{
  "best_metric": 6.8727312088012695,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.10752688172043011,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002150537634408602,
      "grad_norm": 0.7187415361404419,
      "learning_rate": 0.0001,
      "loss": 6.9324,
      "step": 1
    },
    {
      "epoch": 0.002150537634408602,
      "eval_loss": 6.925315856933594,
      "eval_runtime": 0.9232,
      "eval_samples_per_second": 848.099,
      "eval_steps_per_second": 106.148,
      "step": 1
    },
    {
      "epoch": 0.004301075268817204,
      "grad_norm": 0.5852924585342407,
      "learning_rate": 0.0002,
      "loss": 6.9212,
      "step": 2
    },
    {
      "epoch": 0.0064516129032258064,
      "grad_norm": 0.46351271867752075,
      "learning_rate": 0.00019978589232386035,
      "loss": 6.9259,
      "step": 3
    },
    {
      "epoch": 0.008602150537634409,
      "grad_norm": 0.42912644147872925,
      "learning_rate": 0.00019914448613738106,
      "loss": 6.9299,
      "step": 4
    },
    {
      "epoch": 0.010752688172043012,
      "grad_norm": 0.4773295819759369,
      "learning_rate": 0.00019807852804032305,
      "loss": 6.925,
      "step": 5
    },
    {
      "epoch": 0.012903225806451613,
      "grad_norm": 0.33238333463668823,
      "learning_rate": 0.00019659258262890683,
      "loss": 6.9294,
      "step": 6
    },
    {
      "epoch": 0.015053763440860216,
      "grad_norm": 0.34401118755340576,
      "learning_rate": 0.0001946930129495106,
      "loss": 6.9161,
      "step": 7
    },
    {
      "epoch": 0.017204301075268817,
      "grad_norm": 0.4122662842273712,
      "learning_rate": 0.0001923879532511287,
      "loss": 6.9158,
      "step": 8
    },
    {
      "epoch": 0.01935483870967742,
      "grad_norm": 0.3456857204437256,
      "learning_rate": 0.00018968727415326884,
      "loss": 6.9132,
      "step": 9
    },
    {
      "epoch": 0.021505376344086023,
      "grad_norm": 0.31681370735168457,
      "learning_rate": 0.00018660254037844388,
      "loss": 6.9168,
      "step": 10
    },
    {
      "epoch": 0.023655913978494623,
      "grad_norm": 0.3703623414039612,
      "learning_rate": 0.00018314696123025454,
      "loss": 6.9129,
      "step": 11
    },
    {
      "epoch": 0.025806451612903226,
      "grad_norm": 0.34536635875701904,
      "learning_rate": 0.00017933533402912354,
      "loss": 6.9048,
      "step": 12
    },
    {
      "epoch": 0.02795698924731183,
      "grad_norm": 0.38983359932899475,
      "learning_rate": 0.00017518398074789775,
      "loss": 6.8984,
      "step": 13
    },
    {
      "epoch": 0.030107526881720432,
      "grad_norm": 0.6622103452682495,
      "learning_rate": 0.00017071067811865476,
      "loss": 6.8893,
      "step": 14
    },
    {
      "epoch": 0.03225806451612903,
      "grad_norm": 0.5960562229156494,
      "learning_rate": 0.00016593458151000688,
      "loss": 6.8951,
      "step": 15
    },
    {
      "epoch": 0.034408602150537634,
      "grad_norm": 0.3657277822494507,
      "learning_rate": 0.00016087614290087208,
      "loss": 6.9074,
      "step": 16
    },
    {
      "epoch": 0.03655913978494624,
      "grad_norm": 0.47530630230903625,
      "learning_rate": 0.00015555702330196023,
      "loss": 6.9009,
      "step": 17
    },
    {
      "epoch": 0.03870967741935484,
      "grad_norm": 0.3645869493484497,
      "learning_rate": 0.00015000000000000001,
      "loss": 6.8928,
      "step": 18
    },
    {
      "epoch": 0.04086021505376344,
      "grad_norm": 0.34106141328811646,
      "learning_rate": 0.00014422886902190014,
      "loss": 6.9025,
      "step": 19
    },
    {
      "epoch": 0.043010752688172046,
      "grad_norm": 0.3415951728820801,
      "learning_rate": 0.000138268343236509,
      "loss": 6.904,
      "step": 20
    },
    {
      "epoch": 0.04516129032258064,
      "grad_norm": 0.3897996246814728,
      "learning_rate": 0.00013214394653031616,
      "loss": 6.8908,
      "step": 21
    },
    {
      "epoch": 0.047311827956989246,
      "grad_norm": 0.410493403673172,
      "learning_rate": 0.00012588190451025207,
      "loss": 6.8993,
      "step": 22
    },
    {
      "epoch": 0.04946236559139785,
      "grad_norm": 0.31212905049324036,
      "learning_rate": 0.00011950903220161285,
      "loss": 6.9013,
      "step": 23
    },
    {
      "epoch": 0.05161290322580645,
      "grad_norm": 0.32377174496650696,
      "learning_rate": 0.00011305261922200519,
      "loss": 6.8955,
      "step": 24
    },
    {
      "epoch": 0.053763440860215055,
      "grad_norm": 0.43582895398139954,
      "learning_rate": 0.00010654031292301432,
      "loss": 6.903,
      "step": 25
    },
    {
      "epoch": 0.053763440860215055,
      "eval_loss": 6.884809970855713,
      "eval_runtime": 0.9249,
      "eval_samples_per_second": 846.615,
      "eval_steps_per_second": 105.962,
      "step": 25
    },
    {
      "epoch": 0.05591397849462366,
      "grad_norm": 0.5507829189300537,
      "learning_rate": 0.0001,
      "loss": 6.8577,
      "step": 26
    },
    {
      "epoch": 0.05806451612903226,
      "grad_norm": 0.7507437467575073,
      "learning_rate": 9.345968707698569e-05,
      "loss": 6.8641,
      "step": 27
    },
    {
      "epoch": 0.060215053763440864,
      "grad_norm": 0.48704901337623596,
      "learning_rate": 8.694738077799488e-05,
      "loss": 6.8725,
      "step": 28
    },
    {
      "epoch": 0.06236559139784946,
      "grad_norm": 0.4629966914653778,
      "learning_rate": 8.049096779838719e-05,
      "loss": 6.8839,
      "step": 29
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 0.40799272060394287,
      "learning_rate": 7.411809548974792e-05,
      "loss": 6.8805,
      "step": 30
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 0.3880249559879303,
      "learning_rate": 6.785605346968386e-05,
      "loss": 6.8746,
      "step": 31
    },
    {
      "epoch": 0.06881720430107527,
      "grad_norm": 0.41283485293388367,
      "learning_rate": 6.173165676349103e-05,
      "loss": 6.8814,
      "step": 32
    },
    {
      "epoch": 0.07096774193548387,
      "grad_norm": 0.40532612800598145,
      "learning_rate": 5.577113097809989e-05,
      "loss": 6.8813,
      "step": 33
    },
    {
      "epoch": 0.07311827956989247,
      "grad_norm": 0.3707815706729889,
      "learning_rate": 5.000000000000002e-05,
      "loss": 6.8839,
      "step": 34
    },
    {
      "epoch": 0.07526881720430108,
      "grad_norm": 0.3721561133861542,
      "learning_rate": 4.444297669803981e-05,
      "loss": 6.8814,
      "step": 35
    },
    {
      "epoch": 0.07741935483870968,
      "grad_norm": 0.3550940752029419,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 6.885,
      "step": 36
    },
    {
      "epoch": 0.07956989247311828,
      "grad_norm": 0.3907034993171692,
      "learning_rate": 3.406541848999312e-05,
      "loss": 6.8828,
      "step": 37
    },
    {
      "epoch": 0.08172043010752689,
      "grad_norm": 0.42349421977996826,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 6.8592,
      "step": 38
    },
    {
      "epoch": 0.08387096774193549,
      "grad_norm": 0.5302990674972534,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 6.8493,
      "step": 39
    },
    {
      "epoch": 0.08602150537634409,
      "grad_norm": 0.4581059217453003,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 6.8631,
      "step": 40
    },
    {
      "epoch": 0.08817204301075268,
      "grad_norm": 0.39196085929870605,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 6.8809,
      "step": 41
    },
    {
      "epoch": 0.09032258064516129,
      "grad_norm": 0.4368338882923126,
      "learning_rate": 1.339745962155613e-05,
      "loss": 6.877,
      "step": 42
    },
    {
      "epoch": 0.09247311827956989,
      "grad_norm": 0.4000701606273651,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 6.8684,
      "step": 43
    },
    {
      "epoch": 0.09462365591397849,
      "grad_norm": 0.40346625447273254,
      "learning_rate": 7.612046748871327e-06,
      "loss": 6.8676,
      "step": 44
    },
    {
      "epoch": 0.0967741935483871,
      "grad_norm": 0.3889538645744324,
      "learning_rate": 5.306987050489442e-06,
      "loss": 6.8741,
      "step": 45
    },
    {
      "epoch": 0.0989247311827957,
      "grad_norm": 0.35344064235687256,
      "learning_rate": 3.40741737109318e-06,
      "loss": 6.8848,
      "step": 46
    },
    {
      "epoch": 0.1010752688172043,
      "grad_norm": 0.3989741802215576,
      "learning_rate": 1.921471959676957e-06,
      "loss": 6.8769,
      "step": 47
    },
    {
      "epoch": 0.1032258064516129,
      "grad_norm": 0.33190953731536865,
      "learning_rate": 8.555138626189618e-07,
      "loss": 6.88,
      "step": 48
    },
    {
      "epoch": 0.1053763440860215,
      "grad_norm": 0.3976621627807617,
      "learning_rate": 2.141076761396521e-07,
      "loss": 6.883,
      "step": 49
    },
    {
      "epoch": 0.10752688172043011,
      "grad_norm": 0.44902920722961426,
      "learning_rate": 0.0,
      "loss": 6.8747,
      "step": 50
    },
    {
      "epoch": 0.10752688172043011,
      "eval_loss": 6.8727312088012695,
      "eval_runtime": 0.9232,
      "eval_samples_per_second": 848.142,
      "eval_steps_per_second": 106.153,
      "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": 2357211955200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}