{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 74.17102966841186,
  "eval_steps": 500,
  "global_step": 42500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8726003490401396,
      "grad_norm": 0.931673526763916,
      "learning_rate": 0.0009956369982547994,
      "loss": 2.6507,
      "step": 500
    },
    {
      "epoch": 1.7452006980802792,
      "grad_norm": 1.8975260257720947,
      "learning_rate": 0.0009912739965095986,
      "loss": 1.6969,
      "step": 1000
    },
    {
      "epoch": 2.6178010471204187,
      "grad_norm": 0.5923702120780945,
      "learning_rate": 0.000986910994764398,
      "loss": 1.287,
      "step": 1500
    },
    {
      "epoch": 3.4904013961605584,
      "grad_norm": 0.79058438539505,
      "learning_rate": 0.000982547993019197,
      "loss": 0.9398,
      "step": 2000
    },
    {
      "epoch": 4.363001745200698,
      "grad_norm": 0.7330807447433472,
      "learning_rate": 0.0009781849912739965,
      "loss": 0.6968,
      "step": 2500
    },
    {
      "epoch": 5.2356020942408374,
      "grad_norm": 0.6996338963508606,
      "learning_rate": 0.0009738219895287959,
      "loss": 0.4816,
      "step": 3000
    },
    {
      "epoch": 6.108202443280978,
      "grad_norm": 0.5383062362670898,
      "learning_rate": 0.0009694589877835951,
      "loss": 0.3189,
      "step": 3500
    },
    {
      "epoch": 6.980802792321117,
      "grad_norm": 0.6486771106719971,
      "learning_rate": 0.0009650959860383944,
      "loss": 0.2218,
      "step": 4000
    },
    {
      "epoch": 7.853403141361256,
      "grad_norm": 0.507366955280304,
      "learning_rate": 0.0009607329842931938,
      "loss": 0.1542,
      "step": 4500
    },
    {
      "epoch": 8.726003490401396,
      "grad_norm": 0.8452386260032654,
      "learning_rate": 0.000956369982547993,
      "loss": 0.1285,
      "step": 5000
    },
    {
      "epoch": 9.598603839441536,
      "grad_norm": 0.43142977356910706,
      "learning_rate": 0.0009520069808027923,
      "loss": 0.1175,
      "step": 5500
    },
    {
      "epoch": 10.471204188481675,
      "grad_norm": 0.2331060916185379,
      "learning_rate": 0.0009476439790575916,
      "loss": 0.1053,
      "step": 6000
    },
    {
      "epoch": 11.343804537521814,
      "grad_norm": 0.4272315800189972,
      "learning_rate": 0.000943280977312391,
      "loss": 0.092,
      "step": 6500
    },
    {
      "epoch": 12.216404886561955,
      "grad_norm": 0.2999955117702484,
      "learning_rate": 0.0009389179755671902,
      "loss": 0.0878,
      "step": 7000
    },
    {
      "epoch": 13.089005235602095,
      "grad_norm": 2.55757474899292,
      "learning_rate": 0.0009345549738219895,
      "loss": 0.0884,
      "step": 7500
    },
    {
      "epoch": 13.961605584642234,
      "grad_norm": 0.33913654088974,
      "learning_rate": 0.0009301919720767889,
      "loss": 0.0805,
      "step": 8000
    },
    {
      "epoch": 14.834205933682373,
      "grad_norm": 0.3642922341823578,
      "learning_rate": 0.0009258289703315882,
      "loss": 0.0721,
      "step": 8500
    },
    {
      "epoch": 15.706806282722512,
      "grad_norm": 0.7718423008918762,
      "learning_rate": 0.0009214659685863874,
      "loss": 0.0687,
      "step": 9000
    },
    {
      "epoch": 16.57940663176265,
      "grad_norm": 0.5820666551589966,
      "learning_rate": 0.0009171029668411868,
      "loss": 0.0644,
      "step": 9500
    },
    {
      "epoch": 17.452006980802793,
      "grad_norm": 0.2773011028766632,
      "learning_rate": 0.000912739965095986,
      "loss": 0.0598,
      "step": 10000
    },
    {
      "epoch": 18.324607329842934,
      "grad_norm": 0.25250518321990967,
      "learning_rate": 0.0009083769633507853,
      "loss": 0.0653,
      "step": 10500
    },
    {
