{
  "best_metric": 1.2644882202148438,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.011259993244004054,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00022519986488008108,
      "grad_norm": 2.122084617614746,
      "learning_rate": 5e-05,
      "loss": 3.074,
      "step": 1
    },
    {
      "epoch": 0.00022519986488008108,
      "eval_loss": 4.716169834136963,
      "eval_runtime": 4.3744,
      "eval_samples_per_second": 11.43,
      "eval_steps_per_second": 2.972,
      "step": 1
    },
    {
      "epoch": 0.00045039972976016217,
      "grad_norm": 2.830608367919922,
      "learning_rate": 0.0001,
      "loss": 3.7294,
      "step": 2
    },
    {
      "epoch": 0.0006755995946402432,
      "grad_norm": 3.064732789993286,
      "learning_rate": 9.990365154573717e-05,
      "loss": 3.7796,
      "step": 3
    },
    {
      "epoch": 0.0009007994595203243,
      "grad_norm": 3.182643413543701,
      "learning_rate": 9.961501876182148e-05,
      "loss": 3.1952,
      "step": 4
    },
    {
      "epoch": 0.0011259993244004053,
      "grad_norm": 4.543271541595459,
      "learning_rate": 9.913533761814537e-05,
      "loss": 2.7225,
      "step": 5
    },
    {
      "epoch": 0.0013511991892804864,
      "grad_norm": 3.080681562423706,
      "learning_rate": 9.846666218300807e-05,
      "loss": 2.2662,
      "step": 6
    },
    {
      "epoch": 0.0015763990541605676,
      "grad_norm": 2.3999526500701904,
      "learning_rate": 9.761185582727977e-05,
      "loss": 2.0563,
      "step": 7
    },
    {
      "epoch": 0.0018015989190406487,
      "grad_norm": 3.0142905712127686,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.8755,
      "step": 8
    },
    {
      "epoch": 0.0020267987839207298,
      "grad_norm": 2.3593528270721436,
      "learning_rate": 9.535927336897098e-05,
      "loss": 1.8256,
      "step": 9
    },
    {
      "epoch": 0.0022519986488008107,
      "grad_norm": 3.116464138031006,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.7319,
      "step": 10
    },
    {
      "epoch": 0.002477198513680892,
      "grad_norm": 2.228400945663452,
      "learning_rate": 9.241613255361455e-05,
      "loss": 1.6228,
      "step": 11
    },
    {
      "epoch": 0.002702398378560973,
      "grad_norm": 1.6856660842895508,
      "learning_rate": 9.070090031310558e-05,
      "loss": 1.7847,
      "step": 12
    },
    {
      "epoch": 0.0029275982434410538,
      "grad_norm": 3.382547378540039,
      "learning_rate": 8.883279133655399e-05,
      "loss": 1.7837,
      "step": 13
    },
    {
      "epoch": 0.003152798108321135,
      "grad_norm": 2.6809465885162354,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.618,
      "step": 14
    },
    {
      "epoch": 0.003377997973201216,
      "grad_norm": 1.2869559526443481,
      "learning_rate": 8.467056167950311e-05,
      "loss": 1.5055,
      "step": 15
    },
    {
      "epoch": 0.0036031978380812973,
      "grad_norm": 1.0291166305541992,
      "learning_rate": 8.239426430539243e-05,
      "loss": 1.4246,
      "step": 16
    },
    {
      "epoch": 0.0038283977029613782,
      "grad_norm": 1.2066419124603271,
      "learning_rate": 8.000066048588211e-05,
      "loss": 1.4303,
      "step": 17
    },
    {
      "epoch": 0.0040535975678414595,
      "grad_norm": 1.1600651741027832,
      "learning_rate": 7.75e-05,
      "loss": 1.3399,
      "step": 18
    },
    {
      "epoch": 0.00427879743272154,
      "grad_norm": 1.2080273628234863,
      "learning_rate": 7.490299105985507e-05,
      "loss": 1.522,
      "step": 19
    },
    {
      "epoch": 0.004503997297601621,
      "grad_norm": 1.0143496990203857,
      "learning_rate": 7.222075445642904e-05,
      "loss": 1.4593,
      "step": 20
    },
    {
      "epoch": 0.004729197162481703,
      "grad_norm": 1.0247677564620972,
      "learning_rate": 6.946477593864228e-05,
      "loss": 1.4167,
      "step": 21
    },
    {
      "epoch": 0.004954397027361784,
      "grad_norm": 1.1484954357147217,
      "learning_rate": 6.664685702961344e-05,
      "loss": 1.4359,
      "step": 22
    },
    {
      "epoch": 0.0051795968922418644,
      "grad_norm": 1.0636186599731445,
      "learning_rate": 6.377906449072578e-05,
      "loss": 1.4486,
      "step": 23
    },
    {
      "epoch": 0.005404796757121946,
      "grad_norm": 0.9768655896186829,
      "learning_rate": 6.087367864990233e-05,
      "loss": 1.4177,
      "step": 24
    },
    {
      "epoch": 0.005629996622002027,
      "grad_norm": 1.5598772764205933,
      "learning_rate": 5.794314081535644e-05,
      "loss": 1.6263,
      "step": 25
    },
    {
      "epoch": 0.005629996622002027,
      "eval_loss": 1.383743166923523,
      "eval_runtime": 4.3597,
      "eval_samples_per_second": 11.469,
      "eval_steps_per_second": 2.982,
      "step": 25
    },
    {
      "epoch": 0.0058551964868821076,
      "grad_norm": 1.440894365310669,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.437,
      "step": 26
    },
    {
      "epoch": 0.006080396351762189,
      "grad_norm": 1.1735705137252808,
      "learning_rate": 5.205685918464356e-05,
      "loss": 1.3097,
      "step": 27
    },
    {
      "epoch": 0.00630559621664227,
      "grad_norm": 1.1329774856567383,
      "learning_rate": 4.912632135009769e-05,
      "loss": 1.3424,
      "step": 28
    },
    {
      "epoch": 0.006530796081522351,
      "grad_norm": 0.9169742465019226,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 1.3145,
      "step": 29
    },
    {
      "epoch": 0.006755995946402432,
      "grad_norm": 0.9972285032272339,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 1.293,
      "step": 30
    },
    {
      "epoch": 0.006981195811282513,
      "grad_norm": 0.7764326930046082,
      "learning_rate": 4.053522406135775e-05,
      "loss": 1.1881,
      "step": 31
    },
    {
      "epoch": 0.007206395676162595,
      "grad_norm": 0.9762597680091858,
      "learning_rate": 3.777924554357096e-05,
      "loss": 1.2747,
      "step": 32
    },
    {
      "epoch": 0.007431595541042675,
      "grad_norm": 0.9153839349746704,
      "learning_rate": 3.509700894014496e-05,
      "loss": 1.3023,
      "step": 33
    },
    {
      "epoch": 0.0076567954059227564,
      "grad_norm": 1.050321102142334,
      "learning_rate": 3.250000000000001e-05,
      "loss": 1.3403,
      "step": 34
    },
    {
      "epoch": 0.007881995270802838,
      "grad_norm": 1.0363044738769531,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 1.356,
      "step": 35
    },
    {
      "epoch": 0.008107195135682919,
      "grad_norm": 1.1488126516342163,
      "learning_rate": 2.760573569460757e-05,
      "loss": 1.4176,
      "step": 36
    },
    {
      "epoch": 0.008332395000563,
      "grad_norm": 1.3928390741348267,
      "learning_rate": 2.53294383204969e-05,
      "loss": 1.483,
      "step": 37
    },
    {
      "epoch": 0.00855759486544308,
      "grad_norm": 0.9444141387939453,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.2024,
      "step": 38
    },
    {
      "epoch": 0.008782794730323161,
      "grad_norm": 1.0579701662063599,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 1.2282,
      "step": 39
    },
    {
      "epoch": 0.009007994595203243,
      "grad_norm": 1.11298668384552,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 1.2977,
      "step": 40
    },
    {
      "epoch": 0.009233194460083324,
      "grad_norm": 0.9378632307052612,
      "learning_rate": 1.758386744638546e-05,
      "loss": 1.3119,
      "step": 41
    },
    {
      "epoch": 0.009458394324963405,
      "grad_norm": 0.821485161781311,
      "learning_rate": 1.602885682970026e-05,
      "loss": 1.3546,
      "step": 42
    },
    {
      "epoch": 0.009683594189843487,
      "grad_norm": 0.7577347755432129,
      "learning_rate": 1.464072663102903e-05,
      "loss": 1.3223,
      "step": 43
    },
    {
      "epoch": 0.009908794054723568,
      "grad_norm": 0.7188370823860168,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 1.266,
      "step": 44
    },
    {
      "epoch": 0.010133993919603648,
      "grad_norm": 0.7744938135147095,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 1.3402,
      "step": 45
    },
    {
      "epoch": 0.010359193784483729,
      "grad_norm": 0.6904383301734924,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 1.2561,
      "step": 46
    },
    {
      "epoch": 0.01058439364936381,
      "grad_norm": 0.9495808482170105,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 1.395,
      "step": 47
    },
    {
      "epoch": 0.010809593514243892,
      "grad_norm": 0.967199981212616,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 1.4136,
      "step": 48
    },
    {
      "epoch": 0.011034793379123973,
      "grad_norm": 1.231441855430603,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 1.4461,
      "step": 49
    },
    {
      "epoch": 0.011259993244004054,
      "grad_norm": 1.7717180252075195,
      "learning_rate": 1e-05,
      "loss": 1.4848,
      "step": 50
    },
    {
      "epoch": 0.011259993244004054,
      "eval_loss": 1.2644882202148438,
      "eval_runtime": 4.484,
      "eval_samples_per_second": 11.151,
      "eval_steps_per_second": 2.899,
      "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": 5.968083617316864e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}