{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.997349589186324,
  "eval_steps": 200,
  "global_step": 942,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010601643254704479,
      "grad_norm": 0.8797913789749146,
      "learning_rate": 5.208333333333334e-06,
      "loss": 3.3968,
      "num_input_tokens_seen": 10485760,
      "step": 5
    },
    {
      "epoch": 0.021203286509408958,
      "grad_norm": 0.5857719779014587,
      "learning_rate": 1.0416666666666668e-05,
      "loss": 3.3102,
      "num_input_tokens_seen": 20971520,
      "step": 10
    },
    {
      "epoch": 0.031804929764113435,
      "grad_norm": 0.38287150859832764,
      "learning_rate": 1.5625e-05,
      "loss": 3.3919,
      "num_input_tokens_seen": 31457280,
      "step": 15
    },
    {
      "epoch": 0.042406573018817915,
      "grad_norm": 0.2890233099460602,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 3.3448,
      "num_input_tokens_seen": 41943040,
      "step": 20
    },
    {
      "epoch": 0.053008216273522396,
      "grad_norm": 0.28800511360168457,
      "learning_rate": 2.604166666666667e-05,
      "loss": 3.247,
      "num_input_tokens_seen": 52428800,
      "step": 25
    },
    {
      "epoch": 0.06360985952822687,
      "grad_norm": 0.5624825358390808,
      "learning_rate": 3.125e-05,
      "loss": 3.3736,
      "num_input_tokens_seen": 62914560,
      "step": 30
    },
    {
      "epoch": 0.07421150278293136,
      "grad_norm": 0.2708434760570526,
      "learning_rate": 3.6458333333333336e-05,
      "loss": 3.3105,
      "num_input_tokens_seen": 73400320,
      "step": 35
    },
    {
      "epoch": 0.08481314603763583,
      "grad_norm": 0.26101428270339966,
      "learning_rate": 4.166666666666667e-05,
      "loss": 3.3523,
      "num_input_tokens_seen": 83886080,
      "step": 40
    },
    {
      "epoch": 0.09541478929234032,
      "grad_norm": 0.22077707946300507,
      "learning_rate": 4.6875e-05,
      "loss": 3.3395,
      "num_input_tokens_seen": 94371840,
      "step": 45
    },
    {
      "epoch": 0.10601643254704479,
      "grad_norm": 0.2976844608783722,
      "learning_rate": 4.9999382562611344e-05,
      "loss": 3.2379,
      "num_input_tokens_seen": 104857600,
      "step": 50
    },
    {
      "epoch": 0.11661807580174927,
      "grad_norm": 0.32657739520072937,
      "learning_rate": 4.999243674223826e-05,
      "loss": 3.2281,
      "num_input_tokens_seen": 115343360,
      "step": 55
    },
    {
      "epoch": 0.12721971905645374,
      "grad_norm": 0.2382456362247467,
      "learning_rate": 4.997777545616258e-05,
      "loss": 3.2807,
      "num_input_tokens_seen": 125829120,
      "step": 60
    },
    {
      "epoch": 0.13782136231115824,
      "grad_norm": 0.4440530836582184,
      "learning_rate": 4.99554032304996e-05,
      "loss": 3.2192,
      "num_input_tokens_seen": 136314880,
      "step": 65
    },
    {
      "epoch": 0.14842300556586271,
      "grad_norm": 0.2103557139635086,
      "learning_rate": 4.9925326971824345e-05,
      "loss": 3.3152,
      "num_input_tokens_seen": 146800640,
      "step": 70
    },
    {
      "epoch": 0.1590246488205672,
      "grad_norm": 0.252693772315979,
      "learning_rate": 4.988755596503948e-05,
      "loss": 3.2393,
      "num_input_tokens_seen": 157286400,
      "step": 75
    },
    {
      "epoch": 0.16962629207527166,
      "grad_norm": 0.21133287250995636,
      "learning_rate": 4.9842101870508904e-05,
      "loss": 3.2727,
      "num_input_tokens_seen": 167772160,
      "step": 80
    },
    {
      "epoch": 0.18022793532997614,
      "grad_norm": 0.24876847863197327,
      "learning_rate": 4.9788978720458104e-05,
      "loss": 3.2566,
      "num_input_tokens_seen": 178257920,
      "step": 85
    },
    {
      "epoch": 0.19082957858468064,
      "grad_norm": 0.2968827486038208,
      "learning_rate": 4.9728202914642183e-05,
      "loss": 3.3258,
      "num_input_tokens_seen": 188743680,
      "step": 90
    },
    {
      "epoch": 0.2014312218393851,
      "grad_norm": 0.17700955271720886,
      "learning_rate": 4.965979321528309e-05,
      "loss": 3.2355,
      "num_input_tokens_seen": 199229440,
      "step": 95
    },
    {
      "epoch": 0.21203286509408958,
      "grad_norm": 0.20748387277126312,
      "learning_rate": 4.9583770741277505e-05,
      "loss": 3.195,
      "num_input_tokens_seen": 209715200,
      "step": 100
    },
    {
      "epoch": 0.22263450834879406,
      "grad_norm": 1.2878308296203613,
      "learning_rate": 4.950015896167716e-05,
      "loss": 3.3275,
      "num_input_tokens_seen": 220200960,
      "step": 105
    },
    {
      "epoch": 0.23323615160349853,
      "grad_norm": 0.26103636622428894,
      "learning_rate": 4.9408983688443654e-05,
      "loss": 3.3154,
      "num_input_tokens_seen": 230686720,
      "step": 110
    },
    {
      "epoch": 0.24383779485820303,
      "grad_norm": 0.2692287266254425,
      "learning_rate": 4.931027306848004e-05,
      "loss": 3.2573,
      "num_input_tokens_seen": 241172480,
      "step": 115
    },
    {
      "epoch": 0.2544394381129075,
      "grad_norm": 0.2487805187702179,
      "learning_rate": 4.920405757494147e-05,
      "loss": 3.2915,
      "num_input_tokens_seen": 251658240,
      "step": 120
    },
    {
      "epoch": 0.26504108136761195,
