{
  "best_metric": 0.6878839731216431,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.029605506624232107,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005921101324846421,
      "grad_norm": 17.604625701904297,
      "learning_rate": 5e-05,
      "loss": 31.8806,
      "step": 1
    },
    {
      "epoch": 0.0005921101324846421,
      "eval_loss": 3.1362521648406982,
      "eval_runtime": 2.1009,
      "eval_samples_per_second": 23.799,
      "eval_steps_per_second": 6.188,
      "step": 1
    },
    {
      "epoch": 0.0011842202649692843,
      "grad_norm": 33.06697463989258,
      "learning_rate": 0.0001,
      "loss": 44.5091,
      "step": 2
    },
    {
      "epoch": 0.0017763303974539263,
      "grad_norm": 36.880313873291016,
      "learning_rate": 9.990365154573717e-05,
      "loss": 49.7069,
      "step": 3
    },
    {
      "epoch": 0.0023684405299385686,
      "grad_norm": 37.61426544189453,
      "learning_rate": 9.961501876182148e-05,
      "loss": 44.2544,
      "step": 4
    },
    {
      "epoch": 0.0029605506624232106,
      "grad_norm": 33.017112731933594,
      "learning_rate": 9.913533761814537e-05,
      "loss": 38.5715,
      "step": 5
    },
    {
      "epoch": 0.0035526607949078527,
      "grad_norm": 23.70199203491211,
      "learning_rate": 9.846666218300807e-05,
      "loss": 28.7762,
      "step": 6
    },
    {
      "epoch": 0.004144770927392495,
      "grad_norm": 22.765506744384766,
      "learning_rate": 9.761185582727977e-05,
      "loss": 26.4315,
      "step": 7
    },
    {
      "epoch": 0.004736881059877137,
      "grad_norm": 21.75705337524414,
      "learning_rate": 9.657457896300791e-05,
      "loss": 26.0281,
      "step": 8
    },
    {
      "epoch": 0.005328991192361779,
      "grad_norm": 21.938560485839844,
      "learning_rate": 9.535927336897098e-05,
      "loss": 28.5602,
      "step": 9
    },
    {
      "epoch": 0.005921101324846421,
      "grad_norm": 37.198631286621094,
      "learning_rate": 9.397114317029975e-05,
      "loss": 31.6136,
      "step": 10
    },
    {
      "epoch": 0.006513211457331063,
      "grad_norm": 40.3657341003418,
      "learning_rate": 9.241613255361455e-05,
      "loss": 33.5207,
      "step": 11
    },
    {
      "epoch": 0.007105321589815705,
      "grad_norm": 34.34028244018555,
      "learning_rate": 9.070090031310558e-05,
      "loss": 43.4837,
      "step": 12
    },
    {
      "epoch": 0.007697431722300348,
      "grad_norm": 21.483396530151367,
      "learning_rate": 8.883279133655399e-05,
      "loss": 33.467,
      "step": 13
    },
    {
      "epoch": 0.00828954185478499,
      "grad_norm": 17.009862899780273,
      "learning_rate": 8.681980515339464e-05,
      "loss": 17.567,
      "step": 14
    },
    {
      "epoch": 0.008881651987269631,
      "grad_norm": 17.309255599975586,
      "learning_rate": 8.467056167950311e-05,
      "loss": 17.6681,
      "step": 15
    },
    {
      "epoch": 0.009473762119754274,
      "grad_norm": 17.438411712646484,
      "learning_rate": 8.239426430539243e-05,
      "loss": 16.7533,
      "step": 16
    },
    {
      "epoch": 0.010065872252238917,
      "grad_norm": 15.839043617248535,
      "learning_rate": 8.000066048588211e-05,
      "loss": 17.7077,
      "step": 17
    },
    {
      "epoch": 0.010657982384723558,
      "grad_norm": 14.868587493896484,
      "learning_rate": 7.75e-05,
      "loss": 14.6147,
      "step": 18
    },
    {
      "epoch": 0.011250092517208201,
      "grad_norm": 12.83969783782959,
      "learning_rate": 7.490299105985507e-05,
      "loss": 14.174,
      "step": 19
    },
    {
      "epoch": 0.011842202649692843,
      "grad_norm": 15.310847282409668,
      "learning_rate": 7.222075445642904e-05,
      "loss": 14.82,
      "step": 20
    },
    {
      "epoch": 0.012434312782177485,
      "grad_norm": 15.526948928833008,
      "learning_rate": 6.946477593864228e-05,
      "loss": 17.0657,
      "step": 21
    },
    {
      "epoch": 0.013026422914662127,
      "grad_norm": 14.14400863647461,
      "learning_rate": 6.664685702961344e-05,
      "loss": 19.0217,
      "step": 22
    },
    {
      "epoch": 0.01361853304714677,
      "grad_norm": 19.764976501464844,
      "learning_rate": 6.377906449072578e-05,
      "loss": 21.4482,
      "step": 23
    },
    {
      "epoch": 0.01421064317963141,
      "grad_norm": 20.062236785888672,
      "learning_rate": 6.087367864990233e-05,
      "loss": 30.8147,
      "step": 24
    },
    {
      "epoch": 0.014802753312116054,
      "grad_norm": 26.751684188842773,
      "learning_rate": 5.794314081535644e-05,
      "loss": 39.0464,
      "step": 25
    },
    {
      "epoch": 0.014802753312116054,
      "eval_loss": 0.8598223924636841,
