{
  "best_metric": 0.9104208946228027,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.03994108689682718,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007988217379365436,
      "grad_norm": 63.3208122253418,
      "learning_rate": 5e-05,
      "loss": 36.324,
      "step": 1
    },
    {
      "epoch": 0.0007988217379365436,
      "eval_loss": 1.5224533081054688,
      "eval_runtime": 5.7379,
      "eval_samples_per_second": 8.714,
      "eval_steps_per_second": 2.266,
      "step": 1
    },
    {
      "epoch": 0.0015976434758730872,
      "grad_norm": 71.54033660888672,
      "learning_rate": 0.0001,
      "loss": 36.1531,
      "step": 2
    },
    {
      "epoch": 0.002396465213809631,
      "grad_norm": 46.256126403808594,
      "learning_rate": 9.990365154573717e-05,
      "loss": 34.0182,
      "step": 3
    },
    {
      "epoch": 0.0031952869517461744,
      "grad_norm": 56.13178253173828,
      "learning_rate": 9.961501876182148e-05,
      "loss": 32.1905,
      "step": 4
    },
    {
      "epoch": 0.003994108689682718,
      "grad_norm": 48.684913635253906,
      "learning_rate": 9.913533761814537e-05,
      "loss": 31.9449,
      "step": 5
    },
    {
      "epoch": 0.004792930427619262,
      "grad_norm": 34.00423049926758,
      "learning_rate": 9.846666218300807e-05,
      "loss": 29.6352,
      "step": 6
    },
    {
      "epoch": 0.005591752165555805,
      "grad_norm": 37.10193634033203,
      "learning_rate": 9.761185582727977e-05,
      "loss": 29.7769,
      "step": 7
    },
    {
      "epoch": 0.006390573903492349,
      "grad_norm": 30.896135330200195,
      "learning_rate": 9.657457896300791e-05,
      "loss": 30.0841,
      "step": 8
    },
    {
      "epoch": 0.007189395641428892,
      "grad_norm": 42.899131774902344,
      "learning_rate": 9.535927336897098e-05,
      "loss": 31.2927,
      "step": 9
    },
    {
      "epoch": 0.007988217379365435,
      "grad_norm": 47.98681640625,
      "learning_rate": 9.397114317029975e-05,
      "loss": 30.033,
      "step": 10
    },
    {
      "epoch": 0.008787039117301979,
      "grad_norm": 78.70600891113281,
      "learning_rate": 9.241613255361455e-05,
      "loss": 32.3263,
      "step": 11
    },
    {
      "epoch": 0.009585860855238524,
      "grad_norm": 97.83395385742188,
      "learning_rate": 9.070090031310558e-05,
      "loss": 31.6688,
      "step": 12
    },
    {
      "epoch": 0.010384682593175067,
      "grad_norm": 97.70650482177734,
      "learning_rate": 8.883279133655399e-05,
      "loss": 38.8669,
      "step": 13
    },
    {
      "epoch": 0.01118350433111161,
      "grad_norm": 86.65507507324219,
      "learning_rate": 8.681980515339464e-05,
      "loss": 34.51,
      "step": 14
    },
    {
      "epoch": 0.011982326069048154,
      "grad_norm": 67.9210205078125,
      "learning_rate": 8.467056167950311e-05,
      "loss": 32.7077,
      "step": 15
    },
    {
      "epoch": 0.012781147806984697,
      "grad_norm": 40.76219940185547,
      "learning_rate": 8.239426430539243e-05,
      "loss": 30.987,
      "step": 16
    },
    {
      "epoch": 0.01357996954492124,
      "grad_norm": 29.58269691467285,
      "learning_rate": 8.000066048588211e-05,
      "loss": 28.4159,
      "step": 17
    },
    {
      "epoch": 0.014378791282857784,
      "grad_norm": 29.042133331298828,
      "learning_rate": 7.75e-05,
      "loss": 28.8869,
      "step": 18
    },
    {
      "epoch": 0.015177613020794328,
      "grad_norm": 30.39849853515625,
      "learning_rate": 7.490299105985507e-05,
      "loss": 28.4458,
      "step": 19
    },
    {
      "epoch": 0.01597643475873087,
      "grad_norm": 31.308870315551758,
      "learning_rate": 7.222075445642904e-05,
      "loss": 27.7839,
      "step": 20
    },
    {
      "epoch": 0.016775256496667414,
      "grad_norm": 32.65206527709961,
      "learning_rate": 6.946477593864228e-05,
      "loss": 28.4097,
      "step": 21
    },
    {
      "epoch": 0.017574078234603958,
      "grad_norm": 40.95891189575195,
      "learning_rate": 6.664685702961344e-05,
      "loss": 30.1679,
      "step": 22
    },
    {
      "epoch": 0.0183728999725405,
      "grad_norm": 51.54391098022461,
      "learning_rate": 6.377906449072578e-05,
      "loss": 29.1528,
      "step": 23
    },
    {
      "epoch": 0.019171721710477048,
      "grad_norm": 78.71659088134766,
      "learning_rate": 6.087367864990233e-05,
      "loss": 31.258,
      "step": 24
    },
    {
      "epoch": 0.01997054344841359,
      "grad_norm": 193.09556579589844,
      "learning_rate": 5.794314081535644e-05,
      "loss": 40.0064,
      "step": 25
    },
    {
      "epoch": 0.01997054344841359,
      "eval_loss": 0.9694052338600159,
      "eval_runtime": 5.7695,
      "eval_samples_per_second": 8.666,
      "eval_steps_per_second": 2.253,
      "step": 25
    },
    {
      "epoch": 0.020769365186350135,
      "grad_norm": 40.4317626953125,
      "learning_rate": 5.500000000000001e-05,
      "loss": 29.3446,
      "step": 26
    },
    {
      "epoch": 0.021568186924286678,
      "grad_norm": 40.03319549560547,
      "learning_rate": 5.205685918464356e-05,
      "loss": 31.2248,
      "step": 27
    },
    {
      "epoch": 0.02236700866222322,
      "grad_norm": 36.50101089477539,
      "learning_rate": 4.912632135009769e-05,
      "loss": 27.8306,
      "step": 28
    },
    {
      "epoch": 0.023165830400159765,
      "grad_norm": 31.140682220458984,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 28.5794,
      "step": 29
    },
    {
      "epoch": 0.023964652138096308,
      "grad_norm": 27.054738998413086,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 28.399,
      "step": 30
    },
    {
      "epoch": 0.02476347387603285,
      "grad_norm": 26.70485496520996,
      "learning_rate": 4.053522406135775e-05,
      "loss": 27.7768,
      "step": 31
    },
    {
      "epoch": 0.025562295613969395,
      "grad_norm": 25.162357330322266,
      "learning_rate": 3.777924554357096e-05,
      "loss": 28.1579,
      "step": 32
    },
    {
      "epoch": 0.02636111735190594,
      "grad_norm": 27.582172393798828,
      "learning_rate": 3.509700894014496e-05,
      "loss": 27.5623,
      "step": 33
    },
    {
      "epoch": 0.02715993908984248,
      "grad_norm": 32.30332565307617,
      "learning_rate": 3.250000000000001e-05,
      "loss": 27.2632,
      "step": 34
    },
    {
      "epoch": 0.027958760827779025,
      "grad_norm": 36.16336441040039,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 29.1573,
      "step": 35
    },
    {
      "epoch": 0.02875758256571557,
      "grad_norm": 51.47412872314453,
      "learning_rate": 2.760573569460757e-05,
      "loss": 28.9492,
      "step": 36
    },
    {
      "epoch": 0.029556404303652112,
      "grad_norm": 84.6512222290039,
      "learning_rate": 2.53294383204969e-05,
      "loss": 29.1161,
      "step": 37
    },
    {
      "epoch": 0.030355226041588655,
      "grad_norm": 97.35894012451172,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 35.2686,
      "step": 38
    },
    {
      "epoch": 0.031154047779525202,
      "grad_norm": 24.390233993530273,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 27.3161,
      "step": 39
    },
    {
      "epoch": 0.03195286951746174,
      "grad_norm": 22.151939392089844,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 27.7894,
      "step": 40
    },
    {
      "epoch": 0.032751691255398285,
      "grad_norm": 23.40633201599121,
      "learning_rate": 1.758386744638546e-05,
      "loss": 26.9961,
      "step": 41
    },
    {
      "epoch": 0.03355051299333483,
      "grad_norm": 23.386327743530273,
      "learning_rate": 1.602885682970026e-05,
      "loss": 27.1492,
      "step": 42
    },
    {
      "epoch": 0.03434933473127137,
      "grad_norm": 21.015361785888672,
      "learning_rate": 1.464072663102903e-05,
      "loss": 25.6054,
      "step": 43
    },
    {
      "epoch": 0.035148156469207915,
      "grad_norm": 22.845361709594727,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 26.6839,
      "step": 44
    },
    {
      "epoch": 0.03594697820714446,
      "grad_norm": 22.830120086669922,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 25.4521,
      "step": 45
    },
    {
      "epoch": 0.036745799945081,
      "grad_norm": 25.423442840576172,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 27.7628,
      "step": 46
    },
    {
      "epoch": 0.03754462168301755,
      "grad_norm": 28.231496810913086,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 28.1701,
      "step": 47
    },
    {
      "epoch": 0.038343443420954096,
      "grad_norm": 36.929622650146484,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 26.3994,
      "step": 48
    },
    {
      "epoch": 0.03914226515889064,
      "grad_norm": 59.25780487060547,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 29.69,
      "step": 49
    },
    {
      "epoch": 0.03994108689682718,
      "grad_norm": 106.83480834960938,
      "learning_rate": 1e-05,
      "loss": 34.6511,
      "step": 50
    },
    {
      "epoch": 0.03994108689682718,
      "eval_loss": 0.9104208946228027,
      "eval_runtime": 5.7718,
      "eval_samples_per_second": 8.663,
      "eval_steps_per_second": 2.252,
      "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": 5.658021338284032e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}