{
  "best_metric": 10.3732271194458,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.0690428928972124,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013808578579442479,
      "grad_norm": 0.04430418834090233,
      "learning_rate": 5e-05,
      "loss": 10.38,
      "step": 1
    },
    {
      "epoch": 0.0013808578579442479,
      "eval_loss": 10.379789352416992,
      "eval_runtime": 5.6107,
      "eval_samples_per_second": 869.585,
      "eval_steps_per_second": 108.72,
      "step": 1
    },
    {
      "epoch": 0.0027617157158884957,
      "grad_norm": 0.038629110902547836,
      "learning_rate": 0.0001,
      "loss": 10.38,
      "step": 2
    },
    {
      "epoch": 0.0041425735738327436,
      "grad_norm": 0.038315873593091965,
      "learning_rate": 9.989294616193017e-05,
      "loss": 10.3767,
      "step": 3
    },
    {
      "epoch": 0.005523431431776991,
      "grad_norm": 0.046442147344350815,
      "learning_rate": 9.957224306869053e-05,
      "loss": 10.376,
      "step": 4
    },
    {
      "epoch": 0.006904289289721239,
      "grad_norm": 0.040845803916454315,
      "learning_rate": 9.903926402016153e-05,
      "loss": 10.3827,
      "step": 5
    },
    {
      "epoch": 0.008285147147665487,
      "grad_norm": 0.043120551854372025,
      "learning_rate": 9.829629131445342e-05,
      "loss": 10.3805,
      "step": 6
    },
    {
      "epoch": 0.009666005005609735,
      "grad_norm": 0.040485601872205734,
      "learning_rate": 9.73465064747553e-05,
      "loss": 10.3751,
      "step": 7
    },
    {
      "epoch": 0.011046862863553983,
      "grad_norm": 0.042762305587530136,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.3755,
      "step": 8
    },
    {
      "epoch": 0.01242772072149823,
      "grad_norm": 0.04394875466823578,
      "learning_rate": 9.484363707663442e-05,
      "loss": 10.3773,
      "step": 9
    },
    {
      "epoch": 0.013808578579442479,
      "grad_norm": 0.05203820392489433,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.3811,
      "step": 10
    },
    {
      "epoch": 0.015189436437386726,
      "grad_norm": 0.05413264036178589,
      "learning_rate": 9.157348061512727e-05,
      "loss": 10.3795,
      "step": 11
    },
    {
      "epoch": 0.016570294295330974,
      "grad_norm": 0.05413591116666794,
      "learning_rate": 8.966766701456177e-05,
      "loss": 10.3788,
      "step": 12
    },
    {
      "epoch": 0.017951152153275224,
      "grad_norm": 0.047628093510866165,
      "learning_rate": 8.759199037394887e-05,
      "loss": 10.3779,
      "step": 13
    },
    {
      "epoch": 0.01933201001121947,
      "grad_norm": 0.04531467705965042,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3757,
      "step": 14
    },
    {
      "epoch": 0.02071286786916372,
      "grad_norm": 0.04937678948044777,
      "learning_rate": 8.296729075500344e-05,
      "loss": 10.3807,
      "step": 15
    },
    {
      "epoch": 0.022093725727107966,
      "grad_norm": 0.04754887521266937,
      "learning_rate": 8.043807145043604e-05,
      "loss": 10.3743,
      "step": 16
    },
    {
      "epoch": 0.023474583585052215,
      "grad_norm": 0.05430467426776886,
      "learning_rate": 7.777851165098012e-05,
      "loss": 10.3782,
      "step": 17
    },
    {
      "epoch": 0.02485544144299646,
      "grad_norm": 0.04250817373394966,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.3776,
      "step": 18
    },
    {
      "epoch": 0.02623629930094071,
      "grad_norm": 0.04432254284620285,
      "learning_rate": 7.211443451095007e-05,
      "loss": 10.3703,
      "step": 19
    },
    {
      "epoch": 0.027617157158884957,
      "grad_norm": 0.04795295000076294,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3756,
      "step": 20
    },
    {
      "epoch": 0.028998015016829207,
      "grad_norm": 0.05414075031876564,
      "learning_rate": 6.607197326515808e-05,
      "loss": 10.375,
      "step": 21
    },
    {
      "epoch": 0.030378872874773453,
      "grad_norm": 0.06041138619184494,
      "learning_rate": 6.294095225512603e-05,
      "loss": 10.3773,
      "step": 22
    },
    {
      "epoch": 0.0317597307327177,
      "grad_norm": 0.05988826975226402,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 10.3734,
      "step": 23
    },
    {
      "epoch": 0.03314058859066195,
      "grad_norm": 0.07752064615488052,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 10.3771,
      "step": 24
    },
    {
      "epoch": 0.0345214464486062,
      "grad_norm": 0.07231460511684418,
      "learning_rate": 5.327015646150716e-05,
      "loss": 10.3769,
      "step": 25
    },
    {
      "epoch": 0.0345214464486062,
      "eval_loss": 10.375181198120117,
