{
  "best_metric": 3.968430519104004,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.129680661371373,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00259361322742746,
      "grad_norm": 1.902022361755371,
      "learning_rate": 5e-05,
      "loss": 4.6741,
      "step": 1
    },
    {
      "epoch": 0.00259361322742746,
      "eval_loss": 6.233793258666992,
      "eval_runtime": 4.1532,
      "eval_samples_per_second": 12.039,
      "eval_steps_per_second": 3.13,
      "step": 1
    },
    {
      "epoch": 0.00518722645485492,
      "grad_norm": 2.0263686180114746,
      "learning_rate": 0.0001,
      "loss": 4.9183,
      "step": 2
    },
    {
      "epoch": 0.007780839682282379,
      "grad_norm": 2.203455924987793,
      "learning_rate": 9.990365154573717e-05,
      "loss": 5.0213,
      "step": 3
    },
    {
      "epoch": 0.01037445290970984,
      "grad_norm": 2.6399178504943848,
      "learning_rate": 9.961501876182148e-05,
      "loss": 4.893,
      "step": 4
    },
    {
      "epoch": 0.0129680661371373,
      "grad_norm": 2.767346143722534,
      "learning_rate": 9.913533761814537e-05,
      "loss": 4.662,
      "step": 5
    },
    {
      "epoch": 0.015561679364564759,
      "grad_norm": 2.5981667041778564,
      "learning_rate": 9.846666218300807e-05,
      "loss": 4.5425,
      "step": 6
    },
    {
      "epoch": 0.01815529259199222,
      "grad_norm": 2.883164405822754,
      "learning_rate": 9.761185582727977e-05,
      "loss": 4.3674,
      "step": 7
    },
    {
      "epoch": 0.02074890581941968,
      "grad_norm": 2.9204041957855225,
      "learning_rate": 9.657457896300791e-05,
      "loss": 4.3619,
      "step": 8
    },
    {
      "epoch": 0.02334251904684714,
      "grad_norm": 2.609384059906006,
      "learning_rate": 9.535927336897098e-05,
      "loss": 4.2608,
      "step": 9
    },
    {
      "epoch": 0.0259361322742746,
      "grad_norm": 1.9416592121124268,
      "learning_rate": 9.397114317029975e-05,
      "loss": 4.1495,
      "step": 10
    },
    {
      "epoch": 0.028529745501702057,
      "grad_norm": 2.2332334518432617,
      "learning_rate": 9.241613255361455e-05,
      "loss": 4.1326,
      "step": 11
    },
    {
      "epoch": 0.031123358729129517,
      "grad_norm": 3.553846597671509,
      "learning_rate": 9.070090031310558e-05,
      "loss": 4.0793,
      "step": 12
    },
    {
      "epoch": 0.03371697195655698,
      "grad_norm": 4.239763259887695,
      "learning_rate": 8.883279133655399e-05,
      "loss": 4.2095,
      "step": 13
    },
    {
      "epoch": 0.03631058518398444,
      "grad_norm": 4.549452304840088,
      "learning_rate": 8.681980515339464e-05,
      "loss": 4.1556,
      "step": 14
    },
    {
      "epoch": 0.0389041984114119,
      "grad_norm": 3.1622366905212402,
      "learning_rate": 8.467056167950311e-05,
      "loss": 4.0014,
      "step": 15
    },
    {
      "epoch": 0.04149781163883936,
      "grad_norm": 2.73994517326355,
      "learning_rate": 8.239426430539243e-05,
      "loss": 3.9156,
      "step": 16
    },
    {
      "epoch": 0.04409142486626682,
      "grad_norm": 1.9007859230041504,
      "learning_rate": 8.000066048588211e-05,
      "loss": 3.9051,
      "step": 17
    },
    {
      "epoch": 0.04668503809369428,
      "grad_norm": 1.6103969812393188,
      "learning_rate": 7.75e-05,
      "loss": 4.0154,
      "step": 18
    },
    {
      "epoch": 0.04927865132112174,
      "grad_norm": 1.9297362565994263,
      "learning_rate": 7.490299105985507e-05,
      "loss": 3.8945,
      "step": 19
    },
    {
      "epoch": 0.0518722645485492,
      "grad_norm": 2.2431869506835938,
      "learning_rate": 7.222075445642904e-05,
      "loss": 4.0675,
      "step": 20
    },
    {
      "epoch": 0.05446587777597666,
      "grad_norm": 2.006739854812622,
      "learning_rate": 6.946477593864228e-05,
      "loss": 3.967,
      "step": 21
    },
    {
      "epoch": 0.057059491003404114,
      "grad_norm": 1.811024785041809,
      "learning_rate": 6.664685702961344e-05,
      "loss": 3.9877,
      "step": 22
    },
    {
      "epoch": 0.059653104230831575,
      "grad_norm": 1.7786964178085327,
      "learning_rate": 6.377906449072578e-05,
      "loss": 4.0813,
      "step": 23
    },
    {
      "epoch": 0.062246717458259035,
      "grad_norm": 1.8203603029251099,
      "learning_rate": 6.087367864990233e-05,
      "loss": 4.073,
      "step": 24
    },
    {
      "epoch": 0.0648403306856865,
      "grad_norm": 3.903754949569702,
      "learning_rate": 5.794314081535644e-05,
      "loss": 4.0649,
      "step": 25
    },
    {
      "epoch": 0.0648403306856865,
      "eval_loss": 4.0869059562683105,
