{
  "best_metric": 10.943249702453613,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.6097560975609756,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024390243902439025,
      "grad_norm": 19.364469528198242,
      "learning_rate": 5e-05,
      "loss": 177.2609,
      "step": 1
    },
    {
      "epoch": 0.024390243902439025,
      "eval_loss": 11.061498641967773,
      "eval_runtime": 0.5919,
      "eval_samples_per_second": 84.467,
      "eval_steps_per_second": 21.961,
      "step": 1
    },
    {
      "epoch": 0.04878048780487805,
      "grad_norm": 21.8754825592041,
      "learning_rate": 0.0001,
      "loss": 177.4062,
      "step": 2
    },
    {
      "epoch": 0.07317073170731707,
      "grad_norm": 19.161231994628906,
      "learning_rate": 9.990365154573717e-05,
      "loss": 177.2047,
      "step": 3
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 18.24640464782715,
      "learning_rate": 9.961501876182148e-05,
      "loss": 177.1078,
      "step": 4
    },
    {
      "epoch": 0.12195121951219512,
      "grad_norm": 16.007835388183594,
      "learning_rate": 9.913533761814537e-05,
      "loss": 176.9187,
      "step": 5
    },
    {
      "epoch": 0.14634146341463414,
      "grad_norm": 19.088781356811523,
      "learning_rate": 9.846666218300807e-05,
      "loss": 176.8813,
      "step": 6
    },
    {
      "epoch": 0.17073170731707318,
      "grad_norm": 19.20107650756836,
      "learning_rate": 9.761185582727977e-05,
      "loss": 176.7016,
      "step": 7
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 19.330705642700195,
      "learning_rate": 9.657457896300791e-05,
      "loss": 176.4891,
      "step": 8
    },
    {
      "epoch": 0.21951219512195122,
      "grad_norm": 19.035329818725586,
      "learning_rate": 9.535927336897098e-05,
      "loss": 176.3313,
      "step": 9
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 17.692354202270508,
      "learning_rate": 9.397114317029975e-05,
      "loss": 176.2516,
      "step": 10
    },
    {
      "epoch": 0.2682926829268293,
      "grad_norm": 14.887166976928711,
      "learning_rate": 9.241613255361455e-05,
      "loss": 176.2938,
      "step": 11
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 17.759241104125977,
      "learning_rate": 9.070090031310558e-05,
      "loss": 176.0484,
      "step": 12
    },
    {
      "epoch": 0.3170731707317073,
      "grad_norm": 15.97523307800293,
      "learning_rate": 8.883279133655399e-05,
      "loss": 176.0563,
      "step": 13
    },
    {
      "epoch": 0.34146341463414637,
      "grad_norm": 14.555109024047852,
      "learning_rate": 8.681980515339464e-05,
      "loss": 176.0516,
      "step": 14
    },
    {
      "epoch": 0.36585365853658536,
      "grad_norm": 16.004714965820312,
      "learning_rate": 8.467056167950311e-05,
      "loss": 175.5969,
      "step": 15
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 14.519476890563965,
      "learning_rate": 8.239426430539243e-05,
      "loss": 175.7828,
      "step": 16
    },
    {
      "epoch": 0.4146341463414634,
      "grad_norm": 14.627748489379883,
      "learning_rate": 8.000066048588211e-05,
      "loss": 175.4203,
      "step": 17
    },
    {
      "epoch": 0.43902439024390244,
      "grad_norm": 13.422088623046875,
      "learning_rate": 7.75e-05,
      "loss": 175.5359,
      "step": 18
    },
    {
      "epoch": 0.4634146341463415,
      "grad_norm": 14.52273941040039,
      "learning_rate": 7.490299105985507e-05,
      "loss": 175.2516,
      "step": 19
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 13.916686058044434,
      "learning_rate": 7.222075445642904e-05,
      "loss": 175.2609,
      "step": 20
    },
    {
      "epoch": 0.5121951219512195,
      "grad_norm": 13.594751358032227,
      "learning_rate": 6.946477593864228e-05,
      "loss": 175.2906,
      "step": 21
    },
    {
      "epoch": 0.5365853658536586,
      "grad_norm": 13.359724044799805,
      "learning_rate": 6.664685702961344e-05,
      "loss": 175.2016,
      "step": 22
    },
    {
      "epoch": 0.5609756097560976,
      "grad_norm": 13.708386421203613,
      "learning_rate": 6.377906449072578e-05,
      "loss": 174.9641,
      "step": 23
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 12.235694885253906,
      "learning_rate": 6.087367864990233e-05,
      "loss": 175.1891,
      "step": 24
    },
    {
      "epoch": 0.6097560975609756,
      "grad_norm": 12.791362762451172,
      "learning_rate": 5.794314081535644e-05,
      "loss": 175.0234,
      "step": 25
    },
    {
      "epoch": 0.6097560975609756,
      "eval_loss": 10.943249702453613,
      "eval_runtime": 0.0727,
      "eval_samples_per_second": 687.986,
      "eval_steps_per_second": 178.876,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2101346304000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}