{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 12.698412698412698,
  "eval_steps": 500,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15873015873015872,
      "grad_norm": 0.42645490169525146,
      "learning_rate": 4.999720254525684e-05,
      "loss": 1.3067,
      "num_input_tokens_seen": 269280,
      "step": 10
    },
    {
      "epoch": 0.31746031746031744,
      "grad_norm": 0.10797163844108582,
      "learning_rate": 4.9987533135093934e-05,
      "loss": 0.2064,
      "num_input_tokens_seen": 536656,
      "step": 20
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.10832954943180084,
      "learning_rate": 4.997095990396411e-05,
      "loss": 0.2025,
      "num_input_tokens_seen": 804720,
      "step": 30
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 0.11103782057762146,
      "learning_rate": 4.994748743089566e-05,
      "loss": 0.2011,
      "num_input_tokens_seen": 1073520,
      "step": 40
    },
    {
      "epoch": 0.7936507936507936,
      "grad_norm": 0.09958792477846146,
      "learning_rate": 4.9917122201112656e-05,
      "loss": 0.2028,
      "num_input_tokens_seen": 1341184,
      "step": 50
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.6581681370735168,
      "learning_rate": 4.9879872604243184e-05,
      "loss": 0.1993,
      "num_input_tokens_seen": 1609968,
      "step": 60
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.2799030542373657,
      "learning_rate": 4.983574893200139e-05,
      "loss": 0.1979,
      "num_input_tokens_seen": 1878240,
      "step": 70
    },
    {
      "epoch": 1.2698412698412698,
      "grad_norm": 0.17586013674736023,
      "learning_rate": 4.978476337534393e-05,
      "loss": 0.1931,
      "num_input_tokens_seen": 2146528,
      "step": 80
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.24899278581142426,
      "learning_rate": 4.972693002110176e-05,
      "loss": 0.1931,
      "num_input_tokens_seen": 2415696,
      "step": 90
    },
    {
      "epoch": 1.5873015873015874,
      "grad_norm": 0.16181747615337372,
      "learning_rate": 4.9662264848088034e-05,
      "loss": 0.192,
      "num_input_tokens_seen": 2683600,
      "step": 100
    },
    {
      "epoch": 1.746031746031746,
      "grad_norm": 0.18402352929115295,
      "learning_rate": 4.959078572268337e-05,
      "loss": 0.1874,
      "num_input_tokens_seen": 2950720,
      "step": 110
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.2943824827671051,
      "learning_rate": 4.951251239389948e-05,
      "loss": 0.1871,
      "num_input_tokens_seen": 3219792,
      "step": 120
    },
    {
      "epoch": 2.0634920634920633,
      "grad_norm": 0.18450967967510223,
      "learning_rate": 4.942746648792274e-05,
      "loss": 0.1887,
      "num_input_tokens_seen": 3488400,
      "step": 130
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.2516356408596039,
      "learning_rate": 4.9335671502139024e-05,
      "loss": 0.1876,
      "num_input_tokens_seen": 3757952,
      "step": 140
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.23607608675956726,
      "learning_rate": 4.9237152798641696e-05,
      "loss": 0.1843,
      "num_input_tokens_seen": 4025536,
      "step": 150
    },
    {
      "epoch": 2.5396825396825395,
      "grad_norm": 0.1812293380498886,
      "learning_rate": 4.9131937597224185e-05,
      "loss": 0.1791,
      "num_input_tokens_seen": 4294240,
      "step": 160
    },
    {
      "epoch": 2.6984126984126986,
