{
  "best_metric": 11.67446517944336,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 2.857142857142857,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 0.3634489178657532,
      "learning_rate": 5e-05,
      "loss": 11.7424,
      "step": 1
    },
    {
      "epoch": 0.05714285714285714,
      "eval_loss": 11.731431007385254,
      "eval_runtime": 0.3912,
      "eval_samples_per_second": 127.816,
      "eval_steps_per_second": 33.232,
      "step": 1
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.40381717681884766,
      "learning_rate": 0.0001,
      "loss": 11.7457,
      "step": 2
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.44402992725372314,
      "learning_rate": 9.990365154573717e-05,
      "loss": 11.7378,
      "step": 3
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.538850724697113,
      "learning_rate": 9.961501876182148e-05,
      "loss": 11.7264,
      "step": 4
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.37543636560440063,
      "learning_rate": 9.913533761814537e-05,
      "loss": 11.727,
      "step": 5
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.3850094974040985,
      "learning_rate": 9.846666218300807e-05,
      "loss": 11.7344,
      "step": 6
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.45715221762657166,
      "learning_rate": 9.761185582727977e-05,
      "loss": 11.7323,
      "step": 7
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.4692140519618988,
      "learning_rate": 9.657457896300791e-05,
      "loss": 11.7278,
      "step": 8
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.43474239110946655,
      "learning_rate": 9.535927336897098e-05,
      "loss": 11.7316,
      "step": 9
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.36733418703079224,
      "learning_rate": 9.397114317029975e-05,
      "loss": 11.7345,
      "step": 10
    },
    {
      "epoch": 0.6285714285714286,
      "grad_norm": 0.47201812267303467,
      "learning_rate": 9.241613255361455e-05,
      "loss": 11.7161,
      "step": 11
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.4983007311820984,
      "learning_rate": 9.070090031310558e-05,
      "loss": 11.7293,
      "step": 12
    },
    {
      "epoch": 0.7428571428571429,
      "grad_norm": 0.5103781819343567,
      "learning_rate": 8.883279133655399e-05,
      "loss": 11.7192,
      "step": 13
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.41874220967292786,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.7316,
      "step": 14
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.48194950819015503,
      "learning_rate": 8.467056167950311e-05,
      "loss": 11.721,
      "step": 15
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 0.5447810888290405,
      "learning_rate": 8.239426430539243e-05,
      "loss": 11.7185,
      "step": 16
    },
    {
      "epoch": 0.9714285714285714,
      "grad_norm": 0.6754027009010315,
      "learning_rate": 8.000066048588211e-05,
      "loss": 11.7119,
      "step": 17
    },
    {
      "epoch": 1.0285714285714285,
      "grad_norm": 0.7376911640167236,
      "learning_rate": 7.75e-05,
      "loss": 17.7852,
      "step": 18
    },
    {
      "epoch": 1.0857142857142856,
      "grad_norm": 0.49144265055656433,
      "learning_rate": 7.490299105985507e-05,
      "loss": 11.595,
      "step": 19
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.505672037601471,
      "learning_rate": 7.222075445642904e-05,
      "loss": 11.6319,
      "step": 20
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.6034504771232605,
      "learning_rate": 6.946477593864228e-05,
      "loss": 11.6915,
      "step": 21
    },
    {
      "epoch": 1.2571428571428571,
      "grad_norm": 0.612768292427063,
      "learning_rate": 6.664685702961344e-05,
      "loss": 11.2564,
      "step": 22
    },
    {
      "epoch": 1.3142857142857143,
      "grad_norm": 0.5627082586288452,
      "learning_rate": 6.377906449072578e-05,
      "loss": 12.2818,
      "step": 23
    },
    {
      "epoch": 1.3714285714285714,
      "grad_norm": 0.5549542903900146,
      "learning_rate": 6.087367864990233e-05,
      "loss": 11.614,
      "step": 24
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.6301306486129761,
      "learning_rate": 5.794314081535644e-05,
      "loss": 11.6534,
      "step": 25
    },
    {
      "epoch": 1.4285714285714286,
      "eval_loss": 11.692843437194824,
      "eval_runtime": 0.4171,
      "eval_samples_per_second": 119.864,
