{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 2376,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008417508417508417,
      "grad_norm": NaN,
      "learning_rate": 4.990179573512907e-05,
      "loss": 3.4797,
      "step": 10
    },
    {
      "epoch": 0.016835016835016835,
      "grad_norm": 1.8723673820495605,
      "learning_rate": 4.97615039281706e-05,
      "loss": 3.4589,
      "step": 20
    },
    {
      "epoch": 0.025252525252525252,
      "grad_norm": 1.6116461753845215,
      "learning_rate": 4.962121212121213e-05,
      "loss": 3.3366,
      "step": 30
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 1.6241545677185059,
      "learning_rate": 4.9480920314253646e-05,
      "loss": 3.0591,
      "step": 40
    },
    {
      "epoch": 0.04208754208754209,
      "grad_norm": 1.6978979110717773,
      "learning_rate": 4.934062850729518e-05,
      "loss": 3.2064,
      "step": 50
    },
    {
      "epoch": 0.050505050505050504,
      "grad_norm": 2.229762077331543,
      "learning_rate": 4.92003367003367e-05,
      "loss": 3.0569,
      "step": 60
    },
    {
      "epoch": 0.058922558922558925,
      "grad_norm": 1.3693021535873413,
      "learning_rate": 4.906004489337823e-05,
      "loss": 2.9715,
      "step": 70
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 1.712484359741211,
      "learning_rate": 4.891975308641975e-05,
      "loss": 2.9787,
      "step": 80
    },
    {
      "epoch": 0.07575757575757576,
      "grad_norm": 1.933789610862732,
      "learning_rate": 4.877946127946128e-05,
      "loss": 2.9016,
      "step": 90
    },
    {
      "epoch": 0.08417508417508418,
      "grad_norm": 2.0508992671966553,
      "learning_rate": 4.863916947250281e-05,
      "loss": 2.93,
      "step": 100
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 1.8941344022750854,
      "learning_rate": 4.8498877665544335e-05,
      "loss": 2.852,
      "step": 110
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 1.5971471071243286,
      "learning_rate": 4.835858585858586e-05,
      "loss": 2.8484,
      "step": 120
    },
    {
      "epoch": 0.10942760942760943,
      "grad_norm": 1.8011534214019775,
      "learning_rate": 4.8218294051627386e-05,
      "loss": 2.8801,
      "step": 130
    },
    {
      "epoch": 0.11784511784511785,
      "grad_norm": 2.071338176727295,
      "learning_rate": 4.807800224466891e-05,
      "loss": 2.7344,
      "step": 140
    },
    {
      "epoch": 0.12626262626262627,
      "grad_norm": 1.5685261487960815,
      "learning_rate": 4.793771043771044e-05,
      "loss": 2.8886,
      "step": 150
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 1.719056487083435,
      "learning_rate": 4.779741863075197e-05,
      "loss": 2.7326,
      "step": 160
    },
    {
      "epoch": 0.14309764309764308,
      "grad_norm": 1.8598765134811401,
      "learning_rate": 4.765712682379349e-05,
      "loss": 2.7544,
      "step": 170
    },
    {
      "epoch": 0.15151515151515152,
      "grad_norm": 1.7602612972259521,
      "learning_rate": 4.751683501683502e-05,
      "loss": 2.7759,
      "step": 180
    },
    {
      "epoch": 0.15993265993265993,
      "grad_norm": 2.0498409271240234,
      "learning_rate": 4.7376543209876543e-05,
      "loss": 2.7495,
      "step": 190
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 1.8029284477233887,
      "learning_rate": 4.723625140291807e-05,
      "loss": 2.6568,
      "step": 200
    },
    {
      "epoch": 0.17676767676767677,
      "grad_norm": 2.052203416824341,
      "learning_rate": 4.70959595959596e-05,
      "loss": 2.6162,
      "step": 210
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 1.693206787109375,
      "learning_rate": 4.6955667789001126e-05,
      "loss": 2.7206,
      "step": 220
    },
    {
      "epoch": 0.1936026936026936,
      "grad_norm": 1.7983921766281128,
      "learning_rate": 4.681537598204265e-05,
      "loss": 2.699,
      "step": 230
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 2.1269702911376953,
      "learning_rate": 4.6675084175084176e-05,
      "loss": 2.8926,
      "step": 240
    },
    {
      "epoch": 0.21043771043771045,
      "grad_norm": 2.1926703453063965,
      "learning_rate": 4.65347923681257e-05,
      "loss": 2.6839,
      "step": 250
    },
    {
      "epoch": 0.21885521885521886,
      "grad_norm": 1.9844324588775635,
      "learning_rate": 4.639450056116723e-05,
      "loss": 2.6166,
      "step": 260
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 2.1632473468780518,
      "learning_rate": 4.625420875420876e-05,
      "loss": 2.6975,
      "step": 270
    },
    {
      "epoch": 0.2356902356902357,
      "grad_norm": 1.8100026845932007,
      "learning_rate": 4.6113916947250283e-05,
      "loss": 2.7679,
      "step": 280
    },
    {
      "epoch": 0.2441077441077441,
      "grad_norm": 1.765960693359375,
      "learning_rate": 4.597362514029181e-05,
      "loss": 2.6372,
      "step": 290
    },
    {
      "epoch": 0.25252525252525254,
      "grad_norm": 2.0554540157318115,
      "learning_rate": 4.5833333333333334e-05,
