{
  "best_metric": 0.33107176423072815,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.12795905310300704,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025591810620601407,
      "grad_norm": 0.4111393988132477,
      "learning_rate": 5e-05,
      "loss": 0.412,
      "step": 1
    },
    {
      "epoch": 0.0025591810620601407,
      "eval_loss": 0.5183330178260803,
      "eval_runtime": 3.3511,
      "eval_samples_per_second": 14.92,
      "eval_steps_per_second": 3.879,
      "step": 1
    },
    {
      "epoch": 0.005118362124120281,
      "grad_norm": 0.5222029089927673,
      "learning_rate": 0.0001,
      "loss": 0.4869,
      "step": 2
    },
    {
      "epoch": 0.007677543186180422,
      "grad_norm": 0.3767395317554474,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.4539,
      "step": 3
    },
    {
      "epoch": 0.010236724248240563,
      "grad_norm": 0.6278697848320007,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.4387,
      "step": 4
    },
    {
      "epoch": 0.012795905310300703,
      "grad_norm": 0.3426453769207001,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.4136,
      "step": 5
    },
    {
      "epoch": 0.015355086372360844,
      "grad_norm": 0.31006333231925964,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.408,
      "step": 6
    },
    {
      "epoch": 0.017914267434420986,
      "grad_norm": 0.2717861533164978,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.371,
      "step": 7
    },
    {
      "epoch": 0.020473448496481125,
      "grad_norm": 0.23935860395431519,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.3897,
      "step": 8
    },
    {
      "epoch": 0.023032629558541268,
      "grad_norm": 0.23376871645450592,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.3539,
      "step": 9
    },
    {
      "epoch": 0.025591810620601407,
      "grad_norm": 0.289098858833313,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.38,
      "step": 10
    },
    {
      "epoch": 0.02815099168266155,
      "grad_norm": 0.29994460940361023,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.3643,
      "step": 11
    },
    {
      "epoch": 0.030710172744721688,
      "grad_norm": 0.22812917828559875,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.3518,
      "step": 12
    },
    {
      "epoch": 0.03326935380678183,
      "grad_norm": 0.1643439531326294,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.3452,
      "step": 13
    },
    {
      "epoch": 0.03582853486884197,
      "grad_norm": 0.19197794795036316,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.3688,
      "step": 14
    },
    {
      "epoch": 0.03838771593090211,
      "grad_norm": 0.17241746187210083,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.381,
      "step": 15
    },
    {
      "epoch": 0.04094689699296225,
      "grad_norm": 0.16896656155586243,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.3832,
      "step": 16
    },
    {
      "epoch": 0.04350607805502239,
      "grad_norm": 0.15949086844921112,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.3679,
      "step": 17
    },
    {
      "epoch": 0.046065259117082535,
      "grad_norm": 0.2003166228532791,
      "learning_rate": 7.75e-05,
      "loss": 0.3631,
      "step": 18
    },
    {
      "epoch": 0.04862444017914268,
      "grad_norm": 0.18040768802165985,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.3598,
      "step": 19
    },
    {
      "epoch": 0.05118362124120281,
      "grad_norm": 0.17178280651569366,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.3691,
      "step": 20
    },
    {
      "epoch": 0.053742802303262956,
      "grad_norm": 0.17435070872306824,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.3564,
      "step": 21
    },
    {
      "epoch": 0.0563019833653231,
      "grad_norm": 0.18055517971515656,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.3523,
      "step": 22
    },
    {
      "epoch": 0.05886116442738324,
      "grad_norm": 0.18856243789196014,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.3737,
      "step": 23
    },
    {
      "epoch": 0.061420345489443376,
      "grad_norm": 0.18847958743572235,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.356,
      "step": 24
    },
    {
      "epoch": 0.06397952655150352,
      "grad_norm": 0.2135154902935028,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.3275,
      "step": 25
    },
    {
      "epoch": 0.06397952655150352,
      "eval_loss": 0.33710530400276184,
      "eval_runtime": 3.4552,
