{
  "best_metric": 0.18073219060897827,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.045215621997400104,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009043124399480021,
      "grad_norm": 5.457483291625977,
      "learning_rate": 5e-05,
      "loss": 1.118,
      "step": 1
    },
    {
      "epoch": 0.0009043124399480021,
      "eval_loss": 3.656862258911133,
      "eval_runtime": 3.9691,
      "eval_samples_per_second": 12.597,
      "eval_steps_per_second": 3.275,
      "step": 1
    },
    {
      "epoch": 0.0018086248798960041,
      "grad_norm": 9.676811218261719,
      "learning_rate": 0.0001,
      "loss": 1.9065,
      "step": 2
    },
    {
      "epoch": 0.002712937319844006,
      "grad_norm": 6.939542293548584,
      "learning_rate": 9.990365154573717e-05,
      "loss": 1.8026,
      "step": 3
    },
    {
      "epoch": 0.0036172497597920083,
      "grad_norm": 4.408699035644531,
      "learning_rate": 9.961501876182148e-05,
      "loss": 1.1022,
      "step": 4
    },
    {
      "epoch": 0.00452156219974001,
      "grad_norm": 3.139526128768921,
      "learning_rate": 9.913533761814537e-05,
      "loss": 0.7039,
      "step": 5
    },
    {
      "epoch": 0.005425874639688012,
      "grad_norm": 3.6901752948760986,
      "learning_rate": 9.846666218300807e-05,
      "loss": 0.4753,
      "step": 6
    },
    {
      "epoch": 0.006330187079636014,
      "grad_norm": 4.00541353225708,
      "learning_rate": 9.761185582727977e-05,
      "loss": 0.4156,
      "step": 7
    },
    {
      "epoch": 0.007234499519584017,
      "grad_norm": 10.569222450256348,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.5245,
      "step": 8
    },
    {
      "epoch": 0.008138811959532019,
      "grad_norm": 1.3185478448867798,
      "learning_rate": 9.535927336897098e-05,
      "loss": 0.3026,
      "step": 9
    },
    {
      "epoch": 0.00904312439948002,
      "grad_norm": 3.6592326164245605,
      "learning_rate": 9.397114317029975e-05,
      "loss": 0.3811,
      "step": 10
    },
    {
      "epoch": 0.009947436839428022,
      "grad_norm": 3.1792221069335938,
      "learning_rate": 9.241613255361455e-05,
      "loss": 0.3194,
      "step": 11
    },
    {
      "epoch": 0.010851749279376025,
      "grad_norm": 1.6078685522079468,
      "learning_rate": 9.070090031310558e-05,
      "loss": 0.2317,
      "step": 12
    },
    {
      "epoch": 0.011756061719324026,
      "grad_norm": 2.7015645503997803,
      "learning_rate": 8.883279133655399e-05,
      "loss": 0.3042,
      "step": 13
    },
    {
      "epoch": 0.012660374159272028,
      "grad_norm": 3.5483405590057373,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.3244,
      "step": 14
    },
    {
      "epoch": 0.01356468659922003,
      "grad_norm": 4.097019672393799,
      "learning_rate": 8.467056167950311e-05,
      "loss": 0.3704,
      "step": 15
    },
    {
      "epoch": 0.014468999039168033,
      "grad_norm": 2.48213529586792,
      "learning_rate": 8.239426430539243e-05,
      "loss": 0.3323,
      "step": 16
    },
    {
      "epoch": 0.015373311479116034,
      "grad_norm": 1.7427242994308472,
      "learning_rate": 8.000066048588211e-05,
      "loss": 0.296,
      "step": 17
    },
    {
      "epoch": 0.016277623919064038,
      "grad_norm": 0.8796375393867493,
      "learning_rate": 7.75e-05,
      "loss": 0.2567,
      "step": 18
    },
    {
      "epoch": 0.017181936359012037,
      "grad_norm": 0.987083911895752,
      "learning_rate": 7.490299105985507e-05,
      "loss": 0.2335,
      "step": 19
    },
    {
      "epoch": 0.01808624879896004,
      "grad_norm": 0.6607208251953125,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.215,
      "step": 20
    },
    {
      "epoch": 0.018990561238908042,
      "grad_norm": 0.7064231038093567,
      "learning_rate": 6.946477593864228e-05,
      "loss": 0.2372,
      "step": 21
    },
    {
      "epoch": 0.019894873678856045,
      "grad_norm": 1.7021199464797974,
      "learning_rate": 6.664685702961344e-05,
      "loss": 0.2504,
      "step": 22
    },
    {
      "epoch": 0.020799186118804047,
      "grad_norm": 1.9892632961273193,
      "learning_rate": 6.377906449072578e-05,
      "loss": 0.2139,
      "step": 23
    },
    {
      "epoch": 0.02170349855875205,
      "grad_norm": 1.2977501153945923,
      "learning_rate": 6.087367864990233e-05,
      "loss": 0.2125,
      "step": 24
    },
    {
      "epoch": 0.022607810998700052,
      "grad_norm": 0.8224288821220398,
      "learning_rate": 5.794314081535644e-05,
      "loss": 0.2192,
      "step": 25
    },
    {
      "epoch": 0.022607810998700052,
      "eval_loss": 0.18073219060897827,
      "eval_runtime": 4.0909,
