{
  "best_metric": 0.8514222502708435,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.7634408602150538,
  "eval_steps": 25,
  "global_step": 71,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010752688172043012,
      "grad_norm": 2.4238014221191406,
      "learning_rate": 5e-05,
      "loss": 1.4918,
      "step": 1
    },
    {
      "epoch": 0.010752688172043012,
      "eval_loss": 1.3816931247711182,
      "eval_runtime": 2.4913,
      "eval_samples_per_second": 20.07,
      "eval_steps_per_second": 3.613,
      "step": 1
    },
    {
      "epoch": 0.021505376344086023,
      "grad_norm": 2.2297356128692627,
      "learning_rate": 0.0001,
      "loss": 1.2278,
      "step": 2
    },
    {
      "epoch": 0.03225806451612903,
      "grad_norm": 2.2073001861572266,
      "learning_rate": 9.995336531410274e-05,
      "loss": 1.3697,
      "step": 3
    },
    {
      "epoch": 0.043010752688172046,
      "grad_norm": 1.6624882221221924,
      "learning_rate": 9.981355791391891e-05,
      "loss": 1.1219,
      "step": 4
    },
    {
      "epoch": 0.053763440860215055,
      "grad_norm": 1.6604645252227783,
      "learning_rate": 9.958086757163489e-05,
      "loss": 1.1475,
      "step": 5
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 1.6998720169067383,
      "learning_rate": 9.92557765735184e-05,
      "loss": 1.0778,
      "step": 6
    },
    {
      "epoch": 0.07526881720430108,
      "grad_norm": 1.714016318321228,
      "learning_rate": 9.883895872030657e-05,
      "loss": 1.0594,
      "step": 7
    },
    {
      "epoch": 0.08602150537634409,
      "grad_norm": 1.6773078441619873,
      "learning_rate": 9.833127793065098e-05,
      "loss": 1.0144,
      "step": 8
    },
    {
      "epoch": 0.0967741935483871,
      "grad_norm": 1.657386064529419,
      "learning_rate": 9.773378645051438e-05,
      "loss": 1.0591,
      "step": 9
    },
    {
      "epoch": 0.10752688172043011,
      "grad_norm": 1.5666390657424927,
      "learning_rate": 9.70477226722302e-05,
      "loss": 1.046,
      "step": 10
    },
    {
      "epoch": 0.11827956989247312,
      "grad_norm": 1.3943883180618286,
      "learning_rate": 9.627450856774539e-05,
      "loss": 0.9919,
      "step": 11
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 1.389440655708313,
      "learning_rate": 9.541574674136633e-05,
      "loss": 1.0354,
      "step": 12
    },
    {
      "epoch": 0.13978494623655913,
      "grad_norm": 1.302047848701477,
      "learning_rate": 9.447321710811675e-05,
      "loss": 0.9882,
      "step": 13
    },
    {
      "epoch": 0.15053763440860216,
      "grad_norm": 1.1911146640777588,
      "learning_rate": 9.3448873204592e-05,
      "loss": 0.8856,
      "step": 14
    },
    {
      "epoch": 0.16129032258064516,
      "grad_norm": 1.1654369831085205,
      "learning_rate": 9.234483813995613e-05,
      "loss": 0.9539,
      "step": 15
    },
    {
      "epoch": 0.17204301075268819,
      "grad_norm": 1.4484726190567017,
      "learning_rate": 9.116340019547403e-05,
      "loss": 1.0391,
      "step": 16
    },
    {
      "epoch": 0.1827956989247312,
      "grad_norm": 1.2450820207595825,
      "learning_rate": 8.990700808169889e-05,
      "loss": 1.0139,
      "step": 17
    },
    {
      "epoch": 0.1935483870967742,
      "grad_norm": 1.2063860893249512,
      "learning_rate": 8.857826586314586e-05,
      "loss": 1.0437,
      "step": 18
    },
    {
      "epoch": 0.20430107526881722,
      "grad_norm": 1.1757769584655762,
      "learning_rate": 8.717992756097048e-05,
      "loss": 0.9011,
      "step": 19
    },
    {
      "epoch": 0.21505376344086022,
      "grad_norm": 1.050092339515686,
      "learning_rate": 8.571489144483944e-05,
      "loss": 0.8287,
      "step": 20
    },
    {
      "epoch": 0.22580645161290322,
      "grad_norm": 1.1617540121078491,
      "learning_rate": 8.418619402582402e-05,
      "loss": 0.8964,
      "step": 21
    },
    {
      "epoch": 0.23655913978494625,
      "grad_norm": 1.3131704330444336,
      "learning_rate": 8.259700376276725e-05,
      "loss": 1.0047,
      "step": 22
    },
    {
      "epoch": 0.24731182795698925,
      "grad_norm": 1.2672499418258667,
      "learning_rate": 8.095061449516903e-05,
      "loss": 0.934,
      "step": 23
