{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9991537376586743,
  "eval_steps": 500,
  "global_step": 1329,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022566995768688293,
      "grad_norm": 1.117345456275619,
      "learning_rate": 1e-05,
      "loss": 0.7777,
      "step": 10
    },
    {
      "epoch": 0.045133991537376586,
      "grad_norm": 1.0558061335418885,
      "learning_rate": 1e-05,
      "loss": 0.6809,
      "step": 20
    },
    {
      "epoch": 0.06770098730606489,
      "grad_norm": 0.786744915916081,
      "learning_rate": 1e-05,
      "loss": 0.6629,
      "step": 30
    },
    {
      "epoch": 0.09026798307475317,
      "grad_norm": 0.6578526402761529,
      "learning_rate": 1e-05,
      "loss": 0.64,
      "step": 40
    },
    {
      "epoch": 0.11283497884344147,
      "grad_norm": 0.9472125951879998,
      "learning_rate": 1e-05,
      "loss": 0.6341,
      "step": 50
    },
    {
      "epoch": 0.13540197461212977,
      "grad_norm": 0.7916168262477907,
      "learning_rate": 1e-05,
      "loss": 0.6334,
      "step": 60
    },
    {
      "epoch": 0.15796897038081806,
      "grad_norm": 0.6185653413275111,
      "learning_rate": 1e-05,
      "loss": 0.6289,
      "step": 70
    },
    {
      "epoch": 0.18053596614950634,
      "grad_norm": 0.6314110707958094,
      "learning_rate": 1e-05,
      "loss": 0.6309,
      "step": 80
    },
    {
      "epoch": 0.20310296191819463,
      "grad_norm": 0.6437711204273149,
      "learning_rate": 1e-05,
      "loss": 0.6284,
      "step": 90
    },
    {
      "epoch": 0.22566995768688294,
      "grad_norm": 0.5873253051536941,
      "learning_rate": 1e-05,
      "loss": 0.6278,
      "step": 100
    },
    {
      "epoch": 0.24823695345557123,
      "grad_norm": 0.6310355255651338,
      "learning_rate": 1e-05,
      "loss": 0.6186,
      "step": 110
    },
    {
      "epoch": 0.27080394922425954,
      "grad_norm": 0.5820625150389357,
      "learning_rate": 1e-05,
      "loss": 0.6183,
      "step": 120
    },
    {
      "epoch": 0.2933709449929478,
      "grad_norm": 1.0554389485004765,
      "learning_rate": 1e-05,
      "loss": 0.6195,
      "step": 130
    },
    {
      "epoch": 0.3159379407616361,
      "grad_norm": 0.6233930054861221,
      "learning_rate": 1e-05,
      "loss": 0.6145,
      "step": 140
    },
    {
      "epoch": 0.3385049365303244,
      "grad_norm": 0.6986865104427797,
      "learning_rate": 1e-05,
      "loss": 0.6151,
      "step": 150
    },
    {
      "epoch": 0.3610719322990127,
      "grad_norm": 0.5976696884021512,
      "learning_rate": 1e-05,
      "loss": 0.617,
      "step": 160
    },
    {
      "epoch": 0.383638928067701,
      "grad_norm": 0.6385884442182311,
      "learning_rate": 1e-05,
      "loss": 0.613,
      "step": 170
    },
    {
      "epoch": 0.40620592383638926,
      "grad_norm": 0.6603893761394777,
      "learning_rate": 1e-05,
      "loss": 0.6102,
      "step": 180
    },
    {
      "epoch": 0.4287729196050776,
      "grad_norm": 0.604355711330525,
      "learning_rate": 1e-05,
      "loss": 0.6046,
      "step": 190
    },
    {
      "epoch": 0.4513399153737659,
      "grad_norm": 0.6253189521389119,
      "learning_rate": 1e-05,
      "loss": 0.6113,
      "step": 200
    },
    {
      "epoch": 0.47390691114245415,
      "grad_norm": 0.5813973254659559,
      "learning_rate": 1e-05,
      "loss": 0.6078,
      "step": 210
    },
    {
      "epoch": 0.49647390691114246,
      "grad_norm": 0.6102101539308531,
      "learning_rate": 1e-05,
      "loss": 0.5996,
      "step": 220
    },
    {
      "epoch": 0.5190409026798307,
