{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 12.0, "eval_steps": 500, "global_step": 432, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.028169014084507043, "grad_norm": 5.418299028662257, "learning_rate": 9.999993146109795e-07, "loss": 0.5132051110267639, "step": 1 }, { "epoch": 0.056338028169014086, "grad_norm": 5.165609347936129, "learning_rate": 9.999972584460056e-07, "loss": 0.5073634386062622, "step": 2 }, { "epoch": 0.08450704225352113, "grad_norm": 5.195437990428209, "learning_rate": 9.99993831511342e-07, "loss": 0.5153955221176147, "step": 3 }, { "epoch": 0.11267605633802817, "grad_norm": 4.79583419513962, "learning_rate": 9.999890338174275e-07, "loss": 0.4989941716194153, "step": 4 }, { "epoch": 0.14084507042253522, "grad_norm": 4.207848876215671, "learning_rate": 9.99982865378877e-07, "loss": 0.48423337936401367, "step": 5 }, { "epoch": 0.16901408450704225, "grad_norm": 4.218583800715356, "learning_rate": 9.999753262144804e-07, "loss": 0.48089924454689026, "step": 6 }, { "epoch": 0.19718309859154928, "grad_norm": 4.005100353285046, "learning_rate": 9.999664163472034e-07, "loss": 0.47420695424079895, "step": 7 }, { "epoch": 0.22535211267605634, "grad_norm": 3.929557609614918, "learning_rate": 9.999561358041868e-07, "loss": 0.47918927669525146, "step": 8 }, { "epoch": 0.2535211267605634, "grad_norm": 2.694796145734545, "learning_rate": 9.99944484616747e-07, "loss": 0.4395635426044464, "step": 9 }, { "epoch": 0.28169014084507044, "grad_norm": 2.427520188062667, "learning_rate": 9.99931462820376e-07, "loss": 0.42557471990585327, "step": 10 }, { "epoch": 0.30985915492957744, "grad_norm": 2.4361246746804692, "learning_rate": 9.999170704547398e-07, "loss": 0.43526768684387207, "step": 11 }, { "epoch": 0.3380281690140845, "grad_norm": 2.394762841017111, "learning_rate": 9.999013075636804e-07, "loss": 0.4402061104774475, "step": 12 }, { "epoch": 0.36619718309859156, "grad_norm": 2.083652020594123, "learning_rate": 9.998841741952141e-07, "loss": 0.4102749824523926, "step": 13 }, { "epoch": 0.39436619718309857, "grad_norm": 2.0892711360401948, "learning_rate": 9.998656704015323e-07, "loss": 0.42078256607055664, "step": 14 }, { "epoch": 0.4225352112676056, "grad_norm": 2.0344088244674343, "learning_rate": 9.998457962390008e-07, "loss": 0.4181898832321167, "step": 15 }, { "epoch": 0.4507042253521127, "grad_norm": 1.940959597352366, "learning_rate": 9.998245517681593e-07, "loss": 0.40955501794815063, "step": 16 }, { "epoch": 0.4788732394366197, "grad_norm": 0.8816622805671499, "learning_rate": 9.998019370537227e-07, "loss": 0.3903525471687317, "step": 17 }, { "epoch": 0.5070422535211268, "grad_norm": 0.8501184697349302, "learning_rate": 9.997779521645791e-07, "loss": 0.3796430230140686, "step": 18 }, { "epoch": 0.5352112676056338, "grad_norm": 0.8116182529970104, "learning_rate": 9.997525971737909e-07, "loss": 0.3822035789489746, "step": 19 }, { "epoch": 0.5633802816901409, "grad_norm": 0.7873864669427912, "learning_rate": 9.997258721585931e-07, "loss": 0.3768383860588074, "step": 20 }, { "epoch": 0.5915492957746479, "grad_norm": 0.7538308754999873, "learning_rate": 9.99697777200395e-07, "loss": 0.3780366778373718, "step": 21 }, { "epoch": 0.6197183098591549, "grad_norm": 0.746877326907616, "learning_rate": 9.996683123847795e-07, "loss": 0.37998318672180176, "step": 22 }, { "epoch": 0.647887323943662, "grad_norm": 0.7186953728538551, "learning_rate": 9.996374778015007e-07, "loss": 0.37321770191192627, "step": 23 }, { "epoch": 0.676056338028169, "grad_norm": 0.6944848844555613, "learning_rate": 9.996052735444862e-07, "loss": 0.3735676109790802, "step": 24 }, { "epoch": 0.704225352112676, "grad_norm": 0.6362193589652109, "learning_rate": 9.99571699711836e-07, "loss": 0.37480324506759644, "step": 25 }, { "epoch": 0.7323943661971831, "grad_norm": 0.6333241594644416, "learning_rate": 9.995367564058216e-07, "loss": 0.36993861198425293, "step": 26 }, { "epoch": 0.7605633802816901, "grad_norm": 0.6098149107884999, "learning_rate": 9.995004437328865e-07, "loss": 0.3650243282318115, "step": 27 }, { "epoch": 0.7887323943661971, "grad_norm": 0.5944375419192803, "learning_rate": 9.994627618036452e-07, "loss": 0.3905714750289917, "step": 28 }, { "epoch": 0.8169014084507042, "grad_norm": 0.5736619217852436, "learning_rate": 9.994237107328838e-07, "loss": 0.3627358675003052, "step": 29 }, { "epoch": 0.8450704225352113, "grad_norm": 0.5886929426905549, "learning_rate": 9.993832906395582e-07, "loss": 0.3565104603767395, "step": 30 }, { "epoch": 0.8732394366197183, "grad_norm": 0.5353744882375503, "learning_rate": 9.993415016467952e-07, "loss": 0.36376649141311646, "step": 31 }, { "epoch": 0.9014084507042254, "grad_norm": 0.49225367207832443, "learning_rate": 9.992983438818915e-07, "loss": 0.369179368019104, "step": 32 }, { "epoch": 0.9295774647887324, "grad_norm": 0.4556896703645998, "learning_rate": 9.992538174763127e-07, "loss": 0.3526361882686615, "step": 33 }, { "epoch": 0.9577464788732394, "grad_norm": 0.5188804849989508, "learning_rate": 9.992079225656944e-07, "loss": 0.3492780327796936, "step": 34 }, { "epoch": 0.9859154929577465, "grad_norm": 0.5109563747610114, "learning_rate": 9.9916065928984e-07, "loss": 0.3500766158103943, "step": 35 }, { "epoch": 1.0, "grad_norm": 0.5562934346388212, "learning_rate": 9.991120277927223e-07, "loss": 0.37105804681777954, "step": 36 }, { "epoch": 1.028169014084507, "grad_norm": 0.5221736259155545, "learning_rate": 9.990620282224806e-07, "loss": 0.3426528871059418, "step": 37 }, { "epoch": 1.056338028169014, "grad_norm": 0.5312140458936209, "learning_rate": 9.990106607314225e-07, "loss": 0.3402440547943115, "step": 38 }, { "epoch": 1.084507042253521, "grad_norm": 0.4925804810345089, "learning_rate": 9.989579254760224e-07, "loss": 0.3478923439979553, "step": 39 }, { "epoch": 1.1126760563380282, "grad_norm": 0.4713456639902427, "learning_rate": 9.989038226169207e-07, "loss": 0.3395651578903198, "step": 40 }, { "epoch": 1.1408450704225352, "grad_norm": 0.40869144140431884, "learning_rate": 9.988483523189248e-07, "loss": 0.33732888102531433, "step": 41 }, { "epoch": 1.1690140845070423, "grad_norm": 0.4315316017587138, "learning_rate": 9.98791514751006e-07, "loss": 0.32492154836654663, "step": 42 }, { "epoch": 1.1971830985915493, "grad_norm": 0.37481864132677223, "learning_rate": 9.98733310086302e-07, "loss": 0.34133073687553406, "step": 43 }, { "epoch": 1.2253521126760563, "grad_norm": 0.3574253218229588, "learning_rate": 9.98673738502114e-07, "loss": 0.3353017568588257, "step": 44 }, { "epoch": 1.2535211267605635, "grad_norm": 0.3440064791263243, "learning_rate": 9.986128001799076e-07, "loss": 0.3392435312271118, "step": 45 }, { "epoch": 1.2816901408450705, "grad_norm": 0.340263808482957, "learning_rate": 9.985504953053113e-07, "loss": 0.3362383544445038, "step": 46 }, { "epoch": 1.3098591549295775, "grad_norm": 0.33745919836931715, "learning_rate": 9.984868240681164e-07, "loss": 0.3242315649986267, "step": 47 }, { "epoch": 1.3380281690140845, "grad_norm": 0.3289741626977548, "learning_rate": 9.98421786662277e-07, "loss": 0.3304663896560669, "step": 48 }, { "epoch": 1.3661971830985915, "grad_norm": 0.31460186215251207, "learning_rate": 9.983553832859078e-07, "loss": 0.32084885239601135, "step": 49 }, { "epoch": 1.3943661971830985, "grad_norm": 0.3245154924065007, "learning_rate": 9.982876141412855e-07, "loss": 0.3394209146499634, "step": 50 }, { "epoch": 1.4225352112676055, "grad_norm": 0.31250544820074627, "learning_rate": 9.982184794348462e-07, "loss": 0.32516294717788696, "step": 51 }, { "epoch": 1.4507042253521127, "grad_norm": 0.30500960409480415, "learning_rate": 9.981479793771866e-07, "loss": 0.33079296350479126, "step": 52 }, { "epoch": 1.4788732394366197, "grad_norm": 0.7536289161405646, "learning_rate": 9.98076114183062e-07, "loss": 0.32204341888427734, "step": 53 }, { "epoch": 1.5070422535211268, "grad_norm": 0.2960511511830655, "learning_rate": 