{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.567398119122257,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001567398119122257,
      "grad_norm": 0.5552594661712646,
      "learning_rate": 3.448275862068966e-06,
      "loss": 3.3921,
      "step": 1
    },
    {
      "epoch": 0.01567398119122257,
      "grad_norm": 0.660531222820282,
      "learning_rate": 3.4482758620689657e-05,
      "loss": 3.5922,
      "step": 10
    },
    {
      "epoch": 0.03134796238244514,
      "grad_norm": 0.5598097443580627,
      "learning_rate": 6.896551724137931e-05,
      "loss": 3.619,
      "step": 20
    },
    {
      "epoch": 0.047021943573667714,
      "grad_norm": 0.5996779799461365,
      "learning_rate": 0.00010344827586206898,
      "loss": 3.4824,
      "step": 30
    },
    {
      "epoch": 0.06269592476489028,
      "grad_norm": 0.8172075152397156,
      "learning_rate": 0.00013793103448275863,
      "loss": 3.3997,
      "step": 40
    },
    {
      "epoch": 0.07836990595611286,
      "grad_norm": 1.6439019441604614,
      "learning_rate": 0.00017241379310344826,
      "loss": 3.2485,
      "step": 50
    },
    {
      "epoch": 0.09404388714733543,
      "grad_norm": 0.28180772066116333,
      "learning_rate": 0.00019999942697524717,
      "loss": 2.9975,
      "step": 60
    },
    {
      "epoch": 0.109717868338558,
      "grad_norm": 0.3870689868927002,
      "learning_rate": 0.00019997937179843937,
      "loss": 3.0446,
      "step": 70
    },
    {
      "epoch": 0.12539184952978055,
      "grad_norm": 0.575548529624939,
      "learning_rate": 0.00019993067195079803,
      "loss": 3.0178,
      "step": 80
    },
    {
      "epoch": 0.14106583072100312,
      "grad_norm": 0.781446635723114,
      "learning_rate": 0.00019985334138511237,
      "loss": 3.0394,
      "step": 90
    },
    {
      "epoch": 0.15673981191222572,
      "grad_norm": 1.725696325302124,
      "learning_rate": 0.00019974740225703878,
      "loss": 3.0751,
      "step": 100
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 0.2845414876937866,
      "learning_rate": 0.00019961288491875278,
      "loss": 2.9291,
      "step": 110
    },
    {
      "epoch": 0.18808777429467086,
      "grad_norm": 0.36810651421546936,
      "learning_rate": 0.00019944982791025333,
      "loss": 2.9491,
      "step": 120
    },
    {
      "epoch": 0.20376175548589343,
      "grad_norm": 0.5454439520835876,
      "learning_rate": 0.00019925827794832056,
      "loss": 3.0337,
      "step": 130
    },
    {
      "epoch": 0.219435736677116,
      "grad_norm": 0.6503669619560242,
      "learning_rate": 0.00019903828991313138,
      "loss": 3.0246,
      "step": 140
    },
    {
      "epoch": 0.23510971786833856,
      "grad_norm": 1.4392451047897339,
      "learning_rate": 0.00019878992683253582,
      "loss": 3.0232,
      "step": 150
    },
    {
      "epoch": 0.2507836990595611,
      "grad_norm": 0.2859440743923187,
      "learning_rate": 0.00019851325986399934,
      "loss": 2.8955,
      "step": 160
    },
    {
      "epoch": 0.2664576802507837,
      "grad_norm": 0.44268104434013367,
      "learning_rate": 0.0001982083682742156,
      "loss": 2.9338,
      "step": 170
    },
    {
      "epoch": 0.28213166144200624,
      "grad_norm": 0.5128395557403564,
      "learning_rate": 0.00019787533941639638,
      "loss": 3.0089,
      "step": 180
    },
    {
      "epoch": 0.29780564263322884,
      "grad_norm": 0.7328920364379883,
      "learning_rate": 0.00019751426870524407,
      "loss": 3.0157,
