{
  "best_metric": 0.0007735264953225851,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.06422349777224742,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012844699554449485,
      "grad_norm": 0.4256947338581085,
      "learning_rate": 5e-05,
      "loss": 0.2276,
      "step": 1
    },
    {
      "epoch": 0.0012844699554449485,
      "eval_loss": 0.677666425704956,
      "eval_runtime": 4.4084,
      "eval_samples_per_second": 11.342,
      "eval_steps_per_second": 2.949,
      "step": 1
    },
    {
      "epoch": 0.002568939910889897,
      "grad_norm": 0.6038024425506592,
      "learning_rate": 0.0001,
      "loss": 0.293,
      "step": 2
    },
    {
      "epoch": 0.0038534098663348454,
      "grad_norm": 0.6201955676078796,
      "learning_rate": 9.990365154573717e-05,
      "loss": 0.293,
      "step": 3
    },
    {
      "epoch": 0.005137879821779794,
      "grad_norm": 0.5803629755973816,
      "learning_rate": 9.961501876182148e-05,
      "loss": 0.188,
      "step": 4
    },
    {
      "epoch": 0.006422349777224742,
      "grad_norm": 0.7291942834854126,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.0932,
      "step": 5
    },
    {
      "epoch": 0.007706819732669691,
      "grad_norm": 0.40918484330177307,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.0342,
      "step": 6
    },
    {
      "epoch": 0.00899128968811464,
      "grad_norm": 0.12289566546678543,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.0142,
      "step": 7
    },
    {
      "epoch": 0.010275759643559588,
      "grad_norm": 0.1680525243282318,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.008,
      "step": 8
    },
    {
      "epoch": 0.011560229599004535,
      "grad_norm": 0.1499042958021164,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.0072,
      "step": 9
    },
    {
      "epoch": 0.012844699554449484,
      "grad_norm": 0.2799448072910309,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.0068,
      "step": 10
    },
    {
      "epoch": 0.014129169509894433,
      "grad_norm": 0.133848637342453,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.004,
      "step": 11
    },
    {
      "epoch": 0.015413639465339381,
      "grad_norm": 0.1770220845937729,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.0023,
      "step": 12
    },
    {
      "epoch": 0.01669810942078433,
      "grad_norm": 0.15663890540599823,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.0092,
      "step": 13
    },
    {
      "epoch": 0.01798257937622928,
      "grad_norm": 0.10464489459991455,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0022,
      "step": 14
    },
    {
      "epoch": 0.019267049331674228,
      "grad_norm": 0.04404686391353607,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.0017,
      "step": 15
    },
    {
      "epoch": 0.020551519287119176,
      "grad_norm": 0.11664877831935883,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.0032,
      "step": 16
    },
    {
      "epoch": 0.02183598924256412,
      "grad_norm": 0.029631242156028748,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.001,
      "step": 17
    },
    {
      "epoch": 0.02312045919800907,
      "grad_norm": 0.031208191066980362,
      "learning_rate": 7.75e-05,
      "loss": 0.0008,
      "step": 18
    },
    {
      "epoch": 0.02440492915345402,
      "grad_norm": 0.012599286623299122,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.0008,
      "step": 19
    },
    {
      "epoch": 0.025689399108898968,
      "grad_norm": 0.038206346333026886,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0022,
      "step": 20
    },
    {
      "epoch": 0.026973869064343917,
      "grad_norm": 0.07825364172458649,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.001,
      "step": 21
    },
    {
      "epoch": 0.028258339019788865,
      "grad_norm": 0.032390445470809937,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.0003,
      "step": 22
    },
    {
      "epoch": 0.029542808975233814,
      "grad_norm": 0.023471064865589142,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.0007,
      "step": 23
    },
    {
      "epoch": 0.030827278930678763,
      "grad_norm": 0.09747525304555893,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.0017,
      "step": 24
    },
    {
      "epoch": 0.03211174888612371,
      "grad_norm": 0.025140415877103806,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.0009,
      "step": 25
    },
    {
      "epoch": 0.03211174888612371,
      "eval_loss": 0.0013123254757374525,
      "eval_runtime": 4.3445,
