{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 939, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.003194888178913738, "grad_norm": 6.409714948226888, "learning_rate": 1.0638297872340426e-07, "loss": 0.9383, "step": 1 }, { "epoch": 0.006389776357827476, "grad_norm": 5.882820413352701, "learning_rate": 2.1276595744680852e-07, "loss": 0.8501, "step": 2 }, { "epoch": 0.009584664536741214, "grad_norm": 5.957247801225133, "learning_rate": 3.1914893617021275e-07, "loss": 0.8875, "step": 3 }, { "epoch": 0.012779552715654952, "grad_norm": 5.724998203884164, "learning_rate": 4.2553191489361704e-07, "loss": 0.8129, "step": 4 }, { "epoch": 0.01597444089456869, "grad_norm": 6.23206077824922, "learning_rate": 5.319148936170213e-07, "loss": 0.8894, "step": 5 }, { "epoch": 0.019169329073482427, "grad_norm": 6.15372248339717, "learning_rate": 6.382978723404255e-07, "loss": 0.8576, "step": 6 }, { "epoch": 0.022364217252396165, "grad_norm": 6.07845232983042, "learning_rate": 7.446808510638298e-07, "loss": 0.8891, "step": 7 }, { "epoch": 0.025559105431309903, "grad_norm": 5.63391011618048, "learning_rate": 8.510638297872341e-07, "loss": 0.8551, "step": 8 }, { "epoch": 0.02875399361022364, "grad_norm": 5.534522933447544, "learning_rate": 9.574468085106384e-07, "loss": 0.8428, "step": 9 }, { "epoch": 0.03194888178913738, "grad_norm": 5.418239884527311, "learning_rate": 1.0638297872340427e-06, "loss": 0.8059, "step": 10 }, { "epoch": 0.03514376996805112, "grad_norm": 4.9589364905240805, "learning_rate": 1.170212765957447e-06, "loss": 0.8492, "step": 11 }, { "epoch": 0.038338658146964855, "grad_norm": 4.799766698395383, "learning_rate": 1.276595744680851e-06, "loss": 0.879, "step": 12 }, { "epoch": 0.04153354632587859, "grad_norm": 4.519154133051823, "learning_rate": 1.3829787234042555e-06, "loss": 0.824, "step": 13 }, { "epoch": 0.04472843450479233, "grad_norm": 2.836911275221638, "learning_rate": 1.4893617021276596e-06, "loss": 0.7959, "step": 14 }, { "epoch": 0.04792332268370607, "grad_norm": 2.436716671685153, "learning_rate": 1.595744680851064e-06, "loss": 0.7458, "step": 15 }, { "epoch": 0.051118210862619806, "grad_norm": 2.5306910044508966, "learning_rate": 1.7021276595744682e-06, "loss": 0.7691, "step": 16 }, { "epoch": 0.054313099041533544, "grad_norm": 2.223202815090778, "learning_rate": 1.8085106382978727e-06, "loss": 0.7256, "step": 17 }, { "epoch": 0.05750798722044728, "grad_norm": 2.0892129964533477, "learning_rate": 1.9148936170212767e-06, "loss": 0.7825, "step": 18 }, { "epoch": 0.06070287539936102, "grad_norm": 2.4490319759010633, "learning_rate": 2.021276595744681e-06, "loss": 0.7727, "step": 19 }, { "epoch": 0.06389776357827476, "grad_norm": 2.8593345098103855, "learning_rate": 2.1276595744680853e-06, "loss": 0.7154, "step": 20 }, { "epoch": 0.0670926517571885, "grad_norm": 2.9984640074592877, "learning_rate": 2.2340425531914894e-06, "loss": 0.7033, "step": 21 }, { "epoch": 0.07028753993610223, "grad_norm": 2.81387823783635, "learning_rate": 2.340425531914894e-06, "loss": 0.6523, "step": 22 }, { "epoch": 0.07348242811501597, "grad_norm": 3.018564967672109, "learning_rate": 2.446808510638298e-06, "loss": 0.7746, "step": 23 }, { "epoch": 0.07667731629392971, "grad_norm": 2.856610406420041, "learning_rate": 2.553191489361702e-06, "loss": 0.7548, "step": 24 }, { "epoch": 0.07987220447284345, "grad_norm": 2.331383834536258, "learning_rate": 2.6595744680851065e-06, "loss": 0.6684, "step": 25 }, { "epoch": 0.08306709265175719, "grad_norm": 2.1989383298002485, "learning_rate": 2.765957446808511e-06, "loss": 0.7405, "step": 26 }, { "epoch": 0.08626198083067092, "grad_norm": 1.5941806085953258, "learning_rate": 2.8723404255319155e-06, "loss": 0.6736, "step": 27 }, { "epoch": 0.08945686900958466, "grad_norm": 1.5505780124124287, "learning_rate": 2.978723404255319e-06, "loss": 0.6973, "step": 28 }, { "epoch": 0.0926517571884984, "grad_norm": 1.4789842434436071, "learning_rate": 3.0851063829787237e-06, "loss": 0.7071, "step": 29 }, { "epoch": 0.09584664536741214, "grad_norm": 1.3346837979890005, "learning_rate": 3.191489361702128e-06, "loss": 0.6911, "step": 30 }, { "epoch": 0.09904153354632587, "grad_norm": 1.4475279708550588, "learning_rate": 3.297872340425532e-06, "loss": 0.6605, "step": 31 }, { "epoch": 0.10223642172523961, "grad_norm": 1.5471942641165661, "learning_rate": 3.4042553191489363e-06, "loss": 0.6891, "step": 32 }, { "epoch": 0.10543130990415335, "grad_norm": 1.2336120130098014, "learning_rate": 3.510638297872341e-06, "loss": 0.6334, "step": 33 }, { "epoch": 0.10862619808306709, "grad_norm": 1.2579672960093606, "learning_rate": 3.6170212765957453e-06, "loss": 0.6557, "step": 34 }, { "epoch": 0.11182108626198083, "grad_norm": 1.2231859178637319, "learning_rate": 3.723404255319149e-06, "loss": 0.6491, "step": 35 }, { "epoch": 0.11501597444089456, "grad_norm": 1.1385946023643831, "learning_rate": 3.8297872340425535e-06, "loss": 0.5842, "step": 36 }, { "epoch": 0.1182108626198083, "grad_norm": 0.9165940060653626, "learning_rate": 3.936170212765958e-06, "loss": 0.6432, "step": 37 }, { "epoch": 0.12140575079872204, "grad_norm": 1.0311853588560047, "learning_rate": 4.042553191489362e-06, "loss": 0.6392, "step": 38 }, { "epoch": 0.12460063897763578, "grad_norm": 1.1972768617611755, "learning_rate": 4.148936170212766e-06, "loss": 0.6042, "step": 39 }, { "epoch": 0.12779552715654952, "grad_norm": 1.1467995823095627, "learning_rate": 4.255319148936171e-06, "loss": 0.5756, "step": 40 }, { "epoch": 0.13099041533546327, "grad_norm": 1.2232522924355278, "learning_rate": 4.361702127659575e-06, "loss": 0.6, "step": 41 }, { "epoch": 0.134185303514377, "grad_norm": 0.9926550062713587, "learning_rate": 4.468085106382979e-06, "loss": 0.6201, "step": 42 }, { "epoch": 0.13738019169329074, "grad_norm": 0.9837243414486642, "learning_rate": 4.574468085106383e-06, "loss": 0.6119, "step": 43 }, { "epoch": 0.14057507987220447, "grad_norm": 0.7421864380116049, "learning_rate": 4.680851063829788e-06, "loss": 0.5856, "step": 44 }, { "epoch": 0.14376996805111822, "grad_norm": 0.9035767642840998, "learning_rate": 4.787234042553192e-06, "loss": 0.6272, "step": 45 }, { "epoch": 0.14696485623003194, "grad_norm": 1.0213511082377889, "learning_rate": 4.893617021276596e-06, "loss": 0.5995, "step": 46 }, { "epoch": 0.1501597444089457, "grad_norm": 0.8830146417372309, "learning_rate": 5e-06, "loss": 0.6345, "step": 47 }, { "epoch": 0.15335463258785942, "grad_norm": 0.791319537107259, "learning_rate": 5.106382978723404e-06, "loss": 0.6101, "step": 48 }, { "epoch": 0.15654952076677317, "grad_norm": 0.8284190199994919, "learning_rate": 5.212765957446809e-06, "loss": 0.6044, "step": 49 }, { "epoch": 0.1597444089456869, "grad_norm": 0.9510398823607971, "learning_rate": 5.319148936170213e-06, "loss": 0.5714, "step": 50 }, { "epoch": 0.16293929712460065, "grad_norm": 0.9998952434573138, "learning_rate": 5.425531914893617e-06, "loss": 0.6129, "step": 51 }, { "epoch": 0.16613418530351437, "grad_norm": 0.9860559729186523, "learning_rate": 5.531914893617022e-06, "loss": 0.6297, "step": 52 }, { "epoch": 0.16932907348242812, "grad_norm": 0.9463323345389851, "learning_rate": 5.638297872340426e-06, "loss": 0.5753, "step": 53 }, { "epoch": 0.17252396166134185, "grad_norm": 0.8257562888308732, "learning_rate": 5.744680851063831e-06, "loss": 0.5689, "step": 54 }, { "epoch": 0.1757188498402556, "grad_norm": 0.9121399111640456, "learning_rate": 5.851063829787235e-06, "loss": 0.5864, "step": 55 }, { "epoch": 0.17891373801916932, "grad_norm": 0.7597161760676522, "learning_rate": 5.957446808510638e-06, "loss": 0.549, "step": 56 }, { "epoch": 0.18210862619808307, "grad_norm": 1.0158634395768724, "learning_rate": 6.063829787234044e-06, "loss": 0.5829, "step": 57 }, { "epoch": 0.1853035143769968, "grad_norm": 0.8684762573966118, "learning_rate": 6.170212765957447e-06, "loss": 0.5608, "step": 58 }, { "epoch": 0.18849840255591055, "grad_norm": 0.8595474370965593, "learning_rate": 6.276595744680851e-06, "loss": 0.5806, "step": 59 }, { "epoch": 0.19169329073482427, "grad_norm": 0.8573534321100813, "learning_rate": 6.382978723404256e-06, "loss": 0.5736, "step": 60 }, { "epoch": 0.19488817891373802, "grad_norm": 0.8739703998606017, "learning_rate": 6.48936170212766e-06, "loss": 0.5716, "step": 61 }, { "epoch": 0.19808306709265175, "grad_norm": 0.8937605093917412, "learning_rate": 6.595744680851064e-06, "loss": 0.5287, "step": 62 }, { "epoch": 0.2012779552715655, "grad_norm": 0.7969931244942438, "learning_rate": 6.702127659574469e-06, "loss": 0.5664, "step": 63 }, { "epoch": 0.20447284345047922, "grad_norm": 0.7915012047099632, "learning_rate": 6.808510638297873e-06, "loss": 0.5622, "step": 64 }, { "epoch": 0.20766773162939298, "grad_norm": 0.8806575952893214, "learning_rate": 6.914893617021278e-06, "loss": 0.5966, "step": 65 }, { "epoch": 0.2108626198083067, "grad_norm": 0.973404020541715, "learning_rate": 7.021276595744682e-06, "loss": 0.5325, "step": 66 }, { "epoch": 0.21405750798722045, "grad_norm": 0.8197327493931416, "learning_rate": 7.127659574468085e-06, "loss": 0.5378, "step": 67 }, { "epoch": 0.21725239616613418, "grad_norm": 0.8154232260544038, "learning_rate": 7.234042553191491e-06, "loss": 0.5294, "step": 68 }, { "epoch": 0.22044728434504793, "grad_norm": 0.8048146414091009, "learning_rate": 7.340425531914894e-06, "loss": 0.5835, "step": 69 }, { "epoch": 0.22364217252396165, "grad_norm": 0.9431792825447465, "learning_rate": 7.446808510638298e-06, "loss": 0.6016, "step": 70 }, { "epoch": 0.2268370607028754, "grad_norm": 0.9042800238596417, "learning_rate": 7.553191489361703e-06, "loss": 0.5148, "step": 71 }, { "epoch": 0.23003194888178913, "grad_norm": 0.7370561189551593, "learning_rate": 7.659574468085107e-06, "loss": 0.5407, "step": 72 }, { "epoch": 0.23322683706070288, "grad_norm": 0.8525656922874479, "learning_rate": 7.765957446808511e-06, "loss": 0.541, "step": 73 }, { "epoch": 0.2364217252396166, "grad_norm": 0.8221124716437727, "learning_rate": 7.872340425531916e-06, "loss": 0.5215, "step": 74 }, { "epoch": 0.23961661341853036, "grad_norm": 0.777647704665899, "learning_rate": 7.97872340425532e-06, "loss": 0.5259, "step": 75 }, { "epoch": 0.24281150159744408, "grad_norm": 0.7599909140676149, "learning_rate": 8.085106382978723e-06, "loss": 0.5485, "step": 76 }, { "epoch": 0.24600638977635783, "grad_norm": 0.685227020557745, "learning_rate": 8.191489361702128e-06, "loss": 0.498, "step": 77 }, { "epoch": 0.24920127795527156, "grad_norm": 0.8431319429416056, "learning_rate": 8.297872340425532e-06, "loss": 0.5384, "step": 78 }, { "epoch": 0.2523961661341853, "grad_norm": 0.8795817172427665, "learning_rate": 8.404255319148937e-06, "loss": 0.5514, "step": 79 }, { "epoch": 0.25559105431309903, "grad_norm": 0.8078101765493096, "learning_rate": 8.510638297872341e-06, "loss": 0.5093, "step": 80 }, { "epoch": 0.25878594249201275, "grad_norm": 0.7660885386250705, "learning_rate": 8.617021276595746e-06, "loss": 0.5594, "step": 81 }, { "epoch": 0.26198083067092653, "grad_norm": 0.8652722799288994, "learning_rate": 8.72340425531915e-06, "loss": 0.5729, "step": 82 }, { "epoch": 0.26517571884984026, "grad_norm": 0.8601708327765593, "learning_rate": 8.829787234042555e-06, "loss": 0.5233, "step": 83 }, { "epoch": 0.268370607028754, "grad_norm": 0.8309693856068712, "learning_rate": 8.936170212765958e-06, "loss": 0.4808, "step": 84 }, { "epoch": 0.2715654952076677, "grad_norm": 0.9088041717182157, "learning_rate": 9.042553191489362e-06, "loss": 0.5767, "step": 85 }, { "epoch": 0.2747603833865815, "grad_norm": 0.908456866251118, "learning_rate": 9.148936170212767e-06, "loss": 0.5543, "step": 86 }, { "epoch": 0.2779552715654952, "grad_norm": 0.9219476257453414, "learning_rate": 9.255319148936171e-06, "loss": 0.5555, "step": 87 }, { "epoch": 0.28115015974440893, "grad_norm": 0.9639792987268722, "learning_rate": 9.361702127659576e-06, "loss": 0.5871, "step": 88 }, { "epoch": 0.28434504792332266, "grad_norm": 0.9084931124261426, "learning_rate": 9.46808510638298e-06, "loss": 0.4884, "step": 89 }, { "epoch": 0.28753993610223644, "grad_norm": 0.7606675941137307, "learning_rate": 9.574468085106385e-06, "loss": 0.5232, "step": 90 }, { "epoch": 0.29073482428115016, "grad_norm": 1.1309944787796808, "learning_rate": 9.680851063829787e-06, "loss": 0.5364, "step": 91 }, { "epoch": 0.2939297124600639, "grad_norm": 1.0148322322106438, "learning_rate": 9.787234042553192e-06, "loss": 0.502, "step": 92 }, { "epoch": 0.2971246006389776, "grad_norm": 0.8194146060783313, "learning_rate": 9.893617021276596e-06, "loss": 0.5379, "step": 93 }, { "epoch": 0.3003194888178914, "grad_norm": 0.9444330231028176, "learning_rate": 1e-05, "loss": 0.5857, "step": 94 }, { "epoch": 0.3035143769968051, "grad_norm": 1.0778206337140743, "learning_rate": 9.999965443811378e-06, "loss": 0.5236, "step": 95 }, { "epoch": 0.30670926517571884, "grad_norm": 1.0986290906153802, "learning_rate": 9.999861775723162e-06, "loss": 0.5526, "step": 96 }, { "epoch": 0.30990415335463256, "grad_norm": 0.9078029833378195, "learning_rate": 9.999688997168301e-06, "loss": 0.518, "step": 97 }, { "epoch": 0.31309904153354634, "grad_norm": 1.002162501813825, "learning_rate": 9.999447110535026e-06, "loss": 0.5433, "step": 98 }, { "epoch": 0.31629392971246006, "grad_norm": 1.0679692282792004, "learning_rate": 9.999136119166803e-06, "loss": 0.5233, "step": 99 }, { "epoch": 0.3194888178913738, "grad_norm": 0.9013455224092123, "learning_rate": 9.998756027362308e-06, "loss": 0.5787, "step": 100 }, { "epoch": 0.3226837060702875, "grad_norm": 0.9715869077223206, "learning_rate": 9.99830684037535e-06, "loss": 0.5398, "step": 101 }, { "epoch": 0.3258785942492013, "grad_norm": 1.0246249595859571, "learning_rate": 9.9977885644148e-06, "loss": 0.5612, "step": 102 }, { "epoch": 0.329073482428115, "grad_norm": 0.9640732938631273, "learning_rate": 9.997201206644522e-06, "loss": 0.506, "step": 103 }, { "epoch": 0.33226837060702874, "grad_norm": 0.8481753728957393, "learning_rate": 9.99654477518325e-06, "loss": 0.5465, "step": 104 }, { "epoch": 0.3354632587859425, "grad_norm": 1.0785966848337503, "learning_rate": 9.995819279104494e-06, "loss": 0.5071, "step": 105 }, { "epoch": 0.33865814696485624, "grad_norm": 0.9621589109623367, "learning_rate": 9.995024728436402e-06, "loss": 0.5008, "step": 106 }, { "epoch": 0.34185303514376997, "grad_norm": 0.9742254294374358, "learning_rate": 9.994161134161635e-06, "loss": 0.5627, "step": 107 }, { "epoch": 0.3450479233226837, "grad_norm": 0.9339518708258924, "learning_rate": 9.993228508217201e-06, "loss": 0.5221, "step": 108 }, { "epoch": 0.34824281150159747, "grad_norm": 0.8352060269189646, "learning_rate": 9.9922268634943e-06, "loss": 0.5327, "step": 109 }, { "epoch": 0.3514376996805112, "grad_norm": 0.9672282064745698, "learning_rate": 9.991156213838143e-06, "loss": 0.5285, "step": 110 }, { "epoch": 0.3546325878594249, "grad_norm": 0.9928070546447347, "learning_rate": 9.990016574047757e-06, "loss": 0.6163, "step": 111 }, { "epoch": 0.35782747603833864, "grad_norm": 0.980621046187048, "learning_rate": 9.988807959875785e-06, "loss": 0.5783, "step": 112 }, { "epoch": 0.3610223642172524, "grad_norm": 0.9698153125433151, "learning_rate": 9.987530388028269e-06, "loss": 0.5686, "step": 113 }, { "epoch": 0.36421725239616615, "grad_norm": 0.9660154212525479, "learning_rate": 9.986183876164412e-06, "loss": 0.6109, "step": 114 }, { "epoch": 0.36741214057507987, "grad_norm": 0.9000420730099195, "learning_rate": 9.984768442896342e-06, "loss": 0.4905, "step": 115 }, { "epoch": 0.3706070287539936, "grad_norm": 0.8723111757350182, "learning_rate": 9.983284107788852e-06, "loss": 0.5219, "step": 116 }, { "epoch": 0.3738019169329074, "grad_norm": 0.8504971094012811, "learning_rate": 9.981730891359123e-06, "loss": 0.4976, "step": 117 }, { "epoch": 0.3769968051118211, "grad_norm": 