{
  "best_metric": 1.098335862159729,
  "best_model_checkpoint": "miner_id_24/checkpoint-75",
  "epoch": 0.23491229425855806,
  "eval_steps": 25,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002472760992195348,
      "grad_norm": 47.05653381347656,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 41.7908,
      "step": 1
    },
    {
      "epoch": 0.002472760992195348,
      "eval_loss": 1.7607932090759277,
      "eval_runtime": 2.3095,
      "eval_samples_per_second": 21.65,
      "eval_steps_per_second": 5.629,
      "step": 1
    },
    {
      "epoch": 0.004945521984390696,
      "grad_norm": 53.91913986206055,
      "learning_rate": 6.666666666666667e-05,
      "loss": 42.5491,
      "step": 2
    },
    {
      "epoch": 0.007418282976586045,
      "grad_norm": 40.81502914428711,
      "learning_rate": 0.0001,
      "loss": 41.2687,
      "step": 3
    },
    {
      "epoch": 0.009891043968781392,
      "grad_norm": 39.34718704223633,
      "learning_rate": 9.997376600647783e-05,
      "loss": 40.5321,
      "step": 4
    },
    {
      "epoch": 0.01236380496097674,
      "grad_norm": 44.35953903198242,
      "learning_rate": 9.989509461357426e-05,
      "loss": 40.7421,
      "step": 5
    },
    {
      "epoch": 0.01483656595317209,
      "grad_norm": 46.38814926147461,
      "learning_rate": 9.976407754861426e-05,
      "loss": 38.9692,
      "step": 6
    },
    {
      "epoch": 0.017309326945367437,
      "grad_norm": 58.17334747314453,
      "learning_rate": 9.958086757163489e-05,
      "loss": 38.9604,
      "step": 7
    },
    {
      "epoch": 0.019782087937562785,
      "grad_norm": 80.08734130859375,
      "learning_rate": 9.934567829727386e-05,
      "loss": 41.4573,
      "step": 8
    },
    {
      "epoch": 0.022254848929758132,
      "grad_norm": 78.48131561279297,
      "learning_rate": 9.905878394570453e-05,
      "loss": 39.2966,
      "step": 9
    },
    {
      "epoch": 0.02472760992195348,
      "grad_norm": 95.64398956298828,
      "learning_rate": 9.872051902290737e-05,
      "loss": 43.9062,
      "step": 10
    },
    {
      "epoch": 0.027200370914148828,
      "grad_norm": 139.08731079101562,
      "learning_rate": 9.833127793065098e-05,
      "loss": 42.225,
      "step": 11
    },
    {
      "epoch": 0.02967313190634418,
      "grad_norm": 174.1289825439453,
      "learning_rate": 9.789151450663723e-05,
      "loss": 48.2078,
      "step": 12
    },
    {
      "epoch": 0.03214589289853952,
      "grad_norm": 127.45459747314453,
      "learning_rate": 9.740174149534693e-05,
      "loss": 45.7045,
      "step": 13
    },
    {
      "epoch": 0.034618653890734874,
      "grad_norm": 74.5115966796875,
      "learning_rate": 9.686252995020249e-05,
      "loss": 42.8674,
      "step": 14
    },
    {
      "epoch": 0.037091414882930225,
      "grad_norm": 50.860382080078125,
      "learning_rate": 9.627450856774539e-05,
      "loss": 40.047,
      "step": 15
    },
    {
      "epoch": 0.03956417587512557,
      "grad_norm": 31.999807357788086,
      "learning_rate": 9.563836295460398e-05,
      "loss": 39.1383,
      "step": 16
    },
    {
      "epoch": 0.04203693686732092,
      "grad_norm": 33.651119232177734,
      "learning_rate": 9.495483482810688e-05,
      "loss": 38.756,
      "step": 17
    },
    {
      "epoch": 0.044509697859516265,
      "grad_norm": 35.75480270385742,
      "learning_rate": 9.422472115147382e-05,
      "loss": 39.7262,
      "step": 18
    },
    {
      "epoch": 0.046982458851711616,
      "grad_norm": 43.49586486816406,
      "learning_rate": 9.3448873204592e-05,
      "loss": 38.2868,
      "step": 19
    },
    {
      "epoch": 0.04945521984390696,
      "grad_norm": 69.08320617675781,
      "learning_rate": 9.2628195591462e-05,
      "loss": 41.9362,
      "step": 20
    },
    {
      "epoch": 0.05192798083610231,
      "grad_norm": 67.43238067626953,
      "learning_rate": 9.176364518546989e-05,
      "loss": 37.1524,
      "step": 21
    },
    {
      "epoch": 0.054400741828297655,
      "grad_norm": 85.18617248535156,
      "learning_rate": 9.08562300137157e-05,
      "loss": 37.6795,
      "step": 22
    },
    {
      "epoch": 0.056873502820493006,
      "grad_norm": 82.79244995117188,
      "learning_rate": 8.990700808169889e-05,
      "loss": 38.9042,
      "step": 23
    },
    {
      "epoch": 0.05934626381268836,
      "grad_norm": 90.79505920410156,
      "learning_rate": 8.891708613973126e-05,
      "loss": 37.9686,
      "step": 24
    },
    {
      "epoch": 0.0618190248048837,
      "grad_norm": 213.368896484375,
      "learning_rate": 8.788761839251559e-05,
      "loss": 53.6117,
      "step": 25
    },
    {
      "epoch": 0.0618190248048837,
      "eval_loss": 1.2167118787765503,
      "eval_runtime": 2.3071,
      "eval_samples_per_second": 21.672,
      "eval_steps_per_second": 5.635,
      "step": 25
    },
    {
      "epoch": 0.06429178579707905,
      "grad_norm": 37.73557662963867,
      "learning_rate": 8.681980515339464e-05,
      "loss": 39.1072,
      "step": 26
    },
    {
      "epoch": 0.0667645467892744,
      "grad_norm": 39.4856071472168,
      "learning_rate": 8.571489144483944e-05,
      "loss": 40.2629,
      "step": 27
    },
    {
      "epoch": 0.06923730778146975,
      "grad_norm": 33.05232620239258,
      "learning_rate": 8.457416554680877e-05,
      "loss": 38.4942,
      "step": 28
    },
    {
      "epoch": 0.07171006877366509,
      "grad_norm": 29.005043029785156,
      "learning_rate": 8.339895749467238e-05,
      "loss": 38.0044,
      "step": 29
    },
    {
      "epoch": 0.07418282976586045,
      "grad_norm": 29.954980850219727,
      "learning_rate": 8.219063752844926e-05,
      "loss": 38.3598,
      "step": 30
    },
    {
      "epoch": 0.0766555907580558,
      "grad_norm": 31.648218154907227,
      "learning_rate": 8.095061449516903e-05,
      "loss": 38.6649,
      "step": 31
    },
    {
      "epoch": 0.07912835175025114,
      "grad_norm": 43.9088134765625,
      "learning_rate": 7.968033420621935e-05,
      "loss": 37.3321,
      "step": 32
    },
    {
      "epoch": 0.08160111274244648,
      "grad_norm": 45.55607604980469,
      "learning_rate": 7.838127775159452e-05,
      "loss": 34.0225,
      "step": 33
    },
    {
      "epoch": 0.08407387373464184,
      "grad_norm": 74.37454986572266,
      "learning_rate": 7.705495977301078e-05,
      "loss": 36.4667,
      "step": 34
    },
    {
      "epoch": 0.08654663472683718,
      "grad_norm": 66.72908782958984,
      "learning_rate": 7.570292669790186e-05,
      "loss": 33.7556,
      "step": 35
    },
    {
      "epoch": 0.08901939571903253,
      "grad_norm": 82.05652618408203,
      "learning_rate": 7.43267549363537e-05,
      "loss": 35.8552,
      "step": 36
    },
    {
      "epoch": 0.09149215671122789,
      "grad_norm": 118.45052337646484,
      "learning_rate": 7.292804904308087e-05,
      "loss": 41.1993,
      "step": 37
    },
    {
      "epoch": 0.09396491770342323,
