{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1025,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04878048780487805,
      "grad_norm": 0.4036892056465149,
      "learning_rate": 0.00019999478113897612,
      "loss": 1.0282,
      "step": 10
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.3629762828350067,
      "learning_rate": 0.0001999791251006346,
      "loss": 0.7875,
      "step": 20
    },
    {
      "epoch": 0.14634146341463414,
      "grad_norm": 0.4877622425556183,
      "learning_rate": 0.0001999530335191093,
      "loss": 0.5942,
      "step": 30
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.4466260075569153,
      "learning_rate": 0.00019991650911776695,
      "loss": 0.3866,
      "step": 40
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 0.649118959903717,
      "learning_rate": 0.000199869555708923,
      "loss": 0.3928,
      "step": 50
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 0.8762800097465515,
      "learning_rate": 0.0001998121781934438,
      "loss": 0.3258,
      "step": 60
    },
    {
      "epoch": 0.34146341463414637,
      "grad_norm": 0.9195622801780701,
      "learning_rate": 0.0001997443825602349,
      "loss": 0.2885,
      "step": 70
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 0.5856262445449829,
      "learning_rate": 0.00019966617588561609,
      "loss": 0.2888,
      "step": 80
    },
    {
      "epoch": 0.43902439024390244,
      "grad_norm": 0.5520443320274353,
      "learning_rate": 0.00019957756633258265,
      "loss": 0.2242,
      "step": 90
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 0.9435800909996033,
      "learning_rate": 0.00019947856314995349,
      "loss": 0.1629,
      "step": 100
    },
    {
      "epoch": 0.5365853658536586,
      "grad_norm": 0.9416623115539551,
      "learning_rate": 0.00019936917667140555,
      "loss": 0.1555,
      "step": 110
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 0.802065372467041,
      "learning_rate": 0.0001992494183143955,
      "loss": 0.1339,
      "step": 120
    },
    {
      "epoch": 0.6341463414634146,
      "grad_norm": 0.7007794380187988,
      "learning_rate": 0.00019911930057896774,
      "loss": 0.1191,
      "step": 130
    },
    {
      "epoch": 0.6829268292682927,
      "grad_norm": 0.6755990386009216,
      "learning_rate": 0.00019897883704644983,
      "loss": 0.1571,
      "step": 140
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 1.6951078176498413,
      "learning_rate": 0.00019882804237803488,
      "loss": 0.1309,
      "step": 150
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 0.567158579826355,
      "learning_rate": 0.0001986669323132512,
      "loss": 0.0766,
      "step": 160
    },
    {
      "epoch": 0.8292682926829268,
      "grad_norm": 0.8820038437843323,
      "learning_rate": 0.0001984955236683196,
      "loss": 0.0839,
      "step": 170
    },
    {
      "epoch": 0.8780487804878049,
      "grad_norm": 0.6520794034004211,
      "learning_rate": 0.00019831383433439797,
      "loss": 0.0863,
      "step": 180
    },
    {
      "epoch": 0.926829268292683,
      "grad_norm": 0.45519864559173584,
      "learning_rate": 0.00019812188327571399,
      "loss": 0.0889,
      "step": 190
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.614235520362854,
      "learning_rate": 0.00019791969052758562,
      "loss": 0.0725,
      "step": 200
    },
    {
      "epoch": 1.024390243902439,
      "grad_norm": 0.2764686644077301,
      "learning_rate": 0.00019770727719432994,
      "loss": 0.0407,