0.83454729499801, "learning_rate": 9.980108815076456e-06, "loss": 0.518, "step": 118 }, { "epoch": 0.3801916932907348, "grad_norm": 0.8907660506902001, "learning_rate": 9.978417901361958e-06, "loss": 0.5111, "step": 119 }, { "epoch": 0.38338658146964855, "grad_norm": 0.8962456117326467, "learning_rate": 9.976658173588244e-06, "loss": 0.5197, "step": 120 }, { "epoch": 0.3865814696485623, "grad_norm": 0.8723572110377498, "learning_rate": 9.974829656079106e-06, "loss": 0.5394, "step": 121 }, { "epoch": 0.38977635782747605, "grad_norm": 1.0284398448699272, "learning_rate": 9.972932374109184e-06, "loss": 0.5117, "step": 122 }, { "epoch": 0.3929712460063898, "grad_norm": 0.831752579591158, "learning_rate": 9.97096635390361e-06, "loss": 0.5527, "step": 123 }, { "epoch": 0.3961661341853035, "grad_norm": 0.8332127211329551, "learning_rate": 9.968931622637652e-06, "loss": 0.5466, "step": 124 }, { "epoch": 0.3993610223642173, "grad_norm": 0.9889873759146678, "learning_rate": 9.966828208436332e-06, "loss": 0.5412, "step": 125 }, { "epoch": 0.402555910543131, "grad_norm": 0.9280680742855908, "learning_rate": 9.96465614037404e-06, "loss": 0.602, "step": 126 }, { "epoch": 0.4057507987220447, "grad_norm": 0.8293097370353433, "learning_rate": 9.962415448474134e-06, "loss": 0.5469, "step": 127 }, { "epoch": 0.40894568690095845, "grad_norm": 0.7617699546730983, "learning_rate": 9.960106163708522e-06, "loss": 0.5003, "step": 128 }, { "epoch": 0.41214057507987223, "grad_norm": 0.9666132086437509, "learning_rate": 9.95772831799724e-06, "loss": 0.5305, "step": 129 }, { "epoch": 0.41533546325878595, "grad_norm": 0.8515196546140202, "learning_rate": 9.955281944207998e-06, "loss": 0.5667, "step": 130 }, { "epoch": 0.4185303514376997, "grad_norm": 0.8268237405590374, "learning_rate": 9.95276707615574e-06, "loss": 0.5512, "step": 131 }, { "epoch": 0.4217252396166134, "grad_norm": 0.8399302374244939, "learning_rate": 9.950183748602164e-06, "loss": 0.5074, "step": 132 }, { "epoch": 0.4249201277955272, "grad_norm": 0.798796366583729, "learning_rate": 9.947531997255256e-06, "loss": 0.5252, "step": 133 }, { "epoch": 0.4281150159744409, "grad_norm": 0.8461211398114474, "learning_rate": 9.944811858768782e-06, "loss": 0.5889, "step": 134 }, { "epoch": 0.43130990415335463, "grad_norm": 0.8645072380749989, "learning_rate": 9.94202337074179e-06, "loss": 0.532, "step": 135 }, { "epoch": 0.43450479233226835, "grad_norm": 0.7905196447402825, "learning_rate": 9.939166571718086e-06, "loss": 0.5234, "step": 136 }, { "epoch": 0.43769968051118213, "grad_norm": 0.8422357866045145, "learning_rate": 9.936241501185706e-06, "loss": 0.5283, "step": 137 }, { "epoch": 0.44089456869009586, "grad_norm": 0.9541587953845362, "learning_rate": 9.933248199576366e-06, "loss": 0.5404, "step": 138 }, { "epoch": 0.4440894568690096, "grad_norm": 0.8496124061447565, "learning_rate": 9.930186708264902e-06, "loss": 0.5509, "step": 139 }, { "epoch": 0.4472843450479233, "grad_norm": 0.9820024145545019, "learning_rate": 9.927057069568704e-06, "loss": 0.5155, "step": 140 }, { "epoch": 0.4504792332268371, "grad_norm": 0.8320575514975224, "learning_rate": 9.923859326747125e-06, "loss": 0.5829, "step": 141 }, { "epoch": 0.4536741214057508, "grad_norm": 0.7831612160017987, "learning_rate": 9.920593524000887e-06, "loss": 0.52, "step": 142 }, { "epoch": 0.45686900958466453, "grad_norm": 0.840014154368057, "learning_rate": 9.917259706471469e-06, "loss": 0.5283, "step": 143 }, { "epoch": 0.46006389776357826, "grad_norm": 0.9362051002065757, "learning_rate": 9.913857920240481e-06, "loss": 0.5155, "step": 144 }, { "epoch": 0.46325878594249204, "grad_norm": 0.8512954379893516, "learning_rate": 9.91038821232903e-06, "loss": 0.5403, "step": 145 }, { "epoch": 0.46645367412140576, "grad_norm": 0.7839424808363111, "learning_rate": 9.906850630697068e-06, "loss": 0.5234, "step": 146 }, { "epoch": 0.4696485623003195, "grad_norm": 0.8648328590724287, "learning_rate": 9.903245224242732e-06, "loss": 0.5187, "step": 147 }, { "epoch": 0.4728434504792332, "grad_norm": 0.8792377942973435, "learning_rate": 9.899572042801662e-06, "loss": 0.5577, "step": 148 }, { "epoch": 0.476038338658147, "grad_norm": 0.8925497509434575, "learning_rate": 9.895831137146319e-06, "loss": 0.5622, "step": 149 }, { "epoch": 0.4792332268370607, "grad_norm": 0.8150179359015267, "learning_rate": 9.89202255898528e-06, "loss": 0.4704, "step": 150 }, { "epoch": 0.48242811501597443, "grad_norm": 0.9444671033438701, "learning_rate": 9.888146360962523e-06, "loss": 0.5426, "step": 151 }, { "epoch": 0.48562300319488816, "grad_norm": 0.8751489294460165, "learning_rate": 9.8842025966567e-06, "loss": 0.5051, "step": 152 }, { "epoch": 0.48881789137380194, "grad_norm": 0.8540535350580652, "learning_rate": 9.880191320580396e-06, "loss": 0.5203, "step": 153 }, { "epoch": 0.49201277955271566, "grad_norm": 0.9280441125692708, "learning_rate": 9.876112588179378e-06, "loss": 0.5137, "step": 154 }, { "epoch": 0.4952076677316294, "grad_norm": 0.8596304256499511, "learning_rate": 9.87196645583182e-06, "loss": 0.5207, "step": 155 }, { "epoch": 0.4984025559105431, "grad_norm": 0.9988776485113224, "learning_rate": 9.86775298084754e-06, "loss": 0.5505, "step": 156 }, { "epoch": 0.5015974440894568, "grad_norm": 0.8471613181896762, "learning_rate": 9.863472221467189e-06, "loss": 0.474, "step": 157 }, { "epoch": 0.5047923322683706, "grad_norm": 0.9539587230629798, "learning_rate": 9.85912423686146e-06, "loss": 0.4911, "step": 158 }, { "epoch": 0.5079872204472844, "grad_norm": 0.8978617942444193, "learning_rate": 9.854709087130261e-06, "loss": 0.5203, "step": 159 }, { "epoch": 0.5111821086261981, "grad_norm": 0.8714417484517785, "learning_rate": 9.850226833301893e-06, "loss": 0.5028, "step": 160 }, { "epoch": 0.5143769968051118, "grad_norm": 1.1739862547523015, "learning_rate": 9.8456775373322e-06, "loss": 0.5262, "step": 161 }, { "epoch": 0.5175718849840255, "grad_norm": 1.0233461372531267, "learning_rate": 9.841061262103713e-06, "loss": 0.5206, "step": 162 }, { "epoch": 0.5207667731629393, "grad_norm": 0.8883324987583867, "learning_rate": 9.836378071424782e-06, "loss": 0.5538, "step": 163 }, { "epoch": 0.5239616613418531, "grad_norm": 1.0012586097209828, "learning_rate": 9.831628030028698e-06, "loss": 0.543, "step": 164 }, { "epoch": 0.5271565495207667, "grad_norm": 0.9562090852478352, "learning_rate": 9.826811203572785e-06, "loss": 0.5294, "step": 165 }, { "epoch": 0.5303514376996805, "grad_norm": 0.9049046293095923, "learning_rate": 9.821927658637518e-06, "loss": 0.5156, "step": 166 }, { "epoch": 0.5335463258785943, "grad_norm": 0.7877641278063916, "learning_rate": 9.81697746272557e-06, "loss": 0.4903, "step": 167 }, { "epoch": 0.536741214057508, "grad_norm": 0.8443481947780415, "learning_rate": 9.811960684260907e-06, "loss": 0.4907, "step": 168 }, { "epoch": 0.5399361022364217, "grad_norm": 0.898083258200536, "learning_rate": 9.80687739258782e-06, "loss": 0.5494, "step": 169 }, { "epoch": 0.5431309904153354, "grad_norm": 0.8517585039933291, "learning_rate": 9.801727657969988e-06, "loss": 0.5349, "step": 170 }, { "epoch": 0.5463258785942492, "grad_norm": 0.8024396946511465, "learning_rate": 9.796511551589492e-06, "loss": 0.5363, "step": 171 }, { "epoch": 0.549520766773163, "grad_norm": 1.0176737585507962, "learning_rate": 9.791229145545832e-06, "loss": 0.5323, "step": 172 }, { "epoch": 0.5527156549520766, "grad_norm": 0.8838906840771191, "learning_rate": 9.785880512854937e-06, "loss": 0.542, "step": 173 }, { "epoch": 0.5559105431309904, "grad_norm": 0.8473030231523261, "learning_rate": 9.78046572744815e-06, "loss": 0.5699, "step": 174 }, { "epoch": 0.5591054313099042, "grad_norm": 0.825059066819414, "learning_rate": 9.77498486417121e-06, "loss": 0.518, "step": 175 }, { "epoch": 0.5623003194888179, "grad_norm": 0.9674728298434031, "learning_rate": 9.769437998783216e-06, "loss": 0.5058, "step": 176 }, { "epoch": 0.5654952076677316, "grad_norm": 0.8024091577609612, "learning_rate": 9.763825207955577e-06, "loss": 0.5356, "step": 177 }, { "epoch": 0.5686900958466453, "grad_norm": 0.984512919291256, "learning_rate": 9.758146569270957e-06, "loss": 0.5093, "step": 178 }, { "epoch": 0.5718849840255591, "grad_norm": 0.8625469308559135, "learning_rate": 9.7524021612222e-06, "loss": 0.5041, "step": 179 }, { "epoch": 0.5750798722044729, "grad_norm": 0.8997458559279546, "learning_rate": 9.746592063211247e-06, "loss": 0.5406, "step": 180 }, { "epoch": 0.5782747603833865, "grad_norm": 0.8040161888487145, "learning_rate": 9.74071635554803e-06, "loss": 0.5403, "step": 181 }, { "epoch": 0.5814696485623003, "grad_norm": 0.8251026410970733, "learning_rate": 9.73477511944938e-06, "loss": 0.5193, "step": 182 }, { "epoch": 0.5846645367412141, "grad_norm": 0.8831385892825742, "learning_rate": 9.728768437037882e-06, "loss": 0.5198, "step": 183 }, { "epoch": 0.5878594249201278, "grad_norm": 0.770865412532913, "learning_rate": 9.722696391340762e-06, "loss": 0.5051, "step": 184 }, { "epoch": 0.5910543130990416, "grad_norm": 0.8272777118151003, "learning_rate": 9.716559066288716e-06, "loss": 0.5204, "step": 185 }, { "epoch": 0.5942492012779552, "grad_norm": 0.8810836012906247, "learning_rate": 9.710356546714774e-06, "loss": 0.4819, "step": 186 }, { "epoch": 0.597444089456869, "grad_norm": 0.8321988164095505, "learning_rate": 9.704088918353108e-06, "loss": 0.4975, "step": 187 }, { "epoch": 0.6006389776357828, "grad_norm": 0.8350120588975233, "learning_rate": 9.697756267837856e-06, "loss": 0.506, "step": 188 }, { "epoch": 0.6038338658146964, "grad_norm": 0.7780826409389476, "learning_rate": 9.691358682701927e-06, "loss": 0.4885, "step": 189 }, { "epoch": 0.6070287539936102, "grad_norm": 0.8938697808686494, "learning_rate": 9.684896251375784e-06, "loss": 0.5204, "step": 190 }, { "epoch": 0.610223642172524, "grad_norm": 0.8297429232981851, "learning_rate": 9.678369063186224e-06, "loss": 0.4774, "step": 191 }, { "epoch": 0.6134185303514377, "grad_norm": 0.8969345717007828, "learning_rate": 9.671777208355146e-06, "loss": 0.5183, "step": 192 }, { "epoch": 0.6166134185303515, "grad_norm": 0.8605903779349711, "learning_rate": 9.665120777998303e-06, "loss": 0.5393, "step": 193 }, { "epoch": 0.6198083067092651, "grad_norm": 0.8478878853382145, "learning_rate": 9.658399864124037e-06, "loss": 0.5264, "step": 194 }, { "epoch": 0.6230031948881789, "grad_norm": 0.9236215575439594, "learning_rate": 9.65161455963202e-06, "loss": 0.5184, "step": 195 }, { "epoch": 0.6261980830670927, "grad_norm": 0.7325089308594785, "learning_rate": 9.64476495831195e-06, "loss": 0.5213, "step": 196 }, { "epoch": 0.6293929712460063, "grad_norm": 0.8193350984719754, "learning_rate": 9.637851154842279e-06, "loss": 0.5167, "step": 197 }, { "epoch": 0.6325878594249201, "grad_norm": 0.8155853253850004, "learning_rate": 9.630873244788884e-06, "loss": 0.4814, "step": 198 }, { "epoch": 0.6357827476038339, "grad_norm": 0.8266019460516769, "learning_rate": 9.623831324603755e-06, "loss": 0.487, "step": 199 }, { "epoch": 0.6389776357827476, "grad_norm": 1.029547472699715, "learning_rate": 9.61672549162366e-06, "loss": 0.4843, "step": 200 }, { "epoch": 0.6421725239616614, "grad_norm": 0.8453539576168925, "learning_rate": 9.6095558440688e-06, "loss": 0.5234, "step": 201 }, { "epoch": 0.645367412140575, "grad_norm": 0.8910853768115474, "learning_rate": 9.602322481041457e-06, "loss": 0.535, "step": 202 }, { "epoch": 0.6485623003194888, "grad_norm": 1.039608374119123, "learning_rate": 9.595025502524609e-06, "loss": 0.4762, "step": 203 }, { "epoch": 0.6517571884984026, "grad_norm": 0.9738033589237602, "learning_rate": 9.587665009380565e-06, "loss": 0.5302, "step": 204 }, { "epoch": 0.6549520766773163, "grad_norm": 0.9057631459448521, "learning_rate": 9.580241103349562e-06, "loss": 0.4887, "step": 205 }, { "epoch": 0.65814696485623, "grad_norm": 0.9009879245399683, "learning_rate": 9.572753887048353e-06, "loss": 0.5172, "step": 206 }, { "epoch": 0.6613418530351438, "grad_norm": 0.7947928914543034, "learning_rate": 9.565203463968808e-06, "loss": 0.4967, "step": 207 }, { "epoch": 0.6645367412140575, "grad_norm": 0.9387010712796708, "learning_rate": 9.557589938476462e-06, "loss": 0.5581, "step": 208 }, { "epoch": 0.6677316293929713, "grad_norm": 0.8039755278927958, "learning_rate": 9.549913415809084e-06, "loss": 0.547, "step": 209 }, { "epoch": 0.670926517571885, "grad_norm": 0.899702008695738, "learning_rate": 9.542174002075221e-06, "loss": 0.4954, "step": 210 }, { "epoch": 0.6741214057507987, "grad_norm": 0.860505060633573, "learning_rate": 9.534371804252727e-06, "loss": 0.5166, "step": 211 }, { "epoch": 0.6773162939297125, "grad_norm": 0.742092503955616, "learning_rate": 9.526506930187294e-06, "loss": 0.5348, "step": 212 }, { "epoch": 0.6805111821086262, "grad_norm": 0.7823402422263195, "learning_rate": 9.518579488590947e-06, "loss": 0.5431, "step": 213 }, { "epoch": 0.6837060702875399, "grad_norm": 0.9661234253998444, "learning_rate": 9.510589589040554e-06, "loss": 0.5562, "step": 214 }, { "epoch": 0.6869009584664537, "grad_norm": 0.7521161190353953, "learning_rate": 9.502537341976305e-06, "loss": 0.4647, "step": 215 }, { "epoch": 0.6900958466453674, "grad_norm": 0.7987183646840882, "learning_rate": 9.494422858700188e-06, "loss": 0.5153, "step": 216 }, { "epoch": 0.6932907348242812, "grad_norm": 0.9841955582435438, "learning_rate": 9.48624625137445e-06, "loss": 0.5555, "step": 217 }, { "epoch": 0.6964856230031949, "grad_norm": 0.8401707334735183, "learning_rate": 9.478007633020043e-06, "loss": 0.5471, "step": 218 }, { "epoch": 0.6996805111821086, "grad_norm": 0.8710741844589728, "learning_rate": 9.469707117515068e-06, "loss": 0.5439, "step": 219 }, { "epoch": 0.7028753993610224, "grad_norm": 0.8481362485002034, "learning_rate": 9.461344819593194e-06, "loss": 0.5397, "step": 220 }, { "epoch": 0.7060702875399361, "grad_norm": 0.9234317739603707, "learning_rate": 9.452920854842085e-06, "loss": 0.5103, "step": 221 }, { "epoch": 0.7092651757188498, "grad_norm": 0.7849131415351538, "learning_rate": 9.44443533970178e-06, "loss": 0.5386, "step": 222 }, { "epoch": 0.7124600638977636, "grad_norm": 0.7364218991408114, "learning_rate": 9.435888391463108e-06, "loss": 0.4815, "step": 223 }, { "epoch": 0.7156549520766773, "grad_norm": 0.824648899698229, "learning_rate": 9.427280128266049e-06, "loss": 0.4967, "step": 224 }, { "epoch": 0.7188498402555911, "grad_norm": 0.8053371492291931, "learning_rate": 9.418610669098114e-06, "loss": 0.502, "step": 225 }, { "epoch": 0.7220447284345048, "grad_norm": 0.8745575246788325, "learning_rate": 9.409880133792684e-06, "loss": 0.5471, "step": 226 }, { "epoch": 0.7252396166134185, "grad_norm": 0.8426487522968908, "learning_rate": 9.40108864302737e-06, "loss": 0.5415, "step": 227 }, { "epoch": 0.7284345047923323, "grad_norm": 0.8446459909213165, "learning_rate": 9.392236318322339e-06, "loss": 0.5131, "step": 228 }, { "epoch": 0.731629392971246, "grad_norm": 0.8940769463027018, "learning_rate": 9.383323282038632e-06, "loss": 0.5174, "step": 229 }, { "epoch": 0.7348242811501597, "grad_norm": 0.7504679870390856, "learning_rate": 9.374349657376473e-06, "loss": 0.5025, "step": 230 }, { "epoch": 0.7380191693290735, "grad_norm": 0.8843745789113971, "learning_rate": 9.365315568373569e-06, "loss": 0.5119, "step": 231 }, { "epoch": 0.7412140575079872, "grad_norm": 0.7359230595220048, "learning_rate": 9.356221139903395e-06, "loss": 0.5222, "step": 232 }, { "epoch": 0.744408945686901, "grad_norm": 0.8000874826998402, "learning_rate": 9.347066497673462e-06, "loss": 0.4956, "step": 233 }, { "epoch": 0.7476038338658147, "grad_norm": 0.8244411036517779, "learning_rate": 9.337851768223589e-06, "loss": 0.4948, "step": 234 }, { "epoch": 0.7507987220447284, "grad_norm": 0.8355217449150175, "learning_rate": 9.328577078924151e-06, "loss": 0.5117, "step": 