{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.99626400996264,
  "eval_steps": 500,
  "global_step": 1203,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024906600249066,
      "grad_norm": 44.361316887243134,
      "learning_rate": 5e-06,
      "loss": 1.0469,
      "step": 10
    },
    {
      "epoch": 0.049813200498132,
      "grad_norm": 1.9340361918852786,
      "learning_rate": 5e-06,
      "loss": 0.9485,
      "step": 20
    },
    {
      "epoch": 0.074719800747198,
      "grad_norm": 1.5810624474405115,
      "learning_rate": 5e-06,
      "loss": 0.9118,
      "step": 30
    },
    {
      "epoch": 0.099626400996264,
      "grad_norm": 1.0226804734735437,
      "learning_rate": 5e-06,
      "loss": 0.896,
      "step": 40
    },
    {
      "epoch": 0.12453300124533001,
      "grad_norm": 0.8059494431972822,
      "learning_rate": 5e-06,
      "loss": 0.885,
      "step": 50
    },
    {
      "epoch": 0.149439601494396,
      "grad_norm": 1.0759666179613023,
      "learning_rate": 5e-06,
      "loss": 0.8743,
      "step": 60
    },
    {
      "epoch": 0.17434620174346202,
      "grad_norm": 0.6070805032397537,
      "learning_rate": 5e-06,
      "loss": 0.865,
      "step": 70
    },
    {
      "epoch": 0.199252801992528,
      "grad_norm": 0.8206282215157027,
      "learning_rate": 5e-06,
      "loss": 0.8637,
      "step": 80
    },
    {
      "epoch": 0.22415940224159403,
      "grad_norm": 0.8375312112666434,
      "learning_rate": 5e-06,
      "loss": 0.8538,
      "step": 90
    },
    {
      "epoch": 0.24906600249066002,
      "grad_norm": 0.8745465775067757,
      "learning_rate": 5e-06,
      "loss": 0.8462,
      "step": 100
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 0.7671374593440573,
      "learning_rate": 5e-06,
      "loss": 0.8516,
      "step": 110
    },
    {
      "epoch": 0.298879202988792,
      "grad_norm": 0.6357492120016651,
      "learning_rate": 5e-06,
      "loss": 0.8424,
      "step": 120
    },
    {
      "epoch": 0.32378580323785805,
      "grad_norm": 0.7985944551248969,
      "learning_rate": 5e-06,
      "loss": 0.838,
      "step": 130
    },
    {
      "epoch": 0.34869240348692404,
      "grad_norm": 0.6906428387839867,
      "learning_rate": 5e-06,
      "loss": 0.8425,
      "step": 140
    },
    {
      "epoch": 0.37359900373599003,
      "grad_norm": 0.63382119448828,
      "learning_rate": 5e-06,
      "loss": 0.8394,
      "step": 150
    },
    {
      "epoch": 0.398505603985056,
      "grad_norm": 0.7372274527250459,
      "learning_rate": 5e-06,
      "loss": 0.8331,
      "step": 160
    },
    {
      "epoch": 0.42341220423412207,
      "grad_norm": 0.6083911703654408,
      "learning_rate": 5e-06,
      "loss": 0.8326,
      "step": 170
    },
    {
      "epoch": 0.44831880448318806,
      "grad_norm": 1.1261618495477859,
      "learning_rate": 5e-06,
      "loss": 0.8279,
      "step": 180
    },
    {
      "epoch": 0.47322540473225405,
      "grad_norm": 0.7015056078596724,
      "learning_rate": 5e-06,
      "loss": 0.8289,
      "step": 190
    },
    {
      "epoch": 0.49813200498132004,
      "grad_norm": 0.7547586360167027,
      "learning_rate": 5e-06,
      "loss": 0.8269,
      "step": 200
    },
    {
      "epoch": 0.523038605230386,
      "grad_norm": 0.729606315703109,
