{
  "best_metric": 0.9675429463386536,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.014399107255350168,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00028798214510700334,
      "grad_norm": 0.4402148723602295,
      "learning_rate": 5e-05,
      "loss": 0.8523,
      "step": 1
    },
    {
      "epoch": 0.00028798214510700334,
      "eval_loss": 1.954984188079834,
      "eval_runtime": 867.4955,
      "eval_samples_per_second": 26.966,
      "eval_steps_per_second": 3.372,
      "step": 1
    },
    {
      "epoch": 0.0005759642902140067,
      "grad_norm": 0.42306187748908997,
      "learning_rate": 0.0001,
      "loss": 0.9454,
      "step": 2
    },
    {
      "epoch": 0.0008639464353210101,
      "grad_norm": 0.4823541045188904,
      "learning_rate": 9.989294616193017e-05,
      "loss": 0.9907,
      "step": 3
    },
    {
      "epoch": 0.0011519285804280134,
      "grad_norm": 0.3786833584308624,
      "learning_rate": 9.957224306869053e-05,
      "loss": 1.0285,
      "step": 4
    },
    {
      "epoch": 0.0014399107255350168,
      "grad_norm": 0.4701792895793915,
      "learning_rate": 9.903926402016153e-05,
      "loss": 1.1516,
      "step": 5
    },
    {
      "epoch": 0.0017278928706420203,
      "grad_norm": 0.5278692245483398,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.1892,
      "step": 6
    },
    {
      "epoch": 0.0020158750157490235,
      "grad_norm": 0.4424656927585602,
      "learning_rate": 9.73465064747553e-05,
      "loss": 1.119,
      "step": 7
    },
    {
      "epoch": 0.0023038571608560267,
      "grad_norm": 0.4306755065917969,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.1545,
      "step": 8
    },
    {
      "epoch": 0.0025918393059630304,
      "grad_norm": 0.5283858180046082,
      "learning_rate": 9.484363707663442e-05,
      "loss": 1.0925,
      "step": 9
    },
    {
      "epoch": 0.0028798214510700336,
      "grad_norm": 0.5383047461509705,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.1418,
      "step": 10
    },
    {
      "epoch": 0.003167803596177037,
      "grad_norm": 0.7130797505378723,
      "learning_rate": 9.157348061512727e-05,
      "loss": 1.1789,
      "step": 11
    },
    {
      "epoch": 0.0034557857412840405,
      "grad_norm": 0.7311781644821167,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.1646,
      "step": 12
    },
    {
      "epoch": 0.0037437678863910437,
      "grad_norm": 0.5451828241348267,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.6486,
      "step": 13
    },
    {
      "epoch": 0.004031750031498047,
      "grad_norm": 0.24554657936096191,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.6591,
      "step": 14
    },
    {
      "epoch": 0.004319732176605051,
      "grad_norm": 0.31400996446609497,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.763,
      "step": 15
    },
    {
      "epoch": 0.004607714321712053,
      "grad_norm": 0.3591472804546356,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.8131,
      "step": 16
    },
    {
      "epoch": 0.004895696466819057,
      "grad_norm": 0.38543662428855896,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.8584,
      "step": 17
    },
    {
      "epoch": 0.005183678611926061,
      "grad_norm": 0.2971915602684021,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.8013,
      "step": 18
    },
    {
      "epoch": 0.0054716607570330636,
      "grad_norm": 0.275538831949234,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.8332,
      "step": 19
    },
    {
      "epoch": 0.005759642902140067,
      "grad_norm": 0.2692081332206726,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.9509,
      "step": 20
    },
    {
      "epoch": 0.006047625047247071,
      "grad_norm": 0.2863736152648926,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.9027,
      "step": 21
    },
    {
      "epoch": 0.006335607192354074,
      "grad_norm": 0.322714626789093,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.9391,
      "step": 22
    },
    {
      "epoch": 0.006623589337461077,
      "grad_norm": 0.3566325008869171,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.0315,
      "step": 23
    },
    {
      "epoch": 0.006911571482568081,
      "grad_norm": 0.38864895701408386,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.0839,
      "step": 24
    },
    {
      "epoch": 0.007199553627675084,
      "grad_norm": 0.4408244490623474,
      "learning_rate": 5.327015646150716e-05,
      "loss": 1.0898,
      "step": 25
    },
    {
      "epoch": 0.007199553627675084,
      "eval_loss": 0.9995794296264648,
