{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 2195,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022779043280182234,
      "grad_norm": 1.461890268182302,
      "learning_rate": 5e-06,
      "loss": 0.7557,
      "step": 10
    },
    {
      "epoch": 0.04555808656036447,
      "grad_norm": 0.8438010452400335,
      "learning_rate": 5e-06,
      "loss": 0.6991,
      "step": 20
    },
    {
      "epoch": 0.0683371298405467,
      "grad_norm": 0.9176367932491145,
      "learning_rate": 5e-06,
      "loss": 0.6807,
      "step": 30
    },
    {
      "epoch": 0.09111617312072894,
      "grad_norm": 0.8591490414558551,
      "learning_rate": 5e-06,
      "loss": 0.6795,
      "step": 40
    },
    {
      "epoch": 0.11389521640091116,
      "grad_norm": 0.8079754565291697,
      "learning_rate": 5e-06,
      "loss": 0.6751,
      "step": 50
    },
    {
      "epoch": 0.1366742596810934,
      "grad_norm": 0.676950753600941,
      "learning_rate": 5e-06,
      "loss": 0.6551,
      "step": 60
    },
    {
      "epoch": 0.15945330296127563,
      "grad_norm": 0.4397948544262224,
      "learning_rate": 5e-06,
      "loss": 0.6519,
      "step": 70
    },
    {
      "epoch": 0.18223234624145787,
      "grad_norm": 0.36816486280988786,
      "learning_rate": 5e-06,
      "loss": 0.6552,
      "step": 80
    },
    {
      "epoch": 0.20501138952164008,
      "grad_norm": 0.31467376370284666,
      "learning_rate": 5e-06,
      "loss": 0.6394,
      "step": 90
    },
    {
      "epoch": 0.22779043280182232,
      "grad_norm": 0.2990731503632509,
      "learning_rate": 5e-06,
      "loss": 0.6413,
      "step": 100
    },
    {
      "epoch": 0.2505694760820046,
      "grad_norm": 0.34146204165056326,
      "learning_rate": 5e-06,
      "loss": 0.6325,
      "step": 110
    },
    {
      "epoch": 0.2733485193621868,
      "grad_norm": 0.3118885479261177,
      "learning_rate": 5e-06,
      "loss": 0.6411,
      "step": 120
    },
    {
      "epoch": 0.296127562642369,
      "grad_norm": 0.29309780131472263,
      "learning_rate": 5e-06,
      "loss": 0.6422,
      "step": 130
    },
    {
      "epoch": 0.31890660592255127,
      "grad_norm": 0.3076465447126475,
      "learning_rate": 5e-06,
      "loss": 0.6443,
      "step": 140
    },
    {
      "epoch": 0.3416856492027335,
      "grad_norm": 0.3146670257810527,
      "learning_rate": 5e-06,
      "loss": 0.6369,
      "step": 150
    },
    {
      "epoch": 0.36446469248291574,
      "grad_norm": 0.3089804621013958,
      "learning_rate": 5e-06,
      "loss": 0.6424,
      "step": 160
    },
    {
      "epoch": 0.38724373576309795,
      "grad_norm": 0.34694834193027213,
      "learning_rate": 5e-06,
      "loss": 0.6335,
      "step": 170
    },
    {
      "epoch": 0.41002277904328016,
      "grad_norm": 0.3056788305992376,
      "learning_rate": 5e-06,
      "loss": 0.6399,
      "step": 180
    },
    {
      "epoch": 0.4328018223234624,
      "grad_norm": 0.30612032878616063,
      "learning_rate": 5e-06,
      "loss": 0.6313,
      "step": 190
    },
    {
      "epoch": 0.45558086560364464,
      "grad_norm": 0.3055698368680009,
      "learning_rate": 5e-06,
      "loss": 0.6408,
      "step": 200
    },
    {
      "epoch": 0.4783599088838269,
      "grad_norm": 0.3093335714854928,
      "learning_rate": 5e-06,
      "loss": 0.6357,
      "step": 210
    },
    {
      "epoch": 0.5011389521640092,
      "grad_norm": 0.2994802389469234,
      "learning_rate": 5e-06,
      "loss": 0.6396,
      "step": 220
    },
    {
      "epoch": 0.5239179954441914,
      "grad_norm": 0.3262302042973422,
      "learning_rate": 5e-06,
      "loss": 0.6351,
      "step": 230
    },
    {
      "epoch": 0.5466970387243736,
      "grad_norm": 0.3003963990271382,
      "learning_rate": 5e-06,
      "loss": 0.6317,
      "step": 240
    },
    {
      "epoch": 0.5694760820045558,
      "grad_norm": 0.3387577414932059,
      "learning_rate": 5e-06,
      "loss": 0.6354,
      "step": 250
    },
    {
      "epoch": 0.592255125284738,
      "grad_norm": 0.30285545820421356,
      "learning_rate": 5e-06,
      "loss": 0.6335,
      "step": 260
    },
    {
      "epoch": 0.6150341685649203,
      "grad_norm": 0.3155840468520353,
      "learning_rate": 5e-06,
      "loss": 0.6313,
      "step": 270
    },
    {
      "epoch": 0.6378132118451025,
      "grad_norm": 0.31986432306959706,
      "learning_rate": 5e-06,
      "loss": 0.6429,
      "step": 280
    },
    {