      "learning_rate": 5e-06,
      "loss": 0.827,
      "step": 210
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.576263809426071,
      "learning_rate": 5e-06,
      "loss": 0.8278,
      "step": 220
    },
    {
      "epoch": 0.572851805728518,
      "grad_norm": 0.608656960705352,
      "learning_rate": 5e-06,
      "loss": 0.8255,
      "step": 230
    },
    {
      "epoch": 0.597758405977584,
      "grad_norm": 0.6942678291488105,
      "learning_rate": 5e-06,
      "loss": 0.8247,
      "step": 240
    },
    {
      "epoch": 0.6226650062266501,
      "grad_norm": 0.8474112920696388,
      "learning_rate": 5e-06,
      "loss": 0.8211,
      "step": 250
    },
    {
      "epoch": 0.6475716064757161,
      "grad_norm": 0.7436541561484579,
      "learning_rate": 5e-06,
      "loss": 0.8205,
      "step": 260
    },
    {
      "epoch": 0.6724782067247821,
      "grad_norm": 0.5723501381180358,
      "learning_rate": 5e-06,
      "loss": 0.8175,
      "step": 270
    },
    {
      "epoch": 0.6973848069738481,
      "grad_norm": 0.7393336592407068,
      "learning_rate": 5e-06,
      "loss": 0.8266,
      "step": 280
    },
    {
      "epoch": 0.7222914072229141,
      "grad_norm": 0.8642437433242355,
      "learning_rate": 5e-06,
      "loss": 0.8213,
      "step": 290
    },
    {
      "epoch": 0.7471980074719801,
      "grad_norm": 0.6599736959065436,
      "learning_rate": 5e-06,
      "loss": 0.8197,
      "step": 300
    },
    {
      "epoch": 0.772104607721046,
      "grad_norm": 0.589894020890247,
      "learning_rate": 5e-06,
      "loss": 0.8171,
      "step": 310
    },
    {
      "epoch": 0.797011207970112,
      "grad_norm": 0.6770015328448542,
      "learning_rate": 5e-06,
      "loss": 0.8159,
      "step": 320
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 0.6953955951335576,
      "learning_rate": 5e-06,
      "loss": 0.8156,
      "step": 330
    },
    {
      "epoch": 0.8468244084682441,
      "grad_norm": 0.8401761226093455,
      "learning_rate": 5e-06,
      "loss": 0.8136,
      "step": 340
    },
    {
      "epoch": 0.8717310087173101,
      "grad_norm": 0.6479655559695816,
      "learning_rate": 5e-06,
      "loss": 0.8091,
      "step": 350
    },
    {
      "epoch": 0.8966376089663761,
      "grad_norm": 0.7636033751591921,
      "learning_rate": 5e-06,
      "loss": 0.8127,
      "step": 360
    },
    {
      "epoch": 0.9215442092154421,
      "grad_norm": 0.5680882933927079,
      "learning_rate": 5e-06,
      "loss": 0.8139,
      "step": 370
    },
    {
      "epoch": 0.9464508094645081,
      "grad_norm": 0.5317095758960971,
      "learning_rate": 5e-06,
      "loss": 0.8148,
      "step": 380
    },
    {
      "epoch": 0.9713574097135741,
      "grad_norm": 0.5355215121901621,
      "learning_rate": 5e-06,
      "loss": 0.8133,
      "step": 390
    },
    {
      "epoch": 0.9962640099626401,
      "grad_norm": 0.5034767977871308,
      "learning_rate": 5e-06,
      "loss": 0.8102,
      "step": 400
    },
    {
      "epoch": 0.9987546699875467,
      "eval_loss": 0.8109647631645203,
      "eval_runtime": 429.8587,
      "eval_samples_per_second": 25.166,
      "eval_steps_per_second": 0.395,
      "step": 401
    },
    {
      "epoch": 1.0211706102117062,