      "eval_samples_per_second": 12.222,
      "eval_steps_per_second": 3.178,
      "step": 25
    },
    {
      "epoch": 0.02351212343864805,
      "grad_norm": 0.8658391833305359,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.2303,
      "step": 26
    },
    {
      "epoch": 0.024416435878596054,
      "grad_norm": 1.3089148998260498,
      "learning_rate": 5.205685918464356e-05,
      "loss": 0.2659,
      "step": 27
    },
    {
      "epoch": 0.025320748318544056,
      "grad_norm": 1.2251063585281372,
      "learning_rate": 4.912632135009769e-05,
      "loss": 0.2603,
      "step": 28
    },
    {
      "epoch": 0.02622506075849206,
      "grad_norm": 1.0497297048568726,
      "learning_rate": 4.6220935509274235e-05,
      "loss": 0.2554,
      "step": 29
    },
    {
      "epoch": 0.02712937319844006,
      "grad_norm": 0.9416800737380981,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 0.235,
      "step": 30
    },
    {
      "epoch": 0.028033685638388064,
      "grad_norm": 0.5241763591766357,
      "learning_rate": 4.053522406135775e-05,
      "loss": 0.2213,
      "step": 31
    },
    {
      "epoch": 0.028937998078336066,
      "grad_norm": 0.44901642203330994,
      "learning_rate": 3.777924554357096e-05,
      "loss": 0.2101,
      "step": 32
    },
    {
      "epoch": 0.02984231051828407,
      "grad_norm": 0.4875888228416443,
      "learning_rate": 3.509700894014496e-05,
      "loss": 0.2119,
      "step": 33
    },
    {
      "epoch": 0.030746622958232068,
      "grad_norm": 0.7351800799369812,
      "learning_rate": 3.250000000000001e-05,
      "loss": 0.2293,
      "step": 34
    },
    {
      "epoch": 0.03165093539818007,
      "grad_norm": 1.3973286151885986,
      "learning_rate": 2.9999339514117912e-05,
      "loss": 0.2553,
      "step": 35
    },
    {
      "epoch": 0.032555247838128076,
      "grad_norm": 3.9271860122680664,
      "learning_rate": 2.760573569460757e-05,
      "loss": 0.3603,
      "step": 36
    },
    {
      "epoch": 0.033459560278076075,
      "grad_norm": 3.7809767723083496,
      "learning_rate": 2.53294383204969e-05,
      "loss": 0.3397,
      "step": 37
    },
    {
      "epoch": 0.034363872718024074,
      "grad_norm": 0.44919636845588684,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 0.1591,
      "step": 38
    },
    {
      "epoch": 0.03526818515797208,
      "grad_norm": 0.34611591696739197,
      "learning_rate": 2.1167208663446025e-05,
      "loss": 0.1738,
      "step": 39
    },
    {
      "epoch": 0.03617249759792008,
      "grad_norm": 0.40247368812561035,
      "learning_rate": 1.9299099686894423e-05,
      "loss": 0.2025,
      "step": 40
    },
    {
      "epoch": 0.037076810037868085,
      "grad_norm": 0.43827882409095764,
      "learning_rate": 1.758386744638546e-05,
      "loss": 0.2249,
      "step": 41
    },
    {
      "epoch": 0.037981122477816084,
      "grad_norm": 0.4481740891933441,
      "learning_rate": 1.602885682970026e-05,
      "loss": 0.2241,
      "step": 42
    },
    {
      "epoch": 0.03888543491776409,
      "grad_norm": 0.4621007442474365,
      "learning_rate": 1.464072663102903e-05,
      "loss": 0.2183,
      "step": 43
    },
    {
      "epoch": 0.03978974735771209,
      "grad_norm": 0.4554919898509979,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 0.2058,
      "step": 44
    },
    {
      "epoch": 0.04069405979766009,
      "grad_norm": 0.4693317115306854,
      "learning_rate": 1.2388144172720251e-05,
      "loss": 0.2045,
      "step": 45
    },
    {
      "epoch": 0.041598372237608094,
      "grad_norm": 0.4140600562095642,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 0.2187,
      "step": 46
    },
    {
      "epoch": 0.042502684677556093,
      "grad_norm": 0.43594950437545776,
      "learning_rate": 1.0864662381854632e-05,
      "loss": 0.2041,
      "step": 47
    },
    {
      "epoch": 0.0434069971175041,
      "grad_norm": 0.8684248328208923,
      "learning_rate": 1.0384981238178534e-05,
      "loss": 0.1878,
      "step": 48
    },
    {
      "epoch": 0.0443113095574521,
      "grad_norm": 1.767745018005371,
      "learning_rate": 1.0096348454262845e-05,
      "loss": 0.2154,
      "step": 49
    },
    {
      "epoch": 0.045215621997400104,
      "grad_norm": 1.667569875717163,
      "learning_rate": 1e-05,
      "loss": 0.1845,
      "step": 50
    },
    {
      "epoch": 0.045215621997400104,
      "eval_loss": 0.19976621866226196,
      "eval_runtime": 4.0333,
      "eval_samples_per_second": 12.397,
      "eval_steps_per_second": 3.223,
      "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.174479344467968e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}