      "epoch": 0.6605922551252847,
      "grad_norm": 0.3215717385758522,
      "learning_rate": 5e-06,
      "loss": 0.6306,
      "step": 290
    },
    {
      "epoch": 0.683371298405467,
      "grad_norm": 0.2843677230367682,
      "learning_rate": 5e-06,
      "loss": 0.6288,
      "step": 300
    },
    {
      "epoch": 0.7061503416856492,
      "grad_norm": 0.29860979950924554,
      "learning_rate": 5e-06,
      "loss": 0.6286,
      "step": 310
    },
    {
      "epoch": 0.7289293849658315,
      "grad_norm": 0.3421102512943671,
      "learning_rate": 5e-06,
      "loss": 0.6304,
      "step": 320
    },
    {
      "epoch": 0.7517084282460137,
      "grad_norm": 0.30230237595313497,
      "learning_rate": 5e-06,
      "loss": 0.6259,
      "step": 330
    },
    {
      "epoch": 0.7744874715261959,
      "grad_norm": 0.3242375947167446,
      "learning_rate": 5e-06,
      "loss": 0.6316,
      "step": 340
    },
    {
      "epoch": 0.7972665148063781,
      "grad_norm": 0.33505088740414596,
      "learning_rate": 5e-06,
      "loss": 0.6396,
      "step": 350
    },
    {
      "epoch": 0.8200455580865603,
      "grad_norm": 0.3181545099474234,
      "learning_rate": 5e-06,
      "loss": 0.6313,
      "step": 360
    },
    {
      "epoch": 0.8428246013667426,
      "grad_norm": 0.33228646342910256,
      "learning_rate": 5e-06,
      "loss": 0.6246,
      "step": 370
    },
    {
      "epoch": 0.8656036446469249,
      "grad_norm": 0.31771307346794053,
      "learning_rate": 5e-06,
      "loss": 0.6364,
      "step": 380
    },
    {
      "epoch": 0.8883826879271071,
      "grad_norm": 0.33335301062788486,
      "learning_rate": 5e-06,
      "loss": 0.6356,
      "step": 390
    },
    {
      "epoch": 0.9111617312072893,
      "grad_norm": 0.3008063121883294,
      "learning_rate": 5e-06,
      "loss": 0.6389,
      "step": 400
    },
    {
      "epoch": 0.9339407744874715,
      "grad_norm": 0.2849573758523548,
      "learning_rate": 5e-06,
      "loss": 0.6344,
      "step": 410
    },
    {
      "epoch": 0.9567198177676538,
      "grad_norm": 0.30446671994288743,
      "learning_rate": 5e-06,
      "loss": 0.6218,
      "step": 420
    },
    {
      "epoch": 0.979498861047836,
      "grad_norm": 0.34683096229419913,
      "learning_rate": 5e-06,
      "loss": 0.6342,
      "step": 430
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6256291270256042,
      "eval_runtime": 113.4259,
      "eval_samples_per_second": 104.235,
      "eval_steps_per_second": 0.414,
      "step": 439
    },
    {
      "epoch": 1.0022779043280183,
      "grad_norm": 0.3602620020640227,
      "learning_rate": 5e-06,
      "loss": 0.6154,
      "step": 440
    },
    {
      "epoch": 1.0250569476082005,
      "grad_norm": 0.34395688755773274,
      "learning_rate": 5e-06,
      "loss": 0.6008,
      "step": 450
    },
    {
      "epoch": 1.0478359908883828,
      "grad_norm": 0.28793755227416584,
      "learning_rate": 5e-06,
      "loss": 0.5988,
      "step": 460
    },
    {
      "epoch": 1.070615034168565,
      "grad_norm": 0.3130290296959807,
      "learning_rate": 5e-06,
      "loss": 0.5963,
      "step": 470
    },
    {
      "epoch": 1.0933940774487472,
      "grad_norm": 0.3499557098228171,
      "learning_rate": 5e-06,
      "loss": 0.6032,
      "step": 480
    },
    {
      "epoch": 1.1161731207289294,
      "grad_norm": 0.3167538370762415,
      "learning_rate": 5e-06,
      "loss": 0.6081,
      "step": 490
    },
    {
      "epoch": 1.1389521640091116,
      "grad_norm": 0.3349317939917438,
      "learning_rate": 5e-06,
      "loss": 0.5983,
      "step": 500
    },
    {
      "epoch": 1.1617312072892938,
      "grad_norm": 0.3292658287931989,
      "learning_rate": 5e-06,
      "loss": 0.5955,
      "step": 510
    },
    {
      "epoch": 1.184510250569476,
      "grad_norm": 0.2967678480397173,
      "learning_rate": 5e-06,
      "loss": 0.6023,
      "step": 520
    },
    {
      "epoch": 1.2072892938496582,
      "grad_norm": 0.30361211541373534,
      "learning_rate": 5e-06,
      "loss": 0.5979,
      "step": 530
    },
    {
      "epoch": 1.2300683371298406,
      "grad_norm": 0.3144938982592506,
      "learning_rate": 5e-06,
      "loss": 0.6031,
      "step": 540
    },
    {
      "epoch": 1.2528473804100229,
      "grad_norm": 0.3224243344188798,
      "learning_rate": 5e-06,
      "loss": 0.6057,
      "step": 550
    },
    {
      "epoch": 1.275626423690205,