      "grad_norm": 0.17953425645828247,
      "learning_rate": 4.9090369997827826e-05,
      "loss": 3.1941,
      "num_input_tokens_seen": 262144000,
      "step": 125
    },
    {
      "epoch": 0.2756427246223165,
      "grad_norm": 0.19957853853702545,
      "learning_rate": 4.896924543386099e-05,
      "loss": 3.3033,
      "num_input_tokens_seen": 272629760,
      "step": 130
    },
    {
      "epoch": 0.28624436787702096,
      "grad_norm": 0.22015607357025146,
      "learning_rate": 4.884072127565014e-05,
      "loss": 3.2327,
      "num_input_tokens_seen": 283115520,
      "step": 135
    },
    {
      "epoch": 0.29684601113172543,
      "grad_norm": 0.241306334733963,
      "learning_rate": 4.870483720014814e-05,
      "loss": 3.2124,
      "num_input_tokens_seen": 293601280,
      "step": 140
    },
    {
      "epoch": 0.3074476543864299,
      "grad_norm": 0.49794742465019226,
      "learning_rate": 4.85616351564028e-05,
      "loss": 3.312,
      "num_input_tokens_seen": 304087040,
      "step": 145
    },
    {
      "epoch": 0.3180492976411344,
      "grad_norm": 0.18301662802696228,
      "learning_rate": 4.8411159352606734e-05,
      "loss": 3.295,
      "num_input_tokens_seen": 314572800,
      "step": 150
    },
    {
      "epoch": 0.32865094089583885,
      "grad_norm": 0.23481640219688416,
      "learning_rate": 4.8253456242449704e-05,
      "loss": 3.2555,
      "num_input_tokens_seen": 325058560,
      "step": 155
    },
    {
      "epoch": 0.3392525841505433,
      "grad_norm": 0.2195325493812561,
      "learning_rate": 4.808857451077788e-05,
      "loss": 3.1667,
      "num_input_tokens_seen": 335544320,
      "step": 160
    },
    {
      "epoch": 0.3498542274052478,
      "grad_norm": 0.23738664388656616,
      "learning_rate": 4.7916565058564155e-05,
      "loss": 3.2499,
      "num_input_tokens_seen": 346030080,
      "step": 165
    },
    {
      "epoch": 0.36045587065995227,
      "grad_norm": 0.3056640028953552,
      "learning_rate": 4.7737480987194484e-05,
      "loss": 3.2478,
      "num_input_tokens_seen": 356515840,
      "step": 170
    },
    {
      "epoch": 0.37105751391465674,
      "grad_norm": 0.18291524052619934,
      "learning_rate": 4.755137758207479e-05,
      "loss": 3.2648,
      "num_input_tokens_seen": 367001600,
      "step": 175
    },
    {
      "epoch": 0.3816591571693613,
      "grad_norm": 0.20183615386486053,
      "learning_rate": 4.7358312295563734e-05,
      "loss": 3.1717,
      "num_input_tokens_seen": 377487360,
      "step": 180
    },
    {
      "epoch": 0.39226080042406575,
      "grad_norm": 0.19222132861614227,
      "learning_rate": 4.7158344729236454e-05,
      "loss": 3.2288,
      "num_input_tokens_seen": 387973120,
      "step": 185
    },
    {
      "epoch": 0.4028624436787702,
      "grad_norm": 0.16234181821346283,
      "learning_rate": 4.6951536615484854e-05,
      "loss": 3.2316,
      "num_input_tokens_seen": 398458880,
      "step": 190
    },
    {
      "epoch": 0.4134640869334747,
      "grad_norm": 0.21459302306175232,
      "learning_rate": 4.673795179846007e-05,
      "loss": 3.1703,
      "num_input_tokens_seen": 408944640,
      "step": 195
    },
    {
      "epoch": 0.42406573018817917,
      "grad_norm": 0.1751609593629837,
      "learning_rate": 4.651765621436303e-05,
      "loss": 3.2013,
      "num_input_tokens_seen": 419430400,
      "step": 200
    },
    {
      "epoch": 0.42406573018817917,
      "eval_accuracy": 0.44791084254003133,
      "eval_loss": 3.0653164386749268,
      "eval_runtime": 36.089,
      "eval_samples_per_second": 8.313,
      "eval_steps_per_second": 2.078,
      "num_input_tokens_seen": 419430400,
      "step": 200
    },
    {
      "epoch": 0.43466737344288364,
      "grad_norm": 0.15440785884857178,
      "learning_rate": 4.62907178710891e-05,
      "loss": 3.2764,
      "num_input_tokens_seen": 429916160,
      "step": 205
    },
    {
      "epoch": 0.4452690166975881,
      "grad_norm": 0.19598723948001862,
      "learning_rate": 4.60572068272333e-05,
      "loss": 3.2128,
      "num_input_tokens_seen": 440401920,
      "step": 210
    },
    {
      "epoch": 0.4558706599522926,
      "grad_norm": 0.21214532852172852,
      "learning_rate": 4.581719517046236e-05,
      "loss": 3.1353,
      "num_input_tokens_seen": 450887680,
      "step": 215
    },
    {
      "epoch": 0.46647230320699706,
      "grad_norm": 0.181034654378891,
      "learning_rate": 4.557075699526032e-05,
      "loss": 3.2866,
      "num_input_tokens_seen": 461373440,
      "step": 220
    },
    {
      "epoch": 0.47707394646170154,
      "grad_norm": 0.16727791726589203,
      "learning_rate": 4.531796838005477e-05,
      "loss": 3.2111,
      "num_input_tokens_seen": 471859200,
      "step": 225
    },
    {
      "epoch": 0.48767558971640607,
      "grad_norm": 0.1804332137107849,
      "learning_rate": 4.505890736373045e-05,
      "loss": 3.297,
      "num_input_tokens_seen": 482344960,
      "step": 230
    },
    {
      "epoch": 0.49827723297111054,
      "grad_norm": 0.21492359042167664,
      "learning_rate": 4.479365392153776e-05,
      "loss": 3.1203,
      "num_input_tokens_seen": 492830720,
      "step": 235
    },
    {
      "epoch": 0.508878876225815,
      "grad_norm": 0.2664985656738281,
