{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.031221096094631143,
  "eval_steps": 334,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.1221096094631145e-05,
      "eval_loss": 2.5151805877685547,
      "eval_runtime": 12858.7571,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 1
    },
    {
      "epoch": 0.0003122109609463114,
      "grad_norm": 1.6301891803741455,
      "learning_rate": 0.0002,
      "loss": 1.2603,
      "step": 10
    },
    {
      "epoch": 0.0006244219218926228,
      "grad_norm": 2.2189297676086426,
      "learning_rate": 0.00019994965423831854,
      "loss": 0.8201,
      "step": 20
    },
    {
      "epoch": 0.0009366328828389343,
      "grad_norm": 1.6551645994186401,
      "learning_rate": 0.00019979866764718843,
      "loss": 0.7913,
      "step": 30
    },
    {
      "epoch": 0.0012488438437852456,
      "grad_norm": 4.437395095825195,
      "learning_rate": 0.00019954719225730847,
      "loss": 1.2831,
      "step": 40
    },
    {
      "epoch": 0.001561054804731557,
      "grad_norm": 7.653807163238525,
      "learning_rate": 0.00019919548128307954,
      "loss": 1.6268,
      "step": 50
    },
    {
      "epoch": 0.0018732657656778686,
      "grad_norm": 1.2926839590072632,
      "learning_rate": 0.00019874388886763944,
      "loss": 1.1779,
      "step": 60
    },
    {
      "epoch": 0.00218547672662418,
      "grad_norm": 1.5756969451904297,
      "learning_rate": 0.00019819286972627066,
      "loss": 0.6204,
      "step": 70
    },
    {
      "epoch": 0.002497687687570491,
      "grad_norm": 1.8183478116989136,
      "learning_rate": 0.00019754297868854073,
      "loss": 0.8666,
      "step": 80
    },
    {
      "epoch": 0.0028098986485168027,
      "grad_norm": 4.023663520812988,
      "learning_rate": 0.00019679487013963564,
      "loss": 1.1012,
      "step": 90
    },
    {
      "epoch": 0.003122109609463114,
      "grad_norm": 3.675027847290039,
      "learning_rate": 0.00019594929736144976,
      "loss": 1.3794,
      "step": 100
    },
    {
      "epoch": 0.0034343205704094257,
      "grad_norm": 1.1626209020614624,
      "learning_rate": 0.00019500711177409454,
      "loss": 1.1787,
      "step": 110
    },
    {
      "epoch": 0.003746531531355737,
      "grad_norm": 1.4152737855911255,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.471,
      "step": 120
    },
    {
      "epoch": 0.004058742492302049,
      "grad_norm": 2.0098798274993896,
      "learning_rate": 0.00019283679330160726,
      "loss": 0.9037,
      "step": 130
    },
    {
      "epoch": 0.00437095345324836,
      "grad_norm": 2.845428943634033,
      "learning_rate": 0.00019161084574320696,
      "loss": 1.2114,
      "step": 140
    },
    {
      "epoch": 0.004683164414194672,
      "grad_norm": 5.3034749031066895,
      "learning_rate": 0.00019029265382866214,
      "loss": 1.397,
      "step": 150
    },
    {
      "epoch": 0.004995375375140982,
      "grad_norm": 1.5945558547973633,
      "learning_rate": 0.00018888354486549237,
      "loss": 1.145,
      "step": 160
    },
    {
      "epoch": 0.005307586336087294,
      "grad_norm": 1.1813420057296753,
      "learning_rate": 0.00018738493770697852,
      "loss": 0.5603,
      "step": 170
    },
    {
      "epoch": 0.005619797297033605,
      "grad_norm": 2.35960054397583,
      "learning_rate": 0.00018579834132349772,
      "loss": 0.8248,
      "step": 180
    },
    {
      "epoch": 0.005932008257979917,
      "grad_norm": 2.443915605545044,
      "learning_rate": 0.00018412535328311814,
      "loss": 1.1141,
      "step": 190
    },
    {
      "epoch": 0.006244219218926228,