      "grad_norm": 0.2909142280815913,
      "learning_rate": 5e-06,
      "loss": 0.6016,
      "step": 560
    },
    {
      "epoch": 1.2984054669703873,
      "grad_norm": 0.27281571584371533,
      "learning_rate": 5e-06,
      "loss": 0.5977,
      "step": 570
    },
    {
      "epoch": 1.3211845102505695,
      "grad_norm": 0.29393369913014705,
      "learning_rate": 5e-06,
      "loss": 0.599,
      "step": 580
    },
    {
      "epoch": 1.3439635535307517,
      "grad_norm": 0.2806426163732274,
      "learning_rate": 5e-06,
      "loss": 0.5936,
      "step": 590
    },
    {
      "epoch": 1.366742596810934,
      "grad_norm": 0.32181121642041943,
      "learning_rate": 5e-06,
      "loss": 0.6035,
      "step": 600
    },
    {
      "epoch": 1.3895216400911161,
      "grad_norm": 0.33057935312052084,
      "learning_rate": 5e-06,
      "loss": 0.5998,
      "step": 610
    },
    {
      "epoch": 1.4123006833712983,
      "grad_norm": 0.29776416393925226,
      "learning_rate": 5e-06,
      "loss": 0.6048,
      "step": 620
    },
    {
      "epoch": 1.4350797266514808,
      "grad_norm": 0.3187235177646908,
      "learning_rate": 5e-06,
      "loss": 0.604,
      "step": 630
    },
    {
      "epoch": 1.4578587699316627,
      "grad_norm": 0.30109896478239506,
      "learning_rate": 5e-06,
      "loss": 0.5943,
      "step": 640
    },
    {
      "epoch": 1.4806378132118452,
      "grad_norm": 0.3058536488410727,
      "learning_rate": 5e-06,
      "loss": 0.5969,
      "step": 650
    },
    {
      "epoch": 1.5034168564920274,
      "grad_norm": 0.2961055030713261,
      "learning_rate": 5e-06,
      "loss": 0.5934,
      "step": 660
    },
    {
      "epoch": 1.5261958997722096,
      "grad_norm": 0.32268254074465025,
      "learning_rate": 5e-06,
      "loss": 0.6031,
      "step": 670
    },
    {
      "epoch": 1.5489749430523918,
      "grad_norm": 0.2884659126878991,
      "learning_rate": 5e-06,
      "loss": 0.5933,
      "step": 680
    },
    {
      "epoch": 1.571753986332574,
      "grad_norm": 0.297377445772241,
      "learning_rate": 5e-06,
      "loss": 0.5927,
      "step": 690
    },
    {
      "epoch": 1.5945330296127562,
      "grad_norm": 0.2927878668275797,
      "learning_rate": 5e-06,
      "loss": 0.6108,
      "step": 700
    },
    {
      "epoch": 1.6173120728929384,
      "grad_norm": 0.29960294143917904,
      "learning_rate": 5e-06,
      "loss": 0.5971,
      "step": 710
    },
    {
      "epoch": 1.6400911161731209,
      "grad_norm": 0.2823864099624513,
      "learning_rate": 5e-06,
      "loss": 0.599,
      "step": 720
    },
    {
      "epoch": 1.6628701594533029,
      "grad_norm": 0.3298411305027824,
      "learning_rate": 5e-06,
      "loss": 0.5988,
      "step": 730
    },
    {
      "epoch": 1.6856492027334853,
      "grad_norm": 0.32096887145187725,
      "learning_rate": 5e-06,
      "loss": 0.5942,
      "step": 740
    },
    {
      "epoch": 1.7084282460136673,
      "grad_norm": 0.326904120172968,
      "learning_rate": 5e-06,
      "loss": 0.5976,
      "step": 750
    },
    {
      "epoch": 1.7312072892938497,
      "grad_norm": 0.3004047360631492,
      "learning_rate": 5e-06,
      "loss": 0.5948,
      "step": 760
    },
    {
      "epoch": 1.753986332574032,
      "grad_norm": 0.2935646513952348,
      "learning_rate": 5e-06,
      "loss": 0.5949,
      "step": 770
    },
    {
      "epoch": 1.7767653758542141,
      "grad_norm": 0.3125619213493301,
      "learning_rate": 5e-06,
      "loss": 0.6001,
      "step": 780
    },
    {
      "epoch": 1.7995444191343963,
      "grad_norm": 0.3169307013507772,
      "learning_rate": 5e-06,
      "loss": 0.5981,
      "step": 790
    },
    {
      "epoch": 1.8223234624145785,
      "grad_norm": 0.29918234015264383,
      "learning_rate": 5e-06,
      "loss": 0.5894,
      "step": 800
    },
    {
      "epoch": 1.845102505694761,
      "grad_norm": 0.3132325711095288,
      "learning_rate": 5e-06,
      "loss": 0.59,
      "step": 810
    },
    {
      "epoch": 1.867881548974943,
      "grad_norm": 0.32890776445477105,
      "learning_rate": 5e-06,
      "loss": 0.5906,
      "step": 820
    },
    {
      "epoch": 1.8906605922551254,
      "grad_norm": 0.3219739904566219,
      "learning_rate": 5e-06,
      "loss": 0.597,
      "step": 830
    },
    {
      "epoch": 1.9134396355353074,
      "grad_norm": 0.30897624435850635,
      "learning_rate": 5e-06,
      "loss": 0.5986,
      "step": 840
    },
    {