      "learning_rate": 4.4522289940403404e-05,
      "loss": 3.1352,
      "num_input_tokens_seen": 503316480,
      "step": 240
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 0.18706196546554565,
      "learning_rate": 4.4244899193650933e-05,
      "loss": 3.1747,
      "num_input_tokens_seen": 513802240,
      "step": 245
    },
    {
      "epoch": 0.5300821627352239,
      "grad_norm": 0.2427309900522232,
      "learning_rate": 4.3961567315138885e-05,
      "loss": 3.1677,
      "num_input_tokens_seen": 524288000,
      "step": 250
    },
    {
      "epoch": 0.5406838059899285,
      "grad_norm": 0.17540065944194794,
      "learning_rate": 4.3672381772824615e-05,
      "loss": 3.2012,
      "num_input_tokens_seen": 534773760,
      "step": 255
    },
    {
      "epoch": 0.551285449244633,
      "grad_norm": 0.31619423627853394,
      "learning_rate": 4.3377431841761875e-05,
      "loss": 3.1498,
      "num_input_tokens_seen": 545259520,
      "step": 260
    },
    {
      "epoch": 0.5618870924993374,
      "grad_norm": 0.24162785708904266,
      "learning_rate": 4.307680857654052e-05,
      "loss": 3.1703,
      "num_input_tokens_seen": 555745280,
      "step": 265
    },
    {
      "epoch": 0.5724887357540419,
      "grad_norm": 0.22926253080368042,
      "learning_rate": 4.277060478317687e-05,
      "loss": 3.2395,
      "num_input_tokens_seen": 566231040,
      "step": 270
    },
    {
      "epoch": 0.5830903790087464,
      "grad_norm": 0.23989850282669067,
      "learning_rate": 4.245891499046338e-05,
      "loss": 3.2383,
      "num_input_tokens_seen": 576716800,
      "step": 275
    },
    {
      "epoch": 0.5936920222634509,
      "grad_norm": 0.20367790758609772,
      "learning_rate": 4.214183542078646e-05,
      "loss": 3.1489,
      "num_input_tokens_seen": 587202560,
      "step": 280
    },
    {
      "epoch": 0.6042936655181553,
      "grad_norm": 0.22007331252098083,
      "learning_rate": 4.1819463960421454e-05,
      "loss": 3.1707,
      "num_input_tokens_seen": 597688320,
      "step": 285
    },
    {
      "epoch": 0.6148953087728598,
      "grad_norm": 0.19839680194854736,
      "learning_rate": 4.149190012931402e-05,
      "loss": 3.1679,
      "num_input_tokens_seen": 608174080,
      "step": 290
    },
    {
      "epoch": 0.6254969520275643,
      "grad_norm": 0.23358359932899475,
      "learning_rate": 4.1159245050357065e-05,
      "loss": 3.1629,
      "num_input_tokens_seen": 618659840,
      "step": 295
    },
    {
      "epoch": 0.6360985952822688,
      "grad_norm": 0.16982465982437134,
      "learning_rate": 4.082160141817293e-05,
      "loss": 3.16,
      "num_input_tokens_seen": 629145600,
      "step": 300
    },
    {
      "epoch": 0.6467002385369732,
      "grad_norm": 0.3546576201915741,
      "learning_rate": 4.0479073467410286e-05,
      "loss": 3.2448,
      "num_input_tokens_seen": 639631360,
      "step": 305
    },
    {
      "epoch": 0.6573018817916777,
      "grad_norm": 0.16487599909305573,
      "learning_rate": 4.0131766940565715e-05,
      "loss": 3.1789,
      "num_input_tokens_seen": 650117120,
      "step": 310
    },
    {
      "epoch": 0.6679035250463822,
      "grad_norm": 0.26232755184173584,
      "learning_rate": 3.9779789055339656e-05,
      "loss": 3.1994,
      "num_input_tokens_seen": 660602880,
      "step": 315
    },
    {
      "epoch": 0.6785051683010866,
      "grad_norm": 0.17949418723583221,
      "learning_rate": 3.9423248471537065e-05,
      "loss": 3.1464,
      "num_input_tokens_seen": 671088640,
      "step": 320
    },
    {
      "epoch": 0.6891068115557911,
      "grad_norm": 0.22808890044689178,
      "learning_rate": 3.9062255257522794e-05,
      "loss": 3.2207,
      "num_input_tokens_seen": 681574400,
      "step": 325
    },
    {
      "epoch": 0.6997084548104956,
      "grad_norm": 0.20621077716350555,
      "learning_rate": 3.8696920856242174e-05,
      "loss": 3.1688,
      "num_input_tokens_seen": 692060160,
      "step": 330
    },
    {
      "epoch": 0.7103100980652001,
      "grad_norm": 0.20659266412258148,
      "learning_rate": 3.8327358050817234e-05,
      "loss": 3.1726,
      "num_input_tokens_seen": 702545920,
      "step": 335
    },
    {
      "epoch": 0.7209117413199045,
      "grad_norm": 0.23239997029304504,
      "learning_rate": 3.7953680929729215e-05,
      "loss": 3.2254,
      "num_input_tokens_seen": 713031680,
      "step": 340
    },
    {
      "epoch": 0.731513384574609,
      "grad_norm": 0.15853458642959595,
      "learning_rate": 3.757600485159805e-05,
      "loss": 3.1453,
      "num_input_tokens_seen": 723517440,
      "step": 345
    },
    {
      "epoch": 0.7421150278293135,
      "grad_norm": 0.28123387694358826,
      "learning_rate": 3.719444640956981e-05,
      "loss": 3.1849,
      "num_input_tokens_seen": 734003200,
      "step": 350
    },
    {
      "epoch": 0.7527166710840181,
      "grad_norm": 0.16030676662921906,
      "learning_rate": 3.680912339532296e-05,
      "loss": 3.187,
      "num_input_tokens_seen": 744488960,
      "step": 355
    },
    {
      "epoch": 0.7633183143387225,
      "grad_norm": 0.1698087602853775,
      "learning_rate": 3.6420154762704686e-05,
      "loss": 3.1603,
      "num_input_tokens_seen": 754974720,
