{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.935185185185185,
  "eval_steps": 500,
  "global_step": 1073,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 4.0609588623046875,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 0.9653,
      "step": 10
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 3.2480485439300537,
      "learning_rate": 7.407407407407407e-05,
      "loss": 0.4377,
      "step": 20
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 1.2286500930786133,
      "learning_rate": 0.00011111111111111112,
      "loss": 0.2765,
      "step": 30
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.0655648708343506,
      "learning_rate": 0.00014814814814814815,
      "loss": 0.2268,
      "step": 40
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 0.9578745365142822,
      "learning_rate": 0.0001851851851851852,
      "loss": 0.1874,
      "step": 50
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 1.0437668561935425,
      "learning_rate": 0.00019998289151715887,
      "loss": 0.1747,
      "step": 60
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 1.0130860805511475,
      "learning_rate": 0.00019987836087650596,
      "loss": 0.1637,
      "step": 70
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.8844163417816162,
      "learning_rate": 0.0001996789035357663,
      "loss": 0.1493,
      "step": 80
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.7460007667541504,
      "learning_rate": 0.00019938470906380134,
      "loss": 0.1391,
      "step": 90
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 0.5707225203514099,
      "learning_rate": 0.0001989960570698294,
      "loss": 0.1181,
      "step": 100
    },
    {
      "epoch": 1.0185185185185186,
      "grad_norm": 0.5503486394882202,
      "learning_rate": 0.00019851331693767843,
      "loss": 0.1248,
      "step": 110
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.5087465643882751,
      "learning_rate": 0.00019793694747471515,
      "loss": 0.1145,
      "step": 120
    },
    {
      "epoch": 1.2037037037037037,
      "grad_norm": 0.6456828713417053,
      "learning_rate": 0.00019726749647578387,
      "loss": 0.1065,
      "step": 130
    },
    {
      "epoch": 1.2962962962962963,
      "grad_norm": 2.2336721420288086,
      "learning_rate": 0.00019650560020256975,
      "loss": 0.1151,
      "step": 140
    },
    {
      "epoch": 1.3888888888888888,
      "grad_norm": 2.1042354106903076,
      "learning_rate": 0.00019565198277888085,
      "loss": 0.1096,
      "step": 150
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 3.438588857650757,
      "learning_rate": 0.0001947074555024243,
      "loss": 0.1086,
      "step": 160
    },
    {
      "epoch": 1.574074074074074,
      "grad_norm": 0.5174661874771118,
      "learning_rate": 0.0001936729160737301,
      "loss": 0.1047,
      "step": 170
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.5018674731254578,
      "learning_rate": 0.00019254934774295588,
      "loss": 0.0907,
      "step": 180
    },
    {
      "epoch": 1.7592592592592593,
      "grad_norm": 0.47620534896850586,
      "learning_rate": 0.00019133781837538322,
      "loss": 0.0939,
      "step": 190
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 0.4984002709388733,
      "learning_rate": 0.00019003947943649387,
      "loss": 0.09,
      "step": 200
    },
    {
      "epoch": 1.9444444444444444,
      "grad_norm": 0.5507371425628662,
      "learning_rate": 0.00018865556489759038,
      "loss": 0.0874,
      "step": 210
    },
    {
      "epoch": 2.037037037037037,
      "grad_norm": 0.5186899304389954,
      "learning_rate": 0.0001871873900630011,
      "loss": 0.0891,
      "step": 220
    },
    {
      "epoch": 2.1296296296296298,