      "epoch": 1.9362186788154898,
      "grad_norm": 0.2987799249080493,
      "learning_rate": 5e-06,
      "loss": 0.5973,
      "step": 850
    },
    {
      "epoch": 1.958997722095672,
      "grad_norm": 0.28864632125618506,
      "learning_rate": 5e-06,
      "loss": 0.5976,
      "step": 860
    },
    {
      "epoch": 1.9817767653758542,
      "grad_norm": 0.30847409916462015,
      "learning_rate": 5e-06,
      "loss": 0.5978,
      "step": 870
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6193838715553284,
      "eval_runtime": 113.1154,
      "eval_samples_per_second": 104.522,
      "eval_steps_per_second": 0.416,
      "step": 878
    },
    {
      "epoch": 2.0045558086560367,
      "grad_norm": 0.3137021968628789,
      "learning_rate": 5e-06,
      "loss": 0.5872,
      "step": 880
    },
    {
      "epoch": 2.0273348519362187,
      "grad_norm": 0.30071543886182633,
      "learning_rate": 5e-06,
      "loss": 0.556,
      "step": 890
    },
    {
      "epoch": 2.050113895216401,
      "grad_norm": 0.3181241053043949,
      "learning_rate": 5e-06,
      "loss": 0.5683,
      "step": 900
    },
    {
      "epoch": 2.072892938496583,
      "grad_norm": 0.3215476859380607,
      "learning_rate": 5e-06,
      "loss": 0.5671,
      "step": 910
    },
    {
      "epoch": 2.0956719817767655,
      "grad_norm": 0.29933719760378436,
      "learning_rate": 5e-06,
      "loss": 0.5729,
      "step": 920
    },
    {
      "epoch": 2.1184510250569475,
      "grad_norm": 0.2937608437190206,
      "learning_rate": 5e-06,
      "loss": 0.5655,
      "step": 930
    },
    {
      "epoch": 2.14123006833713,
      "grad_norm": 0.310137570277187,
      "learning_rate": 5e-06,
      "loss": 0.5684,
      "step": 940
    },
    {
      "epoch": 2.164009111617312,
      "grad_norm": 0.2880285833232218,
      "learning_rate": 5e-06,
      "loss": 0.5635,
      "step": 950
    },
    {
      "epoch": 2.1867881548974943,
      "grad_norm": 0.29687571567703486,
      "learning_rate": 5e-06,
      "loss": 0.5684,
      "step": 960
    },
    {
      "epoch": 2.2095671981776768,
      "grad_norm": 0.3083759467790449,
      "learning_rate": 5e-06,
      "loss": 0.5694,
      "step": 970
    },
    {
      "epoch": 2.2323462414578588,
      "grad_norm": 0.2960376868080064,
      "learning_rate": 5e-06,
      "loss": 0.5618,
      "step": 980
    },
    {
      "epoch": 2.255125284738041,
      "grad_norm": 0.2729683850426089,
      "learning_rate": 5e-06,
      "loss": 0.5659,
      "step": 990
    },
    {
      "epoch": 2.277904328018223,
      "grad_norm": 0.3676983350737448,
      "learning_rate": 5e-06,
      "loss": 0.5677,
      "step": 1000
    },
    {
      "epoch": 2.3006833712984056,
      "grad_norm": 0.29979543582966117,
      "learning_rate": 5e-06,
      "loss": 0.5657,
      "step": 1010
    },
    {
      "epoch": 2.3234624145785876,
      "grad_norm": 0.3150574450739465,
      "learning_rate": 5e-06,
      "loss": 0.5695,
      "step": 1020
    },
    {
      "epoch": 2.34624145785877,
      "grad_norm": 0.29866514403413835,
      "learning_rate": 5e-06,
      "loss": 0.57,
      "step": 1030
    },
    {
      "epoch": 2.369020501138952,
      "grad_norm": 0.30022038641134147,
      "learning_rate": 5e-06,
      "loss": 0.5678,
      "step": 1040
    },
    {
      "epoch": 2.3917995444191344,
      "grad_norm": 0.30344605993782325,
      "learning_rate": 5e-06,
      "loss": 0.5655,
      "step": 1050
    },
    {
      "epoch": 2.4145785876993164,
      "grad_norm": 0.30571626801721524,
      "learning_rate": 5e-06,
      "loss": 0.5764,
      "step": 1060
    },
    {
      "epoch": 2.437357630979499,
      "grad_norm": 0.32949832175555666,
      "learning_rate": 5e-06,
      "loss": 0.5791,
      "step": 1070
    },
    {
      "epoch": 2.4601366742596813,
      "grad_norm": 0.3149321897462233,
      "learning_rate": 5e-06,
      "loss": 0.5743,
      "step": 1080
    },
    {
      "epoch": 2.4829157175398633,
      "grad_norm": 0.30371196782165644,
      "learning_rate": 5e-06,
      "loss": 0.5726,
      "step": 1090
    },
    {
      "epoch": 2.5056947608200457,
      "grad_norm": 0.3550601237225024,
      "learning_rate": 5e-06,
      "loss": 0.5779,
      "step": 1100
    },
    {
      "epoch": 2.5284738041002277,
      "grad_norm": 0.32449640072708563,
      "learning_rate": 5e-06,
      "loss": 0.5696,
      "step": 1110
    },
    {
      "epoch": 2.55125284738041,