      "eval_samples_per_second": 14.471,
      "eval_steps_per_second": 3.762,
      "step": 25
    },
    {
      "epoch": 0.06653870761356366,
      "grad_norm": 0.14013031125068665,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.34,
      "step": 26
    },
    {
      "epoch": 0.0690978886756238,
      "grad_norm": 0.1556030660867691,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.3469,
      "step": 27
    },
    {
      "epoch": 0.07165706973768395,
      "grad_norm": 0.16703511774539948,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.3745,
      "step": 28
    },
    {
      "epoch": 0.07421625079974409,
      "grad_norm": 0.1567988246679306,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.373,
      "step": 29
    },
    {
      "epoch": 0.07677543186180422,
      "grad_norm": 0.16023825109004974,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.3801,
      "step": 30
    },
    {
      "epoch": 0.07933461292386436,
      "grad_norm": 0.15885958075523376,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.3569,
      "step": 31
    },
    {
      "epoch": 0.0818937939859245,
      "grad_norm": 0.15370488166809082,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.3678,
      "step": 32
    },
    {
      "epoch": 0.08445297504798464,
      "grad_norm": 0.16905587911605835,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.3617,
      "step": 33
    },
    {
      "epoch": 0.08701215611004479,
      "grad_norm": 0.18098001182079315,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.3593,
      "step": 34
    },
    {
      "epoch": 0.08957133717210493,
      "grad_norm": 0.17493058741092682,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.3738,
      "step": 35
    },
    {
      "epoch": 0.09213051823416507,
      "grad_norm": 0.18294112384319305,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.3448,
      "step": 36
    },
    {
      "epoch": 0.09468969929622521,
      "grad_norm": 0.1955849975347519,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.3488,
      "step": 37
    },
    {
      "epoch": 0.09724888035828536,
      "grad_norm": 0.1269148886203766,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.3316,
      "step": 38
    },
    {
      "epoch": 0.09980806142034548,
      "grad_norm": 0.11683975160121918,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.3704,
      "step": 39
    },
    {
      "epoch": 0.10236724248240563,
      "grad_norm": 0.1327202469110489,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.3693,
      "step": 40
    },
    {
      "epoch": 0.10492642354446577,
      "grad_norm": 0.13617070019245148,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.3638,
      "step": 41
    },
    {
      "epoch": 0.10748560460652591,
      "grad_norm": 0.1420089602470398,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.3789,
      "step": 42
    },
    {
      "epoch": 0.11004478566858605,
      "grad_norm": 0.13661804795265198,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.3617,
      "step": 43
    },
    {
      "epoch": 0.1126039667306462,
      "grad_norm": 0.18816272914409637,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.3645,
      "step": 44
    },
    {
      "epoch": 0.11516314779270634,
      "grad_norm": 0.1535802036523819,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.3545,
      "step": 45
    },
    {
      "epoch": 0.11772232885476648,
      "grad_norm": 0.15371079742908478,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.3251,
      "step": 46
    },
    {
      "epoch": 0.12028150991682661,
      "grad_norm": 0.1656692773103714,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.3545,
      "step": 47
    },
    {
      "epoch": 0.12284069097888675,
      "grad_norm": 0.17977501451969147,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.3567,
      "step": 48
    },
    {
      "epoch": 0.1253998720409469,
      "grad_norm": 0.17077907919883728,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.3524,
      "step": 49
    },
    {
      "epoch": 0.12795905310300704,
      "grad_norm": 0.19544556736946106,
      "learning_rate": 1e-05,
      "loss": 0.3457,
      "step": 50
    },
    {
      "epoch": 0.12795905310300704,
      "eval_loss": 0.33107176423072815,
      "eval_runtime": 3.4346,
      "eval_samples_per_second": 14.558,
      "eval_steps_per_second": 3.785,
      "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": 6.674900178991841e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}