235 }, { "epoch": 0.7539936102236422, "grad_norm": 0.7893167216575436, "learning_rate": 9.319242557974306e-06, "loss": 0.4821, "step": 236 }, { "epoch": 0.7571884984025559, "grad_norm": 0.92890577949437, "learning_rate": 9.309848334400247e-06, "loss": 0.5237, "step": 237 }, { "epoch": 0.7603833865814696, "grad_norm": 0.8736286224281079, "learning_rate": 9.300394538053395e-06, "loss": 0.5017, "step": 238 }, { "epoch": 0.7635782747603834, "grad_norm": 0.9077340441102514, "learning_rate": 9.29088129960862e-06, "loss": 0.5127, "step": 239 }, { "epoch": 0.7667731629392971, "grad_norm": 0.6940764153582664, "learning_rate": 9.281308750562426e-06, "loss": 0.4893, "step": 240 }, { "epoch": 0.7699680511182109, "grad_norm": 0.880965679725469, "learning_rate": 9.271677023231137e-06, "loss": 0.4983, "step": 241 }, { "epoch": 0.7731629392971247, "grad_norm": 0.8538265562564804, "learning_rate": 9.261986250749068e-06, "loss": 0.4765, "step": 242 }, { "epoch": 0.7763578274760383, "grad_norm": 0.7630022035581716, "learning_rate": 9.252236567066686e-06, "loss": 0.4874, "step": 243 }, { "epoch": 0.7795527156549521, "grad_norm": 0.8281654773029874, "learning_rate": 9.242428106948748e-06, "loss": 0.5903, "step": 244 }, { "epoch": 0.7827476038338658, "grad_norm": 0.9203463968163862, "learning_rate": 9.23256100597246e-06, "loss": 0.5189, "step": 245 }, { "epoch": 0.7859424920127795, "grad_norm": 0.748700979427418, "learning_rate": 9.22263540052558e-06, "loss": 0.5151, "step": 246 }, { "epoch": 0.7891373801916933, "grad_norm": 0.7392344241335602, "learning_rate": 9.212651427804544e-06, "loss": 0.5593, "step": 247 }, { "epoch": 0.792332268370607, "grad_norm": 0.7348453831535354, "learning_rate": 9.202609225812572e-06, "loss": 0.5106, "step": 248 }, { "epoch": 0.7955271565495208, "grad_norm": 0.8370603755867384, "learning_rate": 9.192508933357753e-06, "loss": 0.4975, "step": 249 }, { "epoch": 0.7987220447284346, "grad_norm": 0.817703134992455, "learning_rate": 9.182350690051134e-06, "loss": 0.5089, "step": 250 }, { "epoch": 0.8019169329073482, "grad_norm": 0.7599324215664683, "learning_rate": 9.172134636304783e-06, "loss": 0.4621, "step": 251 }, { "epoch": 0.805111821086262, "grad_norm": 0.8083512869640488, "learning_rate": 9.16186091332985e-06, "loss": 0.5013, "step": 252 }, { "epoch": 0.8083067092651757, "grad_norm": 0.829560542023121, "learning_rate": 9.15152966313462e-06, "loss": 0.4925, "step": 253 }, { "epoch": 0.8115015974440895, "grad_norm": 0.7561288554172421, "learning_rate": 9.141141028522544e-06, "loss": 0.4612, "step": 254 }, { "epoch": 0.8146964856230032, "grad_norm": 0.7950323702810275, "learning_rate": 9.130695153090272e-06, "loss": 0.4837, "step": 255 }, { "epoch": 0.8178913738019169, "grad_norm": 0.8516278924258801, "learning_rate": 9.120192181225658e-06, "loss": 0.5045, "step": 256 }, { "epoch": 0.8210862619808307, "grad_norm": 0.8916603008544254, "learning_rate": 9.109632258105771e-06, "loss": 0.4874, "step": 257 }, { "epoch": 0.8242811501597445, "grad_norm": 0.7691147493078145, "learning_rate": 9.099015529694894e-06, "loss": 0.4771, "step": 258 }, { "epoch": 0.8274760383386581, "grad_norm": 0.869859122278694, "learning_rate": 9.088342142742493e-06, "loss": 0.4943, "step": 259 }, { "epoch": 0.8306709265175719, "grad_norm": 0.8183569250546232, "learning_rate": 9.077612244781196e-06, "loss": 0.5186, "step": 260 }, { "epoch": 0.8338658146964856, "grad_norm": 0.8121246614868811, "learning_rate": 9.066825984124751e-06, "loss": 0.5066, "step": 261 }, { "epoch": 0.8370607028753994, "grad_norm": 0.8809673133319126, "learning_rate": 9.055983509865988e-06, "loss": 0.5428, "step": 262 }, { "epoch": 0.8402555910543131, "grad_norm": 0.948125364179264, "learning_rate": 9.045084971874738e-06, "loss": 0.5276, "step": 263 }, { "epoch": 0.8434504792332268, "grad_norm": 0.8880641547871259, "learning_rate": 9.034130520795774e-06, "loss": 0.5562, "step": 264 }, { "epoch": 0.8466453674121406, "grad_norm": 0.732721292018942, "learning_rate": 9.023120308046726e-06, "loss": 0.504, "step": 265 }, { "epoch": 0.8498402555910544, "grad_norm": 0.9396860529462092, "learning_rate": 9.012054485815995e-06, "loss": 0.4649, "step": 266 }, { "epoch": 0.853035143769968, "grad_norm": 0.8242804566044789, "learning_rate": 9.00093320706063e-06, "loss": 0.4908, "step": 267 }, { "epoch": 0.8562300319488818, "grad_norm": 0.7136166681699279, "learning_rate": 8.989756625504237e-06, "loss": 0.483, "step": 268 }, { "epoch": 0.8594249201277955, "grad_norm": 0.9605400874780818, "learning_rate": 8.978524895634842e-06, "loss": 0.5018, "step": 269 }, { "epoch": 0.8626198083067093, "grad_norm": 0.9100046397923284, "learning_rate": 8.967238172702754e-06, "loss": 0.5439, "step": 270 }, { "epoch": 0.865814696485623, "grad_norm": 0.7997810149108854, "learning_rate": 8.95589661271842e-06, "loss": 0.5334, "step": 271 }, { "epoch": 0.8690095846645367, "grad_norm": 0.9547461697852979, "learning_rate": 8.94450037245028e-06, "loss": 0.4968, "step": 272 }, { "epoch": 0.8722044728434505, "grad_norm": 0.8023978860589094, "learning_rate": 8.933049609422582e-06, "loss": 0.4893, "step": 273 }, { "epoch": 0.8753993610223643, "grad_norm": 0.9014885751500846, "learning_rate": 8.921544481913218e-06, "loss": 0.5345, "step": 274 }, { "epoch": 0.8785942492012779, "grad_norm": 0.8131253814280156, "learning_rate": 8.909985148951528e-06, "loss": 0.5156, "step": 275 }, { "epoch": 0.8817891373801917, "grad_norm": 0.8324175224666767, "learning_rate": 8.898371770316113e-06, "loss": 0.529, "step": 276 }, { "epoch": 0.8849840255591054, "grad_norm": 0.8492286873279923, "learning_rate": 8.886704506532611e-06, "loss": 0.5067, "step": 277 }, { "epoch": 0.8881789137380192, "grad_norm": 0.9125893960779855, "learning_rate": 8.874983518871488e-06, "loss": 0.4631, "step": 278 }, { "epoch": 0.8913738019169329, "grad_norm": 0.8225205350268786, "learning_rate": 8.86320896934581e-06, "loss": 0.5109, "step": 279 }, { "epoch": 0.8945686900958466, "grad_norm": 0.9070535249722314, "learning_rate": 8.851381020709e-06, "loss": 0.5404, "step": 280 }, { "epoch": 0.8977635782747604, "grad_norm": 0.8719696885529683, "learning_rate": 8.839499836452584e-06, "loss": 0.544, "step": 281 }, { "epoch": 0.9009584664536742, "grad_norm": 0.8472227031001561, "learning_rate": 8.827565580803944e-06, "loss": 0.4744, "step": 282 }, { "epoch": 0.9041533546325878, "grad_norm": 0.7744023330970529, "learning_rate": 8.815578418724031e-06, "loss": 0.4917, "step": 283 }, { "epoch": 0.9073482428115016, "grad_norm": 0.6869536247022346, "learning_rate": 8.803538515905102e-06, "loss": 0.4877, "step": 284 }, { "epoch": 0.9105431309904153, "grad_norm": 0.89412421480912, "learning_rate": 8.791446038768416e-06, "loss": 0.5375, "step": 285 }, { "epoch": 0.9137380191693291, "grad_norm": 0.8772749555457497, "learning_rate": 8.779301154461945e-06, "loss": 0.5083, "step": 286 }, { "epoch": 0.9169329073482428, "grad_norm": 0.890143694882453, "learning_rate": 8.76710403085805e-06, "loss": 0.5355, "step": 287 }, { "epoch": 0.9201277955271565, "grad_norm": 0.8678519842166535, "learning_rate": 8.754854836551174e-06, "loss": 0.5028, "step": 288 }, { "epoch": 0.9233226837060703, "grad_norm": 0.7828124341079867, "learning_rate": 8.742553740855507e-06, "loss": 0.465, "step": 289 }, { "epoch": 0.9265175718849841, "grad_norm": 1.0678308340301852, "learning_rate": 8.730200913802638e-06, "loss": 0.5438, "step": 290 }, { "epoch": 0.9297124600638977, "grad_norm": 0.8351824750309134, "learning_rate": 8.717796526139218e-06, "loss": 0.4949, "step": 291 }, { "epoch": 0.9329073482428115, "grad_norm": 0.8499796924611565, "learning_rate": 8.70534074932459e-06, "loss": 0.5081, "step": 292 }, { "epoch": 0.9361022364217252, "grad_norm": 0.9212590356714732, "learning_rate": 8.692833755528426e-06, "loss": 0.5278, "step": 293 }, { "epoch": 0.939297124600639, "grad_norm": 0.8289607688137761, "learning_rate": 8.680275717628336e-06, "loss": 0.5033, "step": 294 }, { "epoch": 0.9424920127795527, "grad_norm": 0.9377628019643448, "learning_rate": 8.667666809207495e-06, "loss": 0.5002, "step": 295 }, { "epoch": 0.9456869009584664, "grad_norm": 0.8595609804694344, "learning_rate": 8.655007204552228e-06, "loss": 0.5699, "step": 296 }, { "epoch": 0.9488817891373802, "grad_norm": 0.9144332718871088, "learning_rate": 8.64229707864961e-06, "loss": 0.4943, "step": 297 }, { "epoch": 0.952076677316294, "grad_norm": 0.8709388293908786, "learning_rate": 8.629536607185042e-06, "loss": 0.5194, "step": 298 }, { "epoch": 0.9552715654952076, "grad_norm": 0.8594579405188586, "learning_rate": 8.616725966539831e-06, "loss": 0.5146, "step": 299 }, { "epoch": 0.9584664536741214, "grad_norm": 0.9937747625380199, "learning_rate": 8.60386533378874e-06, "loss": 0.5002, "step": 300 }, { "epoch": 0.9616613418530351, "grad_norm": 0.8918915409321642, "learning_rate": 8.590954886697554e-06, "loss": 0.4845, "step": 301 }, { "epoch": 0.9648562300319489, "grad_norm": 0.7843164146186518, "learning_rate": 8.577994803720605e-06, "loss": 0.4975, "step": 302 }, { "epoch": 0.9680511182108626, "grad_norm": 0.9015940400069826, "learning_rate": 8.564985263998327e-06, "loss": 0.4797, "step": 303 }, { "epoch": 0.9712460063897763, "grad_norm": 0.7029136656889042, "learning_rate": 8.551926447354759e-06, "loss": 0.4639, "step": 304 }, { "epoch": 0.9744408945686901, "grad_norm": 0.8144223926791186, "learning_rate": 8.538818534295076e-06, "loss": 0.4892, "step": 305 }, { "epoch": 0.9776357827476039, "grad_norm": 0.736223257739176, "learning_rate": 8.525661706003083e-06, "loss": 0.484, "step": 306 }, { "epoch": 0.9808306709265175, "grad_norm": 0.8004441127612412, "learning_rate": 8.512456144338717e-06, "loss": 0.4956, "step": 307 }, { "epoch": 0.9840255591054313, "grad_norm": 0.8092384053836325, "learning_rate": 8.499202031835532e-06, "loss": 0.4973, "step": 308 }, { "epoch": 0.987220447284345, "grad_norm": 0.9020628340911017, "learning_rate": 8.485899551698166e-06, "loss": 0.5086, "step": 309 }, { "epoch": 0.9904153354632588, "grad_norm": 0.7802779374482116, "learning_rate": 8.472548887799833e-06, "loss": 0.4838, "step": 310 }, { "epoch": 0.9936102236421726, "grad_norm": 0.6826024474896338, "learning_rate": 8.45915022467975e-06, "loss": 0.4707, "step": 311 }, { "epoch": 0.9968051118210862, "grad_norm": 0.9604893538879873, "learning_rate": 8.445703747540614e-06, "loss": 0.5721, "step": 312 }, { "epoch": 1.0, "grad_norm": 0.8699409146438202, "learning_rate": 8.43220964224602e-06, "loss": 0.5683, "step": 313 }, { "epoch": 1.0031948881789137, "grad_norm": 0.7764317553928854, "learning_rate": 8.418668095317912e-06, "loss": 0.4403, "step": 314 }, { "epoch": 1.0063897763578276, "grad_norm": 0.7338758896539651, "learning_rate": 8.405079293933986e-06, "loss": 0.4496, "step": 315 }, { "epoch": 1.0095846645367412, "grad_norm": 0.7540355701636785, "learning_rate": 8.391443425925118e-06, "loss": 0.3808, "step": 316 }, { "epoch": 1.012779552715655, "grad_norm": 0.7946391602416338, "learning_rate": 8.37776067977276e-06, "loss": 0.3941, "step": 317 }, { "epoch": 1.0159744408945688, "grad_norm": 0.7751109185829435, "learning_rate": 8.36403124460633e-06, "loss": 0.41, "step": 318 }, { "epoch": 1.0191693290734825, "grad_norm": 0.699379354402552, "learning_rate": 8.350255310200611e-06, "loss": 0.4023, "step": 319 }, { "epoch": 1.0223642172523961, "grad_norm": 0.8578136972746896, "learning_rate": 8.336433066973122e-06, "loss": 0.4308, "step": 320 }, { "epoch": 1.0255591054313098, "grad_norm": 0.8333999234295557, "learning_rate": 8.322564705981476e-06, "loss": 0.4339, "step": 321 }, { "epoch": 1.0287539936102237, "grad_norm": 0.8682415637488364, "learning_rate": 8.308650418920751e-06, "loss": 0.4639, "step": 322 }, { "epoch": 1.0319488817891374, "grad_norm": 0.7010492104711966, "learning_rate": 8.294690398120843e-06, "loss": 0.4138, "step": 323 }, { "epoch": 1.035143769968051, "grad_norm": 0.8352684574898297, "learning_rate": 8.280684836543794e-06, "loss": 0.4181, "step": 324 }, { "epoch": 1.038338658146965, "grad_norm": 0.8062281397866784, "learning_rate": 8.266633927781135e-06, "loss": 0.3765, "step": 325 }, { "epoch": 1.0415335463258786, "grad_norm": 0.8011168130993689, "learning_rate": 8.25253786605121e-06, "loss": 0.4155, "step": 326 }, { "epoch": 1.0447284345047922, "grad_norm": 0.7929363913746529, "learning_rate": 8.238396846196483e-06, "loss": 0.4796, "step": 327 }, { "epoch": 1.0479233226837061, "grad_norm": 0.681042440631801, "learning_rate": 8.224211063680854e-06, "loss": 0.3758, "step": 328 }, { "epoch": 1.0511182108626198, "grad_norm": 0.8718135408032824, "learning_rate": 8.209980714586955e-06, "loss": 0.4103, "step": 329 }, { "epoch": 1.0543130990415335, "grad_norm": 0.8413791063039867, "learning_rate": 8.195705995613436e-06, "loss": 0.4299, "step": 330 }, { "epoch": 1.0575079872204474, "grad_norm": 0.8465944020037799, "learning_rate": 8.181387104072252e-06, "loss": 0.4611, "step": 331 }, { "epoch": 1.060702875399361, "grad_norm": 0.768940507092269, "learning_rate": 8.167024237885927e-06, "loss": 0.4186, "step": 332 }, { "epoch": 1.0638977635782747, "grad_norm": 0.7522783224445742, "learning_rate": 8.152617595584827e-06, "loss": 0.4406, "step": 333 }, { "epoch": 1.0670926517571886, "grad_norm": 0.768895921716199, "learning_rate": 8.138167376304411e-06, "loss": 0.383, "step": 334 }, { "epoch": 1.0702875399361023, "grad_norm": 0.7638818070910931, "learning_rate": 8.123673779782481e-06, "loss": 0.4079, "step": 335 }, { "epoch": 1.073482428115016, "grad_norm": 0.6697970201976026, "learning_rate": 8.10913700635642e-06, "loss": 0.3388, "step": 336 }, { "epoch": 1.0766773162939298, "grad_norm": 0.6812118706436625, "learning_rate": 8.094557256960419e-06, "loss": 0.4072, "step": 337 }, { "epoch": 1.0798722044728435, "grad_norm": 0.8770247682643849, "learning_rate": 8.079934733122708e-06, "loss": 0.4094, "step": 338 }, { "epoch": 1.0830670926517572, "grad_norm": 0.6616362830243507, "learning_rate": 8.065269636962765e-06, "loss": 0.444, "step": 339 }, { "epoch": 1.0862619808306708, "grad_norm": 0.7111069767944058, "learning_rate": 8.05056217118852e-06, "loss": 0.4554, "step": 340 }, { "epoch": 1.0894568690095847, "grad_norm": 0.7694717252053866, "learning_rate": 8.035812539093557e-06, "loss": 0.4552, "step": 341 }, { "epoch": 1.0926517571884984, "grad_norm": 0.7393731584116311, "learning_rate": 8.021020944554305e-06, "loss": 0.4017, "step": 342 }, { "epoch": 1.095846645367412, "grad_norm": 0.6752488842069413, "learning_rate": 8.006187592027215e-06, "loss": 0.4548, "step": 343 }, { "epoch": 1.099041533546326, "grad_norm": 0.6246938261456642, "learning_rate": 7.991312686545939e-06, "loss": 0.4045, "step": 344 }, { "epoch": 1.1022364217252396, "grad_norm": 0.7350229600234459, "learning_rate": 7.976396433718492e-06, "loss": 0.4012, "step": 345 }, { "epoch": 1.1054313099041533, "grad_norm": 0.7695718734465381, "learning_rate": 7.961439039724413e-06, "loss": 0.4361, "step": 346 }, { "epoch": 1.1086261980830672, "grad_norm": 0.7248682429154152, "learning_rate": 7.946440711311913e-06, "loss": 0.371, "step": 347 }, { "epoch": 1.1118210862619808, "grad_norm": 0.7243053070616239, "learning_rate": 7.931401655795021e-06, "loss": 0.4156, "step": 348 }, { "epoch": 1.1150159744408945, "grad_norm": 0.7358516001684667, "learning_rate": 7.916322081050708e-06, "loss": 0.4294, "step": 349 }, { "epoch": 1.1182108626198084, "grad_norm": 0.6989330209550405, "learning_rate": 7.90120219551603e-06, "loss": 0.3772, "step": 350 }, { "epoch": 1.121405750798722, "grad_norm": 0.6979994560001975, "learning_rate": 7.88604220818523e-06, "loss": 0.4097, "step": 351 }, { "epoch": 1.1246006389776357, "grad_norm": 0.7376492259097831, "learning_rate": 7.870842328606863e-06, "loss": 0.4062, "step": 352 }, { "epoch": 1.1277955271565494, "grad_norm": 0.8182890240546004, "learning_rate": 7.85560276688089e-06, "loss": 0.4262, "step": 353 }, { "epoch": 1.1309904153354633, "grad_norm": 0.5929082187409976, "learning_rate": 7.84032373365578e-06, "loss": 0.3847, "step": 354 }, { "epoch": 1.134185303514377, "grad_norm": 0.5999973735326927, "learning_rate": 7.825005440125595e-06, "loss": 0.4121, "step": 355 }, { "epoch": 1.1373801916932909, "grad_norm": 0.7226429475619828, "learning_rate": 7.809648098027067e-06, "loss": 0.3919, "step": 356 }, { "epoch": 1.1405750798722045, "grad_norm": 0.6816845849611944, "learning_rate": 7.794251919636687e-06, "loss": 0.4472, "step": 357 }, { "epoch": 1.1437699680511182, "grad_norm": 0.7573980172847606, "learning_rate": 7.778817117767748e-06, "loss": 0.4232, "step": 358 }, { "epoch": 1.1469648562300319, "grad_norm": 0.7178781383342445, "learning_rate": 7.76334390576742e-06, "loss": 0.3673, "step": 359 }, { "epoch": 1.1501597444089458, "grad_norm": 0.7335817902399818, "learning_rate": 7.747832497513797e-06, "loss": 0.4067, "step": 360 }, { "epoch": 1.1533546325878594, "grad_norm": 0.7133472371686488, "learning_rate": 7.732283107412938e-06, "loss": 0.4314, "step": 361 }, { "epoch": 1.156549520766773, "grad_norm": 0.7986130467269262, "learning_rate": 7.71669595039591e-06, "loss": 0.4333, "step": 362 }, { "epoch": 1.159744408945687, "grad_norm": 0.7068834905394128, "learning_rate": 7.701071241915804e-06, "loss": 0.4318, "step": 363 }, { "epoch": 1.1629392971246006, "grad_norm": 0.737545144664687, "learning_rate": 7.685409197944768e-06, "loss": 0.412, "step": 364 }, { "epoch": 1.1661341853035143, "grad_norm": 0.764234149996104, "learning_rate": 7.669710034971025e-06, "loss": 0.4172, "step": 365 }, { "epoch": 1.1693290734824282, "grad_norm": 0.7134888087174184, "learning_rate": 7.653973969995866e-06, "loss": 0.4085, "step": 366 }, { "epoch": 1.1725239616613419, "grad_norm": 0.675285473832815, "learning_rate": 7.638201220530664e-06, "loss": 0.4266, "step": 367 }, { "epoch": 1.1757188498402555, "grad_norm": 0.8554365485718853, "learning_rate": 7.622392004593862e-06, "loss": 0.4018, "step": 368 }, { "epoch": 1.1789137380191694, "grad_norm": 0.7394321475600621, "learning_rate": 7.60654654070796e-06, "loss": 0.3781, "step": 369 }, { "epoch": 1.182108626198083, "grad_norm": 0.7522087705245671, "learning_rate": 7.59066504789649e-06, "loss": 0.4215, "step": 370 }, { "epoch": 1.1853035143769968, "grad_norm": 0.7859238242025294, "learning_rate": 7.574747745681e-06, "loss": 0.4481, "step": 371 }, { "epoch": 1.1884984025559104, "grad_norm": 0.8893594410231564, "learning_rate": 7.558794854078006e-06, "loss": 0.3957, "step": 372 }, { "epoch": 1.1916932907348243, "grad_norm": 0.7416322294292199, "learning_rate": 7.542806593595963e-06, "loss": 0.4307, "step": 373 }, { "epoch": 1.194888178913738, "grad_norm": 0.8682014698204892, "learning_rate": 7.526783185232208e-06, "loss": 0.4225, "step": 374 }, { "epoch": 1.1980830670926517, "grad_norm": 0.808491779347055, "learning_rate": 7.51072485046991e-06, "loss": 0.4084, "step": 375 }, { "epoch": 1.2012779552715656, "grad_norm": 0.8685719336829648, "learning_rate": 7.494631811275008e-06, "loss": 0.3973, "step": 376 }, { "epoch": 1.2044728434504792, "grad_norm": 0.7901114669485614, "learning_rate": 7.478504290093138e-06, "loss": 0.4257, "step": 377 }, { "epoch": 1.207667731629393, "grad_norm": 0.8160312545633633, "learning_rate": 7.462342509846571e-06, "loss": 0.4048, "step": 378 }, { "epoch": 1.2108626198083068, "grad_norm": 0.7233374312117897, "learning_rate": 7.446146693931111e-06, "loss": 0.3952, "step": 379 }, { "epoch": 1.2140575079872205, "grad_norm": 0.7767917244942978, "learning_rate": 7.42991706621303e-06, "loss": 0.4891, "step": 380 }, { "epoch": 1.2172523961661341, "grad_norm": 0.7072787009379669, "learning_rate": 7.413653851025959e-06, "loss": 0.4741, "step": 381 }, { "epoch": 1.220447284345048, "grad_norm": 0.746065313367986, "learning_rate": 7.397357273167789e-06, "loss": 0.4698, "step": 382 }, { "epoch": 1.2236421725239617, "grad_norm": 0.7234203890871863, "learning_rate": 7.381027557897568e-06, "loss": 0.3802, "step": 383 }, { "epoch": 1.2268370607028753, "grad_norm": 0.7599175690114612, "learning_rate": 7.364664930932385e-06, "loss": 0.439, "step": 384 }, { "epoch": 1.230031948881789, "grad_norm": 0.8277285657761506, "learning_rate": 7.348269618444248e-06, "loss": 0.4635, "step": 385 }, { "epoch": 1.233226837060703, "grad_norm": 0.7151589242001917, "learning_rate": 7.331841847056962e-06, "loss": 0.434, "step": 386 }, { "epoch": 1.2364217252396166, "grad_norm": 0.7885405443701896, "learning_rate": 7.315381843842995e-06, "loss": 0.3901, "step": 387 }, { "epoch": 1.2396166134185305, "grad_norm": 0.7794048735012029, "learning_rate": 7.298889836320334e-06, "loss": 0.4496, "step": 388 }, { "epoch": 1.2428115015974441, "grad_norm": 0.7185850468731043, "learning_rate": 7.282366052449351e-06, "loss": 0.4156, "step": 389 }, { "epoch": 1.2460063897763578, "grad_norm": 0.8761942292460905, "learning_rate": 7.265810720629643e-06, "loss": 0.4381, "step": 390 }, { "epoch": 1.2492012779552715, "grad_norm": 0.7418876903956504, "learning_rate": 7.249224069696876e-06, "loss": 0.4231, "step": 391 }, { "epoch": 1.2523961661341854, "grad_norm": 0.6689548591926106, "learning_rate": 7.232606328919627e-06, "loss": 0.4638, "step": 392 }, { "epoch": 1.255591054313099, "grad_norm": 0.8018636198628307, "learning_rate": 7.215957727996208e-06, "loss": 0.3911, "step": 393 }, { "epoch": 1.2587859424920127, "grad_norm": 0.8634573351751972, "learning_rate": 7.199278497051498e-06, "loss": 0.4627, "step": 394 }, { "epoch": 1.2619808306709266, "grad_norm": 0.7022128622434374, "learning_rate": 7.182568866633757e-06, "loss": 0.3625, "step": 395 }, { "epoch": 1.2651757188498403, "grad_norm": 0.7295361331459049, "learning_rate": 7.16582906771144e-06, "loss": 0.4223, "step": 396 }, { "epoch": 1.268370607028754, "grad_norm": 0.8351272934479426, "learning_rate": 7.149059331670009e-06, "loss": 0.3954, "step": 397 }, { "epoch": 1.2715654952076676, "grad_norm": 0.7773394015956511, "learning_rate": 7.132259890308726e-06, "loss": 0.4082, "step": 398 }, { "epoch": 1.2747603833865815, "grad_norm": 0.854650362078553, "learning_rate": 7.115430975837457e-06, "loss": 0.4168, "step": 399 }, { "epoch": 1.2779552715654952, "grad_norm": 0.7417248588065127, "learning_rate": 7.098572820873461e-06, "loss": 0.4451, "step": 400 }, { "epoch": 1.281150159744409, "grad_norm": 0.7063837427460873, "learning_rate": 7.081685658438173e-06, "loss": 0.4155, "step": 401 }, { "epoch": 1.2843450479233227, "grad_norm": 0.842141676152669, "learning_rate": 7.064769721953975e-06, "loss": 0.4502, "step": 402 }, { "epoch": 1.2875399361022364, "grad_norm": 0.7471309894180018, "learning_rate": 7.047825245240989e-06, "loss": 0.4486, "step": 403 }, { "epoch": 1.29073482428115, "grad_norm": 0.6602847047558186, "learning_rate": 7.030852462513827e-06, "loss": 0.4279, "step": 404 }, { "epoch": 1.293929712460064, "grad_norm": 0.7483995023271691, "learning_rate": 7.013851608378359e-06, "loss": 0.3944, "step": 405 }, { "epoch": 1.2971246006389776, "grad_norm": 0.8281579239977933, "learning_rate": 6.9968229178284775e-06, "loss": 0.4518, "step": 406 }, { "epoch": 1.3003194888178915, "grad_norm": 0.7892389369737978, "learning_rate": 6.979766626242839e-06, "loss": 0.407, "step": 407 }, { "epoch": 1.3035143769968052, "grad_norm": 0.7373915710031449, "learning_rate": 6.9626829693816135e-06, "loss": 0.413, "step": 408 }, { "epoch": 1.3067092651757188, "grad_norm": 0.697910278003432, "learning_rate": 6.945572183383229e-06, "loss": 0.4234, "step": 409 }, { "epoch": 1.3099041533546325, "grad_norm": 0.6940586739732686, "learning_rate": 6.928434504761106e-06, "loss": 0.3888, "step": 410 }, { "epoch": 1.3130990415335464, "grad_norm": 0.7928807853026925, "learning_rate": 6.911270170400385e-06, "loss": 0.4165, "step": 411 }, { "epoch": 1.31629392971246, "grad_norm": 0.7510163375476263, "learning_rate": 6.894079417554657e-06, "loss": 0.419, "step": 412 }, { "epoch": 1.3194888178913737, "grad_norm": 0.7598233883481605, "learning_rate": 6.8768624838426815e-06, "loss": 0.3902, "step": 413 }, { "epoch": 1.3226837060702876, "grad_norm": 0.6512401203280582, "learning_rate": 6.859619607245102e-06, "loss": 0.4362, "step": 414 }, { "epoch": 1.3258785942492013, "grad_norm": 0.8386440871131998, "learning_rate": 6.842351026101155e-06, "loss": 0.4268, "step": 415 }, { "epoch": 1.329073482428115, "grad_norm": 0.7273839937091774, "learning_rate": 6.825056979105382e-06, "loss": 0.4242, "step": 416 }, { "epoch": 1.3322683706070286, "grad_norm": 0.7967716558629548, "learning_rate": 6.807737705304324e-06, "loss": 0.4333, "step": 417 }, { "epoch": 1.3354632587859425, "grad_norm": 0.7164636960417264, "learning_rate": 6.790393444093214e-06, "loss": 0.4354, "step": 418 }, { "epoch": 1.3386581469648562, "grad_norm": 0.7667891952582243, "learning_rate": 6.773024435212678e-06, "loss": 0.4516, "step": 419 }, { "epoch": 1.34185303514377, "grad_norm": 0.6392120988071214, "learning_rate": 6.7556309187454185e-06, "loss": 0.4316, "step": 420 }, { "epoch": 1.3450479233226837, "grad_norm": 0.8002715396359115, "learning_rate": 6.738213135112884e-06, "loss": 0.4272, "step": 421 }, { "epoch": 1.3482428115015974, "grad_norm": 0.7554333578315849, "learning_rate": 6.720771325071965e-06, "loss": 0.4086, "step": 422 }, { "epoch": 1.351437699680511, "grad_norm": 0.8764552858840713, "learning_rate": 6.703305729711653e-06, "loss": 0.4174, "step": 423 }, { "epoch": 1.354632587859425, "grad_norm": 0.7445057916080219, "learning_rate": 6.685816590449708e-06, "loss": 0.4516, "step": 424 }, { "epoch": 1.3578274760383386, "grad_norm": 0.7848197318433568, "learning_rate": 6.668304149029331e-06, "loss": 0.3928, "step": 425 }, { "epoch": 1.3610223642172525, "grad_norm": 0.7472891259669744, "learning_rate": 6.650768647515813e-06, "loss": 0.4303, "step": 426 }, { "epoch": 1.3642172523961662, "grad_norm": 0.8185996282961204, "learning_rate": 6.63321032829319e-06, "loss": 0.4069, "step": 427 }, { "epoch": 1.3674121405750799, "grad_norm": 0.669092369955815, "learning_rate": 6.615629434060903e-06, "loss": 0.4329, "step": 428 }, { "epoch": 1.3706070287539935, "grad_norm": 0.7849739125407705, "learning_rate": 6.598026207830428e-06, "loss": 0.4084, "step": 429 }, { "epoch": 1.3738019169329074, "grad_norm": 0.7162838173137105, "learning_rate": 6.5804008929219284e-06, "loss": 0.3923, "step": 430 }, { "epoch": 1.376996805111821, "grad_norm": 0.66931493645132, "learning_rate": 6.562753732960887e-06, "loss": 0.4008, "step": 431 }, { "epoch": 1.3801916932907348, "grad_norm": 0.7546682360951521, "learning_rate": 6.545084971874738e-06, "loss": 0.3741, "step": 432 }, { "epoch": 1.3833865814696487, "grad_norm": 0.6783918756770292, "learning_rate": 6.527394853889499e-06, "loss": 0.4063, "step": 433 }, { "epoch": 1.3865814696485623, "grad_norm": 0.7141201132534667, "learning_rate": 6.5096836235263904e-06, "loss": 0.43, "step": 434 }, { "epoch": 1.389776357827476, "grad_norm": 0.7605991726766619, "learning_rate": 6.491951525598461e-06, "loss": 0.4376, "step": 435 }, { "epoch": 1.3929712460063897, "grad_norm": 0.7319141260491483, "learning_rate": 6.4741988052071965e-06, "loss": 0.4082, "step": 436 }, { "epoch": 1.3961661341853036, "grad_norm": 0.7643694519158192, "learning_rate": 6.45642570773914e-06, "loss": 0.4081, "step": 437 }, { "epoch": 1.3993610223642172, "grad_norm": 0.722337242212863, "learning_rate": 6.438632478862495e-06, "loss": 0.3884, "step": 438 }, { "epoch": 1.4025559105431311, "grad_norm": 0.7849520980727834, "learning_rate": 6.4208193645237314e-06, "loss": 0.4201, "step": 439 }, { "epoch": 1.4057507987220448, "grad_norm": 0.7276635927449195, "learning_rate": 6.402986610944183e-06, "loss": 0.4186, "step": 440 }, { "epoch": 1.4089456869009584, "grad_norm": 0.6751798380993322, "learning_rate": 6.385134464616649e-06, "loss": 0.4304, "step": 441 }, { "epoch": 1.4121405750798721, "grad_norm": 0.7202423850482267, "learning_rate": 6.367263172301985e-06, "loss": 0.3789, "step": 442 }, { "epoch": 1.415335463258786, "grad_norm": 0.6077196826039813, "learning_rate": 6.3493729810256895e-06, "loss": 0.4144, "step": 443 }, { "epoch": 1.4185303514376997, "grad_norm": 0.738843433648205, "learning_rate": 6.331464138074493e-06, "loss": 0.4115, "step": 444 }, { "epoch": 1.4217252396166133, "grad_norm": 0.7241332647195087, "learning_rate": 6.313536890992935e-06, "loss": 0.3836, "step": 445 }, { "epoch": 1.4249201277955272, "grad_norm": 0.8509078562677063, "learning_rate": 6.29559148757995e-06, "loss": 0.4541, "step": 446 }, { "epoch": 1.428115015974441, "grad_norm": 0.7499421473333086, "learning_rate": 6.277628175885437e-06, "loss": 0.4169, "step": 447 }, { "epoch": 1.4313099041533546, "grad_norm": 0.7763796937501032, "learning_rate": 6.2596472042068275e-06, "loss": 0.4611, "step": 448 }, { "epoch": 1.4345047923322682, "grad_norm": 0.7284959387032885, "learning_rate": 6.241648821085666e-06, "loss": 0.4042, "step": 449 }, { "epoch": 1.4376996805111821, "grad_norm": 0.7181894634050568, "learning_rate": 6.223633275304157e-06, "loss": 0.4181, "step": 450 }, { "epoch": 1.4408945686900958, "grad_norm": 0.847329054523862, "learning_rate": 6.205600815881741e-06, "loss": 0.4005, "step": 451 }, { "epoch": 1.4440894568690097, "grad_norm": 0.7232793981095568, "learning_rate": 6.187551692071648e-06, "loss": 0.3917, "step": 452 }, { "epoch": 1.4472843450479234, "grad_norm": 0.7226887302856251, "learning_rate": 6.1694861533574445e-06, "loss": 0.3711, "step": 453 }, { "epoch": 1.450479233226837, "grad_norm": 0.73844581553021, "learning_rate": 6.1514044494496e-06, "loss": 0.3914, "step": 454 }, { "epoch": 1.4536741214057507, "grad_norm": 0.7328173367904206, "learning_rate": 6.133306830282021e-06, "loss": 0.4771, "step": 455 }, { "epoch": 1.4568690095846646, "grad_norm": 0.739099444257498, "learning_rate": 6.115193546008602e-06, "loss": 0.4165, "step": 456 }, { "epoch": 1.4600638977635783, "grad_norm": 0.7949971330404686, "learning_rate": 6.097064846999774e-06, "loss": 0.4246, "step": 457 }, { "epoch": 1.4632587859424921, "grad_norm": 0.6791102624208766, "learning_rate": 6.078920983839032e-06, "loss": 0.4192, "step": 458 }, { "epoch": 1.4664536741214058, "grad_norm": 0.8073479673710802, "learning_rate": 6.060762207319479e-06, "loss": 0.4323, "step": 459 }, { "epoch": 1.4696485623003195, "grad_norm": 0.6804863979605771, "learning_rate": 6.042588768440358e-06, "loss": 0.4133, "step": 460 }, { "epoch": 1.4728434504792332, "grad_norm": 0.7145970218309506, "learning_rate": 6.024400918403581e-06, "loss": 0.3918, "step": 461 }, { "epoch": 1.476038338658147, "grad_norm": 0.6698235274017075, "learning_rate": 6.006198908610261e-06, "loss": 0.373, "step": 462 }, { "epoch": 1.4792332268370607, "grad_norm": 0.7733574722542599, "learning_rate": 5.987982990657229e-06, "loss": 0.437, "step": 463 }, { "epoch": 1.4824281150159744, "grad_norm": 0.6873053845458954, "learning_rate": 5.9697534163335645e-06, "loss": 0.4473, "step": 464 }, { "epoch": 1.4856230031948883, "grad_norm": 0.7360613158414427, "learning_rate": 5.95151043761711e-06, "loss": 0.4101, "step": 465 }, { "epoch": 1.488817891373802, "grad_norm": 0.7023303887076119, "learning_rate": 5.933254306670995e-06, "loss": 0.4193, "step": 466 }, { "epoch": 1.4920127795527156, "grad_norm": 0.6097269330396781, "learning_rate": 5.914985275840135e-06, "loss": 0.423, "step": 467 }, { "epoch": 1.4952076677316293, "grad_norm": 0.7537445735676624, "learning_rate": 5.896703597647765e-06, "loss": 0.3946, "step": 468 }, { "epoch": 1.4984025559105432, "grad_norm": 0.6616967609184584, "learning_rate": 5.878409524791931e-06, "loss": 0.4284, "step": 469 }, { "epoch": 1.5015974440894568, "grad_norm": 0.752495801790809, "learning_rate": 5.8601033101420055e-06, "loss": 0.4088, "step": 470 }, { "epoch": 1.5047923322683707, "grad_norm": 0.7741168142210769, "learning_rate": 5.841785206735192e-06, "loss": 