{
  "best_metric": 11.931068420410156,
  "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": 0.04618837684392929,
      "learning_rate": 5e-05,
      "loss": 11.9397,
      "step": 1
    },
    {
      "epoch": 0.0032854209445585215,
      "eval_loss": 11.939081192016602,
      "eval_runtime": 0.1706,
      "eval_samples_per_second": 293.143,
      "eval_steps_per_second": 76.217,
      "step": 1
    },
    {
      "epoch": 0.006570841889117043,
      "grad_norm": 0.042119432240724564,
      "learning_rate": 0.0001,
      "loss": 11.9403,
      "step": 2
    },
    {
      "epoch": 0.009856262833675565,
      "grad_norm": 0.04711906984448433,
      "learning_rate": 9.990365154573717e-05,
      "loss": 11.9385,
      "step": 3
    },
    {
      "epoch": 0.013141683778234086,
      "grad_norm": 0.051648277789354324,
      "learning_rate": 9.961501876182148e-05,
      "loss": 11.9403,
      "step": 4
    },
    {
      "epoch": 0.01642710472279261,
      "grad_norm": 0.05331168323755264,
      "learning_rate": 9.913533761814537e-05,
      "loss": 11.9386,
      "step": 5
    },
    {
      "epoch": 0.01971252566735113,
      "grad_norm": 0.06837889552116394,
      "learning_rate": 9.846666218300807e-05,
      "loss": 11.9392,
      "step": 6
    },
    {
      "epoch": 0.02299794661190965,
      "grad_norm": 0.06661276519298553,
      "learning_rate": 9.761185582727977e-05,
      "loss": 11.9411,
      "step": 7
    },
    {
      "epoch": 0.026283367556468172,
      "grad_norm": 0.08176678419113159,
      "learning_rate": 9.657457896300791e-05,
      "loss": 11.9431,
      "step": 8
    },
    {
      "epoch": 0.029568788501026694,
      "grad_norm": 0.07902713865041733,
      "learning_rate": 9.535927336897098e-05,
      "loss": 11.9416,
      "step": 9
    },
    {
      "epoch": 0.03285420944558522,
      "grad_norm": 0.08207160234451294,
      "learning_rate": 9.397114317029975e-05,
      "loss": 11.938,
      "step": 10
    },
    {
      "epoch": 0.036139630390143736,
      "grad_norm": 0.08347855508327484,
      "learning_rate": 9.241613255361455e-05,
      "loss": 11.9378,
      "step": 11
    },
    {
      "epoch": 0.03942505133470226,
      "grad_norm": 0.09518927335739136,
      "learning_rate": 9.070090031310558e-05,
      "loss": 11.9386,
      "step": 12
    },
    {
      "epoch": 0.04271047227926078,
      "grad_norm": 0.05532950907945633,
      "learning_rate": 8.883279133655399e-05,
      "loss": 11.9387,
      "step": 13
    },
    {
      "epoch": 0.0459958932238193,
      "grad_norm": 0.04984002187848091,
      "learning_rate": 8.681980515339464e-05,
      "loss": 11.9381,
      "step": 14
    },
    {
      "epoch": 0.049281314168377825,
      "grad_norm": 0.05239202454686165,
      "learning_rate": 8.467056167950311e-05,
      "loss": 11.9379,
      "step": 15
    },
    {
      "epoch": 0.052566735112936344,
      "grad_norm": 0.05773535370826721,
      "learning_rate": 8.239426430539243e-05,
      "loss": 11.9368,
      "step": 16
    },
    {
      "epoch": 0.05585215605749486,
      "grad_norm": 0.06431864947080612,
      "learning_rate": 8.000066048588211e-05,
      "loss": 11.9357,
      "step": 17
    },
    {
      "epoch": 0.05913757700205339,
      "grad_norm": 0.08065486699342728,
      "learning_rate": 7.75e-05,
      "loss": 11.9376,
      "step": 18
    },
    {
      "epoch": 0.06242299794661191,
      "grad_norm": 0.09095431864261627,
      "learning_rate": 7.490299105985507e-05,
      "loss": 11.936,
      "step": 19
    },
    {
      "epoch": 0.06570841889117043,
      "grad_norm": 0.09189269691705704,
      "learning_rate": 7.222075445642904e-05,
      "loss": 11.9367,
      "step": 20
    },
    {
      "epoch": 0.06899383983572896,
      "grad_norm": 0.0942097082734108,
      "learning_rate": 6.946477593864228e-05,
      "loss": 11.9366,
      "step": 21
    },
    {
      "epoch": 0.07227926078028747,
      "grad_norm": 0.09040320664644241,
      "learning_rate": 6.664685702961344e-05,
      "loss": 11.9376,
      "step": 22
    },
    {
      "epoch": 0.075564681724846,
      "grad_norm": 0.09851648658514023,
      "learning_rate": 6.377906449072578e-05,
      "loss": 11.9352,
      "step": 23
    },
    {
      "epoch": 0.07885010266940452,
      "grad_norm": 0.11245869100093842,
      "learning_rate": 6.087367864990233e-05,
      "loss": 11.9347,
      "step": 24
    },
    {
      "epoch": 0.08213552361396304,
      "grad_norm": 0.12083257734775543,
      "learning_rate": 5.794314081535644e-05,
      "loss": 11.9347,
      "step": 25
    },
    {
      "epoch": 0.08213552361396304,
      "eval_loss": 11.93404769897461,