      "grad_norm": 0.29536363274710853,
      "learning_rate": 5e-06,
      "loss": 0.5708,
      "step": 1120
    },
    {
      "epoch": 2.574031890660592,
      "grad_norm": 0.32326444150399974,
      "learning_rate": 5e-06,
      "loss": 0.5687,
      "step": 1130
    },
    {
      "epoch": 2.5968109339407746,
      "grad_norm": 0.29854931304839455,
      "learning_rate": 5e-06,
      "loss": 0.57,
      "step": 1140
    },
    {
      "epoch": 2.619589977220957,
      "grad_norm": 0.2774546049422405,
      "learning_rate": 5e-06,
      "loss": 0.5687,
      "step": 1150
    },
    {
      "epoch": 2.642369020501139,
      "grad_norm": 0.320847736330343,
      "learning_rate": 5e-06,
      "loss": 0.5683,
      "step": 1160
    },
    {
      "epoch": 2.665148063781321,
      "grad_norm": 0.3038825483920144,
      "learning_rate": 5e-06,
      "loss": 0.5756,
      "step": 1170
    },
    {
      "epoch": 2.6879271070615034,
      "grad_norm": 0.31626522926626655,
      "learning_rate": 5e-06,
      "loss": 0.5688,
      "step": 1180
    },
    {
      "epoch": 2.710706150341686,
      "grad_norm": 0.31475420899136236,
      "learning_rate": 5e-06,
      "loss": 0.5668,
      "step": 1190
    },
    {
      "epoch": 2.733485193621868,
      "grad_norm": 0.3032040716975987,
      "learning_rate": 5e-06,
      "loss": 0.5735,
      "step": 1200
    },
    {
      "epoch": 2.7562642369020502,
      "grad_norm": 0.294489594430855,
      "learning_rate": 5e-06,
      "loss": 0.5746,
      "step": 1210
    },
    {
      "epoch": 2.7790432801822322,
      "grad_norm": 0.28352737426646324,
      "learning_rate": 5e-06,
      "loss": 0.5645,
      "step": 1220
    },
    {
      "epoch": 2.8018223234624147,
      "grad_norm": 0.3019187072329014,
      "learning_rate": 5e-06,
      "loss": 0.5662,
      "step": 1230
    },
    {
      "epoch": 2.8246013667425967,
      "grad_norm": 0.29450570760369266,
      "learning_rate": 5e-06,
      "loss": 0.5776,
      "step": 1240
    },
    {
      "epoch": 2.847380410022779,
      "grad_norm": 0.28917558370883034,
      "learning_rate": 5e-06,
      "loss": 0.5766,
      "step": 1250
    },
    {
      "epoch": 2.8701594533029615,
      "grad_norm": 0.28348244461550015,
      "learning_rate": 5e-06,
      "loss": 0.5712,
      "step": 1260
    },
    {
      "epoch": 2.8929384965831435,
      "grad_norm": 0.29607489274032067,
      "learning_rate": 5e-06,
      "loss": 0.5739,
      "step": 1270
    },
    {
      "epoch": 2.9157175398633255,
      "grad_norm": 0.3154865371104941,
      "learning_rate": 5e-06,
      "loss": 0.5664,
      "step": 1280
    },
    {
      "epoch": 2.938496583143508,
      "grad_norm": 0.3261178018397659,
      "learning_rate": 5e-06,
      "loss": 0.5603,
      "step": 1290
    },
    {
      "epoch": 2.9612756264236904,
      "grad_norm": 0.2965242333469874,
      "learning_rate": 5e-06,
      "loss": 0.5668,
      "step": 1300
    },
    {
      "epoch": 2.9840546697038723,
      "grad_norm": 0.2979844145574236,
      "learning_rate": 5e-06,
      "loss": 0.5732,
      "step": 1310
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6193576455116272,
      "eval_runtime": 113.4465,
      "eval_samples_per_second": 104.217,
      "eval_steps_per_second": 0.414,
      "step": 1317
    },
    {
      "epoch": 3.0068337129840548,
      "grad_norm": 0.2956883479073517,
      "learning_rate": 5e-06,
      "loss": 0.5578,
      "step": 1320
    },
    {
      "epoch": 3.0296127562642368,
      "grad_norm": 0.3283040695026618,
      "learning_rate": 5e-06,
      "loss": 0.5379,
      "step": 1330
    },
    {
      "epoch": 3.052391799544419,
      "grad_norm": 0.28542889086490736,
      "learning_rate": 5e-06,
      "loss": 0.5411,
      "step": 1340
    },
    {
      "epoch": 3.075170842824601,
      "grad_norm": 0.31853253784878555,
      "learning_rate": 5e-06,
      "loss": 0.5424,
      "step": 1350
    },
    {
      "epoch": 3.0979498861047836,
      "grad_norm": 0.2987374379369755,
      "learning_rate": 5e-06,
      "loss": 0.5382,
      "step": 1360
    },
    {
      "epoch": 3.120728929384966,
      "grad_norm": 0.28369399180470734,
      "learning_rate": 5e-06,
      "loss": 0.5396,
      "step": 1370
    },
    {
      "epoch": 3.143507972665148,
      "grad_norm": 0.29848307489101883,
      "learning_rate": 5e-06,
      "loss": 0.5379,
      "step": 1380
    },
    {
      "epoch": 3.1662870159453305,
      "grad_norm": 0.28281172058487525,