      "eval_runtime": 3.8019,
      "eval_samples_per_second": 13.151,
      "eval_steps_per_second": 3.419,
      "step": 25
    },
    {
      "epoch": 0.06743394391311396,
      "grad_norm": 3.166818141937256,
      "learning_rate": 5.500000000000001e-05,
      "loss": 3.9683,
      "step": 26
    },
    {
      "epoch": 0.07002755714054142,
      "grad_norm": 3.9245522022247314,
      "learning_rate": 5.205685918464356e-05,
      "loss": 4.0797,
      "step": 27
    },
    {
      "epoch": 0.07262117036796888,
      "grad_norm": 4.480504512786865,
      "learning_rate": 4.912632135009769e-05,
      "loss": 4.0345,
      "step": 28
    },
    {
      "epoch": 0.07521478359539634,
      "grad_norm": 4.088141918182373,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 4.1171,
      "step": 29
    },
    {
      "epoch": 0.0778083968228238,
      "grad_norm": 3.5814590454101562,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 3.9815,
      "step": 30
    },
    {
      "epoch": 0.08040201005025126,
      "grad_norm": 2.991044282913208,
      "learning_rate": 4.053522406135775e-05,
      "loss": 3.9307,
      "step": 31
    },
    {
      "epoch": 0.08299562327767872,
      "grad_norm": 2.4383318424224854,
      "learning_rate": 3.777924554357096e-05,
      "loss": 3.9331,
      "step": 32
    },
    {
      "epoch": 0.08558923650510618,
      "grad_norm": 2.0898032188415527,
      "learning_rate": 3.509700894014496e-05,
      "loss": 3.9062,
      "step": 33
    },
    {
      "epoch": 0.08818284973253364,
      "grad_norm": 1.9938257932662964,
      "learning_rate": 3.250000000000001e-05,
      "loss": 3.9457,
      "step": 34
    },
    {
      "epoch": 0.0907764629599611,
      "grad_norm": 1.678131341934204,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 3.9616,
      "step": 35
    },
    {
      "epoch": 0.09337007618738856,
      "grad_norm": 2.003936767578125,
      "learning_rate": 2.760573569460757e-05,
      "loss": 4.1226,
      "step": 36
    },
    {
      "epoch": 0.09596368941481602,
      "grad_norm": 2.3786985874176025,
      "learning_rate": 2.53294383204969e-05,
      "loss": 3.9693,
      "step": 37
    },
    {
      "epoch": 0.09855730264224348,
      "grad_norm": 1.0126866102218628,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 3.7566,
      "step": 38
    },
    {
      "epoch": 0.10115091586967094,
      "grad_norm": 1.0450958013534546,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 3.7173,
      "step": 39
    },
    {
      "epoch": 0.1037445290970984,
      "grad_norm": 0.9659586548805237,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 3.7651,
      "step": 40
    },
    {
      "epoch": 0.10633814232452586,
      "grad_norm": 0.9066281914710999,
      "learning_rate": 1.758386744638546e-05,
      "loss": 3.6723,
      "step": 41
    },
    {
      "epoch": 0.10893175555195332,
      "grad_norm": 0.8197788000106812,
      "learning_rate": 1.602885682970026e-05,
      "loss": 3.7228,
      "step": 42
    },
    {
      "epoch": 0.11152536877938077,
      "grad_norm": 0.8055732250213623,
      "learning_rate": 1.464072663102903e-05,
      "loss": 3.8006,
      "step": 43
    },
    {
      "epoch": 0.11411898200680823,
      "grad_norm": 0.9053921699523926,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 3.9203,
      "step": 44
    },
    {
      "epoch": 0.11671259523423569,
      "grad_norm": 1.1126152276992798,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 3.8764,
      "step": 45
    },
    {
      "epoch": 0.11930620846166315,
      "grad_norm": 1.1534708738327026,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 3.872,
      "step": 46
    },
    {
      "epoch": 0.12189982168909061,
      "grad_norm": 1.4054807424545288,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 4.0488,
      "step": 47
    },
    {
      "epoch": 0.12449343491651807,
      "grad_norm": 1.6983075141906738,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 3.9535,
      "step": 48
    },
    {
      "epoch": 0.12708704814394553,
      "grad_norm": 2.652462959289551,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 4.0065,
      "step": 49
    },
    {
      "epoch": 0.129680661371373,
      "grad_norm": 6.116709232330322,
      "learning_rate": 1e-05,
      "loss": 4.2401,
      "step": 50
    },
    {
      "epoch": 0.129680661371373,
      "eval_loss": 3.968430519104004,
      "eval_runtime": 3.7754,
      "eval_samples_per_second": 13.244,
      "eval_steps_per_second": 3.443,
      "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": 5.968086838542336e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}