9.98002884071386e-07, "loss": 0.3231901526451111, "step": 54 }, { "epoch": 1.5352112676056338, "grad_norm": 0.3232856362024084, "learning_rate": 9.979282892652304e-07, "loss": 0.33578696846961975, "step": 55 }, { "epoch": 1.563380281690141, "grad_norm": 0.2944501744644002, "learning_rate": 9.97852329991824e-07, "loss": 0.32318681478500366, "step": 56 }, { "epoch": 1.591549295774648, "grad_norm": 0.2929838195254813, "learning_rate": 9.977750064825519e-07, "loss": 0.339860737323761, "step": 57 }, { "epoch": 1.619718309859155, "grad_norm": 0.3205944314956805, "learning_rate": 9.976963189729547e-07, "loss": 0.32377177476882935, "step": 58 }, { "epoch": 1.647887323943662, "grad_norm": 0.29345488313940016, "learning_rate": 9.976162677027284e-07, "loss": 0.3301998972892761, "step": 59 }, { "epoch": 1.676056338028169, "grad_norm": 0.28471478486927526, "learning_rate": 9.975348529157229e-07, "loss": 0.3226792812347412, "step": 60 }, { "epoch": 1.704225352112676, "grad_norm": 0.2658831538134308, "learning_rate": 9.974520748599421e-07, "loss": 0.3216060996055603, "step": 61 }, { "epoch": 1.732394366197183, "grad_norm": 0.26772727111733485, "learning_rate": 9.973679337875418e-07, "loss": 0.3112826347351074, "step": 62 }, { "epoch": 1.76056338028169, "grad_norm": 0.27607375529137707, "learning_rate": 9.972824299548309e-07, "loss": 0.32318398356437683, "step": 63 }, { "epoch": 1.788732394366197, "grad_norm": 0.276525714664102, "learning_rate": 9.971955636222684e-07, "loss": 0.3215365707874298, "step": 64 }, { "epoch": 1.8169014084507042, "grad_norm": 0.26621366711174155, "learning_rate": 9.971073350544644e-07, "loss": 0.3165343403816223, "step": 65 }, { "epoch": 1.8450704225352113, "grad_norm": 0.28106696236531414, "learning_rate": 9.970177445201783e-07, "loss": 0.32160013914108276, "step": 66 }, { "epoch": 1.8732394366197183, "grad_norm": 0.2647958460920452, "learning_rate": 9.969267922923188e-07, "loss": 0.3175761103630066, "step": 67 }, { "epoch": 1.9014084507042255, "grad_norm": 0.3462438167974764, "learning_rate": 9.968344786479415e-07, "loss": 0.31158342957496643, "step": 68 }, { "epoch": 1.9295774647887325, "grad_norm": 0.2631517138191484, "learning_rate": 9.967408038682505e-07, "loss": 0.3191946744918823, "step": 69 }, { "epoch": 1.9577464788732395, "grad_norm": 0.3059517169103558, "learning_rate": 9.96645768238595e-07, "loss": 0.31686434149742126, "step": 70 }, { "epoch": 1.9859154929577465, "grad_norm": 0.2747560759134169, "learning_rate": 9.965493720484698e-07, "loss": 0.32002022862434387, "step": 71 }, { "epoch": 2.0, "grad_norm": 0.3436945075098925, "learning_rate": 9.964516155915151e-07, "loss": 0.31206002831459045, "step": 72 }, { "epoch": 2.028169014084507, "grad_norm": 0.24759643540050102, "learning_rate": 9.963524991655133e-07, "loss": 0.3164379596710205, "step": 73 }, { "epoch": 2.056338028169014, "grad_norm": 0.2434100698887695, "learning_rate": 9.962520230723906e-07, "loss": 0.31132200360298157, "step": 74 }, { "epoch": 2.084507042253521, "grad_norm": 0.27767056283467373, "learning_rate": 9.961501876182148e-07, "loss": 0.3142748475074768, "step": 75 }, { "epoch": 2.112676056338028, "grad_norm": 0.2383770994918481, "learning_rate": 9.960469931131936e-07, "loss": 0.3118811249732971, "step": 76 }, { "epoch": 2.140845070422535, "grad_norm": 0.2521646078141003, "learning_rate": 9.959424398716763e-07, "loss": 0.3206384778022766, "step": 77 }, { "epoch": 2.169014084507042, "grad_norm": 0.24500926882339497, "learning_rate": 9.958365282121496e-07, "loss": 0.3028615117073059, "step": 78 }, { "epoch": 2.1971830985915495, "grad_norm": 0.24030528199838755, "learning_rate": 9.95729258457239e-07, "loss": 0.2991243600845337, "step": 79 }, { "epoch": 2.2253521126760565, "grad_norm": 0.24540461017636186, "learning_rate": 9.956206309337066e-07, "loss": 0.3028961420059204, "step": 80 }, { "epoch": 2.2535211267605635, "grad_norm": 0.2466946916886877, "learning_rate": 9.955106459724508e-07, "loss": 0.3096856474876404, "step": 81 }, { "epoch": 2.2816901408450705, "grad_norm": 0.2755173295195889, "learning_rate": 9.953993039085048e-07, "loss": 0.30638784170150757, "step": 82 }, { "epoch": 2.3098591549295775, "grad_norm": 0.2514653938379217, "learning_rate": 9.952866050810363e-07, "loss": 0.3001154661178589, "step": 83 }, { "epoch": 2.3380281690140845, "grad_norm": 0.2387732228915944, "learning_rate": 9.951725498333448e-07, "loss": 0.3049381673336029, "step": 84 }, { "epoch": 2.3661971830985915, "grad_norm": 0.23263762732735094, "learning_rate": 9.950571385128625e-07, "loss": 0.2974574565887451, "step": 85 }, { "epoch": 2.3943661971830985, "grad_norm": 0.23061479782330688, "learning_rate": 9.949403714711526e-07, "loss": 0.2910880148410797, "step": 86 }, { "epoch": 2.4225352112676055, "grad_norm": 0.23023752633245553, "learning_rate": 9.948222490639075e-07, "loss": 0.2984412610530853, "step": 87 }, { "epoch": 2.4507042253521125, "grad_norm": 0.2556642237814582, "learning_rate": 9.947027716509488e-07, "loss": 0.29366716742515564, "step": 88 }, { "epoch": 2.4788732394366195, "grad_norm": 0.23091894334348845, "learning_rate": 9.94581939596225e-07, "loss": 0.3076009750366211, "step": 89 }, { "epoch": 2.507042253521127, "grad_norm": 0.22827065781305456, "learning_rate": 9.944597532678119e-07, "loss": 0.30507659912109375, "step": 90 }, { "epoch": 2.535211267605634, "grad_norm": 0.23495783877634624, "learning_rate": 9.943362130379101e-07, "loss": 0.30069300532341003, "step": 91 }, { "epoch": 2.563380281690141, "grad_norm": 0.2648421541967289, "learning_rate": 9.942113192828444e-07, "loss": 0.3237234652042389, "step": 92 }, { "epoch": 2.591549295774648, "grad_norm": 0.2376008941714217, "learning_rate": 9.940850723830632e-07, "loss": 0.30564817786216736, "step": 93 }, { "epoch": 2.619718309859155, "grad_norm": 0.3594923854547647, "learning_rate": 9.939574727231362e-07, "loss": 0.2874234914779663, "step": 94 }, { "epoch": 2.647887323943662, "grad_norm": 0.22882707129774643, "learning_rate": 9.93828520691754e-07, "loss": 0.3145613670349121, "step": 95 }, { "epoch": 2.676056338028169, "grad_norm": 0.22736499094759352, "learning_rate": 9.93698216681727e-07, "loss": 0.30298489332199097, "step": 96 }, { "epoch": 2.704225352112676, "grad_norm": 0.2560977265944999, "learning_rate": 9.93566561089984e-07, "loss": 0.30830079317092896, "step": 97 }, { "epoch": 2.732394366197183, "grad_norm": 0.23579803469255398, "learning_rate": 9.934335543175705e-07, "loss": 0.2954327166080475, "step": 98 }, { "epoch": 2.76056338028169, "grad_norm": 0.24145604440100388, "learning_rate": 9.932991967696482e-07, "loss": 0.3123829960823059, "step": 99 }, { "epoch": 2.788732394366197, "grad_norm": 0.23937111018917692, "learning_rate": 9.931634888554935e-07, "loss": 0.30813831090927124, "step": 100 }, { "epoch": 2.816901408450704, "grad_norm": 0.23102456481544026, "learning_rate": 9.930264309884964e-07, "loss": 0.29939332604408264, "step": 101 }, { "epoch": 2.845070422535211, "grad_norm": 0.2388325654329505, "learning_rate": 9.928880235861588e-07, "loss": 0.3060687184333801, "step": 102 }, { "epoch": 2.873239436619718, "grad_norm": 0.2692772021272968, "learning_rate": 9.927482670700936e-07, "loss": 0.3026995360851288, "step": 103 }, { "epoch": 2.9014084507042255, "grad_norm": 0.2195252664324123, "learning_rate": 9.926071618660237e-07, "loss": 0.29397717118263245, "step": 104 }, { "epoch": 2.9295774647887325, "grad_norm": 0.24295446606786492, "learning_rate": 9.924647084037797e-07, "loss": 0.30009227991104126, "step": 105 }, { "epoch": 2.9577464788732395, "grad_norm": 0.2313070418168474, "learning_rate": 9.923209071172994e-07, "loss": 0.2927643656730652, "step": 106 }, { "epoch": 2.9859154929577465, "grad_norm": 0.22879166840885404, "learning_rate": 9.921757584446268e-07, "loss": 0.2916420102119446, "step": 107 }, { "epoch": 3.0, "grad_norm": 0.3008754833697553, "learning_rate": 9.9202926282791e-07, "loss": 0.28270626068115234, "step": 108 }, { "epoch": 3.028169014084507, "grad_norm": 0.23568699154112785, "learning_rate": 9.918814207133997e-07, "loss": 0.28633755445480347, "step": 109 }, { "epoch": 3.056338028169014, "grad_norm": 0.23303560144939867, "learning_rate": 9.917322325514487e-07, "loss": 0.30074095726013184, "step": 110 }, { "epoch": 3.084507042253521, "grad_norm": 0.2316049153802507, "learning_rate": 9.915816987965102e-07, "loss": 0.2938191294670105, "step": 111 }, { "epoch": 3.112676056338028, "grad_norm": 0.24039981484305117, "learning_rate": 9.91429819907136e-07, "loss": 0.3015148639678955, "step": 112 }, { "epoch": 3.140845070422535, "grad_norm": 0.21607780251617179, "learning_rate": 9.912765963459756e-07, "loss": 0.2841828167438507, "step": 113 }, { "epoch": 3.169014084507042, "grad_norm": 0.24291861075598384, "learning_rate": 9.911220285797748e-07, "loss": 0.2961827218532562, "step": 114 }, { "epoch": 3.1971830985915495, "grad_norm": 0.260079633277976, "learning_rate": 9.909661170793733e-07, "loss": 0.2853129506111145, "step": 115 }, { "epoch": 3.2253521126760565, "grad_norm": 0.22330476823859097, "learning_rate": 9.908088623197048e-07, "loss": 0.30180466175079346, "step": 116 }, { "epoch": 3.2535211267605635, "grad_norm": 0.23280629394443647, "learning_rate": 9.906502647797945e-07, "loss": 0.30052781105041504, "step": 117 }, { "epoch": 3.2816901408450705, "grad_norm": 0.21797810381540847, "learning_rate": 9.904903249427582e-07, "loss": 0.2998088598251343, "step": 118 }, { "epoch": 3.3098591549295775, "grad_norm": 0.2122579387275699, "learning_rate": 9.903290432958003e-07, "loss": 0.2904450297355652, "step": 119 }, { "epoch": 3.3380281690140845, "grad_norm": 0.2306597760843549, "learning_rate": 9.901664203302124e-07, "loss": 0.2772594690322876, "step": 120 }, { "epoch": 3.3661971830985915, "grad_norm": 0.3251131669552687, "learning_rate": 9.900024565413727e-07, "loss": 0.2782062292098999, "step": 121 }, { "epoch": 3.3943661971830985, "grad_norm": 0.21492053378836454, "learning_rate": 9.89837152428743e-07, "loss": 0.2862273156642914, "step": 122 }, { "epoch": 3.4225352112676055, "grad_norm": 0.21940072001551747, "learning_rate": 9.896705084958687e-07, "loss": 0.2992798686027527, "step": 123 }, { "epoch": 3.4507042253521125, "grad_norm": 0.22907980661604213, "learning_rate": 9.895025252503755e-07, "loss": 0.27001839876174927, "step": 124 }, { "epoch": 3.4788732394366195, "grad_norm": 0.22323548107714866, "learning_rate": 9.8933320320397e-07, "loss": 0.2867587208747864, "step": 125 }, { "epoch": 3.507042253521127, "grad_norm": 0.2133180650070634, "learning_rate": 9.891625428724364e-07, "loss": 0.2889852821826935, "step": 126 }, { "epoch": 3.535211267605634, "grad_norm": 0.22234390437617468, "learning_rate": 9.889905447756355e-07, "loss": 0.2830744981765747, "step": 127 }, { "epoch": 3.563380281690141, "grad_norm": 0.22998700794578517, "learning_rate": 9.888172094375033e-07, "loss": 0.29788801074028015, "step": 128 }, { "epoch": 3.591549295774648, "grad_norm": 0.4625877582933462, "learning_rate": 9.886425373860496e-07, "loss": 0.29489147663116455, "step": 129 }, { "epoch": 3.619718309859155, "grad_norm": 0.22935899493352271, "learning_rate": 9.88466529153356e-07, "loss": 0.2970463037490845, "step": 130 }, { "epoch": 3.647887323943662, "grad_norm": 0.24274389064678412, "learning_rate": 9.882891852755732e-07, "loss": 0.2851516008377075, "step": 131 }, { "epoch": 3.676056338028169, "grad_norm": 0.22141629938400506, "learning_rate": 9.881105062929221e-07, "loss": 0.2885037660598755, "step": 132 }, { "epoch": 3.704225352112676, "grad_norm": 0.22752563556013145, "learning_rate": 9.879304927496896e-07, "loss": 0.28612369298934937, "step": 133 }, { "epoch": 3.732394366197183, "grad_norm": 0.21651661785773998, "learning_rate": 9.877491451942284e-07, "loss": 0.2883659601211548, "step": 134 }, { "epoch": 3.76056338028169, "grad_norm": 0.23438766576379866, "learning_rate": 9.875664641789543e-07, "loss": 0.27838006615638733, "step": 135 }, { "epoch": 3.788732394366197, "grad_norm": 0.2253998931695203, "learning_rate": 9.873824502603459e-07, "loss": 0.2768632471561432, "step": 136 }, { "epoch": 3.816901408450704, "grad_norm": 0.2177655119766866, "learning_rate": 9.871971039989407e-07, "loss": 0.2836754322052002, "step": 137 }, { "epoch": 3.845070422535211, "grad_norm": 0.22595230341732617, "learning_rate": 9.870104259593362e-07, "loss": 0.28235411643981934, "step": 138 }, { "epoch": 3.873239436619718, "grad_norm": 0.2482489166005438, "learning_rate": 9.86822416710186e-07, "loss": 0.29619723558425903, "step": 139 }, { "epoch": 3.9014084507042255, "grad_norm": 0.2183147080685166, "learning_rate": 9.866330768241983e-07, "loss": 0.2837688624858856, "step": 140 }, { "epoch": 3.9295774647887325, "grad_norm": 0.23756245135618922, "learning_rate": 9.86442406878136e-07, "loss": 0.29686689376831055, "step": 141 }, { "epoch": 3.9577464788732395, "grad_norm": 0.21910640405689585, "learning_rate": 9.862504074528126e-07, "loss": 0.3005070984363556, "step": 142 }, { "epoch": 3.9859154929577465, "grad_norm": 0.2231139496297488, "learning_rate": 9.860570791330911e-07, "loss": 0.28214913606643677, "step": 143 }, { "epoch": 4.0, "grad_norm": 0.327745139722082, "learning_rate": 9.85862422507884e-07, "loss": 0.2614859938621521, "step": 144 }, { "epoch": 4.028169014084507, "grad_norm": 0.21956180832878694, "learning_rate": 9.856664381701483e-07, "loss": 0.2801395654678345, "step": 145 }, { "epoch": 4.056338028169014, "grad_norm": 0.21981533940846626, "learning_rate": 9.854691267168871e-07, "loss": 0.2805081307888031, "step": 146 }, { "epoch": 4.084507042253521, "grad_norm": 0.22352024368863976, "learning_rate": 9.852704887491445e-07, "loss": 0.2810959815979004, "step": 147 }, { "epoch": 4.112676056338028, "grad_norm": 0.21378340480206676, "learning_rate": 9.850705248720068e-07, "loss": 0.2902711033821106, "step": 148 }, { "epoch": 4.140845070422535, "grad_norm": 0.6576619030457451, "learning_rate": 9.848692356945981e-07, "loss": 0.2759314775466919, "step": 149 }, { "epoch": 4.169014084507042, "grad_norm": 0.22012344359855593, "learning_rate": 9.846666218300807e-07, "loss": 0.268562912940979, "step": 150 }, { "epoch": 4.197183098591549, "grad_norm": 0.21540756213399562, "learning_rate": 9.844626838956513e-07, "loss": 0.29484277963638306, "step": 151 }, { "epoch": 4.225352112676056, "grad_norm": 0.23087516265191377, "learning_rate": 9.8425742251254e-07, "loss": 0.2736097574234009, "step": 152 }, { "epoch": 4.253521126760563, "grad_norm": 0.22858752073312144, "learning_rate": 9.84050838306009e-07, "loss": 0.2795490622520447, "step": 153 }, { "epoch": 4.28169014084507, "grad_norm": 0.2504089824174044, "learning_rate": 9.838429319053495e-07, "loss": 0.27981656789779663, "step": 154 }, { "epoch": 4.309859154929577, "grad_norm": 0.2144903706614124, "learning_rate": 9.836337039438803e-07, "loss": 0.2772422134876251, "step": 155 }, { "epoch": 4.338028169014084, "grad_norm": 0.23097398374379755, "learning_rate": 9.83423155058946e-07, "loss": 0.2819685637950897, "step": 156 }, { "epoch": 4.366197183098592, "grad_norm": 0.24080056507624897, "learning_rate": 9.832112858919155e-07, "loss": 0.28476956486701965, "step": 157 }, { "epoch": 4.394366197183099, "grad_norm": 0.22574168772954528, "learning_rate": 9.829980970881784e-07, "loss": 0.2726949155330658, "step": 158 }, { "epoch": 4.422535211267606, "grad_norm": 0.6972322742026779, "learning_rate": 9.82783589297145e-07, "loss": 0.2827332615852356, "step": 159 }, { "epoch": 4.450704225352113, "grad_norm": 0.2391641337184146, "learning_rate": 9.825677631722435e-07, "loss": 0.28474992513656616, "step": 160 }, { "epoch": 4.47887323943662, "grad_norm": 0.221898655707498, "learning_rate": 9.823506193709174e-07, "loss": 0.28681856393814087, "step": 161 }, { "epoch": 4.507042253521127, "grad_norm": 0.22336161749059524, "learning_rate": 9.821321585546243e-07, "loss": 0.2809918522834778, "step": 162 }, { "epoch": 4.535211267605634, "grad_norm": 0.21973730928374757, "learning_rate": 