      "loss": 2.707,
      "step": 300
    },
    {
      "epoch": 0.2609427609427609,
      "grad_norm": 1.662891149520874,
      "learning_rate": 4.5693041526374866e-05,
      "loss": 2.5671,
      "step": 310
    },
    {
      "epoch": 0.26936026936026936,
      "grad_norm": 1.9311376810073853,
      "learning_rate": 4.555274971941639e-05,
      "loss": 2.6173,
      "step": 320
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 2.077493667602539,
      "learning_rate": 4.541245791245791e-05,
      "loss": 2.7469,
      "step": 330
    },
    {
      "epoch": 0.28619528619528617,
      "grad_norm": 1.8855682611465454,
      "learning_rate": 4.527216610549944e-05,
      "loss": 2.6762,
      "step": 340
    },
    {
      "epoch": 0.2946127946127946,
      "grad_norm": 3.0554871559143066,
      "learning_rate": 4.5131874298540966e-05,
      "loss": 2.6689,
      "step": 350
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 2.175938129425049,
      "learning_rate": 4.49915824915825e-05,
      "loss": 2.5579,
      "step": 360
    },
    {
      "epoch": 0.3114478114478115,
      "grad_norm": 2.187106132507324,
      "learning_rate": 4.485129068462402e-05,
      "loss": 2.6166,
      "step": 370
    },
    {
      "epoch": 0.31986531986531985,
      "grad_norm": 2.1227610111236572,
      "learning_rate": 4.471099887766554e-05,
      "loss": 2.6637,
      "step": 380
    },
    {
      "epoch": 0.3282828282828283,
      "grad_norm": 2.3033812046051025,
      "learning_rate": 4.4570707070707074e-05,
      "loss": 2.6204,
      "step": 390
    },
    {
      "epoch": 0.3367003367003367,
      "grad_norm": 2.34395432472229,
      "learning_rate": 4.44304152637486e-05,
      "loss": 2.6941,
      "step": 400
    },
    {
      "epoch": 0.3451178451178451,
      "grad_norm": 1.7339164018630981,
      "learning_rate": 4.429012345679013e-05,
      "loss": 2.5516,
      "step": 410
    },
    {
      "epoch": 0.35353535353535354,
      "grad_norm": 2.3480944633483887,
      "learning_rate": 4.414983164983165e-05,
      "loss": 2.5533,
      "step": 420
    },
    {
      "epoch": 0.36195286195286197,
      "grad_norm": 2.076554298400879,
      "learning_rate": 4.4009539842873175e-05,
      "loss": 2.5942,
      "step": 430
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 2.461144208908081,
      "learning_rate": 4.3869248035914707e-05,
      "loss": 2.7073,
      "step": 440
    },
    {
      "epoch": 0.3787878787878788,
      "grad_norm": 2.3409440517425537,
      "learning_rate": 4.372895622895623e-05,
      "loss": 2.551,
      "step": 450
    },
    {
      "epoch": 0.3872053872053872,
      "grad_norm": 2.0938796997070312,
      "learning_rate": 4.358866442199776e-05,
      "loss": 2.5157,
      "step": 460
    },
    {
      "epoch": 0.3956228956228956,
      "grad_norm": 2.0075490474700928,
      "learning_rate": 4.344837261503928e-05,
      "loss": 2.6791,
      "step": 470
    },
    {
      "epoch": 0.40404040404040403,
      "grad_norm": 2.0483977794647217,
      "learning_rate": 4.330808080808081e-05,
      "loss": 2.5285,
      "step": 480
    },
    {
      "epoch": 0.41245791245791247,
      "grad_norm": 2.0210118293762207,
      "learning_rate": 4.316778900112234e-05,
      "loss": 2.4894,
      "step": 490
    },
    {
      "epoch": 0.4208754208754209,
      "grad_norm": 2.2782247066497803,
      "learning_rate": 4.3027497194163864e-05,
      "loss": 2.541,
      "step": 500
    },
    {
      "epoch": 0.4292929292929293,
      "grad_norm": 2.6043848991394043,
      "learning_rate": 4.288720538720539e-05,
      "loss": 2.5162,
      "step": 510
    },
    {
      "epoch": 0.4377104377104377,
      "grad_norm": 2.8767223358154297,
      "learning_rate": 4.2746913580246915e-05,
      "loss": 2.5854,
      "step": 520
    },
    {
      "epoch": 0.44612794612794615,
      "grad_norm": 2.8873238563537598,
      "learning_rate": 4.260662177328844e-05,
      "loss": 2.6396,
      "step": 530
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 2.052957057952881,
      "learning_rate": 4.246632996632997e-05,
      "loss": 2.4754,
      "step": 540
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 2.027665376663208,
      "learning_rate": 4.23260381593715e-05,
      "loss": 2.4765,
      "step": 550
    },
    {
      "epoch": 0.4713804713804714,
      "grad_norm": 2.368720293045044,
      "learning_rate": 4.218574635241302e-05,
      "loss": 2.4542,
      "step": 560
    },
    {
      "epoch": 0.4797979797979798,
      "grad_norm": 2.33085298538208,
      "learning_rate": 4.204545454545455e-05,
      "loss": 2.4622,
      "step": 570
    },
    {
      "epoch": 0.4882154882154882,
      "grad_norm": 2.237562417984009,
      "learning_rate": 4.190516273849607e-05,
      "loss": 2.5542,
      "step": 580
    },
    {
      "epoch": 0.49663299663299665,
      "grad_norm": 2.0441579818725586,
      "learning_rate": 4.17648709315376e-05,
      "loss": 2.4717,
      "step": 590
    },
    {
      "epoch": 0.5050505050505051,
      "grad_norm": 2.248406171798706,
      "learning_rate": 4.162457912457913e-05,