      "step": 190
    },
    {
      "epoch": 0.31347962382445144,
      "grad_norm": 1.5265012979507446,
      "learning_rate": 0.000197125259589615,
      "loss": 2.9007,
      "step": 200
    },
    {
      "epoch": 0.329153605015674,
      "grad_norm": 0.2766813635826111,
      "learning_rate": 0.0001967084235228807,
      "loss": 2.8275,
      "step": 210
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 0.36695396900177,
      "learning_rate": 0.00019626387993099579,
      "loss": 2.9158,
      "step": 220
    },
    {
      "epoch": 0.3605015673981191,
      "grad_norm": 0.5359162092208862,
      "learning_rate": 0.00019579175617828187,
      "loss": 2.9465,
      "step": 230
    },
    {
      "epoch": 0.3761755485893417,
      "grad_norm": 0.6529833674430847,
      "learning_rate": 0.0001952921875309368,
      "loss": 2.981,
      "step": 240
    },
    {
      "epoch": 0.39184952978056425,
      "grad_norm": 1.5314627885818481,
      "learning_rate": 0.00019476531711828027,
      "loss": 2.9737,
      "step": 250
    },
    {
      "epoch": 0.40752351097178685,
      "grad_norm": 0.2949506342411041,
      "learning_rate": 0.00019421129589174618,
      "loss": 2.8208,
      "step": 260
    },
    {
      "epoch": 0.4231974921630094,
      "grad_norm": 0.39567869901657104,
      "learning_rate": 0.00019363028258163447,
      "loss": 2.8557,
      "step": 270
    },
    {
      "epoch": 0.438871473354232,
      "grad_norm": 0.5587254166603088,
      "learning_rate": 0.00019302244365163376,
      "loss": 2.9494,
      "step": 280
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 0.7218978404998779,
      "learning_rate": 0.0001923879532511287,
      "loss": 2.9742,
      "step": 290
    },
    {
      "epoch": 0.4702194357366771,
      "grad_norm": 1.4482598304748535,
      "learning_rate": 0.0001917269931653049,
      "loss": 2.8646,
      "step": 300
    },
    {
      "epoch": 0.48589341692789967,
      "grad_norm": 0.2901701033115387,
      "learning_rate": 0.00019103975276306678,
      "loss": 2.7788,
      "step": 310
    },
    {
      "epoch": 0.5015673981191222,
      "grad_norm": 0.4310539960861206,
      "learning_rate": 0.00019032642894278192,
      "loss": 2.8655,
      "step": 320
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 0.5589954853057861,
      "learning_rate": 0.0001895872260758688,
      "loss": 2.914,
      "step": 330
    },
    {
      "epoch": 0.5329153605015674,
      "grad_norm": 0.7243526577949524,
      "learning_rate": 0.00018882235594824308,
      "loss": 2.9191,
      "step": 340
    },
    {
      "epoch": 0.54858934169279,
      "grad_norm": 1.4200222492218018,
      "learning_rate": 0.00018803203769963967,
      "loss": 2.8128,
      "step": 350
    },
    {
      "epoch": 0.5642633228840125,
      "grad_norm": 0.26594147086143494,
      "learning_rate": 0.000187216497760828,
      "loss": 2.762,
      "step": 360
    },
    {
      "epoch": 0.5799373040752351,
      "grad_norm": 0.3894258439540863,
      "learning_rate": 0.00018637596978873835,
      "loss": 2.9077,
      "step": 370
    },
    {
      "epoch": 0.5956112852664577,
      "grad_norm": 0.5348561406135559,
      "learning_rate": 0.00018551069459951758,
      "loss": 2.9292,
      "step": 380
    },
    {
      "epoch": 0.6112852664576802,
      "grad_norm": 0.746507465839386,
      "learning_rate": 0.00018462092009953408,
      "loss": 2.8795,
      "step": 390
    },
    {
      "epoch": 0.6269592476489029,
      "grad_norm": 1.5225753784179688,
