.7020623080298376,
      "eval_loss": 2.51250958442688,
      "eval_runtime": 0.5058,
      "eval_samples_per_second": 98.857,
      "eval_steps_per_second": 25.703,
      "step": 50
    },
    {
      "epoch": 0.7161035541904344,
      "grad_norm": 0.2579071819782257,
      "learning_rate": 5.7231268960295e-05,
      "loss": 1.8802,
      "step": 51
    },
    {
      "epoch": 0.7301448003510311,
      "grad_norm": 0.4030728042125702,
      "learning_rate": 5.574402751448614e-05,
      "loss": 1.6649,
      "step": 52
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 0.5643269419670105,
      "learning_rate": 5.425597248551387e-05,
      "loss": 2.049,
      "step": 53
    },
    {
      "epoch": 0.7582272926722247,
      "grad_norm": 0.7029362916946411,
      "learning_rate": 5.2768731039705e-05,
      "loss": 2.2015,
      "step": 54
    },
    {
      "epoch": 0.7722685388328214,
      "grad_norm": 0.9349853992462158,
      "learning_rate": 5.128392945374505e-05,
      "loss": 2.4515,
      "step": 55
    },
    {
      "epoch": 0.7863097849934182,
      "grad_norm": 0.9511843323707581,
      "learning_rate": 4.980319133636863e-05,
      "loss": 2.6827,
      "step": 56
    },
    {
      "epoch": 0.800351031154015,
      "grad_norm": 1.3044384717941284,
      "learning_rate": 4.83281358529671e-05,
      "loss": 2.8935,
      "step": 57
    },
    {
      "epoch": 0.8143922773146117,
      "grad_norm": 1.4280407428741455,
      "learning_rate": 4.686037595505507e-05,
      "loss": 2.9421,
      "step": 58
    },
    {
      "epoch": 0.8284335234752084,
      "grad_norm": 1.7793262004852295,
      "learning_rate": 4.54015166165314e-05,
      "loss": 3.0256,
      "step": 59
    },
    {
      "epoch": 0.8424747696358051,
      "grad_norm": 2.2841506004333496,
      "learning_rate": 4.395315307866405e-05,
      "loss": 3.1879,
      "step": 60
    },
    {
      "epoch": 0.8565160157964019,
      "grad_norm": 3.2203478813171387,
      "learning_rate": 4.2516869105717004e-05,
      "loss": 3.5137,
      "step": 61
    },
    {
      "epoch": 0.8705572619569987,
      "grad_norm": 4.7022576332092285,
      "learning_rate": 4.109423525312738e-05,
      "loss": 3.5993,
      "step": 62
    },
    {
      "epoch": 0.8845985081175954,
      "grad_norm": 0.3040692210197449,
      "learning_rate": 3.968680715012606e-05,
      "loss": 2.1119,
      "step": 63
    },
    {
      "epoch": 0.8986397542781922,
      "grad_norm": 0.37016022205352783,
      "learning_rate": 3.829612379868006e-05,
      "loss": 1.8168,
      "step": 64
    },
    {
      "epoch": 0.912681000438789,
      "grad_norm": 0.7952561378479004,
      "learning_rate": 3.692370589061639e-05,
      "loss": 2.1704,
      "step": 65
    },
    {
      "epoch": 0.9267222465993857,
      "grad_norm": 1.0236883163452148,
      "learning_rate": 3.557105414476782e-05,
      "loss": 2.3811,
      "step": 66
    },
    {
      "epoch": 0.9407634927599825,
      "grad_norm": 1.1880155801773071,
      "learning_rate": 3.423964766595906e-05,
      "loss": 2.6713,
      "step": 67
    },
    {
      "epoch": 0.9548047389205792,
      "grad_norm": 1.3189986944198608,
      "learning_rate": 3.293094232762715e-05,
      "loss": 2.7698,
      "step": 68
    },
    {
      "epoch": 0.9688459850811759,
      "grad_norm": 1.691144347190857,
      "learning_rate": 3.164636917984534e-05,
      "loss": 3.0012,
      "step": 69
    },
    {
      "epoch": 0.9828872312417727,
      "grad_norm": 2.0627942085266113,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 3.2204,
      "step": 70
    },
    {
      "epoch": 0.9969284774023695,
      "grad_norm": 4.911252498626709,
      "learning_rate": 2.9155210179267546e-05,
      "loss": 3.705,
      "step": 71
    },
    {
      "epoch": 1.0109697235629662,
      "grad_norm": 11.608001708984375,
      "learning_rate": 2.7951348372263875e-05,
      "loss": 4.9898,
      "step": 72
    },
    {
      "epoch": 1.025010969723563,
      "grad_norm": 0.3285130262374878,
      "learning_rate": 2.677706386869083e-05,
      "loss": 1.4574,
      "step": 73
    },
    {
      "epoch": 1.0390522158841597,
      "grad_norm": 0.49857988953590393,
      "learning_rate": 2.5633640731412412e-05,
      "loss": 1.9682,
      "step": 74
    },
    {
      "epoch": 1.0530934620447565,
      "grad_norm": 0.6986849308013916,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 1.9892,
      "step": 75
    },
    {
      "epoch": 1.0530934620447565,
      "eval_loss": 2.4749317169189453,
      "eval_runtime": 0.5047,
      "eval_samples_per_second": 99.064,
      "eval_steps_per_second": 25.757,
      "step": 75
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.42951368966144e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}