{
  "best_metric": 0.45144757628440857,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.015338599585857812,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003067719917171562,
      "grad_norm": 3.7495951652526855,
      "learning_rate": 7e-06,
      "loss": 1.3425,
      "step": 1
    },
    {
      "epoch": 0.0003067719917171562,
      "eval_loss": 0.5136561393737793,
      "eval_runtime": 430.5928,
      "eval_samples_per_second": 12.75,
      "eval_steps_per_second": 3.189,
      "step": 1
    },
    {
      "epoch": 0.0006135439834343124,
      "grad_norm": 4.0081987380981445,
      "learning_rate": 1.4e-05,
      "loss": 1.536,
      "step": 2
    },
    {
      "epoch": 0.0009203159751514687,
      "grad_norm": 4.015089988708496,
      "learning_rate": 2.1e-05,
      "loss": 1.6788,
      "step": 3
    },
    {
      "epoch": 0.0012270879668686248,
      "grad_norm": 3.7536773681640625,
      "learning_rate": 2.8e-05,
      "loss": 1.6255,
      "step": 4
    },
    {
      "epoch": 0.0015338599585857811,
      "grad_norm": 3.3928744792938232,
      "learning_rate": 3.5e-05,
      "loss": 1.8201,
      "step": 5
    },
    {
      "epoch": 0.0018406319503029374,
      "grad_norm": 3.9312448501586914,
      "learning_rate": 4.2e-05,
      "loss": 1.699,
      "step": 6
    },
    {
      "epoch": 0.0021474039420200934,
      "grad_norm": 4.036737442016602,
      "learning_rate": 4.899999999999999e-05,
      "loss": 1.893,
      "step": 7
    },
    {
      "epoch": 0.0024541759337372497,
      "grad_norm": 3.745652437210083,
      "learning_rate": 5.6e-05,
      "loss": 1.799,
      "step": 8
    },
    {
      "epoch": 0.002760947925454406,
      "grad_norm": 3.411588191986084,
      "learning_rate": 6.3e-05,
      "loss": 1.829,
      "step": 9
    },
    {
      "epoch": 0.0030677199171715622,
      "grad_norm": 3.5523102283477783,
      "learning_rate": 7e-05,
      "loss": 1.8915,
      "step": 10
    },
    {
      "epoch": 0.0033744919088887185,
      "grad_norm": 3.2218644618988037,
      "learning_rate": 6.999521567473641e-05,
      "loss": 1.936,
      "step": 11
    },
    {
      "epoch": 0.0036812639006058748,
      "grad_norm": 3.2266080379486084,
      "learning_rate": 6.998086400693241e-05,
      "loss": 1.7437,
      "step": 12
    },
    {
      "epoch": 0.003988035892323031,
      "grad_norm": 3.168818950653076,
      "learning_rate": 6.995694892019065e-05,
      "loss": 1.9077,
      "step": 13
    },
    {
      "epoch": 0.004294807884040187,
      "grad_norm": 3.1822073459625244,
      "learning_rate": 6.99234769526571e-05,
      "loss": 1.8901,
      "step": 14
    },
    {
      "epoch": 0.004601579875757343,
      "grad_norm": 3.098999500274658,
      "learning_rate": 6.988045725523343e-05,
      "loss": 1.8588,
      "step": 15
    },
    {
      "epoch": 0.004908351867474499,
      "grad_norm": 3.074695587158203,
      "learning_rate": 6.982790158907539e-05,
      "loss": 1.8403,
      "step": 16
    },
    {
      "epoch": 0.005215123859191656,
      "grad_norm": 3.289018154144287,
      "learning_rate": 6.976582432237733e-05,
      "loss": 2.0474,
      "step": 17
    },
    {
      "epoch": 0.005521895850908812,
      "grad_norm": 3.1470084190368652,
      "learning_rate": 6.969424242644413e-05,
      "loss": 1.774,
      "step": 18
    },
    {
      "epoch": 0.005828667842625968,
      "grad_norm": 3.417246103286743,
      "learning_rate": 6.961317547105138e-05,
      "loss": 1.9962,
      "step": 19
    },
    {
      "epoch": 0.0061354398343431244,
      "grad_norm": 3.2956278324127197,
      "learning_rate": 6.952264561909527e-05,
      "loss": 1.8747,
      "step": 20
    },
    {
      "epoch": 0.006442211826060281,
      "grad_norm": 3.1632611751556396,
      "learning_rate": 6.942267762053337e-05,
      "loss": 1.8501,
      "step": 21
    },
    {
      "epoch": 0.006748983817777437,
      "grad_norm": 3.133277416229248,
      "learning_rate": 6.931329880561832e-05,
      "loss": 1.9094,
      "step": 22
    },
    {
      "epoch": 0.007055755809494593,
      "grad_norm": 3.3376052379608154,
      "learning_rate": 6.919453907742597e-05,
      "loss": 2.1212,
      "step": 23
    },
    {
      "epoch": 0.0073625278012117495,
      "grad_norm": 3.125730276107788,
      "learning_rate": 6.90664309036802e-05,
      "loss": 1.8213,
      "step": 24
    },
    {
      "epoch": 0.007669299792928906,
      "grad_norm": 3.062613010406494,
      "learning_rate": 6.892900930787656e-05,
      "loss": 1.882,
      "step": 25
    },
    {
      "epoch": 0.007976071784646061,
      "grad_norm": 3.1579535007476807,
