{
  "best_metric": 0.07148449122905731,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 1.5065666041275798,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0300187617260788,
      "grad_norm": 2.7021851539611816,
      "learning_rate": 5e-05,
      "loss": 0.7051,
      "step": 1
    },
    {
      "epoch": 0.0300187617260788,
      "eval_loss": 1.0643727779388428,
      "eval_runtime": 1.0349,
      "eval_samples_per_second": 48.312,
      "eval_steps_per_second": 12.561,
      "step": 1
    },
    {
      "epoch": 0.0600375234521576,
      "grad_norm": 3.3005504608154297,
      "learning_rate": 0.0001,
      "loss": 0.7091,
      "step": 2
    },
    {
      "epoch": 0.0900562851782364,
      "grad_norm": 3.4198787212371826,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.6392,
      "step": 3
    },
    {
      "epoch": 0.1200750469043152,
      "grad_norm": 2.235022783279419,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.3837,
      "step": 4
    },
    {
      "epoch": 0.150093808630394,
      "grad_norm": 2.217057466506958,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.2606,
      "step": 5
    },
    {
      "epoch": 0.1801125703564728,
      "grad_norm": 1.4608210325241089,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.1948,
      "step": 6
    },
    {
      "epoch": 0.2101313320825516,
      "grad_norm": 1.3691318035125732,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.1344,
      "step": 7
    },
    {
      "epoch": 0.2401500938086304,
      "grad_norm": 2.4961891174316406,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.1769,
      "step": 8
    },
    {
      "epoch": 0.2701688555347092,
      "grad_norm": 0.8466782569885254,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.1313,
      "step": 9
    },
    {
      "epoch": 0.300187617260788,
      "grad_norm": 0.8075828552246094,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0907,
      "step": 10
    },
    {
      "epoch": 0.3302063789868668,
      "grad_norm": 0.8902330994606018,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.0865,
      "step": 11
    },
    {
      "epoch": 0.3602251407129456,
      "grad_norm": 0.5716490745544434,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.0593,
      "step": 12
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 0.8448879718780518,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.0711,
      "step": 13
    },
    {
      "epoch": 0.4202626641651032,
      "grad_norm": 0.6287146806716919,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0876,
      "step": 14
    },
    {
      "epoch": 0.450281425891182,
      "grad_norm": 0.5882350206375122,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.088,
      "step": 15
    },
    {
      "epoch": 0.4803001876172608,
      "grad_norm": 1.1153855323791504,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.1396,
      "step": 16
    },
    {
      "epoch": 0.5103189493433395,
      "grad_norm": 1.0493085384368896,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.1456,
      "step": 17
    },
    {
      "epoch": 0.5403377110694184,
      "grad_norm": 0.5638002753257751,
      "learning_rate": 7.75e-05,
      "loss": 0.0847,
      "step": 18
    },
    {
      "epoch": 0.5703564727954972,
      "grad_norm": 0.4582909047603607,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0663,
      "step": 19
    },
    {
      "epoch": 0.600375234521576,
      "grad_norm": 0.5192967057228088,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0738,
      "step": 20
    },
    {
      "epoch": 0.6303939962476548,
      "grad_norm": 0.4521695673465729,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0564,
      "step": 21
    },
    {
      "epoch": 0.6604127579737336,
      "grad_norm": 0.5137154459953308,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0719,
      "step": 22
    },
    {
      "epoch": 0.6904315196998124,
      "grad_norm": 0.4951167404651642,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.063,
      "step": 23
    },
    {
      "epoch": 0.7204502814258912,
      "grad_norm": 0.4783044159412384,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0634,
      "step": 24
    },
    {
      "epoch": 0.7504690431519699,
      "grad_norm": 0.6463940739631653,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.1044,
      "step": 25
    },
    {
      "epoch": 0.7504690431519699,
      "eval_loss": 0.07915771007537842,
      "eval_runtime": 0.5107,
      "eval_samples_per_second": 97.907,
      "eval_steps_per_second": 25.456,
      "step": 25
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 0.343092679977417,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0684,
      "step": 26
    },
    {
      "epoch": 0.8105065666041276,
      "grad_norm": 0.4893798828125,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.0856,
      "step": 27
    },
    {
      "epoch": 0.8405253283302064,
      "grad_norm": 0.3412076532840729,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.0524,
      "step": 28
    },
    {
      "epoch": 0.8705440900562852,
      "grad_norm": 0.2977481484413147,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.0512,
      "step": 29
    },
    {
      "epoch": 0.900562851782364,
      "grad_norm": 0.46509039402008057,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0816,
      "step": 30
    },
    {
      "epoch": 0.9305816135084428,
      "grad_norm": 0.35923728346824646,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.0508,
      "step": 31
    },
    {
      "epoch": 0.9606003752345216,
      "grad_norm": 0.3046703636646271,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0554,
      "step": 32
    },
    {
      "epoch": 0.9906191369606003,
      "grad_norm": 0.5392127633094788,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.0891,
      "step": 33
    },
    {
      "epoch": 1.026266416510319,
      "grad_norm": 1.2058653831481934,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.1407,
      "step": 34
    },
    {
      "epoch": 1.0562851782363978,
      "grad_norm": 0.30028584599494934,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.0585,
      "step": 35
    },
    {
      "epoch": 1.0863039399624765,
      "grad_norm": 0.2767581045627594,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.0491,
      "step": 36
    },
    {
      "epoch": 1.1163227016885553,
      "grad_norm": 0.21375228464603424,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.038,
      "step": 37
    },
    {
      "epoch": 1.146341463414634,
      "grad_norm": 0.23358739912509918,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.0488,
      "step": 38
    },
    {
      "epoch": 1.176360225140713,
      "grad_norm": 0.27062949538230896,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.0428,
      "step": 39
    },
    {
      "epoch": 1.2063789868667918,
      "grad_norm": 0.2964523434638977,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.0477,
      "step": 40
    },
    {
      "epoch": 1.2363977485928705,
      "grad_norm": 0.4315393269062042,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.0784,
      "step": 41
    },
    {
      "epoch": 1.2664165103189493,
      "grad_norm": 0.3308286964893341,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.0739,
      "step": 42
    },
    {
      "epoch": 1.296435272045028,
      "grad_norm": 0.2603258490562439,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.0538,
      "step": 43
    },
    {
      "epoch": 1.3264540337711068,
      "grad_norm": 0.28217029571533203,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.0567,
      "step": 44
    },
    {
      "epoch": 1.3564727954971858,
      "grad_norm": 0.2887519896030426,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.0342,
      "step": 45
    },
    {
      "epoch": 1.3864915572232646,
      "grad_norm": 0.2621736526489258,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.0373,
      "step": 46
    },
    {
      "epoch": 1.4165103189493433,
      "grad_norm": 0.34490787982940674,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.0515,
      "step": 47
    },
    {
      "epoch": 1.446529080675422,
      "grad_norm": 0.253924161195755,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.0366,
      "step": 48
    },
    {
      "epoch": 1.476547842401501,
      "grad_norm": 0.3293060064315796,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.0464,
      "step": 49
    },
    {
      "epoch": 1.5065666041275798,
      "grad_norm": 0.3785974979400635,
      "learning_rate": 1e-05,
      "loss": 0.0638,
      "step": 50
    },
    {
      "epoch": 1.5065666041275798,
      "eval_loss": 0.07148449122905731,
      "eval_runtime": 0.4989,
      "eval_samples_per_second": 100.22,
      "eval_steps_per_second": 26.057,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2.95300912644096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}