      "grad_norm": 0.32078972458839417,
      "learning_rate": 0.00018563635031998497,
      "loss": 0.0816,
      "step": 230
    },
    {
      "epoch": 2.2222222222222223,
      "grad_norm": 0.35380446910858154,
      "learning_rate": 0.00018400391981252277,
      "loss": 0.0902,
      "step": 240
    },
    {
      "epoch": 2.314814814814815,
      "grad_norm": 0.3749984800815582,
      "learning_rate": 0.00018229165004025712,
      "loss": 0.0773,
      "step": 250
    },
    {
      "epoch": 2.4074074074074074,
      "grad_norm": 0.9008009433746338,
      "learning_rate": 0.000180501168383911,
      "loss": 0.0853,
      "step": 260
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.6653043627738953,
      "learning_rate": 0.00017863417655858776,
      "loss": 0.0796,
      "step": 270
    },
    {
      "epoch": 2.5925925925925926,
      "grad_norm": 0.5696312189102173,
      "learning_rate": 0.00017669244899642182,
      "loss": 0.0773,
      "step": 280
    },
    {
      "epoch": 2.685185185185185,
      "grad_norm": 0.49613088369369507,
      "learning_rate": 0.00017467783116011722,
      "loss": 0.0755,
      "step": 290
    },
    {
      "epoch": 2.7777777777777777,
      "grad_norm": 0.37407752871513367,
      "learning_rate": 0.00017259223778897748,
      "loss": 0.0795,
      "step": 300
    },
    {
      "epoch": 2.8703703703703702,
      "grad_norm": 0.19830532371997833,
      "learning_rate": 0.00017043765107909296,
      "loss": 0.0793,
      "step": 310
    },
    {
      "epoch": 2.962962962962963,
      "grad_norm": 0.34773755073547363,
      "learning_rate": 0.0001682161187994161,
      "loss": 0.0642,
      "step": 320
    },
    {
      "epoch": 3.0555555555555554,
      "grad_norm": 0.4124683439731598,
      "learning_rate": 0.00016592975234551438,
      "loss": 0.0751,
      "step": 330
    },
    {
      "epoch": 3.148148148148148,
      "grad_norm": 0.321125328540802,
      "learning_rate": 0.0001635807247328514,
      "loss": 0.0788,
      "step": 340
    },
    {
      "epoch": 3.240740740740741,
      "grad_norm": 0.34814882278442383,
      "learning_rate": 0.00016117126853150264,
      "loss": 0.073,
      "step": 350
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 0.461489737033844,
      "learning_rate": 0.00015870367374426936,
      "loss": 0.0788,
      "step": 360
    },
    {
      "epoch": 3.425925925925926,
      "grad_norm": 0.32594698667526245,
      "learning_rate": 0.00015618028563020727,
      "loss": 0.065,
      "step": 370
    },
    {
      "epoch": 3.5185185185185186,
      "grad_norm": 0.311172753572464,
      "learning_rate": 0.00015360350247563774,
      "loss": 0.0611,
      "step": 380
    },
    {
      "epoch": 3.611111111111111,
      "grad_norm": 0.4604165852069855,
      "learning_rate": 0.00015097577331476164,
      "loss": 0.063,
      "step": 390
    },
    {
      "epoch": 3.7037037037037037,
      "grad_norm": 0.42682307958602905,
      "learning_rate": 0.00014829959560204035,
      "loss": 0.0614,
      "step": 400
    },
    {
      "epoch": 3.7962962962962963,
      "grad_norm": 0.39028409123420715,
      "learning_rate": 0.00014557751283855735,
      "loss": 0.0651,
      "step": 410
    },
    {
      "epoch": 3.888888888888889,
      "grad_norm": 0.3820561170578003,
      "learning_rate": 0.0001428121121546163,
      "loss": 0.0589,
      "step": 420
    },
    {
      "epoch": 3.9814814814814814,
      "grad_norm": 0.31287339329719543,
      "learning_rate": 0.00014000602185087254,
      "loss": 0.0633,
      "step": 430
    },
    {
      "epoch": 4.074074074074074,
      "grad_norm": 0.42882245779037476,
      "learning_rate": 0.00013716190890033543,
      "loss": 0.0606,
      "step": 440
    },