      "learning_rate": 6.87823118597072e-05,
      "loss": 1.8683,
      "step": 26
    },
    {
      "epoch": 0.008282843776363218,
      "grad_norm": 3.150268316268921,
      "learning_rate": 6.862637866478969e-05,
      "loss": 1.9691,
      "step": 27
    },
    {
      "epoch": 0.008589615768080374,
      "grad_norm": 3.1286489963531494,
      "learning_rate": 6.846125235370252e-05,
      "loss": 1.7716,
      "step": 28
    },
    {
      "epoch": 0.00889638775979753,
      "grad_norm": 3.434857130050659,
      "learning_rate": 6.828697807033038e-05,
      "loss": 1.8311,
      "step": 29
    },
    {
      "epoch": 0.009203159751514686,
      "grad_norm": 3.493105888366699,
      "learning_rate": 6.81036034595222e-05,
      "loss": 1.8715,
      "step": 30
    },
    {
      "epoch": 0.009509931743231843,
      "grad_norm": 3.204404354095459,
      "learning_rate": 6.791117865406564e-05,
      "loss": 1.635,
      "step": 31
    },
    {
      "epoch": 0.009816703734948999,
      "grad_norm": 3.2127530574798584,
      "learning_rate": 6.770975626098112e-05,
      "loss": 1.7038,
      "step": 32
    },
    {
      "epoch": 0.010123475726666156,
      "grad_norm": 3.0898277759552,
      "learning_rate": 6.749939134713974e-05,
      "loss": 1.5416,
      "step": 33
    },
    {
      "epoch": 0.010430247718383311,
      "grad_norm": 3.249939441680908,
      "learning_rate": 6.728014142420846e-05,
      "loss": 1.5933,
      "step": 34
    },
    {
      "epoch": 0.010737019710100468,
      "grad_norm": 3.3410327434539795,
      "learning_rate": 6.7052066432927e-05,
      "loss": 1.545,
      "step": 35
    },
    {
      "epoch": 0.011043791701817624,
      "grad_norm": 2.9800238609313965,
      "learning_rate": 6.681522872672069e-05,
      "loss": 1.4148,
      "step": 36
    },
    {
      "epoch": 0.011350563693534781,
      "grad_norm": 3.2996833324432373,
      "learning_rate": 6.656969305465356e-05,
      "loss": 1.4536,
      "step": 37
    },
    {
      "epoch": 0.011657335685251936,
      "grad_norm": 3.3368849754333496,
      "learning_rate": 6.631552654372672e-05,
      "loss": 1.5,
      "step": 38
    },
    {
      "epoch": 0.011964107676969093,
      "grad_norm": 3.478151321411133,
      "learning_rate": 6.60527986805264e-05,
      "loss": 1.5469,
      "step": 39
    },
    {
      "epoch": 0.012270879668686249,
      "grad_norm": 3.412599802017212,
      "learning_rate": 6.578158129222711e-05,
      "loss": 1.4183,
      "step": 40
    },
    {
      "epoch": 0.012577651660403406,
      "grad_norm": 3.7741832733154297,
      "learning_rate": 6.550194852695469e-05,
      "loss": 1.4992,
      "step": 41
    },
    {
      "epoch": 0.012884423652120561,
      "grad_norm": 3.9010705947875977,
      "learning_rate": 6.521397683351509e-05,
      "loss": 1.5144,
      "step": 42
    },
    {
      "epoch": 0.013191195643837717,
      "grad_norm": 4.069062232971191,
      "learning_rate": 6.491774494049386e-05,
      "loss": 1.4617,
      "step": 43
    },
    {
      "epoch": 0.013497967635554874,
      "grad_norm": 4.3247785568237305,
      "learning_rate": 6.461333383473272e-05,
      "loss": 1.6182,
      "step": 44
    },
    {
      "epoch": 0.01380473962727203,
      "grad_norm": 4.433003902435303,
      "learning_rate": 6.430082673918849e-05,
      "loss": 1.3577,
      "step": 45
    },
    {
      "epoch": 0.014111511618989186,
      "grad_norm": 4.900903224945068,
      "learning_rate": 6.398030909018069e-05,
      "loss": 1.6088,
      "step": 46
    },
    {
      "epoch": 0.014418283610706342,
      "grad_norm": 5.257229804992676,
      "learning_rate": 6.365186851403423e-05,
      "loss": 1.5353,
      "step": 47
    },
    {
      "epoch": 0.014725055602423499,
      "grad_norm": 5.429163932800293,
      "learning_rate": 6.331559480312315e-05,
      "loss": 1.322,
      "step": 48
    },
    {
      "epoch": 0.015031827594140654,
      "grad_norm": 7.3463053703308105,
      "learning_rate": 6.297157989132236e-05,
      "loss": 1.9904,
      "step": 49
    },
    {
      "epoch": 0.015338599585857812,
      "grad_norm": 22.010234832763672,
      "learning_rate": 6.261991782887377e-05,
      "loss": 1.6099,
      "step": 50
    },
    {
      "epoch": 0.015338599585857812,
      "eval_loss": 0.45144757628440857,
      "eval_runtime": 433.9082,
      "eval_samples_per_second": 12.652,
      "eval_steps_per_second": 3.164,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 4,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.405423031431987e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}