{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 977,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01023541453428864,
      "grad_norm": 7.7834055877958335,
      "learning_rate": 9.183673469387756e-06,
      "loss": 1.3341,
      "step": 10
    },
    {
      "epoch": 0.02047082906857728,
      "grad_norm": 3.3236709051524596,
      "learning_rate": 1.9387755102040817e-05,
      "loss": 0.9581,
      "step": 20
    },
    {
      "epoch": 0.030706243602865915,
      "grad_norm": 2.977258761181777,
      "learning_rate": 2.959183673469388e-05,
      "loss": 0.8198,
      "step": 30
    },
    {
      "epoch": 0.04094165813715456,
      "grad_norm": 2.6517473738880017,
      "learning_rate": 3.979591836734694e-05,
      "loss": 0.8068,
      "step": 40
    },
    {
      "epoch": 0.0511770726714432,
      "grad_norm": 2.4411980164190483,
      "learning_rate": 5e-05,
      "loss": 0.7806,
      "step": 50
    },
    {
      "epoch": 0.06141248720573183,
      "grad_norm": 2.722909425904186,
      "learning_rate": 6.0204081632653065e-05,
      "loss": 0.7813,
      "step": 60
    },
    {
      "epoch": 0.07164790174002048,
      "grad_norm": 2.438870821286421,
      "learning_rate": 7.040816326530612e-05,
      "loss": 0.7638,
      "step": 70
    },
    {
      "epoch": 0.08188331627430911,
      "grad_norm": 2.7409885678697834,
      "learning_rate": 8.061224489795919e-05,
      "loss": 0.7851,
      "step": 80
    },
    {
      "epoch": 0.09211873080859775,
      "grad_norm": 2.420673755200228,
      "learning_rate": 9.081632653061225e-05,
      "loss": 0.8118,
      "step": 90
    },
    {
      "epoch": 0.1023541453428864,
      "grad_norm": 2.1160173262738424,
      "learning_rate": 9.999968065395524e-05,
      "loss": 0.7849,
      "step": 100
    },
    {
      "epoch": 0.11258955987717502,
      "grad_norm": 2.3266961924172422,
      "learning_rate": 9.996136406426098e-05,
      "loss": 0.7867,
      "step": 110
    },
    {
      "epoch": 0.12282497441146366,
      "grad_norm": 2.1879000329125553,
      "learning_rate": 9.985923434387545e-05,
      "loss": 0.7762,
      "step": 120
    },
    {
      "epoch": 0.1330603889457523,
      "grad_norm": 1.9268306021116635,
      "learning_rate": 9.969342193793992e-05,
      "loss": 0.7805,
      "step": 130
    },
    {
      "epoch": 0.14329580348004095,
      "grad_norm": 1.8233490072221166,
      "learning_rate": 9.94641386302783e-05,
      "loss": 0.767,
      "step": 140
    },
    {
      "epoch": 0.1535312180143296,
      "grad_norm": 1.654947019917813,
      "learning_rate": 9.91716772728964e-05,
      "loss": 0.7929,
      "step": 150
    },
    {
      "epoch": 0.16376663254861823,
      "grad_norm": 1.7646195870148857,
      "learning_rate": 9.881641141193671e-05,
      "loss": 0.7922,
      "step": 160
    },
    {
      "epoch": 0.17400204708290687,
      "grad_norm": 1.798313457582181,
      "learning_rate": 9.839879481056682e-05,
      "loss": 0.7732,
      "step": 170
    },
    {
      "epoch": 0.1842374616171955,
      "grad_norm": 1.6813305854347143,
      "learning_rate": 9.791936086941064e-05,
      "loss": 0.7811,
      "step": 180
    },
    {
      "epoch": 0.19447287615148415,
      "grad_norm": 1.542624416844649,
      "learning_rate": 9.737872194526263e-05,
      "loss": 0.7861,
      "step": 190
    },
    {
      "epoch": 0.2047082906857728,
      "grad_norm": 1.8454764465355653,
      "learning_rate": 9.677756856895532e-05,
      "loss": 0.7815,
      "step": 200
    },
    {
      "epoch": 0.21494370522006143,
      "grad_norm": 1.8285780958025841,
      "learning_rate": 9.611666856337919e-05,
      "loss": 0.7712,
      "step": 210
    },
    {
      "epoch": 0.22517911975435004,
      "grad_norm": 1.5460714131980207,
      "learning_rate": 9.53968660627812e-05,
      "loss": 0.7562,
      "step": 220
    },
    {
      "epoch": 0.23541453428863868,
      "grad_norm": 1.6371167797582773,
      "learning_rate": 9.461908043459458e-05,
      "loss": 0.7546,
      "step": 230
    },
    {
      "epoch": 0.24564994882292732,
      "grad_norm": 1.4018916277593396,
      "learning_rate": 9.378430510517731e-05,
      "loss": 0.7593,
      "step": 240
    },
    {
      "epoch": 0.25588536335721596,
      "grad_norm": 1.433153418900028,
      "learning_rate": 9.289360629095867e-05,
      "loss": 0.7567,
      "step": 250
    },
    {
      "epoch": 0.2661207778915046,
      "grad_norm": 1.586845159995946,
      "learning_rate": 9.194812163661474e-05,
      "loss": 0.7519,
      "step": 260
    },
    {
      "epoch": 0.27635619242579323,
      "grad_norm": 1.487396419818292,
      "learning_rate": 9.094905876201229e-05,
      "loss": 0.7487,
      "step": 270
    },
    {
      "epoch": 0.2865916069600819,
      "grad_norm": 1.4036484092983759,
      "learning_rate": 8.989769371977678e-05,
      "loss": 0.7522,
      "step": 280
    },
    {
      "epoch": 0.2968270214943705,
      "grad_norm": 1.3663625769783851,
      "learning_rate": 8.879536936545472e-05,
      "loss": 0.7628,
      "step": 290
    },
    {
      "epoch": 0.3070624360286592,
      "grad_norm": 1.3897510215020903,
      "learning_rate": 8.764349364235196e-05,
      "loss": 0.7513,
      "step": 300
    },
    {
      "epoch": 0.3172978505629478,
      "grad_norm": 1.4132771035791343,
      "learning_rate": 8.644353778323877e-05,
      "loss": 0.7545,
      "step": 310
    },
    {
      "epoch": 0.32753326509723646,
      "grad_norm": 1.3470486921727471,
      "learning_rate": 8.519703443121839e-05,
      "loss": 0.7206,
      "step": 320
    },
    {
      "epoch": 0.33776867963152507,
      "grad_norm": 1.3516050517615625,
      "learning_rate": 8.390557568215928e-05,
      "loss": 0.7379,
      "step": 330
    },
    {
      "epoch": 0.34800409416581374,
      "grad_norm": 1.3452010008303381,
      "learning_rate": 8.25708110511914e-05,
      "loss": 0.7279,
      "step": 340
    },
    {
      "epoch": 0.35823950870010235,
      "grad_norm": 1.5922569137427653,
      "learning_rate": 8.119444536586362e-05,
      "loss": 0.7239,
      "step": 350
    },
    {
      "epoch": 0.368474923234391,
      "grad_norm": 1.3277390469665615,
      "learning_rate": 7.977823658865364e-05,
      "loss": 0.7244,
      "step": 360
    },
    {
      "epoch": 0.37871033776867963,
      "grad_norm": 1.368862098001025,
      "learning_rate": 7.832399357161096e-05,
      "loss": 0.7138,
      "step": 370
    },
    {
      "epoch": 0.3889457523029683,
      "grad_norm": 1.256874657883898,
      "learning_rate": 7.683357374600157e-05,
      "loss": 0.7253,
      "step": 380
    },
    {
      "epoch": 0.3991811668372569,
      "grad_norm": 1.3620144893554462,
      "learning_rate": 7.530888074990457e-05,
      "loss": 0.7041,
      "step": 390
    },
    {
      "epoch": 0.4094165813715456,
      "grad_norm": 1.2847799590301334,
      "learning_rate": 7.375186199679128e-05,
      "loss": 0.7156,
      "step": 400
    },
    {
      "epoch": 0.4196519959058342,
      "grad_norm": 1.479890947990238,
      "learning_rate": 7.216450618819221e-05,
      "loss": 0.7321,
      "step": 410
    },
    {
      "epoch": 0.42988741044012285,
      "grad_norm": 1.2988278165331997,
      "learning_rate": 7.054884077362892e-05,
      "loss": 0.7205,
      "step": 420
    },
    {
      "epoch": 0.44012282497441146,
      "grad_norm": 1.352603176837788,
      "learning_rate": 6.890692936105493e-05,
      "loss": 0.7184,
      "step": 430
    },
    {
      "epoch": 0.4503582395087001,
      "grad_norm": 1.3167027225109398,
      "learning_rate": 6.724086908111342e-05,
      "loss": 0.7043,
      "step": 440
    },
    {
      "epoch": 0.46059365404298874,
      "grad_norm": 1.1605514478149297,
      "learning_rate": 6.5552787908578e-05,
      "loss": 0.7141,
      "step": 450
    },
    {
      "epoch": 0.47082906857727735,
      "grad_norm": 1.3647229291712017,
      "learning_rate": 6.384484194439783e-05,
      "loss": 0.7277,
      "step": 460
    },
    {
      "epoch": 0.481064483111566,
      "grad_norm": 1.3613262015550092,
      "learning_rate": 6.211921266181862e-05,
      "loss": 0.6942,
      "step": 470
    },
    {
      "epoch": 0.49129989764585463,
      "grad_norm": 1.2303260031230618,
      "learning_rate": 6.037810412009692e-05,
      "loss": 0.7105,
      "step": 480
    },
    {
      "epoch": 0.5015353121801432,
      "grad_norm": 1.2236723217345244,
      "learning_rate": 5.8623740149366266e-05,
      "loss": 0.6919,
      "step": 490
    },
    {
      "epoch": 0.5117707267144319,
      "grad_norm": 1.2925387655719225,
      "learning_rate": 5.685836151025124e-05,
      "loss": 0.7004,
      "step": 500
    },
    {
      "epoch": 0.5220061412487206,
      "grad_norm": 1.1330725313044812,
      "learning_rate": 5.508422303185682e-05,
      "loss": 0.6809,
      "step": 510
    },
    {
      "epoch": 0.5322415557830092,
      "grad_norm": 1.277900149808847,
      "learning_rate": 5.3303590731788967e-05,
      "loss": 0.676,
      "step": 520
    },
    {
      "epoch": 0.5424769703172978,
      "grad_norm": 1.320596225367009,
      "learning_rate": 5.1518738921884526e-05,
      "loss": 0.7019,
      "step": 530
    },
    {
      "epoch": 0.5527123848515865,
      "grad_norm": 1.2316789595997863,
      "learning_rate": 4.973194730334748e-05,
      "loss": 0.652,
      "step": 540
    },
    {
      "epoch": 0.5629477993858751,
      "grad_norm": 1.3019922622420315,
      "learning_rate": 4.794549805500157e-05,
      "loss": 0.6727,
      "step": 550
    },
    {
      "epoch": 0.5731832139201638,
      "grad_norm": 1.1745654063581337,
      "learning_rate": 4.616167291837833e-05,
      "loss": 0.6787,
      "step": 560
    },
    {
      "epoch": 0.5834186284544524,
      "grad_norm": 1.1840028131717766,
      "learning_rate": 4.4382750283363734e-05,
      "loss": 0.678,
      "step": 570
    },
    {
      "epoch": 0.593654042988741,
      "grad_norm": 1.1804801771916893,
      "learning_rate": 4.2611002278125716e-05,
      "loss": 0.6702,
      "step": 580
    },
    {
      "epoch": 0.6038894575230297,
      "grad_norm": 1.235979212193821,
      "learning_rate": 4.084869186703939e-05,
      "loss": 0.6837,
      "step": 590
    },
    {
      "epoch": 0.6141248720573184,
      "grad_norm": 1.207257384479852,