    {
      "epoch": 4.166666666666667,
      "grad_norm": 0.3459970951080322,
      "learning_rate": 0.00013428247641361572,
      "loss": 0.0532,
      "step": 450
    },
    {
      "epoch": 4.2592592592592595,
      "grad_norm": 0.3979005217552185,
      "learning_rate": 0.00013137046106982683,
      "loss": 0.0547,
      "step": 460
    },
    {
      "epoch": 4.351851851851852,
      "grad_norm": 0.22608621418476105,
      "learning_rate": 0.00012842863051558168,
      "loss": 0.0507,
      "step": 470
    },
    {
      "epoch": 4.444444444444445,
      "grad_norm": 0.3078368604183197,
      "learning_rate": 0.00012545978073455754,
      "loss": 0.0614,
      "step": 480
    },
    {
      "epoch": 4.537037037037037,
      "grad_norm": 0.3212282657623291,
      "learning_rate": 0.0001224667333901287,
      "loss": 0.0584,
      "step": 490
    },
    {
      "epoch": 4.62962962962963,
      "grad_norm": 0.3688996136188507,
      "learning_rate": 0.0001194523331435924,
      "loss": 0.0604,
      "step": 500
    },
    {
      "epoch": 4.722222222222222,
      "grad_norm": 0.2440503090620041,
      "learning_rate": 0.00011641944495053689,
      "loss": 0.0536,
      "step": 510
    },
    {
      "epoch": 4.814814814814815,
      "grad_norm": 0.29373106360435486,
      "learning_rate": 0.00011337095133792168,
      "loss": 0.0517,
      "step": 520
    },
    {
      "epoch": 4.907407407407407,
      "grad_norm": 0.28415507078170776,
      "learning_rate": 0.00011030974966445735,
      "loss": 0.0483,
      "step": 530
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.6739519238471985,
      "learning_rate": 0.00010723874936688885,
      "loss": 0.0597,
      "step": 540
    },
    {
      "epoch": 5.092592592592593,
      "grad_norm": 0.3474346101284027,
      "learning_rate": 0.00010416086919479975,
      "loss": 0.0468,
      "step": 550
    },
    {
      "epoch": 5.185185185185185,
      "grad_norm": 0.3007705807685852,
      "learning_rate": 0.00010107903443656521,
      "loss": 0.0546,
      "step": 560
    },
    {
      "epoch": 5.277777777777778,
      "grad_norm": 0.35039541125297546,
      "learning_rate": 9.799617413909027e-05,
      "loss": 0.0548,
      "step": 570
    },
    {
      "epoch": 5.37037037037037,
      "grad_norm": 0.2516862154006958,
      "learning_rate": 9.491521832397619e-05,
      "loss": 0.0542,
      "step": 580
    },
    {
      "epoch": 5.462962962962963,
      "grad_norm": 0.3877411484718323,
      "learning_rate": 9.183909520276032e-05,
      "loss": 0.0481,
      "step": 590
    },
    {
      "epoch": 5.555555555555555,
      "grad_norm": 0.3625725507736206,
      "learning_rate": 8.877072839387602e-05,
      "loss": 0.0474,
      "step": 600
    },
    {
      "epoch": 5.648148148148148,
      "grad_norm": 0.2881794273853302,
      "learning_rate": 8.57130341439784e-05,
      "loss": 0.0513,
      "step": 610
    },
    {
      "epoch": 5.7407407407407405,
      "grad_norm": 0.2732185125350952,
      "learning_rate": 8.266891855627611e-05,
      "loss": 0.0445,
      "step": 620
    },
    {
      "epoch": 5.833333333333333,
      "grad_norm": 0.34640687704086304,
      "learning_rate": 7.964127482850372e-05,
      "loss": 0.0449,
      "step": 630
    },
    {
      "epoch": 5.925925925925926,
      "grad_norm": 0.3285965919494629,
      "learning_rate": 7.663298050315993e-05,
      "loss": 0.0484,
      "step": 640
    },
    {
      "epoch": 6.018518518518518,
      "grad_norm": 0.28891757130622864,
      "learning_rate": 7.364689473262452e-05,
      "loss": 0.0521,
      "step": 650
    },
    {
      "epoch": 6.111111111111111,
      "grad_norm": 0.34271323680877686,
      "learning_rate": 7.068585556175412e-05,
      "loss": 0.0463,
      "step": 660
    },
    {
      "epoch": 6.203703703703703,
      "grad_norm": 0.2897927463054657,
      "learning_rate": 6.77526772305388e-05,
      "loss": 0.0441,
      "step": 670
    },
    {
      "epoch": 6.296296296296296,
      "grad_norm": 0.20959234237670898,
      "learning_rate": 6.485014749938336e-05,
      "loss": 0.0379,
      "step": 680
    },
    {
      "epoch": 6.388888888888889,
      "grad_norm": 0.26397034525871277,
      "learning_rate": 6.198102499955545e-05,
      "loss": 0.0408,
      "step": 690
    },
    {
      "epoch": 6.481481481481482,
      "grad_norm": 0.28571462631225586,
      "learning_rate": 5.914803661131895e-05,
      "loss": 0.0377,
      "step": 700
    },
    {
      "epoch": 6.574074074074074,
      "grad_norm": 0.17670756578445435,
      "learning_rate": 5.6353874872243716e-05,
      "loss": 0.04,
      "step": 710
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 0.2153652012348175,
      "learning_rate": 5.360119541815587e-05,
      "loss": 0.0438,
      "step": 720
    },
    {
      "epoch": 6.7592592592592595,
      "grad_norm": 0.20676399767398834,
      "learning_rate": 5.089261445916018e-05,
      "loss": 0.0433,
      "step": 730
    },
    {
      "epoch": 6.851851851851852,
      "grad_norm": 0.2535192370414734,
      "learning_rate": 4.8230706293133656e-05,
      "loss": 0.0429,
      "step": 740
    },
    {
      "epoch": 6.944444444444445,
      "grad_norm": 0.21110829710960388,
      "learning_rate": 4.561800085905312e-05,
      "loss": 0.0381,
      "step": 750
    },
    {
      "epoch": 7.037037037037037,
      "grad_norm": 0.24194058775901794,
      "learning_rate": 4.305698133248319e-05,
      "loss": 0.0456,
      "step": 760
    },
    {
      "epoch": 7.12962962962963,
      "grad_norm": 0.21028666198253632,
      "learning_rate": 4.055008176550869e-05,
      "loss": 0.0385,
      "step": 770
    },
    {
      "epoch": 7.222222222222222,
      "grad_norm": 0.2054344266653061,
      "learning_rate": 3.8099684773355196e-05,
      "loss": 0.0409,
      "step": 780
    },
    {
      "epoch": 7.314814814814815,
      "grad_norm": 0.23474320769309998,
      "learning_rate": 3.570811926989689e-05,
      "loss": 0.0343,
      "step": 790
    },
    {
      "epoch": 7.407407407407407,
      "grad_norm": 0.1761438399553299,
      "learning_rate": 3.337765825420277e-05,
      "loss": 0.0346,
      "step": 800
    },
    {
      "epoch": 7.5,
      "grad_norm": 0.1905253529548645,
      "learning_rate": 3.111051665022584e-05,
      "loss": 0.0318,
      "step": 810
    },
    {
      "epoch": 7.592592592592593,
      "grad_norm": 0.32174453139305115,
      "learning_rate": 2.890884920168856e-05,
      "loss": 0.031,
      "step": 820
    },
    {
      "epoch": 7.685185185185185,
      "grad_norm": 0.18767257034778595,
      "learning_rate": 2.6774748424164207e-05,
      "loss": 0.0391,
      "step": 830
    },
    {
      "epoch": 7.777777777777778,
      "grad_norm": 0.22317418456077576,
      "learning_rate": 2.471024261630215e-05,
      "loss": 0.0323,
      "step": 840
    },
    {
      "epoch": 7.87037037037037,
      "grad_norm": 0.25181177258491516,
      "learning_rate": 2.2717293932085827e-05,
      "loss": 0.039,
      "step": 850
    },
    {
      "epoch": 7.962962962962963,
      "grad_norm": 0.1966754049062729,
      "learning_rate": 2.0797796515956237e-05,
      "loss": 0.0326,
      "step": 860
    },
    {
      "epoch": 8.055555555555555,
      "grad_norm": 0.1419260948896408,
      "learning_rate": 1.895357470257345e-05,
      "loss": 0.037,
      "step": 870
    },
    {
      "epoch": 8.148148148148149,
      "grad_norm": 0.16165828704833984,
      "learning_rate": 1.7186381282926833e-05,