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 1.506225824356079,
      "learning_rate": 7.925043861620091e-05,
      "loss": 0.9909,
      "step": 24
    },
    {
      "epoch": 0.26881720430107525,
      "grad_norm": 1.1839021444320679,
      "learning_rate": 7.75e-05,
      "loss": 0.7994,
      "step": 25
    },
    {
      "epoch": 0.26881720430107525,
      "eval_loss": 0.8984464406967163,
      "eval_runtime": 2.556,
      "eval_samples_per_second": 19.562,
      "eval_steps_per_second": 3.521,
      "step": 25
    },
    {
      "epoch": 0.27956989247311825,
      "grad_norm": 1.2005083560943604,
      "learning_rate": 7.570292669790186e-05,
      "loss": 0.8812,
      "step": 26
    },
    {
      "epoch": 0.2903225806451613,
      "grad_norm": 1.1817283630371094,
      "learning_rate": 7.386294341874989e-05,
      "loss": 0.918,
      "step": 27
    },
    {
      "epoch": 0.3010752688172043,
      "grad_norm": 1.283726453781128,
      "learning_rate": 7.198386380886765e-05,
      "loss": 0.9037,
      "step": 28
    },
    {
      "epoch": 0.3118279569892473,
      "grad_norm": 1.1192891597747803,
      "learning_rate": 7.006958254769438e-05,
      "loss": 0.8936,
      "step": 29
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 1.106978178024292,
      "learning_rate": 6.812406727546713e-05,
      "loss": 0.9516,
      "step": 30
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.1660184860229492,
      "learning_rate": 6.61513503696805e-05,
      "loss": 0.9056,
      "step": 31
    },
    {
      "epoch": 0.34408602150537637,
      "grad_norm": 1.0723466873168945,
      "learning_rate": 6.415552058736854e-05,
      "loss": 0.823,
      "step": 32
    },
    {
      "epoch": 0.3548387096774194,
      "grad_norm": 1.0570652484893799,
      "learning_rate": 6.214071459053132e-05,
      "loss": 0.8688,
      "step": 33
    },
    {
      "epoch": 0.3655913978494624,
      "grad_norm": 1.0927484035491943,
      "learning_rate": 6.0111108372271376e-05,
      "loss": 0.901,
      "step": 34
    },
    {
      "epoch": 0.3763440860215054,
      "grad_norm": 1.2289843559265137,
      "learning_rate": 5.80709086014102e-05,
      "loss": 0.9617,
      "step": 35
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 1.010915994644165,
      "learning_rate": 5.6024343903524755e-05,
      "loss": 0.7569,
      "step": 36
    },
    {
      "epoch": 0.3978494623655914,
      "grad_norm": 0.9901615381240845,
      "learning_rate": 5.397565609647525e-05,
      "loss": 0.8592,
      "step": 37
    },
    {
      "epoch": 0.40860215053763443,
      "grad_norm": 1.1046444177627563,
      "learning_rate": 5.192909139858981e-05,
      "loss": 0.7586,
      "step": 38
    },
    {
      "epoch": 0.41935483870967744,
      "grad_norm": 1.07370126247406,
      "learning_rate": 4.988889162772863e-05,
      "loss": 0.8669,
      "step": 39
    },
    {
      "epoch": 0.43010752688172044,
      "grad_norm": 1.0143686532974243,
      "learning_rate": 4.785928540946869e-05,
      "loss": 0.8277,
      "step": 40
    },
    {
      "epoch": 0.44086021505376344,
      "grad_norm": 0.9582819938659668,
      "learning_rate": 4.584447941263149e-05,
      "loss": 0.8128,
      "step": 41
    },
    {
      "epoch": 0.45161290322580644,
      "grad_norm": 1.1986384391784668,
      "learning_rate": 4.384864963031951e-05,
      "loss": 0.8032,
      "step": 42
    },
    {
      "epoch": 0.46236559139784944,
      "grad_norm": 1.00569748878479,
      "learning_rate": 4.1875932724532885e-05,
      "loss": 0.8394,
      "step": 43
    },
    {
      "epoch": 0.4731182795698925,
      "grad_norm": 1.094247817993164,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 0.7881,
      "step": 44
    },
    {
      "epoch": 0.4838709677419355,
      "grad_norm": 1.1001094579696655,
      "learning_rate": 3.8016136191132356e-05,
      "loss": 0.7501,
      "step": 45
    },
    {
      "epoch": 0.4946236559139785,
      "grad_norm": 1.1981114149093628,
      "learning_rate": 3.613705658125014e-05,
      "loss": 0.8529,
      "step": 46
    },
    {
      "epoch": 0.5053763440860215,
      "grad_norm": 1.2741680145263672,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 0.8109,
      "step": 47
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 0.9917993545532227,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.7039,