      "eval_runtime": 5.5296,
      "eval_samples_per_second": 882.34,
      "eval_steps_per_second": 110.315,
      "step": 25
    },
    {
      "epoch": 0.03590230430655045,
      "grad_norm": 0.04664011299610138,
      "learning_rate": 5e-05,
      "loss": 10.3719,
      "step": 26
    },
    {
      "epoch": 0.03728316216449469,
      "grad_norm": 0.05778327211737633,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 10.375,
      "step": 27
    },
    {
      "epoch": 0.03866402002243894,
      "grad_norm": 0.058514900505542755,
      "learning_rate": 4.347369038899744e-05,
      "loss": 10.3731,
      "step": 28
    },
    {
      "epoch": 0.04004487788038319,
      "grad_norm": 0.05111503601074219,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 10.3747,
      "step": 29
    },
    {
      "epoch": 0.04142573573832744,
      "grad_norm": 0.05608419328927994,
      "learning_rate": 3.705904774487396e-05,
      "loss": 10.3708,
      "step": 30
    },
    {
      "epoch": 0.04280659359627168,
      "grad_norm": 0.05180015042424202,
      "learning_rate": 3.392802673484193e-05,
      "loss": 10.3723,
      "step": 31
    },
    {
      "epoch": 0.04418745145421593,
      "grad_norm": 0.05850755050778389,
      "learning_rate": 3.086582838174551e-05,
      "loss": 10.3715,
      "step": 32
    },
    {
      "epoch": 0.04556830931216018,
      "grad_norm": 0.06536441296339035,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 10.3722,
      "step": 33
    },
    {
      "epoch": 0.04694916717010443,
      "grad_norm": 0.07440488785505295,
      "learning_rate": 2.500000000000001e-05,
      "loss": 10.371,
      "step": 34
    },
    {
      "epoch": 0.04833002502804867,
      "grad_norm": 0.05948636308312416,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 10.3782,
      "step": 35
    },
    {
      "epoch": 0.04971088288599292,
      "grad_norm": 0.07729078829288483,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 10.3717,
      "step": 36
    },
    {
      "epoch": 0.05109174074393717,
      "grad_norm": 0.08918135613203049,
      "learning_rate": 1.703270924499656e-05,
      "loss": 10.3685,
      "step": 37
    },
    {
      "epoch": 0.05247259860188142,
      "grad_norm": 0.07335370033979416,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 10.3754,
      "step": 38
    },
    {
      "epoch": 0.053853456459825665,
      "grad_norm": 0.06451977044343948,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 10.3683,
      "step": 39
    },
    {
      "epoch": 0.055234314317769914,
      "grad_norm": 0.060118626803159714,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 10.3729,
      "step": 40
    },
    {
      "epoch": 0.056615172175714164,
      "grad_norm": 0.07454778999090195,
      "learning_rate": 8.426519384872733e-06,
      "loss": 10.3741,
      "step": 41
    },
    {
      "epoch": 0.05799603003365841,
      "grad_norm": 0.05518777668476105,
      "learning_rate": 6.698729810778065e-06,
      "loss": 10.3729,
      "step": 42
    },
    {
      "epoch": 0.059376887891602656,
      "grad_norm": 0.07119714468717575,
      "learning_rate": 5.156362923365588e-06,
      "loss": 10.3775,
      "step": 43
    },
    {
      "epoch": 0.060757745749546906,
      "grad_norm": 0.05778723955154419,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 10.3726,
      "step": 44
    },
    {
      "epoch": 0.062138603607491155,
      "grad_norm": 0.06477804481983185,
      "learning_rate": 2.653493525244721e-06,
      "loss": 10.3738,
      "step": 45
    },
    {
      "epoch": 0.0635194614654354,
      "grad_norm": 0.05684743449091911,
      "learning_rate": 1.70370868554659e-06,
      "loss": 10.3747,
      "step": 46
    },
    {
      "epoch": 0.06490031932337965,
      "grad_norm": 0.07884101569652557,
      "learning_rate": 9.607359798384785e-07,
      "loss": 10.372,
      "step": 47
    },
    {
      "epoch": 0.0662811771813239,
      "grad_norm": 0.08536732941865921,
      "learning_rate": 4.277569313094809e-07,
      "loss": 10.3673,
      "step": 48
    },
    {
      "epoch": 0.06766203503926814,
      "grad_norm": 0.08748302608728409,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 10.3732,
      "step": 49
    },
    {
      "epoch": 0.0690428928972124,
      "grad_norm": 0.09697441756725311,
      "learning_rate": 0.0,
      "loss": 10.3802,
      "step": 50
    },
    {
      "epoch": 0.0690428928972124,
      "eval_loss": 10.3732271194458,
      "eval_runtime": 5.4793,
      "eval_samples_per_second": 890.444,
      "eval_steps_per_second": 111.328,
      "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": 42768059596800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}