      "grad_norm": 0.7772306063471781,
      "learning_rate": 5e-06,
      "loss": 0.8079,
      "step": 410
    },
    {
      "epoch": 1.046077210460772,
      "grad_norm": 0.547172758232467,
      "learning_rate": 5e-06,
      "loss": 0.7693,
      "step": 420
    },
    {
      "epoch": 1.0709838107098382,
      "grad_norm": 0.6602663338851202,
      "learning_rate": 5e-06,
      "loss": 0.7659,
      "step": 430
    },
    {
      "epoch": 1.095890410958904,
      "grad_norm": 0.5563021526867751,
      "learning_rate": 5e-06,
      "loss": 0.7669,
      "step": 440
    },
    {
      "epoch": 1.1207970112079702,
      "grad_norm": 0.5764004393923637,
      "learning_rate": 5e-06,
      "loss": 0.7676,
      "step": 450
    },
    {
      "epoch": 1.145703611457036,
      "grad_norm": 0.6104368430877777,
      "learning_rate": 5e-06,
      "loss": 0.7668,
      "step": 460
    },
    {
      "epoch": 1.1706102117061021,
      "grad_norm": 0.5856299384522291,
      "learning_rate": 5e-06,
      "loss": 0.7653,
      "step": 470
    },
    {
      "epoch": 1.195516811955168,
      "grad_norm": 0.5968500894238352,
      "learning_rate": 5e-06,
      "loss": 0.7691,
      "step": 480
    },
    {
      "epoch": 1.2204234122042341,
      "grad_norm": 0.6425311166512483,
      "learning_rate": 5e-06,
      "loss": 0.7692,
      "step": 490
    },
    {
      "epoch": 1.2453300124533002,
      "grad_norm": 0.5800761501783642,
      "learning_rate": 5e-06,
      "loss": 0.77,
      "step": 500
    },
    {
      "epoch": 1.270236612702366,
      "grad_norm": 0.5217881601799819,
      "learning_rate": 5e-06,
      "loss": 0.7649,
      "step": 510
    },
    {
      "epoch": 1.2951432129514322,
      "grad_norm": 0.7577819320627684,
      "learning_rate": 5e-06,
      "loss": 0.7682,
      "step": 520
    },
    {
      "epoch": 1.320049813200498,
      "grad_norm": 0.7467713696988785,
      "learning_rate": 5e-06,
      "loss": 0.7712,
      "step": 530
    },
    {
      "epoch": 1.3449564134495642,
      "grad_norm": 0.6010822997576867,
      "learning_rate": 5e-06,
      "loss": 0.7664,
      "step": 540
    },
    {
      "epoch": 1.36986301369863,
      "grad_norm": 0.689181454056687,
      "learning_rate": 5e-06,
      "loss": 0.7679,
      "step": 550
    },
    {
      "epoch": 1.3947696139476962,
      "grad_norm": 0.4747660184884877,
      "learning_rate": 5e-06,
      "loss": 0.7639,
      "step": 560
    },
    {
      "epoch": 1.419676214196762,
      "grad_norm": 0.5116161932838977,
      "learning_rate": 5e-06,
      "loss": 0.7677,
      "step": 570
    },
    {
      "epoch": 1.4445828144458281,
      "grad_norm": 0.6433790988167347,
      "learning_rate": 5e-06,
      "loss": 0.7626,
      "step": 580
    },
    {
      "epoch": 1.4694894146948942,
      "grad_norm": 0.6145972003931011,
      "learning_rate": 5e-06,
      "loss": 0.7639,
      "step": 590
    },
    {
      "epoch": 1.4943960149439601,
      "grad_norm": 0.5887457741602182,
      "learning_rate": 5e-06,
      "loss": 0.7612,
      "step": 600
    },
    {
      "epoch": 1.519302615193026,
      "grad_norm": 0.5628593594779383,
      "learning_rate": 5e-06,
      "loss": 0.7685,
      "step": 610
    },
    {
      "epoch": 1.544209215442092,
      "grad_norm": 0.49978624448408865,