      "step": 48
    },
    {
      "epoch": 0.5268817204301075,
      "grad_norm": 0.9533838033676147,
      "learning_rate": 3.074956138379911e-05,
      "loss": 0.7464,
      "step": 49
    },
    {
      "epoch": 0.5376344086021505,
      "grad_norm": 1.1153020858764648,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 1.0776,
      "step": 50
    },
    {
      "epoch": 0.5376344086021505,
      "eval_loss": 0.8514222502708435,
      "eval_runtime": 2.5572,
      "eval_samples_per_second": 19.552,
      "eval_steps_per_second": 3.519,
      "step": 50
    },
    {
      "epoch": 0.5483870967741935,
      "grad_norm": 0.9954845309257507,
      "learning_rate": 2.740299623723276e-05,
      "loss": 0.7883,
      "step": 51
    },
    {
      "epoch": 0.5591397849462365,
      "grad_norm": 0.9178506135940552,
      "learning_rate": 2.5813805974175988e-05,
      "loss": 0.8541,
      "step": 52
    },
    {
      "epoch": 0.5698924731182796,
      "grad_norm": 1.0208925008773804,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 0.7694,
      "step": 53
    },
    {
      "epoch": 0.5806451612903226,
      "grad_norm": 1.0292917490005493,
      "learning_rate": 2.2820072439029525e-05,
      "loss": 0.8974,
      "step": 54
    },
    {
      "epoch": 0.5913978494623656,
      "grad_norm": 1.062528133392334,
      "learning_rate": 2.1421734136854156e-05,
      "loss": 0.8796,
      "step": 55
    },
    {
      "epoch": 0.6021505376344086,
      "grad_norm": 0.994775652885437,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 0.7694,
      "step": 56
    },
    {
      "epoch": 0.6129032258064516,
      "grad_norm": 0.9980999231338501,
      "learning_rate": 1.883659980452598e-05,
      "loss": 0.8256,
      "step": 57
    },
    {
      "epoch": 0.6236559139784946,
      "grad_norm": 0.891745924949646,
      "learning_rate": 1.765516186004387e-05,
      "loss": 0.7038,
      "step": 58
    },
    {
      "epoch": 0.6344086021505376,
      "grad_norm": 1.0422624349594116,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 0.8348,
      "step": 59
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 0.9354367852210999,
      "learning_rate": 1.552678289188326e-05,
      "loss": 0.7824,
      "step": 60
    },
    {
      "epoch": 0.6559139784946236,
      "grad_norm": 1.0644829273223877,
      "learning_rate": 1.4584253258633682e-05,
      "loss": 0.8215,
      "step": 61
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.8735445141792297,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 0.7796,
      "step": 62
    },
    {
      "epoch": 0.6774193548387096,
      "grad_norm": 0.9756590723991394,
      "learning_rate": 1.2952277327769804e-05,
      "loss": 0.7496,
      "step": 63
    },
    {
      "epoch": 0.6881720430107527,
      "grad_norm": 1.0405932664871216,
      "learning_rate": 1.2266213549485638e-05,
      "loss": 0.7398,
      "step": 64
    },
    {
      "epoch": 0.6989247311827957,
      "grad_norm": 1.0412120819091797,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 0.7613,
      "step": 65
    },
    {
      "epoch": 0.7096774193548387,
      "grad_norm": 1.0129188299179077,
      "learning_rate": 1.1161041279693446e-05,
      "loss": 0.8097,
      "step": 66
    },
    {
      "epoch": 0.7204301075268817,
      "grad_norm": 1.0584628582000732,
      "learning_rate": 1.074422342648161e-05,
      "loss": 0.877,
      "step": 67
    },
    {
      "epoch": 0.7311827956989247,
      "grad_norm": 1.030712366104126,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 0.8288,
      "step": 68
    },
    {
      "epoch": 0.7419354838709677,
      "grad_norm": 1.2178075313568115,
      "learning_rate": 1.0186442086081093e-05,
      "loss": 0.8672,
      "step": 69
    },
    {
      "epoch": 0.7526881720430108,
      "grad_norm": 1.0627042055130005,
      "learning_rate": 1.0046634685897261e-05,
      "loss": 0.9266,
      "step": 70
    },
    {
      "epoch": 0.7634408602150538,
      "grad_norm": 0.9612053632736206,
      "learning_rate": 1e-05,
      "loss": 0.8116,
      "step": 71
    }
  ],
  "logging_steps": 1,
  "max_steps": 71,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 2.8284068806262784e+16,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}