      "eval_steps_per_second": 31.165,
      "step": 25
    },
    {
      "epoch": 1.4857142857142858,
      "grad_norm": 0.6384664177894592,
      "learning_rate": 5.500000000000001e-05,
      "loss": 10.5887,
      "step": 26
    },
    {
      "epoch": 1.5428571428571427,
      "grad_norm": 0.5847898721694946,
      "learning_rate": 5.205685918464356e-05,
      "loss": 12.9826,
      "step": 27
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.5193647146224976,
      "learning_rate": 4.912632135009769e-05,
      "loss": 11.7588,
      "step": 28
    },
    {
      "epoch": 1.657142857142857,
      "grad_norm": 0.6379705667495728,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 11.7865,
      "step": 29
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.6999430656433105,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 10.8408,
      "step": 30
    },
    {
      "epoch": 1.7714285714285714,
      "grad_norm": 0.59225994348526,
      "learning_rate": 4.053522406135775e-05,
      "loss": 12.1514,
      "step": 31
    },
    {
      "epoch": 1.8285714285714287,
      "grad_norm": 0.6103184819221497,
      "learning_rate": 3.777924554357096e-05,
      "loss": 11.9794,
      "step": 32
    },
    {
      "epoch": 1.8857142857142857,
      "grad_norm": 0.6637409329414368,
      "learning_rate": 3.509700894014496e-05,
      "loss": 12.1227,
      "step": 33
    },
    {
      "epoch": 1.9428571428571428,
      "grad_norm": 0.6952071785926819,
      "learning_rate": 3.250000000000001e-05,
      "loss": 11.4498,
      "step": 34
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.0240678787231445,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 17.2048,
      "step": 35
    },
    {
      "epoch": 2.057142857142857,
      "grad_norm": 0.5756257772445679,
      "learning_rate": 2.760573569460757e-05,
      "loss": 11.6984,
      "step": 36
    },
    {
      "epoch": 2.1142857142857143,
      "grad_norm": 0.5698725581169128,
      "learning_rate": 2.53294383204969e-05,
      "loss": 11.7011,
      "step": 37
    },
    {
      "epoch": 2.1714285714285713,
      "grad_norm": 0.6899914145469666,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 11.6889,
      "step": 38
    },
    {
      "epoch": 2.2285714285714286,
      "grad_norm": 0.7464070320129395,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 11.6845,
      "step": 39
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.6132884621620178,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 11.6976,
      "step": 40
    },
    {
      "epoch": 2.342857142857143,
      "grad_norm": 0.5735512375831604,
      "learning_rate": 1.758386744638546e-05,
      "loss": 11.6943,
      "step": 41
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.6627440452575684,
      "learning_rate": 1.602885682970026e-05,
      "loss": 11.6889,
      "step": 42
    },
    {
      "epoch": 2.4571428571428573,
      "grad_norm": 0.7545081973075867,
      "learning_rate": 1.464072663102903e-05,
      "loss": 11.7002,
      "step": 43
    },
    {
      "epoch": 2.5142857142857142,
      "grad_norm": 0.6548402905464172,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 11.6905,
      "step": 44
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.607690155506134,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 11.6993,
      "step": 45
    },
    {
      "epoch": 2.6285714285714286,
      "grad_norm": 0.6367803812026978,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 11.6844,
      "step": 46
    },
    {
      "epoch": 2.685714285714286,
      "grad_norm": 0.7036944627761841,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 11.6783,
      "step": 47
    },
    {
      "epoch": 2.742857142857143,
      "grad_norm": 0.6986067295074463,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 11.6745,
      "step": 48
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.6702983975410461,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 11.6877,
      "step": 49
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.6647158861160278,
      "learning_rate": 1e-05,
      "loss": 11.6849,
      "step": 50
    },
    {
      "epoch": 2.857142857142857,
      "eval_loss": 11.67446517944336,
      "eval_runtime": 0.4257,
      "eval_samples_per_second": 117.444,
      "eval_steps_per_second": 30.535,
      "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": 163886137344000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}