      "step": 360
    },
    {
      "epoch": 0.773919957593427,
      "grad_norm": 0.1804792284965515,
      "learning_rate": 3.602766059100838e-05,
      "loss": 3.1501,
      "num_input_tokens_seen": 765460480,
      "step": 365
    },
    {
      "epoch": 0.7845216008481315,
      "grad_norm": 0.22060543298721313,
      "learning_rate": 3.563176204790374e-05,
      "loss": 3.2135,
      "num_input_tokens_seen": 775946240,
      "step": 370
    },
    {
      "epoch": 0.795123244102836,
      "grad_norm": 0.2411007434129715,
      "learning_rate": 3.523258135203087e-05,
      "loss": 3.1263,
      "num_input_tokens_seen": 786432000,
      "step": 375
    },
    {
      "epoch": 0.8057248873575404,
      "grad_norm": 0.17039397358894348,
      "learning_rate": 3.483024173526985e-05,
      "loss": 3.1278,
      "num_input_tokens_seen": 796917760,
      "step": 380
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 0.17096886038780212,
      "learning_rate": 3.442486740469766e-05,
      "loss": 3.1805,
      "num_input_tokens_seen": 807403520,
      "step": 385
    },
    {
      "epoch": 0.8269281738669494,
      "grad_norm": 0.20285804569721222,
      "learning_rate": 3.401658350424389e-05,
      "loss": 3.1093,
      "num_input_tokens_seen": 817889280,
      "step": 390
    },
    {
      "epoch": 0.8375298171216539,
      "grad_norm": 0.17684973776340485,
      "learning_rate": 3.360551607605735e-05,
      "loss": 3.1336,
      "num_input_tokens_seen": 828375040,
      "step": 395
    },
    {
      "epoch": 0.8481314603763583,
      "grad_norm": 0.16076605021953583,
      "learning_rate": 3.3191792021595316e-05,
      "loss": 3.1976,
      "num_input_tokens_seen": 838860800,
      "step": 400
    },
    {
      "epoch": 0.8481314603763583,
      "eval_accuracy": 0.4506036745406824,
      "eval_loss": 3.043421983718872,
      "eval_runtime": 36.2661,
      "eval_samples_per_second": 8.272,
      "eval_steps_per_second": 2.068,
      "num_input_tokens_seen": 838860800,
      "step": 400
    },
    {
      "epoch": 0.8587331036310628,
      "grad_norm": 0.1959790736436844,
      "learning_rate": 3.277553906244756e-05,
      "loss": 3.2013,
      "num_input_tokens_seen": 849346560,
      "step": 405
    },
    {
      "epoch": 0.8693347468857673,
      "grad_norm": 0.15397347509860992,
      "learning_rate": 3.23568857009071e-05,
      "loss": 3.124,
      "num_input_tokens_seen": 859832320,
      "step": 410
    },
    {
      "epoch": 0.8799363901404718,
      "grad_norm": 0.22286681830883026,
      "learning_rate": 3.193596118030005e-05,
      "loss": 3.1723,
      "num_input_tokens_seen": 870318080,
      "step": 415
    },
    {
      "epoch": 0.8905380333951762,
      "grad_norm": 0.22909095883369446,
      "learning_rate": 3.1512895445086636e-05,
      "loss": 3.1068,
      "num_input_tokens_seen": 880803840,
      "step": 420
    },
    {
      "epoch": 0.9011396766498807,
      "grad_norm": 0.24190495908260345,
      "learning_rate": 3.108781910074578e-05,
      "loss": 3.143,
      "num_input_tokens_seen": 891289600,
      "step": 425
    },
    {
      "epoch": 0.9117413199045852,
      "grad_norm": 0.24453699588775635,
      "learning_rate": 3.0660863373455595e-05,
      "loss": 3.1667,
      "num_input_tokens_seen": 901775360,
      "step": 430
    },
    {
      "epoch": 0.9223429631592897,
      "grad_norm": 0.1636463701725006,
      "learning_rate": 3.0232160069582332e-05,
      "loss": 3.1123,
      "num_input_tokens_seen": 912261120,
      "step": 435
    },
    {
      "epoch": 0.9329446064139941,
      "grad_norm": 0.14330972731113434,
      "learning_rate": 2.9801841534990115e-05,
      "loss": 3.1616,
      "num_input_tokens_seen": 922746880,
      "step": 440
    },
    {
      "epoch": 0.9435462496686986,
      "grad_norm": 0.14314919710159302,
      "learning_rate": 2.9370040614184245e-05,
      "loss": 3.1241,
      "num_input_tokens_seen": 933232640,
      "step": 445
    },
    {
      "epoch": 0.9541478929234031,
      "grad_norm": 0.15261518955230713,
      "learning_rate": 2.893689060930045e-05,
      "loss": 3.1573,
      "num_input_tokens_seen": 943718400,
      "step": 450
    },
    {
      "epoch": 0.9647495361781077,
      "grad_norm": 0.14767758548259735,
      "learning_rate": 2.8502525238952916e-05,
      "loss": 3.2165,
      "num_input_tokens_seen": 954204160,
      "step": 455
    },
    {
      "epoch": 0.9753511794328121,
      "grad_norm": 0.161110982298851,
      "learning_rate": 2.8067078596953796e-05,
      "loss": 3.1457,
      "num_input_tokens_seen": 964689920,
      "step": 460
    },
    {
      "epoch": 0.9859528226875166,
      "grad_norm": 0.15843427181243896,
      "learning_rate": 2.7630685110916778e-05,
      "loss": 3.143,
      "num_input_tokens_seen": 975175680,
      "step": 465
    },
    {
      "epoch": 0.9965544659422211,
      "grad_norm": 0.24187405407428741,
      "learning_rate": 2.7193479500757685e-05,
      "loss": 3.2156,
      "num_input_tokens_seen": 985661440,
      "step": 470
    },
    {
      "epoch": 1.0071561091969254,
      "grad_norm": 0.15035971999168396,
      "learning_rate": 2.675559673710485e-05,
      "loss": 3.0852,
      "num_input_tokens_seen": 996147200,
      "step": 475
    },
    {
      "epoch": 1.01775775245163,