      "learning_rate": 5e-06,
      "loss": 0.5378,
      "step": 1390
    },
    {
      "epoch": 3.1890660592255125,
      "grad_norm": 0.326068339866218,
      "learning_rate": 5e-06,
      "loss": 0.5355,
      "step": 1400
    },
    {
      "epoch": 3.211845102505695,
      "grad_norm": 0.286394634763708,
      "learning_rate": 5e-06,
      "loss": 0.5392,
      "step": 1410
    },
    {
      "epoch": 3.234624145785877,
      "grad_norm": 0.29481950476140845,
      "learning_rate": 5e-06,
      "loss": 0.5453,
      "step": 1420
    },
    {
      "epoch": 3.2574031890660593,
      "grad_norm": 0.30132819765081525,
      "learning_rate": 5e-06,
      "loss": 0.5462,
      "step": 1430
    },
    {
      "epoch": 3.2801822323462413,
      "grad_norm": 0.2995713700746164,
      "learning_rate": 5e-06,
      "loss": 0.5389,
      "step": 1440
    },
    {
      "epoch": 3.3029612756264237,
      "grad_norm": 0.30326731163716586,
      "learning_rate": 5e-06,
      "loss": 0.536,
      "step": 1450
    },
    {
      "epoch": 3.3257403189066057,
      "grad_norm": 0.3083162582031878,
      "learning_rate": 5e-06,
      "loss": 0.5386,
      "step": 1460
    },
    {
      "epoch": 3.348519362186788,
      "grad_norm": 0.29491218271079633,
      "learning_rate": 5e-06,
      "loss": 0.5399,
      "step": 1470
    },
    {
      "epoch": 3.3712984054669706,
      "grad_norm": 0.32397760989963276,
      "learning_rate": 5e-06,
      "loss": 0.5424,
      "step": 1480
    },
    {
      "epoch": 3.3940774487471526,
      "grad_norm": 0.3109701142211013,
      "learning_rate": 5e-06,
      "loss": 0.541,
      "step": 1490
    },
    {
      "epoch": 3.416856492027335,
      "grad_norm": 0.28649653583977264,
      "learning_rate": 5e-06,
      "loss": 0.5383,
      "step": 1500
    },
    {
      "epoch": 3.439635535307517,
      "grad_norm": 0.29162775892122766,
      "learning_rate": 5e-06,
      "loss": 0.543,
      "step": 1510
    },
    {
      "epoch": 3.4624145785876994,
      "grad_norm": 0.328813316428343,
      "learning_rate": 5e-06,
      "loss": 0.5402,
      "step": 1520
    },
    {
      "epoch": 3.4851936218678814,
      "grad_norm": 0.296329700264349,
      "learning_rate": 5e-06,
      "loss": 0.548,
      "step": 1530
    },
    {
      "epoch": 3.507972665148064,
      "grad_norm": 0.32679718874242103,
      "learning_rate": 5e-06,
      "loss": 0.5481,
      "step": 1540
    },
    {
      "epoch": 3.5307517084282463,
      "grad_norm": 0.2978227357429331,
      "learning_rate": 5e-06,
      "loss": 0.5436,
      "step": 1550
    },
    {
      "epoch": 3.5535307517084282,
      "grad_norm": 0.30550394149901167,
      "learning_rate": 5e-06,
      "loss": 0.5429,
      "step": 1560
    },
    {
      "epoch": 3.5763097949886102,
      "grad_norm": 0.34688194348484774,
      "learning_rate": 5e-06,
      "loss": 0.5458,
      "step": 1570
    },
    {
      "epoch": 3.5990888382687927,
      "grad_norm": 0.2994450574269458,
      "learning_rate": 5e-06,
      "loss": 0.546,
      "step": 1580
    },
    {
      "epoch": 3.621867881548975,
      "grad_norm": 0.31537321423200465,
      "learning_rate": 5e-06,
      "loss": 0.5422,
      "step": 1590
    },
    {
      "epoch": 3.644646924829157,
      "grad_norm": 0.3063603045559125,
      "learning_rate": 5e-06,
      "loss": 0.5359,
      "step": 1600
    },
    {
      "epoch": 3.6674259681093395,
      "grad_norm": 0.2916735901907535,
      "learning_rate": 5e-06,
      "loss": 0.5422,
      "step": 1610
    },
    {
      "epoch": 3.6902050113895215,
      "grad_norm": 0.30734650480956516,
      "learning_rate": 5e-06,
      "loss": 0.5427,
      "step": 1620
    },
    {
      "epoch": 3.712984054669704,
      "grad_norm": 0.3033502937728263,
      "learning_rate": 5e-06,
      "loss": 0.5419,
      "step": 1630
    },
    {
      "epoch": 3.735763097949886,
      "grad_norm": 0.30259245354328573,
      "learning_rate": 5e-06,
      "loss": 0.5384,
      "step": 1640
    },
    {
      "epoch": 3.7585421412300684,
      "grad_norm": 0.31130340672642876,
      "learning_rate": 5e-06,
      "loss": 0.552,
      "step": 1650
    },
    {
      "epoch": 3.781321184510251,
      "grad_norm": 0.30596028970571365,
      "learning_rate": 5e-06,
      "loss": 0.5416,
      "step": 1660
    },
    {
      "epoch": 3.8041002277904328,
      "grad_norm": 0.29635873101912724,
      "learning_rate": 5e-06,
      "loss": 0.5497,
      "step": 1670
    },
    {