      "step": 210
    },
    {
      "epoch": 1.0731707317073171,
      "grad_norm": 0.6082726716995239,
      "learning_rate": 0.00019748466544706022,
      "loss": 0.044,
      "step": 220
    },
    {
      "epoch": 1.1219512195121952,
      "grad_norm": 0.9295619130134583,
      "learning_rate": 0.00019725187852137195,
      "loss": 0.0675,
      "step": 230
    },
    {
      "epoch": 1.170731707317073,
      "grad_norm": 0.3758924603462219,
      "learning_rate": 0.00019700894071491732,
      "loss": 0.0439,
      "step": 240
    },
    {
      "epoch": 1.2195121951219512,
      "grad_norm": 0.46514585614204407,
      "learning_rate": 0.00019675587738486936,
      "loss": 0.0398,
      "step": 250
    },
    {
      "epoch": 1.2682926829268293,
      "grad_norm": 0.5870018005371094,
      "learning_rate": 0.0001964927149452751,
      "loss": 0.0406,
      "step": 260
    },
    {
      "epoch": 1.3170731707317074,
      "grad_norm": 0.30292996764183044,
      "learning_rate": 0.00019621948086429844,
      "loss": 0.028,
      "step": 270
    },
    {
      "epoch": 1.3658536585365852,
      "grad_norm": 0.47037121653556824,
      "learning_rate": 0.00019593620366135337,
      "loss": 0.0239,
      "step": 280
    },
    {
      "epoch": 1.4146341463414633,
      "grad_norm": 0.4176475405693054,
      "learning_rate": 0.00019564291290412688,
      "loss": 0.0281,
      "step": 290
    },
    {
      "epoch": 1.4634146341463414,
      "grad_norm": 0.3179157078266144,
      "learning_rate": 0.00019533963920549306,
      "loss": 0.0281,
      "step": 300
    },
    {
      "epoch": 1.5121951219512195,
      "grad_norm": 0.5817562937736511,
      "learning_rate": 0.00019502641422031763,
      "loss": 0.0296,
      "step": 310
    },
    {
      "epoch": 1.5609756097560976,
      "grad_norm": 0.7409655451774597,
      "learning_rate": 0.00019470327064215383,
      "loss": 0.029,
      "step": 320
    },
    {
      "epoch": 1.6097560975609757,
      "grad_norm": 0.4418310225009918,
      "learning_rate": 0.00019437024219983028,
      "loss": 0.0583,
      "step": 330
    },
    {
      "epoch": 1.6585365853658538,
      "grad_norm": 0.31637728214263916,
      "learning_rate": 0.0001940273636539301,
      "loss": 0.0354,
      "step": 340
    },
    {
      "epoch": 1.7073170731707317,
      "grad_norm": 0.22175493836402893,
      "learning_rate": 0.00019367467079316279,
      "loss": 0.0514,
      "step": 350
    },
    {
      "epoch": 1.7560975609756098,
      "grad_norm": 0.6636152267456055,
      "learning_rate": 0.00019331220043062894,
      "loss": 0.034,
      "step": 360
    },
    {
      "epoch": 1.8048780487804879,
      "grad_norm": 0.8424332141876221,
      "learning_rate": 0.00019293999039997746,
      "loss": 0.0299,
      "step": 370
    },
    {
      "epoch": 1.8536585365853657,
      "grad_norm": 0.6435155272483826,
      "learning_rate": 0.00019255807955145677,
      "loss": 0.0508,
      "step": 380
    },
    {
      "epoch": 1.9024390243902438,
      "grad_norm": 0.7734220027923584,
      "learning_rate": 0.00019216650774785972,
      "loss": 0.035,
      "step": 390
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 0.2854250967502594,
      "learning_rate": 0.0001917653158603628,
      "loss": 0.0339,
      "step": 400
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6165639758110046,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.0323,
      "step": 410
    },
    {
      "epoch": 2.048780487804878,
      "grad_norm": 0.2167205959558487,
      "learning_rate": 0.00019093424033459248,