      "grad_norm": 0.17717382311820984,
      "learning_rate": 2.631717199963199e-05,
      "loss": 3.1221,
      "num_input_tokens_seen": 1006632960,
      "step": 480
    },
    {
      "epoch": 1.0283593957063344,
      "grad_norm": 0.1390335112810135,
      "learning_rate": 2.5878340635326686e-05,
      "loss": 3.1358,
      "num_input_tokens_seen": 1017118720,
      "step": 485
    },
    {
      "epoch": 1.0389610389610389,
      "grad_norm": 0.14454010128974915,
      "learning_rate": 2.5439238116707102e-05,
      "loss": 3.1307,
      "num_input_tokens_seen": 1027604480,
      "step": 490
    },
    {
      "epoch": 1.0495626822157433,
      "grad_norm": 0.19984786212444305,
      "learning_rate": 2.5e-05,
      "loss": 3.1269,
      "num_input_tokens_seen": 1038090240,
      "step": 495
    },
    {
      "epoch": 1.0601643254704478,
      "grad_norm": 0.263656347990036,
      "learning_rate": 2.45607618832929e-05,
      "loss": 3.1076,
      "num_input_tokens_seen": 1048576000,
      "step": 500
    },
    {
      "epoch": 1.0707659687251523,
      "grad_norm": 0.15432648360729218,
      "learning_rate": 2.412165936467332e-05,
      "loss": 3.1218,
      "num_input_tokens_seen": 1059061760,
      "step": 505
    },
    {
      "epoch": 1.081367611979857,
      "grad_norm": 0.24721471965312958,
      "learning_rate": 2.368282800036801e-05,
      "loss": 3.1035,
      "num_input_tokens_seen": 1069547520,
      "step": 510
    },
    {
      "epoch": 1.0919692552345615,
      "grad_norm": 0.1441834270954132,
      "learning_rate": 2.3244403262895153e-05,
      "loss": 3.1801,
      "num_input_tokens_seen": 1080033280,
      "step": 515
    },
    {
      "epoch": 1.102570898489266,
      "grad_norm": 0.1535598337650299,
      "learning_rate": 2.280652049924232e-05,
      "loss": 3.2002,
      "num_input_tokens_seen": 1090519040,
      "step": 520
    },
    {
      "epoch": 1.1131725417439704,
      "grad_norm": 0.15322482585906982,
      "learning_rate": 2.2369314889083235e-05,
      "loss": 3.1208,
      "num_input_tokens_seen": 1101004800,
      "step": 525
    },
    {
      "epoch": 1.1237741849986749,
      "grad_norm": 0.1468251496553421,
      "learning_rate": 2.1932921403046207e-05,
      "loss": 3.1917,
      "num_input_tokens_seen": 1111490560,
      "step": 530
    },
    {
      "epoch": 1.1343758282533793,
      "grad_norm": 0.1530437469482422,
      "learning_rate": 2.1497474761047086e-05,
      "loss": 3.0797,
      "num_input_tokens_seen": 1121976320,
      "step": 535
    },
    {
      "epoch": 1.1449774715080838,
      "grad_norm": 0.1411171704530716,
      "learning_rate": 2.106310939069956e-05,
      "loss": 3.1136,
      "num_input_tokens_seen": 1132462080,
      "step": 540
    },
    {
      "epoch": 1.1555791147627883,
      "grad_norm": 0.14499180018901825,
      "learning_rate": 2.0629959385815757e-05,
      "loss": 3.1427,
      "num_input_tokens_seen": 1142947840,
      "step": 545
    },
    {
      "epoch": 1.1661807580174928,
      "grad_norm": 0.14953380823135376,
      "learning_rate": 2.019815846500988e-05,
      "loss": 3.1948,
      "num_input_tokens_seen": 1153433600,
      "step": 550
    },
    {
      "epoch": 1.1767824012721972,
      "grad_norm": 0.1349666863679886,
      "learning_rate": 1.9767839930417673e-05,
      "loss": 3.1605,
      "num_input_tokens_seen": 1163919360,
      "step": 555
    },
    {
      "epoch": 1.1873840445269017,
      "grad_norm": 0.144802987575531,
      "learning_rate": 1.9339136626544407e-05,
      "loss": 3.1857,
      "num_input_tokens_seen": 1174405120,
      "step": 560
    },
    {
      "epoch": 1.1979856877816062,
      "grad_norm": 0.16848242282867432,
      "learning_rate": 1.891218089925423e-05,
      "loss": 3.18,
      "num_input_tokens_seen": 1184890880,
      "step": 565
    },
    {
      "epoch": 1.2085873310363107,
      "grad_norm": 0.15472151339054108,
      "learning_rate": 1.8487104554913363e-05,
      "loss": 3.1939,
      "num_input_tokens_seen": 1195376640,
      "step": 570
    },
    {
      "epoch": 1.2191889742910151,
      "grad_norm": 0.1529063582420349,
      "learning_rate": 1.806403881969996e-05,
      "loss": 3.142,
      "num_input_tokens_seen": 1205862400,
      "step": 575
    },
    {
      "epoch": 1.2297906175457196,
      "grad_norm": 0.1687614619731903,
      "learning_rate": 1.764311429909291e-05,
      "loss": 3.1344,
      "num_input_tokens_seen": 1216348160,
      "step": 580
    },
    {
      "epoch": 1.240392260800424,
      "grad_norm": 0.13812561333179474,
      "learning_rate": 1.7224460937552446e-05,
      "loss": 3.1626,
      "num_input_tokens_seen": 1226833920,
      "step": 585
    },
    {
      "epoch": 1.2509939040551286,
      "grad_norm": 0.16453585028648376,
      "learning_rate": 1.6808207978404683e-05,
      "loss": 3.1616,
      "num_input_tokens_seen": 1237319680,
      "step": 590
    },
    {
      "epoch": 1.261595547309833,
      "grad_norm": 0.13337315618991852,
      "learning_rate": 1.6394483923942655e-05,
      "loss": 3.1413,
      "num_input_tokens_seen": 1247805440,
      "step": 595
    },
    {
      "epoch": 1.2721971905645375,
      "grad_norm": 0.2029571831226349,
      "learning_rate": 1.5983416495756116e-05,
      "loss": 3.1485,