      "eval_runtime": 0.1728,
      "eval_samples_per_second": 289.278,
      "eval_steps_per_second": 75.212,
      "step": 25
    },
    {
      "epoch": 0.08542094455852156,
      "grad_norm": 0.061159469187259674,
      "learning_rate": 5.500000000000001e-05,
      "loss": 11.9353,
      "step": 26
    },
    {
      "epoch": 0.08870636550308009,
      "grad_norm": 0.0698854923248291,
      "learning_rate": 5.205685918464356e-05,
      "loss": 11.936,
      "step": 27
    },
    {
      "epoch": 0.0919917864476386,
      "grad_norm": 0.07924137264490128,
      "learning_rate": 4.912632135009769e-05,
      "loss": 11.935,
      "step": 28
    },
    {
      "epoch": 0.09527720739219712,
      "grad_norm": 0.08310386538505554,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 11.9348,
      "step": 29
    },
    {
      "epoch": 0.09856262833675565,
      "grad_norm": 0.08692660182714462,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 11.9347,
      "step": 30
    },
    {
      "epoch": 0.10184804928131416,
      "grad_norm": 0.1117107942700386,
      "learning_rate": 4.053522406135775e-05,
      "loss": 11.9329,
      "step": 31
    },
    {
      "epoch": 0.10513347022587269,
      "grad_norm": 0.10682588070631027,
      "learning_rate": 3.777924554357096e-05,
      "loss": 11.9364,
      "step": 32
    },
    {
      "epoch": 0.10841889117043121,
      "grad_norm": 0.11467161029577255,
      "learning_rate": 3.509700894014496e-05,
      "loss": 11.936,
      "step": 33
    },
    {
      "epoch": 0.11170431211498973,
      "grad_norm": 0.11791813373565674,
      "learning_rate": 3.250000000000001e-05,
      "loss": 11.9345,
      "step": 34
    },
    {
      "epoch": 0.11498973305954825,
      "grad_norm": 0.12620225548744202,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 11.9336,
      "step": 35
    },
    {
      "epoch": 0.11827515400410678,
      "grad_norm": 0.12209944427013397,
      "learning_rate": 2.760573569460757e-05,
      "loss": 11.9307,
      "step": 36
    },
    {
      "epoch": 0.1215605749486653,
      "grad_norm": 0.14005905389785767,
      "learning_rate": 2.53294383204969e-05,
      "loss": 11.932,
      "step": 37
    },
    {
      "epoch": 0.12484599589322382,
      "grad_norm": 0.0928557962179184,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 11.935,
      "step": 38
    },
    {
      "epoch": 0.12813141683778234,
      "grad_norm": 0.08085311949253082,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 11.9346,
      "step": 39
    },
    {
      "epoch": 0.13141683778234087,
      "grad_norm": 0.08359197527170181,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 11.9352,
      "step": 40
    },
    {
      "epoch": 0.1347022587268994,
      "grad_norm": 0.08855370432138443,
      "learning_rate": 1.758386744638546e-05,
      "loss": 11.9366,
      "step": 41
    },
    {
      "epoch": 0.13798767967145792,
      "grad_norm": 0.09516077488660812,
      "learning_rate": 1.602885682970026e-05,
      "loss": 11.9326,
      "step": 42
    },
    {
      "epoch": 0.14127310061601642,
      "grad_norm": 0.11417657136917114,
      "learning_rate": 1.464072663102903e-05,
      "loss": 11.9341,
      "step": 43
    },
    {
      "epoch": 0.14455852156057494,
      "grad_norm": 0.12174195796251297,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 11.9319,
      "step": 44
    },
    {
      "epoch": 0.14784394250513347,
      "grad_norm": 0.1158878356218338,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 11.934,
      "step": 45
    },
    {
      "epoch": 0.151129363449692,
      "grad_norm": 0.12922489643096924,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 11.933,
      "step": 46
    },
    {
      "epoch": 0.15441478439425052,
      "grad_norm": 0.13009999692440033,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 11.9317,
      "step": 47
    },
    {
      "epoch": 0.15770020533880905,
      "grad_norm": 0.12648075819015503,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 11.9299,
      "step": 48
    },
    {
      "epoch": 0.16098562628336754,
      "grad_norm": 0.1377834528684616,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 11.9311,
      "step": 49
    },
    {
      "epoch": 0.16427104722792607,
      "grad_norm": 0.14867839217185974,
      "learning_rate": 1e-05,
      "loss": 11.9286,
      "step": 50
    },
    {
      "epoch": 0.16427104722792607,
      "eval_loss": 11.931068420410156,
      "eval_runtime": 0.1711,
      "eval_samples_per_second": 292.261,
      "eval_steps_per_second": 75.988,
      "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
}