{
  "best_metric": 11.930280685424805,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.16427104722792607,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032854209445585215,
      "grad_norm": 0.04408927634358406,
      "learning_rate": 5e-05,
      "loss": 11.9397,
      "step": 1
    },
    {
      "epoch": 0.0032854209445585215,
      "eval_loss": 11.939081192016602,
      "eval_runtime": 0.1266,
      "eval_samples_per_second": 395.099,
      "eval_steps_per_second": 102.726,
      "step": 1
    },
    {
      "epoch": 0.006570841889117043,
      "grad_norm": 0.04008512571454048,
      "learning_rate": 0.0001,
      "loss": 11.9403,
      "step": 2
    },
    {
      "epoch": 0.009856262833675565,
      "grad_norm": 0.045601632446050644,
      "learning_rate": 9.990365154573717e-05,
      "loss": 11.9385,
      "step": 3
    },
    {
      "epoch": 0.013141683778234086,
      "grad_norm": 0.04960702359676361,
      "learning_rate": 9.961501876182148e-05,
      "loss": 11.9403,
      "step": 4
    },
    {
      "epoch": 0.01642710472279261,
      "grad_norm": 0.051543205976486206,
      "learning_rate": 9.913533761814537e-05,
      "loss": 11.9386,
      "step": 5
    },
    {
      "epoch": 0.01971252566735113,
      "grad_norm": 0.06613066792488098,
      "learning_rate": 9.846666218300807e-05,
      "loss": 11.9392,
      "step": 6
    },
    {
      "epoch": 0.02299794661190965,
      "grad_norm": 0.06934976577758789,
      "learning_rate": 9.761185582727977e-05,
      "loss": 11.9411,
      "step": 7
    },
    {
      "epoch": 0.026283367556468172,
      "grad_norm": 0.08847657591104507,
      "learning_rate": 9.657457896300791e-05,
      "loss": 11.943,
      "step": 8
    },
    {
      "epoch": 0.029568788501026694,
      "grad_norm": 0.08571144938468933,
      "learning_rate": 9.535927336897098e-05,
      "loss": 11.9415,
      "step": 9
    },
    {
      "epoch": 0.03285420944558522,
      "grad_norm": 0.09028773009777069,
      "learning_rate": 9.397114317029975e-05,
      "loss": 11.9378,
      "step": 10
    },
    {
      "epoch": 0.036139630390143736,
      "grad_norm": 0.09118658304214478,
      "learning_rate": 9.241613255361455e-05,
      "loss": 11.9376,
      "step": 11
    },
    {
      "epoch": 0.03942505133470226,
      "grad_norm": 0.10126759111881256,
      "learning_rate": 9.070090031310558e-05,
      "loss": 11.9385,
      "step": 12
    },
    {
      "epoch": 0.04271047227926078,
      "grad_norm": 0.05890859290957451,
      "learning_rate": 8.883279133655399e-05,
      "loss": 11.9386,
      "step": 13
    },
    {
      "epoch": 0.0459958932238193,
      "grad_norm": 0.04999909549951553,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.9382,
      "step": 14
    },
    {
      "epoch": 0.049281314168377825,
      "grad_norm": 0.05274686962366104,
      "learning_rate": 8.467056167950311e-05,
      "loss": 11.9379,
      "step": 15
    },
    {
      "epoch": 0.052566735112936344,
      "grad_norm": 0.058122288435697556,
      "learning_rate": 8.239426430539243e-05,
      "loss": 11.9368,
      "step": 16
    },
    {
      "epoch": 0.05585215605749486,
      "grad_norm": 0.06514733284711838,
      "learning_rate": 8.000066048588211e-05,
      "loss": 11.9358,
      "step": 17
    },
    {
      "epoch": 0.05913757700205339,
      "grad_norm": 0.08202402293682098,
      "learning_rate": 7.75e-05,
      "loss": 11.9376,
      "step": 18
    },
    {
      "epoch": 0.06242299794661191,
      "grad_norm": 0.08955523371696472,
      "learning_rate": 7.490299105985507e-05,
      "loss": 11.936,
      "step": 19
    },
    {
      "epoch": 0.06570841889117043,
      "grad_norm": 0.10108736902475357,
      "learning_rate": 7.222075445642904e-05,
      "loss": 11.9365,
      "step": 20
    },
    {
      "epoch": 0.06899383983572896,
      "grad_norm": 0.1104000136256218,
      "learning_rate": 6.946477593864228e-05,
      "loss": 11.9361,
      "step": 21
    },
    {
      "epoch": 0.07227926078028747,
      "grad_norm": 0.1032886728644371,
      "learning_rate": 6.664685702961344e-05,
      "loss": 11.9372,
      "step": 22
    },
    {
      "epoch": 0.075564681724846,
      "grad_norm": 0.11523859947919846,
      "learning_rate": 6.377906449072578e-05,
      "loss": 11.9346,
      "step": 23
    },
    {
      "epoch": 0.07885010266940452,
      "grad_norm": 0.12590207159519196,
      "learning_rate": 6.087367864990233e-05,
      "loss": 11.9342,
      "step": 24
    },
    {
      "epoch": 0.08213552361396304,
      "grad_norm": 0.14144425094127655,
      "learning_rate": 5.794314081535644e-05,
      "loss": 11.9341,
      "step": 25
    },
    {
      "epoch": 0.08213552361396304,