      "num_input_tokens_seen": 1258291200,
      "step": 600
    },
    {
      "epoch": 1.2721971905645375,
      "eval_accuracy": 0.45126899835195017,
      "eval_loss": 3.0374794006347656,
      "eval_runtime": 36.1798,
      "eval_samples_per_second": 8.292,
      "eval_steps_per_second": 2.073,
      "num_input_tokens_seen": 1258291200,
      "step": 600
    },
    {
      "epoch": 1.282798833819242,
      "grad_norm": 0.21333394944667816,
      "learning_rate": 1.5575132595302352e-05,
      "loss": 3.1131,
      "num_input_tokens_seen": 1268776960,
      "step": 605
    },
    {
      "epoch": 1.2934004770739465,
      "grad_norm": 0.1743020862340927,
      "learning_rate": 1.516975826473015e-05,
      "loss": 3.1177,
      "num_input_tokens_seen": 1279262720,
      "step": 610
    },
    {
      "epoch": 1.304002120328651,
      "grad_norm": 0.15571139752864838,
      "learning_rate": 1.4767418647969133e-05,
      "loss": 3.1626,
      "num_input_tokens_seen": 1289748480,
      "step": 615
    },
    {
      "epoch": 1.3146037635833554,
      "grad_norm": 0.16648022830486298,
      "learning_rate": 1.4368237952096258e-05,
      "loss": 3.1987,
      "num_input_tokens_seen": 1300234240,
      "step": 620
    },
    {
      "epoch": 1.3252054068380599,
      "grad_norm": 0.2865128219127655,
      "learning_rate": 1.3972339408991626e-05,
      "loss": 3.176,
      "num_input_tokens_seen": 1310720000,
      "step": 625
    },
    {
      "epoch": 1.3358070500927643,
      "grad_norm": 0.14998364448547363,
      "learning_rate": 1.357984523729533e-05,
      "loss": 3.1568,
      "num_input_tokens_seen": 1321205760,
      "step": 630
    },
    {
      "epoch": 1.3464086933474688,
      "grad_norm": 0.14780345559120178,
      "learning_rate": 1.3190876604677043e-05,
      "loss": 3.1895,
      "num_input_tokens_seen": 1331691520,
      "step": 635
    },
    {
      "epoch": 1.3570103366021733,
      "grad_norm": 0.15796662867069244,
      "learning_rate": 1.2805553590430197e-05,
      "loss": 3.1708,
      "num_input_tokens_seen": 1342177280,
      "step": 640
    },
    {
      "epoch": 1.3676119798568778,
      "grad_norm": 0.14260126650333405,
      "learning_rate": 1.2423995148401954e-05,
      "loss": 3.1649,
      "num_input_tokens_seen": 1352663040,
      "step": 645
    },
    {
      "epoch": 1.3782136231115822,
      "grad_norm": 0.16667188704013824,
      "learning_rate": 1.2046319070270792e-05,
      "loss": 3.1345,
      "num_input_tokens_seen": 1363148800,
      "step": 650
    },
    {
      "epoch": 1.3888152663662867,
      "grad_norm": 0.13283655047416687,
      "learning_rate": 1.1672641949182769e-05,
      "loss": 3.1653,
      "num_input_tokens_seen": 1373634560,
      "step": 655
    },
    {
      "epoch": 1.3994169096209912,
      "grad_norm": 0.1479809582233429,
      "learning_rate": 1.130307914375783e-05,
      "loss": 3.2014,
      "num_input_tokens_seen": 1384120320,
      "step": 660
    },
    {
      "epoch": 1.4100185528756957,
      "grad_norm": 0.1443646103143692,
      "learning_rate": 1.093774474247721e-05,
      "loss": 3.1561,
      "num_input_tokens_seen": 1394606080,
      "step": 665
    },
    {
      "epoch": 1.4206201961304001,
      "grad_norm": 0.15595485270023346,
      "learning_rate": 1.0576751528462935e-05,
      "loss": 3.1774,
      "num_input_tokens_seen": 1405091840,
      "step": 670
    },
    {
      "epoch": 1.4312218393851046,
      "grad_norm": 0.1376049816608429,
      "learning_rate": 1.0220210944660338e-05,
      "loss": 3.1102,
      "num_input_tokens_seen": 1415577600,
      "step": 675
    },
    {
      "epoch": 1.4418234826398093,
      "grad_norm": 0.14685603976249695,
      "learning_rate": 9.868233059434288e-06,
      "loss": 3.2077,
      "num_input_tokens_seen": 1426063360,
      "step": 680
    },
    {
      "epoch": 1.4524251258945138,
      "grad_norm": 0.13503292202949524,
      "learning_rate": 9.520926532589725e-06,
      "loss": 3.1899,
      "num_input_tokens_seen": 1436549120,
      "step": 685
    },
    {
      "epoch": 1.4630267691492183,
      "grad_norm": 0.18555864691734314,
      "learning_rate": 9.178398581827085e-06,
      "loss": 3.2424,
      "num_input_tokens_seen": 1447034880,
      "step": 690
    },
    {
      "epoch": 1.4736284124039227,
      "grad_norm": 0.26128634810447693,
      "learning_rate": 8.840754949642935e-06,
      "loss": 3.1609,
      "num_input_tokens_seen": 1457520640,
      "step": 695
    },
    {
      "epoch": 1.4842300556586272,
      "grad_norm": 0.13384391367435455,
      "learning_rate": 8.50809987068598e-06,
      "loss": 3.1455,
      "num_input_tokens_seen": 1468006400,
      "step": 700
    },
    {
      "epoch": 1.4948316989133317,
      "grad_norm": 0.20566639304161072,
      "learning_rate": 8.180536039578545e-06,
      "loss": 3.1995,
      "num_input_tokens_seen": 1478492160,
      "step": 705
    },
    {
      "epoch": 1.5054333421680361,
      "grad_norm": 0.13730423152446747,
      "learning_rate": 7.858164579213547e-06,
      "loss": 3.134,
      "num_input_tokens_seen": 1488977920,
      "step": 710
    },
    {
      "epoch": 1.5160349854227406,
      "grad_norm": 0.14655794203281403,
      "learning_rate": 7.541085009536625e-06,
      "loss": 3.0949,
      "num_input_tokens_seen": 1499463680,