      "eval_runtime": 1314.3613,
      "eval_samples_per_second": 17.798,
      "eval_steps_per_second": 2.225,
      "step": 25
    },
    {
      "epoch": 0.0074875357727820875,
      "grad_norm": 0.1074371486902237,
      "learning_rate": 5e-05,
      "loss": 0.6208,
      "step": 26
    },
    {
      "epoch": 0.007775517917889091,
      "grad_norm": 0.13460542261600494,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.7484,
      "step": 27
    },
    {
      "epoch": 0.008063500062996094,
      "grad_norm": 0.14959374070167542,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.7917,
      "step": 28
    },
    {
      "epoch": 0.008351482208103098,
      "grad_norm": 0.18210013210773468,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.7766,
      "step": 29
    },
    {
      "epoch": 0.008639464353210101,
      "grad_norm": 0.2088140994310379,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.7724,
      "step": 30
    },
    {
      "epoch": 0.008927446498317105,
      "grad_norm": 0.21003039181232452,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.8387,
      "step": 31
    },
    {
      "epoch": 0.009215428643424107,
      "grad_norm": 0.19656838476657867,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.8587,
      "step": 32
    },
    {
      "epoch": 0.00950341078853111,
      "grad_norm": 0.22205334901809692,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.8314,
      "step": 33
    },
    {
      "epoch": 0.009791392933638114,
      "grad_norm": 0.22005382180213928,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.8041,
      "step": 34
    },
    {
      "epoch": 0.010079375078745118,
      "grad_norm": 0.2383647859096527,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.0052,
      "step": 35
    },
    {
      "epoch": 0.010367357223852122,
      "grad_norm": 0.3092731535434723,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.1196,
      "step": 36
    },
    {
      "epoch": 0.010655339368959125,
      "grad_norm": 0.39753103256225586,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.1256,
      "step": 37
    },
    {
      "epoch": 0.010943321514066127,
      "grad_norm": 0.08987879753112793,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.6193,
      "step": 38
    },
    {
      "epoch": 0.01123130365917313,
      "grad_norm": 0.11447886377573013,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.6659,
      "step": 39
    },
    {
      "epoch": 0.011519285804280134,
      "grad_norm": 0.11815035343170166,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.6756,
      "step": 40
    },
    {
      "epoch": 0.011807267949387138,
      "grad_norm": 0.15227173268795013,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.8462,
      "step": 41
    },
    {
      "epoch": 0.012095250094494142,
      "grad_norm": 0.14129722118377686,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.7612,
      "step": 42
    },
    {
      "epoch": 0.012383232239601145,
      "grad_norm": 0.16149425506591797,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.7903,
      "step": 43
    },
    {
      "epoch": 0.012671214384708147,
      "grad_norm": 0.1861640214920044,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.784,
      "step": 44
    },
    {
      "epoch": 0.012959196529815151,
      "grad_norm": 0.18323907256126404,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.8417,
      "step": 45
    },
    {
      "epoch": 0.013247178674922155,
      "grad_norm": 0.2482207715511322,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.8842,
      "step": 46
    },
    {
      "epoch": 0.013535160820029158,
      "grad_norm": 0.24446065723896027,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.8933,
      "step": 47
    },
    {
      "epoch": 0.013823142965136162,
      "grad_norm": 0.2554016709327698,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.9438,
      "step": 48
    },
    {
      "epoch": 0.014111125110243166,
      "grad_norm": 0.3131295442581177,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.9895,
      "step": 49
    },
    {
      "epoch": 0.014399107255350168,
      "grad_norm": 0.37427470088005066,
      "learning_rate": 0.0,
      "loss": 1.1602,
      "step": 50
    },
    {
      "epoch": 0.014399107255350168,
      "eval_loss": 0.9675429463386536,
      "eval_runtime": 921.6436,
      "eval_samples_per_second": 25.382,
      "eval_steps_per_second": 3.174,
      "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": 2.6947910513564058e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}