      "eval_loss": 11.933664321899414,
      "eval_runtime": 0.1332,
      "eval_samples_per_second": 375.404,
      "eval_steps_per_second": 97.605,
      "step": 25
    },
    {
      "epoch": 0.08542094455852156,
      "grad_norm": 0.06499142199754715,
      "learning_rate": 5.500000000000001e-05,
      "loss": 11.9352,
      "step": 26
    },
    {
      "epoch": 0.08870636550308009,
      "grad_norm": 0.07195829600095749,
      "learning_rate": 5.205685918464356e-05,
      "loss": 11.9359,
      "step": 27
    },
    {
      "epoch": 0.0919917864476386,
      "grad_norm": 0.08275531977415085,
      "learning_rate": 4.912632135009769e-05,
      "loss": 11.9349,
      "step": 28
    },
    {
      "epoch": 0.09527720739219712,
      "grad_norm": 0.0864858403801918,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 11.9346,
      "step": 29
    },
    {
      "epoch": 0.09856262833675565,
      "grad_norm": 0.09011158347129822,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 11.9346,
      "step": 30
    },
    {
      "epoch": 0.10184804928131416,
      "grad_norm": 0.11460696160793304,
      "learning_rate": 4.053522406135775e-05,
      "loss": 11.9328,
      "step": 31
    },
    {
      "epoch": 0.10513347022587269,
      "grad_norm": 0.12090381234884262,
      "learning_rate": 3.777924554357096e-05,
      "loss": 11.9359,
      "step": 32
    },
    {
      "epoch": 0.10841889117043121,
      "grad_norm": 0.1383199840784073,
      "learning_rate": 3.509700894014496e-05,
      "loss": 11.9351,
      "step": 33
    },
    {
      "epoch": 0.11170431211498973,
      "grad_norm": 0.13779231905937195,
      "learning_rate": 3.250000000000001e-05,
      "loss": 11.9337,
      "step": 34
    },
    {
      "epoch": 0.11498973305954825,
      "grad_norm": 0.14960968494415283,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 11.9327,
      "step": 35
    },
    {
      "epoch": 0.11827515400410678,
      "grad_norm": 0.1385083943605423,
      "learning_rate": 2.760573569460757e-05,
      "loss": 11.9301,
      "step": 36
    },
    {
      "epoch": 0.1215605749486653,
      "grad_norm": 0.1653468757867813,
      "learning_rate": 2.53294383204969e-05,
      "loss": 11.9311,
      "step": 37
    },
    {
      "epoch": 0.12484599589322382,
      "grad_norm": 0.1065315380692482,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 11.9345,
      "step": 38
    },
    {
      "epoch": 0.12813141683778234,
      "grad_norm": 0.08866146951913834,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 11.9343,
      "step": 39
    },
    {
      "epoch": 0.13141683778234087,
      "grad_norm": 0.08867151290178299,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 11.935,
      "step": 40
    },
    {
      "epoch": 0.1347022587268994,
      "grad_norm": 0.09577291458845139,
      "learning_rate": 1.758386744638546e-05,
      "loss": 11.9363,
      "step": 41
    },
    {
      "epoch": 0.13798767967145792,
      "grad_norm": 0.10058815032243729,
      "learning_rate": 1.602885682970026e-05,
      "loss": 11.9324,
      "step": 42
    },
    {
      "epoch": 0.14127310061601642,
      "grad_norm": 0.1172858327627182,
      "learning_rate": 1.464072663102903e-05,
      "loss": 11.934,
      "step": 43
    },
    {
      "epoch": 0.14455852156057494,
      "grad_norm": 0.1324712485074997,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 11.9315,
      "step": 44
    },
    {
      "epoch": 0.14784394250513347,
      "grad_norm": 0.13862480223178864,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 11.9331,
      "step": 45
    },
    {
      "epoch": 0.151129363449692,
      "grad_norm": 0.15307292342185974,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 11.9321,
      "step": 46
    },
    {
      "epoch": 0.15441478439425052,
      "grad_norm": 0.15332862734794617,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 11.9307,
      "step": 47
    },
    {
      "epoch": 0.15770020533880905,
      "grad_norm": 0.15136313438415527,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 11.9288,
      "step": 48
    },
    {
      "epoch": 0.16098562628336754,
      "grad_norm": 0.16502180695533752,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 11.93,
      "step": 49
    },
    {
      "epoch": 0.16427104722792607,
      "grad_norm": 0.17262661457061768,
      "learning_rate": 1e-05,
      "loss": 11.9276,
      "step": 50
    },
    {
      "epoch": 0.16427104722792607,
      "eval_loss": 11.930280685424805,
      "eval_runtime": 0.1411,
      "eval_samples_per_second": 354.28,
      "eval_steps_per_second": 92.113,
      "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": 1042494259200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}