      "step": 715
    },
    {
      "epoch": 1.526636628677445,
      "grad_norm": 0.12526313960552216,
      "learning_rate": 7.2293952168231316e-06,
      "loss": 3.1615,
      "num_input_tokens_seen": 1509949440,
      "step": 720
    },
    {
      "epoch": 1.5372382719321496,
      "grad_norm": 0.1351662427186966,
      "learning_rate": 6.923191423459482e-06,
      "loss": 3.1805,
      "num_input_tokens_seen": 1520435200,
      "step": 725
    },
    {
      "epoch": 1.547839915186854,
      "grad_norm": 0.1686793714761734,
      "learning_rate": 6.622568158238126e-06,
      "loss": 3.1779,
      "num_input_tokens_seen": 1530920960,
      "step": 730
    },
    {
      "epoch": 1.5584415584415585,
      "grad_norm": 0.14492954313755035,
      "learning_rate": 6.327618227175389e-06,
      "loss": 3.1046,
      "num_input_tokens_seen": 1541406720,
      "step": 735
    },
    {
      "epoch": 1.569043201696263,
      "grad_norm": 0.14910686016082764,
      "learning_rate": 6.0384326848611225e-06,
      "loss": 3.0803,
      "num_input_tokens_seen": 1551892480,
      "step": 740
    },
    {
      "epoch": 1.5796448449509675,
      "grad_norm": 0.1342857927083969,
      "learning_rate": 5.755100806349076e-06,
      "loss": 3.062,
      "num_input_tokens_seen": 1562378240,
      "step": 745
    },
    {
      "epoch": 1.590246488205672,
      "grad_norm": 0.1598527878522873,
      "learning_rate": 5.4777100595965994e-06,
      "loss": 3.2036,
      "num_input_tokens_seen": 1572864000,
      "step": 750
    },
    {
      "epoch": 1.6008481314603764,
      "grad_norm": 0.1773335188627243,
      "learning_rate": 5.206346078462249e-06,
      "loss": 3.1892,
      "num_input_tokens_seen": 1583349760,
      "step": 755
    },
    {
      "epoch": 1.6114497747150809,
      "grad_norm": 0.17586533725261688,
      "learning_rate": 4.941092636269554e-06,
      "loss": 3.1995,
      "num_input_tokens_seen": 1593835520,
      "step": 760
    },
    {
      "epoch": 1.6220514179697854,
      "grad_norm": 0.16583110392093658,
      "learning_rate": 4.682031619945238e-06,
      "loss": 3.1309,
      "num_input_tokens_seen": 1604321280,
      "step": 765
    },
    {
      "epoch": 1.6326530612244898,
      "grad_norm": 0.1462288796901703,
      "learning_rate": 4.4292430047396914e-06,
      "loss": 3.1376,
      "num_input_tokens_seen": 1614807040,
      "step": 770
    },
    {
      "epoch": 1.6432547044791943,
      "grad_norm": 0.13279996812343597,
      "learning_rate": 4.182804829537654e-06,
      "loss": 3.1541,
      "num_input_tokens_seen": 1625292800,
      "step": 775
    },
    {
      "epoch": 1.6538563477338988,
      "grad_norm": 0.18102097511291504,
      "learning_rate": 3.942793172766699e-06,
      "loss": 3.1894,
      "num_input_tokens_seen": 1635778560,
      "step": 780
    },
    {
      "epoch": 1.6644579909886033,
      "grad_norm": 0.16354134678840637,
      "learning_rate": 3.709282128910907e-06,
      "loss": 3.1664,
      "num_input_tokens_seen": 1646264320,
      "step": 785
    },
    {
      "epoch": 1.6750596342433077,
      "grad_norm": 0.32594841718673706,
      "learning_rate": 3.4823437856369794e-06,
      "loss": 3.1721,
      "num_input_tokens_seen": 1656750080,
      "step": 790
    },
    {
      "epoch": 1.6856612774980122,
      "grad_norm": 0.13957597315311432,
      "learning_rate": 3.2620482015399302e-06,
      "loss": 3.2471,
      "num_input_tokens_seen": 1667235840,
      "step": 795
    },
    {
      "epoch": 1.6962629207527167,
      "grad_norm": 0.13924147188663483,
      "learning_rate": 3.0484633845151488e-06,
      "loss": 3.1871,
      "num_input_tokens_seen": 1677721600,
      "step": 800
    },
    {
      "epoch": 1.6962629207527167,
      "eval_accuracy": 0.4514018596512645,
      "eval_loss": 3.0366272926330566,
      "eval_runtime": 36.0138,
      "eval_samples_per_second": 8.33,
      "eval_steps_per_second": 2.083,
      "num_input_tokens_seen": 1677721600,
      "step": 800
    },
    {
      "epoch": 1.7068645640074211,
      "grad_norm": 0.14513356983661652,
      "learning_rate": 2.841655270763549e-06,
      "loss": 3.066,
      "num_input_tokens_seen": 1688207360,
      "step": 805
    },
    {
      "epoch": 1.7174662072621256,
      "grad_norm": 0.14862333238124847,
      "learning_rate": 2.6416877044362685e-06,
      "loss": 3.1206,
      "num_input_tokens_seen": 1698693120,
      "step": 810
    },
    {
      "epoch": 1.72806785051683,
      "grad_norm": 0.13608209788799286,
      "learning_rate": 2.448622417925214e-06,
      "loss": 3.2281,
      "num_input_tokens_seen": 1709178880,
      "step": 815
    },
    {
      "epoch": 1.7386694937715346,
      "grad_norm": 0.1472754031419754,
      "learning_rate": 2.2625190128055168e-06,
      "loss": 3.2023,
      "num_input_tokens_seen": 1719664640,
      "step": 820
    },
    {
      "epoch": 1.749271137026239,
      "grad_norm": 0.17672620713710785,
      "learning_rate": 2.0834349414358495e-06,
      "loss": 3.2217,
      "num_input_tokens_seen": 1730150400,
      "step": 825
    },
    {
      "epoch": 1.7598727802809435,
      "grad_norm": 0.14799125492572784,
      "learning_rate": 1.911425489222127e-06,
      "loss": 3.2231,
      "num_input_tokens_seen": 1740636160,
      "step": 830
