{
  "best_metric": 4.073652744293213,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.129680661371373,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00259361322742746,
      "grad_norm": 1.7529813051223755,
      "learning_rate": 5e-05,
      "loss": 4.7617,
      "step": 1
    },
    {
      "epoch": 0.00259361322742746,
      "eval_loss": 6.2509355545043945,
      "eval_runtime": 2.3583,
      "eval_samples_per_second": 21.201,
      "eval_steps_per_second": 5.512,
      "step": 1
    },
    {
      "epoch": 0.00518722645485492,
      "grad_norm": 1.9488269090652466,
      "learning_rate": 0.0001,
      "loss": 5.0497,
      "step": 2
    },
    {
      "epoch": 0.007780839682282379,
      "grad_norm": 2.015064239501953,
      "learning_rate": 9.990365154573717e-05,
      "loss": 5.142,
      "step": 3
    },
    {
      "epoch": 0.01037445290970984,
      "grad_norm": 1.8435602188110352,
      "learning_rate": 9.961501876182148e-05,
      "loss": 5.1729,
      "step": 4
    },
    {
      "epoch": 0.0129680661371373,
      "grad_norm": 2.0161666870117188,
      "learning_rate": 9.913533761814537e-05,
      "loss": 5.1653,
      "step": 5
    },
    {
      "epoch": 0.015561679364564759,
      "grad_norm": 2.190350294113159,
      "learning_rate": 9.846666218300807e-05,
      "loss": 5.2045,
      "step": 6
    },
    {
      "epoch": 0.01815529259199222,
      "grad_norm": 2.8864424228668213,
      "learning_rate": 9.761185582727977e-05,
      "loss": 4.9362,
      "step": 7
    },
    {
      "epoch": 0.02074890581941968,
      "grad_norm": 2.970374822616577,
      "learning_rate": 9.657457896300791e-05,
      "loss": 4.9305,
      "step": 8
    },
    {
      "epoch": 0.02334251904684714,
      "grad_norm": 2.8725414276123047,
      "learning_rate": 9.535927336897098e-05,
      "loss": 4.7503,
      "step": 9
    },
    {
      "epoch": 0.0259361322742746,
      "grad_norm": 2.503429412841797,
      "learning_rate": 9.397114317029975e-05,
      "loss": 4.6666,
      "step": 10
    },
    {
      "epoch": 0.028529745501702057,
      "grad_norm": 2.6886935234069824,
      "learning_rate": 9.241613255361455e-05,
      "loss": 4.5236,
      "step": 11
    },
    {
      "epoch": 0.031123358729129517,
      "grad_norm": 3.6442995071411133,
      "learning_rate": 9.070090031310558e-05,
      "loss": 4.2699,
      "step": 12
    },
    {
      "epoch": 0.03371697195655698,
      "grad_norm": 5.20770788192749,
      "learning_rate": 8.883279133655399e-05,
      "loss": 4.8124,
      "step": 13
    },
    {
      "epoch": 0.03631058518398444,
      "grad_norm": 5.5132527351379395,
      "learning_rate": 8.681980515339464e-05,
      "loss": 5.0373,
      "step": 14
    },
    {
      "epoch": 0.0389041984114119,
      "grad_norm": 4.1492085456848145,
      "learning_rate": 8.467056167950311e-05,
      "loss": 4.6733,
      "step": 15
    },
    {
      "epoch": 0.04149781163883936,
      "grad_norm": 3.5699918270111084,
      "learning_rate": 8.239426430539243e-05,
      "loss": 4.4491,
      "step": 16
    },
    {
      "epoch": 0.04409142486626682,
      "grad_norm": 2.771456241607666,
      "learning_rate": 8.000066048588211e-05,
      "loss": 4.4571,
      "step": 17
    },
    {
      "epoch": 0.04668503809369428,
      "grad_norm": 1.737979531288147,
      "learning_rate": 7.75e-05,
      "loss": 4.3732,
      "step": 18
    },
    {
      "epoch": 0.04927865132112174,
      "grad_norm": 6.20866584777832,
      "learning_rate": 7.490299105985507e-05,
      "loss": 4.2321,
      "step": 19
    },
    {
      "epoch": 0.0518722645485492,
      "grad_norm": 1.432242512702942,
      "learning_rate": 7.222075445642904e-05,
      "loss": 4.4104,
      "step": 20
    },
    {
      "epoch": 0.05446587777597666,
      "grad_norm": 2.0080277919769287,
      "learning_rate": 6.946477593864228e-05,
      "loss": 4.3783,
      "step": 21
    },
    {
      "epoch": 0.057059491003404114,
      "grad_norm": 2.657991886138916,
      "learning_rate": 6.664685702961344e-05,
      "loss": 4.4785,
      "step": 22
    },
    {
      "epoch": 0.059653104230831575,
      "grad_norm": 3.228008985519409,
      "learning_rate": 6.377906449072578e-05,
      "loss": 4.5171,
      "step": 23
    },
    {
      "epoch": 0.062246717458259035,
      "grad_norm": 3.676307439804077,
      "learning_rate": 6.087367864990233e-05,
      "loss": 4.3676,
      "step": 24
    },
    {
      "epoch": 0.0648403306856865,
      "grad_norm": 6.881477355957031,
      "learning_rate": 5.794314081535644e-05,
      "loss": 4.3583,
      "step": 25
    },
    {
      "epoch": 0.0648403306856865,
      "eval_loss": 4.252082824707031,