      "grad_norm": 0.1874535083770752,
      "learning_rate": 4.902005496785951e-05,
      "loss": 0.1851,
      "num_input_tokens_seen": 4563376,
      "step": 170
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.25721630454063416,
      "learning_rate": 4.8901535822668446e-05,
      "loss": 0.1836,
      "num_input_tokens_seen": 4831168,
      "step": 180
    },
    {
      "epoch": 3.015873015873016,
      "grad_norm": 0.22797122597694397,
      "learning_rate": 4.877641290737884e-05,
      "loss": 0.1834,
      "num_input_tokens_seen": 5098496,
      "step": 190
    },
    {
      "epoch": 3.1746031746031744,
      "grad_norm": 0.16337507963180542,
      "learning_rate": 4.8644720792278264e-05,
      "loss": 0.186,
      "num_input_tokens_seen": 5368864,
      "step": 200
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.17769697308540344,
      "learning_rate": 4.850649586266255e-05,
      "loss": 0.1803,
      "num_input_tokens_seen": 5637456,
      "step": 210
    },
    {
      "epoch": 3.492063492063492,
      "grad_norm": 0.2481444925069809,
      "learning_rate": 4.836177630878289e-05,
      "loss": 0.1798,
      "num_input_tokens_seen": 5905104,
      "step": 220
    },
    {
      "epoch": 3.6507936507936507,
      "grad_norm": 0.22745923697948456,
      "learning_rate": 4.821060211529424e-05,
      "loss": 0.1815,
      "num_input_tokens_seen": 6174032,
      "step": 230
    },
    {
      "epoch": 3.8095238095238093,
      "grad_norm": 0.16727988421916962,
      "learning_rate": 4.8053015050207915e-05,
      "loss": 0.1811,
      "num_input_tokens_seen": 6442896,
      "step": 240
    },
    {
      "epoch": 3.9682539682539684,
      "grad_norm": 0.3471706807613373,
      "learning_rate": 4.7889058653351485e-05,
      "loss": 0.1795,
      "num_input_tokens_seen": 6710352,
      "step": 250
    },
    {
      "epoch": 4.1269841269841265,
      "grad_norm": 0.23989547789096832,
      "learning_rate": 4.771877822433911e-05,
      "loss": 0.1769,
      "num_input_tokens_seen": 6977744,
      "step": 260
    },
    {
      "epoch": 4.285714285714286,
      "grad_norm": 0.23704519867897034,
      "learning_rate": 4.754222081005574e-05,
      "loss": 0.174,
      "num_input_tokens_seen": 7246272,
      "step": 270
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.2272966355085373,
      "learning_rate": 4.7359435191658425e-05,
      "loss": 0.1716,
      "num_input_tokens_seen": 7512592,
      "step": 280
    },
    {
      "epoch": 4.603174603174603,
      "grad_norm": 0.23121878504753113,
      "learning_rate": 4.717047187109861e-05,
      "loss": 0.1804,
      "num_input_tokens_seen": 7780144,
      "step": 290
    },
    {
      "epoch": 4.761904761904762,
      "grad_norm": 0.31674066185951233,
      "learning_rate": 4.697538305716885e-05,
      "loss": 0.1784,
      "num_input_tokens_seen": 8049392,
      "step": 300
    },
    {
      "epoch": 4.920634920634921,
      "grad_norm": 0.2399132400751114,
      "learning_rate": 4.6774222651078106e-05,
      "loss": 0.1796,
      "num_input_tokens_seen": 8316912,
      "step": 310
    },
    {
      "epoch": 5.079365079365079,
      "grad_norm": 0.2677905261516571,
      "learning_rate": 4.656704623155922e-05,
      "loss": 0.1736,
      "num_input_tokens_seen": 8586544,
      "step": 320
    },
    {
      "epoch": 5.238095238095238,
      "grad_norm": 0.33959662914276123,
      "learning_rate": 4.6353911039513145e-05,
      "loss": 0.1766,
      "num_input_tokens_seen": 8855680,
      "step": 330
    },
    {
      "epoch": 5.396825396825397,
      "grad_norm": 0.26891693472862244,
      "learning_rate": 4.613487596219376e-05,
      "loss": 0.1724,
      "num_input_tokens_seen": 9123808,
      "step": 340
    },
    {
      "epoch": 5.555555555555555,
      "grad_norm": 0.2796987295150757,
      "learning_rate": 4.591000151693789e-05,
      "loss": 0.1721,
      "num_input_tokens_seen": 9392560,
      "step": 350
    },
    {
      "epoch": 5.714285714285714,
      "grad_norm": 0.257348895072937,
      "learning_rate": 4.567934983444495e-05,
      "loss": 0.1718,
      "num_input_tokens_seen": 9660480,
      "step": 360
    },
    {
      "epoch": 5.8730158730158735,
      "grad_norm": 0.2910774052143097,
      "learning_rate": 4.544298464161079e-05,
      "loss": 0.1718,
      "num_input_tokens_seen": 9927936,
      "step": 370
    },
    {
      "epoch": 6.031746031746032,
      "grad_norm": 0.3452795445919037,
      "learning_rate": 4.520097124392055e-05,
      "loss": 0.1711,
      "num_input_tokens_seen": 10197520,
      "step": 380
    },
    {
      "epoch": 6.190476190476191,
      "grad_norm": 0.46368861198425293,
      "learning_rate": 4.49533765074054e-05,
      "loss": 0.1652,
      "num_input_tokens_seen": 10466240,
      "step": 390
    },
    {
      "epoch": 6.349206349206349,
      "grad_norm": 0.42205390334129333,
      "learning_rate": 4.4700268840168045e-05,
      "loss": 0.1677,
      "num_input_tokens_seen": 10734496,
      "step": 400
    },
    {
      "epoch": 6.507936507936508,
      "grad_norm": 0.25223520398139954,
      "learning_rate": 4.444171817348225e-05,
      "loss": 0.1684,
      "num_input_tokens_seen": 11004416,
      "step": 410
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.4380488991737366,
      "learning_rate": 4.417779594247143e-05,
      "loss": 0.1655,
      "num_input_tokens_seen": 11272656,
      "step": 420
    },
    {
      "epoch": 6.825396825396825,
      "grad_norm": 0.2701490819454193,
      "learning_rate": 4.3908575066371835e-05,
      "loss": 0.1722,
      "num_input_tokens_seen": 11540112,
      "step": 430
    },
    {
      "epoch": 6.984126984126984,
      "grad_norm": 0.3422671854496002,
      "learning_rate": 4.363412992838566e-05,
      "loss": 0.1676,
      "num_input_tokens_seen": 11808816,
      "step": 440
    },
    {
      "epoch": 7.142857142857143,
      "grad_norm": 0.6143015623092651,
      "learning_rate": 4.335453635512961e-05,
      "loss": 0.1538,
      "num_input_tokens_seen": 12077648,
      "step": 450
    },
    {
      "epoch": 7.301587301587301,
      "grad_norm": 0.44244784116744995,
      "learning_rate": 4.306987159568479e-05,
      "loss": 0.1572,
      "num_input_tokens_seen": 12346240,
      "step": 460
    },
    {
      "epoch": 7.4603174603174605,
      "grad_norm": 0.441853404045105,
      "learning_rate": 4.278021430025343e-05,
      "loss": 0.1587,
      "num_input_tokens_seen": 12614864,
      "step": 470
    },
    {
      "epoch": 7.619047619047619,
      "grad_norm": 0.520702600479126,
      "learning_rate": 4.248564449842864e-05,
      "loss": 0.1616,
      "num_input_tokens_seen": 12883088,
      "step": 480
    },
    {
      "epoch": 7.777777777777778,
      "grad_norm": 0.473958283662796,
      "learning_rate": 4.2186243577082954e-05,
      "loss": 0.1602,
      "num_input_tokens_seen": 13151264,
      "step": 490
    },
    {
      "epoch": 7.936507936507937,
      "grad_norm": 0.4550235867500305,
      "learning_rate": 4.1882094257881885e-05,
      "loss": 0.1597,
      "num_input_tokens_seen": 13419344,
      "step": 500
    },
    {
      "epoch": 8.095238095238095,
      "grad_norm": 0.7338590025901794,
      "learning_rate": 4.157328057442874e-05,
      "loss": 0.1473,
      "num_input_tokens_seen": 13686752,
      "step": 510
    },
    {
      "epoch": 8.253968253968253,
      "grad_norm": 0.6510297060012817,
      "learning_rate": 4.1259887849046906e-05,
      "loss": 0.1363,
      "num_input_tokens_seen": 13954352,
      "step": 520
    },
    {
      "epoch": 8.412698412698413,
      "grad_norm": 0.767859160900116,
      "learning_rate": 4.0942002669206085e-05,
      "loss": 0.1408,
      "num_input_tokens_seen": 14222352,
      "step": 530
    },
    {
      "epoch": 8.571428571428571,
      "grad_norm": 0.7285030484199524,
      "learning_rate": 4.0619712863599e-05,
      "loss": 0.1422,
      "num_input_tokens_seen": 14491920,
      "step": 540
    },
    {
      "epoch": 8.73015873015873,
      "grad_norm": 0.6987579464912415,
      "learning_rate": 4.029310747787516e-05,
      "loss": 0.1483,
      "num_input_tokens_seen": 14760400,
      "step": 550
    },
    {
      "epoch": 8.88888888888889,
      "grad_norm": 0.7618018984794617,
      "learning_rate": 3.996227675003834e-05,
      "loss": 0.1437,
      "num_input_tokens_seen": 15029280,
      "step": 560
    },
    {
      "epoch": 9.047619047619047,
      "grad_norm": 0.7082319855690002,
      "learning_rate": 3.962731208551474e-05,
      "loss": 0.1386,
      "num_input_tokens_seen": 15298416,
      "step": 570
    },
    {
      "epoch": 9.206349206349206,
      "grad_norm": 0.9523563385009766,
      "learning_rate": 3.928830603189844e-05,
      "loss": 0.1034,
      "num_input_tokens_seen": 15567104,
      "step": 580
    },
    {
      "epoch": 9.365079365079366,
      "grad_norm": 1.1607928276062012,
      "learning_rate": 3.894535225338143e-05,
      "loss": 0.1073,
      "num_input_tokens_seen": 15835952,
      "step": 590
    },
    {
      "epoch": 9.523809523809524,
      "grad_norm": 1.0483174324035645,
      "learning_rate": 3.859854550487506e-05,
      "loss": 0.1124,
      "num_input_tokens_seen": 16103648,
      "step": 600
    },
    {
      "epoch": 9.682539682539682,
      "grad_norm": 0.9111513495445251,
      "learning_rate": 3.824798160583012e-05,
      "loss": 0.1202,
      "num_input_tokens_seen": 16373888,
      "step": 610
    },
    {
      "epoch": 9.841269841269842,
      "grad_norm": 1.031439185142517,
      "learning_rate": 3.789375741376286e-05,
      "loss": 0.1194,
      "num_input_tokens_seen": 16642320,
      "step": 620
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.9815431237220764,
      "learning_rate": 3.7535970797494136e-05,
      "loss": 0.117,
      "num_input_tokens_seen": 16910032,
      "step": 630
    },
    {
      "epoch": 10.158730158730158,
      "grad_norm": 1.4907585382461548,
      "learning_rate": 3.717472061010918e-05,
      "loss": 0.0739,
      "num_input_tokens_seen": 17178576,
      "step": 640
    },
    {
      "epoch": 10.317460317460318,
      "grad_norm": 1.1762831211090088,
      "learning_rate": 3.681010666164546e-05,
      "loss": 0.0704,
      "num_input_tokens_seen": 17448288,
      "step": 650
    },
    {
      "epoch": 10.476190476190476,
      "grad_norm": 1.2105902433395386,
      "learning_rate": 3.644222969151605e-05,
      "loss": 0.0735,
      "num_input_tokens_seen": 17716784,
      "step": 660
    },
    {
      "epoch": 10.634920634920634,
      "grad_norm": 1.1394544839859009,
      "learning_rate": 3.607119134067629e-05,
      "loss": 0.077,
      "num_input_tokens_seen": 17984944,
      "step": 670
    },
    {
      "epoch": 10.793650793650794,
      "grad_norm": 1.2243598699569702,
      "learning_rate": 3.569709412354136e-05,
      "loss": 0.0763,
      "num_input_tokens_seen": 18252080,
      "step": 680
    },
    {
      "epoch": 10.952380952380953,
      "grad_norm": 1.0364540815353394,
      "learning_rate": 3.5320041399662494e-05,
      "loss": 0.0762,
      "num_input_tokens_seen": 18520464,
      "step": 690
    },
    {
      "epoch": 11.11111111111111,
      "grad_norm": 1.0455269813537598,
      "learning_rate": 3.494013734516971e-05,
      "loss": 0.0514,
      "num_input_tokens_seen": 18786528,
      "step": 700
    },
    {
      "epoch": 11.26984126984127,
      "grad_norm": 1.2155787944793701,
      "learning_rate": 3.4557486923988924e-05,
      "loss": 0.0375,
      "num_input_tokens_seen": 19055536,
      "step": 710
    },
    {
      "epoch": 11.428571428571429,
      "grad_norm": 1.1954303979873657,
      "learning_rate": 3.4172195858841404e-05,
      "loss": 0.0389,
      "num_input_tokens_seen": 19324304,
      "step": 720
    },
    {
      "epoch": 11.587301587301587,
      "grad_norm": 1.1928291320800781,
      "learning_rate": 3.378437060203357e-05,
      "loss": 0.0374,
      "num_input_tokens_seen": 19593552,
      "step": 730
    },
    {
      "epoch": 11.746031746031747,
      "grad_norm": 1.192438006401062,
      "learning_rate": 3.3394118306045217e-05,
      "loss": 0.0426,
      "num_input_tokens_seen": 19862784,
      "step": 740
    },
    {
      "epoch": 11.904761904761905,
      "grad_norm": 1.1554771661758423,
      "learning_rate": 3.3001546793924285e-05,
      "loss": 0.0432,
      "num_input_tokens_seen": 20131584,
      "step": 750
    },
    {
      "epoch": 12.063492063492063,
      "grad_norm": 0.7850580215454102,
      "learning_rate": 3.260676452949641e-05,
      "loss": 0.0348,
      "num_input_tokens_seen": 20401120,
      "step": 760
    },
    {
      "epoch": 12.222222222222221,
      "grad_norm": 0.6133368611335754,
      "learning_rate": 3.22098805873973e-05,
      "loss": 0.0165,
      "num_input_tokens_seen": 20670080,
      "step": 770
    },
    {
      "epoch": 12.380952380952381,
      "grad_norm": 0.9954155087471008,
      "learning_rate": 3.1811004622936525e-05,
      "loss": 0.0192,
      "num_input_tokens_seen": 20938000,
      "step": 780
    },
    {
      "epoch": 12.53968253968254,
      "grad_norm": 0.9651346206665039,
      "learning_rate": 3.141024684180071e-05,
      "loss": 0.0212,
      "num_input_tokens_seen": 21206432,
      "step": 790
    },
    {
      "epoch": 12.698412698412698,
      "grad_norm": 1.0618289709091187,
      "learning_rate": 3.10077179696048e-05,
      "loss": 0.0231,
      "num_input_tokens_seen": 21476960,
      "step": 800
    }
  ],
  "logging_steps": 10,
  "max_steps": 1890,
  "num_input_tokens_seen": 21476960,
  "num_train_epochs": 30,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.216970364477768e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}