{
  "best_metric": 10.354788780212402,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0011751433674908338,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.7005734699633354e-05,
      "grad_norm": 0.0749775841832161,
      "learning_rate": 0.0001,
      "loss": 10.3598,
      "step": 1
    },
    {
      "epoch": 4.7005734699633354e-05,
      "eval_loss": 10.364864349365234,
      "eval_runtime": 89.7799,
      "eval_samples_per_second": 99.777,
      "eval_steps_per_second": 49.889,
      "step": 1
    },
    {
      "epoch": 9.401146939926671e-05,
      "grad_norm": 0.07384652644395828,
      "learning_rate": 0.0002,
      "loss": 10.3608,
      "step": 2
    },
    {
      "epoch": 0.00014101720409890006,
      "grad_norm": 0.06634382903575897,
      "learning_rate": 0.00019978589232386035,
      "loss": 10.3596,
      "step": 3
    },
    {
      "epoch": 0.00018802293879853342,
      "grad_norm": 0.0664483979344368,
      "learning_rate": 0.00019914448613738106,
      "loss": 10.3572,
      "step": 4
    },
    {
      "epoch": 0.00023502867349816677,
      "grad_norm": 0.06566525250673294,
      "learning_rate": 0.00019807852804032305,
      "loss": 10.3572,
      "step": 5
    },
    {
      "epoch": 0.0002820344081978001,
      "grad_norm": 0.07329878211021423,
      "learning_rate": 0.00019659258262890683,
      "loss": 10.3577,
      "step": 6
    },
    {
      "epoch": 0.0003290401428974335,
      "grad_norm": 0.06763594597578049,
      "learning_rate": 0.0001946930129495106,
      "loss": 10.3599,
      "step": 7
    },
    {
      "epoch": 0.00037604587759706683,
      "grad_norm": 0.07483668625354767,
      "learning_rate": 0.0001923879532511287,
      "loss": 10.3616,
      "step": 8
    },
    {
      "epoch": 0.0004230516122967002,
      "grad_norm": 0.07877986133098602,
      "learning_rate": 0.00018968727415326884,
      "loss": 10.3555,
      "step": 9
    },
    {
      "epoch": 0.00047005734699633354,
      "grad_norm": 0.07481114566326141,
      "learning_rate": 0.00018660254037844388,
      "loss": 10.355,
      "step": 10
    },
    {
      "epoch": 0.000517063081695967,
      "grad_norm": 0.07228323817253113,
      "learning_rate": 0.00018314696123025454,
      "loss": 10.3554,
      "step": 11
    },
    {
      "epoch": 0.0005640688163956002,
      "grad_norm": 0.07729602605104446,
      "learning_rate": 0.00017933533402912354,
      "loss": 10.3498,
      "step": 12
    },
    {
      "epoch": 0.0006110745510952337,
      "grad_norm": 0.08047541975975037,
      "learning_rate": 0.00017518398074789775,
      "loss": 10.3607,
      "step": 13
    },
    {
      "epoch": 0.000658080285794867,
      "grad_norm": 0.08818409591913223,
      "learning_rate": 0.00017071067811865476,
      "loss": 10.3619,
      "step": 14
    },
    {
      "epoch": 0.0007050860204945004,
      "grad_norm": 0.08615565299987793,
      "learning_rate": 0.00016593458151000688,
      "loss": 10.3581,
      "step": 15
    },
    {
      "epoch": 0.0007520917551941337,
      "grad_norm": 0.0926477387547493,
      "learning_rate": 0.00016087614290087208,
      "loss": 10.354,
      "step": 16
    },
    {
      "epoch": 0.0007990974898937671,
      "grad_norm": 0.09321993589401245,
      "learning_rate": 0.00015555702330196023,
      "loss": 10.3572,
      "step": 17
    },
    {
      "epoch": 0.0008461032245934004,
      "grad_norm": 0.09032484143972397,
      "learning_rate": 0.00015000000000000001,
      "loss": 10.3594,
      "step": 18
    },
    {
      "epoch": 0.0008931089592930338,
      "grad_norm": 0.07716833800077438,
      "learning_rate": 0.00014422886902190014,
      "loss": 10.3532,
      "step": 19
    },
    {
      "epoch": 0.0009401146939926671,
      "grad_norm": 0.1036844253540039,
      "learning_rate": 0.000138268343236509,
      "loss": 10.3561,
      "step": 20
    },
    {
      "epoch": 0.0009871204286923004,
      "grad_norm": 0.08591034263372421,
      "learning_rate": 0.00013214394653031616,
      "loss": 10.3554,
      "step": 21
    },
    {
      "epoch": 0.001034126163391934,
      "grad_norm": 0.09223807603120804,
      "learning_rate": 0.00012588190451025207,
      "loss": 10.3524,
      "step": 22
    },
    {
      "epoch": 0.0010811318980915672,
      "grad_norm": 0.09289194643497467,
      "learning_rate": 0.00011950903220161285,
      "loss": 10.3576,
      "step": 23
    },
    {
      "epoch": 0.0011281376327912005,
      "grad_norm": 0.10053667426109314,
      "learning_rate": 0.00011305261922200519,
      "loss": 10.3523,
      "step": 24
    },
    {
      "epoch": 0.0011751433674908338,
      "grad_norm": 0.0925389751791954,
      "learning_rate": 0.00010654031292301432,
      "loss": 10.3616,
      "step": 25
    },
    {
      "epoch": 0.0011751433674908338,
      "eval_loss": 10.354788780212402,
      "eval_runtime": 89.8027,
      "eval_samples_per_second": 99.752,
      "eval_steps_per_second": 49.876,
      "step": 25
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2615122329600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}