{
  "best_metric": 1.4871836356178392e-05,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.11301031219098742,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022602062438197485,
      "grad_norm": 36.595455169677734,
      "learning_rate": 5e-05,
      "loss": 34.7665,
      "step": 1
    },
    {
      "epoch": 0.0022602062438197485,
      "eval_loss": 2.0630860328674316,
      "eval_runtime": 1.719,
      "eval_samples_per_second": 29.086,
      "eval_steps_per_second": 7.562,
      "step": 1
    },
    {
      "epoch": 0.004520412487639497,
      "grad_norm": 39.6614875793457,
      "learning_rate": 0.0001,
      "loss": 33.471,
      "step": 2
    },
    {
      "epoch": 0.006780618731459246,
      "grad_norm": 32.70667266845703,
      "learning_rate": 9.990365154573717e-05,
      "loss": 31.7103,
      "step": 3
    },
    {
      "epoch": 0.009040824975278994,
      "grad_norm": 36.67475891113281,
      "learning_rate": 9.961501876182148e-05,
      "loss": 25.9939,
      "step": 4
    },
    {
      "epoch": 0.011301031219098742,
      "grad_norm": 36.65296936035156,
      "learning_rate": 9.913533761814537e-05,
      "loss": 19.2306,
      "step": 5
    },
    {
      "epoch": 0.013561237462918492,
      "grad_norm": 31.071895599365234,
      "learning_rate": 9.846666218300807e-05,
      "loss": 12.5263,
      "step": 6
    },
    {
      "epoch": 0.01582144370673824,
      "grad_norm": 21.966489791870117,
      "learning_rate": 9.761185582727977e-05,
      "loss": 7.6308,
      "step": 7
    },
    {
      "epoch": 0.018081649950557988,
      "grad_norm": 16.192794799804688,
      "learning_rate": 9.657457896300791e-05,
      "loss": 4.9293,
      "step": 8
    },
    {
      "epoch": 0.020341856194377738,
      "grad_norm": 15.897909164428711,
      "learning_rate": 9.535927336897098e-05,
      "loss": 2.8646,
      "step": 9
    },
    {
      "epoch": 0.022602062438197484,
      "grad_norm": 8.273239135742188,
      "learning_rate": 9.397114317029975e-05,
      "loss": 1.566,
      "step": 10
    },
    {
      "epoch": 0.024862268682017234,
      "grad_norm": 6.1374125480651855,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.6113,
      "step": 11
    },
    {
      "epoch": 0.027122474925836984,
      "grad_norm": 2.8855037689208984,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.2869,
      "step": 12
    },
    {
      "epoch": 0.02938268116965673,
      "grad_norm": 1.617836833000183,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.2442,
      "step": 13
    },
    {
      "epoch": 0.03164288741347648,
      "grad_norm": 0.9079189896583557,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0921,
      "step": 14
    },
    {
      "epoch": 0.03390309365729623,
      "grad_norm": 0.7938075661659241,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0645,
      "step": 15
    },
    {
      "epoch": 0.036163299901115976,
      "grad_norm": 0.4913981854915619,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0119,
      "step": 16
    },
    {
      "epoch": 0.038423506144935726,
      "grad_norm": 0.8335649967193604,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.0098,
      "step": 17
    },
    {
      "epoch": 0.040683712388755476,
      "grad_norm": 1.2266008853912354,
      "learning_rate": 7.75e-05,
      "loss": 0.0091,
      "step": 18
    },
    {
      "epoch": 0.042943918632575226,
      "grad_norm": 0.26017099618911743,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0042,
      "step": 19
    },
    {
      "epoch": 0.04520412487639497,
      "grad_norm": 0.37957748770713806,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0031,
      "step": 20
    },
    {
      "epoch": 0.04746433112021472,
      "grad_norm": 0.07026153057813644,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.0014,
      "step": 21
    },
    {
      "epoch": 0.04972453736403447,
      "grad_norm": 0.02709748037159443,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0012,
      "step": 22
    },
    {
      "epoch": 0.05198474360785422,
      "grad_norm": 0.2505216896533966,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.0013,
      "step": 23
    },
    {
      "epoch": 0.05424494985167397,
      "grad_norm": 0.022128494456410408,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0007,
      "step": 24
    },
    {
      "epoch": 0.05650515609549371,
      "grad_norm": 0.019597666338086128,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0006,
      "step": 25
    },
    {
      "epoch": 0.05650515609549371,
      "eval_loss": 2.039912396867294e-05,