      "grad_norm": 5.689703941345215,
      "learning_rate": 0.0001823676581429833,
      "loss": 1.2009,
      "step": 200
    },
    {
      "epoch": 0.00655643017987254,
      "grad_norm": 1.4314906597137451,
      "learning_rate": 0.00018052702575310588,
      "loss": 1.1061,
      "step": 210
    },
    {
      "epoch": 0.006868641140818851,
      "grad_norm": 0.6448104977607727,
      "learning_rate": 0.00017860530947427875,
      "loss": 0.4016,
      "step": 220
    },
    {
      "epoch": 0.007180852101765163,
      "grad_norm": 2.0396196842193604,
      "learning_rate": 0.0001766044443118978,
      "loss": 0.8709,
      "step": 230
    },
    {
      "epoch": 0.007493063062711474,
      "grad_norm": 2.5875227451324463,
      "learning_rate": 0.0001745264449675755,
      "loss": 1.1121,
      "step": 240
    },
    {
      "epoch": 0.007805274023657786,
      "grad_norm": 3.9609525203704834,
      "learning_rate": 0.00017237340381050703,
      "loss": 1.251,
      "step": 250
    },
    {
      "epoch": 0.008117484984604097,
      "grad_norm": 1.2032607793807983,
      "learning_rate": 0.00017014748877063214,
      "loss": 1.1823,
      "step": 260
    },
    {
      "epoch": 0.008429695945550408,
      "grad_norm": 1.186848521232605,
      "learning_rate": 0.00016785094115571322,
      "loss": 0.6219,
      "step": 270
    },
    {
      "epoch": 0.00874190690649672,
      "grad_norm": 1.85453462600708,
      "learning_rate": 0.00016548607339452853,
      "loss": 0.5809,
      "step": 280
    },
    {
      "epoch": 0.009054117867443031,
      "grad_norm": 2.0443332195281982,
      "learning_rate": 0.00016305526670845226,
      "loss": 1.2146,
      "step": 290
    },
    {
      "epoch": 0.009366328828389343,
      "grad_norm": 7.1448516845703125,
      "learning_rate": 0.00016056096871376667,
      "loss": 1.2524,
      "step": 300
    },
    {
      "epoch": 0.009678539789335654,
      "grad_norm": 1.334848165512085,
      "learning_rate": 0.00015800569095711982,
      "loss": 1.1966,
      "step": 310
    },
    {
      "epoch": 0.009990750750281965,
      "grad_norm": 0.4558267295360565,
      "learning_rate": 0.00015539200638661104,
      "loss": 0.589,
      "step": 320
    },
    {
      "epoch": 0.010302961711228277,
      "grad_norm": 1.8344190120697021,
      "learning_rate": 0.00015272254676105025,
      "loss": 0.5806,
      "step": 330
    },
    {
      "epoch": 0.010427846095606801,
      "eval_loss": 0.9566133618354797,
      "eval_runtime": 13592.0734,
      "eval_samples_per_second": 2.095,
      "eval_steps_per_second": 2.095,
      "step": 334
    },
    {
      "epoch": 0.010615172672174588,
      "grad_norm": 1.9632649421691895,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.0551,
      "step": 340
    },
    {
      "epoch": 0.0109273836331209,
      "grad_norm": 4.136826992034912,
      "learning_rate": 0.0001472271074772683,
      "loss": 1.0784,
      "step": 350
    },
    {
      "epoch": 0.01123959459406721,
      "grad_norm": 1.1779104471206665,
      "learning_rate": 0.00014440666126057744,
      "loss": 1.1613,
      "step": 360
    },
    {
      "epoch": 0.011551805555013523,
      "grad_norm": 0.8325644731521606,
      "learning_rate": 0.00014154150130018866,
      "loss": 0.5119,
      "step": 370
    },
    {
      "epoch": 0.011864016515959834,
      "grad_norm": 1.6711801290512085,
      "learning_rate": 0.00013863451256931287,
      "loss": 0.6156,
      "step": 380
    },
    {
      "epoch": 0.012176227476906146,
      "grad_norm": 2.293975353240967,
      "learning_rate": 0.00013568862215918717,
      "loss": 1.0706,
      "step": 390
    },
    {