    },
    {
      "epoch": 1.770474423535648,
      "grad_norm": 0.14448776841163635,
      "learning_rate": 1.7465437575502952e-06,
      "loss": 3.1126,
      "num_input_tokens_seen": 1751121920,
      "step": 835
    },
    {
      "epoch": 1.7810760667903525,
      "grad_norm": 0.14082539081573486,
      "learning_rate": 1.5888406473932692e-06,
      "loss": 3.0933,
      "num_input_tokens_seen": 1761607680,
      "step": 840
    },
    {
      "epoch": 1.791677710045057,
      "grad_norm": 0.18886087834835052,
      "learning_rate": 1.4383648435972007e-06,
      "loss": 3.2596,
      "num_input_tokens_seen": 1772093440,
      "step": 845
    },
    {
      "epoch": 1.8022793532997614,
      "grad_norm": 0.14818327128887177,
      "learning_rate": 1.2951627998518623e-06,
      "loss": 3.1292,
      "num_input_tokens_seen": 1782579200,
      "step": 850
    },
    {
      "epoch": 1.8128809965544659,
      "grad_norm": 0.14874930679798126,
      "learning_rate": 1.1592787243498631e-06,
      "loss": 3.1284,
      "num_input_tokens_seen": 1793064960,
      "step": 855
    },
    {
      "epoch": 1.8234826398091704,
      "grad_norm": 0.16616405546665192,
      "learning_rate": 1.0307545661390139e-06,
      "loss": 3.1422,
      "num_input_tokens_seen": 1803550720,
      "step": 860
    },
    {
      "epoch": 1.8340842830638748,
      "grad_norm": 0.15211746096611023,
      "learning_rate": 9.09630002172182e-07,
      "loss": 3.1793,
      "num_input_tokens_seen": 1814036480,
      "step": 865
    },
    {
      "epoch": 1.8446859263185793,
      "grad_norm": 0.14233224093914032,
      "learning_rate": 7.959424250585323e-07,
      "loss": 3.1624,
      "num_input_tokens_seen": 1824522240,
      "step": 870
    },
    {
      "epoch": 1.8552875695732838,
      "grad_norm": 0.13079190254211426,
      "learning_rate": 6.897269315199628e-07,
      "loss": 3.2029,
      "num_input_tokens_seen": 1835008000,
      "step": 875
    },
    {
      "epoch": 1.8658892128279883,
      "grad_norm": 0.1364782601594925,
      "learning_rate": 5.910163115563471e-07,
      "loss": 3.1872,
      "num_input_tokens_seen": 1845493760,
      "step": 880
    },
    {
      "epoch": 1.8764908560826927,
      "grad_norm": 0.22711250185966492,
      "learning_rate": 4.998410383228458e-07,
      "loss": 3.1676,
      "num_input_tokens_seen": 1855979520,
      "step": 885
    },
    {
      "epoch": 1.8870924993373972,
      "grad_norm": 0.21140585839748383,
      "learning_rate": 4.162292587224947e-07,
      "loss": 3.1227,
      "num_input_tokens_seen": 1866465280,
      "step": 890
    },
    {
      "epoch": 1.8976941425921017,
      "grad_norm": 0.2973221242427826,
      "learning_rate": 3.4020678471690934e-07,
      "loss": 3.1285,
      "num_input_tokens_seen": 1876951040,
      "step": 895
    },
    {
      "epoch": 1.9082957858468061,
      "grad_norm": 0.15094168484210968,
      "learning_rate": 2.7179708535781943e-07,
      "loss": 3.152,
      "num_input_tokens_seen": 1887436800,
      "step": 900
    },
    {
      "epoch": 1.9188974291015106,
      "grad_norm": 0.14399217069149017,
      "learning_rate": 2.110212795418953e-07,
      "loss": 3.1971,
      "num_input_tokens_seen": 1897922560,
      "step": 905
    },
    {
      "epoch": 1.929499072356215,
      "grad_norm": 0.15141591429710388,
      "learning_rate": 1.578981294910936e-07,
      "loss": 3.1604,
      "num_input_tokens_seen": 1908408320,
      "step": 910
    },
    {
      "epoch": 1.9401007156109196,
      "grad_norm": 0.15116803348064423,
      "learning_rate": 1.1244403496052658e-07,
      "loss": 3.0712,
      "num_input_tokens_seen": 1918894080,
      "step": 915
    },
    {
      "epoch": 1.950702358865624,
      "grad_norm": 0.1515650451183319,
      "learning_rate": 7.46730281756619e-08,
      "loss": 3.0719,
      "num_input_tokens_seen": 1929379840,
      "step": 920
    },
    {
      "epoch": 1.9613040021203285,
      "grad_norm": 0.1448003053665161,
      "learning_rate": 4.4596769500407366e-08,
      "loss": 3.2699,
      "num_input_tokens_seen": 1939865600,
      "step": 925
    },
    {
      "epoch": 1.971905645375033,
      "grad_norm": 0.18116047978401184,
      "learning_rate": 2.2224543837423562e-08,
      "loss": 3.1134,
      "num_input_tokens_seen": 1950351360,
      "step": 930
    },
    {
      "epoch": 1.9825072886297375,
      "grad_norm": 0.3333103358745575,
      "learning_rate": 7.563257761744601e-09,
      "loss": 3.1083,
      "num_input_tokens_seen": 1960837120,
      "step": 935
    },
    {
      "epoch": 1.993108931884442,
      "grad_norm": 0.15106463432312012,
      "learning_rate": 6.174373886586037e-10,
      "loss": 3.2087,
      "num_input_tokens_seen": 1971322880,
      "step": 940
    },
    {
      "epoch": 1.997349589186324,
      "num_input_tokens_seen": 1975517184,
      "step": 942,
      "total_flos": 9.732316690586272e+18,
      "train_loss": 3.186332613039928,
      "train_runtime": 34789.3198,
      "train_samples_per_second": 3.47,
      "train_steps_per_second": 0.027
    }
  ],
  "logging_steps": 5,
  "max_steps": 942,
  "num_input_tokens_seen": 1975517184,
  "num_train_epochs": 2,
  "save_steps": 100,
  "total_flos": 9.732316690586272e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}