      "eval_runtime": 1.7431,
      "eval_samples_per_second": 28.684,
      "eval_steps_per_second": 7.458,
      "step": 25
    },
    {
      "epoch": 0.05876536233931346,
      "grad_norm": 0.014457793906331062,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0008,
      "step": 26
    },
    {
      "epoch": 0.06102556858313321,
      "grad_norm": 0.1443701684474945,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.0014,
      "step": 27
    },
    {
      "epoch": 0.06328577482695295,
      "grad_norm": 0.0193707924336195,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.0006,
      "step": 28
    },
    {
      "epoch": 0.06554598107077271,
      "grad_norm": 0.15904578566551208,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.0015,
      "step": 29
    },
    {
      "epoch": 0.06780618731459245,
      "grad_norm": 0.029126852750778198,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0007,
      "step": 30
    },
    {
      "epoch": 0.07006639355841221,
      "grad_norm": 0.021486882120370865,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.0006,
      "step": 31
    },
    {
      "epoch": 0.07232659980223195,
      "grad_norm": 0.02886809967458248,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0006,
      "step": 32
    },
    {
      "epoch": 0.0745868060460517,
      "grad_norm": 0.024365216493606567,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.0008,
      "step": 33
    },
    {
      "epoch": 0.07684701228987145,
      "grad_norm": 0.004941640887409449,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.0003,
      "step": 34
    },
    {
      "epoch": 0.0791072185336912,
      "grad_norm": 0.009240135550498962,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.0004,
      "step": 35
    },
    {
      "epoch": 0.08136742477751095,
      "grad_norm": 0.014623638242483139,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.0003,
      "step": 36
    },
    {
      "epoch": 0.0836276310213307,
      "grad_norm": 0.003545256331562996,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.0002,
      "step": 37
    },
    {
      "epoch": 0.08588783726515045,
      "grad_norm": 0.3244648277759552,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.1677,
      "step": 38
    },
    {
      "epoch": 0.0881480435089702,
      "grad_norm": 1.182705283164978,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.0106,
      "step": 39
    },
    {
      "epoch": 0.09040824975278994,
      "grad_norm": 1.5810155868530273,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.0373,
      "step": 40
    },
    {
      "epoch": 0.0926684559966097,
      "grad_norm": 1.5483887195587158,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.1527,
      "step": 41
    },
    {
      "epoch": 0.09492866224042944,
      "grad_norm": 0.06926979124546051,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.0006,
      "step": 42
    },
    {
      "epoch": 0.0971888684842492,
      "grad_norm": 0.02940315008163452,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.0005,
      "step": 43
    },
    {
      "epoch": 0.09944907472806894,
      "grad_norm": 0.025981120765209198,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.0008,
      "step": 44
    },
    {
      "epoch": 0.10170928097188868,
      "grad_norm": 0.05548268184065819,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.0006,
      "step": 45
    },
    {
      "epoch": 0.10396948721570844,
      "grad_norm": 0.017940428107976913,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.0003,
      "step": 46
    },
    {
      "epoch": 0.10622969345952818,
      "grad_norm": 0.0061012692749500275,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.0003,
      "step": 47
    },
    {
      "epoch": 0.10848989970334794,
      "grad_norm": 0.0036830762401223183,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.0002,
      "step": 48
    },
    {
      "epoch": 0.11075010594716768,
      "grad_norm": 0.006693420931696892,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.0002,
      "step": 49
    },
    {
      "epoch": 0.11301031219098742,
      "grad_norm": 0.008400761522352695,
      "learning_rate": 1e-05,
      "loss": 0.0003,
      "step": 50
    },
    {
      "epoch": 0.11301031219098742,
      "eval_loss": 1.4871836356178392e-05,
      "eval_runtime": 1.7601,
      "eval_samples_per_second": 28.407,
      "eval_steps_per_second": 7.386,
      "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": 5.259156315439104e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}