      "epoch": 0.012488438437852457,
      "grad_norm": 2.2785656452178955,
      "learning_rate": 0.00013270679633174218,
      "loss": 1.2872,
      "step": 400
    },
    {
      "epoch": 0.012800649398798769,
      "grad_norm": 1.2502048015594482,
      "learning_rate": 0.0001296920375328275,
      "loss": 1.0768,
      "step": 410
    },
    {
      "epoch": 0.01311286035974508,
      "grad_norm": 0.7812928557395935,
      "learning_rate": 0.00012664738136900348,
      "loss": 0.5199,
      "step": 420
    },
    {
      "epoch": 0.01342507132069139,
      "grad_norm": 2.0176918506622314,
      "learning_rate": 0.00012357589355094275,
      "loss": 0.8125,
      "step": 430
    },
    {
      "epoch": 0.013737282281637703,
      "grad_norm": 2.014697313308716,
      "learning_rate": 0.00012048066680651908,
      "loss": 1.0261,
      "step": 440
    },
    {
      "epoch": 0.014049493242584013,
      "grad_norm": 3.0161404609680176,
      "learning_rate": 0.00011736481776669306,
      "loss": 1.1352,
      "step": 450
    },
    {
      "epoch": 0.014361704203530326,
      "grad_norm": 1.1186920404434204,
      "learning_rate": 0.00011423148382732853,
      "loss": 1.1374,
      "step": 460
    },
    {
      "epoch": 0.014673915164476636,
      "grad_norm": 0.9820886850357056,
      "learning_rate": 0.00011108381999010111,
      "loss": 0.5135,
      "step": 470
    },
    {
      "epoch": 0.014986126125422949,
      "grad_norm": 2.8473262786865234,
      "learning_rate": 0.00010792499568567884,
      "loss": 0.8812,
      "step": 480
    },
    {
      "epoch": 0.01529833708636926,
      "grad_norm": 2.1481053829193115,
      "learning_rate": 0.00010475819158237425,
      "loss": 1.0178,
      "step": 490
    },
    {
      "epoch": 0.015610548047315572,
      "grad_norm": 1.20015287399292,
      "learning_rate": 0.00010158659638348081,
      "loss": 1.0468,
      "step": 500
    },
    {
      "epoch": 0.015922759008261882,
      "grad_norm": 1.3715260028839111,
      "learning_rate": 9.84134036165192e-05,
      "loss": 1.0121,
      "step": 510
    },
    {
      "epoch": 0.016234969969208195,
      "grad_norm": 0.9032047390937805,
      "learning_rate": 9.524180841762577e-05,
      "loss": 0.5379,
      "step": 520
    },
    {
      "epoch": 0.016547180930154507,
      "grad_norm": 1.6322988271713257,
      "learning_rate": 9.207500431432115e-05,
      "loss": 0.5695,
      "step": 530
    },
    {
      "epoch": 0.016859391891100816,
      "grad_norm": 2.7707173824310303,
      "learning_rate": 8.891618000989891e-05,
      "loss": 0.9264,
      "step": 540
    },
    {
      "epoch": 0.01717160285204713,
      "grad_norm": 2.905618667602539,
      "learning_rate": 8.57685161726715e-05,
      "loss": 1.0027,
      "step": 550
    },
    {
      "epoch": 0.01748381381299344,
      "grad_norm": 1.0891023874282837,
      "learning_rate": 8.263518223330697e-05,
      "loss": 1.0168,
      "step": 560
    },
    {
      "epoch": 0.01779602477393975,
      "grad_norm": 1.0451884269714355,
      "learning_rate": 7.951933319348095e-05,
      "loss": 0.3617,
      "step": 570
    },
    {
      "epoch": 0.018108235734886062,
      "grad_norm": 1.5976777076721191,
      "learning_rate": 7.642410644905726e-05,
      "loss": 0.7168,
      "step": 580
    },
    {
      "epoch": 0.018420446695832374,
      "grad_norm": 2.3960399627685547,
      "learning_rate": 7.335261863099651e-05,
      "loss": 0.9692,
      "step": 590
    },
    {
      "epoch": 0.018732657656778687,
      "grad_norm": 2.764636516571045,
      "learning_rate": 7.030796246717255e-05,
      "loss": 1.0993,
      "step": 600
    },