9.81912381388834e-07, "loss": 0.265026330947876, "step": 163 }, { "epoch": 4.563380281690141, "grad_norm": 0.25521582293188844, "learning_rate": 9.816912885430258e-07, "loss": 0.27740782499313354, "step": 164 }, { "epoch": 4.591549295774648, "grad_norm": 0.22348230986657833, "learning_rate": 9.814688806906868e-07, "loss": 0.2830485701560974, "step": 165 }, { "epoch": 4.619718309859155, "grad_norm": 0.23949143954055024, "learning_rate": 9.812451585093098e-07, "loss": 0.2732582092285156, "step": 166 }, { "epoch": 4.647887323943662, "grad_norm": 0.24011757347977605, "learning_rate": 9.810201226803917e-07, "loss": 0.27790567278862, "step": 167 }, { "epoch": 4.676056338028169, "grad_norm": 0.2208241856254554, "learning_rate": 9.807937738894303e-07, "loss": 0.27999186515808105, "step": 168 }, { "epoch": 4.704225352112676, "grad_norm": 0.22207182950383192, "learning_rate": 9.805661128259235e-07, "loss": 0.2758759558200836, "step": 169 }, { "epoch": 4.732394366197183, "grad_norm": 0.2223130884819787, "learning_rate": 9.80337140183366e-07, "loss": 0.2783896327018738, "step": 170 }, { "epoch": 4.76056338028169, "grad_norm": 0.2251473945003646, "learning_rate": 9.801068566592483e-07, "loss": 0.2750943601131439, "step": 171 }, { "epoch": 4.788732394366197, "grad_norm": 0.20904181797718158, "learning_rate": 9.798752629550546e-07, "loss": 0.2790430784225464, "step": 172 }, { "epoch": 4.816901408450704, "grad_norm": 0.22738399964996078, "learning_rate": 9.796423597762588e-07, "loss": 0.2752009630203247, "step": 173 }, { "epoch": 4.845070422535211, "grad_norm": 0.3424040844187128, "learning_rate": 9.794081478323245e-07, "loss": 0.2811102271080017, "step": 174 }, { "epoch": 4.873239436619718, "grad_norm": 0.22370787445632553, "learning_rate": 9.791726278367021e-07, "loss": 0.27801671624183655, "step": 175 }, { "epoch": 4.901408450704225, "grad_norm": 0.244597442698197, "learning_rate": 9.78935800506826e-07, "loss": 0.2749514579772949, "step": 176 }, { "epoch": 4.929577464788732, "grad_norm": 0.22603846349643272, "learning_rate": 9.786976665641138e-07, "loss": 0.2660600543022156, "step": 177 }, { "epoch": 4.957746478873239, "grad_norm": 0.22615957713600704, "learning_rate": 9.784582267339622e-07, "loss": 0.28135621547698975, "step": 178 }, { "epoch": 4.985915492957746, "grad_norm": 0.22802110120296137, "learning_rate": 9.78217481745747e-07, "loss": 0.27813419699668884, "step": 179 }, { "epoch": 5.0, "grad_norm": 0.31867363735197585, "learning_rate": 9.779754323328192e-07, "loss": 0.28184953331947327, "step": 180 }, { "epoch": 5.028169014084507, "grad_norm": 0.23359190602929383, "learning_rate": 9.777320792325025e-07, "loss": 0.2600752115249634, "step": 181 }, { "epoch": 5.056338028169014, "grad_norm": 0.24395267689073322, "learning_rate": 9.774874231860935e-07, "loss": 0.265809565782547, "step": 182 }, { "epoch": 5.084507042253521, "grad_norm": 0.2492192509436832, "learning_rate": 9.772414649388568e-07, "loss": 0.2792435884475708, "step": 183 }, { "epoch": 5.112676056338028, "grad_norm": 0.21622914380528604, "learning_rate": 9.769942052400235e-07, "loss": 0.26818716526031494, "step": 184 }, { "epoch": 5.140845070422535, "grad_norm": 0.27867715267424076, "learning_rate": 9.767456448427896e-07, "loss": 0.27086278796195984, "step": 185 }, { "epoch": 5.169014084507042, "grad_norm": 0.2346306080793482, "learning_rate": 9.764957845043135e-07, "loss": 0.2673496901988983, "step": 186 }, { "epoch": 5.197183098591549, "grad_norm": 0.23851487965670903, "learning_rate": 9.76244624985713e-07, "loss": 0.2633378803730011, "step": 187 }, { "epoch": 5.225352112676056, "grad_norm": 0.2362238221478819, "learning_rate": 9.759921670520634e-07, "loss": 0.27480238676071167, "step": 188 }, { "epoch": 5.253521126760563, "grad_norm": 0.23011578681816747, "learning_rate": 9.757384114723953e-07, "loss": 0.28158247470855713, "step": 189 }, { "epoch": 5.28169014084507, "grad_norm": 0.2323771506860616, "learning_rate": 9.754833590196926e-07, "loss": 0.2691372334957123, "step": 190 }, { "epoch": 5.309859154929577, "grad_norm": 0.23247640324241922, "learning_rate": 9.752270104708888e-07, "loss": 0.2666372060775757, "step": 191 }, { "epoch": 5.338028169014084, "grad_norm": 0.35005461804027077, "learning_rate": 9.749693666068663e-07, "loss": 0.2779178321361542, "step": 192 }, { "epoch": 5.366197183098592, "grad_norm": 0.29793203943964064, "learning_rate": 9.747104282124531e-07, "loss": 0.26953545212745667, "step": 193 }, { "epoch": 5.394366197183099, "grad_norm": 0.2262507700581054, "learning_rate": 9.744501960764203e-07, "loss": 0.26865124702453613, "step": 194 }, { "epoch": 5.422535211267606, "grad_norm": 0.21683849012894404, "learning_rate": 9.741886709914803e-07, "loss": 0.25939399003982544, "step": 195 }, { "epoch": 5.450704225352113, "grad_norm": 0.22595351538334174, "learning_rate": 9.739258537542835e-07, "loss": 0.2663502097129822, "step": 196 }, { "epoch": 5.47887323943662, "grad_norm": 0.22169050419160188, "learning_rate": 9.73661745165417e-07, "loss": 0.2786925435066223, "step": 197 }, { "epoch": 5.507042253521127, "grad_norm": 0.24492486958596588, "learning_rate": 9.733963460294015e-07, "loss": 0.27515316009521484, "step": 198 }, { "epoch": 5.535211267605634, "grad_norm": 0.22826949989900344, "learning_rate": 9.731296571546885e-07, "loss": 0.28115102648735046, "step": 199 }, { "epoch": 5.563380281690141, "grad_norm": 0.26522607771513945, "learning_rate": 9.728616793536587e-07, "loss": 0.2721824645996094, "step": 200 }, { "epoch": 5.591549295774648, "grad_norm": 0.22800471881703901, "learning_rate": 9.72592413442619e-07, "loss": 0.28054916858673096, "step": 201 }, { "epoch": 5.619718309859155, "grad_norm": 0.2347149530251392, "learning_rate": 9.723218602418e-07, "loss": 0.28160133957862854, "step": 202 }, { "epoch": 5.647887323943662, "grad_norm": 0.239273549722643, "learning_rate": 9.720500205753538e-07, "loss": 0.26327449083328247, "step": 203 }, { "epoch": 5.676056338028169, "grad_norm": 0.24387472862754722, "learning_rate": 9.717768952713511e-07, "loss": 0.2734866738319397, "step": 204 }, { "epoch": 5.704225352112676, "grad_norm": 0.23364964137411087, "learning_rate": 9.71502485161779e-07, "loss": 0.2678722143173218, "step": 205 }, { "epoch": 5.732394366197183, "grad_norm": 0.22168298331328018, "learning_rate": 9.71226791082538e-07, "loss": 0.28682976961135864, "step": 206 }, { "epoch": 5.76056338028169, "grad_norm": 0.22794997018956722, "learning_rate": 9.709498138734403e-07, "loss": 0.26408618688583374, "step": 207 }, { "epoch": 5.788732394366197, "grad_norm": 0.23082951390472506, "learning_rate": 9.706715543782064e-07, "loss": 0.26725077629089355, "step": 208 }, { "epoch": 5.816901408450704, "grad_norm": 0.23772477020760396, "learning_rate": 9.703920134444632e-07, "loss": 0.264972060918808, "step": 209 }, { "epoch": 5.845070422535211, "grad_norm": 0.24144546698053745, "learning_rate": 9.701111919237408e-07, "loss": 0.27345162630081177, "step": 210 }, { "epoch": 5.873239436619718, "grad_norm": 0.21694849932490126, "learning_rate": 9.698290906714702e-07, "loss": 0.25832873582839966, "step": 211 }, { "epoch": 5.901408450704225, "grad_norm": 0.23606790891410948, "learning_rate": 9.695457105469804e-07, "loss": 0.27317512035369873, "step": 212 }, { "epoch": 5.929577464788732, "grad_norm": 0.22036780479653179, "learning_rate": 9.69261052413497e-07, "loss": 0.278011292219162, "step": 213 }, { "epoch": 5.957746478873239, "grad_norm": 0.22667530947182388, "learning_rate": 9.689751171381377e-07, "loss": 0.2705678641796112, "step": 214 }, { "epoch": 5.985915492957746, "grad_norm": 0.21789301750027548, "learning_rate": 9.68687905591911e-07, "loss": 0.26159361004829407, "step": 215 }, { "epoch": 6.0, "grad_norm": 0.307035373509359, "learning_rate": 9.683994186497132e-07, "loss": 0.268825888633728, "step": 216 }, { "epoch": 6.028169014084507, "grad_norm": 0.3152032154597242, "learning_rate": 9.681096571903252e-07, "loss": 0.26456916332244873, "step": 217 }, { "epoch": 6.056338028169014, "grad_norm": 0.22257647731470015, "learning_rate": 9.67818622096411e-07, "loss": 0.25304824113845825, "step": 218 }, { "epoch": 6.084507042253521, "grad_norm": 0.22819800840776633, "learning_rate": 9.67526314254514e-07, "loss": 0.2657697796821594, "step": 219 }, { "epoch": 6.112676056338028, "grad_norm": 0.22326346608679778, "learning_rate": 9.672327345550543e-07, "loss": 0.2606521248817444, "step": 220 }, { "epoch": 6.140845070422535, "grad_norm": 0.24238210645266042, "learning_rate": 9.669378838923267e-07, "loss": 0.259613037109375, "step": 221 }, { "epoch": 6.169014084507042, "grad_norm": 0.23469955143149954, "learning_rate": 9.666417631644976e-07, "loss": 0.27692991495132446, "step": 222 }, { "epoch": 6.197183098591549, "grad_norm": 0.32987217731044594, "learning_rate": 9.66344373273602e-07, "loss": 0.2645450532436371, "step": 223 }, { "epoch": 6.225352112676056, "grad_norm": 0.22700888241362085, "learning_rate": 9.66045715125541e-07, "loss": 0.2646715044975281, "step": 224 }, { "epoch": 6.253521126760563, "grad_norm": 0.22957306298672545, "learning_rate": 9.657457896300791e-07, "loss": 0.24674871563911438, "step": 225 }, { "epoch": 6.28169014084507, "grad_norm": 0.23586354836136889, "learning_rate": 9.654445977008414e-07, "loss": 0.2587713599205017, "step": 226 }, { "epoch": 6.309859154929577, "grad_norm": 0.2285859030240268, "learning_rate": 9.651421402553108e-07, "loss": 0.2513459026813507, "step": 227 }, { "epoch": 6.338028169014084, "grad_norm": 0.24331804613486147, "learning_rate": 9.648384182148252e-07, "loss": 0.2715184688568115, "step": 228 }, { "epoch": 6.366197183098592, "grad_norm": 0.2305076454423525, "learning_rate": 9.645334325045745e-07, "loss": 0.2733456492424011, "step": 229 }, { "epoch": 6.394366197183099, "grad_norm": 0.24182818411808535, "learning_rate": 9.64227184053598e-07, "loss": 0.27919310331344604, "step": 230 }, { "epoch": 6.422535211267606, "grad_norm": 0.24680603573979737, "learning_rate": 9.63919673794782e-07, "loss": 0.26471200585365295, "step": 231 }, { "epoch": 6.450704225352113, "grad_norm": 0.24016603586966853, "learning_rate": 9.636109026648554e-07, "loss": 0.26608601212501526, "step": 232 }, { "epoch": 6.47887323943662, "grad_norm": 0.23221033716137462, "learning_rate": 9.633008716043892e-07, "loss": 0.2712378203868866, "step": 233 }, { "epoch": 6.507042253521127, "grad_norm": 0.22946156470598095, "learning_rate": 9.629895815577915e-07, "loss": 0.2693229913711548, "step": 234 }, { "epoch": 6.535211267605634, "grad_norm": 0.24256759776346887, "learning_rate": 9.626770334733058e-07, "loss": 0.25974130630493164, "step": 235 }, { "epoch": 6.563380281690141, "grad_norm": 0.2284537050943504, "learning_rate": 9.623632283030077e-07, "loss": 0.27251625061035156, "step": 236 }, { "epoch": 6.591549295774648, "grad_norm": 0.22616819126049306, "learning_rate": 9.620481670028026e-07, "loss": 0.26490986347198486, "step": 237 }, { "epoch": 6.619718309859155, "grad_norm": 0.22191171035923044, "learning_rate": 9.617318505324212e-07, "loss": 0.25655436515808105, "step": 238 }, { "epoch": 6.647887323943662, "grad_norm": 0.23707447655959804, "learning_rate": 9.614142798554186e-07, "loss": 0.2742191553115845, "step": 239 }, { "epoch": 6.676056338028169, "grad_norm": 0.2553264029309018, "learning_rate": 9.610954559391704e-07, "loss": 0.25515586137771606, "step": 240 }, { "epoch": 6.704225352112676, "grad_norm": 0.24273871332366953, "learning_rate": 9.607753797548691e-07, "loss": 0.2646741271018982, "step": 241 }, { "epoch": 6.732394366197183, "grad_norm": 0.2333343519162289, "learning_rate": 9.604540522775227e-07, "loss": 0.26033157110214233, "step": 242 }, { "epoch": 6.76056338028169, "grad_norm": 0.22965997751864728, "learning_rate": 9.601314744859504e-07, "loss": 0.27026018500328064, "step": 243 }, { "epoch": 6.788732394366197, "grad_norm": 0.23498879472224687, "learning_rate": 9.598076473627796e-07, "loss": 0.26615339517593384, "step": 244 }, { "epoch": 6.816901408450704, "grad_norm": 0.22789781362841657, "learning_rate": 9.594825718944444e-07, "loss": 0.25952741503715515, "step": 245 }, { "epoch": 6.845070422535211, "grad_norm": 0.4285246410791299, "learning_rate": 9.59156249071181e-07, "loss": 0.2581027150154114, "step": 246 }, { "epoch": 6.873239436619718, "grad_norm": 0.22610447167940628, "learning_rate": 9.588286798870248e-07, "loss": 0.27599114179611206, "step": 247 }, { "epoch": 6.901408450704225, "grad_norm": 0.22882782061457732, "learning_rate": 9.58499865339809e-07, "loss": 0.2618204653263092, "step": 248 }, { "epoch": 6.929577464788732, "grad_norm": 0.26429160943599095, "learning_rate": 9.581698064311592e-07, "loss": 0.2596527338027954, "step": 249 }, { "epoch": 6.957746478873239, "grad_norm": 0.30324449730772324, "learning_rate": 9.578385041664925e-07, "loss": 0.26591378450393677, "step": 250 }, { "epoch": 6.985915492957746, "grad_norm": 0.24030702361568637, "learning_rate": 9.575059595550127e-07, "loss": 0.2602125406265259, "step": 251 }, { "epoch": 7.0, "grad_norm": 0.3109240011602677, "learning_rate": 9.571721736097088e-07, "loss": 0.2538529634475708, "step": 252 }, { "epoch": 7.028169014084507, "grad_norm": 0.2296122757795814, "learning_rate": 9.568371473473503e-07, "loss": 0.27390003204345703, "step": 253 }, { "epoch": 7.056338028169014, "grad_norm": 0.23108143057622355, "learning_rate": 9.565008817884854e-07, "loss": 0.262205570936203, "step": 254 }, { "epoch": 7.084507042253521, "grad_norm": 0.3057597754632391, "learning_rate": 9.561633779574372e-07, "loss": 0.2676515579223633, "step": 255 }, { "epoch": 7.112676056338028, "grad_norm": 0.2384413247157669, "learning_rate": 9.55824636882301e-07, "loss": 0.25623461604118347, "step": 256 }, { "epoch": 7.140845070422535, "grad_norm": 0.22577575110661233, "learning_rate": 9.554846595949413e-07, "loss": 0.25066760182380676, "step": 257 }, { "epoch": 7.169014084507042, "grad_norm": 0.22810299013323876, "learning_rate": 9.55143447130987e-07, "loss": 0.25772857666015625, "step": 258 }, { "epoch": 7.197183098591549, "grad_norm": 0.2866432998882861, "learning_rate": 9.54801000529831e-07, "loss": 0.25286948680877686, "step": 259 }, { "epoch": 7.225352112676056, "grad_norm": 0.27677955881524746, "learning_rate": 9.54457320834625e-07, "loss": 0.2480214238166809, "step": 260 }, { "epoch": 7.253521126760563, "grad_norm": 0.23561125478874487, "learning_rate": 9.54112409092277e-07, "loss": 0.273529589176178, "step": 261 }, { "epoch": 7.28169014084507, "grad_norm": 0.23173643804892863, "learning_rate": 9.537662663534477e-07, "loss": 0.2518290877342224, "step": 262 }, { "epoch": 7.309859154929577, "grad_norm": 0.2256175554720283, "learning_rate": 9.534188936725483e-07, "loss": 0.2571009695529938, "step": 263 }, { "epoch": 7.338028169014084, "grad_norm": 0.2355621515439768, "learning_rate": 9.530702921077358e-07, "loss": 0.25834065675735474, "step": 264 }, { "epoch": 7.366197183098592, "grad_norm": 0.2228326754230289, "learning_rate": 9.527204627209112e-07, "loss": 0.25286680459976196, "step": 265 }, { "epoch": 7.394366197183099, "grad_norm": 0.23194189643389376, "learning_rate": 9.523694065777156e-07, "loss": 0.2616320848464966, "step": 266 }, { "epoch": 7.422535211267606, "grad_norm": 0.23212710466470063, "learning_rate": 9.520171247475268e-07, "loss": 0.2550612688064575, "step": 267 }, { "epoch": 7.450704225352113, "grad_norm": 0.2630254038278628, "learning_rate": 9.516636183034564e-07, "loss": 0.2545396089553833, "step": 268 }, { "epoch": 7.47887323943662, "grad_norm": 0.22233881792271545, "learning_rate": 9.513088883223463e-07, "loss": 0.244547039270401, "step": 269 }, { "epoch": 7.507042253521127, "grad_norm": 0.24058852766292496, "learning_rate": 9.509529358847654e-07, "loss": 0.258344829082489, "step": 270 }, { "epoch": 7.535211267605634, "grad_norm": 0.2591231329098907, "learning_rate": 9.505957620750069e-07, "loss": 0.2509728670120239, "step": 271 }, { "epoch": 7.563380281690141, "grad_norm": 0.22516830746766386, "learning_rate": 9.502373679810839e-07, "loss": 0.260656476020813, "step": 272 }, { "epoch": 7.591549295774648, "grad_norm": 0.32992687123033926, "learning_rate": 9.49877754694727e-07, "loss": 0.2461855411529541, "step": 273 }, { "epoch": 7.619718309859155, "grad_norm": 0.22517930953114113, "learning_rate": 9.495169233113806e-07, "loss": 0.26402074098587036, "step": 274 }, { "epoch": 7.647887323943662, "grad_norm": 0.2303015677956865, "learning_rate": 9.491548749301997e-07, "loss": 0.2625475823879242, "step": 275 }, { "epoch": 7.676056338028169, "grad_norm": 0.24736115424944397, "learning_rate": 9.487916106540465e-07, "loss": 0.261366605758667, "step": 276 }, { "epoch": 7.704225352112676, "grad_norm": 0.3054635100649164, "learning_rate": 9.484271315894871e-07, "loss": 0.2583233714103699, "step": 277 }, { "epoch": 7.732394366197183, "grad_norm": 0.23888784253517656, "learning_rate": 9.480614388467877e-07, "loss": 0.26100364327430725, "step": 278 }, { "epoch": 7.76056338028169, "grad_norm": 0.23035518389984047, "learning_rate": 9.47694533539912e-07, "loss": 0.25427085161209106, "step": 279 }, { "epoch": 7.788732394366197, "grad_norm": 0.2397167748787147, "learning_rate": 9.473264167865171e-07, "loss": 0.26791495084762573, "step": 280 }, { "epoch": 7.816901408450704, "grad_norm": 0.2324670883748479, "learning_rate": 9.469570897079504e-07, "loss": 0.25854068994522095, "step": 281 }, { "epoch": 7.845070422535211, "grad_norm": 0.2407835066696354, "learning_rate": 9.465865534292464e-07, "loss": 0.25427621603012085, "step": 282 }, { "epoch": 7.873239436619718, "grad_norm": 0.24566208023836886, "learning_rate": 9.462148090791228e-07, "loss": 0.25798651576042175, "step": 283 }, { "epoch": 7.901408450704225, "grad_norm": 0.25230839039720004, "learning_rate": 9.458418577899774e-07, "loss": 0.2794758379459381, "step": 284 }, { "epoch": 7.929577464788732, "grad_norm": 0.22946111074733544, "learning_rate": 9.454677006978842e-07, "loss": 0.2522087097167969, "step": 285 }, { "epoch": 7.957746478873239, "grad_norm": 0.23483999818710283, "learning_rate": 9.450923389425911e-07, "loss": 0.24993300437927246, "step": 286 }, { "epoch": 7.985915492957746, "grad_norm": 0.23222784962960594, "learning_rate": 9.44715773667515e-07, "loss": 0.2578023672103882, "step": 287 }, { "epoch": 8.0, "grad_norm": 0.33496486871987224, "learning_rate": 9.443380060197385e-07, "loss": 0.2590055763721466, "step": 288 }, { "epoch": 8.028169014084508, "grad_norm": 0.22978114673982541, "learning_rate": 9.43959037150008e-07, "loss": 0.2533671259880066, "step": 289 }, { "epoch": 8.056338028169014, "grad_norm": 0.24537281724911067, "learning_rate": 9.43578868212728e-07, "loss": 0.2540019154548645, "step": 290 }, { "epoch": 8.084507042253522, "grad_norm": 0.23952878163512892, "learning_rate": 9.431975003659594e-07, "loss": 0.2519161105155945, "step": 291 }, { "epoch": 8.112676056338028, "grad_norm": 0.22410269302607416, "learning_rate": 9.428149347714143e-07, "loss": 0.2534847855567932, "step": 292 }, { "epoch": 8.140845070422536, "grad_norm": 0.22515357416422843, "learning_rate": 9.424311725944543e-07, "loss": 0.2480982393026352, "step": 293 }, { "epoch": 8.169014084507042, "grad_norm": 0.22463212198832308, "learning_rate": 9.420462150040852e-07, "loss": 0.25113674998283386, "step": 294 }, { "epoch": 8.19718309859155, "grad_norm": 0.24243654364581727, "learning_rate": 9.416600631729548e-07, "loss": 0.2588122487068176, "step": 295 }, { "epoch": 8.225352112676056, "grad_norm": 0.23662758753633675, "learning_rate": 9.412727182773486e-07, "loss": 0.2564491033554077, "step": 296 }, { "epoch": 8.253521126760564, "grad_norm": 0.22745130948641154, "learning_rate": 9.408841814971861e-07, "loss": 0.25671282410621643, "step": 297 }, { "epoch": 8.28169014084507, "grad_norm": 0.23421703627414328, "learning_rate": 9.404944540160177e-07, "loss": 0.25537922978401184, "step": 298 }, { "epoch": 8.309859154929578, "grad_norm": 0.25808749865907027, "learning_rate": 9.401035370210212e-07, "loss": 0.2609266936779022, "step": 299 }, { "epoch": 8.338028169014084, "grad_norm": 0.26628076978008886, "learning_rate": 9.397114317029974e-07, "loss": 0.26676198840141296, "step": 300 }, { "epoch": 8.366197183098592, "grad_norm": 0.24806292816726846, "learning_rate": 9.393181392563669e-07, "loss": 0.2629510462284088, "step": 301 }, { "epoch": 8.394366197183098, "grad_norm": 0.2450141484218029, "learning_rate": 9.38923660879167e-07, "loss": 0.24178162217140198, "step": 302 }, { "epoch": 8.422535211267606, "grad_norm": 0.22586508580682582, "learning_rate": 9.385279977730472e-07, "loss": 0.2511584460735321, "step": 303 }, { "epoch": 8.450704225352112, "grad_norm": 0.2351453280752253, "learning_rate": 9.381311511432658e-07, "loss": 0.2653919458389282, "step": 304 }, { "epoch": 8.47887323943662, "grad_norm": 0.241646635077158, "learning_rate": 9.377331221986866e-07, "loss": 0.24603968858718872, "step": 305 }, { "epoch": 8.507042253521126, "grad_norm": 0.2340015157165136, "learning_rate": 9.373339121517746e-07, "loss": 0.2578321695327759, "step": 306 }, { "epoch": 8.535211267605634, "grad_norm": 0.2545851654819562, "learning_rate": 9.36933522218593e-07, "loss": 0.2556232213973999, "step": 307 }, { "epoch": 8.56338028169014, "grad_norm": 0.2402873441824482, "learning_rate": 9.36531953618799e-07, "loss": 0.24149319529533386, "step": 308 }, { "epoch": 8.591549295774648, "grad_norm": 0.22732048023459145, "learning_rate": 9.361292075756401e-07, "loss": 0.2583070695400238, "step": 309 }, { "epoch": 8.619718309859154, "grad_norm": 0.23686044423247699, "learning_rate": 9.357252853159505e-07, "loss": 0.2552328407764435, "step": 310 }, { "epoch": 8.647887323943662, "grad_norm": 0.248000780112058, "learning_rate": 9.353201880701477e-07, "loss": 0.2555694878101349, "step": 311 }, { "epoch": 8.676056338028168, "grad_norm": 0.23819636245003398, "learning_rate": 9.34913917072228e-07, "loss": 0.2535495162010193, "step": 312 }, { "epoch": 8.704225352112676, "grad_norm": 0.23289151649857873, "learning_rate": 9.345064735597633e-07, "loss": 0.23895904421806335, "step": 313 }, { "epoch": 8.732394366197184, "grad_norm": 0.24456775846548265, "learning_rate": 9.340978587738972e-07, "loss": 0.24082013964653015, "step": 314 }, { "epoch": 8.76056338028169, "grad_norm": 0.24111494311817017, "learning_rate": 9.336880739593415e-07, "loss": 0.2520008683204651, "step": 315 }, { "epoch": 8.788732394366198, "grad_norm": 0.23455464565416306, "learning_rate": 9.332771203643714e-07, "loss": 0.24615193903446198, "step": 316 }, { "epoch": 8.816901408450704, "grad_norm": 0.23820264470002048, "learning_rate": 9.328649992408231e-07, "loss": 0.24194085597991943, "step": 317 }, { "epoch": 8.845070422535212, "grad_norm": 0.2509852236357078, "learning_rate": 9.324517118440888e-07, "loss": 0.2486490160226822, "step": 318 }, { "epoch": 8.873239436619718, "grad_norm": 0.2364300073153734, "learning_rate": 9.320372594331137e-07, "loss": 0.26214224100112915, "step": 319 }, { "epoch": 8.901408450704226, "grad_norm": 0.23707535806054583, "learning_rate": 9.316216432703916e-07, "loss": 0.2599393129348755, "step": 320 }, { "epoch": 8.929577464788732, "grad_norm": 0.2623964552394443, "learning_rate": 9.312048646219617e-07, "loss": 0.2490779161453247, "step": 321 }, { "epoch": 8.95774647887324, "grad_norm": 0.3409018820717708, "learning_rate": 9.307869247574038e-07, "loss": 0.24981269240379333, "step": 322 }, { "epoch": 8.985915492957746, "grad_norm": 0.23275952122730492, "learning_rate": 9.303678249498352e-07, "loss": 0.24256354570388794, "step": 323 }, { "epoch": 9.0, "grad_norm": 0.3314779892334818, "learning_rate": 9.299475664759068e-07, "loss": 0.2582060396671295, "step": 324 }, { "epoch": 9.028169014084508, "grad_norm": 0.22855183478172078, "learning_rate": 9.295261506157985e-07, "loss": 0.24924015998840332, "step": 325 }, { "epoch": 9.056338028169014, "grad_norm": 0.23011630291450727, "learning_rate": 9.291035786532163e-07, "loss": 0.24119523167610168, "step": 326 }, { "epoch": 9.084507042253522, "grad_norm": 0.25455626881208104, "learning_rate": 9.286798518753878e-07, "loss": 0.2545008659362793, "step": 327 }, { "epoch": 9.112676056338028, "grad_norm": 0.2470912179191389, "learning_rate": 9.282549715730579e-07, "loss": 0.25637179613113403, "step": 328 }, { "epoch": 9.140845070422536, "grad_norm": 0.2361076856223727, "learning_rate": 9.278289390404859e-07, "loss": 0.24920859932899475, "step": 329 }, { "epoch": 9.169014084507042, "grad_norm": 0.24962180209080553, "learning_rate": 9.274017555754407e-07, "loss": 0.25139665603637695, "step": 330 }, { "epoch": 9.19718309859155, "grad_norm": 0.2661403261625342, "learning_rate": 9.269734224791974e-07, "loss": 0.25162649154663086, "step": 331 }, { "epoch": 9.225352112676056, "grad_norm": 0.23321448395515867, "learning_rate": 9.265439410565328e-07, "loss": 0.2531318962574005, "step": 332 }, { "epoch": 9.253521126760564, "grad_norm": 0.2489447660723762, "learning_rate": 9.261133126157217e-07, "loss": 0.2439672201871872, "step": 333 }, { "epoch": 9.28169014084507, "grad_norm": 0.24654854069751458, "learning_rate": 9.256815384685328e-07, "loss": 0.24593070149421692, "step": 334 }, { "epoch": 9.309859154929578, "grad_norm": 0.24922607082895212, "learning_rate": 9.252486199302256e-07, "loss": 0.24202078580856323, "step": 335 }, { "epoch": 9.338028169014084, "grad_norm": 0.23810892907222608, "learning_rate": 9.248145583195447e-07, "loss": 0.24281273782253265, "step": 336 }, { "epoch": 9.366197183098592, "grad_norm": 0.2414836664150074, "learning_rate": 9.243793549587171e-07, "loss": 0.24529415369033813, "step": 337 }, { "epoch": 9.394366197183098, "grad_norm": 0.45146527719151147, "learning_rate": 9.239430111734476e-07, "loss": 0.24313722550868988, "step": 338 }, { "epoch": 9.422535211267606, "grad_norm": 0.2513687754640395, "learning_rate": 9.235055282929153e-07, "loss": 0.24014408886432648, "step": 339 }, { "epoch": 9.450704225352112, "grad_norm": 0.2464123403137622, "learning_rate": 9.230669076497687e-07, "loss": 0.25664836168289185, "step": 340 }, { "epoch": 9.47887323943662, "grad_norm": 0.25003507348604787, "learning_rate": 9.226271505801224e-07, "loss": 0.25439685583114624, "step": 341 }, { "epoch": 9.507042253521126, "grad_norm": 0.2460113899454725, "learning_rate": 9.221862584235526e-07, "loss": 0.2463434338569641, "step": 342 }, { "epoch": 9.535211267605634, "grad_norm": 0.29434373718545254, "learning_rate": 9.217442325230936e-07, "loss": 0.2347492277622223, "step": 343 }, { "epoch": 9.56338028169014, "grad_norm": 0.2426325292229501, "learning_rate": 9.213010742252327e-07, "loss": 0.2540351450443268, "step": 344 }, { "epoch": 9.591549295774648, "grad_norm": 0.23873379819321794, "learning_rate": 9.208567848799069e-07, "loss": 0.23636561632156372, "step": 345 }, { "epoch": 9.619718309859154, "grad_norm": 0.2536452901368959, "learning_rate": 9.204113658404989e-07, "loss": 0.2521906793117523, "step": 346 }, { "epoch": 9.647887323943662, "grad_norm": 0.23819082363894303, "learning_rate": 9.199648184638318e-07, "loss": 0.23743756115436554, "step": 347 }, { "epoch": 9.676056338028168, "grad_norm": 0.24809194025801815, "learning_rate": 9.195171441101668e-07, "loss": 0.2550021708011627, "step": 348 }, { "epoch": 9.704225352112676, "grad_norm": 0.2407861067961907, "learning_rate": 9.190683441431974e-07, "loss": 0.23909378051757812, "step": 349 }, { "epoch": 9.732394366197184, "grad_norm": 0.25194809703933585, "learning_rate": 9.186184199300463e-07, "loss": 0.2386261522769928, "step": 350 }, { "epoch": 9.76056338028169, "grad_norm": 0.3109079135054994, "learning_rate": 9.181673728412605e-07, "loss": 0.24811868369579315, "step": 351 }, { "epoch": 9.788732394366198, "grad_norm": 0.24849445193131672, "learning_rate": 9.177152042508077e-07, "loss": 0.24510633945465088, "step": 352 }, { "epoch": 9.816901408450704, "grad_norm": 0.25056831997285267, "learning_rate": 9.17261915536072e-07, "loss": 0.2476453185081482, "step": 353 }, { "epoch": 9.845070422535212, "grad_norm": 0.24753809085881498, "learning_rate": 9.168075080778494e-07, "loss": 0.24052247405052185, "step": 354 }, { "epoch": 9.873239436619718, "grad_norm": 0.27322821616611875, "learning_rate": 9.163519832603436e-07, "loss": 0.2500559687614441, "step": 355 }, { "epoch": 9.901408450704226, "grad_norm": 0.24879142424699366, "learning_rate": 9.158953424711624e-07, "loss": 0.26202425360679626, "step": 356 }, { "epoch": 9.929577464788732, "grad_norm": 0.2566208852525709, "learning_rate": 9.154375871013128e-07, "loss": 0.24967315793037415, "step": 357 }, { "epoch": 9.95774647887324, "grad_norm": 0.2544024404845266, "learning_rate": 9.149787185451969e-07, "loss": 0.25556012988090515, "step": 358 }, { "epoch": 9.985915492957746, "grad_norm": 0.2694091003451415, "learning_rate": 9.145187382006081e-07, "loss": 0.24726629257202148, "step": 359 }, { "epoch": 10.0, "grad_norm": 0.3663693099814081, "learning_rate": 9.140576474687263e-07, "loss": 0.26241111755371094, "step": 360 }, { "epoch": 10.028169014084508, "grad_norm": 0.23090643712953313, "learning_rate": 9.135954477541137e-07, "loss": 0.24851879477500916, "step": 361 }, { "epoch": 10.056338028169014, "grad_norm": 0.2616114206455057, "learning_rate": 9.131321404647109e-07, "loss": 0.25464296340942383, "step": 362 }, { "epoch": 10.084507042253522, "grad_norm": 1.0513495732621954, "learning_rate": 9.126677270118322e-07, "loss": 0.2508964538574219, "step": 363 }, { "epoch": 10.112676056338028, "grad_norm": 0.2430762392307408, "learning_rate": 9.122022088101613e-07, "loss": 0.23258915543556213, "step": 364 }, { "epoch": 10.140845070422536, "grad_norm": 0.2382764499634006, "learning_rate": 9.117355872777477e-07, "loss": 0.23789361119270325, "step": 365 }, { "epoch": 10.169014084507042, "grad_norm": 0.23857586756321417, "learning_rate": 9.112678638360015e-07, "loss": 0.2322252094745636, "step": 366 }, { "epoch": 10.19718309859155, "grad_norm": 0.24330523331980736, "learning_rate": 9.107990399096893e-07, "loss": 0.2315920889377594, "step": 367 }, { "epoch": 10.225352112676056, "grad_norm": 0.24433633894014556, "learning_rate": 9.103291169269299e-07, "loss": 0.2451440989971161, "step": 368 }, { "epoch": 10.253521126760564, "grad_norm": 0.24610806276364772, "learning_rate": 9.098580963191907e-07, "loss": 0.23949627578258514, "step": 369 }, { "epoch": 10.28169014084507, "grad_norm": 0.2523755182308413, "learning_rate": 9.093859795212817e-07, "loss": 0.255041241645813, "step": 370 }, { "epoch": 10.309859154929578, "grad_norm": 0.26254221360687513, "learning_rate": 9.089127679713529e-07, "loss": 0.24673743546009064, "step": 371 }, { "epoch": 10.338028169014084, "grad_norm": 0.2659551535025712, "learning_rate": 9.084384631108882e-07, "loss": 0.24092882871627808, "step": 372 }, { "epoch": 10.366197183098592, "grad_norm": 0.2498699583878038, "learning_rate": 9.079630663847031e-07, "loss": 0.25087377429008484, "step": 373 }, { "epoch": 10.394366197183098, "grad_norm": 0.24152932921989356, "learning_rate": 9.074865792409381e-07, "loss": 0.24652892351150513, "step": 374 }, { "epoch": 10.422535211267606, "grad_norm": 0.2975373111612133, "learning_rate": 9.070090031310558e-07, "loss": 0.24474310874938965, "step": 375 }, { "epoch": 10.450704225352112, "grad_norm": 0.24529378455418052, "learning_rate": 9.065303395098358e-07, "loss": 0.24984315037727356, "step": 376 }, { "epoch": 10.47887323943662, "grad_norm": 0.28844340433996196, "learning_rate": 9.060505898353705e-07, "loss": 0.2597285509109497, "step": 377 }, { "epoch": 10.507042253521126, "grad_norm": 0.2519686815558072, "learning_rate": 9.055697555690607e-07, "loss": 0.24229422211647034, "step": 378 }, { "epoch": 10.535211267605634, "grad_norm": 0.2540659099568006, "learning_rate": 9.050878381756107e-07, "loss": 0.24451278150081635, "step": 379 }, { "epoch": 10.56338028169014, "grad_norm": 0.25284268194412596, "learning_rate": 