      "epoch": 3.8268792710706148,
      "grad_norm": 0.3197535185114282,
      "learning_rate": 5e-06,
      "loss": 0.5429,
      "step": 1680
    },
    {
      "epoch": 3.849658314350797,
      "grad_norm": 0.3011450510960511,
      "learning_rate": 5e-06,
      "loss": 0.5451,
      "step": 1690
    },
    {
      "epoch": 3.8724373576309796,
      "grad_norm": 0.29556191119994085,
      "learning_rate": 5e-06,
      "loss": 0.5422,
      "step": 1700
    },
    {
      "epoch": 3.8952164009111616,
      "grad_norm": 0.29782230107739593,
      "learning_rate": 5e-06,
      "loss": 0.5463,
      "step": 1710
    },
    {
      "epoch": 3.917995444191344,
      "grad_norm": 0.2786017141276205,
      "learning_rate": 5e-06,
      "loss": 0.5505,
      "step": 1720
    },
    {
      "epoch": 3.940774487471526,
      "grad_norm": 0.3011821733566416,
      "learning_rate": 5e-06,
      "loss": 0.5496,
      "step": 1730
    },
    {
      "epoch": 3.9635535307517085,
      "grad_norm": 0.2891980461006773,
      "learning_rate": 5e-06,
      "loss": 0.5511,
      "step": 1740
    },
    {
      "epoch": 3.9863325740318905,
      "grad_norm": 0.29323206246213684,
      "learning_rate": 5e-06,
      "loss": 0.5461,
      "step": 1750
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.6239981055259705,
      "eval_runtime": 113.6401,
      "eval_samples_per_second": 104.039,
      "eval_steps_per_second": 0.414,
      "step": 1756
    },
    {
      "epoch": 4.009111617312073,
      "grad_norm": 0.31845782541537054,
      "learning_rate": 5e-06,
      "loss": 0.5355,
      "step": 1760
    },
    {
      "epoch": 4.031890660592255,
      "grad_norm": 0.3247571121989434,
      "learning_rate": 5e-06,
      "loss": 0.5112,
      "step": 1770
    },
    {
      "epoch": 4.054669703872437,
      "grad_norm": 0.33205526411756225,
      "learning_rate": 5e-06,
      "loss": 0.5155,
      "step": 1780
    },
    {
      "epoch": 4.077448747152619,
      "grad_norm": 0.2961306281740012,
      "learning_rate": 5e-06,
      "loss": 0.5107,
      "step": 1790
    },
    {
      "epoch": 4.100227790432802,
      "grad_norm": 0.29404582667456747,
      "learning_rate": 5e-06,
      "loss": 0.5168,
      "step": 1800
    },
    {
      "epoch": 4.123006833712984,
      "grad_norm": 0.29099721485432206,
      "learning_rate": 5e-06,
      "loss": 0.5126,
      "step": 1810
    },
    {
      "epoch": 4.145785876993166,
      "grad_norm": 0.2850302733912273,
      "learning_rate": 5e-06,
      "loss": 0.5134,
      "step": 1820
    },
    {
      "epoch": 4.168564920273348,
      "grad_norm": 0.28612051891525286,
      "learning_rate": 5e-06,
      "loss": 0.5093,
      "step": 1830
    },
    {
      "epoch": 4.191343963553531,
      "grad_norm": 0.29474345150964504,
      "learning_rate": 5e-06,
      "loss": 0.5174,
      "step": 1840
    },
    {
      "epoch": 4.214123006833713,
      "grad_norm": 0.3002301077876599,
      "learning_rate": 5e-06,
      "loss": 0.5172,
      "step": 1850
    },
    {
      "epoch": 4.236902050113895,
      "grad_norm": 0.2920498114457919,
      "learning_rate": 5e-06,
      "loss": 0.5121,
      "step": 1860
    },
    {
      "epoch": 4.259681093394078,
      "grad_norm": 0.2942506005889262,
      "learning_rate": 5e-06,
      "loss": 0.5101,
      "step": 1870
    },
    {
      "epoch": 4.28246013667426,
      "grad_norm": 0.3069703095242122,
      "learning_rate": 5e-06,
      "loss": 0.5144,
      "step": 1880
    },
    {
      "epoch": 4.305239179954442,
      "grad_norm": 0.2997675139173423,
      "learning_rate": 5e-06,
      "loss": 0.517,
      "step": 1890
    },
    {
      "epoch": 4.328018223234624,
      "grad_norm": 0.3017224318798671,
      "learning_rate": 5e-06,
      "loss": 0.5163,
      "step": 1900
    },
    {
      "epoch": 4.350797266514807,
      "grad_norm": 0.32710267583639663,
      "learning_rate": 5e-06,
      "loss": 0.517,
      "step": 1910
    },
    {
      "epoch": 4.373576309794989,
      "grad_norm": 0.35589318746923176,
      "learning_rate": 5e-06,
      "loss": 0.5148,
      "step": 1920
    },
    {
      "epoch": 4.396355353075171,
      "grad_norm": 0.29856323049173306,
      "learning_rate": 5e-06,
      "loss": 0.5167,
      "step": 1930
    },
    {
      "epoch": 4.4191343963553535,
      "grad_norm": 0.31561434261206783,
      "learning_rate": 5e-06,
      "loss": 0.51,
      "step": 1940
    },
    {
      "epoch": 4.4419134396355355,