0.3907, "step": 471 }, { "epoch": 1.5079872204472844, "grad_norm": 0.6406185492300456, "learning_rate": 5.823455467773027e-06, "loss": 0.3849, "step": 472 }, { "epoch": 1.511182108626198, "grad_norm": 0.6778501202960715, "learning_rate": 5.805114346617874e-06, "loss": 0.4269, "step": 473 }, { "epoch": 1.5143769968051117, "grad_norm": 0.7392061873417373, "learning_rate": 5.786762096789431e-06, "loss": 0.4127, "step": 474 }, { "epoch": 1.5175718849840254, "grad_norm": 0.7388450985889835, "learning_rate": 5.768398971961221e-06, "loss": 0.358, "step": 475 }, { "epoch": 1.5207667731629393, "grad_norm": 0.655106266677778, "learning_rate": 5.750025225957086e-06, "loss": 0.4013, "step": 476 }, { "epoch": 1.5239616613418532, "grad_norm": 0.6419997806479123, "learning_rate": 5.731641112747679e-06, "loss": 0.4178, "step": 477 }, { "epoch": 1.5271565495207668, "grad_norm": 0.5916675647122845, "learning_rate": 5.713246886446954e-06, "loss": 0.4074, "step": 478 }, { "epoch": 1.5303514376996805, "grad_norm": 0.7409131229492478, "learning_rate": 5.694842801308651e-06, "loss": 0.4265, "step": 479 }, { "epoch": 1.5335463258785942, "grad_norm": 0.6924800181246356, "learning_rate": 5.676429111722786e-06, "loss": 0.4319, "step": 480 }, { "epoch": 1.5367412140575079, "grad_norm": 0.6384862154935599, "learning_rate": 5.6580060722121325e-06, "loss": 0.4451, "step": 481 }, { "epoch": 1.5399361022364217, "grad_norm": 0.6020575738289815, "learning_rate": 5.639573937428699e-06, "loss": 0.4583, "step": 482 }, { "epoch": 1.5431309904153354, "grad_norm": 0.7242056238178548, "learning_rate": 5.621132962150216e-06, "loss": 0.378, "step": 483 }, { "epoch": 1.5463258785942493, "grad_norm": 0.7557911284079408, "learning_rate": 5.6026834012766155e-06, "loss": 0.4267, "step": 484 }, { "epoch": 1.549520766773163, "grad_norm": 0.7095401782411899, "learning_rate": 5.584225509826497e-06, "loss": 0.3909, "step": 485 }, { "epoch": 1.5527156549520766, "grad_norm": 0.7881660312713781, "learning_rate": 5.565759542933612e-06, "loss": 0.4146, "step": 486 }, { "epoch": 1.5559105431309903, "grad_norm": 0.6862528849699476, "learning_rate": 5.547285755843334e-06, "loss": 0.4191, "step": 487 }, { "epoch": 1.5591054313099042, "grad_norm": 0.6513704867306412, "learning_rate": 5.5288044039091335e-06, "loss": 0.4014, "step": 488 }, { "epoch": 1.5623003194888179, "grad_norm": 0.6820165967193221, "learning_rate": 5.510315742589042e-06, "loss": 0.4625, "step": 489 }, { "epoch": 1.5654952076677318, "grad_norm": 0.6813253610979702, "learning_rate": 5.491820027442126e-06, "loss": 0.3698, "step": 490 }, { "epoch": 1.5686900958466454, "grad_norm": 0.6207775366733131, "learning_rate": 5.473317514124958e-06, "loss": 0.4226, "step": 491 }, { "epoch": 1.571884984025559, "grad_norm": 0.7219582547757427, "learning_rate": 5.454808458388069e-06, "loss": 0.3577, "step": 492 }, { "epoch": 1.5750798722044728, "grad_norm": 0.587531289408549, "learning_rate": 5.436293116072431e-06, "loss": 0.4408, "step": 493 }, { "epoch": 1.5782747603833864, "grad_norm": 0.5936564578931848, "learning_rate": 5.417771743105908e-06, "loss": 0.3885, "step": 494 }, { "epoch": 1.5814696485623003, "grad_norm": 0.6256323503523564, "learning_rate": 5.399244595499721e-06, "loss": 0.3866, "step": 495 }, { "epoch": 1.5846645367412142, "grad_norm": 0.6985126034785164, "learning_rate": 5.380711929344915e-06, "loss": 0.4288, "step": 496 }, { "epoch": 1.5878594249201279, "grad_norm": 0.6558224942187812, "learning_rate": 5.362174000808813e-06, "loss": 0.4128, "step": 497 }, { "epoch": 1.5910543130990416, "grad_norm": 0.7059041917135856, "learning_rate": 5.343631066131476e-06, "loss": 0.4302, "step": 498 }, { "epoch": 1.5942492012779552, "grad_norm": 0.6947594122866555, "learning_rate": 5.325083381622165e-06, "loss": 0.401, "step": 499 }, { "epoch": 1.5974440894568689, "grad_norm": 0.6832288077833533, "learning_rate": 5.30653120365579e-06, "loss": 0.4533, "step": 500 }, { "epoch": 1.6006389776357828, "grad_norm": 0.762224714736928, "learning_rate": 5.28797478866938e-06, "loss": 0.4358, "step": 501 }, { "epoch": 1.6038338658146964, "grad_norm": 0.8092440212010764, "learning_rate": 5.269414393158523e-06, "loss": 0.3818, "step": 502 }, { "epoch": 1.6070287539936103, "grad_norm": 0.6376129418611447, "learning_rate": 5.250850273673831e-06, "loss": 0.3758, "step": 503 }, { "epoch": 1.610223642172524, "grad_norm": 0.6767891876418427, "learning_rate": 5.232282686817392e-06, "loss": 0.4082, "step": 504 }, { "epoch": 1.6134185303514377, "grad_norm": 0.6922410705874523, "learning_rate": 5.213711889239214e-06, "loss": 0.4136, "step": 505 }, { "epoch": 1.6166134185303513, "grad_norm": 0.7054447503164165, "learning_rate": 5.195138137633695e-06, "loss": 0.4522, "step": 506 }, { "epoch": 1.619808306709265, "grad_norm": 0.6668419928190755, "learning_rate": 5.17656168873606e-06, "loss": 0.3966, "step": 507 }, { "epoch": 1.623003194888179, "grad_norm": 0.725965975535835, "learning_rate": 5.157982799318817e-06, "loss": 0.3691, "step": 508 }, { "epoch": 1.6261980830670928, "grad_norm": 0.7243890485488652, "learning_rate": 5.139401726188208e-06, "loss": 0.3885, "step": 509 }, { "epoch": 1.6293929712460065, "grad_norm": 0.6514265757359697, "learning_rate": 5.120818726180662e-06, "loss": 0.3729, "step": 510 }, { "epoch": 1.6325878594249201, "grad_norm": 0.7542793277756046, "learning_rate": 5.1022340561592396e-06, "loss": 0.4298, "step": 511 }, { "epoch": 1.6357827476038338, "grad_norm": 0.7727874769900948, "learning_rate": 5.083647973010085e-06, "loss": 0.4047, "step": 512 }, { "epoch": 1.6389776357827475, "grad_norm": 0.77685653742761, "learning_rate": 5.065060733638878e-06, "loss": 0.4556, "step": 513 }, { "epoch": 1.6421725239616614, "grad_norm": 0.727081945835971, "learning_rate": 5.046472594967279e-06, "loss": 0.3998, "step": 514 }, { "epoch": 1.645367412140575, "grad_norm": 0.6201784166139842, "learning_rate": 5.027883813929374e-06, "loss": 0.3983, "step": 515 }, { "epoch": 1.648562300319489, "grad_norm": 0.6293419628548934, "learning_rate": 5.009294647468137e-06, "loss": 0.4013, "step": 516 }, { "epoch": 1.6517571884984026, "grad_norm": 0.6657061153428472, "learning_rate": 4.990705352531864e-06, "loss": 0.3764, "step": 517 }, { "epoch": 1.6549520766773163, "grad_norm": 0.7353093271163771, "learning_rate": 4.972116186070626e-06, "loss": 0.4076, "step": 518 }, { "epoch": 1.65814696485623, "grad_norm": 0.6983863986741474, "learning_rate": 4.953527405032723e-06, "loss": 0.3882, "step": 519 }, { "epoch": 1.6613418530351438, "grad_norm": 0.7717442178352649, "learning_rate": 4.934939266361123e-06, "loss": 0.412, "step": 520 }, { "epoch": 1.6645367412140575, "grad_norm": 0.7813215600588967, "learning_rate": 4.916352026989914e-06, "loss": 0.4301, "step": 521 }, { "epoch": 1.6677316293929714, "grad_norm": 0.6636520728805212, "learning_rate": 4.897765943840761e-06, "loss": 0.3977, "step": 522 }, { "epoch": 1.670926517571885, "grad_norm": 0.7979382389574217, "learning_rate": 4.87918127381934e-06, "loss": 0.4131, "step": 523 }, { "epoch": 1.6741214057507987, "grad_norm": 0.7142829720788711, "learning_rate": 4.860598273811793e-06, "loss": 0.4427, "step": 524 }, { "epoch": 1.6773162939297124, "grad_norm": 0.719461762977339, "learning_rate": 4.842017200681185e-06, "loss": 0.3764, "step": 525 }, { "epoch": 1.680511182108626, "grad_norm": 0.7030911473478874, "learning_rate": 4.823438311263943e-06, "loss": 0.4515, "step": 526 }, { "epoch": 1.68370607028754, "grad_norm": 0.6773019245318261, "learning_rate": 4.804861862366306e-06, "loss": 0.3632, "step": 527 }, { "epoch": 1.6869009584664538, "grad_norm": 0.6222261749245824, "learning_rate": 4.786288110760787e-06, "loss": 0.4396, "step": 528 }, { "epoch": 1.6900958466453675, "grad_norm": 0.6310219300708585, "learning_rate": 4.767717313182611e-06, "loss": 0.4233, "step": 529 }, { "epoch": 1.6932907348242812, "grad_norm": 0.6345900048229579, "learning_rate": 4.74914972632617e-06, "loss": 0.4146, "step": 530 }, { "epoch": 1.6964856230031948, "grad_norm": 0.8515608156634364, "learning_rate": 4.730585606841479e-06, "loss": 0.4206, "step": 531 }, { "epoch": 1.6996805111821085, "grad_norm": 0.7405010020462823, "learning_rate": 4.7120252113306216e-06, "loss": 0.4514, "step": 532 }, { "epoch": 1.7028753993610224, "grad_norm": 0.7009601501256475, "learning_rate": 4.693468796344211e-06, "loss": 0.4437, "step": 533 }, { "epoch": 1.706070287539936, "grad_norm": 0.7896649309522711, "learning_rate": 4.6749166183778375e-06, "loss": 0.4411, "step": 534 }, { "epoch": 1.70926517571885, "grad_norm": 0.66481894530652, "learning_rate": 4.656368933868525e-06, "loss": 0.4003, "step": 535 }, { "epoch": 1.7124600638977636, "grad_norm": 0.6803181892467599, "learning_rate": 4.637825999191189e-06, "loss": 0.4078, "step": 536 }, { "epoch": 1.7156549520766773, "grad_norm": 0.7907155834251054, "learning_rate": 4.619288070655086e-06, "loss": 0.3947, "step": 537 }, { "epoch": 1.718849840255591, "grad_norm": 0.6202721344766233, "learning_rate": 4.600755404500281e-06, "loss": 0.384, "step": 538 }, { "epoch": 1.7220447284345048, "grad_norm": 0.6323756992860589, "learning_rate": 4.582228256894093e-06, "loss": 0.4088, "step": 539 }, { "epoch": 1.7252396166134185, "grad_norm": 0.8071309721816631, "learning_rate": 4.56370688392757e-06, "loss": 0.4265, "step": 540 }, { "epoch": 1.7284345047923324, "grad_norm": 0.6983078682901872, "learning_rate": 4.545191541611933e-06, "loss": 0.4343, "step": 541 }, { "epoch": 1.731629392971246, "grad_norm": 0.7064389255875589, "learning_rate": 4.526682485875044e-06, "loss": 0.4311, "step": 542 }, { "epoch": 1.7348242811501597, "grad_norm": 0.686557281979509, "learning_rate": 4.508179972557875e-06, "loss": 0.4624, "step": 543 }, { "epoch": 1.7380191693290734, "grad_norm": 0.6391560477651345, "learning_rate": 4.489684257410959e-06, "loss": 0.3948, "step": 544 }, { "epoch": 1.741214057507987, "grad_norm": 0.7274004317464743, "learning_rate": 4.471195596090867e-06, "loss": 0.4383, "step": 545 }, { "epoch": 1.744408945686901, "grad_norm": 0.671746811039263, "learning_rate": 4.452714244156667e-06, "loss": 0.4214, "step": 546 }, { "epoch": 1.7476038338658149, "grad_norm": 0.711865936170259, "learning_rate": 4.434240457066388e-06, "loss": 0.4467, "step": 547 }, { "epoch": 1.7507987220447285, "grad_norm": 0.6189430505826393, "learning_rate": 4.415774490173504e-06, "loss": 0.4564, "step": 548 }, { "epoch": 1.7539936102236422, "grad_norm": 0.6910611899978649, "learning_rate": 4.397316598723385e-06, "loss": 0.3772, "step": 549 }, { "epoch": 1.7571884984025559, "grad_norm": 0.6304070800723548, "learning_rate": 4.3788670378497836e-06, "loss": 0.4319, "step": 550 }, { "epoch": 1.7603833865814695, "grad_norm": 0.7333431181761982, "learning_rate": 4.360426062571303e-06, "loss": 0.4113, "step": 551 }, { "epoch": 1.7635782747603834, "grad_norm": 0.6622969583504559, "learning_rate": 4.341993927787871e-06, "loss": 0.4356, "step": 552 }, { "epoch": 1.766773162939297, "grad_norm": 0.6471194513704625, "learning_rate": 4.323570888277215e-06, "loss": 0.3546, "step": 553 }, { "epoch": 1.769968051118211, "grad_norm": 0.6810785974779886, "learning_rate": 4.305157198691351e-06, "loss": 0.4073, "step": 554 }, { "epoch": 1.7731629392971247, "grad_norm": 0.7339503997464327, "learning_rate": 4.286753113553049e-06, "loss": 0.4656, "step": 555 }, { "epoch": 1.7763578274760383, "grad_norm": 0.6489710558856068, "learning_rate": 4.268358887252322e-06, "loss": 0.3985, "step": 556 }, { "epoch": 1.779552715654952, "grad_norm": 0.718662578260408, "learning_rate": 4.249974774042915e-06, "loss": 0.3576, "step": 557 }, { "epoch": 1.7827476038338657, "grad_norm": 0.738057529915224, "learning_rate": 4.231601028038781e-06, "loss": 0.4163, "step": 558 }, { "epoch": 1.7859424920127795, "grad_norm": 0.6705392426998533, "learning_rate": 4.2132379032105695e-06, "loss": 0.3962, "step": 559 }, { "epoch": 1.7891373801916934, "grad_norm": 0.7591308369500366, "learning_rate": 4.194885653382128e-06, "loss": 0.4214, "step": 560 }, { "epoch": 1.792332268370607, "grad_norm": 0.6420351490088527, "learning_rate": 4.176544532226974e-06, "loss": 0.423, "step": 561 }, { "epoch": 1.7955271565495208, "grad_norm": 0.6691805563891343, "learning_rate": 4.158214793264808e-06, "loss": 0.4048, "step": 562 }, { "epoch": 1.7987220447284344, "grad_norm": 0.795969904519421, "learning_rate": 4.139896689857995e-06, "loss": 0.4095, "step": 563 }, { "epoch": 1.8019169329073481, "grad_norm": 0.6883215009844186, "learning_rate": 4.121590475208071e-06, "loss": 0.3969, "step": 564 }, { "epoch": 1.805111821086262, "grad_norm": 0.636119055044423, "learning_rate": 4.1032964023522366e-06, "loss": 0.4361, "step": 565 }, { "epoch": 1.8083067092651757, "grad_norm": 0.7202448770364853, "learning_rate": 4.085014724159866e-06, "loss": 0.3922, "step": 566 }, { "epoch": 1.8115015974440896, "grad_norm": 0.6465617444869258, "learning_rate": 4.066745693329008e-06, "loss": 0.4258, "step": 567 }, { "epoch": 1.8146964856230032, "grad_norm": 0.7002728972461814, "learning_rate": 4.0484895623828906e-06, "loss": 0.464, "step": 568 }, { "epoch": 1.817891373801917, "grad_norm": 0.7864770283392628, "learning_rate": 4.030246583666437e-06, "loss": 0.4247, "step": 569 }, { "epoch": 1.8210862619808306, "grad_norm": 0.6572550114907124, "learning_rate": 4.012017009342773e-06, "loss": 0.3674, "step": 570 }, { "epoch": 1.8242811501597445, "grad_norm": 0.6482078420972358, "learning_rate": 3.99380109138974e-06, "loss": 0.426, "step": 571 }, { "epoch": 1.8274760383386581, "grad_norm": 0.6089049101637908, "learning_rate": 3.97559908159642e-06, "loss": 0.4648, "step": 572 }, { "epoch": 1.830670926517572, "grad_norm": 0.654869830004242, "learning_rate": 3.9574112315596425e-06, "loss": 0.4081, "step": 573 }, { "epoch": 1.8338658146964857, "grad_norm": 0.6766372004787461, "learning_rate": 3.9392377926805226e-06, "loss": 0.3991, "step": 574 }, { "epoch": 1.8370607028753994, "grad_norm": 0.6156484093536729, "learning_rate": 3.92107901616097e-06, "loss": 0.4051, "step": 575 }, { "epoch": 1.840255591054313, "grad_norm": 0.7209332365753569, "learning_rate": 3.9029351530002264e-06, "loss": 0.4325, "step": 576 }, { "epoch": 1.8434504792332267, "grad_norm": 0.6884876431700547, "learning_rate": 3.884806453991399e-06, "loss": 0.3899, "step": 577 }, { "epoch": 1.8466453674121406, "grad_norm": 0.6895779669790771, "learning_rate": 3.866693169717982e-06, "loss": 0.4257, "step": 578 }, { "epoch": 1.8498402555910545, "grad_norm": 0.591765095160724, "learning_rate": 3.848595550550401e-06, "loss": 0.4319, "step": 579 }, { "epoch": 1.8530351437699681, "grad_norm": 0.6890579406960579, "learning_rate": 3.830513846642556e-06, "loss": 0.4109, "step": 580 }, { "epoch": 1.8562300319488818, "grad_norm": 0.6475782916684093, "learning_rate": 3.8124483079283546e-06, "loss": 0.3852, "step": 581 }, { "epoch": 1.8594249201277955, "grad_norm": 0.6079636893365562, "learning_rate": 3.7943991841182586e-06, "loss": 0.4199, "step": 582 }, { "epoch": 1.8626198083067091, "grad_norm": 0.5989261528100488, "learning_rate": 3.7763667246958447e-06, "loss": 0.3634, "step": 583 }, { "epoch": 1.865814696485623, "grad_norm": 0.7170408623649442, "learning_rate": 3.758351178914336e-06, "loss": 0.4269, "step": 584 }, { "epoch": 1.8690095846645367, "grad_norm": 0.6802970749740577, "learning_rate": 3.7403527957931716e-06, "loss": 0.4, "step": 585 }, { "epoch": 1.8722044728434506, "grad_norm": 0.7045362752006943, "learning_rate": 3.7223718241145646e-06, "loss": 0.4146, "step": 586 }, { "epoch": 1.8753993610223643, "grad_norm": 0.7431509526456225, "learning_rate": 3.7044085124200517e-06, "loss": 0.3965, "step": 587 }, { "epoch": 1.878594249201278, "grad_norm": 0.7345778010151496, "learning_rate": 3.6864631090070656e-06, "loss": 0.3875, "step": 588 }, { "epoch": 1.8817891373801916, "grad_norm": 