      "loss": 2.4661,
      "step": 600
    },
    {
      "epoch": 0.5134680134680135,
      "grad_norm": 2.1775243282318115,
      "learning_rate": 4.1484287317620655e-05,
      "loss": 2.5614,
      "step": 610
    },
    {
      "epoch": 0.5218855218855218,
      "grad_norm": 2.319425344467163,
      "learning_rate": 4.134399551066218e-05,
      "loss": 2.5012,
      "step": 620
    },
    {
      "epoch": 0.5303030303030303,
      "grad_norm": 2.232248544692993,
      "learning_rate": 4.1203703703703705e-05,
      "loss": 2.5689,
      "step": 630
    },
    {
      "epoch": 0.5387205387205387,
      "grad_norm": 2.3449838161468506,
      "learning_rate": 4.106341189674523e-05,
      "loss": 2.4287,
      "step": 640
    },
    {
      "epoch": 0.5471380471380471,
      "grad_norm": 2.412785768508911,
      "learning_rate": 4.092312008978676e-05,
      "loss": 2.5041,
      "step": 650
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 2.432955503463745,
      "learning_rate": 4.078282828282828e-05,
      "loss": 2.4476,
      "step": 660
    },
    {
      "epoch": 0.563973063973064,
      "grad_norm": 2.642298698425293,
      "learning_rate": 4.064253647586981e-05,
      "loss": 2.421,
      "step": 670
    },
    {
      "epoch": 0.5723905723905723,
      "grad_norm": 2.232794761657715,
      "learning_rate": 4.050224466891134e-05,
      "loss": 2.5912,
      "step": 680
    },
    {
      "epoch": 0.5808080808080808,
      "grad_norm": 2.8323323726654053,
      "learning_rate": 4.036195286195286e-05,
      "loss": 2.3986,
      "step": 690
    },
    {
      "epoch": 0.5892255892255892,
      "grad_norm": 4.2033891677856445,
      "learning_rate": 4.0221661054994395e-05,
      "loss": 2.5413,
      "step": 700
    },
    {
      "epoch": 0.5976430976430976,
      "grad_norm": 2.3608999252319336,
      "learning_rate": 4.008136924803591e-05,
      "loss": 2.5453,
      "step": 710
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 2.5277252197265625,
      "learning_rate": 3.9941077441077445e-05,
      "loss": 2.4956,
      "step": 720
    },
    {
      "epoch": 0.6144781144781145,
      "grad_norm": 2.5772793292999268,
      "learning_rate": 3.980078563411897e-05,
      "loss": 2.5238,
      "step": 730
    },
    {
      "epoch": 0.622895622895623,
      "grad_norm": 2.718047618865967,
      "learning_rate": 3.9660493827160496e-05,
      "loss": 2.4327,
      "step": 740
    },
    {
      "epoch": 0.6313131313131313,
      "grad_norm": 2.5964958667755127,
      "learning_rate": 3.952020202020202e-05,
      "loss": 2.5208,
      "step": 750
    },
    {
      "epoch": 0.6397306397306397,
      "grad_norm": 2.4600930213928223,
      "learning_rate": 3.9379910213243546e-05,
      "loss": 2.6661,
      "step": 760
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 2.449575662612915,
      "learning_rate": 3.923961840628507e-05,
      "loss": 2.5442,
      "step": 770
    },
    {
      "epoch": 0.6565656565656566,
      "grad_norm": 2.3219118118286133,
      "learning_rate": 3.90993265993266e-05,
      "loss": 2.3805,
      "step": 780
    },
    {
      "epoch": 0.664983164983165,
      "grad_norm": 2.774872064590454,
      "learning_rate": 3.895903479236813e-05,
      "loss": 2.4343,
      "step": 790
    },
    {
      "epoch": 0.6734006734006734,
      "grad_norm": 2.466688632965088,
      "learning_rate": 3.881874298540965e-05,
      "loss": 2.4088,
      "step": 800
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 3.1128170490264893,
      "learning_rate": 3.867845117845118e-05,
      "loss": 2.5768,
      "step": 810
    },
    {
      "epoch": 0.6902356902356902,
      "grad_norm": 4.245325088500977,
      "learning_rate": 3.8538159371492704e-05,
      "loss": 2.3917,
      "step": 820
    },
    {
      "epoch": 0.6986531986531986,
      "grad_norm": 2.6386542320251465,
      "learning_rate": 3.8397867564534236e-05,
      "loss": 2.3603,
      "step": 830
    },
    {
      "epoch": 0.7070707070707071,
      "grad_norm": 3.0349717140197754,
      "learning_rate": 3.825757575757576e-05,
      "loss": 2.5057,
      "step": 840
    },
    {
      "epoch": 0.7154882154882155,
      "grad_norm": 2.524481773376465,
      "learning_rate": 3.8117283950617286e-05,
      "loss": 2.5321,
      "step": 850
    },
    {
      "epoch": 0.7239057239057239,
      "grad_norm": 3.5061841011047363,
      "learning_rate": 3.797699214365881e-05,
      "loss": 2.6322,
      "step": 860
    },
    {
      "epoch": 0.7323232323232324,
      "grad_norm": 2.5284855365753174,
      "learning_rate": 3.7836700336700336e-05,
      "loss": 2.5965,
      "step": 870
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 2.923661231994629,
      "learning_rate": 3.769640852974187e-05,
      "loss": 2.4343,
      "step": 880
    },
    {
      "epoch": 0.7491582491582491,
      "grad_norm": 2.788609743118286,
      "learning_rate": 3.7556116722783393e-05,
      "loss": 2.4594,
      "step": 890
    },
    {
      "epoch": 0.7575757575757576,
      "grad_norm": 2.8142261505126953,
      "learning_rate": 3.741582491582492e-05,
      "loss": 2.4316,
      "step": 900
    },
    {
      "epoch": 0.765993265993266,
      "grad_norm": 2.7626090049743652,
      "learning_rate": 3.7275533108866444e-05,
      "loss": 2.454,
      "step": 910
    },
    {
      "epoch": 0.7744107744107744,
      "grad_norm": 2.700515031814575,
      "learning_rate": 3.713524130190797e-05,
      "loss": 2.5807,
      "step": 920
    },
    {
      "epoch": 0.7828282828282829,
      "grad_norm": 2.9090945720672607,
      "learning_rate": 3.69949494949495e-05,
      "loss": 2.461,
      "step": 930
    },
    {
      "epoch": 0.7912457912457912,
      "grad_norm": 2.439922332763672,
      "learning_rate": 3.6854657687991026e-05,
      "loss": 2.454,
      "step": 940
    },
    {
      "epoch": 0.7996632996632996,
      "grad_norm": 2.9203062057495117,
      "learning_rate": 3.6714365881032544e-05,
      "loss": 2.4361,
      "step": 950
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 2.6928439140319824,
      "learning_rate": 3.6574074074074076e-05,
      "loss": 2.4572,
      "step": 960
    },
    {
      "epoch": 0.8164983164983165,
      "grad_norm": 2.66032338142395,
      "learning_rate": 3.64337822671156e-05,
      "loss": 2.4882,
      "step": 970
    },
    {
      "epoch": 0.8249158249158249,
      "grad_norm": 2.4645493030548096,
      "learning_rate": 3.6293490460157134e-05,
      "loss": 2.4432,
      "step": 980
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 2.7508137226104736,
      "learning_rate": 3.615319865319866e-05,
      "loss": 2.3677,
      "step": 990
    },
    {
      "epoch": 0.8417508417508418,
      "grad_norm": 3.1264898777008057,
      "learning_rate": 3.601290684624018e-05,
      "loss": 2.444,
      "step": 1000
    },
    {
      "epoch": 0.8501683501683501,
      "grad_norm": 2.5735745429992676,
      "learning_rate": 3.587261503928171e-05,
      "loss": 2.4514,
      "step": 1010
    },
    {
      "epoch": 0.8585858585858586,
      "grad_norm": 2.614163637161255,
      "learning_rate": 3.5732323232323234e-05,
      "loss": 2.4012,
      "step": 1020
    },
    {
      "epoch": 0.867003367003367,
      "grad_norm": 3.058293342590332,
      "learning_rate": 3.559203142536476e-05,
      "loss": 2.5346,
      "step": 1030
    },
    {
      "epoch": 0.8754208754208754,
      "grad_norm": 2.299180507659912,
      "learning_rate": 3.5451739618406285e-05,
      "loss": 2.4102,
      "step": 1040
    },
    {
      "epoch": 0.8838383838383839,
      "grad_norm": 2.3540875911712646,
      "learning_rate": 3.531144781144781e-05,
      "loss": 2.3884,
      "step": 1050
    },
    {
      "epoch": 0.8922558922558923,
      "grad_norm": 2.4985461235046387,
      "learning_rate": 3.517115600448934e-05,
      "loss": 2.5071,
      "step": 1060
    },
    {
      "epoch": 0.9006734006734006,
      "grad_norm": 2.615652322769165,
      "learning_rate": 3.503086419753087e-05,
      "loss": 2.4177,
      "step": 1070
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 2.617262601852417,
      "learning_rate": 3.489057239057239e-05,
      "loss": 2.3434,
      "step": 1080
    },
    {
      "epoch": 0.9175084175084175,
      "grad_norm": 2.422133445739746,
      "learning_rate": 3.475028058361392e-05,
      "loss": 2.4621,
      "step": 1090
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 2.65753173828125,
      "learning_rate": 3.460998877665544e-05,
      "loss": 2.398,
      "step": 1100
    },
    {
      "epoch": 0.9343434343434344,
      "grad_norm": 2.8853819370269775,
      "learning_rate": 3.4469696969696974e-05,
      "loss": 2.5412,
      "step": 1110
    },
    {
      "epoch": 0.9427609427609428,
      "grad_norm": 2.287621021270752,
      "learning_rate": 3.43294051627385e-05,
      "loss": 2.3842,
      "step": 1120
    },
    {
      "epoch": 0.9511784511784511,
      "grad_norm": 2.8708698749542236,
      "learning_rate": 3.4189113355780025e-05,
      "loss": 2.365,
      "step": 1130
    },
    {
      "epoch": 0.9595959595959596,
      "grad_norm": 2.9824109077453613,
      "learning_rate": 3.404882154882155e-05,
      "loss": 2.5138,
      "step": 1140
    },
    {
      "epoch": 0.968013468013468,
      "grad_norm": 3.031399726867676,
      "learning_rate": 3.3908529741863075e-05,
      "loss": 2.4326,
      "step": 1150
    },
    {
      "epoch": 0.9764309764309764,
      "grad_norm": 2.725060224533081,
      "learning_rate": 3.37682379349046e-05,
      "loss": 2.3802,
      "step": 1160
    },
    {
      "epoch": 0.9848484848484849,
      "grad_norm": 2.43306303024292,
      "learning_rate": 3.362794612794613e-05,
      "loss": 2.4778,
      "step": 1170
    },
    {
      "epoch": 0.9932659932659933,
      "grad_norm": 2.6997814178466797,
      "learning_rate": 3.348765432098766e-05,
      "loss": 2.4728,
      "step": 1180
    },
    {
      "epoch": 1.0016835016835017,
      "grad_norm": 2.8203701972961426,
      "learning_rate": 3.334736251402918e-05,
      "loss": 2.4017,
      "step": 1190
    },
    {
      "epoch": 1.0101010101010102,
      "grad_norm": 2.8343305587768555,
      "learning_rate": 3.320707070707071e-05,
      "loss": 2.3664,
      "step": 1200
    },
    {
      "epoch": 1.0185185185185186,
      "grad_norm": 3.814268112182617,
      "learning_rate": 3.306677890011223e-05,
      "loss": 2.5748,
      "step": 1210
    },
    {
      "epoch": 1.026936026936027,
      "grad_norm": 2.555053234100342,
      "learning_rate": 3.2926487093153765e-05,
      "loss": 2.4044,
      "step": 1220
    },
    {
      "epoch": 1.0353535353535352,
      "grad_norm": 3.142622470855713,
      "learning_rate": 3.278619528619529e-05,
      "loss": 2.3966,
      "step": 1230
    },
    {
      "epoch": 1.0437710437710437,
      "grad_norm": 2.609618663787842,
      "learning_rate": 3.2645903479236815e-05,
      "loss": 2.556,
      "step": 1240
    },
    {
      "epoch": 1.0521885521885521,
      "grad_norm": 3.1092679500579834,
      "learning_rate": 3.250561167227834e-05,
      "loss": 2.2779,
      "step": 1250
    },
    {
      "epoch": 1.0606060606060606,
      "grad_norm": 3.010402202606201,
      "learning_rate": 3.2365319865319865e-05,
      "loss": 2.3634,
      "step": 1260
    },
    {
      "epoch": 1.069023569023569,
      "grad_norm": 2.553971290588379,
      "learning_rate": 3.22250280583614e-05,
      "loss": 2.3588,
      "step": 1270
    },
    {
      "epoch": 1.0774410774410774,
      "grad_norm": 2.712143898010254,
      "learning_rate": 3.208473625140292e-05,
      "loss": 2.3728,
      "step": 1280
    },
    {
      "epoch": 1.0858585858585859,
      "grad_norm": 2.4108312129974365,
      "learning_rate": 3.194444444444444e-05,
      "loss": 2.2615,
      "step": 1290
    },
    {
      "epoch": 1.0942760942760943,
      "grad_norm": 2.677093267440796,
      "learning_rate": 3.180415263748597e-05,
      "loss": 2.267,
      "step": 1300
    },
    {
      "epoch": 1.1026936026936027,
      "grad_norm": 2.9490318298339844,
      "learning_rate": 3.16638608305275e-05,
      "loss": 2.6672,
      "step": 1310
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 2.6774485111236572,
      "learning_rate": 3.152356902356903e-05,
      "loss": 2.4183,
      "step": 1320
    },
    {
      "epoch": 1.1195286195286196,
      "grad_norm": 3.1193931102752686,
      "learning_rate": 3.138327721661055e-05,
      "loss": 2.4276,
      "step": 1330
    },
    {
      "epoch": 1.127946127946128,
      "grad_norm": 2.6562869548797607,
      "learning_rate": 3.1242985409652074e-05,
      "loss": 2.4551,
      "step": 1340
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 2.88474440574646,
      "learning_rate": 3.1102693602693605e-05,
      "loss": 2.3054,
      "step": 1350
    },
    {
      "epoch": 1.144781144781145,
      "grad_norm": 2.933032989501953,
      "learning_rate": 3.096240179573513e-05,
      "loss": 2.4734,
      "step": 1360
    },
    {
      "epoch": 1.1531986531986531,
      "grad_norm": 2.922410488128662,
      "learning_rate": 3.082210998877666e-05,
      "loss": 2.499,
      "step": 1370
    },
    {
      "epoch": 1.1616161616161615,
      "grad_norm": 2.990966320037842,
      "learning_rate": 3.068181818181818e-05,
      "loss": 2.4067,
      "step": 1380
    },
    {
      "epoch": 1.17003367003367,
      "grad_norm": 2.89037823677063,
      "learning_rate": 3.0541526374859706e-05,
      "loss": 2.3944,
      "step": 1390
    },
    {
      "epoch": 1.1784511784511784,
      "grad_norm": 2.6384222507476807,
      "learning_rate": 3.0401234567901238e-05,
      "loss": 2.2478,
      "step": 1400
    },
    {
      "epoch": 1.1868686868686869,
      "grad_norm": 3.4815266132354736,
      "learning_rate": 3.0260942760942763e-05,
      "loss": 2.3356,
      "step": 1410
    },
    {
      "epoch": 1.1952861952861953,
      "grad_norm": 3.02565336227417,
      "learning_rate": 3.0120650953984285e-05,
      "loss": 2.4739,
      "step": 1420
    },
    {
      "epoch": 1.2037037037037037,
      "grad_norm": 2.780487060546875,
      "learning_rate": 2.9980359147025817e-05,
      "loss": 2.3009,
      "step": 1430
    },
    {
      "epoch": 1.2121212121212122,
      "grad_norm": 3.0833890438079834,
      "learning_rate": 2.984006734006734e-05,
      "loss": 2.4,
      "step": 1440
    },
    {
      "epoch": 1.2205387205387206,
      "grad_norm": 2.707517623901367,
      "learning_rate": 2.969977553310887e-05,
      "loss": 2.4067,
      "step": 1450
    },
    {
      "epoch": 1.228956228956229,
      "grad_norm": 2.5139541625976562,
      "learning_rate": 2.9559483726150396e-05,
      "loss": 2.3598,
      "step": 1460
    },
    {
      "epoch": 1.2373737373737375,
      "grad_norm": 3.169325590133667,
      "learning_rate": 2.9419191919191918e-05,
      "loss": 2.4147,
      "step": 1470
    },
    {
      "epoch": 1.2457912457912457,
      "grad_norm": 2.7292799949645996,
      "learning_rate": 2.927890011223345e-05,
      "loss": 2.4204,
      "step": 1480
    },
    {
      "epoch": 1.2542087542087543,
      "grad_norm": 2.791738271713257,
      "learning_rate": 2.913860830527497e-05,
      "loss": 2.4267,
      "step": 1490
    },
    {
      "epoch": 1.2626262626262625,
      "grad_norm": 2.608445882797241,
      "learning_rate": 2.8998316498316503e-05,
      "loss": 2.3114,
      "step": 1500
    },
    {
      "epoch": 1.271043771043771,
      "grad_norm": 2.5103442668914795,
      "learning_rate": 2.8858024691358025e-05,
      "loss": 2.2693,
      "step": 1510
    },
    {
      "epoch": 1.2794612794612794,
      "grad_norm": 2.824044942855835,
      "learning_rate": 2.871773288439955e-05,
      "loss": 2.394,
      "step": 1520
    },
    {
      "epoch": 1.2878787878787878,
      "grad_norm": 3.275538444519043,
      "learning_rate": 2.8577441077441082e-05,
      "loss": 2.5109,
      "step": 1530
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 3.2262158393859863,
      "learning_rate": 2.8437149270482604e-05,
      "loss": 2.3438,
      "step": 1540
    },
    {
      "epoch": 1.3047138047138047,
      "grad_norm": 2.8264598846435547,
      "learning_rate": 2.829685746352413e-05,
      "loss": 2.4934,
      "step": 1550
    },
    {
      "epoch": 1.3131313131313131,
      "grad_norm": 2.9306719303131104,
      "learning_rate": 2.8156565656565658e-05,
      "loss": 2.2246,
      "step": 1560
    },
    {
      "epoch": 1.3215488215488216,
      "grad_norm": 2.6973257064819336,
      "learning_rate": 2.8016273849607183e-05,
      "loss": 2.3807,
      "step": 1570
    },
    {
      "epoch": 1.32996632996633,
      "grad_norm": 3.0139241218566895,
      "learning_rate": 2.787598204264871e-05,
      "loss": 2.5024,
      "step": 1580
    },
    {
      "epoch": 1.3383838383838385,
      "grad_norm": 2.5364763736724854,
      "learning_rate": 2.7735690235690237e-05,
      "loss": 2.2749,
      "step": 1590
    },
    {
      "epoch": 1.3468013468013469,
      "grad_norm": 2.8624165058135986,
      "learning_rate": 2.7595398428731762e-05,
      "loss": 2.3387,
      "step": 1600
    },
    {
      "epoch": 1.355218855218855,
      "grad_norm": 2.9810757637023926,
      "learning_rate": 2.745510662177329e-05,
      "loss": 2.1873,
      "step": 1610
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 2.5730276107788086,
      "learning_rate": 2.7314814814814816e-05,
      "loss": 2.273,
      "step": 1620
    },
    {
      "epoch": 1.372053872053872,
      "grad_norm": 3.2745449542999268,
      "learning_rate": 2.7174523007856344e-05,
      "loss": 2.2767,
      "step": 1630
    },
    {
      "epoch": 1.3804713804713804,
      "grad_norm": 2.857235908508301,
      "learning_rate": 2.703423120089787e-05,
      "loss": 2.4409,
      "step": 1640
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 2.7736656665802,
      "learning_rate": 2.6893939393939394e-05,
      "loss": 2.3483,
      "step": 1650
    },
    {
      "epoch": 1.3973063973063973,
      "grad_norm": 3.5529961585998535,
      "learning_rate": 2.6753647586980923e-05,
      "loss": 2.4341,
      "step": 1660
    },
    {
      "epoch": 1.4057239057239057,
      "grad_norm": 2.9840221405029297,
      "learning_rate": 2.6613355780022448e-05,
      "loss": 2.3764,
      "step": 1670
    },
    {
      "epoch": 1.4141414141414141,
      "grad_norm": 3.015062093734741,
      "learning_rate": 2.6473063973063973e-05,
      "loss": 2.3547,
      "step": 1680
    },
    {
      "epoch": 1.4225589225589226,
      "grad_norm": 3.440065860748291,
      "learning_rate": 2.6332772166105502e-05,
      "loss": 2.3314,
      "step": 1690
    },
    {
      "epoch": 1.430976430976431,
      "grad_norm": 3.125835657119751,
      "learning_rate": 2.6192480359147027e-05,
      "loss": 2.3632,
      "step": 1700
    },
    {
      "epoch": 1.4393939393939394,
      "grad_norm": 2.9020016193389893,
      "learning_rate": 2.6052188552188556e-05,
      "loss": 2.4821,
      "step": 1710
    },
    {
      "epoch": 1.4478114478114479,
      "grad_norm": 3.136042594909668,
      "learning_rate": 2.591189674523008e-05,
      "loss": 2.4106,
      "step": 1720
    },
    {
      "epoch": 1.4562289562289563,
      "grad_norm": 2.7179207801818848,
      "learning_rate": 2.5771604938271603e-05,
      "loss": 2.3794,
      "step": 1730
    },
    {
      "epoch": 1.4646464646464645,
      "grad_norm": 2.6184420585632324,
      "learning_rate": 2.5631313131313135e-05,
      "loss": 2.3573,
      "step": 1740
    },
    {
      "epoch": 1.4730639730639732,
      "grad_norm": 2.7196948528289795,
      "learning_rate": 2.549102132435466e-05,
      "loss": 2.4751,
      "step": 1750
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 3.360743999481201,
      "learning_rate": 2.5350729517396188e-05,
      "loss": 2.4172,
      "step": 1760
    },
    {
      "epoch": 1.4898989898989898,
      "grad_norm": 3.908057689666748,
      "learning_rate": 2.5210437710437713e-05,
      "loss": 2.3338,
      "step": 1770
    },
    {
      "epoch": 1.4983164983164983,
      "grad_norm": 3.2845561504364014,
      "learning_rate": 2.5070145903479235e-05,
      "loss": 2.4202,
      "step": 1780
    },
    {
      "epoch": 1.5067340067340067,
      "grad_norm": 2.720625638961792,
      "learning_rate": 2.4929854096520764e-05,
      "loss": 2.5369,
      "step": 1790
    },
    {
      "epoch": 1.5151515151515151,
      "grad_norm": 2.977970600128174,
      "learning_rate": 2.478956228956229e-05,
      "loss": 2.2776,
      "step": 1800
    },
    {
      "epoch": 1.5235690235690236,
      "grad_norm": 2.835860252380371,
      "learning_rate": 2.4649270482603818e-05,
      "loss": 2.329,
      "step": 1810
    },
    {
      "epoch": 1.531986531986532,
      "grad_norm": 3.039226531982422,
      "learning_rate": 2.4508978675645343e-05,
      "loss": 2.4787,
      "step": 1820
    },
    {
      "epoch": 1.5404040404040404,
      "grad_norm": 2.7011232376098633,
      "learning_rate": 2.4368686868686868e-05,
      "loss": 2.4924,
      "step": 1830
    },
    {
      "epoch": 1.5488215488215489,
      "grad_norm": 2.741283893585205,
      "learning_rate": 2.4228395061728396e-05,
      "loss": 2.4265,
      "step": 1840
    },
    {
      "epoch": 1.557239057239057,
      "grad_norm": 2.7896602153778076,
      "learning_rate": 2.408810325476992e-05,
      "loss": 2.2275,
      "step": 1850
    },
    {
      "epoch": 1.5656565656565657,
      "grad_norm": 3.505488872528076,
      "learning_rate": 2.394781144781145e-05,
      "loss": 2.4043,
      "step": 1860
    },
    {
      "epoch": 1.574074074074074,
      "grad_norm": 2.921954393386841,
      "learning_rate": 2.3807519640852975e-05,
      "loss": 2.3513,
      "step": 1870
    },
    {
      "epoch": 1.5824915824915826,
      "grad_norm": 3.427619695663452,
      "learning_rate": 2.36672278338945e-05,
      "loss": 2.3622,
      "step": 1880
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 3.277251720428467,
      "learning_rate": 2.352693602693603e-05,
      "loss": 2.3942,
      "step": 1890
    },
    {
      "epoch": 1.5993265993265995,
      "grad_norm": 3.206590175628662,
      "learning_rate": 2.3386644219977554e-05,
      "loss": 2.4197,
      "step": 1900
    },
    {
      "epoch": 1.6077441077441077,
      "grad_norm": 3.070993423461914,
      "learning_rate": 2.3246352413019083e-05,
      "loss": 2.3346,
      "step": 1910
    },
    {
      "epoch": 1.6161616161616161,
      "grad_norm": 2.9139037132263184,
      "learning_rate": 2.3106060606060605e-05,
      "loss": 2.2375,
      "step": 1920
    },
    {
      "epoch": 1.6245791245791246,
      "grad_norm": 3.173426628112793,
      "learning_rate": 2.2965768799102133e-05,
      "loss": 2.3717,
      "step": 1930
    },
    {
      "epoch": 1.632996632996633,
      "grad_norm": 2.910637855529785,
      "learning_rate": 2.282547699214366e-05,
      "loss": 2.28,
      "step": 1940
    },
    {
      "epoch": 1.6414141414141414,
      "grad_norm": 3.881056785583496,
      "learning_rate": 2.2685185185185187e-05,
      "loss": 2.3383,
      "step": 1950
    },
    {
      "epoch": 1.6498316498316499,
      "grad_norm": 3.2495148181915283,
      "learning_rate": 2.2544893378226712e-05,
      "loss": 2.3704,
      "step": 1960
    },
    {
      "epoch": 1.6582491582491583,
      "grad_norm": 2.6956305503845215,
      "learning_rate": 2.2404601571268237e-05,
      "loss": 2.3639,
      "step": 1970
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 3.1080222129821777,
      "learning_rate": 2.2264309764309766e-05,
      "loss": 2.4179,
      "step": 1980
    },
    {
      "epoch": 1.6750841750841752,
      "grad_norm": 2.9564356803894043,
      "learning_rate": 2.212401795735129e-05,
      "loss": 2.3974,
      "step": 1990
    },
    {
      "epoch": 1.6835016835016834,
      "grad_norm": 2.73732590675354,
      "learning_rate": 2.198372615039282e-05,
      "loss": 2.2624,
      "step": 2000
    },
    {
      "epoch": 1.691919191919192,
      "grad_norm": 2.9970414638519287,
      "learning_rate": 2.1843434343434345e-05,
      "loss": 2.3246,
      "step": 2010
    },
    {
      "epoch": 1.7003367003367003,
      "grad_norm": 3.410376787185669,
      "learning_rate": 2.170314253647587e-05,
      "loss": 2.3357,
      "step": 2020
    },
    {
      "epoch": 1.708754208754209,
      "grad_norm": 2.965650796890259,
      "learning_rate": 2.15628507295174e-05,
      "loss": 2.3428,
      "step": 2030
    },
    {
      "epoch": 1.7171717171717171,
      "grad_norm": 3.167226791381836,
      "learning_rate": 2.1422558922558924e-05,
      "loss": 2.1527,
      "step": 2040
    },
    {
      "epoch": 1.7255892255892256,
      "grad_norm": 4.487528324127197,
      "learning_rate": 2.128226711560045e-05,
      "loss": 2.4263,
      "step": 2050
    },
    {
      "epoch": 1.734006734006734,
      "grad_norm": 3.309645414352417,
      "learning_rate": 2.1141975308641977e-05,
      "loss": 2.313,
      "step": 2060
    },
    {
      "epoch": 1.7424242424242424,
      "grad_norm": 3.7654778957366943,
      "learning_rate": 2.1001683501683502e-05,
      "loss": 2.3591,
      "step": 2070
    },
    {
      "epoch": 1.7508417508417509,
      "grad_norm": 3.188965320587158,
      "learning_rate": 2.086139169472503e-05,
      "loss": 2.4313,
      "step": 2080
    },
    {
      "epoch": 1.7592592592592593,
      "grad_norm": 3.119352102279663,
      "learning_rate": 2.0721099887766553e-05,
      "loss": 2.3364,
      "step": 2090
    },
    {
      "epoch": 1.7676767676767677,
      "grad_norm": 3.435917854309082,
      "learning_rate": 2.058080808080808e-05,
      "loss": 2.4577,
      "step": 2100
    },
    {
      "epoch": 1.776094276094276,
      "grad_norm": 3.3111941814422607,
      "learning_rate": 2.0440516273849607e-05,
      "loss": 2.3218,
      "step": 2110
    },
    {
      "epoch": 1.7845117845117846,
      "grad_norm": 4.261884689331055,
      "learning_rate": 2.0300224466891135e-05,
      "loss": 2.4014,
      "step": 2120
    },
    {
      "epoch": 1.7929292929292928,
      "grad_norm": 2.9653213024139404,
      "learning_rate": 2.0159932659932664e-05,
      "loss": 2.309,
      "step": 2130
    },
    {
      "epoch": 1.8013468013468015,
      "grad_norm": 2.784932851791382,
      "learning_rate": 2.0019640852974185e-05,
      "loss": 2.3611,
      "step": 2140
    },
    {
      "epoch": 1.8097643097643097,
      "grad_norm": 3.5843029022216797,
      "learning_rate": 1.9879349046015714e-05,
      "loss": 2.4837,
      "step": 2150
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 3.4695231914520264,
      "learning_rate": 1.973905723905724e-05,
      "loss": 2.284,
      "step": 2160
    },
    {
      "epoch": 1.8265993265993266,
      "grad_norm": 3.2327258586883545,
      "learning_rate": 1.9598765432098768e-05,
      "loss": 2.3084,
      "step": 2170
    },
    {
      "epoch": 1.835016835016835,
      "grad_norm": 2.878326177597046,
      "learning_rate": 1.9458473625140293e-05,
      "loss": 2.5618,
      "step": 2180
    },
    {
      "epoch": 1.8434343434343434,
      "grad_norm": 3.4700164794921875,
      "learning_rate": 1.9318181818181818e-05,
      "loss": 2.3738,
      "step": 2190
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 3.615539789199829,
      "learning_rate": 1.9177890011223347e-05,
      "loss": 2.2962,
      "step": 2200
    },
    {
      "epoch": 1.8602693602693603,
      "grad_norm": 3.0230872631073,
      "learning_rate": 1.9037598204264872e-05,
      "loss": 2.3229,
      "step": 2210
    },
    {
      "epoch": 1.8686868686868687,
      "grad_norm": 3.3907663822174072,
      "learning_rate": 1.8897306397306397e-05,
      "loss": 2.4199,
      "step": 2220
    },
    {
      "epoch": 1.8771043771043772,
      "grad_norm": 3.1739697456359863,
      "learning_rate": 1.8757014590347925e-05,
      "loss": 2.3878,
      "step": 2230
    },
    {
      "epoch": 1.8855218855218854,
      "grad_norm": 3.4084649085998535,
      "learning_rate": 1.861672278338945e-05,
      "loss": 2.3386,
      "step": 2240
    },
    {
      "epoch": 1.893939393939394,
      "grad_norm": 2.9609739780426025,
      "learning_rate": 1.847643097643098e-05,
      "loss": 2.3211,
      "step": 2250
    },
    {
      "epoch": 1.9023569023569022,
      "grad_norm": 3.075378894805908,
      "learning_rate": 1.8336139169472504e-05,
      "loss": 2.3675,
      "step": 2260
    },
    {
      "epoch": 1.910774410774411,
      "grad_norm": 2.9113922119140625,
      "learning_rate": 1.819584736251403e-05,
      "loss": 2.3151,
      "step": 2270
    },
    {
      "epoch": 1.9191919191919191,
      "grad_norm": 3.364899158477783,
      "learning_rate": 1.8055555555555555e-05,
      "loss": 2.1976,
      "step": 2280
    },
    {
      "epoch": 1.9276094276094278,
      "grad_norm": 4.041044235229492,
      "learning_rate": 1.7915263748597083e-05,
      "loss": 2.366,
      "step": 2290
    },
    {
      "epoch": 1.936026936026936,
      "grad_norm": 2.874314785003662,
      "learning_rate": 1.777497194163861e-05,
      "loss": 2.2946,
      "step": 2300
    },
    {
      "epoch": 1.9444444444444444,
      "grad_norm": 3.636214256286621,
      "learning_rate": 1.7634680134680134e-05,
      "loss": 2.2318,
      "step": 2310
    },
    {
      "epoch": 1.9528619528619529,
      "grad_norm": 3.3151936531066895,
      "learning_rate": 1.7494388327721662e-05,
      "loss": 2.484,
      "step": 2320
    },
    {
      "epoch": 1.9612794612794613,
      "grad_norm": 2.95894193649292,
      "learning_rate": 1.7354096520763187e-05,
      "loss": 2.2886,
      "step": 2330
    },
    {
      "epoch": 1.9696969696969697,
      "grad_norm": 3.3470945358276367,
      "learning_rate": 1.7213804713804716e-05,
      "loss": 2.331,
      "step": 2340
    },
    {
      "epoch": 1.9781144781144782,
      "grad_norm": 2.9090137481689453,
      "learning_rate": 1.707351290684624e-05,
      "loss": 2.3689,
      "step": 2350
    },
    {
      "epoch": 1.9865319865319866,
      "grad_norm": 2.894779682159424,
      "learning_rate": 1.6933221099887766e-05,
      "loss": 2.4426,
      "step": 2360
    },
    {
      "epoch": 1.9949494949494948,
      "grad_norm": 3.315685749053955,
      "learning_rate": 1.6792929292929295e-05,
      "loss": 2.3809,
      "step": 2370
    }
  ],
  "logging_steps": 10,
  "max_steps": 3564,
  "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": 5099434873454592.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}