      "eval_runtime": 2.1571,
      "eval_samples_per_second": 23.179,
      "eval_steps_per_second": 6.027,
      "step": 25
    },
    {
      "epoch": 0.015394863444600696,
      "grad_norm": 28.344457626342773,
      "learning_rate": 5.500000000000001e-05,
      "loss": 20.5411,
      "step": 26
    },
    {
      "epoch": 0.01598697357708534,
      "grad_norm": 27.111478805541992,
      "learning_rate": 5.205685918464356e-05,
      "loss": 12.6905,
      "step": 27
    },
    {
      "epoch": 0.01657908370956998,
      "grad_norm": 26.745271682739258,
      "learning_rate": 4.912632135009769e-05,
      "loss": 12.5729,
      "step": 28
    },
    {
      "epoch": 0.017171193842054622,
      "grad_norm": 25.625160217285156,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 11.3855,
      "step": 29
    },
    {
      "epoch": 0.017763303974539263,
      "grad_norm": 21.623184204101562,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 10.6879,
      "step": 30
    },
    {
      "epoch": 0.018355414107023908,
      "grad_norm": 12.587967872619629,
      "learning_rate": 4.053522406135775e-05,
      "loss": 10.3589,
      "step": 31
    },
    {
      "epoch": 0.01894752423950855,
      "grad_norm": 9.164191246032715,
      "learning_rate": 3.777924554357096e-05,
      "loss": 11.7987,
      "step": 32
    },
    {
      "epoch": 0.01953963437199319,
      "grad_norm": 11.130849838256836,
      "learning_rate": 3.509700894014496e-05,
      "loss": 13.9788,
      "step": 33
    },
    {
      "epoch": 0.020131744504477835,
      "grad_norm": 16.064083099365234,
      "learning_rate": 3.250000000000001e-05,
      "loss": 16.487,
      "step": 34
    },
    {
      "epoch": 0.020723854636962476,
      "grad_norm": 14.369626998901367,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 17.3887,
      "step": 35
    },
    {
      "epoch": 0.021315964769447117,
      "grad_norm": 17.29195785522461,
      "learning_rate": 2.760573569460757e-05,
      "loss": 23.9256,
      "step": 36
    },
    {
      "epoch": 0.021908074901931758,
      "grad_norm": 19.806123733520508,
      "learning_rate": 2.53294383204969e-05,
      "loss": 32.8144,
      "step": 37
    },
    {
      "epoch": 0.022500185034416403,
      "grad_norm": 15.529447555541992,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 28.3572,
      "step": 38
    },
    {
      "epoch": 0.023092295166901044,
      "grad_norm": 15.903905868530273,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 10.3876,
      "step": 39
    },
    {
      "epoch": 0.023684405299385685,
      "grad_norm": 19.85993194580078,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 9.8589,
      "step": 40
    },
    {
      "epoch": 0.024276515431870326,
      "grad_norm": 13.756356239318848,
      "learning_rate": 1.758386744638546e-05,
      "loss": 8.4382,
      "step": 41
    },
    {
      "epoch": 0.02486862556435497,
      "grad_norm": 14.453191757202148,
      "learning_rate": 1.602885682970026e-05,
      "loss": 9.2444,
      "step": 42
    },
    {
      "epoch": 0.025460735696839612,
      "grad_norm": 13.35396671295166,
      "learning_rate": 1.464072663102903e-05,
      "loss": 8.7736,
      "step": 43
    },
    {
      "epoch": 0.026052845829324253,
      "grad_norm": 9.098504066467285,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 9.8412,
      "step": 44
    },
    {
      "epoch": 0.026644955961808898,
      "grad_norm": 10.487635612487793,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 12.0429,
      "step": 45
    },
    {
      "epoch": 0.02723706609429354,
      "grad_norm": 10.247054100036621,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 15.9474,
      "step": 46
    },
    {
      "epoch": 0.02782917622677818,
      "grad_norm": 12.563997268676758,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 15.3706,
      "step": 47
    },
    {
      "epoch": 0.02842128635926282,
      "grad_norm": 12.691200256347656,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 16.1405,
      "step": 48
    },
    {
      "epoch": 0.029013396491747466,
      "grad_norm": 16.123600006103516,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 28.5094,
      "step": 49
    },
    {
      "epoch": 0.029605506624232107,
      "grad_norm": 24.73943519592285,
      "learning_rate": 1e-05,
      "loss": 38.8374,
      "step": 50
    },
    {
      "epoch": 0.029605506624232107,
      "eval_loss": 0.6878839731216431,
      "eval_runtime": 2.1562,
      "eval_samples_per_second": 23.189,
      "eval_steps_per_second": 6.029,
      "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": 2.968064857808568e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}