0.6242646310295729, "learning_rate": 3.668535861925509e-06, "loss": 0.3929, "step": 589 }, { "epoch": 1.8849840255591053, "grad_norm": 0.807998432581044, "learning_rate": 3.650627018974312e-06, "loss": 0.4604, "step": 590 }, { "epoch": 1.8881789137380192, "grad_norm": 0.7330025954364637, "learning_rate": 3.632736827698015e-06, "loss": 0.3935, "step": 591 }, { "epoch": 1.891373801916933, "grad_norm": 0.6709313587984049, "learning_rate": 3.6148655353833518e-06, "loss": 0.4509, "step": 592 }, { "epoch": 1.8945686900958467, "grad_norm": 0.5919122845314795, "learning_rate": 3.5970133890558184e-06, "loss": 0.3787, "step": 593 }, { "epoch": 1.8977635782747604, "grad_norm": 0.6565056726940224, "learning_rate": 3.5791806354762702e-06, "loss": 0.4142, "step": 594 }, { "epoch": 1.900958466453674, "grad_norm": 0.6240820286909862, "learning_rate": 3.5613675211375066e-06, "loss": 0.4014, "step": 595 }, { "epoch": 1.9041533546325877, "grad_norm": 0.618594688160155, "learning_rate": 3.5435742922608618e-06, "loss": 0.4526, "step": 596 }, { "epoch": 1.9073482428115016, "grad_norm": 0.6258816708488183, "learning_rate": 3.525801194792805e-06, "loss": 0.3905, "step": 597 }, { "epoch": 1.9105431309904153, "grad_norm": 0.6273674561595595, "learning_rate": 3.508048474401541e-06, "loss": 0.421, "step": 598 }, { "epoch": 1.9137380191693292, "grad_norm": 0.7106954736201235, "learning_rate": 3.4903163764736104e-06, "loss": 0.4552, "step": 599 }, { "epoch": 1.9169329073482428, "grad_norm": 0.685935308297769, "learning_rate": 3.4726051461105016e-06, "loss": 0.4295, "step": 600 }, { "epoch": 1.9201277955271565, "grad_norm": 0.7048971741463542, "learning_rate": 3.4549150281252635e-06, "loss": 0.4589, "step": 601 }, { "epoch": 1.9233226837060702, "grad_norm": 0.6779199644574317, "learning_rate": 3.437246267039115e-06, "loss": 0.3862, "step": 602 }, { "epoch": 1.926517571884984, "grad_norm": 0.6370062532929827, "learning_rate": 3.419599107078073e-06, "loss": 0.4318, "step": 603 }, { "epoch": 1.9297124600638977, "grad_norm": 0.6664293929584083, "learning_rate": 3.401973792169574e-06, "loss": 0.4114, "step": 604 }, { "epoch": 1.9329073482428116, "grad_norm": 0.6801661249853935, "learning_rate": 3.384370565939098e-06, "loss": 0.4056, "step": 605 }, { "epoch": 1.9361022364217253, "grad_norm": 0.6088422098648698, "learning_rate": 3.3667896717068105e-06, "loss": 0.4354, "step": 606 }, { "epoch": 1.939297124600639, "grad_norm": 0.604568022948054, "learning_rate": 3.34923135248419e-06, "loss": 0.4406, "step": 607 }, { "epoch": 1.9424920127795526, "grad_norm": 0.6480032914789063, "learning_rate": 3.33169585097067e-06, "loss": 0.3947, "step": 608 }, { "epoch": 1.9456869009584663, "grad_norm": 0.6813468114241855, "learning_rate": 3.314183409550293e-06, "loss": 0.4278, "step": 609 }, { "epoch": 1.9488817891373802, "grad_norm": 0.6963996997813214, "learning_rate": 3.2966942702883494e-06, "loss": 0.4375, "step": 610 }, { "epoch": 1.952076677316294, "grad_norm": 0.6666051546482046, "learning_rate": 3.279228674928035e-06, "loss": 0.3713, "step": 611 }, { "epoch": 1.9552715654952078, "grad_norm": 0.6465525719691291, "learning_rate": 3.261786864887117e-06, "loss": 0.4502, "step": 612 }, { "epoch": 1.9584664536741214, "grad_norm": 0.6823761874452812, "learning_rate": 3.244369081254585e-06, "loss": 0.4154, "step": 613 }, { "epoch": 1.961661341853035, "grad_norm": 0.7074455898920645, "learning_rate": 3.226975564787322e-06, "loss": 0.4445, "step": 614 }, { "epoch": 1.9648562300319488, "grad_norm": 0.767027927273249, "learning_rate": 3.209606555906788e-06, "loss": 0.3778, "step": 615 }, { "epoch": 1.9680511182108626, "grad_norm": 0.7511580726189006, "learning_rate": 3.192262294695679e-06, "loss": 0.4058, "step": 616 }, { "epoch": 1.9712460063897763, "grad_norm": 0.6400233820575995, "learning_rate": 3.174943020894618e-06, "loss": 0.4111, "step": 617 }, { "epoch": 1.9744408945686902, "grad_norm": 0.6063251534219226, "learning_rate": 3.1576489738988457e-06, "loss": 0.3939, "step": 618 }, { "epoch": 1.9776357827476039, "grad_norm": 0.7399192760884882, "learning_rate": 3.140380392754901e-06, "loss": 0.4171, "step": 619 }, { "epoch": 1.9808306709265175, "grad_norm": 0.6044585985743741, "learning_rate": 3.12313751615732e-06, "loss": 0.4044, "step": 620 }, { "epoch": 1.9840255591054312, "grad_norm": 0.6646425537074524, "learning_rate": 3.1059205824453446e-06, "loss": 0.4111, "step": 621 }, { "epoch": 1.9872204472843449, "grad_norm": 0.7426412039388861, "learning_rate": 3.0887298295996183e-06, "loss": 0.4106, "step": 622 }, { "epoch": 1.9904153354632588, "grad_norm": 0.7001604424708607, "learning_rate": 3.0715654952388957e-06, "loss": 0.4245, "step": 623 }, { "epoch": 1.9936102236421727, "grad_norm": 0.6520937772952098, "learning_rate": 3.054427816616773e-06, "loss": 0.4505, "step": 624 }, { "epoch": 1.9968051118210863, "grad_norm": 0.6491525580746756, "learning_rate": 3.0373170306183885e-06, "loss": 0.3938, "step": 625 }, { "epoch": 2.0, "grad_norm": 0.6087684003574786, "learning_rate": 3.020233373757162e-06, "loss": 0.3807, "step": 626 }, { "epoch": 2.0031948881789137, "grad_norm": 0.796879751420443, "learning_rate": 3.0031770821715233e-06, "loss": 0.3505, "step": 627 }, { "epoch": 2.0063897763578273, "grad_norm": 0.6970718865013494, "learning_rate": 2.9861483916216404e-06, "loss": 0.3527, "step": 628 }, { "epoch": 2.009584664536741, "grad_norm": 0.7046188469203205, "learning_rate": 2.969147537486175e-06, "loss": 0.3574, "step": 629 }, { "epoch": 2.012779552715655, "grad_norm": 0.6005350583532081, "learning_rate": 2.952174754759012e-06, "loss": 0.3127, "step": 630 }, { "epoch": 2.015974440894569, "grad_norm": 0.7209443417400784, "learning_rate": 2.935230278046025e-06, "loss": 0.3729, "step": 631 }, { "epoch": 2.0191693290734825, "grad_norm": 0.8211482482920919, "learning_rate": 2.9183143415618297e-06, "loss": 0.319, "step": 632 }, { "epoch": 2.022364217252396, "grad_norm": 0.809977750202282, "learning_rate": 2.9014271791265403e-06, "loss": 0.3497, "step": 633 }, { "epoch": 2.02555910543131, "grad_norm": 0.6927159562036598, "learning_rate": 2.8845690241625437e-06, "loss": 0.3024, "step": 634 }, { "epoch": 2.0287539936102235, "grad_norm": 0.668355825951265, "learning_rate": 2.867740109691277e-06, "loss": 0.3549, "step": 635 }, { "epoch": 2.0319488817891376, "grad_norm": 0.6321723989880009, "learning_rate": 2.850940668329996e-06, "loss": 0.33, "step": 636 }, { "epoch": 2.0351437699680512, "grad_norm": 0.6012009576345978, "learning_rate": 2.8341709322885624e-06, "loss": 0.3694, "step": 637 }, { "epoch": 2.038338658146965, "grad_norm": 0.6253436415906143, "learning_rate": 2.817431133366246e-06, "loss": 0.3398, "step": 638 }, { "epoch": 2.0415335463258786, "grad_norm": 0.6206197586366787, "learning_rate": 2.800721502948506e-06, "loss": 0.3874, "step": 639 }, { "epoch": 2.0447284345047922, "grad_norm": 0.7037107523881407, "learning_rate": 2.7840422720037943e-06, "loss": 0.3482, "step": 640 }, { "epoch": 2.047923322683706, "grad_norm": 0.6125405702932848, "learning_rate": 2.767393671080376e-06, "loss": 0.3626, "step": 641 }, { "epoch": 2.0511182108626196, "grad_norm": 0.6626098393166985, "learning_rate": 2.7507759303031257e-06, "loss": 0.355, "step": 642 }, { "epoch": 2.0543130990415337, "grad_norm": 0.6089018851505401, "learning_rate": 2.7341892793703594e-06, "loss": 0.3335, "step": 643 }, { "epoch": 2.0575079872204474, "grad_norm": 0.6251075562703512, "learning_rate": 2.7176339475506515e-06, "loss": 0.3276, "step": 644 }, { "epoch": 2.060702875399361, "grad_norm": 0.6414220113333703, "learning_rate": 2.7011101636796677e-06, "loss": 0.3414, "step": 645 }, { "epoch": 2.0638977635782747, "grad_norm": 0.6394774601567328, "learning_rate": 2.6846181561570085e-06, "loss": 0.3493, "step": 646 }, { "epoch": 2.0670926517571884, "grad_norm": 0.6872192296218651, "learning_rate": 2.668158152943039e-06, "loss": 0.3652, "step": 647 }, { "epoch": 2.070287539936102, "grad_norm": 0.6476410999573231, "learning_rate": 2.651730381555754e-06, "loss": 0.3551, "step": 648 }, { "epoch": 2.073482428115016, "grad_norm": 0.654984785941934, "learning_rate": 2.635335069067617e-06, "loss": 0.3163, "step": 649 }, { "epoch": 2.07667731629393, "grad_norm": 0.6008860032389618, "learning_rate": 2.618972442102432e-06, "loss": 0.3125, "step": 650 }, { "epoch": 2.0798722044728435, "grad_norm": 0.5630007847350497, "learning_rate": 2.602642726832212e-06, "loss": 0.3599, "step": 651 }, { "epoch": 2.083067092651757, "grad_norm": 0.6548423010020595, "learning_rate": 2.5863461489740403e-06, "loss": 0.3545, "step": 652 }, { "epoch": 2.086261980830671, "grad_norm": 0.720979078940375, "learning_rate": 2.57008293378697e-06, "loss": 0.3461, "step": 653 }, { "epoch": 2.0894568690095845, "grad_norm": 0.6131533408331629, "learning_rate": 2.553853306068888e-06, "loss": 0.3184, "step": 654 }, { "epoch": 2.0926517571884986, "grad_norm": 0.7007832032216074, "learning_rate": 2.5376574901534303e-06, "loss": 0.328, "step": 655 }, { "epoch": 2.0958466453674123, "grad_norm": 0.6545588991789442, "learning_rate": 2.5214957099068613e-06, "loss": 0.2982, "step": 656 }, { "epoch": 2.099041533546326, "grad_norm": 0.5863148928130069, "learning_rate": 2.5053681887249916e-06, "loss": 0.3363, "step": 657 }, { "epoch": 2.1022364217252396, "grad_norm": 0.5301073800260551, "learning_rate": 2.4892751495300893e-06, "loss": 0.3115, "step": 658 }, { "epoch": 2.1054313099041533, "grad_norm": 0.6542479327855456, "learning_rate": 2.4732168147677927e-06, "loss": 0.3703, "step": 659 }, { "epoch": 2.108626198083067, "grad_norm": 0.5886520139377257, "learning_rate": 2.4571934064040364e-06, "loss": 0.3059, "step": 660 }, { "epoch": 2.1118210862619806, "grad_norm": 0.6484195186593826, "learning_rate": 2.4412051459219945e-06, "loss": 0.3342, "step": 661 }, { "epoch": 2.1150159744408947, "grad_norm": 0.6221889551743696, "learning_rate": 2.425252254319002e-06, "loss": 0.3322, "step": 662 }, { "epoch": 2.1182108626198084, "grad_norm": 0.6267777822744369, "learning_rate": 2.4093349521035105e-06, "loss": 0.3322, "step": 663 }, { "epoch": 2.121405750798722, "grad_norm": 0.6167910293671043, "learning_rate": 2.3934534592920416e-06, "loss": 0.3397, "step": 664 }, { "epoch": 2.1246006389776357, "grad_norm": 0.624875888457256, "learning_rate": 2.3776079954061385e-06, "loss": 0.3193, "step": 665 }, { "epoch": 2.1277955271565494, "grad_norm": 0.5365887324860252, "learning_rate": 2.3617987794693358e-06, "loss": 0.3103, "step": 666 }, { "epoch": 2.130990415335463, "grad_norm": 0.5822223965195731, "learning_rate": 2.3460260300041355e-06, "loss": 0.3798, "step": 667 }, { "epoch": 2.134185303514377, "grad_norm": 0.5880605470571858, "learning_rate": 2.3302899650289773e-06, "loss": 0.317, "step": 668 }, { "epoch": 2.137380191693291, "grad_norm": 0.6029997324505392, "learning_rate": 2.314590802055232e-06, "loss": 0.3361, "step": 669 }, { "epoch": 2.1405750798722045, "grad_norm": 0.6879520601227666, "learning_rate": 2.2989287580841985e-06, "loss": 0.3282, "step": 670 }, { "epoch": 2.143769968051118, "grad_norm": 0.644984182089056, "learning_rate": 2.2833040496040925e-06, "loss": 0.3991, "step": 671 }, { "epoch": 2.146964856230032, "grad_norm": 0.6134578939862448, "learning_rate": 2.267716892587062e-06, "loss": 0.3324, "step": 672 }, { "epoch": 2.1501597444089455, "grad_norm": 0.619449643912175, "learning_rate": 2.252167502486205e-06, "loss": 0.3411, "step": 673 }, { "epoch": 2.1533546325878596, "grad_norm": 0.5532087352133281, "learning_rate": 2.2366560942325833e-06, "loss": 0.3841, "step": 674 }, { "epoch": 2.1565495207667733, "grad_norm": 0.574888067545758, "learning_rate": 2.2211828822322547e-06, "loss": 0.3869, "step": 675 }, { "epoch": 2.159744408945687, "grad_norm": 0.5891390751264961, "learning_rate": 2.205748080363316e-06, "loss": 0.319, "step": 676 }, { "epoch": 2.1629392971246006, "grad_norm": 0.5512648483481606, "learning_rate": 2.190351901972935e-06, "loss": 0.326, "step": 677 }, { "epoch": 2.1661341853035143, "grad_norm": 0.6477399909641972, "learning_rate": 2.1749945598744076e-06, "loss": 0.2812, "step": 678 }, { "epoch": 2.169329073482428, "grad_norm": 0.5713512138383214, "learning_rate": 2.159676266344222e-06, "loss": 0.312, "step": 679 }, { "epoch": 2.1725239616613417, "grad_norm": 0.5926489667194774, "learning_rate": 2.144397233119112e-06, "loss": 0.3057, "step": 680 }, { "epoch": 2.1757188498402558, "grad_norm": 0.6329817251734594, "learning_rate": 2.1291576713931382e-06, "loss": 0.3277, "step": 681 }, { "epoch": 2.1789137380191694, "grad_norm": 0.662841400229032, "learning_rate": 2.1139577918147715e-06, "loss": 0.3495, "step": 682 }, { "epoch": 2.182108626198083, "grad_norm": 0.5585397178700957, "learning_rate": 2.0987978044839707e-06, "loss": 0.3369, "step": 683 }, { "epoch": 2.1853035143769968, "grad_norm": 0.6043833320321034, "learning_rate": 2.0836779189492925e-06, "loss": 0.3818, "step": 684 }, { "epoch": 2.1884984025559104, "grad_norm": 0.6296409627632911, "learning_rate": 2.068598344204981e-06, "loss": 0.3485, "step": 685 }, { "epoch": 2.191693290734824, "grad_norm": 0.5920218690789573, "learning_rate": 2.053559288688086e-06, "loss": 0.3341, "step": 686 }, { "epoch": 2.194888178913738, "grad_norm": 0.5980200487693809, "learning_rate": 2.0385609602755878e-06, "loss": 0.3602, "step": 687 }, { "epoch": 2.198083067092652, "grad_norm": 0.573442518449572, "learning_rate": 2.02360356628151e-06, "loss": 0.3478, "step": 688 }, { "epoch": 2.2012779552715656, "grad_norm": 0.6391131250417024, "learning_rate": 2.0086873134540626e-06, "loss": 0.3702, "step": 689 }, { "epoch": 2.2044728434504792, "grad_norm": 0.5708177643091218, "learning_rate": 1.9938124079727874e-06, "loss": 0.4001, "step": 690 }, { "epoch": 2.207667731629393, "grad_norm": 0.5727453414449702, "learning_rate": 1.9789790554456977e-06, "loss": 0.3731, "step": 691 }, { "epoch": 2.2108626198083066, "grad_norm": 0.5379357735943615, "learning_rate": 1.9641874609064443e-06, "loss": 0.2939, "step": 692 }, { "epoch": 2.2140575079872207, "grad_norm": 0.5871823007917029, "learning_rate": 1.9494378288114816e-06, "loss": 0.3367, "step": 693 }, { "epoch": 2.2172523961661343, "grad_norm": 0.5545788841888406, "learning_rate": 1.9347303630372373e-06, "loss": 0.3841, "step": 694 }, { "epoch": 2.220447284345048, "grad_norm": 0.5809745870760499, "learning_rate": 1.9200652668772924e-06, "loss": 0.3744, "step": 695 }, { "epoch": 2.2236421725239617, "grad_norm": 0.61731448322226, "learning_rate": 1.9054427430395828e-06, "loss": 0.3337, "step": 696 }, { "epoch": 2.2268370607028753, "grad_norm": 0.6443806470537478, "learning_rate": 1.890862993643583e-06, "loss": 0.3178, "step": 697 }, { "epoch": 2.230031948881789, "grad_norm": 0.5521573052667518, "learning_rate": 1.8763262202175204e-06, "loss": 0.3031, "step": 698 }, { "epoch": 2.2332268370607027, "grad_norm": 0.6068058013107389, "learning_rate": 1.8618326236955908e-06, "loss": 0.3506, "step": 699 }, { "epoch": 2.236421725239617, "grad_norm": 0.7265520680014468, "learning_rate": 1.8473824044151762e-06, "loss": 0.3467, "step": 700 }, { "epoch": 2.2396166134185305, "grad_norm": 0.5898120244137373, "learning_rate": 1.8329757621140748e-06, "loss": 0.2709, "step": 701 }, { "epoch": 2.242811501597444, "grad_norm": 0.5982923461568086, "learning_rate": 1.81861289592775e-06, "loss": 0.359, "step": 702 }, { "epoch": 2.246006389776358, "grad_norm": 0.67972593546476, "learning_rate": 1.8042940043865658e-06, "loss": 0.3312, "step": 703 }, { "epoch": 2.2492012779552715, "grad_norm": 0.5901426297699548, "learning_rate": 1.7900192854130465e-06, "loss": 0.3302, "step": 704 }, { "epoch": 2.252396166134185, "grad_norm": 0.60108804841194, "learning_rate": 1.7757889363191484e-06, "loss": 0.3719, "step": 705 }, { "epoch": 2.255591054313099, "grad_norm": 0.6096808438842122, "learning_rate": 1.7616031538035189e-06, "loss": 0.3416, "step": 706 }, { "epoch": 2.258785942492013, "grad_norm": 0.5925477125196335, "learning_rate": 1.7474621339487925e-06, "loss": 0.2894, "step": 707 }, { "epoch": 2.2619808306709266, "grad_norm": 0.614301208774155, "learning_rate": 1.7333660722188667e-06, "loss": 0.3121, "step": 708 }, { "epoch": 2.2651757188498403, "grad_norm": 0.6007739770559021, "learning_rate": 1.7193151634562071e-06, "loss": 0.3032, "step": 709 }, { "epoch": 2.268370607028754, "grad_norm": 0.5962665238863614, "learning_rate": 1.7053096018791588e-06, "loss": 0.3448, "step": 710 }, { "epoch": 2.2715654952076676, "grad_norm": 0.6320189634924153, "learning_rate": 1.691349581079249e-06, "loss": 0.3498, "step": 711 }, { "epoch": 2.2747603833865817, "grad_norm": 0.5508132536324674, "learning_rate": 1.6774352940185269e-06, "loss": 0.319, "step": 712 }, { "epoch": 2.2779552715654954, "grad_norm": 0.5831514260830296, "learning_rate": 1.663566933026879e-06, "loss": 0.2965, "step": 713 }, { "epoch": 2.281150159744409, "grad_norm": 0.6756524107691178, "learning_rate": 1.6497446897993885e-06, "loss": 0.3431, "step": 714 }, { "epoch": 2.2843450479233227, "grad_norm": 0.629012585363301, "learning_rate": 1.6359687553936714e-06, "loss": 0.3044, "step": 715 }, { "epoch": 2.2875399361022364, "grad_norm": 0.5674347593064819, "learning_rate": 1.6222393202272414e-06, "loss": 0.3367, "step": 716 }, { "epoch": 2.29073482428115, "grad_norm": 0.5972708434410853, "learning_rate": 1.6085565740748825e-06, "loss": 0.3704, "step": 717 }, { "epoch": 2.2939297124600637, "grad_norm": 0.6370082376546686, "learning_rate": 1.5949207060660138e-06, "loss": 0.331, "step": 718 }, { "epoch": 2.297124600638978, "grad_norm": 0.6145160755163914, "learning_rate": 1.581331904682089e-06, "loss": 0.2636, "step": 719 }, { "epoch": 2.3003194888178915, "grad_norm": 0.5424418826013051, "learning_rate": 1.5677903577539806e-06, "loss": 0.3342, "step": 720 }, { "epoch": 2.303514376996805, "grad_norm": 0.5583080472065144, "learning_rate": 1.5542962524593869e-06, "loss": 0.3383, "step": 721 }, { "epoch": 2.306709265175719, "grad_norm": 0.5412287113161306, "learning_rate": 1.54084977532025e-06, "loss": 0.292, "step": 722 }, { "epoch": 2.3099041533546325, "grad_norm": 0.6030318899286576, "learning_rate": 1.5274511122001684e-06, "loss": 0.3022, "step": 723 }, { "epoch": 2.313099041533546, "grad_norm": 0.5405867270565389, "learning_rate": 1.5141004483018323e-06, "loss": 0.3472, "step": 724 }, { "epoch": 2.31629392971246, "grad_norm": 0.6308143569571145, "learning_rate": 1.5007979681644696e-06, "loss": 0.3837, "step": 725 }, { "epoch": 2.319488817891374, "grad_norm": 0.5826126513421058, "learning_rate": 1.4875438556612836e-06, "loss": 0.3448, "step": 726 }, { "epoch": 2.3226837060702876, "grad_norm": 0.6221338096279452, "learning_rate": 1.474338293996917e-06, "loss": 0.3381, "step": 727 }, { "epoch": 2.3258785942492013, "grad_norm": 0.6151988705616945, "learning_rate": 1.4611814657049257e-06, "loss": 0.3384, "step": 728 }, { "epoch": 2.329073482428115, "grad_norm": 0.5958140430045699, "learning_rate": 1.4480735526452427e-06, "loss": 0.3172, "step": 729 }, { "epoch": 2.3322683706070286, "grad_norm": 0.641656670755964, "learning_rate": 1.4350147360016743e-06, "loss": 0.3036, "step": 730 }, { "epoch": 2.3354632587859427, "grad_norm": 0.5444493599912078, "learning_rate": 1.4220051962793952e-06, "loss": 0.3685, "step": 731 }, { "epoch": 2.3386581469648564, "grad_norm": 0.6108367672947721, "learning_rate": 1.4090451133024473e-06, "loss": 0.3594, "step": 732 }, { "epoch": 2.34185303514377, "grad_norm": 0.5799568994930356, "learning_rate": 1.3961346662112585e-06, "loss": 0.3455, "step": 733 }, { "epoch": 2.3450479233226837, "grad_norm": 0.5895952335522295, "learning_rate": 1.3832740334601692e-06, "loss": 0.3454, "step": 734 }, { "epoch": 2.3482428115015974, "grad_norm": 0.5631879419117699, "learning_rate": 1.3704633928149575e-06, "loss": 0.3494, "step": 735 }, { "epoch": 2.351437699680511, "grad_norm": 0.5764377352709202, "learning_rate": 1.3577029213503911e-06, "loss": 0.3253, "step": 736 }, { "epoch": 2.3546325878594248, "grad_norm": 0.5881785734208798, "learning_rate": 1.3449927954477732e-06, "loss": 0.3962, "step": 737 }, { "epoch": 2.357827476038339, "grad_norm": 0.6095133753271015, "learning_rate": 1.3323331907925046e-06, "loss": 0.323, "step": 738 }, { "epoch": 2.3610223642172525, "grad_norm": 0.588572224896148, "learning_rate": 1.319724282371664e-06, "loss": 0.3189, "step": 739 }, { "epoch": 2.364217252396166, "grad_norm": 0.5882639679146385, "learning_rate": 1.307166244471576e-06, "loss": 0.3057, "step": 740 }, { "epoch": 2.36741214057508, "grad_norm": 0.6100840603730344, "learning_rate": 1.2946592506754097e-06, "loss": 0.3168, "step": 741 }, { "epoch": 2.3706070287539935, "grad_norm": 0.531991241724588, "learning_rate": 1.282203473860783e-06, "loss": 0.3474, "step": 742 }, { "epoch": 2.373801916932907, "grad_norm": 0.5856809075810936, "learning_rate": 1.2697990861973635e-06, "loss": 0.3608, "step": 743 }, { "epoch": 2.376996805111821, "grad_norm": 0.6568708624300119, "learning_rate": 1.257446259144494e-06, "loss": 0.3243, "step": 744 }, { "epoch": 2.380191693290735, "grad_norm": 0.5645315607240472, "learning_rate": 1.2451451634488264e-06, "loss": 0.3398, "step": 745 }, { "epoch": 2.3833865814696487, "grad_norm": 0.6351309420537445, "learning_rate": 1.2328959691419517e-06, "loss": 0.3241, "step": 746 }, { "epoch": 2.3865814696485623, "grad_norm": 0.6014845684937911, "learning_rate": 1.2206988455380558e-06, "loss": 0.3881, "step": 747 }, { "epoch": 2.389776357827476, "grad_norm": 0.5738972638891255, "learning_rate": 1.2085539612315844e-06, "loss": 0.3812, "step": 748 }, { "epoch": 2.3929712460063897, "grad_norm": 0.6190610431226268, "learning_rate": 1.1964614840949002e-06, "loss": 0.2771, "step": 749 }, { "epoch": 2.3961661341853033, "grad_norm": 0.6683751164215797, "learning_rate": 1.1844215812759708e-06, "loss": 0.3456, "step": 750 }, { "epoch": 2.3993610223642174, "grad_norm": 0.5735299842922226, "learning_rate": 1.1724344191960591e-06, "loss": 0.3288, "step": 751 }, { "epoch": 2.402555910543131, "grad_norm": 0.5263173276571057, "learning_rate": 1.1605001635474183e-06, "loss": 0.3329, "step": 752 }, { "epoch": 2.405750798722045, "grad_norm": 0.546286668746822, "learning_rate": 1.1486189792910024e-06, "loss": 0.3392, "step": 753 }, { "epoch": 2.4089456869009584, "grad_norm": 0.5782538648080976, "learning_rate": 1.1367910306541918e-06, "loss": 0.3269, "step": 754 }, { "epoch": 2.412140575079872, "grad_norm": 0.6093496989550087, "learning_rate": 1.1250164811285148e-06, "loss": 0.3638, "step": 755 }, { "epoch": 2.415335463258786, "grad_norm": 0.5735979784153206, "learning_rate": 1.1132954934673911e-06, "loss": 0.3791, "step": 756 }, { "epoch": 2.4185303514377, "grad_norm": 0.5890688098840547, "learning_rate": 1.1016282296838887e-06, "loss": 0.32, "step": 757 }, { "epoch": 2.4217252396166136, "grad_norm": 0.5863770137863203, "learning_rate": 1.090014851048473e-06, "loss": 0.3568, "step": 758 }, { "epoch": 2.4249201277955272, "grad_norm": 0.6198422389021179, "learning_rate": 1.078455518086784e-06, "loss": 0.3503, "step": 759 }, { "epoch": 2.428115015974441, "grad_norm": 0.6182003603538643, "learning_rate": 1.0669503905774198e-06, "loss": 0.276, "step": 760 }, { "epoch": 2.4313099041533546, "grad_norm": 0.5741243544821852, "learning_rate": 1.055499627549722e-06, "loss": 0.3543, "step": 761 }, { "epoch": 2.4345047923322682, "grad_norm": 0.6100024382594507, "learning_rate": 1.0441033872815804e-06, "loss": 0.3125, "step": 762 }, { "epoch": 2.437699680511182, "grad_norm": 0.5573545364538265, "learning_rate": 1.0327618272972484e-06, "loss": 0.3568, "step": 763 }, { "epoch": 2.440894568690096, "grad_norm": 0.5804442588333518, "learning_rate": 1.0214751043651582e-06, "loss": 0.3516, "step": 764 }, { "epoch": 2.4440894568690097, "grad_norm": 0.5645715954304487, "learning_rate": 1.010243374495763e-06, "loss": 0.3364, "step": 765 }, { "epoch": 2.4472843450479234, "grad_norm": 0.607743565693485, "learning_rate": 9.990667929393715e-07, "loss": 0.3504, "step": 766 }, { "epoch": 2.450479233226837, "grad_norm": 0.5358496244943224, "learning_rate": 9.879455141840067e-07, "loss": 0.3134, "step": 767 }, { "epoch": 2.4536741214057507, "grad_norm": 0.5391020845721134, "learning_rate": 9.768796919532742e-07, "loss": 0.3583, "step": 768 }, { "epoch": 2.4568690095846644, "grad_norm": 0.6072255362664878, "learning_rate": 9.658694792042284e-07, "loss": 0.3071, "step": 769 }, { "epoch": 2.460063897763578, "grad_norm": 0.5743396369605449, "learning_rate": 9.549150281252633e-07, "loss": 0.3462, "step": 770 }, { "epoch": 2.463258785942492, "grad_norm": 0.5900799064692686, "learning_rate": 9.440164901340127e-07, "loss": 0.3449, "step": 771 }, { "epoch": 2.466453674121406, "grad_norm": 0.6200473626128713, "learning_rate": 9.331740158752495e-07, "loss": 0.319, "step": 772 }, { "epoch": 2.4696485623003195, "grad_norm": 0.548623410679532, "learning_rate": 9.223877552188065e-07, "loss": 0.3401, "step": 773 }, { "epoch": 2.472843450479233, "grad_norm": 0.6543995742480747, "learning_rate": 9.116578572575091e-07, "loss": 0.285, "step": 774 }, { "epoch": 2.476038338658147, "grad_norm": 0.5299382551555714, "learning_rate": 9.009844703051063e-07, "loss": 0.3277, "step": 775 }, { "epoch": 2.479233226837061, "grad_norm": 0.8119843967078852, "learning_rate": 8.903677418942292e-07, "loss": 0.3512, "step": 776 }, { "epoch": 2.4824281150159746, "grad_norm": 0.6285438913643876, "learning_rate": 8.79807818774343e-07, "loss": 0.2908, "step": 777 }, { "epoch": 2.4856230031948883, "grad_norm": 0.585663977782034, "learning_rate": 8.693048469097293e-07, "loss": 0.389, "step": 778 }, { "epoch": 2.488817891373802, "grad_norm": 0.6289592265394592, "learning_rate": 8.58858971477457e-07, "loss": 0.3521, "step": 779 }, { "epoch": 2.4920127795527156, "grad_norm": 0.6366693928238198, "learning_rate": 8.484703368653812e-07, "loss": 0.3701, "step": 780 }, { "epoch": 2.4952076677316293, "grad_norm": 0.5782660026502604, "learning_rate": 8.381390866701517e-07, "loss": 0.3195, "step": 781 }, { "epoch": 2.498402555910543, "grad_norm": 0.5832900554761841, "learning_rate": 8.278653636952177e-07, "loss": 0.378, "step": 782 }, { "epoch": 2.501597444089457, "grad_norm": 0.5684336949228438, "learning_rate": 8.176493099488664e-07, "loss": 0.3276, "step": 783 }, { "epoch": 2.5047923322683707, "grad_norm": 0.5609191253603198, "learning_rate": 8.074910666422475e-07, "loss": 0.3247, "step": 784 }, { "epoch": 2.5079872204472844, "grad_norm": 0.5438570856558302, "learning_rate": 7.973907741874287e-07, "loss": 0.351, "step": 785 }, { "epoch": 2.511182108626198, "grad_norm": 0.6219071230831505, "learning_rate": 7.873485721954572e-07, "loss": 0.2938, "step": 786 }, { "epoch": 2.5143769968051117, "grad_norm": 0.5617327223895177, "learning_rate": 7.773645994744222e-07, "loss": 0.335, "step": 787 }, { "epoch": 2.5175718849840254, "grad_norm": 0.5473340299935876, "learning_rate": 7.674389940275406e-07, "loss": 0.3505, "step": 788 }, { "epoch": 2.520766773162939, "grad_norm": 0.5651021204281824, "learning_rate": 7.575718930512516e-07, "loss": 0.2984, "step": 789 }, { "epoch": 2.523961661341853, "grad_norm": 0.5707528680423285, "learning_rate": 7.47763432933315e-07, "loss": 0.3519, "step": 790 }, { "epoch": 2.527156549520767, "grad_norm": 0.5768375956828472, "learning_rate": 7.380137492509309e-07, "loss": 0.2979, "step": 791 }, { "epoch": 2.5303514376996805, "grad_norm": 0.5307202912335556, "learning_rate": 7.283229767688627e-07, "loss": 0.3365, "step": 792 }, { "epoch": 2.533546325878594, "grad_norm": 0.5711642876819738, "learning_rate": 7.186912494375736e-07, "loss": 0.3803, "step": 793 }, { "epoch": 2.536741214057508, "grad_norm": 0.5349026632263273, "learning_rate": 7.091187003913802e-07, "loss": 0.3239, "step": 794 }, { "epoch": 2.539936102236422, "grad_norm": 0.583012121489221, "learning_rate": 6.996054619466053e-07, "loss": 0.3392, "step": 795 }, { "epoch": 2.543130990415335, "grad_norm": 0.5609705350332282, "learning_rate": 6.901516655997536e-07, "loss": 0.4193, "step": 796 }, { "epoch": 2.5463258785942493, "grad_norm": 0.594967536141309, "learning_rate": 6.80757442025694e-07, "loss": 0.3052, "step": 797 }, { "epoch": 2.549520766773163, "grad_norm": 0.5940460186489407, "learning_rate": 6.714229210758516e-07, "loss": 0.3529, "step": 798 }, { "epoch": 2.5527156549520766, "grad_norm": 0.5612092748543441, "learning_rate": 6.621482317764105e-07, "loss": 0.3472, "step": 799 }, { "epoch": 2.5559105431309903, "grad_norm": 0.5679709101998861, "learning_rate": 6.529335023265387e-07, "loss": 0.3357, "step": 800 }, { "epoch": 2.559105431309904, "grad_norm": 0.5440415384971896, "learning_rate": 6.437788600966066e-07, "loss": 0.3111, "step": 801 }, { "epoch": 2.562300319488818, "grad_norm": 0.5964765736359275, "learning_rate": 6.346844316264312e-07, "loss": 0.3534, "step": 802 }, { "epoch": 2.5654952076677318, "grad_norm": 0.6245549454681938, "learning_rate": 6.256503426235277e-07, "loss": 0.3279, "step": 803 }, { "epoch": 2.5686900958466454, "grad_norm": 0.5850388477288754, "learning_rate": 6.166767179613691e-07, "loss": 0.3099, "step": 804 }, { "epoch": 2.571884984025559, "grad_norm": 0.5637280336385339, "learning_rate": 6.077636816776611e-07, "loss": 0.2819, "step": 805 }, { "epoch": 2.5750798722044728, "grad_norm": 0.6176991831171035, "learning_rate": 5.989113569726312e-07, "loss": 0.3039, "step": 806 }, { "epoch": 2.5782747603833864, "grad_norm": 0.71187271410236, "learning_rate": 5.901198662073188e-07, "loss": 0.315, "step": 807 }, { "epoch": 2.5814696485623, "grad_norm": 0.5821053609324206, "learning_rate": 5.813893309018881e-07, "loss": 0.3552, "step": 808 }, { "epoch": 2.584664536741214, "grad_norm": 0.6223346311833248, "learning_rate": 5.727198717339511e-07, "loss": 0.2929, "step": 809 }, { "epoch": 2.587859424920128, "grad_norm": 0.584315668054316, "learning_rate": 5.641116085368931e-07, "loss": 0.317, "step": 810 }, { "epoch": 2.5910543130990416, "grad_norm": 0.5746440164268632, "learning_rate": 5.555646602982207e-07, "loss": 0.4032, "step": 811 }, { "epoch": 2.594249201277955, "grad_norm": 0.587232658805564, "learning_rate": 5.470791451579172e-07, "loss": 0.3184, "step": 812 }, { "epoch": 2.597444089456869, "grad_norm": 0.5864420347378898, "learning_rate": 5.386551804068063e-07, "loss": 0.3602, "step": 813 }, { "epoch": 2.600638977635783, "grad_norm": 0.5302312882381615, "learning_rate": 5.302928824849335e-07, "loss": 0.3254, "step": 814 }, { "epoch": 2.6038338658146962, "grad_norm": 0.6004537769625552, "learning_rate": 5.219923669799587e-07, "loss": 0.3542, "step": 815 }, { "epoch": 2.6070287539936103, "grad_norm": 0.6579884319558386, "learning_rate": 5.137537486255517e-07, "loss": 0.3635, "step": 816 }, { "epoch": 2.610223642172524, "grad_norm": 0.5717327429721044, "learning_rate": 5.055771412998122e-07, "loss": 0.355, "step": 817 }, { "epoch": 2.6134185303514377, "grad_norm": 0.5435195536221277, "learning_rate": 4.974626580236957e-07, "loss": 0.3727, "step": 818 }, { "epoch": 2.6166134185303513, "grad_norm": 0.5452473807702689, "learning_rate": 4.894104109594466e-07, "loss": 0.3415, "step": 819 }, { "epoch": 2.619808306709265, "grad_norm": 0.5614197697797106, "learning_rate": 4.814205114090543e-07, "loss": 0.353, "step": 820 }, { "epoch": 2.623003194888179, "grad_norm": 0.6036099876529709, "learning_rate": 4.734930698127077e-07, "loss": 0.3329, "step": 821 }, { "epoch": 2.626198083067093, "grad_norm": 0.5610318957311481, "learning_rate": 4.6562819574727304e-07, "loss": 0.3557, "step": 822 }, { "epoch": 2.6293929712460065, "grad_norm": 0.525351462374241, "learning_rate": 4.578259979247801e-07, "loss": 0.3385, "step": 823 }, { "epoch": 2.63258785942492, "grad_norm": 0.6776441821920868, "learning_rate": 4.500865841909169e-07, "loss": 