      "learning_rate": 5e-06,
      "loss": 0.7655,
      "step": 620
    },
    {
      "epoch": 1.5691158156911582,
      "grad_norm": 0.5121970961880906,
      "learning_rate": 5e-06,
      "loss": 0.7646,
      "step": 630
    },
    {
      "epoch": 1.5940224159402243,
      "grad_norm": 0.5120901081120943,
      "learning_rate": 5e-06,
      "loss": 0.7633,
      "step": 640
    },
    {
      "epoch": 1.6189290161892902,
      "grad_norm": 0.5708046084852306,
      "learning_rate": 5e-06,
      "loss": 0.7701,
      "step": 650
    },
    {
      "epoch": 1.643835616438356,
      "grad_norm": 0.559772892922969,
      "learning_rate": 5e-06,
      "loss": 0.7671,
      "step": 660
    },
    {
      "epoch": 1.6687422166874222,
      "grad_norm": 0.508876685275154,
      "learning_rate": 5e-06,
      "loss": 0.7627,
      "step": 670
    },
    {
      "epoch": 1.6936488169364883,
      "grad_norm": 0.5547904679119214,
      "learning_rate": 5e-06,
      "loss": 0.7665,
      "step": 680
    },
    {
      "epoch": 1.7185554171855542,
      "grad_norm": 0.5327048566040764,
      "learning_rate": 5e-06,
      "loss": 0.7612,
      "step": 690
    },
    {
      "epoch": 1.74346201743462,
      "grad_norm": 0.5681641331800833,
      "learning_rate": 5e-06,
      "loss": 0.7625,
      "step": 700
    },
    {
      "epoch": 1.7683686176836861,
      "grad_norm": 0.5583754277477581,
      "learning_rate": 5e-06,
      "loss": 0.7678,
      "step": 710
    },
    {
      "epoch": 1.7932752179327522,
      "grad_norm": 0.5821109954208563,
      "learning_rate": 5e-06,
      "loss": 0.7641,
      "step": 720
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 0.6033561880814401,
      "learning_rate": 5e-06,
      "loss": 0.7671,
      "step": 730
    },
    {
      "epoch": 1.8430884184308842,
      "grad_norm": 0.6575859282775093,
      "learning_rate": 5e-06,
      "loss": 0.7569,
      "step": 740
    },
    {
      "epoch": 1.86799501867995,
      "grad_norm": 0.5332781614516378,
      "learning_rate": 5e-06,
      "loss": 0.7617,
      "step": 750
    },
    {
      "epoch": 1.8929016189290162,
      "grad_norm": 0.6171829234250781,
      "learning_rate": 5e-06,
      "loss": 0.7628,
      "step": 760
    },
    {
      "epoch": 1.9178082191780823,
      "grad_norm": 0.553381597192015,
      "learning_rate": 5e-06,
      "loss": 0.7623,
      "step": 770
    },
    {
      "epoch": 1.9427148194271482,
      "grad_norm": 0.5971496735780886,
      "learning_rate": 5e-06,
      "loss": 0.7595,
      "step": 780
    },
    {
      "epoch": 1.967621419676214,
      "grad_norm": 0.566450928468519,
      "learning_rate": 5e-06,
      "loss": 0.7613,
      "step": 790
    },
    {
      "epoch": 1.9925280199252802,
      "grad_norm": 0.6533740130175245,
      "learning_rate": 5e-06,
      "loss": 0.7613,
      "step": 800
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.798328697681427,
      "eval_runtime": 427.8716,
      "eval_samples_per_second": 25.283,
      "eval_steps_per_second": 0.397,
      "step": 803
    },
    {
      "epoch": 2.0174346201743463,
      "grad_norm": 0.9428578537809662,
      "learning_rate": 5e-06,
      "loss": 0.764,
      "step": 810
    },
    {
      "epoch": 2.0423412204234124,
      "grad_norm": 0.682790769401012,
      "learning_rate": 5e-06,
