{
  "best_metric": 4.195949554443359,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.34873583260680036,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013949433304272014,
      "grad_norm": 7.106900215148926,
      "learning_rate": 5e-05,
      "loss": 5.874,
      "step": 1
    },
    {
      "epoch": 0.013949433304272014,
      "eval_loss": 9.32523250579834,
      "eval_runtime": 1.227,
      "eval_samples_per_second": 40.751,
      "eval_steps_per_second": 10.595,
      "step": 1
    },
    {
      "epoch": 0.02789886660854403,
      "grad_norm": 9.483339309692383,
      "learning_rate": 0.0001,
      "loss": 6.576,
      "step": 2
    },
    {
      "epoch": 0.041848299912816043,
      "grad_norm": 7.642940998077393,
      "learning_rate": 9.990365154573717e-05,
      "loss": 6.3436,
      "step": 3
    },
    {
      "epoch": 0.05579773321708806,
      "grad_norm": 3.3282408714294434,
      "learning_rate": 9.961501876182148e-05,
      "loss": 5.8063,
      "step": 4
    },
    {
      "epoch": 0.06974716652136007,
      "grad_norm": 3.352458953857422,
      "learning_rate": 9.913533761814537e-05,
      "loss": 5.5666,
      "step": 5
    },
    {
      "epoch": 0.08369659982563209,
      "grad_norm": 4.008856773376465,
      "learning_rate": 9.846666218300807e-05,
      "loss": 5.354,
      "step": 6
    },
    {
      "epoch": 0.0976460331299041,
      "grad_norm": 4.195788383483887,
      "learning_rate": 9.761185582727977e-05,
      "loss": 5.1062,
      "step": 7
    },
    {
      "epoch": 0.11159546643417612,
      "grad_norm": 3.3430533409118652,
      "learning_rate": 9.657457896300791e-05,
      "loss": 5.0175,
      "step": 8
    },
    {
      "epoch": 0.12554489973844812,
      "grad_norm": 4.7011260986328125,
      "learning_rate": 9.535927336897098e-05,
      "loss": 4.8241,
      "step": 9
    },
    {
      "epoch": 0.13949433304272013,
      "grad_norm": 3.9869306087493896,
      "learning_rate": 9.397114317029975e-05,
      "loss": 4.518,
      "step": 10
    },
    {
      "epoch": 0.15344376634699217,
      "grad_norm": 3.9573750495910645,
      "learning_rate": 9.241613255361455e-05,
      "loss": 4.5197,
      "step": 11
    },
    {
      "epoch": 0.16739319965126417,
      "grad_norm": 5.384781360626221,
      "learning_rate": 9.070090031310558e-05,
      "loss": 3.7971,
      "step": 12
    },
    {
      "epoch": 0.18134263295553618,
      "grad_norm": 5.28661584854126,
      "learning_rate": 8.883279133655399e-05,
      "loss": 4.5532,
      "step": 13
    },
    {
      "epoch": 0.1952920662598082,
      "grad_norm": 5.131237030029297,
      "learning_rate": 8.681980515339464e-05,
      "loss": 4.6504,
      "step": 14
    },
    {
      "epoch": 0.2092414995640802,
      "grad_norm": 3.915031909942627,
      "learning_rate": 8.467056167950311e-05,
      "loss": 4.6089,
      "step": 15
    },
    {
      "epoch": 0.22319093286835223,
      "grad_norm": 2.7362663745880127,
      "learning_rate": 8.239426430539243e-05,
      "loss": 4.4754,
      "step": 16
    },
    {
      "epoch": 0.23714036617262424,
      "grad_norm": 1.646876573562622,
      "learning_rate": 8.000066048588211e-05,
      "loss": 4.3783,
      "step": 17
    },
    {
      "epoch": 0.25108979947689625,
      "grad_norm": 1.9029401540756226,
      "learning_rate": 7.75e-05,
      "loss": 4.4637,
      "step": 18
    },
    {
      "epoch": 0.26503923278116825,
      "grad_norm": 2.314201593399048,
      "learning_rate": 7.490299105985507e-05,
      "loss": 4.3935,
      "step": 19
    },
    {
      "epoch": 0.27898866608544026,
      "grad_norm": 2.7802789211273193,
      "learning_rate": 7.222075445642904e-05,
      "loss": 4.4136,
      "step": 20
    },
    {
      "epoch": 0.29293809938971227,
      "grad_norm": 2.629115581512451,
      "learning_rate": 6.946477593864228e-05,
      "loss": 4.4096,
      "step": 21
    },
    {
      "epoch": 0.30688753269398433,
      "grad_norm": 2.255183219909668,
      "learning_rate": 6.664685702961344e-05,
      "loss": 4.3375,
      "step": 22
    },
    {
      "epoch": 0.32083696599825634,
      "grad_norm": 2.447622776031494,
      "learning_rate": 6.377906449072578e-05,
      "loss": 4.0912,
      "step": 23
    },
    {
      "epoch": 0.33478639930252835,
      "grad_norm": 2.6348073482513428,
      "learning_rate": 6.087367864990233e-05,
      "loss": 3.8303,
      "step": 24
    },
    {
      "epoch": 0.34873583260680036,
      "grad_norm": 3.514143466949463,
      "learning_rate": 5.794314081535644e-05,
      "loss": 3.6484,
      "step": 25
    },
    {
      "epoch": 0.34873583260680036,
      "eval_loss": 4.195949554443359,
      "eval_runtime": 1.2663,
      "eval_samples_per_second": 39.485,
      "eval_steps_per_second": 10.266,
      "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": 8.1240447254528e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}