      "grad_norm": 105.6920394897461,
      "learning_rate": 7.150843984658754e-05,
      "loss": 40.8987,
      "step": 38
    },
    {
      "epoch": 0.09643767869561858,
      "grad_norm": 34.49168014526367,
      "learning_rate": 7.006958254769438e-05,
      "loss": 36.2643,
      "step": 39
    },
    {
      "epoch": 0.09891043968781392,
      "grad_norm": 24.8678035736084,
      "learning_rate": 6.861315478964841e-05,
      "loss": 37.1254,
      "step": 40
    },
    {
      "epoch": 0.10138320068000928,
      "grad_norm": 24.664064407348633,
      "learning_rate": 6.714085470206609e-05,
      "loss": 37.3573,
      "step": 41
    },
    {
      "epoch": 0.10385596167220462,
      "grad_norm": 24.782764434814453,
      "learning_rate": 6.56543989209901e-05,
      "loss": 37.732,
      "step": 42
    },
    {
      "epoch": 0.10632872266439997,
      "grad_norm": 27.32329750061035,
      "learning_rate": 6.415552058736854e-05,
      "loss": 37.1562,
      "step": 43
    },
    {
      "epoch": 0.10880148365659531,
      "grad_norm": 30.12747573852539,
      "learning_rate": 6.264596732629e-05,
      "loss": 37.8521,
      "step": 44
    },
    {
      "epoch": 0.11127424464879067,
      "grad_norm": 42.28104019165039,
      "learning_rate": 6.112749920933111e-05,
      "loss": 36.7405,
      "step": 45
    },
    {
      "epoch": 0.11374700564098601,
      "grad_norm": 81.71856689453125,
      "learning_rate": 5.960188670239154e-05,
      "loss": 33.6306,
      "step": 46
    },
    {
      "epoch": 0.11621976663318136,
      "grad_norm": 55.820823669433594,
      "learning_rate": 5.80709086014102e-05,
      "loss": 34.3689,
      "step": 47
    },
    {
      "epoch": 0.11869252762537671,
      "grad_norm": 68.78173065185547,
      "learning_rate": 5.653634995836856e-05,
      "loss": 36.5956,
      "step": 48
    },
    {
      "epoch": 0.12116528861757206,
      "grad_norm": 112.97760772705078,
      "learning_rate": 5.500000000000001e-05,
      "loss": 40.6305,
      "step": 49
    },
    {
      "epoch": 0.1236380496097674,
      "grad_norm": 154.30474853515625,
      "learning_rate": 5.346365004163145e-05,
      "loss": 48.397,
      "step": 50
    },
    {
      "epoch": 0.1236380496097674,
      "eval_loss": 1.126763105392456,
      "eval_runtime": 2.3094,
      "eval_samples_per_second": 21.651,
      "eval_steps_per_second": 5.629,
      "step": 50
    },
    {
      "epoch": 0.12611081060196275,
      "grad_norm": 21.046512603759766,
      "learning_rate": 5.192909139858981e-05,
      "loss": 35.696,
      "step": 51
    },
    {
      "epoch": 0.1285835715941581,
      "grad_norm": 21.431148529052734,
      "learning_rate": 5.0398113297608465e-05,
      "loss": 36.7394,
      "step": 52
    },
    {
      "epoch": 0.13105633258635346,
      "grad_norm": 19.29589080810547,
      "learning_rate": 4.887250079066892e-05,
      "loss": 35.4277,
      "step": 53
    },
    {
      "epoch": 0.1335290935785488,
      "grad_norm": 21.196760177612305,
      "learning_rate": 4.7354032673710005e-05,
      "loss": 36.2991,
      "step": 54
    },
    {
      "epoch": 0.13600185457074415,
      "grad_norm": 23.4837703704834,
      "learning_rate": 4.584447941263149e-05,
      "loss": 34.555,
      "step": 55
    },
    {
      "epoch": 0.1384746155629395,
      "grad_norm": 28.75949478149414,
      "learning_rate": 4.43456010790099e-05,
      "loss": 36.8271,
      "step": 56
    },
    {
      "epoch": 0.14094737655513484,
      "grad_norm": 45.79991149902344,
      "learning_rate": 4.285914529793391e-05,
      "loss": 35.2289,
      "step": 57
    },
    {
      "epoch": 0.14342013754733018,
      "grad_norm": 50.974853515625,
      "learning_rate": 4.13868452103516e-05,
      "loss": 35.6219,
      "step": 58
    },
    {
      "epoch": 0.14589289853952553,
      "grad_norm": 56.22457504272461,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 32.0898,
      "step": 59
    },
    {
      "epoch": 0.1483656595317209,
      "grad_norm": 67.21727752685547,
      "learning_rate": 3.8491560153412466e-05,
      "loss": 33.8773,
      "step": 60
    },
    {
      "epoch": 0.15083842052391624,
      "grad_norm": 68.95596313476562,
      "learning_rate": 3.707195095691913e-05,
      "loss": 34.8849,
      "step": 61
    },
    {
      "epoch": 0.1533111815161116,
      "grad_norm": 117.9299087524414,
      "learning_rate": 3.567324506364632e-05,
      "loss": 40.8557,
      "step": 62
    },
    {
      "epoch": 0.15578394250830693,
      "grad_norm": 103.53528594970703,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 41.3747,
      "step": 63
    },
    {
      "epoch": 0.15825670350050228,
      "grad_norm": 20.954896926879883,
      "learning_rate": 3.2945040226989244e-05,
      "loss": 35.2383,
      "step": 64
    },
    {
      "epoch": 0.16072946449269762,
      "grad_norm": 21.524629592895508,
      "learning_rate": 3.16187222484055e-05,
      "loss": 37.1098,
      "step": 65
    },
    {
      "epoch": 0.16320222548489297,
      "grad_norm": 21.390296936035156,
      "learning_rate": 3.0319665793780648e-05,
      "loss": 35.8181,
      "step": 66
    },
    {
      "epoch": 0.16567498647708834,
      "grad_norm": 23.68910026550293,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 36.9141,
      "step": 67
    },
    {
      "epoch": 0.16814774746928368,
      "grad_norm": 24.922632217407227,
      "learning_rate": 2.7809362471550748e-05,
      "loss": 35.7167,
      "step": 68
    },
    {
      "epoch": 0.17062050846147903,
      "grad_norm": 31.565319061279297,
      "learning_rate": 2.660104250532764e-05,
      "loss": 37.4784,
      "step": 69
    },
    {
      "epoch": 0.17309326945367437,
      "grad_norm": 38.932884216308594,
      "learning_rate": 2.5425834453191232e-05,
      "loss": 35.6836,
      "step": 70
    },
    {
      "epoch": 0.17556603044586971,
      "grad_norm": 56.36356735229492,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 32.2436,
      "step": 71
    },
    {
      "epoch": 0.17803879143806506,
      "grad_norm": 54.911075592041016,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 33.7913,
      "step": 72
    },
    {
      "epoch": 0.1805115524302604,
      "grad_norm": 118.47933959960938,
      "learning_rate": 2.2112381607484417e-05,
      "loss": 35.8596,
      "step": 73
    },
    {
      "epoch": 0.18298431342245577,
      "grad_norm": 72.63341522216797,
      "learning_rate": 2.1082913860268765e-05,
      "loss": 29.9843,
      "step": 74
    },
    {
      "epoch": 0.18545707441465112,
      "grad_norm": 122.82919311523438,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 42.1549,
      "step": 75
    },
    {
      "epoch": 0.18545707441465112,
      "eval_loss": 1.098335862159729,
      "eval_runtime": 2.3061,
      "eval_samples_per_second": 21.682,
      "eval_steps_per_second": 5.637,
      "step": 75
    },
    {
      "epoch": 0.18792983540684646,
      "grad_norm": 17.364578247070312,
      "learning_rate": 1.91437699862843e-05,
      "loss": 35.0187,
      "step": 76
    },
    {
      "epoch": 0.1904025963990418,
      "grad_norm": 18.669057846069336,
      "learning_rate": 1.8236354814530112e-05,
      "loss": 36.0203,
      "step": 77
    },
    {
      "epoch": 0.19287535739123715,
      "grad_norm": 19.705821990966797,
      "learning_rate": 1.7371804408538024e-05,
      "loss": 34.0516,
      "step": 78
    },
    {
      "epoch": 0.1953481183834325,
      "grad_norm": 43.49521255493164,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 35.3763,
      "step": 79
    },
    {
      "epoch": 0.19782087937562784,
      "grad_norm": 26.601503372192383,
      "learning_rate": 1.577527884852619e-05,
      "loss": 35.9202,
      "step": 80
    },
    {
      "epoch": 0.2002936403678232,
      "grad_norm": 28.90140724182129,
      "learning_rate": 1.5045165171893116e-05,
      "loss": 35.4497,
      "step": 81
    },
    {
      "epoch": 0.20276640136001856,
      "grad_norm": 36.83986282348633,
      "learning_rate": 1.4361637045396029e-05,
      "loss": 34.5661,
      "step": 82
    },
    {
      "epoch": 0.2052391623522139,
      "grad_norm": 52.21437454223633,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 33.2943,
      "step": 83
    },
    {
      "epoch": 0.20771192334440924,
      "grad_norm": 66.34123229980469,
      "learning_rate": 1.313747004979751e-05,
      "loss": 31.1867,
      "step": 84
    },
    {
      "epoch": 0.2101846843366046,
      "grad_norm": 67.18898010253906,
      "learning_rate": 1.2598258504653081e-05,
      "loss": 32.7304,
      "step": 85
    },
    {
      "epoch": 0.21265744532879993,
      "grad_norm": 88.95117950439453,
      "learning_rate": 1.2108485493362765e-05,
      "loss": 37.2158,
      "step": 86
    },
    {
      "epoch": 0.21513020632099528,
      "grad_norm": 107.02346801757812,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 42.2313,
      "step": 87
    },
    {
      "epoch": 0.21760296731319062,
      "grad_norm": 107.11490631103516,
      "learning_rate": 1.1279480977092635e-05,
      "loss": 41.0211,
      "step": 88
    },
    {
      "epoch": 0.220075728305386,
      "grad_norm": 17.021472930908203,
      "learning_rate": 1.094121605429547e-05,
      "loss": 34.3979,
      "step": 89
    },
    {
      "epoch": 0.22254848929758134,
      "grad_norm": 19.336572647094727,
      "learning_rate": 1.0654321702726141e-05,
      "loss": 34.0475,
      "step": 90
    },
    {
      "epoch": 0.22502125028977668,
      "grad_norm": 21.753398895263672,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 36.3888,
      "step": 91
    },
    {
      "epoch": 0.22749401128197203,
      "grad_norm": 35.4598274230957,
      "learning_rate": 1.0235922451385733e-05,
      "loss": 35.5557,
      "step": 92
    },
    {
      "epoch": 0.22996677227416737,
      "grad_norm": 25.34788703918457,
      "learning_rate": 1.0104905386425733e-05,
      "loss": 37.8843,
      "step": 93
    },
    {
      "epoch": 0.2324395332663627,
      "grad_norm": 46.66182327270508,
      "learning_rate": 1.002623399352217e-05,
      "loss": 34.0918,
      "step": 94
    },
    {
      "epoch": 0.23491229425855806,
      "grad_norm": 50.13078689575195,
      "learning_rate": 1e-05,
      "loss": 36.2002,
      "step": 95
    }
  ],
  "logging_steps": 1,
  "max_steps": 95,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.0750240542739661e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}