      "learning_rate": 3.909806996031681e-05,
      "loss": 0.6803,
      "step": 600
    },
    {
      "epoch": 0.6243602865916069,
      "grad_norm": 1.2100444508139683,
      "learning_rate": 3.736137253903294e-05,
      "loss": 0.6571,
      "step": 610
    },
    {
      "epoch": 0.6345957011258956,
      "grad_norm": 1.316273926337265,
      "learning_rate": 3.564081779921964e-05,
      "loss": 0.6733,
      "step": 620
    },
    {
      "epoch": 0.6448311156601843,
      "grad_norm": 1.185100923547794,
      "learning_rate": 3.393860331867589e-05,
      "loss": 0.679,
      "step": 630
    },
    {
      "epoch": 0.6550665301944729,
      "grad_norm": 1.290593515241855,
      "learning_rate": 3.2256903250112384e-05,
      "loss": 0.6679,
      "step": 640
    },
    {
      "epoch": 0.6653019447287615,
      "grad_norm": 1.18768723258656,
      "learning_rate": 3.0597865544216024e-05,
      "loss": 0.6579,
      "step": 650
    },
    {
      "epoch": 0.6755373592630501,
      "grad_norm": 1.2124615745663647,
      "learning_rate": 2.8963609206180714e-05,
      "loss": 0.6534,
      "step": 660
    },
    {
      "epoch": 0.6857727737973388,
      "grad_norm": 1.2143635604470278,
      "learning_rate": 2.735622158920898e-05,
      "loss": 0.653,
      "step": 670
    },
    {
      "epoch": 0.6960081883316275,
      "grad_norm": 1.1266034141680707,
      "learning_rate": 2.5777755728441e-05,
      "loss": 0.6504,
      "step": 680
    },
    {
      "epoch": 0.706243602865916,
      "grad_norm": 1.1361699853176876,
      "learning_rate": 2.4230227718716235e-05,
      "loss": 0.6441,
      "step": 690
    },
    {
      "epoch": 0.7164790174002047,
      "grad_norm": 1.0797816282004906,
      "learning_rate": 2.271561413951735e-05,
      "loss": 0.6461,
      "step": 700
    },
    {
      "epoch": 0.7267144319344934,
      "grad_norm": 1.143836664526645,
      "learning_rate": 2.1235849530384762e-05,
      "loss": 0.6451,
      "step": 710
    },
    {
      "epoch": 0.736949846468782,
      "grad_norm": 1.0227443680313577,
      "learning_rate": 1.979282392002691e-05,
      "loss": 0.6384,
      "step": 720
    },
    {
      "epoch": 0.7471852610030706,
      "grad_norm": 1.1893039038961186,
      "learning_rate": 1.8388380412281907e-05,
      "loss": 0.6449,
      "step": 730
    },
    {
      "epoch": 0.7574206755373593,
      "grad_norm": 1.064334883901842,
      "learning_rate": 1.7024312832013977e-05,
      "loss": 0.6326,
      "step": 740
    },
    {
      "epoch": 0.7676560900716479,
      "grad_norm": 1.054448727433728,
      "learning_rate": 1.5702363433951407e-05,
      "loss": 0.631,
      "step": 750
    },
    {
      "epoch": 0.7778915046059366,
      "grad_norm": 1.1264394043969406,
      "learning_rate": 1.4424220677392387e-05,
      "loss": 0.642,
      "step": 760
    },
    {
      "epoch": 0.7881269191402251,
      "grad_norm": 1.126137103609967,
      "learning_rate": 1.3191517069621157e-05,
      "loss": 0.6063,
      "step": 770
    },
    {
      "epoch": 0.7983623336745138,
      "grad_norm": 1.1153938175009752,
      "learning_rate": 1.2005827080788834e-05,
      "loss": 0.6267,
      "step": 780
    },
    {
      "epoch": 0.8085977482088025,
      "grad_norm": 1.0912738220038205,
      "learning_rate": 1.086866513292198e-05,
      "loss": 0.626,
      "step": 790
    },
    {
      "epoch": 0.8188331627430911,
      "grad_norm": 1.1583625795892225,
      "learning_rate": 9.781483665627778e-06,
      "loss": 0.6379,
      "step": 800
    },
    {
      "epoch": 0.8290685772773797,
      "grad_norm": 1.1399750694513615,
      "learning_rate": 8.745671280966177e-06,
      "loss": 0.6166,
      "step": 810
    },
    {
      "epoch": 0.8393039918116684,
      "grad_norm": 1.0599921308972278,
      "learning_rate": 7.762550969858512e-06,
      "loss": 0.6283,
      "step": 820
    },
    {
      "epoch": 0.849539406345957,
      "grad_norm": 1.1503335495527243,
      "learning_rate": 6.8333784222979146e-06,
      "loss": 0.6188,
      "step": 830
    },
    {
      "epoch": 0.8597748208802457,
      "grad_norm": 1.1681827538174718,
      "learning_rate": 5.959340423519777e-06,
      "loss": 0.6118,
      "step": 840
    },
    {
      "epoch": 0.8700102354145343,
      "grad_norm": 1.1817688022234127,
      "learning_rate": 5.14155333818086e-06,
      "loss": 0.6171,
      "step": 850
    },
    {
      "epoch": 0.8802456499488229,
      "grad_norm": 1.1827879341955665,
      "learning_rate": 4.381061684483018e-06,
      "loss": 0.6275,
      "step": 860
    },
    {
      "epoch": 0.8904810644831116,
      "grad_norm": 1.1011880464938935,
      "learning_rate": 3.6788368000627625e-06,
      "loss": 0.6346,
      "step": 870
    },
    {
      "epoch": 0.9007164790174002,
      "grad_norm": 1.0928432800529013,
      "learning_rate": 3.035775601350688e-06,
      "loss": 0.6223,
      "step": 880
    },
    {
      "epoch": 0.9109518935516888,
      "grad_norm": 1.2022735713545292,
      "learning_rate": 2.4526994379853617e-06,
      "loss": 0.6219,
      "step": 890
    },
    {
      "epoch": 0.9211873080859775,
      "grad_norm": 1.0320057049672093,
      "learning_rate": 1.9303530437448035e-06,
      "loss": 0.6008,
      "step": 900
    },
    {
      "epoch": 0.9314227226202662,
      "grad_norm": 1.1035889382326984,
      "learning_rate": 1.4694035853356769e-06,
      "loss": 0.6169,
      "step": 910
    },
    {
      "epoch": 0.9416581371545547,
      "grad_norm": 1.0074516839569725,
      "learning_rate": 1.070439810254803e-06,
      "loss": 0.619,
      "step": 920
    },
    {
      "epoch": 0.9518935516888434,
      "grad_norm": 1.0580374820863356,
      "learning_rate": 7.339712948117417e-07,
      "loss": 0.5986,
      "step": 930
    },
    {
      "epoch": 0.962128966223132,
      "grad_norm": 1.1248396918780994,
      "learning_rate": 4.6042779327264973e-07,
      "loss": 0.6225,
      "step": 940
    },
    {
      "epoch": 0.9723643807574207,
      "grad_norm": 1.0845960469737606,
      "learning_rate": 2.5015868895682527e-07,
      "loss": 0.616,
      "step": 950
    },
    {
      "epoch": 0.9825997952917093,
      "grad_norm": 0.9791928313243706,
      "learning_rate": 1.0343254798702018e-07,
      "loss": 0.6218,
      "step": 960
    },
    {
      "epoch": 0.9928352098259979,
      "grad_norm": 1.0874653472043414,
      "learning_rate": 2.0436776263471624e-08,
      "loss": 0.6047,
      "step": 970
    },
    {
      "epoch": 1.0,
      "step": 977,
      "total_flos": 56817270915072.0,
      "train_loss": 0.706230254353862,
      "train_runtime": 8491.106,
      "train_samples_per_second": 7.363,
      "train_steps_per_second": 0.115
    }
  ],
  "logging_steps": 10,
  "max_steps": 977,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 56817270915072.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}