      "eval_runtime": 1.9389,
      "eval_samples_per_second": 25.788,
      "eval_steps_per_second": 6.705,
      "step": 25
    },
    {
      "epoch": 0.06743394391311396,
      "grad_norm": 1.0263198614120483,
      "learning_rate": 5.500000000000001e-05,
      "loss": 4.0817,
      "step": 26
    },
    {
      "epoch": 0.07002755714054142,
      "grad_norm": 0.9885427951812744,
      "learning_rate": 5.205685918464356e-05,
      "loss": 4.0925,
      "step": 27
    },
    {
      "epoch": 0.07262117036796888,
      "grad_norm": 0.9994748830795288,
      "learning_rate": 4.912632135009769e-05,
      "loss": 4.1732,
      "step": 28
    },
    {
      "epoch": 0.07521478359539634,
      "grad_norm": 1.1177375316619873,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 4.2198,
      "step": 29
    },
    {
      "epoch": 0.0778083968228238,
      "grad_norm": 1.0211936235427856,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 4.2575,
      "step": 30
    },
    {
      "epoch": 0.08040201005025126,
      "grad_norm": 0.9716774821281433,
      "learning_rate": 4.053522406135775e-05,
      "loss": 4.1516,
      "step": 31
    },
    {
      "epoch": 0.08299562327767872,
      "grad_norm": 0.9779271483421326,
      "learning_rate": 3.777924554357096e-05,
      "loss": 4.0588,
      "step": 32
    },
    {
      "epoch": 0.08558923650510618,
      "grad_norm": 1.3039002418518066,
      "learning_rate": 3.509700894014496e-05,
      "loss": 4.2819,
      "step": 33
    },
    {
      "epoch": 0.08818284973253364,
      "grad_norm": 1.6353998184204102,
      "learning_rate": 3.250000000000001e-05,
      "loss": 4.2722,
      "step": 34
    },
    {
      "epoch": 0.0907764629599611,
      "grad_norm": 1.7478457689285278,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 4.3754,
      "step": 35
    },
    {
      "epoch": 0.09337007618738856,
      "grad_norm": 2.0654168128967285,
      "learning_rate": 2.760573569460757e-05,
      "loss": 4.3284,
      "step": 36
    },
    {
      "epoch": 0.09596368941481602,
      "grad_norm": 2.983126163482666,
      "learning_rate": 2.53294383204969e-05,
      "loss": 4.1292,
      "step": 37
    },
    {
      "epoch": 0.09855730264224348,
      "grad_norm": 1.1246665716171265,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 3.9209,
      "step": 38
    },
    {
      "epoch": 0.10115091586967094,
      "grad_norm": 0.9749646186828613,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 4.0122,
      "step": 39
    },
    {
      "epoch": 0.1037445290970984,
      "grad_norm": 0.9288861155509949,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 4.1111,
      "step": 40
    },
    {
      "epoch": 0.10633814232452586,
      "grad_norm": 0.971885621547699,
      "learning_rate": 1.758386744638546e-05,
      "loss": 3.9324,
      "step": 41
    },
    {
      "epoch": 0.10893175555195332,
      "grad_norm": 0.9863269329071045,
      "learning_rate": 1.602885682970026e-05,
      "loss": 3.9597,
      "step": 42
    },
    {
      "epoch": 0.11152536877938077,
      "grad_norm": 0.9098839163780212,
      "learning_rate": 1.464072663102903e-05,
      "loss": 4.09,
      "step": 43
    },
    {
      "epoch": 0.11411898200680823,
      "grad_norm": 0.9183852672576904,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 4.0903,
      "step": 44
    },
    {
      "epoch": 0.11671259523423569,
      "grad_norm": 0.9638357162475586,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 4.1408,
      "step": 45
    },
    {
      "epoch": 0.11930620846166315,
      "grad_norm": 1.0947378873825073,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 4.1255,
      "step": 46
    },
    {
      "epoch": 0.12189982168909061,
      "grad_norm": 1.312705159187317,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 4.3,
      "step": 47
    },
    {
      "epoch": 0.12449343491651807,
      "grad_norm": 1.7013065814971924,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 4.17,
      "step": 48
    },
    {
      "epoch": 0.12708704814394553,
      "grad_norm": 2.3629062175750732,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 4.1915,
      "step": 49
    },
    {
      "epoch": 0.129680661371373,
      "grad_norm": 5.0966715812683105,
      "learning_rate": 1e-05,
      "loss": 4.0061,
      "step": 50
    },
    {
      "epoch": 0.129680661371373,
      "eval_loss": 4.073652744293213,
      "eval_runtime": 1.9512,
      "eval_samples_per_second": 25.626,
      "eval_steps_per_second": 6.663,
      "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": 2.229252309123072e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}