      "grad_norm": 0.658410522798456,
      "learning_rate": 1e-05,
      "loss": 0.6085,
      "step": 230
    },
    {
      "epoch": 0.5416078984485191,
      "grad_norm": 0.5171965459388821,
      "learning_rate": 1e-05,
      "loss": 0.6073,
      "step": 240
    },
    {
      "epoch": 0.5641748942172073,
      "grad_norm": 0.5420540762306473,
      "learning_rate": 1e-05,
      "loss": 0.6014,
      "step": 250
    },
    {
      "epoch": 0.5867418899858956,
      "grad_norm": 0.5990662436826361,
      "learning_rate": 1e-05,
      "loss": 0.604,
      "step": 260
    },
    {
      "epoch": 0.609308885754584,
      "grad_norm": 0.6117507775347968,
      "learning_rate": 1e-05,
      "loss": 0.5994,
      "step": 270
    },
    {
      "epoch": 0.6318758815232722,
      "grad_norm": 0.4958425936800036,
      "learning_rate": 1e-05,
      "loss": 0.6062,
      "step": 280
    },
    {
      "epoch": 0.6544428772919605,
      "grad_norm": 0.5709185176836223,
      "learning_rate": 1e-05,
      "loss": 0.5997,
      "step": 290
    },
    {
      "epoch": 0.6770098730606487,
      "grad_norm": 0.6170008311522954,
      "learning_rate": 1e-05,
      "loss": 0.6057,
      "step": 300
    },
    {
      "epoch": 0.6995768688293371,
      "grad_norm": 0.5139138560022294,
      "learning_rate": 1e-05,
      "loss": 0.5989,
      "step": 310
    },
    {
      "epoch": 0.7221438645980254,
      "grad_norm": 0.5333874763237837,
      "learning_rate": 1e-05,
      "loss": 0.6024,
      "step": 320
    },
    {
      "epoch": 0.7447108603667136,
      "grad_norm": 0.5889113166712524,
      "learning_rate": 1e-05,
      "loss": 0.5981,
      "step": 330
    },
    {
      "epoch": 0.767277856135402,
      "grad_norm": 0.5225707524660949,
      "learning_rate": 1e-05,
      "loss": 0.5975,
      "step": 340
    },
    {
      "epoch": 0.7898448519040903,
      "grad_norm": 0.6893032805838972,
      "learning_rate": 1e-05,
      "loss": 0.5988,
      "step": 350
    },
    {
      "epoch": 0.8124118476727785,
      "grad_norm": 0.6261033841645678,
      "learning_rate": 1e-05,
      "loss": 0.598,
      "step": 360
    },
    {
      "epoch": 0.8349788434414669,
      "grad_norm": 0.684123896553497,
      "learning_rate": 1e-05,
      "loss": 0.6051,
      "step": 370
    },
    {
      "epoch": 0.8575458392101551,
      "grad_norm": 0.5508946780372964,
      "learning_rate": 1e-05,
      "loss": 0.6019,
      "step": 380
    },
    {
      "epoch": 0.8801128349788434,
      "grad_norm": 0.5302374542473679,
      "learning_rate": 1e-05,
      "loss": 0.5957,
      "step": 390
    },
    {
      "epoch": 0.9026798307475318,
      "grad_norm": 0.507958965436953,
      "learning_rate": 1e-05,
      "loss": 0.5981,
      "step": 400
    },
    {
      "epoch": 0.92524682651622,
      "grad_norm": 0.581587543499489,
      "learning_rate": 1e-05,
      "loss": 0.596,
      "step": 410
    },
    {
      "epoch": 0.9478138222849083,
      "grad_norm": 0.539148015427264,
      "learning_rate": 1e-05,
      "loss": 0.5966,
      "step": 420
    },
    {
      "epoch": 0.9703808180535967,
      "grad_norm": 0.5252927128459512,
      "learning_rate": 1e-05,
      "loss": 0.591,
      "step": 430
    },
    {
      "epoch": 0.9929478138222849,
      "grad_norm": 0.5858806021828552,
      "learning_rate": 1e-05,
      "loss": 0.5956,
      "step": 440
    },
    {
      "epoch": 0.9997179125528914,
      "eval_loss": 0.5935375690460205,
      "eval_runtime": 684.3448,
      "eval_samples_per_second": 17.449,
      "eval_steps_per_second": 0.547,
      "step": 443
    },
    {
      "epoch": 1.0155148095909732,
      "grad_norm": 0.8434739321536706,
      "learning_rate": 1e-05,
      "loss": 0.584,
      "step": 450
    },
    {
      "epoch": 1.0380818053596614,
      "grad_norm": 0.6017756380395787,
      "learning_rate": 1e-05,
      "loss": 0.5023,
      "step": 460
    },
    {
      "epoch": 1.0606488011283497,
      "grad_norm": 0.6256862182331746,
      "learning_rate": 1e-05,
      "loss": 0.5159,
      "step": 470
    },
    {
      "epoch": 1.0832157968970382,
      "grad_norm": 1.379595144956799,
      "learning_rate": 1e-05,
      "loss": 0.5047,
      "step": 480
    },
    {
      "epoch": 1.1057827926657264,
      "grad_norm": 0.575633032379168,
      "learning_rate": 1e-05,
      "loss": 0.5144,
      "step": 490
    },
    {
      "epoch": 1.1283497884344147,
      "grad_norm": 0.5650356167737031,
      "learning_rate": 1e-05,
      "loss": 0.5134,
      "step": 500
    },
    {
      "epoch": 1.150916784203103,
      "grad_norm": 0.5870031722788323,
      "learning_rate": 1e-05,
      "loss": 0.5156,
      "step": 510
    },
    {
      "epoch": 1.1734837799717912,
      "grad_norm": 0.5561576740474349,
      "learning_rate": 1e-05,
      "loss": 0.5087,
      "step": 520
    },
    {
      "epoch": 1.1960507757404795,
      "grad_norm": 0.5663151169242476,
      "learning_rate": 1e-05,
      "loss": 0.5151,
      "step": 530
    },
    {
      "epoch": 1.2186177715091677,
      "grad_norm": 0.5516566934998122,
      "learning_rate": 1e-05,
      "loss": 0.5131,
      "step": 540
    },
    {
      "epoch": 1.2411847672778562,
      "grad_norm": 0.5341756994409715,
      "learning_rate": 1e-05,
      "loss": 0.5183,
      "step": 550
    },
    {
      "epoch": 1.2637517630465445,
      "grad_norm": 0.5681526755854495,
      "learning_rate": 1e-05,
      "loss": 0.5202,
      "step": 560
    },
    {
      "epoch": 1.2863187588152327,
      "grad_norm": 0.5454106174889405,
      "learning_rate": 1e-05,
      "loss": 0.5176,
      "step": 570
    },
    {
      "epoch": 1.308885754583921,
      "grad_norm": 0.5295480753938753,
      "learning_rate": 1e-05,
      "loss": 0.5183,
      "step": 580
    },
    {
      "epoch": 1.3314527503526092,
      "grad_norm": 0.5553763662767303,
      "learning_rate": 1e-05,
      "loss": 0.5188,
      "step": 590
    },
    {
      "epoch": 1.3540197461212977,
      "grad_norm": 0.5699250476565831,
      "learning_rate": 1e-05,
      "loss": 0.5239,
      "step": 600
    },
    {
      "epoch": 1.376586741889986,
      "grad_norm": 0.498877394770178,
      "learning_rate": 1e-05,
      "loss": 0.517,
      "step": 610
    },
    {
      "epoch": 1.3991537376586742,
      "grad_norm": 0.5331267296890156,
      "learning_rate": 1e-05,
      "loss": 0.5216,
      "step": 620
    },
    {
      "epoch": 1.4217207334273625,
      "grad_norm": 0.4935333371824384,
      "learning_rate": 1e-05,
      "loss": 0.5198,
      "step": 630
    },
    {
      "epoch": 1.4442877291960508,
      "grad_norm": 0.5423574323269279,
      "learning_rate": 1e-05,
      "loss": 0.5199,
      "step": 640
    },
    {
      "epoch": 1.466854724964739,
      "grad_norm": 0.4969638383295812,
      "learning_rate": 1e-05,
      "loss": 0.5207,
      "step": 650
    },
    {
      "epoch": 1.4894217207334273,
      "grad_norm": 0.5388185933509291,
      "learning_rate": 1e-05,
      "loss": 0.5249,
      "step": 660
    },
    {
      "epoch": 1.5119887165021155,
      "grad_norm": 0.8324061995525175,
      "learning_rate": 1e-05,
      "loss": 0.5197,
      "step": 670
    },
    {
      "epoch": 1.5345557122708038,
      "grad_norm": 0.5075632126837448,
      "learning_rate": 1e-05,
      "loss": 0.5148,
      "step": 680
    },
    {
      "epoch": 1.5571227080394923,
      "grad_norm": 0.5172564571798306,
      "learning_rate": 1e-05,
      "loss": 0.5168,
      "step": 690
    },
    {
      "epoch": 1.5796897038081805,
      "grad_norm": 0.5281467913316902,
      "learning_rate": 1e-05,
      "loss": 0.5213,
      "step": 700
    },
    {
      "epoch": 1.6022566995768688,
      "grad_norm": 0.5515199946319926,
      "learning_rate": 1e-05,
      "loss": 0.524,
      "step": 710
    },
    {
      "epoch": 1.6248236953455573,
      "grad_norm": 0.5192914911496922,
      "learning_rate": 1e-05,
      "loss": 0.5317,
      "step": 720
    },
    {
      "epoch": 1.6473906911142455,
      "grad_norm": 0.47221599050032936,
      "learning_rate": 1e-05,
      "loss": 0.5158,
      "step": 730
    },
    {
      "epoch": 1.6699576868829338,
      "grad_norm": 0.5269832106054182,
      "learning_rate": 1e-05,
      "loss": 0.5311,
      "step": 740
    },
    {
      "epoch": 1.692524682651622,
      "grad_norm": 0.5388959892077222,
      "learning_rate": 1e-05,
      "loss": 0.5228,
      "step": 750
    },
    {
      "epoch": 1.7150916784203103,
      "grad_norm": 0.5180254038572052,
      "learning_rate": 1e-05,
      "loss": 0.5222,
      "step": 760
    },
    {
      "epoch": 1.7376586741889986,
      "grad_norm": 0.5172436551564527,
      "learning_rate": 1e-05,
      "loss": 0.5231,
      "step": 770
    },
    {
      "epoch": 1.7602256699576868,
      "grad_norm": 0.517012214090436,
      "learning_rate": 1e-05,
      "loss": 0.5189,
      "step": 780
    },
    {
      "epoch": 1.782792665726375,
      "grad_norm": 0.48521961127923036,
      "learning_rate": 1e-05,
      "loss": 0.5224,
      "step": 790
    },
    {
      "epoch": 1.8053596614950633,
      "grad_norm": 0.4888044342841827,
      "learning_rate": 1e-05,
      "loss": 0.518,
      "step": 800
    },
    {
      "epoch": 1.8279266572637518,
      "grad_norm": 0.587945690471643,
      "learning_rate": 1e-05,
      "loss": 0.5287,
      "step": 810
    },
    {
      "epoch": 1.85049365303244,
      "grad_norm": 0.4775513549114315,
      "learning_rate": 1e-05,
      "loss": 0.5166,
      "step": 820
    },
    {
      "epoch": 1.8730606488011283,
      "grad_norm": 0.5092949817644183,
      "learning_rate": 1e-05,
      "loss": 0.5281,
      "step": 830
    },
    {
      "epoch": 1.8956276445698168,
      "grad_norm": 0.5097079128384413,
      "learning_rate": 1e-05,
      "loss": 0.5285,
      "step": 840
    },
    {
      "epoch": 1.918194640338505,
      "grad_norm": 0.499556610945679,
      "learning_rate": 1e-05,
      "loss": 0.517,
      "step": 850
    },
    {
      "epoch": 1.9407616361071933,
      "grad_norm": 0.5569809320167849,
      "learning_rate": 1e-05,
      "loss": 0.522,
      "step": 860
    },
    {
      "epoch": 1.9633286318758816,
      "grad_norm": 0.5683761959538197,
      "learning_rate": 1e-05,
      "loss": 0.5283,
      "step": 870
    },
    {
      "epoch": 1.9858956276445698,
      "grad_norm": 0.5687411239067621,
      "learning_rate": 1e-05,
      "loss": 0.5266,
      "step": 880
    },
    {
      "epoch": 1.9994358251057829,
      "eval_loss": 0.5968770980834961,
      "eval_runtime": 684.5791,
      "eval_samples_per_second": 17.443,
      "eval_steps_per_second": 0.546,
      "step": 886
    },
    {
      "epoch": 2.008462623413258,
      "grad_norm": 1.096703899411794,
      "learning_rate": 1e-05,
      "loss": 0.5349,
      "step": 890
    },
    {
      "epoch": 2.0310296191819464,
      "grad_norm": 0.6799454543606133,
      "learning_rate": 1e-05,
      "loss": 0.424,
      "step": 900
    },
    {
      "epoch": 2.0535966149506346,
      "grad_norm": 0.6132080616683041,
      "learning_rate": 1e-05,
      "loss": 0.4237,
      "step": 910
    },
    {
      "epoch": 2.076163610719323,
      "grad_norm": 0.6713486314229204,
      "learning_rate": 1e-05,
      "loss": 0.4165,
      "step": 920
    },
    {
      "epoch": 2.098730606488011,
      "grad_norm": 0.5347323921552215,
      "learning_rate": 1e-05,
      "loss": 0.4236,
      "step": 930
    },
    {
      "epoch": 2.1212976022566994,
      "grad_norm": 0.5544837024093184,
      "learning_rate": 1e-05,
      "loss": 0.4282,
      "step": 940
    },
    {
      "epoch": 2.143864598025388,
      "grad_norm": 0.5509405969417356,
      "learning_rate": 1e-05,
      "loss": 0.4303,
      "step": 950
    },
    {
      "epoch": 2.1664315937940763,
      "grad_norm": 0.577496452978975,
      "learning_rate": 1e-05,
      "loss": 0.4271,
      "step": 960
    },
    {
      "epoch": 2.1889985895627646,
      "grad_norm": 0.5418851243041242,
      "learning_rate": 1e-05,
      "loss": 0.4268,
      "step": 970
    },
    {
      "epoch": 2.211565585331453,
      "grad_norm": 0.5803958676204557,
      "learning_rate": 1e-05,
      "loss": 0.4228,
      "step": 980
    },
    {
      "epoch": 2.234132581100141,
      "grad_norm": 0.5400245120421421,
      "learning_rate": 1e-05,
      "loss": 0.4235,
      "step": 990
    },
    {
      "epoch": 2.2566995768688294,
      "grad_norm": 0.622011804604851,
      "learning_rate": 1e-05,
      "loss": 0.4311,
      "step": 1000
    },
    {
      "epoch": 2.2792665726375176,
      "grad_norm": 0.5843478503049186,
      "learning_rate": 1e-05,
      "loss": 0.4372,
      "step": 1010
    },
    {
      "epoch": 2.301833568406206,
      "grad_norm": 0.567509026386281,
      "learning_rate": 1e-05,
      "loss": 0.4334,
      "step": 1020
    },
    {
      "epoch": 2.324400564174894,
      "grad_norm": 0.5661516251744374,
      "learning_rate": 1e-05,
      "loss": 0.4375,
      "step": 1030
    },
    {
      "epoch": 2.3469675599435824,
      "grad_norm": 0.5401769432174753,
      "learning_rate": 1e-05,
      "loss": 0.4363,
      "step": 1040
    },
    {
      "epoch": 2.3695345557122707,
      "grad_norm": 0.565849197485967,
      "learning_rate": 1e-05,
      "loss": 0.4348,
      "step": 1050
    },
    {
      "epoch": 2.392101551480959,
      "grad_norm": 0.5535601855977871,
      "learning_rate": 1e-05,
      "loss": 0.4342,
      "step": 1060
    },
    {
      "epoch": 2.414668547249647,
      "grad_norm": 0.5370762503841174,
      "learning_rate": 1e-05,
      "loss": 0.4358,
      "step": 1070
    },
    {
      "epoch": 2.4372355430183354,
      "grad_norm": 0.5558415782830175,
      "learning_rate": 1e-05,
      "loss": 0.4385,
      "step": 1080
    },
    {
      "epoch": 2.459802538787024,
      "grad_norm": 0.5491033439583674,
      "learning_rate": 1e-05,
      "loss": 0.4376,
      "step": 1090
    },
    {
      "epoch": 2.4823695345557124,
      "grad_norm": 0.5525848375854203,
      "learning_rate": 1e-05,
      "loss": 0.4416,
      "step": 1100
    },
    {
      "epoch": 2.5049365303244007,
      "grad_norm": 0.5569218173084504,
      "learning_rate": 1e-05,
      "loss": 0.4442,
      "step": 1110
    },
    {
      "epoch": 2.527503526093089,
      "grad_norm": 0.5818935529719582,
      "learning_rate": 1e-05,
      "loss": 0.4367,
      "step": 1120
    },
    {
      "epoch": 2.550070521861777,
      "grad_norm": 0.5161300306268278,
      "learning_rate": 1e-05,
      "loss": 0.4413,
      "step": 1130