      "loss": 0.026,
      "step": 420
    },
    {
      "epoch": 2.097560975609756,
      "grad_norm": 0.2723434269428253,
      "learning_rate": 0.0001905044434416725,
      "loss": 0.0176,
      "step": 430
    },
    {
      "epoch": 2.1463414634146343,
      "grad_norm": 0.4085879325866699,
      "learning_rate": 0.00019006519994650513,
      "loss": 0.0138,
      "step": 440
    },
    {
      "epoch": 2.1951219512195124,
      "grad_norm": 0.17931397259235382,
      "learning_rate": 0.00018961655569610557,
      "loss": 0.0358,
      "step": 450
    },
    {
      "epoch": 2.2439024390243905,
      "grad_norm": 0.3886450231075287,
      "learning_rate": 0.00018915855751871363,
      "loss": 0.0209,
      "step": 460
    },
    {
      "epoch": 2.292682926829268,
      "grad_norm": 0.11022531986236572,
      "learning_rate": 0.0001886912532189061,
      "loss": 0.0101,
      "step": 470
    },
    {
      "epoch": 2.341463414634146,
      "grad_norm": 0.14626094698905945,
      "learning_rate": 0.00018821469157260685,
      "loss": 0.0156,
      "step": 480
    },
    {
      "epoch": 2.3902439024390243,
      "grad_norm": 0.18015721440315247,
      "learning_rate": 0.00018772892232199592,
      "loss": 0.0156,
      "step": 490
    },
    {
      "epoch": 2.4390243902439024,
      "grad_norm": 0.3262254595756531,
      "learning_rate": 0.00018723399617031751,
      "loss": 0.0295,
      "step": 500
    },
    {
      "epoch": 2.4878048780487805,
      "grad_norm": 0.10063759982585907,
      "learning_rate": 0.00018672996477658767,
      "loss": 0.0164,
      "step": 510
    },
    {
      "epoch": 2.5365853658536586,
      "grad_norm": 0.11382050812244415,
      "learning_rate": 0.00018621688075020227,
      "loss": 0.0207,
      "step": 520
    },
    {
      "epoch": 2.5853658536585367,
      "grad_norm": 0.12307539582252502,
      "learning_rate": 0.0001856947976454459,
      "loss": 0.0326,
      "step": 530
    },
    {
      "epoch": 2.6341463414634148,
      "grad_norm": 0.18902955949306488,
      "learning_rate": 0.00018516376995590187,
      "loss": 0.0144,
      "step": 540
    },
    {
      "epoch": 2.682926829268293,
      "grad_norm": 0.18087974190711975,
      "learning_rate": 0.00018462385310876443,
      "loss": 0.0111,
      "step": 550
    },
    {
      "epoch": 2.7317073170731705,
      "grad_norm": 0.2894444465637207,
      "learning_rate": 0.00018407510345905332,
      "loss": 0.0081,
      "step": 560
    },
    {
      "epoch": 2.7804878048780486,
      "grad_norm": 0.24273361265659332,
      "learning_rate": 0.0001835175782837318,
      "loss": 0.0301,
      "step": 570
    },
    {
      "epoch": 2.8292682926829267,
      "grad_norm": 0.069428451359272,
      "learning_rate": 0.00018295133577572799,
      "loss": 0.0234,
      "step": 580
    },
    {
      "epoch": 2.8780487804878048,
      "grad_norm": 0.1845165342092514,
      "learning_rate": 0.00018237643503786095,
      "loss": 0.0112,
      "step": 590
    },
    {
      "epoch": 2.926829268292683,
      "grad_norm": 0.06373828649520874,
      "learning_rate": 0.00018179293607667178,
      "loss": 0.0241,
      "step": 600
    },
    {
      "epoch": 2.975609756097561,
      "grad_norm": 0.09466666728258133,
      "learning_rate": 0.0001812008997961602,
      "loss": 0.0151,
      "step": 610
    },
    {
      "epoch": 3.024390243902439,
      "grad_norm": 0.5068451762199402,
      "learning_rate": 0.00018060038799142759,
      "loss": 0.02,
      "step": 620
    },
    {
      "epoch": 3.073170731707317,
      "grad_norm": 0.17547158896923065,
      "learning_rate": 0.00017999146334222695,
      "loss": 0.0111,
      "step": 630
    },
    {
      "epoch": 3.1219512195121952,
      "grad_norm": 0.24108292162418365,
      "learning_rate": 0.00017937418940642074,
      "loss": 0.0095,
      "step": 640
    },
    {
      "epoch": 3.1707317073170733,
      "grad_norm": 0.24457822740077972,
      "learning_rate": 0.00017874863061334657,
      "loss": 0.0134,
      "step": 650
    },
    {
      "epoch": 3.2195121951219514,
      "grad_norm": 0.2185467779636383,
      "learning_rate": 0.00017811485225709256,
      "loss": 0.0135,
      "step": 660
    },
    {
      "epoch": 3.2682926829268295,
      "grad_norm": 0.12849357724189758,
      "learning_rate": 0.00017747292048968187,
      "loss": 0.0154,
      "step": 670
    },
    {
      "epoch": 3.317073170731707,
      "grad_norm": 0.09158976376056671,
      "learning_rate": 0.0001768229023141682,
      "loss": 0.0137,
      "step": 680
    },
    {
      "epoch": 3.3658536585365852,
      "grad_norm": 0.09520118683576584,
      "learning_rate": 0.00017616486557764187,
      "loss": 0.0147,
      "step": 690
    },
    {
      "epoch": 3.4146341463414633,
      "grad_norm": 0.11151307821273804,
      "learning_rate": 0.00017549887896414851,
      "loss": 0.0168,
      "step": 700
    },
    {
      "epoch": 3.4634146341463414,
      "grad_norm": 0.1175757572054863,
      "learning_rate": 0.00017482501198751965,
      "loss": 0.015,
      "step": 710
    },
    {
      "epoch": 3.5121951219512195,
      "grad_norm": 0.12314116209745407,
      "learning_rate": 0.00017414333498411733,
      "loss": 0.0179,
      "step": 720
    },
    {
      "epoch": 3.5609756097560976,
      "grad_norm": 0.08803991228342056,
      "learning_rate": 0.00017345391910549238,
      "loss": 0.0105,
      "step": 730
    },
    {
      "epoch": 3.6097560975609757,
      "grad_norm": 0.06382381916046143,
      "learning_rate": 0.000172756836310958,
      "loss": 0.0106,
      "step": 740
    },
    {
      "epoch": 3.658536585365854,
      "grad_norm": 0.47523975372314453,
      "learning_rate": 0.0001720521593600787,
      "loss": 0.0085,
      "step": 750
    },
    {
      "epoch": 3.7073170731707314,
      "grad_norm": 0.1268441379070282,
      "learning_rate": 0.000171339961805076,
      "loss": 0.0155,
      "step": 760
    },
    {
      "epoch": 3.7560975609756095,
      "grad_norm": 0.23719309270381927,
      "learning_rate": 0.000170620317983151,
      "loss": 0.015,
      "step": 770
    },
    {
      "epoch": 3.8048780487804876,
      "grad_norm": 0.0664207935333252,
      "learning_rate": 0.00016989330300872576,
      "loss": 0.0179,
      "step": 780
    },
    {
      "epoch": 3.8536585365853657,
      "grad_norm": 0.3121427893638611,
      "learning_rate": 0.00016915899276560237,
      "loss": 0.0138,
      "step": 790
    },
    {
      "epoch": 3.902439024390244,
      "grad_norm": 0.0784049853682518,
      "learning_rate": 0.00016841746389904304,
      "loss": 0.0114,
      "step": 800
    },
    {
      "epoch": 3.951219512195122,
      "grad_norm": 0.7239044904708862,
      "learning_rate": 0.0001676687938077698,
      "loss": 0.0251,
      "step": 810
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.2333860546350479,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0135,
      "step": 820
    },
    {
      "epoch": 4.048780487804878,
      "grad_norm": 0.7087911367416382,
      "learning_rate": 0.00016615034326471898,
      "loss": 0.0195,
      "step": 830
    },
    {
      "epoch": 4.097560975609756,
      "grad_norm": 0.07190815359354019,
      "learning_rate": 0.00016538072130458853,
      "loss": 0.0095,
      "step": 840
    },
    {
      "epoch": 4.146341463414634,
      "grad_norm": 0.33951500058174133,
      "learning_rate": 0.00016460427508649546,
      "loss": 0.0131,
      "step": 850
    },
    {
      "epoch": 4.195121951219512,
      "grad_norm": 0.06381627917289734,
      "learning_rate": 0.00016382108565373785,
      "loss": 0.0119,
      "step": 860
    },
    {
      "epoch": 4.2439024390243905,
      "grad_norm": 0.44717633724212646,
      "learning_rate": 0.00016303123475345182,
      "loss": 0.0127,
      "step": 870
    },
    {
      "epoch": 4.2926829268292686,
      "grad_norm": 0.6674973368644714,
      "learning_rate": 0.00016223480482807894,
      "loss": 0.0111,
      "step": 880
    },
    {
      "epoch": 4.341463414634147,
      "grad_norm": 0.3303108215332031,
      "learning_rate": 0.00016143187900676112,
      "loss": 0.0159,
      "step": 890
    },
    {
      "epoch": 4.390243902439025,
      "grad_norm": 0.2972947359085083,
      "learning_rate": 0.0001606225410966638,
      "loss": 0.0086,
      "step": 900
    },
    {
      "epoch": 4.439024390243903,
      "grad_norm": 0.059205561876297,
      "learning_rate": 0.00015980687557422854,
      "loss": 0.0104,
      "step": 910
    },
    {
      "epoch": 4.487804878048781,
      "grad_norm": 0.08515360206365585,
      "learning_rate": 0.00015898496757635536,
      "loss": 0.0079,
      "step": 920
    },
    {
      "epoch": 4.536585365853659,
      "grad_norm": 0.14600469172000885,
      "learning_rate": 0.00015815690289151658,
      "loss": 0.0101,
      "step": 930
    },
    {
      "epoch": 4.585365853658536,
      "grad_norm": 0.05901546776294708,
      "learning_rate": 0.0001573227679508024,
      "loss": 0.0075,
      "step": 940
    },
    {
      "epoch": 4.634146341463414,
      "grad_norm": 0.3404502868652344,
      "learning_rate": 0.00015648264981889934,
      "loss": 0.0158,
      "step": 950
    },
    {
      "epoch": 4.682926829268292,
      "grad_norm": 0.0968211218714714,
      "learning_rate": 0.00015563663618500302,
      "loss": 0.0092,
      "step": 960
    },
    {
      "epoch": 4.7317073170731705,
      "grad_norm": 0.08040373027324677,
      "learning_rate": 0.00015478481535366494,
      "loss": 0.0088,
      "step": 970
    },
    {
      "epoch": 4.780487804878049,
      "grad_norm": 0.7208348512649536,
      "learning_rate": 0.00015392727623557585,
      "loss": 0.0132,
      "step": 980
    },
    {
      "epoch": 4.829268292682927,
      "grad_norm": 0.26821044087409973,
      "learning_rate": 0.00015306410833828535,
      "loss": 0.0113,
      "step": 990
    },
    {
      "epoch": 4.878048780487805,
      "grad_norm": 0.09240720421075821,
      "learning_rate": 0.00015219540175685938,
      "loss": 0.0096,
      "step": 1000
    },
    {
      "epoch": 4.926829268292683,
      "grad_norm": 0.3397311270236969,
      "learning_rate": 0.00015132124716447627,
      "loss": 0.0072,
      "step": 1010
    },
    {
      "epoch": 4.975609756097561,
      "grad_norm": 0.07910922169685364,
      "learning_rate": 0.00015044173580296266,
      "loss": 0.0115,
      "step": 1020
    }
  ],
  "logging_steps": 10,
  "max_steps": 3075,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "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": 4.1079468558336e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}