      "epoch": 19.19720767888307,
      "grad_norm": 0.24120768904685974,
      "learning_rate": 0.0009040139616055847,
      "loss": 0.0632,
      "step": 11000
    },
    {
      "epoch": 20.069808027923212,
      "grad_norm": 0.2897244989871979,
      "learning_rate": 0.0008996509598603839,
      "loss": 0.0594,
      "step": 11500
    },
    {
      "epoch": 20.94240837696335,
      "grad_norm": 0.25145065784454346,
      "learning_rate": 0.0008952879581151833,
      "loss": 0.0556,
      "step": 12000
    },
    {
      "epoch": 21.81500872600349,
      "grad_norm": 0.27175939083099365,
      "learning_rate": 0.0008909249563699826,
      "loss": 0.0481,
      "step": 12500
    },
    {
      "epoch": 22.68760907504363,
      "grad_norm": 0.8626015782356262,
      "learning_rate": 0.0008865619546247818,
      "loss": 0.0466,
      "step": 13000
    },
    {
      "epoch": 23.56020942408377,
      "grad_norm": 0.18672889471054077,
      "learning_rate": 0.0008821989528795812,
      "loss": 0.0512,
      "step": 13500
    },
    {
      "epoch": 24.43280977312391,
      "grad_norm": 0.2387542873620987,
      "learning_rate": 0.0008778359511343804,
      "loss": 0.0512,
      "step": 14000
    },
    {
      "epoch": 25.305410122164048,
      "grad_norm": 0.2665075957775116,
      "learning_rate": 0.0008734729493891797,
      "loss": 0.0483,
      "step": 14500
    },
    {
      "epoch": 26.17801047120419,
      "grad_norm": 0.16715960204601288,
      "learning_rate": 0.0008691099476439791,
      "loss": 0.0441,
      "step": 15000
    },
    {
      "epoch": 27.050610820244327,
      "grad_norm": 0.1875993311405182,
      "learning_rate": 0.0008647469458987784,
      "loss": 0.0397,
      "step": 15500
    },
    {
      "epoch": 27.923211169284468,
      "grad_norm": 0.25451162457466125,
      "learning_rate": 0.0008603839441535776,
      "loss": 0.039,
      "step": 16000
    },
    {
      "epoch": 28.79581151832461,
      "grad_norm": 0.307054728269577,
      "learning_rate": 0.000856020942408377,
      "loss": 0.0443,
      "step": 16500
    },
    {
      "epoch": 29.668411867364746,
      "grad_norm": 0.2467741221189499,
      "learning_rate": 0.0008516579406631763,
      "loss": 0.038,
      "step": 17000
    },
    {
      "epoch": 30.541012216404887,
      "grad_norm": 0.23178012669086456,
      "learning_rate": 0.0008472949389179755,
      "loss": 0.0351,
      "step": 17500
    },
    {
      "epoch": 31.413612565445025,
      "grad_norm": 0.35061487555503845,
      "learning_rate": 0.0008429319371727748,
      "loss": 0.0323,
      "step": 18000
    },
    {
      "epoch": 32.28621291448517,
      "grad_norm": 0.3363337218761444,
      "learning_rate": 0.0008385689354275742,
      "loss": 0.038,
      "step": 18500
    },
    {
      "epoch": 33.1588132635253,
      "grad_norm": 0.24015972018241882,
      "learning_rate": 0.0008342059336823735,
      "loss": 0.0361,
      "step": 19000
    },
    {
      "epoch": 34.031413612565444,
      "grad_norm": 0.5147364735603333,
      "learning_rate": 0.0008298429319371727,
      "loss": 0.0318,
      "step": 19500
    },
    {
      "epoch": 34.904013961605585,
      "grad_norm": 0.17477251589298248,
      "learning_rate": 0.0008254799301919721,
      "loss": 0.0307,
      "step": 20000
    },
    {
      "epoch": 35.776614310645726,
      "grad_norm": 0.2511900067329407,
      "learning_rate": 0.0008211169284467714,
      "loss": 0.0348,
      "step": 20500
    },
    {
      "epoch": 36.64921465968587,
      "grad_norm": 0.2036200314760208,
      "learning_rate": 0.0008167539267015707,
      "loss": 0.0298,
      "step": 21000
    },
    {
      "epoch": 37.521815008726,
      "grad_norm": 0.16981545090675354,
      "learning_rate": 0.00081239092495637,
      "loss": 0.0319,