    },
    {
      "epoch": 2.5726375176304654,
      "grad_norm": 0.537320221224185,
      "learning_rate": 1e-05,
      "loss": 0.4398,
      "step": 1140
    },
    {
      "epoch": 2.5952045133991537,
      "grad_norm": 0.5869253511067546,
      "learning_rate": 1e-05,
      "loss": 0.4405,
      "step": 1150
    },
    {
      "epoch": 2.617771509167842,
      "grad_norm": 0.5136143375362393,
      "learning_rate": 1e-05,
      "loss": 0.4442,
      "step": 1160
    },
    {
      "epoch": 2.64033850493653,
      "grad_norm": 0.5451923653937446,
      "learning_rate": 1e-05,
      "loss": 0.435,
      "step": 1170
    },
    {
      "epoch": 2.6629055007052185,
      "grad_norm": 0.5769843924471573,
      "learning_rate": 1e-05,
      "loss": 0.4449,
      "step": 1180
    },
    {
      "epoch": 2.685472496473907,
      "grad_norm": 0.595565823982304,
      "learning_rate": 1e-05,
      "loss": 0.4456,
      "step": 1190
    },
    {
      "epoch": 2.7080394922425954,
      "grad_norm": 0.5455659140255756,
      "learning_rate": 1e-05,
      "loss": 0.4447,
      "step": 1200
    },
    {
      "epoch": 2.7306064880112837,
      "grad_norm": 0.5675844306750867,
      "learning_rate": 1e-05,
      "loss": 0.4459,
      "step": 1210
    },
    {
      "epoch": 2.753173483779972,
      "grad_norm": 0.5810578650041014,
      "learning_rate": 1e-05,
      "loss": 0.4434,
      "step": 1220
    },
    {
      "epoch": 2.77574047954866,
      "grad_norm": 0.5631164060028497,
      "learning_rate": 1e-05,
      "loss": 0.4496,
      "step": 1230
    },
    {
      "epoch": 2.7983074753173485,
      "grad_norm": 0.5874402659987488,
      "learning_rate": 1e-05,
      "loss": 0.4476,
      "step": 1240
    },
    {
      "epoch": 2.8208744710860367,
      "grad_norm": 0.5466578963772318,
      "learning_rate": 1e-05,
      "loss": 0.4485,
      "step": 1250
    },
    {
      "epoch": 2.843441466854725,
      "grad_norm": 0.5699905672954687,
      "learning_rate": 1e-05,
      "loss": 0.4503,
      "step": 1260
    },
    {
      "epoch": 2.8660084626234132,
      "grad_norm": 0.5095374168618119,
      "learning_rate": 1e-05,
      "loss": 0.448,
      "step": 1270
    },
    {
      "epoch": 2.8885754583921015,
      "grad_norm": 0.538746652630106,
      "learning_rate": 1e-05,
      "loss": 0.4467,
      "step": 1280
    },
    {
      "epoch": 2.9111424541607898,
      "grad_norm": 0.5544375388853288,
      "learning_rate": 1e-05,
      "loss": 0.4495,
      "step": 1290
    },
    {
      "epoch": 2.933709449929478,
      "grad_norm": 0.5172853690545651,
      "learning_rate": 1e-05,
      "loss": 0.446,
      "step": 1300
    },
    {
      "epoch": 2.9562764456981663,
      "grad_norm": 0.5521495505908127,
      "learning_rate": 1e-05,
      "loss": 0.4494,
      "step": 1310
    },
    {
      "epoch": 2.9788434414668545,
      "grad_norm": 0.5476055969008398,
      "learning_rate": 1e-05,
      "loss": 0.4473,
      "step": 1320
    },
    {
      "epoch": 2.9991537376586743,
      "eval_loss": 0.6338749527931213,
      "eval_runtime": 684.2714,
      "eval_samples_per_second": 17.451,
      "eval_steps_per_second": 0.547,
      "step": 1329
    },
    {
      "epoch": 2.9991537376586743,
      "step": 1329,
      "total_flos": 5064195066298368.0,
      "train_loss": 0.5251943295480973,
      "train_runtime": 120013.5789,
      "train_samples_per_second": 5.671,
      "train_steps_per_second": 0.011
    }
  ],
  "logging_steps": 10,
  "max_steps": 1329,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5064195066298368.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}