    {
      "epoch": 0.019044868617724996,
      "grad_norm": 1.0002310276031494,
      "learning_rate": 6.729320366825784e-05,
      "loss": 1.1104,
      "step": 610
    },
    {
      "epoch": 0.019357079578671308,
      "grad_norm": 1.2536269426345825,
      "learning_rate": 6.431137784081282e-05,
      "loss": 0.5409,
      "step": 620
    },
    {
      "epoch": 0.01966929053961762,
      "grad_norm": 1.9996048212051392,
      "learning_rate": 6.136548743068713e-05,
      "loss": 0.7138,
      "step": 630
    },
    {
      "epoch": 0.01998150150056393,
      "grad_norm": 1.9154224395751953,
      "learning_rate": 5.845849869981137e-05,
      "loss": 0.9189,
      "step": 640
    },
    {
      "epoch": 0.02029371246151024,
      "grad_norm": 0.8520050644874573,
      "learning_rate": 5.559333873942259e-05,
      "loss": 1.1057,
      "step": 650
    },
    {
      "epoch": 0.020605923422456554,
      "grad_norm": 0.821565568447113,
      "learning_rate": 5.277289252273174e-05,
      "loss": 0.9571,
      "step": 660
    },
    {
      "epoch": 0.020855692191213603,
      "eval_loss": 0.8139573931694031,
      "eval_runtime": 11568.1075,
      "eval_samples_per_second": 2.461,
      "eval_steps_per_second": 2.461,
      "step": 668
    },
    {
      "epoch": 0.020918134383402866,
      "grad_norm": 1.3406473398208618,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.4458,
      "step": 670
    },
    {
      "epoch": 0.021230345344349175,
      "grad_norm": 1.6482555866241455,
      "learning_rate": 4.727745323894976e-05,
      "loss": 0.8605,
      "step": 680
    },
    {
      "epoch": 0.021542556305295488,
      "grad_norm": 2.3034768104553223,
      "learning_rate": 4.4607993613388976e-05,
      "loss": 0.8842,
      "step": 690
    },
    {
      "epoch": 0.0218547672662418,
      "grad_norm": 2.2205710411071777,
      "learning_rate": 4.19943090428802e-05,
      "loss": 1.0044,
      "step": 700
    },
    {
      "epoch": 0.022166978227188112,
      "grad_norm": 1.0776264667510986,
      "learning_rate": 3.943903128623335e-05,
      "loss": 0.9987,
      "step": 710
    },
    {
      "epoch": 0.02247918918813442,
      "grad_norm": 0.7974869012832642,
      "learning_rate": 3.694473329154778e-05,
      "loss": 0.4341,
      "step": 720
    },
    {
      "epoch": 0.022791400149080734,
      "grad_norm": 1.410180926322937,
      "learning_rate": 3.45139266054715e-05,
      "loss": 0.7361,
      "step": 730
    },
    {
      "epoch": 0.023103611110027046,
      "grad_norm": 1.5520089864730835,
      "learning_rate": 3.21490588442868e-05,
      "loss": 0.8486,
      "step": 740
    },
    {
      "epoch": 0.023415822070973355,
      "grad_norm": 4.628422260284424,
      "learning_rate": 2.9852511229367865e-05,
      "loss": 1.1191,
      "step": 750
    },
    {
      "epoch": 0.023728033031919667,
      "grad_norm": 1.1060361862182617,
      "learning_rate": 2.7626596189492983e-05,
      "loss": 1.018,
      "step": 760
    },
    {
      "epoch": 0.02404024399286598,
      "grad_norm": 1.108621597290039,
      "learning_rate": 2.5473555032424533e-05,
      "loss": 0.4265,
      "step": 770
    },
    {
      "epoch": 0.024352454953812292,
      "grad_norm": 1.4980049133300781,
      "learning_rate": 2.339555568810221e-05,
      "loss": 0.6406,
      "step": 780
    },
    {
      "epoch": 0.0246646659147586,
      "grad_norm": 1.4313726425170898,
      "learning_rate": 2.139469052572127e-05,
      "loss": 0.9413,
      "step": 790
    },
    {
      "epoch": 0.024976876875704913,
      "grad_norm": 1.4710307121276855,
      "learning_rate": 1.947297424689414e-05,
      "loss": 1.0135,
      "step": 800
    },
    {
      "epoch": 0.025289087836651226,
      "grad_norm": 0.8172721266746521,
      "learning_rate": 1.763234185701673e-05,
      "loss": 0.9491,
      "step": 810
    },
    {
      "epoch": 0.025601298797597538,
      "grad_norm": 1.1474344730377197,
      "learning_rate": 1.587464671688187e-05,
      "loss": 0.5334,
      "step": 820
    },
    {
      "epoch": 0.025913509758543847,
      "grad_norm": 1.4124549627304077,
      "learning_rate": 1.4201658676502294e-05,
      "loss": 0.7033,
      "step": 830
    },
    {
      "epoch": 0.02622572071949016,
      "grad_norm": 1.3929728269577026,
      "learning_rate": 1.2615062293021507e-05,
      "loss": 0.852,
      "step": 840
    },
    {
      "epoch": 0.026537931680436472,
      "grad_norm": 0.782926619052887,
      "learning_rate": 1.1116455134507664e-05,
      "loss": 1.0648,
      "step": 850
    },
    {
      "epoch": 0.02685014264138278,
      "grad_norm": 1.1986958980560303,
      "learning_rate": 9.707346171337894e-06,
      "loss": 0.9374,
      "step": 860
    },
    {
      "epoch": 0.027162353602329093,
      "grad_norm": 1.0474522113800049,
      "learning_rate": 8.38915425679304e-06,
      "loss": 0.5091,
      "step": 870
    },
    {
      "epoch": 0.027474564563275405,
      "grad_norm": 1.569217562675476,
      "learning_rate": 7.163206698392744e-06,
      "loss": 0.6196,
      "step": 880
    },
    {
      "epoch": 0.027786775524221718,
      "grad_norm": 2.387129306793213,
      "learning_rate": 6.030737921409169e-06,
      "loss": 0.8911,
      "step": 890
    },
    {
      "epoch": 0.028098986485168027,
      "grad_norm": 1.0116970539093018,
      "learning_rate": 4.992888225905468e-06,
      "loss": 0.893,
      "step": 900
    },
    {
      "epoch": 0.02841119744611434,
      "grad_norm": 1.056663155555725,
      "learning_rate": 4.050702638550275e-06,
      "loss": 0.9925,
      "step": 910
    },
    {
      "epoch": 0.02872340840706065,
      "grad_norm": 1.0909359455108643,
      "learning_rate": 3.2051298603643753e-06,
      "loss": 0.634,
      "step": 920
    },
    {
      "epoch": 0.029035619368006964,
      "grad_norm": 1.5931735038757324,
      "learning_rate": 2.4570213114592954e-06,
      "loss": 0.6653,
      "step": 930
    },
    {
      "epoch": 0.029347830328953273,
      "grad_norm": 1.73000967502594,
      "learning_rate": 1.8071302737293295e-06,
      "loss": 0.7891,
      "step": 940
    },
    {
      "epoch": 0.029660041289899585,
      "grad_norm": 0.5561469197273254,
      "learning_rate": 1.2561111323605712e-06,
      "loss": 0.9679,
      "step": 950
    },
    {
      "epoch": 0.029972252250845897,
      "grad_norm": 1.1528609991073608,
      "learning_rate": 8.04518716920466e-07,
      "loss": 0.9362,
      "step": 960
    },
    {
      "epoch": 0.030284463211792206,
      "grad_norm": 0.6554343104362488,
      "learning_rate": 4.5280774269154115e-07,
      "loss": 0.3348,
      "step": 970
    },
    {
      "epoch": 0.03059667417273852,
      "grad_norm": 1.3619601726531982,
      "learning_rate": 2.0133235281156736e-07,
      "loss": 0.5258,
      "step": 980
    },
    {
      "epoch": 0.03090888513368483,
      "grad_norm": 1.2936415672302246,
      "learning_rate": 5.0345761681491746e-08,
      "loss": 0.9126,
      "step": 990
    },
    {
      "epoch": 0.031221096094631143,
      "grad_norm": 1.708081841468811,
      "learning_rate": 0.0,
      "loss": 1.0155,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 167,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.641564097334477e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}