{
  "best_metric": 11.8941650390625,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0435516359083238,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008710327181664761,
      "grad_norm": 0.14870582520961761,
      "learning_rate": 5e-05,
      "loss": 11.9338,
      "step": 1
    },
    {
      "epoch": 0.0008710327181664761,
      "eval_loss": 11.937056541442871,
      "eval_runtime": 0.9171,
      "eval_samples_per_second": 54.52,
      "eval_steps_per_second": 14.175,
      "step": 1
    },
    {
      "epoch": 0.0017420654363329523,
      "grad_norm": 0.17123878002166748,
      "learning_rate": 0.0001,
      "loss": 11.9349,
      "step": 2
    },
    {
      "epoch": 0.0026130981544994283,
      "grad_norm": 0.15057794749736786,
      "learning_rate": 9.990365154573717e-05,
      "loss": 11.9333,
      "step": 3
    },
    {
      "epoch": 0.0034841308726659046,
      "grad_norm": 0.17761482298374176,
      "learning_rate": 9.961501876182148e-05,
      "loss": 11.933,
      "step": 4
    },
    {
      "epoch": 0.004355163590832381,
      "grad_norm": 0.14865589141845703,
      "learning_rate": 9.913533761814537e-05,
      "loss": 11.9333,
      "step": 5
    },
    {
      "epoch": 0.005226196308998857,
      "grad_norm": 0.19009239971637726,
      "learning_rate": 9.846666218300807e-05,
      "loss": 11.9303,
      "step": 6
    },
    {
      "epoch": 0.0060972290271653325,
      "grad_norm": 0.16483457386493683,
      "learning_rate": 9.761185582727977e-05,
      "loss": 11.9335,
      "step": 7
    },
    {
      "epoch": 0.006968261745331809,
      "grad_norm": 0.19065271317958832,
      "learning_rate": 9.657457896300791e-05,
      "loss": 11.9288,
      "step": 8
    },
    {
      "epoch": 0.007839294463498285,
      "grad_norm": 0.2016676813364029,
      "learning_rate": 9.535927336897098e-05,
      "loss": 11.9268,
      "step": 9
    },
    {
      "epoch": 0.008710327181664762,
      "grad_norm": 0.2314668893814087,
      "learning_rate": 9.397114317029975e-05,
      "loss": 11.9269,
      "step": 10
    },
    {
      "epoch": 0.009581359899831237,
      "grad_norm": 0.24742108583450317,
      "learning_rate": 9.241613255361455e-05,
      "loss": 11.9237,
      "step": 11
    },
    {
      "epoch": 0.010452392617997713,
      "grad_norm": 0.23251473903656006,
      "learning_rate": 9.070090031310558e-05,
      "loss": 11.9249,
      "step": 12
    },
    {
      "epoch": 0.01132342533616419,
      "grad_norm": 0.2271156907081604,
      "learning_rate": 8.883279133655399e-05,
      "loss": 11.9214,
      "step": 13
    },
    {
      "epoch": 0.012194458054330665,
      "grad_norm": 0.25586220622062683,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.9205,
      "step": 14
    },
    {
      "epoch": 0.013065490772497142,
      "grad_norm": 0.23470079898834229,
      "learning_rate": 8.467056167950311e-05,
      "loss": 11.9209,
      "step": 15
    },
    {
      "epoch": 0.013936523490663618,
      "grad_norm": 0.2868376076221466,
      "learning_rate": 8.239426430539243e-05,
      "loss": 11.9152,
      "step": 16
    },
    {
      "epoch": 0.014807556208830093,
      "grad_norm": 0.28257161378860474,
      "learning_rate": 8.000066048588211e-05,
      "loss": 11.9185,
      "step": 17
    },
    {
      "epoch": 0.01567858892699657,
      "grad_norm": 0.2799442410469055,
      "learning_rate": 7.75e-05,
      "loss": 11.9177,
      "step": 18
    },
    {
      "epoch": 0.016549621645163045,
      "grad_norm": 0.301929771900177,
      "learning_rate": 7.490299105985507e-05,
      "loss": 11.9148,
      "step": 19
    },
    {
      "epoch": 0.017420654363329523,
      "grad_norm": 0.2986518144607544,
      "learning_rate": 7.222075445642904e-05,
      "loss": 11.9137,
      "step": 20
    },
    {
      "epoch": 0.018291687081496,
      "grad_norm": 0.33487677574157715,
      "learning_rate": 6.946477593864228e-05,
      "loss": 11.9113,
      "step": 21
    },
    {
      "epoch": 0.019162719799662473,
      "grad_norm": 0.339459091424942,
      "learning_rate": 6.664685702961344e-05,
      "loss": 11.9104,
      "step": 22
    },
    {
      "epoch": 0.020033752517828952,
      "grad_norm": 0.36398395895957947,
      "learning_rate": 6.377906449072578e-05,
      "loss": 11.9104,
      "step": 23
    },
    {
      "epoch": 0.020904785235995427,
      "grad_norm": 0.3283174932003021,
      "learning_rate": 6.087367864990233e-05,
      "loss": 11.9056,
      "step": 24
    },
    {
      "epoch": 0.0217758179541619,
      "grad_norm": 0.3487694263458252,
      "learning_rate": 5.794314081535644e-05,
      "loss": 11.9057,
      "step": 25
    },
    {
      "epoch": 0.0217758179541619,
      "eval_loss": 11.909122467041016,
      "eval_runtime": 0.4072,
      "eval_samples_per_second": 122.78,
      "eval_steps_per_second": 31.923,
      "step": 25
    },
    {
      "epoch": 0.02264685067232838,
      "grad_norm": 0.3583414852619171,
      "learning_rate": 5.500000000000001e-05,
      "loss": 11.9017,
      "step": 26
    },
    {
      "epoch": 0.023517883390494855,
      "grad_norm": 0.3218832314014435,
      "learning_rate": 5.205685918464356e-05,
      "loss": 11.903,
      "step": 27
    },
    {
      "epoch": 0.02438891610866133,
      "grad_norm": 0.33500561118125916,
      "learning_rate": 4.912632135009769e-05,
      "loss": 11.9,
      "step": 28
    },
    {
      "epoch": 0.02525994882682781,
      "grad_norm": 0.3144049048423767,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 11.904,
      "step": 29
    },
    {
      "epoch": 0.026130981544994283,
      "grad_norm": 0.33048567175865173,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 11.9027,
      "step": 30
    },
    {
      "epoch": 0.02700201426316076,
      "grad_norm": 0.3038746118545532,
      "learning_rate": 4.053522406135775e-05,
      "loss": 11.8999,
      "step": 31
    },
    {
      "epoch": 0.027873046981327237,
      "grad_norm": 0.2892683744430542,
      "learning_rate": 3.777924554357096e-05,
      "loss": 11.9014,
      "step": 32
    },
    {
      "epoch": 0.02874407969949371,
      "grad_norm": 0.32294026017189026,
      "learning_rate": 3.509700894014496e-05,
      "loss": 11.8961,
      "step": 33
    },
    {
      "epoch": 0.029615112417660187,
      "grad_norm": 0.3208608627319336,
      "learning_rate": 3.250000000000001e-05,
      "loss": 11.8962,
      "step": 34
    },
    {
      "epoch": 0.030486145135826665,
      "grad_norm": 0.2977166175842285,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 11.896,
      "step": 35
    },
    {
      "epoch": 0.03135717785399314,
      "grad_norm": 0.305480033159256,
      "learning_rate": 2.760573569460757e-05,
      "loss": 11.8966,
      "step": 36
    },
    {
      "epoch": 0.03222821057215962,
      "grad_norm": 0.3342093527317047,
      "learning_rate": 2.53294383204969e-05,
      "loss": 11.893,
      "step": 37
    },
    {
      "epoch": 0.03309924329032609,
      "grad_norm": 0.34257322549819946,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 11.8929,
      "step": 38
    },
    {
      "epoch": 0.03397027600849257,
      "grad_norm": 0.3188397288322449,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 11.8923,
      "step": 39
    },
    {
      "epoch": 0.03484130872665905,
      "grad_norm": 0.3122134804725647,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 11.8898,
      "step": 40
    },
    {
      "epoch": 0.03571234144482552,
      "grad_norm": 0.3161143362522125,
      "learning_rate": 1.758386744638546e-05,
      "loss": 11.8928,
      "step": 41
    },
    {
      "epoch": 0.036583374162992,
      "grad_norm": 0.3282131552696228,
      "learning_rate": 1.602885682970026e-05,
      "loss": 11.8886,
      "step": 42
    },
    {
      "epoch": 0.037454406881158475,
      "grad_norm": 0.3042701780796051,
      "learning_rate": 1.464072663102903e-05,
      "loss": 11.8902,
      "step": 43
    },
    {
      "epoch": 0.03832543959932495,
      "grad_norm": 0.27346542477607727,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 11.893,
      "step": 44
    },
    {
      "epoch": 0.039196472317491425,
      "grad_norm": 0.29086118936538696,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 11.8937,
      "step": 45
    },
    {
      "epoch": 0.040067505035657904,
      "grad_norm": 0.31170573830604553,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 11.8936,
      "step": 46
    },
    {
      "epoch": 0.040938537753824375,
      "grad_norm": 0.313886433839798,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 11.8857,
      "step": 47
    },
    {
      "epoch": 0.04180957047199085,
      "grad_norm": 0.29732245206832886,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 11.888,
      "step": 48
    },
    {
      "epoch": 0.04268060319015733,
      "grad_norm": 0.30892470479011536,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 11.8872,
      "step": 49
    },
    {
      "epoch": 0.0435516359083238,
      "grad_norm": 0.3599565923213959,
      "learning_rate": 1e-05,
      "loss": 11.8921,
      "step": 50
    },
    {
      "epoch": 0.0435516359083238,
      "eval_loss": 11.8941650390625,
      "eval_runtime": 0.4156,
      "eval_samples_per_second": 120.304,
      "eval_steps_per_second": 31.279,
      "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": 419171026862080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}