      "loss": 0.0313,
      "step": 880
    },
    {
      "epoch": 8.24074074074074,
      "grad_norm": 0.17430561780929565,
      "learning_rate": 1.549789583844192e-05,
      "loss": 0.0357,
      "step": 890
    },
    {
      "epoch": 8.333333333333334,
      "grad_norm": 0.2748219668865204,
      "learning_rate": 1.3889723144667477e-05,
      "loss": 0.0378,
      "step": 900
    },
    {
      "epoch": 8.425925925925926,
      "grad_norm": 0.27772700786590576,
      "learning_rate": 1.2363391646059886e-05,
      "loss": 0.0354,
      "step": 910
    },
    {
      "epoch": 8.518518518518519,
      "grad_norm": 0.2717374563217163,
      "learning_rate": 1.0920352003314105e-05,
      "loss": 0.032,
      "step": 920
    },
    {
      "epoch": 8.61111111111111,
      "grad_norm": 0.217156782746315,
      "learning_rate": 9.561975714622295e-06,
      "loss": 0.03,
      "step": 930
    },
    {
      "epoch": 8.703703703703704,
      "grad_norm": 0.2336784154176712,
      "learning_rate": 8.289553812170326e-06,
      "loss": 0.0334,
      "step": 940
    },
    {
      "epoch": 8.796296296296296,
      "grad_norm": 0.20166803896427155,
      "learning_rate": 7.104295635110936e-06,
      "loss": 0.0298,
      "step": 950
    },
    {
      "epoch": 8.88888888888889,
      "grad_norm": 0.16439595818519592,
      "learning_rate": 6.00732768017982e-06,
      "loss": 0.0334,
      "step": 960
    },
    {
      "epoch": 8.981481481481481,
      "grad_norm": 0.18842309713363647,
      "learning_rate": 4.999692531047307e-06,
      "loss": 0.0344,
      "step": 970
    },
    {
      "epoch": 9.074074074074074,
      "grad_norm": 0.18367870151996613,
      "learning_rate": 4.082347867422553e-06,
      "loss": 0.0337,
      "step": 980
    },
    {
      "epoch": 9.166666666666666,
      "grad_norm": 0.2120891809463501,
      "learning_rate": 3.2561655548527636e-06,
      "loss": 0.0309,
      "step": 990
    },
    {
      "epoch": 9.25925925925926,
      "grad_norm": 0.27212539315223694,
      "learning_rate": 2.521930816082063e-06,
      "loss": 0.0375,
      "step": 1000
    },
    {
      "epoch": 9.351851851851851,
      "grad_norm": 0.16872258484363556,
      "learning_rate": 1.8803414847575417e-06,
      "loss": 0.0255,
      "step": 1010
    },
    {
      "epoch": 9.444444444444445,
      "grad_norm": 0.1719067543745041,
      "learning_rate": 1.3320073421921986e-06,
      "loss": 0.0336,
      "step": 1020
    },
    {
      "epoch": 9.537037037037036,
      "grad_norm": 0.16031451523303986,
      "learning_rate": 8.77449537814623e-07,
      "loss": 0.0324,
      "step": 1030
    },
    {
      "epoch": 9.62962962962963,
      "grad_norm": 0.15033039450645447,
      "learning_rate": 5.171000938565484e-07,
      "loss": 0.0284,
      "step": 1040
    },
    {
      "epoch": 9.722222222222221,
      "grad_norm": 0.1727823168039322,
      "learning_rate": 2.513014947489678e-07,
      "loss": 0.0263,
      "step": 1050
    },
    {
      "epoch": 9.814814814814815,
      "grad_norm": 0.14446181058883667,
      "learning_rate": 8.030636161701078e-08,
      "loss": 0.029,
      "step": 1060
    },
    {
      "epoch": 9.907407407407408,
      "grad_norm": 0.3018522262573242,
      "learning_rate": 4.27721218301258e-09,
      "loss": 0.0307,
      "step": 1070
    },
    {
      "epoch": 9.935185185185185,
      "step": 1073,
      "total_flos": 1.5130009512588355e+17,
      "train_loss": 0.07705365996269678,
      "train_runtime": 1230.2164,
      "train_samples_per_second": 55.821,
      "train_steps_per_second": 0.872
    }
  ],
  "logging_steps": 10,
  "max_steps": 1073,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5130009512588355e+17,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}