{
  "best_metric": 3.743145704269409,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 2.8368794326241136,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 8.392451286315918,
      "learning_rate": 5e-05,
      "loss": 5.6743,
      "step": 1
    },
    {
      "epoch": 0.05673758865248227,
      "eval_loss": 10.523259162902832,
      "eval_runtime": 4.7149,
      "eval_samples_per_second": 10.605,
      "eval_steps_per_second": 2.757,
      "step": 1
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": 11.811187744140625,
      "learning_rate": 0.0001,
      "loss": 8.385,
      "step": 2
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 10.521172523498535,
      "learning_rate": 9.990365154573717e-05,
      "loss": 9.7147,
      "step": 3
    },
    {
      "epoch": 0.22695035460992907,
      "grad_norm": 11.874200820922852,
      "learning_rate": 9.961501876182148e-05,
      "loss": 12.2553,
      "step": 4
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 6.8266191482543945,
      "learning_rate": 9.913533761814537e-05,
      "loss": 5.1718,
      "step": 5
    },
    {
      "epoch": 0.3404255319148936,
      "grad_norm": 7.819369316101074,
      "learning_rate": 9.846666218300807e-05,
      "loss": 5.2077,
      "step": 6
    },
    {
      "epoch": 0.3971631205673759,
      "grad_norm": 10.502732276916504,
      "learning_rate": 9.761185582727977e-05,
      "loss": 5.1158,
      "step": 7
    },
    {
      "epoch": 0.45390070921985815,
      "grad_norm": 14.014196395874023,
      "learning_rate": 9.657457896300791e-05,
      "loss": 4.8454,
      "step": 8
    },
    {
      "epoch": 0.5106382978723404,
      "grad_norm": 18.714672088623047,
      "learning_rate": 9.535927336897098e-05,
      "loss": 5.0092,
      "step": 9
    },
    {
      "epoch": 0.5673758865248227,
      "grad_norm": 24.235963821411133,
      "learning_rate": 9.397114317029975e-05,
      "loss": 4.963,
      "step": 10
    },
    {
      "epoch": 0.624113475177305,
      "grad_norm": 14.31279182434082,
      "learning_rate": 9.241613255361455e-05,
      "loss": 4.1562,
      "step": 11
    },
    {
      "epoch": 0.6808510638297872,
      "grad_norm": 5.5505571365356445,
      "learning_rate": 9.070090031310558e-05,
      "loss": 3.9652,
      "step": 12
    },
    {
      "epoch": 0.7375886524822695,
      "grad_norm": 9.763359069824219,
      "learning_rate": 8.883279133655399e-05,
      "loss": 4.7272,
      "step": 13
    },
    {
      "epoch": 0.7943262411347518,
      "grad_norm": 7.2530317306518555,
      "learning_rate": 8.681980515339464e-05,
      "loss": 2.8598,
      "step": 14
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 7.526337623596191,
      "learning_rate": 8.467056167950311e-05,
      "loss": 3.1447,
      "step": 15
    },
    {
      "epoch": 0.9078014184397163,
      "grad_norm": 9.060070991516113,
      "learning_rate": 8.239426430539243e-05,
      "loss": 3.854,
      "step": 16
    },
    {
      "epoch": 0.9645390070921985,
      "grad_norm": 23.306001663208008,
      "learning_rate": 8.000066048588211e-05,
      "loss": 7.9826,
      "step": 17
    },
    {
      "epoch": 1.0212765957446808,
      "grad_norm": 6.283840179443359,
      "learning_rate": 7.75e-05,
      "loss": 3.801,
      "step": 18
    },
    {
      "epoch": 1.0780141843971631,
      "grad_norm": 3.4587056636810303,
      "learning_rate": 7.490299105985507e-05,
      "loss": 2.0528,
      "step": 19
    },
    {
      "epoch": 1.1347517730496455,
      "grad_norm": 4.050403594970703,
      "learning_rate": 7.222075445642904e-05,
      "loss": 2.6914,
      "step": 20
    },
    {
      "epoch": 1.1914893617021276,
      "grad_norm": 6.144046783447266,
      "learning_rate": 6.946477593864228e-05,
      "loss": 3.4362,
      "step": 21
    },
    {
      "epoch": 1.24822695035461,
      "grad_norm": 9.191603660583496,
      "learning_rate": 6.664685702961344e-05,
      "loss": 3.8856,
      "step": 22
    },
    {
      "epoch": 1.3049645390070923,
      "grad_norm": 5.413357734680176,
      "learning_rate": 6.377906449072578e-05,
      "loss": 2.4884,
      "step": 23
    },
    {
      "epoch": 1.3617021276595744,
      "grad_norm": 4.658510208129883,
      "learning_rate": 6.087367864990233e-05,
      "loss": 2.388,
      "step": 24
    },
    {
      "epoch": 1.4184397163120568,
      "grad_norm": 5.317564010620117,
      "learning_rate": 5.794314081535644e-05,
      "loss": 3.1641,
      "step": 25
    },
    {
      "epoch": 1.4184397163120568,
      "eval_loss": 4.228944778442383,
      "eval_runtime": 4.3635,
      "eval_samples_per_second": 11.459,
      "eval_steps_per_second": 2.979,
      "step": 25
    },
    {
      "epoch": 1.475177304964539,
      "grad_norm": 7.520847320556641,
      "learning_rate": 5.500000000000001e-05,
      "loss": 3.2305,
      "step": 26
    },
    {
      "epoch": 1.5319148936170213,
      "grad_norm": 6.371490001678467,
      "learning_rate": 5.205685918464356e-05,
      "loss": 2.9182,
      "step": 27
    },
    {
      "epoch": 1.5886524822695036,
      "grad_norm": 3.166982412338257,
      "learning_rate": 4.912632135009769e-05,
      "loss": 2.331,
      "step": 28
    },
    {
      "epoch": 1.645390070921986,
      "grad_norm": 4.1069016456604,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 2.9918,
      "step": 29
    },
    {
      "epoch": 1.702127659574468,
      "grad_norm": 5.494497299194336,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 3.0673,
      "step": 30
    },
    {
      "epoch": 1.7588652482269502,
      "grad_norm": 9.687826156616211,
      "learning_rate": 4.053522406135775e-05,
      "loss": 2.9902,
      "step": 31
    },
    {
      "epoch": 1.8156028368794326,
      "grad_norm": 3.650472402572632,
      "learning_rate": 3.777924554357096e-05,
      "loss": 2.2526,
      "step": 32
    },
    {
      "epoch": 1.872340425531915,
      "grad_norm": 4.139589309692383,
      "learning_rate": 3.509700894014496e-05,
      "loss": 2.7633,
      "step": 33
    },
    {
      "epoch": 1.9290780141843973,
      "grad_norm": 7.082653045654297,
      "learning_rate": 3.250000000000001e-05,
      "loss": 3.8162,
      "step": 34
    },
    {
      "epoch": 1.9858156028368794,
      "grad_norm": 21.436193466186523,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 5.175,
      "step": 35
    },
    {
      "epoch": 2.0425531914893615,
      "grad_norm": 3.4575095176696777,
      "learning_rate": 2.760573569460757e-05,
      "loss": 2.1421,
      "step": 36
    },
    {
      "epoch": 2.099290780141844,
      "grad_norm": 3.1642634868621826,
      "learning_rate": 2.53294383204969e-05,
      "loss": 1.9559,
      "step": 37
    },
    {
      "epoch": 2.1560283687943262,
      "grad_norm": 3.7310965061187744,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 2.442,
      "step": 38
    },
    {
      "epoch": 2.2127659574468086,
      "grad_norm": 6.142940998077393,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 3.7213,
      "step": 39
    },
    {
      "epoch": 2.269503546099291,
      "grad_norm": 9.058276176452637,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 2.5916,
      "step": 40
    },
    {
      "epoch": 2.326241134751773,
      "grad_norm": 2.9689388275146484,
      "learning_rate": 1.758386744638546e-05,
      "loss": 1.9181,
      "step": 41
    },
    {
      "epoch": 2.382978723404255,
      "grad_norm": 3.1938860416412354,
      "learning_rate": 1.602885682970026e-05,
      "loss": 2.3449,
      "step": 42
    },
    {
      "epoch": 2.4397163120567376,
      "grad_norm": 5.2489752769470215,
      "learning_rate": 1.464072663102903e-05,
      "loss": 3.3714,
      "step": 43
    },
    {
      "epoch": 2.49645390070922,
      "grad_norm": 10.633807182312012,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 2.5432,
      "step": 44
    },
    {
      "epoch": 2.5531914893617023,
      "grad_norm": 3.7500996589660645,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 2.0958,
      "step": 45
    },
    {
      "epoch": 2.6099290780141846,
      "grad_norm": 3.7776594161987305,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 2.2518,
      "step": 46
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 4.717670440673828,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 2.848,
      "step": 47
    },
    {
      "epoch": 2.723404255319149,
      "grad_norm": 15.359528541564941,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 2.6212,
      "step": 48
    },
    {
      "epoch": 2.780141843971631,
      "grad_norm": 4.678123950958252,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 2.3551,
      "step": 49
    },
    {
      "epoch": 2.8368794326241136,
      "grad_norm": 3.875638723373413,
      "learning_rate": 1e-05,
      "loss": 2.1527,
      "step": 50
    },
    {
      "epoch": 2.8368794326241136,
      "eval_loss": 3.743145704269409,
      "eval_runtime": 4.3478,
      "eval_samples_per_second": 11.5,
      "eval_steps_per_second": 2.99,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 6.823228785819648e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}