{
  "best_metric": 0.43726277351379395,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.02185732630256004,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004371465260512008,
      "grad_norm": 0.7138184905052185,
      "learning_rate": 5e-05,
      "loss": 0.486,
      "step": 1
    },
    {
      "epoch": 0.0004371465260512008,
      "eval_loss": 0.5118860006332397,
      "eval_runtime": 1.0334,
      "eval_samples_per_second": 48.384,
      "eval_steps_per_second": 12.58,
      "step": 1
    },
    {
      "epoch": 0.0008742930521024015,
      "grad_norm": 0.6570831537246704,
      "learning_rate": 0.0001,
      "loss": 0.4875,
      "step": 2
    },
    {
      "epoch": 0.0013114395781536024,
      "grad_norm": 0.5541381239891052,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.4766,
      "step": 3
    },
    {
      "epoch": 0.001748586104204803,
      "grad_norm": 1.4234938621520996,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.4778,
      "step": 4
    },
    {
      "epoch": 0.0021857326302560038,
      "grad_norm": 0.37663623690605164,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.4877,
      "step": 5
    },
    {
      "epoch": 0.002622879156307205,
      "grad_norm": 0.21502217650413513,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.4557,
      "step": 6
    },
    {
      "epoch": 0.0030600256823584055,
      "grad_norm": 0.19036097824573517,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.428,
      "step": 7
    },
    {
      "epoch": 0.003497172208409606,
      "grad_norm": 0.29344573616981506,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.4509,
      "step": 8
    },
    {
      "epoch": 0.003934318734460807,
      "grad_norm": 0.22489379346370697,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.459,
      "step": 9
    },
    {
      "epoch": 0.0043714652605120075,
      "grad_norm": 0.16101472079753876,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.4505,
      "step": 10
    },
    {
      "epoch": 0.004808611786563209,
      "grad_norm": 0.12483734637498856,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.4075,
      "step": 11
    },
    {
      "epoch": 0.00524575831261441,
      "grad_norm": 0.13228893280029297,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.412,
      "step": 12
    },
    {
      "epoch": 0.00568290483866561,
      "grad_norm": 0.14945045113563538,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.4078,
      "step": 13
    },
    {
      "epoch": 0.006120051364716811,
      "grad_norm": 0.18098153173923492,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.4405,
      "step": 14
    },
    {
      "epoch": 0.006557197890768012,
      "grad_norm": 0.12866996228694916,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.414,
      "step": 15
    },
    {
      "epoch": 0.006994344416819212,
      "grad_norm": 0.1270732879638672,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.4155,
      "step": 16
    },
    {
      "epoch": 0.0074314909428704135,
      "grad_norm": 0.10422370582818985,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.4153,
      "step": 17
    },
    {
      "epoch": 0.007868637468921615,
      "grad_norm": 0.1436351239681244,
      "learning_rate": 7.75e-05,
      "loss": 0.3871,
      "step": 18
    },
    {
      "epoch": 0.008305783994972815,
      "grad_norm": 0.2538048326969147,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.431,
      "step": 19
    },
    {
      "epoch": 0.008742930521024015,
      "grad_norm": 0.1760319322347641,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.4419,
      "step": 20
    },
    {
      "epoch": 0.009180077047075217,
      "grad_norm": 0.19340398907661438,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.403,
      "step": 21
    },
    {
      "epoch": 0.009617223573126417,
      "grad_norm": 0.18303807079792023,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.4495,
      "step": 22
    },
    {
      "epoch": 0.010054370099177617,
      "grad_norm": 0.153054878115654,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.4351,
      "step": 23
    },
    {
      "epoch": 0.01049151662522882,
      "grad_norm": 0.17695312201976776,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.4215,
      "step": 24
    },
    {
      "epoch": 0.01092866315128002,
      "grad_norm": 0.14918991923332214,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.4419,
      "step": 25
    },
    {
      "epoch": 0.01092866315128002,
      "eval_loss": 0.4473043382167816,
      "eval_runtime": 0.5973,
      "eval_samples_per_second": 83.71,
      "eval_steps_per_second": 21.765,
      "step": 25
    },
    {
      "epoch": 0.01136580967733122,
      "grad_norm": 0.12351560592651367,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.4167,
      "step": 26
    },
    {
      "epoch": 0.011802956203382422,
      "grad_norm": 0.1452387571334839,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.4281,
      "step": 27
    },
    {
      "epoch": 0.012240102729433622,
      "grad_norm": 0.09778492152690887,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.4602,
      "step": 28
    },
    {
      "epoch": 0.012677249255484822,
      "grad_norm": 0.13965074717998505,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.4197,
      "step": 29
    },
    {
      "epoch": 0.013114395781536024,
      "grad_norm": 0.11117494106292725,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.4266,
      "step": 30
    },
    {
      "epoch": 0.013551542307587225,
      "grad_norm": 0.1902451366186142,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.4378,
      "step": 31
    },
    {
      "epoch": 0.013988688833638425,
      "grad_norm": 0.0919874906539917,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.403,
      "step": 32
    },
    {
      "epoch": 0.014425835359689627,
      "grad_norm": 0.13868221640586853,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.4227,
      "step": 33
    },
    {
      "epoch": 0.014862981885740827,
      "grad_norm": 0.0835568979382515,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.3739,
      "step": 34
    },
    {
      "epoch": 0.015300128411792027,
      "grad_norm": 0.08689092099666595,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.3906,
      "step": 35
    },
    {
      "epoch": 0.01573727493784323,
      "grad_norm": 0.14874935150146484,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.4052,
      "step": 36
    },
    {
      "epoch": 0.016174421463894428,
      "grad_norm": 0.10629599541425705,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.4037,
      "step": 37
    },
    {
      "epoch": 0.01661156798994563,
      "grad_norm": 0.10195549577474594,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.429,
      "step": 38
    },
    {
      "epoch": 0.01704871451599683,
      "grad_norm": 0.11101008206605911,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.4121,
      "step": 39
    },
    {
      "epoch": 0.01748586104204803,
      "grad_norm": 0.086122527718544,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.4265,
      "step": 40
    },
    {
      "epoch": 0.017923007568099232,
      "grad_norm": 0.09646829962730408,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.4043,
      "step": 41
    },
    {
      "epoch": 0.018360154094150434,
      "grad_norm": 0.0811895951628685,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.383,
      "step": 42
    },
    {
      "epoch": 0.018797300620201633,
      "grad_norm": 0.11058395355939865,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.4021,
      "step": 43
    },
    {
      "epoch": 0.019234447146252834,
      "grad_norm": 0.1073421910405159,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.3988,
      "step": 44
    },
    {
      "epoch": 0.019671593672304036,
      "grad_norm": 0.10188556462526321,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.4105,
      "step": 45
    },
    {
      "epoch": 0.020108740198355235,
      "grad_norm": 0.12634286284446716,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.3868,
      "step": 46
    },
    {
      "epoch": 0.020545886724406437,
      "grad_norm": 0.10863292217254639,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.4126,
      "step": 47
    },
    {
      "epoch": 0.02098303325045764,
      "grad_norm": 0.07743315398693085,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.4153,
      "step": 48
    },
    {
      "epoch": 0.021420179776508837,
      "grad_norm": 0.08929809182882309,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.423,
      "step": 49
    },
    {
      "epoch": 0.02185732630256004,
      "grad_norm": 0.1446986198425293,
      "learning_rate": 1e-05,
      "loss": 0.4138,
      "step": 50
    },
    {
      "epoch": 0.02185732630256004,
      "eval_loss": 0.43726277351379395,
      "eval_runtime": 0.5912,
      "eval_samples_per_second": 84.58,
      "eval_steps_per_second": 21.991,
      "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": 2.95300912644096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}