      "step": 21500
    },
    {
      "epoch": 38.39441535776614,
      "grad_norm": 0.22329097986221313,
      "learning_rate": 0.0008080279232111692,
      "loss": 0.0359,
      "step": 22000
    },
    {
      "epoch": 39.26701570680628,
      "grad_norm": 0.13258185982704163,
      "learning_rate": 0.0008036649214659686,
      "loss": 0.0266,
      "step": 22500
    },
    {
      "epoch": 40.139616055846425,
      "grad_norm": 0.12790647149085999,
      "learning_rate": 0.000799301919720768,
      "loss": 0.026,
      "step": 23000
    },
    {
      "epoch": 41.01221640488656,
      "grad_norm": 0.23635344207286835,
      "learning_rate": 0.0007949389179755671,
      "loss": 0.0279,
      "step": 23500
    },
    {
      "epoch": 41.8848167539267,
      "grad_norm": 0.11364254355430603,
      "learning_rate": 0.0007905759162303665,
      "loss": 0.0257,
      "step": 24000
    },
    {
      "epoch": 42.75741710296684,
      "grad_norm": 0.2781168520450592,
      "learning_rate": 0.0007862129144851659,
      "loss": 0.0295,
      "step": 24500
    },
    {
      "epoch": 43.63001745200698,
      "grad_norm": 0.106789730489254,
      "learning_rate": 0.0007818499127399651,
      "loss": 0.0308,
      "step": 25000
    },
    {
      "epoch": 44.50261780104712,
      "grad_norm": 0.16404911875724792,
      "learning_rate": 0.0007774869109947644,
      "loss": 0.0222,
      "step": 25500
    },
    {
      "epoch": 45.37521815008726,
      "grad_norm": 0.14249293506145477,
      "learning_rate": 0.0007731239092495637,
      "loss": 0.0225,
      "step": 26000
    },
    {
      "epoch": 46.2478184991274,
      "grad_norm": 0.1853444129228592,
      "learning_rate": 0.0007687609075043631,
      "loss": 0.0261,
      "step": 26500
    },
    {
      "epoch": 47.12041884816754,
      "grad_norm": 0.1456003040075302,
      "learning_rate": 0.0007643979057591623,
      "loss": 0.0252,
      "step": 27000
    },
    {
      "epoch": 47.99301919720768,
      "grad_norm": 0.16386698186397552,
      "learning_rate": 0.0007600349040139616,
      "loss": 0.0259,
      "step": 27500
    },
    {
      "epoch": 48.86561954624782,
      "grad_norm": 0.12221992015838623,
      "learning_rate": 0.000755671902268761,
      "loss": 0.0253,
      "step": 28000
    },
    {
      "epoch": 49.738219895287955,
      "grad_norm": 0.14093224704265594,
      "learning_rate": 0.0007513089005235602,
      "loss": 0.0203,
      "step": 28500
    },
    {
      "epoch": 50.610820244328096,
      "grad_norm": 0.1189383938908577,
      "learning_rate": 0.0007469458987783595,
      "loss": 0.0207,
      "step": 29000
    },
    {
      "epoch": 51.48342059336824,
      "grad_norm": 0.1471104919910431,
      "learning_rate": 0.0007425828970331589,
      "loss": 0.0209,
      "step": 29500
    },
    {
      "epoch": 52.35602094240838,
      "grad_norm": 0.08947575837373734,
      "learning_rate": 0.0007382198952879581,
      "loss": 0.0234,
      "step": 30000
    },
    {
      "epoch": 53.22862129144852,
      "grad_norm": 0.18746259808540344,
      "learning_rate": 0.0007338568935427574,
      "loss": 0.0245,
      "step": 30500
    },
    {
      "epoch": 54.10122164048865,
      "grad_norm": 0.1539311408996582,
      "learning_rate": 0.0007294938917975568,
      "loss": 0.0214,
      "step": 31000
    },
    {
      "epoch": 54.973821989528794,
      "grad_norm": 0.11201947182416916,
      "learning_rate": 0.000725130890052356,
      "loss": 0.0194,
      "step": 31500
    },
    {
      "epoch": 55.846422338568935,
      "grad_norm": 0.16618479788303375,
      "learning_rate": 0.0007207678883071554,
      "loss": 0.0185,
      "step": 32000
    },
    {
      "epoch": 56.719022687609076,
      "grad_norm": 0.1569599211215973,
      "learning_rate": 0.0007164048865619547,
      "loss": 0.0234,
      "step": 32500
    },
    {
      "epoch": 57.59162303664922,
      "grad_norm": 0.11062045395374298,
      "learning_rate": 0.0007120418848167539,
      "loss": 0.0187,
      "step": 33000
    },
    {
      "epoch": 58.46422338568935,
      "grad_norm": 0.1617700457572937,
      "learning_rate": 0.0007076788830715533,
      "loss": 0.0176,
      "step": 33500
    },
    {
      "epoch": 59.33682373472949,
      "grad_norm": 0.11750755459070206,
      "learning_rate": 0.0007033158813263525,
      "loss": 0.0188,
      "step": 34000
    },
    {
      "epoch": 60.20942408376963,
      "grad_norm": 0.24937282502651215,
      "learning_rate": 0.0006989528795811518,
      "loss": 0.0225,
      "step": 34500
    },
    {
      "epoch": 61.082024432809774,
      "grad_norm": 0.22410957515239716,
      "learning_rate": 0.0006945898778359512,
      "loss": 0.0192,
      "step": 35000
    },
    {
      "epoch": 61.954624781849915,
      "grad_norm": 0.18029357492923737,
      "learning_rate": 0.0006902268760907505,
      "loss": 0.0169,
      "step": 35500
    },
    {
      "epoch": 62.82722513089005,
      "grad_norm": 0.14077898859977722,
      "learning_rate": 0.0006858638743455497,
      "loss": 0.0167,
      "step": 36000
    },
    {
      "epoch": 63.69982547993019,
      "grad_norm": 0.12804169952869415,
      "learning_rate": 0.0006815008726003491,
      "loss": 0.0167,
      "step": 36500
    },
    {
      "epoch": 64.57242582897034,
      "grad_norm": 0.11356078833341599,
      "learning_rate": 0.0006771378708551484,
      "loss": 0.0183,
      "step": 37000
    },
    {
      "epoch": 65.44502617801047,
      "grad_norm": 0.07214757055044174,
      "learning_rate": 0.0006727748691099476,
      "loss": 0.0167,
      "step": 37500
    },
    {
      "epoch": 66.3176265270506,
      "grad_norm": 0.20497408509254456,
      "learning_rate": 0.0006684118673647469,
      "loss": 0.0186,
      "step": 38000
    },
    {
      "epoch": 67.19022687609075,
      "grad_norm": 0.09408937394618988,
      "learning_rate": 0.0006640488656195463,
      "loss": 0.0169,
      "step": 38500
    },
    {
      "epoch": 68.06282722513089,
      "grad_norm": 0.12423662841320038,
      "learning_rate": 0.0006596858638743456,
      "loss": 0.0179,
      "step": 39000
    },
    {
      "epoch": 68.93542757417103,
      "grad_norm": 0.4406953752040863,
      "learning_rate": 0.0006553228621291448,
      "loss": 0.019,
      "step": 39500
    },
    {
      "epoch": 69.80802792321117,
      "grad_norm": 0.11233725398778915,
      "learning_rate": 0.0006509598603839442,
      "loss": 0.0151,
      "step": 40000
    },
    {
      "epoch": 70.68062827225131,
      "grad_norm": 0.08892803639173508,
      "learning_rate": 0.0006465968586387435,
      "loss": 0.0137,
      "step": 40500
    },
    {
      "epoch": 71.55322862129145,
      "grad_norm": 0.11712398380041122,
      "learning_rate": 0.0006422338568935428,
      "loss": 0.0145,
      "step": 41000
    },
    {
      "epoch": 72.4258289703316,
      "grad_norm": 0.11560557782649994,
      "learning_rate": 0.0006378708551483421,
      "loss": 0.0181,
      "step": 41500
    },
    {
      "epoch": 73.29842931937172,
      "grad_norm": 0.10780952870845795,
      "learning_rate": 0.0006335078534031413,
      "loss": 0.0162,
      "step": 42000
    },
    {
      "epoch": 74.17102966841186,
      "grad_norm": 0.06540343165397644,
      "learning_rate": 0.0006291448516579407,
      "loss": 0.0157,
      "step": 42500
    }
  ],
  "logging_steps": 500,
  "max_steps": 114600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 200,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.392554571005952e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}