      "grad_norm": 0.32343506635297187,
      "learning_rate": 5e-06,
      "loss": 0.5172,
      "step": 1950
    },
    {
      "epoch": 4.4646924829157175,
      "grad_norm": 0.2920601079152555,
      "learning_rate": 5e-06,
      "loss": 0.5134,
      "step": 1960
    },
    {
      "epoch": 4.4874715261958995,
      "grad_norm": 0.30047616053441856,
      "learning_rate": 5e-06,
      "loss": 0.5123,
      "step": 1970
    },
    {
      "epoch": 4.510250569476082,
      "grad_norm": 0.299324693496857,
      "learning_rate": 5e-06,
      "loss": 0.5177,
      "step": 1980
    },
    {
      "epoch": 4.533029612756264,
      "grad_norm": 0.30340189870468204,
      "learning_rate": 5e-06,
      "loss": 0.5095,
      "step": 1990
    },
    {
      "epoch": 4.555808656036446,
      "grad_norm": 0.32578537933466617,
      "learning_rate": 5e-06,
      "loss": 0.5126,
      "step": 2000
    },
    {
      "epoch": 4.578587699316628,
      "grad_norm": 0.3214168201654836,
      "learning_rate": 5e-06,
      "loss": 0.516,
      "step": 2010
    },
    {
      "epoch": 4.601366742596811,
      "grad_norm": 0.33535913909657655,
      "learning_rate": 5e-06,
      "loss": 0.516,
      "step": 2020
    },
    {
      "epoch": 4.624145785876993,
      "grad_norm": 0.34950298355241916,
      "learning_rate": 5e-06,
      "loss": 0.5159,
      "step": 2030
    },
    {
      "epoch": 4.646924829157175,
      "grad_norm": 0.3067631933457454,
      "learning_rate": 5e-06,
      "loss": 0.5103,
      "step": 2040
    },
    {
      "epoch": 4.669703872437358,
      "grad_norm": 0.31011573141446475,
      "learning_rate": 5e-06,
      "loss": 0.526,
      "step": 2050
    },
    {
      "epoch": 4.69248291571754,
      "grad_norm": 0.31485826733211975,
      "learning_rate": 5e-06,
      "loss": 0.5205,
      "step": 2060
    },
    {
      "epoch": 4.715261958997722,
      "grad_norm": 0.2981899092207014,
      "learning_rate": 5e-06,
      "loss": 0.5128,
      "step": 2070
    },
    {
      "epoch": 4.738041002277904,
      "grad_norm": 0.30070781244970324,
      "learning_rate": 5e-06,
      "loss": 0.5195,
      "step": 2080
    },
    {
      "epoch": 4.760820045558087,
      "grad_norm": 0.29089650375946846,
      "learning_rate": 5e-06,
      "loss": 0.5192,
      "step": 2090
    },
    {
      "epoch": 4.783599088838269,
      "grad_norm": 0.32942349791391345,
      "learning_rate": 5e-06,
      "loss": 0.5155,
      "step": 2100
    },
    {
      "epoch": 4.806378132118451,
      "grad_norm": 0.30690284165223813,
      "learning_rate": 5e-06,
      "loss": 0.5157,
      "step": 2110
    },
    {
      "epoch": 4.829157175398633,
      "grad_norm": 0.29755186369998715,
      "learning_rate": 5e-06,
      "loss": 0.515,
      "step": 2120
    },
    {
      "epoch": 4.851936218678816,
      "grad_norm": 0.29726224376764365,
      "learning_rate": 5e-06,
      "loss": 0.52,
      "step": 2130
    },
    {
      "epoch": 4.874715261958998,
      "grad_norm": 0.3121093770179605,
      "learning_rate": 5e-06,
      "loss": 0.5214,
      "step": 2140
    },
    {
      "epoch": 4.89749430523918,
      "grad_norm": 0.2921989069170297,
      "learning_rate": 5e-06,
      "loss": 0.5141,
      "step": 2150
    },
    {
      "epoch": 4.920273348519363,
      "grad_norm": 0.3137625481692737,
      "learning_rate": 5e-06,
      "loss": 0.5191,
      "step": 2160
    },
    {
      "epoch": 4.943052391799545,
      "grad_norm": 0.31268104737726976,
      "learning_rate": 5e-06,
      "loss": 0.5204,
      "step": 2170
    },
    {
      "epoch": 4.965831435079727,
      "grad_norm": 0.31240087794789345,
      "learning_rate": 5e-06,
      "loss": 0.5214,
      "step": 2180
    },
    {
      "epoch": 4.988610478359909,
      "grad_norm": 0.27920850439212735,
      "learning_rate": 5e-06,
      "loss": 0.5179,
      "step": 2190
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.6346195340156555,
      "eval_runtime": 112.3467,
      "eval_samples_per_second": 105.237,
      "eval_steps_per_second": 0.418,
      "step": 2195
    },
    {
      "epoch": 5.0,
      "step": 2195,
      "total_flos": 4601905523195904.0,
      "train_loss": 0.5737499028512177,
      "train_runtime": 30529.5931,
      "train_samples_per_second": 36.787,
      "train_steps_per_second": 0.072
    }
  ],
  "logging_steps": 10,
  "max_steps": 2195,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4601905523195904.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}