      "learning_rate": 0.0001837069012143511,
      "loss": 2.8263,
      "step": 400
    },
    {
      "epoch": 0.6426332288401254,
      "grad_norm": 0.26905450224876404,
      "learning_rate": 0.00018276889981568906,
      "loss": 2.7218,
      "step": 410
    },
    {
      "epoch": 0.658307210031348,
      "grad_norm": 0.3912515342235565,
      "learning_rate": 0.00018180718464639787,
      "loss": 2.819,
      "step": 420
    },
    {
      "epoch": 0.6739811912225705,
      "grad_norm": 0.5661373138427734,
      "learning_rate": 0.00018082203124346045,
      "loss": 2.8772,
      "step": 430
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.805776059627533,
      "learning_rate": 0.0001798137218590498,
      "loss": 2.9562,
      "step": 440
    },
    {
      "epoch": 0.7053291536050157,
      "grad_norm": 1.4879732131958008,
      "learning_rate": 0.00017878254537966216,
      "loss": 2.7925,
      "step": 450
    },
    {
      "epoch": 0.7210031347962382,
      "grad_norm": 0.28762391209602356,
      "learning_rate": 0.00017772879724334937,
      "loss": 2.8006,
      "step": 460
    },
    {
      "epoch": 0.7366771159874608,
      "grad_norm": 0.41769474744796753,
      "learning_rate": 0.00017665277935507398,
      "loss": 2.8148,
      "step": 470
    },
    {
      "epoch": 0.7523510971786834,
      "grad_norm": 0.633671760559082,
      "learning_rate": 0.00017555480000021198,
      "loss": 2.8461,
      "step": 480
    },
    {
      "epoch": 0.768025078369906,
      "grad_norm": 0.816681444644928,
      "learning_rate": 0.00017443517375622704,
      "loss": 2.8826,
      "step": 490
    },
    {
      "epoch": 0.7836990595611285,
      "grad_norm": 1.3913438320159912,
      "learning_rate": 0.00017329422140254235,
      "loss": 2.7449,
      "step": 500
    },
    {
      "epoch": 0.799373040752351,
      "grad_norm": 0.30519339442253113,
      "learning_rate": 0.0001721322698286354,
      "loss": 2.7933,
      "step": 510
    },
    {
      "epoch": 0.8150470219435737,
      "grad_norm": 0.3911365270614624,
      "learning_rate": 0.0001709496519403823,
      "loss": 2.8433,
      "step": 520
    },
    {
      "epoch": 0.8307210031347962,
      "grad_norm": 0.5197113752365112,
      "learning_rate": 0.00016974670656467824,
      "loss": 2.828,
      "step": 530
    },
    {
      "epoch": 0.8463949843260188,
      "grad_norm": 0.7463776469230652,
      "learning_rate": 0.00016852377835236166,
      "loss": 2.9549,
      "step": 540
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 1.6616039276123047,
      "learning_rate": 0.00016728121767946977,
      "loss": 2.8843,
      "step": 550
    },
    {
      "epoch": 0.877742946708464,
      "grad_norm": 0.2525625228881836,
      "learning_rate": 0.00016601938054685385,
      "loss": 2.7715,
      "step": 560
    },
    {
      "epoch": 0.8934169278996865,
      "grad_norm": 0.4268622100353241,
      "learning_rate": 0.00016473862847818277,
      "loss": 2.8196,
      "step": 570
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.5538944005966187,
      "learning_rate": 0.00016343932841636456,
      "loss": 2.8619,
      "step": 580
    },
    {
      "epoch": 0.9247648902821317,
      "grad_norm": 0.7213597297668457,
      "learning_rate": 0.00016212185261841499,
      "loss": 2.9276,
      "step": 590
    },
    {
      "epoch": 0.9404388714733543,
      "grad_norm": 1.6927486658096313,
      "learning_rate": 0.00016078657854880376,
      "loss": 2.7446,
      "step": 600
    },
    {