9.046048391230247e-07, "loss": 0.232026606798172, "step": 380 }, { "epoch": 10.591549295774648, "grad_norm": 0.2509160048760181, "learning_rate": 9.041207598826017e-07, "loss": 0.2384566068649292, "step": 381 }, { "epoch": 10.619718309859154, "grad_norm": 0.35519399545629293, "learning_rate": 9.036356019289309e-07, "loss": 0.24372628331184387, "step": 382 }, { "epoch": 10.647887323943662, "grad_norm": 0.2439787106834223, "learning_rate": 9.031493667398872e-07, "loss": 0.23376773297786713, "step": 383 }, { "epoch": 10.676056338028168, "grad_norm": 0.25658992692397564, "learning_rate": 9.026620557966279e-07, "loss": 0.2388392984867096, "step": 384 }, { "epoch": 10.704225352112676, "grad_norm": 0.2491570641039132, "learning_rate": 9.021736705835862e-07, "loss": 0.2429148256778717, "step": 385 }, { "epoch": 10.732394366197184, "grad_norm": 0.32073931464521355, "learning_rate": 9.016842125884684e-07, "loss": 0.22875139117240906, "step": 386 }, { "epoch": 10.76056338028169, "grad_norm": 0.2502280989278628, "learning_rate": 9.011936833022484e-07, "loss": 0.23325741291046143, "step": 387 }, { "epoch": 10.788732394366198, "grad_norm": 0.7429272352122884, "learning_rate": 9.007020842191634e-07, "loss": 0.25491032004356384, "step": 388 }, { "epoch": 10.816901408450704, "grad_norm": 0.25366909205038285, "learning_rate": 9.002094168367095e-07, "loss": 0.25390559434890747, "step": 389 }, { "epoch": 10.845070422535212, "grad_norm": 0.2532418479840136, "learning_rate": 8.997156826556369e-07, "loss": 0.239566832780838, "step": 390 }, { "epoch": 10.873239436619718, "grad_norm": 0.24862594273960315, "learning_rate": 8.992208831799456e-07, "loss": 0.24101951718330383, "step": 391 }, { "epoch": 10.901408450704226, "grad_norm": 0.36453597595458426, "learning_rate": 8.987250199168808e-07, "loss": 0.22447983920574188, "step": 392 }, { "epoch": 10.929577464788732, "grad_norm": 0.26909996327806845, "learning_rate": 8.982280943769278e-07, "loss": 0.24062535166740417, "step": 393 }, { "epoch": 10.95774647887324, "grad_norm": 0.2638850341939346, "learning_rate": 8.977301080738079e-07, "loss": 0.2585245966911316, "step": 394 }, { "epoch": 10.985915492957746, "grad_norm": 0.3097784840969631, "learning_rate": 8.97231062524474e-07, "loss": 0.2358318418264389, "step": 395 }, { "epoch": 11.0, "grad_norm": 0.3849386810629798, "learning_rate": 8.967309592491052e-07, "loss": 0.25533783435821533, "step": 396 }, { "epoch": 11.028169014084508, "grad_norm": 0.26256476010695584, "learning_rate": 8.962297997711027e-07, "loss": 0.22924092411994934, "step": 397 }, { "epoch": 11.056338028169014, "grad_norm": 0.2639241753105924, "learning_rate": 8.957275856170855e-07, "loss": 0.24100372195243835, "step": 398 }, { "epoch": 11.084507042253522, "grad_norm": 0.298152727306937, "learning_rate": 8.952243183168848e-07, "loss": 0.24404382705688477, "step": 399 }, { "epoch": 11.112676056338028, "grad_norm": 0.2702268162010949, "learning_rate": 8.9471999940354e-07, "loss": 0.23476135730743408, "step": 400 }, { "epoch": 11.140845070422536, "grad_norm": 0.38346237984716247, "learning_rate": 8.942146304132943e-07, "loss": 0.2230163812637329, "step": 401 }, { "epoch": 11.169014084507042, "grad_norm": 0.30719276755462255, "learning_rate": 8.937082128855891e-07, "loss": 0.24640659987926483, "step": 402 }, { "epoch": 11.19718309859155, "grad_norm": 0.2522559076259691, "learning_rate": 8.932007483630596e-07, "loss": 0.2337941825389862, "step": 403 }, { "epoch": 11.225352112676056, "grad_norm": 0.2811477850391036, "learning_rate": 8.926922383915315e-07, "loss": 0.24217446148395538, "step": 404 }, { "epoch": 11.253521126760564, "grad_norm": 0.2937577324495388, "learning_rate": 8.921826845200138e-07, "loss": 0.23650123178958893, "step": 405 }, { "epoch": 11.28169014084507, "grad_norm": 0.2665251490542768, "learning_rate": 8.916720883006963e-07, "loss": 0.23723018169403076, "step": 406 }, { "epoch": 11.309859154929578, "grad_norm": 0.2577956520635811, "learning_rate": 8.911604512889434e-07, "loss": 0.23821580410003662, "step": 407 }, { "epoch": 11.338028169014084, "grad_norm": 0.2747361963021525, "learning_rate": 8.906477750432903e-07, "loss": 0.23665378987789154, "step": 408 }, { "epoch": 11.366197183098592, "grad_norm": 0.36401043696800917, "learning_rate": 8.901340611254378e-07, "loss": 0.24189358949661255, "step": 409 }, { "epoch": 11.394366197183098, "grad_norm": 0.2520809121047697, "learning_rate": 8.896193111002475e-07, "loss": 0.2461044192314148, "step": 410 }, { "epoch": 11.422535211267606, "grad_norm": 0.2762514295319336, "learning_rate": 8.891035265357371e-07, "loss": 0.22839877009391785, "step": 411 }, { "epoch": 11.450704225352112, "grad_norm": 0.2766703038586183, "learning_rate": 8.88586709003076e-07, "loss": 0.2436380237340927, "step": 412 }, { "epoch": 11.47887323943662, "grad_norm": 0.25607243680163955, "learning_rate": 8.8806886007658e-07, "loss": 0.24581144750118256, "step": 413 }, { "epoch": 11.507042253521126, "grad_norm": 0.25612907513591854, "learning_rate": 8.875499813337067e-07, "loss": 0.24154463410377502, "step": 414 }, { "epoch": 11.535211267605634, "grad_norm": 0.26351210813960735, "learning_rate": 8.87030074355051e-07, "loss": 0.23528064787387848, "step": 415 }, { "epoch": 11.56338028169014, "grad_norm": 0.25456237789297487, "learning_rate": 8.865091407243394e-07, "loss": 0.23557059466838837, "step": 416 }, { "epoch": 11.591549295774648, "grad_norm": 0.26763665810579157, "learning_rate": 8.859871820284261e-07, "loss": 0.2497173398733139, "step": 417 }, { "epoch": 11.619718309859154, "grad_norm": 0.47514856857684123, "learning_rate": 8.85464199857288e-07, "loss": 0.24749311804771423, "step": 418 }, { "epoch": 11.647887323943662, "grad_norm": 0.5410123563974302, "learning_rate": 8.849401958040192e-07, "loss": 0.2356778383255005, "step": 419 }, { "epoch": 11.676056338028168, "grad_norm": 0.2597674855652335, "learning_rate": 8.844151714648274e-07, "loss": 0.24779964983463287, "step": 420 }, { "epoch": 11.704225352112676, "grad_norm": 0.26052872396427884, "learning_rate": 8.838891284390273e-07, "loss": 0.24069969356060028, "step": 421 }, { "epoch": 11.732394366197184, "grad_norm": 0.24768122719136823, "learning_rate": 8.833620683290375e-07, "loss": 0.23677203059196472, "step": 422 }, { "epoch": 11.76056338028169, "grad_norm": 0.2673480579083074, "learning_rate": 8.828339927403745e-07, "loss": 0.23263472318649292, "step": 423 }, { "epoch": 11.788732394366198, "grad_norm": 0.2542699067266434, "learning_rate": 8.823049032816478e-07, "loss": 0.23910850286483765, "step": 424 }, { "epoch": 11.816901408450704, "grad_norm": 0.2623369584647608, "learning_rate": 8.817748015645558e-07, "loss": 0.23500274121761322, "step": 425 }, { "epoch": 11.845070422535212, "grad_norm": 0.2741171560352947, "learning_rate": 8.812436892038805e-07, "loss": 0.2363435924053192, "step": 426 }, { "epoch": 11.873239436619718, "grad_norm": 0.2764265991901865, "learning_rate": 8.807115678174819e-07, "loss": 0.23622967302799225, "step": 427 }, { "epoch": 11.901408450704226, "grad_norm": 0.26408384561026765, "learning_rate": 8.801784390262943e-07, "loss": 0.2463335543870926, "step": 428 }, { "epoch": 11.929577464788732, "grad_norm": 0.2675833299403756, "learning_rate": 8.796443044543203e-07, "loss": 0.23592045903205872, "step": 429 }, { "epoch": 11.95774647887324, "grad_norm": 0.2992956465951693, "learning_rate": 8.791091657286267e-07, "loss": 0.23169052600860596, "step": 430 }, { "epoch": 11.985915492957746, "grad_norm": 0.25981524018584473, "learning_rate": 8.785730244793386e-07, "loss": 0.2329520881175995, "step": 431 }, { "epoch": 12.0, "grad_norm": 0.3813833592995728, "learning_rate": 8.780358823396352e-07, "loss": 0.24386751651763916, "step": 432 } ], "logging_steps": 1, "max_steps": 1800, "num_input_tokens_seen": 0, "num_train_epochs": 50, "save_steps": 1.0, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 261065740386304.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }