{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.3522493384298735,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011761246692149369,
      "grad_norm": 0.25049906969070435,
      "learning_rate": 0.0002,
      "loss": 2.1846,
      "step": 10
    },
    {
      "epoch": 0.023522493384298737,
      "grad_norm": 0.28385764360427856,
      "learning_rate": 0.00019952830188679245,
      "loss": 1.9496,
      "step": 20
    },
    {
      "epoch": 0.035283740076448106,
      "grad_norm": 0.27383577823638916,
      "learning_rate": 0.0001990566037735849,
      "loss": 2.003,
      "step": 30
    },
    {
      "epoch": 0.047044986768597474,
      "grad_norm": 0.3645761013031006,
      "learning_rate": 0.00019858490566037736,
      "loss": 1.9349,
      "step": 40
    },
    {
      "epoch": 0.058806233460746836,
      "grad_norm": 0.6317451596260071,
      "learning_rate": 0.00019811320754716983,
      "loss": 1.7642,
      "step": 50
    },
    {
      "epoch": 0.07056748015289621,
      "grad_norm": 0.18650729954242706,
      "learning_rate": 0.00019764150943396227,
      "loss": 1.9489,
      "step": 60
    },
    {
      "epoch": 0.08232872684504558,
      "grad_norm": 0.2123485505580902,
      "learning_rate": 0.00019716981132075472,
      "loss": 1.9835,
      "step": 70
    },
    {
      "epoch": 0.09408997353719495,
      "grad_norm": 0.2508566379547119,
      "learning_rate": 0.00019669811320754718,
      "loss": 1.8866,
      "step": 80
    },
    {
      "epoch": 0.10585122022934432,
      "grad_norm": 0.31404730677604675,
      "learning_rate": 0.00019622641509433963,
      "loss": 1.8954,
      "step": 90
    },
    {
      "epoch": 0.11761246692149367,
      "grad_norm": 0.5218461155891418,
      "learning_rate": 0.00019575471698113207,
      "loss": 1.7887,
      "step": 100
    },
    {
      "epoch": 0.12937371361364305,
      "grad_norm": 0.2055450826883316,
      "learning_rate": 0.00019528301886792454,
      "loss": 1.8669,
      "step": 110
    },
    {
      "epoch": 0.14113496030579242,
      "grad_norm": 0.22005008161067963,
      "learning_rate": 0.000194811320754717,
      "loss": 1.8794,
      "step": 120
    },
    {
      "epoch": 0.1528962069979418,
      "grad_norm": 0.2914157807826996,
      "learning_rate": 0.00019433962264150945,
      "loss": 1.8953,
      "step": 130
    },
    {
      "epoch": 0.16465745369009116,
      "grad_norm": 0.303595632314682,
      "learning_rate": 0.0001938679245283019,
      "loss": 1.8921,
      "step": 140
    },
    {
      "epoch": 0.17641870038224053,
      "grad_norm": 0.6398317813873291,
      "learning_rate": 0.00019339622641509433,
      "loss": 1.8473,
      "step": 150
    },
    {
      "epoch": 0.1881799470743899,
      "grad_norm": 0.20719175040721893,
      "learning_rate": 0.0001929245283018868,
      "loss": 1.8451,
      "step": 160
    },
    {
      "epoch": 0.19994119376653927,
      "grad_norm": 0.21924979984760284,
      "learning_rate": 0.00019245283018867927,
      "loss": 1.9988,
      "step": 170
    },
    {
      "epoch": 0.21170244045868863,
      "grad_norm": 0.3456704914569855,
      "learning_rate": 0.0001919811320754717,
      "loss": 1.8011,
      "step": 180
    },
    {
      "epoch": 0.22346368715083798,
      "grad_norm": 0.3223501741886139,
      "learning_rate": 0.00019150943396226415,
      "loss": 1.8616,
      "step": 190
    },
    {
      "epoch": 0.23522493384298734,
      "grad_norm": 0.6237074136734009,
      "learning_rate": 0.00019103773584905662,
      "loss": 1.7474,
      "step": 200
    },
    {
      "epoch": 0.2469861805351367,
      "grad_norm": 0.19962406158447266,
      "learning_rate": 0.00019056603773584906,
      "loss": 1.9342,
      "step": 210
    },
    {
      "epoch": 0.2587474272272861,
      "grad_norm": 0.23922637104988098,
      "learning_rate": 0.0001900943396226415,
      "loss": 1.8467,
      "step": 220
    },
    {
      "epoch": 0.27050867391943545,
      "grad_norm": 0.28077131509780884,
      "learning_rate": 0.00018962264150943397,
      "loss": 1.8587,
      "step": 230
    },
    {
      "epoch": 0.28226992061158485,
      "grad_norm": 0.3607043921947479,
      "learning_rate": 0.00018915094339622644,
      "loss": 1.7562,
      "step": 240
    },
    {
      "epoch": 0.2940311673037342,
      "grad_norm": 0.5218331217765808,
      "learning_rate": 0.00018867924528301889,
      "loss": 1.6972,
      "step": 250
    },
    {
      "epoch": 0.3057924139958836,
      "grad_norm": 0.22418326139450073,
      "learning_rate": 0.00018820754716981133,
      "loss": 1.9769,
      "step": 260
    },
    {
      "epoch": 0.3175536606880329,
      "grad_norm": 0.2506936192512512,
      "learning_rate": 0.00018773584905660377,
      "loss": 1.9306,
      "step": 270
    },
    {
      "epoch": 0.3293149073801823,
      "grad_norm": 0.2900485396385193,
      "learning_rate": 0.00018726415094339624,
      "loss": 1.8749,
      "step": 280
    },
    {
      "epoch": 0.34107615407233166,
      "grad_norm": 0.36592498421669006,
      "learning_rate": 0.00018679245283018868,
      "loss": 1.8406,
      "step": 290
    },
    {
      "epoch": 0.35283740076448106,
      "grad_norm": 0.7308420538902283,
      "learning_rate": 0.00018632075471698115,
      "loss": 1.7093,
      "step": 300
    },
    {
      "epoch": 0.3645986474566304,
      "grad_norm": 0.2798251509666443,
      "learning_rate": 0.0001858490566037736,
      "loss": 1.9505,
      "step": 310
    },
    {
      "epoch": 0.3763598941487798,
      "grad_norm": 0.26333555579185486,
      "learning_rate": 0.00018537735849056606,
      "loss": 1.9265,
      "step": 320
    },
    {
      "epoch": 0.38812114084092914,
      "grad_norm": 0.34414273500442505,
      "learning_rate": 0.0001849056603773585,
      "loss": 1.8182,
      "step": 330
    },
    {
      "epoch": 0.39988238753307853,
      "grad_norm": 0.36221399903297424,
      "learning_rate": 0.00018443396226415094,
      "loss": 1.8312,
      "step": 340
    },
    {
      "epoch": 0.4116436342252279,
      "grad_norm": 0.7047480344772339,
      "learning_rate": 0.00018396226415094339,
      "loss": 1.743,
      "step": 350
    },
    {
      "epoch": 0.42340488091737727,
      "grad_norm": 0.2410486787557602,
      "learning_rate": 0.00018349056603773585,
      "loss": 1.9485,
      "step": 360
    },
    {
      "epoch": 0.4351661276095266,
      "grad_norm": 0.30608782172203064,
      "learning_rate": 0.00018301886792452832,
      "loss": 1.8891,
      "step": 370
    },
    {
      "epoch": 0.44692737430167595,
      "grad_norm": 0.32783588767051697,
      "learning_rate": 0.00018254716981132077,
      "loss": 1.8253,
      "step": 380
    },
    {
      "epoch": 0.45868862099382535,
      "grad_norm": 0.37461912631988525,
      "learning_rate": 0.0001820754716981132,
      "loss": 1.8013,
      "step": 390
    },
    {
      "epoch": 0.4704498676859747,
      "grad_norm": 0.7036715149879456,
      "learning_rate": 0.00018160377358490568,
      "loss": 1.7548,
      "step": 400
    },
    {
      "epoch": 0.4822111143781241,
      "grad_norm": 0.23341324925422668,
      "learning_rate": 0.00018113207547169812,
      "loss": 1.8426,
      "step": 410
    },
    {
      "epoch": 0.4939723610702734,
      "grad_norm": 0.29215207695961,
      "learning_rate": 0.00018066037735849056,
      "loss": 1.8704,
      "step": 420
    },
    {
      "epoch": 0.5057336077624228,
      "grad_norm": 0.37499144673347473,
      "learning_rate": 0.00018018867924528303,
      "loss": 1.7602,
      "step": 430
    },
    {
      "epoch": 0.5174948544545722,
      "grad_norm": 0.41657859086990356,
      "learning_rate": 0.0001797169811320755,
      "loss": 1.8011,
      "step": 440
    },
    {
      "epoch": 0.5292561011467215,
      "grad_norm": 0.6587756872177124,
      "learning_rate": 0.00017924528301886794,
      "loss": 1.6643,
      "step": 450
    },
    {
      "epoch": 0.5410173478388709,
      "grad_norm": 0.28515782952308655,
      "learning_rate": 0.00017877358490566038,
      "loss": 1.8037,
      "step": 460
    },
    {
      "epoch": 0.5527785945310203,
      "grad_norm": 0.2742769420146942,
      "learning_rate": 0.00017830188679245282,
      "loss": 1.8544,
      "step": 470
    },
    {
      "epoch": 0.5645398412231697,
      "grad_norm": 0.34683799743652344,
      "learning_rate": 0.0001778301886792453,
      "loss": 1.7819,
      "step": 480
    },
    {
      "epoch": 0.576301087915319,
      "grad_norm": 0.47388383746147156,
      "learning_rate": 0.00017735849056603776,
      "loss": 1.786,
      "step": 490
    },
    {
      "epoch": 0.5880623346074684,
      "grad_norm": 0.617415726184845,
      "learning_rate": 0.0001768867924528302,
      "loss": 1.7053,
      "step": 500
    },
    {
      "epoch": 0.5998235812996178,
      "grad_norm": 0.26782867312431335,
      "learning_rate": 0.00017641509433962265,
      "loss": 1.8774,
      "step": 510
    },
    {
      "epoch": 0.6115848279917672,
      "grad_norm": 0.3381577134132385,
      "learning_rate": 0.00017594339622641511,
      "loss": 1.8537,
      "step": 520
    },
    {
      "epoch": 0.6233460746839165,
      "grad_norm": 0.3665984272956848,
      "learning_rate": 0.00017547169811320756,
      "loss": 1.7465,
      "step": 530
    },
    {
      "epoch": 0.6351073213760658,
      "grad_norm": 0.46630290150642395,
      "learning_rate": 0.000175,
      "loss": 1.7545,
      "step": 540
    },
    {
      "epoch": 0.6468685680682152,
      "grad_norm": 0.7455469369888306,
      "learning_rate": 0.00017452830188679247,
      "loss": 1.6776,
      "step": 550
    },
    {
      "epoch": 0.6586298147603646,
      "grad_norm": 0.27579784393310547,
      "learning_rate": 0.0001740566037735849,
      "loss": 1.8787,
      "step": 560
    },
    {
      "epoch": 0.6703910614525139,
      "grad_norm": 0.3148879110813141,
      "learning_rate": 0.00017358490566037738,
      "loss": 1.8989,
      "step": 570
    },
    {
      "epoch": 0.6821523081446633,
      "grad_norm": 0.3903751075267792,
      "learning_rate": 0.00017311320754716982,
      "loss": 1.7702,
      "step": 580
    },
    {
      "epoch": 0.6939135548368127,
      "grad_norm": 0.4537353217601776,
      "learning_rate": 0.00017264150943396226,
      "loss": 1.758,
      "step": 590
    },
    {
      "epoch": 0.7056748015289621,
      "grad_norm": 0.7169495224952698,
      "learning_rate": 0.0001721698113207547,
      "loss": 1.5495,
      "step": 600
    },
    {
      "epoch": 0.7174360482211114,
      "grad_norm": 0.2942892909049988,
      "learning_rate": 0.00017169811320754717,
      "loss": 1.7981,
      "step": 610
    },
    {
      "epoch": 0.7291972949132608,
      "grad_norm": 0.39550286531448364,
      "learning_rate": 0.00017122641509433964,
      "loss": 1.7919,
      "step": 620
    },
    {
      "epoch": 0.7409585416054102,
      "grad_norm": 0.3948846459388733,
      "learning_rate": 0.00017075471698113208,
      "loss": 1.7793,
      "step": 630
    },
    {
      "epoch": 0.7527197882975596,
      "grad_norm": 0.4996489882469177,
      "learning_rate": 0.00017028301886792453,
      "loss": 1.6956,
      "step": 640
    },
    {
      "epoch": 0.7644810349897089,
      "grad_norm": 0.7511508464813232,
      "learning_rate": 0.000169811320754717,
      "loss": 1.6399,
      "step": 650
    },
    {
      "epoch": 0.7762422816818583,
      "grad_norm": 0.3312196433544159,
      "learning_rate": 0.00016933962264150944,
      "loss": 1.7876,
      "step": 660
    },
    {
      "epoch": 0.7880035283740077,
      "grad_norm": 0.40000253915786743,
      "learning_rate": 0.00016886792452830188,
      "loss": 1.8278,
      "step": 670
    },
    {
      "epoch": 0.7997647750661571,
      "grad_norm": 0.4055274724960327,
      "learning_rate": 0.00016839622641509435,
      "loss": 1.6638,
      "step": 680
    },
    {
      "epoch": 0.8115260217583063,
      "grad_norm": 0.48130497336387634,
      "learning_rate": 0.00016792452830188682,
      "loss": 1.7075,
      "step": 690
    },
    {
      "epoch": 0.8232872684504557,
      "grad_norm": 1.0582154989242554,
      "learning_rate": 0.00016745283018867926,
      "loss": 1.5322,
      "step": 700
    },
    {
      "epoch": 0.8350485151426051,
      "grad_norm": 0.31292250752449036,
      "learning_rate": 0.0001669811320754717,
      "loss": 1.8269,
      "step": 710
    },
    {
      "epoch": 0.8468097618347545,
      "grad_norm": 0.3395911157131195,
      "learning_rate": 0.00016650943396226414,
      "loss": 1.7563,
      "step": 720
    },
    {
      "epoch": 0.8585710085269038,
      "grad_norm": 0.4362980127334595,
      "learning_rate": 0.0001660377358490566,
      "loss": 1.6545,
      "step": 730
    },
    {
      "epoch": 0.8703322552190532,
      "grad_norm": 0.5648341774940491,
      "learning_rate": 0.00016556603773584908,
      "loss": 1.5902,
      "step": 740
    },
    {
      "epoch": 0.8820935019112026,
      "grad_norm": 0.8163714408874512,
      "learning_rate": 0.00016509433962264152,
      "loss": 1.6889,
      "step": 750
    },
    {
      "epoch": 0.8938547486033519,
      "grad_norm": 0.3610120117664337,
      "learning_rate": 0.00016462264150943396,
      "loss": 1.8061,
      "step": 760
    },
    {
      "epoch": 0.9056159952955013,
      "grad_norm": 0.40071502327919006,
      "learning_rate": 0.00016415094339622643,
      "loss": 1.7412,
      "step": 770
    },
    {
      "epoch": 0.9173772419876507,
      "grad_norm": 0.4744262993335724,
      "learning_rate": 0.00016367924528301887,
      "loss": 1.7553,
      "step": 780
    },
    {
      "epoch": 0.9291384886798001,
      "grad_norm": 0.5387608408927917,
      "learning_rate": 0.00016320754716981132,
      "loss": 1.6238,
      "step": 790
    },
    {
      "epoch": 0.9408997353719494,
      "grad_norm": 0.9463699460029602,
      "learning_rate": 0.00016273584905660379,
      "loss": 1.4965,
      "step": 800
    },
    {
      "epoch": 0.9526609820640988,
      "grad_norm": 0.39017385244369507,
      "learning_rate": 0.00016226415094339625,
      "loss": 1.7494,
      "step": 810
    },
    {
      "epoch": 0.9644222287562482,
      "grad_norm": 0.39241862297058105,
      "learning_rate": 0.0001617924528301887,
      "loss": 1.745,
      "step": 820
    },
    {
      "epoch": 0.9761834754483976,
      "grad_norm": 0.4188750982284546,
      "learning_rate": 0.00016132075471698114,
      "loss": 1.7072,
      "step": 830
    },
    {
      "epoch": 0.9879447221405468,
      "grad_norm": 0.54363614320755,
      "learning_rate": 0.00016084905660377358,
      "loss": 1.6571,
      "step": 840
    },
    {
      "epoch": 0.9997059688326962,
      "grad_norm": 0.8282334804534912,
      "learning_rate": 0.00016037735849056605,
      "loss": 1.5609,
      "step": 850
    },
    {
      "epoch": 1.0114672155248456,
      "grad_norm": 0.4861317574977875,
      "learning_rate": 0.0001599056603773585,
      "loss": 1.7427,
      "step": 860
    },
    {
      "epoch": 1.023228462216995,
      "grad_norm": 0.47034987807273865,
      "learning_rate": 0.00015943396226415096,
      "loss": 1.4911,
      "step": 870
    },
    {
      "epoch": 1.0349897089091444,
      "grad_norm": 0.8243444561958313,
      "learning_rate": 0.0001589622641509434,
      "loss": 1.242,
      "step": 880
    },
    {
      "epoch": 1.0467509556012937,
      "grad_norm": 0.8107286095619202,
      "learning_rate": 0.00015849056603773587,
      "loss": 1.1067,
      "step": 890
    },
    {
      "epoch": 1.058512202293443,
      "grad_norm": 0.9792178869247437,
      "learning_rate": 0.0001580188679245283,
      "loss": 0.9078,
      "step": 900
    },
    {
      "epoch": 1.0702734489855925,
      "grad_norm": 0.4514322280883789,
      "learning_rate": 0.00015754716981132075,
      "loss": 1.5328,
      "step": 910
    },
    {
      "epoch": 1.0820346956777418,
      "grad_norm": 0.5203831791877747,
      "learning_rate": 0.0001570754716981132,
      "loss": 1.4851,
      "step": 920
    },
    {
      "epoch": 1.0937959423698913,
      "grad_norm": 0.7015544176101685,
      "learning_rate": 0.00015660377358490567,
      "loss": 1.2215,
      "step": 930
    },
    {
      "epoch": 1.1055571890620406,
      "grad_norm": 0.7290483117103577,
      "learning_rate": 0.00015613207547169813,
      "loss": 1.0831,
      "step": 940
    },
    {
      "epoch": 1.1173184357541899,
      "grad_norm": 1.0971975326538086,
      "learning_rate": 0.00015566037735849058,
      "loss": 0.8673,
      "step": 950
    },
    {
      "epoch": 1.1290796824463394,
      "grad_norm": 0.5123384594917297,
      "learning_rate": 0.00015518867924528302,
      "loss": 1.5301,
      "step": 960
    },
    {
      "epoch": 1.1408409291384887,
      "grad_norm": 0.6260602474212646,
      "learning_rate": 0.0001547169811320755,
      "loss": 1.4956,
      "step": 970
    },
    {
      "epoch": 1.152602175830638,
      "grad_norm": 0.6829984188079834,
      "learning_rate": 0.00015424528301886793,
      "loss": 1.3128,
      "step": 980
    },
    {
      "epoch": 1.1643634225227875,
      "grad_norm": 0.7748053073883057,
      "learning_rate": 0.00015377358490566037,
      "loss": 1.1702,
      "step": 990
    },
    {
      "epoch": 1.1761246692149367,
      "grad_norm": 1.001291036605835,
      "learning_rate": 0.00015330188679245284,
      "loss": 0.8918,
      "step": 1000
    },
    {
      "epoch": 1.1878859159070863,
      "grad_norm": 0.517902135848999,
      "learning_rate": 0.0001528301886792453,
      "loss": 1.4376,
      "step": 1010
    },
    {
      "epoch": 1.1996471625992355,
      "grad_norm": 0.6000102758407593,
      "learning_rate": 0.00015235849056603775,
      "loss": 1.4512,
      "step": 1020
    },
    {
      "epoch": 1.2114084092913848,
      "grad_norm": 0.762768566608429,
      "learning_rate": 0.0001518867924528302,
      "loss": 1.3248,
      "step": 1030
    },
    {
      "epoch": 1.2231696559835343,
      "grad_norm": 0.9720354676246643,
      "learning_rate": 0.00015141509433962263,
      "loss": 1.0415,
      "step": 1040
    },
    {
      "epoch": 1.2349309026756836,
      "grad_norm": 0.902864396572113,
      "learning_rate": 0.0001509433962264151,
      "loss": 0.8803,
      "step": 1050
    },
    {
      "epoch": 1.246692149367833,
      "grad_norm": 0.5235794186592102,
      "learning_rate": 0.00015047169811320757,
      "loss": 1.4755,
      "step": 1060
    },
    {
      "epoch": 1.2584533960599824,
      "grad_norm": 0.5898970365524292,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.4036,
      "step": 1070
    },
    {
      "epoch": 1.2702146427521317,
      "grad_norm": 0.9541133642196655,
      "learning_rate": 0.00014952830188679246,
      "loss": 1.197,
      "step": 1080
    },
    {
      "epoch": 1.281975889444281,
      "grad_norm": 0.9920721054077148,
      "learning_rate": 0.0001490566037735849,
      "loss": 1.0743,
      "step": 1090
    },
    {
      "epoch": 1.2937371361364305,
      "grad_norm": 1.3523385524749756,
      "learning_rate": 0.00014858490566037737,
      "loss": 0.8989,
      "step": 1100
    },
    {
      "epoch": 1.3054983828285798,
      "grad_norm": 0.5665034055709839,
      "learning_rate": 0.0001481132075471698,
      "loss": 1.4432,
      "step": 1110
    },
    {
      "epoch": 1.3172596295207293,
      "grad_norm": 0.6107054352760315,
      "learning_rate": 0.00014764150943396228,
      "loss": 1.356,
      "step": 1120
    },
    {
      "epoch": 1.3290208762128786,
      "grad_norm": 0.7833155393600464,
      "learning_rate": 0.00014716981132075472,
      "loss": 1.2708,
      "step": 1130
    },
    {
      "epoch": 1.3407821229050279,
      "grad_norm": 0.9629625082015991,
      "learning_rate": 0.0001466981132075472,
      "loss": 0.9813,
      "step": 1140
    },
    {
      "epoch": 1.3525433695971774,
      "grad_norm": 1.0938910245895386,
      "learning_rate": 0.00014622641509433963,
      "loss": 0.8002,
      "step": 1150
    },
    {
      "epoch": 1.3643046162893266,
      "grad_norm": 0.5895722508430481,
      "learning_rate": 0.00014575471698113207,
      "loss": 1.469,
      "step": 1160
    },
    {
      "epoch": 1.3760658629814762,
      "grad_norm": 0.6274592280387878,
      "learning_rate": 0.00014528301886792451,
      "loss": 1.2954,
      "step": 1170
    },
    {
      "epoch": 1.3878271096736254,
      "grad_norm": 0.748171329498291,
      "learning_rate": 0.00014481132075471698,
      "loss": 1.1003,
      "step": 1180
    },
    {
      "epoch": 1.3995883563657747,
      "grad_norm": 1.0281026363372803,
      "learning_rate": 0.00014433962264150945,
      "loss": 1.0006,
      "step": 1190
    },
    {
      "epoch": 1.411349603057924,
      "grad_norm": 1.0714832544326782,
      "learning_rate": 0.0001438679245283019,
      "loss": 0.8439,
      "step": 1200
    },
    {
      "epoch": 1.4231108497500735,
      "grad_norm": 0.6404314637184143,
      "learning_rate": 0.00014339622641509434,
      "loss": 1.4463,
      "step": 1210
    },
    {
      "epoch": 1.4348720964422228,
      "grad_norm": 0.6800934672355652,
      "learning_rate": 0.0001429245283018868,
      "loss": 1.2484,
      "step": 1220
    },
    {
      "epoch": 1.4466333431343723,
      "grad_norm": 0.8627371191978455,
      "learning_rate": 0.00014245283018867925,
      "loss": 1.1863,
      "step": 1230
    },
    {
      "epoch": 1.4583945898265216,
      "grad_norm": 1.0996595621109009,
      "learning_rate": 0.0001419811320754717,
      "loss": 0.9519,
      "step": 1240
    },
    {
      "epoch": 1.4701558365186709,
      "grad_norm": 1.1529676914215088,
      "learning_rate": 0.00014150943396226416,
      "loss": 0.8407,
      "step": 1250
    },
    {
      "epoch": 1.4819170832108204,
      "grad_norm": 0.611027717590332,
      "learning_rate": 0.00014103773584905663,
      "loss": 1.3786,
      "step": 1260
    },
    {
      "epoch": 1.4936783299029697,
      "grad_norm": 0.7889626026153564,
      "learning_rate": 0.00014056603773584907,
      "loss": 1.2603,
      "step": 1270
    },
    {
      "epoch": 1.5054395765951192,
      "grad_norm": 0.8136641979217529,
      "learning_rate": 0.0001400943396226415,
      "loss": 1.0535,
      "step": 1280
    },
    {
      "epoch": 1.5172008232872685,
      "grad_norm": 1.0993061065673828,
      "learning_rate": 0.00013962264150943395,
      "loss": 0.9192,
      "step": 1290
    },
    {
      "epoch": 1.5289620699794177,
      "grad_norm": 1.2532891035079956,
      "learning_rate": 0.00013915094339622642,
      "loss": 0.8772,
      "step": 1300
    },
    {
      "epoch": 1.540723316671567,
      "grad_norm": 0.6979594826698303,
      "learning_rate": 0.0001386792452830189,
      "loss": 1.3564,
      "step": 1310
    },
    {
      "epoch": 1.5524845633637165,
      "grad_norm": 0.6345073580741882,
      "learning_rate": 0.00013820754716981133,
      "loss": 1.235,
      "step": 1320
    },
    {
      "epoch": 1.564245810055866,
      "grad_norm": 1.0022692680358887,
      "learning_rate": 0.00013773584905660377,
      "loss": 1.0533,
      "step": 1330
    },
    {
      "epoch": 1.5760070567480153,
      "grad_norm": 1.0487345457077026,
      "learning_rate": 0.00013726415094339624,
      "loss": 0.9879,
      "step": 1340
    },
    {
      "epoch": 1.5877683034401646,
      "grad_norm": 1.3332520723342896,
      "learning_rate": 0.00013679245283018868,
      "loss": 0.8568,
      "step": 1350
    },
    {
      "epoch": 1.599529550132314,
      "grad_norm": 0.6801854968070984,
      "learning_rate": 0.00013632075471698113,
      "loss": 1.3149,
      "step": 1360
    },
    {
      "epoch": 1.6112907968244634,
      "grad_norm": 0.7094405293464661,
      "learning_rate": 0.0001358490566037736,
      "loss": 1.2843,
      "step": 1370
    },
    {
      "epoch": 1.623052043516613,
      "grad_norm": 0.7568113803863525,
      "learning_rate": 0.00013537735849056606,
      "loss": 1.1169,
      "step": 1380
    },
    {
      "epoch": 1.6348132902087622,
      "grad_norm": 1.1939420700073242,
      "learning_rate": 0.0001349056603773585,
      "loss": 0.8441,
      "step": 1390
    },
    {
      "epoch": 1.6465745369009115,
      "grad_norm": 1.4502966403961182,
      "learning_rate": 0.00013443396226415095,
      "loss": 0.801,
      "step": 1400
    },
    {
      "epoch": 1.6583357835930608,
      "grad_norm": 0.6542213559150696,
      "learning_rate": 0.0001339622641509434,
      "loss": 1.4153,
      "step": 1410
    },
    {
      "epoch": 1.6700970302852103,
      "grad_norm": 0.7604705691337585,
      "learning_rate": 0.00013349056603773586,
      "loss": 1.25,
      "step": 1420
    },
    {
      "epoch": 1.6818582769773596,
      "grad_norm": 0.8076483607292175,
      "learning_rate": 0.0001330188679245283,
      "loss": 1.1673,
      "step": 1430
    },
    {
      "epoch": 1.693619523669509,
      "grad_norm": 0.9957693815231323,
      "learning_rate": 0.00013254716981132077,
      "loss": 0.9437,
      "step": 1440
    },
    {
      "epoch": 1.7053807703616584,
      "grad_norm": 1.2569739818572998,
      "learning_rate": 0.0001320754716981132,
      "loss": 0.7948,
      "step": 1450
    },
    {
      "epoch": 1.7171420170538076,
      "grad_norm": 0.8244763016700745,
      "learning_rate": 0.00013160377358490568,
      "loss": 1.3546,
      "step": 1460
    },
    {
      "epoch": 1.728903263745957,
      "grad_norm": 0.8371909856796265,
      "learning_rate": 0.00013113207547169812,
      "loss": 1.2031,
      "step": 1470
    },
    {
      "epoch": 1.7406645104381064,
      "grad_norm": 1.203465223312378,
      "learning_rate": 0.00013066037735849056,
      "loss": 1.0183,
      "step": 1480
    },
    {
      "epoch": 1.752425757130256,
      "grad_norm": 1.2281197309494019,
      "learning_rate": 0.000130188679245283,
      "loss": 0.9311,
      "step": 1490
    },
    {
      "epoch": 1.7641870038224052,
      "grad_norm": 1.3259741067886353,
      "learning_rate": 0.00012971698113207548,
      "loss": 0.872,
      "step": 1500
    },
    {
      "epoch": 1.7759482505145545,
      "grad_norm": 0.7928496599197388,
      "learning_rate": 0.00012924528301886794,
      "loss": 1.3436,
      "step": 1510
    },
    {
      "epoch": 1.7877094972067038,
      "grad_norm": 0.8125369548797607,
      "learning_rate": 0.00012877358490566039,
      "loss": 1.0189,
      "step": 1520
    },
    {
      "epoch": 1.7994707438988533,
      "grad_norm": 1.0345025062561035,
      "learning_rate": 0.00012830188679245283,
      "loss": 1.0006,
      "step": 1530
    },
    {
      "epoch": 1.8112319905910026,
      "grad_norm": 0.8656748533248901,
      "learning_rate": 0.0001278301886792453,
      "loss": 0.8927,
      "step": 1540
    },
    {
      "epoch": 1.822993237283152,
      "grad_norm": 1.12923264503479,
      "learning_rate": 0.00012735849056603774,
      "loss": 0.7717,
      "step": 1550
    },
    {
      "epoch": 1.8347544839753014,
      "grad_norm": 0.898140549659729,
      "learning_rate": 0.00012688679245283018,
      "loss": 1.2768,
      "step": 1560
    },
    {
      "epoch": 1.8465157306674507,
      "grad_norm": 0.748009204864502,
      "learning_rate": 0.00012641509433962265,
      "loss": 1.1579,
      "step": 1570
    },
    {
      "epoch": 1.8582769773596,
      "grad_norm": 1.3326165676116943,
      "learning_rate": 0.00012594339622641512,
      "loss": 0.973,
      "step": 1580
    },
    {
      "epoch": 1.8700382240517495,
      "grad_norm": 0.9244058132171631,
      "learning_rate": 0.00012547169811320756,
      "loss": 0.929,
      "step": 1590
    },
    {
      "epoch": 1.881799470743899,
      "grad_norm": 1.3473211526870728,
      "learning_rate": 0.000125,
      "loss": 0.7777,
      "step": 1600
    },
    {
      "epoch": 1.8935607174360483,
      "grad_norm": 0.8593601584434509,
      "learning_rate": 0.00012452830188679244,
      "loss": 1.327,
      "step": 1610
    },
    {
      "epoch": 1.9053219641281975,
      "grad_norm": 0.8441507816314697,
      "learning_rate": 0.0001240566037735849,
      "loss": 1.1585,
      "step": 1620
    },
    {
      "epoch": 1.9170832108203468,
      "grad_norm": 0.908469557762146,
      "learning_rate": 0.00012358490566037738,
      "loss": 0.9916,
      "step": 1630
    },
    {
      "epoch": 1.9288444575124963,
      "grad_norm": 1.1003684997558594,
      "learning_rate": 0.00012311320754716982,
      "loss": 0.7808,
      "step": 1640
    },
    {
      "epoch": 1.9406057042046458,
      "grad_norm": 1.2000435590744019,
      "learning_rate": 0.00012264150943396227,
      "loss": 0.847,
      "step": 1650
    },
    {
      "epoch": 1.9523669508967951,
      "grad_norm": 0.7908065915107727,
      "learning_rate": 0.0001221698113207547,
      "loss": 1.2671,
      "step": 1660
    },
    {
      "epoch": 1.9641281975889444,
      "grad_norm": 0.8809382319450378,
      "learning_rate": 0.00012169811320754718,
      "loss": 1.1279,
      "step": 1670
    },
    {
      "epoch": 1.9758894442810937,
      "grad_norm": 1.1937824487686157,
      "learning_rate": 0.00012122641509433963,
      "loss": 0.8854,
      "step": 1680
    },
    {
      "epoch": 1.9876506909732432,
      "grad_norm": 1.0509068965911865,
      "learning_rate": 0.00012075471698113207,
      "loss": 0.7986,
      "step": 1690
    },
    {
      "epoch": 1.9994119376653925,
      "grad_norm": 1.2940934896469116,
      "learning_rate": 0.00012028301886792453,
      "loss": 0.8177,
      "step": 1700
    },
    {
      "epoch": 2.011173184357542,
      "grad_norm": 1.00706148147583,
      "learning_rate": 0.000119811320754717,
      "loss": 0.9009,
      "step": 1710
    },
    {
      "epoch": 2.0229344310496913,
      "grad_norm": 0.7884982824325562,
      "learning_rate": 0.00011933962264150944,
      "loss": 0.5944,
      "step": 1720
    },
    {
      "epoch": 2.0346956777418406,
      "grad_norm": 0.8072102069854736,
      "learning_rate": 0.00011886792452830188,
      "loss": 0.4579,
      "step": 1730
    },
    {
      "epoch": 2.04645692443399,
      "grad_norm": 1.0868206024169922,
      "learning_rate": 0.00011839622641509434,
      "loss": 0.3714,
      "step": 1740
    },
    {
      "epoch": 2.0582181711261396,
      "grad_norm": 1.2487127780914307,
      "learning_rate": 0.00011792452830188681,
      "loss": 0.2964,
      "step": 1750
    },
    {
      "epoch": 2.069979417818289,
      "grad_norm": 0.8450261354446411,
      "learning_rate": 0.00011745283018867925,
      "loss": 0.8774,
      "step": 1760
    },
    {
      "epoch": 2.081740664510438,
      "grad_norm": 0.8103846311569214,
      "learning_rate": 0.0001169811320754717,
      "loss": 0.6733,
      "step": 1770
    },
    {
      "epoch": 2.0935019112025874,
      "grad_norm": 0.7691318392753601,
      "learning_rate": 0.00011650943396226415,
      "loss": 0.5036,
      "step": 1780
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 0.8625450134277344,
      "learning_rate": 0.00011603773584905662,
      "loss": 0.33,
      "step": 1790
    },
    {
      "epoch": 2.117024404586886,
      "grad_norm": 1.036942481994629,
      "learning_rate": 0.00011556603773584907,
      "loss": 0.3417,
      "step": 1800
    },
    {
      "epoch": 2.1287856512790357,
      "grad_norm": 0.7786136269569397,
      "learning_rate": 0.00011509433962264151,
      "loss": 0.7165,
      "step": 1810
    },
    {
      "epoch": 2.140546897971185,
      "grad_norm": 0.7121214866638184,
      "learning_rate": 0.00011462264150943395,
      "loss": 0.5809,
      "step": 1820
    },
    {
      "epoch": 2.1523081446633343,
      "grad_norm": 0.8065999150276184,
      "learning_rate": 0.00011415094339622642,
      "loss": 0.4644,
      "step": 1830
    },
    {
      "epoch": 2.1640693913554836,
      "grad_norm": 1.0368797779083252,
      "learning_rate": 0.00011367924528301888,
      "loss": 0.3668,
      "step": 1840
    },
    {
      "epoch": 2.175830638047633,
      "grad_norm": 0.7784335613250732,
      "learning_rate": 0.00011320754716981132,
      "loss": 0.2946,
      "step": 1850
    },
    {
      "epoch": 2.1875918847397826,
      "grad_norm": 1.0500203371047974,
      "learning_rate": 0.00011273584905660378,
      "loss": 0.8046,
      "step": 1860
    },
    {
      "epoch": 2.199353131431932,
      "grad_norm": 0.8676533699035645,
      "learning_rate": 0.00011226415094339624,
      "loss": 0.6096,
      "step": 1870
    },
    {
      "epoch": 2.211114378124081,
      "grad_norm": 0.8250516057014465,
      "learning_rate": 0.00011179245283018869,
      "loss": 0.4479,
      "step": 1880
    },
    {
      "epoch": 2.2228756248162305,
      "grad_norm": 1.0254476070404053,
      "learning_rate": 0.00011132075471698113,
      "loss": 0.3672,
      "step": 1890
    },
    {
      "epoch": 2.2346368715083798,
      "grad_norm": 0.9448462128639221,
      "learning_rate": 0.00011084905660377358,
      "loss": 0.2956,
      "step": 1900
    },
    {
      "epoch": 2.2463981182005295,
      "grad_norm": 0.9094712138175964,
      "learning_rate": 0.00011037735849056605,
      "loss": 0.8546,
      "step": 1910
    },
    {
      "epoch": 2.2581593648926788,
      "grad_norm": 0.7168066501617432,
      "learning_rate": 0.0001099056603773585,
      "loss": 0.6113,
      "step": 1920
    },
    {
      "epoch": 2.269920611584828,
      "grad_norm": 0.9491825699806213,
      "learning_rate": 0.00010943396226415095,
      "loss": 0.4896,
      "step": 1930
    },
    {
      "epoch": 2.2816818582769773,
      "grad_norm": 0.9781097173690796,
      "learning_rate": 0.00010896226415094339,
      "loss": 0.3119,
      "step": 1940
    },
    {
      "epoch": 2.2934431049691266,
      "grad_norm": 1.6303428411483765,
      "learning_rate": 0.00010849056603773586,
      "loss": 0.3224,
      "step": 1950
    },
    {
      "epoch": 2.305204351661276,
      "grad_norm": 0.9339887499809265,
      "learning_rate": 0.00010801886792452832,
      "loss": 0.7914,
      "step": 1960
    },
    {
      "epoch": 2.3169655983534256,
      "grad_norm": 0.8690701127052307,
      "learning_rate": 0.00010754716981132076,
      "loss": 0.5327,
      "step": 1970
    },
    {
      "epoch": 2.328726845045575,
      "grad_norm": 0.8797821998596191,
      "learning_rate": 0.0001070754716981132,
      "loss": 0.3846,
      "step": 1980
    },
    {
      "epoch": 2.340488091737724,
      "grad_norm": 1.1787986755371094,
      "learning_rate": 0.00010660377358490567,
      "loss": 0.3308,
      "step": 1990
    },
    {
      "epoch": 2.3522493384298735,
      "grad_norm": 1.682032585144043,
      "learning_rate": 0.00010613207547169812,
      "loss": 0.3173,
      "step": 2000
    }
  ],
  "logging_steps": 10,
  "max_steps": 4250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.9950155919985664e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}