      "loss": 0.7174,
      "step": 820
    },
    {
      "epoch": 2.067247820672478,
      "grad_norm": 0.732474650025201,
      "learning_rate": 5e-06,
      "loss": 0.7136,
      "step": 830
    },
    {
      "epoch": 2.092154420921544,
      "grad_norm": 0.5517924405803882,
      "learning_rate": 5e-06,
      "loss": 0.7141,
      "step": 840
    },
    {
      "epoch": 2.1170610211706102,
      "grad_norm": 0.527980258175362,
      "learning_rate": 5e-06,
      "loss": 0.7205,
      "step": 850
    },
    {
      "epoch": 2.1419676214196763,
      "grad_norm": 0.5578355324627287,
      "learning_rate": 5e-06,
      "loss": 0.7182,
      "step": 860
    },
    {
      "epoch": 2.166874221668742,
      "grad_norm": 0.5384061514408854,
      "learning_rate": 5e-06,
      "loss": 0.7174,
      "step": 870
    },
    {
      "epoch": 2.191780821917808,
      "grad_norm": 0.5433323621552549,
      "learning_rate": 5e-06,
      "loss": 0.7227,
      "step": 880
    },
    {
      "epoch": 2.216687422166874,
      "grad_norm": 0.5934434020270568,
      "learning_rate": 5e-06,
      "loss": 0.7154,
      "step": 890
    },
    {
      "epoch": 2.2415940224159403,
      "grad_norm": 0.5610116690136854,
      "learning_rate": 5e-06,
      "loss": 0.7181,
      "step": 900
    },
    {
      "epoch": 2.2665006226650064,
      "grad_norm": 0.5956518936383002,
      "learning_rate": 5e-06,
      "loss": 0.7188,
      "step": 910
    },
    {
      "epoch": 2.291407222914072,
      "grad_norm": 0.5700434018521554,
      "learning_rate": 5e-06,
      "loss": 0.7189,
      "step": 920
    },
    {
      "epoch": 2.316313823163138,
      "grad_norm": 0.6159365804430498,
      "learning_rate": 5e-06,
      "loss": 0.7208,
      "step": 930
    },
    {
      "epoch": 2.3412204234122043,
      "grad_norm": 0.5739840813262334,
      "learning_rate": 5e-06,
      "loss": 0.7191,
      "step": 940
    },
    {
      "epoch": 2.3661270236612704,
      "grad_norm": 0.517298472276118,
      "learning_rate": 5e-06,
      "loss": 0.7254,
      "step": 950
    },
    {
      "epoch": 2.391033623910336,
      "grad_norm": 0.5309037963536546,
      "learning_rate": 5e-06,
      "loss": 0.7177,
      "step": 960
    },
    {
      "epoch": 2.415940224159402,
      "grad_norm": 0.5464343303315381,
      "learning_rate": 5e-06,
      "loss": 0.7162,
      "step": 970
    },
    {
      "epoch": 2.4408468244084682,
      "grad_norm": 0.5884939657248605,
      "learning_rate": 5e-06,
      "loss": 0.7238,
      "step": 980
    },
    {
      "epoch": 2.4657534246575343,
      "grad_norm": 0.6058278477423068,
      "learning_rate": 5e-06,
      "loss": 0.7217,
      "step": 990
    },
    {
      "epoch": 2.4906600249066004,
      "grad_norm": 0.575706246130651,
      "learning_rate": 5e-06,
      "loss": 0.7211,
      "step": 1000
    },
    {
      "epoch": 2.515566625155666,
      "grad_norm": 0.6210182727077225,
      "learning_rate": 5e-06,
      "loss": 0.722,
      "step": 1010
    },
    {
      "epoch": 2.540473225404732,
      "grad_norm": 0.6248334338554098,
      "learning_rate": 5e-06,
      "loss": 0.7226,
      "step": 1020
    },
    {
      "epoch": 2.5653798256537983,
      "grad_norm": 0.6075603863013977,
      "learning_rate": 5e-06,
      "loss": 0.7201,
      "step": 1030
    },
    {
      "epoch": 2.5902864259028644,
      "grad_norm": 0.6125989005343908,
      "learning_rate": 5e-06,
      "loss": 0.7225,
      "step": 1040
    },
    {
      "epoch": 2.61519302615193,
      "grad_norm": 0.5723698102141317,
      "learning_rate": 5e-06,
      "loss": 0.7184,
      "step": 1050
    },
    {
      "epoch": 2.640099626400996,
      "grad_norm": 0.5988876404053375,
      "learning_rate": 5e-06,
      "loss": 0.7228,
      "step": 1060
    },
    {
      "epoch": 2.6650062266500623,
      "grad_norm": 0.5535541669685047,
      "learning_rate": 5e-06,
      "loss": 0.7219,
      "step": 1070
    },
    {
      "epoch": 2.6899128268991284,
      "grad_norm": 0.6560134586878092,
      "learning_rate": 5e-06,
      "loss": 0.7231,
      "step": 1080
    },
    {
      "epoch": 2.7148194271481945,
      "grad_norm": 0.570154529031656,
      "learning_rate": 5e-06,
      "loss": 0.7207,
      "step": 1090
    },
    {
      "epoch": 2.73972602739726,
      "grad_norm": 0.6903793080558596,
      "learning_rate": 5e-06,
      "loss": 0.7225,
      "step": 1100
    },
    {
      "epoch": 2.7646326276463262,
      "grad_norm": 0.609309475396782,
      "learning_rate": 5e-06,
      "loss": 0.7199,
      "step": 1110
    },
    {
      "epoch": 2.7895392278953923,
      "grad_norm": 0.4982077265492007,
      "learning_rate": 5e-06,
      "loss": 0.723,
      "step": 1120
    },
    {
      "epoch": 2.8144458281444584,
      "grad_norm": 0.5520401600798728,
      "learning_rate": 5e-06,
      "loss": 0.7195,
      "step": 1130
    },
    {
      "epoch": 2.839352428393524,
      "grad_norm": 0.5678772706098874,
      "learning_rate": 5e-06,
      "loss": 0.7241,
      "step": 1140
    },
    {
      "epoch": 2.86425902864259,
      "grad_norm": 0.6919987752510048,
      "learning_rate": 5e-06,
      "loss": 0.7218,
      "step": 1150
    },
    {
      "epoch": 2.8891656288916563,
      "grad_norm": 0.5523800519721218,
      "learning_rate": 5e-06,
      "loss": 0.7223,
      "step": 1160
    },
    {
      "epoch": 2.9140722291407224,
      "grad_norm": 0.5786175424826561,
      "learning_rate": 5e-06,
      "loss": 0.7248,
      "step": 1170
    },
    {
      "epoch": 2.9389788293897885,
      "grad_norm": 0.5805260846296417,
      "learning_rate": 5e-06,
      "loss": 0.7186,
      "step": 1180
    },
    {
      "epoch": 2.963885429638854,
      "grad_norm": 0.6087027130014465,
      "learning_rate": 5e-06,
      "loss": 0.7225,
      "step": 1190
    },
    {
      "epoch": 2.9887920298879203,
      "grad_norm": 0.6138969910749299,
      "learning_rate": 5e-06,
      "loss": 0.7228,
      "step": 1200
    },
    {
      "epoch": 2.99626400996264,
      "eval_loss": 0.7962795495986938,
      "eval_runtime": 431.1284,
      "eval_samples_per_second": 25.092,
      "eval_steps_per_second": 0.394,
      "step": 1203
    },
    {
      "epoch": 2.99626400996264,
      "step": 1203,
      "total_flos": 2014860426608640.0,
      "train_loss": 0.7768312251676843,
      "train_runtime": 70934.0832,
      "train_samples_per_second": 8.693,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 1203,
  "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": 2014860426608640.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}