{
  "best_metric": 11.930197715759277,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.9913258983890955,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01982651796778191,
      "grad_norm": 0.011147715151309967,
      "learning_rate": 5e-05,
      "loss": 11.9331,
      "step": 1
    },
    {
      "epoch": 0.01982651796778191,
      "eval_loss": 11.932327270507812,
      "eval_runtime": 1.3407,
      "eval_samples_per_second": 253.603,
      "eval_steps_per_second": 32.073,
      "step": 1
    },
    {
      "epoch": 0.03965303593556382,
      "grad_norm": 0.01382710412144661,
      "learning_rate": 0.0001,
      "loss": 11.9336,
      "step": 2
    },
    {
      "epoch": 0.05947955390334572,
      "grad_norm": 0.015198501758277416,
      "learning_rate": 9.989294616193017e-05,
      "loss": 11.9329,
      "step": 3
    },
    {
      "epoch": 0.07930607187112763,
      "grad_norm": 0.013364885002374649,
      "learning_rate": 9.957224306869053e-05,
      "loss": 11.9324,
      "step": 4
    },
    {
      "epoch": 0.09913258983890955,
      "grad_norm": 0.016064196825027466,
      "learning_rate": 9.903926402016153e-05,
      "loss": 11.9334,
      "step": 5
    },
    {
      "epoch": 0.11895910780669144,
      "grad_norm": 0.019382789731025696,
      "learning_rate": 9.829629131445342e-05,
      "loss": 11.932,
      "step": 6
    },
    {
      "epoch": 0.13878562577447337,
      "grad_norm": 0.017111532390117645,
      "learning_rate": 9.73465064747553e-05,
      "loss": 11.9334,
      "step": 7
    },
    {
      "epoch": 0.15861214374225527,
      "grad_norm": 0.02031642384827137,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9313,
      "step": 8
    },
    {
      "epoch": 0.17843866171003717,
      "grad_norm": 0.025809045881032944,
      "learning_rate": 9.484363707663442e-05,
      "loss": 11.9307,
      "step": 9
    },
    {
      "epoch": 0.1982651796778191,
      "grad_norm": 0.02880113758146763,
      "learning_rate": 9.330127018922194e-05,
      "loss": 11.9303,
      "step": 10
    },
    {
      "epoch": 0.218091697645601,
      "grad_norm": 0.026642320677638054,
      "learning_rate": 9.157348061512727e-05,
      "loss": 11.9304,
      "step": 11
    },
    {
      "epoch": 0.2379182156133829,
      "grad_norm": 0.031131992116570473,
      "learning_rate": 8.966766701456177e-05,
      "loss": 11.9295,
      "step": 12
    },
    {
      "epoch": 0.2577447335811648,
      "grad_norm": 0.014886637218296528,
      "learning_rate": 8.759199037394887e-05,
      "loss": 11.9325,
      "step": 13
    },
    {
      "epoch": 0.27757125154894674,
      "grad_norm": 0.01976705901324749,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9331,
      "step": 14
    },
    {
      "epoch": 0.29739776951672864,
      "grad_norm": 0.018739132210612297,
      "learning_rate": 8.296729075500344e-05,
      "loss": 11.9332,
      "step": 15
    },
    {
      "epoch": 0.31722428748451054,
      "grad_norm": 0.024744203314185143,
      "learning_rate": 8.043807145043604e-05,
      "loss": 11.932,
      "step": 16
    },
    {
      "epoch": 0.33705080545229243,
      "grad_norm": 0.02045373059809208,
      "learning_rate": 7.777851165098012e-05,
      "loss": 11.9315,
      "step": 17
    },
    {
      "epoch": 0.35687732342007433,
      "grad_norm": 0.024953598156571388,
      "learning_rate": 7.500000000000001e-05,
      "loss": 11.9319,
      "step": 18
    },
    {
      "epoch": 0.37670384138785623,
      "grad_norm": 0.028660297393798828,
      "learning_rate": 7.211443451095007e-05,
      "loss": 11.9318,
      "step": 19
    },
    {
      "epoch": 0.3965303593556382,
      "grad_norm": 0.02539646625518799,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.9308,
      "step": 20
    },
    {
      "epoch": 0.4163568773234201,
      "grad_norm": 0.0284788366407156,
      "learning_rate": 6.607197326515808e-05,
      "loss": 11.9301,
      "step": 21
    },
    {
      "epoch": 0.436183395291202,
      "grad_norm": 0.03549646958708763,
      "learning_rate": 6.294095225512603e-05,
      "loss": 11.9306,
      "step": 22
    },
    {
      "epoch": 0.4560099132589839,
      "grad_norm": 0.03313276916742325,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 11.9303,
      "step": 23
    },
    {
      "epoch": 0.4758364312267658,
      "grad_norm": 0.04793617129325867,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 11.9294,
      "step": 24
    },
    {
      "epoch": 0.49566294919454773,
      "grad_norm": 0.04718635603785515,
      "learning_rate": 5.327015646150716e-05,
      "loss": 11.9262,
      "step": 25
    },
    {
      "epoch": 0.49566294919454773,
      "eval_loss": 11.930814743041992,
      "eval_runtime": 1.3988,
      "eval_samples_per_second": 243.069,
      "eval_steps_per_second": 30.741,
      "step": 25
    },
    {
      "epoch": 0.5154894671623296,
      "grad_norm": 0.023722823709249496,
      "learning_rate": 5e-05,
      "loss": 11.9321,
      "step": 26
    },
    {
      "epoch": 0.5353159851301115,
      "grad_norm": 0.029193179681897163,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 11.9326,
      "step": 27
    },
    {
      "epoch": 0.5551425030978935,
      "grad_norm": 0.029724499210715294,
      "learning_rate": 4.347369038899744e-05,
      "loss": 11.9332,
      "step": 28
    },
    {
      "epoch": 0.5749690210656754,
      "grad_norm": 0.03591114282608032,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 11.9309,
      "step": 29
    },
    {
      "epoch": 0.5947955390334573,
      "grad_norm": 0.03057137131690979,
      "learning_rate": 3.705904774487396e-05,
      "loss": 11.9321,
      "step": 30
    },
    {
      "epoch": 0.6146220570012392,
      "grad_norm": 0.032220229506492615,
      "learning_rate": 3.392802673484193e-05,
      "loss": 11.9313,
      "step": 31
    },
    {
      "epoch": 0.6344485749690211,
      "grad_norm": 0.032921236008405685,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.9307,
      "step": 32
    },
    {
      "epoch": 0.654275092936803,
      "grad_norm": 0.04445214569568634,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 11.9299,
      "step": 33
    },
    {
      "epoch": 0.6741016109045849,
      "grad_norm": 0.03545578941702843,
      "learning_rate": 2.500000000000001e-05,
      "loss": 11.93,
      "step": 34
    },
    {
      "epoch": 0.6939281288723668,
      "grad_norm": 0.03545760363340378,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 11.9299,
      "step": 35
    },
    {
      "epoch": 0.7137546468401487,
      "grad_norm": 0.04920024797320366,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 11.9295,
      "step": 36
    },
    {
      "epoch": 0.7335811648079306,
      "grad_norm": 0.06207504868507385,
      "learning_rate": 1.703270924499656e-05,
      "loss": 11.9269,
      "step": 37
    },
    {
      "epoch": 0.7534076827757125,
      "grad_norm": 0.03247861936688423,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 11.9312,
      "step": 38
    },
    {
      "epoch": 0.7732342007434945,
      "grad_norm": 0.03084028698503971,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 11.9317,
      "step": 39
    },
    {
      "epoch": 0.7930607187112764,
      "grad_norm": 0.03489547595381737,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 11.9312,
      "step": 40
    },
    {
      "epoch": 0.8128872366790583,
      "grad_norm": 0.03439491242170334,
      "learning_rate": 8.426519384872733e-06,
      "loss": 11.932,
      "step": 41
    },
    {
      "epoch": 0.8327137546468402,
      "grad_norm": 0.04392773285508156,
      "learning_rate": 6.698729810778065e-06,
      "loss": 11.9317,
      "step": 42
    },
    {
      "epoch": 0.8525402726146221,
      "grad_norm": 0.037023965269327164,
      "learning_rate": 5.156362923365588e-06,
      "loss": 11.9313,
      "step": 43
    },
    {
      "epoch": 0.872366790582404,
      "grad_norm": 0.04017459973692894,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 11.9304,
      "step": 44
    },
    {
      "epoch": 0.8921933085501859,
      "grad_norm": 0.034759581089019775,
      "learning_rate": 2.653493525244721e-06,
      "loss": 11.9293,
      "step": 45
    },
    {
      "epoch": 0.9120198265179678,
      "grad_norm": 0.03923869878053665,
      "learning_rate": 1.70370868554659e-06,
      "loss": 11.9295,
      "step": 46
    },
    {
      "epoch": 0.9318463444857497,
      "grad_norm": 0.04526235908269882,
      "learning_rate": 9.607359798384785e-07,
      "loss": 11.9299,
      "step": 47
    },
    {
      "epoch": 0.9516728624535316,
      "grad_norm": 0.04564972221851349,
      "learning_rate": 4.277569313094809e-07,
      "loss": 11.9289,
      "step": 48
    },
    {
      "epoch": 0.9714993804213135,
      "grad_norm": 0.047993697226047516,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 11.9268,
      "step": 49
    },
    {
      "epoch": 0.9913258983890955,
      "grad_norm": 0.04707922041416168,
      "learning_rate": 0.0,
      "loss": 11.9271,
      "step": 50
    },
    {
      "epoch": 0.9913258983890955,
      "eval_loss": 11.930197715759277,
      "eval_runtime": 1.3493,
      "eval_samples_per_second": 251.982,
      "eval_steps_per_second": 31.868,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": 1042494259200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}