0.342, "step": 824 }, { "epoch": 2.635782747603834, "grad_norm": 0.5299009647564896, "learning_rate": 4.4241006152353885e-07, "loss": 0.3793, "step": 825 }, { "epoch": 2.6389776357827475, "grad_norm": 0.5369364999737113, "learning_rate": 4.3479653603119287e-07, "loss": 0.381, "step": 826 }, { "epoch": 2.642172523961661, "grad_norm": 0.5920800154248469, "learning_rate": 4.2724611295164755e-07, "loss": 0.3242, "step": 827 }, { "epoch": 2.6453674121405752, "grad_norm": 0.5663358573294414, "learning_rate": 4.197588966504401e-07, "loss": 0.3463, "step": 828 }, { "epoch": 2.648562300319489, "grad_norm": 0.5471794089375958, "learning_rate": 4.123349906194357e-07, "loss": 0.3375, "step": 829 }, { "epoch": 2.6517571884984026, "grad_norm": 0.6014709675824612, "learning_rate": 4.0497449747539217e-07, "loss": 0.3686, "step": 830 }, { "epoch": 2.6549520766773163, "grad_norm": 0.6082660885321246, "learning_rate": 3.9767751895854467e-07, "loss": 0.3165, "step": 831 }, { "epoch": 2.65814696485623, "grad_norm": 0.5376902168917983, "learning_rate": 3.904441559312006e-07, "loss": 0.3175, "step": 832 }, { "epoch": 2.661341853035144, "grad_norm": 0.5349176977828113, "learning_rate": 3.8327450837634284e-07, "loss": 0.3153, "step": 833 }, { "epoch": 2.6645367412140573, "grad_norm": 0.5793405702321877, "learning_rate": 3.7616867539624733e-07, "loss": 0.3516, "step": 834 }, { "epoch": 2.6677316293929714, "grad_norm": 0.5410240793370933, "learning_rate": 3.691267552111183e-07, "loss": 0.4026, "step": 835 }, { "epoch": 2.670926517571885, "grad_norm": 0.5694849372788428, "learning_rate": 3.621488451577221e-07, "loss": 0.3407, "step": 836 }, { "epoch": 2.6741214057507987, "grad_norm": 0.5975521361869505, "learning_rate": 3.552350416880507e-07, "loss": 0.3373, "step": 837 }, { "epoch": 2.6773162939297124, "grad_norm": 0.569768311072208, "learning_rate": 3.483854403679832e-07, "loss": 0.3297, "step": 838 }, { "epoch": 2.680511182108626, "grad_norm": 0.6903061046518503, "learning_rate": 3.416001358759635e-07, "loss": 0.2955, "step": 839 }, { "epoch": 2.68370607028754, "grad_norm": 0.5841017513426691, "learning_rate": 3.3487922200169944e-07, "loss": 0.358, "step": 840 }, { "epoch": 2.686900958466454, "grad_norm": 0.545896489919343, "learning_rate": 3.2822279164485494e-07, "loss": 0.3632, "step": 841 }, { "epoch": 2.6900958466453675, "grad_norm": 0.6588046443317735, "learning_rate": 3.2163093681377765e-07, "loss": 0.3551, "step": 842 }, { "epoch": 2.693290734824281, "grad_norm": 0.5748802973182505, "learning_rate": 3.151037486242181e-07, "loss": 0.3248, "step": 843 }, { "epoch": 2.696485623003195, "grad_norm": 0.5908314428457524, "learning_rate": 3.08641317298074e-07, "loss": 0.2885, "step": 844 }, { "epoch": 2.6996805111821085, "grad_norm": 0.5528724107582127, "learning_rate": 3.022437321621452e-07, "loss": 0.352, "step": 845 }, { "epoch": 2.702875399361022, "grad_norm": 0.5585598362246621, "learning_rate": 2.959110816468935e-07, "loss": 0.3332, "step": 846 }, { "epoch": 2.7060702875399363, "grad_norm": 0.6050385908159153, "learning_rate": 2.896434532852277e-07, "loss": 0.3136, "step": 847 }, { "epoch": 2.70926517571885, "grad_norm": 0.6064065560927091, "learning_rate": 2.834409337112842e-07, "loss": 0.3533, "step": 848 }, { "epoch": 2.7124600638977636, "grad_norm": 0.5280435683159072, "learning_rate": 2.7730360865923954e-07, "loss": 0.3252, "step": 849 }, { "epoch": 2.7156549520766773, "grad_norm": 0.578523313304179, "learning_rate": 2.712315629621176e-07, "loss": 0.3023, "step": 850 }, { "epoch": 2.718849840255591, "grad_norm": 0.6163076832373001, "learning_rate": 2.6522488055062076e-07, "loss": 0.3341, "step": 851 }, { "epoch": 2.722044728434505, "grad_norm": 0.6117384691824501, "learning_rate": 2.5928364445196975e-07, "loss": 0.3132, "step": 852 }, { "epoch": 2.7252396166134183, "grad_norm": 0.5703662607136886, "learning_rate": 2.534079367887549e-07, "loss": 0.3251, "step": 853 }, { "epoch": 2.7284345047923324, "grad_norm": 0.6190014779819151, "learning_rate": 2.475978387778e-07, "loss": 0.3569, "step": 854 }, { "epoch": 2.731629392971246, "grad_norm": 0.5604661408318365, "learning_rate": 2.4185343072904376e-07, "loss": 0.3395, "step": 855 }, { "epoch": 2.7348242811501597, "grad_norm": 0.5489428613929013, "learning_rate": 2.3617479204442462e-07, "loss": 0.3313, "step": 856 }, { "epoch": 2.7380191693290734, "grad_norm": 0.5534611059961758, "learning_rate": 2.305620012167853e-07, "loss": 0.3172, "step": 857 }, { "epoch": 2.741214057507987, "grad_norm": 0.5769562053475937, "learning_rate": 2.2501513582879108e-07, "loss": 0.3466, "step": 858 }, { "epoch": 2.744408945686901, "grad_norm": 0.54615446896986, "learning_rate": 2.1953427255185122e-07, "loss": 0.3582, "step": 859 }, { "epoch": 2.747603833865815, "grad_norm": 0.5834092046516896, "learning_rate": 2.1411948714506414e-07, "loss": 0.3887, "step": 860 }, { "epoch": 2.7507987220447285, "grad_norm": 0.5516422872250117, "learning_rate": 2.0877085445416889e-07, "loss": 0.3605, "step": 861 }, { "epoch": 2.753993610223642, "grad_norm": 0.6121681780880922, "learning_rate": 2.034884484105093e-07, "loss": 0.3498, "step": 862 }, { "epoch": 2.757188498402556, "grad_norm": 0.5662039053316421, "learning_rate": 1.98272342030012e-07, "loss": 0.375, "step": 863 }, { "epoch": 2.7603833865814695, "grad_norm": 0.6474986303524936, "learning_rate": 1.9312260741218114e-07, "loss": 0.3808, "step": 864 }, { "epoch": 2.763578274760383, "grad_norm": 0.6092793057060697, "learning_rate": 1.8803931573909584e-07, "loss": 0.2861, "step": 865 }, { "epoch": 2.7667731629392973, "grad_norm": 0.5653652953607464, "learning_rate": 1.8302253727443041e-07, "loss": 0.3665, "step": 866 }, { "epoch": 2.769968051118211, "grad_norm": 0.5262527951801934, "learning_rate": 1.7807234136248296e-07, "loss": 0.348, "step": 867 }, { "epoch": 2.7731629392971247, "grad_norm": 0.6010527895059987, "learning_rate": 1.731887964272144e-07, "loss": 0.3269, "step": 868 }, { "epoch": 2.7763578274760383, "grad_norm": 0.5152094861239386, "learning_rate": 1.6837196997130434e-07, "loss": 0.3454, "step": 869 }, { "epoch": 2.779552715654952, "grad_norm": 0.5909709681738667, "learning_rate": 1.6362192857521942e-07, "loss": 0.344, "step": 870 }, { "epoch": 2.7827476038338657, "grad_norm": 0.5029070496695086, "learning_rate": 1.5893873789628812e-07, "loss": 0.3648, "step": 871 }, { "epoch": 2.7859424920127793, "grad_norm": 0.5577303918259516, "learning_rate": 1.5432246266780083e-07, "loss": 0.3716, "step": 872 }, { "epoch": 2.7891373801916934, "grad_norm": 0.5665556944271241, "learning_rate": 1.4977316669810782e-07, "loss": 0.3611, "step": 873 }, { "epoch": 2.792332268370607, "grad_norm": 0.543905991284816, "learning_rate": 1.4529091286973994e-07, "loss": 0.3035, "step": 874 }, { "epoch": 2.7955271565495208, "grad_norm": 0.6350011040549947, "learning_rate": 1.4087576313854212e-07, "loss": 0.3211, "step": 875 }, { "epoch": 2.7987220447284344, "grad_norm": 0.589866349573948, "learning_rate": 1.365277785328123e-07, "loss": 0.3134, "step": 876 }, { "epoch": 2.801916932907348, "grad_norm": 0.5322922994710118, "learning_rate": 1.3224701915246053e-07, "loss": 0.3123, "step": 877 }, { "epoch": 2.8051118210862622, "grad_norm": 0.5583751783696411, "learning_rate": 1.280335441681796e-07, "loss": 0.3051, "step": 878 }, { "epoch": 2.8083067092651754, "grad_norm": 0.5538379069248649, "learning_rate": 1.2388741182062348e-07, "loss": 0.3642, "step": 879 }, { "epoch": 2.8115015974440896, "grad_norm": 0.6159417305152532, "learning_rate": 1.198086794196035e-07, "loss": 0.3348, "step": 880 }, { "epoch": 2.8146964856230032, "grad_norm": 0.5898313061788408, "learning_rate": 1.1579740334330014e-07, "loss": 0.3, "step": 881 }, { "epoch": 2.817891373801917, "grad_norm": 0.5018089700878364, "learning_rate": 1.1185363903747748e-07, "loss": 0.3716, "step": 882 }, { "epoch": 2.8210862619808306, "grad_norm": 0.6168872718383936, "learning_rate": 1.0797744101472052e-07, "loss": 0.3369, "step": 883 }, { "epoch": 2.8242811501597442, "grad_norm": 0.5505660776029496, "learning_rate": 1.0416886285368188e-07, "loss": 0.3703, "step": 884 }, { "epoch": 2.8274760383386583, "grad_norm": 0.5300963985701472, "learning_rate": 1.0042795719833964e-07, "loss": 0.4103, "step": 885 }, { "epoch": 2.830670926517572, "grad_norm": 0.6561731290395931, "learning_rate": 9.675477575726954e-08, "loss": 0.332, "step": 886 }, { "epoch": 2.8338658146964857, "grad_norm": 0.5544282515328289, "learning_rate": 9.314936930293283e-08, "loss": 0.3053, "step": 887 }, { "epoch": 2.8370607028753994, "grad_norm": 0.5235068301613184, "learning_rate": 8.961178767097178e-08, "loss": 0.3522, "step": 888 }, { "epoch": 2.840255591054313, "grad_norm": 0.6769353156025437, "learning_rate": 8.614207975952083e-08, "loss": 0.3801, "step": 889 }, { "epoch": 2.8434504792332267, "grad_norm": 0.5446946980464149, "learning_rate": 8.274029352853264e-08, "loss": 0.332, "step": 890 }, { "epoch": 2.8466453674121404, "grad_norm": 0.49142751252317257, "learning_rate": 7.940647599911477e-08, "loss": 0.3462, "step": 891 }, { "epoch": 2.8498402555910545, "grad_norm": 0.5256070158129452, "learning_rate": 7.614067325287632e-08, "loss": 0.3708, "step": 892 }, { "epoch": 2.853035143769968, "grad_norm": 0.6187672006800049, "learning_rate": 7.294293043129785e-08, "loss": 0.3342, "step": 893 }, { "epoch": 2.856230031948882, "grad_norm": 0.5653221557610779, "learning_rate": 6.981329173509909e-08, "loss": 0.3443, "step": 894 }, { "epoch": 2.8594249201277955, "grad_norm": 1.1954807605844084, "learning_rate": 6.675180042363505e-08, "loss": 0.3882, "step": 895 }, { "epoch": 2.862619808306709, "grad_norm": 0.5765003588637598, "learning_rate": 6.375849881429418e-08, "loss": 0.3061, "step": 896 }, { "epoch": 2.8658146964856233, "grad_norm": 0.5165502215161434, "learning_rate": 6.083342828191453e-08, "loss": 0.3934, "step": 897 }, { "epoch": 2.8690095846645365, "grad_norm": 0.5579060004933497, "learning_rate": 5.797662925821068e-08, "loss": 0.364, "step": 898 }, { "epoch": 2.8722044728434506, "grad_norm": 0.5357705818949167, "learning_rate": 5.518814123121885e-08, "loss": 0.333, "step": 899 }, { "epoch": 2.8753993610223643, "grad_norm": 0.6215205130389762, "learning_rate": 5.246800274474439e-08, "loss": 0.3215, "step": 900 }, { "epoch": 2.878594249201278, "grad_norm": 0.5362725801320283, "learning_rate": 4.981625139783619e-08, "loss": 0.3625, "step": 901 }, { "epoch": 2.8817891373801916, "grad_norm": 0.5832017290942086, "learning_rate": 4.723292384426203e-08, "loss": 0.4049, "step": 902 }, { "epoch": 2.8849840255591053, "grad_norm": 0.6011616287171958, "learning_rate": 4.471805579200239e-08, "loss": 0.3256, "step": 903 }, { "epoch": 2.8881789137380194, "grad_norm": 0.5601944631354882, "learning_rate": 4.227168200276077e-08, "loss": 0.3686, "step": 904 }, { "epoch": 2.891373801916933, "grad_norm": 0.5472469736396958, "learning_rate": 3.989383629147747e-08, "loss": 0.3418, "step": 905 }, { "epoch": 2.8945686900958467, "grad_norm": 0.5338171927335532, "learning_rate": 3.758455152586715e-08, "loss": 0.3715, "step": 906 }, { "epoch": 2.8977635782747604, "grad_norm": 0.6101596416839852, "learning_rate": 3.534385962596143e-08, "loss": 0.3564, "step": 907 }, { "epoch": 2.900958466453674, "grad_norm": 0.5311824758840752, "learning_rate": 3.3171791563669785e-08, "loss": 0.3974, "step": 908 }, { "epoch": 2.9041533546325877, "grad_norm": 0.5897397502333577, "learning_rate": 3.10683773623488e-08, "loss": 0.3643, "step": 909 }, { "epoch": 2.9073482428115014, "grad_norm": 0.5451862506343562, "learning_rate": 2.9033646096390255e-08, "loss": 0.4077, "step": 910 }, { "epoch": 2.9105431309904155, "grad_norm": 0.537285429472973, "learning_rate": 2.706762589081646e-08, "loss": 0.3777, "step": 911 }, { "epoch": 2.913738019169329, "grad_norm": 0.553809502847126, "learning_rate": 2.517034392089446e-08, "loss": 0.3414, "step": 912 }, { "epoch": 2.916932907348243, "grad_norm": 0.5872150553419763, "learning_rate": 2.3341826411756863e-08, "loss": 0.3312, "step": 913 }, { "epoch": 2.9201277955271565, "grad_norm": 0.5982165518925496, "learning_rate": 2.158209863804217e-08, "loss": 0.3105, "step": 914 }, { "epoch": 2.92332268370607, "grad_norm": 0.5953312685899663, "learning_rate": 1.9891184923544472e-08, "loss": 0.2881, "step": 915 }, { "epoch": 2.9265175718849843, "grad_norm": 0.5589989469340159, "learning_rate": 1.826910864087761e-08, "loss": 0.3441, "step": 916 }, { "epoch": 2.9297124600638975, "grad_norm": 0.5352148216822907, "learning_rate": 1.6715892211150442e-08, "loss": 0.3537, "step": 917 }, { "epoch": 2.9329073482428116, "grad_norm": 0.647867530843516, "learning_rate": 1.5231557103658755e-08, "loss": 0.2741, "step": 918 }, { "epoch": 2.9361022364217253, "grad_norm": 0.5517267321893599, "learning_rate": 1.3816123835588835e-08, "loss": 0.3679, "step": 919 }, { "epoch": 2.939297124600639, "grad_norm": 0.5804393153053172, "learning_rate": 1.2469611971731576e-08, "loss": 0.3643, "step": 920 }, { "epoch": 2.9424920127795526, "grad_norm": 0.5637831632290987, "learning_rate": 1.1192040124214931e-08, "loss": 0.38, "step": 921 }, { "epoch": 2.9456869009584663, "grad_norm": 0.5791231995251553, "learning_rate": 9.983425952243552e-09, "loss": 0.362, "step": 922 }, { "epoch": 2.9488817891373804, "grad_norm": 0.613327768846829, "learning_rate": 8.84378616185788e-09, "loss": 0.3305, "step": 923 }, { "epoch": 2.952076677316294, "grad_norm": 0.523776663808406, "learning_rate": 7.773136505700995e-09, "loss": 0.3285, "step": 924 }, { "epoch": 2.9552715654952078, "grad_norm": 0.5372633451404858, "learning_rate": 6.7714917828004545e-09, "loss": 0.3553, "step": 925 }, { "epoch": 2.9584664536741214, "grad_norm": 0.5997913801512937, "learning_rate": 5.838865838366792e-09, "loss": 0.329, "step": 926 }, { "epoch": 2.961661341853035, "grad_norm": 0.5572950173147985, "learning_rate": 4.975271563599227e-09, "loss": 0.3111, "step": 927 }, { "epoch": 2.9648562300319488, "grad_norm": 0.5826358090737692, "learning_rate": 4.180720895508028e-09, "loss": 0.3306, "step": 928 }, { "epoch": 2.9680511182108624, "grad_norm": 0.5738688144268712, "learning_rate": 3.4552248167507576e-09, "loss": 0.3519, "step": 929 }, { "epoch": 2.9712460063897765, "grad_norm": 0.5323772177269126, "learning_rate": 2.798793355478502e-09, "loss": 0.3854, "step": 930 }, { "epoch": 2.97444089456869, "grad_norm": 0.5154651602015146, "learning_rate": 2.2114355851993175e-09, "loss": 0.3371, "step": 931 }, { "epoch": 2.977635782747604, "grad_norm": 0.5355099037607711, "learning_rate": 1.6931596246516636e-09, "loss": 0.3501, "step": 932 }, { "epoch": 2.9808306709265175, "grad_norm": 0.5195387643181241, "learning_rate": 1.24397263769227e-09, "loss": 0.3754, "step": 933 }, { "epoch": 2.984025559105431, "grad_norm": 0.5496579222846415, "learning_rate": 8.638808331973281e-10, "loss": 0.3486, "step": 934 }, { "epoch": 2.987220447284345, "grad_norm": 0.580032230336796, "learning_rate": 5.528894649758921e-10, "loss": 0.3533, "step": 935 }, { "epoch": 2.9904153354632586, "grad_norm": 0.6028588307685283, "learning_rate": 3.1100283169938074e-10, "loss": 0.35, "step": 936 }, { "epoch": 2.9936102236421727, "grad_norm": 0.5597644612132677, "learning_rate": 1.3822427683884975e-10, "loss": 0.3851, "step": 937 }, { "epoch": 2.9968051118210863, "grad_norm": 0.5543081962122827, "learning_rate": 3.4556188622802964e-11, "loss": 0.3398, "step": 938 }, { "epoch": 3.0, "grad_norm": 0.5681028010288746, "learning_rate": 0.0, "loss": 0.3356, "step": 939 }, { "epoch": 3.0, "step": 939, "total_flos": 406391461183488.0, "train_loss": 0.43733476487973244, "train_runtime": 10132.2972, "train_samples_per_second": 2.96, "train_steps_per_second": 0.093 } ], "logging_steps": 1.0, "max_steps": 939, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 406391461183488.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }