{
  "best_metric": 0.7074735760688782,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.05355469272995046,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021421877091980183,
      "grad_norm": 50.62263107299805,
      "learning_rate": 5e-05,
      "loss": 135.4249,
      "step": 1
    },
    {
      "epoch": 0.0021421877091980183,
      "eval_loss": 3.7290472984313965,
      "eval_runtime": 1.894,
      "eval_samples_per_second": 26.399,
      "eval_steps_per_second": 6.864,
      "step": 1
    },
    {
      "epoch": 0.0042843754183960366,
      "grad_norm": 51.79439926147461,
      "learning_rate": 0.0001,
      "loss": 135.4853,
      "step": 2
    },
    {
      "epoch": 0.006426563127594056,
      "grad_norm": 41.13816452026367,
      "learning_rate": 9.990365154573717e-05,
      "loss": 115.4843,
      "step": 3
    },
    {
      "epoch": 0.008568750836792073,
      "grad_norm": 47.22391891479492,
      "learning_rate": 9.961501876182148e-05,
      "loss": 107.7687,
      "step": 4
    },
    {
      "epoch": 0.010710938545990093,
      "grad_norm": 53.1937255859375,
      "learning_rate": 9.913533761814537e-05,
      "loss": 99.0971,
      "step": 5
    },
    {
      "epoch": 0.012853126255188111,
      "grad_norm": 60.40630340576172,
      "learning_rate": 9.846666218300807e-05,
      "loss": 84.7703,
      "step": 6
    },
    {
      "epoch": 0.01499531396438613,
      "grad_norm": 63.6907958984375,
      "learning_rate": 9.761185582727977e-05,
      "loss": 71.1636,
      "step": 7
    },
    {
      "epoch": 0.017137501673584146,
      "grad_norm": 50.863460540771484,
      "learning_rate": 9.657457896300791e-05,
      "loss": 60.1154,
      "step": 8
    },
    {
      "epoch": 0.019279689382782166,
      "grad_norm": 44.446754455566406,
      "learning_rate": 9.535927336897098e-05,
      "loss": 51.6302,
      "step": 9
    },
    {
      "epoch": 0.021421877091980186,
      "grad_norm": 38.45900344848633,
      "learning_rate": 9.397114317029975e-05,
      "loss": 45.8112,
      "step": 10
    },
    {
      "epoch": 0.023564064801178203,
      "grad_norm": 55.98357391357422,
      "learning_rate": 9.241613255361455e-05,
      "loss": 42.1688,
      "step": 11
    },
    {
      "epoch": 0.025706252510376223,
      "grad_norm": 62.22966384887695,
      "learning_rate": 9.070090031310558e-05,
      "loss": 40.1158,
      "step": 12
    },
    {
      "epoch": 0.02784844021957424,
      "grad_norm": 43.237266540527344,
      "learning_rate": 8.883279133655399e-05,
      "loss": 49.6329,
      "step": 13
    },
    {
      "epoch": 0.02999062792877226,
      "grad_norm": 56.661930084228516,
      "learning_rate": 8.681980515339464e-05,
      "loss": 54.1158,
      "step": 14
    },
    {
      "epoch": 0.032132815637970276,
      "grad_norm": 36.406776428222656,
      "learning_rate": 8.467056167950311e-05,
      "loss": 39.4958,
      "step": 15
    },
    {
      "epoch": 0.03427500334716829,
      "grad_norm": 25.86240005493164,
      "learning_rate": 8.239426430539243e-05,
      "loss": 28.7934,
      "step": 16
    },
    {
      "epoch": 0.036417191056366316,
      "grad_norm": 20.257965087890625,
      "learning_rate": 8.000066048588211e-05,
      "loss": 26.7077,
      "step": 17
    },
    {
      "epoch": 0.03855937876556433,
      "grad_norm": 16.05629539489746,
      "learning_rate": 7.75e-05,
      "loss": 24.8365,
      "step": 18
    },
    {
      "epoch": 0.04070156647476235,
      "grad_norm": 10.645811080932617,
      "learning_rate": 7.490299105985507e-05,
      "loss": 23.427,
      "step": 19
    },
    {
      "epoch": 0.04284375418396037,
      "grad_norm": 8.209049224853516,
      "learning_rate": 7.222075445642904e-05,
      "loss": 22.857,
      "step": 20
    },
    {
      "epoch": 0.04498594189315839,
      "grad_norm": 7.825160026550293,
      "learning_rate": 6.946477593864228e-05,
      "loss": 22.7208,
      "step": 21
    },
    {
      "epoch": 0.047128129602356406,
      "grad_norm": 3.304943323135376,
      "learning_rate": 6.664685702961344e-05,
      "loss": 22.5555,
      "step": 22
    },
    {
      "epoch": 0.04927031731155442,
      "grad_norm": 3.214045286178589,
      "learning_rate": 6.377906449072578e-05,
      "loss": 22.4719,
      "step": 23
    },
    {
      "epoch": 0.051412505020752446,
      "grad_norm": 3.0567023754119873,
      "learning_rate": 6.087367864990233e-05,
      "loss": 22.5119,
      "step": 24
    },
    {
      "epoch": 0.05355469272995046,
      "grad_norm": 15.677796363830566,
      "learning_rate": 5.794314081535644e-05,
      "loss": 23.024,
      "step": 25
    },
    {
      "epoch": 0.05355469272995046,
      "eval_loss": 0.7074735760688782,
      "eval_runtime": 1.8945,
      "eval_samples_per_second": 26.393,
      "eval_steps_per_second": 6.862,
      "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": 3.039627994810286e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}