      "eval_samples_per_second": 11.509,
      "eval_steps_per_second": 2.992,
      "step": 25
    },
    {
      "epoch": 0.03339621884156866,
      "grad_norm": 0.03296463191509247,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0031,
      "step": 26
    },
    {
      "epoch": 0.03468068879701361,
      "grad_norm": 0.009304686449468136,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.0002,
      "step": 27
    },
    {
      "epoch": 0.03596515875245856,
      "grad_norm": 0.03837191313505173,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.0003,
      "step": 28
    },
    {
      "epoch": 0.03724962870790351,
      "grad_norm": 0.01317751593887806,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.0002,
      "step": 29
    },
    {
      "epoch": 0.038534098663348455,
      "grad_norm": 0.004668551497161388,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.0001,
      "step": 30
    },
    {
      "epoch": 0.039818568618793404,
      "grad_norm": 0.004472915083169937,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.0002,
      "step": 31
    },
    {
      "epoch": 0.04110303857423835,
      "grad_norm": 0.027437467128038406,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.0003,
      "step": 32
    },
    {
      "epoch": 0.042387508529683295,
      "grad_norm": 0.03394826501607895,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.0008,
      "step": 33
    },
    {
      "epoch": 0.04367197848512824,
      "grad_norm": 0.0036464990116655827,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.0001,
      "step": 34
    },
    {
      "epoch": 0.04495644844057319,
      "grad_norm": 0.00979373138397932,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.0001,
      "step": 35
    },
    {
      "epoch": 0.04624091839601814,
      "grad_norm": 0.007723589427769184,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.0001,
      "step": 36
    },
    {
      "epoch": 0.04752538835146309,
      "grad_norm": 0.004872419405728579,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.0001,
      "step": 37
    },
    {
      "epoch": 0.04880985830690804,
      "grad_norm": 0.06656903773546219,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.0026,
      "step": 38
    },
    {
      "epoch": 0.05009432826235299,
      "grad_norm": 0.005854337941855192,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.0002,
      "step": 39
    },
    {
      "epoch": 0.051378798217797936,
      "grad_norm": 0.014837726019322872,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.0003,
      "step": 40
    },
    {
      "epoch": 0.052663268173242885,
      "grad_norm": 0.02827686071395874,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.0004,
      "step": 41
    },
    {
      "epoch": 0.05394773812868783,
      "grad_norm": 0.03673672676086426,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.0003,
      "step": 42
    },
    {
      "epoch": 0.05523220808413278,
      "grad_norm": 0.028990410268306732,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.0009,
      "step": 43
    },
    {
      "epoch": 0.05651667803957773,
      "grad_norm": 0.08530328422784805,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.0005,
      "step": 44
    },
    {
      "epoch": 0.05780114799502268,
      "grad_norm": 0.014214947819709778,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.0002,
      "step": 45
    },
    {
      "epoch": 0.05908561795046763,
      "grad_norm": 0.05118153989315033,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.0017,
      "step": 46
    },
    {
      "epoch": 0.06037008790591258,
      "grad_norm": 0.004213218577206135,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.0001,
      "step": 47
    },
    {
      "epoch": 0.061654557861357526,
      "grad_norm": 0.0012244737008586526,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.0001,
      "step": 48
    },
    {
      "epoch": 0.06293902781680247,
      "grad_norm": 0.0034681984689086676,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.0001,
      "step": 49
    },
    {
      "epoch": 0.06422349777224742,
      "grad_norm": 0.02723923698067665,
      "learning_rate": 1e-05,
      "loss": 0.0006,
      "step": 50
    },
    {
      "epoch": 0.06422349777224742,
      "eval_loss": 0.0007735264953225851,
      "eval_runtime": 4.4018,
      "eval_samples_per_second": 11.359,
      "eval_steps_per_second": 2.953,
      "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": 5.969016129878753e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}