      "epoch": 0.9561128526645768,
      "grad_norm": 0.3090650141239166,
      "learning_rate": 0.000159433888771309,
      "loss": 2.747,
      "step": 610
    },
    {
      "epoch": 0.9717868338557993,
      "grad_norm": 0.4454885423183441,
      "learning_rate": 0.00015806417083941002,
      "loss": 2.8622,
      "step": 620
    },
    {
      "epoch": 0.987460815047022,
      "grad_norm": 0.8089830279350281,
      "learning_rate": 0.00015667781718525157,
      "loss": 2.8568,
      "step": 630
    },
    {
      "epoch": 1.0031347962382444,
      "grad_norm": 0.21911662817001343,
      "learning_rate": 0.00015527522500720934,
      "loss": 2.7012,
      "step": 640
    },
    {
      "epoch": 1.0188087774294672,
      "grad_norm": 0.3196061849594116,
      "learning_rate": 0.00015385679615609042,
      "loss": 2.7127,
      "step": 650
    },
    {
      "epoch": 1.0344827586206897,
      "grad_norm": 0.4679659605026245,
      "learning_rate": 0.00015242293702000086,
      "loss": 2.7103,
      "step": 660
    },
    {
      "epoch": 1.0501567398119123,
      "grad_norm": 0.6506277322769165,
      "learning_rate": 0.00015097405840791276,
      "loss": 2.6762,
      "step": 670
    },
    {
      "epoch": 1.0658307210031348,
      "grad_norm": 0.9151834845542908,
      "learning_rate": 0.00014951057543196566,
      "loss": 2.6503,
      "step": 680
    },
    {
      "epoch": 1.0815047021943573,
      "grad_norm": 0.2834145724773407,
      "learning_rate": 0.00014803290738853395,
      "loss": 2.5103,
      "step": 690
    },
    {
      "epoch": 1.09717868338558,
      "grad_norm": 0.3199128210544586,
      "learning_rate": 0.00014654147763809637,
      "loss": 2.7147,
      "step": 700
    },
    {
      "epoch": 1.1128526645768024,
      "grad_norm": 0.5001178979873657,
      "learning_rate": 0.00014503671348394057,
      "loss": 2.7124,
      "step": 710
    },
    {
      "epoch": 1.1285266457680252,
      "grad_norm": 0.6373796463012695,
      "learning_rate": 0.0001435190460497384,
      "loss": 2.7012,
      "step": 720
    },
    {
      "epoch": 1.1442006269592477,
      "grad_norm": 0.9262835383415222,
      "learning_rate": 0.00014198891015602646,
      "loss": 2.6493,
      "step": 730
    },
    {
      "epoch": 1.1598746081504703,
      "grad_norm": 0.2955109775066376,
      "learning_rate": 0.00014044674419562734,
      "loss": 2.5023,
      "step": 740
    },
    {
      "epoch": 1.1755485893416928,
      "grad_norm": 0.34623944759368896,
      "learning_rate": 0.0001388929900080476,
      "loss": 2.6849,
      "step": 750
    },
    {
      "epoch": 1.1912225705329154,
      "grad_norm": 0.43281346559524536,
      "learning_rate": 0.00013732809275288828,
      "loss": 2.6655,
      "step": 760
    },
    {
      "epoch": 1.206896551724138,
      "grad_norm": 0.6403496265411377,
      "learning_rate": 0.000135752500782304,
      "loss": 2.6557,
      "step": 770
    },
    {
      "epoch": 1.2225705329153604,
      "grad_norm": 0.8644494414329529,
      "learning_rate": 0.00013416666551254748,
      "loss": 2.6162,
      "step": 780
    },
    {
      "epoch": 1.238244514106583,
      "grad_norm": 0.2673655152320862,
      "learning_rate": 0.00013257104129463614,
      "loss": 2.4991,
      "step": 790
    },
    {
      "epoch": 1.2539184952978055,
      "grad_norm": 0.3414609432220459,
      "learning_rate": 0.00013096608528417788,
      "loss": 2.6638,
      "step": 800
    },
    {
      "epoch": 1.2695924764890283,
      "grad_norm": 0.47588247060775757,
      "learning_rate": 0.00012935225731039348,
      "loss": 2.6465,
      "step": 810
    },
    {
      "epoch": 1.2852664576802508,
      "grad_norm": 0.6843693852424622,
      "learning_rate": 0.00012773001974437267,
      "loss": 2.6697,
      "step": 820
    },
    {
      "epoch": 1.3009404388714734,
      "grad_norm": 0.9213519096374512,
      "learning_rate": 0.0001260998373666022,
      "loss": 2.6691,
      "step": 830
    },
    {
      "epoch": 1.316614420062696,
      "grad_norm": 0.26475438475608826,
      "learning_rate": 0.0001244621772338036,
      "loss": 2.5109,
      "step": 840
    },
    {
      "epoch": 1.3322884012539185,
      "grad_norm": 0.3754674196243286,
      "learning_rate": 0.0001228175085451186,
      "loss": 2.6699,
      "step": 850
    },
    {
      "epoch": 1.347962382445141,
      "grad_norm": 0.49352237582206726,
      "learning_rate": 0.00012116630250768097,
      "loss": 2.6889,
      "step": 860
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.7134298086166382,
      "learning_rate": 0.00011950903220161285,
      "loss": 2.6502,
      "step": 870
    },
    {
      "epoch": 1.3793103448275863,
      "grad_norm": 0.9475263953208923,
      "learning_rate": 0.00011784617244448451,
      "loss": 2.6062,
      "step": 880
    },
    {
      "epoch": 1.3949843260188088,
      "grad_norm": 0.2767506539821625,
      "learning_rate": 0.0001161781996552765,
      "loss": 2.4584,
      "step": 890
    },
    {
      "epoch": 1.4106583072100314,
      "grad_norm": 0.38563597202301025,
      "learning_rate": 0.00011450559171788269,
      "loss": 2.6751,
      "step": 900
    },
    {
      "epoch": 1.426332288401254,
      "grad_norm": 0.466782808303833,
      "learning_rate": 0.00011282882784419398,
      "loss": 2.6181,
      "step": 910
    },
    {
      "epoch": 1.4420062695924765,
      "grad_norm": 0.7600008845329285,
      "learning_rate": 0.00011114838843680095,
      "loss": 2.6729,
      "step": 920
    },
    {
      "epoch": 1.457680250783699,
      "grad_norm": 0.956167459487915,
      "learning_rate": 0.0001094647549513561,
      "loss": 2.5486,
      "step": 930
    },
    {
      "epoch": 1.4733542319749215,
      "grad_norm": 0.257744699716568,
      "learning_rate": 0.00010777840975863383,
      "loss": 2.4545,
      "step": 940
    },
    {
      "epoch": 1.489028213166144,
      "grad_norm": 0.347033828496933,
      "learning_rate": 0.00010608983600632831,
      "loss": 2.6313,
      "step": 950
    },
    {
      "epoch": 1.5047021943573666,
      "grad_norm": 0.5105902552604675,
      "learning_rate": 0.00010439951748062912,
      "loss": 2.623,
      "step": 960
    },
    {
      "epoch": 1.5203761755485894,
      "grad_norm": 0.7116357684135437,
      "learning_rate": 0.00010270793846761347,
      "loss": 2.6493,
      "step": 970
    },
    {
      "epoch": 1.536050156739812,
      "grad_norm": 0.9367708563804626,
      "learning_rate": 0.00010101558361449552,
      "loss": 2.6081,
      "step": 980
    },
    {
      "epoch": 1.5517241379310345,
      "grad_norm": 0.25939515233039856,
      "learning_rate": 9.932293779077216e-05,
      "loss": 2.4289,
      "step": 990
    },
    {
      "epoch": 1.567398119122257,
      "grad_norm": 0.3675819933414459,
      "learning_rate": 9.763048594930502e-05,
      "loss": 2.6617,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 1914,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.8760263209474458e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}