{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02594033722438392,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00025940337224383917,
      "grad_norm": 13.49365234375,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.5584,
      "step": 10
    },
    {
      "epoch": 0.0005188067444876783,
      "grad_norm": 2.6006040573120117,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.7111,
      "step": 20
    },
    {
      "epoch": 0.0007782101167315176,
      "grad_norm": 4.435553073883057,
      "learning_rate": 4.8e-05,
      "loss": 0.3076,
      "step": 30
    },
    {
      "epoch": 0.0010376134889753567,
      "grad_norm": 1.1146177053451538,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.1826,
      "step": 40
    },
    {
      "epoch": 0.0012970168612191958,
      "grad_norm": 0.8707008957862854,
      "learning_rate": 8e-05,
      "loss": 0.1341,
      "step": 50
    },
    {
      "epoch": 0.0015564202334630351,
      "grad_norm": 1.7411352396011353,
      "learning_rate": 9.6e-05,
      "loss": 0.1144,
      "step": 60
    },
    {
      "epoch": 0.0018158236057068742,
      "grad_norm": 0.9691908955574036,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.0831,
      "step": 70
    },
    {
      "epoch": 0.0020752269779507134,
      "grad_norm": 1.0398532152175903,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.0801,
      "step": 80
    },
    {
      "epoch": 0.0023346303501945525,
      "grad_norm": 0.5252112746238708,
      "learning_rate": 0.000144,
      "loss": 0.081,
      "step": 90
    },
    {
      "epoch": 0.0025940337224383916,
      "grad_norm": 0.6552278995513916,
      "learning_rate": 0.00016,
      "loss": 0.0821,
      "step": 100
    },
    {
      "epoch": 0.0028534370946822307,
      "grad_norm": 0.6302046775817871,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.0749,
      "step": 110
    },
    {
      "epoch": 0.0031128404669260703,
      "grad_norm": 0.7439587712287903,
      "learning_rate": 0.000192,
      "loss": 0.0647,
      "step": 120
    },
    {
      "epoch": 0.0033722438391699094,
      "grad_norm": 6.8584771156311035,
      "learning_rate": 0.0001999978128380225,
      "loss": 0.0726,
      "step": 130
    },
    {
      "epoch": 0.0036316472114137485,
      "grad_norm": 2.014613389968872,
      "learning_rate": 0.0001999803161162393,
      "loss": 0.0936,
      "step": 140
    },
    {
      "epoch": 0.0038910505836575876,
      "grad_norm": 1.3758050203323364,
      "learning_rate": 0.00019994532573409262,
      "loss": 0.1089,
      "step": 150
    },
    {
      "epoch": 0.004150453955901427,
      "grad_norm": 1.3027769327163696,
      "learning_rate": 0.00019989284781388617,
      "loss": 0.0772,
      "step": 160
    },
    {
      "epoch": 0.004409857328145266,
      "grad_norm": 1.021938443183899,
      "learning_rate": 0.00019982289153773646,
      "loss": 0.0695,
      "step": 170
    },
    {
      "epoch": 0.004669260700389105,
      "grad_norm": 0.8069638609886169,
      "learning_rate": 0.00019973546914596623,
      "loss": 0.0624,
      "step": 180
    },
    {
      "epoch": 0.004928664072632944,
      "grad_norm": 0.5198134779930115,
      "learning_rate": 0.00019963059593496268,
      "loss": 0.0481,
      "step": 190
    },
    {
      "epoch": 0.005188067444876783,
      "grad_norm": 0.39965012669563293,
      "learning_rate": 0.00019950829025450114,
      "loss": 0.0493,
      "step": 200
    },
    {
      "epoch": 0.005447470817120622,
      "grad_norm": 0.8152652978897095,
      "learning_rate": 0.0001993685735045343,
      "loss": 0.0477,
      "step": 210
    },
    {
      "epoch": 0.005706874189364461,
      "grad_norm": 0.7083427309989929,
      "learning_rate": 0.0001992114701314478,
      "loss": 0.0501,
      "step": 220
    },
    {
      "epoch": 0.0059662775616083005,
      "grad_norm": 0.690096914768219,
      "learning_rate": 0.000199037007623783,
      "loss": 0.0509,
      "step": 230
    },
    {
      "epoch": 0.0062256809338521405,
      "grad_norm": 0.871699869632721,
      "learning_rate": 0.00019884521650742715,
      "loss": 0.0464,
      "step": 240
    },
    {
      "epoch": 0.00648508430609598,
      "grad_norm": 0.6445639133453369,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.0462,
      "step": 250
    },
    {
      "epoch": 0.006744487678339819,
      "grad_norm": 0.4920782148838043,
      "learning_rate": 0.0001984097857063434,
      "loss": 0.0425,
      "step": 260
    },
    {
      "epoch": 0.007003891050583658,
      "grad_norm": 0.8624788522720337,
      "learning_rate": 0.0001981662222093976,
      "loss": 0.0471,
      "step": 270
    },
    {
      "epoch": 0.007263294422827497,
      "grad_norm": 0.5704030990600586,
      "learning_rate": 0.00019790548246599447,
      "loss": 0.0571,
      "step": 280
    },
    {
      "epoch": 0.007522697795071336,
      "grad_norm": 0.569247841835022,
      "learning_rate": 0.00019762761209803927,
      "loss": 0.0531,
      "step": 290
    },
    {
      "epoch": 0.007782101167315175,
      "grad_norm": 0.7414583563804626,
      "learning_rate": 0.0001973326597248006,
      "loss": 0.0455,
      "step": 300
    },
    {
      "epoch": 0.008041504539559013,
      "grad_norm": 0.42905348539352417,
      "learning_rate": 0.00019702067695440332,
      "loss": 0.0542,
      "step": 310
    },
    {
      "epoch": 0.008300907911802853,
      "grad_norm": 0.6132651567459106,
      "learning_rate": 0.00019669171837479873,
      "loss": 0.0439,
      "step": 320
    },
    {
      "epoch": 0.008560311284046693,
      "grad_norm": 0.44733384251594543,
      "learning_rate": 0.00019634584154421317,
      "loss": 0.0429,
      "step": 330
    },
    {
      "epoch": 0.008819714656290532,
      "grad_norm": 0.516659677028656,
      "learning_rate": 0.00019598310698107702,
      "loss": 0.0407,
      "step": 340
    },
    {
      "epoch": 0.009079118028534372,
      "grad_norm": 0.2340136468410492,
      "learning_rate": 0.00019560357815343577,
      "loss": 0.036,
      "step": 350
    },
    {
      "epoch": 0.00933852140077821,
      "grad_norm": 0.6629723906517029,
      "learning_rate": 0.00019520732146784491,
      "loss": 0.041,
      "step": 360
    },
    {
      "epoch": 0.00959792477302205,
      "grad_norm": 0.3777199387550354,
      "learning_rate": 0.0001947944062577507,
      "loss": 0.0414,
      "step": 370
    },
    {
      "epoch": 0.009857328145265888,
      "grad_norm": 0.44298338890075684,
      "learning_rate": 0.00019436490477135878,
      "loss": 0.0371,
      "step": 380
    },
    {
      "epoch": 0.010116731517509728,
      "grad_norm": 0.4530090093612671,
      "learning_rate": 0.00019391889215899299,
      "loss": 0.037,
      "step": 390
    },
    {
      "epoch": 0.010376134889753566,
      "grad_norm": 0.36142367124557495,
      "learning_rate": 0.0001934564464599461,
      "loss": 0.0387,
      "step": 400
    },
    {
      "epoch": 0.010635538261997406,
      "grad_norm": 0.36559927463531494,
      "learning_rate": 0.00019297764858882514,
      "loss": 0.0386,
      "step": 410
    },
    {
      "epoch": 0.010894941634241245,
      "grad_norm": 0.47660204768180847,
      "learning_rate": 0.00019248258232139388,
      "loss": 0.0316,
      "step": 420
    },
    {
      "epoch": 0.011154345006485085,
      "grad_norm": 0.2614981234073639,
      "learning_rate": 0.00019197133427991436,
      "loss": 0.0417,
      "step": 430
    },
    {
      "epoch": 0.011413748378728923,
      "grad_norm": 0.44811561703681946,
      "learning_rate": 0.00019144399391799043,
      "loss": 0.036,
      "step": 440
    },
    {
      "epoch": 0.011673151750972763,
      "grad_norm": 0.4213508367538452,
      "learning_rate": 0.00019090065350491626,
      "loss": 0.0399,
      "step": 450
    },
    {
      "epoch": 0.011932555123216601,
      "grad_norm": 0.29146406054496765,
      "learning_rate": 0.0001903414081095315,
      "loss": 0.0376,
      "step": 460
    },
    {
      "epoch": 0.012191958495460441,
      "grad_norm": 0.2714293897151947,
      "learning_rate": 0.00018976635558358722,
      "loss": 0.0362,
      "step": 470
    },
    {
      "epoch": 0.012451361867704281,
      "grad_norm": 0.3767367899417877,
      "learning_rate": 0.00018917559654462474,
      "loss": 0.0364,
      "step": 480
    },
    {
      "epoch": 0.01271076523994812,
      "grad_norm": 0.36578992009162903,
      "learning_rate": 0.00018856923435837022,
      "loss": 0.0327,
      "step": 490
    },
    {
      "epoch": 0.01297016861219196,
      "grad_norm": 0.32976096868515015,
      "learning_rate": 0.0001879473751206489,
      "loss": 0.04,
      "step": 500
    },
    {
      "epoch": 0.013229571984435798,
      "grad_norm": 0.4037308990955353,
      "learning_rate": 0.00018731012763882133,
      "loss": 0.0365,
      "step": 510
    },
    {
      "epoch": 0.013488975356679637,
      "grad_norm": 0.3599701225757599,
      "learning_rate": 0.00018665760341274505,
      "loss": 0.0337,
      "step": 520
    },
    {
      "epoch": 0.013748378728923476,
      "grad_norm": 0.6167535185813904,
      "learning_rate": 0.00018598991661526572,
      "loss": 0.0384,
      "step": 530
    },
    {
      "epoch": 0.014007782101167316,
      "grad_norm": 0.44012153148651123,
      "learning_rate": 0.00018530718407223974,
      "loss": 0.0291,
      "step": 540
    },
    {
      "epoch": 0.014267185473411154,
      "grad_norm": 0.5593993663787842,
      "learning_rate": 0.00018460952524209355,
      "loss": 0.0328,
      "step": 550
    },
    {
      "epoch": 0.014526588845654994,
      "grad_norm": 0.3970232307910919,
      "learning_rate": 0.00018389706219492147,
      "loss": 0.0282,
      "step": 560
    },
    {
      "epoch": 0.014785992217898832,
      "grad_norm": 0.2354394942522049,
      "learning_rate": 0.00018316991959112716,
      "loss": 0.0317,
      "step": 570
    },
    {
      "epoch": 0.015045395590142672,
      "grad_norm": 0.35121485590934753,
      "learning_rate": 0.00018242822465961176,
      "loss": 0.0328,
      "step": 580
    },
    {
      "epoch": 0.01530479896238651,
      "grad_norm": 0.4026910066604614,
      "learning_rate": 0.00018167210717551224,
      "loss": 0.0346,
      "step": 590
    },
    {
      "epoch": 0.01556420233463035,
      "grad_norm": 0.36058488488197327,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0356,
      "step": 600
    },
    {
      "epoch": 0.01582360570687419,
      "grad_norm": 0.43329063057899475,
      "learning_rate": 0.00018011713624460608,
      "loss": 0.039,
      "step": 610
    },
    {
      "epoch": 0.016083009079118027,
      "grad_norm": 0.5267623662948608,
      "learning_rate": 0.00017931855487268782,
      "loss": 0.034,
      "step": 620
    },
    {
      "epoch": 0.01634241245136187,
      "grad_norm": 0.4230927526950836,
      "learning_rate": 0.0001785060950503568,
      "loss": 0.031,
      "step": 630
    },
    {
      "epoch": 0.016601815823605707,
      "grad_norm": 0.3721458613872528,
      "learning_rate": 0.00017767989893455698,
      "loss": 0.0306,
      "step": 640
    },
    {
      "epoch": 0.016861219195849545,
      "grad_norm": 0.4158923029899597,
      "learning_rate": 0.00017684011108568592,
      "loss": 0.0343,
      "step": 650
    },
    {
      "epoch": 0.017120622568093387,
      "grad_norm": 0.42805808782577515,
      "learning_rate": 0.00017598687844230088,
      "loss": 0.0348,
      "step": 660
    },
    {
      "epoch": 0.017380025940337225,
      "grad_norm": 0.2532889246940613,
      "learning_rate": 0.00017512035029540885,
      "loss": 0.0348,
      "step": 670
    },
    {
      "epoch": 0.017639429312581063,
      "grad_norm": 0.33485907316207886,
      "learning_rate": 0.000174240678262345,
      "loss": 0.0382,
      "step": 680
    },
    {
      "epoch": 0.0178988326848249,
      "grad_norm": 0.33811262249946594,
      "learning_rate": 0.000173348016260244,
      "loss": 0.0321,
      "step": 690
    },
    {
      "epoch": 0.018158236057068743,
      "grad_norm": 0.5319349765777588,
      "learning_rate": 0.00017244252047910892,
      "loss": 0.0369,
      "step": 700
    },
    {
      "epoch": 0.01841763942931258,
      "grad_norm": 0.1967012882232666,
      "learning_rate": 0.00017152434935448256,
      "loss": 0.0392,
      "step": 710
    },
    {
      "epoch": 0.01867704280155642,
      "grad_norm": 0.491212397813797,
      "learning_rate": 0.0001705936635397259,
      "loss": 0.034,
      "step": 720
    },
    {
      "epoch": 0.018936446173800258,
      "grad_norm": 0.3200204074382782,
      "learning_rate": 0.00016965062587790823,
      "loss": 0.0349,
      "step": 730
    },
    {
      "epoch": 0.0191958495460441,
      "grad_norm": 0.29090484976768494,
      "learning_rate": 0.00016869540137331445,
      "loss": 0.0302,
      "step": 740
    },
    {
      "epoch": 0.019455252918287938,
      "grad_norm": 0.4633236825466156,
      "learning_rate": 0.00016772815716257412,
      "loss": 0.0305,
      "step": 750
    },
    {
      "epoch": 0.019714656290531776,
      "grad_norm": 0.6030534505844116,
      "learning_rate": 0.00016674906248541726,
      "loss": 0.0331,
      "step": 760
    },
    {
      "epoch": 0.019974059662775615,
      "grad_norm": 0.28692400455474854,
      "learning_rate": 0.00016575828865506245,
      "loss": 0.0319,
      "step": 770
    },
    {
      "epoch": 0.020233463035019456,
      "grad_norm": 0.3799605667591095,
      "learning_rate": 0.0001647560090282419,
      "loss": 0.0316,
      "step": 780
    },
    {
      "epoch": 0.020492866407263294,
      "grad_norm": 0.529679536819458,
      "learning_rate": 0.000163742398974869,
      "loss": 0.0317,
      "step": 790
    },
    {
      "epoch": 0.020752269779507133,
      "grad_norm": 0.328056275844574,
      "learning_rate": 0.0001627176358473537,
      "loss": 0.0332,
      "step": 800
    },
    {
      "epoch": 0.021011673151750974,
      "grad_norm": 0.3303374648094177,
      "learning_rate": 0.0001616818989495711,
      "loss": 0.0323,
      "step": 810
    },
    {
      "epoch": 0.021271076523994813,
      "grad_norm": 0.23507635295391083,
      "learning_rate": 0.00016063536950548826,
      "loss": 0.0338,
      "step": 820
    },
    {
      "epoch": 0.02153047989623865,
      "grad_norm": 0.3870477080345154,
      "learning_rate": 0.0001595782306274553,
      "loss": 0.0326,
      "step": 830
    },
    {
      "epoch": 0.02178988326848249,
      "grad_norm": 0.37890198826789856,
      "learning_rate": 0.00015851066728416618,
      "loss": 0.0309,
      "step": 840
    },
    {
      "epoch": 0.02204928664072633,
      "grad_norm": 0.48460447788238525,
      "learning_rate": 0.00015743286626829437,
      "loss": 0.0351,
      "step": 850
    },
    {
      "epoch": 0.02230869001297017,
      "grad_norm": 0.38216733932495117,
      "learning_rate": 0.00015634501616380967,
      "loss": 0.0331,
      "step": 860
    },
    {
      "epoch": 0.022568093385214007,
      "grad_norm": 0.31668373942375183,
      "learning_rate": 0.00015524730731298134,
      "loss": 0.0306,
      "step": 870
    },
    {
      "epoch": 0.022827496757457846,
      "grad_norm": 0.5256275534629822,
      "learning_rate": 0.0001541399317830738,
      "loss": 0.0307,
      "step": 880
    },
    {
      "epoch": 0.023086900129701687,
      "grad_norm": 0.2295175939798355,
      "learning_rate": 0.0001530230833327405,
      "loss": 0.0297,
      "step": 890
    },
    {
      "epoch": 0.023346303501945526,
      "grad_norm": 0.35704338550567627,
      "learning_rate": 0.00015189695737812152,
      "loss": 0.0358,
      "step": 900
    },
    {
      "epoch": 0.023605706874189364,
      "grad_norm": 0.31458932161331177,
      "learning_rate": 0.0001507617509586517,
      "loss": 0.0278,
      "step": 910
    },
    {
      "epoch": 0.023865110246433202,
      "grad_norm": 0.47554951906204224,
      "learning_rate": 0.00014961766270258422,
      "loss": 0.0332,
      "step": 920
    },
    {
      "epoch": 0.024124513618677044,
      "grad_norm": 0.29959654808044434,
      "learning_rate": 0.00014846489279223652,
      "loss": 0.0268,
      "step": 930
    },
    {
      "epoch": 0.024383916990920882,
      "grad_norm": 0.31856444478034973,
      "learning_rate": 0.0001473036429289641,
      "loss": 0.028,
      "step": 940
    },
    {
      "epoch": 0.02464332036316472,
      "grad_norm": 0.23568253219127655,
      "learning_rate": 0.0001461341162978688,
      "loss": 0.0339,
      "step": 950
    },
    {
      "epoch": 0.024902723735408562,
      "grad_norm": 0.4032520055770874,
      "learning_rate": 0.00014495651753224705,
      "loss": 0.0291,
      "step": 960
    },
    {
      "epoch": 0.0251621271076524,
      "grad_norm": 0.36155375838279724,
      "learning_rate": 0.00014377105267778518,
      "loss": 0.0261,
      "step": 970
    },
    {
      "epoch": 0.02542153047989624,
      "grad_norm": 0.2985226511955261,
      "learning_rate": 0.00014257792915650728,
      "loss": 0.03,
      "step": 980
    },
    {
      "epoch": 0.025680933852140077,
      "grad_norm": 0.3420771658420563,
      "learning_rate": 0.00014137735573048233,
      "loss": 0.0318,
      "step": 990
    },
    {
      "epoch": 0.02594033722438392,
      "grad_norm": 0.19557547569274902,
      "learning_rate": 0.00014016954246529696,
      "loss": 0.0287,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.31459956342784e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}